Merge branch 'bpf-cgroup2'

Martin KaFai Lau says:

====================
cgroup: bpf: cgroup2 membership test on skb

This series is to implement a bpf-way to
check the cgroup2 membership of a skb (sk_buff).

It is similar to the feature added in netfilter:
c38c459 ("netfilter: implement xt_cgroup cgroup2 path match")

The current target is the tc-like usage.

v3:
- Remove WARN_ON_ONCE(!rcu_read_lock_held())
- Stop BPF_MAP_TYPE_CGROUP_ARRAY usage in patch 2/4
- Avoid mounting bpf fs manually in patch 4/4

- Thanks for Daniel's review and the above suggestions

- Check CONFIG_SOCK_CGROUP_DATA instead of CONFIG_CGROUPS.  Thanks to
  the kbuild bot's report.
  Patch 2/4 only needs CONFIG_CGROUPS while patch 3/4 needs
  CONFIG_SOCK_CGROUP_DATA.  Since a single bpf cgrp2 array alone is
  not useful for now, CONFIG_SOCK_CGROUP_DATA is also used in
  patch 2/4.  We can fine tune it later if we find other use cases
  for the cgrp2 array.
- Return EAGAIN instead of ENOENT if the cgrp2 array entry is
  NULL.  It is to distinguish these two cases: 1) the userland has
  not populated this array entry yet. or 2) not finding cgrp2 from the skb.

- Be-lated thanks to Alexei and Tejun on reviewing v1 and giving advice on
  this work.

v2:
- Fix two return cases in cgroup_get_from_fd()
- Fix compilation errors when CONFIG_CGROUPS is not used:
  - arraymap.c: avoid registering BPF_MAP_TYPE_CGROUP_ARRAY
  - filter.c: tc_cls_act_func_proto() returns NULL on BPF_FUNC_skb_in_cgroup
- Add comments to BPF_FUNC_skb_in_cgroup and cgroup_get_from_fd()
====================

Signed-off-by: David S. Miller <[email protected]>

include/linux/cgroup.h

@@ -87,6 +87,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 						       struct cgroup_subsys *ss);
 
 struct cgroup *cgroup_get_from_path(const char *path);
+struct cgroup *cgroup_get_from_fd(int fd);
 
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);

include/uapi/linux/bpf.h

@@ -84,6 +84,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_PERCPU_HASH,
 	BPF_MAP_TYPE_PERCPU_ARRAY,
 	BPF_MAP_TYPE_STACK_TRACE,
+	BPF_MAP_TYPE_CGROUP_ARRAY,
 };
 
 enum bpf_prog_type {
@@ -336,6 +337,17 @@ enum bpf_func_id {
 	 */
 	BPF_FUNC_skb_change_type,
 
+	/**
+	 * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+	 * @skb: pointer to skb
+	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+	 * @index: index of the cgroup in the bpf_map
+	 * Return:
+	 *   == 0 skb failed the cgroup2 descendant test
+	 *   == 1 skb succeeded the cgroup2 descendant test
+	 *    < 0 error
+	 */
+	BPF_FUNC_skb_in_cgroup,
 	__BPF_FUNC_MAX_ID,
 };
 

kernel/bpf/arraymap.c

@@ -537,3 +537,46 @@ static int __init register_perf_event_array_map(void)
 	return 0;
 }
 late_initcall(register_perf_event_array_map);
+
+#ifdef CONFIG_SOCK_CGROUP_DATA
+static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
+				     struct file *map_file /* not used */,
+				     int fd)
+{
+	return cgroup_get_from_fd(fd);
+}
+
+static void cgroup_fd_array_put_ptr(void *ptr)
+{
+	/* cgroup_put free cgrp after a rcu grace period */
+	cgroup_put(ptr);
+}
+
+static void cgroup_fd_array_free(struct bpf_map *map)
+{
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static const struct bpf_map_ops cgroup_array_ops = {
+	.map_alloc = fd_array_map_alloc,
+	.map_free = cgroup_fd_array_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
+	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
+};
+
+static struct bpf_map_type_list cgroup_array_type __read_mostly = {
+	.ops = &cgroup_array_ops,
+	.type = BPF_MAP_TYPE_CGROUP_ARRAY,
+};
+
+static int __init register_cgroup_array_map(void)
+{
+	bpf_register_map_type(&cgroup_array_type);
+	return 0;
+}
+late_initcall(register_cgroup_array_map);
+#endif

kernel/bpf/syscall.c

@@ -393,7 +393,8 @@ static int map_update_elem(union bpf_attr *attr)
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
-		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) {
 		rcu_read_lock();
 		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
 						   attr->flags);

kernel/bpf/verifier.c

@@ -1035,6 +1035,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (func_id != BPF_FUNC_get_stackid)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+		if (func_id != BPF_FUNC_skb_in_cgroup)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -1054,6 +1058,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
 			goto error;
 		break;
+	case BPF_FUNC_skb_in_cgroup:
+		if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
+			goto error;
+		break;
 	default:
 		break;
 	}

kernel/cgroup.c

@@ -62,6 +62,7 @@
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
 #include <linux/proc_ns.h>
+#include <linux/file.h>
 #include <net/sock.h>
 
 /*
@@ -6209,6 +6210,40 @@ struct cgroup *cgroup_get_from_path(const char *path)
 }
 EXPORT_SYMBOL_GPL(cgroup_get_from_path);
 
