Merge branches 'vfsmount-guts', 'umode_t' and 'partitions' into Z
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ba42719..1c16141 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -25,7 +25,6 @@
#include <linux/bio.h>
#include <linux/blkdev.h>
-#include <linux/buffer_head.h>
#include <linux/device.h>
#include <linux/errno.h>
#include <linux/fs.h>
diff --git a/block/Kconfig b/block/Kconfig
index e97934e..09acf1b 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -99,6 +99,12 @@
See Documentation/cgroups/blkio-controller.txt for more information.
+menu "Partition Types"
+
+source "block/partitions/Kconfig"
+
+endmenu
+
endif # BLOCK
config BLOCK_COMPAT
diff --git a/block/Makefile b/block/Makefile
index 514c6e4..39b76ba 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,8 @@
obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
- blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o
+ blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o \
+ partition-generic.o partitions/
obj-$(CONFIG_BLK_DEV_BSG) += bsg.o
obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o
diff --git a/block/genhd.c b/block/genhd.c
index 80578f3..83e7c04 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -15,7 +15,6 @@
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/kobj_map.h>
-#include <linux/buffer_head.h>
#include <linux/mutex.h>
#include <linux/idr.h>
#include <linux/log2.h>
@@ -507,7 +506,7 @@
return 0;
}
-void register_disk(struct gendisk *disk)
+static void register_disk(struct gendisk *disk)
{
struct device *ddev = disk_to_dev(disk);
struct block_device *bdev;
diff --git a/block/ioctl.c b/block/ioctl.c
index ca939fc..91e7b19c 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -5,7 +5,7 @@
#include <linux/blkpg.h>
#include <linux/hdreg.h>
#include <linux/backing-dev.h>
-#include <linux/buffer_head.h>
+#include <linux/fs.h>
#include <linux/blktrace_api.h>
#include <asm/uaccess.h>
diff --git a/fs/partitions/check.c b/block/partition-generic.c
similarity index 79%
rename from fs/partitions/check.c
rename to block/partition-generic.c
index e3c63d1..d06ec1c 100644
--- a/fs/partitions/check.c
+++ b/block/partition-generic.c
@@ -1,6 +1,4 @@
/*
- * fs/partitions/check.c
- *
* Code extracted from drivers/block/genhd.c
* Copyright (C) 1991-1998 Linus Torvalds
* Re-organised Feb 1998 Russell King
@@ -9,8 +7,6 @@
* block drivers, which allows all the partition code to
* be grouped in one location, and it to be mostly self
* contained.
- *
- * Added needed MAJORS for new pairs, {hdi,hdj}, {hdk,hdl}
*/
#include <linux/init.h>
@@ -22,98 +18,11 @@
#include <linux/genhd.h>
#include <linux/blktrace_api.h>
-#include "check.h"
-
-#include "acorn.h"
-#include "amiga.h"
-#include "atari.h"
-#include "ldm.h"
-#include "mac.h"
-#include "msdos.h"
-#include "osf.h"
-#include "sgi.h"
-#include "sun.h"
-#include "ibm.h"
-#include "ultrix.h"
-#include "efi.h"
-#include "karma.h"
-#include "sysv68.h"
+#include "partitions/check.h"
#ifdef CONFIG_BLK_DEV_MD
extern void md_autodetect_dev(dev_t dev);
#endif
-
-int warn_no_part = 1; /*This is ugly: should make genhd removable media aware*/
-
-static int (*check_part[])(struct parsed_partitions *) = {
- /*
- * Probe partition formats with tables at disk address 0
- * that also have an ADFS boot block at 0xdc0.
- */
-#ifdef CONFIG_ACORN_PARTITION_ICS
- adfspart_check_ICS,
-#endif
-#ifdef CONFIG_ACORN_PARTITION_POWERTEC
- adfspart_check_POWERTEC,
-#endif
-#ifdef CONFIG_ACORN_PARTITION_EESOX
- adfspart_check_EESOX,
-#endif
-
- /*
- * Now move on to formats that only have partition info at
- * disk address 0xdc0. Since these may also have stale
- * PC/BIOS partition tables, they need to come before
- * the msdos entry.
