Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-09-05

The following pull-request contains BPF updates for your *net-next* tree.

We've added 106 non-merge commits during the last 18 day(s) which contain
a total of 159 files changed, 5225 insertions(+), 1358 deletions(-).

There are two small merge conflicts, resolve them as follows:

1) tools/testing/selftests/bpf/DENYLIST.s390x

  Commit 27e23836ce22 ("selftests/bpf: Add lru_bug to s390x deny list") in
  bpf tree was needed to get BPF CI green on s390x, but it conflicted with
  newly added tests on bpf-next. Resolve by adding both hunks, result:

  [...]
  lru_bug                                  # prog 'printk': failed to auto-attach: -524
  setget_sockopt                           # attach unexpected error: -524                                               (trampoline)
  cb_refs                                  # expected error message unexpected error: -524                               (trampoline)
  cgroup_hierarchical_stats                # JIT does not support calling kernel function                                (kfunc)
  htab_update                              # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
  [...]

2) net/core/filter.c

  Commit 1227c1771dd2 ("net: Fix data-races around sysctl_[rw]mem_(max|default).")
  from net tree conflicts with commit 29003875bd5b ("bpf: Change bpf_setsockopt(SOL_SOCKET)
  to reuse sk_setsockopt()") from bpf-next tree. Take the code as it is from
  bpf-next tree, result:

  [...]
	if (getopt) {
		if (optname == SO_BINDTODEVICE)
			return -EINVAL;
		return sk_getsockopt(sk, SOL_SOCKET, optname,
				     KERNEL_SOCKPTR(optval),
				     KERNEL_SOCKPTR(optlen));
	}

	return sk_setsockopt(sk, SOL_SOCKET, optname,
			     KERNEL_SOCKPTR(optval), *optlen);
  [...]

The main changes are:

1) Add any-context BPF specific memory allocator which is useful in particular for BPF
   tracing with bonus of performance equal to full prealloc, from Alexei Starovoitov.

2) Big batch to remove duplicated code from bpf_{get,set}sockopt() helpers as an effort
   to reuse the existing core socket code as much as possible, from Martin KaFai Lau.

3) Extend BPF flow dissector for BPF programs to just augment the in-kernel dissector
   with custom logic. In other words, allow for partial replacement, from Shmulik Ladkani.

4) Add a new cgroup iterator to BPF with different traversal options, from Hao Luo.

5) Support for BPF to collect hierarchical cgroup statistics efficiently through BPF
   integration with the rstat framework, from Yosry Ahmed.

6) Support bpf_{g,s}et_retval() under more BPF cgroup hooks, from Stanislav Fomichev.

7) BPF hash table and local storages fixes under fully preemptible kernel, from Hou Tao.

8) Add various improvements to BPF selftests and libbpf for compilation with gcc BPF
   backend, from James Hilliard.

9) Fix verifier helper permissions and reference state management for synchronous
   callbacks, from Kumar Kartikeya Dwivedi.

10) Add support for BPF selftest's xskxceiver to also be used against real devices that
    support MAC loopback, from Maciej Fijalkowski.

11) Various fixes to the bpf-helpers(7) man page generation script, from Quentin Monnet.

12) Document BPF verifier's tnum_in(tnum_range(), ...) gotchas, from Shung-Hsi Yu.

