bpf: Introduce bpf_sysctl_get_name helper

Add bpf_sysctl_get_name() helper to copy sysctl name (/proc/sys/ entry)
into provided by BPF_PROG_TYPE_CGROUP_SYSCTL program buffer.

By default full name (w/o /proc/sys/) is copied, e.g. "net/ipv4/tcp_mem".

If BPF_F_SYSCTL_BASE_NAME flag is set, only base name will be copied,
e.g. "tcp_mem".

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

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cc2a246..9c8a2f3 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2506,6 +2506,22 @@ union bpf_attr {
  *     Return
  *             0 if iph and th are a valid SYN cookie ACK, or a negative error
  *             otherwise.
+ *
+ * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ *     Description
+ *             Get name of sysctl in /proc/sys/ and copy it into provided by
+ *             program buffer *buf* of size *buf_len*.
+ *
+ *             The buffer is always NUL terminated, unless it's zero-sized.
+ *
+ *             If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
+ *             copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
+ *             only (e.g. "tcp_mem").
+ *     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).
  */
 #define __BPF_FUNC_MAPPER(FN)          \
        FN(unspec),                     \
@@ -2608,7 +2624,8 @@ union bpf_attr {
        FN(skb_ecn_set_ce),             \
        FN(get_listener_sock),          \
        FN(skc_lookup_tcp),             \
-       FN(tcp_check_syncookie),
+       FN(tcp_check_syncookie),        \
+       FN(sysctl_get_name),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2681,6 +2698,9 @@ enum bpf_func_id {
                                          BPF_ADJ_ROOM_ENCAP_L2_MASK) \
                                         << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
+/* BPF_FUNC_sysctl_get_name flags. */
+#define BPF_F_SYSCTL_BASE_NAME         (1ULL << 0)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
        BPF_ADJ_ROOM_NET,

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 610491b..a683870 100644 (file)
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -14,6 +14,7 @@
 #include <linux/filter.h>
 #include <linux/slab.h>
 #include <linux/sysctl.h>
+#include <linux/string.h>
 #include <linux/bpf.h>
 #include <linux/bpf-cgroup.h>
 #include <net/sock.h>
@@ -806,10 +807,77 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
 
+static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
+                             size_t *lenp)
+{
+       ssize_t tmp_ret = 0, ret;
+
+       if (dir->header.parent) {
+               tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp);
+               if (tmp_ret < 0)
+                       return tmp_ret;
+       }
+
+       ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp);
+       if (ret < 0)
+               return ret;
+       *bufp += ret;
+       *lenp -= ret;
+       ret += tmp_ret;
+
+       /* Avoid leading slash. */
+       if (!ret)
+               return ret;
+
+       tmp_ret = strscpy(*bufp, "/", *lenp);
+       if (tmp_ret < 0)
+               return tmp_ret;
+       *bufp += tmp_ret;
+       *lenp -= tmp_ret;
+
+       return ret + tmp_ret;
+}
+
+BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf,
+          size_t, buf_len, u64, flags)
+{
+       ssize_t tmp_ret = 0, ret;
+
+       if (!buf)
+               return -EINVAL;
+
+       if (!(flags & BPF_F_SYSCTL_BASE_NAME)) {
+               if (!ctx->head)
+                       return -EINVAL;
+               tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len);
+               if (tmp_ret < 0)
+                       return tmp_ret;
+       }
+
+       ret = strscpy(buf, ctx->table->procname, buf_len);
+
+       return ret < 0 ? ret : tmp_ret + ret;
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
+       .func           = bpf_sysctl_get_name,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_PTR_TO_CTX,
+       .arg2_type      = ARG_PTR_TO_MEM,
+       .arg3_type      = ARG_CONST_SIZE,
+       .arg4_type      = ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
-       return cgroup_base_func_proto(func_id, prog);
+       switch (func_id) {
+       case BPF_FUNC_sysctl_get_name:
+               return &bpf_sysctl_get_name_proto;
+       default:
+               return cgroup_base_func_proto(func_id, prog);
+       }
 }
 
 static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,