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

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-09-01

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

There are two small conflicts when pulling, resolve as follows:

1) Merge conflict in tools/lib/bpf/libbpf.c between 88a82120282b ("libbpf: Factor
   out common ELF operations and improve logging") in bpf-next and 1e891e513e16
   ("libbpf: Fix map index used in error message") in net-next. Resolve by taking
   the hunk in bpf-next:

        [...]
        scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx);
        data = elf_sec_data(obj, scn);
        if (!scn || !data) {
                pr_warn("elf: failed to get %s map definitions for %s\n",
                        MAPS_ELF_SEC, obj->path);
                return -EINVAL;
        }
        [...]

2) Merge conflict in drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c between
   9647c57b11e5 ("xsk: i40e: ice: ixgbe: mlx5: Test for dma_need_sync earlier for
   better performance") in bpf-next and e20f0dbf204f ("net/mlx5e: RX, Add a prefetch
   command for small L1_CACHE_BYTES") in net-next. Resolve the two locations by retaining
   net_prefetch() and taking xsk_buff_dma_sync_for_cpu() from bpf-next. Should look like:

        [...]
        xdp_set_data_meta_invalid(xdp);
        xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool);
        net_prefetch(xdp->data);
        [...]

We've added 133 non-merge commits during the last 14 day(s) which contain
a total of 246 files changed, 13832 insertions(+), 3105 deletions(-).

The main changes are:

1) Initial support for sleepable BPF programs along with bpf_copy_from_user() helper
   for tracing to reliably access user memory, from Alexei Starovoitov.

2) Add BPF infra for writing and parsing TCP header options, from Martin KaFai Lau.

3) bpf_d_path() helper for returning full path for given 'struct path', from Jiri Olsa.

4) AF_XDP support for shared umems between devices and queues, from Magnus Karlsson.

5) Initial prep work for full BPF-to-BPF call support in libbpf, from Andrii Nakryiko.

6) Generalize bpf_sk_storage map & add local storage for inodes, from KP Singh.

7) Implement sockmap/hash updates from BPF context, from Lorenz Bauer.

8) BPF xor verification for scalar types & add BPF link iterator, from Yonghong Song.

9) Use target's prog type for BPF_PROG_TYPE_EXT prog verification, from Udip Pant.

10) Rework BPF tracing samples to use libbpf loader, from Daniel T. Lee.

11) Fix xdpsock sample to really cycle through all buffers, from Weqaar Janjua.

12) Improve type safety for tun/veth XDP frame handling, from Maciej Żenczykowski.

13) Various smaller cleanups and improvements all over the place.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

38 files changed, 2542 insertions, 119 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 9a20016d4900..22b0760660fc 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -12,7 +12,7 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
 	    async.o range.o smpboot.o ucount.o regset.o
 
-obj-$(CONFIG_BPFILTER) += usermode_driver.o
+obj-$(CONFIG_USERMODE_DRIVER) += usermode_driver.o
 obj-$(CONFIG_MODULES) += kmod.o
 obj-$(CONFIG_MULTIUSER) += groups.o
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e6eb9c0402da..bdc8cd1b6767 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -5,6 +5,7 @@ CFLAGS_core.o += $(call cc-disable-warning, override-init)
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.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
@@ -12,6 +13,7 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += offload.o
 obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
 endif
@@ -29,3 +31,4 @@ ifeq ($(CONFIG_BPF_JIT),y)
 obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
 obj-${CONFIG_BPF_LSM} += bpf_lsm.o
 endif
+obj-$(CONFIG_BPF_PRELOAD) += preload/
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 8ff419b632a6..e046fb7d17cd 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -10,6 +10,7 @@
 #include <linux/filter.h>
 #include <linux/perf_event.h>
 #include <uapi/linux/btf.h>
+#include <linux/rcupdate_trace.h>
 
 #include "map_in_map.h"
 
@@ -487,6 +488,13 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 				   vma->vm_pgoff + pgoff);
 }
 
