From 7b146cebe30cb481b0f70d85779da938da818637 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 27 Feb 2019 12:59:24 -0800
Subject: bpf: Sysctl hook

Containerized applications may run as root and it may create problems
for whole host. Specifically such applications may change a sysctl and
affect applications in other containers.

Furthermore in existing infrastructure it may not be possible to just
completely disable writing to sysctl, instead such a process should be
gradual with ability to log what sysctl are being changed by a
container, investigate, limit the set of writable sysctl to currently
used ones (so that new ones can not be changed) and eventually reduce
this set to zero.

The patch introduces new program type BPF_PROG_TYPE_CGROUP_SYSCTL and
attach type BPF_CGROUP_SYSCTL to solve these problems on cgroup basis.

New program type has access to following minimal context:
	struct bpf_sysctl {
		__u32	write;
	};

Where @write indicates whether sysctl is being read (= 0) or written (=
1).

Helpers to access sysctl name and value will be introduced separately.

BPF_CGROUP_SYSCTL attach point is added to sysctl code right before
passing control to ctl_table->proc_handler so that BPF program can
either allow or deny access to sysctl.

Suggested-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf-cgroup.h | 18 ++++++++++++++++++
 include/linux/bpf_types.h  |  1 +
 include/linux/filter.h     |  8 ++++++++
 3 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index a4c644c1c091..b1c45da20a26 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -17,6 +17,8 @@ struct bpf_map;
 struct bpf_prog;
 struct bpf_sock_ops_kern;
 struct bpf_cgroup_storage;
+struct ctl_table;
+struct ctl_table_header;
 
 #ifdef CONFIG_CGROUP_BPF
 
@@ -109,6 +111,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum bpf_attach_type type);
 
+int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
+				   struct ctl_table *table, int write,
+				   enum bpf_attach_type type);
+
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
 {
@@ -253,6 +259,17 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 									      \
 	__ret;								      \
 })
+
+
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
+						       BPF_CGROUP_SYSCTL);     \
+	__ret;								       \
+})
+
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog);
 int cgroup_bpf_prog_detach(const union bpf_attr *attr,
@@ -321,6 +338,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 08bf2f1fe553..d26991a16894 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -28,6 +28,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
 #endif
 #ifdef CONFIG_BPF_LIRC_MODE2
 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6074aa064b54..a17732057880 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -33,6 +33,8 @@ struct bpf_prog_aux;
 struct xdp_rxq_info;
 struct xdp_buff;
 struct sock_reuseport;
+struct ctl_table;
+struct ctl_table_header;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -1177,4 +1179,10 @@ struct bpf_sock_ops_kern {
 					 */
 };
 
+struct bpf_sysctl_kern {
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	int write;
+};
+
 #endif /* __LINUX_FILTER_H__ */
-- 
cgit v1.2.3


From 1d11b3016cec4ed9770b98e82a61708c8f4926e7 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 28 Feb 2019 19:22:15 -0800
Subject: bpf: Introduce bpf_sysctl_get_current_value helper

Add bpf_sysctl_get_current_value() helper to copy current sysctl value
into provided by BPF_PROG_TYPE_CGROUP_SYSCTL program buffer.

It provides same string as user space can see by reading corresponding
file in /proc/sys/, including new line, etc.

Documentation for the new helper is provided in bpf.h UAPI.

Since current value is kept in ctl_table->data in a parsed form,
ctl_table->proc_handler() with write=0 is called to read that data and
convert it to a string. Such a string can later be parsed by a program
using helpers that will be introduced separately.

Unfortunately it's not trivial to provide API to access parsed data due to
variety of data representations (string, intvec, uintvec, ulongvec,
custom structures, even NULL, etc). Instead it's assumed that user know
how to handle specific sysctl they're interested in and appropriate
helpers can be used.

Since ctl_table->proc_handler() expects __user buffer, conversion to
__user happens for kernel allocated one where the value is stored.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h   |  2 ++
 include/uapi/linux/bpf.h | 22 +++++++++++++++-
 kernel/bpf/cgroup.c      | 65 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 88 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index a17732057880..f254ff92819f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1182,6 +1182,8 @@ struct bpf_sock_ops_kern {
 struct bpf_sysctl_kern {
 	struct ctl_table_header *head;
 	struct ctl_table *table;
+	void *cur_val;
+	size_t cur_len;
 	int write;
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9c8a2f3ccb9b..063543afa359 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2522,6 +2522,25 @@ union bpf_attr {
  *
  *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
  *		truncated name in this case).
+ *
+ * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ *	Description
+ *		Get current value of sysctl as it is presented in /proc/sys
+ *		(incl. newline, etc), and copy it as a string into provided
+ *		by program buffer *buf* of size *buf_len*.
+ *
+ *		The whole value is copied, no matter what file position user
+ *		space issued e.g. sys_read at.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
+ *
+ *		**-EINVAL** if current value was unavailable, e.g. because
+ *		sysctl is uninitialized and read returns -EIO for it.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2625,7 +2644,8 @@ union bpf_attr {
 	FN(get_listener_sock),		\
 	FN(skc_lookup_tcp),		\
 	FN(tcp_check_syncookie),	\
-	FN(sysctl_get_name),
+	FN(sysctl_get_name),		\
+	FN(sysctl_get_current_value),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a68387043244..c6b2cf29a54b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -794,15 +794,37 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		.head = head,
 		.table = table,
 		.write = write,
+		.cur_val = NULL,
+		.cur_len = PAGE_SIZE,
 	};
 	struct cgroup *cgrp;
 	int ret;
 
