Merge branch 'bpf-sockopt-hooks'

Stanislav Fomichev says:

====================
This series implements two new per-cgroup hooks: getsockopt and
setsockopt along with a new sockopt program type. The idea is pretty
similar to recently introduced cgroup sysctl hooks, but
implementation is simpler (no need to convert to/from strings).

What this can be applied to:
* move business logic of what tos/priority/etc can be set by
  containers (either pass or reject)
* handle existing options (or introduce new ones) differently by
  propagating some information in cgroup/socket local storage

Compared to a simple syscall/{g,s}etsockopt tracepoint, those
hooks are context aware. Meaning, they can access underlying socket
and use cgroup and socket local storage.

v9:
* allow overwriting setsocktop arguments (Alexei Starovoitov)
  (see individual changes for more changelog details)
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Documentation/bpf/index.rst

@@ -42,6 +42,7 @@ Program types
 .. toctree::
    :maxdepth: 1
 
+   prog_cgroup_sockopt
    prog_cgroup_sysctl
    prog_flow_dissector
 

Documentation/bpf/prog_cgroup_sockopt.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+BPF_PROG_TYPE_CGROUP_SOCKOPT
+============================
+
+``BPF_PROG_TYPE_CGROUP_SOCKOPT`` program type can be attached to two
+cgroup hooks:
+
+* ``BPF_CGROUP_GETSOCKOPT`` - called every time process executes ``getsockopt``
+  system call.
+* ``BPF_CGROUP_SETSOCKOPT`` - called every time process executes ``setsockopt``
+  system call.
+
+The context (``struct bpf_sockopt``) has associated socket (``sk``) and
+all input arguments: ``level``, ``optname``, ``optval`` and ``optlen``.
+
+BPF_CGROUP_SETSOCKOPT
+=====================
+
+``BPF_CGROUP_SETSOCKOPT`` is triggered *before* the kernel handling of
+sockopt and it has writable context: it can modify the supplied arguments
+before passing them down to the kernel. This hook has access to the cgroup
+and socket local storage.
+
+If BPF program sets ``optlen`` to -1, the control will be returned
+back to the userspace after all other BPF programs in the cgroup
+chain finish (i.e. kernel ``setsockopt`` handling will *not* be executed).
+
+Note, that ``optlen`` can not be increased beyond the user-supplied
+value. It can only be decreased or set to -1. Any other value will
+trigger ``EFAULT``.
+
+Return Type
+-----------
+
+* ``0`` - reject the syscall, ``EPERM`` will be returned to the userspace.
+* ``1`` - success, continue with next BPF program in the cgroup chain.
+
+BPF_CGROUP_GETSOCKOPT
+=====================
+
+``BPF_CGROUP_GETSOCKOPT`` is triggered *after* the kernel handing of
+sockopt. The BPF hook can observe ``optval``, ``optlen`` and ``retval``
+if it's interested in whatever kernel has returned. BPF hook can override
+the values above, adjust ``optlen`` and reset ``retval`` to 0. If ``optlen``
+has been increased above initial ``getsockopt`` value (i.e. userspace
+buffer is too small), ``EFAULT`` is returned.
+
+This hook has access to the cgroup and socket local storage.
+
+Note, that the only acceptable value to set to ``retval`` is 0 and the
+original value that the kernel returned. Any other value will trigger
+``EFAULT``.
+
+Return Type
+-----------
+
+* ``0`` - reject the syscall, ``EPERM`` will be returned to the userspace.
+* ``1`` - success: copy ``optval`` and ``optlen`` to userspace, return
+  ``retval`` from the syscall (note that this can be overwritten by
+  the BPF program from the parent cgroup).
+
+Cgroup Inheritance
+==================
+
+Suppose, there is the following cgroup hierarchy where each cgroup
+has ``BPF_CGROUP_GETSOCKOPT`` attached at each level with
+``BPF_F_ALLOW_MULTI`` flag::
+
+  A (root, parent)
+   \
+    B (child)
+
+When the application calls ``getsockopt`` syscall from the cgroup B,
+the programs are executed from the bottom up: B, A. First program
+(B) sees the result of kernel's ``getsockopt``. It can optionally
+adjust ``optval``, ``optlen`` and reset ``retval`` to 0. After that
+control will be passed to the second (A) program which will see the
+same context as B including any potential modifications.
+
+Same for ``BPF_CGROUP_SETSOCKOPT``: if the program is attached to
+A and B, the trigger order is B, then A. If B does any changes
+to the input arguments (``level``, ``optname``, ``optval``, ``optlen``),
+then the next program in the chain (A) will see those changes,
+*not* the original input ``setsockopt`` arguments. The potentially
+modified values will be then passed down to the kernel.
+
+Example
+=======
+
+See ``tools/testing/selftests/bpf/progs/sockopt_sk.c`` for an example
+of BPF program that handles socket options.

include/linux/bpf-cgroup.h

@@ -124,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   loff_t *ppos, void **new_buf,
 				   enum bpf_attach_type type);
 
+int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
+				       int *optname, char __user *optval,
+				       int *optlen, char **kernel_optval);
+int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
+				       int optname, char __user *optval,
+				       int __user *optlen, int max_optlen,
+				       int retval);
+
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
 {
@@ -286,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 	__ret;								       \
 })
 
+#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen,   \
+				       kernel_optval)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_setsockopt(sock, level,	       \
+							   optname, optval,    \
+							   optlen,	       \
+							   kernel_optval);     \
+	__ret;								       \
+})
+
+#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)						       \
+		get_user(__ret, optlen);				       \
+	__ret;								       \
+})
+
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen,   \
+				       max_optlen, retval)		       \
+({									       \
+	int __ret = retval;						       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_getsockopt(sock, level,	       \
+							   optname, optval,    \
+							   optlen, max_optlen, \
+							   retval);	       \
+	__ret;								       \
+})
+
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog);
 int cgroup_bpf_prog_detach(const union bpf_attr *attr,
@@ -357,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
+#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_SETSOCKOPT(sock, level, optname, optval, optlen, \
+				       kernel_optval) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 

include/linux/bpf.h

@@ -518,6 +518,7 @@ struct bpf_prog_array {
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
 void bpf_prog_array_free(struct bpf_prog_array *progs);
 int bpf_prog_array_length(struct bpf_prog_array *progs);
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
 int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
 				__u32 __user *prog_ids, u32 cnt);
 
@@ -1051,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto;
 extern const struct bpf_func_proto bpf_get_local_storage_proto;
 extern const struct bpf_func_proto bpf_strtol_proto;
 extern const struct bpf_func_proto bpf_strtoul_proto;
+extern const struct bpf_func_proto bpf_tcp_sock_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);

include/linux/bpf_types.h

@@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt)
 #endif
 #ifdef CONFIG_BPF_LIRC_MODE2
 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)

include/linux/filter.h

@@ -1199,4 +1199,14 @@ struct bpf_sysctl_kern {
 	u64 tmp_reg;
 };
 
+struct bpf_sockopt_kern {
+	struct sock	*sk;
+	u8		*optval;
+	u8		*optval_end;
+	s32		level;
+	s32		optname;
+	s32		optlen;
+	s32		retval;
+};
+
 #endif /* __LINUX_FILTER_H__ */

include/uapi/linux/bpf.h

@@ -170,6 +170,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
 	BPF_PROG_TYPE_CGROUP_SYSCTL,
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 };
 
 enum bpf_attach_type {
@@ -194,6 +195,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_SYSCTL,
 	BPF_CGROUP_UDP4_RECVMSG,
 	BPF_CGROUP_UDP6_RECVMSG,
+	BPF_CGROUP_GETSOCKOPT,
+	BPF_CGROUP_SETSOCKOPT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3541,4 +3544,15 @@ struct bpf_sysctl {
 				 */
 };
 
+struct bpf_sockopt {
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(void *, optval);
+	__bpf_md_ptr(void *, optval_end);
+
+	__s32	level;
+	__s32	optname;
+	__s32	optlen;
+	__s32	retval;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

kernel/bpf/cgroup.c

@@ -15,6 +15,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf-cgroup.h>
 #include <net/sock.h>
+#include <net/bpf_sk_storage.h>
 
 #include "../cgroup/cgroup-internal.h"
 
@@ -938,6 +939,188 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
 
+static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
+					     enum bpf_attach_type attach_type)
+{
+	struct bpf_prog_array *prog_array;
+	bool empty;
+
+	rcu_read_lock();
+	prog_array = rcu_dereference(cgrp->bpf.effective[attach_type]);
+	empty = bpf_prog_array_is_empty(prog_array);
+	rcu_read_unlock();
+
+	return empty;
+}
+
+static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
+{
+	if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0)
+		return -EINVAL;
+
+	ctx->optval = kzalloc(max_optlen, GFP_USER);
+	if (!ctx->optval)
+		return -ENOMEM;
+
+	ctx->optval_end = ctx->optval + max_optlen;
+	ctx->optlen = max_optlen;
+
+	return 0;
+}
+
+static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
+{
+	kfree(ctx->optval);
+}
+
+int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
+				       int *optname, char __user *optval,
+				       int *optlen, char **kernel_optval)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_kern ctx = {
+		.sk = sk,
+		.level = *level,
+		.optname = *optname,
+	};
+	int ret;
+
+	/* Opportunistic check to see whether we have any BPF program
+	 * attached to the hook so we don't waste time allocating
+	 * memory and locking the socket.
+	 */
+	if (!cgroup_bpf_enabled ||
+	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
+		return 0;
+
+	ret = sockopt_alloc_buf(&ctx, *optlen);
+	if (ret)
+		return ret;
+
+	if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	lock_sock(sk);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT],
+				 &ctx, BPF_PROG_RUN);
+	release_sock(sk);
+
+	if (!ret) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	if (ctx.optlen == -1) {
+		/* optlen set to -1, bypass kernel */
+		ret = 1;
+	} else if (ctx.optlen > *optlen || ctx.optlen < -1) {
+		/* optlen is out of bounds */
+		ret = -EFAULT;
+	} else {
+		/* optlen within bounds, run kernel handler */
+		ret = 0;
+
+		/* export any potential modifications */
+		*level = ctx.level;
+		*optname = ctx.optname;
+		*optlen = ctx.optlen;
+		*kernel_optval = ctx.optval;
+	}
+
+out:
+	if (ret)
+		sockopt_free_buf(&ctx);
+	return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_setsockopt);
+
+int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
+				       int optname, char __user *optval,
+				       int __user *optlen, int max_optlen,
+				       int retval)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_kern ctx = {
+		.sk = sk,
+		.level = level,
+		.optname = optname,
+		.retval = retval,
+	};
+	int ret;
+
+	/* Opportunistic check to see whether we have any BPF program
+	 * attached to the hook so we don't waste time allocating
+	 * memory and locking the socket.
+	 */
+	if (!cgroup_bpf_enabled ||
+	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
+		return retval;
+
+	ret = sockopt_alloc_buf(&ctx, max_optlen);
+	if (ret)
+		return ret;
+
+	if (!retval) {
+		/* If kernel getsockopt finished successfully,
+		 * copy whatever was returned to the user back
+		 * into our temporary buffer. Set optlen to the
+		 * one that kernel returned as well to let
+		 * BPF programs inspect the value.
+		 */
+
+		if (get_user(ctx.optlen, optlen)) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		if (ctx.optlen > max_optlen)
+			ctx.optlen = max_optlen;
+
+		if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
+			ret = -EFAULT;
+			goto out;
+		}
+	}
+
+	lock_sock(sk);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT],
+				 &ctx, BPF_PROG_RUN);
+	release_sock(sk);
+
+	if (!ret) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	if (ctx.optlen > max_optlen) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	/* BPF programs only allowed to set retval to 0, not some
+	 * arbitrary value.
+	 */
+	if (ctx.retval != 0 && ctx.retval != retval) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
+	    put_user(ctx.optlen, optlen)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = ctx.retval;
+
+out:
+	sockopt_free_buf(&ctx);
+	return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
+
 static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
 			      size_t *lenp)
 {
@@ -1198,3 +1381,153 @@ const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
 
 const struct bpf_prog_ops cg_sysctl_prog_ops = {
 };
+
+static const struct bpf_func_proto *
+cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
+#ifdef CONFIG_INET
+	case BPF_FUNC_tcp_sock:
+		return &bpf_tcp_sock_proto;
+#endif
+	default:
+		return cgroup_base_func_proto(func_id, prog);
+	}
+}
+
+static bool cg_sockopt_is_valid_access(int off, int size,
+				       enum bpf_access_type type,
+				       const struct bpf_prog *prog,
+				       struct bpf_insn_access_aux *info)
+{
+	const int size_default = sizeof(__u32);
+
+	if (off < 0 || off >= sizeof(struct bpf_sockopt))
+		return false;
+
+	if (off % size != 0)
+		return false;
+
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case offsetof(struct bpf_sockopt, retval):
+			if (size != size_default)
+				return false;
+			return prog->expected_attach_type ==
+				BPF_CGROUP_GETSOCKOPT;
+		case offsetof(struct bpf_sockopt, optname):
+			/* fallthrough */
+		case offsetof(struct bpf_sockopt, level):
+			if (size != size_default)
+				return false;
+			return prog->expected_attach_type ==
+				BPF_CGROUP_SETSOCKOPT;
+		case offsetof(struct bpf_sockopt, optlen):
+			return size == size_default;
+		default:
+			return false;
+		}
+	}
+
+	switch (off) {
+	case offsetof(struct bpf_sockopt, sk):
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_SOCKET;
+		break;
+	case offsetof(struct bpf_sockopt, optval):
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_PACKET;
+		break;
+	case offsetof(struct bpf_sockopt, optval_end):
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_PACKET_END;
+		break;
+	case offsetof(struct bpf_sockopt, retval):
+		if (size != size_default)
+			return false;
+		return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT;
+	default:
+		if (size != size_default)
+			return false;
+		break;
+	}
+	return true;
+}
+
+#define CG_SOCKOPT_ACCESS_FIELD(T, F)					\
+	T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F),			\
+	  si->dst_reg, si->src_reg,					\
+	  offsetof(struct bpf_sockopt_kern, F))
+
+static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type,
+					 const struct bpf_insn *si,
+					 struct bpf_insn *insn_buf,
+					 struct bpf_prog *prog,
+					 u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct bpf_sockopt, sk):
+		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk);
+		break;
+	case offsetof(struct bpf_sockopt, level):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level);
+		break;
+	case offsetof(struct bpf_sockopt, optname):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname);
+		break;
+	case offsetof(struct bpf_sockopt, optlen):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen);
+		break;
+	case offsetof(struct bpf_sockopt, retval):
+		if (type == BPF_WRITE)
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval);
+		else
+			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval);
+		break;
+	case offsetof(struct bpf_sockopt, optval):
+		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval);
+		break;
+	case offsetof(struct bpf_sockopt, optval_end):
+		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end);
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf,
+				   bool direct_write,
+				   const struct bpf_prog *prog)
+{
+	/* Nothing to do for sockopt argument. The data is kzalloc'ated.
+	 */
+	return 0;
+}
+
+const struct bpf_verifier_ops cg_sockopt_verifier_ops = {
+	.get_func_proto		= cg_sockopt_func_proto,
+	.is_valid_access	= cg_sockopt_is_valid_access,
+	.convert_ctx_access	= cg_sockopt_convert_ctx_access,
+	.gen_prologue		= cg_sockopt_get_prologue,
+};
+
+const struct bpf_prog_ops cg_sockopt_prog_ops = {
+};

kernel/bpf/core.c

@@ -1809,6 +1809,15 @@ int bpf_prog_array_length(struct bpf_prog_array *array)
 	return cnt;
 }
 
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array)
+{
+	struct bpf_prog_array_item *item;
+
+	for (item = array->items; item->prog; item++)
+		if (item->prog != &dummy_bpf_prog.prog)
+			return false;
+	return true;
+}
 
 static bool bpf_prog_array_copy_core(struct bpf_prog_array *array,
 				     u32 *prog_ids,

kernel/bpf/syscall.c

@@ -1590,6 +1590,14 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+		switch (expected_attach_type) {
+		case BPF_CGROUP_SETSOCKOPT:
+		case BPF_CGROUP_GETSOCKOPT:
+			return 0;
+		default:
+			return -EINVAL;
+		}
 	default:
 		return 0;
 	}
@@ -1840,6 +1848,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	switch (prog->type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		return prog->enforce_expected_attach_type &&
@@ -1912,6 +1921,10 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_CGROUP_SYSCTL:
 		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
 		break;
+	case BPF_CGROUP_GETSOCKOPT:
+	case BPF_CGROUP_SETSOCKOPT:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1995,6 +2008,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_CGROUP_SYSCTL:
 		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
 		break;
+	case BPF_CGROUP_GETSOCKOPT:
+	case BPF_CGROUP_SETSOCKOPT:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -2031,6 +2048,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_SOCK_OPS:
 	case BPF_CGROUP_DEVICE:
 	case BPF_CGROUP_SYSCTL:
+	case BPF_CGROUP_GETSOCKOPT:
+	case BPF_CGROUP_SETSOCKOPT:
 		break;
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);

kernel/bpf/verifier.c

@@ -2215,6 +2215,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 
 		env->seen_direct_write = true;
 		return true;
+
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+		if (t == BPF_WRITE)
+			env->seen_direct_write = true;
+
+		return true;
+
 	default:
 		return false;
 	}
@@ -6066,6 +6073,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 	case BPF_PROG_TYPE_SOCK_OPS:
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		break;
 	default:
 		return 0;

net/core/filter.c

@@ -5651,7 +5651,7 @@ BPF_CALL_1(bpf_tcp_sock, struct sock *, sk)
 	return (unsigned long)NULL;
 }
 
-static const struct bpf_func_proto bpf_tcp_sock_proto = {
+const struct bpf_func_proto bpf_tcp_sock_proto = {
 	.func		= bpf_tcp_sock,
 	.gpl_only	= false,
 	.ret_type	= RET_PTR_TO_TCP_SOCK_OR_NULL,

net/socket.c

@@ -2051,6 +2051,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
 static int __sys_setsockopt(int fd, int level, int optname,
 			    char __user *optval, int optlen)
 {
+	mm_segment_t oldfs = get_fs();
+	char *kernel_optval = NULL;
 	int err, fput_needed;
 	struct socket *sock;
 
@@ -2063,6 +2065,22 @@ static int __sys_setsockopt(int fd, int level, int optname,
 		if (err)
 			goto out_put;
 
+		err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level,
+						     &optname, optval, &optlen,
+						     &kernel_optval);
+
+		if (err < 0) {
+			goto out_put;
+		} else if (err > 0) {
+			err = 0;
+			goto out_put;
+		}
+
+		if (kernel_optval) {
+			set_fs(KERNEL_DS);
+			optval = (char __user __force *)kernel_optval;
+		}
+
 		if (level == SOL_SOCKET)
 			err =
 			    sock_setsockopt(sock, level, optname, optval,
@@ -2071,6 +2089,11 @@ static int __sys_setsockopt(int fd, int level, int optname,
 			err =
 			    sock->ops->setsockopt(sock, level, optname, optval,
 						  optlen);
+
+		if (kernel_optval) {
+			set_fs(oldfs);
+			kfree(kernel_optval);
+		}
 out_put:
 		fput_light(sock->file, fput_needed);
 	}
@@ -2093,6 +2116,7 @@ static int __sys_getsockopt(int fd, int level, int optname,
 {
 	int err, fput_needed;
 	struct socket *sock;
+	int max_optlen;
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock != NULL) {
@@ -2100,6 +2124,8 @@ static int __sys_getsockopt(int fd, int level, int optname,
 		if (err)
 			goto out_put;
 
+		max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
+
 		if (level == SOL_SOCKET)
 			err =
 			    sock_getsockopt(sock, level, optname, optval,
@@ -2108,6 +2134,10 @@ static int __sys_getsockopt(int fd, int level, int optname,
 			err =
 			    sock->ops->getsockopt(sock, level, optname, optval,
 						  optlen);
+
+		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
+						     optval, optlen,
+						     max_optlen, err);
 out_put:
 		fput_light(sock->file, fput_needed);
 	}

tools/bpf/bpftool/Documentation/bpftool-cgroup.rst

@@ -29,7 +29,8 @@ CGROUP COMMANDS
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
 |	*ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** |
 |		**bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** |
-|		**sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** }
+|		**sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** |
+|		**getsockopt** | **setsockopt** }
 |	*ATTACH_FLAGS* := { **multi** | **override** }
 
 DESCRIPTION
@@ -90,7 +91,9 @@ DESCRIPTION
                   an unconnected udp4 socket (since 5.2);
 		  **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
                   an unconnected udp6 socket (since 5.2);
-		  **sysctl** sysctl access (since 5.2).
+		  **sysctl** sysctl access (since 5.2);
+		  **getsockopt** call to getsockopt (since 5.3);
+		  **setsockopt** call to setsockopt (since 5.3).
 
 	**bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
 		  Detach *PROG* from the cgroup *CGROUP* and attach type

tools/bpf/bpftool/Documentation/bpftool-prog.rst

@@ -40,7 +40,8 @@ PROG COMMANDS
 |		**lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
 |		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
 |		**cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** |
-|		**cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl**
+|		**cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** |
+|		**cgroup/getsockopt** | **cgroup/setsockopt**
 |	}
 |       *ATTACH_TYPE* := {
 |		**msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector**

tools/bpf/bpftool/bash-completion/bpftool

@@ -379,7 +379,8 @@ _bpftool()
                                 cgroup/sendmsg4 cgroup/sendmsg6 \
                                 cgroup/recvmsg4 cgroup/recvmsg6 \
                                 cgroup/post_bind4 cgroup/post_bind6 \
-                                cgroup/sysctl" -- \
+                                cgroup/sysctl cgroup/getsockopt \
+                                cgroup/setsockopt" -- \
                                                    "$cur" ) )
                             return 0
                             ;;
@@ -689,7 +690,8 @@ _bpftool()
                 attach|detach)
                     local ATTACH_TYPES='ingress egress sock_create sock_ops \
                         device bind4 bind6 post_bind4 post_bind6 connect4 \
-                        connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl'
+                        connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \
+                        getsockopt setsockopt'
                     local ATTACH_FLAGS='multi override'
                     local PROG_TYPE='id pinned tag'
                     case $prev in
@@ -699,7 +701,8 @@ _bpftool()
                             ;;
                         ingress|egress|sock_create|sock_ops|device|bind4|bind6|\
                         post_bind4|post_bind6|connect4|connect6|sendmsg4|\
-                        sendmsg6|recvmsg4|recvmsg6|sysctl)
+                        sendmsg6|recvmsg4|recvmsg6|sysctl|getsockopt|\
+                        setsockopt)
                             COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
                                 "$cur" ) )
                             return 0

tools/bpf/bpftool/cgroup.c

@@ -26,7 +26,8 @@
 	"                        sock_ops | device | bind4 | bind6 |\n"	       \
 	"                        post_bind4 | post_bind6 | connect4 |\n"       \
 	"                        connect6 | sendmsg4 | sendmsg6 |\n"           \
-	"                        recvmsg4 | recvmsg6 | sysctl }"
+	"                        recvmsg4 | recvmsg6 | sysctl |\n"	       \
+	"                        getsockopt | setsockopt }"
 
 static const char * const attach_type_strings[] = {
 	[BPF_CGROUP_INET_INGRESS] = "ingress",
@@ -45,6 +46,8 @@ static const char * const attach_type_strings[] = {
 	[BPF_CGROUP_SYSCTL] = "sysctl",
 	[BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4",
 	[BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6",
+	[BPF_CGROUP_GETSOCKOPT] = "getsockopt",
+	[BPF_CGROUP_SETSOCKOPT] = "setsockopt",
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 

tools/bpf/bpftool/main.h

@@ -74,6 +74,7 @@ static const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_SK_REUSEPORT]		= "sk_reuseport",
 	[BPF_PROG_TYPE_FLOW_DISSECTOR]		= "flow_dissector",
 	[BPF_PROG_TYPE_CGROUP_SYSCTL]		= "cgroup_sysctl",
+	[BPF_PROG_TYPE_CGROUP_SOCKOPT]		= "cgroup_sockopt",
 };
 
 extern const char * const map_type_name[];

tools/bpf/bpftool/prog.c

@@ -1071,7 +1071,8 @@ static int do_help(int argc, char **argv)
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
 		"                 cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n"
-		"                 cgroup/recvmsg6 }\n"
+		"                 cgroup/recvmsg6 | cgroup/getsockopt |\n"
+		"                 cgroup/setsockopt }\n"
 		"       ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
 		"                        flow_dissector }\n"
 		"       " HELP_SPEC_OPTIONS "\n"

tools/include/uapi/linux/bpf.h

@@ -170,6 +170,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
 	BPF_PROG_TYPE_CGROUP_SYSCTL,
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 };
 
 enum bpf_attach_type {
@@ -194,6 +195,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_SYSCTL,
 	BPF_CGROUP_UDP4_RECVMSG,
 	BPF_CGROUP_UDP6_RECVMSG,
+	BPF_CGROUP_GETSOCKOPT,
+	BPF_CGROUP_SETSOCKOPT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3541,4 +3544,15 @@ struct bpf_sysctl {
 				 */
 };
 
+struct bpf_sockopt {
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(void *, optval);
+	__bpf_md_ptr(void *, optval_end);
+
+	__s32	level;
+	__s32	optname;
+	__s32	optlen;
+	__s32	retval;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

tools/lib/bpf/libbpf.c

@@ -2646,6 +2646,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		return false;
 	case BPF_PROG_TYPE_KPROBE:
 	default:
@@ -3604,6 +3605,10 @@ static const struct {
 						BPF_CGROUP_UDP6_RECVMSG),
 	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
 						BPF_CGROUP_SYSCTL),
+	BPF_EAPROG_SEC("cgroup/getsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
+						BPF_CGROUP_GETSOCKOPT),
+	BPF_EAPROG_SEC("cgroup/setsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
+						BPF_CGROUP_SETSOCKOPT),
 };
 
 #undef BPF_PROG_SEC_IMPL

tools/lib/bpf/libbpf_probes.c

@@ -101,6 +101,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	default:
 		break;
 	}

tools/testing/selftests/bpf/.gitignore

@@ -39,3 +39,6 @@ libbpf.so.*
 test_hashmap
 test_btf_dump
 xdping
+test_sockopt
+test_sockopt_sk
+test_sockopt_multi

tools/testing/selftests/bpf/Makefile

@@ -26,7 +26,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage test_select_reuseport test_section_names \
 	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
-	test_btf_dump test_cgroup_attach xdping
+	test_btf_dump test_cgroup_attach xdping test_sockopt test_sockopt_sk \
+	test_sockopt_multi
 
 BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
 TEST_GEN_FILES = $(BPF_OBJ_FILES)
@@ -103,6 +104,9 @@ $(OUTPUT)/test_netcnt: cgroup_helpers.c
 $(OUTPUT)/test_sock_fields: cgroup_helpers.c
 $(OUTPUT)/test_sysctl: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_attach: cgroup_helpers.c
+$(OUTPUT)/test_sockopt: cgroup_helpers.c
+$(OUTPUT)/test_sockopt_sk: cgroup_helpers.c
+$(OUTPUT)/test_sockopt_multi: cgroup_helpers.c
 
 .PHONY: force
 

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

+// SPDX-License-Identifier: GPL-2.0
+#include <netinet/in.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
+
+SEC("cgroup/getsockopt/child")
+int _getsockopt_child(struct bpf_sockopt *ctx)
+{
+	__u8 *optval_end = ctx->optval_end;
+	__u8 *optval = ctx->optval;
+
+	if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
+		return 1;
+
+	if (optval + 1 > optval_end)
+		return 0; /* EPERM, bounds check */
+
+	if (optval[0] != 0x80)
+		return 0; /* EPERM, unexpected optval from the kernel */
+
+	ctx->retval = 0; /* Reset system call return value to zero */
+
+	optval[0] = 0x90;
+	ctx->optlen = 1;
+
+	return 1;
+}
+
+SEC("cgroup/getsockopt/parent")
+int _getsockopt_parent(struct bpf_sockopt *ctx)
+{
+	__u8 *optval_end = ctx->optval_end;
+	__u8 *optval = ctx->optval;
+
+	if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
+		return 1;
+
+	if (optval + 1 > optval_end)
+		return 0; /* EPERM, bounds check */
+
+	if (optval[0] != 0x90)
+		return 0; /* EPERM, unexpected optval from the kernel */
+
+	ctx->retval = 0; /* Reset system call return value to zero */
+
+	optval[0] = 0xA0;
+	ctx->optlen = 1;
+
+	return 1;
+}
+
+SEC("cgroup/setsockopt")
+int _setsockopt(struct bpf_sockopt *ctx)
+{
+	__u8 *optval_end = ctx->optval_end;
+	__u8 *optval = ctx->optval;
+
+	if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
+		return 1;
+
+	if (optval + 1 > optval_end)
+		return 0; /* EPERM, bounds check */
+
+	optval[0] += 0x10;
+	ctx->optlen = 1;
+
+	return 1;
+}

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

+// SPDX-License-Identifier: GPL-2.0
+#include <netinet/in.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
+
+#define SOL_CUSTOM			0xdeadbeef
+
+struct sockopt_sk {
+	__u8 val;
+};
+
+struct bpf_map_def SEC("maps") socket_storage_map = {
+	.type = BPF_MAP_TYPE_SK_STORAGE,
+	.key_size = sizeof(int),
+	.value_size = sizeof(struct sockopt_sk),
+	.map_flags = BPF_F_NO_PREALLOC,
+};
+BPF_ANNOTATE_KV_PAIR(socket_storage_map, int, struct sockopt_sk);
+
+SEC("cgroup/getsockopt")
+int _getsockopt(struct bpf_sockopt *ctx)
+{
+	__u8 *optval_end = ctx->optval_end;
+	__u8 *optval = ctx->optval;
+	struct sockopt_sk *storage;
+
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+		/* Not interested in SOL_IP:IP_TOS;
+		 * let next BPF program in the cgroup chain or kernel
+		 * handle it.
+		 */
+		return 1;
+
+	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
+		/* Not interested in SOL_SOCKET:SO_SNDBUF;
+		 * let next BPF program in the cgroup chain or kernel
+		 * handle it.
+		 */
+		return 1;
+	}
+
+	if (ctx->level != SOL_CUSTOM)
+		return 0; /* EPERM, deny everything except custom level */
+
+	if (optval + 1 > optval_end)
+		return 0; /* EPERM, bounds check */
+
+	storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0,
+				     BPF_SK_STORAGE_GET_F_CREATE);
+	if (!storage)
+		return 0; /* EPERM, couldn't get sk storage */
+
+	if (!ctx->retval)
+		return 0; /* EPERM, kernel should not have handled
+			   * SOL_CUSTOM, something is wrong!
+			   */
+	ctx->retval = 0; /* Reset system call return value to zero */
+
+	optval[0] = storage->val;
+	ctx->optlen = 1;
+
+	return 1;
+}
+
+SEC("cgroup/setsockopt")
+int _setsockopt(struct bpf_sockopt *ctx)
+{
+	__u8 *optval_end = ctx->optval_end;
+	__u8 *optval = ctx->optval;
+	struct sockopt_sk *storage;
+
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+		/* Not interested in SOL_IP:IP_TOS;
+		 * let next BPF program in the cgroup chain or kernel
+		 * handle it.
+		 */
+		return 1;
+
+	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
+		/* Overwrite SO_SNDBUF value */
+
+		if (optval + sizeof(__u32) > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		*(__u32 *)optval = 0x55AA;
+		ctx->optlen = 4;
+
+		return 1;
+	}
+
+	if (ctx->level != SOL_CUSTOM)
+		return 0; /* EPERM, deny everything except custom level */
+
+	if (optval + 1 > optval_end)
+		return 0; /* EPERM, bounds check */
+
+	storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0,
+				     BPF_SK_STORAGE_GET_F_CREATE);
+	if (!storage)
+		return 0; /* EPERM, couldn't get sk storage */
+
+	storage->val = optval[0];
+	ctx->optlen = -1; /* BPF has consumed this option, don't call kernel
+			   * setsockopt handler.
+			   */
+
+	return 1;
+}

tools/testing/selftests/bpf/test_section_names.c

@@ -134,6 +134,16 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL},
 		{0, BPF_CGROUP_SYSCTL},
 	},
+	{
+		"cgroup/getsockopt",
+		{0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT},
+		{0, BPF_CGROUP_GETSOCKOPT},
+	},
+	{
+		"cgroup/setsockopt",
+		{0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT},
+		{0, BPF_CGROUP_SETSOCKOPT},
+	},
 };
 
 static int test_prog_type_by_name(const struct sec_name_test *test)

tools/testing/selftests/bpf/test_sockopt_multi.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <error.h>
+#include <errno.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include <linux/filter.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
+{
+	enum bpf_attach_type attach_type;
+	enum bpf_prog_type prog_type;
+	struct bpf_program *prog;
+	int err;
+
+	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
+	if (err) {
+		log_err("Failed to deduct types for %s BPF program", title);
+		return -1;
+	}
+
+	prog = bpf_object__find_program_by_title(obj, title);
+	if (!prog) {
+		log_err("Failed to find %s BPF program", title);
+		return -1;
+	}
+
+	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
+			      attach_type, BPF_F_ALLOW_MULTI);
+	if (err) {
+		log_err("Failed to attach %s BPF program", title);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title)
+{
+	enum bpf_attach_type attach_type;
+	enum bpf_prog_type prog_type;
+	struct bpf_program *prog;
+	int err;
+
+	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
+	if (err)
+		return -1;
+
+	prog = bpf_object__find_program_by_title(obj, title);
+	if (!prog)
+		return -1;
+
+	err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd,
+			       attach_type);
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
+			       int cg_child, int sock_fd)
+{
+	socklen_t optlen;
+	__u8 buf;
+	int err;
+
+	/* Set IP_TOS to the expected value (0x80). */
+
+	buf = 0x80;
+	err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+	if (err < 0) {
+		log_err("Failed to call setsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	if (buf != 0x80) {
+		log_err("Unexpected getsockopt 0x%x != 0x80 without BPF", buf);
+		err = -1;
+		goto detach;
+	}
+
+	/* Attach child program and make sure it returns new value:
+	 * - kernel:      -> 0x80
+	 * - child:  0x80 -> 0x90
+	 */
+
+	err = prog_attach(obj, cg_child, "cgroup/getsockopt/child");
+	if (err)
+		goto detach;
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	if (buf != 0x90) {
+		log_err("Unexpected getsockopt 0x%x != 0x90", buf);
+		err = -1;
+		goto detach;
+	}
+
+	/* Attach parent program and make sure it returns new value:
+	 * - kernel:      -> 0x80
+	 * - child:  0x80 -> 0x90
+	 * - parent: 0x90 -> 0xA0
+	 */
+
+	err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent");
+	if (err)
+		goto detach;
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	if (buf != 0xA0) {
+		log_err("Unexpected getsockopt 0x%x != 0xA0", buf);
+		err = -1;
+		goto detach;
+	}
+
+	/* Setting unexpected initial sockopt should return EPERM:
+	 * - kernel: -> 0x40
+	 * - child:  unexpected 0x40, EPERM
+	 * - parent: unexpected 0x40, EPERM
+	 */
+
+	buf = 0x40;
+	if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) {
+		log_err("Failed to call setsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (!err) {
+		log_err("Unexpected success from getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	/* Detach child program and make sure we still get EPERM:
+	 * - kernel: -> 0x40
+	 * - parent: unexpected 0x40, EPERM
+	 */
+
+	err = prog_detach(obj, cg_child, "cgroup/getsockopt/child");
+	if (err) {
+		log_err("Failed to detach child program");
+		goto detach;
+	}
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (!err) {
+		log_err("Unexpected success from getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	/* Set initial value to the one the parent program expects:
+	 * - kernel:      -> 0x90
+	 * - parent: 0x90 -> 0xA0
+	 */
+
+	buf = 0x90;
+	err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+	if (err < 0) {
+		log_err("Failed to call setsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	if (buf != 0xA0) {
+		log_err("Unexpected getsockopt 0x%x != 0xA0", buf);
+		err = -1;
+		goto detach;
+	}
+
+detach:
+	prog_detach(obj, cg_child, "cgroup/getsockopt/child");
+	prog_detach(obj, cg_parent, "cgroup/getsockopt/parent");
+
+	return err;
+}
+
+static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
+			       int cg_child, int sock_fd)
+{
+	socklen_t optlen;
+	__u8 buf;
+	int err;
+
+	/* Set IP_TOS to the expected value (0x80). */
+
+	buf = 0x80;
+	err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+	if (err < 0) {
+		log_err("Failed to call setsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	if (buf != 0x80) {
+		log_err("Unexpected getsockopt 0x%x != 0x80 without BPF", buf);
+		err = -1;
+		goto detach;
+	}
+
+	/* Attach child program and make sure it adds 0x10. */
+
+	err = prog_attach(obj, cg_child, "cgroup/setsockopt");
+	if (err)
+		goto detach;
+
+	buf = 0x80;
+	err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+	if (err < 0) {
+		log_err("Failed to call setsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	if (buf != 0x80 + 0x10) {
+		log_err("Unexpected getsockopt 0x%x != 0x80 + 0x10", buf);
+		err = -1;
+		goto detach;
+	}
+
+	/* Attach parent program and make sure it adds another 0x10. */
+
+	err = prog_attach(obj, cg_parent, "cgroup/setsockopt");
+	if (err)
+		goto detach;
+
+	buf = 0x80;
+	err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+	if (err < 0) {
+		log_err("Failed to call setsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	buf = 0x00;
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto detach;
+	}
+
+	if (buf != 0x80 + 2 * 0x10) {
+		log_err("Unexpected getsockopt 0x%x != 0x80 + 2 * 0x10", buf);
+		err = -1;
+		goto detach;
+	}
+
+detach:
+	prog_detach(obj, cg_child, "cgroup/setsockopt");
+	prog_detach(obj, cg_parent, "cgroup/setsockopt");
+
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_prog_load_attr attr = {
+		.file = "./sockopt_multi.o",
+	};
+	int cg_parent = -1, cg_child = -1;
+	struct bpf_object *obj = NULL;
+	int sock_fd = -1;
+	int err = -1;
+	int ignored;
+
+	if (setup_cgroup_environment()) {
+		log_err("Failed to setup cgroup environment\n");
+		goto out;
+	}
+
+	cg_parent = create_and_get_cgroup("/parent");
+	if (cg_parent < 0) {
+		log_err("Failed to create cgroup /parent\n");
+		goto out;
+	}
+
+	cg_child = create_and_get_cgroup("/parent/child");
+	if (cg_child < 0) {
+		log_err("Failed to create cgroup /parent/child\n");
+		goto out;
+	}
+
+	if (join_cgroup("/parent/child")) {
+		log_err("Failed to join cgroup /parent/child\n");
+		goto out;
+	}
+
+	err = bpf_prog_load_xattr(&attr, &obj, &ignored);
+	if (err) {
+		log_err("Failed to load BPF object");
+		goto out;
+	}
+
+	sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (sock_fd < 0) {
+		log_err("Failed to create socket");
+		goto out;
+	}
+
+	if (run_getsockopt_test(obj, cg_parent, cg_child, sock_fd))
+		err = -1;
+	printf("test_sockopt_multi: getsockopt %s\n",
+	       err ? "FAILED" : "PASSED");
+
+	if (run_setsockopt_test(obj, cg_parent, cg_child, sock_fd))
+		err = -1;
+	printf("test_sockopt_multi: setsockopt %s\n",
+	       err ? "FAILED" : "PASSED");
+
+out:
+	close(sock_fd);
+	bpf_object__close(obj);
+	close(cg_child);
+	close(cg_parent);
+
+	printf("test_sockopt_multi: %s\n", err ? "FAILED" : "PASSED");
+	return err ? EXIT_FAILURE : EXIT_SUCCESS;
+}

tools/testing/selftests/bpf/test_sockopt_sk.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include <linux/filter.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#define CG_PATH				"/sockopt"
+
+#define SOL_CUSTOM			0xdeadbeef
+
+static int getsetsockopt(void)
+{
+	int fd, err;
+	char buf[4] = {};
+	socklen_t optlen;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (fd < 0) {
+		log_err("Failed to create socket");
+		return -1;
+	}
+
+	/* IP_TOS - BPF bypass */
+
+	buf[0] = 0x08;
+	err = setsockopt(fd, SOL_IP, IP_TOS, buf, 1);
+	if (err) {
+		log_err("Failed to call setsockopt(IP_TOS)");
+		goto err;
+	}
+
+	buf[0] = 0x00;
+	optlen = 1;
+	err = getsockopt(fd, SOL_IP, IP_TOS, buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(IP_TOS)");
+		goto err;
+	}
+
+	if (buf[0] != 0x08) {
+		log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08",
+			buf[0]);
+		goto err;
+	}
+
+	/* IP_TTL - EPERM */
+
+	buf[0] = 1;
+	err = setsockopt(fd, SOL_IP, IP_TTL, buf, 1);
+	if (!err || errno != EPERM) {
+		log_err("Unexpected success from setsockopt(IP_TTL)");
+		goto err;
+	}
+
+	/* SOL_CUSTOM - handled by BPF */
+
+	buf[0] = 0x01;
+	err = setsockopt(fd, SOL_CUSTOM, 0, buf, 1);
+	if (err) {
+		log_err("Failed to call setsockopt");
+		goto err;
+	}
+
+	buf[0] = 0x00;
+	optlen = 4;
+	err = getsockopt(fd, SOL_CUSTOM, 0, buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt");
+		goto err;
+	}
+
+	if (optlen != 1) {
+		log_err("Unexpected optlen %d != 1", optlen);
+		goto err;
+	}
+	if (buf[0] != 0x01) {
+		log_err("Unexpected buf[0] 0x%02x != 0x01", buf[0]);
+		goto err;
+	}
+
+	/* SO_SNDBUF is overwritten */
+
+	buf[0] = 0x01;
+	buf[1] = 0x01;
+	buf[2] = 0x01;
+	buf[3] = 0x01;
+	err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, buf, 4);
+	if (err) {
+		log_err("Failed to call setsockopt(SO_SNDBUF)");
+		goto err;
+	}
+
+	buf[0] = 0x00;
+	buf[1] = 0x00;
+	buf[2] = 0x00;
+	buf[3] = 0x00;
+	optlen = 4;
+	err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF, buf, &optlen);
+	if (err) {
+		log_err("Failed to call getsockopt(SO_SNDBUF)");
+		goto err;
+	}
+
+	if (*(__u32 *)buf != 0x55AA*2) {
+		log_err("Unexpected getsockopt(SO_SNDBUF) 0x%x != 0x55AA*2",
+			*(__u32 *)buf);
+		goto err;
+	}
+
+	close(fd);
+	return 0;
+err:
+	close(fd);
+	return -1;
+}
+
+static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
+{
+	enum bpf_attach_type attach_type;
+	enum bpf_prog_type prog_type;
+	struct bpf_program *prog;
+	int err;
+
+	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
+	if (err) {
+		log_err("Failed to deduct types for %s BPF program", title);
+		return -1;
+	}
+
+	prog = bpf_object__find_program_by_title(obj, title);
+	if (!prog) {
+		log_err("Failed to find %s BPF program", title);
+		return -1;
+	}
+
+	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
+			      attach_type, 0);
+	if (err) {
+		log_err("Failed to attach %s BPF program", title);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int run_test(int cgroup_fd)
+{
+	struct bpf_prog_load_attr attr = {
+		.file = "./sockopt_sk.o",
+	};
+	struct bpf_object *obj;
+	int ignored;
+	int err;
+
+	err = bpf_prog_load_xattr(&attr, &obj, &ignored);
+	if (err) {
+		log_err("Failed to load BPF object");
+		return -1;
+	}
+
+	err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt");
+	if (err)
+		goto close_bpf_object;
+
+	err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt");
+	if (err)
+		goto close_bpf_object;
+
+	err = getsetsockopt();
+
+close_bpf_object:
+	bpf_object__close(obj);
+	return err;
+}
+
+int main(int args, char **argv)
+{
+	int cgroup_fd;
+	int err = EXIT_SUCCESS;
+
+	if (setup_cgroup_environment())
+		goto cleanup_obj;
+
+	cgroup_fd = create_and_get_cgroup(CG_PATH);
+	if (cgroup_fd < 0)
+		goto cleanup_cgroup_env;
+
+	if (join_cgroup(CG_PATH))
+		goto cleanup_cgroup;
+
+	if (run_test(cgroup_fd))
+		err = EXIT_FAILURE;
+
+	printf("test_sockopt_sk: %s\n",
+	       err == EXIT_SUCCESS ? "PASSED" : "FAILED");
+
+cleanup_cgroup:
+	close(cgroup_fd);
+cleanup_cgroup_env:
+	cleanup_cgroup_environment();
+cleanup_obj:
+	return err;
+}