Merge branch 'for-davem' into for-next

15 files changed, 298 insertions, 149 deletions

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index a5ae60f..e6983be 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,2 @@
 obj-y := core.o
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o
-ifdef CONFIG_TEST_BPF
-obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
-endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 9eb4d8a..8a66165 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -134,7 +134,7 @@ static void array_map_free(struct bpf_map *map)
 	kvfree(array);
 }
 
-static struct bpf_map_ops array_ops = {
+static const struct bpf_map_ops array_ops = {
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -143,14 +143,14 @@ static struct bpf_map_ops array_ops = {
 	.map_delete_elem = array_map_delete_elem,
 };
 
-static struct bpf_map_type_list tl = {
+static struct bpf_map_type_list array_type __read_mostly = {
 	.ops = &array_ops,
 	.type = BPF_MAP_TYPE_ARRAY,
 };
 
 static int __init register_array_map(void)
 {
-	bpf_register_map_type(&tl);
+	bpf_register_map_type(&array_type);
 	return 0;
 }
 late_initcall(register_array_map);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a64e7a2..4139a0f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -656,6 +656,14 @@ void bpf_prog_free(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_free);
 
+/* Weak definitions of helper functions in case we don't have bpf syscall. */
+const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
+const struct bpf_func_proto bpf_map_update_elem_proto __weak;
+const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
+
+const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
+const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
+
 /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
  * skb_copy_bits(), so provide a weak definition of it for NET-less config.
  */
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index b3ba436..83c209d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -345,7 +345,7 @@ static void htab_map_free(struct bpf_map *map)
 	kfree(htab);
 }
 
-static struct bpf_map_ops htab_ops = {
+static const struct bpf_map_ops htab_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -354,14 +354,14 @@ static struct bpf_map_ops htab_ops = {
 	.map_delete_elem = htab_map_delete_elem,
 };
 
-static struct bpf_map_type_list tl = {
+static struct bpf_map_type_list htab_type __read_mostly = {
 	.ops = &htab_ops,
 	.type = BPF_MAP_TYPE_HASH,
 };
 
 static int __init register_htab_map(void)
 {
-	bpf_register_map_type(&tl);
+	bpf_register_map_type(&htab_type);
 	return 0;
 }
 late_initcall(register_htab_map);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9e3414d..bd7f598 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -11,6 +11,8 @@
  */
 #include <linux/bpf.h>
 #include <linux/rcupdate.h>
+#include <linux/random.h>
+#include <linux/smp.h>
 
 /* If kernel subsystem is allowing eBPF programs to call this function,
  * inside its own verifier_ops->get_func_proto() callback it should return
@@ -41,7 +43,7 @@ static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 	return (unsigned long) value;
 }
 
-struct bpf_func_proto bpf_map_lookup_elem_proto = {
+const struct bpf_func_proto bpf_map_lookup_elem_proto = {
 	.func = bpf_map_lookup_elem,
 	.gpl_only = false,
 	.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
@@ -60,7 +62,7 @@ static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 	return map->ops->map_update_elem(map, key, value, r4);
 }
 
-struct bpf_func_proto bpf_map_update_elem_proto = {
+const struct bpf_func_proto bpf_map_update_elem_proto = {
 	.func = bpf_map_update_elem,
 	.gpl_only = false,
 	.ret_type = RET_INTEGER,
@@ -80,10 +82,32 @@ static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 	return map->ops->map_delete_elem(map, key);
 }
 
-struct bpf_func_proto bpf_map_delete_elem_proto = {
+const struct bpf_func_proto bpf_map_delete_elem_proto = {
 	.func = bpf_map_delete_elem,
 	.gpl_only = false,
 	.ret_type = RET_INTEGER,
 	.arg1_type = ARG_CONST_MAP_PTR,
 	.arg2_type = ARG_PTR_TO_MAP_KEY,
 };
+
+static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	return prandom_u32();
+}
+
+const struct bpf_func_proto bpf_get_prandom_u32_proto = {
+	.func		= bpf_get_prandom_u32,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	return raw_smp_processor_id();
+}
+
+const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
+	.func		= bpf_get_smp_processor_id,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 536edc2..ea75c65 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -354,10 +354,11 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 	list_for_each_entry(tl, &bpf_prog_types, list_node) {
 		if (tl->type == type) {
 			prog->aux->ops = tl->ops;
-			prog->aux->prog_type = type;
+			prog->type = type;
 			return 0;
 		}
 	}
+
 	return -EINVAL;
 }
 
