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

Alexei Starovoitov says:

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

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

We've added 21 non-merge commits during the last 8 day(s) which contain
a total of 21 files changed, 450 insertions(+), 36 deletions(-).

The main changes are:

1) Adjust bpf_mem_alloc buckets to match ksize(), from Hou Tao.

2) Check whether override is allowed in kprobe mult, from Jiri Olsa.

3) Fix btf_id symbol generation with ld.lld, from Jiri and Nick.

4) Fix potential deadlock when using queue and stack maps from NMI, from Toke Høiland-Jørgensen.

Please consider pulling these changes from:

  git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git

Thanks a lot!

Also thanks to reporters, reviewers and testers of commits in this pull-request:

Alan Maguire, Biju Das, Björn Töpel, Dan Carpenter, Daniel Borkmann,
Eduard Zingerman, Hsin-Wei Hung, Marcus Seyfarth, Nathan Chancellor,
Satya Durga Srinivasu Prabhala, Song Liu, Stephen Rothwell
====================

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

include/linux/btf_ids.h

@@ -49,7 +49,7 @@ word							\
 	____BTF_ID(symbol, word)
 
 #define __ID(prefix) \
-	__PASTE(prefix, __COUNTER__)
+	__PASTE(__PASTE(prefix, __COUNTER__), __LINE__)
 
 /*
  * The BTF_ID defines unique symbol for each ID pointing

include/uapi/linux/bpf.h

@@ -1962,7 +1962,9 @@ union bpf_attr {
  * 		performed again, if the helper is used in combination with
  * 		direct packet access.
  * 	Return
- * 		0 on success, or a negative error in case of failure.
+ * 		0 on success, or a negative error in case of failure. Positive
+ * 		error indicates a potential drop or congestion in the target
+ * 		device. The particular positive error codes are not defined.
  *
  * u64 bpf_get_current_pid_tgid(void)
  * 	Description

kernel/bpf/btf.c

@@ -8501,7 +8501,7 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log,
 	tname = btf_name_by_offset(btf, walk_type->name_off);
 
 	ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix);
-	if (ret < 0)
+	if (ret >= sizeof(safe_tname))
 		return false;
 
 	safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info));

kernel/bpf/cgroup.c

@@ -785,7 +785,8 @@ static void replace_effective_prog(struct cgroup *cgrp,
  *                          to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @link: A link for which to replace BPF program
- * @type: Type of attach operation
+ * @new_prog: &struct bpf_prog for the target BPF program with its refcnt
+ *            incremented
  *
  * Must be called with cgroup_mutex held.
  */
@@ -1334,7 +1335,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
  * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
  * @sk: The socket sending or receiving traffic
  * @skb: The skb that is being sent or received
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * If no socket is passed, or the socket is not of type INET or INET6,
  * this function does nothing and returns 0.
@@ -1424,7 +1425,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
 /**
  * __cgroup_bpf_run_filter_sk() - Run a program on a sock
  * @sk: sock structure to manipulate
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * socket is passed is expected to be of type INET or INET6.
  *
@@ -1449,7 +1450,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
  *                                       provided by user sockaddr
  * @sk: sock struct that will use sockaddr
  * @uaddr: sockaddr struct provided by user
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  * @t_ctx: Pointer to attach type specific context
  * @flags: Pointer to u32 which contains higher bits of BPF program
  *         return value (OR'ed together).
@@ -1496,7 +1497,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
  * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
  * sk with connection information (IP addresses, etc.) May not contain
  * cgroup info if it is a req sock.
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * socket passed is expected to be of type INET or INET6.
  *
@@ -1670,7 +1671,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @ppos: value-result argument: value is position at which read from or write
  *	to sysctl is happening, result is new position if program overrode it,
  *	initial value otherwise
- * @type: type of program to be executed
+ * @atype: type of program to be executed
  *
  * Program is run when sysctl is being accessed, either read or written, and
  * can allow or deny such access.

kernel/bpf/memalloc.c

@@ -459,8 +459,7 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
  * Typical case will be between 11K and 116K closer to 11K.
  * bpf progs can and should share bpf_mem_cache when possible.
  */
-
-static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+static void init_refill_work(struct bpf_mem_cache *c)
 {
 	init_irq_work(&c->refill_work, bpf_mem_refill);
 	if (c->unit_size <= 256) {
@@ -476,7 +475,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 		c->high_watermark = max(96 * 256 / c->unit_size, 3);
 	}
 	c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
+}
 
