Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Alexei Starovoitov says:

====================
pull-request: bpf 2020-06-17

The following pull-request contains BPF updates for your *net* tree.

We've added 10 non-merge commits during the last 2 day(s) which contain
a total of 14 files changed, 158 insertions(+), 59 deletions(-).

The main changes are:

1) Important fix for bpf_probe_read_kernel_str() return value, from Andrii.

2) [gs]etsockopt fix for large optlen, from Stanislav.

3) devmap allocation fix, from Toke.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/bpf/prog_cgroup_sockopt.rst

@@ -86,6 +86,20 @@ then the next program in the chain (A) will see those changes,
 *not* the original input ``setsockopt`` arguments. The potentially
 modified values will be then passed down to the kernel.
 
+Large optval
+============
+When the ``optval`` is greater than the ``PAGE_SIZE``, the BPF program
+can access only the first ``PAGE_SIZE`` of that data. So it has to options:
+
+* Set ``optlen`` to zero, which indicates that the kernel should
+  use the original buffer from the userspace. Any modifications
+  done by the BPF program to the ``optval`` are ignored.
+* Set ``optlen`` to the value less than ``PAGE_SIZE``, which
+  indicates that the kernel should use BPF's trimmed ``optval``.
+
+When the BPF program returns with the ``optlen`` greater than
+``PAGE_SIZE``, the userspace will receive ``EFAULT`` errno.
+
 Example
 =======
 

include/uapi/linux/bpf.h

@@ -3168,7 +3168,7 @@ union bpf_attr {
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
  *
- * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
  * 	Description
  * 		Copy *size* bytes from *data* into a ring buffer *ringbuf*.
  * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of

kernel/bpf/cgroup.c

@@ -1276,16 +1276,23 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
 
 static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 {
-	if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0)
+	if (unlikely(max_optlen < 0))
 		return -EINVAL;
 
+	if (unlikely(max_optlen > PAGE_SIZE)) {
+		/* We don't expose optvals that are greater than PAGE_SIZE
+		 * to the BPF program.
+		 */
+		max_optlen = PAGE_SIZE;
+	}
+
 	ctx->optval = kzalloc(max_optlen, GFP_USER);
 	if (!ctx->optval)
 		return -ENOMEM;
 
 	ctx->optval_end = ctx->optval + max_optlen;
 
-	return 0;
+	return max_optlen;
 }
 
 static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
@@ -1319,13 +1326,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	 */
 	max_optlen = max_t(int, 16, *optlen);
 
-	ret = sockopt_alloc_buf(&ctx, max_optlen);
-	if (ret)
-		return ret;
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	if (max_optlen < 0)
+		return max_optlen;
 
 	ctx.optlen = *optlen;
 
-	if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
+	if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) {
 		ret = -EFAULT;
 		goto out;
 	}
@@ -1353,9 +1360,15 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		/* export any potential modifications */
 		*level = ctx.level;
 		*optname = ctx.optname;
+
+		/* optlen == 0 from BPF indicates that we should
+		 * use original userspace data.
+		 */
+		if (ctx.optlen != 0) {
 			*optlen = ctx.optlen;
 			*kernel_optval = ctx.optval;
 		}
+	}
 
 out:
 	if (ret)
@@ -1385,12 +1398,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
 		return retval;
 
-	ret = sockopt_alloc_buf(&ctx, max_optlen);
-	if (ret)
-		return ret;
-
 	ctx.optlen = max_optlen;
 
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	if (max_optlen < 0)
+		return max_optlen;
+
 	if (!retval) {
 		/* If kernel getsockopt finished successfully,
 		 * copy whatever was returned to the user back
@@ -1404,10 +1417,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 			goto out;
 		}
 
-		if (ctx.optlen > max_optlen)
-			ctx.optlen = max_optlen;
-
-		if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
+		if (copy_from_user(ctx.optval, optval,
+				   min(ctx.optlen, max_optlen)) != 0) {
 			ret = -EFAULT;
 			goto out;
 		}
@@ -1436,11 +1447,13 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		goto out;
 	}
 
+	if (ctx.optlen != 0) {
 		if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
 		    put_user(ctx.optlen, optlen)) {
 			ret = -EFAULT;
 			goto out;
 		}
+	}
 
 	ret = ctx.retval;
 

kernel/bpf/devmap.c

@@ -86,12 +86,13 @@ static DEFINE_PER_CPU(struct list_head, dev_flush_list);
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
-static struct hlist_head *dev_map_create_hash(unsigned int entries)
+static struct hlist_head *dev_map_create_hash(unsigned int entries,
+					      int numa_node)
 {
 	int i;
 	struct hlist_head *hash;
 
-	hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL);
+	hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node);
 	if (hash != NULL)
 		for (i = 0; i < entries; i++)
 			INIT_HLIST_HEAD(&hash[i]);
@@ -145,7 +146,8 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 		return -EINVAL;
 
 	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets);
+		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets,
+							   dtab->map.numa_node);
 		if (!dtab->dev_index_head)
 			goto free_charge;
 
