Message-Id: <1236868428-20408-4-git-send-email-jens.axboe@oracle.com>
Date:	Thu, 12 Mar 2009 15:33:44 +0100
From:	Jens Axboe <jens.axboe@...cle.com>
To:	linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org
Cc:	chris.mason@...cle.com, david@...morbit.com, npiggin@...e.de,
	Jens Axboe <jens.axboe@...cle.com>
Subject: [PATCH 3/7] writeback: get rid of pdflush_operation() in emergency sync and remount

Opencode a cheasy approach with kevent. The idea here is that we'll
add some generic delayed work infrastructure, which probably wont be
based on pdflush (or maybe it will, in which case we can just add it
back).

Kill off mm/pdflush.c

Signed-off-by: Jens Axboe <jens.axboe@...cle.com>
---
 fs/fs-writeback.c         |    5 +
 fs/super.c                |   11 ++-
 fs/sync.c                 |   14 +++-
 include/linux/writeback.h |    1 -
 mm/Makefile               |    2 +-
 mm/pdflush.c              |  251 ---------------------------------------------
 6 files changed, 28 insertions(+), 256 deletions(-)
 delete mode 100644 mm/pdflush.c

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 209c6fa..37b042f 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -29,6 +29,11 @@
 
 #define inode_to_bdi(inode)	(inode)->i_mapping->backing_dev_info
 
+/*
+ * We don't actually have pdflush, but this one is exported though /proc...
+ */
+int nr_pdflush_threads = 0;
+
 /**
  * writeback_acquire - attempt to get exclusive writeback access to a device
  * @bdi: the device's backing_dev_info structure
diff --git a/fs/super.c b/fs/super.c
index e3c5b6f..3c715fd 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -668,7 +668,7 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 	return 0;
 }
 
-static void do_emergency_remount(unsigned long foo)
+static void do_emergency_remount(struct work_struct *work)
 {
 	struct super_block *sb;
 
@@ -691,12 +691,19 @@ static void do_emergency_remount(unsigned long foo)
 		spin_lock(&sb_lock);
 	}
 	spin_unlock(&sb_lock);
+	kfree(work);
 	printk("Emergency Remount complete\n");
 }
 
 void emergency_remount(void)
 {
-	pdflush_operation(do_emergency_remount, 0);
+	struct work_struct *work;
+
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (work) {
+		INIT_WORK(work, do_emergency_remount);
+		schedule_work(work);
+	}
 }
 
 /*
diff --git a/fs/sync.c b/fs/sync.c
index f4ddcef..4552be6 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -42,9 +42,21 @@ SYSCALL_DEFINE0(sync)
 	return 0;
 }
 
+static void do_sync_work(struct work_struct *work)
+{
+	do_sync(0);
+	kfree(work);
+}
+
 void emergency_sync(void)
 {
-	pdflush_operation(do_sync, 0);
+	struct work_struct *work;
+
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (work) {
+		INIT_WORK(work, do_sync_work);
+		schedule_work(work);
+	}
 }
 
 /*
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 3697e91..724327b 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -151,7 +151,6 @@ balance_dirty_pages_ratelimited(struct address_space *mapping)
 typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 				void *data);
 
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
 int generic_writepages(struct address_space *mapping,
 		       struct writeback_control *wbc);
 int write_cache_pages(struct address_space *mapping,
diff --git a/mm/Makefile b/mm/Makefile
index 72255be..6443e19 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -8,7 +8,7 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   vmalloc.o
 
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
-			   maccess.o page_alloc.o page-writeback.o pdflush.o \
+			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   page_isolation.o mm_init.o $(mmu-y)
diff --git a/mm/pdflush.c b/mm/pdflush.c
deleted file mode 100644
index 15de509..0000000
--- a/mm/pdflush.c
+++ /dev/null
@@ -1,251 +0,0 @@
-/*
- * mm/pdflush.c - worker threads for writing back filesystem data
- *
- * Copyright (C) 2002, Linus Torvalds.
- *
- * 09Apr2002	Andrew Morton
- *		Initial version
- * 29Feb2004	kaos@....com
- *		Move worker thread creation to kthread to avoid chewing
- *		up stack space with nested calls to kernel_thread.
- */
-
-#include <linux/sched.h>
-#include <linux/list.h>
-#include <linux/signal.h>
-#include <linux/spinlock.h>
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/fs.h>		/* Needed by writeback.h	  */
-#include <linux/writeback.h>	/* Prototypes pdflush_operation() */
-#include <linux/kthread.h>
-#include <linux/cpuset.h>
-#include <linux/freezer.h>
-
-
-/*
- * Minimum and maximum number of pdflush instances
- */
-#define MIN_PDFLUSH_THREADS	2
-#define MAX_PDFLUSH_THREADS	8
-
-static void start_one_pdflush_thread(void);
-
-
-/*
- * The pdflush threads are worker threads for writing back dirty data.
- * Ideally, we'd like one thread per active disk spindle.  But the disk
- * topology is very hard to divine at this level.   Instead, we take
- * care in various places to prevent more than one pdflush thread from
- * performing writeback against a single filesystem.  pdflush threads
- * have the PF_FLUSHER flag set in current->flags to aid in this.
- */
-
-/*
- * All the pdflush threads.  Protected by pdflush_lock
- */
-static LIST_HEAD(pdflush_list);
-static DEFINE_SPINLOCK(pdflush_lock);
-
-/*
- * The count of currently-running pdflush threads.  Protected
- * by pdflush_lock.
- *
- * Readable by sysctl, but not writable.  Published to userspace at
- * /proc/sys/vm/nr_pdflush_threads.
- */
-int nr_pdflush_threads = 0;
-
-/*
- * The time at which the pdflush thread pool last went empty
- */
-static unsigned long last_empty_jifs;
-
-/*
- * The pdflush thread.
- *
- * Thread pool management algorithm:
- * 
- * - The minimum and maximum number of pdflush instances are bound
- *   by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
- * 
- * - If there have been no idle pdflush instances for 1 second, create
- *   a new one.
- * 
- * - If the least-recently-went-to-sleep pdflush thread has been asleep
- *   for more than one second, terminate a thread.
- */
-
-/*
- * A structure for passing work to a pdflush thread.  Also for passing
- * state information between pdflush threads.  Protected by pdflush_lock.
- */
-struct pdflush_work {
-	struct task_struct *who;	/* The thread */
-	void (*fn)(unsigned long);	/* A callback function */
-	unsigned long arg0;		/* An argument to the callback */
-	struct list_head list;		/* On pdflush_list, when idle */
-	unsigned long when_i_went_to_sleep;
-};
-
-static int __pdflush(struct pdflush_work *my_work)
-{
-	current->flags |= PF_FLUSHER | PF_SWAPWRITE;
-	set_freezable();
-	my_work->fn = NULL;
-	my_work->who = current;
-	INIT_LIST_HEAD(&my_work->list);
-
-	spin_lock_irq(&pdflush_lock);
-	nr_pdflush_threads++;
-	for ( ; ; ) {
-		struct pdflush_work *pdf;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		list_move(&my_work->list, &pdflush_list);
-		my_work->when_i_went_to_sleep = jiffies;
-		spin_unlock_irq(&pdflush_lock);
-		schedule();
-		try_to_freeze();
-		spin_lock_irq(&pdflush_lock);
-		if (!list_empty(&my_work->list)) {
-			/*
-			 * Someone woke us up, but without removing our control
-			 * structure from the global list.  swsusp will do this
