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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

1 files changed, 150 insertions, 35 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 361a69dfe543..004334ea13ba 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -16,6 +16,7 @@
 #include <linux/rculist_nulls.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
+#include "map_in_map.h"
 
 struct bucket {
 	struct hlist_nulls_head head;
@@ -86,6 +87,11 @@ static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size
 	return *(void __percpu **)(l->key + key_size);
 }
 
+static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
+{
+	return *(void **)(l->key + roundup(map->key_size, 8));
+}
+
 static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
 {
 	return (struct htab_elem *) (htab->elems + i * htab->elem_size);
@@ -426,7 +432,11 @@ again:
 	return NULL;
 }
 
-/* Called from syscall or from eBPF program */
+/* Called from syscall or from eBPF program directly, so
+ * arguments have to match bpf_map_lookup_elem() exactly.
+ * The return value is adjusted by BPF instructions
+ * in htab_map_gen_lookup().
+ */
 static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
@@ -458,6 +468,30 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
 	return NULL;
 }
 
+/* inline bpf_map_lookup_elem() call.
+ * Instead of:
+ * bpf_prog
+ *   bpf_map_lookup_elem
+ *     map->ops->map_lookup_elem
+ *       htab_map_lookup_elem
+ *         __htab_map_lookup_elem
+ * do:
+ * bpf_prog
+ *   __htab_map_lookup_elem
+ */
+static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+	const int ret = BPF_REG_0;
+
+	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
+	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
+				offsetof(struct htab_elem, key) +
+				round_up(map->key_size, 8));
+	return insn - insn_buf;
+}
+
 static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
@@ -506,12 +540,15 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	struct hlist_nulls_head *head;
 	struct htab_elem *l, *next_l;
 	u32 hash, key_size;
-	int i;
+	int i = 0;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	key_size = map->key_size;
 
+	if (!key)
+		goto find_first_elem;
+
 	hash = htab_map_hash(key, key_size);
 
 	head = select_bucket(htab, hash);
@@ -519,10 +556,8 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	/* lookup the key */
 	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
 
-	if (!l) {
-		i = 0;
+	if (!l)
 		goto find_first_elem;
-	}
 
 	/* key was found, get next key in the same bucket */
 	next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
@@ -582,6 +617,14 @@ static void htab_elem_free_rcu(struct rcu_head *head)
 
 static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 {
+	struct bpf_map *map = &htab->map;
+
+	if (map->ops->map_fd_put_ptr) {
+		void *ptr = fd_htab_map_get_ptr(map, l);
+
+		map->ops->map_fd_put_ptr(ptr);
+	}
+
 	if (htab_is_prealloc(htab)) {
 		pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
@@ -1027,6 +1070,7 @@ static void delete_all_elements(struct bpf_htab *htab)
 		}
 	}
 }
+
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 static void htab_map_free(struct bpf_map *map)
 {
@@ -1053,21 +1097,17 @@ static void htab_map_free(struct bpf_map *map)
 	kfree(htab);
 }
 
-static const struct bpf_map_ops htab_ops = {
+const struct bpf_map_ops htab_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
 	.map_lookup_elem = htab_map_lookup_elem,
 	.map_update_elem = htab_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
+	.map_gen_lookup = htab_map_gen_lookup,
 };
 
-static struct bpf_map_type_list htab_type __ro_after_init = {
-	.ops = &htab_ops,
-	.type = BPF_MAP_TYPE_HASH,
-};
-
-static const struct bpf_map_ops htab_lru_ops = {
+const struct bpf_map_ops htab_lru_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1076,11 +1116,6 @@ static const struct bpf_map_ops htab_lru_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 };
 
-static struct bpf_map_type_list htab_lru_type __ro_after_init = {
-	.ops = &htab_lru_ops,
-	.type = BPF_MAP_TYPE_LRU_HASH,
-};
-
 /* Called from eBPF program */
 static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 {
@@ -1154,7 +1189,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 	return ret;
 }
 
-static const struct bpf_map_ops htab_percpu_ops = {
+const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1163,12 +1198,7 @@ static const struct bpf_map_ops htab_percpu_ops = {
 	.map_delete_elem = htab_map_delete_elem,
 };
 
-static struct bpf_map_type_list htab_percpu_type __ro_after_init = {
-	.ops = &htab_percpu_ops,
-	.type = BPF_MAP_TYPE_PERCPU_HASH,
-};
-
-static const struct bpf_map_ops htab_lru_percpu_ops = {
+const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
@@ -1177,17 +1207,102 @@ static const struct bpf_map_ops htab_lru_percpu_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 };
 
-static struct bpf_map_type_list htab_lru_percpu_type __ro_after_init = {
-	.ops = &htab_lru_percpu_ops,
-	.type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
-};
+static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map;
+
+	if (attr->value_size != sizeof(u32))
+		return ERR_PTR(-EINVAL);
+
+	/* pointer is stored internally */
+	attr->value_size = sizeof(void *);
+	map = htab_map_alloc(attr);
+	attr->value_size = sizeof(u32);
 
-static int __init register_htab_map(void)
+	return map;
+}
+
+static void fd_htab_map_free(struct bpf_map *map)
 {
-	bpf_register_map_type(&htab_type);
-	bpf_register_map_type(&htab_percpu_type);
-	bpf_register_map_type(&htab_lru_type);
-	bpf_register_map_type(&htab_lru_percpu_type);
-	return 0;
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct hlist_nulls_node *n;
+	struct hlist_nulls_head *head;
+	struct htab_elem *l;
+	int i;
+
+	for (i = 0; i < htab->n_buckets; i++) {
+		head = select_bucket(htab, i);
+
+		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+			void *ptr = fd_htab_map_get_ptr(map, l);
+
+			map->ops->map_fd_put_ptr(ptr);
+		}
+	}
+
+	htab_map_free(map);
+}
+
+/* only called from syscall */
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+				void *key, void *value, u64 map_flags)
+{
+	void *ptr;
+	int ret;
+	u32 ufd = *(u32 *)value;
+
+	ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	ret = htab_map_update_elem(map, key, &ptr, map_flags);
+	if (ret)
+		map->ops->map_fd_put_ptr(ptr);
+
+	return ret;
+}
+
+static struct bpf_map *htab_of_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map, *inner_map_meta;
+
+	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+	if (IS_ERR(inner_map_meta))
+		return inner_map_meta;
+
+	map = fd_htab_map_alloc(attr);
+	if (IS_ERR(map)) {
+		bpf_map_meta_free(inner_map_meta);
+		return map;
+	}
+
+	map->inner_map_meta = inner_map_meta;
+
+	return map;
 }
-late_initcall(register_htab_map);
+
+static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_map **inner_map  = htab_map_lookup_elem(map, key);
+
+	if (!inner_map)
+		return NULL;
+
+	return READ_ONCE(*inner_map);
+}
+
+static void htab_of_map_free(struct bpf_map *map)
+{
+	bpf_map_meta_free(map->inner_map_meta);
+	fd_htab_map_free(map);
+}
+
+const struct bpf_map_ops htab_of_maps_map_ops = {
+	.map_alloc = htab_of_map_alloc,
+	.map_free = htab_of_map_free,
+	.map_get_next_key = htab_map_get_next_key,
+	.map_lookup_elem = htab_of_map_lookup_elem,
+	.map_delete_elem = htab_map_delete_elem,
+	.map_fd_get_ptr = bpf_map_fd_get_ptr,
+	.map_fd_put_ptr = bpf_map_fd_put_ptr,
+};