Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

1 files changed, 267 insertions, 115 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ace1cfaa24b6..e3461ec59570 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -23,13 +23,15 @@
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
 #include <linux/nospec.h>
+#include <uapi/linux/btf.h>
 
-#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
-			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
-			   (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
-			   (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
+#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
+			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
+			  (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
+#define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY)
 #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
-#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map))
+#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \
+			IS_FD_HASH(map))
 
 #define BPF_OBJ_FLAG_MASK   (BPF_F_RDONLY | BPF_F_WRONLY)
 
@@ -42,7 +44,7 @@ static DEFINE_SPINLOCK(map_idr_lock);
 int sysctl_unprivileged_bpf_disabled __read_mostly;
 
 static const struct bpf_map_ops * const bpf_map_types[] = {
-#define BPF_PROG_TYPE(_id, _ops)
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
 #define BPF_MAP_TYPE(_id, _ops) \
 	[_id] = &_ops,
 #include <linux/bpf_types.h>
@@ -126,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
-void *bpf_map_area_alloc(u64 size, int numa_node)
+static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
 {
 	/* We really just want to fail instead of triggering OOM killer
 	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
@@ -144,18 +146,33 @@ void *bpf_map_area_alloc(u64 size, int numa_node)
 	if (size >= SIZE_MAX)
 		return NULL;
 
-	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+	/* 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,
 				    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));
 }
 
+void *bpf_map_area_alloc(u64 size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, false);
+}
+
+void *bpf_map_area_mmapable_alloc(u64 size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, true);
+}
+
 void bpf_map_area_free(void *area)
 {
 	kvfree(area);
@@ -313,7 +330,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 static void bpf_map_put_uref(struct bpf_map *map)
 {
-	if (atomic_dec_and_test(&map->usercnt)) {
+	if (atomic64_dec_and_test(&map->usercnt)) {
 		if (map->ops->map_release_uref)
 			map->ops->map_release_uref(map);
 	}
@@ -324,7 +341,7 @@ static void bpf_map_put_uref(struct bpf_map *map)
  */
 static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
 {
-	if (atomic_dec_and_test(&map->refcnt)) {
+	if (atomic64_dec_and_test(&map->refcnt)) {
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map, do_idr_lock);
 		btf_put(map->btf);
@@ -373,13 +390,12 @@ 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;
-	u32 owner_jited = 0;
+	u32 type = 0, jited = 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;
-		owner_jited = array->owner_jited;
+		type  = array->aux->type;
+		jited = array->aux->jited;
 	}
 
 	seq_printf(m,
@@ -399,12 +415,9 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   map->memory.pages * 1ULL << PAGE_SHIFT,
 		   map->id,
 		   READ_ONCE(map->frozen));
-
-	if (owner_prog_type) {
-		seq_printf(m, "owner_prog_type:\t%u\n",
-			   owner_prog_type);
-		seq_printf(m, "owner_jited:\t%u\n",
-			   owner_jited);
+	if (type) {
+		seq_printf(m, "owner_prog_type:\t%u\n", type);
+		seq_printf(m, "owner_jited:\t%u\n", jited);
 	}
 }
 #endif
@@ -427,6 +440,74 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
 	return -EINVAL;
 }
 
+/* called for any extra memory-mapped regions (except initial) */
+static void bpf_map_mmap_open(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt++;
+		mutex_unlock(&map->freeze_mutex);
+	}
+}
+
+/* called for all unmapped memory region (including initial) */
+static void bpf_map_mmap_close(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt--;
+		mutex_unlock(&map->freeze_mutex);
+	}
+
+	bpf_map_put_with_uref(map);
+}
+
+static const struct vm_operations_struct bpf_map_default_vmops = {
+	.open		= bpf_map_mmap_open,
+	.close		= bpf_map_mmap_close,
+};
+
+static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct bpf_map *map = filp->private_data;
+	int err;
+
+	if (!map->ops->map_mmap || map_value_has_spin_lock(map))
+		return -ENOTSUPP;
+
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	mutex_lock(&map->freeze_mutex);
+
+	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
+		err = -EPERM;
+		goto out;
+	}
+
+	/* set default open/close callbacks */
+	vma->vm_ops = &bpf_map_default_vmops;
+	vma->vm_private_data = map;
+
+	err = map->ops->map_mmap(map, vma);
+	if (err)
+		goto out;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE)
+		map->writecnt++;
+out:
+	mutex_unlock(&map->freeze_mutex);
+	return err;
+}
+
 const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
@@ -434,6 +515,7 @@ const struct file_operations bpf_map_fops = {
 	.release	= bpf_map_release,
 	.read		= bpf_dummy_read,
 	.write		= bpf_dummy_write,
+	.mmap		= bpf_map_mmap,
 };
 
 int bpf_map_new_fd(struct bpf_map *map, int flags)
@@ -577,8 +659,9 @@ static int map_create(union bpf_attr *attr)
 	if (err)
 		goto free_map;
 
