Merge branch 'replace-cg_bpf-prog'

Andrey Ignatov says:

====================
v3->v4:
- use OPTS_VALID and OPTS_GET to handle bpf_prog_attach_opts.

v2->v3:
- rely on DECLARE_LIBBPF_OPTS from libbpf_common.h;
- separate "required" and "optional" arguments in bpf_prog_attach_xattr;
- convert test_cgroup_attach to prog_tests;
- move the new selftest to prog_tests/cgroup_attach_multi.

v1->v2:
- move DECLARE_LIBBPF_OPTS from libbpf.h to bpf.h (patch 4);
- switch new libbpf API to OPTS framework;
- switch selftest to libbpf OPTS framework.

This patch set adds support for replacing cgroup-bpf programs attached with
BPF_F_ALLOW_MULTI flag so that any program in a list can be updated to a new
version without service interruption and order of programs can be preserved.

Please see patch 3 for details on the use-case and API changes.

Other patches:
Patch 1 is preliminary refactoring of __cgroup_bpf_attach to simplify it.
Patch 2 is minor cleanup of hierarchy_allows_attach.
Patch 4 extends libbpf API to support new set of attach attributes.
Patch 5 converts test_cgroup_attach to prog_tests.
Patch 6 adds selftest coverage for the new API.
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf-cgroup.h

@@ -85,6 +85,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp);
 void cgroup_bpf_offline(struct cgroup *cgrp);
 
 int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+			struct bpf_prog *replace_prog,
 			enum bpf_attach_type type, u32 flags);
 int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 			enum bpf_attach_type type);
@@ -93,7 +94,8 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 
 /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
 int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, u32 flags);
+		      struct bpf_prog *replace_prog, enum bpf_attach_type type,
+		      u32 flags);
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		      enum bpf_attach_type type, u32 flags);
 int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,

include/uapi/linux/bpf.h

@@ -231,6 +231,11 @@ enum bpf_attach_type {
  * When children program makes decision (like picking TCP CA or sock bind)
  * parent program has a chance to override it.
  *
+ * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of
+ * programs for a cgroup. Though it's possible to replace an old program at
+ * any position by also specifying BPF_F_REPLACE flag and position itself in
+ * replace_bpf_fd attribute. Old program at this position will be released.
+ *
  * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
  * A cgroup with NONE doesn't allow any programs in sub-cgroups.
  * Ex1:
@@ -249,6 +254,7 @@ enum bpf_attach_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 #define BPF_F_ALLOW_MULTI	(1U << 1)
+#define BPF_F_REPLACE		(1U << 2)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -442,6 +448,10 @@ union bpf_attr {
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
 		__u32		attach_flags;
+		__u32		replace_bpf_fd;	/* previously attached eBPF
+						 * program to replace if
+						 * BPF_F_REPLACE is used
+						 */
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */

kernel/bpf/cgroup.c

@@ -103,8 +103,7 @@ static u32 prog_list_length(struct list_head *head)
  * if parent has overridable or multi-prog, allow attaching
  */
 static bool hierarchy_allows_attach(struct cgroup *cgrp,
-				    enum bpf_attach_type type,
-				    u32 new_flags)
+				    enum bpf_attach_type type)
 {
 	struct cgroup *p;
 
@@ -283,31 +282,34 @@ static int update_effective_progs(struct cgroup *cgrp,
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @prog: A program to attach
+ * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set
  * @type: Type of attach operation
  * @flags: Option flags
  *
  * Must be called with cgroup_mutex held.
  */
 int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+			struct bpf_prog *replace_prog,
 			enum bpf_attach_type type, u32 flags)
 {
+	u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
 		*old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL};
+	struct bpf_prog_list *pl, *replace_pl = NULL;
 	enum bpf_cgroup_storage_type stype;
-	struct bpf_prog_list *pl;
-	bool pl_was_allocated;
 	int err;
 
-	if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
+	if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) ||
+	    ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI)))
 		/* invalid combination */
 		return -EINVAL;
 
-	if (!hierarchy_allows_attach(cgrp, type, flags))
+	if (!hierarchy_allows_attach(cgrp, type))
 		return -EPERM;
 
-	if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
+	if (!list_empty(progs) && cgrp->bpf.flags[type] != saved_flags)
 		/* Disallow attaching non-overridable on top
 		 * of existing overridable in this cgroup.
 		 * Disallow attaching multi-prog if overridable or none
@@ -317,6 +319,21 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
 		return -E2BIG;
 
+	if (flags & BPF_F_ALLOW_MULTI) {
+		list_for_each_entry(pl, progs, node) {
+			if (pl->prog == prog)
+				/* disallow attaching the same prog twice */
+				return -EINVAL;
+			if (pl->prog == replace_prog)
+				replace_pl = pl;
+		}
+		if ((flags & BPF_F_REPLACE) && !replace_pl)
+			/* prog to replace not found for cgroup */
+			return -ENOENT;
+	} else if (!list_empty(progs)) {
+		replace_pl = list_first_entry(progs, typeof(*pl), node);
+	}
+
 	for_each_cgroup_storage_type(stype) {
 		storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
 		if (IS_ERR(storage[stype])) {
@@ -327,53 +344,28 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 		}
 	}
 
-	if (flags & BPF_F_ALLOW_MULTI) {
-		list_for_each_entry(pl, progs, node) {
-			if (pl->prog == prog) {
-				/* disallow attaching the same prog twice */
-				for_each_cgroup_storage_type(stype)
-					bpf_cgroup_storage_free(storage[stype]);
-				return -EINVAL;
-			}
+	if (replace_pl) {
+		pl = replace_pl;
+		old_prog = pl->prog;
+		for_each_cgroup_storage_type(stype) {
+			old_storage[stype] = pl->storage[stype];
+			bpf_cgroup_storage_unlink(old_storage[stype]);
 		}
-
+	} else {
 		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
 		if (!pl) {
 			for_each_cgroup_storage_type(stype)
 				bpf_cgroup_storage_free(storage[stype]);
 			return -ENOMEM;
 		}
-
-		pl_was_allocated = true;
-		pl->prog = prog;
-		for_each_cgroup_storage_type(stype)
-			pl->storage[stype] = storage[stype];
 		list_add_tail(&pl->node, progs);
-	} else {
-		if (list_empty(progs)) {
-			pl = kmalloc(sizeof(*pl), GFP_KERNEL);
-			if (!pl) {
-				for_each_cgroup_storage_type(stype)
-					bpf_cgroup_storage_free(storage[stype]);
-				return -ENOMEM;
-			}
-			pl_was_allocated = true;
-			list_add_tail(&pl->node, progs);
-		} else {
-			pl = list_first_entry(progs, typeof(*pl), node);
-			old_prog = pl->prog;
-			for_each_cgroup_storage_type(stype) {
-				old_storage[stype] = pl->storage[stype];
-				bpf_cgroup_storage_unlink(old_storage[stype]);
-			}
-			pl_was_allocated = false;
-		}
-		pl->prog = prog;
-		for_each_cgroup_storage_type(stype)
-			pl->storage[stype] = storage[stype];
 	}
 
-	cgrp->bpf.flags[type] = flags;
+	pl->prog = prog;
+	for_each_cgroup_storage_type(stype)
+		pl->storage[stype] = storage[stype];
+
+	cgrp->bpf.flags[type] = saved_flags;
 
 	err = update_effective_progs(cgrp, type);
 	if (err)
@@ -401,7 +393,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 		pl->storage[stype] = old_storage[stype];
 		bpf_cgroup_storage_link(old_storage[stype], cgrp, type);
 	}
-	if (pl_was_allocated) {
+	if (!replace_pl) {
 		list_del(&pl->node);
 		kfree(pl);
 	}
@@ -539,6 +531,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog)
 {
+	struct bpf_prog *replace_prog = NULL;
 	struct cgroup *cgrp;
 	int ret;
 
@@ -546,8 +539,20 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 	if (IS_ERR(cgrp))
 		return PTR_ERR(cgrp);
 
-	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+	if ((attr->attach_flags & BPF_F_ALLOW_MULTI) &&
+	    (attr->attach_flags & BPF_F_REPLACE)) {
+		replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype);
+		if (IS_ERR(replace_prog)) {
+			cgroup_put(cgrp);
+			return PTR_ERR(replace_prog);
+		}
+	}
+
+	ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type,
 				attr->attach_flags);
+
+	if (replace_prog)
+		bpf_prog_put(replace_prog);
 	cgroup_put(cgrp);
 	return ret;
 }

kernel/bpf/syscall.c

@@ -2073,10 +2073,10 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	}
 }
 
-#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
+#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
 
 #define BPF_F_ATTACH_MASK \
-	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
+	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {

kernel/cgroup/cgroup.c

@@ -6288,12 +6288,13 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
 
 #ifdef CONFIG_CGROUP_BPF
 int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, u32 flags)
+		      struct bpf_prog *replace_prog, enum bpf_attach_type type,
+		      u32 flags)
 {
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_attach(cgrp, prog, type, flags);
+	ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, type, flags);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }

tools/include/uapi/linux/bpf.h

@@ -231,6 +231,11 @@ enum bpf_attach_type {
  * When children program makes decision (like picking TCP CA or sock bind)
  * parent program has a chance to override it.
  *
+ * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of
+ * programs for a cgroup. Though it's possible to replace an old program at
+ * any position by also specifying BPF_F_REPLACE flag and position itself in
+ * replace_bpf_fd attribute. Old program at this position will be released.
+ *
  * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
  * A cgroup with NONE doesn't allow any programs in sub-cgroups.
  * Ex1:
@@ -249,6 +254,7 @@ enum bpf_attach_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 #define BPF_F_ALLOW_MULTI	(1U << 1)
+#define BPF_F_REPLACE		(1U << 2)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -442,6 +448,10 @@ union bpf_attr {
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
 		__u32		attach_flags;
+		__u32		replace_bpf_fd;	/* previously attached eBPF
+						 * program to replace if
+						 * BPF_F_REPLACE is used
+						 */
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */

tools/lib/bpf/bpf.c

@@ -466,14 +466,29 @@ int bpf_obj_get(const char *pathname)
 
 int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
 		    unsigned int flags)
+{
+	DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, opts,
+		.flags = flags,
+	);
+
+	return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts);
+}
+
+int bpf_prog_attach_xattr(int prog_fd, int target_fd,
+			  enum bpf_attach_type type,
+			  const struct bpf_prog_attach_opts *opts)
 {
 	union bpf_attr attr;
 
+	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
+		return -EINVAL;
+
 	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	   = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type   = type;
-	attr.attach_flags  = flags;
+	attr.attach_flags  = OPTS_GET(opts, flags, 0);
+	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
 
 	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
 }

tools/lib/bpf/bpf.h

@@ -126,8 +126,19 @@ LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
 LIBBPF_API int bpf_obj_get(const char *pathname);
+
+struct bpf_prog_attach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	unsigned int flags;
+	int replace_prog_fd;
+};
+#define bpf_prog_attach_opts__last_field replace_prog_fd
+
 LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
 			       enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd,
+				     enum bpf_attach_type type,
+				     const struct bpf_prog_attach_opts *opts);
 LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);

tools/lib/bpf/libbpf.map

@@ -219,6 +219,7 @@ LIBBPF_0.0.7 {
 		bpf_object__detach_skeleton;
 		bpf_object__load_skeleton;
 		bpf_object__open_skeleton;
+		bpf_prog_attach_xattr;
 		bpf_program__attach;
 		bpf_program__name;
 		btf__align_of;

tools/testing/selftests/bpf/.gitignore

@@ -21,7 +21,6 @@ test_lirc_mode2_user
 get_cgroup_id_user
 test_skb_cgroup_id_user
 test_socket_cookie
-test_cgroup_attach
 test_cgroup_storage
 test_select_reuseport
 test_flow_dissector

tools/testing/selftests/bpf/Makefile

@@ -32,7 +32,7 @@ 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_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
-	test_cgroup_attach test_progs-no_alu32
+	test_progs-no_alu32
 
 # Also test bpf-gcc, if present
 ifneq ($(BPF_GCC),)
@@ -136,7 +136,6 @@ $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
 $(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
 
 .PHONY: force
 

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

+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int prog_load(void)
+{
+	struct bpf_insn prog[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+
+	return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+}
+
+void test_cgroup_attach_autodetach(void)
+{
+	__u32 duration = 0, prog_cnt = 4, attach_flags;
+	int allow_prog[2] = {-1};
+	__u32 prog_ids[2] = {0};
+	void *ptr = NULL;
+	int cg = 0, i;
+	int attempts;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		allow_prog[i] = prog_load();
+		if (CHECK(allow_prog[i] < 0, "prog_load",
+			  "verifier output:\n%s\n-------\n", bpf_log_buf))
+			goto err;
+	}
+
+	if (CHECK_FAIL(setup_cgroup_environment()))
+		goto err;
+
+	/* create a cgroup, attach two programs and remember their ids */
+	cg = create_and_get_cgroup("/cg_autodetach");
+	if (CHECK_FAIL(cg < 0))
+		goto err;
+
+	if (CHECK_FAIL(join_cgroup("/cg_autodetach")))
+		goto err;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (CHECK(bpf_prog_attach(allow_prog[i], cg,
+					  BPF_CGROUP_INET_EGRESS,
+					  BPF_F_ALLOW_MULTI),
+			  "prog_attach", "prog[%d], errno=%d\n", i, errno))
+			goto err;
+
+	/* make sure that programs are attached and run some traffic */
+	if (CHECK(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags,
+				 prog_ids, &prog_cnt),
+		  "prog_query", "errno=%d\n", errno))
+		goto err;
+	if (CHECK_FAIL(system(PING_CMD)))
+		goto err;
+
+	/* allocate some memory (4Mb) to pin the original cgroup */
+	ptr = malloc(4 * (1 << 20));
+	if (CHECK_FAIL(!ptr))
+		goto err;
+
+	/* close programs and cgroup fd */
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		close(allow_prog[i]);
+		allow_prog[i] = -1;
+	}
+
+	close(cg);
+	cg = 0;
+
+	/* leave the cgroup and remove it. don't detach programs */
+	cleanup_cgroup_environment();
+
+	/* wait for the asynchronous auto-detachment.
+	 * wait for no more than 5 sec and give up.
+	 */
+	for (i = 0; i < ARRAY_SIZE(prog_ids); i++) {
+		for (attempts = 5; attempts >= 0; attempts--) {
+			int fd = bpf_prog_get_fd_by_id(prog_ids[i]);
+
+			if (fd < 0)
+				break;
+
+			/* don't leave the fd open */
+			close(fd);
+
+			if (CHECK_FAIL(!attempts))
+				goto err;
+
+			sleep(1);
+		}
+	}
+
+err:
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (allow_prog[i] >= 0)
+			close(allow_prog[i]);
+	if (cg)
+		close(cg);
+	free(ptr);
+	cleanup_cgroup_environment();
+}

