From 6648e613226e18897231ab5e42ffc29e63fa3365 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Thu, 4 Apr 2024 10:10:01 +0800
Subject: bpf, skmsg: Fix NULL pointer dereference in
 sk_psock_skb_ingress_enqueue

Fix NULL pointer data-races in sk_psock_skb_ingress_enqueue() which
syzbot reported [1].

[1]
BUG: KCSAN: data-race in sk_psock_drop / sk_psock_skb_ingress_enqueue

write to 0xffff88814b3278b8 of 8 bytes by task 10724 on cpu 1:
 sk_psock_stop_verdict net/core/skmsg.c:1257 [inline]
 sk_psock_drop+0x13e/0x1f0 net/core/skmsg.c:843
 sk_psock_put include/linux/skmsg.h:459 [inline]
 sock_map_close+0x1a7/0x260 net/core/sock_map.c:1648
 unix_release+0x4b/0x80 net/unix/af_unix.c:1048
 __sock_release net/socket.c:659 [inline]
 sock_close+0x68/0x150 net/socket.c:1421
 __fput+0x2c1/0x660 fs/file_table.c:422
 __fput_sync+0x44/0x60 fs/file_table.c:507
 __do_sys_close fs/open.c:1556 [inline]
 __se_sys_close+0x101/0x1b0 fs/open.c:1541
 __x64_sys_close+0x1f/0x30 fs/open.c:1541
 do_syscall_64+0xd3/0x1d0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

read to 0xffff88814b3278b8 of 8 bytes by task 10713 on cpu 0:
 sk_psock_data_ready include/linux/skmsg.h:464 [inline]
 sk_psock_skb_ingress_enqueue+0x32d/0x390 net/core/skmsg.c:555
 sk_psock_skb_ingress_self+0x185/0x1e0 net/core/skmsg.c:606
 sk_psock_verdict_apply net/core/skmsg.c:1008 [inline]
 sk_psock_verdict_recv+0x3e4/0x4a0 net/core/skmsg.c:1202
 unix_read_skb net/unix/af_unix.c:2546 [inline]
 unix_stream_read_skb+0x9e/0xf0 net/unix/af_unix.c:2682
 sk_psock_verdict_data_ready+0x77/0x220 net/core/skmsg.c:1223
 unix_stream_sendmsg+0x527/0x860 net/unix/af_unix.c:2339
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg+0x140/0x180 net/socket.c:745
 ____sys_sendmsg+0x312/0x410 net/socket.c:2584
 ___sys_sendmsg net/socket.c:2638 [inline]
 __sys_sendmsg+0x1e9/0x280 net/socket.c:2667
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x46/0x50 net/socket.c:2674
 do_syscall_64+0xd3/0x1d0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

value changed: 0xffffffff83d7feb0 -> 0x0000000000000000

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 10713 Comm: syz-executor.4 Tainted: G        W          6.8.0-syzkaller-08951-gfe46a7dd189e #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/29/2024

Prior to this, commit 4cd12c6065df ("bpf, sockmap: Fix NULL pointer
dereference in sk_psock_verdict_data_ready()") fixed one NULL pointer
similarly due to no protection of saved_data_ready. Here is another
different caller causing the same issue because of the same reason. So
we should protect it with sk_callback_lock read lock because the writer
side in the sk_psock_drop() uses "write_lock_bh(&sk->sk_callback_lock);".

To avoid errors that could happen in future, I move those two pairs of
lock into the sk_psock_data_ready(), which is suggested by John Fastabend.

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Reported-by: syzbot+aa8c8ec2538929f18f2d@syzkaller.appspotmail.com
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Closes: https://syzkaller.appspot.com/bug?extid=aa8c8ec2538929f18f2d
Link: https://lore.kernel.org/all/20240329134037.92124-1-kerneljasonxing@gmail.com
Link: https://lore.kernel.org/bpf/20240404021001.94815-1-kerneljasonxing@gmail.com
---
 include/linux/skmsg.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux/skmsg.h')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e65ec3fd2799..a509caf823d6 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -461,10 +461,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
 
 static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
 {
+	read_lock_bh(&sk->sk_callback_lock);
 	if (psock->saved_data_ready)
 		psock->saved_data_ready(sk);
 	else
 		sk->sk_data_ready(sk);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static inline void psock_set_prog(struct bpf_prog **pprog,
-- 
cgit v1.2.3


From 699c23f02c65cbfc3e638f14ce0d70c23a2e1f02 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 9 Apr 2024 21:35:27 -0700
Subject: bpf: Add bpf_link support for sk_msg and sk_skb progs

Add bpf_link support for sk_msg and sk_skb programs. We have an
internal request to support bpf_link for sk_msg programs so user
space can have a uniform handling with bpf_link based libbpf
APIs. Using bpf_link based libbpf API also has a benefit which
makes system robust by decoupling prog life cycle and
attachment life cycle.

Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20240410043527.3737160-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |   6 +
 include/linux/skmsg.h          |   4 +
 include/uapi/linux/bpf.h       |   5 +
 kernel/bpf/syscall.c           |   4 +
 net/core/sock_map.c            | 263 ++++++++++++++++++++++++++++++++++++++---
 tools/include/uapi/linux/bpf.h |   5 +
 6 files changed, 271 insertions(+), 16 deletions(-)

(limited to 'include/linux/skmsg.h')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 62762390c93d..5034c1b4ded7 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2996,6 +2996,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
 int sock_map_bpf_prog_query(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr);
+int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog);
 
 void sock_map_unhash(struct sock *sk);
 void sock_map_destroy(struct sock *sk);
@@ -3094,6 +3095,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e65ec3fd2799..9c8dd4c01412 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -58,6 +58,10 @@ struct sk_psock_progs {
 	struct bpf_prog			*stream_parser;
 	struct bpf_prog			*stream_verdict;
 	struct bpf_prog			*skb_verdict;
+	struct bpf_link			*msg_parser_link;
+	struct bpf_link			*stream_parser_link;
+	struct bpf_link			*stream_verdict_link;
+	struct bpf_link			*skb_verdict_link;
 };
 
 enum sk_psock_state_bits {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6fe9f11c8abe..cee0a7915c08 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1135,6 +1135,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
+	BPF_LINK_TYPE_SOCKMAP = 14,
 	__MAX_BPF_LINK_TYPE,
 };
 