+	ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL);
+	if (ctx.cur_val) {
+		mm_segment_t old_fs;
+		loff_t pos = 0;
+
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		if (table->proc_handler(table, 0, (void __user *)ctx.cur_val,
+					&ctx.cur_len, &pos)) {
+			/* Let BPF program decide how to proceed. */
+			ctx.cur_len = 0;
+		}
+		set_fs(old_fs);
+	} else {
+		/* Let BPF program decide how to proceed. */
+		ctx.cur_len = 0;
+	}
+
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
 	rcu_read_unlock();
 
+	kfree(ctx.cur_val);
+
 	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
@@ -869,12 +891,55 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+static int copy_sysctl_value(char *dst, size_t dst_len, char *src,
+			     size_t src_len)
+{
+	if (!dst)
+		return -EINVAL;
+
+	if (!dst_len)
+		return -E2BIG;
+
+	if (!src || !src_len) {
+		memset(dst, 0, dst_len);
+		return -EINVAL;
+	}
+
+	memcpy(dst, src, min(dst_len, src_len));
+
+	if (dst_len > src_len) {
+		memset(dst + src_len, '\0', dst_len - src_len);
+		return src_len;
+	}
+
+	dst[dst_len - 1] = '\0';
+
+	return -E2BIG;
+}
+
+BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx,
+	   char *, buf, size_t, buf_len)
+{
+	return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len);
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = {
+	.func		= bpf_sysctl_get_current_value,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sysctl_get_name:
 		return &bpf_sysctl_get_name_proto;
+	case BPF_FUNC_sysctl_get_current_value:
+		return &bpf_sysctl_get_current_value_proto;
 	default:
 		return cgroup_base_func_proto(func_id, prog);
 	}
-- 
cgit v1.2.3


From 4e63acdff864654cee0ac5aaeda3913798ee78f6 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 7 Mar 2019 18:38:43 -0800
Subject: bpf: Introduce bpf_sysctl_{get,set}_new_value helpers

Add helpers to work with new value being written to sysctl by user
space.

bpf_sysctl_get_new_value() copies value being written to sysctl into
provided buffer.

bpf_sysctl_set_new_value() overrides new value being written by user
space with a one from provided buffer. Buffer should contain string
representation of the value, similar to what can be seen in /proc/sys/.

Both helpers can be used only on sysctl write.

File position matters and can be managed by an interface that will be
introduced separately. E.g. if user space calls sys_write to a file in
/proc/sys/ at file position = X, where X > 0, then the value set by
bpf_sysctl_set_new_value() will be written starting from X. If program
wants to override whole value with specified buffer, file position has
to be set to zero.

Documentation for the new helpers is provided in bpf.h UAPI.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 fs/proc/proc_sysctl.c      | 22 ++++++++++---
 include/linux/bpf-cgroup.h |  8 +++--
 include/linux/filter.h     |  3 ++
 include/uapi/linux/bpf.h   | 38 +++++++++++++++++++++-
 kernel/bpf/cgroup.c        | 81 +++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 142 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index e01b02150340..023101c6f0d7 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -570,8 +570,8 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 	struct inode *inode = file_inode(filp);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+	void *new_buf = NULL;
 	ssize_t error;
-	size_t res;
 
 	if (IS_ERR(head))
 		return PTR_ERR(head);
@@ -589,15 +589,27 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 	if (!table->proc_handler)
 		goto out;
 
-	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write);
+	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count,
+					   &new_buf);
 	if (error)
 		goto out;
 
 	/* careful: calling conventions are nasty here */
-	res = count;
-	error = table->proc_handler(table, write, buf, &res, ppos);
+	if (new_buf) {
+		mm_segment_t old_fs;
+
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		error = table->proc_handler(table, write, (void __user *)new_buf,
+					    &count, ppos);
+		set_fs(old_fs);
+		kfree(new_buf);
+	} else {
+		error = table->proc_handler(table, write, buf, &count, ppos);
+	}
+
 	if (!error)
-		error = res;
+		error = count;
 out:
 	sysctl_head_finish(head);
 
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index b1c45da20a26..1e97271f9a10 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -113,7 +113,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   enum bpf_attach_type type);
+				   void __user *buf, size_t *pcount,
+				   void **new_buf, enum bpf_attach_type type);
 
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
@@ -261,11 +262,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 })
 
