From daedfb22451dd02b35c0549566cbb7cc06bdd53b Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Thu, 4 Sep 2014 22:17:18 -0700
Subject: net: filter: split filter.h and expose eBPF to user space

allow user space to generate eBPF programs

uapi/linux/bpf.h: eBPF instruction set definition

linux/filter.h: the rest

This patch only moves macro definitions, but practically it freezes existing
eBPF instruction set, though new instructions can still be added in the future.

These eBPF definitions cannot go into uapi/linux/filter.h, since the names
may conflict with existing applications.

Full eBPF ISA description is in Documentation/networking/filter.txt

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h | 65 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 include/uapi/linux/bpf.h

(limited to 'include/uapi/linux/bpf.h')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
new file mode 100644
index 000000000000..479ed0b6be16
--- /dev/null
+++ b/include/uapi/linux/bpf.h
@@ -0,0 +1,65 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_H__
+#define _UAPI__LINUX_BPF_H__
+
+#include <linux/types.h>
+
+/* Extended instruction set based on top of classic BPF */
+
+/* instruction classes */
+#define BPF_ALU64	0x07	/* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW		0x18	/* double word */
+#define BPF_XADD	0xc0	/* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV		0xb0	/* mov reg to reg */
+#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END		0xd0	/* flags for endianness conversion: */
+#define BPF_TO_LE	0x00	/* convert to little-endian */
+#define BPF_TO_BE	0x08	/* convert to big-endian */
+#define BPF_FROM_LE	BPF_TO_LE
+#define BPF_FROM_BE	BPF_TO_BE
+
+#define BPF_JNE		0x50	/* jump != */
+#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
+#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
+#define BPF_CALL	0x80	/* function call */
+#define BPF_EXIT	0x90	/* function return */
+
+/* Register numbers */
+enum {
+	BPF_REG_0 = 0,
+	BPF_REG_1,
+	BPF_REG_2,
+	BPF_REG_3,
+	BPF_REG_4,
+	BPF_REG_5,
+	BPF_REG_6,
+	BPF_REG_7,
+	BPF_REG_8,
+	BPF_REG_9,
+	BPF_REG_10,
+	__MAX_BPF_REG,
+};
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG	__MAX_BPF_REG
+
+struct bpf_insn {
+	__u8	code;		/* opcode */
+	__u8	dst_reg:4;	/* dest register */
+	__u8	src_reg:4;	/* source register */
+	__s16	off;		/* signed offset */
+	__s32	imm;		/* signed immediate constant */
+};
+
+#endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From 99c55f7d47c0dc6fc64729f37bf435abf43f4c60 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:16:57 -0700
Subject: bpf: introduce BPF syscall and maps

BPF syscall is a multiplexor for a range of different operations on eBPF.
This patch introduces syscall with single command to create a map.
Next patch adds commands to access maps.

'maps' is a generic storage of different types for sharing data between kernel
and userspace.

Userspace example:
/* this syscall wrapper creates a map with given type and attributes
 * and returns map_fd on success.
 * use close(map_fd) to delete the map
 */
int bpf_create_map(enum bpf_map_type map_type, int key_size,
                   int value_size, int max_entries)
{
    union bpf_attr attr = {
        .map_type = map_type,
        .key_size = key_size,
        .value_size = value_size,
        .max_entries = max_entries
    };

    return bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}

'union bpf_attr' is backwards compatible with future extensions.

More details in Documentation/networking/filter.txt and in manpage

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/filter.txt |  39 +++++++++
 include/linux/bpf.h                 |  41 +++++++++
 include/uapi/linux/bpf.h            |  23 +++++
 kernel/bpf/Makefile                 |   2 +-
 kernel/bpf/syscall.c                | 169 ++++++++++++++++++++++++++++++++++++
 5 files changed, 273 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/bpf.h
 create mode 100644 kernel/bpf/syscall.c

(limited to 'include/uapi/linux/bpf.h')

diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 014e0319a5c4..4a01d71785e9 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -1001,6 +1001,45 @@ instruction that loads 64-bit immediate value into a dst_reg.
 Classic BPF has similar instruction: BPF_LD | BPF_W | BPF_IMM which loads
 32-bit immediate value into a register.
 
+eBPF maps
+---------
+'maps' is a generic storage of different types for sharing data between kernel
+and userspace.
+
+The maps are accessed from user space via BPF syscall, which has commands:
+- create a map with given type and attributes
+  map_fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
+  using attr->map_type, attr->key_size, attr->value_size, attr->max_entries
+  returns process-local file descriptor or negative error
+
+- lookup key in a given map
+  err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
+  using attr->map_fd, attr->key, attr->value
+  returns zero and stores found elem into value or negative error
+
+- create or update key/value pair in a given map
+  err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
+  using attr->map_fd, attr->key, attr->value
+  returns zero or negative error
+
+- find and delete element by key in a given map
+  err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
+  using attr->map_fd, attr->key
+
+- to delete map: close(fd)
+  Exiting process will delete maps automatically
+
+userspace programs use this syscall to create/access maps that eBPF programs
+are concurrently updating.
+
+maps can have different types: hash, array, bloom filter, radix-tree, etc.
+
+The map is defined by:
+  . type
+  . max number of elements
+  . key size in bytes
+  . value size in bytes
+
 Testing
 -------
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
new file mode 100644
index 000000000000..48014a71f0fe
--- /dev/null
+++ b/include/linux/bpf.h
@@ -0,0 +1,41 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _LINUX_BPF_H
+#define _LINUX_BPF_H 1
+
+#include <uapi/linux/bpf.h>
+#include <linux/workqueue.h>
+
+struct bpf_map;
+
+/* map is generic key/value storage optionally accesible by eBPF programs */
+struct bpf_map_ops {
+	/* funcs callable from userspace (via syscall) */
+	struct bpf_map *(*map_alloc)(union bpf_attr *attr);
+	void (*map_free)(struct bpf_map *);
+};
+
+struct bpf_map {
+	atomic_t refcnt;
+	enum bpf_map_type map_type;
+	u32 key_size;
+	u32 value_size;
+	u32 max_entries;
+	struct bpf_map_ops *ops;
+	struct work_struct work;
+};
+
+struct bpf_map_type_list {
+	struct list_head list_node;
+	struct bpf_map_ops *ops;
+	enum bpf_map_type type;
+};
+
+void bpf_register_map_type(struct bpf_map_type_list *tl);
+void bpf_map_put(struct bpf_map *map);
+
+#endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 479ed0b6be16..f58a10f9670c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -62,4 +62,27 @@ struct bpf_insn {
 	__s32	imm;		/* signed immediate constant */
 };
 