@@ -6724,6 +6725,10 @@ struct bpf_link_info {
 			__u32 ifindex;
 			__u32 attach_type;
 		} netkit;
+		struct {
+			__u32 map_id;
+			__u32 attach_type;
+		} sockmap;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e44c276e8617..7d392ec83655 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5213,6 +5213,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		ret = netns_bpf_link_create(attr, prog);
 		break;
+	case BPF_PROG_TYPE_SK_MSG:
+	case BPF_PROG_TYPE_SK_SKB:
+		ret = sock_map_link_create(attr, prog);
+		break;
 #ifdef CONFIG_NET
 	case BPF_PROG_TYPE_XDP:
 		ret = bpf_xdp_link_attach(attr, prog);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 27d733c0f65e..63c016b4c169 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -24,8 +24,16 @@ struct bpf_stab {
 #define SOCK_CREATE_FLAG_MASK				\
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
+/* This mutex is used to
+ *  - protect race between prog/link attach/detach and link prog update, and
+ *  - protect race between releasing and accessing map in bpf_link.
+ * A single global mutex lock is used since it is expected contention is low.
+ */
+static DEFINE_MUTEX(sockmap_mutex);
+
 static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
-				struct bpf_prog *old, u32 which);
+				struct bpf_prog *old, struct bpf_link *link,
+				u32 which);
 static struct sk_psock_progs *sock_map_progs(struct bpf_map *map);
 
 static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
@@ -71,7 +79,9 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-	ret = sock_map_prog_update(map, prog, NULL, attr->attach_type);
+	mutex_lock(&sockmap_mutex);
+	ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type);
+	mutex_unlock(&sockmap_mutex);
 	fdput(f);
 	return ret;
 }
@@ -103,7 +113,9 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
 		goto put_prog;
 	}
 
-	ret = sock_map_prog_update(map, NULL, prog, attr->attach_type);
+	mutex_lock(&sockmap_mutex);
+	ret = sock_map_prog_update(map, NULL, prog, NULL, attr->attach_type);
+	mutex_unlock(&sockmap_mutex);
 put_prog:
 	bpf_prog_put(prog);
 put_map:
@@ -1454,55 +1466,84 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
 	return NULL;
 }
 
-static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog,
-				u32 which)
+static int sock_map_prog_link_lookup(struct bpf_map *map, struct bpf_prog ***pprog,
+				     struct bpf_link ***plink, u32 which)
 {
 	struct sk_psock_progs *progs = sock_map_progs(map);
+	struct bpf_prog **cur_pprog;
+	struct bpf_link **cur_plink;
 
 	if (!progs)
 		return -EOPNOTSUPP;
 
 	switch (which) {
 	case BPF_SK_MSG_VERDICT:
-		*pprog = &progs->msg_parser;
+		cur_pprog = &progs->msg_parser;
+		cur_plink = &progs->msg_parser_link;
 		break;
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 	case BPF_SK_SKB_STREAM_PARSER:
-		*pprog = &progs->stream_parser;
+		cur_pprog = &progs->stream_parser;
+		cur_plink = &progs->stream_parser_link;
 		break;
 #endif
 	case BPF_SK_SKB_STREAM_VERDICT:
 		if (progs->skb_verdict)
 			return -EBUSY;
-		*pprog = &progs->stream_verdict;
+		cur_pprog = &progs->stream_verdict;
+		cur_plink = &progs->stream_verdict_link;
 		break;
 	case BPF_SK_SKB_VERDICT:
 		if (progs->stream_verdict)
 			return -EBUSY;
-		*pprog = &progs->skb_verdict;
+		cur_pprog = &progs->skb_verdict;
+		cur_plink = &progs->skb_verdict_link;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
+	*pprog = cur_pprog;
+	if (plink)
+		*plink = cur_plink;
 	return 0;
 }
 
+/* Handle the following four cases:
+ * prog_attach: prog != NULL, old == NULL, link == NULL
+ * prog_detach: prog == NULL, old != NULL, link == NULL
+ * link_attach: prog != NULL, old == NULL, link != NULL
+ * link_detach: prog == NULL, old != NULL, link != NULL
+ */
 static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
-				struct bpf_prog *old, u32 which)
+				struct bpf_prog *old, struct bpf_link *link,
+				u32 which)
 {
 	struct bpf_prog **pprog;
+	struct bpf_link **plink;
 	int ret;
 
-	ret = sock_map_prog_lookup(map, &pprog, which);
+	ret = sock_map_prog_link_lookup(map, &pprog, &plink, which);
 	if (ret)
 		return ret;
 
-	if (old)
-		return psock_replace_prog(pprog, prog, old);
+	/* for prog_attach/prog_detach/link_attach, return error if a bpf_link
+	 * exists for that prog.
+	 */
+	if ((!link || prog) && *plink)
+		return -EBUSY;
 
-	psock_set_prog(pprog, prog);
-	return 0;
+	if (old) {
+		ret = psock_replace_prog(pprog, prog, old);
+		if (!ret)
+			*plink = NULL;
+	} else {
+		psock_set_prog(pprog, prog);
+		if (link)
+			*plink = link;
+	}
+
+	return ret;
 }
 
 int sock_map_bpf_prog_query(const union bpf_attr *attr,
@@ -1527,7 +1568,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr,
 
 	rcu_read_lock();
 
-	ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type);
+	ret = sock_map_prog_link_lookup(map, &pprog, NULL, attr->query.attach_type);
 	if (ret)
 		goto end;
 
@@ -1657,6 +1698,196 @@ void sock_map_close(struct sock *sk, long timeout)
 }
 EXPORT_SYMBOL_GPL(sock_map_close);
 
