From e8c423fb31fa8b1ef6d7cd14a168de33e7c0d702 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:24:55 -0700
Subject: bpf: Add typecast to raw_tracepoints to help BTF generation

When pahole converts dwarf to btf it emits only used types.
Wrap existing __bpf_trace_##template() function into
btf_trace_##template typedef and use it in type cast to
make gcc emits this type into dwarf. Then pahole will convert it to btf.
The "btf_trace_" prefix will be used to identify BTF enabled raw tracepoints.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-2-ast@kernel.org
---
 include/trace/bpf_probe.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
index d6e556c0a085..b04c29270973 100644
--- a/include/trace/bpf_probe.h
+++ b/include/trace/bpf_probe.h
@@ -74,11 +74,12 @@ static inline void bpf_test_probe_##call(void)				\
 {									\
 	check_trace_callback_type_##call(__bpf_trace_##template);	\
 }									\
+typedef void (*btf_trace_##call)(void *__data, proto);			\
 static struct bpf_raw_event_map	__used					\
 	__attribute__((section("__bpf_raw_tp_map")))			\
 __bpf_trace_tp_map_##call = {						\
 	.tp		= &__tracepoint_##call,				\
-	.bpf_func	= (void *)__bpf_trace_##template,		\
+	.bpf_func	= (void *)(btf_trace_##call)__bpf_trace_##template,	\
 	.num_args	= COUNT_ARGS(args),				\
 	.writable_size	= size,						\
 };
-- 
cgit v1.2.3


From 7c6a469e3416fa23568c2395a3faa7dd6e376dcb Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:24:56 -0700
Subject: bpf: Add typecast to bpf helpers to help BTF generation

When pahole converts dwarf to btf it emits only used types.
Wrap existing bpf helper functions into typedef and use it in
typecast to make gcc emits this type into dwarf.
Then pahole will convert it to btf.
The "btf_#name_of_helper" types will be used to figure out
types of arguments of bpf helpers.
The generated code before and after is the same.
Only dwarf and btf sections are different.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-3-ast@kernel.org
---
 include/linux/filter.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 2ce57645f3cd..d3d51d7aff2c 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -464,10 +464,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 #define BPF_CALL_x(x, name, ...)					       \
 	static __always_inline						       \
 	u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__));   \
+	typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \
 	u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__));	       \
 	u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__))	       \
 	{								       \
-		return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\
+		return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\
 	}								       \
 	static __always_inline						       \
 	u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__))
-- 
cgit v1.2.3


From 8580ac9404f6240668a026785d7d8856f0530409 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:24:57 -0700
Subject: bpf: Process in-kernel BTF

If in-kernel BTF exists parse it and prepare 'struct btf *btf_vmlinux'
for further use by the verifier.
In-kernel BTF is trusted just like kallsyms and other build artifacts
embedded into vmlinux.
Yet run this BTF image through BTF verifier to make sure
that it is valid and it wasn't mangled during the build.
If in-kernel BTF is incorrect it means either gcc or pahole or kernel
are buggy. In such case disallow loading BPF programs.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-4-ast@kernel.org
---
 include/linux/bpf_verifier.h |  4 ++-
 include/linux/btf.h          |  1 +
 kernel/bpf/btf.c             | 71 +++++++++++++++++++++++++++++++++++++++++++-
 kernel/bpf/verifier.c        | 20 +++++++++++++
 4 files changed, 94 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 26a6d58ca78c..713efae62e96 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -330,10 +330,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
 #define BPF_LOG_STATS	4
 #define BPF_LOG_LEVEL	(BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
 #define BPF_LOG_MASK	(BPF_LOG_LEVEL | BPF_LOG_STATS)
+#define BPF_LOG_KERNEL	(BPF_LOG_MASK + 1) /* kernel internal flag */
 
 static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 {
-	return log->level && log->ubuf && !bpf_verifier_log_full(log);
+	return (log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
+		log->level == BPF_LOG_KERNEL;
 }
 
 #define BPF_MAX_SUBPROGS 256
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 64cdf2a23d42..55d43bc856be 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -56,6 +56,7 @@ bool btf_type_is_void(const struct btf_type *t);
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
+struct btf *btf_parse_vmlinux(void);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 29c7c06c6bd6..ddeab1e8d21e 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -698,6 +698,13 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
 	if (!bpf_verifier_log_needed(log))
 		return;
 
+	/* btf verifier prints all types it is processing via
+	 * btf_verifier_log_type(..., fmt = NULL).
+	 * Skip those prints for in-kernel BTF verification.
+	 */
+	if (log->level == BPF_LOG_KERNEL && !fmt)
+		return;
+
 	__btf_verifier_log(log, "[%u] %s %s%s",
 			   env->log_type_id,
 			   btf_kind_str[kind],
@@ -735,6 +742,8 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
 	if (!bpf_verifier_log_needed(log))
 		return;
 
+	if (log->level == BPF_LOG_KERNEL && !fmt)
+		return;
 	/* The CHECK_META phase already did a btf dump.
 	 *
 	 * If member is logged again, it must hit an error in
@@ -777,6 +786,8 @@ static void btf_verifier_log_vsi(struct btf_verifier_env *env,
 
 	if (!bpf_verifier_log_needed(log))
 		return;
+	if (log->level == BPF_LOG_KERNEL && !fmt)
+		return;
 	if (env->phase != CHECK_META)
 		btf_verifier_log_type(env, datasec_type, NULL);
 
@@ -802,6 +813,8 @@ static void btf_verifier_log_hdr(struct btf_verifier_env *env,
 	if (!bpf_verifier_log_needed(log))
 		return;
 
+	if (log->level == BPF_LOG_KERNEL)
+		return;
 	hdr = &btf->hdr;
 	__btf_verifier_log(log, "magic: 0x%x\n", hdr->magic);
 	__btf_verifier_log(log, "version: %u\n", hdr->version);
@@ -2405,7 +2418,8 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
-
+		if (env->log.level == BPF_LOG_KERNEL)
+			continue;
 		btf_verifier_log(env, "\t%s val=%d\n",
 				 __btf_name_by_offset(btf, enums[i].name_off),
 				 enums[i].val);
@@ -3367,6 +3381,61 @@ errout:
 	return ERR_PTR(err);
 }
 
+extern char __weak _binary__btf_vmlinux_bin_start[];
+extern char __weak _binary__btf_vmlinux_bin_end[];
+
+struct btf *btf_parse_vmlinux(void)
+{
+	struct btf_verifier_env *env = NULL;
+	struct bpf_verifier_log *log;
+	struct btf *btf = NULL;
+	int err;
+
+	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
+	if (!env)
+		return ERR_PTR(-ENOMEM);
+
+	log = &env->log;
+	log->level = BPF_LOG_KERNEL;
+
+	btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
+	if (!btf) {
+		err = -ENOMEM;
+		goto errout;
+	}
+	env->btf = btf;
+
+	btf->data = _binary__btf_vmlinux_bin_start;
+	btf->data_size = _binary__btf_vmlinux_bin_end -
+		_binary__btf_vmlinux_bin_start;
+
+	err = btf_parse_hdr(env);
+	if (err)
+		goto errout;
+
+	btf->nohdr_data = btf->data + btf->hdr.hdr_len;
+
+	err = btf_parse_str_sec(env);
+	if (err)
+		goto errout;
+
+	err = btf_check_all_metas(env);
+	if (err)
+		goto errout;
+
+	btf_verifier_env_free(env);
+	refcount_set(&btf->refcnt, 1);
+	return btf;
+
+errout:
+	btf_verifier_env_free(env);
+	if (btf) {
+		kvfree(btf->types);
+		kfree(btf);
+	}
+	return ERR_PTR(err);
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d3446f018b9a..466b3b19de4d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -207,6 +207,8 @@ struct bpf_call_arg_meta {
 	int func_id;
 };
 