13) Various minor misc improvements all over the place.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (106 commits)
  bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc.
  bpf: Remove usage of kmem_cache from bpf_mem_cache.
  bpf: Remove prealloc-only restriction for sleepable bpf programs.
  bpf: Prepare bpf_mem_alloc to be used by sleepable bpf programs.
  bpf: Remove tracing program restriction on map types
  bpf: Convert percpu hash map to per-cpu bpf_mem_alloc.
  bpf: Add percpu allocation support to bpf_mem_alloc.
  bpf: Batch call_rcu callbacks instead of SLAB_TYPESAFE_BY_RCU.
  bpf: Adjust low/high watermarks in bpf_mem_cache
  bpf: Optimize call_rcu in non-preallocated hash map.
  bpf: Optimize element count in non-preallocated hash map.
  bpf: Relax the requirement to use preallocated hash maps in tracing progs.
  samples/bpf: Reduce syscall overhead in map_perf_test.
  selftests/bpf: Improve test coverage of test_maps
  bpf: Convert hash map to bpf_mem_alloc.
  bpf: Introduce any context BPF specific memory allocator.
  selftest/bpf: Add test for bpf_getsockopt()
  bpf: Change bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt()
  bpf: Change bpf_getsockopt(SOL_IP) to reuse do_ip_getsockopt()
  bpf: Change bpf_getsockopt(SOL_TCP) to reuse do_tcp_getsockopt()
  ...
====================

Link: https://lore.kernel.org/r/20220905161136.9150-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

13 files changed, 1258 insertions, 193 deletions

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 057ba8e01e70..341c94f208f4 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
 obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
-obj-$(CONFIG_BPF_SYSCALL) += btf.o
+obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o
 obj-$(CONFIG_BPF_JIT) += dispatcher.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
@@ -24,6 +24,9 @@ endif
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif
+ifeq ($(CONFIG_CGROUPS),y)
+obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o
+endif
 obj-$(CONFIG_CGROUP_BPF) += cgroup.o
 ifeq ($(CONFIG_INET),y)
 obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 97bb57493ed5..5dc307bdeaeb 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -694,19 +694,24 @@ struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop)
 
 int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
 {
+	struct bpf_run_ctx run_ctx, *old_run_ctx;
 	int ret;
 
 	if (prog->aux->sleepable) {
 		rcu_read_lock_trace();
 		migrate_disable();
 		might_fault();
+		old_run_ctx = bpf_set_run_ctx(&run_ctx);
 		ret = bpf_prog_run(prog, ctx);
+		bpf_reset_run_ctx(old_run_ctx);
 		migrate_enable();
 		rcu_read_unlock_trace();
 	} else {
 		rcu_read_lock();
 		migrate_disable();
+		old_run_ctx = bpf_set_run_ctx(&run_ctx);
 		ret = bpf_prog_run(prog, ctx);
+		bpf_reset_run_ctx(old_run_ctx);
 		migrate_enable();
 		rcu_read_unlock();
 	}
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 4ee2e7286c23..802fc15b0d73 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -555,11 +555,11 @@ void bpf_local_storage_map_free(struct bpf_local_storage_map *smap,
 				struct bpf_local_storage_elem, map_node))) {
 			if (busy_counter) {
 				migrate_disable();
-				__this_cpu_inc(*busy_counter);
+				this_cpu_inc(*busy_counter);
 			}
 			bpf_selem_unlink(selem, false);
 			if (busy_counter) {
-				__this_cpu_dec(*busy_counter);
+				this_cpu_dec(*busy_counter);
 				migrate_enable();
 			}
 			cond_resched_rcu();
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index fa71d58b7ded..4fd845bc5a12 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -41,17 +41,21 @@ BTF_SET_END(bpf_lsm_hooks)
  */
 BTF_SET_START(bpf_lsm_current_hooks)
 /* operate on freshly allocated sk without any cgroup association */
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_sk_alloc_security)
 BTF_ID(func, bpf_lsm_sk_free_security)
+#endif
 BTF_SET_END(bpf_lsm_current_hooks)
 
 /* List of LSM hooks that trigger while the socket is properly locked.
  */
 BTF_SET_START(bpf_lsm_locked_sockopt_hooks)
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_socket_sock_rcv_skb)
 BTF_ID(func, bpf_lsm_sock_graft)
 BTF_ID(func, bpf_lsm_inet_csk_clone)
 BTF_ID(func, bpf_lsm_inet_conn_established)
+#endif
 BTF_SET_END(bpf_lsm_locked_sockopt_hooks)
 