+/**
+ * cgroup_get_from_fd - get a cgroup pointer from a fd
+ * @fd: fd obtained by open(cgroup2_dir)
+ *
+ * Find the cgroup from a fd which should be obtained
+ * by opening a cgroup directory.  Returns a pointer to the
+ * cgroup on success. ERR_PTR is returned if the cgroup
+ * cannot be found.
+ */
+struct cgroup *cgroup_get_from_fd(int fd)
+{
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+	struct file *f;
+
+	f = fget_raw(fd);
+	if (!f)
+		return ERR_PTR(-EBADF);
+
+	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+	fput(f);
+	if (IS_ERR(css))
+		return ERR_CAST(css);
+
+	cgrp = css->cgroup;
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+
+	return cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
+
 /*
  * sock->sk_cgrp_data handling.  For more info, see sock_cgroup_data
  * definition in cgroup-defs.h.

net/core/filter.c

@@ -2239,6 +2239,40 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
 	}
 }
 
+#ifdef CONFIG_SOCK_CGROUP_DATA
+static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(long)r1;
+	struct bpf_map *map = (struct bpf_map *)(long)r2;
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct cgroup *cgrp;
+	struct sock *sk;
+	u32 i = (u32)r3;
+
+	sk = skb->sk;
+	if (!sk || !sk_fullsock(sk))
+		return -ENOENT;
+
+	if (unlikely(i >= array->map.max_entries))
+		return -E2BIG;
+
+	cgrp = READ_ONCE(array->ptrs[i]);
+	if (unlikely(!cgrp))
+		return -EAGAIN;
+
+	return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp);
+}
+
+static const struct bpf_func_proto bpf_skb_in_cgroup_proto = {
+	.func		= bpf_skb_in_cgroup,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+#endif
+
 static const struct bpf_func_proto *
 sk_filter_func_proto(enum bpf_func_id func_id)
 {
@@ -2307,6 +2341,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return bpf_get_event_output_proto();
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
+#ifdef CONFIG_SOCK_CGROUP_DATA
+	case BPF_FUNC_skb_in_cgroup:
+		return &bpf_skb_in_cgroup_proto;
+#endif
 	default:
 		return sk_filter_func_proto(func_id);
 	}

samples/bpf/Makefile

@@ -20,6 +20,7 @@ hostprogs-y += offwaketime
 hostprogs-y += spintest
 hostprogs-y += map_perf_test
 hostprogs-y += test_overhead
+hostprogs-y += test_cgrp2_array_pin
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
@@ -40,6 +41,7 @@ offwaketime-objs := bpf_load.o libbpf.o offwaketime_user.o
 spintest-objs := bpf_load.o libbpf.o spintest_user.o
 map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o
 test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
+test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -61,6 +63,7 @@ always += map_perf_test_kern.o
 always += test_overhead_tp_kern.o
 always += test_overhead_kprobe_kern.o
 always += parse_varlen.o parse_simple.o parse_ldabs.o
+always += test_cgrp2_tc_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 

samples/bpf/bpf_helpers.h

@@ -70,6 +70,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag
 	(void *) BPF_FUNC_l3_csum_replace;
 static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
 	(void *) BPF_FUNC_l4_csum_replace;
+static int (*bpf_skb_in_cgroup)(void *ctx, void *map, int index) =
+	(void *) BPF_FUNC_skb_in_cgroup;
 
 #if defined(__x86_64__)
 

samples/bpf/test_cgrp2_array_pin.c

@@ -0,0 +1,109 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdio.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <fcntl.h>
+
+#include "libbpf.h"
+
+static void usage(void)
+{
+	printf("Usage: test_cgrp2_array_pin [...]\n");
+	printf("       -F <file>   File to pin an BPF cgroup array\n");
+	printf("       -U <file>   Update an already pinned BPF cgroup array\n");
+	printf("       -v <value>  Full path of the cgroup2\n");
+	printf("       -h          Display this help\n");
+}
+
+int main(int argc, char **argv)
+{
+	const char *pinned_file = NULL, *cg2 = NULL;
+	int create_array = 1;
+	int array_key = 0;
+	int array_fd = -1;
+	int cg2_fd = -1;
+	int ret = -1;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "F:U:v:")) != -1) {
+		switch (opt) {
+		/* General args */
+		case 'F':
+			pinned_file = optarg;
+			break;
+		case 'U':
+			pinned_file = optarg;
+			create_array = 0;
+			break;
+		case 'v':
+			cg2 = optarg;
+			break;
+		default:
+			usage();
+			goto out;
+		}
+	}
+
+	if (!cg2 || !pinned_file) {
+		usage();
+		goto out;
+	}
+
+	cg2_fd = open(cg2, O_RDONLY);
+	if (cg2_fd < 0) {
+		fprintf(stderr, "open(%s,...): %s(%d)\n",
+			cg2, strerror(errno), errno);
+		goto out;
+	}
+
+	if (create_array) {
+		array_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY,
+					  sizeof(uint32_t), sizeof(uint32_t),
+					  1, 0);
+		if (array_fd < 0) {
+			fprintf(stderr,
+				"bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY,...): %s(%d)\n",
+				strerror(errno), errno);
+			goto out;
+		}
+	} else {
+		array_fd = bpf_obj_get(pinned_file);
+		if (array_fd < 0) {
+			fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
+				pinned_file, strerror(errno), errno);
+			goto out;
+		}
+	}
+
+	ret = bpf_update_elem(array_fd, &array_key, &cg2_fd, 0);
+	if (ret) {
+		perror("bpf_update_elem");
+		goto out;
+	}
+
+	if (create_array) {
+		ret = bpf_obj_pin(array_fd, pinned_file);
+		if (ret) {
+			fprintf(stderr, "bpf_obj_pin(..., %s): %s(%d)\n",
+				pinned_file, strerror(errno), errno);
+			goto out;
+		}
+	}
+
+out:
+	if (array_fd != -1)
+		close(array_fd);
+	if (cg2_fd != -1)
+		close(cg2_fd);
+	return ret;
+}