Merge remote-tracking branch 'net-next/master' into mac80211-next

Bring in net-next which had pulled in net, so I have the changes
from mac80211 and can apply a patch that would otherwise conflict.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>

12 files changed, 3822 insertions, 397 deletions

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index a713fd23ec88..f27f5496d6fe 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -4,9 +4,13 @@ obj-y := core.o
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+ifeq ($(CONFIG_XDP_SOCKETS),y)
+obj-$(CONFIG_BPF_SYSCALL) += xskmap.o
+endif
 obj-$(CONFIG_BPF_SYSCALL) += offload.o
 ifeq ($(CONFIG_STREAM_PARSER),y)
 ifeq ($(CONFIG_INET),y)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 14750e7c5ee4..0fd8d8f1a398 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -11,11 +11,13 @@
  * General Public License for more details.
  */
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/filter.h>
 #include <linux/perf_event.h>
+#include <uapi/linux/btf.h>
 
 #include "map_in_map.h"
 
@@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map)
 	bpf_map_area_free(array);
 }
 
+static void array_map_seq_show_elem(struct bpf_map *map, void *key,
+				    struct seq_file *m)
+{
+	void *value;
+
+	rcu_read_lock();
+
+	value = array_map_lookup_elem(map, key);
+	if (!value) {
+		rcu_read_unlock();
+		return;
+	}
+
+	seq_printf(m, "%u: ", *(u32 *)key);
+	btf_type_seq_show(map->btf, map->btf_value_id, value, m);
+	seq_puts(m, "\n");
+
+	rcu_read_unlock();
+}
+
+static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+			       u32 btf_key_id, u32 btf_value_id)
+{
+	const struct btf_type *key_type, *value_type;
+	u32 key_size, value_size;
+	u32 int_data;
+
+	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+	if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+		return -EINVAL;
+
+	int_data = *(u32 *)(key_type + 1);
+	/* bpf array can only take a u32 key.  This check makes
+	 * sure that the btf matches the attr used during map_create.
+	 */
+	if (BTF_INT_BITS(int_data) != 32 || key_size != 4 ||
+	    BTF_INT_OFFSET(int_data))
+		return -EINVAL;
+
+	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
+	if (!value_type || value_size > map->value_size)
+		return -EINVAL;
+
+	return 0;
+}
+
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = {
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
 	.map_gen_lookup = array_map_gen_lookup,
+	.map_seq_show_elem = array_map_seq_show_elem,
+	.map_check_btf = array_map_check_btf,
 };
 
 const struct bpf_map_ops percpu_array_map_ops = {
@@ -476,7 +526,7 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -495,6 +545,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+	.map_release_uref = bpf_fd_array_map_clear,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
new file mode 100644
index 000000000000..ded10ab47b8a
--- /dev/null
+++ b/kernel/bpf/btf.c
@@ -0,0 +1,2168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#include <uapi/linux/btf.h>
+#include <uapi/linux/types.h>
+#include <linux/seq_file.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/idr.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+
+/* BTF (BPF Type Format) is the meta data format which describes
+ * the data types of BPF program/map.  Hence, it basically focus
+ * on the C programming language which the modern BPF is primary
+ * using.
+ *
+ * ELF Section:
+ * ~~~~~~~~~~~
+ * The BTF data is stored under the ".BTF" ELF section
+ *
+ * struct btf_type:
+ * ~~~~~~~~~~~~~~~
+ * Each 'struct btf_type' object describes a C data type.
+ * Depending on the type it is describing, a 'struct btf_type'
+ * object may be followed by more data.  F.e.
+ * To describe an array, 'struct btf_type' is followed by
+ * 'struct btf_array'.
+ *
+ * 'struct btf_type' and any extra data following it are
+ * 4 bytes aligned.
+ *
+ * Type section:
+ * ~~~~~~~~~~~~~
+ * The BTF type section contains a list of 'struct btf_type' objects.
+ * Each one describes a C type.  Recall from the above section
+ * that a 'struct btf_type' object could be immediately followed by extra
+ * data in order to desribe some particular C types.
+ *
+ * type_id:
+ * ~~~~~~~
+ * Each btf_type object is identified by a type_id.  The type_id
+ * is implicitly implied by the location of the btf_type object in
+ * the BTF type section.  The first one has type_id 1.  The second
+ * one has type_id 2...etc.  Hence, an earlier btf_type has
+ * a smaller type_id.
+ *
+ * A btf_type object may refer to another btf_type object by using
+ * type_id (i.e. the "type" in the "struct btf_type").
+ *
+ * NOTE that we cannot assume any reference-order.
+ * A btf_type object can refer to an earlier btf_type object
+ * but it can also refer to a later btf_type object.
+ *
+ * For example, to describe "const void *".  A btf_type
+ * object describing "const" may refer to another btf_type
+ * object describing "void *".  This type-reference is done
+ * by specifying type_id:
+ *
+ * [1] CONST (anon) type_id=2
+ * [2] PTR (anon) type_id=0
+ *
+ * The above is the btf_verifier debug log:
+ *   - Each line started with "[?]" is a btf_type object
+ *   - [?] is the type_id of the btf_type object.
+ *   - CONST/PTR is the BTF_KIND_XXX
+ *   - "(anon)" is the name of the type.  It just
+ *     happens that CONST and PTR has no name.
+ *   - type_id=XXX is the 'u32 type' in btf_type
+ *
+ * NOTE: "void" has type_id 0
+ *
+ * String section:
+ * ~~~~~~~~~~~~~~
+ * The BTF string section contains the names used by the type section.
+ * Each string is referred by an "offset" from the beginning of the
+ * string section.
+ *
+ * Each string is '\0' terminated.
+ *
+ * The first character in the string section must be '\0'
+ * which is used to mean 'anonymous'. Some btf_type may not
+ * have a name.
+ */
+
+/* BTF verification:
+ *
+ * To verify BTF data, two passes are needed.
+ *
+ * Pass #1
+ * ~~~~~~~
+ * The first pass is to collect all btf_type objects to
+ * an array: "btf->types".
+ *
+ * Depending on the C type that a btf_type is describing,
+ * a btf_type may be followed by extra data.  We don't know
+ * how many btf_type is there, and more importantly we don't
+ * know where each btf_type is located in the type section.
+ *
+ * Without knowing the location of each type_id, most verifications
+ * cannot be done.  e.g. an earlier btf_type may refer to a later
+ * btf_type (recall the "const void *" above), so we cannot
+ * check this type-reference in the first pass.
+ *
+ * In the first pass, it still does some verifications (e.g.
+ * checking the name is a valid offset to the string section).
+ *
+ * Pass #2
+ * ~~~~~~~
+ * The main focus is to resolve a btf_type that is referring
+ * to another type.
+ *
+ * We have to ensure the referring type:
+ * 1) does exist in the BTF (i.e. in btf->types[])
+ * 2) does not cause a loop:
+ *	struct A {
+ *		struct B b;
+ *	};
+ *
+ *	struct B {
+ *		struct A a;
+ *	};
+ *
+ * btf_type_needs_resolve() decides if a btf_type needs
+ * to be resolved.
+ *
+ * The needs_resolve type implements the "resolve()" ops which
+ * essentially does a DFS and detects backedge.
+ *
+ * During resolve (or DFS), different C types have different
+ * "RESOLVED" conditions.
+ *
+ * When resolving a BTF_KIND_STRUCT, we need to resolve all its
+ * members because a member is always referring to another
+ * type.  A struct's member can be treated as "RESOLVED" if
+ * it is referring to a BTF_KIND_PTR.  Otherwise, the
+ * following valid C struct would be rejected:
+ *
+ *	struct A {
+ *		int m;
+ *		struct A *a;
+ *	};
+ *
+ * When resolving a BTF_KIND_PTR, it needs to keep resolving if
+ * it is referring to another BTF_KIND_PTR.  Otherwise, we cannot
+ * detect a pointer loop, e.g.:
+ * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR +
+ *                        ^                                         |
+ *                        +-----------------------------------------+
+ *
+ */
+
+#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE)
+#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
+#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
+#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
+#define BITS_ROUNDUP_BYTES(bits) \
+	(BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
+
+/* 16MB for 64k structs and each has 16 members and
+ * a few MB spaces for the string section.
+ * The hard limit is S32_MAX.
+ */
+#define BTF_MAX_SIZE (16 * 1024 * 1024)
+/* 64k. We can raise it later. The hard limit is S32_MAX. */
+#define BTF_MAX_NR_TYPES 65535
+
+#define for_each_member(i, struct_type, member)			\
+	for (i = 0, member = btf_type_member(struct_type);	\
+	     i < btf_type_vlen(struct_type);			\
+	     i++, member++)
+
+#define for_each_member_from(i, from, struct_type, member)		\
+	for (i = from, member = btf_type_member(struct_type) + from;	\
+	     i < btf_type_vlen(struct_type);				\
+	     i++, member++)
+
+static DEFINE_IDR(btf_idr);
+static DEFINE_SPINLOCK(btf_idr_lock);
+
+struct btf {
+	union {
+		struct btf_header *hdr;
+		void *data;
+	};
+	struct btf_type **types;
+	u32 *resolved_ids;
+	u32 *resolved_sizes;
+	const char *strings;
+	void *nohdr_data;
+	u32 nr_types;
+	u32 types_size;
+	u32 data_size;
+	refcount_t refcnt;
+	u32 id;
+	struct rcu_head rcu;
+};
+
+enum verifier_phase {
+	CHECK_META,
+	CHECK_TYPE,
+};
+
+struct resolve_vertex {
+	const struct btf_type *t;
+	u32 type_id;
+	u16 next_member;
+};
+
+enum visit_state {
+	NOT_VISITED,
+	VISITED,
+	RESOLVED,
+};
+
+enum resolve_mode {
+	RESOLVE_TBD,	/* To Be Determined */
+	RESOLVE_PTR,	/* Resolving for Pointer */
+	RESOLVE_STRUCT_OR_ARRAY,	/* Resolving for struct/union
+					 * or array
+					 */
+};
+
+#define MAX_RESOLVE_DEPTH 32
+
+struct btf_verifier_env {
+	struct btf *btf;
+	u8 *visit_states;
+	struct resolve_vertex stack[MAX_RESOLVE_DEPTH];
+	struct bpf_verifier_log log;
+	u32 log_type_id;
+	u32 top_stack;
+	enum verifier_phase phase;
+	enum resolve_mode resolve_mode;
+};
+
+static const char * const btf_kind_str[NR_BTF_KINDS] = {
+	[BTF_KIND_UNKN]		= "UNKNOWN",
+	[BTF_KIND_INT]		= "INT",
+	[BTF_KIND_PTR]		= "PTR",
+	[BTF_KIND_ARRAY]	= "ARRAY",
+	[BTF_KIND_STRUCT]	= "STRUCT",
+	[BTF_KIND_UNION]	= "UNION",
+	[BTF_KIND_ENUM]		= "ENUM",
+	[BTF_KIND_FWD]		= "FWD",
+	[BTF_KIND_TYPEDEF]	= "TYPEDEF",
+	[BTF_KIND_VOLATILE]	= "VOLATILE",
+	[BTF_KIND_CONST]	= "CONST",
+	[BTF_KIND_RESTRICT]	= "RESTRICT",
+};
+
+struct btf_kind_operations {
+	s32 (*check_meta)(struct btf_verifier_env *env,
+			  const struct btf_type *t,
+			  u32 meta_left);
+	int (*resolve)(struct btf_verifier_env *env,
+		       const struct resolve_vertex *v);
+	int (*check_member)(struct btf_verifier_env *env,
+			    const struct btf_type *struct_type,
+			    const struct btf_member *member,
+			    const struct btf_type *member_type);
+	void (*log_details)(struct btf_verifier_env *env,
+			    const struct btf_type *t);
+	void (*seq_show)(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offsets,
+			 struct seq_file *m);
+};
+
+static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
+static struct btf_type btf_void;
+
+static bool btf_type_is_modifier(const struct btf_type *t)
+{
+	/* Some of them is not strictly a C modifier
+	 * but they are grouped into the same bucket
+	 * for BTF concern:
+	 *   A type (t) that refers to another
+	 *   type through t->type AND its size cannot
+	 *   be determined without following the t->type.
+	 *
+	 * ptr does not fall into this bucket
+	 * because its size is always sizeof(void *).
+	 */
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_CONST:
+	case BTF_KIND_RESTRICT:
+		return true;
+	}
+
+	return false;
+}
+
+static bool btf_type_is_void(const struct btf_type *t)
+{
+	/* void => no type and size info.
+	 * Hence, FWD is also treated as void.
+	 */
+	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+}
+
+static bool btf_type_is_void_or_null(const struct btf_type *t)
+{
+	return !t || btf_type_is_void(t);
+}
+
+/* union is only a special case of struct:
+ * all its offsetof(member) == 0
+ */
+static bool btf_type_is_struct(const struct btf_type *t)
+{
+	u8 kind = BTF_INFO_KIND(t->info);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static bool btf_type_is_array(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
+}
+
+static bool btf_type_is_ptr(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
+}
+
+static bool btf_type_is_int(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
+}
+
+/* What types need to be resolved?
+ *
+ * btf_type_is_modifier() is an obvious one.
+ *
+ * btf_type_is_struct() because its member refers to
+ * another type (through member->type).
+
+ * btf_type_is_array() because its element (array->type)
+ * refers to another type.  Array can be thought of a
+ * special case of struct while array just has the same
+ * member-type repeated by array->nelems of times.
+ */
+static bool btf_type_needs_resolve(const struct btf_type *t)
+{
+	return btf_type_is_modifier(t) ||
+		btf_type_is_ptr(t) ||
+		btf_type_is_struct(t) ||
+		btf_type_is_array(t);
+}
+
+/* t->size can be used */
+static bool btf_type_has_size(const struct btf_type *t)
+{
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_INT:
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+	case BTF_KIND_ENUM:
+		return true;
+	}
+
+	return false;
+}
+
+static const char *btf_int_encoding_str(u8 encoding)
+{
+	if (encoding == 0)
+		return "(none)";
+	else if (encoding == BTF_INT_SIGNED)
+		return "SIGNED";
+	else if (encoding == BTF_INT_CHAR)
+		return "CHAR";
+	else if (encoding == BTF_INT_BOOL)
+		return "BOOL";
+	else if (encoding == BTF_INT_VARARGS)
+		return "VARARGS";
+	else
+		return "UNKN";
+}
+
+static u16 btf_type_vlen(const struct btf_type *t)
+{
+	return BTF_INFO_VLEN(t->info);
+}
+
+static u32 btf_type_int(const struct btf_type *t)
+{
+	return *(u32 *)(t + 1);
+}
+
+static const struct btf_array *btf_type_array(const struct btf_type *t)
+{
+	return (const struct btf_array *)(t + 1);
+}
+
+static const struct btf_member *btf_type_member(const struct btf_type *t)
+{
+	return (const struct btf_member *)(t + 1);
+}
+
+static const struct btf_enum *btf_type_enum(const struct btf_type *t)
+{
+	return (const struct btf_enum *)(t + 1);
+}
+
+static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
+{
+	return kind_ops[BTF_INFO_KIND(t->info)];
+}
+
+static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
+{
+	return !BTF_STR_TBL_ELF_ID(offset) &&
+		BTF_STR_OFFSET(offset) < btf->hdr->str_len;
+}
+
+static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+{
+	if (!BTF_STR_OFFSET(offset))
+		return "(anon)";
+	else if (BTF_STR_OFFSET(offset) < btf->hdr->str_len)
+		return &btf->strings[BTF_STR_OFFSET(offset)];
+	else
+		return "(invalid-name-offset)";
+}
+
+static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
+{
+	if (type_id > btf->nr_types)
+		return NULL;
+
+	return btf->types[type_id];
+}
+
+__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
+					      const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	bpf_verifier_vlog(log, fmt, args);
+	va_end(args);
+}
+
+__printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env,
+					    const char *fmt, ...)
+{
+	struct bpf_verifier_log *log = &env->log;
+	va_list args;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+
+	va_start(args, fmt);
+	bpf_verifier_vlog(log, fmt, args);
+	va_end(args);
+}
+
+__printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
+						   const struct btf_type *t,
+						   bool log_details,
+						   const char *fmt, ...)
+{
+	struct bpf_verifier_log *log = &env->log;
+	u8 kind = BTF_INFO_KIND(t->info);
+	struct btf *btf = env->btf;
+	va_list args;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+
+	__btf_verifier_log(log, "[%u] %s %s%s",
+			   env->log_type_id,
+			   btf_kind_str[kind],
+			   btf_name_by_offset(btf, t->name_off),
+			   log_details ? " " : "");
+
+	if (log_details)
+		btf_type_ops(t)->log_details(env, t);
+
+	if (fmt && *fmt) {
+		__btf_verifier_log(log, " ");
+		va_start(args, fmt);
+		bpf_verifier_vlog(log, fmt, args);
+		va_end(args);
+	}
+
+	__btf_verifier_log(log, "\n");
+}
+
+#define btf_verifier_log_type(env, t, ...) \
+	__btf_verifier_log_type((env), (t), true, __VA_ARGS__)
+#define btf_verifier_log_basic(env, t, ...) \
+	__btf_verifier_log_type((env), (t), false, __VA_ARGS__)
+
+__printf(4, 5)
+static void btf_verifier_log_member(struct btf_verifier_env *env,
+				    const struct btf_type *struct_type,
+				    const struct btf_member *member,
+				    const char *fmt, ...)
+{
+	struct bpf_verifier_log *log = &env->log;
+	struct btf *btf = env->btf;
+	va_list args;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+
+	/* The CHECK_META phase already did a btf dump.
+	 *
+	 * If member is logged again, it must hit an error in
+	 * parsing this member.  It is useful to print out which
+	 * struct this member belongs to.
+	 */
+	if (env->phase != CHECK_META)
+		btf_verifier_log_type(env, struct_type, NULL);
+
+	__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
+			   btf_name_by_offset(btf, member->name_off),
+			   member->type, member->offset);
+
+	if (fmt && *fmt) {
+		__btf_verifier_log(log, " ");
+		va_start(args, fmt);
+		bpf_verifier_vlog(log, fmt, args);
+		va_end(args);
+	}
+
+	__btf_verifier_log(log, "\n");
+}
+
+static void btf_verifier_log_hdr(struct btf_verifier_env *env)
+{
+	struct bpf_verifier_log *log = &env->log;
+	const struct btf *btf = env->btf;
+	const struct btf_header *hdr;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+
+	hdr = btf->hdr;
+	__btf_verifier_log(log, "magic: 0x%x\n", hdr->magic);
+	__btf_verifier_log(log, "version: %u\n", hdr->version);
+	__btf_verifier_log(log, "flags: 0x%x\n", hdr->flags);
+	__btf_verifier_log(log, "parent_label: %u\n", hdr->parent_label);
+	__btf_verifier_log(log, "parent_name: %u\n", hdr->parent_name);
+	__btf_verifier_log(log, "label_off: %u\n", hdr->label_off);
+	__btf_verifier_log(log, "object_off: %u\n", hdr->object_off);
+	__btf_verifier_log(log, "func_off: %u\n", hdr->func_off);
+	__btf_verifier_log(log, "type_off: %u\n", hdr->type_off);
+	__btf_verifier_log(log, "str_off: %u\n", hdr->str_off);
+	__btf_verifier_log(log, "str_len: %u\n", hdr->str_len);
+	__btf_verifier_log(log, "btf_total_size: %u\n", btf->data_size);
+}
+
+static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t)
+{
+	struct btf *btf = env->btf;
+
+	/* < 2 because +1 for btf_void which is always in btf->types[0].
+	 * btf_void is not accounted in btf->nr_types because btf_void
+	 * does not come from the BTF file.
+	 */
+	if (btf->types_size - btf->nr_types < 2) {
+		/* Expand 'types' array */
+
+		struct btf_type **new_types;
+		u32 expand_by, new_size;
+
+		if (btf->types_size == BTF_MAX_NR_TYPES) {
+			btf_verifier_log(env, "Exceeded max num of types");
+			return -E2BIG;
+		}
+
+		expand_by = max_t(u32, btf->types_size >> 2, 16);
+		new_size = min_t(u32, BTF_MAX_NR_TYPES,
+				 btf->types_size + expand_by);
+
+		new_types = kvzalloc(new_size * sizeof(*new_types),
+				     GFP_KERNEL | __GFP_NOWARN);
+		if (!new_types)
+			return -ENOMEM;
+
+		if (btf->nr_types == 0)
+			new_types[0] = &btf_void;
+		else
+			memcpy(new_types, btf->types,
+			       sizeof(*btf->types) * (btf->nr_types + 1));
+
+		kvfree(btf->types);
+		btf->types = new_types;
+		btf->types_size = new_size;
+	}
+
+	btf->types[++(btf->nr_types)] = t;
+
+	return 0;
+}
+
+static int btf_alloc_id(struct btf *btf)
+{
+	int id;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock_bh(&btf_idr_lock);
+	id = idr_alloc_cyclic(&btf_idr, btf, 1, INT_MAX, GFP_ATOMIC);
+	if (id > 0)
+		btf->id = id;
+	spin_unlock_bh(&btf_idr_lock);
+	idr_preload_end();
+
+	if (WARN_ON_ONCE(!id))
+		return -ENOSPC;
+
+	return id > 0 ? 0 : id;
+}
+
+static void btf_free_id(struct btf *btf)
+{
+	unsigned long flags;
+
+	/*
+	 * In map-in-map, calling map_delete_elem() on outer
+	 * map will call bpf_map_put on the inner map.
+	 * It will then eventually call btf_free_id()
+	 * on the inner map.  Some of the map_delete_elem()
+	 * implementation may have irq disabled, so
+	 * we need to use the _irqsave() version instead
+	 * of the _bh() version.
+	 */
+	spin_lock_irqsave(&btf_idr_lock, flags);
+	idr_remove(&btf_idr, btf->id);
+	spin_unlock_irqrestore(&btf_idr_lock, flags);
+}
+
+static void btf_free(struct btf *btf)
+{
+	kvfree(btf->types);
+	kvfree(btf->resolved_sizes);
+	kvfree(btf->resolved_ids);
+	kvfree(btf->data);
+	kfree(btf);
+}
+
+static void btf_free_rcu(struct rcu_head *rcu)
+{
+	struct btf *btf = container_of(rcu, struct btf, rcu);
+
+	btf_free(btf);
+}
+
+void btf_put(struct btf *btf)
+{
+	if (btf && refcount_dec_and_test(&btf->refcnt)) {
+		btf_free_id(btf);
+		call_rcu(&btf->rcu, btf_free_rcu);
+	}
+}
+
+static int env_resolve_init(struct btf_verifier_env *env)
+{
+	struct btf *btf = env->btf;
+	u32 nr_types = btf->nr_types;
+	u32 *resolved_sizes = NULL;
+	u32 *resolved_ids = NULL;
+	u8 *visit_states = NULL;
+
+	/* +1 for btf_void */
+	resolved_sizes = kvzalloc((nr_types + 1) * sizeof(*resolved_sizes),
+				  GFP_KERNEL | __GFP_NOWARN);
+	if (!resolved_sizes)
+		goto nomem;
+
+	resolved_ids = kvzalloc((nr_types + 1) * sizeof(*resolved_ids),
+				GFP_KERNEL | __GFP_NOWARN);
+	if (!resolved_ids)
+		goto nomem;
+
+	visit_states = kvzalloc((nr_types + 1) * sizeof(*visit_states),
+				GFP_KERNEL | __GFP_NOWARN);
+	if (!visit_states)
+		goto nomem;
+
+	btf->resolved_sizes = resolved_sizes;
+	btf->resolved_ids = resolved_ids;
+	env->visit_states = visit_states;
+
+	return 0;
+
+nomem:
+	kvfree(resolved_sizes);
+	kvfree(resolved_ids);
+	kvfree(visit_states);
+	return -ENOMEM;
+}
+
+static void btf_verifier_env_free(struct btf_verifier_env *env)
+{
+	kvfree(env->visit_states);
+	kfree(env);
+}
+
+static bool env_type_is_resolve_sink(const struct btf_verifier_env *env,
+				     const struct btf_type *next_type)
+{
+	switch (env->resolve_mode) {
+	case RESOLVE_TBD:
+		/* int, enum or void is a sink */
+		return !btf_type_needs_resolve(next_type);
+	case RESOLVE_PTR:
+		/* int, enum, void, struct or array is a sink for ptr */
+		return !btf_type_is_modifier(next_type) &&
+			!btf_type_is_ptr(next_type);
+	case RESOLVE_STRUCT_OR_ARRAY:
+		/* int, enum, void or ptr is a sink for struct and array */
+		return !btf_type_is_modifier(next_type) &&
+			!btf_type_is_array(next_type) &&
+			!btf_type_is_struct(next_type);
+	default:
+		BUG_ON(1);
+	}
+}
+
+static bool env_type_is_resolved(const struct btf_verifier_env *env,
+				 u32 type_id)
+{
+	return env->visit_states[type_id] == RESOLVED;
+}
+
+static int env_stack_push(struct btf_verifier_env *env,
+			  const struct btf_type *t, u32 type_id)
+{
+	struct resolve_vertex *v;
+
+	if (env->top_stack == MAX_RESOLVE_DEPTH)
+		return -E2BIG;
+
+	if (env->visit_states[type_id] != NOT_VISITED)
+		return -EEXIST;
+
+	env->visit_states[type_id] = VISITED;
+
+	v = &env->stack[env->top_stack++];
+	v->t = t;
+	v->type_id = type_id;
+	v->next_member = 0;
+
+	if (env->resolve_mode == RESOLVE_TBD) {
+		if (btf_type_is_ptr(t))
+			env->resolve_mode = RESOLVE_PTR;
+		else if (btf_type_is_struct(t) || btf_type_is_array(t))
+			env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY;
+	}
+
+	return 0;
+}
+
+static void env_stack_set_next_member(struct btf_verifier_env *env,
+				      u16 next_member)
+{
+	env->stack[env->top_stack - 1].next_member = next_member;
+}
+
+static void env_stack_pop_resolved(struct btf_verifier_env *env,
+				   u32 resolved_type_id,
+				   u32 resolved_size)
+{
+	u32 type_id = env->stack[--(env->top_stack)].type_id;
+	struct btf *btf = env->btf;
+
+	btf->resolved_sizes[type_id] = resolved_size;
+	btf->resolved_ids[type_id] = resolved_type_id;
+	env->visit_states[type_id] = RESOLVED;
+}
+
+static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
+{
+	return env->top_stack ? &env->stack[env->top_stack - 1] : NULL;
+}
+
+/* The input param "type_id" must point to a needs_resolve type */
+static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
+						  u32 *type_id)
+{
+	*type_id = btf->resolved_ids[*type_id];
+	return btf_type_by_id(btf, *type_id);
+}
+
+const struct btf_type *btf_type_id_size(const struct btf *btf,
+					u32 *type_id, u32 *ret_size)
+{
+	const struct btf_type *size_type;
+	u32 size_type_id = *type_id;
+	u32 size = 0;
+
+	size_type = btf_type_by_id(btf, size_type_id);
+	if (btf_type_is_void_or_null(size_type))
+		return NULL;
+
+	if (btf_type_has_size(size_type)) {
+		size = size_type->size;
+	} else if (btf_type_is_array(size_type)) {
+		size = btf->resolved_sizes[size_type_id];
+	} else if (btf_type_is_ptr(size_type)) {
+		size = sizeof(void *);
+	} else {
+		if (WARN_ON_ONCE(!btf_type_is_modifier(size_type)))
+			return NULL;
+
+		size = btf->resolved_sizes[size_type_id];
+		size_type_id = btf->resolved_ids[size_type_id];
+		size_type = btf_type_by_id(btf, size_type_id);
+		if (btf_type_is_void(size_type))
+			return NULL;
+	}
+
+	*type_id = size_type_id;
+	if (ret_size)
+		*ret_size = size;
+
+	return size_type;
+}
+
+static int btf_df_check_member(struct btf_verifier_env *env,
+			       const struct btf_type *struct_type,
+			       const struct btf_member *member,
+			       const struct btf_type *member_type)
+{
+	btf_verifier_log_basic(env, struct_type,
+			       "Unsupported check_member");
+	return -EINVAL;
+}
+
+static int btf_df_resolve(struct btf_verifier_env *env,
+			  const struct resolve_vertex *v)
+{
+	btf_verifier_log_basic(env, v->t, "Unsupported resolve");
+	return -EINVAL;
+}
+
+static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t,
+			    u32 type_id, void *data, u8 bits_offsets,
+			    struct seq_file *m)
+{
+	seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
+}
+
+static int btf_int_check_member(struct btf_verifier_env *env,
+				const struct btf_type *struct_type,
+				const struct btf_member *member,
+				const struct btf_type *member_type)
+{
+	u32 int_data = btf_type_int(member_type);
+	u32 struct_bits_off = member->offset;
+	u32 struct_size = struct_type->size;
+	u32 nr_copy_bits;
+	u32 bytes_offset;
+
+	if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"bits_offset exceeds U32_MAX");
+		return -EINVAL;
+	}
+
+	struct_bits_off += BTF_INT_OFFSET(int_data);
+	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+	nr_copy_bits = BTF_INT_BITS(int_data) +
+		BITS_PER_BYTE_MASKED(struct_bits_off);
+
+	if (nr_copy_bits > BITS_PER_U64) {
+		btf_verifier_log_member(env, struct_type, member,
+					"nr_copy_bits exceeds 64");
+		return -EINVAL;
+	}
+
+	if (struct_size < bytes_offset ||
+	    struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static s32 btf_int_check_meta(struct btf_verifier_env *env,
+			      const struct btf_type *t,
+			      u32 meta_left)
+{
+	u32 int_data, nr_bits, meta_needed = sizeof(int_data);
+	u16 encoding;
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	int_data = btf_type_int(t);
+	nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data);
+
+	if (nr_bits > BITS_PER_U64) {
+		btf_verifier_log_type(env, t, "nr_bits exceeds %zu",
+				      BITS_PER_U64);
+		return -EINVAL;
+	}
+
+	if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) {
+		btf_verifier_log_type(env, t, "nr_bits exceeds type_size");
+		return -EINVAL;
+	}
+
+	encoding = BTF_INT_ENCODING(int_data);
+	if (encoding &&
+	    encoding != BTF_INT_SIGNED &&
+	    encoding != BTF_INT_CHAR &&
+	    encoding != BTF_INT_BOOL &&
+	    encoding != BTF_INT_VARARGS) {
+		btf_verifier_log_type(env, t, "Unsupported encoding");
+		return -ENOTSUPP;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static void btf_int_log(struct btf_verifier_env *env,
+			const struct btf_type *t)
+{
+	int int_data = btf_type_int(t);
+
+	btf_verifier_log(env,
+			 "size=%u bits_offset=%u nr_bits=%u encoding=%s",
+			 t->size, BTF_INT_OFFSET(int_data),
+			 BTF_INT_BITS(int_data),
+			 btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
+}
+
+static void btf_int_bits_seq_show(const struct btf *btf,
+				  const struct btf_type *t,
+				  void *data, u8 bits_offset,
+				  struct seq_file *m)
+{
+	u32 int_data = btf_type_int(t);
+	u16 nr_bits = BTF_INT_BITS(int_data);
+	u16 total_bits_offset;
+	u16 nr_copy_bytes;
+	u16 nr_copy_bits;
+	u8 nr_upper_bits;
+	union {
+		u64 u64_num;
+		u8  u8_nums[8];
+	} print_num;
+
+	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
+	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+	nr_copy_bits = nr_bits + bits_offset;
+	nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
+
+	print_num.u64_num = 0;
+	memcpy(&print_num.u64_num, data, nr_copy_bytes);
+
+	/* Ditch the higher order bits */
+	nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
+	if (nr_upper_bits) {
+		/* We need to mask out some bits of the upper byte. */
+		u8 mask = (1 << nr_upper_bits) - 1;
+
+		print_num.u8_nums[nr_copy_bytes - 1] &= mask;
+	}
+
+	print_num.u64_num >>= bits_offset;
+
+	seq_printf(m, "0x%llx", print_num.u64_num);
+}
+
+static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
+			     u32 type_id, void *data, u8 bits_offset,
+			     struct seq_file *m)
+{
+	u32 int_data = btf_type_int(t);
+	u8 encoding = BTF_INT_ENCODING(int_data);
+	bool sign = encoding & BTF_INT_SIGNED;
+	u32 nr_bits = BTF_INT_BITS(int_data);
+
+	if (bits_offset || BTF_INT_OFFSET(int_data) ||
+	    BITS_PER_BYTE_MASKED(nr_bits)) {
+		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+		return;
+	}
+
+	switch (nr_bits) {
+	case 64:
+		if (sign)
+			seq_printf(m, "%lld", *(s64 *)data);
+		else
+			seq_printf(m, "%llu", *(u64 *)data);
+		break;
+	case 32:
+		if (sign)
+			seq_printf(m, "%d", *(s32 *)data);
+		else
+			seq_printf(m, "%u", *(u32 *)data);
+		break;
+	case 16:
+		if (sign)
+			seq_printf(m, "%d", *(s16 *)data);
+		else
+			seq_printf(m, "%u", *(u16 *)data);
+		break;
+	case 8:
+		if (sign)
+			seq_printf(m, "%d", *(s8 *)data);
+		else
+			seq_printf(m, "%u", *(u8 *)data);
+		break;
+	default:
+		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+	}
