1 files changed, 534 insertions, 109 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7626b8024471..4d530b1d5683 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -25,7 +25,10 @@
 #include <linux/nospec.h>
 #include <linux/audit.h>
 #include <uapi/linux/btf.h>
+#include <asm/pgtable.h>
 #include <linux/bpf_lsm.h>
+#include <linux/poll.h>
+#include <linux/bpf-netns.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -42,6 +45,8 @@ static DEFINE_IDR(prog_idr);
 static DEFINE_SPINLOCK(prog_idr_lock);
 static DEFINE_IDR(map_idr);
 static DEFINE_SPINLOCK(map_idr_lock);
+static DEFINE_IDR(link_idr);
+static DEFINE_SPINLOCK(link_idr_lock);
 
 int sysctl_unprivileged_bpf_disabled __read_mostly;
 
@@ -49,9 +54,11 @@ static const struct bpf_map_ops * const bpf_map_types[] = {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
 #define BPF_MAP_TYPE(_id, _ops) \
 	[_id] = &_ops,
+#define BPF_LINK_TYPE(_id, _name)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 };
 
 /*
@@ -281,27 +288,29 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
 	 * __GFP_RETRY_MAYFAIL to avoid such situations.
 	 */
 
-	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
+	const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO;
+	unsigned int flags = 0;
+	unsigned long align = 1;
 	void *area;
 
 	if (size >= SIZE_MAX)
 		return NULL;
 
 	/* kmalloc()'ed memory can't be mmap()'ed */
-	if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
+	if (mmapable) {
+		BUG_ON(!PAGE_ALIGNED(size));
+		align = SHMLBA;
+		flags = VM_USERMAP;
+	} else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+		area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY,
 				    numa_node);
 		if (area != NULL)
 			return area;
 	}
-	if (mmapable) {
-		BUG_ON(!PAGE_ALIGNED(size));
-		return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL |
-					       __GFP_RETRY_MAYFAIL | flags);
-	}
-	return __vmalloc_node_flags_caller(size, numa_node,
-					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |
-					   flags, __builtin_return_address(0));
+
+	return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
+			gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL,
+			flags, numa_node, __builtin_return_address(0));
 }
 
 void *bpf_map_area_alloc(u64 size, int numa_node)
@@ -623,9 +632,20 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	mutex_lock(&map->freeze_mutex);
 
-	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
-		err = -EPERM;
-		goto out;
+	if (vma->vm_flags & VM_WRITE) {
+		if (map->frozen) {
+			err = -EPERM;
+			goto out;
+		}
+		/* map is meant to be read-only, so do not allow mapping as
+		 * writable, because it's possible to leak a writable page
+		 * reference and allows user-space to still modify it after
+		 * freezing, while verifier will assume contents do not change
+		 */
+		if (map->map_flags & BPF_F_RDONLY_PROG) {
+			err = -EACCES;
+			goto out;
+		}
 	}
 
 	/* set default open/close callbacks */
@@ -647,6 +667,16 @@ out:
 	return err;
 }
 
+static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts)
+{
+	struct bpf_map *map = filp->private_data;
+
+	if (map->ops->map_poll)
+		return map->ops->map_poll(map, filp, pts);
+
+	return EPOLLERR;
+}
+
 const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
@@ -655,6 +685,7 @@ const struct file_operations bpf_map_fops = {
 	.read		= bpf_dummy_read,
 	.write		= bpf_dummy_write,
 	.mmap		= bpf_map_mmap,
+	.poll		= bpf_map_poll,
 };
 
 int bpf_map_new_fd(struct bpf_map *map, int flags)
@@ -1372,7 +1403,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
 
 	buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN);
 	if (!buf) {
-		kvfree(buf_prevkey);
+		kfree(buf_prevkey);
 		return -ENOMEM;
 	}
 
@@ -1457,7 +1488,8 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
+	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1485,8 +1517,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (err)
 		goto free_value;
 
-	if (copy_to_user(uvalue, value, value_size) != 0)
+	if (copy_to_user(uvalue, value, value_size) != 0) {
+		err = -EFAULT;
 		goto free_value;
+	}
 
 	err = 0;
 
