Merge drm/drm-next into drm-misc-next

Backmerging to get drm-misc-next up to v7.3-rc2. Requested for
commit 3a2c4d55e32a ("treewide: refresh kmalloc_obj() conversions").

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>

67 files changed, 3548 insertions, 118 deletions

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0ba307e78fe1..4d5993da9f94 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -27,6 +27,7 @@ CFLAGS += -fno-strict-aliasing
 ifeq ($(CC_NO_CLANG), 0)
   CLANG_TARGET_FLAGS_arm	:= arm-linux-gnueabi
   CLANG_TARGET_FLAGS_arm64	:= aarch64-linux-gnu
+  CLANG_TARGET_FLAGS_loongarch	:= loongarch64-linux-gnu
   CLANG_TARGET_FLAGS_m68k	:= m68k-linux-gnu
   CLANG_TARGET_FLAGS_mips	:= mipsel-linux-gnu
   CLANG_TARGET_FLAGS_powerpc	:= powerpc64le-linux-gnu
@@ -1142,6 +1143,7 @@ ifndef NO_RUST
   ifneq ($(CROSS_COMPILE),)
     RUST_TARGET_FLAGS_arm	:= arm-unknown-linux-gnueabi
     RUST_TARGET_FLAGS_arm64	:= aarch64-unknown-linux-gnu
+    RUST_TARGET_FLAGS_loongarch	:= loongarch64-unknown-linux-gnu
     RUST_TARGET_FLAGS_m68k	:= m68k-unknown-linux-gnu
     RUST_TARGET_FLAGS_mips	:= mipsel-unknown-linux-gnu
     RUST_TARGET_FLAGS_powerpc	:= powerpc64le-unknown-linux-gnu
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 979d4cabfaf9..76f5e025e107 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -48,6 +48,7 @@
 extern int LINUX_KERNEL_VERSION __kconfig;
 extern const char CONFIG_CC_VERSION_TEXT[64] __kconfig __weak;
 extern const char CONFIG_LOCALVERSION[64] __kconfig __weak;
+extern bool CONFIG_PREEMPT_RCU __kconfig __weak;
 
 /*
  * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can
@@ -97,6 +98,7 @@ s32 scx_bpf_pick_any_cpu_node(const cpumask_t *cpus_allowed, int node, u64 flags
 s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
 bool scx_bpf_task_running(const struct task_struct *p) __ksym;
 s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym;
+struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym __weak;
 struct rq *scx_bpf_locked_rq(void) __ksym;
 struct task_struct *scx_bpf_cpu_curr(s32 cpu) __ksym __weak;
 struct task_struct *scx_bpf_tid_to_task(u64 tid) __ksym __weak;
@@ -528,31 +530,102 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask)
 }
 
 /*
+ * True if the non-sleepable BPF trampoline prolog (__bpf_prog_enter) calls
+ * migrate_disable() for the current task. Recorded once by
+ * scx_lib_init_probe, an fentry program on bpf_scx_reg() that fires during
+ * the natural scheduler-attach call chain (auto-attached by scx_ops_attach!).
+ *
+ * Defaults to true (conservative). Over-reporting in is_migration_disabled()
+ * causes local-only dispatch, which is safe. Under-reporting can crash the
+ * scheduler, so we err high if the probe somehow fails to run.
+ */
+bool __scx_prolog_disables_migration __weak = true;
+
+/*
+ * scx_lib_init_probe - non-sleepable prolog probe.
+ *
+ * Attached to bpf_scx_reg(), the .reg callback in bpf_sched_ext_ops
+ * (kernel/sched/ext.c). The kernel's struct_ops machinery invokes
+ * bpf_scx_reg when userspace creates the scheduler link, before
+ * ops.init() fires. Its address is taken in the vtable, so the symbol
+ * is non-inlinable and has been stable since introduction.
+ *
+ * Entering via fentry runs us through __bpf_prog_enter -- the
+ * non-sleepable prolog that consumers of is_migration_disabled() live
+ * under.
+ *
+ * Loud warning: the prolog adds at most 1 to migration_disabled.
+ * Reading > 1 means something upstream in the
+ * bpf_struct_ops_link_create -> bpf_scx_reg path disabled migration
+ * before the prolog ran, invalidating the probe; audit and adjust.
+ */
+SEC("fentry/bpf_scx_reg") __weak
+int scx_lib_init_probe(void *ctx)
+{
+	if (bpf_core_field_exists(((struct task_struct *)0)->migration_disabled)) {
+		const struct task_struct *p = bpf_get_current_task_btf();
+		unsigned int md = p->migration_disabled;
+
+		if (md > 1)
+			bpf_printk("scx_lib_init_probe: unexpected migration_disabled=%u "
+				   "upstream of BPF prolog; probe result unreliable",
+				   md);
+
+		__scx_prolog_disables_migration = md > 0;
+	}
+	return 0;
+}
+
+/*
  * Return true if task @p cannot migrate to a different CPU, false
  * otherwise.
+ *
+ * IMPORTANT: designed for NON-SLEEPABLE BPF contexts only. Sleepable
+ * contexts (BPF_STRUCT_OPS_SLEEPABLE, SEC("syscall"),
+ * SEC("fentry.s/...")) enter via __bpf_prog_enter_sleepable() or
+ * __bpf_prog_enter_sleepable_recur(), both of which unconditionally
+ * call migrate_disable(); this helper can yield a false negative for
+ * p == current there, which can crash the scheduler.
  */
 static inline bool is_migration_disabled(const struct task_struct *p)
 {
 	/*
-	 * Testing p->migration_disabled in a BPF code is tricky because the
-	 * migration is _always_ disabled while running the BPF code.
-	 * The prolog (__bpf_prog_enter) and epilog (__bpf_prog_exit) for BPF
-	 * code execution disable and re-enable the migration of the current
-	 * task, respectively. So, the _current_ task of the sched_ext ops is
-	 * always migration-disabled. Moreover, p->migration_disabled could be
-	 * two or greater when a sched_ext ops BPF code (e.g., ops.tick) is
-	 * executed in the middle of the other BPF code execution.
+	 * Testing p->migration_disabled in BPF is tricky because the BPF prolog
+	 * (__bpf_prog_enter) may call migrate_disable() for the current task,
+	 * making migration_disabled == 1 even for tasks that are not truly
+	 * migration-disabled.
+	 *
+	 * Since commit 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for
+	 * trampoline.c"), the BPF prolog calls migrate_disable() only when
+	 * CONFIG_PREEMPT_RCU is enabled. Two fast paths cover the common cases:
+	 *
+	 *   1) CONFIG_PREEMPT_RCU: prolog always calls migrate_disable(), so
+	 *      migration_disabled == 1 for the current task is ambiguous.
+	 *      Disambiguate by checking p == current.
+	 *
+	 *   2) v6.18+ without CONFIG_PREEMPT_RCU: prolog never calls
+	 *      migrate_disable(), so migration_disabled == 1 is unambiguously
+	 *      a real migrate_disable() call.
 	 *
-	 * Therefore, we should decide that the _current_ task is
-	 * migration-disabled only when its migration_disabled count is greater
-	 * than one. In other words, when  p->migration_disabled == 1, there is
-	 * an ambiguity, so we should check if @p is the current task or not.
+	 * A slow path handles pre-v6.18 kernels without CONFIG_PREEMPT_RCU,
+	 * where the prolog historically called migrate_disable() unconditionally
+	 * but a cherry-picked downstream kernel may not. The runtime-probed flag
+	 * __scx_prolog_disables_migration (set by scx_lib_init_probe) distinguishes
+	 * the two cases without relying on the kernel version alone.
 	 */
 	if (bpf_core_field_exists(p->migration_disabled)) {
-		if (p->migration_disabled == 1)
-			return bpf_get_current_task_btf() != p;
-		else
-			return p->migration_disabled;
+		if (p->migration_disabled == 1) {
+			/* Fast path: prolog always disables migration */
+			if (CONFIG_PREEMPT_RCU)
+				return bpf_get_current_task_btf() != p;
+			/* Fast path: prolog never disables migration */
+			if (LINUX_KERNEL_VERSION >= KERNEL_VERSION(6, 18, 0))
+				return true;
+			/* Slow path: pre-v6.18, !PREEMPT_RCU - use runtime flag */
+			return __scx_prolog_disables_migration ?
+			       bpf_get_current_task_btf() != p : true;
+		}
+		return p->migration_disabled;
 	}
 	return false;
 }
@@ -1021,7 +1094,20 @@ static inline u64 scx_clock_task(u32 cpu)
 {
 	struct rq___local *rq = get_current_rq(cpu);
 
-	/* Equivalent to the kernel's rq_clock_task(). */
+	/*
+	 * Equivalent to the kernel's rq_clock_task(): wall-clock time minus
+	 * cumulative IRQ time (CONFIG_IRQ_TIME_ACCOUNTING) and hypervisor
+	 * steal time (CONFIG_PARAVIRT_TIME_ACCOUNTING). Without those configs,
+	 * it equals rq->clock.
+	 *
+	 * Conceptually this clock advances during idle (the idle task counts
+	 * as a running task), but rq->clock_task is only updated on scheduling
+	 * events. With NO_HZ_IDLE (the default), the periodic tick is stopped
+	 * on idle CPUs, so rq->clock_task is not refreshed while a CPU is
+	 * idle. Reading this clock for a remote idle CPU from a BPF timer
+	 * callback returns the value from when the CPU last went idle, making
+	 * the delta over an idle interval effectively zero.
+	 */
 	return rq ? rq->clock_task : 0;
 }
 
@@ -1032,9 +1118,23 @@ static inline u64 scx_clock_pelt(u32 cpu)
 	/*
 	 * Equivalent to the kernel's rq_clock_pelt(): subtracts
 	 * lost_idle_time from clock_pelt to absorb the jump that occurs
-	 * when clock_pelt resyncs with clock_task at idle exit. The result
-	 * is a continuous, capacity-invariant clock safe for both task
-	 * execution time stamping and cross-idle measurements.
+	 * when clock_pelt resyncs with clock_task at idle exit. The intent
+	 * is a continuous, capacity- and frequency-invariant clock that is
+	 * frozen during idle, IRQ, and hypervisor steal.
+	 *
+	 * However, like scx_clock_task(), this clock has a stale-read issue
+	 * for remote idle CPUs with NO_HZ_IDLE (the default). clock_pelt
+	 * itself advances at wall-clock rate (hardware-clock based), but
+	 * lost_idle_time is only updated via update_rq_clock_pelt(), which
+	 * requires update_rq_clock() to be called. With NO_HZ_IDLE, the
+	 * periodic tick is stopped on idle CPUs, so lost_idle_time is not
+	 * refreshed during idle. Reading this clock for a remote idle CPU
+	 * from a BPF timer callback therefore returns a value that drifts
+	 * at wall-clock rate -- the same stale behaviour as scx_clock_task().
+	 *
+	 * Without NO_HZ_IDLE, periodic ticks keep lost_idle_time nearly in
+	 * sync (stale by at most one tick period, ~1 ms), so the result is
+	 * accurate.
 	 */
 	return rq ? (rq->clock_pelt - rq->lost_idle_time) : 0;
 }
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
index 3ab642f92c8a..6944221f96cc 100644
--- a/tools/sched_ext/include/scx/compat.bpf.h
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -92,15 +92,20 @@ int bpf_cpumask_populate(struct bpf_cpumask *dst, void *src, size_t src__sz) __k
 
 /*
  * v6.19: Introduce lockless peek API for user DSQs.
+ * v7.1:  Fix scx_bpf_dsq_peek() spuriously returning NULL on non-empty
+ *        FIFO DSQs (2f2ea7709266).
  *
- * Preserve the following macro until v6.21.
+ * The kfunc exists from v6.19 but can return NULL for a non-empty FIFO DSQ
+ * before the v7.1 fix. Require kernel version >= 7.1.0 before calling it;
+ * otherwise fall through to the bpf_iter_scx_dsq fallback below.
  */
 static inline struct task_struct *__COMPAT_scx_bpf_dsq_peek(u64 dsq_id)
 {
 	struct task_struct *p = NULL;
 	struct bpf_iter_scx_dsq it;
 
-	if (bpf_ksym_exists(scx_bpf_dsq_peek))
+	if (bpf_ksym_exists(scx_bpf_dsq_peek) &&
+	    LINUX_KERNEL_VERSION >= KERNEL_VERSION(7, 1, 0))
 		return scx_bpf_dsq_peek(dsq_id);
 	if (!bpf_iter_scx_dsq_new(&it, dsq_id, 0))
 		p = bpf_iter_scx_dsq_next(&it);
@@ -239,6 +244,26 @@ static inline bool __COMPAT_is_enq_cpu_selected(u64 enq_flags)
 	 scx_bpf_pick_any_cpu(cpus_allowed, flags))
 
 /*
+ * v6.18: Add a helper to retrieve the current task running on a CPU.
+ *
+ * The kernel tree dropped this helper and scx_bpf_cpu_rq(), but schedulers in
+ * this tree still support pre-v6.18 kernels where scx_bpf_cpu_curr() doesn't
+ * resolve and the scx_bpf_cpu_rq() fallback still exists. Keep it until
+ * pre-v6.18 kernels fall out of the support window.
+ */
+static inline struct task_struct *__COMPAT_scx_bpf_cpu_curr(int cpu)
+{
+	struct rq *rq;
+
+	if (bpf_ksym_exists(scx_bpf_cpu_curr))
+		return scx_bpf_cpu_curr(cpu);
+
+	rq = scx_bpf_cpu_rq(cpu);
+
+	return rq ? rq->curr : NULL;
+}
+
+/*
  * v6.19: To work around BPF maximum parameter limit, the following kfuncs are
  * replaced with variants that pack scalar arguments in a struct. Wrappers are
  * provided to maintain source compatibility.
@@ -379,6 +404,17 @@ static inline void scx_bpf_task_set_dsq_vtime(struct task_struct *p, u64 vtime)
 }
 
 /*
+ * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This
+ * will eventually deprecate scx_bpf_reenqueue_local().
+ */
+void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak;
+
+static inline bool __COMPAT_has_generic_reenq(void)
+{
+	return bpf_ksym_exists(scx_bpf_dsq_reenq___compat);
+}
+
+/*
  * v6.19: The new void variant can be called from anywhere while the older v1
  * variant can only be called from ops.cpu_release(). The double ___ prefixes on
  * the v2 variant need to be removed once libbpf is updated to ignore ___ prefix
@@ -395,21 +431,31 @@ static inline bool __COMPAT_scx_bpf_reenqueue_local_from_anywhere(void)
 
 static inline void scx_bpf_reenqueue_local(void)
 {
-	if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere())
+	if (__COMPAT_has_generic_reenq())
+		scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0);
+	else if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere())
 		scx_bpf_reenqueue_local___v2___compat();
 	else
 		scx_bpf_reenqueue_local___v1();
 }
 
-/*
- * v7.1: New scx_bpf_dsq_reenq() that allows re-enqueues on more DSQs. This
- * will eventually deprecate scx_bpf_reenqueue_local().
- */
-void scx_bpf_dsq_reenq___compat(u64 dsq_id, u64 reenq_flags) __ksym __weak;
-
-static inline bool __COMPAT_has_generic_reenq(void)
+static inline int scx_bpf_reenqueue_local_from_anywhere(void)
 {
-	return bpf_ksym_exists(scx_bpf_dsq_reenq___compat);
+	/*
+	 * The generic reenq kfunc and the v2 reenqueue-local variant can both be
+	 * called from anywhere; v1 cannot. Test each ksym in its own branch with a
+	 * distinct call: combining them with || would fold into a bitwise OR of the
+	 * two ksym addresses, which the verifier rejects.
+	 */
+	if (__COMPAT_has_generic_reenq()) {
+		scx_bpf_dsq_reenq___compat(SCX_DSQ_LOCAL, 0);
+		return 0;
+	}
+	if (__COMPAT_scx_bpf_reenqueue_local_from_anywhere()) {
+		scx_bpf_reenqueue_local___v2___compat();
+		return 0;
+	}
+	return -EOPNOTSUPP;
 }
 
 static inline void scx_bpf_dsq_reenq(u64 dsq_id, u64 reenq_flags)
diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
index d2e4384df5af..7c12df45fdba 100644
--- a/tools/sched_ext/include/scx/compat.h
+++ b/tools/sched_ext/include/scx/compat.h
@@ -10,9 +10,14 @@
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
 #include <fcntl.h>
+#include <stdint.h>
+#include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <unistd.h>
 
+#include "enums_abi.autogen.h"
+
 struct btf *__COMPAT_vmlinux_btf __attribute__((weak));
 
 static inline void __COMPAT_load_vmlinux_btf(void)
@@ -23,6 +28,85 @@ static inline void __COMPAT_load_vmlinux_btf(void)
 	}
 }
 
