mm: bdi: export BDI attributes in sysfs

Provide a place in sysfs (/sys/class/bdi) for the backing_dev_info object.
This allows us to see and set the various BDI specific variables.

In particular this properly exposes the read-ahead window for all relevant
users and /sys/block/<block>/queue/read_ahead_kb should be deprecated.

With patient help from Kay Sievers and Greg KH

[mszeredi@suse.cz]

 - split off NFS and FUSE changes into separate patches
 - document new sysfs attributes under Documentation/ABI
 - do bdi_class_init as a core_initcall, otherwise the "default" BDI
   won't be initialized
 - remove bdi_init_fmt macro, it's not used very much

[akpm@linux-foundation.org: fix ia64 warning]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Acked-by: Greg KH <greg@kroah.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 127 insertions, 2 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index e8644b1e5527..847eabe4824c 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -4,12 +4,129 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <linux/writeback.h>
+#include <linux/device.h>
+
+
+static struct class *bdi_class;
+
+static ssize_t read_ahead_kb_store(struct device *dev,
+                                  struct device_attribute *attr,
+                                  const char *buf, size_t count)
+{
+        struct backing_dev_info *bdi = dev_get_drvdata(dev);
+        char *end;
+        unsigned long read_ahead_kb;
+        ssize_t ret = -EINVAL;
+
+        read_ahead_kb = simple_strtoul(buf, &end, 10);
+        if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
+                bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);
+                ret = count;
+        }
+        return ret;
+}
+
+#define K(pages) ((pages) << (PAGE_SHIFT - 10))
+
+#define BDI_SHOW(name, expr)                                            \
+static ssize_t name##_show(struct device *dev,                          \
+                           struct device_attribute *attr, char *page)   \
+{                                                                       \
+        struct backing_dev_info *bdi = dev_get_drvdata(dev);            \
+                                                                        \
+        return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr);  \
+}
+
+BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
+
+BDI_SHOW(reclaimable_kb, K(bdi_stat(bdi, BDI_RECLAIMABLE)))
+BDI_SHOW(writeback_kb, K(bdi_stat(bdi, BDI_WRITEBACK)))
+
+static inline unsigned long get_dirty(struct backing_dev_info *bdi, int i)
+{
+        unsigned long thresh[3];
+
+        get_dirty_limits(&thresh[0], &thresh[1], &thresh[2], bdi);
+
+        return thresh[i];
+}
+
+BDI_SHOW(dirty_kb, K(get_dirty(bdi, 1)))
+BDI_SHOW(bdi_dirty_kb, K(get_dirty(bdi, 2)))
+
+#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
+
+static struct device_attribute bdi_dev_attrs[] = {
+        __ATTR_RW(read_ahead_kb),
+        __ATTR_RO(reclaimable_kb),
+        __ATTR_RO(writeback_kb),
+        __ATTR_RO(dirty_kb),
+        __ATTR_RO(bdi_dirty_kb),
+        __ATTR_NULL,
+};
+
+static __init int bdi_class_init(void)
+{
+        bdi_class = class_create(THIS_MODULE, "bdi");
+        bdi_class->dev_attrs = bdi_dev_attrs;
+        return 0;
+}
+
+core_initcall(bdi_class_init);
+
+int bdi_register(struct backing_dev_info *bdi, struct device *parent,
+                const char *fmt, ...)
+{
+        char *name;
+        va_list args;
+        int ret = 0;
+        struct device *dev;
+
+        va_start(args, fmt);
+        name = kvasprintf(GFP_KERNEL, fmt, args);
+        va_end(args);
+
+        if (!name)
+                return -ENOMEM;
+
+        dev = device_create(bdi_class, parent, MKDEV(0, 0), name);
+        if (IS_ERR(dev)) {
+                ret = PTR_ERR(dev);
+                goto exit;
+        }
+
+        bdi->dev = dev;
+        dev_set_drvdata(bdi->dev, bdi);
+
+exit:
+        kfree(name);
+        return ret;
+}
+EXPORT_SYMBOL(bdi_register);
+
+int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
+{
+        return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev));
+}
+EXPORT_SYMBOL(bdi_register_dev);
+
+void bdi_unregister(struct backing_dev_info *bdi)
+{
+        if (bdi->dev) {
+                device_unregister(bdi->dev);
+                bdi->dev = NULL;
+        }
+}
+EXPORT_SYMBOL(bdi_unregister);
 
 int bdi_init(struct backing_dev_info *bdi)
 {
         int i;
         int err;
 
+        bdi->dev = NULL;
+
         for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
                 err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0);
                 if (err)
@@ -33,6 +150,8 @@ void bdi_destroy(struct backing_dev_info *bdi)
 {
         int i;
 
+        bdi_unregister(bdi);
+
         for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
                 percpu_counter_destroy(&bdi->bdi_stat[i]);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5e00f1772c20..e5b6b1190a95 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -300,7 +300,7 @@ static unsigned long determine_dirtyable_memory(void)
         return x + 1;   /* Ensure that we never return 0 */
 }
 
-static void
+void
 get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
                  struct backing_dev_info *bdi)
 {
diff --git a/mm/readahead.c b/mm/readahead.c
index 8762e8988972..d8723a5f6496 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -235,7 +235,13 @@ unsigned long max_sane_readahead(unsigned long nr)
 
 static int __init readahead_init(void)
 {
-        return bdi_init(&default_backing_dev_info);
+        int err;
+
+        err = bdi_init(&default_backing_dev_info);
+        if (!err)
+                bdi_register(&default_backing_dev_info, NULL, "default");
+
+        return err;
 }
 subsys_initcall(readahead_init);