@@ -1530,7 +1564,7 @@ static int map_freeze(const union bpf_attr *attr)
 		err = -EBUSY;
 		goto err_put;
 	}
-	if (!capable(CAP_SYS_ADMIN)) {
+	if (!bpf_capable()) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1546,9 +1580,11 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	[_id] = & _name ## _prog_ops,
 #define BPF_MAP_TYPE(_id, _ops)
+#define BPF_LINK_TYPE(_id, _name)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 };
 
 static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
@@ -1970,6 +2006,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
 		case BPF_CGROUP_UDP4_RECVMSG:
@@ -2003,6 +2043,55 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 	}
 }
 
+static bool is_net_admin_prog_type(enum bpf_prog_type prog_type)
+{
+	switch (prog_type) {
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+	case BPF_PROG_TYPE_XDP:
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_XMIT:
+	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+	case BPF_PROG_TYPE_SK_SKB:
+	case BPF_PROG_TYPE_SK_MSG:
+	case BPF_PROG_TYPE_LIRC_MODE2:
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_EXT: /* extends any prog */
+		return true;
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		/* always unpriv */
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+		/* equivalent to SOCKET_FILTER. need CAP_BPF only */
+	default:
+		return false;
+	}
+}
+
+static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
+{
+	switch (prog_type) {
+	case BPF_PROG_TYPE_KPROBE:
+	case BPF_PROG_TYPE_TRACEPOINT:
+	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */
+	case BPF_PROG_TYPE_EXT: /* extends any prog */
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* last field in 'union bpf_attr' used by this command */
 #define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
 
@@ -2025,7 +2114,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
 	    (attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
-	    !capable(CAP_SYS_ADMIN))
+	    !bpf_capable())
 		return -EPERM;
 
 	/* copy eBPF program license from user space */
@@ -2038,11 +2127,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	is_gpl = license_is_gpl_compatible(license);
 
 	if (attr->insn_cnt == 0 ||
-	    attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
+	    attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
 		return -E2BIG;
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
-	    !capable(CAP_SYS_ADMIN))
+	    !bpf_capable())
+		return -EPERM;
+
+	if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN))
+		return -EPERM;
+	if (is_perfmon_prog_type(type) && !perfmon_capable())
 		return -EPERM;
 
 	bpf_prog_load_fixup_attach_type(attr);
@@ -2181,25 +2275,39 @@ static int bpf_obj_get(const union bpf_attr *attr)
 				attr->file_flags);
 }
 
-void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops,
-		   struct bpf_prog *prog)
+void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog)
 {
 	atomic64_set(&link->refcnt, 1);
+	link->type = type;
+	link->id = 0;
 	link->ops = ops;
 	link->prog = prog;
 }
 
+static void bpf_link_free_id(int id)
+{
+	if (!id)
+		return;
+
+	spin_lock_bh(&link_idr_lock);
+	idr_remove(&link_idr, id);
+	spin_unlock_bh(&link_idr_lock);
+}
+
 /* Clean up bpf_link and corresponding anon_inode file and FD. After
  * anon_inode is created, bpf_link can't be just kfree()'d due to deferred
- * anon_inode's release() call. This helper manages marking bpf_link as
- * defunct, releases anon_inode file and puts reserved FD.
+ * anon_inode's release() call. This helper marksbpf_link as
+ * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt
+ * is not decremented, it's the responsibility of a calling code that failed
+ * to complete bpf_link initialization.
  */
-void bpf_link_cleanup(struct bpf_link *link, struct file *link_file,
-		      int link_fd)
+void bpf_link_cleanup(struct bpf_link_primer *primer)
 {
-	link->prog = NULL;
-	fput(link_file);
-	put_unused_fd(link_fd);
+	primer->link->prog = NULL;
+	bpf_link_free_id(primer->id);
+	fput(primer->file);
+	put_unused_fd(primer->fd);
 }
 
 void bpf_link_inc(struct bpf_link *link)
@@ -2210,6 +2318,7 @@ void bpf_link_inc(struct bpf_link *link)
 /* bpf_link_free is guaranteed to be called from process context */
 static void bpf_link_free(struct bpf_link *link)
 {
+	bpf_link_free_id(link->id);
 	if (link->prog) {
 		/* detach BPF program, clean up used resources */
 		link->ops->release(link);
@@ -2251,35 +2360,35 @@ static int bpf_link_release(struct inode *inode, struct file *filp)
 }
 