+/* BPF syscall commands */
+enum bpf_cmd {
+	/* create a map with given type and attributes
+	 * fd = bpf(BPF_MAP_CREATE, union bpf_attr *, u32 size)
+	 * returns fd or negative error
+	 * map is deleted when fd is closed
+	 */
+	BPF_MAP_CREATE,
+};
+
+enum bpf_map_type {
+	BPF_MAP_TYPE_UNSPEC,
+};
+
+union bpf_attr {
+	struct { /* anonymous struct used by BPF_MAP_CREATE command */
+		__u32	map_type;	/* one of enum bpf_map_type */
+		__u32	key_size;	/* size of key in bytes */
+		__u32	value_size;	/* size of value in bytes */
+		__u32	max_entries;	/* max number of entries in a map */
+	};
+} __attribute__((aligned(8)));
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 6a71145e2769..e9f7334ed07a 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1 +1 @@
-obj-y := core.o
+obj-y := core.o syscall.o
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
new file mode 100644
index 000000000000..428a0e23adc0
--- /dev/null
+++ b/kernel/bpf/syscall.c
@@ -0,0 +1,169 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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/syscalls.h>
+#include <linux/slab.h>
+#include <linux/anon_inodes.h>
+
+static LIST_HEAD(bpf_map_types);
+
+static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
+{
+	struct bpf_map_type_list *tl;
+	struct bpf_map *map;
+
+	list_for_each_entry(tl, &bpf_map_types, list_node) {
+		if (tl->type == attr->map_type) {
+			map = tl->ops->map_alloc(attr);
+			if (IS_ERR(map))
+				return map;
+			map->ops = tl->ops;
+			map->map_type = attr->map_type;
+			return map;
+		}
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+/* boot time registration of different map implementations */
+void bpf_register_map_type(struct bpf_map_type_list *tl)
+{
+	list_add(&tl->list_node, &bpf_map_types);
+}
+
+/* called from workqueue */
+static void bpf_map_free_deferred(struct work_struct *work)
+{
+	struct bpf_map *map = container_of(work, struct bpf_map, work);
+
+	/* implementation dependent freeing */
+	map->ops->map_free(map);
+}
+
+/* decrement map refcnt and schedule it for freeing via workqueue
+ * (unrelying map implementation ops->map_free() might sleep)
+ */
+void bpf_map_put(struct bpf_map *map)
+{
+	if (atomic_dec_and_test(&map->refcnt)) {
+		INIT_WORK(&map->work, bpf_map_free_deferred);
+		schedule_work(&map->work);
+	}
+}
+
+static int bpf_map_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_map *map = filp->private_data;
+
+	bpf_map_put(map);
+	return 0;
+}
+
+static const struct file_operations bpf_map_fops = {
+	.release = bpf_map_release,
+};
+
+/* helper macro to check that unused fields 'union bpf_attr' are zero */
+#define CHECK_ATTR(CMD) \
+	memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
+		   sizeof(attr->CMD##_LAST_FIELD), 0, \
+		   sizeof(*attr) - \
+		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
+		   sizeof(attr->CMD##_LAST_FIELD)) != NULL
+
+#define BPF_MAP_CREATE_LAST_FIELD max_entries
+/* called via syscall */
+static int map_create(union bpf_attr *attr)
+{
+	struct bpf_map *map;
+	int err;
+
+	err = CHECK_ATTR(BPF_MAP_CREATE);
+	if (err)
+		return -EINVAL;
+
+	/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
+	map = find_and_alloc_map(attr);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	atomic_set(&map->refcnt, 1);
+
+	err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC);
+
+	if (err < 0)
+		/* failed to allocate fd */
+		goto free_map;
+
+	return err;
+
+free_map:
+	map->ops->map_free(map);
+	return err;
+}
+
+SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+{
+	union bpf_attr attr = {};
+	int err;
+
+	/* the syscall is limited to root temporarily. This restriction will be
+	 * lifted when security audit is clean. Note that eBPF+tracing must have
+	 * this restriction, since it may pass kernel data to user space
+	 */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!access_ok(VERIFY_READ, uattr, 1))
+		return -EFAULT;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		return -E2BIG;
+
+	/* If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
+	 */
+	if (size > sizeof(attr)) {
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
+
+		addr = (void __user *)uattr + sizeof(attr);
+		end  = (void __user *)uattr + size;
+
+		for (; addr < end; addr++) {
+			err = get_user(val, addr);
+			if (err)
+				return err;
+			if (val)
+				return -E2BIG;
+		}
+		size = sizeof(attr);
+	}
+
+	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
+	if (copy_from_user(&attr, uattr, size) != 0)
+		return -EFAULT;
+
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+		err = map_create(&attr);
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
+}
-- 
cgit v1.2.3


From db20fd2b01087bdfbe30bce314a198eefedcc42e Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:16:59 -0700
Subject: bpf: add lookup/update/delete/iterate methods to BPF maps

'maps' is a generic storage of different types for sharing data between kernel
and userspace.

