Merge tag 'for-linus-5.3-rc1' of git://git.kernel.org/pub/scm/linux/k…

…ernel/git/rw/uml

Pull UML updates from Richard Weinberger:

 - A new timer mode, time travel, for testing with UML

 - Many bugixes/improvements for the serial line driver

 - Various bugfixes

* tag 'for-linus-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml:
  um: fix build without CONFIG_UML_TIME_TRAVEL_SUPPORT
  um: Fix kcov crash during startup
  um: configs: Remove useless UEVENT_HELPER_PATH
  um: Support time travel mode
  um: Pass nsecs to os timer functions
  um: Remove drivers/ssl.h
  um: Don't garbage collect in deactivate_all_fds()
  um: Silence lockdep complaint about mmap_sem
  um: Remove locking in deactivate_all_fds()
  um: Timer code cleanup
  um: fix os_timer_one_shot()
  um: Fix IRQ controller regression on console read

arch/um/Kconfig

@@ -184,6 +184,18 @@ config SECCOMP
 
 	  If unsure, say Y.
 
+config UML_TIME_TRAVEL_SUPPORT
+	bool
+	prompt "Support time-travel mode (e.g. for test execution)"
+	help
+	  Enable this option to support time travel inside the UML instance.
+
+	  After enabling this option, two modes are accessible at runtime
+	  (selected by the kernel command line), see the kernel's command-
+	  line help for more details.
+
+	  It is safe to say Y, but you probably don't need this.
+
 endmenu
 
 source "arch/um/drivers/Kconfig"

arch/um/configs/i386_defconfig

@@ -36,7 +36,6 @@ CONFIG_XTERM_CHAN=y
 CONFIG_CON_CHAN="pts"
 CONFIG_SSL_CHAN="pts"
 CONFIG_UML_SOUND=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_UBD=y

arch/um/configs/x86_64_defconfig

@@ -34,7 +34,6 @@ CONFIG_XTERM_CHAN=y
 CONFIG_CON_CHAN="pts"
 CONFIG_SSL_CHAN="pts"
 CONFIG_UML_SOUND=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_UBD=y

arch/um/drivers/chan_kern.c

@@ -171,19 +171,55 @@ int enable_chan(struct line *line)
 	return err;
 }
 
+/* Items are added in IRQ context, when free_irq can't be called, and
+ * removed in process context, when it can.
+ * This handles interrupt sources which disappear, and which need to
+ * be permanently disabled.  This is discovered in IRQ context, but
+ * the freeing of the IRQ must be done later.
+ */
+static DEFINE_SPINLOCK(irqs_to_free_lock);
+static LIST_HEAD(irqs_to_free);
+
+void free_irqs(void)
+{
+	struct chan *chan;
+	LIST_HEAD(list);
+	struct list_head *ele;
+	unsigned long flags;
+
+	spin_lock_irqsave(&irqs_to_free_lock, flags);
+	list_splice_init(&irqs_to_free, &list);
+	spin_unlock_irqrestore(&irqs_to_free_lock, flags);
+
+	list_for_each(ele, &list) {
+		chan = list_entry(ele, struct chan, free_list);
+
+		if (chan->input && chan->enabled)
+			um_free_irq(chan->line->driver->read_irq, chan);
+		if (chan->output && chan->enabled)
+			um_free_irq(chan->line->driver->write_irq, chan);
+		chan->enabled = 0;
+	}
+}
+
 static void close_one_chan(struct chan *chan, int delay_free_irq)
 {
+	unsigned long flags;
+
 	if (!chan->opened)
 		return;
 
-    /* we can safely call free now - it will be marked
-     *  as free and freed once the IRQ stopped processing
-     */
-	if (chan->input && chan->enabled)
-		um_free_irq(chan->line->driver->read_irq, chan);
-	if (chan->output && chan->enabled)
-		um_free_irq(chan->line->driver->write_irq, chan);
-	chan->enabled = 0;
+	if (delay_free_irq) {
+		spin_lock_irqsave(&irqs_to_free_lock, flags);
+		list_add(&chan->free_list, &irqs_to_free);
+		spin_unlock_irqrestore(&irqs_to_free_lock, flags);
+	} else {
+		if (chan->input && chan->enabled)
+			um_free_irq(chan->line->driver->read_irq, chan);
+		if (chan->output && chan->enabled)
+			um_free_irq(chan->line->driver->write_irq, chan);
+		chan->enabled = 0;
+	}
 	if (chan->ops->close != NULL)
 		(*chan->ops->close)(chan->fd, chan->data);
 

arch/um/drivers/ssl.c

@@ -12,7 +12,6 @@
 #include <linux/console.h>
 #include <asm/termbits.h>
 #include <asm/irq.h>
-#include "ssl.h"
 #include "chan.h"
 #include <init.h>
 #include <irq_user.h>

arch/um/include/asm/mmu_context.h

@@ -52,7 +52,7 @@ static inline void activate_mm(struct mm_struct *old, struct mm_struct *new)
 	 * when the new ->mm is used for the first time.
 	 */
 	__switch_mm(&new->context.id);
-	down_write(&new->mmap_sem);
+	down_write_nested(&new->mmap_sem, 1);
 	uml_setup_stubs(new);
 	up_write(&new->mmap_sem);
 }

arch/um/include/shared/os.h

@@ -250,15 +250,13 @@ extern void os_warn(const char *fmt, ...)
 
 /* time.c */
 extern void os_idle_sleep(unsigned long long nsecs);
-extern int os_timer_create(void* timer);
-extern int os_timer_set_interval(void* timer, void* its);
-extern int os_timer_one_shot(int ticks);
-extern long long os_timer_disable(void);
-extern long os_timer_remain(void* timer);
+extern int os_timer_create(void);
+extern int os_timer_set_interval(unsigned long long nsecs);
+extern int os_timer_one_shot(unsigned long long nsecs);
+extern void os_timer_disable(void);
 extern void uml_idle_timer(void);
 extern long long os_persistent_clock_emulation(void);
 extern long long os_nsecs(void);
-extern long long os_vnsecs(void);
 
 /* skas/mem.c */
 extern long run_syscall_stub(struct mm_id * mm_idp,

arch/um/include/shared/timer-internal.h

@@ -10,4 +10,52 @@
 #define TIMER_MULTIPLIER 256
 #define TIMER_MIN_DELTA  500
 
+enum time_travel_mode {
+	TT_MODE_OFF,
+	TT_MODE_BASIC,
+	TT_MODE_INFCPU,
+};
+
+enum time_travel_timer_mode {
+	TT_TMR_DISABLED,
+	TT_TMR_ONESHOT,
+	TT_TMR_PERIODIC,
+};
+
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+extern enum time_travel_mode time_travel_mode;
+extern unsigned long long time_travel_time;
+extern enum time_travel_timer_mode time_travel_timer_mode;
+extern unsigned long long time_travel_timer_expiry;
+extern unsigned long long time_travel_timer_interval;
+
+static inline void time_travel_set_time(unsigned long long ns)
+{
+	time_travel_time = ns;
+}
+
+static inline void time_travel_set_timer(enum time_travel_timer_mode mode,
+					 unsigned long long expiry)
+{
+	time_travel_timer_mode = mode;
+	time_travel_timer_expiry = expiry;
+}
+#else
+#define time_travel_mode TT_MODE_OFF
+#define time_travel_time 0
+#define time_travel_timer_expiry 0
+#define time_travel_timer_interval 0
+
+static inline void time_travel_set_time(unsigned long long ns)
+{
+}
+
+static inline void time_travel_set_timer(enum time_travel_timer_mode mode,
+					 unsigned long long expiry)
+{
+}
+
+#define time_travel_timer_mode TT_TMR_DISABLED
+#endif
+
 #endif

arch/um/kernel/irq.c

@@ -21,6 +21,8 @@
 #include <irq_user.h>
 
 
+extern void free_irqs(void);
+
 /* When epoll triggers we do not know why it did so
  * we can also have different IRQs for read and write.
  * This is why we keep a small irq_fd array for each fd -
@@ -100,6 +102,8 @@ void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 			}
 		}
 	}
+
+	free_irqs();
 }
 
 static int assign_epoll_events_to_irq(struct irq_entry *irq_entry)
@@ -380,10 +384,8 @@ EXPORT_SYMBOL(deactivate_fd);
  */
 int deactivate_all_fds(void)
 {
-	unsigned long flags;
 	struct irq_entry *to_free;
 