+/*
+ * Recover the true value of a 64-bit enum enumerator whose kernel BTF entry
+ * was truncated to its low 32 bits.
+ *
+ * Kernels whose BTF was generated without BTF_KIND_ENUM64 support encode
+ * 64-bit enums as 8-byte BTF_KIND_ENUM entries whose enumerator values only
+ * carry the low 32 bits. This happens with pahole < 1.24, which predates
+ * ENUM64, and with pahole passing --skip_encoding_btf_enum64 (e.g. Google's
+ * Container-Optimized OS / GKE kernels deliberately pass it for backward
+ * compatibility with older BTF consumers). The high bits
+ * can't be recovered from kernel BTF, so substitute the value from the
+ * vmlinux.h this tree was built against, cross-checked against the low 32
+ * bits the kernel did provide.
+ *
+ * Note that this is a best-effort recovery, not a ground truth. The
+ * substitution assumes the running kernel agrees with this tree's vmlinux.h
+ * on the high 32 bits, but only the low 32 bits can actually be verified.
+ * The cross-check is vacuous for enumerators whose value has no low bits
+ * set (e.g. SCX_DSQ_FLAG_BUILTIN, __SCX_ENQ_INTERNAL_MASK,
+ * SCX_ENQ_CLEAR_OPSS, SCX_ECODE_*): their lo32 is 0 and matches anything,
+ * so those substitutions rest entirely on the high bits never moving. An
+ * enumerator missing from the table (a kernel newer than this tree's
+ * vmlinux.h, or a stale autogen table) can't be recovered at all. If a
+ * substitution is ever wrong, the scheduler operates on bogus values (e.g.
+ * dispatching to nonexistent DSQ ids or silently dropping flags) and can
+ * wildly malfunction, which is why the mismatch and table-miss paths refuse
+ * instead of guessing.
+ */
+static inline bool __COMPAT_recover_truncated_enum64(const char *type,
+						     const char *name,
+						     u32 lo32, u64 *v)
+{
+	static bool warned;
+	size_t i;
+
+	for (i = 0; i < sizeof(__scx_enum_abi_vals) / sizeof(__scx_enum_abi_vals[0]); i++) {
+		const struct __scx_enum_abi_val *e = &__scx_enum_abi_vals[i];
+
+		if (strcmp(e->type, type) || strcmp(e->name, name))
+			continue;
+
+		if (e->val <= (u64)UINT32_MAX) {
+			*v = lo32;
+			return true;
+		}
+
+		if ((u32)e->val != lo32) {
+			fprintf(stderr, "ERROR: kernel BTF value of %s::%s (0x%x) doesn't match the low 32 bits of the vmlinux.h value (0x%llx); refusing to substitute\n",
+				type, name, lo32, (unsigned long long)e->val);
+			return false;
+		}
+
+		if (!warned) {
+			fprintf(stderr,
+				"WARNING: kernel BTF lacks BTF_KIND_ENUM64 encoding (generated by\n"
+				"WARNING: pahole < 1.24 or with --skip_encoding_btf_enum64), so 64-bit\n"
+				"WARNING: scx enum values are truncated to their low 32 bits in kernel\n"
+				"WARNING: BTF. Substituting the full 64-bit values from the vmlinux.h\n"
+				"WARNING: this binary was built against, cross-checked against the low\n"
+				"WARNING: 32 bits the kernel does provide. The high 32 bits cannot be\n"
+				"WARNING: verified: if the running kernel's actual values differ from\n"
+				"WARNING: the build-time vmlinux.h (e.g. an enum that moved in a newer\n"
+				"WARNING: kernel), the scheduler will operate on bogus values, such as\n"
+				"WARNING: dispatching to nonexistent DSQ ids, and can wildly malfunction.\n");
+			warned = true;
+		}
+		*v = e->val;
+		return true;
+	}
+
+	/*
+	 * Unknown enumerator (likely a stale autogen table). Fail
+	 * pessimistically to avoid returning an invalid value.
+	 */
+	fprintf(stderr, "ERROR: kernel BTF truncates 64-bit enum %s::%s to 0x%x; 64-bit variant not found in vmlinux.h\n",
+		type, name, lo32);
+	return false;
+}
+
 static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v)
 {
 	const struct btf_type *t;
@@ -46,6 +130,19 @@ static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v
 			n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off);
 			SCX_BUG_ON(!n, "btf__name_by_offset()");
 			if (!strcmp(n, name)) {
+				/*
+				 * Try to recover a 64-bit enum from an 8-byte
+				 * BTF_KIND_ENUM that was encoded without ENUM64
+				 * support (old pahole or
+				 * --skip_encoding_btf_enum64). Only scx_*
+				 * types are covered by the substitution table;
+				 * non-scx types fall through to the raw value
+				 * so this generic utility keeps working for
+				 * them.
+				 */
+				if (t->size == 8 && !strncmp(type, "scx_", 4))
+					return __COMPAT_recover_truncated_enum64(type, name,
+										 (u32)e[i].val, v);
 				*v = e[i].val;
 				return true;
 			}
diff --git a/tools/sched_ext/include/scx/enum_defs.autogen.h b/tools/sched_ext/include/scx/enum_defs.autogen.h
index 19aa1de3e700..63b6b14b19bd 100644
--- a/tools/sched_ext/include/scx/enum_defs.autogen.h
+++ b/tools/sched_ext/include/scx/enum_defs.autogen.h
@@ -56,6 +56,10 @@
 #define HAVE_SCX_DEQ_SLEEP
 #define HAVE_SCX_DEQ_CORE_SCHED_EXEC
 #define HAVE_SCX_DEQ_SCHED_CHANGE
+#define HAVE_SCX_DSP_NONE
+#define HAVE_SCX_DSP_LOCAL
+#define HAVE_SCX_DSP_PREV
+#define HAVE_SCX_DSP_RETRY
 #define HAVE_SCX_DSQ_FLAG_BUILTIN
 #define HAVE_SCX_DSQ_FLAG_LOCAL_ON
 #define HAVE_SCX_DSQ_INVALID
@@ -188,7 +192,6 @@
 #define HAVE_SCX_RQ_SUB_IDLE_RENOTIFY
 #define HAVE_SCX_RQ_ROOT_IDLE_RENOTIFY
 #define HAVE_SCX_RQ_IN_WAKEUP
-#define HAVE_SCX_RQ_IN_BALANCE
 #define HAVE_SCX_RQ_IN_DISPATCH
 #define HAVE_SCX_SCHED_PCPU_BYPASSING
 #define HAVE_SCX_SLICE_OOB_DUR_BITS
diff --git a/tools/sched_ext/include/scx/enums_abi.autogen.h b/tools/sched_ext/include/scx/enums_abi.autogen.h
new file mode 100644
index 000000000000..d53899764f5a
--- /dev/null
+++ b/tools/sched_ext/include/scx/enums_abi.autogen.h
@@ -0,0 +1,223 @@
+/*
+ * WARNING: This file is autogenerated from gen_enum_defs.py [1].
+ *
+ * scx enumerator values from the vmlinux.h this tree is built against.
+ * Used as the substitution source when the running kernel's BTF lacks
+ * BTF_KIND_ENUM64 encoding and 64-bit enum values are truncated.
+ *
+ * [1] https://github.com/sched-ext/scx/blob/main/scripts/gen_enum_defs.py
+ */
+
+#ifndef __ENUMS_ABI_AUTOGEN_H__
+#define __ENUMS_ABI_AUTOGEN_H__
+
+struct __scx_enum_abi_val {
+	const char *type;
+	const char *name;
+	u64 val;
+};
+
+static const struct __scx_enum_abi_val __scx_enum_abi_vals[]
+	__attribute__((unused)) = {
+	{ "scx_arena_consts", "SCX_ARENA_MIN_ORDER", 0x3LLU },
+	{ "scx_arena_consts", "SCX_ARENA_GROW_PAGES", 0x4LLU },
+	{ "scx_cap_flags", "__SCX_CAP_ENQ_IMMED", 0x0LLU },
+	{ "scx_cap_flags", "__SCX_CAP_ENQ", 0x1LLU },
+	{ "scx_cap_flags", "__SCX_CAP_PREEMPT", 0x2LLU },
+	{ "scx_cap_flags", "__SCX_CAP_PERF", 0x3LLU },
+	{ "scx_cap_flags", "__SCX_NR_CAPS", 0x4LLU },
+	{ "scx_cap_flags", "__SCX_CAP_ALL", 0xfLLU },
+	{ "scx_cap_flags", "SCX_CAP_ENQ_IMMED", 0x1LLU },
+	{ "scx_cap_flags", "SCX_CAP_ENQ", 0x2LLU },
+	{ "scx_cap_flags", "SCX_CAP_PREEMPT", 0x4LLU },
+	{ "scx_cap_flags", "SCX_CAP_PERF", 0x8LLU },
+	{ "scx_cap_flags", "SCX_CAP_BASE", 0x1LLU },
+	{ "scx_cap_flags", "SCX_CAPS_REENQ_ON_LOSS", 0x3LLU },
+	{ "scx_cid_consts", "SCX_CID_SHARD_SIZE_DFL", 0x18LLU },
+	{ "scx_cid_consts", "SCX_CID_SHARD_MAX_CPUS", 0x200LLU },
+	{ "scx_consts", "SCX_DSP_DFL_MAX_BATCH", 0x20LLU },
+	{ "scx_consts", "SCX_DSP_MAX_LOOPS", 0x20LLU },
+	{ "scx_consts", "SCX_WATCHDOG_MAX_TIMEOUT", 0x7530LLU },
+	{ "scx_consts", "SCX_RESCUE_DFL_BW_PPT", 0x14LLU },
+	{ "scx_consts", "SCX_RESCUE_MAX_BW_PPT", 0xfaLLU },
+	{ "scx_consts", "SCX_RESCUE_DISABLE", 0xffffffffLLU },
+	{ "scx_consts", "SCX_RESCUE_DFL_QUANTUM_US", 0x1388LLU },
+	{ "scx_consts", "SCX_RESCUE_MIN_QUANTUM_US", 0x3e8LLU },
+	{ "scx_consts", "SCX_RESCUE_MAX_QUANTUM_US", 0x186a0LLU },
+	{ "scx_consts", "SCX_RESCUE_MIN_SLICE_US", 0x3e8LLU },
+	{ "scx_consts", "SCX_RESCUE_OVERLOAD_MULT", 0x10LLU },
+	{ "scx_consts", "SCX_RESCUE_MIN_OVERLOAD_MS", 0x3e8LLU },
+	{ "scx_consts", "SCX_RESCUE_MAX_OVERLOAD_MS", 0x3a98LLU },
+	{ "scx_consts", "SCX_TID_CHUNK", 0x400LLU },
+	{ "scx_consts", "SCX_EXIT_BT_LEN", 0x40LLU },
+	{ "scx_consts", "SCX_EXIT_MSG_LEN", 0x400LLU },
+	{ "scx_consts", "SCX_EXIT_DUMP_DFL_LEN", 0x8000LLU },
+	{ "scx_consts", "SCX_CPUPERF_ONE", 0x400LLU },
+	{ "scx_consts", "SCX_TASK_ITER_BATCH", 0x20LLU },
+	{ "scx_consts", "SCX_BYPASS_HOST_NTH", 0x2LLU },
+	{ "scx_consts", "SCX_BYPASS_LB_DFL_INTV_US", 0x7a120LLU },
+	{ "scx_consts", "SCX_BYPASS_LB_DONOR_PCT", 0x7dLLU },
+	{ "scx_consts", "SCX_BYPASS_LB_MIN_DELTA_DIV", 0x4LLU },
+	{ "scx_consts", "SCX_BYPASS_LB_BATCH", 0x100LLU },
+	{ "scx_consts", "SCX_REENQ_MAX_REPEAT", 0x100LLU },
+	{ "scx_consts", "SCX_SUB_MAX_DEPTH", 0x4LLU },
+	{ "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_RT", 0x0LLU },
+	{ "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_DL", 0x1LLU },
+	{ "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_STOP", 0x2LLU },
+	{ "scx_cpu_preempt_reason", "SCX_CPU_PREEMPT_UNKNOWN", 0x3LLU },
+	{ "scx_deq_flags", "SCX_DEQ_SLEEP", 0x1LLU },
+	{ "scx_deq_flags", "SCX_DEQ_CORE_SCHED_EXEC", 0x100000000LLU },
+	{ "scx_deq_flags", "SCX_DEQ_SCHED_CHANGE", 0x200000000LLU },
+	{ "scx_dsp_verdict", "SCX_DSP_NONE", 0x0LLU },
+	{ "scx_dsp_verdict", "SCX_DSP_LOCAL", 0x1LLU },
+	{ "scx_dsp_verdict", "SCX_DSP_PREV", 0x2LLU },
+	{ "scx_dsp_verdict", "SCX_DSP_RETRY", 0x3LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_FLAG_BUILTIN", 0x8000000000000000LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_FLAG_LOCAL_ON", 0x4000000000000000LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_INVALID", 0x8000000000000000LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_GLOBAL", 0x8000000000000001LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_LOCAL", 0x8000000000000002LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_BYPASS", 0x8000000000000003LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_REJECT", 0x8000000000000004LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_RESCUE", 0x8000000000000005LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_LOCAL_ON", 0xc000000000000000LLU },
+	{ "scx_dsq_id_flags", "SCX_DSQ_LOCAL_CPU_MASK", 0xffffffffLLU },
+	{ "scx_dsq_iter_flags", "SCX_DSQ_ITER_REV", 0x10000LLU },
+	{ "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_SLICE", 0x40000000LLU },
+	{ "scx_dsq_iter_flags", "__SCX_DSQ_ITER_HAS_VTIME", 0x80000000LLU },
+	{ "scx_dsq_iter_flags", "__SCX_DSQ_ITER_USER_FLAGS", 0x10000LLU },
+	{ "scx_dsq_iter_flags", "__SCX_DSQ_ITER_ALL_FLAGS", 0xc0010000LLU },
+	{ "scx_dsq_lnode_flags", "SCX_DSQ_LNODE_ITER_CURSOR", 0x1LLU },
+	{ "scx_dsq_lnode_flags", "__SCX_DSQ_LNODE_PRIV_SHIFT", 0x10LLU },
+	{ "scx_enable_state", "SCX_ENABLING", 0x0LLU },
+	{ "scx_enable_state", "SCX_ENABLED", 0x1LLU },
+	{ "scx_enable_state", "SCX_DISABLING", 0x2LLU },
+	{ "scx_enable_state", "SCX_DISABLED", 0x3LLU },
+	{ "scx_enq_flags", "SCX_ENQ_WAKEUP", 0x1LLU },
+	{ "scx_enq_flags", "SCX_ENQ_HEAD", 0x10000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_CPU_SELECTED", 0x100000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_PREEMPT", 0x100000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_IMMED", 0x200000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_RESCUE", 0x400000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_REENQ", 0x10000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_LAST", 0x20000000000LLU },
+	{ "scx_enq_flags", "__SCX_ENQ_INTERNAL_MASK", 0xff00000000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_CLEAR_OPSS", 0x100000000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_DSQ_PRIQ", 0x200000000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_NESTED", 0x400000000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_GDSQ_FALLBACK", 0x800000000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_IGNORE_CAPS", 0x1000000000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_APPLY_SLICE", 0x2000000000000000LLU },
+	{ "scx_enq_flags", "SCX_ENQ_SLICE_DFL", 0x4000000000000000LLU },
+	{ "scx_ent_dsq_flags", "SCX_TASK_DSQ_ON_PRIQ", 0x1LLU },
+	{ "scx_ent_flags", "SCX_TASK_QUEUED", 0x1LLU },
+	{ "scx_ent_flags", "SCX_TASK_IN_CUSTODY", 0x2LLU },
+	{ "scx_ent_flags", "SCX_TASK_RESET_RUNNABLE_AT", 0x4LLU },
+	{ "scx_ent_flags", "SCX_TASK_DEQD_FOR_SLEEP", 0x8LLU },
+	{ "scx_ent_flags", "SCX_TASK_SUB_INIT", 0x10LLU },
+	{ "scx_ent_flags", "SCX_TASK_IMMED", 0x20LLU },
+	{ "scx_ent_flags", "SCX_TASK_PROTECTED", 0x40LLU },
+	{ "scx_ent_flags", "SCX_TASK_STATE_SHIFT", 0x8LLU },
+	{ "scx_ent_flags", "SCX_TASK_STATE_BITS", 0x3LLU },
+	{ "scx_ent_flags", "SCX_TASK_STATE_MASK", 0x700LLU },
+	{ "scx_ent_flags", "SCX_TASK_NONE", 0x0LLU },
+	{ "scx_ent_flags", "SCX_TASK_INIT_BEGIN", 0x100LLU },
+	{ "scx_ent_flags", "SCX_TASK_INIT", 0x200LLU },
+	{ "scx_ent_flags", "SCX_TASK_READY", 0x300LLU },
+	{ "scx_ent_flags", "SCX_TASK_ENABLED", 0x400LLU },
+	{ "scx_ent_flags", "SCX_TASK_DEAD", 0x500LLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_REASON_SHIFT", 0xcLLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_REASON_BITS", 0x3LLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_REASON_MASK", 0x7000LLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_NONE", 0x0LLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_KFUNC", 0x1000LLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_IMMED", 0x2000LLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_PREEMPTED", 0x3000LLU },
+	{ "scx_ent_flags", "SCX_TASK_REENQ_CAP", 0x4000LLU },
+	{ "scx_ent_flags", "SCX_TASK_CURSOR", 0xffffffff80000000LLU },
+	{ "scx_exit_code", "SCX_ECODE_RSN_HOTPLUG", 0x100000000LLU },
+	{ "scx_exit_code", "SCX_ECODE_RSN_CGROUP_OFFLINE", 0x200000000LLU },
+	{ "scx_exit_code", "SCX_ECODE_ACT_RESTART", 0x1000000000000LLU },
+	{ "scx_exit_flags", "SCX_EFLAG_INITIALIZED", 0x1LLU },
+	{ "scx_exit_kind", "SCX_EXIT_NONE", 0x0LLU },
+	{ "scx_exit_kind", "SCX_EXIT_DONE", 0x1LLU },
+	{ "scx_exit_kind", "SCX_EXIT_UNREG", 0x40LLU },
+	{ "scx_exit_kind", "SCX_EXIT_UNREG_BPF", 0x41LLU },
+	{ "scx_exit_kind", "SCX_EXIT_UNREG_KERN", 0x42LLU },
+	{ "scx_exit_kind", "SCX_EXIT_SYSRQ", 0x43LLU },
+	{ "scx_exit_kind", "SCX_EXIT_PARENT", 0x44LLU },
+	{ "scx_exit_kind", "SCX_EXIT_PARENT_KILL", 0x45LLU },
+	{ "scx_exit_kind", "SCX_EXIT_ERROR", 0x400LLU },
+	{ "scx_exit_kind", "SCX_EXIT_ERROR_BPF", 0x401LLU },
+	{ "scx_exit_kind", "SCX_EXIT_ERROR_STALL", 0x402LLU },
+	{ "scx_exit_kind", "SCX_EXIT_ERROR_REENQ", 0x403LLU },
+	{ "scx_exit_kind", "SCX_EXIT_ERROR_RESCUE", 0x404LLU },
+	{ "scx_kf_allow_flags", "SCX_KF_ALLOW_UNLOCKED", 0x1LLU },
+	{ "scx_kf_allow_flags", "SCX_KF_ALLOW_INIT_CIDS", 0x2LLU },
+	{ "scx_kf_allow_flags", "SCX_KF_ALLOW_CPU_RELEASE", 0x4LLU },
+	{ "scx_kf_allow_flags", "SCX_KF_ALLOW_DISPATCH", 0x8LLU },
+	{ "scx_kf_allow_flags", "SCX_KF_ALLOW_ENQUEUE", 0x10LLU },
+	{ "scx_kf_allow_flags", "SCX_KF_ALLOW_SELECT_CPU", 0x20LLU },
+	{ "scx_kick_flags", "SCX_KICK_IDLE", 0x1LLU },
+	{ "scx_kick_flags", "SCX_KICK_PREEMPT", 0x2LLU },
+	{ "scx_kick_flags", "SCX_KICK_WAIT", 0x4LLU },
+	{ "scx_opi", "SCX_OPI_BEGIN", 0x0LLU },
+	{ "scx_opi", "SCX_OPI_NORMAL_BEGIN", 0x0LLU },
+	{ "scx_opi", "SCX_OPI_NORMAL_END", 0x21LLU },
+	{ "scx_opi", "SCX_OPI_CPU_HOTPLUG_BEGIN", 0x21LLU },
+	{ "scx_opi", "SCX_OPI_CPU_HOTPLUG_END", 0x23LLU },
+	{ "scx_opi", "SCX_OPI_END", 0x23LLU },
+	{ "scx_ops_flags", "SCX_OPS_KEEP_BUILTIN_IDLE", 0x1LLU },
+	{ "scx_ops_flags", "SCX_OPS_ENQ_LAST", 0x2LLU },
+	{ "scx_ops_flags", "SCX_OPS_ENQ_EXITING", 0x4LLU },
+	{ "scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL", 0x8LLU },
+	{ "scx_ops_flags", "SCX_OPS_ENQ_MIGRATION_DISABLED", 0x10LLU },
+	{ "scx_ops_flags", "SCX_OPS_ALLOW_QUEUED_WAKEUP", 0x20LLU },
+	{ "scx_ops_flags", "SCX_OPS_BUILTIN_IDLE_PER_NODE", 0x40LLU },
+	{ "scx_ops_flags", "SCX_OPS_ALWAYS_ENQ_IMMED", 0x80LLU },
+	{ "scx_ops_flags", "SCX_OPS_TID_TO_TASK", 0x100LLU },
+	{ "scx_ops_flags", "SCX_OPS_ALL_FLAGS", 0x1ffLLU },
+	{ "scx_ops_flags", "__SCX_OPS_INTERNAL_MASK", 0xff00000000000000LLU },
+	{ "scx_ops_flags", "SCX_OPS_HAS_CPU_PREEMPT", 0x100000000000000LLU },
+	{ "scx_ops_state", "SCX_OPSS_NONE", 0x0LLU },
+	{ "scx_ops_state", "SCX_OPSS_QUEUEING", 0x1LLU },
+	{ "scx_ops_state", "SCX_OPSS_QUEUED", 0x2LLU },
+	{ "scx_ops_state", "SCX_OPSS_DISPATCHING", 0x3LLU },
+	{ "scx_ops_state", "SCX_OPSS_QSEQ_SHIFT", 0x2LLU },
+	{ "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_CORE", 0x1LLU },
+	{ "scx_pick_idle_cpu_flags", "SCX_PICK_IDLE_IN_NODE", 0x2LLU },
+	{ "scx_public_consts", "SCX_OPS_NAME_LEN", 0x80LLU },
+	{ "scx_public_consts", "SCX_SLICE_DFL", 0x1312d00LLU },
+	{ "scx_public_consts", "SCX_SLICE_BYPASS", 0x4c4b40LLU },
+	{ "scx_public_consts", "SCX_SLICE_INF", 0xffffffffffffffffLLU },
+	{ "scx_reenq_flags", "SCX_REENQ_ANY", 0x1LLU },
+	{ "scx_reenq_flags", "SCX_REENQ_CAP_REVOKE", 0x2LLU },
+	{ "scx_reenq_flags", "__SCX_REENQ_FILTER_MASK", 0xffffLLU },
+	{ "scx_reenq_flags", "__SCX_REENQ_USER_MASK", 0x1LLU },
+	{ "scx_reenq_flags", "SCX_REENQ_TSR_RQ_OPEN", 0x100000000LLU },
+	{ "scx_reenq_flags", "SCX_REENQ_TSR_NOT_FIRST", 0x200000000LLU },
+	{ "scx_reenq_flags", "__SCX_REENQ_TSR_MASK", 0xf00000000LLU },
+	{ "scx_rq_flags", "SCX_RQ_ONLINE", 0x1LLU },
+	{ "scx_rq_flags", "SCX_RQ_CAN_STOP_TICK", 0x2LLU },
+	{ "scx_rq_flags", "SCX_RQ_CLK_VALID", 0x20LLU },
+	{ "scx_rq_flags", "SCX_RQ_BAL_CB_PENDING", 0x40LLU },
+	{ "scx_rq_flags", "SCX_RQ_SUB_IDLE_RENOTIFY", 0x80LLU },
+	{ "scx_rq_flags", "SCX_RQ_ROOT_IDLE_RENOTIFY", 0x100LLU },
+	{ "scx_rq_flags", "SCX_RQ_IN_WAKEUP", 0x10000LLU },
+	{ "scx_rq_flags", "SCX_RQ_IN_DISPATCH", 0x20000LLU },
+	{ "scx_sched_pcpu_flags", "SCX_SCHED_PCPU_BYPASSING", 0x1LLU },
+	{ "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_BITS", 0x2bLLU },
+	{ "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_BITS", 0x14LLU },
+	{ "scx_slice_oob_consts", "SCX_SLICE_OOB_DUR_MASK", 0x7ffffffffffLLU },
+	{ "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_SHIFT", 0x2bLLU },
+	{ "scx_slice_oob_consts", "SCX_SLICE_OOB_ID_MASK", 0xfffffLLU },
+	{ "scx_slice_oob_consts", "SCX_SLICE_OOB_PENDING", 0x8000000000000000LLU },
+	{ "scx_tg_flags", "SCX_TG_ONLINE", 0x1LLU },
+	{ "scx_tg_flags", "SCX_TG_INITED", 0x2LLU },
+	{ "scx_tg_flags", "SCX_TG_SUB_INIT", 0x4LLU },
+	{ "scx_wake_flags", "SCX_WAKE_FORK", 0x4LLU },
+	{ "scx_wake_flags", "SCX_WAKE_TTWU", 0x8LLU },
+	{ "scx_wake_flags", "SCX_WAKE_SYNC", 0x10LLU },
+};
+
+#endif /* __ENUMS_ABI_AUTOGEN_H__ */
diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c
index 64dd60b3e922..65dae9e45400 100644
--- a/tools/sched_ext/scx_central.bpf.c
+++ b/tools/sched_ext/scx_central.bpf.c
@@ -299,6 +299,7 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer)
 	u64 now = scx_bpf_now();
 	u64 nr_to_kick = nr_queued;
 	s32 i, curr_cpu;
+	int ret;
 
 	curr_cpu = bpf_get_smp_processor_id();
 	if (timer_pinned && (curr_cpu != central_cpu)) {
@@ -332,7 +333,10 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer)
 		scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT);
 	}
 