+static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+{
 	/* To avoid consuming memory assume that 1st run of bpf
 	 * prog won't be doing more than 4 map_update_elem from
 	 * irq disabled region
@@ -484,6 +486,31 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
 }
 
+static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
+{
+	struct llist_node *first;
+	unsigned int obj_size;
+
+	/* For per-cpu allocator, the size of free objects in free list doesn't
+	 * match with unit_size and now there is no way to get the size of
+	 * per-cpu pointer saved in free object, so just skip the checking.
+	 */
+	if (c->percpu_size)
+		return 0;
+
+	first = c->free_llist.first;
+	if (!first)
+		return 0;
+
+	obj_size = ksize(first);
+	if (obj_size != c->unit_size) {
+		WARN_ONCE(1, "bpf_mem_cache[%u]: unexpected object size %u, expect %u\n",
+			  idx, obj_size, c->unit_size);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* When size != 0 bpf_mem_cache for each cpu.
  * This is typical bpf hash map use case when all elements have equal size.
  *
@@ -494,10 +521,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
 	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+	int cpu, i, err, unit_size, percpu_size = 0;
 	struct bpf_mem_caches *cc, __percpu *pcc;
 	struct bpf_mem_cache *c, __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
-	int cpu, i, unit_size, percpu_size = 0;
 
 	if (size) {
 		pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL);
@@ -521,6 +548,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
 			c->tgt = c;
+			init_refill_work(c);
 			prefill_mem_cache(c, cpu);
 		}
 		ma->cache = pc;
@@ -534,6 +562,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 	pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
 	if (!pcc)
 		return -ENOMEM;
+	err = 0;
 #ifdef CONFIG_MEMCG_KMEM
 	objcg = get_obj_cgroup_from_current();
 #endif
@@ -544,11 +573,30 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->unit_size = sizes[i];
 			c->objcg = objcg;
 			c->tgt = c;
+
+			init_refill_work(c);
+			/* Another bpf_mem_cache will be used when allocating
+			 * c->unit_size in bpf_mem_alloc(), so doesn't prefill
+			 * for the bpf_mem_cache because these free objects will
+			 * never be used.
+			 */
+			if (i != bpf_mem_cache_idx(c->unit_size))
+				continue;
 			prefill_mem_cache(c, cpu);
+			err = check_obj_size(c, i);
+			if (err)
+				goto out;
 		}
 	}
+
+out:
 	ma->caches = pcc;
-	return 0;
+	/* refill_work is either zeroed or initialized, so it is safe to
+	 * call irq_work_sync().
+	 */
+	if (err)
+		bpf_mem_alloc_destroy(ma);
+	return err;
 }
 
 static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -916,3 +964,41 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
+
+/* Most of the logic is taken from setup_kmalloc_cache_index_table() */
+static __init int bpf_mem_cache_adjust_size(void)
+{
+	unsigned int size, index;
+
+	/* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be
+	 * up-to 256-bytes.
+	 */
+	size = KMALLOC_MIN_SIZE;
+	if (size <= 192)
+		index = size_index[(size - 1) / 8];
+	else
+		index = fls(size - 1) - 1;
+	for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8)
+		size_index[(size - 1) / 8] = index;
+
+	/* The minimal alignment is 64-bytes, so disable 96-bytes cache and
+	 * use 128-bytes cache instead.
+	 */
+	if (KMALLOC_MIN_SIZE >= 64) {
+		index = size_index[(128 - 1) / 8];
+		for (size = 64 + 8; size <= 96; size += 8)
+			size_index[(size - 1) / 8] = index;
+	}
+
+	/* The minimal alignment is 128-bytes, so disable 192-bytes cache and
+	 * use 256-bytes cache instead.
+	 */
+	if (KMALLOC_MIN_SIZE >= 128) {
+		index = fls(256 - 1) - 1;
+		for (size = 128 + 8; size <= 192; size += 8)
+			size_index[(size - 1) / 8] = index;
+	}
+
+	return 0;
+}
+subsys_initcall(bpf_mem_cache_adjust_size);