+struct sockmap_link {
+	struct bpf_link link;
+	struct bpf_map *map;
+	enum bpf_attach_type attach_type;
+};
+
+static void sock_map_link_release(struct bpf_link *link)
+{
+	struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+
+	mutex_lock(&sockmap_mutex);
+	if (!sockmap_link->map)
+		goto out;
+
+	WARN_ON_ONCE(sock_map_prog_update(sockmap_link->map, NULL, link->prog, link,
+					  sockmap_link->attach_type));
+
+	bpf_map_put_with_uref(sockmap_link->map);
+	sockmap_link->map = NULL;
+out:
+	mutex_unlock(&sockmap_mutex);
+}
+
+static int sock_map_link_detach(struct bpf_link *link)
+{
+	sock_map_link_release(link);
+	return 0;
+}
+
+static void sock_map_link_dealloc(struct bpf_link *link)
+{
+	kfree(link);
+}
+
+/* Handle the following two cases:
+ * case 1: link != NULL, prog != NULL, old != NULL
+ * case 2: link != NULL, prog != NULL, old == NULL
+ */
+static int sock_map_link_update_prog(struct bpf_link *link,
+				     struct bpf_prog *prog,
+				     struct bpf_prog *old)
+{
+	const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+	struct bpf_prog **pprog, *old_link_prog;
+	struct bpf_link **plink;
+	int ret = 0;
+
+	mutex_lock(&sockmap_mutex);
+
+	/* If old prog is not NULL, ensure old prog is the same as link->prog. */
+	if (old && link->prog != old) {
+		ret = -EPERM;
+		goto out;
+	}
+	/* Ensure link->prog has the same type/attach_type as the new prog. */
+	if (link->prog->type != prog->type ||
+	    link->prog->expected_attach_type != prog->expected_attach_type) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink,
+					sockmap_link->attach_type);
+	if (ret)
+		goto out;
+
+	/* return error if the stored bpf_link does not match the incoming bpf_link. */
+	if (link != *plink) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (old) {
+		ret = psock_replace_prog(pprog, prog, old);
+		if (ret)
+			goto out;
+	} else {
+		psock_set_prog(pprog, prog);
+	}
+
+	bpf_prog_inc(prog);
+	old_link_prog = xchg(&link->prog, prog);
+	bpf_prog_put(old_link_prog);
+
+out:
+	mutex_unlock(&sockmap_mutex);
+	return ret;
+}
+
+static u32 sock_map_link_get_map_id(const struct sockmap_link *sockmap_link)
+{
+	u32 map_id = 0;
+
+	mutex_lock(&sockmap_mutex);
+	if (sockmap_link->map)
+		map_id = sockmap_link->map->id;
+	mutex_unlock(&sockmap_mutex);
+	return map_id;
+}
+
+static int sock_map_link_fill_info(const struct bpf_link *link,
+				   struct bpf_link_info *info)
+{
+	const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+	u32 map_id = sock_map_link_get_map_id(sockmap_link);
+
+	info->sockmap.map_id = map_id;
+	info->sockmap.attach_type = sockmap_link->attach_type;
+	return 0;
+}
+
+static void sock_map_link_show_fdinfo(const struct bpf_link *link,
+				      struct seq_file *seq)
+{
+	const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+	u32 map_id = sock_map_link_get_map_id(sockmap_link);
+
+	seq_printf(seq, "map_id:\t%u\n", map_id);
+	seq_printf(seq, "attach_type:\t%u\n", sockmap_link->attach_type);
+}
+
+static const struct bpf_link_ops sock_map_link_ops = {
+	.release = sock_map_link_release,
+	.dealloc = sock_map_link_dealloc,
+	.detach = sock_map_link_detach,
+	.update_prog = sock_map_link_update_prog,
+	.fill_link_info = sock_map_link_fill_info,
+	.show_fdinfo = sock_map_link_show_fdinfo,
+};
+
+int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_link_primer link_primer;
+	struct sockmap_link *sockmap_link;
+	enum bpf_attach_type attach_type;
+	struct bpf_map *map;
+	int ret;
+
+	if (attr->link_create.flags)
+		return -EINVAL;
+
+	map = bpf_map_get_with_uref(attr->link_create.target_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+	if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	sockmap_link = kzalloc(sizeof(*sockmap_link), GFP_USER);
+	if (!sockmap_link) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	attach_type = attr->link_create.attach_type;
+	bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog);
+	sockmap_link->map = map;
+	sockmap_link->attach_type = attach_type;
+
+	ret = bpf_link_prime(&sockmap_link->link, &link_primer);
+	if (ret) {
+		kfree(sockmap_link);
+		goto out;
+	}
+
+	mutex_lock(&sockmap_mutex);
+	ret = sock_map_prog_update(map, prog, NULL, &sockmap_link->link, attach_type);
+	mutex_unlock(&sockmap_mutex);
+	if (ret) {
+		bpf_link_cleanup(&link_primer);
+		goto out;
+	}
+
+	/* Increase refcnt for the prog since when old prog is replaced with
+	 * psock_replace_prog() and psock_set_prog() its refcnt will be decreased.
+	 *
+	 * Actually, we do not need to increase refcnt for the prog since bpf_link
+	 * will hold a reference. But in order to have less complexity w.r.t.
+	 * replacing/setting prog, let us increase the refcnt to make things simpler.
+	 */
+	bpf_prog_inc(prog);
+
+	return bpf_link_settle(&link_primer);
+
+out:
+	bpf_map_put_with_uref(map);
+	return ret;
+}
+
 static int sock_map_iter_attach_target(struct bpf_prog *prog,
 				       union bpf_iter_link_info *linfo,
 				       struct bpf_iter_aux_info *aux)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6fe9f11c8abe..cee0a7915c08 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1135,6 +1135,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
+	BPF_LINK_TYPE_SOCKMAP = 14,
 	__MAX_BPF_LINK_TYPE,
 };
 
@@ -6724,6 +6725,10 @@ struct bpf_link_info {
 			__u32 ifindex;
 			__u32 attach_type;
 		} netkit;
+		struct {
+			__u32 map_id;
+			__u32 attach_type;
+		} sockmap;
 	};
 } __attribute__((aligned(8)));
 
-- 
cgit v1.2.3


From 2c321f3f70bc284510598f712b702ce8d60c4d14 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Sun, 14 Apr 2024 19:07:31 -0700
Subject: mm: change inlined allocation helpers to account at the call site

Main goal of memory allocation profiling patchset is to provide accounting
that is cheap enough to run in production.  To achieve that we inject
counters using codetags at the allocation call sites to account every time
allocation is made.  This injection allows us to perform accounting
efficiently because injected counters are immediately available as opposed
to the alternative methods, such as using _RET_IP_, which would require
counter lookup and appropriate locking that makes accounting much more
expensive.  This method requires all allocation functions to inject
separate counters at their call sites so that their callers can be
individually accounted.  Counter injection is implemented by allocation
hooks which should wrap all allocation functions.

Inlined functions which perform allocations but do not use allocation
hooks are directly charged for the allocations they perform.  In most
cases these functions are just specialized allocation wrappers used from
multiple places to allocate objects of a specific type.  It would be more
useful to do the accounting at their call sites instead.  Instrument these
helpers to do accounting at the call site.  Simple inlined allocation
wrappers are converted directly into macros.  More complex allocators or
allocators with documentation are converted into _noprof versions and
allocation hooks are added.  This allows memory allocation profiling
mechanism to charge allocations to the callers of these functions.