-	bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN);
+	ret = bpf_timer_start(timer, TIMER_INTERVAL_NS,
+			      timer_pinned ? BPF_F_TIMER_CPU_PIN : 0);
+	if (ret)
+		scx_bpf_error("bpf_timer_start failed (%d)", ret);
 	__sync_fetch_and_add(&nr_timers, 1);
 	return 0;
 }
diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c
index 64cf4dd964d6..454ebb820c5e 100644
--- a/tools/sched_ext/scx_flatcg.bpf.c
+++ b/tools/sched_ext/scx_flatcg.bpf.c
@@ -937,7 +937,7 @@ void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p,
 	if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to)))
 		return;
 
-	delta = time_delta(p->scx.dsq_vtime, from_cgc->tvtime_now);
+	delta = (s64)(p->scx.dsq_vtime - from_cgc->tvtime_now);
 	scx_bpf_task_set_dsq_vtime(p, to_cgc->tvtime_now + delta);
 }
 
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 5bb8b90a275a..9f6e61d7ca07 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -1246,7 +1246,8 @@ static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer)
 			   scx_read_event(&events, SCX_EV_BYPASS_ACTIVATE));
 	}
 
-	bpf_timer_start(timer, ONE_SEC_IN_NS, 0);
+	if (bpf_timer_start(timer, ONE_SEC_IN_NS, 0))
+		scx_bpf_error("failed to re-arm stats timer");
 	return 0;
 }
 
@@ -1268,7 +1269,8 @@ struct {
 static int lowpri_timerfn(void *map, int *key, struct bpf_timer *timer)
 {
 	scx_bpf_dsq_reenq(LOWPRI_DSQ, 0);
-	bpf_timer_start(timer, LOWPRI_INTV_NS, 0);
+	if (bpf_timer_start(timer, LOWPRI_INTV_NS, 0))
+		scx_bpf_error("failed to re-arm lowpri timer");
 	return 0;
 }
 
@@ -1747,7 +1749,8 @@ static void rr_advance(void)
 static int round_robin_timerfn(void *map, int *key, struct bpf_timer *timer)
 {
 	rr_advance();
-	bpf_timer_start(timer, round_robin_ns, 0);
+	if (bpf_timer_start(timer, round_robin_ns, 0))
+		scx_bpf_error("failed to re-arm round-robin timer");
 	return 0;
 }
 
diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c
index a329f901c5ed..0857d64c322a 100644
--- a/tools/testing/selftests/alsa/mixer-test.c
+++ b/tools/testing/selftests/alsa/mixer-test.c
@@ -319,8 +319,8 @@ static bool ctl_value_index_valid(struct ctl_data *ctl,
 
 		/* Only check step size if there is one and we're in bounds */
 		if (snd_ctl_elem_info_get_step(ctl->info) &&
-		    (int_val - snd_ctl_elem_info_get_min(ctl->info) %
-		     snd_ctl_elem_info_get_step(ctl->info))) {
+		    (int_val - snd_ctl_elem_info_get_min(ctl->info)) %
+		    snd_ctl_elem_info_get_step(ctl->info)) {
 			ksft_print_msg("%s.%d value %ld invalid for step %ld minimum %ld\n",
 				       ctl->name, index, int_val,
 				       snd_ctl_elem_info_get_step(ctl->info),
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_keyless.c b/tools/testing/selftests/bpf/prog_tests/btf_map_keyless.c
new file mode 100644
index 000000000000..3248bccc3557
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_keyless.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+/*
+ * A hash map with a key-less BTF (btf_key_type_id == 0) used to be accepted
+ * and then NULL-deref in btf_type_show() when dumped through bpffs. A fixed
+ * kernel rejects it at creation; verify that rejection, with a keyed positive
+ * control so the -EINVAL is about the missing key type and not some unrelated
+ * failure.
+ */
+static void check_keyless(int map_type, __u32 map_flags, int btf_fd, int val_id)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
+	int map_fd;
+
+	opts.map_flags = map_flags;
+	opts.btf_fd = btf_fd;
+	opts.btf_value_type_id = val_id;
+
+	/* Positive control: the same map with a real key type is accepted. */
+	opts.btf_key_type_id = val_id;
+	map_fd = bpf_map_create(map_type, "keyed_map", 4, 4, 8, &opts);
+	if (!ASSERT_GE(map_fd, 0, "keyed create is accepted"))
+		return;
+	close(map_fd);
+
+	/* A key-less BTF must be rejected. */
+	opts.btf_key_type_id = 0;
+	map_fd = bpf_map_create(map_type, "keyless_map", 4, 4, 8, &opts);
+	ASSERT_EQ(map_fd, -EINVAL, "key-less create is rejected");
+	if (map_fd >= 0)
+		close(map_fd);
+}
+
+void test_btf_map_keyless(void)
+{
+	int btf_fd, val_id;
+	struct btf *btf;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "btf__new_empty"))
+		return;
+
+	val_id = btf__add_int(btf, "int", 4, BTF_INT_SIGNED);
+	if (!ASSERT_GT(val_id, 0, "btf__add_int"))
+		goto out;
+
+	if (!ASSERT_OK(btf__load_into_kernel(btf), "btf__load_into_kernel"))
+		goto out;
+	btf_fd = btf__fd(btf);
+
+	if (test__start_subtest("hash"))
+		check_keyless(BPF_MAP_TYPE_HASH, 0, btf_fd, val_id);
+	if (test__start_subtest("rhash"))
+		check_keyless(BPF_MAP_TYPE_RHASH, BPF_F_NO_PREALLOC, btf_fd, val_id);
+out:
+	btf__free(btf);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/rhash.c b/tools/testing/selftests/bpf/prog_tests/rhash.c
index 98bb66907b7f..0641bd5b0a9e 100644
--- a/tools/testing/selftests/bpf/prog_tests/rhash.c
+++ b/tools/testing/selftests/bpf/prog_tests/rhash.c
@@ -172,6 +172,12 @@ void test_rhash(void)
 	if (test__start_subtest("test_rhash_delete_nonexistent"))
 		rhash_run("test_rhash_delete_nonexistent");
 
+	if (test__start_subtest("test_rhash_kptr_update"))
+		rhash_run("test_rhash_kptr_update");
+
+	if (test__start_subtest("test_rhash_kptr_delete"))
+		rhash_run("test_rhash_kptr_delete");
+
 	if (test__start_subtest("test_rhash_map_extra_presize"))
 		rhash_map_extra_presize();
 
diff --git a/tools/testing/selftests/bpf/prog_tests/rhash_timer.c b/tools/testing/selftests/bpf/prog_tests/rhash_timer.c
new file mode 100644
index 000000000000..3aad9fc02e06
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/rhash_timer.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <test_progs.h>
+#include "rhash_timer.skel.h"
+
+#define MAX_ATTEMPTS 256
+#define RCU_SYNC_INTERVAL 64
+
+static int pin_to_first_cpu(cpu_set_t *old_mask)
+{
+	cpu_set_t new_mask;
+	int cpu;
+
+	if (sched_getaffinity(0, sizeof(*old_mask), old_mask))
+		return -errno;
+
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++)
+		if (CPU_ISSET(cpu, old_mask))
+			break;
+	if (cpu == CPU_SETSIZE)
+		return -EINVAL;
+
+	CPU_ZERO(&new_mask);
+	CPU_SET(cpu, &new_mask);
+	if (sched_setaffinity(0, sizeof(new_mask), &new_mask))
+		return -errno;
+	return 0;
+}
+
+static int update_timer_map(int map_fd, __u64 key)
+{
+	__u64 value[3] = {};
+
+	return bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST);
+}
+
+static int run_prog(int prog_fd, struct bpf_test_run_opts *opts)
+{
+	int err;
+
+	err = bpf_prog_test_run_opts(prog_fd, opts);
+	if (err)
+		return err;
+	return opts->retval;
+}
+
+void test_rhash_timer(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct rhash_timer *skel = NULL;
+	cpu_set_t old_mask;
+	int map_fd = -1, arm_fd, cancel_fd;
+	bool affinity_set = false;
+	__u64 key = 1;
+	int attempt, err;
+
+	err = pin_to_first_cpu(&old_mask);
+	if (!ASSERT_OK(err, "pin_to_first_cpu"))
+		return;
+	affinity_set = true;
+
+	skel = rhash_timer__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto out;
+
+	map_fd = bpf_map__fd(skel->maps.timer_map);
+	if (!ASSERT_GE(map_fd, 0, "timer_map fd"))
+		goto out;
+	arm_fd = bpf_program__fd(skel->progs.arm_deleted_timer);
+	if (!ASSERT_GE(arm_fd, 0, "arm_deleted_timer fd"))
+		goto out;
+	cancel_fd = bpf_program__fd(skel->progs.cancel_recycled_timer);
+	if (!ASSERT_GE(cancel_fd, 0, "cancel_recycled_timer fd"))
+		goto out;
+
+	err = update_timer_map(map_fd, key);
+	if (!ASSERT_OK(err, "seed_timer_map"))
+		goto out;
+
+	for (attempt = 0; attempt < MAX_ATTEMPTS; attempt++) {
+		err = run_prog(arm_fd, &opts);
+		if (err) {
+			ASSERT_OK(err, "arm_deleted_timer");
+			goto out;
+		}
+		if (skel->bss->armed != attempt + 1) {
+			ASSERT_EQ(skel->bss->armed, attempt + 1, "armed");
+			goto out;
+		}
+		if (skel->bss->timer_init_err) {
+			ASSERT_OK(skel->bss->timer_init_err, "timer_init_err");
+			goto out;
+		}
+		if (skel->bss->timer_set_callback_err) {
+			ASSERT_OK(skel->bss->timer_set_callback_err,
+				  "timer_set_callback_err");
+			goto out;
+		}
+		if (skel->bss->timer_start_err) {
+			ASSERT_OK(skel->bss->timer_start_err, "timer_start_err");
+			goto out;
+		}
+
+		if ((attempt + 1) % RCU_SYNC_INTERVAL == 0) {
+			err = kern_sync_rcu();
+			if (err) {
+				ASSERT_OK(err, "kern_sync_rcu");
+				goto out;
+			}
+		}
+
+		err = update_timer_map(map_fd, ++key);
+		if (err) {
+			ASSERT_OK(err, "replace_timer_map");
+			goto out;
+		}
+
+		err = run_prog(cancel_fd, &opts);
+		if (err) {
+			ASSERT_OK(err, "cancel_recycled_timer");
+			goto out;
+		}
+		if (skel->bss->timer_cancel_err) {
+			ASSERT_OK(skel->bss->timer_cancel_err, "timer_cancel_err");
+			goto out;
+		}
+		if (skel->bss->cancelled)
+			break;
+	}
+
+	ASSERT_GT(skel->bss->cancelled, 0, "preserved timer");
+out:
+	if (map_fd >= 0)
+		bpf_map_delete_elem(map_fd, &key);
+	rhash_timer__destroy(skel);
+	if (affinity_set)
+		sched_setaffinity(0, sizeof(old_mask), &old_mask);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
index dd41b826be30..edce9c1b54fb 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include <linux/btf.h>
+#include <bpf/btf.h>
 #include "netif_receive_skb.skel.h"
+#include "snprintf_btf_void.skel.h"
 
 /* Demonstrate that bpf_snprintf_btf succeeds and that various data types
  * are formatted correctly.
@@ -58,3 +60,80 @@ void serial_test_snprintf_btf(void)
 cleanup:
 	netif_receive_skb__destroy(skel);
 }
+
+/*
+ * bpf_snprintf_btf() renders a type_id taken straight from the vmlinux BTF.
+ * Two such type_ids used to NULL-deref in the BTF show path:
+ *   - a "const void" (a modifier resolving to void) in btf_modifier_show()
+ *   - a BTF_KIND_VAR in btf_var_show() (base BTF has no resolved_ids)
+ * A fixed kernel renders both without crashing.
+ */
+static long run(struct snprintf_btf_void *skel, __u32 type_id)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	char ctx[8] = {};
+
+	skel->bss->type_id = type_id;
+	topts.ctx_in = ctx;
+	topts.ctx_size_in = sizeof(ctx);
+	if (!ASSERT_OK(bpf_prog_test_run_opts(bpf_program__fd(skel->progs.dump_type),
+					      &topts), "test_run"))
+		return -1;
+	return skel->bss->ret;
+}
+
+void test_snprintf_btf_void(void)
+{
+	const struct btf_type *t;
+	struct snprintf_btf_void *skel;
+	int i, n, cv = 0, var = 0;
+	struct btf *btf;
+
+	btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+	if (!btf) {
+		test__skip();
+		return;
+	}
+
+	skel = snprintf_btf_void__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		goto out_btf;
+
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n && !(cv && var); i++) {
+		t = btf__type_by_id(btf, i);
+		if (!cv && btf_kind(t) == BTF_KIND_CONST && t->type == 0)
+			cv = i;
+		/* Pick a VAR small enough to render from the program's buffer. */
+		if (!var && btf_kind(t) == BTF_KIND_VAR) {
+			long sz = btf__resolve_size(btf, t->type);
+
+			if (sz > 0 && sz <= (long)sizeof(skel->bss->obj))
+				var = i;
+		}
+	}
+
+	/* "const void" renders the "<unsupported kind:0>" placeholder. */
+	if (test__start_subtest("const_void")) {
+		if (cv) {
+			ASSERT_EQ(run(skel, cv),
+				  sizeof("<unsupported kind:0>") - 1, "ret");
+			ASSERT_STREQ(skel->bss->out, "<unsupported kind:0>",
+				     "placeholder");
+		} else {
+			test__skip();
+		}
+	}
+
+	/* A BTF_KIND_VAR must resolve and render without error. */
+	if (test__start_subtest("var")) {
+		if (var)
+			ASSERT_GT(run(skel, var), 0, "ret");
+		else
+			test__skip();
+	}
+
+	snprintf_btf_void__destroy(skel);
+out_btf:
+	btf__free(btf);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index c930c7d7105b..fa7bb769ca31 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -59,10 +59,32 @@ void serial_test_timer_mim(void)
 	int err;
 
 	old_print_fn = libbpf_set_print(NULL);
-	timer_reject_skel = timer_mim_reject__open_and_load();
-	libbpf_set_print(old_print_fn);
-	if (!ASSERT_ERR_PTR(timer_reject_skel, "timer_reject_skel_load"))
+	timer_reject_skel = timer_mim_reject__open();
+	if (!ASSERT_OK_PTR(timer_reject_skel, "timer_reject_skel_open"))
+		goto cleanup;
+	bpf_program__set_autoload(timer_reject_skel->progs.test1, true);
+	err = timer_mim_reject__load(timer_reject_skel);
+	ASSERT_ERR(err, "timer_reject_skel_load");
+	timer_mim_reject__destroy(timer_reject_skel);
+
+	timer_reject_skel = timer_mim_reject__open();
+	if (!ASSERT_OK_PTR(timer_reject_skel, "callback_reject_skel_open"))
 		goto cleanup;
+	bpf_program__set_autoload(timer_reject_skel->progs.callback_map_uid_mismatch, true);
+	err = timer_mim_reject__load(timer_reject_skel);
+	ASSERT_ERR(err, "callback_reject_skel_load");
+	timer_mim_reject__destroy(timer_reject_skel);
+
+	timer_reject_skel = timer_mim_reject__open();
+	if (!ASSERT_OK_PTR(timer_reject_skel, "callback_accept_skel_open"))
+		goto cleanup;
+	bpf_program__set_autoload(timer_reject_skel->progs.callback_map_uid_match, true);
+	err = timer_mim_reject__load(timer_reject_skel);
+	if (!ASSERT_OK(err, "callback_accept_skel_load"))
+		goto cleanup;
+	timer_mim_reject__destroy(timer_reject_skel);
+	timer_reject_skel = NULL;
+	libbpf_set_print(old_print_fn);
 
 	timer_skel = timer_mim__open_and_load();
 	if (!timer_skel && errno == EOPNOTSUPP) {
@@ -75,6 +97,7 @@ void serial_test_timer_mim(void)
 	err = timer_mim(timer_skel);
 	ASSERT_OK(err, "timer_mim");
 cleanup:
+	libbpf_set_print(old_print_fn);
 	timer_mim__destroy(timer_skel);
 	timer_mim_reject__destroy(timer_reject_skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 62d7df9e80be..c6699159dacd 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -2149,4 +2149,43 @@ __naked int stack_misc_vs_scalar_in_a_loop(void)
 	);
 }
 
+__used
+static int loop_cb5(int i, __u64 *ctx)
+{
+	/* unsafe on a second iteration */
+	small_arr[*ctx] = i;
+	*ctx = 100500;
+	return 0;
+}
+
+SEC("raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("memory access is {{.*}} and is outside of the object of size 64")
+__naked void loop_counter_precision_2nd_iter(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"*(u64 *)(r10 - 8) = 0;"
+		"r1 = 2;"
+		"if r0 == 42 goto +1;"
+		"r1 = 1;"
+		"r2 = loop_cb5 ll;"
+		"r3 = r10;"
+		"r3 += -8;"
+		"r4 = 0;"
+		/*
+		 * Explore with nr_loops=1 on a first path and nr_loops=2 on a second path.
+		 * Buggy verifier did not propagate r1 precision properly,
+		 * and thus checkpoints created for nr_loops=1 case matched nr_loops=2 case.
+		 */
+		"call %[bpf_loop];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_loop),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_all
+	);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c
index 5e25ca806060..eee35d203b66 100644
--- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c
@@ -409,4 +409,41 @@ int reject_scalar_store_to_kptr(struct __sk_buff *ctx)
 	return 0;
 }
 
+SEC("?tc")
+__description("reject imprecise scalar store to kptr after state pruning")
+__failure __msg("invalid kptr access, R7 type=scalar")
+__naked void reject_imprecise_scalar_store_to_kptr(void)
+{
+	asm volatile (
+		"r0 = 0;"
+		"*(u32 *)(r10 - 4) = r0;"
+		"r2 = r10;"
+		"r2 += -4;"
+		"r1 = %[array_map] ll;"
+		"call %[bpf_map_lookup_elem];"
+		"if r0 == 0 goto l2_%=;"
+		"r6 = r0;"
+		"r9 = *(u64 *)(r6 + 0);"
+		"if r9 != 0 goto l0_%=;"
+		"r7 = 0;"
+		".rept 10;"
+		"r5 = 1;"
+		".endr;"
+		"goto l1_%=;"
+	"l0_%=:"
+		"r7 = 0x4141414141414141 ll;"
+		".rept 10;"
+		"r5 = 1;"
+		".endr;"
+	"l1_%=:"
+		"*(u64 *)(r6 + 8) = r7;"
+	"l2_%=:"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_map_lookup_elem),
+		  __imm_addr(array_map)
+		: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
index 08379c3b6a03..3701f4ea58c7 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
@@ -33,6 +33,20 @@ struct {
 	__type(value, struct elem);
 } array SEC(".maps");
 
+struct kernel_percpu_elem {
+	struct task_struct __percpu_kptr *task;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct kernel_percpu_elem);
+} kernel_percpu_array SEC(".maps");
+
+struct task_struct *bpf_task_from_pid(s32 pid) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
 long ret;
 
 SEC("?fentry/bpf_fentry_test1")
@@ -137,6 +151,51 @@ int BPF_PROG(test_array_map_5)
 	return 0;
 }
 