+}
+
+static const struct btf_kind_operations int_ops = {
+	.check_meta = btf_int_check_meta,
+	.resolve = btf_df_resolve,
+	.check_member = btf_int_check_member,
+	.log_details = btf_int_log,
+	.seq_show = btf_int_seq_show,
+};
+
+static int btf_modifier_check_member(struct btf_verifier_env *env,
+				     const struct btf_type *struct_type,
+				     const struct btf_member *member,
+				     const struct btf_type *member_type)
+{
+	const struct btf_type *resolved_type;
+	u32 resolved_type_id = member->type;
+	struct btf_member resolved_member;
+	struct btf *btf = env->btf;
+
+	resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL);
+	if (!resolved_type) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member");
+		return -EINVAL;
+	}
+
+	resolved_member = *member;
+	resolved_member.type = resolved_type_id;
+
+	return btf_type_ops(resolved_type)->check_member(env, struct_type,
+							 &resolved_member,
+							 resolved_type);
+}
+
+static int btf_ptr_check_member(struct btf_verifier_env *env,
+				const struct btf_type *struct_type,
+				const struct btf_member *member,
+				const struct btf_type *member_type)
+{
+	u32 struct_size, struct_bits_off, bytes_offset;
+
+	struct_size = struct_type->size;
+	struct_bits_off = member->offset;
+	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+
+	if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member is not byte aligned");
+		return -EINVAL;
+	}
+
+	if (struct_size - bytes_offset < sizeof(void *)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_ref_type_check_meta(struct btf_verifier_env *env,
+				   const struct btf_type *t,
+				   u32 meta_left)
+{
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	if (BTF_TYPE_PARENT(t->type)) {
+		btf_verifier_log_type(env, t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return 0;
+}
+
+static int btf_modifier_resolve(struct btf_verifier_env *env,
+				const struct resolve_vertex *v)
+{
+	const struct btf_type *t = v->t;
+	const struct btf_type *next_type;
+	u32 next_type_id = t->type;
+	struct btf *btf = env->btf;
+	u32 next_type_size = 0;
+
+	next_type = btf_type_by_id(btf, next_type_id);
+	if (!next_type) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	/* "typedef void new_void", "const void"...etc */
+	if (btf_type_is_void(next_type))
+		goto resolved;
+
+	if (!env_type_is_resolve_sink(env, next_type) &&
+	    !env_type_is_resolved(env, next_type_id))
+		return env_stack_push(env, next_type, next_type_id);
+
+	/* Figure out the resolved next_type_id with size.
+	 * They will be stored in the current modifier's
+	 * resolved_ids and resolved_sizes such that it can
+	 * save us a few type-following when we use it later (e.g. in
+	 * pretty print).
+	 */
+	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
+	    !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+resolved:
+	env_stack_pop_resolved(env, next_type_id, next_type_size);
+
+	return 0;
+}
+
+static int btf_ptr_resolve(struct btf_verifier_env *env,
+			   const struct resolve_vertex *v)
+{
+	const struct btf_type *next_type;
+	const struct btf_type *t = v->t;
+	u32 next_type_id = t->type;
+	struct btf *btf = env->btf;
+	u32 next_type_size = 0;
+
+	next_type = btf_type_by_id(btf, next_type_id);
+	if (!next_type) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	/* "void *" */
+	if (btf_type_is_void(next_type))
+		goto resolved;
+
+	if (!env_type_is_resolve_sink(env, next_type) &&
+	    !env_type_is_resolved(env, next_type_id))
+		return env_stack_push(env, next_type, next_type_id);
+
+	/* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY,
+	 * the modifier may have stopped resolving when it was resolved
+	 * to a ptr (last-resolved-ptr).
+	 *
+	 * We now need to continue from the last-resolved-ptr to
+	 * ensure the last-resolved-ptr will not referring back to
+	 * the currenct ptr (t).
+	 */
+	if (btf_type_is_modifier(next_type)) {
+		const struct btf_type *resolved_type;
+		u32 resolved_type_id;
+
+		resolved_type_id = next_type_id;
+		resolved_type = btf_type_id_resolve(btf, &resolved_type_id);
+
+		if (btf_type_is_ptr(resolved_type) &&
+		    !env_type_is_resolve_sink(env, resolved_type) &&
+		    !env_type_is_resolved(env, resolved_type_id))
+			return env_stack_push(env, resolved_type,
+					      resolved_type_id);
+	}
+
+	if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
+	    !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+resolved:
+	env_stack_pop_resolved(env, next_type_id, 0);
+
+	return 0;
+}
+
+static void btf_modifier_seq_show(const struct btf *btf,
+				  const struct btf_type *t,
+				  u32 type_id, void *data,
+				  u8 bits_offset, struct seq_file *m)
+{
+	t = btf_type_id_resolve(btf, &type_id);
+
+	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+}
+
+static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
+			     u32 type_id, void *data, u8 bits_offset,
+			     struct seq_file *m)
+{
+	/* It is a hashed value */
+	seq_printf(m, "%p", *(void **)data);
+}
+
+static void btf_ref_type_log(struct btf_verifier_env *env,
+			     const struct btf_type *t)
+{
+	btf_verifier_log(env, "type_id=%u", t->type);
+}
+
+static struct btf_kind_operations modifier_ops = {
+	.check_meta = btf_ref_type_check_meta,
+	.resolve = btf_modifier_resolve,
+	.check_member = btf_modifier_check_member,
+	.log_details = btf_ref_type_log,
+	.seq_show = btf_modifier_seq_show,
+};
+
+static struct btf_kind_operations ptr_ops = {
+	.check_meta = btf_ref_type_check_meta,
+	.resolve = btf_ptr_resolve,
+	.check_member = btf_ptr_check_member,
+	.log_details = btf_ref_type_log,
+	.seq_show = btf_ptr_seq_show,
+};
+
+static struct btf_kind_operations fwd_ops = {
+	.check_meta = btf_ref_type_check_meta,
+	.resolve = btf_df_resolve,
+	.check_member = btf_df_check_member,
+	.log_details = btf_ref_type_log,
+	.seq_show = btf_df_seq_show,
+};
+
+static int btf_array_check_member(struct btf_verifier_env *env,
+				  const struct btf_type *struct_type,
+				  const struct btf_member *member,
+				  const struct btf_type *member_type)
+{
+	u32 struct_bits_off = member->offset;
+	u32 struct_size, bytes_offset;
+	u32 array_type_id, array_size;
+	struct btf *btf = env->btf;
+
+	if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member is not byte aligned");
+		return -EINVAL;
+	}
+
+	array_type_id = member->type;
+	btf_type_id_size(btf, &array_type_id, &array_size);
+	struct_size = struct_type->size;
+	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+	if (struct_size - bytes_offset < array_size) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static s32 btf_array_check_meta(struct btf_verifier_env *env,
+				const struct btf_type *t,
+				u32 meta_left)
+{
+	const struct btf_array *array = btf_type_array(t);
+	u32 meta_needed = sizeof(*array);
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	/* We are a little forgiving on array->index_type since
+	 * the kernel is not using it.
+	 */
+	/* Array elem cannot be in type void,
+	 * so !array->type is not allowed.
+	 */
+	if (!array->type || BTF_TYPE_PARENT(array->type)) {
+		btf_verifier_log_type(env, t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static int btf_array_resolve(struct btf_verifier_env *env,
+			     const struct resolve_vertex *v)
+{
+	const struct btf_array *array = btf_type_array(v->t);
+	const struct btf_type *elem_type;
+	u32 elem_type_id = array->type;
+	struct btf *btf = env->btf;
+	u32 elem_size;
+
+	elem_type = btf_type_by_id(btf, elem_type_id);
+	if (btf_type_is_void_or_null(elem_type)) {
+		btf_verifier_log_type(env, v->t,
+				      "Invalid elem");
+		return -EINVAL;
+	}
+
+	if (!env_type_is_resolve_sink(env, elem_type) &&
+	    !env_type_is_resolved(env, elem_type_id))
+		return env_stack_push(env, elem_type, elem_type_id);
+
+	elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+	if (!elem_type) {
+		btf_verifier_log_type(env, v->t, "Invalid elem");
+		return -EINVAL;
+	}
+
+	if (btf_type_is_int(elem_type)) {
+		int int_type_data = btf_type_int(elem_type);
+		u16 nr_bits = BTF_INT_BITS(int_type_data);
+		u16 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+
+		/* Put more restriction on array of int.  The int cannot
+		 * be a bit field and it must be either u8/u16/u32/u64.
+		 */
+		if (BITS_PER_BYTE_MASKED(nr_bits) ||
+		    BTF_INT_OFFSET(int_type_data) ||
+		    (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
+		     nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) {
+			btf_verifier_log_type(env, v->t,
+					      "Invalid array of int");
+			return -EINVAL;
+		}
+	}
+
+	if (array->nelems && elem_size > U32_MAX / array->nelems) {
+		btf_verifier_log_type(env, v->t,
+				      "Array size overflows U32_MAX");
+		return -EINVAL;
+	}
+
+	env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems);
+
+	return 0;
+}
+
+static void btf_array_log(struct btf_verifier_env *env,
+			  const struct btf_type *t)
+{
+	const struct btf_array *array = btf_type_array(t);
+
+	btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u",
+			 array->type, array->index_type, array->nelems);
+}
+
+static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t,
+			       u32 type_id, void *data, u8 bits_offset,
+			       struct seq_file *m)
+{
+	const struct btf_array *array = btf_type_array(t);
+	const struct btf_kind_operations *elem_ops;
+	const struct btf_type *elem_type;
+	u32 i, elem_size, elem_type_id;
+
+	elem_type_id = array->type;
+	elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+	elem_ops = btf_type_ops(elem_type);
+	seq_puts(m, "[");
+	for (i = 0; i < array->nelems; i++) {
+		if (i)
+			seq_puts(m, ",");
+
+		elem_ops->seq_show(btf, elem_type, elem_type_id, data,
+				   bits_offset, m);
+		data += elem_size;
+	}
+	seq_puts(m, "]");
+}
+
+static struct btf_kind_operations array_ops = {
+	.check_meta = btf_array_check_meta,
+	.resolve = btf_array_resolve,
+	.check_member = btf_array_check_member,
+	.log_details = btf_array_log,
+	.seq_show = btf_array_seq_show,
+};
+
+static int btf_struct_check_member(struct btf_verifier_env *env,
+				   const struct btf_type *struct_type,
+				   const struct btf_member *member,
+				   const struct btf_type *member_type)
+{
+	u32 struct_bits_off = member->offset;
+	u32 struct_size, bytes_offset;
+
+	if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member is not byte aligned");
+		return -EINVAL;
+	}
+
+	struct_size = struct_type->size;
+	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+	if (struct_size - bytes_offset < member_type->size) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static s32 btf_struct_check_meta(struct btf_verifier_env *env,
+				 const struct btf_type *t,
+				 u32 meta_left)
+{
+	bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
+	const struct btf_member *member;
+	struct btf *btf = env->btf;
+	u32 struct_size = t->size;
+	u32 meta_needed;
+	u16 i;
+
+	meta_needed = btf_type_vlen(t) * sizeof(*member);
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	for_each_member(i, t, member) {
+		if (!btf_name_offset_valid(btf, member->name_off)) {
+			btf_verifier_log_member(env, t, member,
+						"Invalid member name_offset:%u",
+						member->name_off);
+			return -EINVAL;
+		}
+
+		/* A member cannot be in type void */
+		if (!member->type || BTF_TYPE_PARENT(member->type)) {
+			btf_verifier_log_member(env, t, member,
+						"Invalid type_id");
+			return -EINVAL;
+		}
+
+		if (is_union && member->offset) {
+			btf_verifier_log_member(env, t, member,
+						"Invalid member bits_offset");
+			return -EINVAL;
+		}
+
+		if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
+			btf_verifier_log_member(env, t, member,
+						"Memmber bits_offset exceeds its struct size");
+			return -EINVAL;
+		}
+
+		btf_verifier_log_member(env, t, member, NULL);
+	}
+
+	return meta_needed;
+}
+
+static int btf_struct_resolve(struct btf_verifier_env *env,
+			      const struct resolve_vertex *v)
+{
+	const struct btf_member *member;
+	int err;
+	u16 i;
+
+	/* Before continue resolving the next_member,
+	 * ensure the last member is indeed resolved to a
+	 * type with size info.
+	 */
+	if (v->next_member) {
+		const struct btf_type *last_member_type;
+		const struct btf_member *last_member;
+		u16 last_member_type_id;
+
+		last_member = btf_type_member(v->t) + v->next_member - 1;
+		last_member_type_id = last_member->type;
+		if (WARN_ON_ONCE(!env_type_is_resolved(env,
+						       last_member_type_id)))
+			return -EINVAL;
+
+		last_member_type = btf_type_by_id(env->btf,
+						  last_member_type_id);
+		err = btf_type_ops(last_member_type)->check_member(env, v->t,
+							last_member,
+							last_member_type);
+		if (err)
+			return err;
+	}
+
+	for_each_member_from(i, v->next_member, v->t, member) {
+		u32 member_type_id = member->type;
+		const struct btf_type *member_type = btf_type_by_id(env->btf,
+								member_type_id);
+
+		if (btf_type_is_void_or_null(member_type)) {
+			btf_verifier_log_member(env, v->t, member,
+						"Invalid member");
+			return -EINVAL;
+		}
+
+		if (!env_type_is_resolve_sink(env, member_type) &&
+		    !env_type_is_resolved(env, member_type_id)) {
+			env_stack_set_next_member(env, i + 1);
+			return env_stack_push(env, member_type, member_type_id);
+		}
+
+		err = btf_type_ops(member_type)->check_member(env, v->t,
+							      member,
+							      member_type);
+		if (err)
+			return err;
+	}
+
+	env_stack_pop_resolved(env, 0, 0);
+
+	return 0;
+}
+
+static void btf_struct_log(struct btf_verifier_env *env,
+			   const struct btf_type *t)
+{
+	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
+}
+
+static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
+				u32 type_id, void *data, u8 bits_offset,
+				struct seq_file *m)
+{
+	const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ",";
+	const struct btf_member *member;
+	u32 i;
+
+	seq_puts(m, "{");
+	for_each_member(i, t, member) {
+		const struct btf_type *member_type = btf_type_by_id(btf,
+								member->type);
+		u32 member_offset = member->offset;
+		u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
+		u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
+		const struct btf_kind_operations *ops;
+
+		if (i)
+			seq_puts(m, seq);
+
+		ops = btf_type_ops(member_type);
+		ops->seq_show(btf, member_type, member->type,
+			      data + bytes_offset, bits8_offset, m);
+	}
+	seq_puts(m, "}");
+}
+
+static struct btf_kind_operations struct_ops = {
+	.check_meta = btf_struct_check_meta,
+	.resolve = btf_struct_resolve,
+	.check_member = btf_struct_check_member,
+	.log_details = btf_struct_log,
+	.seq_show = btf_struct_seq_show,
+};
+
+static int btf_enum_check_member(struct btf_verifier_env *env,
+				 const struct btf_type *struct_type,
+				 const struct btf_member *member,
+				 const struct btf_type *member_type)
+{
+	u32 struct_bits_off = member->offset;
+	u32 struct_size, bytes_offset;
+
+	if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member is not byte aligned");
+		return -EINVAL;
+	}
+
+	struct_size = struct_type->size;
+	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+	if (struct_size - bytes_offset < sizeof(int)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static s32 btf_enum_check_meta(struct btf_verifier_env *env,
+			       const struct btf_type *t,
+			       u32 meta_left)
+{
+	const struct btf_enum *enums = btf_type_enum(t);
+	struct btf *btf = env->btf;
+	u16 i, nr_enums;
+	u32 meta_needed;
+
+	nr_enums = btf_type_vlen(t);
+	meta_needed = nr_enums * sizeof(*enums);
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	if (t->size != sizeof(int)) {
+		btf_verifier_log_type(env, t, "Expected size:%zu",
+				      sizeof(int));
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	for (i = 0; i < nr_enums; i++) {
+		if (!btf_name_offset_valid(btf, enums[i].name_off)) {
+			btf_verifier_log(env, "\tInvalid name_offset:%u",
+					 enums[i].name_off);
+			return -EINVAL;
+		}
+
+		btf_verifier_log(env, "\t%s val=%d\n",
+				 btf_name_by_offset(btf, enums[i].name_off),
+				 enums[i].val);
+	}
+
+	return meta_needed;
+}
+
+static void btf_enum_log(struct btf_verifier_env *env,
+			 const struct btf_type *t)
+{
+	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
+}
+
+static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
+			      u32 type_id, void *data, u8 bits_offset,
+			      struct seq_file *m)
+{
+	const struct btf_enum *enums = btf_type_enum(t);
+	u32 i, nr_enums = btf_type_vlen(t);
+	int v = *(int *)data;
+
+	for (i = 0; i < nr_enums; i++) {
+		if (v == enums[i].val) {
+			seq_printf(m, "%s",
+				   btf_name_by_offset(btf, enums[i].name_off));
+			return;
+		}
+	}
+
+	seq_printf(m, "%d", v);
+}
+
+static struct btf_kind_operations enum_ops = {
+	.check_meta = btf_enum_check_meta,
+	.resolve = btf_df_resolve,
+	.check_member = btf_enum_check_member,
+	.log_details = btf_enum_log,
+	.seq_show = btf_enum_seq_show,
+};
+
+static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
+	[BTF_KIND_INT] = &int_ops,
+	[BTF_KIND_PTR] = &ptr_ops,
+	[BTF_KIND_ARRAY] = &array_ops,
+	[BTF_KIND_STRUCT] = &struct_ops,
+	[BTF_KIND_UNION] = &struct_ops,
+	[BTF_KIND_ENUM] = &enum_ops,
+	[BTF_KIND_FWD] = &fwd_ops,
+	[BTF_KIND_TYPEDEF] = &modifier_ops,
+	[BTF_KIND_VOLATILE] = &modifier_ops,
+	[BTF_KIND_CONST] = &modifier_ops,
+	[BTF_KIND_RESTRICT] = &modifier_ops,
+};
+
+static s32 btf_check_meta(struct btf_verifier_env *env,
+			  const struct btf_type *t,
+			  u32 meta_left)
+{
+	u32 saved_meta_left = meta_left;
+	s32 var_meta_size;
+
+	if (meta_left < sizeof(*t)) {
+		btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu",
+				 env->log_type_id, meta_left, sizeof(*t));
+		return -EINVAL;
+	}
+	meta_left -= sizeof(*t);
+
+	if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX ||
+	    BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) {
+		btf_verifier_log(env, "[%u] Invalid kind:%u",
+				 env->log_type_id, BTF_INFO_KIND(t->info));
+		return -EINVAL;
+	}
+
+	if (!btf_name_offset_valid(env->btf, t->name_off)) {
+		btf_verifier_log(env, "[%u] Invalid name_offset:%u",
+				 env->log_type_id, t->name_off);
+		return -EINVAL;
+	}
+
+	var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left);
+	if (var_meta_size < 0)
+		return var_meta_size;
+
+	meta_left -= var_meta_size;
+
+	return saved_meta_left - meta_left;
+}
+
+static int btf_check_all_metas(struct btf_verifier_env *env)
+{
+	struct btf *btf = env->btf;
+	struct btf_header *hdr;
+	void *cur, *end;
+
+	hdr = btf->hdr;
+	cur = btf->nohdr_data + hdr->type_off;
+	end = btf->nohdr_data + hdr->str_off;
+
+	env->log_type_id = 1;
+	while (cur < end) {
+		struct btf_type *t = cur;
+		s32 meta_size;
+
+		meta_size = btf_check_meta(env, t, end - cur);
+		if (meta_size < 0)
+			return meta_size;
+
+		btf_add_type(env, t);
+		cur += meta_size;
+		env->log_type_id++;
+	}
+
+	return 0;
+}
+
+static int btf_resolve(struct btf_verifier_env *env,
+		       const struct btf_type *t, u32 type_id)
+{
+	const struct resolve_vertex *v;
+	int err = 0;
+
+	env->resolve_mode = RESOLVE_TBD;
+	env_stack_push(env, t, type_id);
+	while (!err && (v = env_stack_peak(env))) {
+		env->log_type_id = v->type_id;
+		err = btf_type_ops(v->t)->resolve(env, v);
+	}
+
+	env->log_type_id = type_id;
+	if (err == -E2BIG)
+		btf_verifier_log_type(env, t,
+				      "Exceeded max resolving depth:%u",
+				      MAX_RESOLVE_DEPTH);
+	else if (err == -EEXIST)
+		btf_verifier_log_type(env, t, "Loop detected");
+
+	return err;
+}
+
+static bool btf_resolve_valid(struct btf_verifier_env *env,
+			      const struct btf_type *t,
+			      u32 type_id)
+{
+	struct btf *btf = env->btf;
+
+	if (!env_type_is_resolved(env, type_id))
+		return false;
+
+	if (btf_type_is_struct(t))
+		return !btf->resolved_ids[type_id] &&
+			!btf->resolved_sizes[type_id];
+
+	if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) {
+		t = btf_type_id_resolve(btf, &type_id);
+		return t && !btf_type_is_modifier(t);
+	}
+
+	if (btf_type_is_array(t)) {
+		const struct btf_array *array = btf_type_array(t);
+		const struct btf_type *elem_type;
+		u32 elem_type_id = array->type;
+		u32 elem_size;
+
+		elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+		return elem_type && !btf_type_is_modifier(elem_type) &&
+			(array->nelems * elem_size ==
+			 btf->resolved_sizes[type_id]);
+	}
+
+	return false;
+}
+
+static int btf_check_all_types(struct btf_verifier_env *env)
+{
+	struct btf *btf = env->btf;
+	u32 type_id;
+	int err;
+
+	err = env_resolve_init(env);
+	if (err)
+		return err;
+
+	env->phase++;
+	for (type_id = 1; type_id <= btf->nr_types; type_id++) {
+		const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+		env->log_type_id = type_id;
+		if (btf_type_needs_resolve(t) &&
+		    !env_type_is_resolved(env, type_id)) {
+			err = btf_resolve(env, t, type_id);
+			if (err)
+				return err;
+		}
+
+		if (btf_type_needs_resolve(t) &&
+		    !btf_resolve_valid(env, t, type_id)) {
+			btf_verifier_log_type(env, t, "Invalid resolve state");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int btf_parse_type_sec(struct btf_verifier_env *env)
+{
+	int err;
+
+	err = btf_check_all_metas(env);
+	if (err)
+		return err;
+
+	return btf_check_all_types(env);
+}
+
+static int btf_parse_str_sec(struct btf_verifier_env *env)
+{
+	const struct btf_header *hdr;
+	struct btf *btf = env->btf;
+	const char *start, *end;
+
+	hdr = btf->hdr;
+	start = btf->nohdr_data + hdr->str_off;
+	end = start + hdr->str_len;
+
+	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
+	    start[0] || end[-1]) {
+		btf_verifier_log(env, "Invalid string section");
+		return -EINVAL;
+	}
+
+	btf->strings = start;
+
+	return 0;
+}
+
+static int btf_parse_hdr(struct btf_verifier_env *env)
+{
+	const struct btf_header *hdr;
+	struct btf *btf = env->btf;
+	u32 meta_left;
+
+	if (btf->data_size < sizeof(*hdr)) {
+		btf_verifier_log(env, "btf_header not found");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_hdr(env);
+
+	hdr = btf->hdr;
+	if (hdr->magic != BTF_MAGIC) {
+		btf_verifier_log(env, "Invalid magic");
+		return -EINVAL;
+	}
+
+	if (hdr->version != BTF_VERSION) {
+		btf_verifier_log(env, "Unsupported version");
+		return -ENOTSUPP;
+	}
+
+	if (hdr->flags) {
+		btf_verifier_log(env, "Unsupported flags");
+		return -ENOTSUPP;
+	}
+
+	meta_left = btf->data_size - sizeof(*hdr);
+	if (!meta_left) {
+		btf_verifier_log(env, "No data");
+		return -EINVAL;
+	}
+
+	if (meta_left < hdr->type_off || hdr->str_off <= hdr->type_off ||
+	    /* Type section must align to 4 bytes */
+	    hdr->type_off & (sizeof(u32) - 1)) {
+		btf_verifier_log(env, "Invalid type_off");
+		return -EINVAL;
+	}
+
+	if (meta_left < hdr->str_off ||
+	    meta_left - hdr->str_off < hdr->str_len) {
+		btf_verifier_log(env, "Invalid str_off or str_len");
+		return -EINVAL;
+	}
+
+	btf->nohdr_data = btf->hdr + 1;
+
+	return 0;
+}
+
+static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
+			     u32 log_level, char __user *log_ubuf, u32 log_size)
+{
+	struct btf_verifier_env *env = NULL;
+	struct bpf_verifier_log *log;
+	struct btf *btf = NULL;
+	u8 *data;
+	int err;
+
+	if (btf_data_size > BTF_MAX_SIZE)
+		return ERR_PTR(-E2BIG);
+
+	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
+	if (!env)
+		return ERR_PTR(-ENOMEM);
+
+	log = &env->log;
+	if (log_level || log_ubuf || log_size) {
+		/* user requested verbose verifier output
+		 * and supplied buffer to store the verification trace
+		 */
+		log->level = log_level;
+		log->ubuf = log_ubuf;
+		log->len_total = log_size;
+
+		/* log attributes have to be sane */
+		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
+		    !log->level || !log->ubuf) {
+			err = -EINVAL;
+			goto errout;
+		}
+	}
+
+	btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
+	if (!btf) {
+		err = -ENOMEM;
+		goto errout;
+	}
+
+	data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN);
+	if (!data) {
+		err = -ENOMEM;
+		goto errout;
+	}
+
+	btf->data = data;
+	btf->data_size = btf_data_size;
+
+	if (copy_from_user(data, btf_data, btf_data_size)) {
+		err = -EFAULT;
+		goto errout;
+	}
+
+	env->btf = btf;
+
+	err = btf_parse_hdr(env);
+	if (err)
+		goto errout;
+
+	err = btf_parse_str_sec(env);
+	if (err)
+		goto errout;
+
+	err = btf_parse_type_sec(env);
+	if (err)
+		goto errout;
+
+	if (!err && log->level && bpf_verifier_log_full(log)) {
+		err = -ENOSPC;
+		goto errout;
+	}
+
+	if (!err) {
+		btf_verifier_env_free(env);
+		refcount_set(&btf->refcnt, 1);
+		return btf;
+	}
+
+errout:
+	btf_verifier_env_free(env);
+	if (btf)
+		btf_free(btf);
+	return ERR_PTR(err);
+}
+
+void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
+		       struct seq_file *m)
+{
+	const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+	btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
+}
+
+static int btf_release(struct inode *inode, struct file *filp)
+{
+	btf_put(filp->private_data);
+	return 0;
+}
+
+const struct file_operations btf_fops = {
+	.release	= btf_release,
+};
+
+static int __btf_new_fd(struct btf *btf)
+{
+	return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC);
+}
+
+int btf_new_fd(const union bpf_attr *attr)
+{
+	struct btf *btf;
+	int ret;
+
+	btf = btf_parse(u64_to_user_ptr(attr->btf),
+			attr->btf_size, attr->btf_log_level,
+			u64_to_user_ptr(attr->btf_log_buf),
+			attr->btf_log_size);
+	if (IS_ERR(btf))
+		return PTR_ERR(btf);
+
+	ret = btf_alloc_id(btf);
+	if (ret) {
+		btf_free(btf);
+		return ret;
+	}
+
+	/*
+	 * The BTF ID is published to the userspace.
+	 * All BTF free must go through call_rcu() from
+	 * now on (i.e. free by calling btf_put()).
+	 */
+
+	ret = __btf_new_fd(btf);
+	if (ret < 0)
+		btf_put(btf);
+
+	return ret;
+}
+
+struct btf *btf_get_by_fd(int fd)
+{
+	struct btf *btf;
+	struct fd f;
+
+	f = fdget(fd);
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	if (f.file->f_op != &btf_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	btf = f.file->private_data;
+	refcount_inc(&btf->refcnt);
+	fdput(f);
+
+	return btf;
+}
+
+int btf_get_info_by_fd(const struct btf *btf,
+		       const union bpf_attr *attr,
+		       union bpf_attr __user *uattr)
+{
+	struct bpf_btf_info __user *uinfo;
+	struct bpf_btf_info info = {};
+	u32 info_copy, btf_copy;
+	void __user *ubtf;
+	u32 uinfo_len;
+
+	uinfo = u64_to_user_ptr(attr->info.info);
+	uinfo_len = attr->info.info_len;
+
+	info_copy = min_t(u32, uinfo_len, sizeof(info));
+	if (copy_from_user(&info, uinfo, info_copy))
+		return -EFAULT;
+
+	info.id = btf->id;
+	ubtf = u64_to_user_ptr(info.btf);
+	btf_copy = min_t(u32, btf->data_size, info.btf_size);
+	if (copy_to_user(ubtf, btf->data, btf_copy))
+		return -EFAULT;
+	info.btf_size = btf->data_size;
+
+	if (copy_to_user(uinfo, &info, info_copy) ||
+	    put_user(info_copy, &uattr->info.info_len))
+		return -EFAULT;
+
+	return 0;
+}
+
+int btf_get_fd_by_id(u32 id)
+{
+	struct btf *btf;
+	int fd;
+
+	rcu_read_lock();
+	btf = idr_find(&btf_idr, id);
+	if (!btf || !refcount_inc_not_zero(&btf->refcnt))
+		btf = ERR_PTR(-ENOENT);
+	rcu_read_unlock();
+
+	if (IS_ERR(btf))
+		return PTR_ERR(btf);
+
+	fd = __btf_new_fd(btf);
+	if (fd < 0)
+		btf_put(btf);
+
+	return fd;
+}
+
+u32 btf_id(const struct btf *btf)
+{
+	return btf->id;
+}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d315b393abdd..b574dddc05b8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -31,6 +31,7 @@
 #include <linux/rbtree_latch.h>
 #include <linux/kallsyms.h>
 #include <linux/rcupdate.h>
+#include <linux/perf_event.h>
 