@@ -418,6 +419,7 @@ void bpf_prog_put(struct bpf_prog *prog)
 		bpf_prog_free(prog);
 	}
 }
+EXPORT_SYMBOL_GPL(bpf_prog_put);
 
 static int bpf_prog_release(struct inode *inode, struct file *filp)
 {
@@ -465,6 +467,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 	fdput(f);
 	return prog;
 }
+EXPORT_SYMBOL_GPL(bpf_prog_get);
 
 /* last field in 'union bpf_attr' used by this command */
 #define	BPF_PROG_LOAD_LAST_FIELD log_buf
@@ -508,7 +511,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	prog->jited = false;
 
 	atomic_set(&prog->aux->refcnt, 1);
-	prog->aux->is_gpl_compatible = is_gpl;
+	prog->gpl_compatible = is_gpl;
 
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
@@ -516,8 +519,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 		goto free_prog;
 
 	/* run eBPF verifier */
-	err = bpf_check(prog, attr);
-
+	err = bpf_check(&prog, attr);
 	if (err < 0)
 		goto free_used_maps;
 
@@ -528,7 +530,6 @@ static int bpf_prog_load(union bpf_attr *attr)
 	bpf_prog_select_runtime(prog);
 
 	err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
-
 	if (err < 0)
 		/* failed to allocate fd */
 		goto free_used_maps;
diff --git a/kernel/bpf/test_stub.c b/kernel/bpf/test_stub.c
deleted file mode 100644
index 0ceae1e..0000000
--- a/kernel/bpf/test_stub.c
+++ /dev/null
@@ -1,78 +0,0 @@
-/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/bpf.h>
-
-/* test stubs for BPF_MAP_TYPE_UNSPEC and for BPF_PROG_TYPE_UNSPEC
- * to be used by user space verifier testsuite
- */
-struct bpf_context {
-	u64 arg1;
-	u64 arg2;
-};
-
-static const struct bpf_func_proto *test_func_proto(enum bpf_func_id func_id)
-{
-	switch (func_id) {
-	case BPF_FUNC_map_lookup_elem:
-		return &bpf_map_lookup_elem_proto;
-	case BPF_FUNC_map_update_elem:
-		return &bpf_map_update_elem_proto;
-	case BPF_FUNC_map_delete_elem:
-		return &bpf_map_delete_elem_proto;
-	default:
-		return NULL;
-	}
-}
-
-static const struct bpf_context_access {
-	int size;
-	enum bpf_access_type type;
-} test_ctx_access[] = {
-	[offsetof(struct bpf_context, arg1)] = {
-		FIELD_SIZEOF(struct bpf_context, arg1),
-		BPF_READ
-	},
-	[offsetof(struct bpf_context, arg2)] = {
-		FIELD_SIZEOF(struct bpf_context, arg2),
-		BPF_READ
-	},
-};
-
-static bool test_is_valid_access(int off, int size, enum bpf_access_type type)
-{
-	const struct bpf_context_access *access;
-
-	if (off < 0 || off >= ARRAY_SIZE(test_ctx_access))
-		return false;
-
-	access = &test_ctx_access[off];
-	if (access->size == size && (access->type & type))
-		return true;
-
-	return false;
-}
-
-static struct bpf_verifier_ops test_ops = {
-	.get_func_proto = test_func_proto,
-	.is_valid_access = test_is_valid_access,
-};
-
-static struct bpf_prog_type_list tl_prog = {
-	.ops = &test_ops,
-	.type = BPF_PROG_TYPE_UNSPEC,
-};
-
-static int __init register_test_ops(void)
-{
-	bpf_register_prog_type(&tl_prog);
-	return 0;
-}
-late_initcall(register_test_ops);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a28e09c..630a7ba 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -755,7 +755,7 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 	enum bpf_reg_type expected_type;
 	int err = 0;
 