 /* List of LSM hooks that trigger while the socket is _not_ locked,
@@ -59,8 +63,10 @@ BTF_SET_END(bpf_lsm_locked_sockopt_hooks)
  * in the early init phase.
  */
 BTF_SET_START(bpf_lsm_unlocked_sockopt_hooks)
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_socket_post_create)
 BTF_ID(func, bpf_lsm_socket_socketpair)
+#endif
 BTF_SET_END(bpf_lsm_unlocked_sockopt_hooks)
 
 #ifdef CONFIG_CGROUP_BPF
@@ -189,6 +195,14 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto = {
 static const struct bpf_func_proto *
 bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	if (prog->expected_attach_type == BPF_LSM_CGROUP) {
+		func_proto = cgroup_common_func_proto(func_id, prog);
+		if (func_proto)
+			return func_proto;
+	}
+
 	switch (func_id) {
 	case BPF_FUNC_inode_storage_get:
 		return &bpf_inode_storage_get_proto;
@@ -212,15 +226,6 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL;
 	case BPF_FUNC_get_attach_cookie:
 		return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL;
-	case BPF_FUNC_get_local_storage:
-		return prog->expected_attach_type == BPF_LSM_CGROUP ?
-			&bpf_get_local_storage_proto : NULL;
-	case BPF_FUNC_set_retval:
-		return prog->expected_attach_type == BPF_LSM_CGROUP ?
-			&bpf_set_retval_proto : NULL;
-	case BPF_FUNC_get_retval:
-		return prog->expected_attach_type == BPF_LSM_CGROUP ?
-			&bpf_get_retval_proto : NULL;
 #ifdef CONFIG_NET
 	case BPF_FUNC_setsockopt:
 		if (prog->expected_attach_type != BPF_LSM_CGROUP)
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index e9014dc62682..6f290623347e 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -26,20 +26,20 @@ static DEFINE_PER_CPU(int, bpf_task_storage_busy);
 static void bpf_task_storage_lock(void)
 {
 	migrate_disable();
-	__this_cpu_inc(bpf_task_storage_busy);
+	this_cpu_inc(bpf_task_storage_busy);
 }
 
 static void bpf_task_storage_unlock(void)
 {
-	__this_cpu_dec(bpf_task_storage_busy);
+	this_cpu_dec(bpf_task_storage_busy);
 	migrate_enable();
 }
 
 static bool bpf_task_storage_trylock(void)
 {
 	migrate_disable();
-	if (unlikely(__this_cpu_inc_return(bpf_task_storage_busy) != 1)) {
-		__this_cpu_dec(bpf_task_storage_busy);
+	if (unlikely(this_cpu_inc_return(bpf_task_storage_busy) != 1)) {
+		this_cpu_dec(bpf_task_storage_busy);
 		migrate_enable();
 		return false;
 	}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 4a400cd63731..00c7f864900e 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1529,6 +1529,37 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 	return ret;
 }
 
+BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
+{
+	/* flags argument is not used now,
+	 * but provides an ability to extend the API.
+	 * verifier checks that its value is correct.
+	 */
+	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
+	struct bpf_cgroup_storage *storage;
+	struct bpf_cg_run_ctx *ctx;
+	void *ptr;
+
+	/* get current cgroup storage from BPF run context */
+	ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+	storage = ctx->prog_item->cgroup_storage[stype];
+
+	if (stype == BPF_CGROUP_STORAGE_SHARED)
+		ptr = &READ_ONCE(storage->buf)->data[0];
+	else
+		ptr = this_cpu_ptr(storage->percpu_buf);
+
+	return (unsigned long)ptr;
+}
+
+const struct bpf_func_proto bpf_get_local_storage_proto = {
+	.func		= bpf_get_local_storage,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_0(bpf_get_retval)
 {
 	struct bpf_cg_run_ctx *ctx =
@@ -1560,32 +1591,26 @@ const struct bpf_func_proto bpf_set_retval_proto = {
 };
 
 static const struct bpf_func_proto *
-cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
-	case BPF_FUNC_get_current_uid_gid:
-		return &bpf_get_current_uid_gid_proto;
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
-	case BPF_FUNC_get_current_cgroup_id:
-		return &bpf_get_current_cgroup_id_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
-	case BPF_FUNC_get_retval:
-		return &bpf_get_retval_proto;
-	case BPF_FUNC_set_retval:
-		return &bpf_set_retval_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
 }
 