 #include <asm/unaligned.h>
 
@@ -218,47 +219,84 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	return 0;
 }
 
-static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
+				u32 curr, const bool probe_pass)
 {
+	const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+	s64 imm = insn->imm;
+
+	if (curr < pos && curr + imm + 1 > pos)
+		imm += delta;
+	else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+		imm -= delta;
+	if (imm < imm_min || imm > imm_max)
+		return -ERANGE;
+	if (!probe_pass)
+		insn->imm = imm;
+	return 0;
+}
+
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
+				u32 curr, const bool probe_pass)
+{
+	const s32 off_min = S16_MIN, off_max = S16_MAX;
+	s32 off = insn->off;
+
+	if (curr < pos && curr + off + 1 > pos)
+		off += delta;
+	else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+		off -= delta;
+	if (off < off_min || off > off_max)
+		return -ERANGE;
+	if (!probe_pass)
+		insn->off = off;
+	return 0;
+}
+
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
+			    const bool probe_pass)
+{
+	u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
 	struct bpf_insn *insn = prog->insnsi;
-	u32 i, insn_cnt = prog->len;
-	bool pseudo_call;
-	u8 code;
-	int off;
+	int ret = 0;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
+		u8 code;
+
+		/* In the probing pass we still operate on the original,
+		 * unpatched image in order to check overflows before we
+		 * do any other adjustments. Therefore skip the patchlet.
+		 */
+		if (probe_pass && i == pos) {
+			i += delta + 1;
+			insn++;
+		}
 		code = insn->code;
-		if (BPF_CLASS(code) != BPF_JMP)
-			continue;
-		if (BPF_OP(code) == BPF_EXIT)
+		if (BPF_CLASS(code) != BPF_JMP ||
+		    BPF_OP(code) == BPF_EXIT)
 			continue;
+		/* Adjust offset of jmps if we cross patch boundaries. */
 		if (BPF_OP(code) == BPF_CALL) {
-			if (insn->src_reg == BPF_PSEUDO_CALL)
-				pseudo_call = true;
-			else
+			if (insn->src_reg != BPF_PSEUDO_CALL)
 				continue;
+			ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
+						   probe_pass);
 		} else {
-			pseudo_call = false;
+			ret = bpf_adj_delta_to_off(insn, pos, delta, i,
+						   probe_pass);
 		}
-		off = pseudo_call ? insn->imm : insn->off;
-
-		/* Adjust offset of jmps if we cross boundaries. */
-		if (i < pos && i + off + 1 > pos)
-			off += delta;
-		else if (i > pos + delta && i + off + 1 <= pos + delta)
-			off -= delta;
-
-		if (pseudo_call)
-			insn->imm = off;
-		else
-			insn->off = off;
+		if (ret)
+			break;
 	}
+
+	return ret;
 }
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len)
 {
 	u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
+	const u32 cnt_max = S16_MAX;
 	struct bpf_prog *prog_adj;
 
 	/* Since our patchlet doesn't expand the image, we're done. */
@@ -269,6 +307,15 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 
 	insn_adj_cnt = prog->len + insn_delta;
 
+	/* Reject anything that would potentially let the insn->off
+	 * target overflow when we have excessive program expansions.
+	 * We need to probe here before we do any reallocation where
+	 * we afterwards may not fail anymore.
+	 */
+	if (insn_adj_cnt > cnt_max &&
+	    bpf_adj_branches(prog, off, insn_delta, true))
+		return NULL;
+
 	/* Several new instructions need to be inserted. Make room
 	 * for them. Likely, there's no need for a new allocation as
 	 * last page could have large enough tailroom.
@@ -294,7 +341,11 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 		sizeof(*patch) * insn_rest);
 	memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
 
-	bpf_adj_branches(prog_adj, off, insn_delta);
+	/* We are guaranteed to not fail at this point, otherwise
+	 * the ship has sailed to reverse to the original state. An
+	 * overflow cannot happen at this point.
+	 */
+	BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
 
 	return prog_adj;
 }
@@ -633,23 +684,6 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 		*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
 		break;
 
-	case BPF_LD | BPF_ABS | BPF_W:
-	case BPF_LD | BPF_ABS | BPF_H:
-	case BPF_LD | BPF_ABS | BPF_B:
-		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
-		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
-		*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
-		break;
-
-	case BPF_LD | BPF_IND | BPF_W:
-	case BPF_LD | BPF_IND | BPF_H:
-	case BPF_LD | BPF_IND | BPF_B:
-		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
-		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
-		*to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg);
-		*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
-		break;
-
 	case BPF_LD | BPF_IMM | BPF_DW:
 		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
 		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
@@ -890,14 +924,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_3(LDX, MEM, W),			\
 	INSN_3(LDX, MEM, DW),			\
 	/*   Immediate based. */		\
-	INSN_3(LD, IMM, DW),			\
-	/*   Misc (old cBPF carry-over). */	\
-	INSN_3(LD, ABS, B),			\
-	INSN_3(LD, ABS, H),			\
-	INSN_3(LD, ABS, W),			\
-	INSN_3(LD, IND, B),			\
-	INSN_3(LD, IND, H),			\
-	INSN_3(LD, IND, W)
+	INSN_3(LD, IMM, DW)
 
 bool bpf_opcode_in_insntable(u8 code)
 {
@@ -907,6 +934,13 @@ bool bpf_opcode_in_insntable(u8 code)
 		[0 ... 255] = false,
 		/* Now overwrite non-defaults ... */
 		BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
+		/* UAPI exposed, but rewritten opcodes. cBPF carry-over. */
+		[BPF_LD | BPF_ABS | BPF_B] = true,
+		[BPF_LD | BPF_ABS | BPF_H] = true,
+		[BPF_LD | BPF_ABS | BPF_W] = true,
+		[BPF_LD | BPF_IND | BPF_B] = true,
+		[BPF_LD | BPF_IND | BPF_H] = true,
+		[BPF_LD | BPF_IND | BPF_W] = true,
 	};
 #undef BPF_INSN_3_TBL
 #undef BPF_INSN_2_TBL
@@ -937,8 +971,6 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 #undef BPF_INSN_3_LBL
 #undef BPF_INSN_2_LBL
 	u32 tail_call_cnt = 0;
-	void *ptr;
-	int off;
 
 #define CONT	 ({ insn++; goto select_insn; })
 #define CONT_JMP ({ insn++; goto select_insn; })
@@ -1265,67 +1297,6 @@ out:
 		atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
 			     (DST + insn->off));
 		CONT;
-	LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
-		off = IMM;
-load_word:
-		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
-		 * appearing in the programs where ctx == skb
-		 * (see may_access_skb() in the verifier). All programs
-		 * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6,
-		 * bpf_convert_filter() saves it in BPF_R6, internal BPF
-		 * verifier will check that BPF_R6 == ctx.
-		 *
-		 * BPF_ABS and BPF_IND are wrappers of function calls,
-		 * so they scratch BPF_R1-BPF_R5 registers, preserve
-		 * BPF_R6-BPF_R9, and store return value into BPF_R0.
-		 *
-		 * Implicit input:
-		 *   ctx == skb == BPF_R6 == CTX
-		 *
-		 * Explicit input:
-		 *   SRC == any register
-		 *   IMM == 32-bit immediate
-		 *
-		 * Output:
-		 *   BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
-		 */
-
-		ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
-		if (likely(ptr != NULL)) {
-			BPF_R0 = get_unaligned_be32(ptr);
-			CONT;
-		}
-
-		return 0;
-	LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
-		off = IMM;
-load_half:
-		ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
-		if (likely(ptr != NULL)) {
-			BPF_R0 = get_unaligned_be16(ptr);
-			CONT;
-		}
-
-		return 0;
-	LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
-		off = IMM;
-load_byte:
-		ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
-		if (likely(ptr != NULL)) {
-			BPF_R0 = *(u8 *)ptr;
-			CONT;
-		}
-
-		return 0;
-	LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
-		off = IMM + SRC;
-		goto load_word;
-	LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
-		off = IMM + SRC;
-		goto load_half;
-	LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
-		off = IMM + SRC;
-		goto load_byte;
 
 	default_label:
 		/* If we ever reach this, we have a bug somewhere. Die hard here
@@ -1572,13 +1543,32 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
 	return cnt;
 }
 
+static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+				     u32 *prog_ids,
+				     u32 request_cnt)
+{
+	int i = 0;
+
+	for (; *prog; prog++) {
+		if (*prog == &dummy_bpf_prog.prog)
+			continue;
+		prog_ids[i] = (*prog)->aux->id;
+		if (++i == request_cnt) {
+			prog++;
+			break;
+		}
+	}
+
+	return !!(*prog);
+}
+
 int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 				__u32 __user *prog_ids, u32 cnt)
 {
 	struct bpf_prog **prog;
 	unsigned long err = 0;
-	u32 i = 0, *ids;
 	bool nospc;
+	u32 *ids;
 
 	/* users of this function are doing:
 	 * cnt = bpf_prog_array_length();
@@ -1595,16 +1585,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 		return -ENOMEM;
 	rcu_read_lock();
 	prog = rcu_dereference(progs)->progs;
-	for (; *prog; prog++) {
-		if (*prog == &dummy_bpf_prog.prog)
-			continue;
-		ids[i] = (*prog)->aux->id;
-		if (++i == cnt) {
-			prog++;
-			break;
-		}
-	}
-	nospc = !!(*prog);
+	nospc = bpf_prog_array_copy_core(prog, ids, cnt);
 	rcu_read_unlock();
 	err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
 	kfree(ids);
@@ -1683,22 +1664,25 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 }
 
 int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
-			     __u32 __user *prog_ids, u32 request_cnt,
-			     __u32 __user *prog_cnt)
+			     u32 *prog_ids, u32 request_cnt,
+			     u32 *prog_cnt)
 {
+	struct bpf_prog **prog;
 	u32 cnt = 0;
 
 	if (array)
 		cnt = bpf_prog_array_length(array);
 
-	if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
-		return -EFAULT;
+	*prog_cnt = cnt;
 
 	/* return early if user requested only program count or nothing to copy */
 	if (!request_cnt || !cnt)
 		return 0;
 
-	return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+	/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
+	prog = rcu_dereference_check(array, 1)->progs;
+	return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+								     : 0;
 }
 
 static void bpf_prog_free_deferred(struct work_struct *work)
@@ -1709,6 +1693,10 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	aux = container_of(work, struct bpf_prog_aux, work);
 	if (bpf_prog_is_dev_bound(aux))
 		bpf_prog_offload_destroy(aux->prog);
+#ifdef CONFIG_PERF_EVENTS
+	if (aux->prog->has_callchain_buf)
+		put_callchain_buffers();
+#endif
 	for (i = 0; i < aux->func_cnt; i++)
 		bpf_jit_free(aux->func[i]);
 	if (aux->func_cnt) {
@@ -1769,6 +1757,7 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
 const struct bpf_func_proto bpf_get_current_comm_proto __weak;
 const struct bpf_func_proto bpf_sock_map_update_proto __weak;
+const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
@@ -1781,6 +1770,7 @@ bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 {
 	return -ENOTSUPP;
 }
+EXPORT_SYMBOL_GPL(bpf_event_output);
 
 /* Always built-in helper functions. */
 const struct bpf_func_proto bpf_tail_call_proto = {
@@ -1827,9 +1817,3 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
 #include <linux/bpf_trace.h>
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
-
-/* These are only used within the BPF_SYSCALL code */
-#ifdef CONFIG_BPF_SYSCALL
-EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu);
-#endif
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index bf6da59ae0d0..ed13645bd80c 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -150,8 +150,154 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	return 0;
 }
 