The maps are accessed from user space via BPF syscall, which has commands:

- create a map with given type and attributes
  fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
  returns fd or negative error

- lookup key in a given map referenced by fd
  err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key, attr->value
  returns zero and stores found elem into value or negative error

- create or update key/value pair in a given map
  err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key, attr->value
  returns zero or negative error

- find and delete element by key in a given map
  err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key

- iterate map elements (based on input key return next_key)
  err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key, attr->next_key

- close(fd) deletes the map

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h      |   8 ++
 include/uapi/linux/bpf.h |  38 ++++++++
 kernel/bpf/syscall.c     | 235 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 281 insertions(+)

(limited to 'include/uapi/linux/bpf.h')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 48014a71f0fe..2887f3f9da59 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -9,6 +9,7 @@
 
 #include <uapi/linux/bpf.h>
 #include <linux/workqueue.h>
+#include <linux/file.h>
 
 struct bpf_map;
 
@@ -17,6 +18,12 @@ struct bpf_map_ops {
 	/* funcs callable from userspace (via syscall) */
 	struct bpf_map *(*map_alloc)(union bpf_attr *attr);
 	void (*map_free)(struct bpf_map *);
+	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+
+	/* funcs callable from userspace and from eBPF programs */
+	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
+	int (*map_update_elem)(struct bpf_map *map, void *key, void *value);
+	int (*map_delete_elem)(struct bpf_map *map, void *key);
 };
 
 struct bpf_map {
@@ -37,5 +44,6 @@ struct bpf_map_type_list {
 
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 void bpf_map_put(struct bpf_map *map);
+struct bpf_map *bpf_map_get(struct fd f);
 
 #endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f58a10f9670c..395cabd2ca0a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -70,6 +70,35 @@ enum bpf_cmd {
 	 * map is deleted when fd is closed
 	 */
 	BPF_MAP_CREATE,
+
+	/* lookup key in a given map
+	 * err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key, attr->value
+	 * returns zero and stores found elem into value
+	 * or negative error
+	 */
+	BPF_MAP_LOOKUP_ELEM,
+
+	/* create or update key/value pair in a given map
+	 * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key, attr->value
+	 * returns zero or negative error
+	 */
+	BPF_MAP_UPDATE_ELEM,
+
+	/* find and delete elem by key in a given map
+	 * err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key
+	 * returns zero or negative error
+	 */
+	BPF_MAP_DELETE_ELEM,
+
+	/* lookup key in a given map and return next key
+	 * err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key, attr->next_key
+	 * returns zero and stores next key or negative error
+	 */
+	BPF_MAP_GET_NEXT_KEY,
 };
 
 enum bpf_map_type {
@@ -83,6 +112,15 @@ union bpf_attr {
 		__u32	value_size;	/* size of value in bytes */
 		__u32	max_entries;	/* max number of entries in a map */
 	};
+
+	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
+		__u32		map_fd;
+		__aligned_u64	key;
+		union {
+			__aligned_u64 value;
+			__aligned_u64 next_key;
+		};
+	};
 } __attribute__((aligned(8)));
 
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 428a0e23adc0..f94349ecaf61 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -13,6 +13,7 @@
 #include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/anon_inodes.h>
+#include <linux/file.h>
 
 static LIST_HEAD(bpf_map_types);
 
@@ -111,6 +112,228 @@ free_map:
 	return err;
 }
 
+/* if error is returned, fd is released.
+ * On success caller should complete fd access with matching fdput()
+ */
+struct bpf_map *bpf_map_get(struct fd f)
+{
+	struct bpf_map *map;
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	if (f.file->f_op != &bpf_map_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = f.file->private_data;
+
+	return map;
+}
+
+/* helper to convert user pointers passed inside __aligned_u64 fields */
+static void __user *u64_to_ptr(__u64 val)
+{
+	return (void __user *) (unsigned long) val;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
+
+static int map_lookup_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	void __user *uvalue = u64_to_ptr(attr->value);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key, *value;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	err = -ESRCH;
+	rcu_read_lock();
+	value = map->ops->map_lookup_elem(map, key);
+	if (!value)
+		goto err_unlock;
+
+	err = -EFAULT;
+	if (copy_to_user(uvalue, value, map->value_size) != 0)
+		goto err_unlock;
+
+	err = 0;
+
+err_unlock:
+	rcu_read_unlock();
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
+#define BPF_MAP_UPDATE_ELEM_LAST_FIELD value
+
+static int map_update_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	void __user *uvalue = u64_to_ptr(attr->value);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key, *value;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	err = -ENOMEM;
+	value = kmalloc(map->value_size, GFP_USER);
+	if (!value)
+		goto free_key;
+
+	err = -EFAULT;
+	if (copy_from_user(value, uvalue, map->value_size) != 0)
+		goto free_value;
+
+	/* eBPF program that use maps are running under rcu_read_lock(),
+	 * therefore all map accessors rely on this fact, so do the same here
+	 */
+	rcu_read_lock();
+	err = map->ops->map_update_elem(map, key, value);
+	rcu_read_unlock();
+
+free_value:
+	kfree(value);
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
+#define BPF_MAP_DELETE_ELEM_LAST_FIELD key
+
+static int map_delete_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	rcu_read_lock();
+	err = map->ops->map_delete_elem(map, key);
+	rcu_read_unlock();
+
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key
+
+static int map_get_next_key(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	void __user *unext_key = u64_to_ptr(attr->next_key);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key, *next_key;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	err = -ENOMEM;
+	next_key = kmalloc(map->key_size, GFP_USER);
+	if (!next_key)
+		goto free_key;
+
+	rcu_read_lock();
+	err = map->ops->map_get_next_key(map, key, next_key);
+	rcu_read_unlock();
+	if (err)
+		goto free_next_key;
+
+	err = -EFAULT;
+	if (copy_to_user(unext_key, next_key, map->key_size) != 0)
+		goto free_next_key;
+
+	err = 0;
+
+free_next_key:
+	kfree(next_key);
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -160,6 +383,18 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_MAP_CREATE:
 		err = map_create(&attr);
 		break;
+	case BPF_MAP_LOOKUP_ELEM:
+		err = map_lookup_elem(&attr);
+		break;
+	case BPF_MAP_UPDATE_ELEM:
+		err = map_update_elem(&attr);
+		break;
+	case BPF_MAP_DELETE_ELEM:
+		err = map_delete_elem(&attr);
+		break;
+	case BPF_MAP_GET_NEXT_KEY:
+		err = map_get_next_key(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 09756af46893c18839062976c3252e93a1beeba7 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:17:00 -0700
Subject: bpf: expand BPF syscall with program load/unload

eBPF programs are similar to kernel modules. They are loaded by the user
process and automatically unloaded when process exits. Each eBPF program is
a safe run-to-completion set of instructions. eBPF verifier statically
determines that the program terminates and is safe to execute.

The following syscall wrapper can be used to load the program:
int bpf_prog_load(enum bpf_prog_type prog_type,
                  const struct bpf_insn *insns, int insn_cnt,
                  const char *license)
{
    union bpf_attr attr = {
        .prog_type = prog_type,
        .insns = ptr_to_u64(insns),
        .insn_cnt = insn_cnt,
        .license = ptr_to_u64(license),
    };

    return bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}
where 'insns' is an array of eBPF instructions and 'license' is a string
that must be GPL compatible to call helper functions marked gpl_only

Upon succesful load the syscall returns prog_fd.
Use close(prog_fd) to unload the program.

User space tests and examples follow in the later patches

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h      |  38 +++++++++++
 include/linux/filter.h   |   8 +--
 include/uapi/linux/bpf.h |  26 ++++++++
 kernel/bpf/core.c        |  29 +++++----
 kernel/bpf/syscall.c     | 165 +++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 246 insertions(+), 20 deletions(-)

(limited to 'include/uapi/linux/bpf.h')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2887f3f9da59..92979182be81 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,4 +46,42 @@ void bpf_register_map_type(struct bpf_map_type_list *tl);
 void bpf_map_put(struct bpf_map *map);
 struct bpf_map *bpf_map_get(struct fd f);
 
+/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
+ * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
+ * instructions after verifying
+ */
+struct bpf_func_proto {
+	u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+	bool gpl_only;
+};
+
+struct bpf_verifier_ops {
+	/* return eBPF function prototype for verification */
+	const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+};
+
+struct bpf_prog_type_list {
+	struct list_head list_node;
+	struct bpf_verifier_ops *ops;
+	enum bpf_prog_type type;
+};
+
+void bpf_register_prog_type(struct bpf_prog_type_list *tl);
+
+struct bpf_prog;
+
+struct bpf_prog_aux {
+	atomic_t refcnt;
+	bool is_gpl_compatible;
+	enum bpf_prog_type prog_type;
+	struct bpf_verifier_ops *ops;
+	struct bpf_map **used_maps;
+	u32 used_map_cnt;
+	struct bpf_prog *prog;
+	struct work_struct work;
+};
+
+void bpf_prog_put(struct bpf_prog *prog);
+struct bpf_prog *bpf_prog_get(u32 ufd);
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1a0bc6d134d7..4ffc0958d85e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -21,6 +21,7 @@
 struct sk_buff;
 struct sock;
 struct seccomp_data;
+struct bpf_prog_aux;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -300,17 +301,12 @@ struct bpf_binary_header {
 	u8 image[];
 };
 
-struct bpf_work_struct {
-	struct bpf_prog *prog;
-	struct work_struct work;
-};
-
 struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	bool			jited;		/* Is our filter JIT'ed? */
 	u32			len;		/* Number of filter blocks */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
-	struct bpf_work_struct	*work;		/* Deferred free work struct */
+	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
 					    const struct bpf_insn *filter);
 	/* Instructions for interpreter */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 395cabd2ca0a..424f442016e7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -99,12 +99,23 @@ enum bpf_cmd {
 	 * returns zero and stores next key or negative error
 	 */
 	BPF_MAP_GET_NEXT_KEY,
+
+	/* verify and load eBPF program
+	 * prog_fd = bpf(BPF_PROG_LOAD, union bpf_attr *attr, u32 size)
+	 * Using attr->prog_type, attr->insns, attr->license
+	 * returns fd or negative error
+	 */
+	BPF_PROG_LOAD,
 };
 
 enum bpf_map_type {
 	BPF_MAP_TYPE_UNSPEC,
 };
 
+enum bpf_prog_type {
+	BPF_PROG_TYPE_UNSPEC,
+};
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -121,6 +132,21 @@ union bpf_attr {
 			__aligned_u64 next_key;
 		};
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_LOAD command */
+		__u32		prog_type;	/* one of enum bpf_prog_type */
+		__u32		insn_cnt;
+		__aligned_u64	insns;
+		__aligned_u64	license;
+	};
 } __attribute__((aligned(8)));
 
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+	BPF_FUNC_unspec,
+	__BPF_FUNC_MAX_ID,
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8b7002488251..f0c30c59b317 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -27,6 +27,7 @@
 #include <linux/random.h>
 #include <linux/moduleloader.h>
 #include <asm/unaligned.h>
+#include <linux/bpf.h>
 
 /* Registers */
 #define BPF_R0	regs[BPF_REG_0]
@@ -71,7 +72,7 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 {
 	gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
 			  gfp_extra_flags;
-	struct bpf_work_struct *ws;
+	struct bpf_prog_aux *aux;
 	struct bpf_prog *fp;
 
 	size = round_up(size, PAGE_SIZE);
@@ -79,14 +80,14 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 	if (fp == NULL)
 		return NULL;
 
-	ws = kmalloc(sizeof(*ws), GFP_KERNEL | gfp_extra_flags);
-	if (ws == NULL) {
+	aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
+	if (aux == NULL) {
 		vfree(fp);
 		return NULL;
 	}
 
 	fp->pages = size / PAGE_SIZE;
-	fp->work = ws;
+	fp->aux = aux;
 
 	return fp;
 }
@@ -110,10 +111,10 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 		memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
 		fp->pages = size / PAGE_SIZE;
 
-		/* We keep fp->work from fp_old around in the new
+		/* We keep fp->aux from fp_old around in the new
 		 * reallocated structure.
 		 */
-		fp_old->work = NULL;
+		fp_old->aux = NULL;
 		__bpf_prog_free(fp_old);
 	}
 
@@ -123,7 +124,7 @@ EXPORT_SYMBOL_GPL(bpf_prog_realloc);
 
 void __bpf_prog_free(struct bpf_prog *fp)
 {
-	kfree(fp->work);
+	kfree(fp->aux);
 	vfree(fp);
 }
 EXPORT_SYMBOL_GPL(__bpf_prog_free);
@@ -638,19 +639,19 @@ EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
-	struct bpf_work_struct *ws;
+	struct bpf_prog_aux *aux;
 
-	ws = container_of(work, struct bpf_work_struct, work);
-	bpf_jit_free(ws->prog);
+	aux = container_of(work, struct bpf_prog_aux, work);
+	bpf_jit_free(aux->prog);
 }
 
 /* Free internal BPF program */
 void bpf_prog_free(struct bpf_prog *fp)
 {
-	struct bpf_work_struct *ws = fp->work;
+	struct bpf_prog_aux *aux = fp->aux;
 
-	INIT_WORK(&ws->work, bpf_prog_free_deferred);
-	ws->prog = fp;
-	schedule_work(&ws->work);
+	INIT_WORK(&aux->work, bpf_prog_free_deferred);
+	aux->prog = fp;
+	schedule_work(&aux->work);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_free);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f94349ecaf61..0afb4eaa1887 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -14,6 +14,8 @@
 #include <linux/slab.h>
 #include <linux/anon_inodes.h>
 #include <linux/file.h>
+#include <linux/license.h>
+#include <linux/filter.h>
 
 static LIST_HEAD(bpf_map_types);
 
@@ -334,6 +336,166 @@ err_put:
 	return err;
 }
 
+static LIST_HEAD(bpf_prog_types);
+
+static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
+{
+	struct bpf_prog_type_list *tl;
+
+	list_for_each_entry(tl, &bpf_prog_types, list_node) {
+		if (tl->type == type) {
+			prog->aux->ops = tl->ops;
+			prog->aux->prog_type = type;
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
+
+void bpf_register_prog_type(struct bpf_prog_type_list *tl)
+{
+	list_add(&tl->list_node, &bpf_prog_types);
+}
+
+/* drop refcnt on maps used by eBPF program and free auxilary data */
+static void free_used_maps(struct bpf_prog_aux *aux)
+{
+	int i;
+
+	for (i = 0; i < aux->used_map_cnt; i++)
+		bpf_map_put(aux->used_maps[i]);
+
+	kfree(aux->used_maps);
+}
+
+void bpf_prog_put(struct bpf_prog *prog)
+{
+	if (atomic_dec_and_test(&prog->aux->refcnt)) {
+		free_used_maps(prog->aux);
+		bpf_prog_free(prog);
+	}
+}
+
+static int bpf_prog_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_prog *prog = filp->private_data;
+
+	bpf_prog_put(prog);
+	return 0;
+}
+
+static const struct file_operations bpf_prog_fops = {
+        .release = bpf_prog_release,
+};
+
+static struct bpf_prog *get_prog(struct fd f)
+{
+	struct bpf_prog *prog;
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	if (f.file->f_op != &bpf_prog_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	prog = f.file->private_data;
+
+	return prog;
+}
+
+/* called by sockets/tracing/seccomp before attaching program to an event
+ * pairs with bpf_prog_put()
+ */
+struct bpf_prog *bpf_prog_get(u32 ufd)
+{
+	struct fd f = fdget(ufd);
+	struct bpf_prog *prog;
+
+	prog = get_prog(f);
+
+	if (IS_ERR(prog))
+		return prog;
+
+	atomic_inc(&prog->aux->refcnt);
+	fdput(f);
+	return prog;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define	BPF_PROG_LOAD_LAST_FIELD license
+
+static int bpf_prog_load(union bpf_attr *attr)
+{
+	enum bpf_prog_type type = attr->prog_type;
+	struct bpf_prog *prog;
+	int err;
+	char license[128];
+	bool is_gpl;
+
+	if (CHECK_ATTR(BPF_PROG_LOAD))
+		return -EINVAL;
+
+	/* copy eBPF program license from user space */
+	if (strncpy_from_user(license, u64_to_ptr(attr->license),
+			      sizeof(license) - 1) < 0)
+		return -EFAULT;
+	license[sizeof(license) - 1] = 0;
+
+	/* eBPF programs must be GPL compatible to use GPL-ed functions */
+	is_gpl = license_is_gpl_compatible(license);
+
+	if (attr->insn_cnt >= BPF_MAXINSNS)
+		return -EINVAL;
+
+	/* plain bpf_prog allocation */
+	prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
+	if (!prog)
+		return -ENOMEM;
+
+	prog->len = attr->insn_cnt;
+
+	err = -EFAULT;
+	if (copy_from_user(prog->insns, u64_to_ptr(attr->insns),
+			   prog->len * sizeof(struct bpf_insn)) != 0)
+		goto free_prog;
+
+	prog->orig_prog = NULL;
+	prog->jited = false;
+
+	atomic_set(&prog->aux->refcnt, 1);
+	prog->aux->is_gpl_compatible = is_gpl;
+
+	/* find program type: socket_filter vs tracing_filter */
+	err = find_prog_type(type, prog);
+	if (err < 0)
+		goto free_prog;
+
+	/* run eBPF verifier */
+	/* err = bpf_check(prog, tb); */
+
+	if (err < 0)
+		goto free_used_maps;
+
+	/* eBPF program is ready to be JITed */
+	bpf_prog_select_runtime(prog);
+
+	err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
+
+	if (err < 0)
+		/* failed to allocate fd */
+		goto free_used_maps;
+
+	return err;
+
+free_used_maps:
+	free_used_maps(prog->aux);
+free_prog:
+	bpf_prog_free(prog);
+	return err;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -395,6 +557,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_MAP_GET_NEXT_KEY:
 		err = map_get_next_key(&attr);
 		break;
+	case BPF_PROG_LOAD:
+		err = bpf_prog_load(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
-- 
cgit v1.2.3


