[PATCH v4 13/15] arm64: Reschedule process on aync PF

[Gavin Shan <gshan@redhat.com>]

The page-not-present notification is delivered by SDEI event. The
guest reschedules current process to another one when the SDEI event
is received. It's not safe to do so in the SDEI event handler because
the SDEI event should be acknowledged as soon as possible.

So the rescheduling is postponed until the current process switches
from kernel to user mode. In order to trigger the switch, the SDEI
event handler sends (reschedule) IPI to current CPU and it's delivered
in time after the SDEI event is acknowledged.

A new thread flag (TIF_ASYNC_PF) is introduced in order to track the
state for the process, to be rescheduled. With the flag is set, there
is a head of wait-queue is associated with the process. The process
keeps rescheduling itself until the flag is cleared when page-ready
notification is received through (PPI) interrupt.

Signed-off-by: Gavin Shan <gshan@redhat.com>
---
 arch/arm64/include/asm/processor.h   |  1 +
 arch/arm64/include/asm/thread_info.h |  4 +++-
 arch/arm64/kernel/signal.c           | 17 +++++++++++++++++
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index b6517fd03d7b..4d05d292baa1 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -156,6 +156,7 @@ struct thread_struct {
 	u64			gcr_user_excl;
 #endif
 	u64			sctlr_user;
+	void			*data;
 };
 
 #define SCTLR_USER_MASK                                                        \
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 6623c99f0984..38567adb26be 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -67,6 +67,7 @@ int arch_dup_task_struct(struct task_struct *dst,
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_MTE_ASYNC_FAULT	5	/* MTE Asynchronous Tag Check Fault */
 #define TIF_NOTIFY_SIGNAL	6	/* signal notifications exist */
+#define TIF_ASYNC_PF		7	/* Asynchronous page fault */
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
 #define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
@@ -97,11 +98,12 @@ int arch_dup_task_struct(struct task_struct *dst,
 #define _TIF_SVE		(1 << TIF_SVE)
 #define _TIF_MTE_ASYNC_FAULT	(1 << TIF_MTE_ASYNC_FAULT)
 #define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
+#define _TIF_ASYNC_PF		(1 << TIF_ASYNC_PF)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
 				 _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \
-				 _TIF_NOTIFY_SIGNAL)
+				 _TIF_NOTIFY_SIGNAL | _TIF_ASYNC_PF)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 23036334f4dc..15c7d115aa5d 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -929,6 +929,23 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned long thread_flags)
 {
 	do {
+		if (thread_flags & _TIF_ASYNC_PF) {
+			struct swait_queue_head *wq =
+				READ_ONCE(current->thread.data);
+			DECLARE_SWAITQUEUE(wait);
+
+			local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+			do {
+				prepare_to_swait_exclusive(wq,
+					&wait, TASK_UNINTERRUPTIBLE);
+				if (!test_thread_flag(TIF_ASYNC_PF))
+					break;
+
+				schedule();
+			} while (test_thread_flag(TIF_ASYNC_PF));
+		}
+
 		if (thread_flags & _TIF_NEED_RESCHED) {
 			/* Unmask Debug and SError for the next task */
 			local_daif_restore(DAIF_PROCCTX_NOIRQ);
-- 
2.23.0