blob: df7e50b8f70c1350a404d446a62e0845b6235bf1 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/*
2 * mm/pdflush.c - worker threads for writing back filesystem data
3 *
4 * Copyright (C) 2002, Linus Torvalds.
5 *
6 * 09Apr2002 akpm@zip.com.au
7 * Initial version
8 * 29Feb2004 kaos@sgi.com
9 * Move worker thread creation to kthread to avoid chewing
10 * up stack space with nested calls to kernel_thread.
11 */
12
13#include <linux/sched.h>
14#include <linux/list.h>
15#include <linux/signal.h>
16#include <linux/spinlock.h>
17#include <linux/gfp.h>
18#include <linux/init.h>
19#include <linux/module.h>
20#include <linux/fs.h> // Needed by writeback.h
21#include <linux/writeback.h> // Prototypes pdflush_operation()
22#include <linux/kthread.h>
Paul Jackson28a42b92005-10-30 15:02:32 -080023#include <linux/cpuset.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070024
25
26/*
27 * Minimum and maximum number of pdflush instances
28 */
29#define MIN_PDFLUSH_THREADS 2
30#define MAX_PDFLUSH_THREADS 8
31
32static void start_one_pdflush_thread(void);
33
34
35/*
36 * The pdflush threads are worker threads for writing back dirty data.
37 * Ideally, we'd like one thread per active disk spindle. But the disk
38 * topology is very hard to divine at this level. Instead, we take
39 * care in various places to prevent more than one pdflush thread from
40 * performing writeback against a single filesystem. pdflush threads
41 * have the PF_FLUSHER flag set in current->flags to aid in this.
42 */
43
44/*
45 * All the pdflush threads. Protected by pdflush_lock
46 */
47static LIST_HEAD(pdflush_list);
48static DEFINE_SPINLOCK(pdflush_lock);
49
50/*
51 * The count of currently-running pdflush threads. Protected
52 * by pdflush_lock.
53 *
54 * Readable by sysctl, but not writable. Published to userspace at
55 * /proc/sys/vm/nr_pdflush_threads.
56 */
57int nr_pdflush_threads = 0;
58
59/*
60 * The time at which the pdflush thread pool last went empty
61 */
62static unsigned long last_empty_jifs;
63
64/*
65 * The pdflush thread.
66 *
67 * Thread pool management algorithm:
68 *
69 * - The minimum and maximum number of pdflush instances are bound
70 * by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
71 *
72 * - If there have been no idle pdflush instances for 1 second, create
73 * a new one.
74 *
75 * - If the least-recently-went-to-sleep pdflush thread has been asleep
76 * for more than one second, terminate a thread.
77 */
78
79/*
80 * A structure for passing work to a pdflush thread. Also for passing
81 * state information between pdflush threads. Protected by pdflush_lock.
82 */
83struct pdflush_work {
84 struct task_struct *who; /* The thread */
85 void (*fn)(unsigned long); /* A callback function */
86 unsigned long arg0; /* An argument to the callback */
87 struct list_head list; /* On pdflush_list, when idle */
88 unsigned long when_i_went_to_sleep;
89};
90
91static int __pdflush(struct pdflush_work *my_work)
92{
Christoph Lameter930d9152006-01-08 01:00:47 -080093 current->flags |= PF_FLUSHER | PF_SWAPWRITE;
Linus Torvalds1da177e2005-04-16 15:20:36 -070094 my_work->fn = NULL;
95 my_work->who = current;
96 INIT_LIST_HEAD(&my_work->list);
97
98 spin_lock_irq(&pdflush_lock);
99 nr_pdflush_threads++;
100 for ( ; ; ) {
101 struct pdflush_work *pdf;
102
103 set_current_state(TASK_INTERRUPTIBLE);
104 list_move(&my_work->list, &pdflush_list);
105 my_work->when_i_went_to_sleep = jiffies;
106 spin_unlock_irq(&pdflush_lock);
107
108 schedule();
Christoph Lameter3e1d1d22005-06-24 23:13:50 -0700109 if (try_to_freeze()) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700110 spin_lock_irq(&pdflush_lock);
111 continue;
112 }
113
114 spin_lock_irq(&pdflush_lock);
115 if (!list_empty(&my_work->list)) {
116 printk("pdflush: bogus wakeup!\n");
117 my_work->fn = NULL;
118 continue;
119 }
120 if (my_work->fn == NULL) {
121 printk("pdflush: NULL work function\n");
122 continue;
123 }
124 spin_unlock_irq(&pdflush_lock);
125
126 (*my_work->fn)(my_work->arg0);
127
128 /*
129 * Thread creation: For how long have there been zero
130 * available threads?
