rseq: Implement sys_rseq_slice_yield()

Provide a new syscall which has the only purpose to yield the CPU after the
kernel granted a time slice extension.

sched_yield() is not suitable for that because it unconditionally
schedules, but the end of the time slice extension is not required to
schedule when the task was already preempted. This also allows to have a
strict check for termination to catch user space invoking random syscalls
including sched_yield() from a time slice extension region.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20251215155708.929634896@linutronix.de

22 files changed, 46 insertions, 1 deletions

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 3fed97478058..f31b7afffc34 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -510,3 +510,4 @@
 578	common	file_getattr			sys_file_getattr
 579	common	file_setattr			sys_file_setattr
 580	common	listns				sys_listns
+581	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index fd09afae72a2..94351e22bfcf 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -485,3 +485,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/arm64/tools/syscall_32.tbl b/arch/arm64/tools/syscall_32.tbl
index 8cdfe5d4dac9..62d93d88e0fe 100644
--- a/arch/arm64/tools/syscall_32.tbl
+++ b/arch/arm64/tools/syscall_32.tbl
@@ -482,3 +482,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 871a5d67bf41..248934257101 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -470,3 +470,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 022fc85d94b3..223d26303627 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -476,3 +476,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 8cedc83c3266..7430714e2b8f 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -409,3 +409,4 @@
 468	n32	file_getattr			sys_file_getattr
 469	n32	file_setattr			sys_file_setattr
 470	n32	listns				sys_listns
+471	n32	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 9b92bddf06b5..630aab9e5425 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -385,3 +385,4 @@
 468	n64	file_getattr			sys_file_getattr
 469	n64	file_setattr			sys_file_setattr
 470	n64	listns				sys_listns
+471	n64	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index f810b8a55716..128653112284 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -458,3 +458,4 @@
 468	o32	file_getattr			sys_file_getattr
 469	o32	file_setattr			sys_file_setattr
 470	o32	listns				sys_listns
+471	o32	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 39bdacaa530b..f6e2d0379d57 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -469,3 +469,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index ec4458cdb97b..4fcc7c58a105 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -561,3 +561,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	nospu	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 417ed16b3c63..09a7ef04d979 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -397,3 +397,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 969c11325ade..70b315cbe710 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -474,3 +474,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 39aa26b6a50b..d5b1a7198410 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -516,3 +516,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index e979a3eac7a3..f832ebd2d79b 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -476,3 +476,4 @@
 468	i386	file_getattr		sys_file_getattr
 469	i386	file_setattr		sys_file_setattr
 470	i386	listns			sys_listns
+471	i386	rseq_slice_yield	sys_rseq_slice_yield
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8a4ac4841be6..524155d655da 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,6 +395,7 @@
 468	common	file_getattr		sys_file_getattr
 469	common	file_setattr		sys_file_setattr
 470	common	listns			sys_listns
+471	common	rseq_slice_yield	sys_rseq_slice_yield
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 438a3b170402..a9bca4e484de 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -441,3 +441,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h
index 67e40c059b1b..8c540e775161 100644
--- a/include/linux/rseq_types.h
+++ b/include/linux/rseq_types.h
@@ -89,9 +89,11 @@ union rseq_slice_state {
 /**
  * struct rseq_slice - Status information for rseq time slice extension
  * @state:	Time slice extension state
+ * @yielded:	Indicator for rseq_slice_yield()
  */
 struct rseq_slice {
 	union rseq_slice_state	state;
+	u8			yielded;
 };
 
 /**
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index cf84d98964b2..6c8a570cf44a 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -961,6 +961,7 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
+asmlinkage long sys_rseq_slice_yield(void);
 asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags);
 asmlinkage long sys_open_tree_attr(int dfd, const char __user *path,
 				   unsigned flags,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 942370b3f5d2..a627acc8fb5f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -860,8 +860,11 @@ __SYSCALL(__NR_file_setattr, sys_file_setattr)
 #define __NR_listns 470
 __SYSCALL(__NR_listns, sys_listns)
 
+#define __NR_rseq_slice_yield 471
+__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield)
+
 #undef __NR_syscalls
-#define __NR_syscalls 471
+#define __NR_syscalls 472
 
 /*
  * 32 bit systems traditionally used different
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 09848bb14ec2..d8e1992edffa 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -553,6 +553,27 @@ die:
 	return -EFAULT;
 }
 
+/**
+ * sys_rseq_slice_yield - yield the current processor side effect free if a
+ *			  task granted with a time slice extension is done with
+ *			  the critical work before being forced out.
+ *
+ * Return: 1 if the task successfully yielded the CPU within the granted slice.
+ *         0 if the slice extension was either never granted or was revoked by
+ *	     going over the granted extension, using a syscall other than this one
+ *	     or being scheduled out earlier due to a subsequent interrupt.
+ *
+ * The syscall does not schedule because the syscall entry work immediately
+ * relinquishes the CPU and schedules if required.
+ */
+SYSCALL_DEFINE0(rseq_slice_yield)
+{
+	int yielded = !!current->rseq.slice.yielded;
+
+	current->rseq.slice.yielded = 0;
+	return yielded;
+}
+
 static int __init rseq_slice_cmdline(char *str)
 {
 	bool on;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index bf5d05c635ff..add3032da16f 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -390,6 +390,7 @@ COND_SYSCALL(setuid16);
 
 /* restartable sequence */
 COND_SYSCALL(rseq);
+COND_SYSCALL(rseq_slice_yield);
 
 COND_SYSCALL(uretprobe);
 COND_SYSCALL(uprobe);
diff --git a/scripts/syscall.tbl b/scripts/syscall.tbl
index e74868be513c..7a42b32b6577 100644
--- a/scripts/syscall.tbl
+++ b/scripts/syscall.tbl
@@ -411,3 +411,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield