Merge v6.18.40linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

12 files changed, 679 insertions, 36 deletions

diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 4bc2d25f33e1..6cb56501a505 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -8,6 +8,7 @@
 #include <errno.h>
 #include <syscall.h>
 #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
+#include <linux/args.h>
 
 static inline unsigned int bpf_num_possible_cpus(void)
 {
@@ -21,25 +22,43 @@ static inline unsigned int bpf_num_possible_cpus(void)
 	return possible_cpus;
 }
 
-/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
- * is zero-terminated string no matter what (unless sz == 0, in which case
- * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
- * in what is returned. Given this is internal helper, it's trivial to extend
- * this, when necessary. Use this instead of strncpy inside libbpf source code.
+/*
+ * Simplified strscpy() implementation. The kernel one is in lib/string.c
  */
-static inline void bpf_strlcpy(char *dst, const char *src, size_t sz)
+static inline ssize_t sized_strscpy(char *dest, const char *src, size_t count)
 {
-	size_t i;
+	long res = 0;
 
-	if (sz == 0)
-		return;
+	if (count == 0)
+		return -E2BIG;
 
-	sz--;
-	for (i = 0; i < sz && src[i]; i++)
-		dst[i] = src[i];
-	dst[i] = '\0';
+	while (count > 1) {
+		char c;
+
+		c = src[res];
+		dest[res] = c;
+		if (!c)
+			return res;
+		res++;
+		count--;
+	}
+
+	/* Force NUL-termination. */
+	dest[res] = '\0';
+
+	/* Return E2BIG if the source didn't stop */
+	return src[res] ? -E2BIG : res;
 }
 
+#define __strscpy0(dst, src, ...)	\
+	sized_strscpy(dst, src, sizeof(dst))
+#define __strscpy1(dst, src, size)	\
+	sized_strscpy(dst, src, size)
+
+#undef strscpy /* Redefine the placeholder from tools/include/linux/string.h */
+#define strscpy(dst, src, ...)	\
+	CONCATENATE(__strscpy, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__)
+
 #define __bpf_percpu_val_align	__attribute__((__aligned__(8)))
 
 #define BPF_DECLARE_PERCPU(type, name)				\
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 20cede4db3ce..45cd0b479fe3 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -86,7 +86,7 @@ static int __enable_controllers(const char *cgroup_path, const char *controllers
 		enable[len] = 0;
 		close(fd);
 	} else {
-		bpf_strlcpy(enable, controllers, sizeof(enable));
+		strscpy(enable, controllers);
 	}
 
 	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_attr_size.c b/tools/testing/selftests/bpf/prog_tests/bpf_attr_size.c
new file mode 100644
index 000000000000..32159dc64da8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_attr_size.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Google LLC */
+#include <linux/bpf.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <cgroup_helpers.h>
+#include "cgroup_skb_direct_packet_access.skel.h"
+
+#define OLD_QUERY_SIZE		offsetofend(union bpf_attr, query.prog_cnt)
+#define FULL_QUERY_SIZE		offsetofend(union bpf_attr, query.revision)
+
+static void test_query_size_boundaries(void)
+{
+	struct cgroup_skb_direct_packet_access *skel;
+	struct bpf_link *link = NULL;
+	union bpf_attr attr;
+	int cg_fd = -1;
+	int err;
+
+	skel = cgroup_skb_direct_packet_access__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		return;
+
+	cg_fd = test__join_cgroup("/attr_size_cg");
+	if (!ASSERT_GE(cg_fd, 0, "join_cgroup"))
+		goto cleanup;
+
+	link = bpf_program__attach_cgroup(skel->progs.direct_packet_access,
+					  cg_fd);
+	if (!ASSERT_OK_PTR(link, "cg_attach"))
+		goto cleanup;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.query.target_fd = cg_fd;
+	attr.query.attach_type = BPF_CGROUP_INET_INGRESS;
+	attr.query.revision = 0xdeadbeefdeadbeefULL;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, OLD_QUERY_SIZE);
+	if (ASSERT_OK(err, "query_old_size")) {
+		ASSERT_EQ(attr.query.prog_cnt, 1, "prog_cnt_written_old");
+		ASSERT_EQ(attr.query.revision, 0xdeadbeefdeadbeefULL,
+			  "revision_not_written_old");
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.query.target_fd = cg_fd;
+	attr.query.attach_type = BPF_CGROUP_INET_INGRESS;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, FULL_QUERY_SIZE);
+	if (!ASSERT_OK(err, "query_full_size"))
+		goto cleanup;
+
+	ASSERT_EQ(attr.query.prog_cnt, 1, "prog_cnt_written");
+	ASSERT_GT(attr.query.revision, 0, "revision_written");
+
+cleanup:
+	if (link)
+		bpf_link__destroy(link);
+	if (cg_fd >= 0)
+		close(cg_fd);
+	cgroup_skb_direct_packet_access__destroy(skel);
+}
+
+void test_bpf_attr_size(void)
+{
+	if (test__start_subtest("query_size_boundaries"))
+		test_query_size_boundaries();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
index e40114620751..f589eefbf9fb 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -469,7 +469,7 @@ verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets,
 
 		ASSERT_EQ(info.uprobe_multi.pid, getpid(), "info.uprobe_multi.pid");
 		ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count");
-		ASSERT_EQ(info.uprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN,
+		ASSERT_EQ(info.uprobe_multi.flags & BPF_F_UPROBE_MULTI_RETURN,
 			  retprobe, "info.uprobe_multi.flags.retprobe");
 		ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, "info.uprobe_multi.path_size");
 		ASSERT_STREQ(path_buf, path, "info.uprobe_multi.path");
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier_log.c b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
index 8337c6bc5b95..abc473c3741f 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier_log.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
@@ -317,6 +317,7 @@ static void verif_btf_log_subtest(bool bad_btf)
 	res = load_btf(&opts, true);
 	ASSERT_EQ(res, -ENOSPC, "half_log_fd");
 	ASSERT_EQ(strlen(logs.buf), 24, "log_fixed_25");
+	strscpy(op_name, "log_fixed", sizeof(op_name));
 	ASSERT_STRNEQ(logs.buf, logs.reference, 24, op_name);
 
 	/* validate rolling verifier log logic: try all variations of log buf
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
index d64ba7ddaed5..d7fb561ed4fb 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
@@ -52,7 +52,7 @@ SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx)
 		bpf_d_path(&file->f_path, d_path_buf, D_PATH_BUF_SIZE);
 
 		BPF_SEQ_PRINTF(seq, "%08llx ", vma->vm_pgoff << 12);
-		BPF_SEQ_PRINTF(seq, "%02x:%02x %u", MAJOR(dev), MINOR(dev),
+		BPF_SEQ_PRINTF(seq, "%02x:%02x %llu", MAJOR(dev), MINOR(dev),
 			       file->f_inode->i_ino);
 		BPF_SEQ_PRINTF(seq, "\t%s\n", d_path_buf);
 	} else {
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
index 0e04c31b91c0..774706e7b058 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_success.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -866,7 +866,7 @@ int BPF_PROG(test_populate, struct task_struct *task, u64 clone_flags)
 	 * access NR_CPUS, the upper bound for nr_cpus, so we infer
 	 * it from the size of cpumask_t.
 	 */
-	if (nr_cpus < 0 || nr_cpus >= CPUMASK_TEST_MASKLEN * 8) {
+	if (nr_cpus < 0 || nr_cpus > CPUMASK_TEST_MASKLEN * 8) {
 		err = 3;
 		goto out;
 	}
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 32127f1cd687..30f1de458669 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -6,6 +6,7 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
+#define BPF_NO_KFUNC_PROTOTYPES
 #include "vmlinux.h"
 #include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
@@ -36,12 +37,10 @@ enum bpf_fou_encap_type___local {
 	FOU_BPF_ENCAP_GUE___local,
 };
 
-struct bpf_fou_encap;
-
 int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
-			  struct bpf_fou_encap *encap, int type) __ksym;
+			  struct bpf_fou_encap___local *encap, int type) __ksym;
 int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
-			  struct bpf_fou_encap *encap) __ksym;
+			  struct bpf_fou_encap___local *encap) __ksym;
 struct xfrm_state *
 bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts,
 		       u32 opts__sz) __ksym;
@@ -781,7 +780,7 @@ int ipip_gue_set_tunnel(struct __sk_buff *skb)
 	encap.sport = 0;
 	encap.dport = bpf_htons(5555);
 
-	ret = bpf_skb_set_fou_encap(skb, (struct bpf_fou_encap *)&encap,
+	ret = bpf_skb_set_fou_encap(skb, &encap,
 				    bpf_core_enum_value(enum bpf_fou_encap_type___local,
 							FOU_BPF_ENCAP_GUE___local));
 	if (ret < 0) {
@@ -820,7 +819,7 @@ int ipip_fou_set_tunnel(struct __sk_buff *skb)
 	encap.sport = 0;
 	encap.dport = bpf_htons(5555);
 