 
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write)			       \
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, nbuf)       \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled)						       \
 		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
+						       buf, count, nbuf,       \
 						       BPF_CGROUP_SYSCTL);     \
 	__ret;								       \
 })
@@ -338,7 +340,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,nbuf) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f254ff92819f..a23653f9460c 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1184,6 +1184,9 @@ struct bpf_sysctl_kern {
 	struct ctl_table *table;
 	void *cur_val;
 	size_t cur_len;
+	void *new_val;
+	size_t new_len;
+	int new_updated;
 	int write;
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 063543afa359..547b8258d731 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2541,6 +2541,40 @@ union bpf_attr {
  *
  *		**-EINVAL** if current value was unavailable, e.g. because
  *		sysctl is uninitialized and read returns -EIO for it.
+ *
+ * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ *	Description
+ *		Get new value being written by user space to sysctl (before
+ *		the actual write happens) and copy it as a string into
+ *		provided by program buffer *buf* of size *buf_len*.
+ *
+ *		User space may write new value at file position > 0.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
+ *
+ *		**-EINVAL** if sysctl is being read.
+ *
+ * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ *	Description
+ *		Override new value being written by user space to sysctl with
+ *		value provided by program in buffer *buf* of size *buf_len*.
+ *
+ *		*buf* should contain a string in same form as provided by user
+ *		space on sysctl write.
+ *
+ *		User space may write new value at file position > 0. To override
+ *		the whole sysctl value file position should be set to zero.
+ *	Return
+ *		0 on success.
+ *
+ *		**-E2BIG** if the *buf_len* is too big.
+ *
+ *		**-EINVAL** if sysctl is being read.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2645,7 +2679,9 @@ union bpf_attr {
 	FN(skc_lookup_tcp),		\
 	FN(tcp_check_syncookie),	\
 	FN(sysctl_get_name),		\
-	FN(sysctl_get_current_value),
+	FN(sysctl_get_current_value),	\
+	FN(sysctl_get_new_value),	\
+	FN(sysctl_set_new_value),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index c6b2cf29a54b..ba4e21986760 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -778,6 +778,13 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @head: sysctl table header
  * @table: sysctl table
  * @write: sysctl is being read (= 0) or written (= 1)
+ * @buf: pointer to buffer passed by user space
+ * @pcount: value-result argument: value is size of buffer pointed to by @buf,
+ *	result is size of @new_buf if program set new value, initial value
+ *	otherwise
+ * @new_buf: pointer to pointer to new buffer that will be allocated if program
+ *	overrides new value provided by user space on sysctl write
+ *	NOTE: it's caller responsibility to free *new_buf if it was set
  * @type: type of program to be executed
  *
  * Program is run when sysctl is being accessed, either read or written, and
@@ -788,7 +795,8 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  */
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   enum bpf_attach_type type)
+				   void __user *buf, size_t *pcount,
+				   void **new_buf, enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {
 		.head = head,
@@ -796,6 +804,9 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		.write = write,
 		.cur_val = NULL,
 		.cur_len = PAGE_SIZE,
+		.new_val = NULL,
+		.new_len = 0,
+		.new_updated = 0,
 	};
 	struct cgroup *cgrp;
 	int ret;
@@ -818,6 +829,18 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		ctx.cur_len = 0;
 	}
 
+	if (write && buf && *pcount) {
+		/* BPF program should be able to override new value with a
+		 * buffer bigger than provided by user.
+		 */
+		ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL);
+		ctx.new_len = min(PAGE_SIZE, *pcount);
+		if (!ctx.new_val ||
+		    copy_from_user(ctx.new_val, buf, ctx.new_len))
+			/* Let BPF program decide how to proceed. */
+			ctx.new_len = 0;
+	}
+
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
@@ -825,6 +848,13 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 
 	kfree(ctx.cur_val);
 
+	if (ret == 1 && ctx.new_updated) {
+		*new_buf = ctx.new_val;
+		*pcount = ctx.new_len;
+	} else {
+		kfree(ctx.new_val);
+	}
+
 	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
@@ -932,6 +962,51 @@ static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = {
 	.arg3_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf,
+	   size_t, buf_len)
+{
+	if (!ctx->write) {
+		if (buf && buf_len)
+			memset(buf, '\0', buf_len);
+		return -EINVAL;
+	}
+	return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len);
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = {
+	.func		= bpf_sysctl_get_new_value,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx,
+	   const char *, buf, size_t, buf_len)
+{
+	if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len)
+		return -EINVAL;
+
+	if (buf_len > PAGE_SIZE - 1)
+		return -E2BIG;
+
+	memcpy(ctx->new_val, buf, buf_len);
+	ctx->new_len = buf_len;
+	ctx->new_updated = 1;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
+	.func		= bpf_sysctl_set_new_value,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -940,6 +1015,10 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sysctl_get_name_proto;
 	case BPF_FUNC_sysctl_get_current_value:
 		return &bpf_sysctl_get_current_value_proto;
+	case BPF_FUNC_sysctl_get_new_value:
+		return &bpf_sysctl_get_new_value_proto;
+	case BPF_FUNC_sysctl_set_new_value:
+		return &bpf_sysctl_set_new_value_proto;
 	default:
 		return cgroup_base_func_proto(func_id, prog);
 	}
-- 
cgit v1.2.3


From e1550bfe0de47e30484ba91de1e50a91ec1c31f5 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 7 Mar 2019 18:50:52 -0800
Subject: bpf: Add file_pos field to bpf_sysctl ctx

Add file_pos field to bpf_sysctl context to read and write sysctl file
position at which sysctl is being accessed (read or written).

The field can be used to e.g. override whole sysctl value on write to
sysctl even when sys_write is called by user space with file_pos > 0. Or
BPF program may reject such accesses.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 fs/proc/proc_sysctl.c      |  2 +-
 include/linux/bpf-cgroup.h |  9 ++++----
 include/linux/filter.h     |  3 +++
 include/uapi/linux/bpf.h   |  3 +++
 kernel/bpf/cgroup.c        | 54 +++++++++++++++++++++++++++++++++++++++++++---
 5 files changed, 63 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 023101c6f0d7..2d61e5e8c863 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -590,7 +590,7 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 		goto out;
 
 	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count,
-					   &new_buf);
+					   ppos, &new_buf);
 	if (error)
 		goto out;
 
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 1e97271f9a10..cb3c6b3b89c8 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -114,7 +114,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
 				   void __user *buf, size_t *pcount,
-				   void **new_buf, enum bpf_attach_type type);
+				   loff_t *ppos, void **new_buf,
+				   enum bpf_attach_type type);
 
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
@@ -262,12 +263,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 })
 
 
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, nbuf)       \
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf)  \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled)						       \
 		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
-						       buf, count, nbuf,       \
+						       buf, count, pos, nbuf,  \
 						       BPF_CGROUP_SYSCTL);     \
 	__ret;								       \
 })
@@ -340,7 +341,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,nbuf) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a23653f9460c..fb0edad75971 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1188,6 +1188,9 @@ struct bpf_sysctl_kern {
 	size_t new_len;
 	int new_updated;
 	int write;
+	loff_t *ppos;
+	/* Temporary "register" for indirect stores to ppos. */
+	u64 tmp_reg;
 };
 
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 547b8258d731..89976de909af 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3391,6 +3391,9 @@ struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.
 				 */
+	__u32	file_pos;	/* Sysctl file position to read from, write to.
+				 * Allows 1,2,4-byte read an 4-byte write.
+				 */
 };
 
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ba4e21986760..b2adf22139b3 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -782,6 +782,9 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @pcount: value-result argument: value is size of buffer pointed to by @buf,
  *	result is size of @new_buf if program set new value, initial value
  *	otherwise
+ * @ppos: value-result argument: value is position at which read from or write
+ *	to sysctl is happening, result is new position if program overrode it,
+ *	initial value otherwise
  * @new_buf: pointer to pointer to new buffer that will be allocated if program
  *	overrides new value provided by user space on sysctl write
  *	NOTE: it's caller responsibility to free *new_buf if it was set
@@ -796,12 +799,14 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
 				   void __user *buf, size_t *pcount,
-				   void **new_buf, enum bpf_attach_type type)
+				   loff_t *ppos, void **new_buf,
+				   enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {
 		.head = head,
 		.table = table,
 		.write = write,
+		.ppos = ppos,
 		.cur_val = NULL,
 		.cur_len = PAGE_SIZE,
 		.new_val = NULL,
@@ -1030,14 +1035,22 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
 {
 	const int size_default = sizeof(__u32);
 
-	if (off < 0 || off + size > sizeof(struct bpf_sysctl) ||
-	    off % size || type != BPF_READ)
+	if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size)
 		return false;
 
 	switch (off) {
 	case offsetof(struct bpf_sysctl, write):
+		if (type != BPF_READ)
+			return false;
 		bpf_ctx_record_field_size(info, size_default);
 		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	case offsetof(struct bpf_sysctl, file_pos):
+		if (type == BPF_READ) {
+			bpf_ctx_record_field_size(info, size_default);
+			return bpf_ctx_narrow_access_ok(off, size, size_default);
+		} else {
+			return size == size_default;
+		}
 	default:
 		return false;
 	}
@@ -1059,6 +1072,41 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
 						    write),
 				       target_size));
 		break;
+	case offsetof(struct bpf_sysctl, file_pos):
+		/* ppos is a pointer so it should be accessed via indirect
+		 * loads and stores. Also for stores additional temporary
+		 * register is used since neither src_reg nor dst_reg can be
+		 * overridden.
+		 */
+		if (type == BPF_WRITE) {
+			int treg = BPF_REG_9;
+
+			if (si->src_reg == treg || si->dst_reg == treg)
+				--treg;
+			if (si->src_reg == treg || si->dst_reg == treg)
+				--treg;
+			*insn++ = BPF_STX_MEM(
+				BPF_DW, si->dst_reg, treg,
+				offsetof(struct bpf_sysctl_kern, tmp_reg));
+			*insn++ = BPF_LDX_MEM(
+				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
+				treg, si->dst_reg,
+				offsetof(struct bpf_sysctl_kern, ppos));
+			*insn++ = BPF_STX_MEM(
+				BPF_SIZEOF(u32), treg, si->src_reg, 0);
+			*insn++ = BPF_LDX_MEM(
+				BPF_DW, treg, si->dst_reg,
+				offsetof(struct bpf_sysctl_kern, tmp_reg));
+		} else {
+			*insn++ = BPF_LDX_MEM(
+				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
+				si->dst_reg, si->src_reg,
+				offsetof(struct bpf_sysctl_kern, ppos));
+			*insn++ = BPF_LDX_MEM(
+				BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0);
+		}
+		*target_size = sizeof(u32);
+		break;
 	}
 
 	return insn - insn_buf;
-- 
cgit v1.2.3


From 57c3bb725a3dd97d960d7e1cd0845d88de53217f Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 18 Mar 2019 16:57:10 -0700
Subject: bpf: Introduce ARG_PTR_TO_{INT,LONG} arg types

Currently the way to pass result from BPF helper to BPF program is to
provide memory area defined by pointer and size: func(void *, size_t).

It works great for generic use-case, but for simple types, such as int,
it's overkill and consumes two arguments when it could use just one.

Introduce new argument types ARG_PTR_TO_INT and ARG_PTR_TO_LONG to be
able to pass result from helper to program via pointer to int and long
correspondingly: func(int *) or func(long *).

New argument types are similar to ARG_PTR_TO_MEM with the following
differences:
* they don't require corresponding ARG_CONST_SIZE argument, predefined
  access sizes are used instead (32bit for int, 64bit for long);
* it's possible to use more than one such an argument in a helper;
* provided pointers have to be aligned.

It's easy to introduce similar ARG_PTR_TO_CHAR and ARG_PTR_TO_SHORT
argument types. It's not done due to lack of use-case though.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/verifier.c | 29 +++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e4d4c1771ab0..fd06ada941ad 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -202,6 +202,8 @@ enum bpf_arg_type {
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
+	ARG_PTR_TO_INT,		/* pointer to int */
+	ARG_PTR_TO_LONG,	/* pointer to long */
 };
 
 /* type of values returned from helper functions */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 20808e3c95a8..15ab6fa817ce 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2462,6 +2462,22 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
 	       type == ARG_CONST_SIZE_OR_ZERO;
 }
 
+static bool arg_type_is_int_ptr(enum bpf_arg_type type)
+{
+	return type == ARG_PTR_TO_INT ||
+	       type == ARG_PTR_TO_LONG;
+}
+
+static int int_ptr_type_to_size(enum bpf_arg_type type)
+{
+	if (type == ARG_PTR_TO_INT)
+		return sizeof(u32);
+	else if (type == ARG_PTR_TO_LONG)
+		return sizeof(u64);
+
+	return -EINVAL;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			  enum bpf_arg_type arg_type,
 			  struct bpf_call_arg_meta *meta)
@@ -2554,6 +2570,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			 type != expected_type)
 			goto err_type;
 		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
+	} else if (arg_type_is_int_ptr(arg_type)) {
+		expected_type = PTR_TO_STACK;
+		if (!type_is_pkt_pointer(type) &&
+		    type != PTR_TO_MAP_VALUE &&
+		    type != expected_type)
+			goto err_type;
 	} else {
 		verbose(env, "unsupported arg_type %d\n", arg_type);
 		return -EFAULT;
@@ -2635,6 +2657,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		err = check_helper_mem_access(env, regno - 1,
 					      reg->umax_value,
 					      zero_size_allowed, meta);
+	} else if (arg_type_is_int_ptr(arg_type)) {
+		int size = int_ptr_type_to_size(arg_type);
+
+		err = check_helper_mem_access(env, regno, size, false, meta);
+		if (err)
+			return err;
+		err = check_ptr_alignment(env, reg, 0, size, true);
 	}
 
 	return err;
-- 
cgit v1.2.3


From d7a4cb9b6705a89937d12c8158a35a3145dc967a Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 18 Mar 2019 17:55:26 -0700
Subject: bpf: Introduce bpf_strtol and bpf_strtoul helpers

Add bpf_strtol and bpf_strtoul to convert a string to long and unsigned
long correspondingly. It's similar to user space strtol(3) and
strtoul(3) with a few changes to the API:

* instead of NUL-terminated C string the helpers expect buffer and
  buffer length;

* resulting long or unsigned long is returned in a separate
  result-argument;

* return value is used to indicate success or failure, on success number
  of consumed bytes is returned that can be used to identify position to
  read next if the buffer is expected to contain multiple integers;

* instead of *base* argument, *flags* is used that provides base in 5
  LSB, other bits are reserved for future use;

* number of supported bases is limited.

Documentation for the new helpers is provided in bpf.h UAPI.

The helpers are made available to BPF_PROG_TYPE_CGROUP_SYSCTL programs to
be able to convert string input to e.g. "ulongvec" output.

E.g. "net/ipv4/tcp_mem" consists of three ulong integers. They can be
parsed by calling to bpf_strtoul three times.

Implementation notes:

Implementation includes "../../lib/kstrtox.h" to reuse integer parsing
functions. It's done exactly same way as fs/proc/base.c already does.

Unfortunately existing kstrtoX function can't be used directly since
they fail if any invalid character is present right after integer in the
string. Existing simple_strtoX functions can't be used either since
they're obsolete and don't handle overflow properly.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      |   2 +
 include/uapi/linux/bpf.h |  51 +++++++++++++++++-
 kernel/bpf/cgroup.c      |   4 ++
 kernel/bpf/helpers.c     | 131 +++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 187 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fd06ada941ad..f15432d90728 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -989,6 +989,8 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
 extern const struct bpf_func_proto bpf_spin_lock_proto;
 extern const struct bpf_func_proto bpf_spin_unlock_proto;
 extern const struct bpf_func_proto bpf_get_local_storage_proto;
+extern const struct bpf_func_proto bpf_strtol_proto;
+extern const struct bpf_func_proto bpf_strtoul_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 89976de909af..c26be24fd5e2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2575,6 +2575,53 @@ union bpf_attr {
  *		**-E2BIG** if the *buf_len* is too big.
  *
  *		**-EINVAL** if sysctl is being read.
+ *
+ * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ *	Description
+ *		Convert the initial part of the string from buffer *buf* of
+ *		size *buf_len* to a long integer according to the given base
+ *		and save the result in *res*.
+ *
+ *		The string may begin with an arbitrary amount of white space
+ *		(as determined by isspace(3)) followed by a single optional '-'
+ *		sign.
+ *
+ *		Five least significant bits of *flags* encode base, other bits
+ *		are currently unused.
+ *
+ *		Base must be either 8, 10, 16 or 0 to detect it automatically
+ *		similar to user space strtol(3).
+ *	Return
+ *		Number of characters consumed on success. Must be positive but
+ *		no more than buf_len.
+ *
+ *		**-EINVAL** if no valid digits were found or unsupported base
+ *		was provided.
+ *
+ *		**-ERANGE** if resulting value was out of range.
+ *
+ * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ *	Description
+ *		Convert the initial part of the string from buffer *buf* of
+ *		size *buf_len* to an unsigned long integer according to the
+ *		given base and save the result in *res*.
+ *
+ *		The string may begin with an arbitrary amount of white space
+ *		(as determined by isspace(3)).
+ *
+ *		Five least significant bits of *flags* encode base, other bits
+ *		are currently unused.
+ *
+ *		Base must be either 8, 10, 16 or 0 to detect it automatically
+ *		similar to user space strtoul(3).
+ *	Return
+ *		Number of characters consumed on success. Must be positive but
+ *		no more than buf_len.
+ *
+ *		**-EINVAL** if no valid digits were found or unsupported base
+ *		was provided.
+ *
+ *		**-ERANGE** if resulting value was out of range.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2681,7 +2728,9 @@ union bpf_attr {
 	FN(sysctl_get_name),		\
 	FN(sysctl_get_current_value),	\
 	FN(sysctl_get_new_value),	\
-	FN(sysctl_set_new_value),
+	FN(sysctl_set_new_value),	\
+	FN(strtol),			\
+	FN(strtoul),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index b2adf22139b3..789d4ab2336e 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1016,6 +1016,10 @@ static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+	case BPF_FUNC_strtol:
+		return &bpf_strtol_proto;
+	case BPF_FUNC_strtoul:
+		return &bpf_strtoul_proto;
 	case BPF_FUNC_sysctl_get_name:
 		return &bpf_sysctl_get_name_proto;
 	case BPF_FUNC_sysctl_get_current_value:
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a411fc17d265..4266ffde07ca 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -18,6 +18,9 @@
 #include <linux/sched.h>
 #include <linux/uidgid.h>
 #include <linux/filter.h>
+#include <linux/ctype.h>
+
+#include "../../lib/kstrtox.h"
 
 /* If kernel subsystem is allowing eBPF programs to call this function,
  * inside its own verifier_ops->get_func_proto() callback it should return
@@ -363,4 +366,132 @@ const struct bpf_func_proto bpf_get_local_storage_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 #endif
+
+#define BPF_STRTOX_BASE_MASK 0x1F
+
+static int __bpf_strtoull(const char *buf, size_t buf_len, u64 flags,
+			  unsigned long long *res, bool *is_negative)
+{
+	unsigned int base = flags & BPF_STRTOX_BASE_MASK;
+	const char *cur_buf = buf;
+	size_t cur_len = buf_len;
+	unsigned int consumed;
+	size_t val_len;
+	char str[64];
+
+	if (!buf || !buf_len || !res || !is_negative)
+		return -EINVAL;
+
+	if (base != 0 && base != 8 && base != 10 && base != 16)
+		return -EINVAL;
+
+	if (flags & ~BPF_STRTOX_BASE_MASK)
+		return -EINVAL;
+
+	while (cur_buf < buf + buf_len && isspace(*cur_buf))
+		++cur_buf;
+
+	*is_negative = (cur_buf < buf + buf_len && *cur_buf == '-');
+	if (*is_negative)
+		++cur_buf;
+
+	consumed = cur_buf - buf;
+	cur_len -= consumed;
+	if (!cur_len)
+		return -EINVAL;
+
+	cur_len = min(cur_len, sizeof(str) - 1);
+	memcpy(str, cur_buf, cur_len);
+	str[cur_len] = '\0';
+	cur_buf = str;
+
+	cur_buf = _parse_integer_fixup_radix(cur_buf, &base);
+	val_len = _parse_integer(cur_buf, base, res);
+
+	if (val_len & KSTRTOX_OVERFLOW)
+		return -ERANGE;
+
+	if (val_len == 0)
+		return -EINVAL;
+
+	cur_buf += val_len;
+	consumed += cur_buf - str;
+
+	return consumed;
+}
+
+static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags,
+			 long long *res)
+{
+	unsigned long long _res;
+	bool is_negative;
+	int err;
+
+	err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
+	if (err < 0)
+		return err;
+	if (is_negative) {
+		if ((long long)-_res > 0)
+			return -ERANGE;
+		*res = -_res;
+	} else {
+		if ((long long)_res < 0)
+			return -ERANGE;
+		*res = _res;
+	}
+	return err;
+}
+
+BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags,
+	   long *, res)
+{
+	long long _res;
+	int err;
+
+	err = __bpf_strtoll(buf, buf_len, flags, &_res);
+	if (err < 0)
+		return err;
+	if (_res != (long)_res)
+		return -ERANGE;
+	*res = _res;
+	return err;
+}
+
+const struct bpf_func_proto bpf_strtol_proto = {
+	.func		= bpf_strtol,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags,
+	   unsigned long *, res)
+{
+	unsigned long long _res;
+	bool is_negative;
+	int err;
+
+	err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
+	if (err < 0)
+		return err;
+	if (is_negative)
+		return -EINVAL;
+	if (_res != (unsigned long)_res)
+		return -ERANGE;
+	*res = _res;
+	return err;
+}
+
+const struct bpf_func_proto bpf_strtoul_proto = {
+	.func		= bpf_strtoul,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_LONG,
+};
 #endif
-- 
cgit v1.2.3


From ba0509b6881efd0c8b26c36490cba87d8fb324c0 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 12 Apr 2019 17:07:37 +0200
Subject: net: core: introduce build_skb_around

The function build_skb() also have the responsibility to allocate and clear
the SKB structure. Introduce a new function build_skb_around(), that moves
the responsibility of allocation and clearing to the caller. This allows
caller to use kmem_cache (slab/slub) bulk allocation API.

Next patch use this function combined with kmem_cache_alloc_bulk.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/skbuff.h |  2 ++
 net/core/skbuff.c      | 71 ++++++++++++++++++++++++++++++++++++--------------
 2 files changed, 54 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a06275a618f0..e81f2b0e8a83 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1042,6 +1042,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
 struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
+struct sk_buff *build_skb_around(struct sk_buff *skb,
+				 void *data, unsigned int frag_size);
 
 /**
  * alloc_skb - allocate a network buffer
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9901f5322852..087622298d77 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -258,6 +258,33 @@ nodata:
 }
 EXPORT_SYMBOL(__alloc_skb);
 
+/* Caller must provide SKB that is memset cleared */
+static struct sk_buff *__build_skb_around(struct sk_buff *skb,
+					  void *data, unsigned int frag_size)
+{
+	struct skb_shared_info *shinfo;
+	unsigned int size = frag_size ? : ksize(data);
+
+	size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	/* Assumes caller memset cleared SKB */
+	skb->truesize = SKB_TRUESIZE(size);
+	refcount_set(&skb->users, 1);
+	skb->head = data;
+	skb->data = data;
+	skb_reset_tail_pointer(skb);
+	skb->end = skb->tail + size;
+	skb->mac_header = (typeof(skb->mac_header))~0U;
+	skb->transport_header = (typeof(skb->transport_header))~0U;
+
+	/* make sure we initialize shinfo sequentially */
+	shinfo = skb_shinfo(skb);
+	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+	atomic_set(&shinfo->dataref, 1);
+
+	return skb;
+}
+
 /**
  * __build_skb - build a network buffer
  * @data: data buffer provided by caller
@@ -279,32 +306,15 @@ EXPORT_SYMBOL(__alloc_skb);
  */
 struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
-	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
-	unsigned int size = frag_size ? : ksize(data);
 
 	skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
-	if (!skb)
+	if (unlikely(!skb))
 		return NULL;
 
-	size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
 	memset(skb, 0, offsetof(struct sk_buff, tail));
-	skb->truesize = SKB_TRUESIZE(size);
-	refcount_set(&skb->users, 1);
-	skb->head = data;
-	skb->data = data;
-	skb_reset_tail_pointer(skb);
-	skb->end = skb->tail + size;
-	skb->mac_header = (typeof(skb->mac_header))~0U;
-	skb->transport_header = (typeof(skb->transport_header))~0U;
 
-	/* make sure we initialize shinfo sequentially */
-	shinfo = skb_shinfo(skb);
-	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
-	atomic_set(&shinfo->dataref, 1);
-
-	return skb;
+	return __build_skb_around(skb, data, frag_size);
 }
 
 /* build_skb() is wrapper over __build_skb(), that specifically
@@ -325,6 +335,29 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 }
 EXPORT_SYMBOL(build_skb);
 
+/**
+ * build_skb_around - build a network buffer around provided skb
+ * @skb: sk_buff provide by caller, must be memset cleared
+ * @data: data buffer provided by caller
+ * @frag_size: size of data, or 0 if head was kmalloced
+ */
+struct sk_buff *build_skb_around(struct sk_buff *skb,
+				 void *data, unsigned int frag_size)
+{
+	if (unlikely(!skb))
+		return NULL;
+
+	skb = __build_skb_around(skb, data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (page_is_pfmemalloc(virt_to_head_page(data)))
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
+EXPORT_SYMBOL(build_skb_around);
+
 #define NAPI_SKB_CACHE_SIZE	64
 
 struct napi_alloc_cache {
-- 
cgit v1.2.3


From 7df737e991069d75eec1ded1c8b37e81b8c54df9 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Fri, 19 Apr 2019 07:44:54 -0700
Subject: bpf: remove global variables

Move three global variables protected by bpf_verifier_lock into
'struct bpf_verifier_env' to allow parallel verification.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_verifier.h |  5 +++++
 kernel/bpf/verifier.c        | 25 +++++++++++++------------
 2 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b3ab61fe1932..1305ccbd8fe6 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -295,6 +295,11 @@ struct bpf_verifier_env {
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
+	struct {
+		int *insn_state;
+		int *insn_stack;
+		int cur_stack;
+	} cfg;
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
 	u32 insn_processed;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index db301e9b5295..5f0eb5bd5589 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5369,10 +5369,6 @@ enum {
 
 #define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)
 
-static int *insn_stack;	/* stack of insns to process */
-static int cur_stack;	/* current stack index */
-static int *insn_state;
-
 /* t, w, e - match pseudo-code above:
  * t - index of current instruction
  * w - next instruction
@@ -5380,6 +5376,9 @@ static int *insn_state;
  */
 static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 {
+	int *insn_stack = env->cfg.insn_stack;
+	int *insn_state = env->cfg.insn_state;
+
 	if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
 		return 0;
 
@@ -5400,9 +5399,9 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		/* tree-edge */
 		insn_state[t] = DISCOVERED | e;
 		insn_state[w] = DISCOVERED;
-		if (cur_stack >= env->prog->len)
+		if (env->cfg.cur_stack >= env->prog->len)
 			return -E2BIG;
-		insn_stack[cur_stack++] = w;
+		insn_stack[env->cfg.cur_stack++] = w;
 		return 1;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
 		verbose_linfo(env, t, "%d: ", t);
@@ -5426,14 +5425,15 @@ static int check_cfg(struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insns = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
+	int *insn_stack, *insn_state;
 	int ret = 0;
 	int i, t;
 
-	insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_state)
 		return -ENOMEM;
 
-	insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_stack) {
 		kvfree(insn_state);
 		return -ENOMEM;
@@ -5441,12 +5441,12 @@ static int check_cfg(struct bpf_verifier_env *env)
 
 	insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
 	insn_stack[0] = 0; /* 0 is the first instruction */
-	cur_stack = 1;
+	env->cfg.cur_stack = 1;
 
 peek_stack:
-	if (cur_stack == 0)
+	if (env->cfg.cur_stack == 0)
 		goto check_state;
-	t = insn_stack[cur_stack - 1];
+	t = insn_stack[env->cfg.cur_stack - 1];
 
 	if (BPF_CLASS(insns[t].code) == BPF_JMP ||
 	    BPF_CLASS(insns[t].code) == BPF_JMP32) {
@@ -5515,7 +5515,7 @@ peek_stack:
 
 mark_explored:
 	insn_state[t] = EXPLORED;
-	if (cur_stack-- <= 0) {
+	if (env->cfg.cur_stack-- <= 0) {
 		verbose(env, "pop stack internal bug\n");
 		ret = -EFAULT;
 		goto err_free;
@@ -5535,6 +5535,7 @@ check_state:
 err_free:
 	kvfree(insn_state);
 	kvfree(insn_stack);
+	env->cfg.insn_state = env->cfg.insn_stack = NULL;
 	return ret;
 }
 
-- 
cgit v1.2.3