+struct btf *btf_vmlinux;
+
 static DEFINE_MUTEX(bpf_verifier_lock);
 
 static const struct bpf_line_info *
@@ -243,6 +245,10 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
 	n = min(log->len_total - log->len_used - 1, n);
 	log->kbuf[n] = '\0';
 
+	if (log->level == BPF_LOG_KERNEL) {
+		pr_err("BPF:%s\n", log->kbuf);
+		return;
+	}
 	if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
 		log->len_used += n;
 	else
@@ -9294,6 +9300,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	env->ops = bpf_verifier_ops[env->prog->type];
 	is_priv = capable(CAP_SYS_ADMIN);
 
+	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
+		mutex_lock(&bpf_verifier_lock);
+		if (!btf_vmlinux)
+			btf_vmlinux = btf_parse_vmlinux();
+		mutex_unlock(&bpf_verifier_lock);
+	}
+
 	/* grab the mutex to protect few globals used by verifier */
 	if (!is_priv)
 		mutex_lock(&bpf_verifier_lock);
@@ -9313,6 +9326,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 			goto err_unlock;
 	}
 
+	if (IS_ERR(btf_vmlinux)) {
+		/* Either gcc or pahole or kernel are broken. */
+		verbose(env, "in-kernel BTF is malformed\n");
+		ret = PTR_ERR(btf_vmlinux);
+		goto err_unlock;
+	}
+
 	env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
 		env->strict_alignment = true;
-- 
cgit v1.2.3


From ccfe29eb29c2edcea6552072ef00ff4117f53e83 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:24:58 -0700
Subject: bpf: Add attach_btf_id attribute to program load

Add attach_btf_id attribute to prog_load command.
It's similar to existing expected_attach_type attribute which is
used in several cgroup based program types.
Unfortunately expected_attach_type is ignored for
tracing programs and cannot be reused for new purpose.
Hence introduce attach_btf_id to verify bpf programs against
given in-kernel BTF type id at load time.
It is strictly checked to be valid for raw_tp programs only.
In a later patches it will become:
btf_id == 0 semantics of existing raw_tp progs.
btd_id > 0 raw_tp with BTF and additional type safety.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-5-ast@kernel.org
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           | 18 ++++++++++++++----
 tools/include/uapi/linux/bpf.h |  1 +
 4 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 282e28bf41ec..f916380675dd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -375,6 +375,7 @@ struct bpf_prog_aux {
 	u32 id;
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
+	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	struct bpf_prog **func;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a65c3b0c6935..3bb2cd1de341 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -420,6 +420,7 @@ union bpf_attr {
 		__u32		line_info_rec_size;	/* userspace bpf_line_info size */
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
+		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 82eabd4e38ad..b56c482c9760 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -23,6 +23,7 @@
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
 #include <linux/nospec.h>
+#include <uapi/linux/btf.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
 			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -1565,8 +1566,9 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 }
 
 static int
-bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
-				enum bpf_attach_type expected_attach_type)
+bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
+			   enum bpf_attach_type expected_attach_type,
+			   u32 btf_id)
 {
 	switch (prog_type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -1608,13 +1610,19 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+		if (btf_id > BTF_MAX_TYPE)
+			return -EINVAL;
+		return 0;
 	default:
+		if (btf_id)
+			return -EINVAL;
 		return 0;
 	}
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD line_info_cnt
+#define	BPF_PROG_LOAD_LAST_FIELD attach_btf_id
 
 static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
@@ -1656,7 +1664,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		return -EPERM;
 
 	bpf_prog_load_fixup_attach_type(attr);
-	if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type))
+	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
+				       attr->attach_btf_id))
 		return -EINVAL;
 
 	/* plain bpf_prog allocation */
@@ -1665,6 +1674,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		return -ENOMEM;
 
 	prog->expected_attach_type = attr->expected_attach_type;
+	prog->aux->attach_btf_id = attr->attach_btf_id;
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a65c3b0c6935..3bb2cd1de341 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -420,6 +420,7 @@ union bpf_attr {
 		__u32		line_info_rec_size;	/* userspace bpf_line_info size */
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
+		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
-- 
cgit v1.2.3


From 9e15db66136a14cde3f35691f1d839d950118826 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:25:00 -0700
Subject: bpf: Implement accurate raw_tp context access via BTF

libbpf analyzes bpf C program, searches in-kernel BTF for given type name
and stores it into expected_attach_type.
The kernel verifier expects this btf_id to point to something like:
typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc);
which represents signature of raw_tracepoint "kfree_skb".

Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb'
and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint.
In first case it passes btf_id of 'struct sk_buff *' back to the verifier core
and 'void *' in second case.

Then the verifier tracks PTR_TO_BTF_ID as any other pointer type.
Like PTR_TO_SOCKET points to 'struct bpf_sock',
PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on.
PTR_TO_BTF_ID points to in-kernel structs.
If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF
then PTR_TO_BTF_ID#1234 points to one of in kernel skbs.

When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32)
the btf_struct_access() checks which field of 'struct sk_buff' is
at offset 32. Checks that size of access matches type definition
of the field and continues to track the dereferenced type.
If that field was a pointer to 'struct net_device' the r2's type
will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device'
in vmlinux's BTF.

Such verifier analysis prevents "cheating" in BPF C program.
The program cannot cast arbitrary pointer to 'struct sk_buff *'
and access it. C compiler would allow type cast, of course,
but the verifier will notice type mismatch based on BPF assembly
and in-kernel BTF.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org
---
 include/linux/bpf.h          |  17 +++-
 include/linux/bpf_verifier.h |   4 +
 kernel/bpf/btf.c             | 190 +++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c        |  88 +++++++++++++++++++-
 kernel/trace/bpf_trace.c     |   2 +-
 5 files changed, 296 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f916380675dd..028555fcd10d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -16,6 +16,7 @@
 #include <linux/u64_stats_sync.h>
 
 struct bpf_verifier_env;
+struct bpf_verifier_log;
 struct perf_event;
 struct bpf_prog;
 struct bpf_map;
@@ -281,6 +282,7 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
+	PTR_TO_BTF_ID,		 /* reg points to kernel struct */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -288,7 +290,11 @@ enum bpf_reg_type {
  */
 struct bpf_insn_access_aux {
 	enum bpf_reg_type reg_type;
-	int ctx_field_size;
+	union {
+		int ctx_field_size;
+		u32 btf_id;
+	};
+	struct bpf_verifier_log *log; /* for verbose logs */
 };
 
 static inline void
@@ -483,6 +489,7 @@ struct bpf_event_entry {
 
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
+const char *kernel_type_name(u32 btf_type_id);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
 
@@ -748,6 +755,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr);
+bool btf_ctx_access(int off, int size, enum bpf_access_type type,
+		    const struct bpf_prog *prog,
+		    struct bpf_insn_access_aux *info);
+int btf_struct_access(struct bpf_verifier_log *log,
+		      const struct btf_type *t, int off, int size,
+		      enum bpf_access_type atype,
+		      u32 *next_btf_id);
+
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 713efae62e96..6e7284ea1468 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -52,6 +52,8 @@ struct bpf_reg_state {
 		 */
 		struct bpf_map *map_ptr;
 