Link: https://lkml.kernel.org/r/20240415020731.1152108-1-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Jan Kara <jack@suse.cz>		[jbd2]
Cc: Anna Schumaker <anna@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/iommu/amd/amd_iommu.h           |  5 +++--
 fs/nfs/iostat.h                         |  5 +----
 include/acpi/platform/aclinuxex.h       | 19 ++++++------------
 include/asm-generic/pgalloc.h           | 35 ++++++++++++++++++++-------------
 include/crypto/hash.h                   |  7 ++++---
 include/crypto/internal/acompress.h     |  5 +++--
 include/crypto/skcipher.h               |  7 ++++---
 include/linux/bpf.h                     | 33 ++++++++-----------------------
 include/linux/bpfptr.h                  |  5 +++--
 include/linux/dma-fence-chain.h         |  6 ++----
 include/linux/hid_bpf.h                 |  6 ++----
 include/linux/jbd2.h                    | 12 ++++-------
 include/linux/mm.h                      |  5 +++--
 include/linux/mm_types.h                |  5 +++--
 include/linux/percpu.h                  |  3 +++
 include/linux/ptr_ring.h                | 28 +++++++++++++++-----------
 include/linux/skb_array.h               | 19 ++++++++++--------
 include/linux/skbuff.h                  | 20 ++++++++-----------
 include/linux/skmsg.h                   |  8 +++-----
 include/linux/slab.h                    |  5 +++++
 include/linux/sockptr.h                 | 10 ++++++----
 include/net/netlabel.h                  | 16 +++++++++------
 include/net/netlink.h                   |  5 +++--
 include/net/request_sock.h              |  5 +++--
 include/net/tcx.h                       |  5 +++--
 net/sunrpc/auth_gss/auth_gss_internal.h |  6 ++++--
 26 files changed, 142 insertions(+), 143 deletions(-)

(limited to 'include/linux/skmsg.h')

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index f482aab420f7..52575ba9a141 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -134,13 +134,14 @@ static inline int get_pci_sbdf_id(struct pci_dev *pdev)
 	return PCI_SEG_DEVID_TO_SBDF(seg, devid);
 }
 
-static inline void *alloc_pgtable_page(int nid, gfp_t gfp)
+static inline void *alloc_pgtable_page_noprof(int nid, gfp_t gfp)
 {
 	struct page *page;
 
-	page = alloc_pages_node(nid, gfp | __GFP_ZERO, 0);
+	page = alloc_pages_node_noprof(nid, gfp | __GFP_ZERO, 0);
 	return page ? page_address(page) : NULL;
 }
+#define alloc_pgtable_page(...)	alloc_hooks(alloc_pgtable_page_noprof(__VA_ARGS__))
 
 /*
  * This must be called after device probe completes. During probe
diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h
index 5aa776b5a3e7..b17a9eb9b148 100644
--- a/fs/nfs/iostat.h
+++ b/fs/nfs/iostat.h
@@ -46,10 +46,7 @@ static inline void nfs_add_stats(const struct inode *inode,
 	nfs_add_server_stats(NFS_SERVER(inode), stat, addend);
 }
 
-static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void)
-{
-	return alloc_percpu(struct nfs_iostats);
-}
+#define nfs_alloc_iostats()	alloc_percpu(struct nfs_iostats)
 
 static inline void nfs_free_iostats(struct nfs_iostats __percpu *stats)
 {
diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h
index 600d4e2641da..62cac266a1c8 100644
--- a/include/acpi/platform/aclinuxex.h
+++ b/include/acpi/platform/aclinuxex.h
@@ -47,26 +47,19 @@ acpi_status acpi_os_terminate(void);
  * However, boot has  (system_state != SYSTEM_RUNNING)
  * to quiet __might_sleep() in kmalloc() and resume does not.
  */
-static inline void *acpi_os_allocate(acpi_size size)
-{
-	return kmalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
-}
+#define acpi_os_allocate(_size)	\
+		kmalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL)
 
-static inline void *acpi_os_allocate_zeroed(acpi_size size)
-{
-	return kzalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
-}
+#define acpi_os_allocate_zeroed(_size)	\
+		kzalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL)
 
 static inline void acpi_os_free(void *memory)
 {
 	kfree(memory);
 }
 
-static inline void *acpi_os_acquire_object(acpi_cache_t * cache)
-{
-	return kmem_cache_zalloc(cache,
-				 irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
-}
+#define acpi_os_acquire_object(_cache)	\
+		kmem_cache_zalloc(_cache, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL)
 
 static inline acpi_thread_id acpi_os_get_thread_id(void)
 {
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 879e5f8aa5e9..7c48f5fbf8aa 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -16,15 +16,16 @@
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm)
+static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
 {
-	struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL &
+	struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL &
 			~__GFP_HIGHMEM, 0);
 
 	if (!ptdesc)
 		return NULL;
 	return ptdesc_address(ptdesc);
 }
+#define __pte_alloc_one_kernel(...)	alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
 
 #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
 /**
@@ -33,10 +34,11 @@ static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm)
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm)
 {
-	return __pte_alloc_one_kernel(mm);
+	return __pte_alloc_one_kernel_noprof(mm);
 }
+#define pte_alloc_one_kernel(...)	alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__))
 #endif
 
 /**
@@ -61,11 +63,11 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
  *
  * Return: `struct page` referencing the ptdesc or %NULL on error
  */
-static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp)
+static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
 {
 	struct ptdesc *ptdesc;
 
-	ptdesc = pagetable_alloc(gfp, 0);
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 	if (!pagetable_pte_ctor(ptdesc)) {
@@ -75,6 +77,7 @@ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp)
 
 	return ptdesc_page(ptdesc);
 }
+#define __pte_alloc_one(...)	alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__))
 
 #ifndef __HAVE_ARCH_PTE_ALLOC_ONE
 /**
@@ -85,10 +88,11 @@ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp)
  *
  * Return: `struct page` referencing the ptdesc or %NULL on error
  */
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm)
 {
-	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
+	return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER);
 }
+#define pte_alloc_one(...)	alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__))
 #endif
 