+struct map_iter {
+	void *key;
+	bool done;
+};
+
+static struct map_iter *map_iter(struct seq_file *m)
+{
+	return m->private;
+}
+
+static struct bpf_map *seq_file_to_map(struct seq_file *m)
+{
+	return file_inode(m->file)->i_private;
+}
+
+static void map_iter_free(struct map_iter *iter)
+{
+	if (iter) {
+		kfree(iter->key);
+		kfree(iter);
+	}
+}
+
+static struct map_iter *map_iter_alloc(struct bpf_map *map)
+{
+	struct map_iter *iter;
+
+	iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN);
+	if (!iter)
+		goto error;
+
+	iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN);
+	if (!iter->key)
+		goto error;
+
+	return iter;
+
+error:
+	map_iter_free(iter);
+	return NULL;
+}
+
+static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct bpf_map *map = seq_file_to_map(m);
+	void *key = map_iter(m)->key;
+
+	if (map_iter(m)->done)
+		return NULL;
+
+	if (unlikely(v == SEQ_START_TOKEN))
+		goto done;
+
+	if (map->ops->map_get_next_key(map, key, key)) {
+		map_iter(m)->done = true;
+		return NULL;
+	}
+
+done:
+	++(*pos);
+	return key;
+}
+
+static void *map_seq_start(struct seq_file *m, loff_t *pos)
+{
+	if (map_iter(m)->done)
+		return NULL;
+
+	return *pos ? map_iter(m)->key : SEQ_START_TOKEN;
+}
+
+static void map_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static int map_seq_show(struct seq_file *m, void *v)
+{
+	struct bpf_map *map = seq_file_to_map(m);
+	void *key = map_iter(m)->key;
+
+	if (unlikely(v == SEQ_START_TOKEN)) {
+		seq_puts(m, "# WARNING!! The output is for debug purpose only\n");
+		seq_puts(m, "# WARNING!! The output format will change\n");
+	} else {
+		map->ops->map_seq_show_elem(map, key, m);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations bpffs_map_seq_ops = {
+	.start	= map_seq_start,
+	.next	= map_seq_next,
+	.show	= map_seq_show,
+	.stop	= map_seq_stop,
+};
+
+static int bpffs_map_open(struct inode *inode, struct file *file)
+{
+	struct bpf_map *map = inode->i_private;
+	struct map_iter *iter;
+	struct seq_file *m;
+	int err;
+
+	iter = map_iter_alloc(map);
+	if (!iter)
+		return -ENOMEM;
+
+	err = seq_open(file, &bpffs_map_seq_ops);
+	if (err) {
+		map_iter_free(iter);
+		return err;
+	}
+
+	m = file->private_data;
+	m->private = iter;
+
+	return 0;
+}
+
+static int bpffs_map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+
+	map_iter_free(map_iter(m));
+
+	return seq_release(inode, file);
+}
+
+/* bpffs_map_fops should only implement the basic
+ * read operation for a BPF map.  The purpose is to
+ * provide a simple user intuitive way to do
+ * "cat bpffs/pathto/a-pinned-map".
+ *
+ * Other operations (e.g. write, lookup...) should be realized by
+ * the userspace tools (e.g. bpftool) through the
+ * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update
+ * interface.
+ */
+static const struct file_operations bpffs_map_fops = {
+	.open		= bpffs_map_open,
+	.read		= seq_read,
+	.release	= bpffs_map_release,
+};
+
 static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
-			 const struct inode_operations *iops)
+			 const struct inode_operations *iops,
+			 const struct file_operations *fops)
 {
 	struct inode *dir = dentry->d_parent->d_inode;
 	struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode);
@@ -159,6 +305,7 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
 		return PTR_ERR(inode);
 
 	inode->i_op = iops;
+	inode->i_fop = fops;
 	inode->i_private = raw;
 
 	bpf_dentry_finalize(dentry, inode, dir);
@@ -167,12 +314,15 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
 
 static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg)
 {
-	return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops);
+	return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, NULL);
 }
 
 static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
 {
-	return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops);
+	struct bpf_map *map = arg;
+
+	return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
+			     map->btf ? &bpffs_map_fops : NULL);
 }
 
 static struct dentry *
@@ -279,13 +429,6 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
 	ret = bpf_obj_do_pin(pname, raw, type);
 	if (ret != 0)
 		bpf_any_put(raw, type);
-	if ((trace_bpf_obj_pin_prog_enabled() ||
-	     trace_bpf_obj_pin_map_enabled()) && !ret) {
-		if (type == BPF_TYPE_PROG)
-			trace_bpf_obj_pin_prog(raw, ufd, pname);
-		if (type == BPF_TYPE_MAP)
-			trace_bpf_obj_pin_map(raw, ufd, pname);
-	}
 out:
 	putname(pname);
 	return ret;
@@ -352,15 +495,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
 	else
 		goto out;
 
-	if (ret < 0) {
+	if (ret < 0)
 		bpf_any_put(raw, type);
-	} else if (trace_bpf_obj_get_prog_enabled() ||
-		   trace_bpf_obj_get_map_enabled()) {
-		if (type == BPF_TYPE_PROG)
-			trace_bpf_obj_get_prog(raw, ret, pname);
-		if (type == BPF_TYPE_MAP)
-			trace_bpf_obj_get_map(raw, ret, pname);
-	}
 out:
 	putname(pname);
 	return ret;
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index c9401075b58c..ac747d5cf7c6 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
  *
  * This software is licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -474,8 +474,10 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map)
 	struct bpf_prog_offload *offload;
 	bool ret;
 
-	if (!bpf_prog_is_dev_bound(prog->aux) || !bpf_map_is_dev_bound(map))
+	if (!bpf_prog_is_dev_bound(prog->aux))
 		return false;
+	if (!bpf_map_is_dev_bound(map))
+		return bpf_map_offload_neutral(map);
 
 	down_read(&bpf_devs_lock);
 	offload = prog->aux->offload;
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 8dd9210d7db7..cd832250a478 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -43,18 +43,45 @@
 #include <net/tcp.h>
 #include <linux/ptr_ring.h>
 #include <net/inet_common.h>
+#include <linux/sched/signal.h>
 
 #define SOCK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
-struct bpf_stab {
-	struct bpf_map map;
-	struct sock **sock_map;
+struct bpf_sock_progs {
 	struct bpf_prog *bpf_tx_msg;
 	struct bpf_prog *bpf_parse;
 	struct bpf_prog *bpf_verdict;
 };
 
+struct bpf_stab {
+	struct bpf_map map;
+	struct sock **sock_map;
+	struct bpf_sock_progs progs;
+};
+
+struct bucket {
+	struct hlist_head head;
+	raw_spinlock_t lock;
+};
+
+struct bpf_htab {
+	struct bpf_map map;
+	struct bucket *buckets;
+	atomic_t count;
+	u32 n_buckets;
+	u32 elem_size;
+	struct bpf_sock_progs progs;
+};
+
+struct htab_elem {
+	struct rcu_head rcu;
+	struct hlist_node hash_node;
+	u32 hash;
+	struct sock *sk;
+	char key[0];
+};
+
 enum smap_psock_state {
 	SMAP_TX_RUNNING,
 };
@@ -62,6 +89,8 @@ enum smap_psock_state {
 struct smap_psock_map_entry {
 	struct list_head list;
 	struct sock **entry;
+	struct htab_elem *hash_link;
+	struct bpf_htab *htab;
 };
 
 struct smap_psock {
@@ -190,6 +219,12 @@ out:
 	rcu_read_unlock();
 }
 
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+	atomic_dec(&htab->count);
+	kfree_rcu(l, rcu);
+}
+
 static void bpf_tcp_close(struct sock *sk, long timeout)
 {
 	void (*close_fun)(struct sock *sk, long timeout);
@@ -226,10 +261,16 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 	}
 
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
-		osk = cmpxchg(e->entry, sk, NULL);
-		if (osk == sk) {
-			list_del(&e->list);
-			smap_release_sock(psock, sk);
+		if (e->entry) {
+			osk = cmpxchg(e->entry, sk, NULL);
+			if (osk == sk) {
+				list_del(&e->list);
+				smap_release_sock(psock, sk);
+			}
+		} else {
+			hlist_del_rcu(&e->hash_link->hash_node);
+			smap_release_sock(psock, e->hash_link->sk);
+			free_htab_elem(e->htab, e->hash_link);
 		}
 	}
 	write_unlock_bh(&sk->sk_callback_lock);
@@ -325,6 +366,9 @@ retry:
 			if (ret > 0) {
 				if (apply)
 					apply_bytes -= ret;
+
+				sg->offset += ret;
+				sg->length -= ret;
 				size -= ret;
 				offset += ret;
 				if (uncharge)
@@ -332,8 +376,6 @@ retry:
 				goto retry;
 			}
 
-			sg->length = size;
-			sg->offset = offset;
 			return ret;
 		}
 
@@ -391,7 +433,8 @@ static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 	} while (i != md->sg_end);
 }
 
-static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+static void free_bytes_sg(struct sock *sk, int bytes,
+			  struct sk_msg_buff *md, bool charge)
 {
 	struct scatterlist *sg = md->sg_data;
 	int i = md->sg_start, free;
@@ -401,11 +444,13 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (bytes < free) {
 			sg[i].length -= bytes;
 			sg[i].offset += bytes;
-			sk_mem_uncharge(sk, bytes);
+			if (charge)
+				sk_mem_uncharge(sk, bytes);
 			break;
 		}
 
-		sk_mem_uncharge(sk, sg[i].length);
+		if (charge)
+			sk_mem_uncharge(sk, sg[i].length);
 		put_page(sg_page(&sg[i]));
 		bytes -= sg[i].length;
 		sg[i].length = 0;
@@ -416,6 +461,7 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (i == MAX_SKB_FRAGS)
 			i = 0;
 	}
+	md->sg_start = i;
 }
 
 static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
@@ -455,7 +501,7 @@ static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md)
 static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md)
 {
 	return ((_rc == SK_PASS) ?
-	       (md->map ? __SK_REDIRECT : __SK_PASS) :
+	       (md->sk_redir ? __SK_REDIRECT : __SK_PASS) :
 	       __SK_DROP);
 }
 
@@ -523,8 +569,6 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 	i = md->sg_start;
 
 	do {
-		r->sg_data[i] = md->sg_data[i];
-
 		size = (apply && apply_bytes < md->sg_data[i].length) ?
 			apply_bytes : md->sg_data[i].length;
 
@@ -535,6 +579,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 		}
 
 		sk_mem_charge(sk, size);
+		r->sg_data[i] = md->sg_data[i];
 		r->sg_data[i].length = size;
 		md->sg_data[i].length -= size;
 		md->sg_data[i].offset += size;
@@ -575,10 +620,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 				       struct sk_msg_buff *md,
 				       int flags)
 {
+	bool ingress = !!(md->flags & BPF_F_INGRESS);
 	struct smap_psock *psock;
 	struct scatterlist *sg;
-	int i, err, free = 0;
-	bool ingress = !!(md->flags & BPF_F_INGRESS);
+	int err = 0;
 
 	sg = md->sg_data;
 
@@ -606,16 +651,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 out_rcu:
 	rcu_read_unlock();
 out:
-	i = md->sg_start;
-	while (sg[i].length) {
-		free += sg[i].length;
-		put_page(sg_page(&sg[i]));
-		sg[i].length = 0;
-		i++;
-		if (i == MAX_SKB_FRAGS)
-			i = 0;
-	}
-	return free;
+	free_bytes_sg(NULL, send, md, false);
+	return err;
 }
 
 static inline void bpf_md_init(struct smap_psock *psock)
@@ -700,19 +737,26 @@ more_data:
 		err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
 		lock_sock(sk);
 
+		if (unlikely(err < 0)) {
+			free_start_sg(sk, m);
+			psock->sg_size = 0;
+			if (!cork)
+				*copied -= send;
+		} else {
+			psock->sg_size -= send;
+		}
+
 		if (cork) {
 			free_start_sg(sk, m);
+			psock->sg_size = 0;
 			kfree(m);
 			m = NULL;
+			err = 0;
 		}
-		if (unlikely(err))
-			*copied -= err;
-		else
-			psock->sg_size -= send;
 		break;
 	case __SK_DROP:
 	default:
-		free_bytes_sg(sk, send, m);
+		free_bytes_sg(sk, send, m, true);
 		apply_bytes_dec(psock, send);
 		*copied -= send;
 		psock->sg_size -= send;
@@ -732,6 +776,26 @@ out_err:
 	return err;
 }
 
+static int bpf_wait_data(struct sock *sk,
+			 struct smap_psock *psk, int flags,
+			 long timeo, int *err)
+{
+	int rc;
+
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	rc = sk_wait_event(sk, &timeo,
+			   !list_empty(&psk->ingress) ||
+			   !skb_queue_empty(&sk->sk_receive_queue),
+			   &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	return rc;
+}
+
 static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			   int nonblock, int flags, int *addr_len)
 {
@@ -755,6 +819,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	lock_sock(sk);
+bytes_ready:
 	while (copied != len) {
 		struct scatterlist *sg;
 		struct sk_msg_buff *md;
@@ -809,6 +874,28 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 	}
 
+	if (!copied) {
+		long timeo;
+		int data;
+		int err = 0;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+		if (data) {
+			if (!skb_queue_empty(&sk->sk_receive_queue)) {
+				release_sock(sk);
+				smap_release_sock(psock, sk);
+				copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+				return copied;
+			}
+			goto bytes_ready;
+		}
+
+		if (err)
+			copied = err;
+	}
+
 	release_sock(sk);
 	smap_release_sock(psock, sk);
 	return copied;
@@ -1045,7 +1132,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 	 * when we orphan the skb so that we don't have the possibility
 	 * to reference a stale map.
 	 */
-	TCP_SKB_CB(skb)->bpf.map = NULL;
+	TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
 	skb->sk = psock->sock;
 	bpf_compute_data_pointers(skb);
 	preempt_disable();
@@ -1055,7 +1142,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 
 	/* Moving return codes from UAPI namespace into internal namespace */
 	return rc == SK_PASS ?
-		(TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) :
+		(TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) :
 		__SK_DROP;
 }
 
@@ -1325,7 +1412,6 @@ static int smap_init_sock(struct smap_psock *psock,
 }
 
 static void smap_init_progs(struct smap_psock *psock,
-			    struct bpf_stab *stab,
 			    struct bpf_prog *verdict,
 			    struct bpf_prog *parse)
 {
@@ -1403,14 +1489,13 @@ static void smap_gc_work(struct work_struct *w)
 	kfree(psock);
 }
 
-static struct smap_psock *smap_init_psock(struct sock *sock,
-					  struct bpf_stab *stab)
+static struct smap_psock *smap_init_psock(struct sock *sock, int node)
 {
 	struct smap_psock *psock;
 
 	psock = kzalloc_node(sizeof(struct smap_psock),
 			     GFP_ATOMIC | __GFP_NOWARN,
-			     stab->map.numa_node);
+			     node);
 	if (!psock)
 		return ERR_PTR(-ENOMEM);
 
@@ -1442,9 +1527,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	    attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
-	if (attr->value_size > KMALLOC_MAX_SIZE)
-		return ERR_PTR(-E2BIG);
-
 	err = bpf_tcp_ulp_register();
 	if (err && err != -EEXIST)
 		return ERR_PTR(err);
@@ -1481,12 +1563,14 @@ free_stab:
 	return ERR_PTR(err);
 }
 
-static void smap_list_remove(struct smap_psock *psock, struct sock **entry)
+static void smap_list_remove(struct smap_psock *psock,
+			     struct sock **entry,
+			     struct htab_elem *hash_link)
 {
 	struct smap_psock_map_entry *e, *tmp;
 
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
-		if (e->entry == entry) {
+		if (e->entry == entry || e->hash_link == hash_link) {
 			list_del(&e->list);
 			break;
 		}
@@ -1524,7 +1608,7 @@ static void sock_map_free(struct bpf_map *map)
 		 * to be null and queued for garbage collection.
 		 */
 		if (likely(psock)) {
-			smap_list_remove(psock, &stab->sock_map[i]);
+			smap_list_remove(psock, &stab->sock_map[i], NULL);
 			smap_release_sock(psock, sock);
 		}
 		write_unlock_bh(&sock->sk_callback_lock);
@@ -1583,7 +1667,7 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
 
 	if (psock->bpf_parse)
 		smap_stop_sock(psock, sock);
-	smap_list_remove(psock, &stab->sock_map[k]);
+	smap_list_remove(psock, &stab->sock_map[k], NULL);
 	smap_release_sock(psock, sock);
 out:
 	write_unlock_bh(&sock->sk_callback_lock);
@@ -1618,40 +1702,26 @@ out:
  *  - sock_map must use READ_ONCE and (cmp)xchg operations
  *  - BPF verdict/parse programs must use READ_ONCE and xchg operations
  */
-static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
-				    struct bpf_map *map,
-				    void *key, u64 flags)
+
+static int __sock_map_ctx_update_elem(struct bpf_map *map,
+				      struct bpf_sock_progs *progs,
+				      struct sock *sock,
+				      struct sock **map_link,
+				      void *key)
 {
-	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
-	struct smap_psock_map_entry *e = NULL;
 	struct bpf_prog *verdict, *parse, *tx_msg;
-	struct sock *osock, *sock;
+	struct smap_psock_map_entry *e = NULL;
 	struct smap_psock *psock;
-	u32 i = *(u32 *)key;
 	bool new = false;
 	int err;
 
-	if (unlikely(flags > BPF_EXIST))
-		return -EINVAL;
-
-	if (unlikely(i >= stab->map.max_entries))
-		return -E2BIG;
-
-	sock = READ_ONCE(stab->sock_map[i]);
-	if (flags == BPF_EXIST && !sock)
-		return -ENOENT;
-	else if (flags == BPF_NOEXIST && sock)
-		return -EEXIST;
-
-	sock = skops->sk;
-
 	/* 1. If sock map has BPF programs those will be inherited by the
 	 * sock being added. If the sock is already attached to BPF programs
 	 * this results in an error.
 	 */
-	verdict = READ_ONCE(stab->bpf_verdict);
-	parse = READ_ONCE(stab->bpf_parse);
-	tx_msg = READ_ONCE(stab->bpf_tx_msg);
+	verdict = READ_ONCE(progs->bpf_verdict);
+	parse = READ_ONCE(progs->bpf_parse);
+	tx_msg = READ_ONCE(progs->bpf_tx_msg);
 
 	if (parse && verdict) {
 		/* bpf prog refcnt may be zero if a concurrent attach operation
@@ -1659,11 +1729,11 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		 * we increment the refcnt. If this is the case abort with an
 		 * error.
 		 */
-		verdict = bpf_prog_inc_not_zero(stab->bpf_verdict);
+		verdict = bpf_prog_inc_not_zero(verdict);
 		if (IS_ERR(verdict))
 			return PTR_ERR(verdict);
 
-		parse = bpf_prog_inc_not_zero(stab->bpf_parse);
+		parse = bpf_prog_inc_not_zero(parse);
 		if (IS_ERR(parse)) {
 			bpf_prog_put(verdict);
 			return PTR_ERR(parse);
@@ -1671,12 +1741,12 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	}
 
 	if (tx_msg) {
-		tx_msg = bpf_prog_inc_not_zero(stab->bpf_tx_msg);
+		tx_msg = bpf_prog_inc_not_zero(tx_msg);
 		if (IS_ERR(tx_msg)) {
-			if (verdict)
-				bpf_prog_put(verdict);
-			if (parse)
+			if (parse && verdict) {
 				bpf_prog_put(parse);
+				bpf_prog_put(verdict);
+			}
 			return PTR_ERR(tx_msg);
 		}
 	}
@@ -1704,7 +1774,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 			goto out_progs;
 		}
 	} else {
-		psock = smap_init_psock(sock, stab);
+		psock = smap_init_psock(sock, map->numa_node);
 		if (IS_ERR(psock)) {
 			err = PTR_ERR(psock);
 			goto out_progs;
@@ -1714,12 +1784,13 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		new = true;
 	}
 