+		u32 btf_id; /* for PTR_TO_BTF_ID */
+
 		/* Max size from any of the above. */
 		unsigned long raw;
 	};
@@ -399,6 +401,8 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
 				      const char *fmt, va_list args);
 __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
 					   const char *fmt, ...);
+__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
+			    const char *fmt, ...);
 
 static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
 {
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ddeab1e8d21e..271d27cd427f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3436,6 +3436,196 @@ errout:
 	return ERR_PTR(err);
 }
 
+extern struct btf *btf_vmlinux;
+
+bool btf_ctx_access(int off, int size, enum bpf_access_type type,
+		    const struct bpf_prog *prog,
+		    struct bpf_insn_access_aux *info)
+{
+	struct bpf_verifier_log *log = info->log;
+	u32 btf_id = prog->aux->attach_btf_id;
+	const struct btf_param *args;
+	const struct btf_type *t;
+	const char prefix[] = "btf_trace_";
+	const char *tname;
+	u32 nr_args, arg;
+
+	if (!btf_id)
+		return true;
+
+	if (IS_ERR(btf_vmlinux)) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
+		return false;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, btf_id);
+	if (!t || BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) {
+		bpf_log(log, "btf_id is invalid\n");
+		return false;
+	}
+
+	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+	if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
+		bpf_log(log, "btf_id points to wrong type name %s\n", tname);
+		return false;
+	}
+	tname += sizeof(prefix) - 1;
+
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_ptr(t))
+		return false;
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_func_proto(t))
+		return false;
+
+	if (off % 8) {
+		bpf_log(log, "raw_tp '%s' offset %d is not multiple of 8\n",
+			tname, off);
+		return false;
+	}
+	arg = off / 8;
+	args = (const struct btf_param *)(t + 1);
+	/* skip first 'void *__data' argument in btf_trace_##name typedef */
+	args++;
+	nr_args = btf_type_vlen(t) - 1;
+	if (arg >= nr_args) {
+		bpf_log(log, "raw_tp '%s' doesn't have %d-th argument\n",
+			tname, arg);
+		return false;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, args[arg].type);
+	/* skip modifiers */
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf_vmlinux, t->type);
+	if (btf_type_is_int(t))
+		/* accessing a scalar */
+		return true;
+	if (!btf_type_is_ptr(t)) {
+		bpf_log(log,
+			"raw_tp '%s' arg%d '%s' has type %s. Only pointer access is allowed\n",
+			tname, arg,
+			__btf_name_by_offset(btf_vmlinux, t->name_off),
+			btf_kind_str[BTF_INFO_KIND(t->info)]);
+		return false;
+	}
+	if (t->type == 0)
+		/* This is a pointer to void.
+		 * It is the same as scalar from the verifier safety pov.
+		 * No further pointer walking is allowed.
+		 */
+		return true;
+
+	/* this is a pointer to another type */
+	info->reg_type = PTR_TO_BTF_ID;
+	info->btf_id = t->type;
+
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	/* skip modifiers */
+	while (btf_type_is_modifier(t))
+		t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_struct(t)) {
+		bpf_log(log,
+			"raw_tp '%s' arg%d type %s is not a struct\n",
+			tname, arg, btf_kind_str[BTF_INFO_KIND(t->info)]);
+		return false;
+	}
+	bpf_log(log, "raw_tp '%s' arg%d has btf_id %d type %s '%s'\n",
+		tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)],
+		__btf_name_by_offset(btf_vmlinux, t->name_off));
+	return true;
+}
+
+int btf_struct_access(struct bpf_verifier_log *log,
+		      const struct btf_type *t, int off, int size,
+		      enum bpf_access_type atype,
+		      u32 *next_btf_id)
+{
+	const struct btf_member *member;
+	const struct btf_type *mtype;
+	const char *tname, *mname;
+	int i, moff = 0, msize;
+
+again:
+	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+	if (!btf_type_is_struct(t)) {
+		bpf_log(log, "Type '%s' is not a struct", tname);
+		return -EINVAL;
+	}
+
+	for_each_member(i, t, member) {
+		/* offset of the field in bits */
+		moff = btf_member_bit_offset(t, member);
+
+		if (btf_member_bitfield_size(t, member))
+			/* bitfields are not supported yet */
+			continue;
+
+		if (off + size <= moff / 8)
+			/* won't find anything, field is already too far */
+			break;
+
+		/* type of the field */
+		mtype = btf_type_by_id(btf_vmlinux, member->type);
+		mname = __btf_name_by_offset(btf_vmlinux, member->name_off);
+
+		/* skip modifiers */
+		while (btf_type_is_modifier(mtype))
+			mtype = btf_type_by_id(btf_vmlinux, mtype->type);
+
+		if (btf_type_is_array(mtype))
+			/* array deref is not supported yet */
+			continue;
+
+		if (!btf_type_has_size(mtype) && !btf_type_is_ptr(mtype)) {
+			bpf_log(log, "field %s doesn't have size\n", mname);
+			return -EFAULT;
+		}
+		if (btf_type_is_ptr(mtype))
+			msize = 8;
+		else
+			msize = mtype->size;
+		if (off >= moff / 8 + msize)
+			/* no overlap with member, keep iterating */
+			continue;
+		/* the 'off' we're looking for is either equal to start
+		 * of this field or inside of this struct
+		 */
+		if (btf_type_is_struct(mtype)) {
+			/* our field must be inside that union or struct */
+			t = mtype;
+
+			/* adjust offset we're looking for */
+			off -= moff / 8;
+			goto again;
+		}
+		if (msize != size) {
+			/* field access size doesn't match */
+			bpf_log(log,
+				"cannot access %d bytes in struct %s field %s that has size %d\n",
+				size, tname, mname, msize);
+			return -EACCES;
+		}
+
+		if (btf_type_is_ptr(mtype)) {
+			const struct btf_type *stype;
+
+			stype = btf_type_by_id(btf_vmlinux, mtype->type);
+			/* skip modifiers */
+			while (btf_type_is_modifier(stype))
+				stype = btf_type_by_id(btf_vmlinux, stype->type);
+			if (btf_type_is_struct(stype)) {
+				*next_btf_id = mtype->type;
+				return PTR_TO_BTF_ID;
+			}
+		}
+		/* all other fields are treated as scalars */
+		return SCALAR_VALUE;
+	}
+	bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off);
+	return -EINVAL;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 466b3b19de4d..42a463e09761 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -286,6 +286,19 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
+__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
+			    const char *fmt, ...)
+{
+	va_list args;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+
+	va_start(args, fmt);
+	bpf_verifier_vlog(log, fmt, args);
+	va_end(args);
+}
+
 static const char *ltrim(const char *s)
 {
 	while (isspace(*s))
@@ -406,6 +419,7 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
 	[PTR_TO_TP_BUFFER]	= "tp_buffer",
 	[PTR_TO_XDP_SOCK]	= "xdp_sock",
+	[PTR_TO_BTF_ID]		= "ptr_",
 };
 
 static char slot_type_char[] = {
@@ -436,6 +450,12 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env,
 	return cur->frame[reg->frameno];
 }
 
+const char *kernel_type_name(u32 id)
+{
+	return btf_name_by_offset(btf_vmlinux,
+				  btf_type_by_id(btf_vmlinux, id)->name_off);
+}
+
 static void print_verifier_state(struct bpf_verifier_env *env,
 				 const struct bpf_func_state *state)
 {
@@ -460,6 +480,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			/* reg->off should be 0 for SCALAR_VALUE */
 			verbose(env, "%lld", reg->var_off.value + reg->off);
 		} else {
+			if (t == PTR_TO_BTF_ID)
+				verbose(env, "%s", kernel_type_name(reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
 				verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
@@ -2337,10 +2359,12 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 
 /* check access to 'struct bpf_context' fields.  Supports fixed offsets only */
 static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
-			    enum bpf_access_type t, enum bpf_reg_type *reg_type)
+			    enum bpf_access_type t, enum bpf_reg_type *reg_type,
+			    u32 *btf_id)
 {
 	struct bpf_insn_access_aux info = {
 		.reg_type = *reg_type,
+		.log = &env->log,
 	};
 
 	if (env->ops->is_valid_access &&
@@ -2354,7 +2378,10 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		 */
 		*reg_type = info.reg_type;
 
-		env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+		if (*reg_type == PTR_TO_BTF_ID)
+			*btf_id = info.btf_id;
+		else
+			env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
 		/* remember the offset of last byte accessed in ctx */
 		if (env->prog->aux->max_ctx_offset < off + size)
 			env->prog->aux->max_ctx_offset = off + size;
@@ -2780,6 +2807,53 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
 	return 0;
 }
 
+static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *regs,
+				   int regno, int off, int size,
+				   enum bpf_access_type atype,
+				   int value_regno)
+{
+	struct bpf_reg_state *reg = regs + regno;
+	const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id);
+	const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+	u32 btf_id;
+	int ret;
+
+	if (atype != BPF_READ) {
+		verbose(env, "only read is supported\n");
+		return -EACCES;
+	}
+
+	if (off < 0) {
+		verbose(env,
+			"R%d is ptr_%s invalid negative access: off=%d\n",
+			regno, tname, off);
+		return -EACCES;
+	}
+	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+		char tn_buf[48];
+
+		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+		verbose(env,
+			"R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n",
+			regno, tname, off, tn_buf);
+		return -EACCES;
+	}
+
+	ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+	if (ret < 0)
+		return ret;
+
+	if (ret == SCALAR_VALUE) {
+		mark_reg_unknown(env, regs, value_regno);
+		return 0;
+	}
+	mark_reg_known_zero(env, regs, value_regno);
+	regs[value_regno].type = PTR_TO_BTF_ID;
+	regs[value_regno].btf_id = btf_id;
+	return 0;
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -2840,6 +2914,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		}
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
+		u32 btf_id = 0;
 
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
@@ -2851,7 +2926,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err < 0)
 			return err;
 
-		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
+		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf_id);
+		if (err)
+			verbose_linfo(env, insn_idx, "; ");
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			/* ctx access returns either a scalar, or a
 			 * PTR_TO_PACKET[_META,_END]. In the latter
@@ -2870,6 +2947,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				 * a sub-register.
 				 */
 				regs[value_regno].subreg_def = DEF_NOT_SUBREG;
+				if (reg_type == PTR_TO_BTF_ID)
+					regs[value_regno].btf_id = btf_id;
 			}
 			regs[value_regno].type = reg_type;
 		}
@@ -2929,6 +3008,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		err = check_tp_buffer_access(env, reg, regno, off, size);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
+	} else if (reg->type == PTR_TO_BTF_ID) {
+		err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
+					      value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str[reg->type]);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 44bd08f2443b..6221e8c6ecc3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1074,7 +1074,7 @@ static bool raw_tp_prog_is_valid_access(int off, int size,
 		return false;
 	if (off % size != 0)
 		return false;
-	return true;
+	return btf_ctx_access(off, size, type, prog, info);
 }
 
 const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
-- 
cgit v1.2.3


From 2a02759ef5f8a34792df22b41d5e10658fd7bbd3 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:25:02 -0700
Subject: bpf: Add support for BTF pointers to interpreter

Pointer to BTF object is a pointer to kernel object or NULL.
The memory access in the interpreter has to be done via probe_kernel_read
to avoid page faults.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-9-ast@kernel.org
---
 include/linux/filter.h |  3 +++
 kernel/bpf/core.c      | 19 +++++++++++++++++++
 kernel/bpf/verifier.c  |  8 ++++++++
 3 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index d3d51d7aff2c..22ebea2e64ea 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -65,6 +65,9 @@ struct ctl_table_header;
 /* unused opcode to mark special call to bpf_tail_call() helper */
 #define BPF_TAIL_CALL	0xf0
 
+/* unused opcode to mark special load instruction. Same as BPF_ABS */
+#define BPF_PROBE_MEM	0x20
+
 /* unused opcode to mark call to interpreter with arguments */
 #define BPF_CALL_ARGS	0xe0
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 66088a9e9b9e..8a765bbd33f0 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1291,6 +1291,11 @@ bool bpf_opcode_in_insntable(u8 code)
 }
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+u64 __weak bpf_probe_read(void * dst, u32 size, const void * unsafe_ptr)
+{
+	memset(dst, 0, size);
+	return -EFAULT;
+}
 /**
  *	__bpf_prog_run - run eBPF program on a given context
  *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1310,6 +1315,10 @@ static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u6
 		/* Non-UAPI available opcodes. */
 		[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
 		[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
+		[BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
+		[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
+		[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
+		[BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
 	};
 #undef BPF_INSN_3_LBL
 #undef BPF_INSN_2_LBL
@@ -1542,6 +1551,16 @@ out:
 	LDST(W,  u32)
 	LDST(DW, u64)
 #undef LDST
+#define LDX_PROBE(SIZEOP, SIZE)						\
+	LDX_PROBE_MEM_##SIZEOP:						\
+		bpf_probe_read(&DST, SIZE, (const void *)(long) SRC);	\
+		CONT;
+	LDX_PROBE(B,  1)
+	LDX_PROBE(H,  2)
+	LDX_PROBE(W,  4)
+	LDX_PROBE(DW, 8)
+#undef LDX_PROBE
+
 	STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
 		atomic_add((u32) SRC, (atomic_t *)(unsigned long)
 			   (DST + insn->off));
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 42a463e09761..c4b6a2cfcd47 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7581,6 +7581,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type)
 	case PTR_TO_TCP_SOCK:
 	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
+	case PTR_TO_BTF_ID:
 		return false;
 	default:
 		return true;
@@ -8722,6 +8723,13 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		case PTR_TO_XDP_SOCK:
 			convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
 			break;
+		case PTR_TO_BTF_ID:
+			if (type == BPF_WRITE) {
+				verbose(env, "Writes through BTF pointers are not allowed\n");
+				return -EINVAL;
+			}
+			insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code);
+			continue;
 		default:
 			continue;
 		}
-- 
cgit v1.2.3


From 3dec541b2e632d630fe7142ed44f0b3702ef1f8c Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:25:03 -0700
Subject: bpf: Add support for BTF pointers to x86 JIT

Pointer to BTF object is a pointer to kernel object or NULL.
Such pointers can only be used by BPF_LDX instructions.
The verifier changed their opcode from LDX|MEM|size
to LDX|PROBE_MEM|size to make JITing easier.
The number of entries in extable is the number of BPF_LDX insns
that access kernel memory via "pointer to BTF type".
Only these load instructions can fault.
Since x86 extable is relative it has to be allocated in the same
memory region as JITed code.
Allocate it prior to last pass of JITing and let the last pass populate it.
Pointer to extable in bpf_prog_aux is necessary to make page fault
handling fast.
Page fault handling is done in two steps:
1. bpf_prog_kallsyms_find() finds BPF program that page faulted.
   It's done by walking rb tree.
2. then extable for given bpf program is binary searched.
This process is similar to how page faulting is done for kernel modules.
The exception handler skips over faulting x86 instruction and
initializes destination register with zero. This mimics exact
behavior of bpf_probe_read (when probe_kernel_read faults dest is zeroed).

JITs for other architectures can add support in similar way.
Until then they will reject unknown opcode and fallback to interpreter.