+SEC("?syscall")
+__failure __msg("invalid kptr access, R2 type=trusted_ptr_ expected=ptr_task_struct")
+int reject_kernel_ptr_into_percpu_kptr(void *ctx)
+{
+	struct kernel_percpu_elem *e;
+	struct task_struct *p, *old;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&kernel_percpu_array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_task_from_pid(1);
+	if (!p)
+		return 0;
+
+	old = bpf_kptr_xchg(&e->task, p);
+	if (old)
+		bpf_task_release(old);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("invalid kptr access, R2 type=ptr_ expected=ptr_val_t")
+int BPF_PROG(reject_plain_alloc_into_percpu_kptr)
+{
+	struct val_t __percpu_kptr *old;
+	struct val_t *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	old = bpf_kptr_xchg(&e->pc, p);
+	if (old)
+		bpf_percpu_obj_drop(old);
+	return 0;
+}
+
 SEC("?fentry.s/bpf_fentry_test1")
 __failure __msg("bpf_percpu_obj_new type ID argument must be of a struct of scalars")
 int BPF_PROG(test_array_map_6)
diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c
index 6d5fce7e6ffc..81c459435680 100644
--- a/tools/testing/selftests/bpf/progs/preempt_lock.c
+++ b/tools/testing/selftests/bpf/progs/preempt_lock.c
@@ -115,6 +115,58 @@ int preempt_sleepable_helper(void *ctx)
 	return 0;
 }
 
+SEC("?uprobe.s")
+__failure __msg("sleepable helper bpf_get_stack#")
+int preempt_sleepable_get_stack(struct pt_regs *ctx)
+{
+	struct bpf_stack_build_id stack;
+
+	bpf_preempt_disable();
+	bpf_get_stack(ctx, &stack, sizeof(stack),
+		      BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+	bpf_preempt_enable();
+	return 0;
+}
+
+SEC("?uprobe.s")
+__failure __msg("sleepable helper bpf_get_task_stack#")
+int preempt_sleepable_get_task_stack(void *ctx)
+{
+	struct bpf_stack_build_id stack;
+	struct task_struct *task;
+
+	task = bpf_get_current_task_btf();
+	bpf_preempt_disable();
+	bpf_get_task_stack(task, &stack, sizeof(stack),
+			   BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+	bpf_preempt_enable();
+	return 0;
+}
+
+SEC("?uprobe.s")
+__success
+int sleepable_get_stack(struct pt_regs *ctx)
+{
+	struct bpf_stack_build_id stack;
+
+	bpf_get_stack(ctx, &stack, sizeof(stack),
+		      BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+	return 0;
+}
+
+SEC("?uprobe.s")
+__success
+int sleepable_get_task_stack(void *ctx)
+{
+	struct bpf_stack_build_id stack;
+	struct task_struct *task;
+
+	task = bpf_get_current_task_btf();
+	bpf_get_task_stack(task, &stack, sizeof(stack),
+			   BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+	return 0;
+}
+
 SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
 __failure __msg("kernel func bpf_copy_from_user_str is sleepable within non-preemptible region")
 int preempt_sleepable_kfunc(void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
index 0d58114a4955..725d73c9ffe1 100644
--- a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
@@ -22,3 +22,56 @@ int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) {
     asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
     return 0;
 }
+
+/* Plain raw tracepoint arguments remain scalar values. */
+SEC("raw_tp/signal_generate")
+__success
+int test_raw_tp_signal_generate_info_scalar(void *ctx)
+{
+	asm volatile("r1 = *(u64 *)(r1 +8); if r1 != 1 goto +0;" ::: __clobber_all);
+	return 0;
+}
+
+/* tp_btf programs may inspect the sentinel as a scalar value. */
+SEC("tp_btf/signal_generate")
+__success
+int test_tp_btf_signal_generate_info_scalar(void *ctx)
+{
+	asm volatile("r1 = *(u64 *)(r1 +8); if r1 != 1 goto +0;" ::: __clobber_all);
+	return 0;
+}
+
+/* SEND_SIG_PRIV is non-NULL, so a NULL check cannot make info safe. */
+SEC("tp_btf/signal_generate")
+__failure __msg("R1 invalid mem access 'scalar'")
+int test_tp_btf_signal_generate_info_no_deref(void *ctx)
+{
+	asm volatile("r1 = *(u64 *)(r1 +8); if r1 == 0 goto +1; "
+		     "r1 = *(u32 *)(r1 +0);" ::: __clobber_all);
+	return 0;
+}
+
+SEC("tp_btf/signal_deliver")
+__failure __msg("R1 invalid mem access 'scalar'")
+int test_tp_btf_signal_deliver_info_no_deref(void *ctx)
+{
+	asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u32 *)(r1 +0);" ::: __clobber_all);
+	return 0;
+}
+
+SEC("tp_btf/sched_process_wait")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_sched_process_wait_arg_1(void *ctx)
+{
+	asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u32 *)(r1 +0);" ::: __clobber_all);
+	return 0;
+}
+
+SEC("tp_btf/sched_process_wait")
+__success
+int test_raw_tp_null_sched_process_wait_arg_1_checked(void *ctx)
+{
+	asm volatile("r1 = *(u64 *)(r1 +0); if r1 == 0 goto +1; "
+		     "r1 = *(u32 *)(r1 +0);" ::: __clobber_all);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c
index 555379952dcc..4504608196ab 100644
--- a/tools/testing/selftests/bpf/progs/rbtree_fail.c
+++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c
@@ -16,6 +16,7 @@ struct node_data {
 private(A) struct bpf_spin_lock glock;
 private(A) struct bpf_rb_root groot __contains(node_data, node);
 private(A) struct bpf_rb_root groot2 __contains(node_data, node);
+private(B) struct bpf_res_spin_lock res_glock;
 
 static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
 {
@@ -265,6 +266,53 @@ static bool less__bad_fn_call_first_unlock_after(struct bpf_rb_node *a, const st
 	return node_a->key < node_b->key;
 }
 
+static bool less__bad_res_spin_unlock(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	bpf_res_spin_unlock(&res_glock);
+	return false;
+}
+
+static __noinline void rbtree_cb_unlock_relock(void)
+{
+	bpf_spin_unlock(&glock);
+	bpf_spin_lock(&glock);
+}
+
+static __noinline void rbtree_cb_nested_unlock(void)
+{
+	rbtree_cb_unlock_relock();
+	asm volatile ("");
+}
+
+static bool less__bad_subprog_unlock(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+	rbtree_cb_nested_unlock();
+
+	return node_a->key < node_b->key;
+}
+
+static __noinline void rbtree_cb_noop(void)
+{
+	asm volatile ("");
+}
+
+static bool less__subprog_allowed(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+	rbtree_cb_noop();
+
+	return node_a->key < node_b->key;
+}
+
 static __always_inline
 long add_with_cb(bool (cb)(struct bpf_rb_node *a, const struct bpf_rb_node *b))
 {
@@ -301,4 +349,40 @@ long rbtree_api_add_bad_cb_bad_fn_call_first_unlock_after(void *ctx)
 	return add_with_cb(less__bad_fn_call_first_unlock_after);
 }
 
+SEC("?tc")
+__failure __msg("can't res_spin_{lock,unlock} in rbtree cb")
+long rbtree_api_add_bad_cb_res_spin_unlock(void *ctx)
+{
+	struct node_data *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	if (bpf_res_spin_lock(&res_glock)) {
+		bpf_spin_unlock(&glock);
+		bpf_obj_drop(n);
+		return 1;
+	}
+	bpf_rbtree_add(&groot, &n->node, less__bad_res_spin_unlock);
+	bpf_res_spin_unlock(&res_glock);
+	bpf_spin_unlock(&glock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("can't spin_{lock,unlock} in rbtree cb")
+long rbtree_api_add_bad_cb_subprog_unlock(void *ctx)
+{
+	return add_with_cb(less__bad_subprog_unlock);
+}
+
+SEC("?tc")
+__success
+long rbtree_api_add_cb_subprog_allowed(void *ctx)
+{
+	return add_with_cb(less__subprog_allowed);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index 31d4081c3a9f..cdb255addbc3 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -592,9 +592,9 @@ int non_own_ref_untrusted_ld(void *ctx)
 	}
 	bpf_rcu_read_unlock();
 	/*
-	 * The unlock leaves node as PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED
-	 * | NON_OWN_REF, and the load below has to get the BPF_PROBE_MEM
-	 * rewrite for it, otherwise a bad address panics the kernel.
+	 * The unlock leaves node as PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED,
+	 * and the load below has to get the BPF_PROBE_MEM rewrite for it,
+	 * otherwise a bad address panics the kernel.
 	 */
 	non_own_ref_key = node->key;
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
index 61906f48025c..cae00f7b0a24 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
@@ -23,6 +23,15 @@ struct map_value {
 	struct node_data __kptr *node;
 };
 
+struct node_refcount_only {
+	long key;
+	struct bpf_refcount refcount;
+};
+
+struct map_value_refcount_only {
+	struct node_refcount_only __kptr *node;
+};
+
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__type(key, int);
@@ -30,6 +39,13 @@ struct {
 	__uint(max_entries, 2);
 } stashed_nodes SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value_refcount_only);
+	__uint(max_entries, 1);
+} stashed_refcount_only SEC(".maps");
+
 struct node_acquire {
 	long key;
 	long data;
@@ -832,6 +848,51 @@ long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
 	return 0;
 }
 
+SEC("tc")
+__success
+long refcount_acquire_owning_input_no_null_check(void *ctx)
+{
+	struct node_refcount_only *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	m = bpf_refcount_acquire(n);
+	bpf_obj_drop(m);
+	bpf_obj_drop(n);
+
+	return 0;
+}
+
+SEC("?syscall")
+__success
+long refcount_acquire_rcu_map_kptr_null_checked(void *ctx)
+{
+	struct map_value_refcount_only *mapval;
+	struct node_refcount_only *n, *m;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx);
+	if (!mapval)
+		return 1;
+
+	bpf_rcu_read_lock();
+	n = mapval->node;
+	if (!n) {
+		bpf_rcu_read_unlock();
+		return 2;
+	}
+	m = bpf_refcount_acquire(n);
+	bpf_rcu_read_unlock();
+
+	if (!m)
+		return 3;
+	bpf_obj_drop(m);
+
+	return 0;
+}
+
 static long __stash_map_empty_xchg(struct node_data *n, int idx)
 {
 	struct map_value *mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
index eaaed0859f94..338e43822ffe 100644
--- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
@@ -19,6 +19,26 @@ struct node_refcounted {
 	struct bpf_refcount refcount;
 };
 
+struct node_refcount_only {
+	long key;
+	struct bpf_refcount refcount;
+};
+
+struct map_value_refcount_only {
+	struct node_refcount_only __kptr *node;
+};
+
+struct rcu_graph_node {
+	struct bpf_rb_node node;
+	long data;
+};
+
+struct rcu_graph_node *just_here_because_btf_bug;
+
+struct map_value_rcu_graph {
+	struct rcu_graph_node __kptr *node;
+};
+
 extern void bpf_rcu_read_lock(void) __ksym;
 extern void bpf_rcu_read_unlock(void) __ksym;
 
@@ -27,6 +47,22 @@ private(A) struct bpf_spin_lock glock;
 private(A) struct bpf_rb_root groot __contains(node_acquire, node);
 private(B) struct bpf_spin_lock lock;
 private(B) struct bpf_list_head head __contains(node_refcounted, list);
+private(C) struct bpf_spin_lock graph_lock;
+private(C) struct bpf_rb_root graph_root __contains(rcu_graph_node, node);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value_refcount_only);
+	__uint(max_entries, 1);
+} stashed_refcount_only SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value_rcu_graph);
+	__uint(max_entries, 1);
+} stashed_rcu_graph SEC(".maps");
 
 static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
 {
@@ -89,6 +125,120 @@ long refcount_acquire_non_object(void *ctx)
 	return bpf_refcount_acquire(ctx) != NULL;
 }
 
+SEC("?syscall")
+__failure __msg("Possibly NULL pointer passed to trusted R1")
+long refcount_acquire_rcu_map_kptr_unchecked_drop(void *ctx)
+{
+	struct map_value_refcount_only *mapval;
+	struct node_refcount_only *tmp, *n, *m;
+	int idx = 0;
+
+	/* Force Clang to emit complete BTF for struct node_refcount_only. */
+	tmp = bpf_obj_new(typeof(*tmp));
+	if (!tmp)
+		return 3;
+	bpf_obj_drop(tmp);
+
+	mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx);
+	if (!mapval)
+		return 1;
+
+	bpf_rcu_read_lock();
+	n = mapval->node;
+	if (!n) {
+		bpf_rcu_read_unlock();
+		return 2;
+	}
+	m = bpf_refcount_acquire(n);
+	bpf_rcu_read_unlock();
+
+	bpf_obj_drop(m);
+
+	return 0;
+}
+
+SEC("?syscall")
+__failure
+__msg("bpf_rbtree_remove can only take non-owning or refcounted "
+      "bpf_rb_node pointer")
+long rbtree_remove_after_rcu_unlock(void *ctx)
+{
+	struct map_value_rcu_graph *mapval;
+	struct bpf_rb_node *rb_node;
+	struct rcu_graph_node *node;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&stashed_rcu_graph, &idx);
+	if (!mapval)
+		return 0;
+
+	bpf_rcu_read_lock();
+	node = mapval->node;
+	if (!node) {
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+	bpf_rcu_read_unlock();
+
+	bpf_spin_lock(&graph_lock);
+	rb_node = bpf_rbtree_remove(&graph_root, &node->node);
+	bpf_spin_unlock(&graph_lock);
+	if (rb_node)
+		bpf_obj_drop(container_of(rb_node, struct rcu_graph_node, node));
+
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("R1 is neither owning or non-owning ref")
+long refcount_acquire_after_rcu_unlock(void *ctx)
+{
+	struct map_value_refcount_only *mapval;
+	struct node_refcount_only *node, *ref;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&stashed_refcount_only, &idx);
+	if (!mapval)
+		return 0;
+
+	bpf_rcu_read_lock();
+	node = mapval->node;
+	if (!node) {
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+	bpf_rcu_read_unlock();
+
+	ref = bpf_refcount_acquire(node);
+	if (ref)
+		bpf_obj_drop(ref);
+
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("invalid mem access 'scalar'")
+long graph_kptr_after_spin_unlock(void *ctx)
+{
+	struct map_value_rcu_graph *mapval;
+	struct rcu_graph_node *node;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&stashed_rcu_graph, &idx);
+	if (!mapval)
+		return 0;
+
+	bpf_spin_lock(&graph_lock);
+	node = mapval->node;
+	if (!node) {
+		bpf_spin_unlock(&graph_lock);
+		return 0;
+	}
+	bpf_spin_unlock(&graph_lock);
+
+	return node->data;
+}
+
 SEC("?tc")
 __failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}")
 long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
diff --git a/tools/testing/selftests/bpf/progs/rhash.c b/tools/testing/selftests/bpf/progs/rhash.c
index fc2dac3a719e..aea4de8dc781 100644
--- a/tools/testing/selftests/bpf/progs/rhash.c
+++ b/tools/testing/selftests/bpf/progs/rhash.c
@@ -19,6 +19,11 @@ struct elem {
 	int val;
 };
 
+struct special_elem {
+	struct task_struct __kptr *task;
+	int val;
+};
+
 struct {
 	__uint(type, BPF_MAP_TYPE_RHASH);
 	__uint(map_flags, BPF_F_NO_PREALLOC);
@@ -27,6 +32,17 @@ struct {
 	__type(value, struct elem);
 } rhmap SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_RHASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct special_elem);
+} special_fields SEC(".maps");
+
+extern struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
+extern void bpf_task_release(struct task_struct *p) __ksym;
+
 SEC("syscall")
 int test_rhash_lookup_update(void *ctx)
 {
@@ -246,3 +262,99 @@ int test_rhash_delete_nonexistent(void *ctx)
 	err = 0;
 	return 0;
 }
+
+SEC("syscall")
+int test_rhash_kptr_update(void *ctx)
+{
+	struct special_elem val1 = { .val = 1 };
+	struct special_elem val2 = { .val = 2 };
+	struct task_struct *task, *old;
+	struct special_elem *elem;
+	int key = 0;
+
+	err = 1;
+	if (bpf_map_update_elem(&special_fields, &key, &val1, BPF_NOEXIST))
+		return 1;
+
+	err = 2;
+	elem = bpf_map_lookup_elem(&special_fields, &key);
+	if (!elem)
+		return 2;
+
+	err = 3;
+	task = bpf_task_acquire(bpf_get_current_task_btf());
+	if (!task)
+		return 3;
+
+	err = 4;
+	old = bpf_kptr_xchg(&elem->task, task);
+	if (old) {
+		bpf_task_release(old);
+		return 4;
+	}
+
+	err = 5;
+	if (bpf_map_update_elem(&special_fields, &key, &val2, BPF_EXIST))
+		return 5;
+
+	err = 6;
+	elem = bpf_map_lookup_elem(&special_fields, &key);
+	if (!elem || elem->val != 2)
+		return 6;
+
+	err = 7;
+	old = bpf_kptr_xchg(&elem->task, NULL);
+	if (!old)
+		return 7;
+	bpf_task_release(old);
+
+	err = 8;
+	if (bpf_map_delete_elem(&special_fields, &key))
+		return 8;
+
+	err = 0;
+	return 0;
+}
+
+SEC("syscall")
+int test_rhash_kptr_delete(void *ctx)
+{
+	struct special_elem val = {};
+	struct task_struct *task, *old;
+	struct special_elem *elem;
+	int key = 0;
+
+	err = 1;
+	if (bpf_map_update_elem(&special_fields, &key, &val, BPF_NOEXIST))
+		return 1;
+
+	err = 2;
+	elem = bpf_map_lookup_elem(&special_fields, &key);
+	if (!elem)
+		return 2;
+
+	err = 3;
+	task = bpf_task_acquire(bpf_get_current_task_btf());
+	if (!task)
+		return 3;
+
+	err = 4;
+	old = bpf_kptr_xchg(&elem->task, task);
+	if (old) {
+		bpf_task_release(old);
+		return 4;
+	}
+
+	err = 5;
+	if (bpf_map_delete_elem(&special_fields, &key))
+		return 5;
+
+	err = 6;
+	old = bpf_kptr_xchg(&elem->task, NULL);
+	if (!old)
+		return 6;
+	bpf_task_release(old);
+
+	err = 0;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/rhash_timer.c b/tools/testing/selftests/bpf/progs/rhash_timer.c
new file mode 100644
index 000000000000..2e06a463c605
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rhash_timer.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+#define CLOCK_MONOTONIC 1
+#define TIMER_NSEC (60ULL * 1000 * 1000 * 1000)
+
+struct timer_value {
+	struct bpf_timer timer;
+	u64 data;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RHASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, 1);
+	__type(key, u64);
+	__type(value, struct timer_value);
+} timer_map SEC(".maps");
+
+u64 armed;
+u64 cancelled;
+long timer_init_err;
+long timer_set_callback_err;
+long timer_start_err;
+long timer_cancel_err;
+
+static int timer_cb(void *map, u64 *key, struct timer_value *value)
+{
+	return 0;
+}
+
+static long arm_timer_cb(struct bpf_map *map, u64 *key,
+			 struct timer_value *value, void *ctx)
+{
+	u64 key_copy = *key;
+	long err;
+
+	err = bpf_map_delete_elem(map, &key_copy);
+	if (err)
+		return 1;
+
+	err = bpf_timer_init(&value->timer, map, CLOCK_MONOTONIC);
+	if (err) {
+		timer_init_err = err;
+		return 1;
+	}
+
+	err = bpf_timer_set_callback(&value->timer, timer_cb);
+	if (err) {
+		timer_set_callback_err = err;
+		return 1;
+	}
+
+	err = bpf_timer_start(&value->timer, TIMER_NSEC, BPF_F_TIMER_CPU_PIN);
+	if (err) {
+		timer_start_err = err;
+		return 1;
+	}
+
+	__sync_fetch_and_add(&armed, 1);
+	return 1;
+}
+
+static long cancel_timer_cb(struct bpf_map *map, u64 *key,
+			    struct timer_value *value, void *ctx)
+{
+	long err;
+
+	err = bpf_timer_cancel(&value->timer);
+	if (err == -EINVAL)
+		return 1;
+	if (err < 0) {
+		timer_cancel_err = err;
+		return 1;
+	}
+
+	__sync_fetch_and_add(&cancelled, 1);
+	return 1;
+}
+
+SEC("syscall")
+int arm_deleted_timer(void *ctx)
+{
+	bpf_for_each_map_elem(&timer_map, arm_timer_cb, NULL, 0);
+	return 0;
+}
+
+SEC("syscall")
+int cancel_recycled_timer(void *ctx)
+{
+	bpf_for_each_map_elem(&timer_map, cancel_timer_cb, NULL, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/snprintf_btf_void.c b/tools/testing/selftests/bpf/progs/snprintf_btf_void.c
new file mode 100644
index 000000000000..44af80fbbb80
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/snprintf_btf_void.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "btf_ptr.h"
+#include <bpf/bpf_helpers.h>
+
+__u32 type_id;
+/* A buffer we own to render the selected type from, kept in bounds. */
+char obj[256];
+char out[64];
+long ret;
+
+SEC("raw_tp/sys_enter")
+int dump_type(void *ctx)
+{
+	struct btf_ptr ptr = {
+		.ptr = obj,
+		.type_id = type_id,
+		.flags = 0,
+	};
+
+	ret = bpf_snprintf_btf(out, sizeof(out), &ptr, sizeof(ptr), 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_callback.c b/tools/testing/selftests/bpf/progs/tailcall_callback.c
index c41632cf423b..14fa7a87028e 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_callback.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_callback.c
@@ -45,6 +45,13 @@ int callback_loop(int index, void **cb_ctx)
 }
 
 static __noinline
+int callback_tail(int index, void **cb_ctx)
+{
+	bpf_tail_call_static(*cb_ctx, &jmp_table, 0);
+	return 0;
+}
+
+static __noinline
 int callback_empty(int index, void *data)
 {
 	return 0;
@@ -78,4 +85,13 @@ int tailcall_callback_2(struct __sk_buff *skb)
 	return 0;
 }
 
