selftests/bpf: Test rhtab kptr cancellation semanticsgrafted

Resizable hash-map updates and deletions must not perform full special-field
destruction in their caller context. In particular, a referenced kptr must
remain attached to the allocation until the memory allocator destructor can
release it safely.

Add separate coverage for both affected paths. The update test stores a task
kptr, replaces the ordinary value bytes with BPF_EXIST, and verifies that the
kptr survived. The delete test removes an element and exchanges its kptr
through the still-valid map-value pointer before the allocation is reclaimed.

Both cases observe a NULL kptr when rhtab uses bpf_obj_free_fields(). They
recover and release the reference after rhtab switches to cancellation
semantics.

Signed-off-by: Nuoqi Gui <gnq25@mails.tsinghua.edu.cn>
[ kkd: Split update and delete coverage and rewrote the commit log ]
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260904104203.345917-5-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 57 insertions, 0 deletions

diff --git a/include/trace/syscall.h b/include/trace/syscall.h
new file mode 100644
index 000000000..0dd7f2b33
--- /dev/null
+++ b/include/trace/syscall.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TRACE_SYSCALL_H
+#define _TRACE_SYSCALL_H
+
+#include <linux/tracepoint.h>
+#include <linux/unistd.h>
+#include <linux/trace_events.h>
+#include <linux/thread_info.h>
+
+#include <asm/ptrace.h>
+
+
+/*
+ * A syscall entry in the ftrace syscalls array.
+ *
+ * @name: name of the syscall
+ * @syscall_nr: number of the syscall
+ * @nb_args: number of parameters it takes
+ * @user_arg_is_str: set if the arg for @user_arg_size is a string
+ * @user_arg_size: holds @arg that has size of the user space to read
+ * @user_mask: mask of @args that will read user space
+ * @types: list of types as strings
+ * @args: list of args as strings (args[i] matches types[i])
+ * @enter_fields: list of fields for syscall_enter trace event
+ * @enter_event: associated syscall_enter trace event
+ * @exit_event: associated syscall_exit trace event
+ */
+struct syscall_metadata {
+	const char	*name;
+	int		syscall_nr;
+	u8		nb_args:7;
+	u8		user_arg_is_str:1;
+	s8		user_arg_size;
+	short		user_mask;
+	const char	**types;
+	const char	**args;
+	struct list_head enter_fields;
+
+	struct trace_event_call *enter_event;
+	struct trace_event_call *exit_event;
+};
+
+#if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+	if (test_syscall_work(SYSCALL_TRACEPOINT))
+		set_task_syscall_work(p, SYSCALL_TRACEPOINT);
+	else
+		clear_task_syscall_work(p, SYSCALL_TRACEPOINT);
+}
+#else
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+}
+#endif
+
+#endif /* _TRACE_SYSCALL_H */