Since extable should be aligned and placed near JITed code
make bpf_jit_binary_alloc() return 4 byte aligned image offset,
so that extable aligning formula in bpf_int_jit_compile() doesn't need
to rely on internal implementation of bpf_jit_binary_alloc().
On x86 gcc defaults to 16-byte alignment for regular kernel functions
due to better performance. JITed code may be aligned to 16 in the future,
but it will use 4 in the meantime.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-10-ast@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 97 +++++++++++++++++++++++++++++++++++++++++++--
 include/linux/bpf.h         |  3 ++
 include/linux/extable.h     | 10 +++++
 kernel/bpf/core.c           | 20 +++++++++-
 kernel/bpf/verifier.c       |  1 +
 kernel/extable.c            |  2 +
 6 files changed, 128 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 3ad2ba1ad855..8cd23d8309bf 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -9,7 +9,7 @@
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
 #include <linux/bpf.h>
-
+#include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 
@@ -123,6 +123,19 @@ static const int reg2hex[] = {
 	[AUX_REG] = 3,    /* R11 temp register */
 };
 
+static const int reg2pt_regs[] = {
+	[BPF_REG_0] = offsetof(struct pt_regs, ax),
+	[BPF_REG_1] = offsetof(struct pt_regs, di),
+	[BPF_REG_2] = offsetof(struct pt_regs, si),
+	[BPF_REG_3] = offsetof(struct pt_regs, dx),
+	[BPF_REG_4] = offsetof(struct pt_regs, cx),
+	[BPF_REG_5] = offsetof(struct pt_regs, r8),
+	[BPF_REG_6] = offsetof(struct pt_regs, bx),
+	[BPF_REG_7] = offsetof(struct pt_regs, r13),
+	[BPF_REG_8] = offsetof(struct pt_regs, r14),
+	[BPF_REG_9] = offsetof(struct pt_regs, r15),
+};
+
 /*
  * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15
  * which need extra byte of encoding.
@@ -377,6 +390,19 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
 	*pprog = prog;
 }
 
+
+static bool ex_handler_bpf(const struct exception_table_entry *x,
+			   struct pt_regs *regs, int trapnr,
+			   unsigned long error_code, unsigned long fault_addr)
+{
+	u32 reg = x->fixup >> 8;
+
+	/* jump over faulting load and clear dest register */
+	*(unsigned long *)((void *)regs + reg) = 0;
+	regs->ip += x->fixup & 0xff;
+	return true;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
@@ -384,7 +410,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	int insn_cnt = bpf_prog->len;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
-	int i, cnt = 0;
+	int i, cnt = 0, excnt = 0;
 	int proglen = 0;
 	u8 *prog = temp;
 
@@ -778,14 +804,17 @@ stx:			if (is_imm8(insn->off))
 
 			/* LDX: dst_reg = *(u8*)(src_reg + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 			/* Emit 'movzx rax, byte ptr [rax + off]' */
 			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
 			/* Emit 'movzx rax, word ptr [rax + off]' */
 			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 			/* Emit 'mov eax, dword ptr [rax+0x14]' */
 			if (is_ereg(dst_reg) || is_ereg(src_reg))
 				EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
@@ -793,6 +822,7 @@ stx:			if (is_imm8(insn->off))
 				EMIT1(0x8B);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_DW:
+		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
 			/* Emit 'mov rax, qword ptr [rax+0x14]' */
 			EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
 ldx:			/*
@@ -805,6 +835,48 @@ ldx:			/*
 			else
 				EMIT1_off32(add_2reg(0x80, src_reg, dst_reg),
 					    insn->off);
+			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
+				struct exception_table_entry *ex;
+				u8 *_insn = image + proglen;
+				s64 delta;
+
+				if (!bpf_prog->aux->extable)
+					break;
+
+				if (excnt >= bpf_prog->aux->num_exentries) {
+					pr_err("ex gen bug\n");
+					return -EFAULT;
+				}
+				ex = &bpf_prog->aux->extable[excnt++];
+
+				delta = _insn - (u8 *)&ex->insn;
+				if (!is_simm32(delta)) {
+					pr_err("extable->insn doesn't fit into 32-bit\n");
+					return -EFAULT;
+				}
+				ex->insn = delta;
+
+				delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler;
+				if (!is_simm32(delta)) {
+					pr_err("extable->handler doesn't fit into 32-bit\n");
+					return -EFAULT;
+				}
+				ex->handler = delta;
+
+				if (dst_reg > BPF_REG_9) {
+					pr_err("verifier error\n");
+					return -EFAULT;
+				}
+				/*
+				 * Compute size of x86 insn and its target dest x86 register.
+				 * ex_handler_bpf() will use lower 8 bits to adjust
+				 * pt_regs->ip to jump over this x86 instruction
+				 * and upper bits to figure out which pt_regs to zero out.
+				 * End result: x86 insn "mov rbx, qword ptr [rax+0x14]"
+				 * of 4 bytes will be ignored and rbx will be zero inited.
+				 */
+				ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8);
+			}
 			break;
 
 			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
@@ -1058,6 +1130,11 @@ emit_jmp:
 		addrs[i] = proglen;
 		prog = temp;
 	}
+
+	if (image && excnt != bpf_prog->aux->num_exentries) {
+		pr_err("extable is not populated\n");
+		return -EFAULT;
+	}
 	return proglen;
 }
 
@@ -1158,12 +1235,24 @@ out_image:
 			break;
 		}
 		if (proglen == oldproglen) {
-			header = bpf_jit_binary_alloc(proglen, &image,
-						      1, jit_fill_hole);
+			/*
+			 * The number of entries in extable is the number of BPF_LDX
+			 * insns that access kernel memory via "pointer to BTF type".
+			 * The verifier changed their opcode from LDX|MEM|size
+			 * to LDX|PROBE_MEM|size to make JITing easier.
+			 */
+			u32 align = __alignof__(struct exception_table_entry);
+			u32 extable_size = prog->aux->num_exentries *
+				sizeof(struct exception_table_entry);
+
+			/* allocate module memory for x86 insns and extable */
+			header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size,
+						      &image, align, jit_fill_hole);
 			if (!header) {
 				prog = orig_prog;
 				goto out_addrs;
 			}
+			prog->aux->extable = (void *) image + roundup(proglen, align);
 		}
 		oldproglen = proglen;
 		cond_resched();
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 028555fcd10d..a7330d75bb94 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -24,6 +24,7 @@ struct sock;
 struct seq_file;
 struct btf;
 struct btf_type;
+struct exception_table_entry;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -423,6 +424,8 @@ struct bpf_prog_aux {
 	 * main prog always has linfo_idx == 0
 	 */
 	u32 linfo_idx;
+	u32 num_exentries;
+	struct exception_table_entry *extable;
 	struct bpf_prog_stats __percpu *stats;
 	union {
 		struct work_struct work;
diff --git a/include/linux/extable.h b/include/linux/extable.h
index 81ecfaa83ad3..4ab9e78f313b 100644
--- a/include/linux/extable.h
+++ b/include/linux/extable.h
@@ -33,4 +33,14 @@ search_module_extables(unsigned long addr)
 }
 #endif /*CONFIG_MODULES*/
 
+#ifdef CONFIG_BPF_JIT
+const struct exception_table_entry *search_bpf_extables(unsigned long addr);
+#else
+static inline const struct exception_table_entry *
+search_bpf_extables(unsigned long addr)
+{
+	return NULL;
+}
+#endif
+
 #endif /* _LINUX_EXTABLE_H */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8a765bbd33f0..673f5d40a93e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -30,7 +30,7 @@
 #include <linux/kallsyms.h>
 #include <linux/rcupdate.h>
 #include <linux/perf_event.h>
-
+#include <linux/extable.h>
 #include <asm/unaligned.h>
 
