Merge tag v4.15 of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git

To resolve conflicts in:
 drivers/infiniband/hw/mlx5/main.c
 drivers/infiniband/hw/mlx5/qp.c

From patches merged into the -rc cycle. The conflict resolution matches
what linux-next has been carrying.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

9 files changed, 148 insertions, 78 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 947d3e2ed5c2..9d5b78aad4c5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1099,8 +1099,6 @@ config PROVE_LOCKING
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
 	select DEBUG_LOCK_ALLOC
-	select LOCKDEP_CROSSRELEASE
-	select LOCKDEP_COMPLETIONS
 	select TRACE_IRQFLAGS
 	default n
 	help
@@ -1170,37 +1168,6 @@ config LOCK_STAT
 	 CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
 	 (CONFIG_LOCKDEP defines "acquire" and "release" events.)
 
-config LOCKDEP_CROSSRELEASE
-	bool
-	help
-	 This makes lockdep work for crosslock which is a lock allowed to
-	 be released in a different context from the acquisition context.
-	 Normally a lock must be released in the context acquiring the lock.
-	 However, relexing this constraint helps synchronization primitives
-	 such as page locks or completions can use the lock correctness
-	 detector, lockdep.
-
-config LOCKDEP_COMPLETIONS
-	bool
-	help
-	 A deadlock caused by wait_for_completion() and complete() can be
-	 detected by lockdep using crossrelease feature.
-
-config BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK
-	bool "Enable the boot parameter, crossrelease_fullstack"
-	depends on LOCKDEP_CROSSRELEASE
-	default n
-	help
-	 The lockdep "cross-release" feature needs to record stack traces
-	 (of calling functions) for all acquisitions, for eventual later
-	 use during analysis. By default only a single caller is recorded,
-	 because the unwind operation can be very expensive with deeper
-	 stack chains.
-
-	 However a boot parameter, crossrelease_fullstack, was
-	 introduced since sometimes deeper traces are required for full
-	 analysis. This option turns on the boot parameter.
-
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 1ef0cec38d78..dc14beae2c9a 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -313,42 +313,47 @@ next_op:
 
 	/* Decide how to handle the operation */
 	switch (op) {
-	case ASN1_OP_MATCH_ANY_ACT:
-	case ASN1_OP_MATCH_ANY_ACT_OR_SKIP:
-	case ASN1_OP_COND_MATCH_ANY_ACT:
-	case ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP:
-		ret = actions[machine[pc + 1]](context, hdr, tag, data + dp, len);
-		if (ret < 0)
-			return ret;
-		goto skip_data;
-
-	case ASN1_OP_MATCH_ACT:
-	case ASN1_OP_MATCH_ACT_OR_SKIP:
-	case ASN1_OP_COND_MATCH_ACT_OR_SKIP:
-		ret = actions[machine[pc + 2]](context, hdr, tag, data + dp, len);
-		if (ret < 0)
-			return ret;
-		goto skip_data;
-
 	case ASN1_OP_MATCH:
 	case ASN1_OP_MATCH_OR_SKIP:
+	case ASN1_OP_MATCH_ACT:
+	case ASN1_OP_MATCH_ACT_OR_SKIP:
 	case ASN1_OP_MATCH_ANY:
 	case ASN1_OP_MATCH_ANY_OR_SKIP:
+	case ASN1_OP_MATCH_ANY_ACT:
+	case ASN1_OP_MATCH_ANY_ACT_OR_SKIP:
 	case ASN1_OP_COND_MATCH_OR_SKIP:
+	case ASN1_OP_COND_MATCH_ACT_OR_SKIP:
 	case ASN1_OP_COND_MATCH_ANY:
 	case ASN1_OP_COND_MATCH_ANY_OR_SKIP:
-	skip_data:
+	case ASN1_OP_COND_MATCH_ANY_ACT:
+	case ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP:
+
 		if (!(flags & FLAG_CONS)) {
 			if (flags & FLAG_INDEFINITE_LENGTH) {
+				size_t tmp = dp;
+
 				ret = asn1_find_indefinite_length(
-					data, datalen, &dp, &len, &errmsg);
+					data, datalen, &tmp, &len, &errmsg);
 				if (ret < 0)
 					goto error;
-			} else {
-				dp += len;
 			}
 			pr_debug("- LEAF: %zu\n", len);
 		}
+
+		if (op & ASN1_OP_MATCH__ACT) {
+			unsigned char act;
+
+			if (op & ASN1_OP_MATCH__ANY)
+				act = machine[pc + 1];
+			else
+				act = machine[pc + 2];
+			ret = actions[act](context, hdr, tag, data + dp, len);
+			if (ret < 0)
+				return ret;
+		}
+
+		if (!(flags & FLAG_CONS))
+			dp += len;
 		pc += asn1_op_lengths[op];
 		goto next_op;
 