-	atomic_set(&map->refcnt, 1);
-	atomic_set(&map->usercnt, 1);
+	atomic64_set(&map->refcnt, 1);
+	atomic64_set(&map->usercnt, 1);
+	mutex_init(&map->freeze_mutex);
 
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
@@ -655,21 +738,19 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-/* prog's and map's refcnt limit */
-#define BPF_MAX_REFCNT 32768
-
-struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
+void bpf_map_inc(struct bpf_map *map)
 {
-	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
-		atomic_dec(&map->refcnt);
-		return ERR_PTR(-EBUSY);
-	}
-	if (uref)
-		atomic_inc(&map->usercnt);
-	return map;
+	atomic64_inc(&map->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_map_inc);
 
+void bpf_map_inc_with_uref(struct bpf_map *map)
+{
+	atomic64_inc(&map->refcnt);
+	atomic64_inc(&map->usercnt);
+}
+EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref);
+
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
 	struct fd f = fdget(ufd);
@@ -679,38 +760,30 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	map = bpf_map_inc(map, true);
+	bpf_map_inc_with_uref(map);
 	fdput(f);
 
 	return map;
 }
 
 /* map_idr_lock should have been held */
-static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map,
-					      bool uref)
+static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
 {
 	int refold;
 
-	refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
-
-	if (refold >= BPF_MAX_REFCNT) {
-		__bpf_map_put(map, false);
-		return ERR_PTR(-EBUSY);
-	}
-
+	refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0);
 	if (!refold)
 		return ERR_PTR(-ENOENT);
-
 	if (uref)
-		atomic_inc(&map->usercnt);
+		atomic64_inc(&map->usercnt);
 
 	return map;
 }
 
-struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
+struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map)
 {
 	spin_lock_bh(&map_idr_lock);
-	map = __bpf_map_inc_not_zero(map, uref);
+	map = __bpf_map_inc_not_zero(map, false);
 	spin_unlock_bh(&map_idr_lock);
 
 	return map;
@@ -805,7 +878,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 		err = bpf_percpu_cgroup_storage_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
 		err = bpf_stackmap_copy(map, key, value);
-	} else if (IS_FD_ARRAY(map)) {
+	} else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
 		err = bpf_fd_array_map_lookup_elem(map, key, value);
 	} else if (IS_FD_HASH(map)) {
 		err = bpf_fd_htab_map_lookup_elem(map, key, value);
@@ -932,6 +1005,10 @@ static int map_update_elem(union bpf_attr *attr)
 		   map->map_type == BPF_MAP_TYPE_SOCKMAP) {
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
 		goto out;
+	} else if (IS_FD_PROG_ARRAY(map)) {
+		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
+						   attr->flags);
+		goto out;
 	}
 
 	/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
@@ -1014,6 +1091,9 @@ static int map_delete_elem(union bpf_attr *attr)
 	if (bpf_map_is_dev_bound(map)) {
 		err = bpf_map_offload_delete_elem(map, key);
 		goto out;
+	} else if (IS_FD_PROG_ARRAY(map)) {
+		err = map->ops->map_delete_elem(map, key);
+		goto out;
 	}
 
 	preempt_disable();
@@ -1175,6 +1255,13 @@ static int map_freeze(const union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+
+	mutex_lock(&map->freeze_mutex);
+
+	if (map->writecnt) {
+		err = -EBUSY;
+		goto err_put;
+	}
 	if (READ_ONCE(map->frozen)) {
 		err = -EBUSY;
 		goto err_put;
@@ -1186,12 +1273,13 @@ static int map_freeze(const union bpf_attr *attr)
 
 	WRITE_ONCE(map->frozen, true);
 err_put:
+	mutex_unlock(&map->freeze_mutex);
 	fdput(f);
 	return err;
 }
 