-static const struct bpf_func_proto *
-cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
-{
-	return cgroup_base_func_proto(func_id, prog);
-}
-
 static bool cgroup_dev_is_valid_access(int off, int size,
 				       enum bpf_access_type type,
 				       const struct bpf_prog *prog,
@@ -2098,11 +2123,17 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
-	case BPF_FUNC_strtol:
-		return &bpf_strtol_proto;
-	case BPF_FUNC_strtoul:
-		return &bpf_strtoul_proto;
 	case BPF_FUNC_sysctl_get_name:
 		return &bpf_sysctl_get_name_proto;
 	case BPF_FUNC_sysctl_get_current_value:
@@ -2113,8 +2144,10 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sysctl_set_new_value_proto;
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
 	default:
-		return cgroup_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -2235,6 +2268,16 @@ static const struct bpf_func_proto bpf_get_netns_cookie_sockopt_proto = {
 static const struct bpf_func_proto *
 cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+	const struct bpf_func_proto *func_proto;
+
+	func_proto = cgroup_common_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
+	func_proto = cgroup_current_func_proto(func_id, prog);
+	if (func_proto)
+		return func_proto;
+
 	switch (func_id) {
 #ifdef CONFIG_NET
 	case BPF_FUNC_get_netns_cookie:
@@ -2256,8 +2299,10 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
 #endif
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
 	default:
-		return cgroup_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -2422,3 +2467,69 @@ const struct bpf_verifier_ops cg_sockopt_verifier_ops = {
 
