The patch titled
mm: bdi: export BDI attributes in sysfs
has been added to the -mm tree. Its filename is
mm-bdi-export-bdi-attributes-in-sysfs.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mm: bdi: export BDI attributes in sysfs
From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
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@xxxxxxx]
- 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
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Kay Sievers <kay.sievers@xxxxxxxx>
Acked-by: Greg KH <greg@xxxxxxxxx>
Cc: Trond Myklebust <trond.myklebust@xxxxxxxxxx>
Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/ABI/testing/sysfs-class-bdi | 50 +++++++++
block/genhd.c | 3
include/linux/backing-dev.h | 8 +
include/linux/writeback.h | 3
lib/percpu_counter.c | 1
mm/backing-dev.c | 108 ++++++++++++++++++++
mm/page-writeback.c | 2
mm/readahead.c | 8 +
8 files changed, 181 insertions(+), 2 deletions(-)
diff -puN /dev/null Documentation/ABI/testing/sysfs-class-bdi
--- /dev/null
+++ a/Documentation/ABI/testing/sysfs-class-bdi
@@ -0,0 +1,50 @@
+What: /sys/class/bdi/<bdi>/
+Date: January 2008
+Contact: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
+Description:
+
+Provide a place in sysfs for the backing_dev_info object.
+This allows us to see and set the various BDI specific variables.
+
+The <bdi> identifyer can take the following forms:
+
+blk-NAME
+
+ Block devices, NAME is 'sda', 'loop0', etc...
+
+FSTYPE-MAJOR:MINOR
+
+ Non-block device backed filesystems which provide their own
+ BDI, such as NFS and FUSE. MAJOR:MINOR is the value of st_dev
+ for files on this filesystem.
+
+default
+
+ The default backing dev, used for non-block device backed
+ filesystems which do not provide their own BDI.
+
+Files under /sys/class/bdi/<bdi>/
+---------------------------------
+
+read_ahead_kb (read-write)
+
+ Size of the read-ahead window in kilobytes
+
+reclaimable_kb (read-only)
+
+ Reclaimable (dirty or unstable) memory destined for writeback
+ to this device
+
+writeback_kb (read-only)
+
+ Memory currently under writeback to this device
+
+dirty_kb (read-only)
+
+ Global threshold for reclaimable + writeback memory
+
+bdi_dirty_kb (read-only)
+
+ Current threshold on this BDI for reclaimable + writeback
+ memory
+
diff -puN block/genhd.c~mm-bdi-export-bdi-attributes-in-sysfs block/genhd.c
--- a/block/genhd.c~mm-bdi-export-bdi-attributes-in-sysfs
+++ a/block/genhd.c
@@ -183,6 +183,8 @@ void add_disk(struct gendisk *disk)
disk->minors, NULL, exact_match, exact_lock, disk);
register_disk(disk);
blk_register_queue(disk);
+ bdi_register(&disk->queue->backing_dev_info, NULL,
+ "blk-%s", disk->disk_name);
}
EXPORT_SYMBOL(add_disk);
@@ -191,6 +193,7 @@ EXPORT_SYMBOL(del_gendisk); /* in partit
void unlink_gendisk(struct gendisk *disk)
{
blk_unregister_queue(disk);
+ bdi_unregister(&disk->queue->backing_dev_info);
blk_unregister_region(MKDEV(disk->major, disk->first_minor),
disk->minors);
}
diff -puN include/linux/backing-dev.h~mm-bdi-export-bdi-attributes-in-sysfs include/linux/backing-dev.h
--- a/include/linux/backing-dev.h~mm-bdi-export-bdi-attributes-in-sysfs
+++ a/include/linux/backing-dev.h
@@ -11,6 +11,8 @@
#include <linux/percpu_counter.h>
#include <linux/log2.h>
#include <linux/proportions.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
#include <asm/atomic.h>
struct page;
@@ -48,11 +50,17 @@ struct backing_dev_info {
struct prop_local_percpu completions;
int dirty_exceeded;
+
+ struct device *dev;
};
int bdi_init(struct backing_dev_info *bdi);
void bdi_destroy(struct backing_dev_info *bdi);
+int bdi_register(struct backing_dev_info *bdi, struct device *parent,
+ const char *fmt, ...);
+void bdi_unregister(struct backing_dev_info *bdi);
+
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
{
diff -puN include/linux/writeback.h~mm-bdi-export-bdi-attributes-in-sysfs include/linux/writeback.h
--- a/include/linux/writeback.h~mm-bdi-export-bdi-attributes-in-sysfs
+++ a/include/linux/writeback.h
@@ -113,6 +113,9 @@ struct file;
int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *,
void __user *, size_t *, loff_t *);
+void get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
+ struct backing_dev_info *bdi);
+
void page_writeback_init(void);
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long nr_pages_dirtied);
diff -puN lib/percpu_counter.c~mm-bdi-export-bdi-attributes-in-sysfs lib/percpu_counter.c
--- a/lib/percpu_counter.c~mm-bdi-export-bdi-attributes-in-sysfs
+++ a/lib/percpu_counter.c
@@ -102,6 +102,7 @@ void percpu_counter_destroy(struct percp
