rseq: Implement syscall entry work for time slice extensions

The kernel sets SYSCALL_WORK_RSEQ_SLICE when it grants a time slice
extension. This allows to handle the rseq_slice_yield() syscall, which is
used by user space to relinquish the CPU after finishing the critical
section for which it requested an extension.

In case the kernel state is still GRANTED, the kernel resets both kernel
and user space state with a set of sanity checks. If the kernel state is
already cleared, then this raced against the timer or some other interrupt
and just clears the work bit.

Doing it in syscall entry work allows to catch misbehaving user space,
which issues an arbitrary syscall, i.e. not rseq_slice_yield(), from the
critical section. Contrary to the initial strict requirement to use
rseq_slice_yield() arbitrary syscalls are not considered a violation of the
ABI contract anymore to allow onion architecture applications, which cannot
control the code inside a critical section, to utilize this as well.

If the code detects inconsistent user space that result in a SIGSEGV for
the application.

If the grant was still active and the task was not preempted yet, the work
code reschedules immediately before continuing through the syscall.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251215155709.005777059@linutronix.de

3 files changed, 12 insertions, 8 deletions

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 87efb38b7081..026201a44aa2 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -36,8 +36,8 @@
 				 SYSCALL_WORK_SYSCALL_EMU |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
 				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
+				 SYSCALL_WORK_SYSCALL_RSEQ_SLICE |	\
 				 ARCH_SYSCALL_WORK_ENTER)
-
 #define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
index 3c194a02ad0a..7a01a0760405 100644
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -164,8 +164,10 @@ static inline void rseq_syscall(struct pt_regs *regs) { }
 #endif /* !CONFIG_DEBUG_RSEQ */
 
 #ifdef CONFIG_RSEQ_SLICE_EXTENSION
+void rseq_syscall_enter_work(long syscall);
 int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3);
 #else /* CONFIG_RSEQ_SLICE_EXTENSION */
+static inline void rseq_syscall_enter_work(long syscall) { }
 static inline int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3)
 {
 	return -ENOTSUPP;
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index b40de9bab4b7..051e42902690 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -46,15 +46,17 @@ enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SYSCALL_AUDIT,
 	SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH,
 	SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP,
+	SYSCALL_WORK_BIT_SYSCALL_RSEQ_SLICE,
 };
 
-#define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
-#define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
-#define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
-#define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
-#define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
-#define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
-#define SYSCALL_WORK_SYSCALL_EXIT_TRAP	BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP)
+#define SYSCALL_WORK_SECCOMP			BIT(SYSCALL_WORK_BIT_SECCOMP)
+#define SYSCALL_WORK_SYSCALL_TRACEPOINT		BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
+#define SYSCALL_WORK_SYSCALL_TRACE		BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
+#define SYSCALL_WORK_SYSCALL_EMU		BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
+#define SYSCALL_WORK_SYSCALL_AUDIT		BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
+#define SYSCALL_WORK_SYSCALL_USER_DISPATCH	BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
+#define SYSCALL_WORK_SYSCALL_EXIT_TRAP		BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP)
+#define SYSCALL_WORK_SYSCALL_RSEQ_SLICE		BIT(SYSCALL_WORK_BIT_SYSCALL_RSEQ_SLICE)
 #endif
 
 #include <asm/thread_info.h>