@@ -232,7 +234,7 @@ static void dev_map_free(struct bpf_map *map)
 			}
 		}
 
-		kfree(dtab->dev_index_head);
+		bpf_map_area_free(dtab->dev_index_head);
 	} else {
 		for (i = 0; i < dtab->map.max_entries; i++) {
 			struct bpf_dtab_netdev *dev;

kernel/trace/bpf_trace.c

@@ -241,7 +241,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
 	if (unlikely(ret < 0))
 		goto fail;
 
-	return 0;
+	return ret;
 fail:
 	memset(dst, 0, size);
 	return ret;

net/core/xdp.c

@@ -462,6 +462,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp)
 	xdpf->len = totsize - metasize;
 	xdpf->headroom = 0;
 	xdpf->metasize = metasize;
+	xdpf->frame_sz = PAGE_SIZE;
 	xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
 
 	xsk_buff_free(xdp);

samples/bpf/xdp_monitor_user.c

@@ -509,11 +509,8 @@ static void *alloc_rec_per_cpu(int record_size)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	void *array;
-	size_t size;
 
-	size = record_size * nr_cpus;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_cpus, record_size);
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
 		exit(EXIT_FAIL_MEM);
@@ -528,8 +525,7 @@ static struct stats_record *alloc_stats_record(void)
 	int i;
 
 	/* Alloc main stats_record structure */
-	rec = malloc(sizeof(*rec));
-	memset(rec, 0, sizeof(*rec));
+	rec = calloc(1, sizeof(*rec));
 	if (!rec) {
 		fprintf(stderr, "Mem alloc error\n");
 		exit(EXIT_FAIL_MEM);

samples/bpf/xdp_redirect_cpu_user.c

@@ -207,11 +207,8 @@ static struct datarec *alloc_record_per_cpu(void)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	struct datarec *array;
-	size_t size;
 
-	size = sizeof(struct datarec) * nr_cpus;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_cpus, sizeof(struct datarec));
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
 		exit(EXIT_FAIL_MEM);
@@ -226,11 +223,11 @@ static struct stats_record *alloc_stats_record(void)
 
 	size = sizeof(*rec) + n_cpus * sizeof(struct record);
 	rec = malloc(size);
-	memset(rec, 0, size);
 	if (!rec) {
 		fprintf(stderr, "Mem alloc error\n");
 		exit(EXIT_FAIL_MEM);
 	}
+	memset(rec, 0, size);
 	rec->rx_cnt.cpu    = alloc_record_per_cpu();
 	rec->redir_err.cpu = alloc_record_per_cpu();
 	rec->kthread.cpu   = alloc_record_per_cpu();

samples/bpf/xdp_rxq_info_user.c

@@ -198,11 +198,8 @@ static struct datarec *alloc_record_per_cpu(void)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	struct datarec *array;
-	size_t size;
 
-	size = sizeof(struct datarec) * nr_cpus;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_cpus, sizeof(struct datarec));
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
 		exit(EXIT_FAIL_MEM);
@@ -214,11 +211,8 @@ static struct record *alloc_record_per_rxq(void)
 {
 	unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
 	struct record *array;
-	size_t size;
 
-	size = sizeof(struct record) * nr_rxqs;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_rxqs, sizeof(struct record));
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs);
 		exit(EXIT_FAIL_MEM);
@@ -232,8 +226,7 @@ static struct stats_record *alloc_stats_record(void)
 	struct stats_record *rec;
 	int i;
 
-	rec = malloc(sizeof(*rec));
-	memset(rec, 0, sizeof(*rec));
+	rec = calloc(1, sizeof(struct stats_record));
 	if (!rec) {
 		fprintf(stderr, "Mem alloc error\n");
 		exit(EXIT_FAIL_MEM);

tools/bpf/bpftool/Documentation/bpftool-map.rst

@@ -49,7 +49,7 @@ MAP COMMANDS
 |		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
 |		| **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
 |		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
-|		| **queue** | **stack** | **sk_storage** | **struct_ops** }
+|		| **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** }
 
 DESCRIPTION
 ===========

tools/bpf/bpftool/map.c

@@ -49,6 +49,7 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_STACK]			= "stack",
 	[BPF_MAP_TYPE_SK_STORAGE]		= "sk_storage",
 	[BPF_MAP_TYPE_STRUCT_OPS]		= "struct_ops",
+	[BPF_MAP_TYPE_RINGBUF]			= "ringbuf",
 };
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -1590,7 +1591,7 @@ static int do_help(int argc, char **argv)
 		"                 lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n"
 		"                 devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n"
 		"                 cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n"
-		"                 queue | stack | sk_storage | struct_ops }\n"
+		"                 queue | stack | sk_storage | struct_ops | ringbuf }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2]);

tools/include/uapi/linux/bpf.h

@@ -3168,7 +3168,7 @@ union bpf_attr {
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
  *
- * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
  * 	Description
  * 		Copy *size* bytes from *data* into a ring buffer *ringbuf*.
  * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of

tools/testing/selftests/bpf/prog_tests/sockopt_sk.c

@@ -13,6 +13,7 @@ static int getsetsockopt(void)
 		char cc[16]; /* TCP_CA_NAME_MAX */
 	} buf = {};
 	socklen_t optlen;
+	char *big_buf = NULL;
 
 	fd = socket(AF_INET, SOCK_STREAM, 0);
 	if (fd < 0) {
@@ -22,24 +23,31 @@ static int getsetsockopt(void)
 