 /*
@@ -124,14 +128,14 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
 {
 	struct ptdesc *ptdesc;
 	gfp_t gfp = GFP_PGTABLE_USER;
 
 	if (mm == &init_mm)
 		gfp = GFP_PGTABLE_KERNEL;
-	ptdesc = pagetable_alloc(gfp, 0);
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 	if (!pagetable_pmd_ctor(ptdesc)) {
@@ -140,6 +144,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 	}
 	return ptdesc_address(ptdesc);
 }
+#define pmd_alloc_one(...)	alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
 #endif
 
 #ifndef __HAVE_ARCH_PMD_FREE
@@ -157,7 +162,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 
 #if CONFIG_PGTABLE_LEVELS > 3
 
-static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
 {
 	gfp_t gfp = GFP_PGTABLE_USER;
 	struct ptdesc *ptdesc;
@@ -166,13 +171,14 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 		gfp = GFP_PGTABLE_KERNEL;
 	gfp &= ~__GFP_HIGHMEM;
 
-	ptdesc = pagetable_alloc(gfp, 0);
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 
 	pagetable_pud_ctor(ptdesc);
 	return ptdesc_address(ptdesc);
 }
+#define __pud_alloc_one(...)	alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
 
 #ifndef __HAVE_ARCH_PUD_ALLOC_ONE
 /**
@@ -184,10 +190,11 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
  *
  * Return: pointer to the allocated memory or %NULL on error
  */
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
 {
-	return __pud_alloc_one(mm, addr);
+	return __pud_alloc_one_noprof(mm, addr);
 }
+#define pud_alloc_one(...)	alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__))
 #endif
 
 static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 5d61f576cfc8..e5181cc9b7c5 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -578,19 +578,20 @@ static inline void ahash_request_set_tfm(struct ahash_request *req,
  *
  * Return: allocated request handle in case of success, or NULL if out of memory
  */
-static inline struct ahash_request *ahash_request_alloc(
+static inline struct ahash_request *ahash_request_alloc_noprof(
 	struct crypto_ahash *tfm, gfp_t gfp)
 {
 	struct ahash_request *req;
 
-	req = kmalloc(sizeof(struct ahash_request) +
-		      crypto_ahash_reqsize(tfm), gfp);
+	req = kmalloc_noprof(sizeof(struct ahash_request) +
+			     crypto_ahash_reqsize(tfm), gfp);
 
 	if (likely(req))
 		ahash_request_set_tfm(req, tfm);
 
 	return req;
 }
+#define ahash_request_alloc(...)	alloc_hooks(ahash_request_alloc_noprof(__VA_ARGS__))
 
 /**
  * ahash_request_free() - zeroize and free the request data structure
diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h
index 4ac46bafba9d..2a67793f52ad 100644
--- a/include/crypto/internal/acompress.h
+++ b/include/crypto/internal/acompress.h
@@ -69,15 +69,16 @@ static inline void acomp_request_complete(struct acomp_req *req,
 	crypto_request_complete(&req->base, err);
 }
 
-static inline struct acomp_req *__acomp_request_alloc(struct crypto_acomp *tfm)
+static inline struct acomp_req *__acomp_request_alloc_noprof(struct crypto_acomp *tfm)
 {
 	struct acomp_req *req;
 
-	req = kzalloc(sizeof(*req) + crypto_acomp_reqsize(tfm), GFP_KERNEL);
+	req = kzalloc_noprof(sizeof(*req) + crypto_acomp_reqsize(tfm), GFP_KERNEL);
 	if (likely(req))
 		acomp_request_set_tfm(req, tfm);
 	return req;
 }
+#define __acomp_request_alloc(...)	alloc_hooks(__acomp_request_alloc_noprof(__VA_ARGS__))
 
 static inline void __acomp_request_free(struct acomp_req *req)
 {
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index c8857d7bdb37..6c5330e316b0 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -861,19 +861,20 @@ static inline struct skcipher_request *skcipher_request_cast(
  *
  * Return: allocated request handle in case of success, or NULL if out of memory
  */
-static inline struct skcipher_request *skcipher_request_alloc(
+static inline struct skcipher_request *skcipher_request_alloc_noprof(
 	struct crypto_skcipher *tfm, gfp_t gfp)
 {
 	struct skcipher_request *req;
 
-	req = kmalloc(sizeof(struct skcipher_request) +
-		      crypto_skcipher_reqsize(tfm), gfp);
+	req = kmalloc_noprof(sizeof(struct skcipher_request) +
+			     crypto_skcipher_reqsize(tfm), gfp);
 
 	if (likely(req))
 		skcipher_request_set_tfm(req, tfm);
 
 	return req;
 }
+#define skcipher_request_alloc(...)	alloc_hooks(skcipher_request_alloc_noprof(__VA_ARGS__))
 
 /**
  * skcipher_request_free() - zeroize and free request data structure
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 890e152d553e..a86da1f38b3c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2244,31 +2244,14 @@ void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size,
 void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
 				    size_t align, gfp_t flags);
 #else
-static inline void *
-bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
-		     int node)
-{
-	return kmalloc_node(size, flags, node);
-}
-
-static inline void *
-bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
-{
-	return kzalloc(size, flags);
-}
-
-static inline void *
-bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags)
-{
-	return kvcalloc(n, size, flags);
-}
-
-static inline void __percpu *
-bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align,
-		     gfp_t flags)
-{
-	return __alloc_percpu_gfp(size, align, flags);
-}
+#define bpf_map_kmalloc_node(_map, _size, _flags, _node)	\
+		kmalloc_node(_size, _flags, _node)
+#define bpf_map_kzalloc(_map, _size, _flags)			\
+		kzalloc(_size, _flags)
+#define bpf_map_kvcalloc(_map, _n, _size, _flags)		\
+		kvcalloc(_n, _size, _flags)
+#define bpf_map_alloc_percpu(_map, _size, _align, _flags)	\
+		__alloc_percpu_gfp(_size, _align, _flags)
 #endif
 
 static inline int
diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h
index 79b2f78eec1a..1af241525a17 100644
--- a/include/linux/bpfptr.h
+++ b/include/linux/bpfptr.h
@@ -65,9 +65,9 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset,
 	return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size);
 }
 