131 */
132 if (jiffies - last_empty_jifs > 1 * HZ) {
133 /* unlocked list_empty() test is OK here */
134 if (list_empty(&pdflush_list)) {
135 /* unlocked test is OK here */
136 if (nr_pdflush_threads < MAX_PDFLUSH_THREADS)
137 start_one_pdflush_thread();
138 }
139 }
140
141 spin_lock_irq(&pdflush_lock);
142 my_work->fn = NULL;
143
144 /*
145 * Thread destruction: For how long has the sleepiest
146 * thread slept?
147 */
148 if (list_empty(&pdflush_list))
149 continue;
150 if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
151 continue;
152 pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
153 if (jiffies - pdf->when_i_went_to_sleep > 1 * HZ) {
154 /* Limit exit rate */
155 pdf->when_i_went_to_sleep = jiffies;
156 break; /* exeunt */
157 }
158 }
159 nr_pdflush_threads--;
160 spin_unlock_irq(&pdflush_lock);
161 return 0;
162}
163
164/*
165 * Of course, my_work wants to be just a local in __pdflush(). It is
166 * separated out in this manner to hopefully prevent the compiler from
167 * performing unfortunate optimisations against the auto variables. Because
168 * these are visible to other tasks and CPUs. (No problem has actually
169 * been observed. This is just paranoia).
170 */
171static int pdflush(void *dummy)
172{
173 struct pdflush_work my_work;
Paul Jackson28a42b92005-10-30 15:02:32 -0800174 cpumask_t cpus_allowed;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700175
176 /*
177 * pdflush can spend a lot of time doing encryption via dm-crypt. We
178 * don't want to do that at keventd's priority.
179 */
180 set_user_nice(current, 0);
Paul Jackson28a42b92005-10-30 15:02:32 -0800181
182 /*
183 * Some configs put our parent kthread in a limited cpuset,
184 * which kthread() overrides, forcing cpus_allowed == CPU_MASK_ALL.
185 * Our needs are more modest - cut back to our cpusets cpus_allowed.
186 * This is needed as pdflush's are dynamically created and destroyed.
187 * The boottime pdflush's are easily placed w/o these 2 lines.
188 */
189 cpus_allowed = cpuset_cpus_allowed(current);
190 set_cpus_allowed(current, cpus_allowed);
191
Linus Torvalds1da177e2005-04-16 15:20:36 -0700192 return __pdflush(&my_work);
193}
194
195/*
196 * Attempt to wake up a pdflush thread, and get it to do some work for you.
197 * Returns zero if it indeed managed to find a worker thread, and passed your
198 * payload to it.
199 */
200int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
201{
202 unsigned long flags;
203 int ret = 0;
204
Eric Sesterhenn125e1872006-06-23 02:06:06 -0700205 BUG_ON(fn == NULL); /* Hard to diagnose if it's deferred */
Linus Torvalds1da177e2005-04-16 15:20:36 -0700206
207 spin_lock_irqsave(&pdflush_lock, flags);
208 if (list_empty(&pdflush_list)) {
209 spin_unlock_irqrestore(&pdflush_lock, flags);
210 ret = -1;
211 } else {
212 struct pdflush_work *pdf;
213
214 pdf = list_entry(pdflush_list.next, struct pdflush_work, list);
215 list_del_init(&pdf->list);
216 if (list_empty(&pdflush_list))
217 last_empty_jifs = jiffies;
218 pdf->fn = fn;
219 pdf->arg0 = arg0;
220 wake_up_process(pdf->who);
221 spin_unlock_irqrestore(&pdflush_lock, flags);
222 }
223 return ret;
224}
225
226static void start_one_pdflush_thread(void)
227{
228 kthread_run(pdflush, NULL, "pdflush");
229}
230
231static int __init pdflush_init(void)
232{
233 int i;
234
235 for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
236 start_one_pdflush_thread();
237 return 0;
238}
239
240module_init(pdflush_init);