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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

16 files changed, 1887 insertions, 413 deletions

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 4c2fa3ac56f6..29d781061cd5 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
+CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 262a321f58a6..1c65ce0098a9 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -75,6 +75,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	u32 elem_size, index_mask, max_entries;
 	bool unpriv = !capable(CAP_SYS_ADMIN);
 	u64 cost, array_size, mask64;
+	struct bpf_map_memory mem;
 	struct bpf_array *array;
 
 	elem_size = round_up(attr->value_size, 8);
@@ -108,32 +109,29 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	/* make sure there is no u32 overflow later in round_up() */
 	cost = array_size;
-	if (cost >= U32_MAX - PAGE_SIZE)
-		return ERR_PTR(-ENOMEM);
-	if (percpu) {
+	if (percpu)
 		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
-		if (cost >= U32_MAX - PAGE_SIZE)
-			return ERR_PTR(-ENOMEM);
-	}
-	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
 
-	ret = bpf_map_precharge_memlock(cost);
+	ret = bpf_map_charge_init(&mem, cost);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
 	array = bpf_map_area_alloc(array_size, numa_node);
-	if (!array)
+	if (!array) {
+		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
+	}
 	array->index_mask = index_mask;
 	array->map.unpriv_array = unpriv;
 
 	/* copy mandatory map attributes */
 	bpf_map_init_from_attr(&array->map, attr);
-	array->map.pages = cost;
+	bpf_map_charge_move(&array->map.memory, &mem);
 	array->elem_size = elem_size;
 
 	if (percpu && bpf_array_alloc_percpu(array)) {
+		bpf_map_charge_finish(&array->map.memory);
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index cad09858a5f2..546ebee39e2a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1928,8 +1928,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
 	/* Check array->index_type */
 	index_type_id = array->index_type;
 	index_type = btf_type_by_id(btf, index_type_id);
-	if (btf_type_is_resolve_source_only(index_type) ||
-	    btf_type_nosize_or_null(index_type)) {
+	if (btf_type_nosize_or_null(index_type) ||
+	    btf_type_is_resolve_source_only(index_type)) {
 		btf_verifier_log_type(env, v->t, "Invalid index");
 		return -EINVAL;
 	}
@@ -1948,8 +1948,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
 	/* Check array->type */
 	elem_type_id = array->type;
 	elem_type = btf_type_by_id(btf, elem_type_id);
-	if (btf_type_is_resolve_source_only(elem_type) ||
-	    btf_type_nosize_or_null(elem_type)) {
+	if (btf_type_nosize_or_null(elem_type) ||
+	    btf_type_is_resolve_source_only(elem_type)) {
 		btf_verifier_log_type(env, v->t,
 				      "Invalid elem");
 		return -EINVAL;
@@ -2170,8 +2170,8 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 		const struct btf_type *member_type = btf_type_by_id(env->btf,
 								member_type_id);
 
-		if (btf_type_is_resolve_source_only(member_type) ||
-		    btf_type_nosize_or_null(member_type)) {
+		if (btf_type_nosize_or_null(member_type) ||
+		    btf_type_is_resolve_source_only(member_type)) {
 			btf_verifier_log_member(env, v->t, member,
 						"Invalid member");
 			return -EINVAL;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 92a7d0cf8d13..0a00eaca6fae 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -15,19 +15,34 @@
 #include <linux/bpf.h>
 #include <linux/bpf-cgroup.h>
 #include <net/sock.h>
+#include <net/bpf_sk_storage.h>
+
+#include "../cgroup/cgroup-internal.h"
 
 DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key);
 EXPORT_SYMBOL(cgroup_bpf_enabled_key);
 
+void cgroup_bpf_offline(struct cgroup *cgrp)
+{
+	cgroup_get(cgrp);
+	percpu_ref_kill(&cgrp->bpf.refcnt);
+}
+
 /**
- * cgroup_bpf_put() - put references of all bpf programs
- * @cgrp: the cgroup to modify
+ * cgroup_bpf_release() - put references of all bpf programs and
+ *                        release all cgroup bpf data
+ * @work: work structure embedded into the cgroup to modify
  */
-void cgroup_bpf_put(struct cgroup *cgrp)
+static void cgroup_bpf_release(struct work_struct *work)
 {
+	struct cgroup *cgrp = container_of(work, struct cgroup,
+					   bpf.release_work);
 	enum bpf_cgroup_storage_type stype;
+	struct bpf_prog_array *old_array;
 	unsigned int type;
 
+	mutex_lock(&cgroup_mutex);
+
 	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
 		struct list_head *progs = &cgrp->bpf.progs[type];
 		struct bpf_prog_list *pl, *tmp;
@@ -42,8 +57,29 @@ void cgroup_bpf_put(struct cgroup *cgrp)
 			kfree(pl);
 			static_branch_dec(&cgroup_bpf_enabled_key);
 		}
-		bpf_prog_array_free(cgrp->bpf.effective[type]);
+		old_array = rcu_dereference_protected(
+				cgrp->bpf.effective[type],
+				lockdep_is_held(&cgroup_mutex));
+		bpf_prog_array_free(old_array);
 	}
+
+	mutex_unlock(&cgroup_mutex);
+
+	percpu_ref_exit(&cgrp->bpf.refcnt);
+	cgroup_put(cgrp);
+}
+
+/**
+ * cgroup_bpf_release_fn() - callback used to schedule releasing
+ *                           of bpf cgroup data
+ * @ref: percpu ref counter structure
+ */
+static void cgroup_bpf_release_fn(struct percpu_ref *ref)
+{
+	struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt);
+
+	INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release);
+	queue_work(system_wq, &cgrp->bpf.release_work);
 }
 
 /* count number of elements in the list.
@@ -98,7 +134,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp,
  */
 static int compute_effective_progs(struct cgroup *cgrp,
 				   enum bpf_attach_type type,
-				   struct bpf_prog_array __rcu **array)
+				   struct bpf_prog_array **array)
 {
 	enum bpf_cgroup_storage_type stype;
 	struct bpf_prog_array *progs;
@@ -136,17 +172,16 @@ static int compute_effective_progs(struct cgroup *cgrp,
 		}
 	} while ((p = cgroup_parent(p)));
 
-	rcu_assign_pointer(*array, progs);
+	*array = progs;
 	return 0;
 }
 
 static void activate_effective_progs(struct cgroup *cgrp,
 				     enum bpf_attach_type type,
-				     struct bpf_prog_array __rcu *array)
+				     struct bpf_prog_array *old_array)
 {
-	struct bpf_prog_array __rcu *old_array;
-
-	old_array = xchg(&cgrp->bpf.effective[type], array);
+	rcu_swap_protected(cgrp->bpf.effective[type], old_array,
+			   lockdep_is_held(&cgroup_mutex));
 	/* free prog array after grace period, since __cgroup_bpf_run_*()
 	 * might be still walking the array
 	 */
@@ -163,8 +198,13 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
  * that array below is variable length
  */
 #define	NR ARRAY_SIZE(cgrp->bpf.effective)
-	struct bpf_prog_array __rcu *arrays[NR] = {};
-	int i;
+	struct bpf_prog_array *arrays[NR] = {};
+	int ret, i;
+
+	ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0,
+			      GFP_KERNEL);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < NR; i++)
 		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
@@ -180,6 +220,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
 cleanup:
 	for (i = 0; i < NR; i++)
 		bpf_prog_array_free(arrays[i]);
+
+	percpu_ref_exit(&cgrp->bpf.refcnt);
+
 	return -ENOMEM;
 }
 
@@ -193,6 +236,9 @@ static int update_effective_progs(struct cgroup *cgrp,
 	css_for_each_descendant_pre(css, &cgrp->self) {
 		struct cgroup *desc = container_of(css, struct cgroup, self);
 
+		if (percpu_ref_is_zero(&desc->bpf.refcnt))
+			continue;
+
 		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
 		if (err)
 			goto cleanup;
@@ -202,6 +248,14 @@ static int update_effective_progs(struct cgroup *cgrp,
 	css_for_each_descendant_pre(css, &cgrp->self) {
 		struct cgroup *desc = container_of(css, struct cgroup, self);
 