 const struct bpf_prog_ops cg_sockopt_prog_ops = {
 };
+
+/* Common helpers for cgroup hooks. */
+const struct bpf_func_proto *
+cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_get_retval:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET_INGRESS:
+		case BPF_CGROUP_INET_EGRESS:
+		case BPF_CGROUP_SOCK_OPS:
+		case BPF_CGROUP_UDP4_RECVMSG:
+		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
+			return NULL;
+		default:
+			return &bpf_get_retval_proto;
+		}
+	case BPF_FUNC_set_retval:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET_INGRESS:
+		case BPF_CGROUP_INET_EGRESS:
+		case BPF_CGROUP_SOCK_OPS:
+		case BPF_CGROUP_UDP4_RECVMSG:
+		case BPF_CGROUP_UDP6_RECVMSG:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
+			return NULL;
+		default:
+			return &bpf_set_retval_proto;
+		}
+	default:
+		return NULL;
+	}
+}
+
+/* Common helpers for cgroup hooks with valid process context. */
+const struct bpf_func_proto *
+cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_get_current_comm:
+		return &bpf_get_current_comm_proto;
+	case BPF_FUNC_get_current_cgroup_id:
+		return &bpf_get_current_cgroup_id_proto;
+	case BPF_FUNC_get_current_ancestor_cgroup_id:
+		return &bpf_get_current_ancestor_cgroup_id_proto;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_curr_proto;
+#endif
+	default:
+		return NULL;
+	}
+}
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
new file mode 100644
index 000000000000..0d200a993489
--- /dev/null
+++ b/kernel/bpf/cgroup_iter.c
@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2022 Google */
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <linux/cgroup.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+
+#include "../cgroup/cgroup-internal.h"  /* cgroup_mutex and cgroup_is_dead */
+
+/* cgroup_iter provides four modes of traversal to the cgroup hierarchy.
+ *
+ *  1. Walk the descendants of a cgroup in pre-order.
+ *  2. Walk the descendants of a cgroup in post-order.
+ *  3. Walk the ancestors of a cgroup.
+ *  4. Show the given cgroup only.
+ *
+ * For walking descendants, cgroup_iter can walk in either pre-order or
+ * post-order. For walking ancestors, the iter walks up from a cgroup to
+ * the root.
+ *
+ * The iter program can terminate the walk early by returning 1. Walk
+ * continues if prog returns 0.
+ *
+ * The prog can check (seq->num == 0) to determine whether this is
+ * the first element. The prog may also be passed a NULL cgroup,
+ * which means the walk has completed and the prog has a chance to
+ * do post-processing, such as outputting an epilogue.
+ *
+ * Note: the iter_prog is called with cgroup_mutex held.
+ *
+ * Currently only one session is supported, which means, depending on the
+ * volume of data bpf program intends to send to user space, the number
+ * of cgroups that can be walked is limited. For example, given the current
+ * buffer size is 8 * PAGE_SIZE, if the program sends 64B data for each
+ * cgroup, assuming PAGE_SIZE is 4kb, the total number of cgroups that can
+ * be walked is 512. This is a limitation of cgroup_iter. If the output data
+ * is larger than the kernel buffer size, after all data in the kernel buffer
+ * is consumed by user space, the subsequent read() syscall will signal
+ * EOPNOTSUPP. In order to work around, the user may have to update their
+ * program to reduce the volume of data sent to output. For example, skip
+ * some uninteresting cgroups.
+ */
+
+struct bpf_iter__cgroup {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct cgroup *, cgroup);
+};
+
+struct cgroup_iter_priv {
+	struct cgroup_subsys_state *start_css;
+	bool visited_all;
+	bool terminate;
+	int order;
+};
+
+static void *cgroup_iter_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct cgroup_iter_priv *p = seq->private;
+
+	mutex_lock(&cgroup_mutex);
+
+	/* cgroup_iter doesn't support read across multiple sessions. */
+	if (*pos > 0) {
+		if (p->visited_all)
+			return NULL;
+
+		/* Haven't visited all, but because cgroup_mutex has dropped,
+		 * return -EOPNOTSUPP to indicate incomplete iteration.
+		 */
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	++*pos;
+	p->terminate = false;
+	p->visited_all = false;
+	if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
+		return css_next_descendant_pre(NULL, p->start_css);
+	else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST)
+		return css_next_descendant_post(NULL, p->start_css);
+	else /* BPF_CGROUP_ITER_SELF_ONLY and BPF_CGROUP_ITER_ANCESTORS_UP */
+		return p->start_css;
+}
+
+static int __cgroup_iter_seq_show(struct seq_file *seq,
+				  struct cgroup_subsys_state *css, int in_stop);
+
+static void cgroup_iter_seq_stop(struct seq_file *seq, void *v)
+{
+	struct cgroup_iter_priv *p = seq->private;
+
+	mutex_unlock(&cgroup_mutex);
+
+	/* pass NULL to the prog for post-processing */
+	if (!v) {
+		__cgroup_iter_seq_show(seq, NULL, true);
+		p->visited_all = true;
+	}
+}
+
+static void *cgroup_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct cgroup_subsys_state *curr = (struct cgroup_subsys_state *)v;
+	struct cgroup_iter_priv *p = seq->private;
+
+	++*pos;
+	if (p->terminate)
