Merge branch 'bpf: misc performance improvements for cgroup'

Stanislav Fomichev says:

====================

First patch adds custom getsockopt for TCP_ZEROCOPY_RECEIVE
to remove kmalloc and lock_sock overhead from the dat path.

Second patch removes kzalloc/kfree from getsockopt for the common cases.

Third patch switches cgroup_bpf_enabled to be per-attach to
to add only overhead for the cgroup attach types used on the system.

No visible user-side changes.

v9:
- include linux/tcp.h instead of netinet/tcp.h in sockopt_sk.c
- note that v9 depends on the commit 4be34f3d ("bpf: Don't leak
  memory in bpf getsockopt when optlen == 0") from bpf tree

v8:
- add bpi.h to tools/include/uapi in the same patch (Martin KaFai Lau)
- kmalloc instead of kzalloc when exporting buffer (Martin KaFai Lau)
- note that v8 depends on the commit 4be34f3d ("bpf: Don't leak
  memory in bpf getsockopt when optlen == 0") from bpf tree

v7:
- add comment about buffer contents for retval != 0 (Martin KaFai Lau)
- export tcp.h into tools/include/uapi (Martin KaFai Lau)
- note that v7 depends on the commit 4be34f3d ("bpf: Don't leak
  memory in bpf getsockopt when optlen == 0") from bpf tree

v6:
- avoid indirect cost for new bpf_bypass_getsockopt (Eric Dumazet)

v5:
- reorder patches to reduce the churn (Martin KaFai Lau)

v4:
- update performance numbers
- bypass_bpf_getsockopt (Martin KaFai Lau)

v3:
- remove extra newline, add comment about sizeof tcp_zerocopy_receive
  (Martin KaFai Lau)
- add another patch to remove lock_sock overhead from
  TCP_ZEROCOPY_RECEIVE; technically, this makes patch #1 obsolete,
  but I'd still prefer to keep it to help with other socket
  options

v2:
- perf numbers for getsockopt kmalloc reduction (Song Liu)
- (sk) in BPF_CGROUP_PRE_CONNECT_ENABLED (Song Liu)
- 128 -> 64 buffer size, BUILD_BUG_ON (Martin KaFai Lau)
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf-cgroup.h

@@ -23,8 +23,8 @@ struct ctl_table_header;
 
 #ifdef CONFIG_CGROUP_BPF
 
-extern struct static_key_false cgroup_bpf_enabled_key;
-#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
+extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE];
+#define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type])
 
 DECLARE_PER_CPU(struct bpf_cgroup_storage*,
 		bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
@@ -147,6 +147,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 				       int __user *optlen, int max_optlen,
 				       int retval);
 
+int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
+					    int optname, void *optval,
+					    int *optlen, int retval);
+
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
 {
@@ -185,7 +189,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
 	int __ret = 0;							      \
-	if (cgroup_bpf_enabled)						      \
+	if (cgroup_bpf_enabled(BPF_CGROUP_INET_INGRESS))		      \
 		__ret = __cgroup_bpf_run_filter_skb(sk, skb,		      \
 						    BPF_CGROUP_INET_INGRESS); \
 									      \
@@ -195,7 +199,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb)			       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled && sk && sk == skb->sk) {		       \
+	if (cgroup_bpf_enabled(BPF_CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \
 		typeof(sk) __sk = sk_to_full_sk(sk);			       \
 		if (sk_fullsock(__sk))					       \
 			__ret = __cgroup_bpf_run_filter_skb(__sk, skb,	       \
@@ -207,7 +211,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_SK_PROG(sk, type)				       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled) {					       \
+	if (cgroup_bpf_enabled(type)) {					       \
 		__ret = __cgroup_bpf_run_filter_sk(sk, type);		       \
 	}								       \
 	__ret;								       \
@@ -228,7 +232,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type)				       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled)						       \
+	if (cgroup_bpf_enabled(type))					       \
 		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type,     \
 							  NULL);	       \
 	__ret;								       \
@@ -237,7 +241,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx)		       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled)	{					       \
+	if (cgroup_bpf_enabled(type))	{				       \
 		lock_sock(sk);						       \
 		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type,     \
 							  t_ctx);	       \
@@ -252,8 +256,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr)			       \
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL)
 
