On (12/31/15 12:13), Sergey Senozhatsky wrote:
[..]
> cond_resched() does its job there, of course. well, a user process still can
> do a lot of call_console_drivers() calls. may be we can check who is calling
> console_unlock() and if we have "!printk_sync && !oops_in_progress" (or just 
> printk_sync
> test) AND a user process then return from console_unlock() doing 
> irq_work_queue()
> and set PRINTK_PENDING_OUTPUT pending bit, the way vprintk_emit() does it.

attached two patches, I ended up having on top of yours. just in case.

    printk: factor out can_printk_async()
    
    console_unlock() can be called directly or indirectly by a user
    space process, so it can end up doing call_console_drivers() loop,
    which will hold it from returning back to user-space from a syscall
    for unpredictable amount of time.
    
    Factor out can_printk_async() function, which queues an irq work and
    sets a PRINTK_PENDING_OUTPUT pending bit (if we can do async printk).
    vprintk_emit() already does it, add can_printk_async() call to
    console_unlock() for !PF_KTHREAD processes.

and

    printk: introduce console_sync_mode
    
    console_sync_mode() should be called early in panic() to switch
    printk from async mode to sync. Otherwise, STOP IPIs can arrive
    to other CPUs too late and those CPUs will see oops_in_progress
    being 0 again.

        -ss
>From c3fc955809adab8f497cdc7581e67e1fa29d6517 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <sergey.senozhat...@gmail.com>
Date: Wed, 30 Dec 2015 20:39:12 +0900
Subject: [PATCH 1/2] printk: introduce console_sync_mode

console_sync_mode() should be called early in panic() to switch
printk from async mode to sync. Otherwise, STOP IPIs can arrive
to other CPUs too late and those CPUs will see oops_in_progress
being 0 again.
---
 include/linux/console.h | 1 +
 kernel/panic.c          | 1 +
 kernel/printk/printk.c  | 5 +++++
 3 files changed, 7 insertions(+)

diff --git a/include/linux/console.h b/include/linux/console.h
index bd19434..f068985 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -150,6 +150,7 @@ extern int console_trylock(void);
 extern void console_unlock(void);
 extern void console_conditional_schedule(void);
 extern void console_unblank(void);
+extern void console_sync_mode(void);
 extern struct tty_driver *console_device(int *);
 extern void console_stop(struct console *);
 extern void console_start(struct console *);
diff --git a/kernel/panic.c b/kernel/panic.c
index b333380..04c8ff4 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -117,6 +117,7 @@ void panic(const char *fmt, ...)
 	if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu)
 		panic_smp_self_stop();
 
+	console_sync_mode();
 	console_verbose();
 	bust_spinlocks(1);
 	va_start(args, fmt);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index de9d31b..47a70a2 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2501,6 +2501,11 @@ void console_unblank(void)
 	console_unlock();
 }
 
+void console_sync_mode(void)
+{
+	printk_sync = true;
+}
+
 /*
  * Return the console tty driver structure and its associated index
  */
-- 
2.6.4

>From 92f2c0f2a5ed015caa2757dcfec4407d708f8628 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <sergey.senozhat...@gmail.com>
Date: Thu, 31 Dec 2015 13:39:58 +0900
Subject: [PATCH 2/2] printk: factor out can_printk_async()

console_unlock() can be called directly or indirectly by a user
space process, so it can end up doing call_console_drivers() loop,
which will hold it from returning back to user-space from a syscall
for unpredictable amount of time.

Factor out can_printk_async() function, which queues an irq work and
sets a PRINTK_PENDING_OUTPUT pending bit (if we can do async printk).
vprintk_emit() already does it, add can_printk_async() call to
console_unlock() for !PF_KTHREAD processes.
---
 kernel/printk/printk.c | 42 ++++++++++++++++++++++++++++--------------
 1 file changed, 28 insertions(+), 14 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 47a70a2..7d3a8e1 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -355,6 +355,26 @@ int printk_deferred(const char *fmt, ...)
 	return r;
 }
 
+static bool can_printk_async(bool sync)
+{
+	/*
+	 * By default we print message to console asynchronously so that kernel
+	 * doesn't get stalled due to slow serial console. That can lead to
+	 * softlockups, lost interrupts, or userspace timing out under heavy
+	 * printing load.
+	 *
+	 * However we resort to synchronous printing of messages during early
+	 * boot, when oops is in progress, or when synchronous printing was
+	 * explicitely requested by kernel parameter.
+	 */
+	if (keventd_up() && !oops_in_progress && !sync) {
+		__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
+		irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
+		return true;
+	}
+	return false;
+}
+
 /* Return log buffer address */
 char *log_buf_addr_get(void)
 {
@@ -1889,20 +1909,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 	logbuf_cpu = UINT_MAX;
 	raw_spin_unlock(&logbuf_lock);
 	lockdep_on();
-	/*
-	 * By default we print message to console asynchronously so that kernel
-	 * doesn't get stalled due to slow serial console. That can lead to
-	 * softlockups, lost interrupts, or userspace timing out under heavy
-	 * printing load.
-	 *
-	 * However we resort to synchronous printing of messages during early
-	 * boot, when oops is in progress, or when synchronous printing was
-	 * explicitely requested by kernel parameter.
-	 */
-	if (keventd_up() && !oops_in_progress && !sync_print) {
-		__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
-		irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
-	} else
+	if (!can_printk_async(sync_print))
 		sync_print = true;
 	local_irq_restore(flags);
 
@@ -2328,6 +2335,13 @@ void console_unlock(void)
 		return;
 	}
 
+	if (!(current->flags & PF_KTHREAD) &&
+			can_printk_async(printk_sync)) {
+		console_locked = 0;
+		up_console_sem();
+		return;
+	}
+
 	/*
 	 * Console drivers are called under logbuf_lock, so
 	 * @console_may_schedule should be cleared before; however, we may
-- 
2.6.4

Reply via email to