+		return NULL;
+
+	if (p->order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
+		return css_next_descendant_pre(curr, p->start_css);
+	else if (p->order == BPF_CGROUP_ITER_DESCENDANTS_POST)
+		return css_next_descendant_post(curr, p->start_css);
+	else if (p->order == BPF_CGROUP_ITER_ANCESTORS_UP)
+		return curr->parent;
+	else  /* BPF_CGROUP_ITER_SELF_ONLY */
+		return NULL;
+}
+
+static int __cgroup_iter_seq_show(struct seq_file *seq,
+				  struct cgroup_subsys_state *css, int in_stop)
+{
+	struct cgroup_iter_priv *p = seq->private;
+	struct bpf_iter__cgroup ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	/* cgroup is dead, skip this element */
+	if (css && cgroup_is_dead(css->cgroup))
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.cgroup = css ? css->cgroup : NULL;
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (prog)
+		ret = bpf_iter_run_prog(prog, &ctx);
+
+	/* if prog returns > 0, terminate after this element. */
+	if (ret != 0)
+		p->terminate = true;
+
+	return 0;
+}
+
+static int cgroup_iter_seq_show(struct seq_file *seq, void *v)
+{
+	return __cgroup_iter_seq_show(seq, (struct cgroup_subsys_state *)v,
+				      false);
+}
+
+static const struct seq_operations cgroup_iter_seq_ops = {
+	.start  = cgroup_iter_seq_start,
+	.next   = cgroup_iter_seq_next,
+	.stop   = cgroup_iter_seq_stop,
+	.show   = cgroup_iter_seq_show,
+};
+
+BTF_ID_LIST_SINGLE(bpf_cgroup_btf_id, struct, cgroup)
+
+static int cgroup_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux)
+{
+	struct cgroup_iter_priv *p = (struct cgroup_iter_priv *)priv;
+	struct cgroup *cgrp = aux->cgroup.start;
+
+	p->start_css = &cgrp->self;
+	p->terminate = false;
+	p->visited_all = false;
+	p->order = aux->cgroup.order;
+	return 0;
+}
+
+static const struct bpf_iter_seq_info cgroup_iter_seq_info = {
+	.seq_ops		= &cgroup_iter_seq_ops,
+	.init_seq_private	= cgroup_iter_seq_init,
+	.seq_priv_size		= sizeof(struct cgroup_iter_priv),
+};
+
+static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
+				  union bpf_iter_link_info *linfo,
+				  struct bpf_iter_aux_info *aux)
+{
+	int fd = linfo->cgroup.cgroup_fd;
+	u64 id = linfo->cgroup.cgroup_id;
+	int order = linfo->cgroup.order;
+	struct cgroup *cgrp;
+
+	if (order != BPF_CGROUP_ITER_DESCENDANTS_PRE &&
+	    order != BPF_CGROUP_ITER_DESCENDANTS_POST &&
+	    order != BPF_CGROUP_ITER_ANCESTORS_UP &&
+	    order != BPF_CGROUP_ITER_SELF_ONLY)
+		return -EINVAL;
+
+	if (fd && id)
+		return -EINVAL;
+
+	if (fd)
+		cgrp = cgroup_get_from_fd(fd);
+	else if (id)
+		cgrp = cgroup_get_from_id(id);
+	else /* walk the entire hierarchy by default. */
+		cgrp = cgroup_get_from_path("/");
+
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	aux->cgroup.start = cgrp;
+	aux->cgroup.order = order;
+	return 0;
+}
+
+static void bpf_iter_detach_cgroup(struct bpf_iter_aux_info *aux)
+{
+	cgroup_put(aux->cgroup.start);
+}
+
+static void bpf_iter_cgroup_show_fdinfo(const struct bpf_iter_aux_info *aux,
+					struct seq_file *seq)
+{
+	char *buf;
+
+	buf = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (!buf) {
+		seq_puts(seq, "cgroup_path:\t<unknown>\n");
+		goto show_order;
+	}
+
+	/* If cgroup_path_ns() fails, buf will be an empty string, cgroup_path
+	 * will print nothing.
+	 *
+	 * Path is in the calling process's cgroup namespace.
+	 */
+	cgroup_path_ns(aux->cgroup.start, buf, PATH_MAX,
+		       current->nsproxy->cgroup_ns);
+	seq_printf(seq, "cgroup_path:\t%s\n", buf);
+	kfree(buf);
+
+show_order:
+	if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_PRE)
+		seq_puts(seq, "order: descendants_pre\n");
+	else if (aux->cgroup.order == BPF_CGROUP_ITER_DESCENDANTS_POST)
+		seq_puts(seq, "order: descendants_post\n");
+	else if (aux->cgroup.order == BPF_CGROUP_ITER_ANCESTORS_UP)
+		seq_puts(seq, "order: ancestors_up\n");
+	else /* BPF_CGROUP_ITER_SELF_ONLY */
+		seq_puts(seq, "order: self_only\n");
+}
+
+static int bpf_iter_cgroup_fill_link_info(const struct bpf_iter_aux_info *aux,
+					  struct bpf_link_info *info)
+{
+	info->iter.cgroup.order = aux->cgroup.order;
+	info->iter.cgroup.cgroup_id = cgroup_id(aux->cgroup.start);
+	return 0;
+}
+
+DEFINE_BPF_ITER_FUNC(cgroup, struct bpf_iter_meta *meta,
+		     struct cgroup *cgroup)
+
+static struct bpf_iter_reg bpf_cgroup_reg_info = {
+	.target			= "cgroup",
+	.feature		= BPF_ITER_RESCHED,
+	.attach_target		= bpf_iter_attach_cgroup,
+	.detach_target		= bpf_iter_detach_cgroup,
+	.show_fdinfo		= bpf_iter_cgroup_show_fdinfo,
+	.fill_link_info		= bpf_iter_cgroup_fill_link_info,
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__cgroup, cgroup),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &cgroup_iter_seq_info,
+};
+
+static int __init bpf_cgroup_iter_init(void)
+{
+	bpf_cgroup_reg_info.ctx_arg_info[0].btf_id = bpf_cgroup_btf_id[0];
+	return bpf_iter_reg_target(&bpf_cgroup_reg_info);
+}
+
+late_initcall(bpf_cgroup_iter_init);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index b301a63afa2f..0fe3f136cbbe 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -14,6 +14,7 @@
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
+#include <linux/bpf_mem_alloc.h>
 