 #ifdef CONFIG_PROC_FS
-static const struct bpf_link_ops bpf_raw_tp_lops;
-static const struct bpf_link_ops bpf_tracing_link_lops;
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
+#define BPF_MAP_TYPE(_id, _ops)
+#define BPF_LINK_TYPE(_id, _name) [_id] = #_name,
+static const char *bpf_link_type_strs[] = {
+	[BPF_LINK_TYPE_UNSPEC] = "<invalid>",
+#include <linux/bpf_types.h>
+};
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 
 static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct bpf_link *link = filp->private_data;
 	const struct bpf_prog *prog = link->prog;
 	char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
-	const char *link_type;
-
-	if (link->ops == &bpf_raw_tp_lops)
-		link_type = "raw_tracepoint";
-	else if (link->ops == &bpf_tracing_link_lops)
-		link_type = "tracing";
-#ifdef CONFIG_CGROUP_BPF
-	else if (link->ops == &bpf_cgroup_link_lops)
-		link_type = "cgroup";
-#endif
-	else
-		link_type = "unknown";
 
 	bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
 	seq_printf(m,
 		   "link_type:\t%s\n"
+		   "link_id:\t%u\n"
 		   "prog_tag:\t%s\n"
 		   "prog_id:\t%u\n",
-		   link_type,
+		   bpf_link_type_strs[link->type],
+		   link->id,
 		   prog_tag,
 		   prog->aux->id);
+	if (link->ops->show_fdinfo)
+		link->ops->show_fdinfo(link, m);
 }
 #endif
 
@@ -2292,36 +2401,77 @@ static const struct file_operations bpf_link_fops = {
 	.write		= bpf_dummy_write,
 };
 
-int bpf_link_new_fd(struct bpf_link *link)
+static int bpf_link_alloc_id(struct bpf_link *link)
 {
-	return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC);
-}
+	int id;
 
-/* Similar to bpf_link_new_fd, create anon_inode for given bpf_link, but
- * instead of immediately installing fd in fdtable, just reserve it and
- * return. Caller then need to either install it with fd_install(fd, file) or
- * release with put_unused_fd(fd).
- * This is useful for cases when bpf_link attachment/detachment are
- * complicated and expensive operations and should be delayed until all the fd
- * reservation and anon_inode creation succeeds.
+	idr_preload(GFP_KERNEL);
+	spin_lock_bh(&link_idr_lock);
+	id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC);
+	spin_unlock_bh(&link_idr_lock);
+	idr_preload_end();
+
+	return id;
+}
+
+/* Prepare bpf_link to be exposed to user-space by allocating anon_inode file,
+ * reserving unused FD and allocating ID from link_idr. This is to be paired
+ * with bpf_link_settle() to install FD and ID and expose bpf_link to
+ * user-space, if bpf_link is successfully attached. If not, bpf_link and
+ * pre-allocated resources are to be freed with bpf_cleanup() call. All the
+ * transient state is passed around in struct bpf_link_primer.
+ * This is preferred way to create and initialize bpf_link, especially when
+ * there are complicated and expensive operations inbetween creating bpf_link
+ * itself and attaching it to BPF hook. By using bpf_link_prime() and
+ * bpf_link_settle() kernel code using bpf_link doesn't have to perform
+ * expensive (and potentially failing) roll back operations in a rare case
+ * that file, FD, or ID can't be allocated.
  */
-struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd)
+int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer)
 {
 	struct file *file;
-	int fd;
+	int fd, id;
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0)
-		return ERR_PTR(fd);
+		return fd;
+
+
+	id = bpf_link_alloc_id(link);
+	if (id < 0) {
+		put_unused_fd(fd);
+		return id;
+	}
 
 	file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC);
 	if (IS_ERR(file)) {
+		bpf_link_free_id(id);
 		put_unused_fd(fd);
-		return file;
+		return PTR_ERR(file);
 	}
 