+/* callback with a direct tail call is rejected without a verifier bug */
+SEC("tc")
+__failure __msg("cannot tail call within callback")
+int tailcall_callback_3(struct __sk_buff *skb)
+{
+	bpf_loop(1, callback_tail, &skb, 0);
+	return 0;
+}
+
 char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
index 0df8a12fd61e..a31a399870be 100644
--- a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
+++ b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
@@ -61,6 +61,7 @@
 #define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1)
 
 #define TLD_MAX_DATA_CNT (__PAGE_SIZE / sizeof(struct tld_metadata) - 1)
+#define TLD_DATA_SIZE (__PAGE_SIZE - sizeof(__u64))
 
 #ifndef TLD_NAME_LEN
 #define TLD_NAME_LEN 62
@@ -189,6 +190,8 @@ static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_s
 			return start + off;
 
 		off += TLD_ROUND_UP(metadata[i].size, 8);
+		if (off > TLD_DATA_SIZE)
+			break;
 	}
 
 	return -cnt;
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
index df43649ecb78..eda9b7bbab75 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
@@ -190,8 +190,8 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 	ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
 		      sizeof(opts_def));
 	if (ct) {
-		__u16 sport = bpf_get_prandom_u32();
-		__u16 dport = bpf_get_prandom_u32();
+		__u16 sport = bpf_get_prandom_u32() % 65535 + 1;
+		__u16 dport = bpf_get_prandom_u32() % 65535 + 1;
 		union nf_inet_addr saddr = {};
 		union nf_inet_addr daddr = {};
 		struct nf_conn *ct_ins;
@@ -293,8 +293,8 @@ nf_ct_opts_new_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *
 	ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
 		      sizeof(opts_def));
 	if (ct) {
-		__u16 sport = bpf_get_prandom_u32();
-		__u16 dport = bpf_get_prandom_u32();
+		__u16 sport = bpf_get_prandom_u32() % 65535 + 1;
+		__u16 dport = bpf_get_prandom_u32() % 65535 + 1;
 		union nf_inet_addr saddr = {};
 		union nf_inet_addr daddr = {};
 		struct nf_conn *ct_ins;
diff --git a/tools/testing/selftests/bpf/progs/timer_mim_reject.c b/tools/testing/selftests/bpf/progs/timer_mim_reject.c
index dd3f1ed6d6e6..83f31138336b 100644
--- a/tools/testing/selftests/bpf/progs/timer_mim_reject.c
+++ b/tools/testing/selftests/bpf/progs/timer_mim_reject.c
@@ -43,7 +43,7 @@ static int timer_cb(void *map, int *key, struct hmap_elem *val)
 	return 0;
 }
 
-SEC("fentry/bpf_fentry_test1")
+SEC("?fentry/bpf_fentry_test1")
 int BPF_PROG(test1, int a)
 {
 	struct hmap_elem init = {};
@@ -72,3 +72,85 @@ int BPF_PROG(test1, int a)
 		err |= 8;
 	return 0;
 }
+
+struct callback_ctx {
+	void *map;
+};
+
+static int mismatch_iter_cb(void *map, int *key, struct hmap_elem *val, struct callback_ctx *ctx)
+{
+	bpf_timer_init(&val->timer, ctx->map, CLOCK_MONOTONIC);
+	return 0;
+}
+
+static int timer_mismatch_cb(void *map, int *key, struct hmap_elem *val)
+{
+	struct callback_ctx ctx = { .map = map };
+	struct bpf_map *inner_map2;
+	int array_key2 = ARRAY_KEY2;
+
+	inner_map2 = bpf_map_lookup_elem(&outer_arr, &array_key2);
+	if (!inner_map2)
+		return 0;
+	bpf_for_each_map_elem(inner_map2, mismatch_iter_cb, &ctx, 0);
+	return 0;
+}
+
+static int match_iter_cb(void *map, int *key, struct hmap_elem *val, struct callback_ctx *ctx)
+{
+	bpf_timer_init(&val->timer, map, CLOCK_MONOTONIC);
+	return 0;
+}
+
+static int timer_match_cb(void *map, int *key, struct hmap_elem *val)
+{
+	struct callback_ctx ctx = {};
+	struct bpf_map *inner_map2;
+	int array_key2 = ARRAY_KEY2;
+
+	inner_map2 = bpf_map_lookup_elem(&outer_arr, &array_key2);
+	if (!inner_map2)
+		return 0;
+	bpf_for_each_map_elem(inner_map2, match_iter_cb, &ctx, 0);
+	return 0;
+}
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(callback_map_uid_mismatch, int a)
+{
+	struct hmap_elem *val;
+	struct bpf_map *inner_map;
+	int array_key = ARRAY_KEY;
+	int hash_key = HASH_KEY;
+
+	inner_map = bpf_map_lookup_elem(&outer_arr, &array_key);
+	if (!inner_map)
+		return 0;
+	val = bpf_map_lookup_elem(inner_map, &hash_key);
+	if (!val)
+		return 0;
+
+	bpf_timer_init(&val->timer, inner_map, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(&val->timer, timer_mismatch_cb);
+	return 0;
+}
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(callback_map_uid_match, int a)
+{
+	struct hmap_elem *val;
+	struct bpf_map *inner_map;
+	int array_key = ARRAY_KEY;
+	int hash_key = HASH_KEY;
+
+	inner_map = bpf_map_lookup_elem(&outer_arr, &array_key);
+	if (!inner_map)
+		return 0;
+	val = bpf_map_lookup_elem(inner_map, &hash_key);
+	if (!val)
+		return 0;
+
+	bpf_timer_init(&val->timer, inner_map, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(&val->timer, timer_match_cb);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
index 6bf95550a024..e0926767bbd3 100644
--- a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
+++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
@@ -62,6 +62,104 @@ int timer_sleepable_prog(void *ctx)
 	return 0;
 }
 
+static int timer_sys_bpf_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	__u64 attr = 0;
+
+	bpf_sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	return 0;
+}
+
+SEC("syscall")
+__failure __msg("sleepable helper bpf_sys_bpf#{{[0-9]+}} in non-sleepable prog")
+int timer_sys_bpf_prog(void *ctx)
+{
+	struct timer_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&timer_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_timer_init(&val->t, &timer_map, 0);
+	bpf_timer_set_callback(&val->t, timer_sys_bpf_cb);
+	return 0;
+}
+
+static int timer_sys_close_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	bpf_sys_close(0);
+	return 0;
+}
+
+SEC("syscall")
+__failure __msg("sleepable helper bpf_sys_close#{{[0-9]+}} in non-sleepable prog")
+int timer_sys_close_prog(void *ctx)
+{
+	struct timer_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&timer_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_timer_init(&val->t, &timer_map, 0);
+	bpf_timer_set_callback(&val->t, timer_sys_close_cb);
+	return 0;
+}
+
+static int timer_btf_find_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	char name[] = "task_struct";
+
+	bpf_btf_find_by_name_kind(name, sizeof(name), BTF_KIND_STRUCT, 0);
+	return 0;
+}
+
+SEC("syscall")
+__failure __msg("sleepable helper bpf_btf_find_by_name_kind#{{[0-9]+}} in non-sleepable prog")
+int timer_btf_find_prog(void *ctx)
+{
+	struct timer_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&timer_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_timer_init(&val->t, &timer_map, 0);
+	bpf_timer_set_callback(&val->t, timer_btf_find_cb);
+	return 0;
+}
+
+SEC("syscall")
+__success
+int syscall_sys_bpf_prog(void *ctx)
+{
+	__u64 attr = 0;
+
+	bpf_sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	return 0;
+}
+
+SEC("syscall")
+__success
+int syscall_sys_close_prog(void *ctx)
+{
+	bpf_sys_close(0);
+	return 0;
+}
+
+SEC("syscall")
+__success
+int syscall_btf_find_prog(void *ctx)
+{
+	char name[] = "task_struct";
+
+	bpf_btf_find_by_name_kind(name, sizeof(name), BTF_KIND_STRUCT, 0);
+	return 0;
+}
+
 /* Workqueue tests */
 
 struct wq_elem {
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 1a273e416fed..df8d5309657e 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -2267,6 +2267,47 @@ __naked void deduce64_from_32_wrapping_32bit(void)
 	: __clobber_all);
 }
 
+/*
+ * Unprivileged variable pointer arithmetic on a PTR_TO_MAP_VALUE whose
+ * offset collapses to a constant. The Spectre-v1 speculative path snapshots
+ * the pointer while its r32 has just been blanked but its offset not yet
+ * synced; the following register move used to trip reg_bounds_sanity_check()
+ * ("const subreg tnum out of sync with range bounds"). With
+ * BPF_F_TEST_REG_INVARIANTS that violation turns into a load failure, so the
+ * unprivileged program must still load.
+ */
+SEC("socket")
+__success __success_unpriv
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void spec_ptr_alu_const_offset(void)
+{
+	asm volatile ("							\
+	call %[bpf_ktime_get_ns];					\
+	*(u64*)(r10 - 16) = r0;						\
+	r1 = 0;								\
+	*(u64*)(r10 - 8) = r1;						\
+	r2 = r10;							\
+	r2 += -8;							\
+	r1 = %[map_hash_8b] ll;						\
+	call %[bpf_map_lookup_elem];					\
+	if r0 == 0 goto l0_%=;						\
+	r1 = *(u64*)(r10 - 16);						\
+	r2 = 0x40000000;						\
+	if r1 > r2 goto l0_%=;						\
+	if r1 s> 1 goto l0_%=;		/* r1 in [0, 1] */		\
+	r0 += r1;			/* ptr += bounded scalar */	\
+	r9 = r0;			/* used to trip the warning */	\
+	*(u8*)(r0 + 0) = r1;						\
+l0_%=:	r0 = 0;								\
+	exit;								\
+	"
+	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
 /* Check that range_within() compares cnum ranges, not min/max projections. */
 SEC("socket")
 __failure __msg("div by zero")
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
index 328cf630210a..a73b837553fb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -621,6 +621,116 @@ __naked void helper_call_does_not_prevent_bpf_fastcall(void)
 	: __clobber_all);
 }
 
+/* A jump to the first spill executes the whole pattern, rewrite is safe. */
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("subprog 0 (jump_to_first_spill) main {{.*}} stack 0")
+__xlated("2: if r0 == 0x2a goto pc+0")
+__xlated("3: r0 = ")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__success
+__naked void jump_to_first_spill(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r1 = 1;"
+	"if r0 == 42 goto l0_%=;"
+"l0_%=:"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+/* A jump to the call skips the spill, the pattern must be kept. */
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("subprog 0 (jump_to_call) main {{.*}} stack 8")
+__xlated("2: if r0 == 0x2a goto pc+1")
+__xlated("3: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("7: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void jump_to_call(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r1 = 1;"
+	"if r0 == 42 goto l0_%=;"
+	"*(u64 *)(r10 - 8) = r1;"
+"l0_%=:"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+/* A jump to the fill skips the spill, the pattern must be kept. */
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("subprog 0 (jump_to_fill) main {{.*}} stack 8")
+__xlated("2: if r0 == 0x2a goto pc+4")
+__xlated("3: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("7: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void jump_to_fill(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r1 = 1;"
+	"if r0 == 42 goto l0_%=;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+"l0_%=:"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+/* Same as above, but the fill is entered by an unconditional jump. */
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("subprog 0 (unconditional_jump_to_fill) main {{.*}} stack 8")
+__xlated("3: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("7: r1 = *(u64 *)(r10 -8)")
+__xlated("8: exit")
+__xlated("9: goto pc-3")
+__success
+__naked void unconditional_jump_to_fill(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r1 = 1;"
+	"if r0 == 42 goto l1_%=;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+"l0_%=:"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+"l1_%=:"
+	"goto l0_%=;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
 SEC("raw_tp")
 __arch_x86_64
 __log_level(4)
diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c
index c1f55e1d80a4..3c3bb03e8217 100644
--- a/tools/testing/selftests/bpf/progs/verifier_cfg.c
+++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c
@@ -3,6 +3,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
 #include "bpf_misc.h"
 
 SEC("socket")
@@ -56,6 +57,19 @@ __naked void out_of_range_jump2(void)
 }
 
 SEC("socket")
+__description("invalid DW LDSX instruction in diagnostics")
+__failure __msg("BUG_ldx_99")
+__log_level(2)
+__naked void invalid_dw_ldsx(void)
+{
+	asm volatile ("					\
+	.8byte %[ldsx_dw];				\
+"	:
+	: __imm_insn(ldsx_dw, BPF_RAW_INSN(BPF_LDX | BPF_MEMSX | BPF_DW, BPF_REG_0, BPF_REG_0, 0, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
 __description("loop (back-edge)")
 __failure __msg("unreachable insn 1")
 __msg_unpriv("back-edge")
diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c
index 9a13f5c11ac7..884080a5bffc 100644
--- a/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c
@@ -305,4 +305,33 @@ __naked void cpu_cgroup_storage_access_6(void)
 	: __clobber_all);
 }
 
+/*
+ * Verification takes two paths: with r2 being scalar zero on path (1)
+ * and with r2 being some other scalar on path (2).
+ * Check that the verifier does not use checkpoints created
+ * on path (1) to prune path (2).
+ */
+SEC("cgroup/skb")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("get_local_storage() doesn't support non-zero flags")
+__naked void non_zero_flags_on_a_pruned_path(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	/* r2 is 0 on the path explored first, 1 on the other */\
+	r2 = 1;						\
+	if r0 == 0 goto 1f;				\
+	r2 = 0;						\
+1:	r1 = %[cgroup_storage] ll;			\
+	call %[bpf_get_local_storage];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_get_local_storage),
+	  __imm_addr(cgroup_storage)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
index 0bdeb7bc4687..a3d2af8dc839 100644
--- a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
+++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
@@ -56,6 +56,30 @@ int trusted_task_arg_nullable(void *ctx)
 	return res;
 }
 
+/*
+ * Check that the verifier does not use checkpoints created
+ * on path with r1 == 0 to prune path with r1 != 0.
+ */
+SEC("?tp_btf/task_newtask")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("R1 type=scalar expected=ptr_, trusted_ptr_, rcu_ptr_")
+__naked int null_btf_id_arg_global_subprog(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"r1 = 42;"
+		"if r0 > 42 goto 1f;"
+		"r1 = 0;"
+	"1:"
+		"call subprog_trusted_task_nullable;"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_all);
+}
+
 __weak int subprog_trusted_task_nonnull(struct task_struct *task __arg_trusted)
 {
 	return task->pid + task->tgid;
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index 75dd922e4e9f..1fbcc5228306 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -169,6 +169,23 @@ static int iter_limit_cb(__u32 idx, struct num_context *ctx)
 }
 
 SEC("?raw_tp")
+__failure __msg("R1 type=ctx expected=scalar")
+__naked void bpf_loop_reject_pointer(void)
+{
+	asm volatile (
+		"r2 = %[iter_limit_cb];"
+		"r3 = 0;"
+		"r4 = 0;"
+		"call %[bpf_loop];"
+		"exit;"
+		:
+		: __imm_ptr(iter_limit_cb),
+		  __imm(bpf_loop)
+		: __clobber_common
+	);
+}
+
+SEC("?raw_tp")
 __success
 int bpf_loop_iter_limit_ok(void *unused)
 {
diff --git a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c
index 3d1e8de4390c..3c789c565b18 100644
--- a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c
+++ b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c
@@ -3,7 +3,9 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <stdbool.h>
 #include "bpf_misc.h"
+#include "bpf_kfuncs.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_XSKMAP);
@@ -12,6 +14,13 @@ struct {
 	__type(value, int);
 } map_xskmap SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} map_hash SEC(".maps");
+
 /* This is equivalent to the following program:
  *
  *   r6 = skb->sk;
@@ -264,4 +273,188 @@ __naked void jne_reg_reg_null_check(void)
         : __clobber_all);
 }
 
+/*
+ * A comparison between PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED and
+ * PTR_TO_MAP_VALUE_OR_NULL should not infer that map pointer is not null.
+ * A bug in check_cond_jmp_op() made such inference possible.
+ */
+SEC("raw_tp")
+__failure
+__msg("error: invalid dereference of R0 (a nullable map value pointer)")
+__msg(">>> 11 | (61) r0 = *(u32 *)(r0 +0)")
+__naked void untrusted_mem_does_not_infer_map_value_non_null(void)
+{
+	asm volatile ("					\
+	/* r6 = bpf_rdonly_cast(0, 0); */		\
+	r1 = 0;						\
+	r2 = 0;						\
+	call %[bpf_rdonly_cast];			\
+	r6 = r0;					\
+	/* r0 = bpf_map_lookup_elem(map_hash, &key); */	\
+	*(u64 *)(r10 - 8) = 0;				\
+	r1 = %[map_hash] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	/*						\
+	 * buggy verifier assumed that r6 can't be null	\
+	 * and marked r0 non-null as well.		\
+	 */						\
+	if r6 != r0 goto 1f;				\
+	r0 = *(u32 *)(r0 + 0);				\
+1:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_rdonly_cast),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash)
+	: __clobber_all);
+}
+
+/*
+ * A pointer with an offset that is not bounded from above may be null at
+ * runtime, hence it is not a witness for the pointer it is compared with.
+ */
+SEC("socket")
+__failure
+__msg("error: invalid dereference of R7 (a nullable map value pointer)")
+__naked void unbounded_offset_does_not_infer_map_value_non_null(void)
+{
+	asm volatile ("					\
+	/* r6 = bpf_map_lookup_elem(map_hash, &0); */	\
+	*(u64 *)(r10 - 8) = 0;				\
+	r1 = %[map_hash] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto 1f;				\
+	r6 = r0;					\
+	/* r7 = bpf_map_lookup_elem(map_hash, &1); */	\
+	*(u64 *)(r10 - 8) = 1;				\
+	r1 = %[map_hash] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	r7 = r0;					\
+	/* pointer - pointer is an unknown scalar */	\
+	r8 = r7;					\
+	r8 -= r6;					\
+	/* r8 is in [0, S64_MAX] */			\
+	r8 <<= 1;					\
+	r8 >>= 1;					\
+	/* r6 may wrap to zero at runtime */		\
+	r6 += r8;					\
+	if r7 != r6 goto 1f;				\
+	r0 = *(u8 *)(r7 + 0);				\
+1:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash)
+	: __clobber_all);
+}
+
+/* Same, but the offset is bounded, so the inference is still done. */
+SEC("socket")
+__success
+__naked void bounded_offset_infers_map_value_non_null(void)
+{
+	asm volatile ("					\
+	/* r6 = bpf_map_lookup_elem(map_hash, &0); */	\
+	*(u64 *)(r10 - 8) = 0;				\
+	r1 = %[map_hash] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto 1f;				\
+	r6 = r0;					\
+	/* r7 = bpf_map_lookup_elem(map_hash, &1); */	\
+	*(u64 *)(r10 - 8) = 1;				\
+	r1 = %[map_hash] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	r7 = r0;					\
+	/* pointer - pointer is an unknown scalar */	\
+	r8 = r7;					\
+	r8 -= r6;					\
+	/* r8 is in [0, 3] */				\
+	r8 &= 3;					\
+	r6 += r8;					\
+	if r7 != r6 goto 1f;				\
+	r0 = *(u8 *)(r7 + 0);				\
+1:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash)
+	: __clobber_all);
+}
+
+/*
+ * The low 32 bits of a map value pointer may be zero, hence a 32-bit
+ * compare with zero cannot be predicted from the pointer being non-NULL
+ * and both successors of such a jump have to be verified.
+ */
+SEC("socket")
+__failure __msg("invalid access to map value, value_size=4 off=32 size=4")
+__naked void jmp32_ptr_vs_zero_jne(void)
+{
+	asm volatile ("					\
+	/* r0 = bpf_map_lookup_elem(map_hash, &key); */	\
+	*(u64 *)(r10 - 8) = 0;				\
+	r1 = %[map_hash] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto 1f;				\
+	if w0 != 0 goto 1f;				\
+	r0 = *(u32 *)(r0 + 32);				\
+1:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash)
+	: __clobber_all);
+}
+
+/*
+ * The below program is explored in two paths: r6 == 0 and r6 == 1.
+ * On the first path comparison "if r0 == r6 goto 2f" should mark r6 as precise,
+ * otherwise unsafe path with r6 == 1 would be incorrectly pruned.
+ */
+SEC("socket")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("error: invalid dereference of R0 (a nullable map value pointer)")
+__naked void imprecise_zero_does_not_infer_map_value_non_null(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	/* r6 is 0 on the path explored first, 1 on the other */\
+	r6 = 1;						\
+	if r0 == 0 goto 1f;				\
+	r6 = 0;						\
+	/* r0 = bpf_map_lookup_elem(map_hash, &0); */	\
+1:	*(u64 *)(r10 - 8) = 0;				\
+	r1 = %[map_hash] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == r6 goto 2f;				\
+	r0 = *(u8 *)(r0 + 0);				\
+2:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash)
+	: __clobber_all);
+}
+
+void kfunc_root(void)
+{
+	bpf_rdonly_cast(0, 0);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ld_ind.c b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c
index 09e81b99eecb..32989f981fb6 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ld_ind.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c
@@ -194,6 +194,102 @@ __naked void ld_ind_subprog_both_paths_safe(void)
 	::: __clobber_all);
 }
 