kernel/bpf/offload.c

@@ -199,12 +199,14 @@ static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *n
 	offload->netdev = netdev;
 
 	ondev = bpf_offload_find_netdev(offload->netdev);
+	/* When program is offloaded require presence of "true"
+	 * bpf_offload_netdev, avoid the one created for !ondev case below.
+	 */
+	if (bpf_prog_is_offloaded(prog->aux) && (!ondev || !ondev->offdev)) {
+		err = -EINVAL;
+		goto err_free;
+	}
 	if (!ondev) {
-		if (bpf_prog_is_offloaded(prog->aux)) {
-			err = -EINVAL;
-			goto err_free;
-		}
-
 		/* When only binding to the device, explicitly
 		 * create an entry in the hashtable.
 		 */

kernel/bpf/queue_stack_maps.c

@@ -98,7 +98,12 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	int err = 0;
 	void *ptr;
 
-	raw_spin_lock_irqsave(&qs->lock, flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, flags);
+	}
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -128,7 +133,12 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 	void *ptr;
 	u32 index;
 
-	raw_spin_lock_irqsave(&qs->lock, flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, flags);
+	}
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -193,7 +203,12 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
 	if (flags & BPF_NOEXIST || flags > BPF_EXIST)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&qs->lock, irq_flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, irq_flags);
+	}
 
 	if (queue_stack_map_is_full(qs)) {
 		if (!replace) {

kernel/trace/bpf_trace.c

@@ -2853,6 +2853,17 @@ static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u3
 	return arr.mods_cnt;
 }
 
+static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt)
+{
+	u32 i;
+
+	for (i = 0; i < cnt; i++) {
+		if (!within_error_injection_list(addrs[i]))
+			return -EINVAL;
+	}
+	return 0;
+}
+
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct bpf_kprobe_multi_link *link = NULL;
@@ -2930,6 +2941,11 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 			goto error;
 	}
 
+	if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) {
+		err = -EINVAL;
+		goto error;
+	}
+
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link) {
 		err = -ENOMEM;
@@ -3207,8 +3223,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		rcu_read_lock();
 		task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
 		rcu_read_unlock();
-		if (!task)
+		if (!task) {
+			err = -ESRCH;
 			goto error_path_put;
+		}
 	}
 
 	err = -ENOMEM;

net/netfilter/nf_conntrack_bpf.c

@@ -381,6 +381,8 @@ __bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i)
 	struct nf_conn *nfct = (struct nf_conn *)nfct_i;
 	int err;
 
+	if (!nf_ct_is_confirmed(nfct))
+		nfct->timeout += nfct_time_stamp;
 	nfct->status |= IPS_CONFIRMED;
 	err = nf_conntrack_hash_check_insert(nfct);
 	if (err < 0) {

tools/include/linux/btf_ids.h

@@ -38,7 +38,7 @@ asm(							\
 	____BTF_ID(symbol)
 
 #define __ID(prefix) \
-	__PASTE(prefix, __COUNTER__)
+	__PASTE(__PASTE(prefix, __COUNTER__), __LINE__)
 
 /*
  * The BTF_ID defines unique symbol for each ID pointing

tools/include/uapi/linux/bpf.h

@@ -1962,7 +1962,9 @@ union bpf_attr {
  * 		performed again, if the helper is used in combination with
  * 		direct packet access.
  * 	Return
- * 		0 on success, or a negative error in case of failure.
+ * 		0 on success, or a negative error in case of failure. Positive
+ * 		error indicates a potential drop or congestion in the target
+ * 		device. The particular positive error codes are not defined.
  *
  * u64 bpf_get_current_pid_tgid(void)
  * 	Description

tools/testing/selftests/bpf/DENYLIST.aarch64

@@ -1,14 +1,8 @@
 bpf_cookie/multi_kprobe_attach_api               # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
 bpf_cookie/multi_kprobe_link_api                 # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
 fexit_sleep                                      # The test never returns. The remaining tests cannot start.
-kprobe_multi_bench_attach                        # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/attach_api_addrs               # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/attach_api_pattern             # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/attach_api_syms                # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/bench_attach                   # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/link_api_addrs                 # link_fd unexpected link_fd: actual -95 < expected 0
-kprobe_multi_test/link_api_syms                  # link_fd unexpected link_fd: actual -95 < expected 0
-kprobe_multi_test/skel_api                       # libbpf: failed to load BPF skeleton 'kprobe_multi': -3
+kprobe_multi_bench_attach                        # needs CONFIG_FPROBE
+kprobe_multi_test                                # needs CONFIG_FPROBE
 module_attach                                    # prog 'kprobe_multi': failed to auto-attach: -95
 fentry_test/fentry_many_args                     # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524
 fexit_test/fexit_many_args                       # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524