-	*reserved_fd = fd;
-	return file;
+	primer->link = link;
+	primer->file = file;
+	primer->fd = fd;
+	primer->id = id;
+	return 0;
+}
+
+int bpf_link_settle(struct bpf_link_primer *primer)
+{
+	/* make bpf_link fetchable by ID */
+	spin_lock_bh(&link_idr_lock);
+	primer->link->id = primer->id;
+	spin_unlock_bh(&link_idr_lock);
+	/* make bpf_link fetchable by FD */
+	fd_install(primer->fd, primer->file);
+	/* pass through installed FD */
+	return primer->fd;
+}
+
+int bpf_link_new_fd(struct bpf_link *link)
+{
+	return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC);
 }
 
 struct bpf_link *bpf_link_get_from_fd(u32 ufd)
@@ -2345,6 +2495,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 
 struct bpf_tracing_link {
 	struct bpf_link link;
+	enum bpf_attach_type attach_type;
 };
 
 static void bpf_tracing_link_release(struct bpf_link *link)
@@ -2360,16 +2511,40 @@ static void bpf_tracing_link_dealloc(struct bpf_link *link)
 	kfree(tr_link);
 }
 
+static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
+					 struct seq_file *seq)
+{
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	seq_printf(seq,
+		   "attach_type:\t%d\n",
+		   tr_link->attach_type);
+}
+
+static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
+					   struct bpf_link_info *info)
+{
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	info->tracing.attach_type = tr_link->attach_type;
+
+	return 0;
+}
+
 static const struct bpf_link_ops bpf_tracing_link_lops = {
 	.release = bpf_tracing_link_release,
 	.dealloc = bpf_tracing_link_dealloc,
+	.show_fdinfo = bpf_tracing_link_show_fdinfo,
+	.fill_link_info = bpf_tracing_link_fill_link_info,
 };
 
 static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 {
+	struct bpf_link_primer link_primer;
 	struct bpf_tracing_link *link;
-	struct file *link_file;
-	int link_fd, err;
+	int err;
 
 	switch (prog->type) {
 	case BPF_PROG_TYPE_TRACING:
@@ -2402,24 +2577,23 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 		err = -ENOMEM;
 		goto out_put_prog;
 	}
-	bpf_link_init(&link->link, &bpf_tracing_link_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING,
+		      &bpf_tracing_link_lops, prog);
+	link->attach_type = prog->expected_attach_type;
 
-	link_file = bpf_link_new_file(&link->link, &link_fd);
-	if (IS_ERR(link_file)) {
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
 		kfree(link);
-		err = PTR_ERR(link_file);
 		goto out_put_prog;
 	}
 
 	err = bpf_trampoline_link_prog(prog);
 	if (err) {
-		bpf_link_cleanup(&link->link, link_file, link_fd);
+		bpf_link_cleanup(&link_primer);
 		goto out_put_prog;
 	}
 
-	fd_install(link_fd, link_file);
-	return link_fd;
-
+	return bpf_link_settle(&link_primer);
 out_put_prog:
 	bpf_prog_put(prog);
 	return err;
@@ -2447,22 +2621,69 @@ static void bpf_raw_tp_link_dealloc(struct bpf_link *link)
 	kfree(raw_tp);
 }
 
-static const struct bpf_link_ops bpf_raw_tp_lops = {
+static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
+					struct seq_file *seq)
+{
+	struct bpf_raw_tp_link *raw_tp_link =
+		container_of(link, struct bpf_raw_tp_link, link);
+
+	seq_printf(seq,
+		   "tp_name:\t%s\n",
+		   raw_tp_link->btp->tp->name);
+}
+
+static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
+					  struct bpf_link_info *info)
+{
+	struct bpf_raw_tp_link *raw_tp_link =
+		container_of(link, struct bpf_raw_tp_link, link);
+	char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name);
+	const char *tp_name = raw_tp_link->btp->tp->name;
+	u32 ulen = info->raw_tracepoint.tp_name_len;
+	size_t tp_len = strlen(tp_name);
+
+	if (ulen && !ubuf)
+		return -EINVAL;
+
+	info->raw_tracepoint.tp_name_len = tp_len + 1;
+
+	if (!ubuf)
+		return 0;
+
+	if (ulen >= tp_len + 1) {
+		if (copy_to_user(ubuf, tp_name, tp_len + 1))
+			return -EFAULT;
+	} else {
+		char zero = '\0';
+
+		if (copy_to_user(ubuf, tp_name, ulen - 1))
+			return -EFAULT;
+		if (put_user(zero, ubuf + ulen - 1))
+			return -EFAULT;
+		return -ENOSPC;
+	}
+
+	return 0;
+}
+
+static const struct bpf_link_ops bpf_raw_tp_link_lops = {
 	.release = bpf_raw_tp_link_release,
 	.dealloc = bpf_raw_tp_link_dealloc,
+	.show_fdinfo = bpf_raw_tp_link_show_fdinfo,
+	.fill_link_info = bpf_raw_tp_link_fill_link_info,
 };
 
