um: insert scheduler ticks when userspace does not yield

In time-travel mode userspace can do a lot of work without any time
passing. Unfortunately, this can result in OOM situations as the RCU
core code will never be run.

Work around this by keeping track of userspace processes that do not
yield for a lot of operations. When this happens, insert a jiffie into
the sched_clock clock to account time against the process and cause the
bookkeeping to run.

As sched_clock is used for tracing, it is useful to keep it in sync
between the different VMs. As such, try to remove added ticks again when
the actual clock ticks.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Link: https://patch.msgid.link/20241010142537.1134685-1-benjamin@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

arch/um/Kconfig

@@ -227,6 +227,21 @@ config UML_TIME_TRAVEL_SUPPORT
 
 	  It is safe to say Y, but you probably don't need this.
 
+config UML_MAX_USERSPACE_ITERATIONS
+	int
+	prompt "Maximum number of unscheduled userspace iterations"
+	default 10000
+	depends on UML_TIME_TRAVEL_SUPPORT
+	help
+	  In UML inf-cpu and ext time-travel mode userspace can run without being
+	  interrupted. This will eventually overwhelm the kernel and create OOM
+	  situations (mainly RCU not running). This setting specifies the number
+	  of kernel/userspace switches (minor/major page fault, signal or syscall)
+	  for the same userspace thread before the sched_clock is advanced by a
+	  jiffie to trigger scheduling.
+
+	  Setting it to zero disables the feature.
+
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN

arch/um/include/shared/common-offsets.h

@@ -28,4 +28,8 @@ DEFINE(UML_CONFIG_64BIT, CONFIG_64BIT);
 #ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
 DEFINE(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT, CONFIG_UML_TIME_TRAVEL_SUPPORT);
 #endif
-
+#ifdef CONFIG_UML_MAX_USERSPACE_ITERATIONS
+DEFINE(UML_CONFIG_UML_MAX_USERSPACE_ITERATIONS, CONFIG_UML_MAX_USERSPACE_ITERATIONS);
+#else
+DEFINE(UML_CONFIG_UML_MAX_USERSPACE_ITERATIONS, 0);
+#endif

arch/um/kernel/time.c

@@ -25,6 +25,8 @@
 #include <shared/init.h>
 
 #ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+#include <linux/sched/clock.h>
+
 enum time_travel_mode time_travel_mode;
 EXPORT_SYMBOL_GPL(time_travel_mode);
 
@@ -47,6 +49,15 @@ static u16 time_travel_shm_id;
 static struct um_timetravel_schedshm *time_travel_shm;
 static union um_timetravel_schedshm_client *time_travel_shm_client;
 
+unsigned long tt_extra_sched_jiffies;
+
+notrace unsigned long long sched_clock(void)
+{
+	return (unsigned long long)(jiffies - INITIAL_JIFFIES +
+				    tt_extra_sched_jiffies)
+					* (NSEC_PER_SEC / HZ);
+}
+
 static void time_travel_set_time(unsigned long long ns)
 {
 	if (unlikely(ns < time_travel_time))
@@ -443,6 +454,11 @@ static void time_travel_periodic_timer(struct time_travel_event *e)
 {
 	time_travel_add_event(&time_travel_timer_event,
 			      time_travel_time + time_travel_timer_interval);
+
+	/* clock tick; decrease extra jiffies by keeping sched_clock constant */
+	if (tt_extra_sched_jiffies > 0)
+		tt_extra_sched_jiffies -= 1;
+
 	deliver_alarm();
 }
 
@@ -594,6 +610,10 @@ EXPORT_SYMBOL_GPL(time_travel_add_irq_event);
 
 static void time_travel_oneshot_timer(struct time_travel_event *e)
 {
+	/* clock tick; decrease extra jiffies by keeping sched_clock constant */
+	if (tt_extra_sched_jiffies > 0)
+		tt_extra_sched_jiffies -= 1;
+
 	deliver_alarm();
 }
 

arch/um/os-Linux/skas/process.c

@@ -388,6 +388,9 @@ int start_userspace(unsigned long stub_stack)
 	return err;
 }
 
+int unscheduled_userspace_iterations;
+extern unsigned long tt_extra_sched_jiffies;
+
 void userspace(struct uml_pt_regs *regs)
 {
 	int err, status, op, pid = userspace_pid[0];
@@ -397,6 +400,27 @@ void userspace(struct uml_pt_regs *regs)
 	interrupt_end();
 
 	while (1) {
+		/*
+		 * When we are in time-travel mode, userspace can theoretically
+		 * do a *lot* of work without being scheduled. The problem with
+		 * this is that it will prevent kernel bookkeeping (primarily
+		 * the RCU) from running and this can for example cause OOM
+		 * situations.
+		 *
+		 * This code accounts a jiffie against the scheduling clock
+		 * after the defined userspace iterations in the same thread.
+		 * By doing so the situation is effectively prevented.
+		 */
+		if (time_travel_mode == TT_MODE_INFCPU ||
+		    time_travel_mode == TT_MODE_EXTERNAL) {
+			if (UML_CONFIG_UML_MAX_USERSPACE_ITERATIONS &&
+			    unscheduled_userspace_iterations++ >
+			    UML_CONFIG_UML_MAX_USERSPACE_ITERATIONS) {
+				tt_extra_sched_jiffies += 1;
+				unscheduled_userspace_iterations = 0;
+			}
+		}
+
 		time_travel_print_bc_msg();
 
 		current_mm_sync();
@@ -539,6 +563,8 @@ void new_thread(void *stack, jmp_buf *buf, void (*handler)(void))
 
 void switch_threads(jmp_buf *me, jmp_buf *you)
 {
+	unscheduled_userspace_iterations = 0;
+
 	if (UML_SETJMP(me) == 0)
 		UML_LONGJMP(you, 1);
 }