From ae24345da54e452880808b011fa2d8a0bbd191ba Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:58:59 -0700
Subject: bpf: Implement an interface to register bpf_iter targets

The target can call bpf_iter_reg_target() to register itself.
The needed information:
  target:           target name
  seq_ops:          the seq_file operations for the target
  init_seq_private  target callback to initialize seq_priv during file open
  fini_seq_private  target callback to clean up seq_priv during file release
  seq_priv_size:    the private_data size needed by the seq_file
                    operations

The target name represents a target which provides a seq_ops
for iterating objects.

The target can provide two callback functions, init_seq_private
and fini_seq_private, called during file open/release time.
For example, /proc/net/{tcp6, ipv6_route, netlink, ...}, net
name space needs to be setup properly during file open and
released properly during file release.

Function bpf_iter_unreg_target() is also implemented to unregister
a particular target.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175859.2474669-1-yhs@fb.com
---
 kernel/bpf/Makefile   |  2 +-
 kernel/bpf/bpf_iter.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/bpf_iter.c

(limited to 'kernel')

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f2d7be596966..6a8b0febd3f6 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -2,7 +2,7 @@
 obj-y := core.o
 CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
new file mode 100644
index 000000000000..5a8119d17d14
--- /dev/null
+++ b/kernel/bpf/bpf_iter.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+
+#include <linux/fs.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+struct bpf_iter_target_info {
+	struct list_head list;
+	const char *target;
+	const struct seq_operations *seq_ops;
+	bpf_iter_init_seq_priv_t init_seq_private;
+	bpf_iter_fini_seq_priv_t fini_seq_private;
+	u32 seq_priv_size;
+};
+
+static struct list_head targets = LIST_HEAD_INIT(targets);
+static DEFINE_MUTEX(targets_mutex);
+
+int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
+{
+	struct bpf_iter_target_info *tinfo;
+
+	tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
+	if (!tinfo)
+		return -ENOMEM;
+
+	tinfo->target = reg_info->target;
+	tinfo->seq_ops = reg_info->seq_ops;
+	tinfo->init_seq_private = reg_info->init_seq_private;
+	tinfo->fini_seq_private = reg_info->fini_seq_private;
+	tinfo->seq_priv_size = reg_info->seq_priv_size;
+	INIT_LIST_HEAD(&tinfo->list);
+
+	mutex_lock(&targets_mutex);
+	list_add(&tinfo->list, &targets);
+	mutex_unlock(&targets_mutex);
+
+	return 0;
+}
+
+void bpf_iter_unreg_target(const char *target)
+{
+	struct bpf_iter_target_info *tinfo;
+	bool found = false;
+
+	mutex_lock(&targets_mutex);
+	list_for_each_entry(tinfo, &targets, list) {
+		if (!strcmp(target, tinfo->target)) {
+			list_del(&tinfo->list);
+			kfree(tinfo);
+			found = true;
+			break;
+		}
+	}
+	mutex_unlock(&targets_mutex);
+
+	WARN_ON(found == false);
+}
-- 
cgit v1.2.3


From 15d83c4d7cef5c067a8b075ce59e97df4f60706e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:00 -0700
Subject: bpf: Allow loading of a bpf_iter program

A bpf_iter program is a tracing program with attach type
BPF_TRACE_ITER. The load attribute
  attach_btf_id
is used by the verifier against a particular kernel function,
which represents a target, e.g., __bpf_iter__bpf_map
for target bpf_map which is implemented later.

The program return value must be 0 or 1 for now.
  0 : successful, except potential seq_file buffer overflow
      which is handled by seq_file reader.
  1 : request to restart the same object

In the future, other return values may be used for filtering or
teminating the iterator.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175900.2474947-1-yhs@fb.com
---
 include/linux/bpf.h            |  3 +++
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/bpf_iter.c          | 36 ++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c          | 21 +++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  1 +
 5 files changed, 62 insertions(+)

(limited to 'kernel')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 40c78b86fe38..f28bdd714754 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1127,6 +1127,8 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
 int bpf_obj_get_user(const char __user *pathname, int flags);
 
+#define BPF_ITER_FUNC_PREFIX "__bpf_iter__"
+
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data);
 typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
 
@@ -1140,6 +1142,7 @@ struct bpf_iter_reg {
 
 int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const char *target);
+bool bpf_iter_prog_supported(struct bpf_prog *prog);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6e5e7caa3739..c8a5325cc8d0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -218,6 +218,7 @@ enum bpf_attach_type {
 	BPF_TRACE_FEXIT,
 	BPF_MODIFY_RETURN,
 	BPF_LSM_MAC,
+	BPF_TRACE_ITER,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 5a8119d17d14..dec182d8395a 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -12,6 +12,7 @@ struct bpf_iter_target_info {
 	bpf_iter_init_seq_priv_t init_seq_private;
 	bpf_iter_fini_seq_priv_t fini_seq_private;
 	u32 seq_priv_size;
+	u32 btf_id;	/* cached value */
 };
 
 static struct list_head targets = LIST_HEAD_INIT(targets);
@@ -57,3 +58,38 @@ void bpf_iter_unreg_target(const char *target)
 
 	WARN_ON(found == false);
 }
+
+static void cache_btf_id(struct bpf_iter_target_info *tinfo,
+			 struct bpf_prog *prog)
+{
+	tinfo->btf_id = prog->aux->attach_btf_id;
+}
+
+bool bpf_iter_prog_supported(struct bpf_prog *prog)
+{
+	const char *attach_fname = prog->aux->attach_func_name;
+	u32 prog_btf_id = prog->aux->attach_btf_id;
+	const char *prefix = BPF_ITER_FUNC_PREFIX;
+	struct bpf_iter_target_info *tinfo;
+	int prefix_len = strlen(prefix);
+	bool supported = false;
+
+	if (strncmp(attach_fname, prefix, prefix_len))
+		return false;
+
+	mutex_lock(&targets_mutex);
+	list_for_each_entry(tinfo, &targets, list) {
+		if (tinfo->btf_id && tinfo->btf_id == prog_btf_id) {
+			supported = true;
+			break;
+		}
+		if (!strcmp(attach_fname + prefix_len, tinfo->target)) {
+			cache_btf_id(tinfo, prog);
+			supported = true;
+			break;
+		}
+	}
+	mutex_unlock(&targets_mutex);
+
+	return supported;
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 70ad009577f8..d725ff7d11db 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7101,6 +7101,10 @@ static int check_return_code(struct bpf_verifier_env *env)
 			return 0;
 		range = tnum_const(0);
 		break;
+	case BPF_PROG_TYPE_TRACING:
+		if (env->prog->expected_attach_type != BPF_TRACE_ITER)
+			return 0;
+		break;
 	default:
 		return 0;
 	}
@@ -10481,6 +10485,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
 	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
+	struct btf_func_model fmodel;
 	int ret = 0, subprog = -1, i;
 	struct bpf_trampoline *tr;
 	const struct btf_type *t;
@@ -10622,6 +10627,22 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		prog->aux->attach_func_proto = t;
 		prog->aux->attach_btf_trace = true;
 		return 0;
+	case BPF_TRACE_ITER:
+		if (!btf_type_is_func(t)) {
+			verbose(env, "attach_btf_id %u is not a function\n",
+				btf_id);
+			return -EINVAL;
+		}
+		t = btf_type_by_id(btf, t->type);
+		if (!btf_type_is_func_proto(t))
+			return -EINVAL;
+		prog->aux->attach_func_name = tname;
+		prog->aux->attach_func_proto = t;
+		if (!bpf_iter_prog_supported(prog))
+			return -EINVAL;
+		ret = btf_distill_func_proto(&env->log, btf, t,
+					     tname, &fmodel);
+		return ret;
 	default:
 		if (!prog_extension)
 			return -EINVAL;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6e5e7caa3739..c8a5325cc8d0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -218,6 +218,7 @@ enum bpf_attach_type {
 	BPF_TRACE_FEXIT,
 	BPF_MODIFY_RETURN,
 	BPF_LSM_MAC,
+	BPF_TRACE_ITER,
 	__MAX_BPF_ATTACH_TYPE
 };
 
-- 
cgit v1.2.3


From de4e05cac46d206f9090051ef09930514bff73e4 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:01 -0700
Subject: bpf: Support bpf tracing/iter programs for BPF_LINK_CREATE

Given a bpf program, the step to create an anonymous bpf iterator is:
  - create a bpf_iter_link, which combines bpf program and the target.
    In the future, there could be more information recorded in the link.
    A link_fd will be returned to the user space.
  - create an anonymous bpf iterator with the given link_fd.

The bpf_iter_link can be pinned to bpffs mount file system to
create a file based bpf iterator as well.

