fscache: convert object to use workqueue instead of slow-work

Make fscache object state transition callbacks use workqueue instead
of slow-work.  New dedicated unbound CPU workqueue fscache_object_wq
is created.  get/put callbacks are renamed and modified to take
@object and called directly from the enqueue wrapper and the work
function.  While at it, make all open coded instances of get/put to
use fscache_get/put_object().

* Unbound workqueue is used.

* work_busy() output is printed instead of slow-work flags in object
  debugging outputs.  They mean basically the same thing bit-for-bit.

* sysctl fscache.object_max_active added to control concurrency.  The
  default value is nr_cpus clamped between 4 and
  WQ_UNBOUND_MAX_ACTIVE.

* slow_work_sleep_till_thread_needed() is replaced with fscache
  private implementation fscache_object_sleep_till_congested() which
  waits on fscache_object_wq congestion.

* debugfs support is dropped for now.  Tracing API based debug
  facility is planned to be added.

Signed-off-by: Tejun Heo <[email protected]>
Acked-by: David Howells <[email protected]>

Documentation/filesystems/caching/fscache.txt

@@ -343,8 +343,8 @@ This will look something like:
 	[root@andromeda ~]# head /proc/fs/fscache/objects
 	OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA       OBJECT_KEY, AUX_DATA
 	======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================
-	   17e4b        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
-	   1693a        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
+	   17e4b        2 ACTV     0   0   0   0  0     0 7b  4 0 0 | NFS.fh           DT  0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
+	   1693a        2 ACTV     0   0   0   0  0     0 7b  4 0 0 | NFS.fh           DT  0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
 
 where the first set of columns before the '|' describe the object:
 
@@ -362,7 +362,7 @@ where the first set of columns before the '|' describe the object:
 	EM	Object's event mask
 	EV	Events raised on this object
 	F	Object flags
-	S	Object slow-work work item flags
+	S	Object work item busy state mask (1:pending 2:running)
 
 and the second set of columns describe the object's cookie, if present:
 
@@ -395,8 +395,8 @@ and the following paired letters:
 	w	Show objects that don't have pending writes
 	R	Show objects that have outstanding reads
 	r	Show objects that don't have outstanding reads
-	S	Show objects that have slow work queued
-	s	Show objects that don't have slow work queued
+	S	Show objects that have work queued
+	s	Show objects that don't have work queued
 
 If neither side of a letter pair is given, then both are implied.  For example:
 

fs/cachefiles/namei.c

@@ -37,9 +37,9 @@ void __cachefiles_printk_object(struct cachefiles_object *object,
 
 	printk(KERN_ERR "%sobject: OBJ%x\n",
 	       prefix, object->fscache.debug_id);
-	printk(KERN_ERR "%sobjstate=%s fl=%lx swfl=%lx ev=%lx[%lx]\n",
+	printk(KERN_ERR "%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n",
 	       prefix, fscache_object_states[object->fscache.state],
-	       object->fscache.flags, object->fscache.work.flags,
+	       object->fscache.flags, work_busy(&object->fscache.work),
 	       object->fscache.events,
 	       object->fscache.event_mask & FSCACHE_OBJECT_EVENTS_MASK);
 	printk(KERN_ERR "%sops=%u inp=%u exc=%u\n",
@@ -212,25 +212,24 @@ static int cachefiles_mark_object_active(struct cachefiles_cache *cache,
 
 		/* if the object we're waiting for is queued for processing,
 		 * then just put ourselves on the queue behind it */
-		if (slow_work_is_queued(&xobject->fscache.work)) {
+		if (work_pending(&xobject->fscache.work)) {
 			_debug("queue OBJ%x behind OBJ%x immediately",
 			       object->fscache.debug_id,
 			       xobject->fscache.debug_id);
 			goto requeue;
 		}
 
 		/* otherwise we sleep until either the object we're waiting for
-		 * is done, or the slow-work facility wants the thread back to
-		 * do other work */
+		 * is done, or the fscache_object is congested */
 		wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE);
 		init_wait(&wait);
 		requeue = false;
 		do {
 			prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
 			if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags))
 				break;
-			requeue = slow_work_sleep_till_thread_needed(
-				&object->fscache.work, &timeout);
+
+			requeue = fscache_object_sleep_till_congested(&timeout);
 		} while (timeout > 0 && !requeue);
 		finish_wait(wq, &wait);
 

fs/fscache/internal.h

@@ -82,6 +82,13 @@ extern unsigned fscache_defer_lookup;
 extern unsigned fscache_defer_create;
 extern unsigned fscache_debug;
 extern struct kobject *fscache_root;
+extern struct workqueue_struct *fscache_object_wq;
+DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait);
+
+static inline bool fscache_object_congested(void)
+{
+	return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq);
+}
 
 extern int fscache_wait_bit(void *);
 extern int fscache_wait_bit_interruptible(void *);

fs/fscache/main.c

@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/completion.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include "internal.h"
 