+static bool array_map_meta_equal(const struct bpf_map *meta0,
+				 const struct bpf_map *meta1)
+{
+	return meta0->max_entries == meta1->max_entries &&
+		bpf_map_meta_equal(meta0, meta1);
+}
+
 struct bpf_iter_seq_array_map_info {
 	struct bpf_map *map;
 	void *percpu_value_buf;
@@ -625,6 +633,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 
 static int array_map_btf_id;
 const struct bpf_map_ops array_map_ops = {
+	.map_meta_equal = array_map_meta_equal,
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
@@ -647,6 +656,7 @@ const struct bpf_map_ops array_map_ops = {
 
 static int percpu_array_map_btf_id;
 const struct bpf_map_ops percpu_array_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
@@ -1003,6 +1013,11 @@ static void prog_array_map_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
+/* prog_array->aux->{type,jited} is a runtime binding.
+ * Doing static check alone in the verifier is not enough.
+ * Thus, prog_array_map cannot be used as an inner_map
+ * and map_meta_equal is not implemented.
+ */
 static int prog_array_map_btf_id;
 const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
@@ -1101,6 +1116,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 
 static int perf_event_array_map_btf_id;
 const struct bpf_map_ops perf_event_array_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = fd_array_map_free,
@@ -1137,6 +1153,7 @@ static void cgroup_fd_array_free(struct bpf_map *map)
 
 static int cgroup_array_map_btf_id;
 const struct bpf_map_ops cgroup_array_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = cgroup_fd_array_free,
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
new file mode 100644
index 000000000000..75be02799c0f
--- /dev/null
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
+#include <linux/fdtable.h>
+
+DEFINE_BPF_STORAGE_CACHE(inode_cache);
+
+static struct bpf_local_storage __rcu **
+inode_storage_ptr(void *owner)
+{
+	struct inode *inode = owner;
+	struct bpf_storage_blob *bsb;
+
+	bsb = bpf_inode(inode);
+	if (!bsb)
+		return NULL;
+	return &bsb->storage;
+}
+
+static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode,
+							   struct bpf_map *map,
+							   bool cacheit_lockit)
+{
+	struct bpf_local_storage *inode_storage;
+	struct bpf_local_storage_map *smap;
+	struct bpf_storage_blob *bsb;
+
+	bsb = bpf_inode(inode);
+	if (!bsb)
+		return NULL;
+
+	inode_storage = rcu_dereference(bsb->storage);
+	if (!inode_storage)
+		return NULL;
+
+	smap = (struct bpf_local_storage_map *)map;
+	return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit);
+}
+
+void bpf_inode_storage_free(struct inode *inode)
+{
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage *local_storage;
+	bool free_inode_storage = false;
+	struct bpf_storage_blob *bsb;
+	struct hlist_node *n;
+
+	bsb = bpf_inode(inode);
+	if (!bsb)
+		return;
+
+	rcu_read_lock();
+
+	local_storage = rcu_dereference(bsb->storage);
+	if (!local_storage) {
+		rcu_read_unlock();
+		return;
+	}
+
+	/* Netiher the bpf_prog nor the bpf-map's syscall
+	 * could be modifying the local_storage->list now.
+	 * Thus, no elem can be added-to or deleted-from the
+	 * local_storage->list by the bpf_prog or by the bpf-map's syscall.
+	 *
+	 * It is racing with bpf_local_storage_map_free() alone
+	 * when unlinking elem from the local_storage->list and
+	 * the map's bucket->list.
+	 */
+	raw_spin_lock_bh(&local_storage->lock);
+	hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
+		/* Always unlink from map before unlinking from
+		 * local_storage.
+		 */
+		bpf_selem_unlink_map(selem);
+		free_inode_storage = bpf_selem_unlink_storage_nolock(
+			local_storage, selem, false);
+	}
+	raw_spin_unlock_bh(&local_storage->lock);
+	rcu_read_unlock();
+
+	/* free_inoode_storage should always be true as long as
+	 * local_storage->list was non-empty.
+	 */
+	if (free_inode_storage)
+		kfree_rcu(local_storage, rcu);
+}
+
+static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_local_storage_data *sdata;
+	struct file *f;
+	int fd;
+
+	fd = *(int *)key;
+	f = fget_raw(fd);
+	if (!f)
+		return NULL;
+
+	sdata = inode_storage_lookup(f->f_inode, map, true);