- */
-#ifdef CONFIG_ACORN_PARTITION_CUMANA
- adfspart_check_CUMANA,
-#endif
-#ifdef CONFIG_ACORN_PARTITION_ADFS
- adfspart_check_ADFS,
-#endif
-
-#ifdef CONFIG_EFI_PARTITION
- efi_partition, /* this must come before msdos */
-#endif
-#ifdef CONFIG_SGI_PARTITION
- sgi_partition,
-#endif
-#ifdef CONFIG_LDM_PARTITION
- ldm_partition, /* this must come before msdos */
-#endif
-#ifdef CONFIG_MSDOS_PARTITION
- msdos_partition,
-#endif
-#ifdef CONFIG_OSF_PARTITION
- osf_partition,
-#endif
-#ifdef CONFIG_SUN_PARTITION
- sun_partition,
-#endif
-#ifdef CONFIG_AMIGA_PARTITION
- amiga_partition,
-#endif
-#ifdef CONFIG_ATARI_PARTITION
- atari_partition,
-#endif
-#ifdef CONFIG_MAC_PARTITION
- mac_partition,
-#endif
-#ifdef CONFIG_ULTRIX_PARTITION
- ultrix_partition,
-#endif
-#ifdef CONFIG_IBM_PARTITION
- ibm_partition,
-#endif
-#ifdef CONFIG_KARMA_PARTITION
- karma_partition,
-#endif
-#ifdef CONFIG_SYSV68_PARTITION
- sysv68_partition,
-#endif
- NULL
-};
/*
* disk_name() is used by partition check code and the genhd driver.
@@ -155,65 +64,6 @@
EXPORT_SYMBOL(__bdevname);
-static struct parsed_partitions *
-check_partition(struct gendisk *hd, struct block_device *bdev)
-{
- struct parsed_partitions *state;
- int i, res, err;
-
- state = kzalloc(sizeof(struct parsed_partitions), GFP_KERNEL);
- if (!state)
- return NULL;
- state->pp_buf = (char *)__get_free_page(GFP_KERNEL);
- if (!state->pp_buf) {
- kfree(state);
- return NULL;
- }
- state->pp_buf[0] = '\0';
-
- state->bdev = bdev;
- disk_name(hd, 0, state->name);
- snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name);
- if (isdigit(state->name[strlen(state->name)-1]))
- sprintf(state->name, "p");
-
- state->limit = disk_max_parts(hd);
- i = res = err = 0;
- while (!res && check_part[i]) {
- memset(&state->parts, 0, sizeof(state->parts));
- res = check_part[i++](state);
- if (res < 0) {
- /* We have hit an I/O error which we don't report now.
- * But record it, and let the others do their job.
- */
- err = res;
- res = 0;
- }
-
- }
- if (res > 0) {
- printk(KERN_INFO "%s", state->pp_buf);
-
- free_page((unsigned long)state->pp_buf);
- return state;
- }
- if (state->access_beyond_eod)
- err = -ENOSPC;
- if (err)
- /* The partition is unrecognized. So report I/O errors if there were any */
- res = err;
- if (!res)
- strlcat(state->pp_buf, " unknown partition table\n", PAGE_SIZE);
- else if (warn_no_part)
- strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE);
-
- printk(KERN_INFO "%s", state->pp_buf);
-
- free_page((unsigned long)state->pp_buf);
- kfree(state);
- return ERR_PTR(res);
-}
-
static ssize_t part_partition_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
diff --git a/fs/partitions/Kconfig b/block/partitions/Kconfig
similarity index 100%
rename from fs/partitions/Kconfig
rename to block/partitions/Kconfig
diff --git a/fs/partitions/Makefile b/block/partitions/Makefile
similarity index 100%
rename from fs/partitions/Makefile
rename to block/partitions/Makefile
diff --git a/fs/partitions/acorn.c b/block/partitions/acorn.c
similarity index 100%
rename from fs/partitions/acorn.c
rename to block/partitions/acorn.c
diff --git a/fs/partitions/acorn.h b/block/partitions/acorn.h
similarity index 100%
rename from fs/partitions/acorn.h
rename to block/partitions/acorn.h
diff --git a/fs/partitions/amiga.c b/block/partitions/amiga.c
similarity index 100%
rename from fs/partitions/amiga.c
rename to block/partitions/amiga.c
diff --git a/fs/partitions/amiga.h b/block/partitions/amiga.h
similarity index 100%
rename from fs/partitions/amiga.h
rename to block/partitions/amiga.h
diff --git a/fs/partitions/atari.c b/block/partitions/atari.c
similarity index 100%
rename from fs/partitions/atari.c
rename to block/partitions/atari.c
diff --git a/fs/partitions/atari.h b/block/partitions/atari.h
similarity index 100%
rename from fs/partitions/atari.h
rename to block/partitions/atari.h
diff --git a/block/partitions/check.c b/block/partitions/check.c
new file mode 100644
index 0000000..bc90867
--- /dev/null
+++ b/block/partitions/check.c
@@ -0,0 +1,166 @@
+/*
+ * fs/partitions/check.c
+ *
+ * Code extracted from drivers/block/genhd.c
+ * Copyright (C) 1991-1998 Linus Torvalds
+ * Re-organised Feb 1998 Russell King
+ *
+ * We now have independent partition support from the
+ * block drivers, which allows all the partition code to
+ * be grouped in one location, and it to be mostly self
+ * contained.