@@ -434,6 +439,8 @@ next_op:
 			else
 				act = machine[pc + 1];
 			ret = actions[act](context, hdr, 0, data + tdp, len);
+			if (ret < 0)
+				return ret;
 		}
 		pc += asn1_op_lengths[op];
 		goto next_op;
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index c3e84edc47c9..2615074d3de5 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -346,7 +346,8 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj,
 static void zap_modalias_env(struct kobj_uevent_env *env)
 {
 	static const char modalias_prefix[] = "MODALIAS=";
-	int i;
+	size_t len;
+	int i, j;
 
 	for (i = 0; i < env->envp_idx;) {
 		if (strncmp(env->envp[i], modalias_prefix,
@@ -355,11 +356,18 @@ static void zap_modalias_env(struct kobj_uevent_env *env)
 			continue;
 		}
 
-		if (i != env->envp_idx - 1)
-			memmove(&env->envp[i], &env->envp[i + 1],
-				sizeof(env->envp[i]) * env->envp_idx - 1);
+		len = strlen(env->envp[i]) + 1;
+
+		if (i != env->envp_idx - 1) {
+			memmove(env->envp[i], env->envp[i + 1],
+				env->buflen - len);
+
+			for (j = i; j < env->envp_idx - 1; j++)
+				env->envp[j] = env->envp[j + 1] - len;
+		}
 
 		env->envp_idx--;
+		env->buflen -= len;
 	}
 }
 
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index 57fd45ab7af1..08c60d10747f 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -671,7 +671,23 @@ do {						\
 	**************  MIPS/64  **************
 	***************************************/
 #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64
-#if (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4)
+#if defined(__mips_isa_rev) && __mips_isa_rev >= 6
+/*
+ * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C
+ * code below, so we special case MIPS64r6 until the compiler can do better.
+ */
+#define umul_ppmm(w1, w0, u, v)						\
+do {									\
+	__asm__ ("dmulu %0,%1,%2"					\
+		 : "=d" ((UDItype)(w0))					\
+		 : "d" ((UDItype)(u)),					\
+		   "d" ((UDItype)(v)));					\
+	__asm__ ("dmuhu %0,%1,%2"					\
+		 : "=d" ((UDItype)(w1))					\
+		 : "d" ((UDItype)(u)),					\
+		   "d" ((UDItype)(v)));					\
+} while (0)
+#elif (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4)
 #define umul_ppmm(w1, w0, u, v) \
 do {									\
 	typedef unsigned int __ll_UTItype __attribute__((mode(TI)));	\
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 8bf78b4b78f0..dfa55c873c13 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -15,7 +15,11 @@
 #include <linux/types.h>
 #include <net/netlink.h>
 
-/* for these data types attribute length must be exactly given size */
+/* For these data types, attribute length should be exactly the given
+ * size. However, to maintain compatibility with broken commands, if the
+ * attribute length does not match the expected size a warning is emitted
+ * to the user that the command is sending invalid data and needs to be fixed.
+ */
 static const u8 nla_attr_len[NLA_TYPE_MAX+1] = {
 	[NLA_U8]	= sizeof(u8),
 	[NLA_U16]	= sizeof(u16),
@@ -28,8 +32,16 @@ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = {
 };
 
 static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
+	[NLA_U8]	= sizeof(u8),
+	[NLA_U16]	= sizeof(u16),
+	[NLA_U32]	= sizeof(u32),
+	[NLA_U64]	= sizeof(u64),
 	[NLA_MSECS]	= sizeof(u64),
 	[NLA_NESTED]	= NLA_HDRLEN,
+	[NLA_S8]	= sizeof(s8),
+	[NLA_S16]	= sizeof(s16),
+	[NLA_S32]	= sizeof(s32),
+	[NLA_S64]	= sizeof(s64),
 };
 
 static int validate_nla_bitfield32(const struct nlattr *nla,
@@ -69,11 +81,9 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 
 	BUG_ON(pt->type > NLA_TYPE_MAX);
 
-	/* for data types NLA_U* and NLA_S* require exact length */
-	if (nla_attr_len[pt->type]) {
-		if (attrlen != nla_attr_len[pt->type])
-			return -ERANGE;
-		return 0;
+	if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) {
+		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
+				    current->comm, type);
 	}
 
 	switch (pt->type) {
diff --git a/lib/oid_registry.c b/lib/oid_registry.c
index 41b9e50711a7..0bcac6ccb1b2 100644
--- a/lib/oid_registry.c
+++ b/lib/oid_registry.c
@@ -116,14 +116,14 @@ int sprint_oid(const void *data, size_t datasize, char *buffer, size_t bufsize)
 	int count;
 
 	if (v >= end)
-		return -EBADMSG;
+		goto bad;
 
 	n = *v++;
 	ret = count = snprintf(buffer, bufsize, "%u.%u", n / 40, n % 40);
+	if (count >= bufsize)
+		return -ENOBUFS;
 	buffer += count;
 	bufsize -= count;
-	if (bufsize == 0)
-		return -ENOBUFS;
 