tools/testing/selftests/bpf/config

@@ -4,6 +4,7 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
 CONFIG_BPF=y
 CONFIG_BPF_EVENTS=y
 CONFIG_BPF_JIT=y
+CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_BPF_LIRC_MODE2=y
 CONFIG_BPF_LSM=y
 CONFIG_BPF_STREAM_PARSER=y

tools/testing/selftests/bpf/config.x86_64

@@ -20,7 +20,6 @@ CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BONDING=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
 CONFIG_BPFILTER=y

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

@@ -24,6 +24,7 @@ void test_empty_skb(void)
 		int *ifindex;
 		int err;
 		int ret;
+		int lwt_egress_ret; /* expected retval at lwt/egress */
 		bool success_on_tc;
 	} tests[] = {
 		/* Empty packets are always rejected. */
@@ -57,6 +58,7 @@ void test_empty_skb(void)
 			.data_size_in = sizeof(eth_hlen),
 			.ifindex = &veth_ifindex,
 			.ret = -ERANGE,
+			.lwt_egress_ret = -ERANGE,
 			.success_on_tc = true,
 		},
 		{
@@ -70,6 +72,7 @@ void test_empty_skb(void)
 			.data_size_in = sizeof(eth_hlen),
 			.ifindex = &ipip_ifindex,
 			.ret = -ERANGE,
+			.lwt_egress_ret = -ERANGE,
 		},
 
 		/* ETH_HLEN+1-sized packet should be redirected. */
@@ -79,6 +82,7 @@ void test_empty_skb(void)
 			.data_in = eth_hlen_pp,
 			.data_size_in = sizeof(eth_hlen_pp),
 			.ifindex = &veth_ifindex,
+			.lwt_egress_ret = 1, /* veth_xmit NET_XMIT_DROP */
 		},
 		{
 			.msg = "ipip ETH_HLEN+1 packet ingress",
@@ -108,8 +112,12 @@ void test_empty_skb(void)
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		bpf_object__for_each_program(prog, bpf_obj->obj) {
-			char buf[128];
+			bool at_egress = strstr(bpf_program__name(prog), "egress") != NULL;
 			bool at_tc = !strncmp(bpf_program__section_name(prog), "tc", 2);
+			int expected_ret;
+			char buf[128];
+
+			expected_ret = at_egress && !at_tc ? tests[i].lwt_egress_ret : tests[i].ret;
 
 			tattr.data_in = tests[i].data_in;
 			tattr.data_size_in = tests[i].data_size_in;
@@ -128,7 +136,7 @@ void test_empty_skb(void)
 			if (at_tc && tests[i].success_on_tc)
 				ASSERT_GE(bpf_obj->bss->ret, 0, buf);
 			else
-				ASSERT_EQ(bpf_obj->bss->ret, tests[i].ret, buf);
+				ASSERT_EQ(bpf_obj->bss->ret, expected_ret, buf);
 		}
 	}
 

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

@@ -3,6 +3,7 @@
 #include "kprobe_multi.skel.h"
 #include "trace_helpers.h"
 #include "kprobe_multi_empty.skel.h"
+#include "kprobe_multi_override.skel.h"
 #include "bpf/libbpf_internal.h"
 #include "bpf/hashmap.h"
 
@@ -453,6 +454,40 @@ static void test_kprobe_multi_bench_attach(bool kernel)
 	}
 }
 