-static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len)
+static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len)
 {
-	void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN);
+	void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
@@ -77,6 +77,7 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len)
 	}
 	return p;
 }
+#define kvmemdup_bpfptr(...)	alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__))
 
 static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count)
 {
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
index 4bdf0b96da28..ad9e2506c2f4 100644
--- a/include/linux/dma-fence-chain.h
+++ b/include/linux/dma-fence-chain.h
@@ -86,10 +86,8 @@ dma_fence_chain_contained(struct dma_fence *fence)
  *
  * Returns a new struct dma_fence_chain object or NULL on failure.
  */
-static inline struct dma_fence_chain *dma_fence_chain_alloc(void)
-{
-	return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL);
-};
+#define dma_fence_chain_alloc()	\
+		((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL))
 
 /**
  * dma_fence_chain_free
diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h
index 7118ac28d468..ca70eeb6393e 100644
--- a/include/linux/hid_bpf.h
+++ b/include/linux/hid_bpf.h
@@ -149,10 +149,8 @@ static inline int hid_bpf_connect_device(struct hid_device *hdev) { return 0; }
 static inline void hid_bpf_disconnect_device(struct hid_device *hdev) {}
 static inline void hid_bpf_destroy_device(struct hid_device *hid) {}
 static inline void hid_bpf_device_init(struct hid_device *hid) {}
-static inline u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size)
-{
-	return kmemdup(rdesc, *size, GFP_KERNEL);
-}
+#define call_hid_bpf_rdesc_fixup(_hdev, _rdesc, _size)	\
+		((u8 *)kmemdup(_rdesc, *(_size), GFP_KERNEL))
 
 #endif /* CONFIG_HID_BPF */
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 971f3e826e15..9512fe332668 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1586,10 +1586,8 @@ void jbd2_journal_put_journal_head(struct journal_head *jh);
  */
 extern struct kmem_cache *jbd2_handle_cache;
 
-static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags)
-{
-	return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags);
-}
+#define jbd2_alloc_handle(_gfp_flags)	\
+		((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags))
 
 static inline void jbd2_free_handle(handle_t *handle)
 {
@@ -1602,10 +1600,8 @@ static inline void jbd2_free_handle(handle_t *handle)
  */
 extern struct kmem_cache *jbd2_inode_cache;
 
-static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags)
-{
-	return kmem_cache_alloc(jbd2_inode_cache, gfp_flags);
-}
+#define jbd2_alloc_inode(_gfp_flags)	\
+		((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags))
 
 static inline void jbd2_free_inode(struct jbd2_inode *jinode)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0dbd737cfabd..60eabc6c8e00 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2860,12 +2860,13 @@ static inline bool pagetable_is_reserved(struct ptdesc *pt)
  *
  * Return: The ptdesc describing the allocated page tables.
  */
-static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order)
+static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order)
 {
-	struct page *page = alloc_pages(gfp | __GFP_COMP, order);
+	struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order);
 
 	return page_ptdesc(page);
 }
+#define pagetable_alloc(...)	alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__))
 
 /**
  * pagetable_free - Free pagetables
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4ae4684d1add..6fef56938a17 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1170,14 +1170,15 @@ static inline void mm_init_cid(struct mm_struct *mm)
 	cpumask_clear(mm_cidmask(mm));
 }
 
-static inline int mm_alloc_cid(struct mm_struct *mm)
+static inline int mm_alloc_cid_noprof(struct mm_struct *mm)
 {
-	mm->pcpu_cid = alloc_percpu(struct mm_cid);
+	mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid);
 	if (!mm->pcpu_cid)
 		return -ENOMEM;
 	mm_init_cid(mm);
 	return 0;
 }
+#define mm_alloc_cid(...)	alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__))
 
 static inline void mm_destroy_cid(struct mm_struct *mm)
 {
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 13a82f11e4fd..03053de557cf 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -151,6 +151,9 @@ extern size_t pcpu_alloc_size(void __percpu *__pdata);
 #define alloc_percpu(type)						\
 	(typeof(type) __percpu *)__alloc_percpu(sizeof(type),		\
 						__alignof__(type))
+#define alloc_percpu_noprof(type)					\
+	((typeof(type) __percpu *)pcpu_alloc_noprof(sizeof(type),	\
+					__alignof__(type), false, GFP_KERNEL))
 
 extern void free_percpu(void __percpu *__pdata);
 
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 808f9d3ee546..fd037c127bb0 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -464,11 +464,11 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r,
 /* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See
  * documentation for vmalloc for which of them are legal.
  */
-static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
+static inline void **__ptr_ring_init_queue_alloc_noprof(unsigned int size, gfp_t gfp)
 {
 	if (size > KMALLOC_MAX_SIZE / sizeof(void *))
 		return NULL;
-	return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO);
+	return kvmalloc_array_noprof(size, sizeof(void *), gfp | __GFP_ZERO);
 }
 
 static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
@@ -484,9 +484,9 @@ static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
 		r->batch = 1;
 }
 
-static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
+static inline int ptr_ring_init_noprof(struct ptr_ring *r, int size, gfp_t gfp)
 {
-	r->queue = __ptr_ring_init_queue_alloc(size, gfp);
+	r->queue = __ptr_ring_init_queue_alloc_noprof(size, gfp);
 	if (!r->queue)
 		return -ENOMEM;
 
@@ -497,6 +497,7 @@ static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
 
 	return 0;
 }
+#define ptr_ring_init(...)	alloc_hooks(ptr_ring_init_noprof(__VA_ARGS__))
 
 /*
  * Return entries into ring. Destroy entries that don't fit.
@@ -587,11 +588,11 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
+static inline int ptr_ring_resize_noprof(struct ptr_ring *r, int size, gfp_t gfp,
 				  void (*destroy)(void *))
 {
 	unsigned long flags;
-	void **queue = __ptr_ring_init_queue_alloc(size, gfp);
+	void **queue = __ptr_ring_init_queue_alloc_noprof(size, gfp);
 	void **old;
 
 	if (!queue)
@@ -609,6 +610,7 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
 
 	return 0;
 }
+#define ptr_ring_resize(...)	alloc_hooks(ptr_ring_resize_noprof(__VA_ARGS__))
 
 /*
  * Note: producer lock is nested within consumer lock, so if you
@@ -616,21 +618,21 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
-					   unsigned int nrings,
-					   int size,
-					   gfp_t gfp, void (*destroy)(void *))
+static inline int ptr_ring_resize_multiple_noprof(struct ptr_ring **rings,
+						  unsigned int nrings,
+						  int size,
+						  gfp_t gfp, void (*destroy)(void *))
 {
 	unsigned long flags;
 	void ***queues;
 	int i;
 