+		if (percpu_ref_is_zero(&desc->bpf.refcnt)) {
+			if (unlikely(desc->bpf.inactive)) {
+				bpf_prog_array_free(desc->bpf.inactive);
+				desc->bpf.inactive = NULL;
+			}
+			continue;
+		}
+
 		activate_effective_progs(desc, type, desc->bpf.inactive);
 		desc->bpf.inactive = NULL;
 	}
@@ -441,10 +495,14 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	enum bpf_attach_type type = attr->query.attach_type;
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	u32 flags = cgrp->bpf.flags[type];
+	struct bpf_prog_array *effective;
 	int cnt, ret = 0, i;
 
+	effective = rcu_dereference_protected(cgrp->bpf.effective[type],
+					      lockdep_is_held(&cgroup_mutex));
+
 	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE)
-		cnt = bpf_prog_array_length(cgrp->bpf.effective[type]);
+		cnt = bpf_prog_array_length(effective);
 	else
 		cnt = prog_list_length(progs);
 
@@ -461,8 +519,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	}
 
 	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
-		return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type],
-						   prog_ids, cnt);
+		return bpf_prog_array_copy_to_user(effective, prog_ids, cnt);
 	} else {
 		struct bpf_prog_list *pl;
 		u32 id;
@@ -545,8 +602,16 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
  * The program type passed in via @type must be suitable for network
  * filtering. No further check is performed to assert that.
  *
- * This function will return %-EPERM if any if an attached program was found
- * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ * For egress packets, this function can return:
+ *   NET_XMIT_SUCCESS    (0)	- continue with packet output
+ *   NET_XMIT_DROP       (1)	- drop packet and notify TCP to call cwr
+ *   NET_XMIT_CN         (2)	- continue with packet output and notify TCP
+ *				  to call cwr
+ *   -EPERM			- drop packet
+ *
+ * For ingress packets, this function will return -EPERM if any
+ * attached program was found and if it returned != 1 during execution.
+ * Otherwise 0 is returned.
  */
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
@@ -572,12 +637,19 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	/* compute pointers for the bpf prog */
 	bpf_compute_and_save_data_end(skb, &saved_data_end);
 
-	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
-				 __bpf_prog_run_save_cb);
+	if (type == BPF_CGROUP_INET_EGRESS) {
+		ret = BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(
+			cgrp->bpf.effective[type], skb, __bpf_prog_run_save_cb);
+	} else {
+		ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
+					  __bpf_prog_run_save_cb);
+		ret = (ret == 1 ? 0 : -EPERM);
+	}
 	bpf_restore_data_end(skb, saved_data_end);
 	__skb_pull(skb, offset);
 	skb->sk = save_sk;
-	return ret == 1 ? 0 : -EPERM;
+
+	return ret;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
 