 MODULE_DESCRIPTION("FS Cache Manager");
@@ -40,22 +41,89 @@ MODULE_PARM_DESC(fscache_debug,
 		 "FS-Cache debugging mask");
 
 struct kobject *fscache_root;
+struct workqueue_struct *fscache_object_wq;
+
+DEFINE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait);
+
+/* these values serve as lower bounds, will be adjusted in fscache_init() */
+static unsigned fscache_object_max_active = 4;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table_header *fscache_sysctl_header;
+
+static int fscache_max_active_sysctl(struct ctl_table *table, int write,
+				     void __user *buffer,
+				     size_t *lenp, loff_t *ppos)
+{
+	struct workqueue_struct **wqp = table->extra1;
+	unsigned int *datap = table->data;
+	int ret;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (ret == 0)
+		workqueue_set_max_active(*wqp, *datap);
+	return ret;
+}
+
+ctl_table fscache_sysctls[] = {
+	{
+		.procname	= "object_max_active",
+		.data		= &fscache_object_max_active,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= fscache_max_active_sysctl,
+		.extra1		= &fscache_object_wq,
+	},
+	{}
+};
+
+ctl_table fscache_sysctls_root[] = {
+	{
+		.procname	= "fscache",
+		.mode		= 0555,
+		.child		= fscache_sysctls,
+	},
+	{}
+};
+#endif
 
 /*
  * initialise the fs caching module
  */
 static int __init fscache_init(void)
 {
+	unsigned int nr_cpus = num_possible_cpus();
+	unsigned int cpu;
 	int ret;
 
 	ret = slow_work_register_user(THIS_MODULE);
 	if (ret < 0)
 		goto error_slow_work;
 
+	fscache_object_max_active =
+		clamp_val(nr_cpus,
+			  fscache_object_max_active, WQ_UNBOUND_MAX_ACTIVE);
+
+	ret = -ENOMEM;
+	fscache_object_wq = alloc_workqueue("fscache_object", WQ_UNBOUND,
+					    fscache_object_max_active);
+	if (!fscache_object_wq)
+		goto error_object_wq;
+
+	for_each_possible_cpu(cpu)
+		init_waitqueue_head(&per_cpu(fscache_object_cong_wait, cpu));
+
 	ret = fscache_proc_init();
 	if (ret < 0)
 		goto error_proc;
 
+#ifdef CONFIG_SYSCTL
+	ret = -ENOMEM;
+	fscache_sysctl_header = register_sysctl_table(fscache_sysctls_root);
+	if (!fscache_sysctl_header)
+		goto error_sysctl;
+#endif
+
 	fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar",
 					       sizeof(struct fscache_cookie),
 					       0,
@@ -78,8 +146,14 @@ static int __init fscache_init(void)
 error_kobj:
 	kmem_cache_destroy(fscache_cookie_jar);
 error_cookie_jar:
+#ifdef CONFIG_SYSCTL
+	unregister_sysctl_table(fscache_sysctl_header);
+error_sysctl:
+#endif
 	fscache_proc_cleanup();
 error_proc:
+	destroy_workqueue(fscache_object_wq);
+error_object_wq:
 	slow_work_unregister_user(THIS_MODULE);
 error_slow_work:
 	return ret;
@@ -96,7 +170,9 @@ static void __exit fscache_exit(void)
 
 	kobject_put(fscache_root);
 	kmem_cache_destroy(fscache_cookie_jar);
+	unregister_sysctl_table(fscache_sysctl_header);
 	fscache_proc_cleanup();
+	destroy_workqueue(fscache_object_wq);
 	slow_work_unregister_user(THIS_MODULE);
 	printk(KERN_NOTICE "FS-Cache: Unloaded\n");
 }

fs/fscache/object-list.c

@@ -34,8 +34,8 @@ struct fscache_objlist_data {
 #define FSCACHE_OBJLIST_CONFIG_NOREADS	0x00000200	/* show objects without active reads */
 #define FSCACHE_OBJLIST_CONFIG_EVENTS	0x00000400	/* show objects with events */
 #define FSCACHE_OBJLIST_CONFIG_NOEVENTS	0x00000800	/* show objects without no events */
-#define FSCACHE_OBJLIST_CONFIG_WORK	0x00001000	/* show objects with slow work */
-#define FSCACHE_OBJLIST_CONFIG_NOWORK	0x00002000	/* show objects without slow work */
+#define FSCACHE_OBJLIST_CONFIG_WORK	0x00001000	/* show objects with work */
+#define FSCACHE_OBJLIST_CONFIG_NOWORK	0x00002000	/* show objects without work */
 
 	u8		buf[512];	/* key and aux data buffer */
 };
@@ -231,12 +231,11 @@ static int fscache_objlist_show(struct seq_file *m, void *v)
 		       READS, NOREADS);
 		FILTER(obj->events & obj->event_mask,
 		       EVENTS, NOEVENTS);
-		FILTER(obj->work.flags & ~(1UL << SLOW_WORK_VERY_SLOW),
-		       WORK, NOWORK);
+		FILTER(work_busy(&obj->work), WORK, NOWORK);
 	}
 
 	seq_printf(m,
-		   "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %1lx %1lx | ",
+		   "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %1lx %1x | ",
 		   obj->debug_id,
 		   obj->parent ? obj->parent->debug_id : -1,
 		   fscache_object_states_short[obj->state],
@@ -249,7 +248,7 @@ static int fscache_objlist_show(struct seq_file *m, void *v)
 		   obj->event_mask & FSCACHE_OBJECT_EVENTS_MASK,
 		   obj->events,
 		   obj->flags,
-		   obj->work.flags);
+		   work_busy(&obj->work));
 
 	no_cookie = true;
 	keylen = auxlen = 0;