Merge branch 'bpf-misc-next'

Daniel Borkmann says: ==================== BPF cleanups and misc updates This patch set adds couple of cleanups in first few patches, exposes owner_prog_type for array maps as well as mlocked mem for maps in fdinfo, allows for mount permissions in fs and fixes various outstanding issues in selftests and samples. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
mariux64 · Nov 28, 2016 · 53c4ce0 · 53c4ce0
2 parents e373909 + e00c7b2
commit 53c4ce0
Show file tree

Hide file tree

Showing 20 changed files with 160 additions and 59 deletions.
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1518,7 +1518,7 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
 	xdp.data = data;
 	xdp.data_end = data + len;
 
-	return BPF_PROG_RUN(prog, (void *)&xdp);
+	return BPF_PROG_RUN(prog, &xdp);
 }
 
 /**

diff --git a/include/linux/filter.h b/include/linux/filter.h
@@ -408,8 +408,8 @@ struct bpf_prog {
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
-	unsigned int		(*bpf_func)(const struct sk_buff *skb,
-					    const struct bpf_insn *filter);
+	unsigned int		(*bpf_func)(const void *ctx,
+					    const struct bpf_insn *insn);
 	/* Instructions for interpreter */
 	union {
 		struct sock_filter	insns[0];
@@ -504,7 +504,7 @@ static inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
 	u32 ret;
 
 	rcu_read_lock();
-	ret = BPF_PROG_RUN(prog, (void *)xdp);
+	ret = BPF_PROG_RUN(prog, xdp);
 	rcu_read_unlock();
 
 	return ret;

diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
@@ -44,4 +44,20 @@ static inline int arp_hdr_len(struct net_device *dev)
 		return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2;
 	}
 }
+
+static inline bool dev_is_mac_header_xmit(const struct net_device *dev)
+{
+	switch (dev->type) {
+	case ARPHRD_TUNNEL:
+	case ARPHRD_TUNNEL6:
+	case ARPHRD_SIT:
+	case ARPHRD_IPGRE:
+	case ARPHRD_VOID:
+	case ARPHRD_NONE:
+		return false;
+	default:
+		return true;
+	}
+}
+
 #endif	/* _LINUX_IF_ARP_H */
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
@@ -18,6 +18,7 @@
 #include <linux/namei.h>
 #include <linux/fs.h>
 #include <linux/kdev_t.h>
+#include <linux/parser.h>
 #include <linux/filter.h>
 #include <linux/bpf.h>
 
@@ -364,15 +365,66 @@ static void bpf_evict_inode(struct inode *inode)
 static const struct super_operations bpf_super_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
+	.show_options	= generic_show_options,
 	.evict_inode	= bpf_evict_inode,
 };
 
+enum {
+	OPT_MODE,
+	OPT_ERR,
+};
+
+static const match_table_t bpf_mount_tokens = {
+	{ OPT_MODE, "mode=%o" },
+	{ OPT_ERR, NULL },
+};
+
+struct bpf_mount_opts {
+	umode_t mode;
+};
+
+static int bpf_parse_options(char *data, struct bpf_mount_opts *opts)
+{
+	substring_t args[MAX_OPT_ARGS];
+	int option, token;
+	char *ptr;
+
+	opts->mode = S_IRWXUGO;
+
+	while ((ptr = strsep(&data, ",")) != NULL) {
+		if (!*ptr)
+			continue;
+
+		token = match_token(ptr, bpf_mount_tokens, args);
+		switch (token) {
+		case OPT_MODE:
+			if (match_octal(&args[0], &option))
+				return -EINVAL;
+			opts->mode = option & S_IALLUGO;
+			break;
+		/* We might like to report bad mount options here, but
+		 * traditionally we've ignored all mount options, so we'd
+		 * better continue to ignore non-existing options for bpf.
+		 */
+		}
+	}
+
+	return 0;
+}
+
 static int bpf_fill_super(struct super_block *sb, void *data, int silent)
 {
 	static struct tree_descr bpf_rfiles[] = { { "" } };
+	struct bpf_mount_opts opts;
 	struct inode *inode;
 	int ret;
 