-	if (arg_type == ARG_ANYTHING)
+	if (arg_type == ARG_DONTCARE)
 		return 0;
 
 	if (reg->type == NOT_INIT) {
@@ -763,6 +763,9 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 		return -EACCES;
 	}
 
+	if (arg_type == ARG_ANYTHING)
+		return 0;
+
 	if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
 	    arg_type == ARG_PTR_TO_MAP_VALUE) {
 		expected_type = PTR_TO_STACK;
@@ -770,6 +773,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 		expected_type = CONST_IMM;
 	} else if (arg_type == ARG_CONST_MAP_PTR) {
 		expected_type = CONST_PTR_TO_MAP;
+	} else if (arg_type == ARG_PTR_TO_CTX) {
+		expected_type = PTR_TO_CTX;
 	} else {
 		verbose("unsupported arg_type %d\n", arg_type);
 		return -EFAULT;
@@ -852,7 +857,7 @@ static int check_call(struct verifier_env *env, int func_id)
 	}
 
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
-	if (!env->prog->aux->is_gpl_compatible && fn->gpl_only) {
+	if (!env->prog->gpl_compatible && fn->gpl_only) {
 		verbose("cannot call GPL only function from proprietary program\n");
 		return -EINVAL;
 	}
@@ -1172,6 +1177,18 @@ static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static bool may_access_skb(enum bpf_prog_type type)
+{
+	switch (type) {
+	case BPF_PROG_TYPE_SOCKET_FILTER:
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* verify safety of LD_ABS|LD_IND instructions:
  * - they can only appear in the programs where ctx == skb
  * - since they are wrappers of function calls, they scratch R1-R5 registers,
@@ -1194,8 +1211,8 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	struct reg_state *reg;
 	int i, err;
 
-	if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
-		verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n");
+	if (!may_access_skb(env->prog->type)) {
+		verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n");
 		return -EINVAL;
 	}
 
@@ -1606,11 +1623,10 @@ static int do_check(struct verifier_env *env)
 				return err;
 
 		} else if (class == BPF_LDX) {
-			if (BPF_MODE(insn->code) != BPF_MEM ||
-			    insn->imm != 0) {
-				verbose("BPF_LDX uses reserved fields\n");
-				return -EINVAL;
-			}
+			enum bpf_reg_type src_reg_type;
+
+			/* check for reserved fields is already done */
+
 			/* check src operand */
 			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
 			if (err)
@@ -1629,6 +1645,29 @@ static int do_check(struct verifier_env *env)
 			if (err)
 				return err;
 
+			src_reg_type = regs[insn->src_reg].type;
+
+			if (insn->imm == 0 && BPF_SIZE(insn->code) == BPF_W) {
+				/* saw a valid insn
+				 * dst_reg = *(u32 *)(src_reg + off)
+				 * use reserved 'imm' field to mark this insn
+				 */
+				insn->imm = src_reg_type;
+
+			} else if (src_reg_type != insn->imm &&
+				   (src_reg_type == PTR_TO_CTX ||
+				    insn->imm == PTR_TO_CTX)) {
+				/* ABuser program is trying to use the same insn
+				 * dst_reg = *(u32*) (src_reg + off)
+				 * with different pointer types:
+				 * src_reg == ctx in one branch and
+				 * src_reg == stack|map in some other branch.
+				 * Reject it.
+				 */
+				verbose("same insn cannot be used with different pointers\n");
+				return -EINVAL;
+			}
+
 		} else if (class == BPF_STX) {
 			if (BPF_MODE(insn->code) == BPF_XADD) {
 				err = check_xadd(env, insn);
@@ -1776,6 +1815,13 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 	int i, j;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (BPF_CLASS(insn->code) == BPF_LDX &&
+		    (BPF_MODE(insn->code) != BPF_MEM ||
+		     insn->imm != 0)) {
+			verbose("BPF_LDX uses reserved fields\n");
+			return -EINVAL;
+		}
+
 		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
 			struct bpf_map *map;
 			struct fd f;
@@ -1867,6 +1913,92 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env)
 			insn->src_reg = 0;
 }
 