 #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
 
 static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 {
+	struct bpf_link_primer link_primer;
 	struct bpf_raw_tp_link *link;
 	struct bpf_raw_event_map *btp;
-	struct file *link_file;
 	struct bpf_prog *prog;
 	const char *tp_name;
 	char buf[128];
-	int link_fd, err;
+	int err;
 
 	if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN))
 		return -EINVAL;
@@ -2515,24 +2736,23 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 		err = -ENOMEM;
 		goto out_put_btp;
 	}
-	bpf_link_init(&link->link, &bpf_raw_tp_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
+		      &bpf_raw_tp_link_lops, prog);
 	link->btp = btp;
 
-	link_file = bpf_link_new_file(&link->link, &link_fd);
-	if (IS_ERR(link_file)) {
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
 		kfree(link);
-		err = PTR_ERR(link_file);
 		goto out_put_btp;
 	}
 
 	err = bpf_probe_register(link->btp, prog);
 	if (err) {
-		bpf_link_cleanup(&link->link, link_file, link_fd);
+		bpf_link_cleanup(&link_primer);
 		goto out_put_btp;
 	}
 
-	fd_install(link_fd, link_file);
-	return link_fd;
+	return bpf_link_settle(&link_primer);
 
 out_put_btp:
 	bpf_put_raw_tracepoint(btp);
@@ -2550,6 +2770,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
+		if (!capable(CAP_NET_ADMIN))
+			/* cg-skb progs can be loaded by unpriv user.
+			 * check permissions at attach time.
+			 */
+			return -EPERM;
 		return prog->enforce_expected_attach_type &&
 			prog->expected_attach_type != attach_type ?
 			-EINVAL : 0;
@@ -2574,6 +2799,10 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_INET4_GETPEERNAME:
+	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_INET4_GETSOCKNAME:
+	case BPF_CGROUP_INET6_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
@@ -2597,6 +2826,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	case BPF_CGROUP_GETSOCKOPT:
 	case BPF_CGROUP_SETSOCKOPT:
 		return BPF_PROG_TYPE_CGROUP_SOCKOPT;
+	case BPF_TRACE_ITER:
+		return BPF_PROG_TYPE_TRACING;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -2613,9 +2844,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	struct bpf_prog *prog;
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
@@ -2644,7 +2872,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		ret = lirc_prog_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		ret = skb_flow_dissector_bpf_prog_attach(attr, prog);
+		ret = netns_bpf_prog_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
@@ -2670,9 +2898,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
 
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
 	if (CHECK_ATTR(BPF_PROG_DETACH))
 		return -EINVAL;
 
@@ -2685,7 +2910,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_PROG_TYPE_LIRC_MODE2:
 		return lirc_prog_detach(attr);
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		return skb_flow_dissector_bpf_prog_detach(attr);
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		return netns_bpf_prog_detach(attr);
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -2721,6 +2948,10 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET6_POST_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_INET4_GETPEERNAME:
+	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_INET4_GETSOCKNAME:
+	case BPF_CGROUP_INET6_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
@@ -2734,7 +2965,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);
 	case BPF_FLOW_DISSECTOR:
-		return skb_flow_dissector_prog_query(attr, uattr);
+		return netns_bpf_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
@@ -2748,8 +2979,6 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
 	struct bpf_prog *prog;
 	int ret = -ENOTSUPP;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
 	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
 		return -EINVAL;
 
@@ -2800,6 +3029,25 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr,
 	return err;
 }
 