+__naked __noinline __used
+static int ld_abs_callback(void)
+{
+	asm volatile (
+	"r6 = *(u64 *)(r2 + 0);"
+	".8byte %[ld_abs];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(ld_abs, BPF_LD_ABS(BPF_W, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ld_abs: reject in callback")
+__failure __msg("cannot use BPF_LD_[ABS|IND] within callback")
+int ld_abs_callback_reject(struct __sk_buff *skb)
+{
+	bpf_loop(1, ld_abs_callback, &skb, 0);
+	return 0;
+}
+
+__naked __noinline __used
+static int ld_ind_callback_subprog(void)
+{
+	asm volatile (
+	"r6 = r1;"
+	"r7 = 0;"
+	".8byte %[ld_ind];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, 0))
+	: __clobber_all);
+}
+
+__naked __noinline __used
+static int ld_ind_callback(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r2 + 0);"
+	"call ld_ind_callback_subprog;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__description("ld_ind: reject in callback subprog")
+__failure __msg("cannot use BPF_LD_[ABS|IND] within callback")
+int ld_ind_callback_subprog_reject(struct __sk_buff *skb)
+{
+	bpf_loop(1, ld_ind_callback, &skb, 0);
+	return 0;
+}
+
+static __noinline int ld_ind_global_static(struct __sk_buff *skb)
+{
+	asm volatile (
+	"r6 = %[skb];"
+	"r7 = 0;"
+	".8byte %[ld_ind];"
+	:
+	: [skb] "r"(skb),
+	  __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, 0))
+	: __clobber_common, "r6", "r7");
+	return skb->mark;
+}
+
+__noinline int ld_ind_global(struct __sk_buff *skb)
+{
+	return ld_ind_global_static(skb);
+}
+
+static int ld_ind_global_callback(__u32 index, struct __sk_buff **ctx)
+{
+	ld_ind_global(*ctx);
+	return 0;
+}
+
+SEC("socket")
+__description("ld_ind: reject in callback global subprog")
+__failure __msg("cannot use BPF_LD_[ABS|IND] within callback")
+int ld_ind_global_callback_reject(struct __sk_buff *skb)
+{
+	bpf_loop(1, ld_ind_global_callback, &skb, 0);
+	return 0;
+}
+
+SEC("socket")
+__description("ld_ind: allow in non-callback global subprog")
+__success
+int ld_ind_global_subprog_ok(struct __sk_buff *skb)
+{
+	return ld_ind_global(skb);
+}
+
 /*
  * ld_{abs,ind} in subprogs require scalar (int) return type in BTF.
  * A test with void return must be rejected.
diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
index e2cbc5bda65e..b5d7f567d0d4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
@@ -113,4 +113,82 @@ int with_valid_ctx_access_test6(struct bpf_nf_ctx *ctx)
 	return th->dest == bpf_htons(22) ? NF_ACCEPT : NF_DROP;
 }
 
+SEC("netfilter")
+__description("netfilter test prog with skb write access")
+__failure __msg("only read is supported")
+int skb_len_write(struct bpf_nf_ctx *ctx)
+{
+	ctx->skb->len = 1;
+	return 1;
+}
+
+SEC("netfilter")
+__description("netfilter test prog with skb data write access")
+__failure __msg("cannot write into rdonly_untrusted_mem")
+int skb_data_write(struct bpf_nf_ctx *ctx)
+{
+	ctx->skb->data[0] = 0;
+	return 1;
+}
+
+SEC("netfilter")
+__description("netfilter test prog with bpf_dynptr_write")
+__success __failure_unpriv
+__retval(0)
+int with_dynptr_write(struct bpf_nf_ctx *ctx)
+{
+	struct __sk_buff *skb = (struct __sk_buff *)ctx->skb;
+	struct bpf_dynptr ptr;
+	u8 buffer[1] = {};
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return 1;
+
+	if (bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0))
+		return 0; /* must always fail */
+
+	return 1;
+}
+
+SEC("netfilter")
+__description("netfilter test prog with bpf_dynptr_slice_rdwr")
+__failure __msg("the prog does not allow writes to packet data")
+int with_dynptr_rdwr(struct bpf_nf_ctx *ctx)
+{
+	struct __sk_buff *skb = (struct __sk_buff *)ctx->skb;
+	u8 buffer_iph[20] = {};
+	struct bpf_dynptr ptr;
+	struct iphdr *iph;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return 1;
+
+	iph = bpf_dynptr_slice_rdwr(&ptr, 0, buffer_iph, sizeof(buffer_iph));
+	if (!iph)
+		return 0;
+
+	return 1;
+}
+
+SEC("netfilter")
+__description("netfilter test prog with bpf_dynptr_slice + write")
+__failure __msg("cannot write into rdonly_mem")
+int with_dynptr_store(struct bpf_nf_ctx *ctx)
+{
+	struct __sk_buff *skb = (struct __sk_buff *)ctx->skb;
+	u8 buffer_iph[20] = {};
+	struct bpf_dynptr ptr;
+	struct iphdr *iph;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return 1;
+
+	iph = bpf_dynptr_slice(&ptr, 0, buffer_iph, sizeof(buffer_iph));
+	if (!iph)
+		return 0;
+	iph->protocol = 42;
+
+	return 1;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 6f325876efdd..f4459561bf39 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -2,8 +2,10 @@
 /* Copyright (C) 2023 SUSE LLC */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <stdbool.h>
 #include "../../../include/linux/filter.h"
 #include "bpf_misc.h"
+#include "bpf_kfuncs.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -642,4 +644,102 @@ __naked int bpf_atomic_cmpxchg_32bit_precision(void)
 	: __clobber_all);
 }
 
+/*
+ * Verification takes two paths: with r1 being scalar zero on path (1)
+ * and with r1 being some other scalar on path (2).
+ * Check that the verifier does not use checkpoints created
+ * on path (1) to prune path (2).
+ */
+SEC("?tc")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("R1 type=scalar expected=fp")
+__naked int null_mem_arg_zero_size(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"r1 = 42;"
+		"if r0 > 42 goto 1f;"
+		"r1 = 0;"
+	"1:"
+		"r2 = 0;"
+		"r3 = 0;"
+		"r4 = 0;"
+		"r5 = 0;"
+		/*
+		 * ARG_PTR_TO_MEM | PTR_MAYBE_NULL parameter can be NULL,
+		 * but can't be some other scalar value.
+		 */
+		"call %[bpf_csum_diff];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_csum_diff)
+		: __clobber_all);
+}
+
+__weak int subprog_mem_arg(int *p)
+{
+	if (p)
+		return *p;
+	return 0;
+}
+
+/*
+ * Verification takes two paths: with r1 being scalar zero on path (1)
+ * and with r1 being some other scalar on path (2).
+ * Check that the verifier does not use checkpoints created
+ * on path (1) to prune path (2).
+ */
+SEC("?raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("R1 type=scalar expected=fp")
+__naked int null_mem_arg_global_subprog(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"r1 = 42;"
+		"if r0 > 42 goto 1f;"
+		"r1 = 0;"
+	"1:"
+		"call subprog_mem_arg;"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_all);
+}
+
+/* Same as above, check that path with r3 == 0 does not prune the path with r3 != 0 */
+SEC("?tc")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("R3 type=scalar expected=fp")
+int null_kfunc_arg_dynptr_slice(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"r3 = 42;"
+		"if r0 > 42 goto 1f;"
+		"r3 = 0;"
+	"1:"
+		"r1 = %[ptr];"
+		"r2 = 0;"
+		"r4 = 8;"
+		"call %[bpf_dynptr_slice];"
+		:
+		: __imm_ptr(ptr),
+		  __imm(bpf_get_prandom_u32),
+		  __imm(bpf_dynptr_slice)
+		: __clobber_common);
+	return 0;
+}
+
+void __kfunc_btf_root(void)
+{
+	bpf_dynptr_slice(0, 0, 0, 0);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
index 663d15fc5fd2..256547048cc4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -380,13 +380,14 @@ SEC("socket")
 __success __log_level(2)
 __flag(BPF_F_TEST_STATE_FREQ)
 /*
- * check that r0 and r5 have different IDs after 'if',
- * collect_linked_regs() can't tie more than 5 registers for a single insn.
+ * check that r5 is unlinked after 'if', collect_linked_regs() can't tie
+ * more than 5 registers for a single insn and the register compared by
+ * the jump is not exempt from that.
  */
-__msg("7: (25) if r0 > 0x7 goto pc+0         ; R0=scalar(id=1")
+__msg("7: (25) if r5 > 0x7 goto pc+0         ; R5=scalar(smin=")
 __msg("12: (bf) r5 = r5                      ; R5=scalar(id=2")
 /* check that r{0-4} are marked precise after 'if' */
-__msg("frame0: regs=r0 stack= before 7: (25) if r0 > 0x7 goto pc+0")
+__msg("frame0: regs=r0 stack= before 7: (25) if r5 > 0x7 goto pc+0")
 __msg("frame0: parent state regs=r0,r1,r2,r3,r4 stack=:")
 __naked void linked_regs_too_many_regs(void)
 {
@@ -400,8 +401,8 @@ __naked void linked_regs_too_many_regs(void)
 	"r3 = r0;"
 	"r4 = r0;"
 	"r5 = r0;"
-	/* propagate range for r{0-5} */
-	"if r0 > 7 goto +0;"
+	/* r{0-4} fill the record, r5 does not fit and is unlinked */
+	"if r5 > 7 goto +0;"
 	/* keep r{1-4} live */
 	"r1 = r1;"
 	"r2 = r2;"
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 8b166c42c4e0..39a1766dae3f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -1403,6 +1403,46 @@ __naked void partial_fill_from_cleaned_pointer_spill(void)
 		      ::: __clobber_all);
 }
 
+SEC("raw_tp")
+__failure
+__msg("access may be outside object bounds")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void imprecise_scalar_spill_half_dead(void)
+{
+	asm volatile (
+	/*
+	 * Fork two paths: the one explored first spills an imprecise zero,
+	 * the one explored second, an imprecise non-zero scalar.
+	 */
+	"call %[bpf_get_prandom_u32];"
+	"if r0 > 42 goto 1f;"
+	"r6 = 0;"
+	"goto 2f;"
+"1:"
+	/* causes out of bounds access on a second path. */
+	"r6 = 100500;"
+"2:"
+	/* Force a checkpoint before the spill. */
+	"goto +0;"
+	"*(u64 *)(r10 - 8) = r6;"
+	/*
+	 * Force stack cleanup, only the low half of the spill is alive,
+	 * so the dead high half is degraded to raw stack bytes.
+	 * Buggy verifier converted it to STACK_ZERO w/o proper precision propagation.
+	 */
+	"goto +0;"
+	"r7 = *(u32 *)(r10 - 4);"
+	/* Use r7 as an offset into a one-byte buffer. */
+	"r1 = %[single_byte_buf] ll;"
+	"r1 += r7;"
+	"r0 = *(u8 *)(r1 + 0);"
+	"exit;"
+:
+: __imm(bpf_get_prandom_u32),
+  __imm_addr(single_byte_buf)
+: __clobber_all);
+}
+
 /* check valid spill/fill, ptr to tp buffer */
 SEC("raw_tracepoint.w")
 __success
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index d21d32f6a676..dc0c7034c04f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -287,9 +287,9 @@ __msg("17: (b7) r0 = 0")
 __msg("18: (95) exit")
 __msg("returning from callee:")
 __msg("to caller at 9:")
-__msg("frame 0: propagating r1,r4")
+__msg("frame 0: propagating r1,r3,r4")
 __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
-__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit")
+__msg("mark_precise: frame0: regs=r1,r3,r4 stack= before 18: (95) exit")
 __msg("from 18 to 9: safe")
 __naked int callback_result_precise(void)
 {
@@ -419,9 +419,9 @@ __msg("to caller at 9:")
 /* r1, r4 are always precise for bpf_loop(),
  * r6 was marked before backtracking to callback body.
  */
-__msg("frame 0: propagating r1,r4,r6")
+__msg("frame 0: propagating r1,r3,r4,r6")
 __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
-__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit")
+__msg("mark_precise: frame0: regs=r1,r3,r4,r6 stack= before 16: (95) exit")
 __msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0")
 __msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop")
 __msg("mark_precise: frame0: parent state regs= stack=:")
@@ -575,9 +575,9 @@ __msg("to caller at 10:")
 /* r1, r4 are always precise for bpf_loop(),
  * fp-8 was marked before backtracking to callback body.
  */
-__msg("frame 0: propagating r1,r4,fp-8")
+__msg("frame 0: propagating r1,r3,r4,fp-8")
 __msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1")
-__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame0: regs=r1,r3,r4 stack=-8 before 18: (95) exit")
 __msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0")
 __msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181")
 __msg("mark_precise: frame0: parent state regs= stack=:")
@@ -846,4 +846,55 @@ __naked int subprog_result_tail_call(void)
 	);
 }
 
+__naked __noinline __used
+static int ld_abs_subprog(void)
+{
+	asm volatile (
+		"r6 = r1;"
+		"r7 = r1;"
+		".8byte %[ld_abs];"
+		"exit;"
+		:
+		: __imm_insn(ld_abs, BPF_LD_ABS(BPF_W, 0))
+		: __clobber_all);
+}
+
+/*
+ * Buggy verifier did not properly backtrack early subprogram exit
+ * modelled for BPF_LD | BPF_ABS instruction, causing a segfault.
+ */
+SEC("socket")
+__success
+__log_level(2)
+/* early exit path */
+__msg("3: (0f) r1 += r7")
+__msg("mark_precise: frame0: regs=r7 stack= before 2: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r7 stack= before 9: (20) r0 = *(u32 *)skb[0]")
+__msg("mark_precise: frame1: regs= stack= before 8: (bf) r7 = r1")
+__msg("mark_precise: frame1: regs= stack= before 7: (bf) r6 = r1")
+__msg("mark_precise: frame1: regs= stack= before 1: (85) call pc+5")
+__msg("mark_precise: frame0: regs=r7 stack= before 0: (b7) r7 = -8")
+/* fallthrough path */
+__msg("3: (0f) r1 += r7")
+__msg("mark_precise: frame0: regs=r7 stack= before 2: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r7 stack= before 10: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 9: (20) r0 = *(u32 *)skb[0]")
+__msg("mark_precise: frame1: regs= stack= before 8: (bf) r7 = r1")
+__msg("mark_precise: frame1: regs= stack= before 7: (bf) r6 = r1")
+__msg("mark_precise: frame1: regs= stack= before 1: (85) call pc+5")
+__msg("mark_precise: frame0: regs=r7 stack= before 0: (b7) r7 = -8")
+__naked int ld_abs_backtrack_both_paths(void)
+{
+	asm volatile (
+		"r7 = -8;"
+		"call ld_abs_subprog;"
+		"r1 = r10;"
+		"r1 += r7;" /* mark r7 as precise */
+		"*(u64 *)(r1 + 0) = 0;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all
+	);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_zext.c b/tools/testing/selftests/bpf/progs/verifier_zext.c
index 8f2362da91d6..572017fe28fb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_zext.c
+++ b/tools/testing/selftests/bpf/progs/verifier_zext.c
@@ -356,6 +356,32 @@ __naked void arena_ptr(void)
 	: __clobber_all);
 }
 
+/*
+ * Result of a 32-bit cmpxchg is always explicitly zero extended.
+ * Check that this holds for arenas (BPF_PROBE_ATOMIC instruction flavor).
+ */
+SEC("socket")
+__success
+__xlated("probe r0 = atomic_cmpxchg((u32 *)(r1 +0), r0, r2)")
+__xlated("w0 = w0")
+__naked void zext_arena_cmpxchg32(void)
+{
+	asm volatile ("					\
+	r9 = %[arena] ll;	/* associate the arena with the program */ \
+	r1 = 0;						\
+	r1 = addr_space_cast(r1, 0, 1);			\
+	r0 = 0;						\
+	r2 = 0;						\
+	.8byte %[cmpxchg32];				\
+	r0 >>= 32;		/* make the upper half live */ \
+	exit;						\
+"	:
+	: __imm_addr(arena),
+	  __imm_insn(cmpxchg32,
+		     BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_1, BPF_REG_2, 0))
+	: __clobber_all);
+}
+
 #endif
 
 /* Check if probe mem loads keep their zero extension. */
diff --git a/tools/testing/selftests/bpf/verifier/pseudo_func.c b/tools/testing/selftests/bpf/verifier/pseudo_func.c
new file mode 100644
index 000000000000..63c5c67d51de
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/pseudo_func.c
@@ -0,0 +1,45 @@
+/*
+ * Buggy verifier accepted the program below while not patching BPF_PSEUDO_FUNC
+ * load instruction to contain a real address. Which resulted in a function call
+ * to a bogus address.
+ */
+{
+	"BPF_PSEUDO_FUNC reference to the main program",
+	.insns = {
+	/* r6 = bpf_map_lookup_elem(&timer_map, &(int){0}); */
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	/* bpf_timer_init(r6, &timer_map, 0); */
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	/* bpf_timer_set_callback(r6, <insn #0>); */
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, BPF_REG_2, BPF_PSEUDO_FUNC, 0, -15),
+	BPF_RAW_INSN(0, 0, 0, 0, 0),
+	BPF_EMIT_CALL(BPF_FUNC_timer_set_callback),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.fixup_map_timer = { 3, 9 },
+	.result = REJECT,
+	.errstr = "callback function cannot be the main program",
+	.func_info = { { 0, 4 /* main_prog */ } },
+	.func_info_cnt = 1,
+	.btf_strings = "\0int\0ctx\0main_prog",
+	.btf_types = {
+	/* 1: int            */ BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	/* 2: void*          */ BTF_PTR_ENC(0),
+	/* 3: int __(void *) */ BTF_FUNC_PROTO_ENC(1, 1),
+				BTF_FUNC_PROTO_ARG_ENC(5, 2),
+	/* 4: main_prog      */ BTF_FUNC_ENC(9, 3),
+	BTF_END_RAW
+	}
+},
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index e9bee164bb70..20d2b63774c3 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -919,7 +919,6 @@ int main(int argc, char *argv[])
 	int i;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
 		if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
 			ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
@@ -932,6 +931,7 @@ int main(int argc, char *argv[])
 			ksft_exit_skip("Failed to set memory controller\n");
 
 post_v2_setup:
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index f9f7017d9299..735a53bb222b 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -832,7 +832,6 @@ int main(int argc, char *argv[])
 	int i;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -840,6 +839,7 @@ int main(int argc, char *argv[])
 		if (cg_write(root, "cgroup.subtree_control", "+cpu"))
 			ksft_exit_skip("Failed to set cpu controller\n");
 
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
index 8c2d4d4ef1fc..3dfadd280c1c 100644
--- a/tools/testing/selftests/cgroup/test_cpuset.c
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -497,7 +497,6 @@ int main(int argc, char *argv[])
 	int i;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -505,6 +504,7 @@ int main(int argc, char *argv[])
 		if (cg_write(root, "cgroup.subtree_control", "+cpuset"))
 			ksft_exit_skip("Failed to set cpuset controller\n");
 