+static void test_attach_override(void)
+{
+	struct kprobe_multi_override *skel = NULL;
+	struct bpf_link *link = NULL;
+
+	skel = kprobe_multi_override__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
+		goto cleanup;
+
+	/* The test_override calls bpf_override_return so it should fail
+	 * to attach to bpf_fentry_test1 function, which is not on error
+	 * injection list.
+	 */
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_override,
+						     "bpf_fentry_test1", NULL);
+	if (!ASSERT_ERR_PTR(link, "override_attached_bpf_fentry_test1")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	/* The should_fail_bio function is on error injection list,
+	 * attach should succeed.
+	 */
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_override,
+						     "should_fail_bio", NULL);
+	if (!ASSERT_OK_PTR(link, "override_attached_should_fail_bio"))
+		goto cleanup;
+
+	bpf_link__destroy(link);
+
+cleanup:
+	kprobe_multi_override__destroy(skel);
+}
+
 void serial_test_kprobe_multi_bench_attach(void)
 {
 	if (test__start_subtest("kernel"))
@@ -480,4 +515,6 @@ void test_kprobe_multi_test(void)
 		test_attach_api_syms();
 	if (test__start_subtest("attach_api_fails"))
 		test_attach_api_fails();
+	if (test__start_subtest("attach_override"))
+		test_attach_override();
 }

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

@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <bpf/btf.h>
+#include <test_progs.h>
+
+#include "test_bpf_ma.skel.h"
+
+void test_test_bpf_ma(void)
+{
+	struct test_bpf_ma *skel;
+	struct btf *btf;
+	int i, err;
+
+	skel = test_bpf_ma__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	btf = bpf_object__btf(skel->obj);
+	if (!ASSERT_OK_PTR(btf, "btf"))
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(skel->rodata->data_sizes); i++) {
+		char name[32];
+		int id;
+
+		snprintf(name, sizeof(name), "bin_data_%u", skel->rodata->data_sizes[i]);
+		id = btf__find_by_name_kind(btf, name, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, "bin_data"))
+			goto out;
+		skel->rodata->data_btf_ids[i] = id;
+	}
+
+	err = test_bpf_ma__load(skel);
+	if (!ASSERT_OK(err, "load"))
+		goto out;
+
+	err = test_bpf_ma__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_OK(skel->bss->err, "test error");
+out:
+	test_bpf_ma__destroy(skel);
+}

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

@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <net/if.h>
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#define LOCAL_NETNS "xdp_dev_bound_only_netns"
+
+static int load_dummy_prog(char *name, __u32 ifindex, __u32 flags)
+{
+	struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN() };
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+
+	opts.prog_flags = flags;
+	opts.prog_ifindex = ifindex;
+	return bpf_prog_load(BPF_PROG_TYPE_XDP, name, "GPL", insns, ARRAY_SIZE(insns), &opts);
+}
+
+/* A test case for bpf_offload_netdev->offload handling bug:
+ * - create a veth device (does not support offload);
+ * - create a device bound XDP program with BPF_F_XDP_DEV_BOUND_ONLY flag
+ *   (such programs are not offloaded);
+ * - create a device bound XDP program without flags (such programs are offloaded).
+ * This might lead to 'BUG: kernel NULL pointer dereference'.
+ */
+void test_xdp_dev_bound_only_offdev(void)
+{
+	struct nstoken *tok = NULL;
+	__u32 ifindex;
+	int fd1 = -1;
+	int fd2 = -1;
+
+	SYS(out, "ip netns add " LOCAL_NETNS);
+	tok = open_netns(LOCAL_NETNS);
+	if (!ASSERT_OK_PTR(tok, "open_netns"))
+		goto out;
+	SYS(out, "ip link add eth42 type veth");
+	ifindex = if_nametoindex("eth42");
+	if (!ASSERT_NEQ(ifindex, 0, "if_nametoindex")) {
+		perror("if_nametoindex");
+		goto out;
+	}
+	fd1 = load_dummy_prog("dummy1", ifindex, BPF_F_XDP_DEV_BOUND_ONLY);
+	if (!ASSERT_GE(fd1, 0, "load_dummy_prog #1")) {
+		perror("load_dummy_prog #1");
+		goto out;
+	}
+	/* Program with ifindex is considered offloaded, however veth
+	 * does not support offload => error should be reported.
+	 */
+	fd2 = load_dummy_prog("dummy2", ifindex, 0);
+	ASSERT_EQ(fd2, -EINVAL, "load_dummy_prog #2 (offloaded)");
+
+out:
+	close(fd1);
+	close(fd2);
+	close_netns(tok);
+	/* eth42 was added inside netns, removing the netns will
+	 * also remove eth42 veth pair.
+	 */
+	SYS_NOFAIL("ip netns del " LOCAL_NETNS);
+}