-	e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
-	if (!e) {
-		err = -ENOMEM;
-		goto out_progs;
+	if (map_link) {
+		e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+		if (!e) {
+			err = -ENOMEM;
+			goto out_progs;
+		}
 	}
-	e->entry = &stab->sock_map[i];
 
 	/* 3. At this point we have a reference to a valid psock that is
 	 * running. Attach any BPF programs needed.
@@ -1736,7 +1807,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		err = smap_init_sock(psock, sock);
 		if (err)
 			goto out_free;
-		smap_init_progs(psock, stab, verdict, parse);
+		smap_init_progs(psock, verdict, parse);
 		smap_start_sock(psock, sock);
 	}
 
@@ -1745,50 +1816,94 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	 * it with. Because we can only have a single set of programs if
 	 * old_sock has a strp we can stop it.
 	 */
-	list_add_tail(&e->list, &psock->maps);
+	if (map_link) {
+		e->entry = map_link;
+		list_add_tail(&e->list, &psock->maps);
+	}
+	write_unlock_bh(&sock->sk_callback_lock);
+	return err;
+out_free:
+	kfree(e);
+	smap_release_sock(psock, sock);
+out_progs:
+	if (parse && verdict) {
+		bpf_prog_put(parse);
+		bpf_prog_put(verdict);
+	}
+	if (tx_msg)
+		bpf_prog_put(tx_msg);
 	write_unlock_bh(&sock->sk_callback_lock);
+	kfree(e);
+	return err;
+}
+
+static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+				    struct bpf_map *map,
+				    void *key, u64 flags)
+{
+	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+	struct bpf_sock_progs *progs = &stab->progs;
+	struct sock *osock, *sock;
+	u32 i = *(u32 *)key;
+	int err;
+
+	if (unlikely(flags > BPF_EXIST))
+		return -EINVAL;
+
+	if (unlikely(i >= stab->map.max_entries))
+		return -E2BIG;
+
+	sock = READ_ONCE(stab->sock_map[i]);
+	if (flags == BPF_EXIST && !sock)
+		return -ENOENT;
+	else if (flags == BPF_NOEXIST && sock)
+		return -EEXIST;
+
+	sock = skops->sk;
+	err = __sock_map_ctx_update_elem(map, progs, sock, &stab->sock_map[i],
+					 key);
+	if (err)
+		goto out;
 
 	osock = xchg(&stab->sock_map[i], sock);
 	if (osock) {
 		struct smap_psock *opsock = smap_psock_sk(osock);
 
 		write_lock_bh(&osock->sk_callback_lock);
-		smap_list_remove(opsock, &stab->sock_map[i]);
+		smap_list_remove(opsock, &stab->sock_map[i], NULL);
 		smap_release_sock(opsock, osock);
 		write_unlock_bh(&osock->sk_callback_lock);
 	}
-	return 0;
-out_free:
-	smap_release_sock(psock, sock);
-out_progs:
-	if (verdict)
-		bpf_prog_put(verdict);
-	if (parse)
-		bpf_prog_put(parse);
-	if (tx_msg)
-		bpf_prog_put(tx_msg);
-	write_unlock_bh(&sock->sk_callback_lock);
-	kfree(e);
+out:
 	return err;
 }
 
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
 {
-	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+	struct bpf_sock_progs *progs;
 	struct bpf_prog *orig;
 
-	if (unlikely(map->map_type != BPF_MAP_TYPE_SOCKMAP))
+	if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+		struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+		progs = &stab->progs;
+	} else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) {
+		struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+		progs = &htab->progs;
+	} else {
 		return -EINVAL;
+	}
 
 	switch (type) {
 	case BPF_SK_MSG_VERDICT:
-		orig = xchg(&stab->bpf_tx_msg, prog);
+		orig = xchg(&progs->bpf_tx_msg, prog);
 		break;
 	case BPF_SK_SKB_STREAM_PARSER:
-		orig = xchg(&stab->bpf_parse, prog);
+		orig = xchg(&progs->bpf_parse, prog);
 		break;
 	case BPF_SK_SKB_STREAM_VERDICT:
-		orig = xchg(&stab->bpf_verdict, prog);
+		orig = xchg(&progs->bpf_verdict, prog);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -1834,23 +1949,423 @@ static int sock_map_update_elem(struct bpf_map *map,
 	return err;
 }
 
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+static void sock_map_release(struct bpf_map *map)
 {
-	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+	struct bpf_sock_progs *progs;
 	struct bpf_prog *orig;
 
-	orig = xchg(&stab->bpf_parse, NULL);
+	if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+		struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+		progs = &stab->progs;
+	} else {
+		struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+		progs = &htab->progs;
+	}
+
+	orig = xchg(&progs->bpf_parse, NULL);
 	if (orig)
 		bpf_prog_put(orig);
-	orig = xchg(&stab->bpf_verdict, NULL);
+	orig = xchg(&progs->bpf_verdict, NULL);
 	if (orig)
 		bpf_prog_put(orig);
 
-	orig = xchg(&stab->bpf_tx_msg, NULL);
+	orig = xchg(&progs->bpf_tx_msg, NULL);
 	if (orig)
 		bpf_prog_put(orig);
 }
 
+static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
+{
+	struct bpf_htab *htab;
+	int i, err;
+	u64 cost;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->value_size != 4 ||
+	    attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
+		return ERR_PTR(-EINVAL);
+
+	if (attr->key_size > MAX_BPF_STACK)
+		/* eBPF programs initialize keys on stack, so they cannot be
+		 * larger than max stack size
+		 */
+		return ERR_PTR(-E2BIG);
+
+	err = bpf_tcp_ulp_register();
+	if (err && err != -EEXIST)
+		return ERR_PTR(err);
+
+	htab = kzalloc(sizeof(*htab), GFP_USER);
+	if (!htab)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&htab->map, attr);
+
+	htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
+	htab->elem_size = sizeof(struct htab_elem) +
+			  round_up(htab->map.key_size, 8);
+	err = -EINVAL;
+	if (htab->n_buckets == 0 ||
+	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
+		goto free_htab;
+
+	cost = (u64) htab->n_buckets * sizeof(struct bucket) +
+	       (u64) htab->elem_size * htab->map.max_entries;
+
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_htab;
+
+	htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+	err = bpf_map_precharge_memlock(htab->map.pages);
+	if (err)
+		goto free_htab;
+
+	err = -ENOMEM;
+	htab->buckets = bpf_map_area_alloc(
+				htab->n_buckets * sizeof(struct bucket),
+				htab->map.numa_node);
+	if (!htab->buckets)
+		goto free_htab;
+
+	for (i = 0; i < htab->n_buckets; i++) {
+		INIT_HLIST_HEAD(&htab->buckets[i].head);
+		raw_spin_lock_init(&htab->buckets[i].lock);
+	}
+
+	return &htab->map;
+free_htab:
+	kfree(htab);
+	return ERR_PTR(err);
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &__select_bucket(htab, hash)->head;
+}
+
+static void sock_hash_free(struct bpf_map *map)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	int i;
+
+	synchronize_rcu();
+
+	/* At this point no update, lookup or delete operations can happen.
+	 * However, be aware we can still get a socket state event updates,
+	 * and data ready callabacks that reference the psock from sk_user_data
+	 * Also psock worker threads are still in-flight. So smap_release_sock
+	 * will only free the psock after cancel_sync on the worker threads
+	 * and a grace period expire to ensure psock is really safe to remove.
+	 */
+	rcu_read_lock();
+	for (i = 0; i < htab->n_buckets; i++) {
+		struct hlist_head *head = select_bucket(htab, i);
+		struct hlist_node *n;
+		struct htab_elem *l;
+
+		hlist_for_each_entry_safe(l, n, head, hash_node) {
+			struct sock *sock = l->sk;
+			struct smap_psock *psock;
+
+			hlist_del_rcu(&l->hash_node);
+			write_lock_bh(&sock->sk_callback_lock);
+			psock = smap_psock_sk(sock);
+			/* This check handles a racing sock event that can get
+			 * the sk_callback_lock before this case but after xchg
+			 * causing the refcnt to hit zero and sock user data
+			 * (psock) to be null and queued for garbage collection.
+			 */
+			if (likely(psock)) {
+				smap_list_remove(psock, NULL, l);
+				smap_release_sock(psock, sock);
+			}
+			write_unlock_bh(&sock->sk_callback_lock);
+			kfree(l);
+		}
+	}
+	rcu_read_unlock();
+	bpf_map_area_free(htab->buckets);
+	kfree(htab);
+}
+
+static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
+					      void *key, u32 key_size, u32 hash,
+					      struct sock *sk,
+					      struct htab_elem *old_elem)
+{
+	struct htab_elem *l_new;
+
+	if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
+		if (!old_elem) {
+			atomic_dec(&htab->count);
+			return ERR_PTR(-E2BIG);
+		}
+	}
+	l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
+			     htab->map.numa_node);
+	if (!l_new)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(l_new->key, key, key_size);
+	l_new->sk = sk;
+	l_new->hash = hash;
+	return l_new;
+}
+
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+					 u32 hash, void *key, u32 key_size)
+{
+	struct htab_elem *l;
+
+	hlist_for_each_entry_rcu(l, head, hash_node) {
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+	}
+
+	return NULL;
+}
+
+static inline u32 htab_map_hash(const void *key, u32 key_len)
+{
+	return jhash(key, key_len, 0);
+}
+
+static int sock_hash_get_next_key(struct bpf_map *map,
+				  void *key, void *next_key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct htab_elem *l, *next_l;
+	struct hlist_head *h;
+	u32 hash, key_size;
+	int i = 0;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	key_size = map->key_size;
+	if (!key)
+		goto find_first_elem;
+	hash = htab_map_hash(key, key_size);
+	h = select_bucket(htab, hash);
+
+	l = lookup_elem_raw(h, hash, key, key_size);
+	if (!l)
+		goto find_first_elem;
+	next_l = hlist_entry_safe(
+		     rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+		     struct htab_elem, hash_node);
+	if (next_l) {
+		memcpy(next_key, next_l->key, key_size);
+		return 0;
+	}
+
+	/* no more elements in this hash list, go to the next bucket */
+	i = hash & (htab->n_buckets - 1);
+	i++;
+
+find_first_elem:
+	/* iterate over buckets */
+	for (; i < htab->n_buckets; i++) {
+		h = select_bucket(htab, i);
+
+		/* pick first element in the bucket */
+		next_l = hlist_entry_safe(
+				rcu_dereference_raw(hlist_first_rcu(h)),
+				struct htab_elem, hash_node);
+		if (next_l) {
+			/* if it's not empty, just return it */
+			memcpy(next_key, next_l->key, key_size);
+			return 0;
+		}
+	}
+
+	/* iterated over all buckets and all elements */
+	return -ENOENT;
+}
+
+static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+				     struct bpf_map *map,
+				     void *key, u64 map_flags)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct bpf_sock_progs *progs = &htab->progs;
+	struct htab_elem *l_new = NULL, *l_old;
+	struct smap_psock_map_entry *e = NULL;
+	struct hlist_head *head;
+	struct smap_psock *psock;
+	u32 key_size, hash;
+	struct sock *sock;
+	struct bucket *b;
+	int err;
+
+	sock = skops->sk;
+
+	if (sock->sk_type != SOCK_STREAM ||
+	    sock->sk_protocol != IPPROTO_TCP)
+		return -EOPNOTSUPP;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+
+	e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+	if (!e)
+		return -ENOMEM;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	key_size = map->key_size;
+	hash = htab_map_hash(key, key_size);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	err = __sock_map_ctx_update_elem(map, progs, sock, NULL, key);
+	if (err)
+		goto err;
+
+	/* bpf_map_update_elem() can be called in_irq() */
+	raw_spin_lock_bh(&b->lock);
+	l_old = lookup_elem_raw(head, hash, key, key_size);
+	if (l_old && map_flags == BPF_NOEXIST) {
+		err = -EEXIST;
+		goto bucket_err;
+	}
+	if (!l_old && map_flags == BPF_EXIST) {
+		err = -ENOENT;
+		goto bucket_err;
+	}
+
+	l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old);
+	if (IS_ERR(l_new)) {
+		err = PTR_ERR(l_new);
+		goto bucket_err;
+	}
+
+	psock = smap_psock_sk(sock);
+	if (unlikely(!psock)) {
+		err = -EINVAL;
+		goto bucket_err;
+	}
+
+	e->hash_link = l_new;
+	e->htab = container_of(map, struct bpf_htab, map);
+	list_add_tail(&e->list, &psock->maps);
+
+	/* add new element to the head of the list, so that
+	 * concurrent search will find it before old elem
+	 */
+	hlist_add_head_rcu(&l_new->hash_node, head);
+	if (l_old) {
+		psock = smap_psock_sk(l_old->sk);
+
+		hlist_del_rcu(&l_old->hash_node);
+		smap_list_remove(psock, NULL, l_old);
+		smap_release_sock(psock, l_old->sk);
+		free_htab_elem(htab, l_old);
+	}
+	raw_spin_unlock_bh(&b->lock);
+	return 0;
+bucket_err:
+	raw_spin_unlock_bh(&b->lock);
+err:
+	kfree(e);
+	psock = smap_psock_sk(sock);
+	if (psock)
+		smap_release_sock(psock, sock);
+	return err;
+}
+
+static int sock_hash_update_elem(struct bpf_map *map,
+				void *key, void *value, u64 flags)
+{
+	struct bpf_sock_ops_kern skops;
+	u32 fd = *(u32 *)value;
+	struct socket *socket;
+	int err;
+
+	socket = sockfd_lookup(fd, &err);
+	if (!socket)
+		return err;
+
+	skops.sk = socket->sk;
+	if (!skops.sk) {
+		fput(socket->file);
+		return -EINVAL;
+	}
+
+	err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+	fput(socket->file);
+	return err;
+}
+
+static int sock_hash_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_head *head;
+	struct bucket *b;
+	struct htab_elem *l;
+	u32 hash, key_size;
+	int ret = -ENOENT;
+
+	key_size = map->key_size;
+	hash = htab_map_hash(key, key_size);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	raw_spin_lock_bh(&b->lock);
+	l = lookup_elem_raw(head, hash, key, key_size);
+	if (l) {
+		struct sock *sock = l->sk;
+		struct smap_psock *psock;
+
+		hlist_del_rcu(&l->hash_node);
+		write_lock_bh(&sock->sk_callback_lock);
+		psock = smap_psock_sk(sock);
+		/* This check handles a racing sock event that can get the
+		 * sk_callback_lock before this case but after xchg happens
+		 * causing the refcnt to hit zero and sock user data (psock)
+		 * to be null and queued for garbage collection.
+		 */
+		if (likely(psock)) {
+			smap_list_remove(psock, NULL, l);
+			smap_release_sock(psock, sock);
+		}
+		write_unlock_bh(&sock->sk_callback_lock);
+		free_htab_elem(htab, l);
+		ret = 0;
+	}
+	raw_spin_unlock_bh(&b->lock);
+	return ret;
+}
+
+struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_head *head;
+	struct htab_elem *l;
+	u32 key_size, hash;
+	struct bucket *b;
+	struct sock *sk;
+
+	key_size = map->key_size;
+	hash = htab_map_hash(key, key_size);
+	b = __select_bucket(htab, hash);
+	head = &b->head;
+
+	raw_spin_lock_bh(&b->lock);
+	l = lookup_elem_raw(head, hash, key, key_size);
+	sk = l ? l->sk : NULL;
+	raw_spin_unlock_bh(&b->lock);
+	return sk;
+}
+
 const struct bpf_map_ops sock_map_ops = {
 	.map_alloc = sock_map_alloc,
 	.map_free = sock_map_free,
@@ -1858,7 +2373,16 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_get_next_key = sock_map_get_next_key,
 	.map_update_elem = sock_map_update_elem,
 	.map_delete_elem = sock_map_delete_elem,
-	.map_release = sock_map_release,
+	.map_release_uref = sock_map_release,
+};
+
+const struct bpf_map_ops sock_hash_ops = {
+	.map_alloc = sock_hash_alloc,
+	.map_free = sock_hash_free,
+	.map_lookup_elem = sock_map_lookup,
+	.map_get_next_key = sock_hash_get_next_key,
+	.map_update_elem = sock_hash_update_elem,
+	.map_delete_elem = sock_hash_delete_elem,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
@@ -1878,3 +2402,21 @@ const struct bpf_func_proto bpf_sock_map_update_proto = {
 	.arg3_type	= ARG_PTR_TO_MAP_KEY,
 	.arg4_type	= ARG_ANYTHING,
 };
+
+BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock,
+	   struct bpf_map *, map, void *, key, u64, flags)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return sock_hash_ctx_update_elem(bpf_sock, map, key, flags);
+}
+
+const struct bpf_func_proto bpf_sock_hash_update_proto = {
+	.func		= bpf_sock_hash_update,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_PTR_TO_MAP_KEY,
+	.arg4_type	= ARG_ANYTHING,
+};
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 57eeb1234b67..b59ace0f0f09 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -11,6 +11,7 @@
 #include <linux/perf_event.h>
 #include <linux/elf.h>
 #include <linux/pagemap.h>
+#include <linux/irq_work.h>
 #include "percpu_freelist.h"
 
 #define STACK_CREATE_FLAG_MASK					\
@@ -32,6 +33,23 @@ struct bpf_stack_map {
 	struct stack_map_bucket *buckets[];
 };
 
+/* irq_work to run up_read() for build_id lookup in nmi context */
+struct stack_map_irq_work {
+	struct irq_work irq_work;
+	struct rw_semaphore *sem;
+};
+
+static void do_up_read(struct irq_work *entry)
+{
+	struct stack_map_irq_work *work;
+
+	work = container_of(entry, struct stack_map_irq_work, irq_work);
+	up_read(work->sem);
+	work->sem = NULL;
+}
+
+static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
+
 static inline bool stack_map_use_build_id(struct bpf_map *map)
 {
 	return (map->map_flags & BPF_F_STACK_BUILD_ID);
@@ -262,27 +280,32 @@ out:
 	return ret;
 }
 
-static void stack_map_get_build_id_offset(struct bpf_map *map,
-					  struct stack_map_bucket *bucket,
+static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 					  u64 *ips, u32 trace_nr, bool user)
 {
 	int i;
 	struct vm_area_struct *vma;
-	struct bpf_stack_build_id *id_offs;
-
-	bucket->nr = trace_nr;
-	id_offs = (struct bpf_stack_build_id *)bucket->data;
+	bool in_nmi_ctx = in_nmi();
+	bool irq_work_busy = false;
+	struct stack_map_irq_work *work;
+
+	if (in_nmi_ctx) {
+		work = this_cpu_ptr(&up_read_work);
+		if (work->irq_work.flags & IRQ_WORK_BUSY)
+			/* cannot queue more up_read, fallback */
+			irq_work_busy = true;
+	}
 