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index da8f7b920178..131d8b4551ef 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -797,7 +797,6 @@ check_isolcpus()
 	EXPECTED_ISOLCPUS=$1
 	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
 	ISOLCPUS=$(cat $ISCPUS)
-	HKICPUS=$(cat /sys/devices/system/cpu/isolated)
 	LASTISOLCPU=
 	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
 	if [[ $EXPECTED_ISOLCPUS = . ]]
@@ -836,11 +835,6 @@ check_isolcpus()
 	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
 
 	#
-	# The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS
-	#
-	[[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1
-
-	#
 	# Use the sched domain in debugfs to check isolated CPUs, if available
 	#
 	[[ -d $SCHED_DOMAINS ]] || return 0
@@ -1162,6 +1156,63 @@ test_isolated()
 }
 
 #
+# Select an online CPU isolated from scheduler domains at boot.
+# $1: test name used in the skip message
+#
+get_boot_isolated_cpu()
+{
+	TEST_NAME=$1
+	BOOT_ISOLATED_FILE=/sys/devices/system/cpu/isolated
+
+	[[ -r $BOOT_ISOLATED_FILE ]] || {
+		echo "$TEST_NAME test SKIPPED: boot isolation state unavailable"
+		return 1
+	}
+	BOOT_CPUS=$(cat $BOOT_ISOLATED_FILE)
+	[[ -n "$BOOT_CPUS" ]] || {
+		echo "$TEST_NAME test SKIPPED: no boot-isolated CPU"
+		return 1
+	}
+
+	BOOT_CPU=$(echo "$BOOT_CPUS" | sed -e 's/[,-].*//')
+	CPU_ONLINE=/sys/devices/system/cpu/cpu${BOOT_CPU}/online
+	[[ ! -e $CPU_ONLINE || $(cat $CPU_ONLINE) -eq 1 ]] || {
+		echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is offline"
+		return 1
+	}
+}
+
+#
+# A CPU isolated at boot must stay isolated after it is released by a dynamic
+# isolated partition.
+#
+test_boot_isolated()
+{
+	TEST_NAME="Boot-isolated CPU partition release"
+	get_boot_isolated_cpu "$TEST_NAME" || return 0
+	echo "Running $TEST_NAME test ..."
+
+	cd $CGROUP2/test
+	echo member > cpuset.cpus.partition
+	echo $BOOT_CPU > cpuset.cpus
+	[[ $(cat cpuset.cpus.effective) = "$BOOT_CPU" ]] || {
+		echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is unavailable"
+		echo "" > cpuset.cpus
+		cd $CGROUP2
+		return 0
+	}
+	test_partition isolated
+	test_partition member
+	check_isolcpus "." || {
+		echo "Boot-isolated CPU $BOOT_CPU was lost after partition release"
+		exit 1
+	}
+	echo "" > cpuset.cpus
+	cd $CGROUP2
+	echo "$TEST_NAME test PASSED."
+}
+
+#
 # Wait for inotify event for the given file and read it
 # $1: cgroup file to wait for
 # $2: file to store the read result
@@ -1232,5 +1283,6 @@ trap cleanup 0 2 3 6
 run_state_test TEST_MATRIX
 run_remote_state_test REMOTE_TEST_MATRIX
 test_isolated
+test_boot_isolated
 test_inotify
 echo "All tests PASSED."
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index 0569e93fa6b0..f28bb02e9783 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -1491,9 +1491,9 @@ int main(int argc, char *argv[])
 	int i;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index f6cd23a8ecc7..bac1ddd8cb94 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -7,6 +7,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
+#include <sys/wait.h>
 #include <unistd.h>
 
 #include "kselftest.h"
@@ -261,6 +262,59 @@ cleanup:
 	return ret;
 }
 
+/*
+ * Test that a cgroup that was killed in the past can still be the target
+ * of clone3(CLONE_INTO_CGROUP): writing cgroup.kill must only kill the
+ * tasks in the cgroup at the time of the write, not tasks cloned into
+ * it afterwards.
+ */
+static int test_cgkill_clone_into_killed(const char *root)
+{
+	pid_t pid;
+	int cgroup_fd = -EBADF;
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+
+	cgroup = cg_name(root, "cg_test_clone_into_killed");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	/* Kill the cgroup while it is still empty. */
+	if (cg_write(cgroup, "cgroup.kill", "1"))
+		goto cleanup;
+
+	cgroup_fd = dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		goto cleanup;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0) {
+		if (errno == ENOSYS)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+
+	/* The child must not be SIGKILLed; it has to exit cleanly. */
+	if (clone_reap(pid, WEXITED) != EXIT_SUCCESS)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
 #define T(x) { x, #x }
 struct cgkill_test {
 	int (*fn)(const char *root);
@@ -269,6 +323,7 @@ struct cgkill_test {
 	T(test_cgkill_simple),
 	T(test_cgkill_tree),
 	T(test_cgkill_forkbomb),
+	T(test_cgkill_clone_into_killed),
 };
 #undef T
 
@@ -278,9 +333,9 @@ int main(int argc, char *argv[])
 	int i;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 1db0ba1226b9..437f2d35f205 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -145,7 +145,7 @@ static int cg_run_in_subcgroups(const char *parent,
 			return -1;
 		}
 
-		if (cg_run(child, fn, NULL)) {
+		if (cg_run(child, fn, arg)) {
 			cg_destroy(child);
 			free(child);
 			return -1;
@@ -426,7 +426,6 @@ int main(int argc, char **argv)
 	int i;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -441,6 +440,7 @@ int main(int argc, char **argv)
 		if (cg_write(root, "cgroup.subtree_control", "+memory"))
 			ksft_exit_skip("Failed to set memory controller\n");
 
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 0ebf796f3cff..3a84d068fbf3 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -1798,7 +1798,6 @@ int main(int argc, char **argv)
 		page_size = BUF_SIZE;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -1823,6 +1822,7 @@ int main(int argc, char **argv)
 		ksft_exit_skip("Failed to query cgroup mount option\n");
 	has_localevents = proc_status;
 
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c
index 9a387c815d2c..710109b53dfe 100644
--- a/tools/testing/selftests/cgroup/test_pids.c
+++ b/tools/testing/selftests/cgroup/test_pids.c
@@ -148,7 +148,6 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -163,6 +162,7 @@ int main(int argc, char **argv)
 		if (cg_write(root, "cgroup.subtree_control", "+pids"))
 			ksft_exit_skip("Failed to set pids controller\n");
 
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (int i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index f7b4c4370db6..609c48f38524 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -819,7 +819,6 @@ int main(int argc, char **argv)
 		page_size = BUF_SIZE;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -836,6 +835,7 @@ int main(int argc, char **argv)
 		if (cg_write(root, "cgroup.subtree_control", "+memory"))
 			ksft_exit_skip("Failed to set memory controller\n");
 
+	ksft_set_plan(ARRAY_SIZE(tests));
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
index fc9694fc4e89..1d49df671919 100644
--- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
+++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
@@ -390,6 +390,116 @@ static void test_alloc_errors(char *heap_name)
 	close(heap_fd);
 }
 
+/*
+ * count_open_fds - return the number of open file descriptors.
+ *
+ * The fd opened by opendir() itself is counted, but since it is opened
+ * and closed within each call, it cancels out when comparing two counts.
+ * Returns -1 on error.
+ */
+static int count_open_fds(void)
+{
+	DIR *d = opendir("/proc/self/fd");
+	struct dirent *de;
+	int count = 0;
+
+	if (!d)
+		return -1;
+
+	while ((de = readdir(d)))
+		if (de->d_name[0] != '.')
+			count++;
+	closedir(d);
+	return count;
+}
+
+/*
+ * test_alloc_no_fd_leak_on_efault - verify no fd is leaked when
+ * copy_to_user() fails during DMA_HEAP_IOCTL_ALLOC.
+ *
+ * The bug: dma_buf_fd() called fd_install() before copy_to_user().
+ * If copy_to_user() then failed (e.g. via mprotect), the fd was
+ * silently installed in the fd table but never returned to userspace.
+ *
+ * The fix: reserve the fd with get_unused_fd_flags() first, attempt
+ * copy_to_user(), and only call fd_install() on success.
+ *
+ * We trigger the failure by placing the ioctl argument in a private
+ * anonymous page and flipping it to PROT_READ before the ioctl.
+ * Inside the kernel, copy_from_user() reads from the page (reads are
+ * allowed under PROT_READ, so it succeeds), but copy_to_user() that
+ * writes the fd number back faults, returning -EFAULT.  We then
+ * count open file descriptors before and after; with the bug an extra
+ * fd is left in the table.
+ */
+static void test_alloc_no_fd_leak_on_efault(char *heap_name)
+{
+	int heap_fd = -1;
+	int fd_before, fd_after;
+	int ret;
+	long page_size;
+	struct dma_heap_allocation_data *req;
+
+	ksft_print_msg("Testing fd leak when copy_to_user() fails:\n");
+
+	heap_fd = dmabuf_heap_open(heap_name);
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	/*
+	 * Place the ioctl argument in its own private anonymous page so
+	 * we can flip its protection independently.
+	 */
+	req = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (req == MAP_FAILED) {
+		ksft_test_result_fail("mmap failed: %s\n", strerror(errno));
+		goto out;
+	}
+
+	memset(req, 0, sizeof(*req));
+	req->len      = page_size;
+	req->fd_flags = O_RDWR | O_CLOEXEC;
+
+	fd_before = count_open_fds();
+	if (fd_before < 0) {
+		ksft_test_result_fail("count_open_fds: %s\n", strerror(errno));
+		munmap(req, page_size);
+		goto out;
+	}
+
+	/*
+	 * Make the page read-only so copy_to_user() will fault.  The
+	 * ioctl must fail with -1; if it returns success the test setup
+	 * is broken (mprotect is synchronous, so there is no race).
+	 */
+	mprotect(req, page_size, PROT_READ);
+
+	ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, req);
+
+	/* Re-allow writes so munmap can clean up */
+	mprotect(req, page_size, PROT_READ | PROT_WRITE);
+	munmap(req, page_size);
+
+	if (ret != -1) {
+		ksft_test_result_fail("ioctl returned %d, expected -1 EFAULT\n",
+				      ret);
+		goto out;
+	}
+
+	fd_after = count_open_fds();
+	if (fd_after < 0) {
+		ksft_test_result_fail("count_open_fds: %s\n", strerror(errno));
+		goto out;
+	}
+
+	ksft_test_result(fd_before == fd_after,
+			 "fd leak on EFAULT: before=%d after=%d\n",
+			 fd_before, fd_after);
+out:
+	close(heap_fd);
+}
+
 static int numer_of_heaps(void)
 {
 	DIR *d = opendir(DEVPATH);
@@ -420,7 +530,7 @@ int main(void)
 		return KSFT_SKIP;
 	}
 
-	ksft_set_plan(11 * numer_of_heaps());
+	ksft_set_plan(12 * numer_of_heaps());
 
 	while ((dir = readdir(d))) {
 		if (!strncmp(dir->d_name, ".", 2))
@@ -435,6 +545,7 @@ int main(void)
 		test_alloc_zeroed(dir->d_name, ONE_MEG);
 		test_alloc_compat(dir->d_name);
 		test_alloc_errors(dir->d_name);
+		test_alloc_no_fd_leak_on_efault(dir->d_name);
 	}
 	closedir(d);
 
diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c
index b851339308c2..7ab86296ff23 100644
--- a/tools/testing/selftests/hid/hid_bpf.c
+++ b/tools/testing/selftests/hid/hid_bpf.c
@@ -67,14 +67,17 @@ struct test_program {
 	int insert_head;
 };
 #define LOAD_PROGRAMS(progs) \
-	load_programs(progs, ARRAY_SIZE(progs), _metadata, self, variant)
+	load_programs(progs, ARRAY_SIZE(progs), false, _metadata, self, variant)
+#define LOAD_PROGRAMS_MAY_FAIL(progs) \
+	load_programs(progs, ARRAY_SIZE(progs), true, _metadata, self, variant)
 #define LOAD_BPF \
-	load_programs(NULL, 0, _metadata, self, variant)
-static void load_programs(const struct test_program programs[],
-			  const size_t progs_count,
-			  struct __test_metadata *_metadata,
-			  FIXTURE_DATA(hid_bpf) * self,
-			  const FIXTURE_VARIANT(hid_bpf) * variant)
+	load_programs(NULL, 0, false, _metadata, self, variant)
+static int load_programs(const struct test_program programs[],
+			 const size_t progs_count,
+			 bool load_may_fail,
+			 struct __test_metadata *_metadata,
+			 FIXTURE_DATA(hid_bpf) * self,
+			 const FIXTURE_VARIANT(hid_bpf) * variant)
 {
 	struct bpf_map *iter_map;
 	int err = -EINVAL;
@@ -128,6 +131,9 @@ static void load_programs(const struct test_program programs[],
 	}
 
 	err = hid__load(self->skel);
+	if (err && load_may_fail)
+		return err;
+
 	ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err);
 
 	for (int i = 0; i < progs_count; i++) {
@@ -147,6 +153,7 @@ static void load_programs(const struct test_program programs[],
 
 	self->hidraw_fd = open_hidraw(&self->hid);
 	ASSERT_GE(self->hidraw_fd, 0) TH_LOG("open_hidraw");
+	return 0;
 }
 
 /*
@@ -904,11 +911,39 @@ TEST_F(hid_bpf, test_rdesc_fixup_get_data_overflow)
 		{ .name = "hid_rdesc_fixup_get_data_overflow" },
 	};
 
-	LOAD_PROGRAMS(progs);
+	/* newer verifier can detect the overflow at load time */
+	if (LOAD_PROGRAMS_MAY_FAIL(progs))
+		return;
 
 	ASSERT_EQ(self->skel->bss->get_data_overflow_check, 1);
 }
 
+TEST_F(hid_bpf, test_rdesc_fixup_change_uniq_name_phys)
+{
+	const struct test_program progs[] = {
+		{ .name = "hid_rdesc_fixup_change_uniq_name_phys" },
+	};
+	char expected[256], buf[256] = {};
+	int err;
+
+	LOAD_PROGRAMS(progs);
+
+	err = ioctl(self->hidraw_fd, HIDIOCGRAWNAME(sizeof(buf)), buf);
+	ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWNAME");
+	ASSERT_STREQ("name coming from bpf", buf);
+
+	snprintf(expected, sizeof(expected), "%d phys:coming:from:bpf", self->hid.dev_id);
+
+	err = ioctl(self->hidraw_fd, HIDIOCGRAWPHYS(sizeof(buf)), buf);
+	ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWPHYS");
+	ASSERT_STREQ(expected, buf);
+
+	err = ioctl(self->hidraw_fd, HIDIOCGRAWUNIQ(sizeof(buf)), buf);
+	ASSERT_GE(err, 0) TH_LOG("HIDIOCGRAWUNIQ");
+	ASSERT_STREQ("uniq:coming:from:bpf", buf);
+
+}
+
 static int libbpf_print_fn(enum libbpf_print_level level,
 			   const char *format, va_list args)
 {
diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c
index b21fbb13c926..361dc7eaad22 100644
--- a/tools/testing/selftests/hid/progs/hid.c
+++ b/tools/testing/selftests/hid/progs/hid.c
@@ -255,6 +255,32 @@ struct hid_bpf_ops rdesc_fixup_get_data_overflow = {
 	.hid_rdesc_fixup = (void *)hid_rdesc_fixup_get_data_overflow,
 };
 
+SEC("?struct_ops.s/hid_rdesc_fixup")
+int BPF_PROG(hid_rdesc_fixup_change_uniq_name_phys, struct hid_bpf_ctx *hid_ctx)
+{
+#define HID_BPF_MEMCPY(target, str) \
+	__builtin_memcpy(target, str, sizeof(str))
+
+	HID_BPF_MEMCPY(hid_ctx->hid->name, "name coming from bpf");
+	HID_BPF_MEMCPY(hid_ctx->hid->uniq, "uniq:coming:from:bpf");
+	/* hid_bpf relies on a phys being a rand % 1024 */
+	for (int i = 0; i < 5; i++) {
+		if (!hid_ctx->hid->phys[i]) {
+			HID_BPF_MEMCPY(hid_ctx->hid->phys + i, " phys:coming:from:bpf");
+			break;
+		}
+	}
+
+#undef HID_BPF_MEMCPY
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct hid_bpf_ops rdesc_fixup_change_uniq_name_phys = {
+	.hid_rdesc_fixup = (void *)hid_rdesc_fixup_change_uniq_name_phys,
+};
+
 SEC("?struct_ops/hid_device_event")
 int BPF_PROG(hid_test_insert1, struct hid_bpf_ctx *hid_ctx, enum hid_report_type type)
 {
diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
index cdca912f3afd..05698793762a 100644
--- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
+++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
@@ -61,6 +61,9 @@ enum hid_report_type {
 
 struct hid_device {
 	unsigned int id;
+	char name[128];
+	char phys[64];
+	char uniq[64];
 } __attribute__((preserve_access_index));
 
 struct bpf_wq {
diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c
index aac4f795c327..c55d84c5e613 100644
--- a/tools/testing/selftests/mm/memfd_secret.c
+++ b/tools/testing/selftests/mm/memfd_secret.c
@@ -57,33 +57,6 @@ static void test_file_apis(int fd)
 		pass("file IO is blocked as expected\n");
 }
 
-static void test_mlock_limit(int fd)
-{
-	size_t len;
-	char *mem;
-
-	len = mlock_limit_cur;
-	if (len % page_size != 0)
-		len = (len/page_size) * page_size;
-
-	mem = mmap(NULL, len, prot, mode, fd, 0);
-	if (mem == MAP_FAILED) {
-		fail("unable to mmap secret memory\n");
-		return;
-	}
-	munmap(mem, len);
-
-	len = mlock_limit_max * 2;
-	mem = mmap(NULL, len, prot, mode, fd, 0);
-	if (mem != MAP_FAILED) {
-		fail("unexpected mlock limit violation\n");
-		munmap(mem, len);
-		return;
-	}
-
-	pass("mlock limit is respected\n");
-}
-
 static void test_vmsplice(int fd, const char *desc)
 {
 	ssize_t transferred;
@@ -297,7 +270,7 @@ static void prepare(void)
 				   strerror(errno));
 }
 
-#define NUM_TESTS 6
+#define NUM_TESTS 5
 
 int main(int argc, char *argv[])
 {
@@ -319,7 +292,6 @@ int main(int argc, char *argv[])
 	if (ftruncate(fd, page_size))
 		ksft_exit_fail_msg("ftruncate failed: %s\n", strerror(errno));
 