 #define HTAB_CREATE_FLAG_MASK						\
 	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
@@ -92,6 +93,8 @@ struct bucket {
 
 struct bpf_htab {
 	struct bpf_map map;
+	struct bpf_mem_alloc ma;
+	struct bpf_mem_alloc pcpu_ma;
 	struct bucket *buckets;
 	void *elems;
 	union {
@@ -99,7 +102,12 @@ struct bpf_htab {
 		struct bpf_lru lru;
 	};
 	struct htab_elem *__percpu *extra_elems;
-	atomic_t count;	/* number of elements in this hashtable */
+	/* number of elements in non-preallocated hashtable are kept
+	 * in either pcount or count
+	 */
+	struct percpu_counter pcount;
+	atomic_t count;
+	bool use_percpu_counter;
 	u32 n_buckets;	/* number of hash buckets */
 	u32 elem_size;	/* size of each element in bytes */
 	u32 hashrnd;
@@ -114,14 +122,14 @@ struct htab_elem {
 		struct {
 			void *padding;
 			union {
-				struct bpf_htab *htab;
 				struct pcpu_freelist_node fnode;
 				struct htab_elem *batch_flink;
 			};
 		};
 	};
 	union {
-		struct rcu_head rcu;
+		/* pointer to per-cpu pointer */
+		void *ptr_to_pptr;
 		struct bpf_lru_node lru_node;
 	};
 	u32 hash;
@@ -162,17 +170,25 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
 				   unsigned long *pflags)
 {
 	unsigned long flags;
+	bool use_raw_lock;
 
 	hash = hash & HASHTAB_MAP_LOCK_MASK;
 
-	migrate_disable();
+	use_raw_lock = htab_use_raw_lock(htab);
+	if (use_raw_lock)
+		preempt_disable();
+	else
+		migrate_disable();
 	if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
 		__this_cpu_dec(*(htab->map_locked[hash]));
-		migrate_enable();
+		if (use_raw_lock)
+			preempt_enable();
+		else
+			migrate_enable();
 		return -EBUSY;
 	}
 