+	fput(f);
+	return sdata ? sdata->data : NULL;
+}
+
+static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key,
+					 void *value, u64 map_flags)
+{
+	struct bpf_local_storage_data *sdata;
+	struct file *f;
+	int fd;
+
+	fd = *(int *)key;
+	f = fget_raw(fd);
+	if (!f || !inode_storage_ptr(f->f_inode))
+		return -EBADF;
+
+	sdata = bpf_local_storage_update(f->f_inode,
+					 (struct bpf_local_storage_map *)map,
+					 value, map_flags);
+	fput(f);
+	return PTR_ERR_OR_ZERO(sdata);
+}
+
+static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
+{
+	struct bpf_local_storage_data *sdata;
+
+	sdata = inode_storage_lookup(inode, map, false);
+	if (!sdata)
+		return -ENOENT;
+
+	bpf_selem_unlink(SELEM(sdata));
+
+	return 0;
+}
+
+static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key)
+{
+	struct file *f;
+	int fd, err;
+
+	fd = *(int *)key;
+	f = fget_raw(fd);
+	if (!f)
+		return -EBADF;
+
+	err = inode_storage_delete(f->f_inode, map);
+	fput(f);
+	return err;
+}
+
+BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
+	   void *, value, u64, flags)
+{
+	struct bpf_local_storage_data *sdata;
+
+	if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
+		return (unsigned long)NULL;
+
+	/* explicitly check that the inode_storage_ptr is not
+	 * NULL as inode_storage_lookup returns NULL in this case and
+	 * bpf_local_storage_update expects the owner to have a
+	 * valid storage pointer.
+	 */
+	if (!inode_storage_ptr(inode))
+		return (unsigned long)NULL;
+
+	sdata = inode_storage_lookup(inode, map, true);
+	if (sdata)
+		return (unsigned long)sdata->data;
+
+	/* This helper must only called from where the inode is gurranteed
+	 * to have a refcount and cannot be freed.
+	 */
+	if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
+		sdata = bpf_local_storage_update(
+			inode, (struct bpf_local_storage_map *)map, value,
+			BPF_NOEXIST);
+		return IS_ERR(sdata) ? (unsigned long)NULL :
+					     (unsigned long)sdata->data;
+	}
+
+	return (unsigned long)NULL;
+}
+
+BPF_CALL_2(bpf_inode_storage_delete,
+	   struct bpf_map *, map, struct inode *, inode)
+{
+	/* This helper must only called from where the inode is gurranteed
+	 * to have a refcount and cannot be freed.
+	 */
+	return inode_storage_delete(inode, map);
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key,
+				void *next_key)
+{
+	return -ENOTSUPP;
+}
+
+static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = bpf_local_storage_map_alloc(attr);
+	if (IS_ERR(smap))
+		return ERR_CAST(smap);
+
+	smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache);
+	return &smap->map;
+}
+
+static void inode_storage_map_free(struct bpf_map *map)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = (struct bpf_local_storage_map *)map;
+	bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx);
+	bpf_local_storage_map_free(smap);
+}
+
+static int inode_storage_map_btf_id;
+const struct bpf_map_ops inode_storage_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = bpf_local_storage_map_alloc_check,
+	.map_alloc = inode_storage_map_alloc,
+	.map_free = inode_storage_map_free,
+	.map_get_next_key = notsupp_get_next_key,
+	.map_lookup_elem = bpf_fd_inode_storage_lookup_elem,
+	.map_update_elem = bpf_fd_inode_storage_update_elem,
+	.map_delete_elem = bpf_fd_inode_storage_delete_elem,
+	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_btf_name = "bpf_local_storage_map",
+	.map_btf_id = &inode_storage_map_btf_id,
+	.map_owner_storage_ptr = inode_storage_ptr,
+};
+
+BTF_ID_LIST(bpf_inode_storage_btf_ids)
+BTF_ID_UNUSED
+BTF_ID(struct, inode)
+
+const struct bpf_func_proto bpf_inode_storage_get_proto = {
+	.func		= bpf_inode_storage_get,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+	.btf_id		= bpf_inode_storage_btf_ids,
+};
+
+const struct bpf_func_proto bpf_inode_storage_delete_proto = {
+	.func		= bpf_inode_storage_delete,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.btf_id		= bpf_inode_storage_btf_ids,
+};
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 8faa2ce89396..30833bbf3019 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -390,10 +390,68 @@ out_unlock:
 	return ret;
 }
 