return;
free_percpu(fbc->counters);
+ fbc->counters = NULL;
#ifdef CONFIG_HOTPLUG_CPU
mutex_lock(&percpu_counters_lock);
list_del(&fbc->list);
diff -puN mm/backing-dev.c~mm-bdi-export-bdi-attributes-in-sysfs mm/backing-dev.c
--- a/mm/backing-dev.c~mm-bdi-export-bdi-attributes-in-sysfs
+++ a/mm/backing-dev.c
@@ -4,12 +4,118 @@
#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;
+
+ bdi->ra_pages = simple_strtoul(buf, &end, 10) >> (PAGE_SHIFT - 10);
+
+ return end - buf;
+}
+
+#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);
+
+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 +139,8 @@ void bdi_destroy(struct backing_dev_info
{
int i;
+ bdi_unregister(bdi);
+
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
diff -puN mm/page-writeback.c~mm-bdi-export-bdi-attributes-in-sysfs mm/page-writeback.c
--- a/mm/page-writeback.c~mm-bdi-export-bdi-attributes-in-sysfs
+++ a/mm/page-writeback.c
@@ -300,7 +300,7 @@ static unsigned long determine_dirtyable
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 -puN mm/readahead.c~mm-bdi-export-bdi-attributes-in-sysfs mm/readahead.c
--- a/mm/readahead.c~mm-bdi-export-bdi-attributes-in-sysfs
+++ a/mm/readahead.c
@@ -235,7 +235,13 @@ unsigned long max_sane_readahead(unsigne
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);
_
Patches currently in -mm which might be from a.p.zijlstra@xxxxxxxxx are
origin.patch
lockdep-annotate-epoll.patch
slub-move-kmem_cache_node-determination-into-add_full-and-add_partial-slub-workaround-for-lockdep-confusion.patch
swapin-needs-gfp_mask-for-loop-on-tmpfs.patch
mm-page-writeback-highmem_is_dirtyable-option.patch
mm-page-writeback-highmem_is_dirtyable-option-fix.patch
skip-writing-data-pages-when-inode-is-under-i_sync.patch
fix-dirty-page-accounting-leak-with-ext3-data=journal.patch
kernel-add-mutex_lock_killable.patch
vfs-use-mutex_lock_killable-in-vfs_readdir.patch
memory-controller-add-documentation.patch
memory-controller-resource-counters-v7.patch
memory-controller-containers-setup-v7.patch
memory-controller-accounting-setup-v7.patch
memory-controller-memory-accounting-v7.patch
memory-controller-task-migration-v7.patch
memory-controller-add-per-container-lru-and-reclaim-v7.patch
memory-controller-improve-user-interface.patch
memory-controller-oom-handling-v7.patch
memory-controller-add-switch-to-control-what-type-of-pages-to-limit-v7.patch
memory-controller-make-page_referenced-container-aware-v7.patch
memory-controller-make-charging-gfp-mask-aware.patch
memcgroup-reinstate-swapoff-mod.patch
bugfix-for-memory-cgroup-controller-charge-refcnt-race-fix.patch
bugfix-for-memory-cgroup-controller-fix-error-handling-path-in-mem_charge_cgroup.patch
bugfix-for-memory-controller-add-helper-function-for-assigning-cgroup-to-page.patch
bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages-fix.patch
memcgroup-fix-zone-isolation-oom.patch
memcgroup-revert-swap_state-mods.patch
memory-cgroup-enhancements-fix-zone-handling-in-try_to_free_mem_cgroup_page.patch
memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-cgroup.patch
memory-cgroup-enhancements-remember-a-page-is-charged-as-page-cache.patch
memory-cgroup-enhancements-remember-a-page-is-on-active-list-of-cgroup-or-not.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup.patch
memory-cgroup-enhancements-add-memorystat-file.patch
memory-cgroup-enhancements-add-pre_destroy-handler.patch
memory-cgroup-enhancements-implicit-force_empty-at-rmdir.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-add-scan_global_lru-macro.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-nid-zid-helper-function-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-active-inactive-counter.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-mapper_ratio-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-active-inactive-imbalance-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-remember-reclaim-priority-in-memory-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-the-number-of-pages-to-be-scanned-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-modifies-vmscanc-for-isolate-globa-cgroup-lru-activity.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lru-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lock-for-cgroup.patch
mm-bdi-export-bdi-attributes-in-sysfs.patch
mm-bdi-expose-the-bdi-object-in-sysfs-for-nfs.patch
mm-bdi-expose-the-bdi-object-in-sysfs-for-fuse.patch
mm-bdi-allow-setting-a-minimum-for-the-bdi-dirty-limit.patch
mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