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

+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int map_fd = -1;
+
+static int prog_load_cnt(int verdict, int val)
+{
+	int cgroup_storage_fd, percpu_cgroup_storage_fd;
+
+	if (map_fd < 0)
+		map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+	if (map_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+				sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	percpu_cgroup_storage_fd = bpf_create_map(
+		BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+		sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (percpu_cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	struct bpf_insn prog[] = {
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+
+		BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+		BPF_MOV64_IMM(BPF_REG_1, val),
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0),
+
+		BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
+		BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+
+		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+	int ret;
+
+	ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+
+	close(cgroup_storage_fd);
+	return ret;
+}
+
+void test_cgroup_attach_multi(void)
+{
+	__u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
+	int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
+	DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, attach_opts);
+	int allow_prog[7] = {-1};
+	unsigned long long value;
+	__u32 duration = 0;
+	int i = 0;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		allow_prog[i] = prog_load_cnt(1, 1 << i);
+		if (CHECK(allow_prog[i] < 0, "prog_load",
+			  "verifier output:\n%s\n-------\n", bpf_log_buf))
+			goto err;
+	}
+
+	if (CHECK_FAIL(setup_cgroup_environment()))
+		goto err;
+
+	cg1 = create_and_get_cgroup("/cg1");
+	if (CHECK_FAIL(cg1 < 0))
+		goto err;
+	cg2 = create_and_get_cgroup("/cg1/cg2");
+	if (CHECK_FAIL(cg2 < 0))
+		goto err;
+	cg3 = create_and_get_cgroup("/cg1/cg2/cg3");
+	if (CHECK_FAIL(cg3 < 0))
+		goto err;
+	cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4");
+	if (CHECK_FAIL(cg4 < 0))
+		goto err;
+	cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5");
+	if (CHECK_FAIL(cg5 < 0))
+		goto err;
+
+	if (CHECK_FAIL(join_cgroup("/cg1/cg2/cg3/cg4/cg5")))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_MULTI),
+		  "prog0_attach_to_cg1_multi", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
+				   BPF_F_ALLOW_MULTI),
+		  "fail_same_prog_attach_to_cg1", "unexpected success\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_MULTI),
+		  "prog1_attach_to_cg1_multi", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog2_attach_to_cg2_override", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_MULTI),
+		  "prog3_attach_to_cg3_multi", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE),
+		  "prog4_attach_to_cg4_override", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0),
+		  "prog5_attach_to_cg5_none", "errno=%d\n", errno))
+		goto err;
+
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 1 + 2 + 8 + 32);
+
+	/* query the number of effective progs in cg5 */
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, NULL, NULL, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 4);
+	/* retrieve prog_ids of effective progs in cg5 */
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, &attach_flags,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 4);
+	CHECK_FAIL(attach_flags != 0);
+	saved_prog_id = prog_ids[0];
+	/* check enospc handling */
+	prog_ids[0] = 0;
+	prog_cnt = 2;
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, &attach_flags,
+				  prog_ids, &prog_cnt) != -1);
+	CHECK_FAIL(errno != ENOSPC);
+	CHECK_FAIL(prog_cnt != 4);
+	/* check that prog_ids are returned even when buffer is too small */
+	CHECK_FAIL(prog_ids[0] != saved_prog_id);
+	/* retrieve prog_id of single attached prog in cg5 */
+	prog_ids[0] = 0;
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 1);
+	CHECK_FAIL(prog_ids[0] != saved_prog_id);
+
+	/* detach bottom program and ping again */
+	if (CHECK(bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_from_cg5", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 1 + 2 + 8 + 16);
+
+	/* test replace */
+
+	attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE;
+	attach_opts.replace_prog_fd = allow_prog[0];
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_override", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != EINVAL);
+
+	attach_opts.flags = BPF_F_REPLACE;
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_no_multi", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != EINVAL);
+
+	attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE;
+	attach_opts.replace_prog_fd = -1;
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_bad_fd", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != EBADF);
+
+	/* replacing a program that is not attached to cgroup should fail  */
+	attach_opts.replace_prog_fd = allow_prog[3];
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_no_ent", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != ENOENT);
+
+	/* replace 1st from the top program */
+	attach_opts.replace_prog_fd = allow_prog[0];
+	if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1,
+					BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "prog_replace", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 64 + 2 + 8 + 16);
+
+	/* detach 3rd from bottom program and ping again */
+	if (CHECK(!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS),
+		  "fail_prog_detach_from_cg3", "unexpected success\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS),
+		  "prog3_detach_from_cg3", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 64 + 2 + 16);
+
+	/* detach 2nd from bottom program and ping again */
+	if (CHECK(bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_from_cg4", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 64 + 2 + 4);
+
+	prog_cnt = 4;
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, &attach_flags,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 3);
+	CHECK_FAIL(attach_flags != 0);
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 0);
+
+err:
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (allow_prog[i] >= 0)
+			close(allow_prog[i]);
+	close(cg1);
+	close(cg2);
+	close(cg3);
+	close(cg4);
+	close(cg5);
+	cleanup_cgroup_environment();
+}