-	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
+	queues = kmalloc_array_noprof(nrings, sizeof(*queues), gfp);
 	if (!queues)
 		goto noqueues;
 
 	for (i = 0; i < nrings; ++i) {
-		queues[i] = __ptr_ring_init_queue_alloc(size, gfp);
+		queues[i] = __ptr_ring_init_queue_alloc_noprof(size, gfp);
 		if (!queues[i])
 			goto nomem;
 	}
@@ -660,6 +662,8 @@ nomem:
 noqueues:
 	return -ENOMEM;
 }
+#define ptr_ring_resize_multiple(...) \
+		alloc_hooks(ptr_ring_resize_multiple_noprof(__VA_ARGS__))
 
 static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *))
 {
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index e2d45b7cb619..926496c9cc9c 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -177,10 +177,11 @@ static inline int skb_array_peek_len_any(struct skb_array *a)
 	return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag);
 }
 
-static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp)
+static inline int skb_array_init_noprof(struct skb_array *a, int size, gfp_t gfp)
 {
-	return ptr_ring_init(&a->ring, size, gfp);
+	return ptr_ring_init_noprof(&a->ring, size, gfp);
 }
+#define skb_array_init(...)	alloc_hooks(skb_array_init_noprof(__VA_ARGS__))
 
 static void __skb_array_destroy_skb(void *ptr)
 {
@@ -198,15 +199,17 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp)
 	return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb);
 }
 
-static inline int skb_array_resize_multiple(struct skb_array **rings,
-					    int nrings, unsigned int size,
-					    gfp_t gfp)
+static inline int skb_array_resize_multiple_noprof(struct skb_array **rings,
+						   int nrings, unsigned int size,
+						   gfp_t gfp)
 {
 	BUILD_BUG_ON(offsetof(struct skb_array, ring));
-	return ptr_ring_resize_multiple((struct ptr_ring **)rings,
-					nrings, size, gfp,
-					__skb_array_destroy_skb);
+	return ptr_ring_resize_multiple_noprof((struct ptr_ring **)rings,
+					       nrings, size, gfp,
+					       __skb_array_destroy_skb);
 }
+#define skb_array_resize_multiple(...)	\
+		alloc_hooks(skb_array_resize_multiple_noprof(__VA_ARGS__))
 
 static inline void skb_array_cleanup(struct skb_array *a)
 {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9d24aec064e8..b72920c9887b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3371,7 +3371,7 @@ void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason);
  *
  * %NULL is returned if there is no free memory.
 */
-static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
+static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask,
 					     unsigned int order)
 {
 	/* This piece of code contains several assumptions.
@@ -3384,13 +3384,11 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
 	 */
 	gfp_mask |= __GFP_COMP | __GFP_MEMALLOC;
 
-	return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+	return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order);
 }
+#define __dev_alloc_pages(...)	alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__))
 
-static inline struct page *dev_alloc_pages(unsigned int order)
-{
-	return __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, order);
-}
+#define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order)
 
 /**
  * __dev_alloc_page - allocate a page for network Rx
@@ -3400,15 +3398,13 @@ static inline struct page *dev_alloc_pages(unsigned int order)
  *
  * %NULL is returned if there is no free memory.
  */
-static inline struct page *__dev_alloc_page(gfp_t gfp_mask)
+static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask)
 {
-	return __dev_alloc_pages(gfp_mask, 0);
+	return __dev_alloc_pages_noprof(gfp_mask, 0);
 }
+#define __dev_alloc_page(...)	alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__))
 
-static inline struct page *dev_alloc_page(void)
-{
-	return dev_alloc_pages(0);
-}
+#define dev_alloc_page()	dev_alloc_pages(0)
 
 /**
  * dev_page_is_reusable - check whether a page can be reused for network Rx
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e65ec3fd2799..78efc5b20284 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -410,11 +410,9 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock);
 int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
 			 struct sk_msg *msg);
 
-static inline struct sk_psock_link *sk_psock_init_link(void)
-{
-	return kzalloc(sizeof(struct sk_psock_link),
-		       GFP_ATOMIC | __GFP_NOWARN);
-}
+#define sk_psock_init_link()	\
+		((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link),	\
+						 GFP_ATOMIC | __GFP_NOWARN))
 
 static inline void sk_psock_free_link(struct sk_psock_link *link)
 {
diff --git a/include/linux/slab.h b/include/linux/slab.h
index c0be1cd03cf6..4cc37ef22aae 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -744,6 +744,9 @@ void *kmalloc_node_track_caller_noprof(size_t size, gfp_t flags, int node,
  */
 #define kmalloc_track_caller(...)		kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE)
 
+#define kmalloc_track_caller_noprof(...)	\
+		kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_)
+
 static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags,
 							  int node)
 {
@@ -781,6 +784,7 @@ extern void *kvmalloc_node_noprof(size_t size, gfp_t flags, int node) __alloc_si
 #define kvmalloc_node(...)			alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__))
 
 #define kvmalloc(_size, _flags)			kvmalloc_node(_size, _flags, NUMA_NO_NODE)
+#define kvmalloc_noprof(_size, _flags)		kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE)
 #define kvzalloc(_size, _flags)			kvmalloc(_size, _flags|__GFP_ZERO)
 
 #define kvzalloc_node(_size, _flags, _node)	kvmalloc_node(_size, _flags|__GFP_ZERO, _node)
@@ -797,6 +801,7 @@ static inline __alloc_size(1, 2) void *kvmalloc_array_noprof(size_t n, size_t si
 
 #define kvmalloc_array(...)			alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__))
 #define kvcalloc(_n, _size, _flags)		kvmalloc_array(_n, _size, _flags|__GFP_ZERO)
+#define kvcalloc_noprof(_n, _size, _flags)	kvmalloc_array_noprof(_n, _size, _flags|__GFP_ZERO)
 
 extern void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
 		      __realloc_size(3);
diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 317200cd3a60..fc5a206c4043 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -117,9 +117,9 @@ static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size)
 	return copy_to_sockptr_offset(dst, 0, src, size);
 }
 
-static inline void *memdup_sockptr(sockptr_t src, size_t len)
+static inline void *memdup_sockptr_noprof(sockptr_t src, size_t len)
 {
-	void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN);
+	void *p = kmalloc_track_caller_noprof(len, GFP_USER | __GFP_NOWARN);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
@@ -129,10 +129,11 @@ static inline void *memdup_sockptr(sockptr_t src, size_t len)
 	}
 	return p;
 }
+#define memdup_sockptr(...)	alloc_hooks(memdup_sockptr_noprof(__VA_ARGS__))
 