-			 * in try_to_freeze()->refrigerator().  Handle it.
-			 */
-			my_work->fn = NULL;
-			continue;
-		}
-		if (my_work->fn == NULL) {
-			printk("pdflush: bogus wakeup\n");
-			continue;
-		}
-		spin_unlock_irq(&pdflush_lock);
-
-		(*my_work->fn)(my_work->arg0);
-
-		/*
-		 * Thread creation: For how long have there been zero
-		 * available threads?
-		 */
-		if (time_after(jiffies, last_empty_jifs + 1 * HZ)) {
-			/* unlocked list_empty() test is OK here */
-			if (list_empty(&pdflush_list)) {
-				/* unlocked test is OK here */
-				if (nr_pdflush_threads < MAX_PDFLUSH_THREADS)
-					start_one_pdflush_thread();
-			}
-		}
-
-		spin_lock_irq(&pdflush_lock);
-		my_work->fn = NULL;
-
-		/*
-		 * Thread destruction: For how long has the sleepiest
-		 * thread slept?
-		 */
-		if (list_empty(&pdflush_list))
-			continue;
-		if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
-			continue;
-		pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
-		if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) {
-			/* Limit exit rate */
-			pdf->when_i_went_to_sleep = jiffies;
-			break;					/* exeunt */
-		}
-	}
-	nr_pdflush_threads--;
-	spin_unlock_irq(&pdflush_lock);
-	return 0;
-}
-
-/*
- * Of course, my_work wants to be just a local in __pdflush().  It is
- * separated out in this manner to hopefully prevent the compiler from
- * performing unfortunate optimisations against the auto variables.  Because
- * these are visible to other tasks and CPUs.  (No problem has actually
- * been observed.  This is just paranoia).
- */
-static int pdflush(void *dummy)
-{
-	struct pdflush_work my_work;
-	cpumask_var_t cpus_allowed;
-
-	/*
-	 * Since the caller doesn't even check kthread_run() worked, let's not
-	 * freak out too much if this fails.
-	 */
-	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
-		printk(KERN_WARNING "pdflush failed to allocate cpumask\n");
-		return 0;
-	}
-
-	/*
-	 * pdflush can spend a lot of time doing encryption via dm-crypt.  We
-	 * don't want to do that at keventd's priority.
-	 */
-	set_user_nice(current, 0);
-
-	/*
-	 * Some configs put our parent kthread in a limited cpuset,
-	 * which kthread() overrides, forcing cpus_allowed == CPU_MASK_ALL.
-	 * Our needs are more modest - cut back to our cpusets cpus_allowed.
-	 * This is needed as pdflush's are dynamically created and destroyed.
-	 * The boottime pdflush's are easily placed w/o these 2 lines.
-	 */
-	cpuset_cpus_allowed(current, cpus_allowed);
-	set_cpus_allowed_ptr(current, cpus_allowed);
-	free_cpumask_var(cpus_allowed);
-
-	return __pdflush(&my_work);
-}
-
-/*
- * Attempt to wake up a pdflush thread, and get it to do some work for you.
- * Returns zero if it indeed managed to find a worker thread, and passed your
- * payload to it.
- */
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
-{
-	unsigned long flags;
-	int ret = 0;
-
-	BUG_ON(fn == NULL);	/* Hard to diagnose if it's deferred */
-
-	spin_lock_irqsave(&pdflush_lock, flags);
-	if (list_empty(&pdflush_list)) {
-		ret = -1;
-	} else {
-		struct pdflush_work *pdf;
-
-		pdf = list_entry(pdflush_list.next, struct pdflush_work, list);
-		list_del_init(&pdf->list);
-		if (list_empty(&pdflush_list))
-			last_empty_jifs = jiffies;
-		pdf->fn = fn;
-		pdf->arg0 = arg0;
-		wake_up_process(pdf->who);
-	}
-	spin_unlock_irqrestore(&pdflush_lock, flags);
-
-	return ret;
-}
-
-static void start_one_pdflush_thread(void)
-{
-	kthread_run(pdflush, NULL, "pdflush");
-}
-
-static int __init pdflush_init(void)
-{
-	int i;
-
-	for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
-		start_one_pdflush_thread();
-	return 0;
-}
-
-module_init(pdflush_init);
-- 
1.6.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists