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>

3 files changed, 45 insertions, 4 deletions

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