-#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \
-					    sk->sk_prot->pre_connect)
+#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk)				       \
+	((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) ||		       \
+	  cgroup_bpf_enabled(BPF_CGROUP_INET6_CONNECT)) &&		       \
+	 (sk)->sk_prot->pre_connect)
 
 #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr)			       \
 	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT)
@@ -297,7 +303,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk)			\
 ({									\
 	int __ret = 0;							\
-	if (cgroup_bpf_enabled)						\
+	if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS))			\
 		__ret = __cgroup_bpf_run_filter_sock_ops(sk,		\
 							 sock_ops,	\
 							 BPF_CGROUP_SOCK_OPS); \
@@ -307,7 +313,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops)				       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled && (sock_ops)->sk) {	       \
+	if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS) && (sock_ops)->sk) {       \
 		typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk);	       \
 		if (__sk && sk_fullsock(__sk))				       \
 			__ret = __cgroup_bpf_run_filter_sock_ops(__sk,	       \
@@ -320,7 +326,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access)	      \
 ({									      \
 	int __ret = 0;							      \
-	if (cgroup_bpf_enabled)						      \
+	if (cgroup_bpf_enabled(BPF_CGROUP_DEVICE))			      \
 		__ret = __cgroup_bpf_check_dev_permission(type, major, minor, \
 							  access,	      \
 							  BPF_CGROUP_DEVICE); \
@@ -332,7 +338,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos)  \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled)						       \
+	if (cgroup_bpf_enabled(BPF_CGROUP_SYSCTL))			       \
 		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
 						       buf, count, pos,        \
 						       BPF_CGROUP_SYSCTL);     \
@@ -343,7 +349,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 				       kernel_optval)			       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled)						       \
+	if (cgroup_bpf_enabled(BPF_CGROUP_SETSOCKOPT))			       \
 		__ret = __cgroup_bpf_run_filter_setsockopt(sock, level,	       \
 							   optname, optval,    \
 							   optlen,	       \
@@ -354,7 +360,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen)			       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled)						       \
+	if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT))			       \
 		get_user(__ret, optlen);				       \
 	__ret;								       \
 })
@@ -363,11 +369,24 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 				       max_optlen, retval)		       \
 ({									       \
 	int __ret = retval;						       \
-	if (cgroup_bpf_enabled)						       \
-		__ret = __cgroup_bpf_run_filter_getsockopt(sock, level,	       \
-							   optname, optval,    \
-							   optlen, max_optlen, \
-							   retval);	       \
+	if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT))			       \
+		if (!(sock)->sk_prot->bpf_bypass_getsockopt ||		       \
+		    !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \
+					tcp_bpf_bypass_getsockopt,	       \
+					level, optname))		       \
+			__ret = __cgroup_bpf_run_filter_getsockopt(	       \
+				sock, level, optname, optval, optlen,	       \
+				max_optlen, retval);			       \
+	__ret;								       \
+})
+
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval,      \
+					    optlen, retval)		       \
+({									       \
+	int __ret = retval;						       \
+	if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT))			       \
+		__ret = __cgroup_bpf_run_filter_getsockopt_kern(	       \
+			sock, level, optname, optval, optlen, retval);	       \
 	__ret;								       \
 })
 
@@ -427,7 +446,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 	return 0;
 }
 
-#define cgroup_bpf_enabled (0)
+#define cgroup_bpf_enabled(type) (0)
 #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; })
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
@@ -452,6 +471,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
 				       optlen, max_optlen, retval) ({ retval; })
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \
+					    optlen, retval) ({ retval; })
 #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
 				       kernel_optval) ({ 0; })
 

include/linux/filter.h

@@ -1298,6 +1298,11 @@ struct bpf_sysctl_kern {
 	u64 tmp_reg;
 };
 
+#define BPF_SOCKOPT_KERN_BUF_SIZE	32
+struct bpf_sockopt_buf {
+	u8		data[BPF_SOCKOPT_KERN_BUF_SIZE];
+};
+
 struct bpf_sockopt_kern {
 	struct sock	*sk;
 	u8		*optval;

include/linux/indirect_call_wrapper.h

@@ -60,4 +60,10 @@
 #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__)
 #endif
 
+#if IS_ENABLED(CONFIG_INET)
+#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
+#else
+#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__)
+#endif
+
 #endif

include/net/sock.h

@@ -1174,6 +1174,8 @@ struct proto {
 
 	int			(*backlog_rcv) (struct sock *sk,
 						struct sk_buff *skb);
+	bool			(*bpf_bypass_getsockopt)(int level,
+							 int optname);
 
 	void		(*release_cb)(struct sock *sk);
 

include/net/tcp.h

@@ -403,6 +403,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
+bool tcp_bpf_bypass_getsockopt(int level, int optname);
 int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen);
 void tcp_set_keepalive(struct sock *sk, int val);

kernel/bpf/cgroup.c

@@ -19,7 +19,7 @@
 
 #include "../cgroup/cgroup-internal.h"
 
-DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key);
+DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_BPF_ATTACH_TYPE);
 EXPORT_SYMBOL(cgroup_bpf_enabled_key);
 
 void cgroup_bpf_offline(struct cgroup *cgrp)
@@ -128,7 +128,7 @@ static void cgroup_bpf_release(struct work_struct *work)
 			if (pl->link)
 				bpf_cgroup_link_auto_detach(pl->link);
 			kfree(pl);
-			static_branch_dec(&cgroup_bpf_enabled_key);
+			static_branch_dec(&cgroup_bpf_enabled_key[type]);
 		}
 		old_array = rcu_dereference_protected(
 				cgrp->bpf.effective[type],
@@ -499,7 +499,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	if (old_prog)
 		bpf_prog_put(old_prog);
 	else
-		static_branch_inc(&cgroup_bpf_enabled_key);
+		static_branch_inc(&cgroup_bpf_enabled_key[type]);
 	bpf_cgroup_storages_link(new_storage, cgrp, type);
 	return 0;
 
@@ -698,7 +698,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		cgrp->bpf.flags[type] = 0;
 	if (old_prog)
 		bpf_prog_put(old_prog);
-	static_branch_dec(&cgroup_bpf_enabled_key);
+	static_branch_dec(&cgroup_bpf_enabled_key[type]);
 	return 0;
 
 cleanup:
@@ -1298,7 +1298,8 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
 	return empty;
 }
 
-static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
+static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen,
+			     struct bpf_sockopt_buf *buf)
 {
 	if (unlikely(max_optlen < 0))
 		return -EINVAL;
@@ -1310,6 +1311,15 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 		max_optlen = PAGE_SIZE;
 	}
 
+	if (max_optlen <= sizeof(buf->data)) {
+		/* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE
+		 * bytes avoid the cost of kzalloc.
+		 */
+		ctx->optval = buf->data;
+		ctx->optval_end = ctx->optval + max_optlen;
+		return max_optlen;
+	}
+
 	ctx->optval = kzalloc(max_optlen, GFP_USER);
 	if (!ctx->optval)
 		return -ENOMEM;
@@ -1319,16 +1329,26 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 	return max_optlen;
 }
 
-static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
+static void sockopt_free_buf(struct bpf_sockopt_kern *ctx,
+			     struct bpf_sockopt_buf *buf)
 {
+	if (ctx->optval == buf->data)
+		return;
 	kfree(ctx->optval);
 }
 
+static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx,
+				  struct bpf_sockopt_buf *buf)
+{
+	return ctx->optval != buf->data;
+}
+
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 				       int *optname, char __user *optval,
 				       int *optlen, char **kernel_optval)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_buf buf = {};
 	struct bpf_sockopt_kern ctx = {
 		.sk = sk,
 		.level = *level,
@@ -1340,8 +1360,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	 * attached to the hook so we don't waste time allocating
 	 * memory and locking the socket.
 	 */
-	if (!cgroup_bpf_enabled ||
-	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
+	if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
 		return 0;
 