+	save_mount_options(sb, data);
+
+	ret = bpf_parse_options(data, &opts);
+	if (ret)
+		return ret;
+
 	ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles);
 	if (ret)
 		return ret;
@@ -382,7 +434,7 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent)
 	inode = sb->s_root->d_inode;
 	inode->i_op = &bpf_dir_iops;
 	inode->i_mode &= ~S_IALLUGO;
-	inode->i_mode |= S_ISVTX | S_IRWXUGO;
+	inode->i_mode |= S_ISVTX | opts.mode;
 
 	return 0;
 }

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
@@ -138,18 +138,31 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct bpf_map *map = filp->private_data;
+	const struct bpf_array *array;
+	u32 owner_prog_type = 0;
+
+	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+		array = container_of(map, struct bpf_array, map);
+		owner_prog_type = array->owner_prog_type;
+	}
 
 	seq_printf(m,
 		   "map_type:\t%u\n"
 		   "key_size:\t%u\n"
 		   "value_size:\t%u\n"
 		   "max_entries:\t%u\n"
-		   "map_flags:\t%#x\n",
+		   "map_flags:\t%#x\n"
+		   "memlock:\t%llu\n",
 		   map->map_type,
 		   map->key_size,
 		   map->value_size,
 		   map->max_entries,
-		   map->map_flags);
+		   map->map_flags,
+		   map->pages * 1ULL << PAGE_SHIFT);
+
+	if (owner_prog_type)
+		seq_printf(m, "owner_prog_type:\t%u\n",
+			   owner_prog_type);
 }
 #endif
 

diff --git a/kernel/events/core.c b/kernel/events/core.c
@@ -7726,7 +7726,7 @@ static void bpf_overflow_handler(struct perf_event *event,
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
 		goto out;
 	rcu_read_lock();
-	ret = BPF_PROG_RUN(event->prog, (void *)&ctx);
+	ret = BPF_PROG_RUN(event->prog, &ctx);
 	rcu_read_unlock();
 out:
 	__this_cpu_dec(bpf_prog_active);

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
@@ -195,7 +195,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd)
 	 * value always takes priority (ignoring the DATA).
 	 */
 	for (; f; f = f->prev) {
-		u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)sd);
+		u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
 
 		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
 			ret = cur_ret;

diff --git a/net/core/filter.c b/net/core/filter.c
@@ -30,6 +30,7 @@
 #include <linux/inet.h>
 #include <linux/netdevice.h>
 #include <linux/if_packet.h>
+#include <linux/if_arp.h>
 #include <linux/gfp.h>
 #include <net/ip.h>
 #include <net/protocol.h>
@@ -1696,17 +1697,10 @@ static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
 static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 			  u32 flags)
 {
-	switch (dev->type) {
-	case ARPHRD_TUNNEL:
-	case ARPHRD_TUNNEL6:
-	case ARPHRD_SIT:
-	case ARPHRD_IPGRE:
-	case ARPHRD_VOID:
-	case ARPHRD_NONE:
-		return __bpf_redirect_no_mac(skb, dev, flags);
-	default:
+	if (dev_is_mac_header_xmit(dev))
 		return __bpf_redirect_common(skb, dev, flags);
-	}
+	else
+		return __bpf_redirect_no_mac(skb, dev, flags);
 }
 
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
@@ -28,7 +28,6 @@ struct tcf_bpf_cfg {
 	struct bpf_prog *filter;
 	struct sock_filter *bpf_ops;
 	const char *bpf_name;
-	u32 bpf_fd;
 	u16 bpf_num_ops;
 	bool is_ebpf;
 };
@@ -118,9 +117,6 @@ static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog,
 static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog,
 				  struct sk_buff *skb)
 {
-	if (nla_put_u32(skb, TCA_ACT_BPF_FD, prog->bpf_fd))
-		return -EMSGSIZE;
-
 	if (prog->bpf_name &&
 	    nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name))
 		return -EMSGSIZE;
@@ -233,7 +229,6 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 		}
 	}
 
-	cfg->bpf_fd = bpf_fd;
 	cfg->bpf_name = name;
 	cfg->filter = fp;
 	cfg->is_ebpf = true;
@@ -332,8 +327,6 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	if (cfg.bpf_num_ops)
 		prog->bpf_num_ops = cfg.bpf_num_ops;
-	if (cfg.bpf_fd)
-		prog->bpf_fd = cfg.bpf_fd;
 
 	prog->tcf_action = parm->action;
 	rcu_assign_pointer(prog->filter, cfg.filter);

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/gfp.h>
+#include <linux/if_arp.h>
 #include <net/net_namespace.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
@@ -73,20 +74,6 @@ static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
 static unsigned int mirred_net_id;
 static struct tc_action_ops act_mirred_ops;
 
-static bool dev_is_mac_header_xmit(const struct net_device *dev)
-{
-	switch (dev->type) {
-	case ARPHRD_TUNNEL:
-	case ARPHRD_TUNNEL6:
-	case ARPHRD_SIT:
-	case ARPHRD_IPGRE:
-	case ARPHRD_VOID:
-	case ARPHRD_NONE:
-		return false;
-	}
-	return true;
-}
-
 static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a, int ovr,
 			   int bind)

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
@@ -45,10 +45,7 @@ struct cls_bpf_prog {
 	u32 gen_flags;
 	struct tcf_exts exts;
 	u32 handle;
-	union {
-		u32 bpf_fd;
-		u16 bpf_num_ops;
-	};
+	u16 bpf_num_ops;
 	struct sock_filter *bpf_ops;
 	const char *bpf_name;
 	struct tcf_proto *tp;
@@ -377,7 +374,6 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
 	}
 
 	prog->bpf_ops = NULL;
-	prog->bpf_fd = bpf_fd;
 	prog->bpf_name = name;
 	prog->filter = fp;
 
@@ -561,9 +557,6 @@ static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog,
 static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog,
 				  struct sk_buff *skb)
 {
-	if (nla_put_u32(skb, TCA_BPF_FD, prog->bpf_fd))
-		return -EMSGSIZE;
-
 	if (prog->bpf_name &&
 	    nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name))
 		return -EMSGSIZE;

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
@@ -91,6 +91,7 @@ always += trace_event_kern.o
 always += sampleip_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
+HOSTCFLAGS += -I$(objtree)/tools/testing/selftests/bpf/
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
 HOSTLOADLIBES_fds_example += -lelf

diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
@@ -16,10 +16,13 @@
 #include <sched.h>
 #include <sys/wait.h>
 #include <sys/stat.h>
+#include <sys/resource.h>
 #include <fcntl.h>
 #include <stdlib.h>
 #include <time.h>
+
 #include "libbpf.h"
+#include "bpf_util.h"
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 #define offsetof(TYPE, MEMBER)	((size_t)&((TYPE *)0)->MEMBER)
@@ -510,7 +513,7 @@ int main(int argc, char **argv)
 
 	srand(time(NULL));
 
-	nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	nr_cpus = bpf_num_possible_cpus();
 	assert(nr_cpus != -1);
 	printf("nr_cpus:%d\n\n", nr_cpus);
 

diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
@@ -4,8 +4,10 @@
 #include <signal.h>
 #include <linux/bpf.h>
 #include <string.h>
+
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "bpf_util.h"
 
 #define MAX_INDEX	64
 #define MAX_STARS	38
@@ -36,8 +38,8 @@ struct hist_key {
 
 static void print_hist_for_pid(int fd, void *task)
 {
+	unsigned int nr_cpus = bpf_num_possible_cpus();
 	struct hist_key key = {}, next_key;
-	unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
 	long values[nr_cpus];
 	char starstr[MAX_STARS];
 	long value;

diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c
@@ -11,16 +11,18 @@
 #include <stdbool.h>
 #include <string.h>
 #include <linux/bpf.h>
+
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "bpf_util.h"
 
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
 
 #define SLOTS 100
 
 static void clear_stats(int fd)
 {
-	unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	unsigned int nr_cpus = bpf_num_possible_cpus();
 	__u64 values[nr_cpus];
 	__u32 key;
 
@@ -77,7 +79,7 @@ static void print_banner(void)
 
 static void print_hist(int fd)
 {
-	unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	unsigned int nr_cpus = bpf_num_possible_cpus();
 	__u64 total_events = 0;
 	long values[nr_cpus];
 	__u64 max_cnt = 0;