 	/* IP_TOS - BPF bypass */
 
-	buf.u8[0] = 0x08;
-	err = setsockopt(fd, SOL_IP, IP_TOS, &buf, 1);
+	optlen = getpagesize() * 2;
+	big_buf = calloc(1, optlen);
+	if (!big_buf) {
+		log_err("Couldn't allocate two pages");
+		goto err;
+	}
+
+	*(int *)big_buf = 0x08;
+	err = setsockopt(fd, SOL_IP, IP_TOS, big_buf, optlen);
 	if (err) {
 		log_err("Failed to call setsockopt(IP_TOS)");
 		goto err;
 	}
 
-	buf.u8[0] = 0x00;
+	memset(big_buf, 0, optlen);
 	optlen = 1;
-	err = getsockopt(fd, SOL_IP, IP_TOS, &buf, &optlen);
+	err = getsockopt(fd, SOL_IP, IP_TOS, big_buf, &optlen);
 	if (err) {
 		log_err("Failed to call getsockopt(IP_TOS)");
 		goto err;
 	}
 
-	if (buf.u8[0] != 0x08) {
-		log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08",
-			buf.u8[0]);
+	if (*(int *)big_buf != 0x08) {
+		log_err("Unexpected getsockopt(IP_TOS) optval 0x%x != 0x08",
+			*(int *)big_buf);
 		goto err;
 	}
 
@@ -78,6 +86,28 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
+	/* IP_FREEBIND - BPF can't access optval past PAGE_SIZE */
+
+	optlen = getpagesize() * 2;
+	memset(big_buf, 0, optlen);
+
+	err = setsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, optlen);
+	if (err != 0) {
+		log_err("Failed to call setsockopt, ret=%d", err);
+		goto err;
+	}
+
+	err = getsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, &optlen);
+	if (err != 0) {
+		log_err("Failed to call getsockopt, ret=%d", err);
+		goto err;
+	}
+
+	if (optlen != 1 || *(__u8 *)big_buf != 0x55) {
+		log_err("Unexpected IP_FREEBIND getsockopt, optlen=%d, optval=0x%x",
+			optlen, *(__u8 *)big_buf);
+	}
+
 	/* SO_SNDBUF is overwritten */
 
 	buf.u32 = 0x01010101;
@@ -124,9 +154,11 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
+	free(big_buf);
 	close(fd);
 	return 0;
 err:
+	free(big_buf);
 	close(fd);
 	return -1;
 }

tools/testing/selftests/bpf/progs/sockopt_sk.c

@@ -8,6 +8,10 @@
 char _license[] SEC("license") = "GPL";
 __u32 _version SEC("version") = 1;
 
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
 #define SOL_CUSTOM			0xdeadbeef
 
 struct sockopt_sk {
@@ -28,12 +32,14 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
-	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
+		ctx->optlen = 0; /* bypass optval>PAGE_SIZE */
 		return 1;
+	}
 
 	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
 		/* Not interested in SOL_SOCKET:SO_SNDBUF;
@@ -51,6 +57,26 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		return 1;
 	}
 
+	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+		if (optval + 1 > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		ctx->retval = 0; /* Reset system call return value to zero */
+
+		/* Always export 0x55 */
+		optval[0] = 0x55;
+		ctx->optlen = 1;
+
+		/* Userspace buffer is PAGE_SIZE * 2, but BPF
+		 * program can only see the first PAGE_SIZE
+		 * bytes of data.
+		 */
+		if (optval_end - optval != PAGE_SIZE)
+			return 0; /* EPERM, unexpected data size */
+
+		return 1;
+	}
+
 	if (ctx->level != SOL_CUSTOM)
 		return 0; /* EPERM, deny everything except custom level */
 
@@ -81,12 +107,14 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
-	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
+		ctx->optlen = 0; /* bypass optval>PAGE_SIZE */
 		return 1;
+	}
 
 	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
 		/* Overwrite SO_SNDBUF value */
@@ -112,6 +140,28 @@ int _setsockopt(struct bpf_sockopt *ctx)
 		return 1;
 	}
 
+	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+		/* Original optlen is larger than PAGE_SIZE. */
+		if (ctx->optlen != PAGE_SIZE * 2)
+			return 0; /* EPERM, unexpected data size */
+
+		if (optval + 1 > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		/* Make sure we can trim the buffer. */
+		optval[0] = 0;
+		ctx->optlen = 1;
+
+		/* Usepace buffer is PAGE_SIZE * 2, but BPF
+		 * program can only see the first PAGE_SIZE
+		 * bytes of data.
+		 */
+		if (optval_end - optval != PAGE_SIZE)
+			return 0; /* EPERM, unexpected data size */
+
+		return 1;
+	}
+
 	if (ctx->level != SOL_CUSTOM)
 		return 0; /* EPERM, deny everything except custom level */