@@ -867,6 +939,190 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
 
+#ifdef CONFIG_NET
+static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
+					     enum bpf_attach_type attach_type)
+{
+	struct bpf_prog_array *prog_array;
+	bool empty;
+
+	rcu_read_lock();
+	prog_array = rcu_dereference(cgrp->bpf.effective[attach_type]);
+	empty = bpf_prog_array_is_empty(prog_array);
+	rcu_read_unlock();
+
+	return empty;
+}
+
+static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
+{
+	if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0)
+		return -EINVAL;
+
+	ctx->optval = kzalloc(max_optlen, GFP_USER);
+	if (!ctx->optval)
+		return -ENOMEM;
+
+	ctx->optval_end = ctx->optval + max_optlen;
+	ctx->optlen = max_optlen;
+
+	return 0;
+}
+
+static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
+{
+	kfree(ctx->optval);
+}
+
+int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
+				       int *optname, char __user *optval,
+				       int *optlen, char **kernel_optval)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_kern ctx = {
+		.sk = sk,
+		.level = *level,
+		.optname = *optname,
+	};
+	int ret;
+
+	/* Opportunistic check to see whether we have any BPF program
+	 * attached to the hook so we don't waste time allocating
+	 * memory and locking the socket.
+	 */
+	if (!cgroup_bpf_enabled ||
+	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
+		return 0;
+
+	ret = sockopt_alloc_buf(&ctx, *optlen);
+	if (ret)
+		return ret;
+
+	if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	lock_sock(sk);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT],
+				 &ctx, BPF_PROG_RUN);
+	release_sock(sk);
+
+	if (!ret) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	if (ctx.optlen == -1) {
+		/* optlen set to -1, bypass kernel */
+		ret = 1;
+	} else if (ctx.optlen > *optlen || ctx.optlen < -1) {
+		/* optlen is out of bounds */
+		ret = -EFAULT;
+	} else {
+		/* optlen within bounds, run kernel handler */
+		ret = 0;
+
+		/* export any potential modifications */
+		*level = ctx.level;
+		*optname = ctx.optname;
+		*optlen = ctx.optlen;
+		*kernel_optval = ctx.optval;
+	}
+
+out:
+	if (ret)
+		sockopt_free_buf(&ctx);
+	return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_setsockopt);
+
+int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
+				       int optname, char __user *optval,
+				       int __user *optlen, int max_optlen,
+				       int retval)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_kern ctx = {
+		.sk = sk,
+		.level = level,
+		.optname = optname,
+		.retval = retval,
+	};
+	int ret;
+
+	/* Opportunistic check to see whether we have any BPF program
+	 * attached to the hook so we don't waste time allocating
+	 * memory and locking the socket.
+	 */
+	if (!cgroup_bpf_enabled ||
+	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
+		return retval;
+
+	ret = sockopt_alloc_buf(&ctx, max_optlen);
+	if (ret)
+		return ret;
+
+	if (!retval) {
+		/* If kernel getsockopt finished successfully,
+		 * copy whatever was returned to the user back
+		 * into our temporary buffer. Set optlen to the
+		 * one that kernel returned as well to let
+		 * BPF programs inspect the value.
+		 */
+
+		if (get_user(ctx.optlen, optlen)) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		if (ctx.optlen > max_optlen)
+			ctx.optlen = max_optlen;
+
+		if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
+			ret = -EFAULT;
+			goto out;
+		}
+	}
+
+	lock_sock(sk);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT],
+				 &ctx, BPF_PROG_RUN);
+	release_sock(sk);
+
+	if (!ret) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	if (ctx.optlen > max_optlen) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	/* BPF programs only allowed to set retval to 0, not some
+	 * arbitrary value.
+	 */
+	if (ctx.retval != 0 && ctx.retval != retval) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
+	    put_user(ctx.optlen, optlen)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = ctx.retval;
+
+out:
+	sockopt_free_buf(&ctx);
+	return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
+#endif
+
 static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
 			      size_t *lenp)
 {
@@ -1127,3 +1383,155 @@ const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
 