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

@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("kprobe.multi")
+int test_override(struct pt_regs *ctx)
+{
+	bpf_override_return(ctx, 123);
+	return 0;
+}

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

@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+struct generic_map_value {
+	void *data;
+};
+
+char _license[] SEC("license") = "GPL";
+
+const unsigned int data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
+const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
+
+int err = 0;
+int pid = 0;
+
+#define DEFINE_ARRAY_WITH_KPTR(_size) \
+	struct bin_data_##_size { \
+		char data[_size - sizeof(void *)]; \
+	}; \
+	struct map_value_##_size { \
+		struct bin_data_##_size __kptr * data; \
+		/* To emit BTF info for bin_data_xx */ \
+		struct bin_data_##_size not_used; \
+	}; \
+	struct { \
+		__uint(type, BPF_MAP_TYPE_ARRAY); \
+		__type(key, int); \
+		__type(value, struct map_value_##_size); \
+		__uint(max_entries, 128); \
+	} array_##_size SEC(".maps");
+
+static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int batch,
+					     unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old, *new;
+
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 1;
+			return;
+		}
+		new = bpf_obj_new_impl(data_btf_ids[idx], NULL);
+		if (!new) {
+			err = 2;
+			return;
+		}
+		old = bpf_kptr_xchg(&value->data, new);
+		if (old) {
+			bpf_obj_drop(old);
+			err = 3;
+			return;
+		}
+	}
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 4;
+			return;
+		}
+		old = bpf_kptr_xchg(&value->data, NULL);
+		if (!old) {
+			err = 5;
+			return;
+		}
+		bpf_obj_drop(old);
+	}
+}
+
+#define CALL_BATCH_ALLOC_FREE(size, batch, idx) \
+	batch_alloc_free((struct bpf_map *)(&array_##size), batch, idx)
+
+DEFINE_ARRAY_WITH_KPTR(8);
+DEFINE_ARRAY_WITH_KPTR(16);
+DEFINE_ARRAY_WITH_KPTR(32);
+DEFINE_ARRAY_WITH_KPTR(64);
+DEFINE_ARRAY_WITH_KPTR(96);
+DEFINE_ARRAY_WITH_KPTR(128);
+DEFINE_ARRAY_WITH_KPTR(192);
+DEFINE_ARRAY_WITH_KPTR(256);
+DEFINE_ARRAY_WITH_KPTR(512);
+DEFINE_ARRAY_WITH_KPTR(1024);
+DEFINE_ARRAY_WITH_KPTR(2048);
+DEFINE_ARRAY_WITH_KPTR(4096);
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int test_bpf_mem_alloc_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 8-bytes objects in batch to trigger refilling,
+	 * then free 128 8-bytes objects in batch to trigger freeing.
+	 */
+	CALL_BATCH_ALLOC_FREE(8, 128, 0);
+	CALL_BATCH_ALLOC_FREE(16, 128, 1);
+	CALL_BATCH_ALLOC_FREE(32, 128, 2);
+	CALL_BATCH_ALLOC_FREE(64, 128, 3);
+	CALL_BATCH_ALLOC_FREE(96, 128, 4);
+	CALL_BATCH_ALLOC_FREE(128, 128, 5);
+	CALL_BATCH_ALLOC_FREE(192, 128, 6);
+	CALL_BATCH_ALLOC_FREE(256, 128, 7);
+	CALL_BATCH_ALLOC_FREE(512, 64, 8);
+	CALL_BATCH_ALLOC_FREE(1024, 32, 9);
+	CALL_BATCH_ALLOC_FREE(2048, 16, 10);
+	CALL_BATCH_ALLOC_FREE(4096, 8, 11);
+
+	return 0;
+}

tools/testing/selftests/bpf/test_verifier.c

@@ -1880,7 +1880,7 @@ int main(int argc, char **argv)
 		}
 	}
 
-	get_unpriv_disabled();
+	unpriv_disabled = get_unpriv_disabled();
 	if (unpriv && unpriv_disabled) {
 		printf("Cannot run as unprivileged user with sysctl %s.\n",
 		       UNPRIV_SYSCTL);