+static void bpf_iter_link_show_fdinfo(const struct bpf_link *link,
+				      struct seq_file *seq)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+	bpf_iter_show_fdinfo_t show_fdinfo;
+
+	seq_printf(seq,
+		   "target_name:\t%s\n",
+		   iter_link->tinfo->reg_info->target);
+
+	show_fdinfo = iter_link->tinfo->reg_info->show_fdinfo;
+	if (show_fdinfo)
+		show_fdinfo(&iter_link->aux, seq);
+}
+
+static int bpf_iter_link_fill_link_info(const struct bpf_link *link,
+					struct bpf_link_info *info)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+	char __user *ubuf = u64_to_user_ptr(info->iter.target_name);
+	bpf_iter_fill_link_info_t fill_link_info;
+	u32 ulen = info->iter.target_name_len;
+	const char *target_name;
+	u32 target_len;
+
+	if (!ulen ^ !ubuf)
+		return -EINVAL;
+
+	target_name = iter_link->tinfo->reg_info->target;
+	target_len =  strlen(target_name);
+	info->iter.target_name_len = target_len + 1;
+
+	if (ubuf) {
+		if (ulen >= target_len + 1) {
+			if (copy_to_user(ubuf, target_name, target_len + 1))
+				return -EFAULT;
+		} else {
+			char zero = '\0';
+
+			if (copy_to_user(ubuf, target_name, ulen - 1))
+				return -EFAULT;
+			if (put_user(zero, ubuf + ulen - 1))
+				return -EFAULT;
+			return -ENOSPC;
+		}
+	}
+
+	fill_link_info = iter_link->tinfo->reg_info->fill_link_info;
+	if (fill_link_info)
+		return fill_link_info(&iter_link->aux, info);
+
+	return 0;
+}
+
 static const struct bpf_link_ops bpf_iter_link_lops = {
 	.release = bpf_iter_link_release,
 	.dealloc = bpf_iter_link_dealloc,
 	.update_prog = bpf_iter_link_replace,
+	.show_fdinfo = bpf_iter_link_show_fdinfo,
+	.fill_link_info = bpf_iter_link_fill_link_info,
 };
 