+static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
+{
+	struct bpf_insn *insn = prog->insnsi;
+	int insn_cnt = prog->len;
+	int i;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (BPF_CLASS(insn->code) != BPF_JMP ||
+		    BPF_OP(insn->code) == BPF_CALL ||
+		    BPF_OP(insn->code) == BPF_EXIT)
+			continue;
+
+		/* adjust offset of jmps if necessary */
+		if (i < pos && i + insn->off + 1 > pos)
+			insn->off += delta;
+		else if (i > pos && i + insn->off + 1 < pos)
+			insn->off -= delta;
+	}
+}
+
+/* convert load instructions that access fields of 'struct __sk_buff'
+ * into sequence of instructions that access fields of 'struct sk_buff'
+ */
+static int convert_ctx_accesses(struct verifier_env *env)
+{
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+	struct bpf_insn insn_buf[16];
+	struct bpf_prog *new_prog;
+	u32 cnt;
+	int i;
+
+	if (!env->prog->aux->ops->convert_ctx_access)
+		return 0;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (insn->code != (BPF_LDX | BPF_MEM | BPF_W))
+			continue;
+
+		if (insn->imm != PTR_TO_CTX) {
+			/* clear internal mark */
+			insn->imm = 0;
+			continue;
+		}
+
+		cnt = env->prog->aux->ops->
+			convert_ctx_access(insn->dst_reg, insn->src_reg,
+					   insn->off, insn_buf);
+		if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+			verbose("bpf verifier is misconfigured\n");
+			return -EINVAL;
+		}
+
+		if (cnt == 1) {
+			memcpy(insn, insn_buf, sizeof(*insn));
+			continue;
+		}
+
+		/* several new insns need to be inserted. Make room for them */
+		insn_cnt += cnt - 1;
+		new_prog = bpf_prog_realloc(env->prog,
+					    bpf_prog_size(insn_cnt),
+					    GFP_USER);
+		if (!new_prog)
+			return -ENOMEM;
+
+		new_prog->len = insn_cnt;
+
+		memmove(new_prog->insnsi + i + cnt, new_prog->insns + i + 1,
+			sizeof(*insn) * (insn_cnt - i - cnt));
+
+		/* copy substitute insns in place of load instruction */
+		memcpy(new_prog->insnsi + i, insn_buf, sizeof(*insn) * cnt);
+
+		/* adjust branches in the whole program */
+		adjust_branches(new_prog, i, cnt - 1);
+
+		/* keep walking new program and skip insns we just inserted */
+		env->prog = new_prog;
+		insn = new_prog->insnsi + i + cnt - 1;
+		i += cnt - 1;
+	}
+
+	return 0;
+}
+
 static void free_states(struct verifier_env *env)
 {
 	struct verifier_state_list *sl, *sln;
@@ -1889,13 +2021,13 @@ static void free_states(struct verifier_env *env)
 	kfree(env->explored_states);
 }
 
-int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
+int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 {
 	char __user *log_ubuf = NULL;
 	struct verifier_env *env;
 	int ret = -EINVAL;
 
-	if (prog->len <= 0 || prog->len > BPF_MAXINSNS)
+	if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS)
 		return -E2BIG;
 
 	/* 'struct verifier_env' can be global, but since it's not small,
@@ -1905,7 +2037,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 	if (!env)
 		return -ENOMEM;
 
-	env->prog = prog;
+	env->prog = *prog;
 
 	/* grab the mutex to protect few globals used by verifier */
 	mutex_lock(&bpf_verifier_lock);
@@ -1937,7 +2069,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 	if (ret < 0)
 		goto skip_full_check;
 
-	env->explored_states = kcalloc(prog->len,
+	env->explored_states = kcalloc(env->prog->len,
 				       sizeof(struct verifier_state_list *),
 				       GFP_USER);
 	ret = -ENOMEM;
@@ -1954,6 +2086,10 @@ skip_full_check:
 	while (pop_stack(env, NULL) >= 0);
 	free_states(env);
 