-	ret = bpf_skb_set_fou_encap(skb, (struct bpf_fou_encap *)&encap,
+	ret = bpf_skb_set_fou_encap(skb, &encap,
 				    FOU_BPF_ENCAP_FOU___local);
 	if (ret < 0) {
 		log_err(ret);
@@ -843,7 +842,7 @@ int ipip_encap_get_tunnel(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	ret = bpf_skb_get_fou_encap(skb, (struct bpf_fou_encap *)&encap);
+	ret = bpf_skb_get_fou_encap(skb, &encap);
 	if (ret < 0) {
 		log_err(ret);
 		return TC_ACT_SHOT;
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index ea5db79da40e..f61733b736f9 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -1742,26 +1742,26 @@ __naked void bounds_refinement_tnum_umax(void *ctx)
 /* This test covers the bounds deduction when the u64 range and the tnum
  * overlap only at umin. After instruction 3, the ranges look as follows:
  *
- * 0    umin=0xe00     umax=0xeff                              U64_MAX
+ * 0    umin=0xe1      umax=0xf0                               U64_MAX
  * |    [xxxxxxxxxxxxxx]                                       |
  * |----------------------------|------------------------------|
  * |    x               x                                      | tnum values
  *
- * The verifier can therefore deduce that the R0=0xe0=224.
+ * The verifier can therefore deduce that the R0=0xe1=225.
  */
 SEC("socket")
 __description("bounds refinement with single-value tnum on umin")
-__msg("3: (15) if r0 == 0xf0 {{.*}} R0=224")
+__msg("3: (15) if r0 == 0xf1 {{.*}} R0=225")
 __success __log_level(2)
 __flag(BPF_F_TEST_REG_INVARIANTS)
 __naked void bounds_refinement_tnum_umin(void *ctx)
 {
 	asm volatile("			\
 	call %[bpf_get_prandom_u32];	\
-	r0 |= 0xe0;			\
-	r0 &= 0xf0;			\
-	if r0 == 0xf0 goto +2;		\
-	if r0 == 0xe0 goto +1;		\
+	r0 |= 0xe1;			\
+	r0 &= 0xf1;			\
+	if r0 == 0xf1 goto +2;		\
+	if r0 == 0xe1 goto +1;		\
 	r10 = 0;			\
 	exit;				\
 "	:
diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
index 8f755d2464cf..3b0c300c9cbd 100644
--- a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
+++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
+#include <limits.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
@@ -18,9 +19,9 @@ __naked void scalars(void)
 	r4 = r1;				\
 	w2 += 0x7FFFFFFF;			\
 	w4 += 0;				\
-	if r2 == 0 goto l1;			\
+	if r2 == 0 goto l0_%=;			\
 	exit;					\
-l1:						\
+l0_%=:						\
 	r4 >>= 63;				\
 	r3 = 1;					\
 	r3 -= r4;				\
@@ -31,4 +32,555 @@ l1:						\
 "	::: __clobber_all);
 }
 