-	if (htab_use_raw_lock(htab))
+	if (use_raw_lock)
 		raw_spin_lock_irqsave(&b->raw_lock, flags);
 	else
 		spin_lock_irqsave(&b->lock, flags);
@@ -185,13 +201,18 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
 				      struct bucket *b, u32 hash,
 				      unsigned long flags)
 {
+	bool use_raw_lock = htab_use_raw_lock(htab);
+
 	hash = hash & HASHTAB_MAP_LOCK_MASK;
-	if (htab_use_raw_lock(htab))
+	if (use_raw_lock)
 		raw_spin_unlock_irqrestore(&b->raw_lock, flags);
 	else
 		spin_unlock_irqrestore(&b->lock, flags);
 	__this_cpu_dec(*(htab->map_locked[hash]));
-	migrate_enable();
+	if (use_raw_lock)
+		preempt_enable();
+	else
+		migrate_enable();
 }
 
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
@@ -428,8 +449,6 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
 	int numa_node = bpf_map_attr_numa_node(attr);
 
-	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
-		     offsetof(struct htab_elem, hash_node.pprev));
 	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
 		     offsetof(struct htab_elem, hash_node.pprev));
 
@@ -550,6 +569,29 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 
 	htab_init_buckets(htab);
 
+/* compute_batch_value() computes batch value as num_online_cpus() * 2
+ * and __percpu_counter_compare() needs
+ * htab->max_entries - cur_number_of_elems to be more than batch * num_online_cpus()
+ * for percpu_counter to be faster than atomic_t. In practice the average bpf
+ * hash map size is 10k, which means that a system with 64 cpus will fill
+ * hashmap to 20% of 10k before percpu_counter becomes ineffective. Therefore
+ * define our own batch count as 32 then 10k hash map can be filled up to 80%:
+ * 10k - 8k > 32 _batch_ * 64 _cpus_
+ * and __percpu_counter_compare() will still be fast. At that point hash map
+ * collisions will dominate its performance anyway. Assume that hash map filled
+ * to 50+% isn't going to be O(1) and use the following formula to choose
+ * between percpu_counter and atomic_t.
+ */
+#define PERCPU_COUNTER_BATCH 32
+	if (attr->max_entries / 2 > num_online_cpus() * PERCPU_COUNTER_BATCH)
+		htab->use_percpu_counter = true;
+
+	if (htab->use_percpu_counter) {
+		err = percpu_counter_init(&htab->pcount, 0, GFP_KERNEL);
+		if (err)
+			goto free_map_locked;
+	}
+
 	if (prealloc) {
 		err = prealloc_init(htab);
 		if (err)
@@ -563,6 +605,16 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 			if (err)
 				goto free_prealloc;
 		}
+	} else {
+		err = bpf_mem_alloc_init(&htab->ma, htab->elem_size, false);
+		if (err)
+			goto free_map_locked;
+		if (percpu) {
+			err = bpf_mem_alloc_init(&htab->pcpu_ma,
+						 round_up(htab->map.value_size, 8), true);
+			if (err)
+				goto free_map_locked;
+		}
 	}
 
 	return &htab->map;
@@ -573,6 +625,8 @@ free_map_locked:
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
 		free_percpu(htab->map_locked[i]);
 	bpf_map_area_free(htab->buckets);
+	bpf_mem_alloc_destroy(&htab->pcpu_ma);
+	bpf_mem_alloc_destroy(&htab->ma);
 free_htab:
 	lockdep_unregister_key(&htab->lockdep_key);
 	bpf_map_area_free(htab);
@@ -847,17 +901,9 @@ find_first_elem:
 static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
 {
 	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
-		free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
+		bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr);
 	check_and_free_fields(htab, l);
-	kfree(l);
-}
-
-static void htab_elem_free_rcu(struct rcu_head *head)
-{
-	struct htab_elem *l = container_of(head, struct htab_elem, rcu);
-	struct bpf_htab *htab = l->htab;
-