 bool bpf_link_is_iter(struct bpf_link *link)
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
new file mode 100644
index 000000000000..ffa7d11fc2bd
--- /dev/null
+++ b/kernel/bpf/bpf_local_storage.c
@@ -0,0 +1,600 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook  */
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <linux/bpf_local_storage.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+
+#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
+
+static struct bpf_local_storage_map_bucket *
+select_bucket(struct bpf_local_storage_map *smap,
+	      struct bpf_local_storage_elem *selem)
+{
+	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
+}
+
+static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size)
+{
+	struct bpf_map *map = &smap->map;
+
+	if (!map->ops->map_local_storage_charge)
+		return 0;
+
+	return map->ops->map_local_storage_charge(smap, owner, size);
+}
+
+static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner,
+			 u32 size)
+{
+	struct bpf_map *map = &smap->map;
+
+	if (map->ops->map_local_storage_uncharge)
+		map->ops->map_local_storage_uncharge(smap, owner, size);
+}
+
+static struct bpf_local_storage __rcu **
+owner_storage(struct bpf_local_storage_map *smap, void *owner)
+{
+	struct bpf_map *map = &smap->map;
+
+	return map->ops->map_owner_storage_ptr(owner);
+}
+
+static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
+{
+	return !hlist_unhashed(&selem->snode);
+}
+
+static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
+{
+	return !hlist_unhashed(&selem->map_node);
+}
+
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
+		void *value, bool charge_mem)
+{
+	struct bpf_local_storage_elem *selem;
+
+	if (charge_mem && mem_charge(smap, owner, smap->elem_size))
+		return NULL;
+
+	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+	if (selem) {
+		if (value)
+			memcpy(SDATA(selem)->data, value, smap->map.value_size);
+		return selem;
+	}
+
+	if (charge_mem)
+		mem_uncharge(smap, owner, smap->elem_size);
+
+	return NULL;
+}
+
+/* local_storage->lock must be held and selem->local_storage == local_storage.
+ * The caller must ensure selem->smap is still valid to be
+ * dereferenced for its smap->elem_size and smap->cache_idx.
+ */
+bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+				     struct bpf_local_storage_elem *selem,
+				     bool uncharge_mem)
+{
+	struct bpf_local_storage_map *smap;
+	bool free_local_storage;
+	void *owner;
+
+	smap = rcu_dereference(SDATA(selem)->smap);
+	owner = local_storage->owner;
+
+	/* All uncharging on the owner must be done first.
+	 * The owner may be freed once the last selem is unlinked
+	 * from local_storage.
+	 */
+	if (uncharge_mem)
+		mem_uncharge(smap, owner, smap->elem_size);
+
+	free_local_storage = hlist_is_singular_node(&selem->snode,
+						    &local_storage->list);
+	if (free_local_storage) {
+		mem_uncharge(smap, owner, sizeof(struct bpf_local_storage));
+		local_storage->owner = NULL;
+
+		/* After this RCU_INIT, owner may be freed and cannot be used */
+		RCU_INIT_POINTER(*owner_storage(smap, owner), NULL);
+
+		/* local_storage is not freed now.  local_storage->lock is
+		 * still held and raw_spin_unlock_bh(&local_storage->lock)
+		 * will be done by the caller.
+		 *
+		 * Although the unlock will be done under
+		 * rcu_read_lock(),  it is more intutivie to
+		 * read if kfree_rcu(local_storage, rcu) is done
+		 * after the raw_spin_unlock_bh(&local_storage->lock).
+		 *
+		 * Hence, a "bool free_local_storage" is returned
+		 * to the caller which then calls the kfree_rcu()
+		 * after unlock.
+		 */
+	}
+	hlist_del_init_rcu(&selem->snode);
+	if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
+	    SDATA(selem))
+		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
+
+	kfree_rcu(selem, rcu);
+
+	return free_local_storage;
+}
+
+static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
+{
+	struct bpf_local_storage *local_storage;
+	bool free_local_storage = false;
+
+	if (unlikely(!selem_linked_to_storage(selem)))
+		/* selem has already been unlinked from sk */
+		return;
+
+	local_storage = rcu_dereference(selem->local_storage);
+	raw_spin_lock_bh(&local_storage->lock);
+	if (likely(selem_linked_to_storage(selem)))
+		free_local_storage = bpf_selem_unlink_storage_nolock(
+			local_storage, selem, true);
+	raw_spin_unlock_bh(&local_storage->lock);
+
+	if (free_local_storage)
+		kfree_rcu(local_storage, rcu);
+}
+
+void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+				   struct bpf_local_storage_elem *selem)
+{
+	RCU_INIT_POINTER(selem->local_storage, local_storage);
+	hlist_add_head(&selem->snode, &local_storage->list);
+}
+
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
+{
+	struct bpf_local_storage_map *smap;
+	struct bpf_local_storage_map_bucket *b;
+
+	if (unlikely(!selem_linked_to_map(selem)))
+		/* selem has already be unlinked from smap */
+		return;
+
+	smap = rcu_dereference(SDATA(selem)->smap);
+	b = select_bucket(smap, selem);
+	raw_spin_lock_bh(&b->lock);
+	if (likely(selem_linked_to_map(selem)))
+		hlist_del_init_rcu(&selem->map_node);
+	raw_spin_unlock_bh(&b->lock);
+}
+
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+			struct bpf_local_storage_elem *selem)
+{
+	struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
+
+	raw_spin_lock_bh(&b->lock);
+	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
+	hlist_add_head_rcu(&selem->map_node, &b->list);
+	raw_spin_unlock_bh(&b->lock);
+}
+
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
+{
+	/* Always unlink from map before unlinking from local_storage
+	 * because selem will be freed after successfully unlinked from
+	 * the local_storage.
+	 */
+	bpf_selem_unlink_map(selem);
+	__bpf_selem_unlink_storage(selem);
+}
+
+struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+			 struct bpf_local_storage_map *smap,
+			 bool cacheit_lockit)
+{
+	struct bpf_local_storage_data *sdata;
+	struct bpf_local_storage_elem *selem;
+
+	/* Fast path (cache hit) */
+	sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
+	if (sdata && rcu_access_pointer(sdata->smap) == smap)
+		return sdata;
+
+	/* Slow path (cache miss) */
+	hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
+		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
+			break;
+
+	if (!selem)
+		return NULL;
+
+	sdata = SDATA(selem);
+	if (cacheit_lockit) {
+		/* spinlock is needed to avoid racing with the
+		 * parallel delete.  Otherwise, publishing an already
+		 * deleted sdata to the cache will become a use-after-free
+		 * problem in the next bpf_local_storage_lookup().
+		 */
+		raw_spin_lock_bh(&local_storage->lock);
+		if (selem_linked_to_storage(selem))
+			rcu_assign_pointer(local_storage->cache[smap->cache_idx],
+					   sdata);
+		raw_spin_unlock_bh(&local_storage->lock);
+	}
+
+	return sdata;
+}
+
+static int check_flags(const struct bpf_local_storage_data *old_sdata,
+		       u64 map_flags)
+{
+	if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
+		/* elem already exists */
+		return -EEXIST;
+
+	if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
+		/* elem doesn't exist, cannot update it */
+		return -ENOENT;
+
+	return 0;
+}
+
+int bpf_local_storage_alloc(void *owner,
+			    struct bpf_local_storage_map *smap,
+			    struct bpf_local_storage_elem *first_selem)
+{
+	struct bpf_local_storage *prev_storage, *storage;
+	struct bpf_local_storage **owner_storage_ptr;
+	int err;
+
+	err = mem_charge(smap, owner, sizeof(*storage));
+	if (err)
+		return err;
+
+	storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN);
+	if (!storage) {
+		err = -ENOMEM