+/*
+ * Test that sync_linked_regs() preserves register IDs.
+ *
+ * The sync_linked_regs() function copies bounds from known_reg to linked
+ * registers. When doing so, it must preserve each register's original id
+ * to allow subsequent syncs from the same source to work correctly.
+ *
+ */
+SEC("socket")
+__success
+__naked void sync_linked_regs_preserves_id(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	r0 &= 0xff;	/* r0 in [0, 255] */			\
+	r1 = r0;	/* r0, r1 linked with id 1 */		\
+	r1 += 4;	/* r1 has id=1 and off=4 in [4, 259] */ \
+	if r1 < 10 goto l0_%=;					\
+	/* r1 in [10, 259], r0 synced to [6, 255] */		\
+	r2 = r0;	/* r2 has id=1 and in [6, 255] */	\
+	if r1 < 14 goto l0_%=;					\
+	/* r1 in [14, 259], r0 synced to [10, 255] */		\
+	if r0 >= 10 goto l0_%=;					\
+	/* Never executed */					\
+	r0 /= 0;						\
+l0_%=:								\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success
+__naked void scalars_neg(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 += -4;					\
+	if r1 s< 0 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Same test but using BPF_SUB instead of BPF_ADD with negative immediate */
+SEC("socket")
+__success
+__naked void scalars_neg_sub(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 -= 4;					\
+	if r1 s< 0 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* alu32 with negative offset */
+SEC("socket")
+__success
+__naked void scalars_neg_alu32_add(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xff;					\
+	w1 = w0;					\
+	w1 += -4;					\
+	if w1 s< 0 goto l0_%=;				\
+	if w0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* alu32 with negative offset using SUB */
+SEC("socket")
+__success
+__naked void scalars_neg_alu32_sub(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xff;					\
+	w1 = w0;					\
+	w1 -= 4;					\
+	if w1 s< 0 goto l0_%=;				\
+	if w0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Positive offset: r1 = r0 + 4, then if r1 >= 6, r0 >= 2, so r0 != 0 */
+SEC("socket")
+__success
+__naked void scalars_pos(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	if r1 < 6 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* SUB with negative immediate: r1 -= -4 is equivalent to r1 += 4 */
+SEC("socket")
+__success
+__naked void scalars_sub_neg_imm(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 -= -4;					\
+	if r1 < 6 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Double ADD clears the ID (can't accumulate offsets) */
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_double_add(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r1 += 2;					\
+	r1 += 2;					\
+	if r1 < 6 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that sync_linked_regs() correctly handles large offset differences.
+ * r1.off = S32_MIN, r2.off = 1, delta = S32_MIN - 1 requires 64-bit math.
+ */
+SEC("socket")
+__success
+__naked void scalars_sync_delta_overflow(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r2 = r0;					\
+	r1 += %[s32_min];				\
+	r2 += 1;					\
+	if r2 s< 100 goto l0_%=;			\
+	if r1 s< 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  [s32_min]"i"(INT_MIN)
+	: __clobber_all);
+}
+
+/*
+ * Another large delta case: r1.off = S32_MAX, r2.off = -1.
+ * delta = S32_MAX - (-1) = S32_MAX + 1 requires 64-bit math.
+ */
+SEC("socket")
+__success
+__naked void scalars_sync_delta_overflow_large_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	r1 = r0;					\
+	r2 = r0;					\
+	r1 += %[s32_max];				\
+	r2 += -1;					\
+	if r2 s< 0 goto l0_%=;				\
+	if r1 s>= 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  [s32_max]"i"(INT_MAX)
+	: __clobber_all);
+}
+
+/*
+ * Test linked scalar tracking with alu32 and large positive offset (0x7FFFFFFF).
+ * After w1 += 0x7FFFFFFF, w1 wraps to negative for any r0 >= 1.
+ * If w1 is signed-negative, then r0 >= 1, so r0 != 0.
+ */
+SEC("socket")
+__success
+__naked void scalars_alu32_big_offset(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xff;					\
+	w1 = w0;					\
+	w1 += 0x7FFFFFFF;				\
+	if w1 s>= 0 goto l0_%=;				\
+	if w0 != 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_alu32_basic(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	w1 += 1;					\
+	if r1 > 10 goto 1f;				\
+	r0 >>= 32;					\
+	if r0 == 0 goto 1f;				\
+	r0 /= 0;					\
+1:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test alu32 linked register tracking with wrapping.
+ * R0 is bounded to [0xffffff00, 0xffffffff] (high 32-bit values)
+ * w1 += 0x100 causes R1 to wrap to [0, 0xff]
+ *
+ * After sync_linked_regs, if bounds are computed correctly:
+ *   R0 should be [0x00000000_ffffff00, 0x00000000_ffffff80]
+ *   R0 >> 32 == 0, so div by zero is unreachable
+ *
+ * If bounds are computed incorrectly (64-bit underflow):
+ *   R0 becomes [0xffffffff_ffffff00, 0xffffffff_ffffff80]
+ *   R0 >> 32 == 0xffffffff != 0, so div by zero is reachable
+ */
+SEC("socket")
+__success
+__naked void scalars_alu32_wrap(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w0 |= 0xffffff00;				\
+	r1 = r0;					\
+	w1 += 0x100;					\
+	if r1 > 0x80 goto l0_%=;			\
+	r2 = r0;					\
+	r2 >>= 32;					\
+	if r2 == 0 goto l0_%=;				\
+	r0 /= 0;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that sync_linked_regs() checks reg->id (the linked target register)
+ * for BPF_ADD_CONST32 rather than known_reg->id (the branch register).
+ */
+SEC("socket")
+__success
+__naked void scalars_alu32_zext_linked_reg(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;		/* r6 in [0, 0xFFFFFFFF] */	\
+	r7 = r6;		/* linked: same id as r6 */	\
+	w7 += 1;		/* alu32: r7.id |= BPF_ADD_CONST32 */ \
+	r8 = 0xFFFFffff ll;					\
+	if r6 < r8 goto l0_%=;					\
+	/* r6 in [0xFFFFFFFF, 0xFFFFFFFF] */			\
+	/* sync_linked_regs: known_reg=r6, reg=r7 */		\
+	/* CPU: w7 = (u32)(0xFFFFFFFF + 1) = 0, zext -> r7 = 0 */ \
+	/* With fix: r7 64-bit = [0, 0] (zext applied) */	\
+	/* Without fix: r7 64-bit = [0x100000000] (no zext) */	\
+	r7 >>= 32;						\
+	if r7 == 0 goto l0_%=;					\
+	r0 /= 0;		/* unreachable with fix */	\
+l0_%=:								\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that sync_linked_regs() skips propagation when one register used
+ * alu32 (BPF_ADD_CONST32) and the other used alu64 (BPF_ADD_CONST64).
+ * The delta relationship doesn't hold across different ALU widths.
+ */
+SEC("socket")
+__failure __msg("div by zero")
+__naked void scalars_alu32_alu64_cross_type(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;		/* r6 in [0, 0xFFFFFFFF] */	\
+	r7 = r6;		/* linked: same id as r6 */	\
+	w7 += 1;		/* alu32: BPF_ADD_CONST32, delta = 1 */ \
+	r8 = r6;		/* linked: same id as r6 */	\
+	r8 += 2;		/* alu64: BPF_ADD_CONST64, delta = 2 */ \
+	r9 = 0xFFFFffff ll;					\
+	if r7 < r9 goto l0_%=;					\
+	/* r7 = 0xFFFFFFFF */					\
+	/* sync: known_reg=r7 (ADD_CONST32), reg=r8 (ADD_CONST64) */ \
+	/* Without fix: r8 = zext(0xFFFFFFFF + 1) = 0 */	\
+	/* With fix: r8 stays [2, 0x100000001] (r8 >= 2) */	\
+	if r8 > 0 goto l1_%=;					\
+	goto l0_%=;						\
+l1_%=:								\
+	r0 /= 0;		/* div by zero */		\
+l0_%=:								\
+	r0 = 0;						\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that regsafe() prevents pruning when two paths reach the same program
+ * point with linked registers carrying different ADD_CONST flags (one
+ * BPF_ADD_CONST32 from alu32, another BPF_ADD_CONST64 from alu64).
+ */
+SEC("socket")
+__failure __msg("div by zero")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void scalars_alu32_alu64_regsafe_pruning(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;		/* r6 in [0, 0xFFFFFFFF] */	\
+	r7 = r6;		/* linked: same id as r6 */	\
+	/* Get another random value for the path branch */	\
+	call %[bpf_get_prandom_u32];				\
+	if r0 > 0 goto l_pathb_%=;				\
+	/* Path A: alu32 */					\
+	w7 += 1;		/* BPF_ADD_CONST32, delta = 1 */\
+	goto l_merge_%=;					\
+l_pathb_%=:							\
+	/* Path B: alu64 */					\
+	r7 += 1;		/* BPF_ADD_CONST64, delta = 1 */\
+l_merge_%=:							\
+	/* Merge point: regsafe() compares path B against cached path A. */ \
+	/* Narrow r6 to trigger sync_linked_regs for r7 */	\
+	r9 = 0xFFFFffff ll;					\
+	if r6 < r9 goto l0_%=;					\
+	/* r6 = 0xFFFFFFFF */					\
+	/* sync: r7 = 0xFFFFFFFF + 1 = 0x100000000 */		\
+	/* Path A: zext -> r7 = 0 */				\
+	/* Path B: no zext -> r7 = 0x100000000 */		\
+	r7 >>= 32;						\
+	if r7 == 0 goto l0_%=;					\
+	r0 /= 0;		/* div by zero on path B */	\
+l0_%=:								\
+	r0 = 0;						\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success
+void alu32_negative_offset(void)
+{
+	volatile char path[5];
+	volatile int offset = bpf_get_prandom_u32();
+	int off = offset;
+
+	if (off >= 5 && off < 10)
+		path[off - 5] = '.';
+
+	/* So compiler doesn't say: error: variable 'path' set but not used */
+	__sink(path[0]);
+}
+
+/*
+ * Test that r += r (self-add, src_reg == dst_reg) clears the scalar ID
+ * so that sync_linked_regs() does not propagate an incorrect delta.
+ */
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_self_add_clears_id(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	r6 = r0;		/* r6 unknown, id A */		\
+	r7 = r6;		/* r7 linked to r6, id A */	\
+	call %[bpf_get_prandom_u32];				\
+	r8 = r0;		/* r8 unknown, id B */		\
+	r9 = r8;		/* r9 linked to r8, id B */	\
+	if r7 != 1 goto l_exit_%=;				\
+	/* r7 == 1; sync propagates: r6 = 1 (known, id A) */	\
+	r6 += r6;		/* r6 = 2; should clear id */	\
+	if r7 == r9 goto l_exit_%=;				\
+	/* Bug: r6 synced to r7(1)+delta(2)=3; Fix: r6 = 2 */	\
+	if r6 == 3 goto l_exit_%=;				\
+	r0 /= 0;						\
+l_exit_%=:							\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Same as above but with alu32 such that w6 += w6 also clears id. */
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_self_add_alu32_clears_id(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;						\
+	w7 = w6;						\
+	call %[bpf_get_prandom_u32];				\
+	w8 = w0;						\
+	w9 = w8;						\
+	if w7 != 1 goto l_exit_%=;				\
+	w6 += w6;						\
+	if w7 == w9 goto l_exit_%=;				\
+	if w6 == 3 goto l_exit_%=;				\
+	r0 /= 0;						\
+l_exit_%=:							\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that stale delta from a cleared BPF_ADD_CONST does not leak
+ * through assign_scalar_id_before_mov() into a new id, causing
+ * sync_linked_regs() to compute an incorrect offset.
+ */
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_stale_delta_from_cleared_id(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	r6 = r0;		/* r6 unknown, gets id A */	\
+	r6 += 5;		/* id A|ADD_CONST, delta 5 */	\
+	r6 ^= 0;		/* id cleared; delta stays 5 */	\
+	r8 = r6;		/* new id B, stale delta 5 */	\
+	r8 += 3;		/* id B|ADD_CONST, delta 3 */	\
+	r9 = r6;		/* id B, stale delta 5 */	\
+	if r9 != 10 goto l_exit_%=;				\
+	/* Bug: r8 = 10+(3-5) = 8; Fix: r8 = 10+(3-0) = 13 */	\
+	if r8 == 8 goto l_exit_%=;				\
+	r0 /= 0;						\
+l_exit_%=:							\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Same as above but with alu32. */
+SEC("socket")
+__failure
+__msg("div by zero")
+__naked void scalars_stale_delta_from_cleared_id_alu32(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;						\
+	w6 += 5;						\
+	w6 ^= 0;						\
+	w8 = w6;						\
+	w8 += 3;						\
+	w9 = w6;						\
+	if w9 != 10 goto l_exit_%=;				\
+	if w8 == 8 goto l_exit_%=;				\
+	r0 /= 0;						\
+l_exit_%=:							\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_flowtable.c b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
index 7fdc7b23ee74..e67daa02749d 100644
--- a/tools/testing/selftests/bpf/progs/xdp_flowtable.c
+++ b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
@@ -15,7 +15,10 @@ struct bpf_flowtable_opts___local {
 	s32 error;
 };
 
-struct flow_offload_tuple_rhash *
+struct flow_offload_tuple_rhash___local {
+};
+
+struct flow_offload_tuple_rhash___local *
 bpf_xdp_flow_lookup(struct xdp_md *, struct bpf_fib_lookup *,
 		    struct bpf_flowtable_opts___local *, u32) __ksym;
 
@@ -67,7 +70,7 @@ int xdp_flowtable_do_lookup(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	struct bpf_flowtable_opts___local opts = {};
-	struct flow_offload_tuple_rhash *tuplehash;
+	struct flow_offload_tuple_rhash___local *tuplehash;
 	struct bpf_fib_lookup tuple = {
 		.ifindex = ctx->ingress_ifindex,
 	};
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 2f869daf8a06..9ca802285393 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -382,7 +382,7 @@ main()
 	local exit_command="poweroff -f"
 	local debug_shell="no"
 
-	while getopts ':hskl:id:j:' opt; do
+	while getopts ':hsl:id:j:' opt; do
 		case ${opt} in
 		l)
 			LOCAL_ROOTFS_IMAGE="$OPTARG"