 const struct bpf_prog_ops cg_sysctl_prog_ops = {
 };
+
+static const struct bpf_func_proto *
+cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+#ifdef CONFIG_NET
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
+#endif
+#ifdef CONFIG_INET
+	case BPF_FUNC_tcp_sock:
+		return &bpf_tcp_sock_proto;
+#endif
+	default:
+		return cgroup_base_func_proto(func_id, prog);
+	}
+}
+
+static bool cg_sockopt_is_valid_access(int off, int size,
+				       enum bpf_access_type type,
+				       const struct bpf_prog *prog,
+				       struct bpf_insn_access_aux *info)
+{
+	const int size_default = sizeof(__u32);
+
+	if (off < 0 || off >= sizeof(struct bpf_sockopt))
+		return false;
+
+	if (off % size != 0)
+		return false;
+
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case offsetof(struct bpf_sockopt, retval):
+			if (size != size_default)
+				return false;
+			return prog->expected_attach_type ==
+				BPF_CGROUP_GETSOCKOPT;
+		case offsetof(struct bpf_sockopt, optname):
+			/* fallthrough */
+		case offsetof(struct bpf_sockopt, level):
+			if (size != size_default)
+				return false;
+			return prog->expected_attach_type ==
+				BPF_CGROUP_SETSOCKOPT;
+		case offsetof(struct bpf_sockopt, optlen):
+			return size == size_default;
+		default:
+			return false;
+		}
+	}
+
+	switch (off) {
+	case offsetof(struct bpf_sockopt, sk):
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_SOCKET;
+		break;
+	case offsetof(struct bpf_sockopt, optval):
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_PACKET;
+		break;
+	case offsetof(struct bpf_sockopt, optval_end):
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_PACKET_END;
+		break;
+	case offsetof(struct bpf_sockopt, retval):
+		if (size != size_default)
+			return false;
+		return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT;
+	default:
+		if (size != size_default)
+			return false;
+		break;
+	}
+	return true;
+}
+
+#define CG_SOCKOPT_ACCESS_FIELD(T, F)					\
+	T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F),			\
+	  si->dst_reg, si->src_reg,					\
+	  offsetof(struct bpf_sockopt_kern, F))
+
+static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type,
+					 const struct bpf_insn *si,
+					 struct bpf_insn *insn_buf,
+					 struct bpf_prog *prog,
+					 u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct bpf_sockopt, sk):
+		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk);
+		break;
+	case offsetof(struct bpf_sockopt, level):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level);
+		break;
+	case offsetof(struct bpf_sockopt, optname):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname);
+		break;
+	case offsetof(struct bpf_sockopt, optlen):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen);
+		break;
+	case offsetof(struct bpf_sockopt, retval):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval);
+		break;
+	case offsetof(struct bpf_sockopt, optval):
+		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval);
+		break;
+	case offsetof(struct bpf_sockopt, optval_end):
+		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end);
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf,
+				   bool direct_write,
+				   const struct bpf_prog *prog)
+{
+	/* Nothing to do for sockopt argument. The data is kzalloc'ated.
+	 */
+	return 0;
+}
+
+const struct bpf_verifier_ops cg_sockopt_verifier_ops = {
+	.get_func_proto		= cg_sockopt_func_proto,
+	.is_valid_access	= cg_sockopt_is_valid_access,
+	.convert_ctx_access	= cg_sockopt_convert_ctx_access,
+	.gen_prologue		= cg_sockopt_get_prologue,
+};
+
+const struct bpf_prog_ops cg_sockopt_prog_ops = {
+};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 080e2bb644cc..16079550db6d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1364,10 +1364,10 @@ select_insn:
 		insn++;
 		CONT;
 	ALU_ARSH_X:
-		DST = (u64) (u32) ((*(s32 *) &DST) >> SRC);
+		DST = (u64) (u32) (((s32) DST) >> SRC);
 		CONT;
 	ALU_ARSH_K:
-		DST = (u64) (u32) ((*(s32 *) &DST) >> IMM);
+		DST = (u64) (u32) (((s32) DST) >> IMM);
 		CONT;
 	ALU64_ARSH_X:
 		(*(s64 *) &DST) >>= SRC;
@@ -1791,38 +1791,42 @@ struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
 	return &empty_prog_array.hdr;
 }
 
-void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+void bpf_prog_array_free(struct bpf_prog_array *progs)
 {
-	if (!progs ||
-	    progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+	if (!progs || progs == &empty_prog_array.hdr)
 		return;
 	kfree_rcu(progs, rcu);
 }
 
-int bpf_prog_array_length(struct bpf_prog_array __rcu *array)
+int bpf_prog_array_length(struct bpf_prog_array *array)
 {
 	struct bpf_prog_array_item *item;
 	u32 cnt = 0;
 
-	rcu_read_lock();
-	item = rcu_dereference(array)->items;
-	for (; item->prog; item++)
+	for (item = array->items; item->prog; item++)
 		if (item->prog != &dummy_bpf_prog.prog)
 			cnt++;
-	rcu_read_unlock();
 	return cnt;
 }
 
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array)
+{
+	struct bpf_prog_array_item *item;
+
+	for (item = array->items; item->prog; item++)
+		if (item->prog != &dummy_bpf_prog.prog)
+			return false;
+	return true;
+}
 
-static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
+static bool bpf_prog_array_copy_core(struct bpf_prog_array *array,
 				     u32 *prog_ids,
 				     u32 request_cnt)
 {
 	struct bpf_prog_array_item *item;
 	int i = 0;
 
-	item = rcu_dereference_check(array, 1)->items;
-	for (; item->prog; item++) {
+	for (item = array->items; item->prog; item++) {
 		if (item->prog == &dummy_bpf_prog.prog)
 			continue;
 		prog_ids[i] = item->prog->aux->id;
@@ -1835,7 +1839,7 @@ static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
 	return !!(item->prog);
 }
 