The benefit to use of bpf_iter_link:
  - using bpf link simplifies design and implementation as bpf link
    is used for other tracing bpf programs.
  - for file based bpf iterator, bpf_iter_link provides a standard
    way to replace underlying bpf programs.
  - for both anonymous and free based iterators, bpf link query
    capability can be leveraged.

The patch added support of tracing/iter programs for BPF_LINK_CREATE.
A new link type BPF_LINK_TYPE_ITER is added to facilitate link
querying. Currently, only prog_id is needed, so there is no
additional in-kernel show_fdinfo() and fill_link_info() hook
is needed for BPF_LINK_TYPE_ITER link.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175901.2475084-1-yhs@fb.com
---
 include/linux/bpf.h            |  1 +
 include/linux/bpf_types.h      |  1 +
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/bpf_iter.c          | 62 ++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c           | 14 ++++++++++
 tools/include/uapi/linux/bpf.h |  1 +
 6 files changed, 80 insertions(+)

(limited to 'kernel')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f28bdd714754..e93d2d33c82c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1143,6 +1143,7 @@ struct bpf_iter_reg {
 int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const char *target);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
+int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 8345cdf553b8..29d22752fc87 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
 #ifdef CONFIG_CGROUP_BPF
 BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
 #endif
+BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c8a5325cc8d0..1e8dfff5d5d4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -229,6 +229,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
 	BPF_LINK_TYPE_TRACING = 2,
 	BPF_LINK_TYPE_CGROUP = 3,
+	BPF_LINK_TYPE_ITER = 4,
 
 	MAX_BPF_LINK_TYPE,
 };
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index dec182d8395a..03f5832909db 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -15,6 +15,11 @@ struct bpf_iter_target_info {
 	u32 btf_id;	/* cached value */
 };
 
+struct bpf_iter_link {
+	struct bpf_link link;
+	struct bpf_iter_target_info *tinfo;
+};
+
 static struct list_head targets = LIST_HEAD_INIT(targets);
 static DEFINE_MUTEX(targets_mutex);
 
@@ -93,3 +98,60 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog)
 
 	return supported;
 }
+
+static void bpf_iter_link_release(struct bpf_link *link)
+{
+}
+
+static void bpf_iter_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+
+	kfree(iter_link);
+}
+
+static const struct bpf_link_ops bpf_iter_link_lops = {
+	.release = bpf_iter_link_release,
+	.dealloc = bpf_iter_link_dealloc,
+};
+
+int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_link_primer link_primer;
+	struct bpf_iter_target_info *tinfo;
+	struct bpf_iter_link *link;
+	bool existed = false;
+	u32 prog_btf_id;
+	int err;
+
+	if (attr->link_create.target_fd || attr->link_create.flags)
+		return -EINVAL;
+
+	prog_btf_id = prog->aux->attach_btf_id;
+	mutex_lock(&targets_mutex);
+	list_for_each_entry(tinfo, &targets, list) {
+		if (tinfo->btf_id == prog_btf_id) {
+			existed = true;
+			break;
+		}
+	}
+	mutex_unlock(&targets_mutex);
+	if (!existed)
+		return -ENOENT;
+
+	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
+	if (!link)
+		return -ENOMEM;
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog);
+	link->tinfo = tinfo;
+
+	err  = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		return err;
+	}
+
+	return bpf_link_settle(&link_primer);
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index bb1ab7da6103..6ffe2d8fb6c7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2729,6 +2729,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	case BPF_CGROUP_GETSOCKOPT:
 	case BPF_CGROUP_SETSOCKOPT:
 		return BPF_PROG_TYPE_CGROUP_SOCKOPT;
+	case BPF_TRACE_ITER:
+		return BPF_PROG_TYPE_TRACING;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -3729,6 +3731,15 @@ err_put:
 	return err;
 }
 
+static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	if (attr->link_create.attach_type == BPF_TRACE_ITER &&
+	    prog->expected_attach_type == BPF_TRACE_ITER)
+		return bpf_iter_link_attach(attr, prog);
+
+	return -EINVAL;
+}
+
 #define BPF_LINK_CREATE_LAST_FIELD link_create.flags
 static int link_create(union bpf_attr *attr)
 {
@@ -3765,6 +3776,9 @@ static int link_create(union bpf_attr *attr)
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		ret = cgroup_bpf_link_attach(attr, prog);
 		break;
+	case BPF_PROG_TYPE_TRACING:
+		ret = tracing_bpf_link_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c8a5325cc8d0..1e8dfff5d5d4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -229,6 +229,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
 	BPF_LINK_TYPE_TRACING = 2,
 	BPF_LINK_TYPE_CGROUP = 3,
+	BPF_LINK_TYPE_ITER = 4,
 
 	MAX_BPF_LINK_TYPE,
 };
-- 
cgit v1.2.3


From 2057c92bc927f09b22f5609425eb37d7e782f484 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:02 -0700
Subject: bpf: Support bpf tracing/iter programs for BPF_LINK_UPDATE

Added BPF_LINK_UPDATE support for tracing/iter programs.
This way, a file based bpf iterator, which holds a reference
to the link, can have its bpf program updated without
creating new files.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175902.2475262-1-yhs@fb.com
---
 kernel/bpf/bpf_iter.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'kernel')

diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 03f5832909db..0542a243b78c 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -23,6 +23,9 @@ struct bpf_iter_link {
 static struct list_head targets = LIST_HEAD_INIT(targets);
 static DEFINE_MUTEX(targets_mutex);
 
+/* protect bpf_iter_link changes */
+static DEFINE_MUTEX(link_mutex);
+
 int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
 {
 	struct bpf_iter_target_info *tinfo;
@@ -111,9 +114,37 @@ static void bpf_iter_link_dealloc(struct bpf_link *link)
 	kfree(iter_link);
 }
 
+static int bpf_iter_link_replace(struct bpf_link *link,
+				 struct bpf_prog *new_prog,
+				 struct bpf_prog *old_prog)
+{
+	int ret = 0;
+
+	mutex_lock(&link_mutex);
+	if (old_prog && link->prog != old_prog) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+
+	if (link->prog->type != new_prog->type ||
+	    link->prog->expected_attach_type != new_prog->expected_attach_type ||
+	    link->prog->aux->attach_btf_id != new_prog->aux->attach_btf_id) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	old_prog = xchg(&link->prog, new_prog);
+	bpf_prog_put(old_prog);
+
+out_unlock:
+	mutex_unlock(&link_mutex);
+	return ret;
+}
+
 static const struct bpf_link_ops bpf_iter_link_lops = {
 	.release = bpf_iter_link_release,
 	.dealloc = bpf_iter_link_dealloc,
+	.update_prog = bpf_iter_link_replace,
 };
 
 int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
-- 
cgit v1.2.3


From fd4f12bc38c3ad9107169e7c9e6e7f81d93dda97 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:04 -0700
Subject: bpf: Implement bpf_seq_read() for bpf iterator

bpf iterator uses seq_file to provide a lossless
way to transfer data to user space. But we want to call
bpf program after all objects have been traversed, and
bpf program may write additional data to the
seq_file buffer. The current seq_read() does not work
for this use case.

Besides allowing stop() function to write to the buffer,
the bpf_seq_read() also fixed the buffer size to one page.
If any single call of show() or stop() will emit data
more than one page to cause overflow, -E2BIG error code
will be returned to user space.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175904.2475468-1-yhs@fb.com
---
 kernel/bpf/bpf_iter.c | 123 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 123 insertions(+)

(limited to 'kernel')

diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 0542a243b78c..832973ee80fa 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -26,6 +26,129 @@ static DEFINE_MUTEX(targets_mutex);
 /* protect bpf_iter_link changes */
 static DEFINE_MUTEX(link_mutex);
 