+struct bpf_map *bpf_map_get_curr_or_next(u32 *id)
+{
+	struct bpf_map *map;
+
+	spin_lock_bh(&map_idr_lock);
+again:
+	map = idr_get_next(&map_idr, id);
+	if (map) {
+		map = __bpf_map_inc_not_zero(map, false);
+		if (IS_ERR(map)) {
+			(*id)++;
+			goto again;
+		}
+	}
+	spin_unlock_bh(&map_idr_lock);
+
+	return map;
+}
+
 #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
 
 struct bpf_prog *bpf_prog_by_id(u32 id)
@@ -3031,7 +3279,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	info.run_time_ns = stats.nsecs;
 	info.run_cnt = stats.cnt;
 
-	if (!capable(CAP_SYS_ADMIN)) {
+	if (!bpf_capable()) {
 		info.jited_prog_len = 0;
 		info.xlated_prog_len = 0;
 		info.nr_jited_ksyms = 0;
@@ -3313,6 +3561,42 @@ static int bpf_btf_get_info_by_fd(struct btf *btf,
 	return btf_get_info_by_fd(btf, attr, uattr);
 }
 
+static int bpf_link_get_info_by_fd(struct bpf_link *link,
+				  const union bpf_attr *attr,
+				  union bpf_attr __user *uattr)
+{
+	struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+	struct bpf_link_info info;
+	u32 info_len = attr->info.info_len;
+	int err;
+
+	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	if (err)
+		return err;
+	info_len = min_t(u32, sizeof(info), info_len);
+
+	memset(&info, 0, sizeof(info));
+	if (copy_from_user(&info, uinfo, info_len))
+		return -EFAULT;
+
+	info.type = link->type;
+	info.id = link->id;
+	info.prog_id = link->prog->aux->id;
+
+	if (link->ops->fill_link_info) {
+		err = link->ops->fill_link_info(link, &info);
+		if (err)
+			return err;
+	}
+
+	if (copy_to_user(uinfo, &info, info_len) ||
+	    put_user(info_len, &uattr->info.info_len))
+		return -EFAULT;
+
+	return 0;
+}
+
+
 #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
 
 static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
@@ -3337,6 +3621,9 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 					     uattr);
 	else if (f.file->f_op == &btf_fops)
 		err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr);
+	else if (f.file->f_op == &bpf_link_fops)
+		err = bpf_link_get_info_by_fd(f.file->private_data,
+					      attr, uattr);
 	else
 		err = -EINVAL;
 
@@ -3351,7 +3638,7 @@ static int bpf_btf_load(const union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return -EPERM;
 
 	return btf_new_fd(attr);
@@ -3464,7 +3751,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 	if (file->f_op == &bpf_link_fops) {
 		struct bpf_link *link = file->private_data;
 
-		if (link->ops == &bpf_raw_tp_lops) {
+		if (link->ops == &bpf_raw_tp_link_lops) {
 			struct bpf_raw_tp_link *raw_tp =
 				container_of(link, struct bpf_raw_tp_link, link);
 			struct bpf_raw_event_map *btp = raw_tp->btp;
@@ -3558,6 +3845,15 @@ err_put:
 	return err;
 }
 
+static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	if (attr->link_create.attach_type == BPF_TRACE_ITER &&
+	    prog->expected_attach_type == BPF_TRACE_ITER)
+		return bpf_iter_link_attach(attr, prog);
+
+	return -EINVAL;
+}
+
 #define BPF_LINK_CREATE_LAST_FIELD link_create.flags
 static int link_create(union bpf_attr *attr)
 {
@@ -3565,9 +3861,6 @@ static int link_create(union bpf_attr *attr)
 	struct bpf_prog *prog;
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
 	if (CHECK_ATTR(BPF_LINK_CREATE))
 		return -EINVAL;
 
@@ -3594,6 +3887,12 @@ static int link_create(union bpf_attr *attr)
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		ret = cgroup_bpf_link_attach(attr, prog);
 		break;
+	case BPF_PROG_TYPE_TRACING:
+		ret = tracing_bpf_link_attach(attr, prog);
+		break;
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+		ret = netns_bpf_link_create(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -3613,9 +3912,6 @@ static int link_update(union bpf_attr *attr)
 	u32 flags;
 	int ret;
 