+	if (ret == 0)
+		/* program is valid, convert *(u32*)(ctx + off) accesses */
+		ret = convert_ctx_accesses(env);
+
 	if (log_level && log_len >= log_size - 1) {
 		BUG_ON(log_len >= log_size);
 		/* verifier log exceeded user supplied buffer */
@@ -1969,18 +2105,18 @@ skip_full_check:
 
 	if (ret == 0 && env->used_map_cnt) {
 		/* if program passed verifier, update used_maps in bpf_prog_info */
-		prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
-						     sizeof(env->used_maps[0]),
-						     GFP_KERNEL);
+		env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
+							  sizeof(env->used_maps[0]),
+							  GFP_KERNEL);
 
-		if (!prog->aux->used_maps) {
+		if (!env->prog->aux->used_maps) {
 			ret = -ENOMEM;
 			goto free_log_buf;
 		}
 
-		memcpy(prog->aux->used_maps, env->used_maps,
+		memcpy(env->prog->aux->used_maps, env->used_maps,
 		       sizeof(env->used_maps[0]) * env->used_map_cnt);
-		prog->aux->used_map_cnt = env->used_map_cnt;
+		env->prog->aux->used_map_cnt = env->used_map_cnt;
 
 		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
 		 * bpf_ld_imm64 instructions
@@ -1992,11 +2128,12 @@ free_log_buf:
 	if (log_level)
 		vfree(log_buf);
 free_env:
-	if (!prog->aux->used_maps)
+	if (!env->prog->aux->used_maps)
 		/* if we didn't copy map pointers into bpf_prog_info, release
 		 * them now. Otherwise free_bpf_prog_info() will release them.
 		 */
 		release_maps(env);
+	*prog = env->prog;
 	kfree(env);
 	mutex_unlock(&bpf_verifier_lock);
 	return ret;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 453ef61..2fabc06 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4574,6 +4574,13 @@ static void perf_pending_event(struct irq_work *entry)
 {
 	struct perf_event *event = container_of(entry,
 			struct perf_event, pending);
+	int rctx;
+
+	rctx = perf_swevent_get_recursion_context();
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
 
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -4584,6 +4591,9 @@ static void perf_pending_event(struct irq_work *entry)
 		event->pending_wakeup = 0;
 		perf_event_wakeup(event);
 	}
+
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
 }
 
 /*
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 88d0d44..ba77ab5 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -633,7 +633,7 @@ static int count_matching_names(struct lock_class *new_class)
 	if (!new_class->name)
 		return 0;
 
-	list_for_each_entry(class, &all_lock_classes, lock_entry) {
+	list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
 		if (new_class->key - new_class->subclass == class->key)
 			return class->name_version;
 		if (class->name && !strcmp(class->name, new_class->name))
@@ -700,10 +700,12 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 	hash_head = classhashentry(key);
 
 	/*
-	 * We can walk the hash lockfree, because the hash only
-	 * grows, and we are careful when adding entries to the end:
+	 * We do an RCU walk of the hash, see lockdep_free_key_range().
 	 */
-	list_for_each_entry(class, hash_head, hash_entry) {
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return NULL;
+
+	list_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key) {
 			/*
 			 * Huh! same key, different name? Did someone trample
@@ -728,7 +730,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	struct lockdep_subclass_key *key;
 	struct list_head *hash_head;
 	struct lock_class *class;
-	unsigned long flags;
+
+	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
 	class = look_up_lock_class(lock, subclass);
 	if (likely(class))
@@ -750,28 +753,26 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	key = lock->key->subkeys + subclass;
 	hash_head = classhashentry(key);
 
-	raw_local_irq_save(flags);
 	if (!graph_lock()) {
-		raw_local_irq_restore(flags);
 		return NULL;
 	}
 	/*
 	 * We have to do the hash-walk again, to avoid races
 	 * with another CPU:
 	 */
-	list_for_each_entry(class, hash_head, hash_entry)
+	list_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key)
 			goto out_unlock_set;
+	}
+
 	/*
 	 * Allocate a new key from the static array, and add it to
 	 * the hash:
 	 */
 	if (nr_lock_classes >= MAX_LOCKDEP_KEYS) {
 		if (!debug_locks_off_graph_unlock()) {
-			raw_local_irq_restore(flags);
 			return NULL;
 		}
-		raw_local_irq_restore(flags);
 
 		print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!");
 		dump_stack();
@@ -798,7 +799,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
 	if (verbose(class)) {
 		graph_unlock();
-		raw_local_irq_restore(flags);
 
 		printk("\nnew class %p: %s", class->key, class->name);
 		if (class->name_version > 1)
@@ -806,15 +806,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 		printk("\n");
 		dump_stack();
 