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

+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define FOO		"/foo"
+#define BAR		"/foo/bar/"
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int prog_load(int verdict)
+{
+	struct bpf_insn prog[] = {
+		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+
+	return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+}
+
+void test_cgroup_attach_override(void)
+{
+	int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1;
+	__u32 duration = 0;
+
+	allow_prog = prog_load(1);
+	if (CHECK(allow_prog < 0, "prog_load_allow",
+		  "verifier output:\n%s\n-------\n", bpf_log_buf))
+		goto err;
+
+	drop_prog = prog_load(0);
+	if (CHECK(drop_prog < 0, "prog_load_drop",
+		  "verifier output:\n%s\n-------\n", bpf_log_buf))
+		goto err;
+
+	foo = test__join_cgroup(FOO);
+	if (CHECK(foo < 0, "cgroup_join_foo", "cgroup setup failed\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_drop_foo_override",
+		  "attach prog to %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+	if (CHECK(!system(PING_CMD), "ping_fail",
+		  "ping unexpectedly succeeded\n"))
+		goto err;
+
+	bar = test__join_cgroup(BAR);
+	if (CHECK(bar < 0, "cgroup_join_bar", "cgroup setup failed\n"))
+		goto err;
+
+	if (CHECK(!system(PING_CMD), "ping_fail",
+		  "ping unexpectedly succeeded\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_allow_bar_override",
+		  "attach prog to %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_bar",
+		  "detach prog from %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(!system(PING_CMD), "ping_fail",
+		  "ping unexpectedly succeeded\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_allow_bar_override",
+		  "attach prog to %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_foo",
+		  "detach prog from %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+	if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_allow_bar_override",
+		  "attach prog to %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0),
+		  "fail_prog_attach_allow_bar_none",
+		  "attach prog to %s unexpectedly succeeded\n", BAR))
+		goto err;
+
+	if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_bar",
+		  "detach prog from %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS),
+		  "fail_prog_detach_foo",
+		  "double detach from %s unexpectedly succeeded\n", FOO))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0),
+		  "prog_attach_allow_foo_none",
+		  "attach prog to %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0),
+		  "fail_prog_attach_allow_bar_none",
+		  "attach prog to %s unexpectedly succeeded\n", BAR))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				   BPF_F_ALLOW_OVERRIDE),
+		  "fail_prog_attach_allow_bar_override",
+		  "attach prog to %s unexpectedly succeeded\n", BAR))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS,
+				   BPF_F_ALLOW_OVERRIDE),
+		  "fail_prog_attach_allow_foo_override",
+		  "attach prog to %s unexpectedly succeeded\n", FOO))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0),
+		  "prog_attach_drop_foo_none",
+		  "attach prog to %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+err:
+	close(foo);
+	close(bar);
+	close(allow_prog);
+	close(drop_prog);
+}