 	while (v < end) {
 		num = 0;
@@ -134,20 +134,24 @@ int sprint_oid(const void *data, size_t datasize, char *buffer, size_t bufsize)
 			num = n & 0x7f;
 			do {
 				if (v >= end)
-					return -EBADMSG;
+					goto bad;
 				n = *v++;
 				num <<= 7;
 				num |= n & 0x7f;
 			} while (n & 0x80);
 		}
 		ret += count = snprintf(buffer, bufsize, ".%lu", num);
-		buffer += count;
-		if (bufsize <= count)
+		if (count >= bufsize)
 			return -ENOBUFS;
+		buffer += count;
 		bufsize -= count;
 	}
 
 	return ret;
+
+bad:
+	snprintf(buffer, bufsize, "(bad)");
+	return -EBADMSG;
 }
 EXPORT_SYMBOL_GPL(sprint_oid);
 
diff --git a/lib/rbtree.c b/lib/rbtree.c
index ba4a9d165f1b..d3ff682fd4b8 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -603,6 +603,16 @@ void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 }
 EXPORT_SYMBOL(rb_replace_node);
 
+void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new,
+			    struct rb_root_cached *root)
+{
+	rb_replace_node(victim, new, &root->rb_root);
+
+	if (root->rb_leftmost == victim)
+		root->rb_leftmost = new;
+}
+EXPORT_SYMBOL(rb_replace_node_cached);
+
 void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new,
 			 struct rb_root *root)
 {
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index aa8812ae6776..f369889e521d 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -435,6 +435,41 @@ loop:
 	return 0;
 }
 
+static int bpf_fill_ld_abs_vlan_push_pop2(struct bpf_test *self)
+{
+	struct bpf_insn *insn;
+
+	insn = kmalloc_array(16, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	/* Due to func address being non-const, we need to
+	 * assemble this here.
+	 */
+	insn[0] = BPF_MOV64_REG(R6, R1);
+	insn[1] = BPF_LD_ABS(BPF_B, 0);
+	insn[2] = BPF_LD_ABS(BPF_H, 0);
+	insn[3] = BPF_LD_ABS(BPF_W, 0);
+	insn[4] = BPF_MOV64_REG(R7, R6);
+	insn[5] = BPF_MOV64_IMM(R6, 0);
+	insn[6] = BPF_MOV64_REG(R1, R7);
+	insn[7] = BPF_MOV64_IMM(R2, 1);
+	insn[8] = BPF_MOV64_IMM(R3, 2);
+	insn[9] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			       bpf_skb_vlan_push_proto.func - __bpf_call_base);
+	insn[10] = BPF_MOV64_REG(R6, R7);
+	insn[11] = BPF_LD_ABS(BPF_B, 0);
+	insn[12] = BPF_LD_ABS(BPF_H, 0);
+	insn[13] = BPF_LD_ABS(BPF_W, 0);
+	insn[14] = BPF_MOV64_IMM(R0, 42);
+	insn[15] = BPF_EXIT_INSN();
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = 16;
+
+	return 0;
+}
+
 static int bpf_fill_jump_around_ld_abs(struct bpf_test *self)
 {
 	unsigned int len = BPF_MAXINSNS;
@@ -6066,6 +6101,14 @@ static struct bpf_test tests[] = {
 		{},
 		{ {0x1, 0x42 } },
 	},
+	{
+		"LD_ABS with helper changing skb data",
+		{ },
+		INTERNAL,
+		{ 0x34 },
+		{ { ETH_HLEN, 42 } },
+		.fill_helper = bpf_fill_ld_abs_vlan_push_pop2,
+	},
 };
 
 static struct net_device dev;
@@ -6207,9 +6250,8 @@ static struct bpf_prog *generate_filter(int which, int *err)
 				return NULL;
 			}
 		}
-		/* We don't expect to fail. */
 		if (*err) {
-			pr_cont("FAIL to attach err=%d len=%d\n",
+			pr_cont("FAIL to prog_create err=%d len=%d\n",
 				*err, fprog.len);
 			return NULL;
 		}
@@ -6233,6 +6275,10 @@ static struct bpf_prog *generate_filter(int which, int *err)
 		 * checks.
 		 */
 		fp = bpf_prog_select_runtime(fp, err);
+		if (*err) {
+			pr_cont("FAIL to select_runtime err=%d\n", *err);
+			return NULL;
+		}
 		break;
 	}
 
@@ -6418,8 +6464,8 @@ static __init int test_bpf(void)
 				pass_cnt++;
 				continue;
 			}
-
-			return err;
+			err_cnt++;
+			continue;
 		}
 
 		pr_cont("jited:%u ", fp->jited);
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index 4a720ed4fdaf..0d54bcbc8170 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -33,8 +33,9 @@
  * @head: head of timerqueue
  * @node: timer node to be added
  *
- * Adds the timer node to the timerqueue, sorted by the
- * node's expires value.
+ * Adds the timer node to the timerqueue, sorted by the node's expires
+ * value. Returns true if the newly added timer is the first expiring timer in
+ * the queue.
  */
 bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 {
@@ -70,7 +71,8 @@ EXPORT_SYMBOL_GPL(timerqueue_add);
  * @head: head of timerqueue
  * @node: timer node to be removed
  *
- * Removes the timer node from the timerqueue.
+ * Removes the timer node from the timerqueue. Returns true if the queue is
+ * not empty after the remove.
  */
 bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 {