+/* bpf_seq_read, a customized and simpler version for bpf iterator.
+ * no_llseek is assumed for this file.
+ * The following are differences from seq_read():
+ *  . fixed buffer size (PAGE_SIZE)
+ *  . assuming no_llseek
+ *  . stop() may call bpf program, handling potential overflow there
+ */
+static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
+			    loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	size_t n, offs, copied = 0;
+	int err = 0;
+	void *p;
+
+	mutex_lock(&seq->lock);
+
+	if (!seq->buf) {
+		seq->size = PAGE_SIZE;
+		seq->buf = kmalloc(seq->size, GFP_KERNEL);
+		if (!seq->buf) {
+			err = -ENOMEM;
+			goto done;
+		}
+	}
+
+	if (seq->count) {
+		n = min(seq->count, size);
+		err = copy_to_user(buf, seq->buf + seq->from, n);
+		if (err) {
+			err = -EFAULT;
+			goto done;
+		}
+		seq->count -= n;
+		seq->from += n;
+		copied = n;
+		goto done;
+	}
+
+	seq->from = 0;
+	p = seq->op->start(seq, &seq->index);
+	if (!p)
+		goto stop;
+	if (IS_ERR(p)) {
+		err = PTR_ERR(p);
+		seq->op->stop(seq, p);
+		seq->count = 0;
+		goto done;
+	}
+
+	err = seq->op->show(seq, p);
+	if (err > 0) {
+		seq->count = 0;
+	} else if (err < 0 || seq_has_overflowed(seq)) {
+		if (!err)
+			err = -E2BIG;
+		seq->op->stop(seq, p);
+		seq->count = 0;
+		goto done;
+	}
+
+	while (1) {
+		loff_t pos = seq->index;
+
+		offs = seq->count;
+		p = seq->op->next(seq, p, &seq->index);
+		if (pos == seq->index) {
+			pr_info_ratelimited("buggy seq_file .next function %ps "
+				"did not updated position index\n",
+				seq->op->next);
+			seq->index++;
+		}
+
+		if (IS_ERR_OR_NULL(p))
+			break;
+
+		if (seq->count >= size)
+			break;
+
+		err = seq->op->show(seq, p);
+		if (err > 0) {
+			seq->count = offs;
+		} else if (err < 0 || seq_has_overflowed(seq)) {
+			seq->count = offs;
+			if (offs == 0) {
+				if (!err)
+					err = -E2BIG;
+				seq->op->stop(seq, p);
+				goto done;
+			}
+			break;
+		}
+	}
+stop:
+	offs = seq->count;
+	/* bpf program called if !p */
+	seq->op->stop(seq, p);
+	if (!p && seq_has_overflowed(seq)) {
+		seq->count = offs;
+		if (offs == 0) {
+			err = -E2BIG;
+			goto done;
+		}
+	}
+
+	n = min(seq->count, size);
+	err = copy_to_user(buf, seq->buf, n);
+	if (err) {
+		err = -EFAULT;
+		goto done;
+	}
+	copied = n;
+	seq->count -= n;
+	seq->from = n;
+done:
+	if (!copied)
+		copied = err;
+	else
+		*ppos += copied;
+	mutex_unlock(&seq->lock);
+	return copied;
+}
+
 int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
 {
 	struct bpf_iter_target_info *tinfo;
-- 
cgit v1.2.3


From ac51d99bf81caac8d8881fe52098948110d0de68 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:05 -0700
Subject: bpf: Create anonymous bpf iterator

A new bpf command BPF_ITER_CREATE is added.

The anonymous bpf iterator is seq_file based.
The seq_file private data are referenced by targets.
The bpf_iter infrastructure allocated additional space
at seq_file->private before the space used by targets
to store some meta data, e.g.,
  prog:       prog to run
  session_id: an unique id for each opened seq_file
  seq_num:    how many times bpf programs are queried in this session
  done_stop:  an internal state to decide whether bpf program
              should be called in seq_ops->stop() or not

The seq_num will start from 0 for valid objects.
The bpf program may see the same seq_num more than once if
 - seq_file buffer overflow happens and the same object
   is retried by bpf_seq_read(), or
 - the bpf program explicitly requests a retry of the
   same object

Since module is not supported for bpf_iter, all target
registeration happens at __init time, so there is no
need to change bpf_iter_unreg_target() as it is used
mostly in error path of the init function at which time
no bpf iterators have been created yet.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175905.2475770-1-yhs@fb.com
---
 include/linux/bpf.h            |   1 +
 include/uapi/linux/bpf.h       |   6 ++
 kernel/bpf/bpf_iter.c          | 129 +++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c           |  26 +++++++++
 tools/include/uapi/linux/bpf.h |   6 ++
 5 files changed, 168 insertions(+)

(limited to 'kernel')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e93d2d33c82c..80b1b9d8a638 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1144,6 +1144,7 @@ int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const char *target);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
 int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int bpf_iter_new_fd(struct bpf_link *link);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1e8dfff5d5d4..708763f702e1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -116,6 +116,7 @@ enum bpf_cmd {
 	BPF_LINK_GET_FD_BY_ID,
 	BPF_LINK_GET_NEXT_ID,
 	BPF_ENABLE_STATS,
+	BPF_ITER_CREATE,
 };
 
 enum bpf_map_type {
@@ -614,6 +615,11 @@ union bpf_attr {
 		__u32		type;
 	} enable_stats;
 
+	struct { /* struct used by BPF_ITER_CREATE command */
+		__u32		link_fd;
+		__u32		flags;
+	} iter_create;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 832973ee80fa..e7129b57865f 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Facebook */
 
 #include <linux/fs.h>
+#include <linux/anon_inodes.h>
 #include <linux/filter.h>
 #include <linux/bpf.h>
 
@@ -20,12 +21,24 @@ struct bpf_iter_link {
 	struct bpf_iter_target_info *tinfo;
 };
 
+struct bpf_iter_priv_data {
+	struct bpf_iter_target_info *tinfo;
+	struct bpf_prog *prog;
+	u64 session_id;
+	u64 seq_num;
+	bool done_stop;
+	u8 target_private[] __aligned(8);
+};
+
 static struct list_head targets = LIST_HEAD_INIT(targets);
 static DEFINE_MUTEX(targets_mutex);
 
 /* protect bpf_iter_link changes */
 static DEFINE_MUTEX(link_mutex);
 
+/* incremented on every opened seq_file */
+static atomic64_t session_id;
+
 /* bpf_seq_read, a customized and simpler version for bpf iterator.
  * no_llseek is assumed for this file.
  * The following are differences from seq_read():
@@ -149,6 +162,33 @@ done:
 	return copied;
 }
 
+static int iter_release(struct inode *inode, struct file *file)
+{
+	struct bpf_iter_priv_data *iter_priv;
+	struct seq_file *seq;
+
+	seq = file->private_data;
+	if (!seq)
+		return 0;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+
+	if (iter_priv->tinfo->fini_seq_private)
+		iter_priv->tinfo->fini_seq_private(seq->private);
+
+	bpf_prog_put(iter_priv->prog);
+	seq->private = iter_priv;
+
+	return seq_release_private(inode, file);
+}
+
+static const struct file_operations bpf_iter_fops = {
+	.llseek		= no_llseek,
+	.read		= bpf_seq_read,
+	.release	= iter_release,
+};
+
 int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
 {
 	struct bpf_iter_target_info *tinfo;
@@ -309,3 +349,92 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 
 	return bpf_link_settle(&link_primer);
 }
+
+static void init_seq_meta(struct bpf_iter_priv_data *priv_data,
+			  struct bpf_iter_target_info *tinfo,
+			  struct bpf_prog *prog)
+{
+	priv_data->tinfo = tinfo;
+	priv_data->prog = prog;
+	priv_data->session_id = atomic64_inc_return(&session_id);
+	priv_data->seq_num = 0;
+	priv_data->done_stop = false;
+}
+
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
+{
+	struct bpf_iter_priv_data *priv_data;
+	struct bpf_iter_target_info *tinfo;
+	struct bpf_prog *prog;
+	u32 total_priv_dsize;
+	struct seq_file *seq;
+	int err = 0;
+
+	mutex_lock(&link_mutex);
+	prog = link->link.prog;
+	bpf_prog_inc(prog);
+	mutex_unlock(&link_mutex);
+
+	tinfo = link->tinfo;
+	total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) +
+			   tinfo->seq_priv_size;
+	priv_data = __seq_open_private(file, tinfo->seq_ops, total_priv_dsize);
+	if (!priv_data) {
+		err = -ENOMEM;
+		goto release_prog;
+	}
+
+	if (tinfo->init_seq_private) {
+		err = tinfo->init_seq_private(priv_data->target_private);
+		if (err)
+			goto release_seq_file;
+	}
+
+	init_seq_meta(priv_data, tinfo, prog);
+	seq = file->private_data;
+	seq->private = priv_data->target_private;
+
+	return 0;
+
+release_seq_file:
+	seq_release_private(file->f_inode, file);
+	file->private_data = NULL;
+release_prog:
+	bpf_prog_put(prog);
+	return err;
+}
+
+int bpf_iter_new_fd(struct bpf_link *link)
+{
+	struct file *file;
+	unsigned int flags;
+	int err, fd;
+
+	if (link->ops != &bpf_iter_link_lops)
+		return -EINVAL;
+
+	flags = O_RDONLY | O_CLOEXEC;
+	fd = get_unused_fd_flags(flags);
+	if (fd < 0)
+		return fd;
+
+	file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto free_fd;
+	}
+
+	err = prepare_seq_file(file,
+			       container_of(link, struct bpf_iter_link, link));
+	if (err)
+		goto free_file;
+
+	fd_install(fd, file);
+	return fd;
+
+free_file:
+	fput(file);
+free_fd:
+	put_unused_fd(fd);
+	return err;
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6ffe2d8fb6c7..a293e88ee01a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3941,6 +3941,29 @@ static int bpf_enable_stats(union bpf_attr *attr)
 	return -EINVAL;
 }
 