-static inline void *memdup_sockptr_nul(sockptr_t src, size_t len)
+static inline void *memdup_sockptr_nul_noprof(sockptr_t src, size_t len)
 {
-	char *p = kmalloc_track_caller(len + 1, GFP_KERNEL);
+	char *p = kmalloc_track_caller_noprof(len + 1, GFP_KERNEL);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
@@ -143,6 +144,7 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len)
 	p[len] = '\0';
 	return p;
 }
+#define memdup_sockptr_nul(...)	alloc_hooks(memdup_sockptr_nul_noprof(__VA_ARGS__))
 
 static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count)
 {
diff --git a/include/net/netlabel.h b/include/net/netlabel.h
index f3ab0b8a4b18..c31bd96dafdb 100644
--- a/include/net/netlabel.h
+++ b/include/net/netlabel.h
@@ -274,15 +274,17 @@ struct netlbl_calipso_ops {
  * on success, NULL on failure.
  *
  */
-static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc(gfp_t flags)
+static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc_noprof(gfp_t flags)
 {
 	struct netlbl_lsm_cache *cache;
 
-	cache = kzalloc(sizeof(*cache), flags);
+	cache = kzalloc_noprof(sizeof(*cache), flags);
 	if (cache)
 		refcount_set(&cache->refcount, 1);
 	return cache;
 }
+#define netlbl_secattr_cache_alloc(...)	\
+		alloc_hooks(netlbl_secattr_cache_alloc_noprof(__VA_ARGS__))
 
 /**
  * netlbl_secattr_cache_free - Frees a netlbl_lsm_cache struct
@@ -311,10 +313,11 @@ static inline void netlbl_secattr_cache_free(struct netlbl_lsm_cache *cache)
  * on failure.
  *
  */
-static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc(gfp_t flags)
+static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc_noprof(gfp_t flags)
 {
-	return kzalloc(sizeof(struct netlbl_lsm_catmap), flags);
+	return kzalloc_noprof(sizeof(struct netlbl_lsm_catmap), flags);
 }
+#define netlbl_catmap_alloc(...)	alloc_hooks(netlbl_catmap_alloc_noprof(__VA_ARGS__))
 
 /**
  * netlbl_catmap_free - Free a LSM secattr catmap
@@ -376,10 +379,11 @@ static inline void netlbl_secattr_destroy(struct netlbl_lsm_secattr *secattr)
  * pointer on success, or NULL on failure.
  *
  */
-static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc(gfp_t flags)
+static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc_noprof(gfp_t flags)
 {
-	return kzalloc(sizeof(struct netlbl_lsm_secattr), flags);
+	return kzalloc_noprof(sizeof(struct netlbl_lsm_secattr), flags);
 }
+#define netlbl_secattr_alloc(...)	alloc_hooks(netlbl_secattr_alloc_noprof(__VA_ARGS__))
 
 /**
  * netlbl_secattr_free - Frees a netlbl_lsm_secattr struct
diff --git a/include/net/netlink.h b/include/net/netlink.h
index c19ff921b661..972b5484fa6f 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1891,10 +1891,11 @@ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla)
  * @src: netlink attribute to duplicate from
  * @gfp: GFP mask
  */
-static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp)
+static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp)
 {
-	return kmemdup(nla_data(src), nla_len(src), gfp);
+	return kmemdup_noprof(nla_data(src), nla_len(src), gfp);
 }
+#define nla_memdup(...)	alloc_hooks(nla_memdup_noprof(__VA_ARGS__))
 
 /**
  * nla_nest_start_noflag - Start a new level of nested attributes
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 004e651e6067..29495c331d20 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -127,12 +127,12 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb,
 }
 
 static inline struct request_sock *
-reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
+reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener,
 	    bool attach_listener)
 {
 	struct request_sock *req;
 
-	req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
+	req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
 	if (!req)
 		return NULL;
 	req->rsk_listener = NULL;
@@ -157,6 +157,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
 
 	return req;
 }
+#define reqsk_alloc(...)	alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__))
 
 static inline void __reqsk_free(struct request_sock *req)
 {
diff --git a/include/net/tcx.h b/include/net/tcx.h
index 04be9377785d..72a3e75e539f 100644
--- a/include/net/tcx.h
+++ b/include/net/tcx.h
@@ -75,9 +75,9 @@ tcx_entry_fetch(struct net_device *dev, bool ingress)
 		return rcu_dereference_rtnl(dev->tcx_egress);
 }
 
-static inline struct bpf_mprog_entry *tcx_entry_create(void)
+static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void)
 {
-	struct tcx_entry *tcx = kzalloc(sizeof(*tcx), GFP_KERNEL);
+	struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL);
 
 	if (tcx) {
 		bpf_mprog_bundle_init(&tcx->bundle);
@@ -85,6 +85,7 @@ static inline struct bpf_mprog_entry *tcx_entry_create(void)
 	}
 	return NULL;
 }
+#define tcx_entry_create(...)	alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__))
 
 static inline void tcx_entry_free(struct bpf_mprog_entry *entry)
 {
diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h
index c53b329092d4..4ebc1b7043d9 100644
--- a/net/sunrpc/auth_gss/auth_gss_internal.h
+++ b/net/sunrpc/auth_gss/auth_gss_internal.h
@@ -23,7 +23,7 @@ simple_get_bytes(const void *p, const void *end, void *res, size_t len)
 }
 
 static inline const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
+simple_get_netobj_noprof(const void *p, const void *end, struct xdr_netobj *dest)
 {
 	const void *q;
 	unsigned int len;
@@ -35,7 +35,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
 	if (unlikely(q > end || q < p))
 		return ERR_PTR(-EFAULT);
 	if (len) {
-		dest->data = kmemdup(p, len, GFP_KERNEL);
+		dest->data = kmemdup_noprof(p, len, GFP_KERNEL);
 		if (unlikely(dest->data == NULL))
 			return ERR_PTR(-ENOMEM);
 	} else
@@ -43,3 +43,5 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
 	dest->len = len;
 	return q;
 }
+
+#define simple_get_netobj(...)	alloc_hooks(simple_get_netobj_noprof(__VA_ARGS__))
-- 
cgit v1.2.3