 	/* Allocate a bit more than the initial user buffer for
@@ -1350,7 +1369,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	 */
 	max_optlen = max_t(int, 16, *optlen);
 
-	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
 	if (max_optlen < 0)
 		return max_optlen;
 
@@ -1390,14 +1409,31 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		 */
 		if (ctx.optlen != 0) {
 			*optlen = ctx.optlen;
+			/* We've used bpf_sockopt_kern->buf as an intermediary
+			 * storage, but the BPF program indicates that we need
+			 * to pass this data to the kernel setsockopt handler.
+			 * No way to export on-stack buf, have to allocate a
+			 * new buffer.
+			 */
+			if (!sockopt_buf_allocated(&ctx, &buf)) {
+				void *p = kmalloc(ctx.optlen, GFP_USER);
+
+				if (!p) {
+					ret = -ENOMEM;
+					goto out;
+				}
+				memcpy(p, ctx.optval, ctx.optlen);
+				*kernel_optval = p;
+			} else {
 				*kernel_optval = ctx.optval;
+			}
 			/* export and don't free sockopt buf */
 			return 0;
 		}
 	}
 
 out:
-	sockopt_free_buf(&ctx);
+	sockopt_free_buf(&ctx, &buf);
 	return ret;
 }
 
@@ -1407,6 +1443,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 				       int retval)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_buf buf = {};
 	struct bpf_sockopt_kern ctx = {
 		.sk = sk,
 		.level = level,
@@ -1419,13 +1456,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	 * attached to the hook so we don't waste time allocating
 	 * memory and locking the socket.
 	 */
-	if (!cgroup_bpf_enabled ||
-	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
+	if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
 		return retval;
 
 	ctx.optlen = max_optlen;
 
-	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
 	if (max_optlen < 0)
 		return max_optlen;
 
@@ -1483,9 +1519,55 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	ret = ctx.retval;
 
 out:
-	sockopt_free_buf(&ctx);
+	sockopt_free_buf(&ctx, &buf);
 	return ret;
 }
+
+int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
+					    int optname, void *optval,
+					    int *optlen, int retval)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_kern ctx = {
+		.sk = sk,
+		.level = level,
+		.optname = optname,
+		.retval = retval,
+		.optlen = *optlen,
+		.optval = optval,
+		.optval_end = optval + *optlen,
+	};
+	int ret;
+
+	/* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy
+	 * user data back into BPF buffer when reval != 0. This is
+	 * done as an optimization to avoid extra copy, assuming
+	 * kernel won't populate the data in case of an error.
+	 * Here we always pass the data and memset() should
+	 * be called if that data shouldn't be "exported".
+	 */
+
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT],
+				 &ctx, BPF_PROG_RUN);
+	if (!ret)
+		return -EPERM;
+
+	if (ctx.optlen > *optlen)
+		return -EFAULT;
+
+	/* BPF programs only allowed to set retval to 0, not some
+	 * arbitrary value.
+	 */
+	if (ctx.retval != 0 && ctx.retval != retval)
+		return -EFAULT;
+
+	/* BPF programs can shrink the buffer, export the modifications.
+	 */
+	if (ctx.optlen != 0)
+		*optlen = ctx.optlen;
+
+	return ctx.retval;
+}
 #endif
 
 static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,

net/ipv4/af_inet.c

@@ -777,18 +777,19 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 			return -ENOTCONN;
 		sin->sin_port = inet->inet_dport;
 		sin->sin_addr.s_addr = inet->inet_daddr;
+		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
+					    BPF_CGROUP_INET4_GETPEERNAME,
+					    NULL);
 	} else {
 		__be32 addr = inet->inet_rcv_saddr;
 		if (!addr)
 			addr = inet->inet_saddr;
 		sin->sin_port = inet->inet_sport;
 		sin->sin_addr.s_addr = addr;
-	}
-	if (cgroup_bpf_enabled)
 		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
-					    peer ? BPF_CGROUP_INET4_GETPEERNAME :
 					    BPF_CGROUP_INET4_GETSOCKNAME,
 					    NULL);
+	}
 	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 	return sizeof(*sin);
 }

net/ipv4/tcp.c

@@ -4099,6 +4099,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		lock_sock(sk);
 		err = tcp_zerocopy_receive(sk, &zc);
+		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
+							  &zc, &len, err);
 		release_sock(sk);
 		if (len >= offsetofend(struct tcp_zerocopy_receive, err))
 			goto zerocopy_rcv_sk_err;
@@ -4133,6 +4135,18 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	return 0;
 }
 
+bool tcp_bpf_bypass_getsockopt(int level, int optname)
+{
+	/* TCP do_tcp_getsockopt has optimized getsockopt implementation
+	 * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE.
+	 */
+	if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt);
+
 int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 		   int __user *optlen)
 {

net/ipv4/tcp_ipv4.c

@@ -2793,6 +2793,7 @@ struct proto tcp_prot = {
 	.shutdown		= tcp_shutdown,
 	.setsockopt		= tcp_setsockopt,
 	.getsockopt		= tcp_getsockopt,
+	.bpf_bypass_getsockopt	= tcp_bpf_bypass_getsockopt,
 	.keepalive		= tcp_set_keepalive,
 	.recvmsg		= tcp_recvmsg,
 	.sendmsg		= tcp_sendmsg,

net/ipv4/udp.c

@@ -1124,7 +1124,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		rcu_read_unlock();
 	}
 
-	if (cgroup_bpf_enabled && !connected) {
+	if (cgroup_bpf_enabled(BPF_CGROUP_UDP4_SENDMSG) && !connected) {
 		err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk,
 					    (struct sockaddr *)usin, &ipc.addr);
 		if (err)
@@ -1858,7 +1858,6 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 		*addr_len = sizeof(*sin);
 
-		if (cgroup_bpf_enabled)
 		BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk,
 						      (struct sockaddr *)sin);
 	}

net/ipv6/af_inet6.c

@@ -527,18 +527,19 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		sin->sin6_addr = sk->sk_v6_daddr;
 		if (np->sndflow)
 			sin->sin6_flowinfo = np->flow_label;
+		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
+					    BPF_CGROUP_INET6_GETPEERNAME,
+					    NULL);
 	} else {
 		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
 			sin->sin6_addr = np->saddr;
 		else
 			sin->sin6_addr = sk->sk_v6_rcv_saddr;
 		sin->sin6_port = inet->inet_sport;
-	}
-	if (cgroup_bpf_enabled)
 		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
-					    peer ? BPF_CGROUP_INET6_GETPEERNAME :
 					    BPF_CGROUP_INET6_GETSOCKNAME,
 					    NULL);
+	}
 	sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr,
 						 sk->sk_bound_dev_if);
 	return sizeof(*sin);

net/ipv6/tcp_ipv6.c

@@ -2121,6 +2121,7 @@ struct proto tcpv6_prot = {
 	.shutdown		= tcp_shutdown,
 	.setsockopt		= tcp_setsockopt,
 	.getsockopt		= tcp_getsockopt,
+	.bpf_bypass_getsockopt	= tcp_bpf_bypass_getsockopt,
 	.keepalive		= tcp_set_keepalive,
 	.recvmsg		= tcp_recvmsg,
 	.sendmsg		= tcp_sendmsg,

net/ipv6/udp.c

@@ -409,7 +409,6 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 		*addr_len = sizeof(*sin6);
 
-		if (cgroup_bpf_enabled)
 		BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk,
 						      (struct sockaddr *)sin6);
 	}
@@ -1462,7 +1461,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.saddr = np->saddr;
 	fl6.fl6_sport = inet->inet_sport;
 
-	if (cgroup_bpf_enabled && !connected) {
+	if (cgroup_bpf_enabled(BPF_CGROUP_UDP6_SENDMSG) && !connected) {
 		err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,
 					   (struct sockaddr *)sin6, &fl6.saddr);
 		if (err)

net/socket.c

@@ -2126,6 +2126,9 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
 	return __sys_setsockopt(fd, level, optname, optval, optlen);
 }
 
+INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level,
+							 int optname));
+
 /*
  *	Get a socket option. Because we don't know the option lengths we have
  *	to pass a user mode parameter for the protocols to sort out.

tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c

@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 
 #include <linux/err.h>
+#include <netinet/tcp.h>
 #include <test_progs.h>
 #include "bpf_dctcp.skel.h"
 #include "bpf_cubic.skel.h"

tools/testing/selftests/bpf/prog_tests/cls_redirect.c

@@ -7,6 +7,7 @@
 #include <string.h>
 
 #include <linux/pkt_cls.h>
+#include <netinet/tcp.h>
 
 #include <test_progs.h>
 

tools/testing/selftests/bpf/prog_tests/sockmap_basic.c

 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Cloudflare
 #include <error.h>
+#include <netinet/tcp.h>
 
 #include "test_progs.h"
 #include "test_skmsg_load_helpers.skel.h"

tools/testing/selftests/bpf/prog_tests/sockopt_sk.c

@@ -2,6 +2,12 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 
+#include <linux/tcp.h>
+
+#ifndef SOL_TCP
+#define SOL_TCP IPPROTO_TCP
+#endif
+
 #define SOL_CUSTOM			0xdeadbeef
 
 static int getsetsockopt(void)
@@ -11,6 +17,7 @@ static int getsetsockopt(void)
 		char u8[4];
 		__u32 u32;
 		char cc[16]; /* TCP_CA_NAME_MAX */
+		struct tcp_zerocopy_receive zc;
 	} buf = {};
 	socklen_t optlen;
 	char *big_buf = NULL;
@@ -154,6 +161,27 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
+	/* TCP_ZEROCOPY_RECEIVE triggers */
+	memset(&buf, 0, sizeof(buf));
+	optlen = sizeof(buf.zc);
+	err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen);
+	if (err) {
+		log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d",
+			err, errno);
+		goto err;
+	}
+
+	memset(&buf, 0, sizeof(buf));
+	buf.zc.address = 12345; /* rejected by BPF */
+	optlen = sizeof(buf.zc);
+	errno = 0;
+	err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen);
+	if (errno != EPERM) {
+		log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d",
+			err, errno);
+		goto err;
+	}
+
 	free(big_buf);
 	close(fd);
 	return 0;

tools/testing/selftests/bpf/progs/sockopt_sk.c

 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
-#include <netinet/in.h>
-#include <netinet/tcp.h>
+#include <linux/tcp.h>
 #include <linux/bpf.h>
+#include <netinet/in.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
@@ -12,6 +12,10 @@ __u32 _version SEC("version") = 1;
 #define PAGE_SIZE 4096
 #endif
 
+#ifndef SOL_TCP
+#define SOL_TCP IPPROTO_TCP
+#endif
+
 #define SOL_CUSTOM			0xdeadbeef
 
 struct sockopt_sk {
@@ -57,6 +61,21 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		return 1;
 	}
 
+	if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) {
+		/* Verify that TCP_ZEROCOPY_RECEIVE triggers.
+		 * It has a custom implementation for performance
+		 * reasons.
+		 */
+
+		if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		if (((struct tcp_zerocopy_receive *)optval)->address != 0)
+			return 0; /* EPERM, unexpected data */
+
+		return 1;
+	}
+
 	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
 		if (optval + 1 > optval_end)
 			return 0; /* EPERM, bounds check */

tools/testing/selftests/bpf/test_progs.h

@@ -16,7 +16,6 @@ typedef __u16 __sum16;
 #include <linux/if_packet.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include <netinet/tcp.h>
 #include <linux/filter.h>
 #include <linux/perf_event.h>
 #include <linux/socket.h>