+#define BPF_ITER_CREATE_LAST_FIELD iter_create.flags
+
+static int bpf_iter_create(union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	int err;
+
+	if (CHECK_ATTR(BPF_ITER_CREATE))
+		return -EINVAL;
+
+	if (attr->iter_create.flags)
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->iter_create.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	err = bpf_iter_new_fd(link);
+	bpf_link_put(link);
+
+	return err;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr;
@@ -4068,6 +4091,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_ENABLE_STATS:
 		err = bpf_enable_stats(&attr);
 		break;
+	case BPF_ITER_CREATE:
+		err = bpf_iter_create(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1e8dfff5d5d4..708763f702e1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -116,6 +116,7 @@ enum bpf_cmd {
 	BPF_LINK_GET_FD_BY_ID,
 	BPF_LINK_GET_NEXT_ID,
 	BPF_ENABLE_STATS,
+	BPF_ITER_CREATE,
 };
 
 enum bpf_map_type {
@@ -614,6 +615,11 @@ union bpf_attr {
 		__u32		type;
 	} enable_stats;
 
+	struct { /* struct used by BPF_ITER_CREATE command */
+		__u32		link_fd;
+		__u32		flags;
+	} iter_create;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
-- 
cgit v1.2.3


From 367ec3e4834cbd611401c2c40a23c22c825474f1 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:06 -0700
Subject: bpf: Create file bpf iterator

To produce a file bpf iterator, the fd must be
corresponding to a link_fd assocciated with a
trace/iter program. When the pinned file is
opened, a seq_file will be generated.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175906.2475893-1-yhs@fb.com
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/bpf_iter.c | 17 ++++++++++++++++-
 kernel/bpf/inode.c    |  5 ++++-
 3 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 80b1b9d8a638..b06653ab3476 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1022,6 +1022,7 @@ static inline void bpf_enable_instrumentation(void)
 
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
+extern const struct file_operations bpf_iter_fops;
 
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	extern const struct bpf_prog_ops _name ## _prog_ops; \
@@ -1145,6 +1146,7 @@ void bpf_iter_unreg_target(const char *target);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
 int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int bpf_iter_new_fd(struct bpf_link *link);
+bool bpf_link_is_iter(struct bpf_link *link);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index e7129b57865f..090f09b0eacb 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -39,6 +39,8 @@ static DEFINE_MUTEX(link_mutex);
 /* incremented on every opened seq_file */
 static atomic64_t session_id;
 
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link);
+
 /* bpf_seq_read, a customized and simpler version for bpf iterator.
  * no_llseek is assumed for this file.
  * The following are differences from seq_read():
@@ -162,6 +164,13 @@ done:
 	return copied;
 }
 
+static int iter_open(struct inode *inode, struct file *file)
+{
+	struct bpf_iter_link *link = inode->i_private;
+
+	return prepare_seq_file(file, link);
+}
+
 static int iter_release(struct inode *inode, struct file *file)
 {
 	struct bpf_iter_priv_data *iter_priv;
@@ -183,7 +192,8 @@ static int iter_release(struct inode *inode, struct file *file)
 	return seq_release_private(inode, file);
 }
 
-static const struct file_operations bpf_iter_fops = {
+const struct file_operations bpf_iter_fops = {
+	.open		= iter_open,
 	.llseek		= no_llseek,
 	.read		= bpf_seq_read,
 	.release	= iter_release,
@@ -310,6 +320,11 @@ static const struct bpf_link_ops bpf_iter_link_lops = {
 	.update_prog = bpf_iter_link_replace,
 };
 
+bool bpf_link_is_iter(struct bpf_link *link)
+{
+	return link->ops == &bpf_iter_link_lops;
+}
+
 int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct bpf_link_primer link_primer;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 95087d9f4ed3..fb878ba3f22f 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -358,8 +358,11 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
 
 static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg)
 {
+	struct bpf_link *link = arg;
+
 	return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops,
-			     &bpffs_obj_fops);
+			     bpf_link_is_iter(link) ?
+			     &bpf_iter_fops : &bpffs_obj_fops);
 }
 
 static struct dentry *
-- 
cgit v1.2.3


From e5158d987b72c3f318b4b52a01ac6f3997bd0c00 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:07 -0700
Subject: bpf: Implement common macros/helpers for target iterators

Macro DEFINE_BPF_ITER_FUNC is implemented so target
can define an init function to capture the BTF type
which represents the target.

The bpf_iter_meta is a structure holding meta data, common
to all targets in the bpf program.

Additional marker functions are called before or after
bpf_seq_read() show()/next()/stop() callback functions
to help calculate precise seq_num and whether call bpf_prog
inside stop().

Two functions, bpf_iter_get_info() and bpf_iter_run_prog(),
are implemented so target can get needed information from
bpf_iter infrastructure and can run the program.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175907.2475956-1-yhs@fb.com
---
 include/linux/bpf.h   | 11 +++++++
 kernel/bpf/bpf_iter.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 91 insertions(+), 5 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b06653ab3476..ffe0b9b669bf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1129,6 +1129,9 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
 int bpf_obj_get_user(const char __user *pathname, int flags);
 
 #define BPF_ITER_FUNC_PREFIX "__bpf_iter__"
+#define DEFINE_BPF_ITER_FUNC(target, args...)			\
+	extern int __bpf_iter__ ## target(args);		\
+	int __init __bpf_iter__ ## target(args) { return 0; }
 
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data);
 typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
@@ -1141,12 +1144,20 @@ struct bpf_iter_reg {
 	u32 seq_priv_size;
 };
 
+struct bpf_iter_meta {
+	__bpf_md_ptr(struct seq_file *, seq);
+	u64 session_id;
+	u64 seq_num;
+};
+
 int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const char *target);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
 int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int bpf_iter_new_fd(struct bpf_link *link);
 bool bpf_link_is_iter(struct bpf_link *link);
+struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
+int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 090f09b0eacb..30efd15cd4a0 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -41,6 +41,33 @@ static atomic64_t session_id;
 
 static int prepare_seq_file(struct file *file, struct bpf_iter_link *link);
 
+static void bpf_iter_inc_seq_num(struct seq_file *seq)
+{
+	struct bpf_iter_priv_data *iter_priv;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+	iter_priv->seq_num++;
+}
+
+static void bpf_iter_dec_seq_num(struct seq_file *seq)
+{
+	struct bpf_iter_priv_data *iter_priv;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+	iter_priv->seq_num--;
+}
+
+static void bpf_iter_done_stop(struct seq_file *seq)
+{
+	struct bpf_iter_priv_data *iter_priv;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+	iter_priv->done_stop = true;
+}
+
 /* bpf_seq_read, a customized and simpler version for bpf iterator.
  * no_llseek is assumed for this file.
  * The following are differences from seq_read():
@@ -93,6 +120,10 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 
 	err = seq->op->show(seq, p);
 	if (err > 0) {
+		/* object is skipped, decrease seq_num, so next
+		 * valid object can reuse the same seq_num.
+		 */
+		bpf_iter_dec_seq_num(seq);
 		seq->count = 0;
 	} else if (err < 0 || seq_has_overflowed(seq)) {
 		if (!err)
@@ -117,11 +148,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 		if (IS_ERR_OR_NULL(p))
 			break;
 
+		/* got a valid next object, increase seq_num */
+		bpf_iter_inc_seq_num(seq);
+
 		if (seq->count >= size)
 			break;
 
 		err = seq->op->show(seq, p);
 		if (err > 0) {
+			bpf_iter_dec_seq_num(seq);
 			seq->count = offs;
 		} else if (err < 0 || seq_has_overflowed(seq)) {
 			seq->count = offs;
@@ -138,11 +173,15 @@ stop:
 	offs = seq->count;
 	/* bpf program called if !p */
 	seq->op->stop(seq, p);
-	if (!p && seq_has_overflowed(seq)) {
-		seq->count = offs;
-		if (offs == 0) {
-			err = -E2BIG;
-			goto done;
+	if (!p) {
+		if (!seq_has_overflowed(seq)) {
+			bpf_iter_done_stop(seq);
+		} else {
+			seq->count = offs;
+			if (offs == 0) {
+				err = -E2BIG;
+				goto done;
+			}
 		}
 	}
 
@@ -453,3 +492,39 @@ free_fd:
 	put_unused_fd(fd);
 	return err;
 }
+
+struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop)
+{
+	struct bpf_iter_priv_data *iter_priv;
+	struct seq_file *seq;
+	void *seq_priv;
+
+	seq = meta->seq;
+	if (seq->file->f_op != &bpf_iter_fops)
+		return NULL;
+
+	seq_priv = seq->private;
+	iter_priv = container_of(seq_priv, struct bpf_iter_priv_data,
+				 target_private);
+
+	if (in_stop && iter_priv->done_stop)
+		return NULL;
+
+	meta->session_id = iter_priv->session_id;
+	meta->seq_num = iter_priv->seq_num;
+
+	return iter_priv->prog;
+}
+
+int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
+{
+	int ret;
+
+	rcu_read_lock();
+	migrate_disable();
+	ret = BPF_PROG_RUN(prog, ctx);
+	migrate_enable();
+	rcu_read_unlock();
+
+	return ret == 0 ? 0 : -EAGAIN;
+}
-- 
cgit v1.2.3


From 6086d29def80edd78f9832ea6eafa74e3818f6a7 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:09 -0700
Subject: bpf: Add bpf_map iterator

Implement seq_file operations to traverse all bpf_maps.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175909.2476096-1-yhs@fb.com
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/Makefile   |  2 +-
 kernel/bpf/map_iter.c | 97 +++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c  | 19 ++++++++++
 4 files changed, 118 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/map_iter.c

(limited to 'kernel')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ffe0b9b669bf..363ab0751967 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1082,6 +1082,7 @@ int  generic_map_update_batch(struct bpf_map *map,
 int  generic_map_delete_batch(struct bpf_map *map,
 			      const union bpf_attr *attr,
 			      union bpf_attr __user *uattr);
+struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 6a8b0febd3f6..b2b5eefc5254 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -2,7 +2,7 @@
 obj-y := core.o
 CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
new file mode 100644
index 000000000000..8162e0c00b9f
--- /dev/null
+++ b/kernel/bpf/map_iter.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <linux/fs.h>
+#include <linux/filter.h>
+#include <linux/kernel.h>
+
+struct bpf_iter_seq_map_info {
+	u32 mid;
+};
+
+static void *bpf_map_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_map_info *info = seq->private;
+	struct bpf_map *map;
+
+	map = bpf_map_get_curr_or_next(&info->mid);
+	if (!map)
+		return NULL;
+
+	++*pos;
+	return map;
+}
+
+static void *bpf_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_map_info *info = seq->private;
+	struct bpf_map *map;
+
+	++*pos;
+	++info->mid;
+	bpf_map_put((struct bpf_map *)v);
+	map = bpf_map_get_curr_or_next(&info->mid);
+	if (!map)
+		return NULL;
+
+	return map;
+}
+
+struct bpf_iter__bpf_map {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_map *, map);
+};
+
+DEFINE_BPF_ITER_FUNC(bpf_map, struct bpf_iter_meta *meta, struct bpf_map *map)
+
+static int __bpf_map_seq_show(struct seq_file *seq, void *v, bool in_stop)
+{
+	struct bpf_iter__bpf_map ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	ctx.meta = &meta;
+	ctx.map = v;
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (prog)
+		ret = bpf_iter_run_prog(prog, &ctx);
+
+	return ret;
+}
+
+static int bpf_map_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_map_seq_show(seq, v, false);
+}
+
+static void bpf_map_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__bpf_map_seq_show(seq, v, true);
+	else
+		bpf_map_put((struct bpf_map *)v);
+}
+
+static const struct seq_operations bpf_map_seq_ops = {
+	.start	= bpf_map_seq_start,
+	.next	= bpf_map_seq_next,
+	.stop	= bpf_map_seq_stop,
+	.show	= bpf_map_seq_show,
+};
+
+static int __init bpf_map_iter_init(void)
+{
+	struct bpf_iter_reg reg_info = {
+		.target			= "bpf_map",
+		.seq_ops		= &bpf_map_seq_ops,
+		.init_seq_private	= NULL,
+		.fini_seq_private	= NULL,
+		.seq_priv_size		= sizeof(struct bpf_iter_seq_map_info),
+	};
+
+	return bpf_iter_reg_target(&reg_info);
+}
+
+late_initcall(bpf_map_iter_init);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a293e88ee01a..de2a75500233 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2934,6 +2934,25 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr,
 	return err;
 }
 
+struct bpf_map *bpf_map_get_curr_or_next(u32 *id)
+{
+	struct bpf_map *map;
+
+	spin_lock_bh(&map_idr_lock);
+again:
+	map = idr_get_next(&map_idr, id);
+	if (map) {
+		map = __bpf_map_inc_not_zero(map, false);
+		if (IS_ERR(map)) {
+			(*id)++;
+			goto again;
+		}
+	}
+	spin_unlock_bh(&map_idr_lock);
+
+	return map;
+}
+
 #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
 
 struct bpf_prog *bpf_prog_by_id(u32 id)
-- 
cgit v1.2.3


From eaaacd23910f2d7c4b22d43f591002cc217d294b Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:11 -0700
Subject: bpf: Add task and task/file iterator targets

Only the tasks belonging to "current" pid namespace
are enumerated.

For task/file target, the bpf program will have access to
  struct task_struct *task
  u32 fd
  struct file *file
where fd/file is an open file for the task.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
---
 kernel/bpf/Makefile    |   2 +-
 kernel/bpf/task_iter.c | 333 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 334 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/task_iter.c

(limited to 'kernel')