-		raw_local_irq_save(flags);
 		if (!graph_lock()) {
-			raw_local_irq_restore(flags);
 			return NULL;
 		}
 	}
 out_unlock_set:
 	graph_unlock();
-	raw_local_irq_restore(flags);
 
 out_set_class_cache:
 	if (!subclass || force)
@@ -870,11 +867,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
 	entry->distance = distance;
 	entry->trace = *trace;
 	/*
-	 * Since we never remove from the dependency list, the list can
-	 * be walked lockless by other CPUs, it's only allocation
-	 * that must be protected by the spinlock. But this also means
-	 * we must make new entries visible only once writes to the
-	 * entry become visible - hence the RCU op:
+	 * Both allocation and removal are done under the graph lock; but
+	 * iteration is under RCU-sched; see look_up_lock_class() and
+	 * lockdep_free_key_range().
 	 */
 	list_add_tail_rcu(&entry->entry, head);
 
@@ -1025,7 +1020,9 @@ static int __bfs(struct lock_list *source_entry,
 		else
 			head = &lock->class->locks_before;
 
-		list_for_each_entry(entry, head, entry) {
+		DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
+		list_for_each_entry_rcu(entry, head, entry) {
 			if (!lock_accessed(entry)) {
 				unsigned int cq_depth;
 				mark_lock_accessed(entry, lock);
@@ -2022,7 +2019,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	 * We can walk it lock-free, because entries only get added
 	 * to the hash:
 	 */
-	list_for_each_entry(chain, hash_head, entry) {
+	list_for_each_entry_rcu(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
 			debug_atomic_inc(chain_lookup_hits);
@@ -2996,8 +2993,18 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 	if (unlikely(!debug_locks))
 		return;
 
-	if (subclass)
+	if (subclass) {
+		unsigned long flags;
+
+		if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+			return;
+
+		raw_local_irq_save(flags);
+		current->lockdep_recursion = 1;
 		register_lock_class(lock, subclass, 1);
+		current->lockdep_recursion = 0;
+		raw_local_irq_restore(flags);
+	}
 }
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
@@ -3887,9 +3894,17 @@ static inline int within(const void *addr, void *start, unsigned long size)
 	return addr >= start && addr < start + size;
 }
 
+/*
+ * Used in module.c to remove lock classes from memory that is going to be
+ * freed; and possibly re-used by other modules.
+ *
+ * We will have had one sync_sched() before getting here, so we're guaranteed
+ * nobody will look up these exact classes -- they're properly dead but still
+ * allocated.
+ */
 void lockdep_free_key_range(void *start, unsigned long size)
 {
-	struct lock_class *class, *next;
+	struct lock_class *class;
 	struct list_head *head;
 	unsigned long flags;
 	int i;
@@ -3905,7 +3920,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 		head = classhash_table + i;
 		if (list_empty(head))
 			continue;
-		list_for_each_entry_safe(class, next, head, hash_entry) {
+		list_for_each_entry_rcu(class, head, hash_entry) {
 			if (within(class->key, start, size))
 				zap_class(class);
 			else if (within(class->name, start, size))
@@ -3916,11 +3931,25 @@ void lockdep_free_key_range(void *start, unsigned long size)
 	if (locked)
 		graph_unlock();
 	raw_local_irq_restore(flags);
+
+	/*
+	 * Wait for any possible iterators from look_up_lock_class() to pass
+	 * before continuing to free the memory they refer to.
+	 *
+	 * sync_sched() is sufficient because the read-side is IRQ disable.
+	 */
+	synchronize_sched();
+
+	/*
+	 * XXX at this point we could return the resources to the pool;
+	 * instead we leak them. We would need to change to bitmap allocators
+	 * instead of the linear allocators we have now.
+	 */
 }
 