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
 	if (CHECK_ATTR(BPF_LINK_UPDATE))
 		return -EINVAL;
 
@@ -3645,13 +3941,10 @@ static int link_update(union bpf_attr *attr)
 		goto out_put_progs;
 	}
 
-#ifdef CONFIG_CGROUP_BPF
-	if (link->ops == &bpf_cgroup_link_lops) {
-		ret = cgroup_bpf_replace(link, old_prog, new_prog);
-		goto out_put_progs;
-	}
-#endif
-	ret = -EINVAL;
+	if (link->ops->update_prog)
+		ret = link->ops->update_prog(link, new_prog, old_prog);
+	else
+		ret = -EINVAL;
 
 out_put_progs:
 	if (old_prog)
@@ -3663,12 +3956,131 @@ out_put_link:
 	return ret;
 }
 
+static int bpf_link_inc_not_zero(struct bpf_link *link)
+{
+	return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT;
+}
+
+#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id
+
+static int bpf_link_get_fd_by_id(const union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	u32 id = attr->link_id;
+	int fd, err;
+
+	if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	spin_lock_bh(&link_idr_lock);
+	link = idr_find(&link_idr, id);
+	/* before link is "settled", ID is 0, pretend it doesn't exist yet */
+	if (link) {
+		if (link->id)
+			err = bpf_link_inc_not_zero(link);
+		else
+			err = -EAGAIN;
+	} else {
+		err = -ENOENT;
+	}
+	spin_unlock_bh(&link_idr_lock);
+
+	if (err)
+		return err;
+
+	fd = bpf_link_new_fd(link);
+	if (fd < 0)
+		bpf_link_put(link);
+
+	return fd;
+}
+
+DEFINE_MUTEX(bpf_stats_enabled_mutex);
+
+static int bpf_stats_release(struct inode *inode, struct file *file)
+{
+	mutex_lock(&bpf_stats_enabled_mutex);
+	static_key_slow_dec(&bpf_stats_enabled_key.key);
+	mutex_unlock(&bpf_stats_enabled_mutex);
+	return 0;
+}
+
+static const struct file_operations bpf_stats_fops = {
+	.release = bpf_stats_release,
+};
+
+static int bpf_enable_runtime_stats(void)
+{
+	int fd;
+
+	mutex_lock(&bpf_stats_enabled_mutex);
+
+	/* Set a very high limit to avoid overflow */
+	if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) {
+		mutex_unlock(&bpf_stats_enabled_mutex);
+		return -EBUSY;
+	}
+
+	fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC);
+	if (fd >= 0)
+		static_key_slow_inc(&bpf_stats_enabled_key.key);
+
+	mutex_unlock(&bpf_stats_enabled_mutex);
+	return fd;
+}
+
+#define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type
+
+static int bpf_enable_stats(union bpf_attr *attr)
+{
+
+	if (CHECK_ATTR(BPF_ENABLE_STATS))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (attr->enable_stats.type) {
+	case BPF_STATS_RUN_TIME:
+		return bpf_enable_runtime_stats();
+	default:
+		break;
+	}
+	return -EINVAL;
+}
+
+#define BPF_ITER_CREATE_LAST_FIELD iter_create.flags
+
+static int bpf_iter_create(union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	int err;
+
+	if (CHECK_ATTR(BPF_ITER_CREATE))
+		return -EINVAL;
+
+	if (attr->iter_create.flags)
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->iter_create.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	err = bpf_iter_new_fd(link);
+	bpf_link_put(link);
+
+	return err;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr;
 	int err;
 
-	if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
+	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
 		return -EPERM;
 
 	err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size);
@@ -3780,6 +4192,19 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_LINK_UPDATE:
 		err = link_update(&attr);
 		break;
+	case BPF_LINK_GET_FD_BY_ID:
+		err = bpf_link_get_fd_by_id(&attr);
+		break;
+	case BPF_LINK_GET_NEXT_ID:
+		err = bpf_obj_get_next_id(&attr, uattr,
+					  &link_idr, &link_idr_lock);
+		break;
+	case BPF_ENABLE_STATS:
+		err = bpf_enable_stats(&attr);
+		break;
+	case BPF_ITER_CREATE:
+		err = bpf_iter_create(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;