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, 80 insertions, 57 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 6b6f41f0b211..5e00b2333c26 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1,4 +1,5 @@
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016,2017 Facebook
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -16,6 +17,8 @@
 #include <linux/filter.h>
 #include <linux/perf_event.h>
 
+#include "map_in_map.h"
+
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
@@ -113,6 +116,30 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	return array->value + array->elem_size * index;
 }
 
+/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
+static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_insn *insn = insn_buf;
+	u32 elem_size = round_up(map->value_size, 8);
+	const int ret = BPF_REG_0;
+	const int map_ptr = BPF_REG_1;
+	const int index = BPF_REG_2;
+
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
+	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+
+	if (is_power_of_2(elem_size)) {
+		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
+	} else {
+		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
+	}
+	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(ret, 0);
+	return insn - insn_buf;
+}
+
 /* Called from eBPF program */
 static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 {
@@ -155,7 +182,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
 static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	u32 index = *(u32 *)key;
+	u32 index = key ? *(u32 *)key : U32_MAX;
 	u32 *next = (u32 *)next_key;
 
 	if (index >= array->map.max_entries) {
@@ -260,21 +287,17 @@ static void array_map_free(struct bpf_map *map)
 	bpf_map_area_free(array);
 }
 
-static const struct bpf_map_ops array_ops = {
+const struct bpf_map_ops array_map_ops = {
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = array_map_lookup_elem,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
+	.map_gen_lookup = array_map_gen_lookup,
 };
 
-static struct bpf_map_type_list array_type __ro_after_init = {
-	.ops = &array_ops,
-	.type = BPF_MAP_TYPE_ARRAY,
-};
-
-static const struct bpf_map_ops percpu_array_ops = {
+const struct bpf_map_ops percpu_array_map_ops = {
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -283,19 +306,6 @@ static const struct bpf_map_ops percpu_array_ops = {
 	.map_delete_elem = array_map_delete_elem,
 };
 
-static struct bpf_map_type_list percpu_array_type __ro_after_init = {
-	.ops = &percpu_array_ops,
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-};
-
-static int __init register_array_map(void)
-{
-	bpf_register_map_type(&array_type);
-	bpf_register_map_type(&percpu_array_type);
-	return 0;
-}
-late_initcall(register_array_map);
-
 static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr)
 {
 	/* only file descriptors can be stored in this type of map */
@@ -399,7 +409,7 @@ void bpf_fd_array_map_clear(struct bpf_map *map)
 		fd_array_map_delete_elem(map, &i);
 }
 
-static const struct bpf_map_ops prog_array_ops = {
+const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc = fd_array_map_alloc,
 	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -409,18 +419,6 @@ static const struct bpf_map_ops prog_array_ops = {
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 };
 
-static struct bpf_map_type_list prog_array_type __ro_after_init = {
-	.ops = &prog_array_ops,
-	.type = BPF_MAP_TYPE_PROG_ARRAY,
-};
-
-static int __init register_prog_array_map(void)
-{
-	bpf_register_map_type(&prog_array_type);
-	return 0;
-}
-late_initcall(register_prog_array_map);
-
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
 						   struct file *map_file)
 {
@@ -511,7 +509,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	rcu_read_unlock();
 }
 
-static const struct bpf_map_ops perf_event_array_ops = {
+const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_alloc = fd_array_map_alloc,
 	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -522,18 +520,6 @@ static const struct bpf_map_ops perf_event_array_ops = {
 	.map_release = perf_event_fd_array_release,
 };
 
-static struct bpf_map_type_list perf_event_array_type __ro_after_init = {
-	.ops = &perf_event_array_ops,
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-};
-
-static int __init register_perf_event_array_map(void)
-{
-	bpf_register_map_type(&perf_event_array_type);
-	return 0;
-}
-late_initcall(register_perf_event_array_map);
-
 #ifdef CONFIG_CGROUPS
 static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
 				     struct file *map_file /* not used */,
@@ -554,7 +540,7 @@ static void cgroup_fd_array_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
-static const struct bpf_map_ops cgroup_array_ops = {
+const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_alloc = fd_array_map_alloc,
 	.map_free = cgroup_fd_array_free,
 	.map_get_next_key = array_map_get_next_key,
@@ -563,16 +549,53 @@ static const struct bpf_map_ops cgroup_array_ops = {
 	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
 	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
 };
+#endif
 
-static struct bpf_map_type_list cgroup_array_type __ro_after_init = {
-	.ops = &cgroup_array_ops,
-	.type = BPF_MAP_TYPE_CGROUP_ARRAY,
-};
+static struct bpf_map *array_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;
 
-static int __init register_cgroup_array_map(void)
+	map = fd_array_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;
+}
+
+static void array_of_map_free(struct bpf_map *map)
 {
-	bpf_register_map_type(&cgroup_array_type);
-	return 0;
+	/* map->inner_map_meta is only accessed by syscall which
+	 * is protected by fdget/fdput.
+	 */
+	bpf_map_meta_free(map->inner_map_meta);
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
 }
-late_initcall(register_cgroup_array_map);
-#endif
+
+static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_map **inner_map = array_map_lookup_elem(map, key);
+
+	if (!inner_map)
+		return NULL;
+
+	return READ_ONCE(*inner_map);
+}
+
+const struct bpf_map_ops array_of_maps_map_ops = {
+	.map_alloc = array_of_map_alloc,
+	.map_free = array_of_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = array_of_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = bpf_map_fd_get_ptr,
+	.map_fd_put_ptr = bpf_map_fd_put_ptr,
+};