-	spin_lock_irqsave(&irq_lock, flags);
 	/* Stop IO. The IRQ loop has no lock so this is our
 	 * only way of making sure we are safe to dispose
 	 * of all IRQ handlers
@@ -399,8 +401,7 @@ int deactivate_all_fds(void)
 		);
 		to_free = to_free->next;
 	}
-	garbage_collect_irq_entries();
-	spin_unlock_irqrestore(&irq_lock, flags);
+	/* don't garbage collect - we can no longer call kfree() here */
 	os_close_epoll_fd();
 	return 0;
 }

arch/um/kernel/process.c

@@ -203,10 +203,50 @@ void initial_thread_cb(void (*proc)(void *), void *arg)
 	kmalloc_ok = save_kmalloc_ok;
 }
 
+static void time_travel_sleep(unsigned long long duration)
+{
+	unsigned long long next = time_travel_time + duration;
+
+	if (time_travel_mode != TT_MODE_INFCPU)
+		os_timer_disable();
+
+	if (time_travel_timer_mode != TT_TMR_DISABLED ||
+	    time_travel_timer_expiry < next) {
+		if (time_travel_timer_mode == TT_TMR_ONESHOT)
+			time_travel_set_timer(TT_TMR_DISABLED, 0);
+		/*
+		 * time_travel_time will be adjusted in the timer
+		 * IRQ handler so it works even when the signal
+		 * comes from the OS timer
+		 */
+		deliver_alarm();
+	} else {
+		time_travel_set_time(next);
+	}
+
+	if (time_travel_mode != TT_MODE_INFCPU) {
+		if (time_travel_timer_mode == TT_TMR_PERIODIC)
+			os_timer_set_interval(time_travel_timer_interval);
+		else if (time_travel_timer_mode == TT_TMR_ONESHOT)
+			os_timer_one_shot(time_travel_timer_expiry - next);
+	}
+}
+
+static void um_idle_sleep(void)
+{
+	unsigned long long duration = UM_NSEC_PER_SEC;
+
+	if (time_travel_mode != TT_MODE_OFF) {
+		time_travel_sleep(duration);
+	} else {
+		os_idle_sleep(duration);
+	}
+}
+
 void arch_cpu_idle(void)
 {
 	cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
-	os_idle_sleep(UM_NSEC_PER_SEC);
+	um_idle_sleep();
 	local_irq_enable();
 }
 

arch/um/kernel/skas/Makefile

@@ -12,4 +12,6 @@ obj-y := clone.o mmu.o process.o syscall.o uaccess.o
 CFLAGS_clone.o := $(CFLAGS_NO_HARDENING)
 UNPROFILE_OBJS := clone.o
 
+KCOV_INSTRUMENT := n
+
 include arch/um/scripts/Makefile.rules

arch/um/kernel/skas/syscall.c

@@ -10,12 +10,23 @@
 #include <sysdep/ptrace.h>
 #include <sysdep/ptrace_user.h>
 #include <sysdep/syscalls.h>
+#include <shared/timer-internal.h>
 
 void handle_syscall(struct uml_pt_regs *r)
 {
 	struct pt_regs *regs = container_of(r, struct pt_regs, regs);
 	int syscall;
 
+	/*
+	 * If we have infinite CPU resources, then make every syscall also a
+	 * preemption point, since we don't have any other preemption in this
+	 * case, and kernel threads would basically never run until userspace
+	 * went to sleep, even if said userspace interacts with the kernel in
+	 * various ways.
+	 */
+	if (time_travel_mode == TT_MODE_INFCPU)
+		schedule();
+
 	/* Initialize the syscall number and default return value. */
 	UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
 	PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);