-	test_mlock_limit(fd);
 	test_file_apis(fd);
 	/*
 	 * We have to run the first vmsplice test before any secretmem page was
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 0f5c178bc224..517c09d60bef 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -28,6 +28,7 @@ TEST_PROGS := \
 	double_udp_encap.sh \
 	drop_monitor_tests.sh \
 	ecmp_rehash.sh \
+	exception_cache.sh \
 	fcnal-ipv4.sh \
 	fcnal-ipv6.sh \
 	fcnal-other.sh \
diff --git a/tools/testing/selftests/net/exception_cache.sh b/tools/testing/selftests/net/exception_cache.sh
new file mode 100755
index 000000000000..8d3eed5c532a
--- /dev/null
+++ b/tools/testing/selftests/net/exception_cache.sh
@@ -0,0 +1,521 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that the state of the route exception cache after an ICMP error is
+# processed does not depend on whether the quoted packet was matched to a
+# socket. Otherwise, an off-path attacker can probe the cache to discover the
+# ephemeral port used by a connected UDP socket.
+#
+# When the quoted packet is not matched to a socket, the same exception is
+# created as when it is matched, so that neither its presence nor its contents
+# reveal the result of socket matching.
+#
+#                              +----+
+#                    +---------| r1 |
+#                    |         +----+
+#  +----+   +--------+            | .1
+#  | h1 |---| bridge |            |    198.51.100.0/30
+#  +----+   +--------+            |    2001:db8:2::/64
+#      .1            |            | .2
+#                    |         +----+           +----+
+#                    +---------| r2 |-----------| h2 |
+#                    .2   .3   +----+ .1     .2 +----+
+#                                   203.0.113.0/24
+#                                   2001:db8:3::/64
+#         192.0.2.0/24
+#         2001:db8:1::/64
+#
+# Traffic from h1 to h2 is routed via r1, which reaches h2's network via r2
+# over the point-to-point link. The MTU of the r2 - h2 link is lowered so that
+# r2 emits ICMP errors towards h1.
+#
+# For the redirect tests r1's route to h2's network is replaced with one via r2
+# on the shared segment, so that r1 forwards the packet back to the segment it
+# arrived from and emits a redirect towards h1.
+#
+# The packets that provoke the ICMP errors are injected with a packet socket so
+# that no socket is ever associated with them. A socket is created separately,
+# with socat, when a test needs the ICMP error to be matched.
+
+# shellcheck disable=SC1091,SC2034,SC2154,SC2329
+source lib.sh
+
+require_command jq
+require_command mausezahn
+require_command nstat
+require_command socat
+
+ALL_TESTS="
+	pmtu_no_socket_ipv4
+	pmtu_no_socket_ipv6
+	pmtu_socket_ipv4
+	pmtu_socket_ipv6
+	pmtu_omit_ipv4
+	pmtu_omit_ipv6
+	redirect_no_socket_ipv4
+	redirect_no_socket_ipv6
+	redirect_socket_ipv4
+	redirect_socket_ipv6
+"
+
+# Shared segment.
+H1_ADDR4=192.0.2.1
+R1_ADDR4=192.0.2.2
+R2_ADDR4=192.0.2.3
+H1_ADDR6=2001:db8:1::1
+R1_ADDR6=2001:db8:1::2
+R2_ADDR6=2001:db8:1::3
+
+# r1 - r2 link.
+R2_R1_ADDR4=198.51.100.2
+R2_R1_ADDR6=2001:db8:2::2
+
+# r2 - h2 link.
+H2_ADDR4=203.0.113.2
+H2_NET4=203.0.113.0/24
+H2_ADDR6=2001:db8:3::2
+H2_NET6=2001:db8:3::/64
+
+SPORT=12345
+DPORT=54321
+
+# The MTU of the shared segment and of the r1 - r2 link. Large enough for the
+# injected packets to reach r2 intact.
+SEGMENT_MTU=2000
+# Size of the injected packets. The PMTU tests need a size that exceeds every
+# MTU used for the r2 - h2 link, so that r2 responds with an ICMP error. The
+# redirect tests need a size that does not, otherwise r2 would respond with an
+# ICMP error in addition to the redirect emitted by r1.
+PMTU_PACKET_SIZE=1800
+REDIRECT_PACKET_SIZE=100
+
+# The MTUs used for the r2 - h2 link. All of them must be at least
+# IPV6_MIN_MTU, otherwise IPv6 silently ignores the error instead of creating
+# an exception.
+MTU_MID=1400
+MTU_LOW=1300
+
+# Values for the IP{,V6}_MTU_DISCOVER socket option.
+PMTUDISC_DONT=0
+PMTUDISC_OMIT=5
+
+SOCAT_PID=
+
+linklocal_get()
+{
+	local ns=$1; shift
+	local dev=$1; shift
+
+	ip -n "$ns" -j -6 addr show dev "$dev" | \
+		jq -r '.[]["addr_info"][] | select(.scope == "link") | .local'
+}
+
+linklocal_exists()
+{
+	local ns=$1; shift
+	local dev=$1; shift
+
+	[ -n "$(linklocal_get "$ns" "$dev")" ]
+}
+
+family_vars_set()
+{
+	local family=$1; shift
+
+	FAMILY=$family
+
+	if [ "$family" -eq 4 ]; then
+		H1_ADDR=$H1_ADDR4
+		H2_ADDR=$H2_ADDR4
+		MZ_FAMILY_OPT=()
+		# Without the Don't Fragment bit set r2 fragments the packet
+		# instead of reporting the MTU of the next hop.
+		MZ_IP_OPTS="df,"
+		SOCAT_DST="UDP4-CONNECT:$H2_ADDR4:$DPORT"
+		SOCAT_BIND="bind=$H1_ADDR4:$SPORT"
+		SOCAT_PMTUDISC="ip-mtu-discover"
+	else
+		H1_ADDR=$H1_ADDR6
+		H2_ADDR=$H2_ADDR6
+		MZ_FAMILY_OPT=(-6)
+		MZ_IP_OPTS=
+		SOCAT_DST="UDP6-CONNECT:[$H2_ADDR6]:$DPORT"
+		SOCAT_BIND="bind=[$H1_ADDR6]:$SPORT"
+		SOCAT_PMTUDISC="ipv6-mtu-discover"
+	fi
+}
+
+topology_setup()
+{
+	local ns
+
+	setup_ns h1 r1 r2 h2 sw
+	defer cleanup_all_ns
+
+	# Link-local addresses are generated from the MAC address and read
+	# back during setup, so request that generation mode explicitly and
+	# make the addresses available as soon as the devices are brought up.
+	for ns in "$h1" "$r1" "$r2" "$h2" "$sw"; do
+		ip netns exec "$ns" sysctl -qw \
+			net.ipv6.conf.default.addr_gen_mode=0 \
+			net.ipv6.conf.default.accept_dad=0 \
+			net.ipv6.conf.all.accept_dad=0
+	done
+
+	ip -n "$sw" link add name br0 type bridge
+	ip -n "$sw" link set dev br0 mtu "$SEGMENT_MTU" up
+
+	ip -n "$h1" link add name eth0 mtu "$SEGMENT_MTU" type veth \
+		peer name swp1 mtu "$SEGMENT_MTU" netns "$sw"
+	ip -n "$r1" link add name eth0 mtu "$SEGMENT_MTU" type veth \
+		peer name swp2 mtu "$SEGMENT_MTU" netns "$sw"
+	ip -n "$r2" link add name eth0 mtu "$SEGMENT_MTU" type veth \
+		peer name swp3 mtu "$SEGMENT_MTU" netns "$sw"
+	ip -n "$r1" link add name eth1 mtu "$SEGMENT_MTU" type veth \
+		peer name eth1 mtu "$SEGMENT_MTU" netns "$r2"
+	ip -n "$r2" link add name eth2 type veth peer name eth0 netns "$h2"
+
+	ip -n "$sw" link set dev swp1 master br0 up
+	ip -n "$sw" link set dev swp2 master br0 up
+	ip -n "$sw" link set dev swp3 master br0 up
+
+	ip -n "$h1" link set dev eth0 up
+	ip -n "$r1" link set dev eth0 up
+	ip -n "$r1" link set dev eth1 up
+	ip -n "$r2" link set dev eth0 up
+	ip -n "$r2" link set dev eth1 up
+	ip -n "$r2" link set dev eth2 up
+	ip -n "$h2" link set dev eth0 up
+
+	ip -n "$h1" address add "$H1_ADDR4/24" dev eth0
+	ip -n "$r1" address add "$R1_ADDR4/24" dev eth0
+	ip -n "$r2" address add "$R2_ADDR4/24" dev eth0
+	ip -n "$r1" address add 198.51.100.1/30 dev eth1
+	ip -n "$r2" address add "$R2_R1_ADDR4/30" dev eth1
+	ip -n "$r2" address add 203.0.113.1/24 dev eth2
+	ip -n "$h2" address add "$H2_ADDR4/24" dev eth0
+
+	ip -n "$h1" -6 address add "$H1_ADDR6/64" dev eth0 nodad
+	ip -n "$r1" -6 address add "$R1_ADDR6/64" dev eth0 nodad
+	ip -n "$r2" -6 address add "$R2_ADDR6/64" dev eth0 nodad
+	ip -n "$r1" -6 address add 2001:db8:2::1/64 dev eth1 nodad
+	ip -n "$r2" -6 address add "$R2_R1_ADDR6/64" dev eth1 nodad
+	ip -n "$r2" -6 address add 2001:db8:3::1/64 dev eth2 nodad
+	ip -n "$h2" -6 address add "$H2_ADDR6/64" dev eth0 nodad
+
+	ip netns exec "$r1" sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec "$r1" sysctl -qw net.ipv4.conf.all.send_redirects=1
+	ip netns exec "$r1" sysctl -qw net.ipv6.conf.all.forwarding=1
+	ip netns exec "$r2" sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec "$r2" sysctl -qw net.ipv6.conf.all.forwarding=1
+
+	ip netns exec "$h1" sysctl -qw net.ipv4.conf.all.accept_redirects=1
+	ip netns exec "$h1" sysctl -qw net.ipv4.conf.eth0.accept_redirects=1
+	ip netns exec "$h1" sysctl -qw net.ipv6.conf.all.accept_redirects=1
+	ip netns exec "$h1" sysctl -qw net.ipv6.conf.eth0.accept_redirects=1
+
+	slowwait 5 linklocal_exists "$r1" eth0
+	check_err $? "r1: link-local address was not generated"
+	slowwait 5 linklocal_exists "$r2" eth0
+	check_err $? "r2: link-local address was not generated"
+
+	R1_LLADDR=$(linklocal_get "$r1" eth0)
+	R2_LLADDR=$(linklocal_get "$r2" eth0)
+	R1_MAC=$(ip -n "$r1" -j link show dev eth0 | jq -r '.[]["address"]')
+	R2_MAC=$(ip -n "$r2" -j link show dev eth0 | jq -r '.[]["address"]')
+
+	ip -n "$h1" route add "$H2_NET4" via "$R1_ADDR4" dev eth0
+	ip -n "$h1" -6 route add "$H2_NET6" via "$R1_LLADDR" dev eth0
+	ip -n "$r1" route add "$H2_NET4" via "$R2_R1_ADDR4" dev eth1
+	ip -n "$r1" -6 route add "$H2_NET6" via "$R2_R1_ADDR6" dev eth1
+	ip -n "$h2" route add default via 203.0.113.1 dev eth0
+	ip -n "$h2" -6 route add default via 2001:db8:3::1 dev eth0
+
+	far_mtu_set "$MTU_MID"
+}
+
+# Make r1 forward towards h2's network over the segment it receives the packet
+# from, so that it emits a redirect towards h1.
+redirect_route_set()
+{
+	ip -n "$r1" route replace "$H2_NET4" via "$R2_ADDR4" dev eth0
+	ip -n "$r1" -6 route replace "$H2_NET6" via "$R2_LLADDR" dev eth0
+
+	# __ip_do_redirect() only creates an exception if the new gateway is
+	# already a valid neighbour. Otherwise it merely triggers address
+	# resolution. IPv6 resolves the target itself, in rt6_do_redirect().
+	ip -n "$h1" neigh replace "$R2_ADDR4" lladdr "$R2_MAC" dev eth0 \
+		nud permanent
+}
+
+far_mtu_set()
+{
+	local mtu=$1; shift
+
+	ip -n "$r2" link set dev eth2 mtu "$mtu"
+	ip -n "$h2" link set dev eth0 mtu "$mtu"
+}
+
+socket_is_open()
+{
+	ip netns exec "$h1" ss -uHn "sport = :$SPORT" | grep -q .
+}
+
+socket_start()
+{
+	# Disable PMTU discovery by default so that ICMP errors are not
+	# reported to the socket. Otherwise socat would exit when the first one
+	# arrives and later packets in the same test would not be matched to a
+	# socket. The exception is still created, as ip{,6}_sk_accept_pmtu()
+	# only rejects IP{,V6}_PMTUDISC_{INTERFACE,OMIT}.
+	local pmtudisc=${1:-$PMTUDISC_DONT}
+
+	# Send socat's diagnostics to /dev/null. It reports the ICMP errors
+	# that reach the socket, which is exactly what the tests provoke.
+	ip netns exec "$h1" socat -u -lf/dev/null \
+		"$SOCAT_DST,$SOCAT_BIND,$SOCAT_PMTUDISC=$pmtudisc" \
+		OPEN:/dev/null,wronly=1 &
+	SOCAT_PID=$!
+	defer socket_stop
+
+	slowwait 5 socket_is_open
+	check_err $? "socket did not open"
+}
+
+socket_stop()
+{
+	[ -z "$SOCAT_PID" ] && return 0
+
+	kill "$SOCAT_PID" &> /dev/null
+	wait "$SOCAT_PID" 2> /dev/null
+	SOCAT_PID=
+}
+
+# Inject a packet towards h2 with a packet socket. No socket is associated with
+# it, so an ICMP error quoting it is matched to a socket only if one was
+# created separately with the same source port.
+packet_send()
+{
+	local size=$1; shift
+
+	ip netns exec "$h1" mausezahn "${MZ_FAMILY_OPT[@]}" eth0 \
+		-a own -b "$R1_MAC" -A "$H1_ADDR" -B "$H2_ADDR" \
+		-t udp "${MZ_IP_OPTS}sp=$SPORT,dp=$DPORT" \
+		-p "$size" -c 1 -q
+}
+
+exception_show()
+{
+	if [ "$FAMILY" -eq 4 ]; then
+		# IPv4 exceptions without a bound route are not dumped, but
+		# "route get" reports the exception and binds a route to it.
+		ip -n "$h1" route get "$H2_ADDR"
+	else
+		# IPv6 does not report a cache indication in "route get"
+		# output, so dump the exceptions instead.
+		ip -n "$h1" -6 route show cache | grep -F "$H2_ADDR" || true
+	fi
+}
+
+exception_mtu_get()
+{
+	exception_show | grep -o "mtu [0-9]*" | cut -d ' ' -f 2
+}
+
+exception_gw_get()
+{
+	exception_show | grep -o "via [0-9a-f.:]*" | cut -d ' ' -f 2
+}
+
+exception_mtu_check()
+{
+	local expected=$1; shift
+
+	[ "$(exception_mtu_get)" = "$expected" ]
+}
+
+icmp_errors_get()
+{
+	local ctr=IcmpInDestUnreachs
+
+	[ "$FAMILY" -eq 6 ] && ctr=Icmp6InPktTooBigs
+
+	ip netns exec "$h1" nstat -asz "$ctr" | \
+		awk -v ctr="$ctr" '$1 == ctr { print $2 }'
+}
+
+exception_pmtu_check()
+{
+	local mtu=$1; shift
+	local desc=$1; shift
+
+	busywait "$BUSYWAIT_TIMEOUT" exception_mtu_check "$mtu"
+	check_err $? "$desc: exception does not carry an MTU of $mtu"
+}
+
+pmtu_no_socket()
+{
+	local family=$1; shift
+
+	RET=0
+	family_vars_set "$family"
+	topology_setup
+
+	packet_send "$PMTU_PACKET_SIZE"
+	exception_pmtu_check "$MTU_MID" "No socket"
+
+	log_test "IPv$family: PMTU: exception without a matching socket"
+}
+
+pmtu_no_socket_ipv4()
+{
+	pmtu_no_socket 4
+}
+
+pmtu_no_socket_ipv6()
+{
+	pmtu_no_socket 6
+}
+
+pmtu_socket()
+{
+	local family=$1; shift
+	local t0
+
+	RET=0
+	family_vars_set "$family"
+	topology_setup
+	socket_start
+
+	packet_send "$PMTU_PACKET_SIZE"
+	exception_pmtu_check "$MTU_MID" "Matching socket"
+
+	# A lower PMTU replaces the one currently stored in the exception.
+	far_mtu_set "$MTU_LOW"
+	packet_send "$PMTU_PACKET_SIZE"
+	exception_pmtu_check "$MTU_LOW" "Lower PMTU"
+
+	# A higher PMTU is ignored, so the exception is left as it is. Wait
+	# for the error to be received, as otherwise the check below would
+	# pass even if it never was.
+	far_mtu_set "$MTU_MID"
+	t0=$(icmp_errors_get)
+	packet_send "$PMTU_PACKET_SIZE"
+	busywait "$BUSYWAIT_TIMEOUT" until_counter_is ">= $((t0 + 1))" \
+		icmp_errors_get > /dev/null
+	check_err $? "Higher PMTU: ICMP error was not received"
+
+	exception_mtu_check "$MTU_LOW"
+	check_err $? "Higher PMTU: exception does not carry an MTU of $MTU_LOW"
+
+	log_test "IPv$family: PMTU: exception with a matching socket"
+}
+
+pmtu_socket_ipv4()
+{
+	pmtu_socket 4
+}
+
+pmtu_socket_ipv6()
+{
+	pmtu_socket 6
+}
+
+pmtu_omit()
+{
+	local family=$1; shift
+
+	RET=0
+	family_vars_set "$family"
+	topology_setup
+	socket_start "$PMTUDISC_OMIT"
+
+	packet_send "$PMTU_PACKET_SIZE"
+	exception_pmtu_check "$MTU_MID" "PMTU discovery disabled"
+
+	log_test "IPv$family: PMTU: exception with a socket ignoring it"
+}
+
+pmtu_omit_ipv4()
+{
+	pmtu_omit 4
+}
+
+pmtu_omit_ipv6()
+{
+	pmtu_omit 6
+}
+
+exception_gw_check()
+{
+	local expected=$1; shift
+
+	[ -n "$expected" ] && [ "$(exception_gw_get)" = "$expected" ]
+}
+
+redirect_gw_new()
+{
+	if [ "$FAMILY" -eq 4 ]; then
+		echo "$R2_ADDR4"
+	else
+		echo "$R2_LLADDR"
+	fi
+}
+
+redirect_no_socket()
+{
+	local family=$1; shift
+
+	RET=0
+	family_vars_set "$family"
+	topology_setup
+	redirect_route_set
+
+	packet_send "$REDIRECT_PACKET_SIZE"
+	busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)"
+	check_err $? "No socket: exception does not carry the new gateway"
+
+	log_test "IPv$family: Redirect: exception without a matching socket"
+}
+
+redirect_no_socket_ipv4()
+{
+	redirect_no_socket 4
+}
+
+redirect_no_socket_ipv6()
+{
+	redirect_no_socket 6
+}
+
+redirect_socket()
+{
+	local family=$1; shift
+
+	RET=0
+	family_vars_set "$family"
+	topology_setup
+	redirect_route_set
+	socket_start
+
+	packet_send "$REDIRECT_PACKET_SIZE"
+	busywait "$BUSYWAIT_TIMEOUT" exception_gw_check "$(redirect_gw_new)"
+	check_err $? "Matching socket: exception does not carry the new gateway"
+
+	log_test "IPv$family: Redirect: exception with a matching socket"
+}
+
+redirect_socket_ipv4()
+{
+	redirect_socket 4
+}
+
+redirect_socket_ipv6()
+{
+	redirect_socket 6
+}
+
+trap defer_scopes_cleanup EXIT
+tests_run
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh
index 58da5de99ac4..f9600aabd4a2 100755
--- a/tools/testing/selftests/net/test_vxlan_mdb.sh
+++ b/tools/testing/selftests/net/test_vxlan_mdb.sh
@@ -685,6 +685,9 @@ star_g_common()
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $grp dst $vtep_ip src_vni 10010"
 	log_test $? 255 "Invalid source in source list"
 
+	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $all_zeros_grp dst $vtep_ip src_vni 10010"
+	log_test $? 255 "All-zeros source in source list"
+
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent source_list $src1 dst $vtep_ip src_vni 10010"
 	log_test $? 255 "Source list without filter mode"
 }
@@ -784,6 +787,9 @@ sg_common()
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $grp permanent dst $vtep_ip src_vni 10010"
 	log_test $? 255 "(S, G) with an invalid source list"
 
+	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $all_zeros_grp permanent dst $vtep_ip src_vni 10010"
+	log_test $? 255 "(S, G) with an all-zeros source"
+
 	run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $all_zeros_grp src $src permanent dst $vtep_ip src_vni 10010"
 	log_test $? 255 "All-zeros group with source"
 }
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
index b2ca9d4e991b..e2b03f2b5e89 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json
@@ -353,5 +353,28 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 parent root drr"
         ]
+    },
+    {
+        "id": "70fd",
+        "name": "Add u32 filter when node ID pool is exhausted (4096th filter rejected)",
+        "category": [
+            "filter",
+            "u32"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DUMMY clsact",
+            "bash -c 'for i in {1..4095}; do echo filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0; done | $TC -b -'"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DUMMY ingress prio 1 protocol ip u32 match u8 0 0 at 0",
+        "expExitCode": "2",
+        "verifyCmd": "$TC -d filter show dev $DUMMY ingress",
+        "matchPattern": "fh 800::",
+        "matchCount": "4095",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY clsact"
+        ]
     }
 ]
diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py
index 31afc24ef17b..9313ebe0c525 100644
--- a/tools/workqueue/wq_dump.py
+++ b/tools/workqueue/wq_dump.py
@@ -78,6 +78,12 @@ def cpumask_str(cpumask):
 
 wq_type_len = 9
 
+def wq_attrs(wq):
+    try:
+        return wq.attrs
+    except AttributeError:
+        return wq.unbound_attrs
+
 def wq_type_str(wq):
     if wq.flags & WQ_BH:
         return f'{"bh":{wq_type_len}}'
@@ -85,7 +91,7 @@ def wq_type_str(wq):
         if wq.flags & WQ_ORDERED:
             return f'{"ordered":{wq_type_len}}'
         else:
-            if wq.attrs.affn_strict:
+            if wq_attrs(wq).affn_strict:
                 return f'{"unbound,S":{wq_type_len}}'
             else:
                 return f'{"unbound":{wq_type_len}}'
@@ -206,7 +212,7 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(
 
     print(f'{wq.name.string_().decode():{WQ_NAME_LEN}}', end='')
     if wq.flags & WQ_UNBOUND:
-        print(f' {cpumask_str(wq.attrs.cpumask):{ucpus_len}}', end='')
+        print(f' {cpumask_str(wq_attrs(wq).cpumask):{ucpus_len}}', end='')
     else:
         print(f' {"":{ucpus_len}}', end='')