From cbd357008604925355ae7b54a09137dabb81b580 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:17:03 -0700
Subject: bpf: verifier (add ability to receive verification log)

add optional attributes for BPF_PROG_LOAD syscall:
union bpf_attr {
    struct {
	...
	__u32         log_level; /* verbosity level of eBPF verifier */
	__u32         log_size;  /* size of user buffer */
	__aligned_u64 log_buf;   /* user supplied 'char *buffer' */
    };
};

when log_level > 0 the verifier will return its verification log in the user
supplied buffer 'log_buf' which can be used by program author to analyze why
verifier rejected given program.

'Understanding eBPF verifier messages' section of Documentation/networking/filter.txt
provides several examples of these messages, like the program:

  BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
  BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
  BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
  BPF_LD_MAP_FD(BPF_REG_1, 0),
  BPF_CALL_FUNC(BPF_FUNC_map_lookup_elem),
  BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
  BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
  BPF_EXIT_INSN(),

will be rejected with the following multi-line message in log_buf:

  0: (7a) *(u64 *)(r10 -8) = 0
  1: (bf) r2 = r10
  2: (07) r2 += -8
  3: (b7) r1 = 0
  4: (85) call 1
  5: (15) if r0 == 0x0 goto pc+1
   R0=map_ptr R10=fp
  6: (7a) *(u64 *)(r0 +4) = 0
  misaligned access off 4 size 8

The format of the output can change at any time as verifier evolves.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h |   3 +
 kernel/bpf/syscall.c     |   2 +-
 kernel/bpf/verifier.c    | 235 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 239 insertions(+), 1 deletion(-)

(limited to 'include/uapi/linux/bpf.h')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 424f442016e7..31b0ac208a52 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -138,6 +138,9 @@ union bpf_attr {
 		__u32		insn_cnt;
 		__aligned_u64	insns;
 		__aligned_u64	license;
+		__u32		log_level;	/* verbosity level of verifier */
+		__u32		log_size;	/* size of user buffer */
+		__aligned_u64	log_buf;	/* user supplied buffer */
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 74b3628c5fdb..ba61c8c16032 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -458,7 +458,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD license
+#define	BPF_PROG_LOAD_LAST_FIELD log_buf
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d6f9c3d6b4d7..871edc1f2e1f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -125,9 +125,244 @@
  * are set to NOT_INIT to indicate that they are no longer readable.
  */
 