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
-	struct lock_class *class, *next;
+	struct lock_class *class;
 	struct list_head *head;
 	unsigned long flags;
 	int i, j;
@@ -3948,7 +3977,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 		head = classhash_table + i;
 		if (list_empty(head))
 			continue;
-		list_for_each_entry_safe(class, next, head, hash_entry) {
+		list_for_each_entry_rcu(class, head, hash_entry) {
 			int match = 0;
 
 			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
diff --git a/kernel/module.c b/kernel/module.c
index b3d634e..99fdf94 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1865,7 +1865,7 @@ static void free_module(struct module *mod)
 	kfree(mod->args);
 	percpu_modfree(mod);
 
-	/* Free lock-classes: */
+	/* Free lock-classes; relies on the preceding sync_rcu(). */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
 	/* Finally, free the core (containing the module structure) */
@@ -3349,9 +3349,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* Free lock-classes: */
-	lockdep_free_key_range(mod->module_core, mod->core_size);
-
 	/* we can't deallocate the module until we clear memory protection */
 	unset_module_init_ro_nx(mod);
 	unset_module_core_ro_nx(mod);
@@ -3375,6 +3372,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	synchronize_rcu();
 	mutex_unlock(&module_mutex);
  free_module:
+	/* Free lock-classes; relies on the preceding sync_rcu() */
+	lockdep_free_key_range(mod->module_core, mod->core_size);
+
 	module_deallocate(mod, info);
  free_copy:
 	free_copy(info);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f0f831e..62671f5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3034,6 +3034,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	} else {
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
+		if (rt_prio(oldprio))
+			p->rt.timeout = 0;
 		p->sched_class = &fair_sched_class;
 	}
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce18f3..bcfe320 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1609,9 +1609,11 @@ static void update_task_scan_period(struct task_struct *p,
 	/*
 	 * If there were no record hinting faults then either the task is
 	 * completely idle or all activity is areas that are not of interest
-	 * to automatic numa balancing. Scan slower
+	 * to automatic numa balancing. Related to that, if there were failed
+	 * migration then it implies we are migrating too quickly or the local
+	 * node is overloaded. In either case, scan slower
 	 */
-	if (local + shared == 0) {
+	if (local + shared == 0 || p->numa_faults_locality[2]) {
 		p->numa_scan_period = min(p->numa_scan_period_max,
 			p->numa_scan_period << 1);
 
@@ -2080,6 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 
 	if (migrated)
 		p->numa_pages_migrated += pages;
+	if (flags & TNF_MIGRATE_FAIL)
+		p->numa_faults_locality[2] += pages;
 
 	p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
 	p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 83d907a..4012336 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1229,6 +1229,14 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	},
 	{
+		.procname	= "dirtytime_expire_seconds",
+		.data		= &dirtytime_expire_interval,
+		.maxlen		= sizeof(dirty_expire_interval),
+		.mode		= 0644,
+		.proc_handler	= dirtytime_interval_handler,
+		.extra1		= &zero,
+	},
+	{
 		.procname       = "nr_pdflush_threads",
 		.mode           = 0444 /* read-only */,
 		.proc_handler   = pdflush_proc_obsolete,
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index eb682d5..6aac4be 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode,
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
+	int bc_moved;
 	/*
 	 * We try to cancel the timer first. If the callback is on
 	 * flight on some other cpu then we let it handle it. If we
@@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 	 * restart the timer because we are in the callback, but we
 	 * can set the expiry time and let the callback return
 	 * HRTIMER_RESTART.
+	 *
+	 * Since we are in the idle loop at this point and because
+	 * hrtimer_{start/cancel} functions call into tracing,
+	 * calls to these functions must be bound within RCU_NONIDLE.
 	 */
-	if (hrtimer_try_to_cancel(&bctimer) >= 0) {
-		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+	RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
+		!hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
+			0);
+	if (bc_moved) {
 		/* Bind the "device" to the cpu */
 		bc->bound_on = smp_processor_id();
 	} else if (bc->bound_on == smp_processor_id()) {