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index b2b5eefc5254..37b2d8620153 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -2,7 +2,7 @@
 obj-y := core.o
 CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
new file mode 100644
index 000000000000..aeed662d8451
--- /dev/null
+++ b/kernel/bpf/task_iter.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/pid_namespace.h>
+#include <linux/fs.h>
+#include <linux/fdtable.h>
+#include <linux/filter.h>
+
+struct bpf_iter_seq_task_common {
+	struct pid_namespace *ns;
+};
+
+struct bpf_iter_seq_task_info {
+	/* The first field must be struct bpf_iter_seq_task_common.
+	 * this is assumed by {init, fini}_seq_pidns() callback functions.
+	 */
+	struct bpf_iter_seq_task_common common;
+	u32 tid;
+};
+
+static struct task_struct *task_seq_get_next(struct pid_namespace *ns,
+					     u32 *tid)
+{
+	struct task_struct *task = NULL;
+	struct pid *pid;
+
+	rcu_read_lock();
+	pid = idr_get_next(&ns->idr, tid);
+	if (pid)
+		task = get_pid_task(pid, PIDTYPE_PID);
+	rcu_read_unlock();
+
+	return task;
+}
+
+static void *task_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_task_info *info = seq->private;
+	struct task_struct *task;
+
+	task = task_seq_get_next(info->common.ns, &info->tid);
+	if (!task)
+		return NULL;
+
+	++*pos;
+	return task;
+}
+
+static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_task_info *info = seq->private;
+	struct task_struct *task;
+
+	++*pos;
+	++info->tid;
+	put_task_struct((struct task_struct *)v);
+	task = task_seq_get_next(info->common.ns, &info->tid);
+	if (!task)
+		return NULL;
+
+	return task;
+}
+
+struct bpf_iter__task {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct task_struct *, task);
+};
+
+DEFINE_BPF_ITER_FUNC(task, struct bpf_iter_meta *meta, struct task_struct *task)
+
+static int __task_seq_show(struct seq_file *seq, struct task_struct *task,
+			   bool in_stop)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_iter__task ctx;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	meta.seq = seq;
+	ctx.meta = &meta;
+	ctx.task = task;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int task_seq_show(struct seq_file *seq, void *v)
+{
+	return __task_seq_show(seq, v, false);
+}
+
+static void task_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__task_seq_show(seq, v, true);
+	else
+		put_task_struct((struct task_struct *)v);
+}
+
+static const struct seq_operations task_seq_ops = {
+	.start	= task_seq_start,
+	.next	= task_seq_next,
+	.stop	= task_seq_stop,
+	.show	= task_seq_show,
+};
+
+struct bpf_iter_seq_task_file_info {
+	/* The first field must be struct bpf_iter_seq_task_common.
+	 * this is assumed by {init, fini}_seq_pidns() callback functions.
+	 */
+	struct bpf_iter_seq_task_common common;
+	struct task_struct *task;
+	struct files_struct *files;
+	u32 tid;
+	u32 fd;
+};
+
+static struct file *
+task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info,
+		       struct task_struct **task, struct files_struct **fstruct)
+{
+	struct pid_namespace *ns = info->common.ns;
+	u32 curr_tid = info->tid, max_fds;
+	struct files_struct *curr_files;
+	struct task_struct *curr_task;
+	int curr_fd = info->fd;
+
+	/* If this function returns a non-NULL file object,
+	 * it held a reference to the task/files_struct/file.
+	 * Otherwise, it does not hold any reference.
+	 */
+again:
+	if (*task) {
+		curr_task = *task;
+		curr_files = *fstruct;
+		curr_fd = info->fd;
+	} else {
+		curr_task = task_seq_get_next(ns, &curr_tid);
+		if (!curr_task)
+			return NULL;
+
+		curr_files = get_files_struct(curr_task);
+		if (!curr_files) {
+			put_task_struct(curr_task);
+			curr_tid = ++(info->tid);
+			info->fd = 0;
+			goto again;
+		}
+
+		/* set *fstruct, *task and info->tid */
+		*fstruct = curr_files;
+		*task = curr_task;
+		if (curr_tid == info->tid) {
+			curr_fd = info->fd;
+		} else {
+			info->tid = curr_tid;
+			curr_fd = 0;
+		}
+	}
+
+	rcu_read_lock();
+	max_fds = files_fdtable(curr_files)->max_fds;
+	for (; curr_fd < max_fds; curr_fd++) {
+		struct file *f;
+
+		f = fcheck_files(curr_files, curr_fd);
+		if (!f)
+			continue;
+
+		/* set info->fd */
+		info->fd = curr_fd;
+		get_file(f);
+		rcu_read_unlock();
+		return f;
+	}
+
+	/* the current task is done, go to the next task */
+	rcu_read_unlock();
+	put_files_struct(curr_files);
+	put_task_struct(curr_task);
+	*task = NULL;
+	*fstruct = NULL;
+	info->fd = 0;
+	curr_tid = ++(info->tid);
+	goto again;
+}
+
+static void *task_file_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+	struct files_struct *files = NULL;
+	struct task_struct *task = NULL;
+	struct file *file;
+
+	file = task_file_seq_get_next(info, &task, &files);
+	if (!file) {
+		info->files = NULL;
+		info->task = NULL;
+		return NULL;
+	}
+
+	++*pos;
+	info->task = task;
+	info->files = files;
+
+	return file;
+}
+
+static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+	struct files_struct *files = info->files;
+	struct task_struct *task = info->task;
+	struct file *file;
+
+	++*pos;
+	++info->fd;
+	fput((struct file *)v);
+	file = task_file_seq_get_next(info, &task, &files);
+	if (!file) {
+		info->files = NULL;
+		info->task = NULL;
+		return NULL;
+	}
+
+	info->task = task;
+	info->files = files;
+
+	return file;
+}
+
+struct bpf_iter__task_file {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct task_struct *, task);
+	u32 fd __aligned(8);
+	__bpf_md_ptr(struct file *, file);
+};
+
+DEFINE_BPF_ITER_FUNC(task_file, struct bpf_iter_meta *meta,
+		     struct task_struct *task, u32 fd,
+		     struct file *file)
+
+static int __task_file_seq_show(struct seq_file *seq, struct file *file,
+				bool in_stop)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+	struct bpf_iter__task_file ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.task = info->task;
+	ctx.fd = info->fd;
+	ctx.file = file;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int task_file_seq_show(struct seq_file *seq, void *v)
+{
+	return __task_file_seq_show(seq, v, false);
+}
+
+static void task_file_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+
+	if (!v) {
+		(void)__task_file_seq_show(seq, v, true);
+	} else {
+		fput((struct file *)v);
+		put_files_struct(info->files);
+		put_task_struct(info->task);
+		info->files = NULL;
+		info->task = NULL;
+	}
+}
+
+static int init_seq_pidns(void *priv_data)
+{
+	struct bpf_iter_seq_task_common *common = priv_data;
+
+	common->ns = get_pid_ns(task_active_pid_ns(current));
+	return 0;
+}
+
+static void fini_seq_pidns(void *priv_data)
+{
+	struct bpf_iter_seq_task_common *common = priv_data;
+
+	put_pid_ns(common->ns);
+}
+
+static const struct seq_operations task_file_seq_ops = {
+	.start	= task_file_seq_start,
+	.next	= task_file_seq_next,
+	.stop	= task_file_seq_stop,
+	.show	= task_file_seq_show,
+};
+
+static int __init task_iter_init(void)
+{
+	struct bpf_iter_reg task_file_reg_info = {
+		.target			= "task_file",
+		.seq_ops		= &task_file_seq_ops,
+		.init_seq_private	= init_seq_pidns,
+		.fini_seq_private	= fini_seq_pidns,
+		.seq_priv_size		= sizeof(struct bpf_iter_seq_task_file_info),
+	};
+	struct bpf_iter_reg task_reg_info = {
+		.target			= "task",
+		.seq_ops		= &task_seq_ops,
+		.init_seq_private	= init_seq_pidns,
+		.fini_seq_private	= fini_seq_pidns,
+		.seq_priv_size		= sizeof(struct bpf_iter_seq_task_info),
+	};
+	int ret;
+
+	ret = bpf_iter_reg_target(&task_reg_info);
+	if (ret)
+		return ret;
+
+	return bpf_iter_reg_target(&task_file_reg_info);
+}
+late_initcall(task_iter_init);
-- 
cgit v1.2.3


From b121b341e5983bdccf7a5d6cf9236a45c965a31f Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:12 -0700
Subject: bpf: Add PTR_TO_BTF_ID_OR_NULL support

Add bpf_reg_type PTR_TO_BTF_ID_OR_NULL support.
For tracing/iter program, the bpf program context
definition, e.g., for previous bpf_map target, looks like
  struct bpf_iter__bpf_map {
    struct bpf_iter_meta *meta;
    struct bpf_map *map;
  };

The kernel guarantees that meta is not NULL, but
map pointer maybe NULL. The NULL map indicates that all
objects have been traversed, so bpf program can take
proper action, e.g., do final aggregation and/or send
final report to user space.

Add btf_id_or_null_non0_off to prog->aux structure, to
indicate that if the context access offset is not 0,
set to PTR_TO_BTF_ID_OR_NULL instead of PTR_TO_BTF_ID.
This bit is set for tracing/iter program.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175912.2476576-1-yhs@fb.com
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/btf.c      |  5 ++++-
 kernel/bpf/verifier.c | 16 ++++++++++++----
 3 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 363ab0751967..cf4b6e44f2bc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -320,6 +320,7 @@ enum bpf_reg_type {
 	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 */
+	PTR_TO_BTF_ID_OR_NULL,	 /* reg points to kernel struct or NULL */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -658,6 +659,7 @@ struct bpf_prog_aux {
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
 	bool func_proto_unreliable;
+	bool btf_id_or_null_non0_off;
 	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a2cfba89a8e1..c490fbde22d4 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3790,7 +3790,10 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		return true;
 
 	/* this is a pointer to another type */
-	info->reg_type = PTR_TO_BTF_ID;
+	if (off != 0 && prog->aux->btf_id_or_null_non0_off)
+		info->reg_type = PTR_TO_BTF_ID_OR_NULL;
+	else
+		info->reg_type = PTR_TO_BTF_ID;
 
 	if (tgt_prog) {
 		ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d725ff7d11db..36b2a38a06fe 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -398,7 +398,8 @@ static bool reg_type_may_be_null(enum bpf_reg_type type)
 	return type == PTR_TO_MAP_VALUE_OR_NULL ||
 	       type == PTR_TO_SOCKET_OR_NULL ||
 	       type == PTR_TO_SOCK_COMMON_OR_NULL ||
-	       type == PTR_TO_TCP_SOCK_OR_NULL;
+	       type == PTR_TO_TCP_SOCK_OR_NULL ||
+	       type == PTR_TO_BTF_ID_OR_NULL;
 }
 
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
@@ -483,6 +484,7 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_TP_BUFFER]	= "tp_buffer",
 	[PTR_TO_XDP_SOCK]	= "xdp_sock",
 	[PTR_TO_BTF_ID]		= "ptr_",
+	[PTR_TO_BTF_ID_OR_NULL]	= "ptr_or_null_",
 };
 
 static char slot_type_char[] = {
@@ -543,7 +545,7 @@ 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)
+			if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL)
 				verbose(env, "%s", kernel_type_name(reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
@@ -2139,6 +2141,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
+	case PTR_TO_BTF_ID_OR_NULL:
 		return true;
 	default:
 		return false;
@@ -2659,7 +2662,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		 */
 		*reg_type = info.reg_type;
 
-		if (*reg_type == PTR_TO_BTF_ID)
+		if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL)
 			*btf_id = info.btf_id;
 		else
 			env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
@@ -3243,7 +3246,8 @@ 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)
+				if (reg_type == PTR_TO_BTF_ID ||
+				    reg_type == PTR_TO_BTF_ID_OR_NULL)
 					regs[value_regno].btf_id = btf_id;
 			}
 			regs[value_regno].type = reg_type;
@@ -6572,6 +6576,8 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 			reg->type = PTR_TO_SOCK_COMMON;
 		} else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) {
 			reg->type = PTR_TO_TCP_SOCK;
+		} else if (reg->type == PTR_TO_BTF_ID_OR_NULL) {
+			reg->type = PTR_TO_BTF_ID;
 		}
 		if (is_null) {
 			/* We don't need id and ref_obj_id from this point
@@ -8429,6 +8435,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type)
 	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
+	case PTR_TO_BTF_ID_OR_NULL:
 		return false;
 	default:
 		return true;
@@ -10640,6 +10647,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		prog->aux->attach_func_proto = t;
 		if (!bpf_iter_prog_supported(prog))
 			return -EINVAL;
+		prog->aux->btf_id_or_null_non0_off = true;
 		ret = btf_distill_func_proto(&env->log, btf, t,
 					     tname, &fmodel);
 		return ret;
-- 
cgit v1.2.3


From 492e639f0c222784e2e0f121966375f641c61b15 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:14 -0700
Subject: bpf: Add bpf_seq_printf and bpf_seq_write helpers

Two helpers bpf_seq_printf and bpf_seq_write, are added for
writing data to the seq_file buffer.

bpf_seq_printf supports common format string flag/width/type
fields so at least I can get identical results for
netlink and ipv6_route targets.

For bpf_seq_printf and bpf_seq_write, return value -EOVERFLOW
specifically indicates a write failure due to overflow, which
means the object will be repeated in the next bpf invocation
if object collection stays the same. Note that if the object
collection is changed, depending how collection traversal is
done, even if the object still in the collection, it may not
be visited.

For bpf_seq_printf, format %s, %p{i,I}{4,6} needs to
read kernel memory. Reading kernel memory may fail in
the following two cases:
  - invalid kernel address, or
  - valid kernel address but requiring a major fault
If reading kernel memory failed, the %s string will be
an empty string and %p{i,I}{4,6} will be all 0.
Not returning error to bpf program is consistent with
what bpf_trace_printk() does for now.

bpf_seq_printf may return -EBUSY meaning that internal percpu
buffer for memory copy of strings or other pointees is
not available. Bpf program can return 1 to indicate it
wants the same object to be repeated. Right now, this should not
happen on no-RT kernels since migrate_disable(), which guards
bpf prog call, calls preempt_disable().

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175914.2476661-1-yhs@fb.com
---
 include/uapi/linux/bpf.h       |  39 +++++++-
 kernel/trace/bpf_trace.c       | 214 +++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |   2 +
 tools/include/uapi/linux/bpf.h |  39 +++++++-
 4 files changed, 292 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 708763f702e1..9d1932e23cec 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3077,6 +3077,41 @@ union bpf_attr {
  * 		See: clock_gettime(CLOCK_BOOTTIME)
  * 	Return
  * 		Current *ktime*.
+ *
+ * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * 	Description
+ * 		seq_printf uses seq_file seq_printf() to print out the format string.
+ * 		The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * 		the format string itself. The *data* and *data_len* are format string
+ * 		arguments. The *data* are a u64 array and corresponding format string
+ * 		values are stored in the array. For strings and pointers where pointees
+ * 		are accessed, only the pointer values are stored in the *data* array.
+ * 		The *data_len* is the *data* size in term of bytes.
+ *
+ *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ *		Reading kernel memory may fail due to either invalid address or
+ *		valid address but requiring a major memory fault. If reading kernel memory
+ *		fails, the string for **%s** will be an empty string, and the ip
+ *		address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ *		bpf program is consistent with what bpf_trace_printk() does for now.
+ * 	Return
+ * 		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EBUSY**		Percpu memory copy buffer is busy, can try again
+ *					by returning 1 from bpf program.
+ *		* **-EINVAL**		Invalid arguments, or invalid/unsupported formats.
+ *		* **-E2BIG**		Too many format specifiers.
+ *		* **-EOVERFLOW**	Overflow happens, the same object will be tried again.
+ *
+ * int bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * 	Description
+ * 		seq_write uses seq_file seq_write() to write the data.
+ * 		The *m* represents the seq_file. The *data* and *len* represent the
+ *		data to write in bytes.
+ * 	Return
+ * 		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EOVERFLOW**	Overflow happens, the same object will be tried again.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3204,7 +3239,9 @@ union bpf_attr {
 	FN(get_netns_cookie),		\
 	FN(get_current_ancestor_cgroup_id),	\
 	FN(sk_assign),			\
-	FN(ktime_get_boot_ns),
+	FN(ktime_get_boot_ns),		\
+	FN(seq_printf),			\
+	FN(seq_write),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e875c95d3ced..d961428fb5b6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -457,6 +457,212 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
+#define MAX_SEQ_PRINTF_VARARGS		12
+#define MAX_SEQ_PRINTF_MAX_MEMCPY	6
+#define MAX_SEQ_PRINTF_STR_LEN		128
+
+struct bpf_seq_printf_buf {
+	char buf[MAX_SEQ_PRINTF_MAX_MEMCPY][MAX_SEQ_PRINTF_STR_LEN];
+};
+static DEFINE_PER_CPU(struct bpf_seq_printf_buf, bpf_seq_printf_buf);
+static DEFINE_PER_CPU(int, bpf_seq_printf_buf_used);
+
+BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
+	   const void *, data, u32, data_len)
+{
+	int err = -EINVAL, fmt_cnt = 0, memcpy_cnt = 0;
+	int i, buf_used, copy_size, num_args;
+	u64 params[MAX_SEQ_PRINTF_VARARGS];
+	struct bpf_seq_printf_buf *bufs;
+	const u64 *args = data;
+
+	buf_used = this_cpu_inc_return(bpf_seq_printf_buf_used);
+	if (WARN_ON_ONCE(buf_used > 1)) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	bufs = this_cpu_ptr(&bpf_seq_printf_buf);
+
+	/*
+	 * bpf_check()->check_func_arg()->check_stack_boundary()
+	 * guarantees that fmt points to bpf program stack,
+	 * fmt_size bytes of it were initialized and fmt_size > 0
+	 */
+	if (fmt[--fmt_size] != 0)
+		goto out;
+
+	if (data_len & 7)
+		goto out;
+
+	for (i = 0; i < fmt_size; i++) {
+		if (fmt[i] == '%') {
+			if (fmt[i + 1] == '%')
+				i++;
+			else if (!data || !data_len)
+				goto out;
+		}
+	}
+
+	num_args = data_len / 8;
+
+	/* check format string for allowed specifiers */
+	for (i = 0; i < fmt_size; i++) {
+		/* only printable ascii for now. */
+		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (fmt[i] != '%')
+			continue;
+
+		if (fmt[i + 1] == '%') {
+			i++;
+			continue;
+		}
+
+		if (fmt_cnt >= MAX_SEQ_PRINTF_VARARGS) {
+			err = -E2BIG;
+			goto out;
+		}
+
+		if (fmt_cnt >= num_args) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
+		i++;
+
+		/* skip optional "[0 +-][num]" width formating field */
+		while (fmt[i] == '0' || fmt[i] == '+'  || fmt[i] == '-' ||
+		       fmt[i] == ' ')
+			i++;
+		if (fmt[i] >= '1' && fmt[i] <= '9') {
+			i++;
+			while (fmt[i] >= '0' && fmt[i] <= '9')
+				i++;
+		}
+
+		if (fmt[i] == 's') {
+			/* try our best to copy */
+			if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+				err = -E2BIG;
+				goto out;
+			}
+
+			err = strncpy_from_unsafe(bufs->buf[memcpy_cnt],
+						  (void *) (long) args[fmt_cnt],
+						  MAX_SEQ_PRINTF_STR_LEN);
+			if (err < 0)
+				bufs->buf[memcpy_cnt][0] = '\0';
+			params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+			fmt_cnt++;
+			memcpy_cnt++;
+			continue;
+		}
+
+		if (fmt[i] == 'p') {
+			if (fmt[i + 1] == 0 ||
+			    fmt[i + 1] == 'K' ||
+			    fmt[i + 1] == 'x') {
+				/* just kernel pointers */
+				params[fmt_cnt] = args[fmt_cnt];
+				fmt_cnt++;
+				continue;
+			}
+
+			/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
+			if (fmt[i + 1] != 'i' && fmt[i + 1] != 'I') {
+				err = -EINVAL;
+				goto out;
+			}
+			if (fmt[i + 2] != '4' && fmt[i + 2] != '6') {
+				err = -EINVAL;
+				goto out;
+			}
+
+			if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+				err = -E2BIG;
+				goto out;
+			}
+
+
+			copy_size = (fmt[i + 2] == '4') ? 4 : 16;
+
+			err = probe_kernel_read(bufs->buf[memcpy_cnt],
+						(void *) (long) args[fmt_cnt],
+						copy_size);
+			if (err < 0)
+				memset(bufs->buf[memcpy_cnt], 0, copy_size);
+			params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+			i += 2;
+			fmt_cnt++;
+			memcpy_cnt++;
+			continue;
+		}
+
+		if (fmt[i] == 'l') {
+			i++;
+			if (fmt[i] == 'l')
+				i++;
+		}
+
+		if (fmt[i] != 'i' && fmt[i] != 'd' &&
+		    fmt[i] != 'u' && fmt[i] != 'x') {
+			err = -EINVAL;
+			goto out;
+		}
+
+		params[fmt_cnt] = args[fmt_cnt];
+		fmt_cnt++;
+	}
+
+	/* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give
+	 * all of them to seq_printf().
+	 */
+	seq_printf(m, fmt, params[0], params[1], params[2], params[3],
+		   params[4], params[5], params[6], params[7], params[8],
+		   params[9], params[10], params[11]);
+
+	err = seq_has_overflowed(m) ? -EOVERFLOW : 0;
+out:
+	this_cpu_dec(bpf_seq_printf_buf_used);
+	return err;
+}
+
+static int bpf_seq_printf_btf_ids[5];
+static const struct bpf_func_proto bpf_seq_printf_proto = {
+	.func		= bpf_seq_printf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_seq_printf_btf_ids,
+};
+
+BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
+{
+	return seq_write(m, data, len) ? -EOVERFLOW : 0;
+}
+
+static int bpf_seq_write_btf_ids[5];
+static const struct bpf_func_proto bpf_seq_write_proto = {
+	.func		= bpf_seq_write,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_seq_write_btf_ids,
+};
+
 static __always_inline int
 get_map_perf_counter(struct bpf_map *map, u64 flags,
 		     u64 *value, u64 *enabled, u64 *running)
@@ -1226,6 +1432,14 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_xdp_output:
 		return &bpf_xdp_output_proto;
 #endif
+	case BPF_FUNC_seq_printf:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_printf_proto :
+		       NULL;
+	case BPF_FUNC_seq_write:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_write_proto :
+		       NULL;
 	default:
 		return raw_tp_prog_func_proto(func_id, prog);
 	}
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index f43d193aff3a..ded304c96a05 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -414,6 +414,7 @@ class PrinterHelpers(Printer):
             'struct sk_reuseport_md',
             'struct sockaddr',
             'struct tcphdr',
+            'struct seq_file',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -450,6 +451,7 @@ class PrinterHelpers(Printer):
             'struct sk_reuseport_md',
             'struct sockaddr',
             'struct tcphdr',
+            'struct seq_file',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 708763f702e1..9d1932e23cec 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3077,6 +3077,41 @@ union bpf_attr {
  * 		See: clock_gettime(CLOCK_BOOTTIME)
  * 	Return
  * 		Current *ktime*.
+ *
+ * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * 	Description
+ * 		seq_printf uses seq_file seq_printf() to print out the format string.
+ * 		The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * 		the format string itself. The *data* and *data_len* are format string
+ * 		arguments. The *data* are a u64 array and corresponding format string
+ * 		values are stored in the array. For strings and pointers where pointees
+ * 		are accessed, only the pointer values are stored in the *data* array.
+ * 		The *data_len* is the *data* size in term of bytes.
+ *
+ *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ *		Reading kernel memory may fail due to either invalid address or
+ *		valid address but requiring a major memory fault. If reading kernel memory
+ *		fails, the string for **%s** will be an empty string, and the ip
+ *		address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ *		bpf program is consistent with what bpf_trace_printk() does for now.
+ * 	Return
+ * 		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EBUSY**		Percpu memory copy buffer is busy, can try again
+ *					by returning 1 from bpf program.
+ *		* **-EINVAL**		Invalid arguments, or invalid/unsupported formats.
+ *		* **-E2BIG**		Too many format specifiers.
+ *		* **-EOVERFLOW**	Overflow happens, the same object will be tried again.
+ *
+ * int bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * 	Description
+ * 		seq_write uses seq_file seq_write() to write the data.
+ * 		The *m* represents the seq_file. The *data* and *len* represent the
+ *		data to write in bytes.
+ * 	Return
+ * 		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EOVERFLOW**	Overflow happens, the same object will be tried again.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3204,7 +3239,9 @@ union bpf_attr {
 	FN(get_netns_cookie),		\
 	FN(get_current_ancestor_cgroup_id),	\
 	FN(sk_assign),			\
-	FN(ktime_get_boot_ns),
+	FN(ktime_get_boot_ns),		\
+	FN(seq_printf),			\
+	FN(seq_write),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 1d68f22b3d53d368d5cc8d09de890250cae5c945 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:15 -0700
Subject: bpf: Handle spilled PTR_TO_BTF_ID properly when checking
 stack_boundary

This specifically to handle the case like below:
   // ptr below is a socket ptr identified by PTR_TO_BTF_ID
   u64 param[2] = { ptr, val };
   bpf_seq_printf(seq, fmt, sizeof(fmt), param, sizeof(param));

In this case, the 16 bytes stack for "param" contains:
   8 bytes for ptr with spilled PTR_TO_BTF_ID
   8 bytes for val as STACK_MISC

The current verifier will complain the ptr should not be visible
to the helper.
   ...
   16: (7b) *(u64 *)(r10 -64) = r2
   18: (7b) *(u64 *)(r10 -56) = r1
   19: (bf) r4 = r10
   ;
   20: (07) r4 += -64
   ; BPF_SEQ_PRINTF(seq, fmt1, (long)s, s->sk_protocol);
   21: (bf) r1 = r6
   22: (18) r2 = 0xffffa8d00018605a
   24: (b4) w3 = 10
   25: (b4) w5 = 16
   26: (85) call bpf_seq_printf#125
    R0=inv(id=0) R1_w=ptr_seq_file(id=0,off=0,imm=0)
    R2_w=map_value(id=0,off=90,ks=4,vs=144,imm=0) R3_w=inv10
    R4_w=fp-64 R5_w=inv16 R6=ptr_seq_file(id=0,off=0,imm=0)
    R7=ptr_netlink_sock(id=0,off=0,imm=0) R10=fp0 fp-56_w=mmmmmmmm
    fp-64_w=ptr_
   last_idx 26 first_idx 13
   regs=8 stack=0 before 25: (b4) w5 = 16
   regs=8 stack=0 before 24: (b4) w3 = 10
   invalid indirect read from stack off -64+0 size 16

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175915.2476783-1-yhs@fb.com
---
 kernel/bpf/verifier.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'kernel')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 36b2a38a06fe..2a1826c76bb6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3494,6 +3494,11 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 			*stype = STACK_MISC;
 			goto mark;
 		}
+
+		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		    state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
+			goto mark;
+
 		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
 		    state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
 			__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
-- 
cgit v1.2.3


From 9c5f8a1008a121e4c6b24af211034e24b0b63081 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 9 May 2020 10:59:16 -0700
Subject: bpf: Support variable length array in tracing programs

In /proc/net/ipv6_route, we have
  struct fib6_info {
    struct fib6_table *fib6_table;
    ...
    struct fib6_nh fib6_nh[0];
  }
  struct fib6_nh {
    struct fib_nh_common nh_common;
    struct rt6_info **rt6i_pcpu;
    struct rt6_exception_bucket *rt6i_exception_bucket;
  };
  struct fib_nh_common {
    ...
    u8 nhc_gw_family;
    ...
  }

The access:
  struct fib6_nh *fib6_nh = &rt->fib6_nh;
  ... fib6_nh->nh_common.nhc_gw_family ...

This patch ensures such an access is handled properly.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200509175916.2476853-1-yhs@fb.com
---
 kernel/bpf/btf.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

(limited to 'kernel')

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index c490fbde22d4..dcd233139294 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3833,6 +3833,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
 	const struct btf_type *mtype, *elem_type = NULL;
 	const struct btf_member *member;
 	const char *tname, *mname;
+	u32 vlen;
 
 again:
 	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
@@ -3841,7 +3842,43 @@ again:
 		return -EINVAL;
 	}
 
+	vlen = btf_type_vlen(t);
 	if (off + size > t->size) {
+		/* If the last element is a variable size array, we may
+		 * need to relax the rule.
+		 */
+		struct btf_array *array_elem;
+
+		if (vlen == 0)
+			goto error;
+
+		member = btf_type_member(t) + vlen - 1;
+		mtype = btf_type_skip_modifiers(btf_vmlinux, member->type,
+						NULL);
+		if (!btf_type_is_array(mtype))
+			goto error;
+
+		array_elem = (struct btf_array *)(mtype + 1);
+		if (array_elem->nelems != 0)
+			goto error;
+
+		moff = btf_member_bit_offset(t, member) / 8;
+		if (off < moff)
+			goto error;
+
+		/* Only allow structure for now, can be relaxed for
+		 * other types later.
+		 */
+		elem_type = btf_type_skip_modifiers(btf_vmlinux,
+						    array_elem->type, NULL);
+		if (!btf_type_is_struct(elem_type))
+			goto error;
+
+		off = (off - moff) % elem_type->size;
+		return btf_struct_access(log, elem_type, off, size, atype,
+					 next_btf_id);
+
+error:
 		bpf_log(log, "access beyond struct %s at off %u size %u\n",
 			tname, off, size);
 		return -EACCES;
-- 
cgit v1.2.3