-int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
+int bpf_prog_array_copy_to_user(struct bpf_prog_array *array,
 				__u32 __user *prog_ids, u32 cnt)
 {
 	unsigned long err = 0;
@@ -1846,18 +1850,12 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
 	 * cnt = bpf_prog_array_length();
 	 * if (cnt > 0)
 	 *     bpf_prog_array_copy_to_user(..., cnt);
-	 * so below kcalloc doesn't need extra cnt > 0 check, but
-	 * bpf_prog_array_length() releases rcu lock and
-	 * prog array could have been swapped with empty or larger array,
-	 * so always copy 'cnt' prog_ids to the user.
-	 * In a rare race the user will see zero prog_ids
+	 * so below kcalloc doesn't need extra cnt > 0 check.
 	 */
 	ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
 	if (!ids)
 		return -ENOMEM;
-	rcu_read_lock();
 	nospc = bpf_prog_array_copy_core(array, ids, cnt);
-	rcu_read_unlock();
 	err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
 	kfree(ids);
 	if (err)
@@ -1867,19 +1865,19 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
 	return 0;
 }
 
-void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array,
+void bpf_prog_array_delete_safe(struct bpf_prog_array *array,
 				struct bpf_prog *old_prog)
 {
-	struct bpf_prog_array_item *item = array->items;
+	struct bpf_prog_array_item *item;
 
-	for (; item->prog; item++)
+	for (item = array->items; item->prog; item++)
 		if (item->prog == old_prog) {
 			WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
 			break;
 		}
 }
 
-int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
 			struct bpf_prog_array **new_array)
@@ -1943,7 +1941,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 	return 0;
 }
 
-int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 			     u32 *prog_ids, u32 request_cnt,
 			     u32 *prog_cnt)
 {
@@ -2086,6 +2084,15 @@ bool __weak bpf_helper_changes_pkt_data(void *func)
 	return false;
 }
 
+/* Return TRUE if the JIT backend wants verifier to enable sub-register usage
+ * analysis code and wants explicit zero extension inserted by verifier.
+ * Otherwise, return FALSE.
+ */
+bool __weak bpf_jit_needs_zext(void)
+{
+	return false;
+}
+
 /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
  * skb_copy_bits(), so provide a weak definition of it for NET-less config.
  */
@@ -2103,3 +2110,4 @@ EXPORT_SYMBOL(bpf_stats_enabled_key);
 #include <linux/bpf_trace.h>
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
+EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8ebd0fa826f8..ef49e17ae47c 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -32,14 +32,19 @@
 
 /* General idea: XDP packets getting XDP redirected to another CPU,
  * will maximum be stored/queued for one driver ->poll() call.  It is
- * guaranteed that setting flush bit and flush operation happen on
+ * guaranteed that queueing the frame and the flush operation happen on
  * same CPU.  Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
  * which queue in bpf_cpu_map_entry contains packets.
  */
 
 #define CPU_MAP_BULK_SIZE 8  /* 8 == one cacheline on 64-bit archs */
+struct bpf_cpu_map_entry;
+struct bpf_cpu_map;
+
 struct xdp_bulk_queue {
 	void *q[CPU_MAP_BULK_SIZE];
+	struct list_head flush_node;
+	struct bpf_cpu_map_entry *obj;
 	unsigned int count;
 };
 
@@ -52,6 +57,8 @@ struct bpf_cpu_map_entry {
 	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
 	struct xdp_bulk_queue __percpu *bulkq;
 
+	struct bpf_cpu_map *cmap;
+
 	/* Queue with potential multi-producers, and single-consumer kthread */
 	struct ptr_ring *queue;
 	struct task_struct *kthread;
@@ -65,23 +72,17 @@ struct bpf_cpu_map {
 	struct bpf_map map;
 	/* Below members specific for map type */
 	struct bpf_cpu_map_entry **cpu_map;
-	unsigned long __percpu *flush_needed;
+	struct list_head __percpu *flush_list;
 };
 
-static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
-			     struct xdp_bulk_queue *bq, bool in_napi_ctx);
-
-static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
-{
-	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
-}
+static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx);
 
 static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_cpu_map *cmap;
 	int err = -ENOMEM;
+	int ret, cpu;
 	u64 cost;
-	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -105,23 +106,21 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 
 	/* make sure page count doesn't overflow */
 	cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
-	cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
-	if (cost >= U32_MAX - PAGE_SIZE)
-		goto free_cmap;
-	cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+	cost += sizeof(struct list_head) * num_possible_cpus();
 
 	/* Notice returns -EPERM on if map size is larger than memlock limit */
-	ret = bpf_map_precharge_memlock(cmap->map.pages