 	/*
-	 * We cannot do up_read() in nmi context, so build_id lookup is
-	 * only supported for non-nmi events. If at some point, it is
-	 * possible to run find_vma() without taking the semaphore, we
-	 * would like to allow build_id lookup in nmi context.
+	 * We cannot do up_read() in nmi context. To do build_id lookup
+	 * in nmi context, we need to run up_read() in irq_work. We use
+	 * a percpu variable to do the irq_work. If the irq_work is
+	 * already used by another lookup, we fall back to report ips.
 	 *
 	 * Same fallback is used for kernel stack (!user) on a stackmap
 	 * with build_id.
 	 */
-	if (!user || !current || !current->mm || in_nmi() ||
+	if (!user || !current || !current->mm || irq_work_busy ||
 	    down_read_trylock(&current->mm->mmap_sem) == 0) {
 		/* cannot access current->mm, fall back to ips */
 		for (i = 0; i < trace_nr; i++) {
@@ -304,7 +327,13 @@ static void stack_map_get_build_id_offset(struct bpf_map *map,
 			- vma->vm_start;
 		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
 	}
-	up_read(&current->mm->mmap_sem);
+
+	if (!in_nmi_ctx) {
+		up_read(&current->mm->mmap_sem);
+	} else {
+		work->sem = &current->mm->mmap_sem;
+		irq_work_queue(&work->irq_work);
+	}
 }
 
 BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
@@ -361,8 +390,10 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 			pcpu_freelist_pop(&smap->freelist);
 		if (unlikely(!new_bucket))
 			return -ENOMEM;
-		stack_map_get_build_id_offset(map, new_bucket, ips,
-					      trace_nr, user);
+		new_bucket->nr = trace_nr;
+		stack_map_get_build_id_offset(
+			(struct bpf_stack_build_id *)new_bucket->data,
+			ips, trace_nr, user);
 		trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
 		if (hash_matches && bucket->nr == trace_nr &&
 		    memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
@@ -405,6 +436,73 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
+	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
+	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+	bool user = flags & BPF_F_USER_STACK;
+	struct perf_callchain_entry *trace;
+	bool kernel = !user;
+	int err = -EINVAL;
+	u64 *ips;
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_USER_BUILD_ID)))
+		goto clear;
+	if (kernel && user_build_id)
+		goto clear;
+
+	elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id)
+					    : sizeof(u64);
+	if (unlikely(size % elem_size))
+		goto clear;
+
+	num_elem = size / elem_size;
+	if (sysctl_perf_event_max_stack < num_elem)
+		init_nr = 0;
+	else
+		init_nr = sysctl_perf_event_max_stack - num_elem;
+	trace = get_perf_callchain(regs, init_nr, kernel, user,
+				   sysctl_perf_event_max_stack, false, false);
+	if (unlikely(!trace))
+		goto err_fault;
+
+	trace_nr = trace->nr - init_nr;
+	if (trace_nr < skip)
+		goto err_fault;
+
+	trace_nr -= skip;
+	trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
+	copy_len = trace_nr * elem_size;
+	ips = trace->ip + skip + init_nr;
+	if (user && user_build_id)
+		stack_map_get_build_id_offset(buf, ips, trace_nr, user);
+	else
+		memcpy(buf, ips, copy_len);
+
+	if (size > copy_len)
+		memset(buf + copy_len, 0, size - copy_len);
+	return copy_len;
+
+err_fault:
+	err = -EFAULT;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+const struct bpf_func_proto bpf_get_stack_proto = {
+	.func		= bpf_get_stack,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 /* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 {
@@ -511,3 +609,16 @@ const struct bpf_map_ops stack_map_ops = {
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 };
+
+static int __init stack_map_init(void)
+{
+	int cpu;
+	struct stack_map_irq_work *work;
+
+	for_each_possible_cpu(cpu) {
+		work = per_cpu_ptr(&up_read_work, cpu);
+		init_irq_work(&work->irq_work, do_up_read);
+	}
+	return 0;
+}
+subsys_initcall(stack_map_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4ca46df19c9a..bfcde949c7f8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -11,6 +11,7 @@
  */
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <linux/btf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/sched/signal.h>
@@ -26,6 +27,8 @@
 #include <linux/cred.h>
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
+#include <linux/btf.h>
+#include <linux/nospec.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
 			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -102,12 +105,14 @@ const struct bpf_map_ops bpf_map_offload_ops = {
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 {
 	const struct bpf_map_ops *ops;
+	u32 type = attr->map_type;
 	struct bpf_map *map;
 	int err;
 
-	if (attr->map_type >= ARRAY_SIZE(bpf_map_types))
+	if (type >= ARRAY_SIZE(bpf_map_types))
 		return ERR_PTR(-EINVAL);
-	ops = bpf_map_types[attr->map_type];
+	type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types));
+	ops = bpf_map_types[type];
 	if (!ops)
 		return ERR_PTR(-EINVAL);
 
@@ -122,7 +127,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return map;
 	map->ops = ops;
-	map->map_type = attr->map_type;
+	map->map_type = type;
 	return map;
 }
 
@@ -257,8 +262,8 @@ static void bpf_map_free_deferred(struct work_struct *work)
 static void bpf_map_put_uref(struct bpf_map *map)
 {
 	if (atomic_dec_and_test(&map->usercnt)) {
-		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-			bpf_fd_array_map_clear(map);
+		if (map->ops->map_release_uref)
+			map->ops->map_release_uref(map);
 	}
 }
 
@@ -270,6 +275,7 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
 	if (atomic_dec_and_test(&map->refcnt)) {
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map, do_idr_lock);
+		btf_put(map->btf);
 		INIT_WORK(&map->work, bpf_map_free_deferred);
 		schedule_work(&map->work);
 	}
@@ -279,6 +285,7 @@ void bpf_map_put(struct bpf_map *map)
 {
 	__bpf_map_put(map, true);
 }
+EXPORT_SYMBOL_GPL(bpf_map_put);
 
 void bpf_map_put_with_uref(struct bpf_map *map)
 {
@@ -415,7 +422,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 	return 0;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_ifindex
+#define BPF_MAP_CREATE_LAST_FIELD btf_value_id
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -449,6 +456,33 @@ static int map_create(union bpf_attr *attr)
 	atomic_set(&map->refcnt, 1);
 	atomic_set(&map->usercnt, 1);
 
+	if (bpf_map_support_seq_show(map) &&
+	    (attr->btf_key_id || attr->btf_value_id)) {
+		struct btf *btf;
+
+		if (!attr->btf_key_id || !attr->btf_value_id) {
+			err = -EINVAL;
+			goto free_map_nouncharge;
+		}
+
+		btf = btf_get_by_fd(attr->btf_fd);
+		if (IS_ERR(btf)) {
+			err = PTR_ERR(btf);
+			goto free_map_nouncharge;
+		}
+
+		err = map->ops->map_check_btf(map, btf, attr->btf_key_id,
+					      attr->btf_value_id);
+		if (err) {
+			btf_put(btf);
+			goto free_map_nouncharge;
+		}
+
+		map->btf = btf;
+		map->btf_key_id = attr->btf_key_id;
+		map->btf_value_id = attr->btf_value_id;
+	}
+
 	err = security_bpf_map_alloc(map);
 	if (err)
 		goto free_map_nouncharge;
@@ -473,7 +507,6 @@ static int map_create(union bpf_attr *attr)
 		return err;
 	}
 
-	trace_bpf_map_create(map, err);
 	return err;
 
 free_map:
@@ -481,6 +514,7 @@ free_map:
 free_map_sec:
 	security_bpf_map_free(map);
 free_map_nouncharge:
+	btf_put(map->btf);
 	map->ops->map_free(map);
 	return err;
 }
@@ -513,6 +547,7 @@ struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
 		atomic_inc(&map->usercnt);
 	return map;
 }
+EXPORT_SYMBOL_GPL(bpf_map_inc);
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
@@ -632,7 +667,6 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (copy_to_user(uvalue, value, value_size) != 0)
 		goto free_value;
 
-	trace_bpf_map_lookup_elem(map, ufd, key, value);
 	err = 0;
 
 free_value:
@@ -729,8 +763,6 @@ static int map_update_elem(union bpf_attr *attr)
 	__this_cpu_dec(bpf_prog_active);
 	preempt_enable();
 out:
-	if (!err)
-		trace_bpf_map_update_elem(map, ufd, key, value);
 free_value:
 	kfree(value);
 free_key:
@@ -783,8 +815,6 @@ static int map_delete_elem(union bpf_attr *attr)
 	__this_cpu_dec(bpf_prog_active);
 	preempt_enable();
 out:
-	if (!err)
-		trace_bpf_map_delete_elem(map, ufd, key);
 	kfree(key);
 err_put:
 	fdput(f);
@@ -848,7 +878,6 @@ out:
 	if (copy_to_user(unext_key, next_key, map->key_size) != 0)
 		goto free_next_key;
 
-	trace_bpf_map_next_key(map, ufd, key, next_key);
 	err = 0;
 
 free_next_key:
@@ -871,11 +900,17 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = {
 
 static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 {
-	if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
+	const struct bpf_prog_ops *ops;
+
+	if (type >= ARRAY_SIZE(bpf_prog_types))
+		return -EINVAL;
+	type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types));
+	ops = bpf_prog_types[type];
+	if (!ops)
 		return -EINVAL;
 
 	if (!bpf_prog_is_dev_bound(prog->aux))
-		prog->aux->ops = bpf_prog_types[type];
+		prog->aux->ops = ops;
 	else
 		prog->aux->ops = &bpf_offload_prog_ops;
 	prog->type = type;
@@ -996,7 +1031,6 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
 		int i;
 
-		trace_bpf_prog_put_rcu(prog);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
 
@@ -1163,11 +1197,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
 				       bool attach_drv)
 {
-	struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv);
-
-	if (!IS_ERR(prog))
-		trace_bpf_prog_get_type(prog);
-	return prog;
+	return __bpf_prog_get(ufd, &type, attach_drv);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
 
@@ -1342,7 +1372,6 @@ static int bpf_prog_load(union bpf_attr *attr)
 	}
 
 	bpf_prog_kallsyms_add(prog);
-	trace_bpf_prog_load(prog, err);
 	return err;
 
 free_used_maps:
@@ -1883,6 +1912,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	info.load_time = prog->aux->load_time;
 	info.created_by_uid = from_kuid_munged(current_user_ns(),
 					       prog->aux->user->uid);
+	info.gpl_compatible = prog->gpl_compatible;
 
 	memcpy(info.tag, prog->tag, sizeof(prog->tag));
 	memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
@@ -1981,6 +2011,12 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 	info.map_flags = map->map_flags;
 	memcpy(info.name, map->name, sizeof(map->name));
 
+	if (map->btf) {
+		info.btf_id = btf_id(map->btf);
+		info.btf_key_id = map->btf_key_id;
+		info.btf_value_id = map->btf_value_id;
+	}
+
 	if (bpf_map_is_dev_bound(map)) {
 		err = bpf_map_offload_info_fill(&info, map);
 		if (err)
@@ -1994,6 +2030,21 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 	return 0;
 }
 
+static int bpf_btf_get_info_by_fd(struct btf *btf,
+				  const union bpf_attr *attr,
+				  union bpf_attr __user *uattr)
+{
+	struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+	u32 info_len = attr->info.info_len;
+	int err;
+
+	err = check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len);
+	if (err)
+		return err;
+
+	return btf_get_info_by_fd(btf, attr, uattr);
+}
+
 #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
 
 static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
@@ -2016,6 +2067,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	else if (f.file->f_op == &bpf_map_fops)
 		err = bpf_map_get_info_by_fd(f.file->private_data, attr,
 					     uattr);
+	else if (f.file->f_op == &btf_fops)
+		err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr);
 	else
 		err = -EINVAL;
 
@@ -2023,6 +2076,32 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	return err;
 }
 
+#define BPF_BTF_LOAD_LAST_FIELD btf_log_level
+
+static int bpf_btf_load(const union bpf_attr *attr)
+{
+	if (CHECK_ATTR(BPF_BTF_LOAD))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return btf_new_fd(attr);
+}
+
+#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id
+
+static int bpf_btf_get_fd_by_id(const union bpf_attr *attr)
+{
+	if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return btf_get_fd_by_id(attr->btf_id);
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -2103,6 +2182,12 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_RAW_TRACEPOINT_OPEN:
 		err = bpf_raw_tracepoint_open(&attr);
 		break;
+	case BPF_BTF_LOAD:
+		err = bpf_btf_load(&attr);
+		break;
+	case BPF_BTF_GET_FD_BY_ID:
+		err = bpf_btf_get_fd_by_id(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 1f4bf68c12db..938d41211be7 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -43,6 +43,16 @@ struct tnum tnum_rshift(struct tnum a, u8 shift)
 	return TNUM(a.value >> shift, a.mask >> shift);
 }
 
+struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+{
+	/* if a.value is negative, arithmetic shifting by minimum shift
+	 * will have larger negative offset compared to more shifting.
+	 * If a.value is nonnegative, arithmetic shifting by minimum shift
+	 * will have larger positive offset compare to more shifting.
+	 */
+	return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+}
+
 struct tnum tnum_add(struct tnum a, struct tnum b)
 {
 	u64 sm, sv, sigma, chi, mu;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5dd1dcb902bf..a9e4b1372da6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -22,6 +22,7 @@
 #include <linux/stringify.h>
 #include <linux/bsearch.h>
 #include <linux/sort.h>
+#include <linux/perf_event.h>
 
 #include "disasm.h"
 
@@ -164,6 +165,8 @@ struct bpf_call_arg_meta {
 	bool pkt_access;
 	int regno;
 	int access_size;
+	s64 msize_smax_value;
+	u64 msize_umax_value;
 };
 
 static DEFINE_MUTEX(bpf_verifier_lock);
@@ -738,18 +741,19 @@ enum reg_arg_type {
 
 static int cmp_subprogs(const void *a, const void *b)
 {
-	return *(int *)a - *(int *)b;
+	return ((struct bpf_subprog_info *)a)->start -
+	       ((struct bpf_subprog_info *)b)->start;
 }
 
 static int find_subprog(struct bpf_verifier_env *env, int off)
 {
-	u32 *p;
+	struct bpf_subprog_info *p;
 
-	p = bsearch(&off, env->subprog_starts, env->subprog_cnt,
-		    sizeof(env->subprog_starts[0]), cmp_subprogs);
+	p = bsearch(&off, env->subprog_info, env->subprog_cnt,
+		    sizeof(env->subprog_info[0]), cmp_subprogs);
 	if (!p)
 		return -ENOENT;
-	return p - env->subprog_starts;
+	return p - env->subprog_info;
 
 }
 
@@ -769,18 +773,24 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
 		verbose(env, "too many subprograms\n");
 		return -E2BIG;
 	}
-	env->subprog_starts[env->subprog_cnt++] = off;
-	sort(env->subprog_starts, env->subprog_cnt,
-	     sizeof(env->subprog_starts[0]), cmp_subprogs, NULL);
+	env->subprog_info[env->subprog_cnt++].start = off;
+	sort(env->subprog_info, env->subprog_cnt,
+	     sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
 	return 0;
 }
 
 static int check_subprogs(struct bpf_verifier_env *env)
 {
 	int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
+	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
 
+	/* Add entry function. */
+	ret = add_subprog(env, 0);
+	if (ret < 0)
+		return ret;
+
 	/* determine subprog starts. The end is one before the next starts */
 	for (i = 0; i < insn_cnt; i++) {
 		if (insn[i].code != (BPF_JMP | BPF_CALL))
@@ -800,16 +810,18 @@ static int check_subprogs(struct bpf_verifier_env *env)
 			return ret;
 	}
 
+	/* Add a fake 'exit' subprog which could simplify subprog iteration
+	 * logic. 'subprog_cnt' should not be increased.
+	 */
+	subprog[env->subprog_cnt].start = insn_cnt;
+
 	if (env->log.level > 1)
 		for (i = 0; i < env->subprog_cnt; i++)
-			verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]);
+			verbose(env, "func#%d @%d\n", i, subprog[i].start);
 
 	/* now check that all jumps are within the same subprog */
-	subprog_start = 0;
-	if (env->subprog_cnt == cur_subprog)
-		subprog_end = insn_cnt;
-	else
-		subprog_end = env->subprog_starts[cur_subprog++];
+	subprog_start = subprog[cur_subprog].start;
+	subprog_end = subprog[cur_subprog + 1].start;
 	for (i = 0; i < insn_cnt; i++) {
 		u8 code = insn[i].code;
 
@@ -834,10 +846,9 @@ next:
 				return -EINVAL;
 			}
 			subprog_start = subprog_end;
-			if (env->subprog_cnt == cur_subprog)
-				subprog_end = insn_cnt;
-			else
-				subprog_end = env->subprog_starts[cur_subprog++];
+			cur_subprog++;
+			if (cur_subprog < env->subprog_cnt)
+				subprog_end = subprog[cur_subprog + 1].start;
 		}
 	}
 	return 0;
@@ -1470,13 +1481,13 @@ static int update_stack_depth(struct bpf_verifier_env *env,
 			      const struct bpf_func_state *func,
 			      int off)
 {
-	u16 stack = env->subprog_stack_depth[func->subprogno];
+	u16 stack = env->subprog_info[func->subprogno].stack_depth;
 
 	if (stack >= -off)
 		return 0;
 
 	/* update known max for given subprogram */
-	env->subprog_stack_depth[func->subprogno] = -off;
+	env->subprog_info[func->subprogno].stack_depth = -off;
 	return 0;
 }
 
@@ -1488,9 +1499,9 @@ static int update_stack_depth(struct bpf_verifier_env *env,
  */
 static int check_max_stack_depth(struct bpf_verifier_env *env)
 {
-	int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end;
+	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
+	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
-	int insn_cnt = env->prog->len;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
 
@@ -1498,17 +1509,14 @@ process_func:
 	/* round up to 32-bytes, since this is granularity
 	 * of interpreter stack size
 	 */
-	depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+	depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
 	if (depth > MAX_BPF_STACK) {
 		verbose(env, "combined stack size of %d calls is %d. Too large\n",
 			frame + 1, depth);
 		return -EACCES;
 	}
 continue_func:
-	if (env->subprog_cnt == subprog)
-		subprog_end = insn_cnt;
-	else
-		subprog_end = env->subprog_starts[subprog];
+	subprog_end = subprog[idx + 1].start;
 	for (; i < subprog_end; i++) {
 		if (insn[i].code != (BPF_JMP | BPF_CALL))
 			continue;
@@ -1516,17 +1524,16 @@ continue_func:
 			continue;
 		/* remember insn and function to return to */
 		ret_insn[frame] = i + 1;
-		ret_prog[frame] = subprog;
+		ret_prog[frame] = idx;
 
 		/* find the callee */
 		i = i + insn[i].imm + 1;
-		subprog = find_subprog(env, i);
-		if (subprog < 0) {
+		idx = find_subprog(env, i);
+		if (idx < 0) {
 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
 				  i);
 			return -EFAULT;
 		}
-		subprog++;
 		frame++;
 		if (frame >= MAX_CALL_FRAMES) {
 			WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
@@ -1539,10 +1546,10 @@ continue_func:
 	 */
 	if (frame == 0)
 		return 0;
-	depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+	depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
 	frame--;
 	i = ret_insn[frame];
-	subprog = ret_prog[frame];
+	idx = ret_prog[frame];
 	goto continue_func;
 }
 