+/* single container for all structs
+ * one verifier_env per bpf_check() call
+ */
+struct verifier_env {
+};
+
+/* verbose verifier prints what it's seeing
+ * bpf_check() is called under lock, so no race to access these global vars
+ */
+static u32 log_level, log_size, log_len;
+static char *log_buf;
+
+static DEFINE_MUTEX(bpf_verifier_lock);
+
+/* log_level controls verbosity level of eBPF verifier.
+ * verbose() is used to dump the verification trace to the log, so the user
+ * can figure out what's wrong with the program
+ */
+static void verbose(const char *fmt, ...)
+{
+	va_list args;
+
+	if (log_level == 0 || log_len >= log_size - 1)
+		return;
+
+	va_start(args, fmt);
+	log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args);
+	va_end(args);
+}
+
+static const char *const bpf_class_string[] = {
+	[BPF_LD]    = "ld",
+	[BPF_LDX]   = "ldx",
+	[BPF_ST]    = "st",
+	[BPF_STX]   = "stx",
+	[BPF_ALU]   = "alu",
+	[BPF_JMP]   = "jmp",
+	[BPF_RET]   = "BUG",
+	[BPF_ALU64] = "alu64",
+};
+
+static const char *const bpf_alu_string[] = {
+	[BPF_ADD >> 4]  = "+=",
+	[BPF_SUB >> 4]  = "-=",
+	[BPF_MUL >> 4]  = "*=",
+	[BPF_DIV >> 4]  = "/=",
+	[BPF_OR  >> 4]  = "|=",
+	[BPF_AND >> 4]  = "&=",
+	[BPF_LSH >> 4]  = "<<=",
+	[BPF_RSH >> 4]  = ">>=",
+	[BPF_NEG >> 4]  = "neg",
+	[BPF_MOD >> 4]  = "%=",
+	[BPF_XOR >> 4]  = "^=",
+	[BPF_MOV >> 4]  = "=",
+	[BPF_ARSH >> 4] = "s>>=",
+	[BPF_END >> 4]  = "endian",
+};
+
+static const char *const bpf_ldst_string[] = {
+	[BPF_W >> 3]  = "u32",
+	[BPF_H >> 3]  = "u16",
+	[BPF_B >> 3]  = "u8",
+	[BPF_DW >> 3] = "u64",
+};
+
+static const char *const bpf_jmp_string[] = {
+	[BPF_JA >> 4]   = "jmp",
+	[BPF_JEQ >> 4]  = "==",
+	[BPF_JGT >> 4]  = ">",
+	[BPF_JGE >> 4]  = ">=",
+	[BPF_JSET >> 4] = "&",
+	[BPF_JNE >> 4]  = "!=",
+	[BPF_JSGT >> 4] = "s>",
+	[BPF_JSGE >> 4] = "s>=",
+	[BPF_CALL >> 4] = "call",
+	[BPF_EXIT >> 4] = "exit",
+};
+
+static void print_bpf_insn(struct bpf_insn *insn)
+{
+	u8 class = BPF_CLASS(insn->code);
+
+	if (class == BPF_ALU || class == BPF_ALU64) {
+		if (BPF_SRC(insn->code) == BPF_X)
+			verbose("(%02x) %sr%d %s %sr%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->src_reg);
+		else
+			verbose("(%02x) %sr%d %s %s%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->imm);
+	} else if (class == BPF_STX) {
+		if (BPF_MODE(insn->code) == BPF_MEM)
+			verbose("(%02x) *(%s *)(r%d %+d) = r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg,
+				insn->off, insn->src_reg);
+		else if (BPF_MODE(insn->code) == BPF_XADD)
+			verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg, insn->off,
+				insn->src_reg);
+		else
+			verbose("BUG_%02x\n", insn->code);
+	} else if (class == BPF_ST) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose("BUG_st_%02x\n", insn->code);
+			return;
+		}
+		verbose("(%02x) *(%s *)(r%d %+d) = %d\n",
+			insn->code,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->dst_reg,
+			insn->off, insn->imm);
+	} else if (class == BPF_LDX) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose("BUG_ldx_%02x\n", insn->code);
+			return;
+		}
+		verbose("(%02x) r%d = *(%s *)(r%d %+d)\n",
+			insn->code, insn->dst_reg,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->src_reg, insn->off);
+	} else if (class == BPF_LD) {
+		if (BPF_MODE(insn->code) == BPF_ABS) {
+			verbose("(%02x) r0 = *(%s *)skb[%d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IND) {
+			verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->src_reg, insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IMM) {
+			verbose("(%02x) r%d = 0x%x\n",
+				insn->code, insn->dst_reg, insn->imm);
+		} else {
+			verbose("BUG_ld_%02x\n", insn->code);
+			return;
+		}
+	} else if (class == BPF_JMP) {
+		u8 opcode = BPF_OP(insn->code);
+
+		if (opcode == BPF_CALL) {
+			verbose("(%02x) call %d\n", insn->code, insn->imm);
+		} else if (insn->code == (BPF_JMP | BPF_JA)) {
+			verbose("(%02x) goto pc%+d\n",
+				insn->code, insn->off);
+		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
+			verbose("(%02x) exit\n", insn->code);
+		} else if (BPF_SRC(insn->code) == BPF_X) {
+			verbose("(%02x) if r%d %s r%d goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->src_reg, insn->off);
+		} else {
+			verbose("(%02x) if r%d %s 0x%x goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->imm, insn->off);
+		}
+	} else {
+		verbose("(%02x) %s\n", insn->code, bpf_class_string[class]);
+	}
+}
+
 int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 {
+	char __user *log_ubuf = NULL;
+	struct verifier_env *env;
 	int ret = -EINVAL;
 
+	if (prog->len <= 0 || prog->len > BPF_MAXINSNS)
+		return -E2BIG;
+
+	/* 'struct verifier_env' can be global, but since it's not small,
+	 * allocate/free it every time bpf_check() is called
+	 */
+	env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL);
+	if (!env)
+		return -ENOMEM;
+
+	/* grab the mutex to protect few globals used by verifier */
+	mutex_lock(&bpf_verifier_lock);
+
+	if (attr->log_level || attr->log_buf || attr->log_size) {
+		/* user requested verbose verifier output
+		 * and supplied buffer to store the verification trace
+		 */
+		log_level = attr->log_level;
+		log_ubuf = (char __user *) (unsigned long) attr->log_buf;
+		log_size = attr->log_size;
+		log_len = 0;
+
+		ret = -EINVAL;
+		/* log_* values have to be sane */
+		if (log_size < 128 || log_size > UINT_MAX >> 8 ||
+		    log_level == 0 || log_ubuf == NULL)
+			goto free_env;
+
+		ret = -ENOMEM;
+		log_buf = vmalloc(log_size);
+		if (!log_buf)
+			goto free_env;
+	} else {
+		log_level = 0;
+	}
+
+	/* ret = do_check(env); */
+
+	if (log_level && log_len >= log_size - 1) {
+		BUG_ON(log_len >= log_size);
+		/* verifier log exceeded user supplied buffer */
+		ret = -ENOSPC;
+		/* fall through to return what was recorded */
+	}
+
+	/* copy verifier log back to user space including trailing zero */
+	if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) {
+		ret = -EFAULT;
+		goto free_log_buf;
+	}
+
+
+free_log_buf:
+	if (log_level)
+		vfree(log_buf);
+free_env:
+	kfree(env);
+	mutex_unlock(&bpf_verifier_lock);
 	return ret;
 }
-- 
cgit v1.2.3


From c15952dc18d8a293d976ac6c06d44d9d98023b45 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Tue, 14 Oct 2014 02:08:54 -0700
Subject: net: filter: move common defines into bpf_common.h

userspace programs that use eBPF instruction macros need to include two files:
uapi/linux/filter.h and uapi/linux/bpf.h
Move common macro definitions that are shared between classic BPF and eBPF
into uapi/linux/bpf_common.h, so that user app can include only one bpf.h file

Cc: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild       |  1 +
 include/uapi/linux/bpf.h        |  1 +
 include/uapi/linux/bpf_common.h | 55 ++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/filter.h     | 56 +----------------------------------------
 4 files changed, 58 insertions(+), 55 deletions(-)
 create mode 100644 include/uapi/linux/bpf_common.h

(limited to 'include/uapi/linux/bpf.h')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 70e150ebc6c9..1115d68b150f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -68,6 +68,7 @@ header-y += binfmts.h
 header-y += blkpg.h
 header-y += blktrace_api.h
 header-y += bpf.h
+header-y += bpf_common.h
 header-y += bpqether.h
 header-y += bsg.h
 header-y += btrfs.h
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 31b0ac208a52..d18316f9e9c4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -8,6 +8,7 @@
 #define _UAPI__LINUX_BPF_H__
 
 #include <linux/types.h>
+#include <linux/bpf_common.h>
 
 /* Extended instruction set based on top of classic BPF */
 
diff --git a/include/uapi/linux/bpf_common.h b/include/uapi/linux/bpf_common.h
new file mode 100644
index 000000000000..a5c220e0828f
--- /dev/null
+++ b/include/uapi/linux/bpf_common.h
@@ -0,0 +1,55 @@
+#ifndef _UAPI__LINUX_BPF_COMMON_H__
+#define _UAPI__LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define		BPF_LD		0x00
+#define		BPF_LDX		0x01
+#define		BPF_ST		0x02
+#define		BPF_STX		0x03
+#define		BPF_ALU		0x04
+#define		BPF_JMP		0x05
+#define		BPF_RET		0x06
+#define		BPF_MISC        0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code)  ((code) & 0x18)
+#define		BPF_W		0x00
+#define		BPF_H		0x08
+#define		BPF_B		0x10
+#define BPF_MODE(code)  ((code) & 0xe0)
+#define		BPF_IMM		0x00
+#define		BPF_ABS		0x20
+#define		BPF_IND		0x40
+#define		BPF_MEM		0x60
+#define		BPF_LEN		0x80
+#define		BPF_MSH		0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code)    ((code) & 0xf0)
+#define		BPF_ADD		0x00
+#define		BPF_SUB		0x10
+#define		BPF_MUL		0x20
+#define		BPF_DIV		0x30
+#define		BPF_OR		0x40
+#define		BPF_AND		0x50
+#define		BPF_LSH		0x60
+#define		BPF_RSH		0x70
+#define		BPF_NEG		0x80
+#define		BPF_MOD		0x90
+#define		BPF_XOR		0xa0
+
+#define		BPF_JA		0x00
+#define		BPF_JEQ		0x10
+#define		BPF_JGT		0x20
+#define		BPF_JGE		0x30
+#define		BPF_JSET        0x40
+#define BPF_SRC(code)   ((code) & 0x08)
+#define		BPF_K		0x00
+#define		BPF_X		0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* _UAPI__LINUX_BPF_COMMON_H__ */
diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h
index 253b4d42cf2b..47785d5ecf17 100644
--- a/include/uapi/linux/filter.h
+++ b/include/uapi/linux/filter.h
@@ -7,7 +7,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-
+#include <linux/bpf_common.h>
 
 /*
  * Current version of the filter code architecture.
@@ -32,56 +32,6 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 	struct sock_filter __user *filter;
 };
 
-/*
- * Instruction classes
- */
-
-#define BPF_CLASS(code) ((code) & 0x07)
-#define         BPF_LD          0x00
-#define         BPF_LDX         0x01
-#define         BPF_ST          0x02
-#define         BPF_STX         0x03
-#define         BPF_ALU         0x04
-#define         BPF_JMP         0x05
-#define         BPF_RET         0x06
-#define         BPF_MISC        0x07
-
-/* ld/ldx fields */
-#define BPF_SIZE(code)  ((code) & 0x18)
-#define         BPF_W           0x00
-#define         BPF_H           0x08
-#define         BPF_B           0x10
-#define BPF_MODE(code)  ((code) & 0xe0)
-#define         BPF_IMM         0x00
-#define         BPF_ABS         0x20
-#define         BPF_IND         0x40
-#define         BPF_MEM         0x60
-#define         BPF_LEN         0x80
-#define         BPF_MSH         0xa0
-
-/* alu/jmp fields */
-#define BPF_OP(code)    ((code) & 0xf0)
-#define         BPF_ADD         0x00
-#define         BPF_SUB         0x10
-#define         BPF_MUL         0x20
-#define         BPF_DIV         0x30
-#define         BPF_OR          0x40
-#define         BPF_AND         0x50
-#define         BPF_LSH         0x60
-#define         BPF_RSH         0x70
-#define         BPF_NEG         0x80
-#define		BPF_MOD		0x90
-#define		BPF_XOR		0xa0
-
-#define         BPF_JA          0x00
-#define         BPF_JEQ         0x10
-#define         BPF_JGT         0x20
-#define         BPF_JGE         0x30
-#define         BPF_JSET        0x40
-#define BPF_SRC(code)   ((code) & 0x08)
-#define         BPF_K           0x00
-#define         BPF_X           0x08
-
 /* ret - BPF_K and BPF_X also apply */
 #define BPF_RVAL(code)  ((code) & 0x18)
 #define         BPF_A           0x10
@@ -91,10 +41,6 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 #define         BPF_TAX         0x00
 #define         BPF_TXA         0x80
 
-#ifndef BPF_MAXINSNS
-#define BPF_MAXINSNS 4096
-#endif
-
 /*
  * Macros for filter block array initializers.
  */
-- 
cgit v1.2.3