| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20121121020034.10225.51692.stgit@blackbox.djwong.org>
Date: Tue, 20 Nov 2012 18:00:34 -0800
From: "Darrick J. Wong" <darrick.wong@...cle.com>
To: axboe@...nel.dk, lucho@...kov.net, jack@...e.cz, ericvh@...il.com,
tytso@....edu, rminnich@...dia.gov, viro@...iv.linux.org.uk
Cc: martin.petersen@...cle.com, neilb@...e.de, david@...morbit.com,
linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
adilger.kernel@...ger.ca, bharrosh@...asas.com, jlayton@...ba.org,
v9fs-developer@...ts.sourceforge.net, linux-ext4@...r.kernel.org
Subject: [PATCH 1/4] bdi: Track users that require stable page writes
This creates a per-backing-device counter that tracks the number of users which
require pages to be held immutable during writeout. Eventually it will be used
to waive wait_for_page_writeback() if nobody requires stable pages.
Signed-off-by: Darrick J. Wong <darrick.wong@...cle.com>
---
Documentation/ABI/testing/sysfs-class-bdi | 7 ++++++
block/blk-integrity.c | 4 +++
include/linux/backing-dev.h | 16 +++++++++++++
include/linux/blkdev.h | 15 ++++++++++++
mm/backing-dev.c | 36 +++++++++++++++++++++++++++++
5 files changed, 78 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index 5f50097..218a618 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -48,3 +48,10 @@ max_ratio (read-write)
most of the write-back cache. For example in case of an NFS
mount that is prone to get stuck, or a FUSE mount which cannot
be trusted to play fair.
+
+stable_pages_required (read-write)
+
+ If set, the backing device requires that all pages comprising a write
+ request must not be changed until writeout is complete. The system
+ administrator can turn this on if the hardware does not do so already.
+ However, once enabled, this flag cannot be disabled.
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index da2a818..cf2dd95 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -420,6 +420,8 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
} else
bi->name = bi_unsupported_name;
+ queue_require_stable_pages(disk->queue);
+
return 0;
}
EXPORT_SYMBOL(blk_integrity_register);
@@ -438,6 +440,8 @@ void blk_integrity_unregister(struct gendisk *disk)
if (!disk || !disk->integrity)
return;
+ queue_unrequire_stable_pages(disk->queue);
+
bi = disk->integrity;
kobject_uevent(&bi->kobj, KOBJ_REMOVE);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 2a9a9ab..af19704 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -253,6 +253,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
#define BDI_CAP_EXEC_MAP 0x00000040
#define BDI_CAP_NO_ACCT_WB 0x00000080
#define BDI_CAP_SWAP_BACKED 0x00000100
+#define BDI_CAP_STABLE_WRITES 0x00000200
#define BDI_CAP_VMFLAGS \
(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
@@ -307,6 +308,21 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout);
int pdflush_proc_obsolete(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
+static inline void bdi_require_stable_pages(struct backing_dev_info *bdi)
+{
+ bdi->capabilities |= BDI_CAP_STABLE_WRITES;
+}
+
+static inline void bdi_unrequire_stable_pages(struct backing_dev_info *bdi)
+{
+ bdi->capabilities &= ~BDI_CAP_STABLE_WRITES;
+}
+
+static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
+{
+ return bdi->capabilities & BDI_CAP_STABLE_WRITES;
+}
+
static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
{
return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1756001..a1c6e91 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -458,6 +458,21 @@ struct request_queue {
(1 << QUEUE_FLAG_SAME_COMP) | \
(1 << QUEUE_FLAG_ADD_RANDOM))
+static inline void queue_require_stable_pages(struct request_queue *q)
+{
+ bdi_require_stable_pages(&q->backing_dev_info);
+}
+
+static inline void queue_unrequire_stable_pages(struct request_queue *q)
+{
+ bdi_unrequire_stable_pages(&q->backing_dev_info);
+}
+
+static inline int queue_requires_stable_pages(struct request_queue *q)
+{
+ return bdi_cap_stable_pages_required(&q->backing_dev_info);
+}
+
static inline void queue_lockdep_assert_held(struct request_queue *q)
{
if (q->queue_lock)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d3ca2b3..fd6e5b5 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -221,12 +221,48 @@ static ssize_t max_ratio_store(struct device *dev,
}
BDI_SHOW(max_ratio, bdi->max_ratio)
+static ssize_t stable_pages_required_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct backing_dev_info *bdi = dev_get_drvdata(dev);
+ unsigned int spw;
+ ssize_t ret;
+
+ ret = kstrtouint(buf, 10, &spw);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * SPW could be enabled due to hw requirement, so don't
+ * let users disable it.
+ */
+ if (bdi_cap_stable_pages_required(bdi) && spw == 0)
+ return -EINVAL;
+
+ if (spw != 0)
+ bdi_require_stable_pages(bdi);
+
+ return count;
+}
+
+static ssize_t stable_pages_required_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, "%d\n",
+ bdi_cap_stable_pages_required(bdi) ? 1 : 0);
+}
+
#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
static struct device_attribute bdi_dev_attrs[] = {
__ATTR_RW(read_ahead_kb),
__ATTR_RW(min_ratio),
__ATTR_RW(max_ratio),
+ __ATTR_RW(stable_pages_required),
__ATTR_NULL,
};
--
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