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
-#define BPF_PROG_TYPE(_id, _name) \
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	[_id] = & _name ## _prog_ops,
 #define BPF_MAP_TYPE(_id, _ops)
 #include <linux/bpf_types.h>
@@ -1218,25 +1306,6 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 	return 0;
 }
 
-/* drop refcnt on maps used by eBPF program and free auxilary data */
-static void free_used_maps(struct bpf_prog_aux *aux)
-{
-	enum bpf_cgroup_storage_type stype;
-	int i;
-
-	for_each_cgroup_storage_type(stype) {
-		if (!aux->cgroup_storage[stype])
-			continue;
-		bpf_cgroup_storage_release(aux->prog,
-					   aux->cgroup_storage[stype]);
-	}
-
-	for (i = 0; i < aux->used_map_cnt; i++)
-		bpf_map_put(aux->used_maps[i]);
-
-	kfree(aux->used_maps);
-}
-
 int __bpf_prog_charge(struct user_struct *user, u32 pages)
 {
 	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
@@ -1330,7 +1399,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
 	kvfree(aux->func_info);
-	free_used_maps(aux);
+	kfree(aux->func_info_aux);
 	bpf_prog_uncharge_memlock(aux->prog);
 	security_bpf_prog_free(aux);
 	bpf_prog_free(aux->prog);
@@ -1350,7 +1419,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
 
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
-	if (atomic_dec_and_test(&prog->aux->refcnt)) {
+	if (atomic64_dec_and_test(&prog->aux->refcnt)) {
 		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
@@ -1456,13 +1525,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
-struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
+void bpf_prog_add(struct bpf_prog *prog, int i)
 {
-	if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
-		atomic_sub(i, &prog->aux->refcnt);
-		return ERR_PTR(-EBUSY);
-	}
-	return prog;
+	atomic64_add(i, &prog->aux->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_add);
 
@@ -1473,13 +1538,13 @@ void bpf_prog_sub(struct bpf_prog *prog, int i)
 	 * path holds a reference to the program, thus atomic_sub() can
 	 * be safely used in such cases!
 	 */
-	WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
+	WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_sub);
 
-struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+void bpf_prog_inc(struct bpf_prog *prog)
 {
-	return bpf_prog_add(prog, 1);
+	atomic64_inc(&prog->aux->refcnt);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_inc);
 
@@ -1488,12 +1553,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 {
 	int refold;
 
-	refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
-
-	if (refold >= BPF_MAX_REFCNT) {
-		__bpf_prog_put(prog, false);
-		return ERR_PTR(-EBUSY);
-	}
+	refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0);
 
 	if (!refold)
 		return ERR_PTR(-ENOENT);
@@ -1531,7 +1591,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
 		goto out;
 	}
 
-	prog = bpf_prog_inc(prog);
+	bpf_prog_inc(prog);
 out:
 	fdput(f);
 	return prog;
@@ -1576,10 +1636,22 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 }
 
 static int
-bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
-				enum bpf_attach_type expected_attach_type)
+bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
+			   enum bpf_attach_type expected_attach_type,
+			   u32 btf_id, u32 prog_fd)
 {
 	switch (prog_type) {
+	case BPF_PROG_TYPE_TRACING:
+		if (btf_id > BTF_MAX_TYPE)
+			return -EINVAL;
+		break;
+	default:
+		if (btf_id || prog_fd)
+			return -EINVAL;
+		break;
+	}
+
+	switch (prog_type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 		switch (expected_attach_type) {
 		case BPF_CGROUP_INET_SOCK_CREATE:
@@ -1625,7 +1697,7 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD line_info_cnt
+#define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
 
 static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
@@ -1667,7 +1739,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		return -EPERM;
 
 	bpf_prog_load_fixup_attach_type(attr);
-	if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type))
+	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
+				       attr->attach_btf_id,
+				       attr->attach_prog_fd))
 		return -EINVAL;
 
 	/* plain bpf_prog allocation */
@@ -1676,6 +1750,17 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		return -ENOMEM;
 
 	prog->expected_attach_type = attr->expected_attach_type;
+	prog->aux->attach_btf_id = attr->attach_btf_id;
+	if (attr->attach_prog_fd) {
+		struct bpf_prog *tgt_prog;
+
+		tgt_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(tgt_prog)) {
+			err = PTR_ERR(tgt_prog);
+			goto free_prog_nouncharge;
+		}
+		prog->aux->linked_prog = tgt_prog;
+	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 
@@ -1697,7 +1782,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->orig_prog = NULL;
 	prog->jited = 0;
 
-	atomic_set(&prog->aux->refcnt, 1);
+	atomic64_set(&prog->aux->refcnt, 1);
 	prog->gpl_compatible = is_gpl ? 1 : 0;
 
 	if (bpf_prog_is_dev_bound(prog->aux)) {
@@ -1787,6 +1872,49 @@ static int bpf_obj_get(const union bpf_attr *attr)
 				attr->file_flags);
 }
 
+static int bpf_tracing_prog_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_prog *prog = filp->private_data;
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
+	bpf_prog_put(prog);
+	return 0;
+}
+
+static const struct file_operations bpf_tracing_prog_fops = {
+	.release	= bpf_tracing_prog_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
+};
+
+static int bpf_tracing_prog_attach(struct bpf_prog *prog)
+{
+	int tr_fd, err;
+
+	if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
+	    prog->expected_attach_type != BPF_TRACE_FEXIT) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
+
+	err = bpf_trampoline_link_prog(prog);
+	if (err)
+		goto out_put_prog;
+
+	tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops,
+				 prog, O_CLOEXEC);
+	if (tr_fd < 0) {
+		WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
+		err = tr_fd;
+		goto out_put_prog;
+	}
+	return tr_fd;
+
+out_put_prog:
+	bpf_prog_put(prog);
+	return err;
+}
+
 struct bpf_raw_tracepoint {
 	struct bpf_raw_event_map *btp;
 	struct bpf_prog *prog;
@@ -1818,17 +1946,52 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 	struct bpf_raw_tracepoint *raw_tp;
 	struct bpf_raw_event_map *btp;
 	struct bpf_prog *prog;
-	char tp_name[128];
+	const char *tp_name;
+	char buf[128];
 	int tp_fd, err;
 
-	if (strncpy_from_user(tp_name, u64_to_user_ptr(attr->raw_tracepoint.name),
-			      sizeof(tp_name) - 1) < 0)
-		return -EFAULT;
-	tp_name[sizeof(tp_name) - 1] = 0;
+	if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN))
+		return -EINVAL;
+
+	prog = bpf_prog_get(attr->raw_tracepoint.prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
+	    prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
+
+	if (prog->type == BPF_PROG_TYPE_TRACING) {
+		if (attr->raw_tracepoint.name) {
+			/* The attach point for this category of programs
+			 * should be specified via btf_id during program load.
+			 */
+			err = -EINVAL;
+			goto out_put_prog;
+		}
+		if (prog->expected_attach_type == BPF_TRACE_RAW_TP)
+			tp_name = prog->aux->attach_func_name;
+		else
+			return bpf_tracing_prog_attach(prog);
+	} else {
+		if (strncpy_from_user(buf,
+				      u64_to_user_ptr(attr->raw_tracepoint.name),
+				      sizeof(buf) - 1) < 0) {
+			err = -EFAULT;
+			goto out_put_prog;
+		}
+		buf[sizeof(buf) - 1] = 0;
+		tp_name = buf;
+	}
 
 	btp = bpf_get_raw_tracepoint(tp_name);
-	if (!btp)
-		return -ENOENT;
+	if (!btp) {
+		err = -ENOENT;
+		goto out_put_prog;
+	}
 
 	raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
 	if (!raw_tp) {
@@ -1836,38 +1999,27 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 		goto out_put_btp;
 	}
 	raw_tp->btp = btp;
-
-	prog = bpf_prog_get(attr->raw_tracepoint.prog_fd);
-	if (IS_ERR(prog)) {
-		err = PTR_ERR(prog);
-		goto out_free_tp;
-	}
-	if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
-	    prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
-		err = -EINVAL;
-		goto out_put_prog;
-	}
+	raw_tp->prog = prog;
 
 	err = bpf_probe_register(raw_tp->btp, prog);
 	if (err)
-		goto out_put_prog;
+		goto out_free_tp;
 
-	raw_tp->prog = prog;
 	tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp,
 				 O_CLOEXEC);
 	if (tp_fd < 0) {
 		bpf_probe_unregister(raw_tp->btp, prog);
 		err = tp_fd;
-		goto out_put_prog;
+		goto out_free_tp;
 	}
 	return tp_fd;
 
-out_put_prog:
-	bpf_prog_put(prog);
 out_free_tp:
 	kfree(raw_tp);
 out_put_btp:
 	bpf_put_raw_tracepoint(btp);
+out_put_prog:
+	bpf_prog_put(prog);
 	return err;
 }