 /* Registers */
@@ -712,6 +712,24 @@ bool is_bpf_text_address(unsigned long addr)
 	return ret;
 }
 
+const struct exception_table_entry *search_bpf_extables(unsigned long addr)
+{
+	const struct exception_table_entry *e = NULL;
+	struct bpf_prog *prog;
+
+	rcu_read_lock();
+	prog = bpf_prog_kallsyms_find(addr);
+	if (!prog)
+		goto out;
+	if (!prog->aux->num_exentries)
+		goto out;
+
+	e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr);
+out:
+	rcu_read_unlock();
+	return e;
+}
+
 int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 		    char *sym)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c4b6a2cfcd47..fba9ef6a831b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8729,6 +8729,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 				return -EINVAL;
 			}
 			insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code);
+			env->prog->aux->num_exentries++;
 			continue;
 		default:
 			continue;
diff --git a/kernel/extable.c b/kernel/extable.c
index f6c9406eec7d..f6920a11e28a 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -56,6 +56,8 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 	e = search_kernel_exception_table(addr);
 	if (!e)
 		e = search_module_extables(addr);
+	if (!e)
+		e = search_bpf_extables(addr);
 	return e;
 }
 
-- 
cgit v1.2.3


From a7658e1a4164ce2b9eb4a11aadbba38586e93bd6 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 15 Oct 2019 20:25:04 -0700
Subject: bpf: Check types of arguments passed into helpers

Introduce new helper that reuses existing skb perf_event output
implementation, but can be called from raw_tracepoint programs
that receive 'struct sk_buff *' as tracepoint argument or
can walk other kernel data structures to skb pointer.

In order to do that teach verifier to resolve true C types
of bpf helpers into in-kernel BTF ids.
The type of kernel pointer passed by raw tracepoint into bpf
program will be tracked by the verifier all the way until
it's passed into helper function.
For example:
kfree_skb() kernel function calls trace_kfree_skb(skb, loc);
bpf programs receives that skb pointer and may eventually
pass it into bpf_skb_output() bpf helper which in-kernel is
implemented via bpf_skb_event_output() kernel function.
Its first argument in the kernel is 'struct sk_buff *'.
The verifier makes sure that types match all the way.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-11-ast@kernel.org
---
 include/linux/bpf.h            | 18 +++++++----
 include/uapi/linux/bpf.h       | 27 ++++++++++++++++-
 kernel/bpf/btf.c               | 68 ++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c          | 44 +++++++++++++++++----------
 kernel/trace/bpf_trace.c       |  4 +++
 net/core/filter.c              | 15 +++++++++-
 tools/include/uapi/linux/bpf.h | 27 ++++++++++++++++-
 7 files changed, 180 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a7330d75bb94..2c2c29b49845 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -213,6 +213,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_INT,		/* pointer to int */
 	ARG_PTR_TO_LONG,	/* pointer to long */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
+	ARG_PTR_TO_BTF_ID,	/* pointer to in-kernel struct */
 };
 
 /* type of values returned from helper functions */
@@ -235,11 +236,17 @@ struct bpf_func_proto {
 	bool gpl_only;
 	bool pkt_access;
 	enum bpf_return_type ret_type;
-	enum bpf_arg_type arg1_type;
-	enum bpf_arg_type arg2_type;
-	enum bpf_arg_type arg3_type;
-	enum bpf_arg_type arg4_type;
-	enum bpf_arg_type arg5_type;
+	union {
+		struct {
+			enum bpf_arg_type arg1_type;
+			enum bpf_arg_type arg2_type;
+			enum bpf_arg_type arg3_type;
+			enum bpf_arg_type arg4_type;
+			enum bpf_arg_type arg5_type;
+		};
+		enum bpf_arg_type arg_type[5];
+	};
+	u32 *btf_id; /* BTF ids of arguments */
 };
 
 /* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -765,6 +772,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      const struct btf_type *t, int off, int size,
 		      enum bpf_access_type atype,
 		      u32 *next_btf_id);
+u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int);
 
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3bb2cd1de341..4af8b0819a32 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2751,6 +2751,30 @@ union bpf_attr {
  *		**-EOPNOTSUPP** kernel configuration does not enable SYN cookies
  *
  *		**-EPROTONOSUPPORT** IP packet version is not 4 or 6
+ *
+ * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * 	Description
+ * 		Write raw *data* blob into a special BPF perf event held by
+ * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * 		event must have the following attributes: **PERF_SAMPLE_RAW**
+ * 		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * 		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * 		The *flags* are used to indicate the index in *map* for which
+ * 		the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * 		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * 		to indicate that the index of the current CPU core should be
+ * 		used.
+ *
+ * 		The value to write, of *size*, is passed through eBPF stack and
+ * 		pointed by *data*.
+ *
+ * 		*ctx* is a pointer to in-kernel struct sk_buff.
+ *
+ * 		This helper is similar to **bpf_perf_event_output**\ () but
+ * 		restricted to raw_tracepoint bpf programs.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2863,7 +2887,8 @@ union bpf_attr {
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
 	FN(send_signal),		\
-	FN(tcp_gen_syncookie),
+	FN(tcp_gen_syncookie),		\
+	FN(skb_output),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 271d27cd427f..f7557af39756 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3626,6 +3626,74 @@ again:
 	return -EINVAL;
 }
 
+u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg)
+{
+	char fnname[KSYM_SYMBOL_LEN + 4] = "btf_";
+	const struct btf_param *args;
+	const struct btf_type *t;
+	const char *tname, *sym;
+	u32 btf_id, i;
+
+	if (IS_ERR(btf_vmlinux)) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
+		return -EINVAL;
+	}
+
+	sym = kallsyms_lookup((long)fn, NULL, NULL, NULL, fnname + 4);
+	if (!sym) {
+		bpf_log(log, "kernel doesn't have kallsyms\n");
+		return -EFAULT;
+	}
+
+	for (i = 1; i <= btf_vmlinux->nr_types; i++) {
+		t = btf_type_by_id(btf_vmlinux, i);
+		if (BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF)
+			continue;
+		tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+		if (!strcmp(tname, fnname))
+			break;
+	}
+	if (i > btf_vmlinux->nr_types) {
+		bpf_log(log, "helper %s type is not found\n", fnname);
+		return -ENOENT;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_ptr(t))
+		return -EFAULT;
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_func_proto(t))
+		return -EFAULT;
+
+	args = (const struct btf_param *)(t + 1);
+	if (arg >= btf_type_vlen(t)) {
+		bpf_log(log, "bpf helper %s doesn't have %d-th argument\n",
+			fnname, arg);
+		return -EINVAL;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, args[arg].type);
+	if (!btf_type_is_ptr(t) || !t->type) {
+		/* anything but the pointer to struct is a helper config bug */
+		bpf_log(log, "ARG_PTR_TO_BTF is misconfigured\n");
+		return -EFAULT;
+	}
+	btf_id = t->type;
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	/* skip modifiers */
+	while (btf_type_is_modifier(t)) {
+		btf_id = t->type;
+		t = btf_type_by_id(btf_vmlinux, t->type);
+	}
+	if (!btf_type_is_struct(t)) {
+		bpf_log(log, "ARG_PTR_TO_BTF is not a struct\n");
+		return -EFAULT;
+	}
+	bpf_log(log, "helper %s arg%d has btf_id %d struct %s\n", fnname + 4,
+		arg, btf_id, __btf_name_by_offset(btf_vmlinux, t->name_off));
+	return btf_id;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fba9ef6a831b..556e82f8869b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -205,6 +205,7 @@ struct bpf_call_arg_meta {
 	u64 msize_umax_value;
 	int ref_obj_id;
 	int func_id;
+	u32 btf_id;
 };
 
 struct btf *btf_vmlinux;
@@ -3439,6 +3440,22 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		expected_type = PTR_TO_SOCKET;
 		if (type != expected_type)
 			goto err_type;
+	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
+		expected_type = PTR_TO_BTF_ID;
+		if (type != expected_type)
+			goto err_type;
+		if (reg->btf_id != meta->btf_id) {
+			verbose(env, "Helper has type %s got %s in R%d\n",
+				kernel_type_name(meta->btf_id),
+				kernel_type_name(reg->btf_id), regno);
+
+			return -EACCES;
+		}
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) {
+			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
+				regno);
+			return -EACCES;
+		}
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
 			if (process_spin_lock(env, regno, true))
@@ -3586,6 +3603,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 		if (func_id != BPF_FUNC_perf_event_read &&
 		    func_id != BPF_FUNC_perf_event_output &&
+		    func_id != BPF_FUNC_skb_output &&
 		    func_id != BPF_FUNC_perf_event_read_value)
 			goto error;
 		break;
@@ -3673,6 +3691,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_perf_event_read:
 	case BPF_FUNC_perf_event_output:
 	case BPF_FUNC_perf_event_read_value:
+	case BPF_FUNC_skb_output:
 		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			goto error;
 		break;
@@ -4127,21 +4146,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 
 	meta.func_id = func_id;
 	/* check args */
-	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
-	if (err)
-		return err;
+	for (i = 0; i < 5; i++) {
+		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID) {
+			if (!fn->btf_id[i])
+				fn->btf_id[i] = btf_resolve_helper_id(&env->log, fn->func, i);
+			meta.btf_id = fn->btf_id[i];
+		}
+		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
+		if (err)
+			return err;
+	}
 
 	err = record_func_map(env, &meta, func_id, insn_idx);
 	if (err)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6221e8c6ecc3..52f7e9d8c29b 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -995,6 +995,8 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
+extern const struct bpf_func_proto bpf_skb_output_proto;
+
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
 {
@@ -1053,6 +1055,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
 		return &bpf_perf_event_output_proto_raw_tp;
+	case BPF_FUNC_skb_output:
+		return &bpf_skb_output_proto;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_raw_tp;
 	case BPF_FUNC_get_stack:
diff --git a/net/core/filter.c b/net/core/filter.c
index 46196e212413..728ba6203c1f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3798,7 +3798,7 @@ BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map,
 
 	if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK)))
 		return -EINVAL;
-	if (unlikely(skb_size > skb->len))
+	if (unlikely(!skb || skb_size > skb->len))
 		return -EFAULT;
 
 	return bpf_event_output(map, flags, meta, meta_size, skb, skb_size,
@@ -3816,6 +3816,19 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
+static u32 bpf_skb_output_btf_ids[5];
+const struct bpf_func_proto bpf_skb_output_proto = {
+	.func		= bpf_skb_event_output,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_skb_output_btf_ids,
+};
+
 static unsigned short bpf_tunnel_key_af(u64 flags)
 {
 	return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3bb2cd1de341..4af8b0819a32 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2751,6 +2751,30 @@ union bpf_attr {
  *		**-EOPNOTSUPP** kernel configuration does not enable SYN cookies
  *
  *		**-EPROTONOSUPPORT** IP packet version is not 4 or 6
+ *
+ * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * 	Description
+ * 		Write raw *data* blob into a special BPF perf event held by
+ * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * 		event must have the following attributes: **PERF_SAMPLE_RAW**
+ * 		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * 		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * 		The *flags* are used to indicate the index in *map* for which
+ * 		the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * 		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * 		to indicate that the index of the current CPU core should be
+ * 		used.
+ *
+ * 		The value to write, of *size*, is passed through eBPF stack and
+ * 		pointed by *data*.
+ *
+ * 		*ctx* is a pointer to in-kernel struct sk_buff.
+ *
+ * 		This helper is similar to **bpf_perf_event_output**\ () but
+ * 		restricted to raw_tracepoint bpf programs.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2863,7 +2887,8 @@ union bpf_attr {
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
 	FN(send_signal),		\
-	FN(tcp_gen_syncookie),
+	FN(tcp_gen_syncookie),		\
+	FN(skb_output),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 5e5b03d163e15a40b0fa57c70b4e8edd549b0b98 Mon Sep 17 00:00:00 2001
From: "Ben Dooks (Codethink)" <ben.dooks@codethink.co.uk>
Date: Tue, 22 Oct 2019 13:59:25 +0100
Subject: xdp: Fix type of string pointer in __XDP_ACT_SYM_TAB

The table entry in __XDP_ACT_SYM_TAB for the last item is set
to { -1, 0 } where it should be { -1, NULL } as the second item
is a pointer to a string.

Fixes the following sparse warnings:

./include/trace/events/xdp.h:28:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:53:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:82:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:140:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:155:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:190:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:225:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:260:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:318:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:356:1: warning: Using plain integer as NULL pointer
./include/trace/events/xdp.h:390:1: warning: Using plain integer as NULL pointer

Signed-off-by: Ben Dooks (Codethink) <ben.dooks@codethink.co.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191022125925.10508-1-ben.dooks@codethink.co.uk
---
 include/trace/events/xdp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 8c8420230a10..c7e3c9c5bad3 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -22,7 +22,7 @@
 #define __XDP_ACT_SYM_FN(x)	\
 	{ XDP_##x, #x },
 #define __XDP_ACT_SYM_TAB	\
-	__XDP_ACT_MAP(__XDP_ACT_SYM_FN) { -1, 0 }
+	__XDP_ACT_MAP(__XDP_ACT_SYM_FN) { -1, NULL }
 __XDP_ACT_MAP(__XDP_ACT_TP_FN)
 
 TRACE_EVENT(xdp_exception,
-- 
cgit v1.2.3


From 3820729160440158a014add69cc0d371061a96b2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 24 Oct 2019 17:18:11 -0700
Subject: bpf: Prepare btf_ctx_access for non raw_tp use case

This patch makes a few changes to btf_ctx_access() to prepare
it for non raw_tp use case where the attach_btf_id is not
necessary a BTF_KIND_TYPEDEF.

It moves the "btf_trace_" prefix check and typedef-follow logic to a new
function "check_attach_btf_id()" which is called only once during
bpf_check().  btf_ctx_access() only operates on a BTF_KIND_FUNC_PROTO
type now. That should also be more efficient since it is done only
one instead of every-time check_ctx_access() is called.

"check_attach_btf_id()" needs to find the func_proto type from
the attach_btf_id.  It needs to store the result into the
newly added prog->aux->attach_func_proto.  func_proto
btf type has no name, so a proper name should be stored into
"attach_func_name" also.

v2:
- Move the "btf_trace_" check to an earlier verifier phase (Alexei)

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20191025001811.1718491-1-kafai@fb.com
---
 include/linux/bpf.h      |  5 ++++
 include/linux/btf.h      | 31 ++++++++++++++++++++
 kernel/bpf/btf.c         | 73 +++++++++---------------------------------------
 kernel/bpf/syscall.c     |  4 +--
 kernel/bpf/verifier.c    | 52 +++++++++++++++++++++++++++++++++-
 kernel/trace/bpf_trace.c |  2 ++
 6 files changed, 103 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2c2c29b49845..171be30fe0ae 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -392,6 +392,11 @@ struct bpf_prog_aux {
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
+	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
+	const struct btf_type *attach_func_proto;
+	/* function name for valid attach_btf_id */
+	const char *attach_func_name;
 	struct bpf_prog **func;
 	void *jit_data; /* JIT specific data. arch dependent */
 	struct latch_tree_node ksym_tnode;
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 55d43bc856be..9dee00859c5f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -5,6 +5,7 @@
 #define _LINUX_BTF_H 1
 
 #include <linux/types.h>
+#include <uapi/linux/btf.h>
 
 struct btf;
 struct btf_member;
@@ -53,6 +54,36 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
 bool btf_type_is_void(const struct btf_type *t);
 
+static inline bool btf_type_is_ptr(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
+}
+
+static inline bool btf_type_is_int(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
+}
+
+static inline bool btf_type_is_enum(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM;
+}
+
+static inline bool btf_type_is_typedef(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF;
+}
+
+static inline bool btf_type_is_func(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC;
+}
+
+static inline bool btf_type_is_func_proto(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f7557af39756..128d89601d73 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -336,16 +336,6 @@ static bool btf_type_is_fwd(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
 }
 
-static bool btf_type_is_func(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC;
-}
-
-static bool btf_type_is_func_proto(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
-}
-
 static bool btf_type_nosize(const struct btf_type *t)
 {
 	return btf_type_is_void(t) || btf_type_is_fwd(t) ||
@@ -377,16 +367,6 @@ 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;
-}
-
 static bool btf_type_is_var(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
@@ -3442,54 +3422,27 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info)
 {
+	const struct btf_type *t = prog->aux->attach_func_proto;
+	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
-	u32 btf_id = prog->aux->attach_btf_id;
 	const struct btf_param *args;
-	const struct btf_type *t;
-	const char prefix[] = "btf_trace_";
-	const char *tname;
 	u32 nr_args, arg;
 
-	if (!btf_id)
-		return true;
-
-	if (IS_ERR(btf_vmlinux)) {
-		bpf_log(log, "btf_vmlinux is malformed\n");
-		return false;
-	}
-
-	t = btf_type_by_id(btf_vmlinux, btf_id);
-	if (!t || BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) {
-		bpf_log(log, "btf_id is invalid\n");
-		return false;
-	}
-
-	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
-	if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
-		bpf_log(log, "btf_id points to wrong type name %s\n", tname);
-		return false;
-	}
-	tname += sizeof(prefix) - 1;
-
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	if (!btf_type_is_ptr(t))
-		return false;
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	if (!btf_type_is_func_proto(t))
-		return false;
-
 	if (off % 8) {
-		bpf_log(log, "raw_tp '%s' offset %d is not multiple of 8\n",
+		bpf_log(log, "func '%s' offset %d is not multiple of 8\n",
 			tname, off);
 		return false;
 	}
 	arg = off / 8;
 	args = (const struct btf_param *)(t + 1);
-	/* skip first 'void *__data' argument in btf_trace_##name typedef */
-	args++;
-	nr_args = btf_type_vlen(t) - 1;
+	nr_args = btf_type_vlen(t);
+	if (prog->aux->attach_btf_trace) {
+		/* skip first 'void *__data' argument in btf_trace_##name typedef */
+		args++;
+		nr_args--;
+	}
 	if (arg >= nr_args) {
-		bpf_log(log, "raw_tp '%s' doesn't have %d-th argument\n",
+		bpf_log(log, "func '%s' doesn't have %d-th argument\n",
 			tname, arg);
 		return false;
 	}
@@ -3503,7 +3456,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		return true;
 	if (!btf_type_is_ptr(t)) {
 		bpf_log(log,
-			"raw_tp '%s' arg%d '%s' has type %s. Only pointer access is allowed\n",
+			"func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n",
 			tname, arg,
 			__btf_name_by_offset(btf_vmlinux, t->name_off),
 			btf_kind_str[BTF_INFO_KIND(t->info)]);
@@ -3526,11 +3479,11 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		t = btf_type_by_id(btf_vmlinux, t->type);
 	if (!btf_type_is_struct(t)) {
 		bpf_log(log,
-			"raw_tp '%s' arg%d type %s is not a struct\n",
+			"func '%s' arg%d type %s is not a struct\n",
 			tname, arg, btf_kind_str[BTF_INFO_KIND(t->info)]);
 		return false;
 	}
-	bpf_log(log, "raw_tp '%s' arg%d has btf_id %d type %s '%s'\n",
+	bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n",
 		tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)],
 		__btf_name_by_offset(btf_vmlinux, t->name_off));
 	return true;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 16ea3c0db4f6..ff5225759553 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1848,9 +1848,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 			goto out_put_prog;
 		}
 		/* raw_tp name is taken from type name instead */
-		tp_name = kernel_type_name(prog->aux->attach_btf_id);
-		/* skip the prefix */
-		tp_name += sizeof("btf_trace_") - 1;
+		tp_name = prog->aux->attach_func_name;
 	} else {
 		if (strncpy_from_user(buf,
 				      u64_to_user_ptr(attr->raw_tracepoint.name),
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 556e82f8869b..c59778c0fc4d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9372,6 +9372,52 @@ static void print_verification_stats(struct bpf_verifier_env *env)
 		env->peak_states, env->longest_mark_read_walk);
 }
 
+static int check_attach_btf_id(struct bpf_verifier_env *env)
+{
+	struct bpf_prog *prog = env->prog;
+	u32 btf_id = prog->aux->attach_btf_id;
+	const struct btf_type *t;
+	const char *tname;
+
+	if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT && btf_id) {
+		const char prefix[] = "btf_trace_";
+
+		t = btf_type_by_id(btf_vmlinux, btf_id);
+		if (!t) {
+			verbose(env, "attach_btf_id %u is invalid\n", btf_id);
+			return -EINVAL;
+		}
+		if (!btf_type_is_typedef(t)) {
+			verbose(env, "attach_btf_id %u is not a typedef\n",
+				btf_id);
+			return -EINVAL;
+		}
+		tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+		if (!tname || strncmp(prefix, tname, sizeof(prefix) - 1)) {
+			verbose(env, "attach_btf_id %u points to wrong type name %s\n",
+				btf_id, tname);
+			return -EINVAL;
+		}
+		tname += sizeof(prefix) - 1;
+		t = btf_type_by_id(btf_vmlinux, t->type);
+		if (!btf_type_is_ptr(t))
+			/* should never happen in valid vmlinux build */
+			return -EINVAL;
+		t = btf_type_by_id(btf_vmlinux, t->type);
+		if (!btf_type_is_func_proto(t))
+			/* should never happen in valid vmlinux build */
+			return -EINVAL;
+
+		/* remember two read only pointers that are valid for
+		 * the life time of the kernel
+		 */
+		prog->aux->attach_func_name = tname;
+		prog->aux->attach_func_proto = t;
+		prog->aux->attach_btf_trace = true;
+	}
+	return 0;
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	      union bpf_attr __user *uattr)
 {
@@ -9435,9 +9481,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 		/* Either gcc or pahole or kernel are broken. */
 		verbose(env, "in-kernel BTF is malformed\n");
 		ret = PTR_ERR(btf_vmlinux);
-		goto err_unlock;
+		goto skip_full_check;
 	}
 
+	ret = check_attach_btf_id(env);
+	if (ret)
+		goto skip_full_check;
+
 	env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
 		env->strict_alignment = true;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c3240898cc44..571c25d60710 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1080,6 +1080,8 @@ static bool raw_tp_prog_is_valid_access(int off, int size,
 		return false;
 	if (off % size != 0)
 		return false;
+	if (!prog->aux->attach_btf_id)
+		return true;
 	return btf_ctx_access(off, size, type, prog, info);
 }
 
-- 
cgit v1.2.3