@@ -1558,8 +1565,7 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
 			  start);
 		return -EFAULT;
 	}
-	subprog++;
-	return env->subprog_stack_depth[subprog];
+	return env->subprog_info[subprog].stack_depth;
 }
 #endif
 
@@ -1914,7 +1920,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 	if (arg_type == ARG_PTR_TO_MAP_KEY ||
 	    arg_type == ARG_PTR_TO_MAP_VALUE) {
 		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
+		if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
 		    type != expected_type)
 			goto err_type;
 	} else if (arg_type == ARG_CONST_SIZE ||
@@ -1966,14 +1972,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			verbose(env, "invalid map_ptr to access map->key\n");
 			return -EACCES;
 		}
-		if (type_is_pkt_pointer(type))
-			err = check_packet_access(env, regno, reg->off,
-						  meta->map_ptr->key_size,
-						  false);
-		else
-			err = check_stack_boundary(env, regno,
-						   meta->map_ptr->key_size,
-						   false, NULL);
+		err = check_helper_mem_access(env, regno,
+					      meta->map_ptr->key_size, false,
+					      NULL);
 	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
 		/* bpf_map_xxx(..., map_ptr, ..., value) call:
 		 * check [value, value + map->value_size) validity
@@ -1983,17 +1984,18 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			verbose(env, "invalid map_ptr to access map->value\n");
 			return -EACCES;
 		}
-		if (type_is_pkt_pointer(type))
-			err = check_packet_access(env, regno, reg->off,
-						  meta->map_ptr->value_size,
-						  false);
-		else
-			err = check_stack_boundary(env, regno,
-						   meta->map_ptr->value_size,
-						   false, NULL);
+		err = check_helper_mem_access(env, regno,
+					      meta->map_ptr->value_size, false,
+					      NULL);
 	} else if (arg_type_is_mem_size(arg_type)) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
+		/* remember the mem_size which may be used later
+		 * to refine return values.
+		 */
+		meta->msize_smax_value = reg->smax_value;
+		meta->msize_umax_value = reg->umax_value;
+
 		/* The register is SCALAR_VALUE; the access check
 		 * happens using its boundaries.
 		 */
@@ -2071,8 +2073,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_redirect_map)
 			goto error;
 		break;
-	/* Restrict bpf side of cpumap, open when use-cases appear */
+	/* Restrict bpf side of cpumap and xskmap, open when use-cases
+	 * appear.
+	 */
 	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_XSKMAP:
 		if (func_id != BPF_FUNC_redirect_map)
 			goto error;
 		break;
@@ -2088,6 +2093,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_msg_redirect_map)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_SOCKHASH:
+		if (func_id != BPF_FUNC_sk_redirect_hash &&
+		    func_id != BPF_FUNC_sock_hash_update &&
+		    func_id != BPF_FUNC_map_delete_elem &&
+		    func_id != BPF_FUNC_msg_redirect_hash)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -2097,7 +2109,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_tail_call:
 		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
 			goto error;
-		if (env->subprog_cnt) {
+		if (env->subprog_cnt > 1) {
 			verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
 			return -EINVAL;
 		}
@@ -2119,16 +2131,20 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		break;
 	case BPF_FUNC_redirect_map:
 		if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
-		    map->map_type != BPF_MAP_TYPE_CPUMAP)
+		    map->map_type != BPF_MAP_TYPE_CPUMAP &&
+		    map->map_type != BPF_MAP_TYPE_XSKMAP)
 			goto error;
 		break;
 	case BPF_FUNC_sk_redirect_map:
 	case BPF_FUNC_msg_redirect_map:
+	case BPF_FUNC_sock_map_update:
 		if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
 			goto error;
 		break;
-	case BPF_FUNC_sock_map_update:
-		if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
+	case BPF_FUNC_sk_redirect_hash:
+	case BPF_FUNC_msg_redirect_hash:
+	case BPF_FUNC_sock_hash_update:
+		if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
 	default:
@@ -2269,7 +2285,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			/* remember the callsite, it will be used by bpf_exit */
 			*insn_idx /* callsite */,
 			state->curframe + 1 /* frameno within this callchain */,
-			subprog + 1 /* subprog number within this prog */);
+			subprog /* subprog number within this prog */);
 
 	/* copy r1 - r5 args that callee can access */
 	for (i = BPF_REG_1; i <= BPF_REG_5; i++)
@@ -2333,6 +2349,23 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	return 0;
 }
 
+static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
+				   int func_id,
+				   struct bpf_call_arg_meta *meta)
+{
+	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
+
+	if (ret_type != RET_INTEGER ||
+	    (func_id != BPF_FUNC_get_stack &&
+	     func_id != BPF_FUNC_probe_read_str))
+		return;
+
+	ret_reg->smax_value = meta->msize_smax_value;
+	ret_reg->umax_value = meta->msize_umax_value;
+	__reg_deduce_bounds(ret_reg);
+	__reg_bound_offset(ret_reg);
+}
+
 static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 {
 	const struct bpf_func_proto *fn = NULL;
@@ -2456,10 +2489,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		return -EINVAL;
 	}
 
+	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+
 	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
 	if (err)
 		return err;
 
+	if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+		const char *err_str;
+
+#ifdef CONFIG_PERF_EVENTS
+		err = get_callchain_buffers(sysctl_perf_event_max_stack);
+		err_str = "cannot get callchain buffer for func %s#%d\n";
+#else
+		err = -ENOTSUPP;
+		err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n";
+#endif
+		if (err) {
+			verbose(env, err_str, func_id_name(func_id), func_id);
+			return err;
+		}
+
+		env->prog->has_callchain_buf = true;
+	}
+
 	if (changes_data)
 		clear_all_pkt_pointers(env);
 	return 0;
@@ -2904,10 +2957,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			dst_reg->umin_value <<= umin_val;
 			dst_reg->umax_value <<= umax_val;
 		}
-		if (src_known)
-			dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
-		else
-			dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val);
+		dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
 		/* We may learn something more from the var_off */
 		__update_reg_bounds(dst_reg);
 		break;
@@ -2935,16 +2985,35 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		 */
 		dst_reg->smin_value = S64_MIN;
 		dst_reg->smax_value = S64_MAX;
-		if (src_known)
-			dst_reg->var_off = tnum_rshift(dst_reg->var_off,
-						       umin_val);
-		else
-			dst_reg->var_off = tnum_rshift(tnum_unknown, umin_val);
+		dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
 		dst_reg->umin_value >>= umax_val;
 		dst_reg->umax_value >>= umin_val;
 		/* We may learn something more from the var_off */
 		__update_reg_bounds(dst_reg);
 		break;
+	case BPF_ARSH:
+		if (umax_val >= insn_bitness) {
+			/* Shifts greater than 31 or 63 are undefined.
+			 * This includes shifts by a negative number.
+			 */
+			mark_reg_unknown(env, regs, insn->dst_reg);
+			break;
+		}
+
+		/* Upon reaching here, src_known is true and
+		 * umax_val is equal to umin_val.
+		 */
+		dst_reg->smin_value >>= umin_val;
+		dst_reg->smax_value >>= umin_val;
+		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+
+		/* blow away the dst_reg umin_value/umax_value and rely on
+		 * dst_reg var_off to refine the result.
+		 */
+		dst_reg->umin_value = 0;
+		dst_reg->umax_value = U64_MAX;
+		__update_reg_bounds(dst_reg);
+		break;
 	default:
 		mark_reg_unknown(env, regs, insn->dst_reg);
 		break;
@@ -3828,7 +3897,12 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}
 
-	if (env->subprog_cnt) {
+	if (!env->ops->gen_ld_abs) {
+		verbose(env, "bpf verifier is misconfigured\n");
+		return -EINVAL;
+	}
+
+	if (env->subprog_cnt > 1) {
 		/* when program has LD_ABS insn JITs and interpreter assume
 		 * that r1 == ctx == skb which is not the case for callees
 		 * that can have arbitrary arguments. It's problematic
@@ -4859,15 +4933,15 @@ process_bpf_exit:
 
 	verbose(env, "processed %d insns (limit %d), stack depth ",
 		insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
-	for (i = 0; i < env->subprog_cnt + 1; i++) {
-		u32 depth = env->subprog_stack_depth[i];
+	for (i = 0; i < env->subprog_cnt; i++) {
+		u32 depth = env->subprog_info[i].stack_depth;
 
 		verbose(env, "%d", depth);
-		if (i + 1 < env->subprog_cnt + 1)
+		if (i + 1 < env->subprog_cnt)
 			verbose(env, "+");
 	}
 	verbose(env, "\n");
-	env->prog->aux->stack_depth = env->subprog_stack_depth[0];
+	env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return 0;
 }
 
@@ -4991,7 +5065,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
-			 * and all maps are released in free_bpf_prog_info()
+			 * and all maps are released in free_used_maps()
 			 */
 			map = bpf_map_inc(map, false);
 			if (IS_ERR(map)) {
@@ -5073,10 +5147,11 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
 
 	if (len == 1)
 		return;
-	for (i = 0; i < env->subprog_cnt; i++) {
-		if (env->subprog_starts[i] < off)
+	/* NOTE: fake 'exit' subprog should be updated as well. */
+	for (i = 0; i <= env->subprog_cnt; i++) {
+		if (env->subprog_info[i].start < off)
 			continue;
-		env->subprog_starts[i] += len - 1;
+		env->subprog_info[i].start += len - 1;
 	}
 }
 
@@ -5150,7 +5225,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		}
 	}
 
-	if (!ops->convert_ctx_access)
+	if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux))
 		return 0;
 
 	insn = env->prog->insnsi + delta;
@@ -5240,7 +5315,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	void *old_bpf_func;
 	int err = -ENOMEM;
 
-	if (env->subprog_cnt == 0)
+	if (env->subprog_cnt <= 1)
 		return 0;
 
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5256,7 +5331,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		/* temporarily remember subprog id inside insn instead of
 		 * aux_data, since next loop will split up all insns into funcs
 		 */
-		insn->off = subprog + 1;
+		insn->off = subprog;
 		/* remember original imm in case JIT fails and fallback
 		 * to interpreter will be needed
 		 */
@@ -5265,16 +5340,13 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		insn->imm = 1;
 	}
 
-	func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL);
+	func = kzalloc(sizeof(prog) * env->subprog_cnt, GFP_KERNEL);
 	if (!func)
 		return -ENOMEM;
 
-	for (i = 0; i <= env->subprog_cnt; i++) {
+	for (i = 0; i < env->subprog_cnt; i++) {
 		subprog_start = subprog_end;
-		if (env->subprog_cnt == i)
-			subprog_end = prog->len;
-		else
-			subprog_end = env->subprog_starts[i];
+		subprog_end = env->subprog_info[i + 1].start;
 
 		len = subprog_end - subprog_start;
 		func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
@@ -5291,7 +5363,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		 * Long term would need debug info to populate names
 		 */
 		func[i]->aux->name[0] = 'F';
-		func[i]->aux->stack_depth = env->subprog_stack_depth[i];
+		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
@@ -5304,7 +5376,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	 * now populate all bpf_calls with correct addresses and
 	 * run last pass of JIT
 	 */
-	for (i = 0; i <= env->subprog_cnt; i++) {
+	for (i = 0; i < env->subprog_cnt; i++) {
 		insn = func[i]->insnsi;
 		for (j = 0; j < func[i]->len; j++, insn++) {
 			if (insn->code != (BPF_JMP | BPF_CALL) ||
@@ -5317,7 +5389,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 				__bpf_call_base;
 		}
 	}
-	for (i = 0; i <= env->subprog_cnt; i++) {
+	for (i = 0; i < env->subprog_cnt; i++) {
 		old_bpf_func = func[i]->bpf_func;
 		tmp = bpf_int_jit_compile(func[i]);
 		if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
@@ -5331,7 +5403,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	/* finally lock prog and jit images for all functions and
 	 * populate kallsysm
 	 */
-	for (i = 0; i <= env->subprog_cnt; i++) {
+	for (i = 0; i < env->subprog_cnt; i++) {
 		bpf_prog_lock_ro(func[i]);
 		bpf_prog_kallsyms_add(func[i]);
 	}
@@ -5348,7 +5420,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 			continue;
 		insn->off = env->insn_aux_data[i].call_imm;
 		subprog = find_subprog(env, i + insn->off + 1);
-		addr  = (unsigned long)func[subprog + 1]->bpf_func;
+		addr  = (unsigned long)func[subprog]->bpf_func;
 		addr &= PAGE_MASK;
 		insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
 			    addr - __bpf_call_base;
@@ -5357,10 +5429,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	prog->jited = 1;
 	prog->bpf_func = func[0]->bpf_func;
 	prog->aux->func = func;
-	prog->aux->func_cnt = env->subprog_cnt + 1;
+	prog->aux->func_cnt = env->subprog_cnt;
 	return 0;
 out_free:
-	for (i = 0; i <= env->subprog_cnt; i++)
+	for (i = 0; i < env->subprog_cnt; i++)
 		if (func[i])
 			bpf_jit_free(func[i]);
 	kfree(func);
@@ -5463,6 +5535,25 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			continue;
 		}
 
+		if (BPF_CLASS(insn->code) == BPF_LD &&
+		    (BPF_MODE(insn->code) == BPF_ABS ||
+		     BPF_MODE(insn->code) == BPF_IND)) {
+			cnt = env->ops->gen_ld_abs(insn, insn_buf);
+			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+				verbose(env, "bpf verifier is misconfigured\n");
+				return -EINVAL;
+			}
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 		if (insn->code != (BPF_JMP | BPF_CALL))
 			continue;
 		if (insn->src_reg == BPF_PSEUDO_CALL)
@@ -5660,16 +5751,16 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
 		env->strict_alignment = true;
 
+	ret = replace_map_fd_with_map_ptr(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	if (bpf_prog_is_dev_bound(env->prog->aux)) {
 		ret = bpf_prog_offload_verifier_prep(env);
 		if (ret)
-			goto err_unlock;
+			goto skip_full_check;
 	}
 
-	ret = replace_map_fd_with_map_ptr(env);
-	if (ret < 0)
-		goto skip_full_check;
-
 	env->explored_states = kcalloc(env->prog->len,
 				       sizeof(struct bpf_verifier_state_list *),
 				       GFP_USER);
@@ -5740,7 +5831,7 @@ skip_full_check:
 err_release_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.
+		 * them now. Otherwise free_used_maps() will release them.
 		 */
 		release_maps(env);
 	*prog = env->prog;
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
new file mode 100644
index 000000000000..cb3a12137404
--- /dev/null
+++ b/kernel/bpf/xskmap.c
@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XSKMAP used for AF_XDP sockets
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/bpf.h>
+#include <linux/capability.h>
+#include <net/xdp_sock.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+
+struct xsk_map {
+	struct bpf_map map;
+	struct xdp_sock **xsk_map;
+	struct list_head __percpu *flush_list;
+};
+
+static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
+{
+	int cpu, err = -EINVAL;
+	struct xsk_map *m;
+	u64 cost;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 ||
+	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
+		return ERR_PTR(-EINVAL);
+
+	m = kzalloc(sizeof(*m), GFP_USER);
+	if (!m)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&m->map, attr);
+
+	cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
+	cost += sizeof(struct list_head) * num_possible_cpus();
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_m;
+
+	m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* Notice returns -EPERM on if map size is larger than memlock limit */
+	err = bpf_map_precharge_memlock(m->map.pages);
+	if (err)
+		goto free_m;
+
+	err = -ENOMEM;
+
+	m->flush_list = alloc_percpu(struct list_head);
+	if (!m->flush_list)
+		goto free_m;
+
+	for_each_possible_cpu(cpu)
+		INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu));
+
+	m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
+					sizeof(struct xdp_sock *),
+					m->map.numa_node);
+	if (!m->xsk_map)
+		goto free_percpu;
+	return &m->map;
+
+free_percpu:
+	free_percpu(m->flush_list);
+free_m:
+	kfree(m);
+	return ERR_PTR(err);
+}
+
+static void xsk_map_free(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	int i;
+
+	synchronize_net();
+
+	for (i = 0; i < map->max_entries; i++) {
+		struct xdp_sock *xs;
+
+		xs = m->xsk_map[i];
+		if (!xs)
+			continue;
+
+		sock_put((struct sock *)xs);
+	}
+
+	free_percpu(m->flush_list);
+	bpf_map_area_free(m->xsk_map);
+	kfree(m);
+}
+
+static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= m->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == m->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock *xs;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	xs = READ_ONCE(m->xsk_map[key]);
+	return xs;
+}
+
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+		       struct xdp_sock *xs)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+	int err;
+
+	err = xsk_rcv(xs, xdp);
+	if (err)
+		return err;
+
+	if (!xs->flush_node.prev)
+		list_add(&xs->flush_node, flush_list);
+
+	return 0;
+}
+
+void __xsk_map_flush(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+	struct xdp_sock *xs, *tmp;
+
+	list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
+		xsk_flush(xs);
+		__list_del(xs->flush_node.prev, xs->flush_node.next);
+		xs->flush_node.prev = NULL;
+	}
+}
+
+static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
+			       u64 map_flags)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	u32 i = *(u32 *)key, fd = *(u32 *)value;
+	struct xdp_sock *xs, *old_xs;
+	struct socket *sock;
+	int err;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(i >= m->map.max_entries))
+		return -E2BIG;
+	if (unlikely(map_flags == BPF_NOEXIST))
+		return -EEXIST;
+
+	sock = sockfd_lookup(fd, &err);
+	if (!sock)
+		return err;
+
+	if (sock->sk->sk_family != PF_XDP) {
+		sockfd_put(sock);
+		return -EOPNOTSUPP;
+	}
+
+	xs = (struct xdp_sock *)sock->sk;
+
+	if (!xsk_is_setup_for_bpf_map(xs)) {
+		sockfd_put(sock);
+		return -EOPNOTSUPP;
+	}
+
+	sock_hold(sock->sk);
+
+	old_xs = xchg(&m->xsk_map[i], xs);
+	if (old_xs) {
+		/* Make sure we've flushed everything. */
+		synchronize_net();
+		sock_put((struct sock *)old_xs);
+	}
+
+	sockfd_put(sock);
+	return 0;
+}
+
+static int xsk_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock *old_xs;
+	int k = *(u32 *)key;
+
+	if (k >= map->max_entries)
+		return -EINVAL;
+
+	old_xs = xchg(&m->xsk_map[k], NULL);
+	if (old_xs) {
+		/* Make sure we've flushed everything. */
+		synchronize_net();
+		sock_put((struct sock *)old_xs);
+	}
+
+	return 0;
+}
+
+const struct bpf_map_ops xsk_map_ops = {
+	.map_alloc = xsk_map_alloc,
+	.map_free = xsk_map_free,
+	.map_get_next_key = xsk_map_get_next_key,
+	.map_lookup_elem = xsk_map_lookup_elem,
+	.map_update_elem = xsk_map_update_elem,
+	.map_delete_elem = xsk_map_delete_elem,
+};
+
+