+ *
+ * Added needed MAJORS for new pairs, {hdi,hdj}, {hdk,hdl}
+ */
+
+#include <linux/slab.h>
+#include <linux/ctype.h>
+#include <linux/genhd.h>
+
+#include "check.h"
+
+#include "acorn.h"
+#include "amiga.h"
+#include "atari.h"
+#include "ldm.h"
+#include "mac.h"
+#include "msdos.h"
+#include "osf.h"
+#include "sgi.h"
+#include "sun.h"
+#include "ibm.h"
+#include "ultrix.h"
+#include "efi.h"
+#include "karma.h"
+#include "sysv68.h"
+
+int warn_no_part = 1; /*This is ugly: should make genhd removable media aware*/
+
+static int (*check_part[])(struct parsed_partitions *) = {
+ /*
+ * Probe partition formats with tables at disk address 0
+ * that also have an ADFS boot block at 0xdc0.
+ */
+#ifdef CONFIG_ACORN_PARTITION_ICS
+ adfspart_check_ICS,
+#endif
+#ifdef CONFIG_ACORN_PARTITION_POWERTEC
+ adfspart_check_POWERTEC,
+#endif
+#ifdef CONFIG_ACORN_PARTITION_EESOX
+ adfspart_check_EESOX,
+#endif
+
+ /*
+ * Now move on to formats that only have partition info at
+ * disk address 0xdc0. Since these may also have stale
+ * PC/BIOS partition tables, they need to come before
+ * the msdos entry.
+ */
+#ifdef CONFIG_ACORN_PARTITION_CUMANA
+ adfspart_check_CUMANA,
+#endif
+#ifdef CONFIG_ACORN_PARTITION_ADFS
+ adfspart_check_ADFS,
+#endif
+
+#ifdef CONFIG_EFI_PARTITION
+ efi_partition, /* this must come before msdos */
+#endif
+#ifdef CONFIG_SGI_PARTITION
+ sgi_partition,
+#endif
+#ifdef CONFIG_LDM_PARTITION
+ ldm_partition, /* this must come before msdos */
+#endif
+#ifdef CONFIG_MSDOS_PARTITION
+ msdos_partition,
+#endif
+#ifdef CONFIG_OSF_PARTITION
+ osf_partition,
+#endif
+#ifdef CONFIG_SUN_PARTITION
+ sun_partition,
+#endif
+#ifdef CONFIG_AMIGA_PARTITION
+ amiga_partition,
+#endif
+#ifdef CONFIG_ATARI_PARTITION
+ atari_partition,
+#endif
+#ifdef CONFIG_MAC_PARTITION
+ mac_partition,
+#endif
+#ifdef CONFIG_ULTRIX_PARTITION
+ ultrix_partition,
+#endif
+#ifdef CONFIG_IBM_PARTITION
+ ibm_partition,
+#endif
+#ifdef CONFIG_KARMA_PARTITION
+ karma_partition,
+#endif
+#ifdef CONFIG_SYSV68_PARTITION
+ sysv68_partition,
+#endif
+ NULL
+};
+
+struct parsed_partitions *
+check_partition(struct gendisk *hd, struct block_device *bdev)
+{
+ struct parsed_partitions *state;
+ int i, res, err;
+
+ state = kzalloc(sizeof(struct parsed_partitions), GFP_KERNEL);
+ if (!state)
+ return NULL;
+ state->pp_buf = (char *)__get_free_page(GFP_KERNEL);
+ if (!state->pp_buf) {
+ kfree(state);
+ return NULL;
+ }
+ state->pp_buf[0] = '\0';
+
+ state->bdev = bdev;
+ disk_name(hd, 0, state->name);
+ snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name);
+ if (isdigit(state->name[strlen(state->name)-1]))
+ sprintf(state->name, "p");
+
+ state->limit = disk_max_parts(hd);
+ i = res = err = 0;
+ while (!res && check_part[i]) {
+ memset(&state->parts, 0, sizeof(state->parts));
+ res = check_part[i++](state);
+ if (res < 0) {
+ /* We have hit an I/O error which we don't report now.
+ * But record it, and let the others do their job.
+ */
+ err = res;
+ res = 0;
+ }
+
+ }
+ if (res > 0) {
+ printk(KERN_INFO "%s", state->pp_buf);
+
+ free_page((unsigned long)state->pp_buf);
+ return state;
+ }
+ if (state->access_beyond_eod)
+ err = -ENOSPC;
+ if (err)
+ /* The partition is unrecognized. So report I/O errors if there were any */
+ res = err;
+ if (!res)
+ strlcat(state->pp_buf, " unknown partition table\n", PAGE_SIZE);
+ else if (warn_no_part)
+ strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE);
+
+ printk(KERN_INFO "%s", state->pp_buf);
+
+ free_page((unsigned long)state->pp_buf);
+ kfree(state);
+ return ERR_PTR(res);
+}
diff --git a/fs/partitions/check.h b/block/partitions/check.h
similarity index 92%
rename from fs/partitions/check.h
rename to block/partitions/check.h
index d68bf4d..52b1003 100644
--- a/fs/partitions/check.h
+++ b/block/partitions/check.h
@@ -22,6 +22,9 @@
char *pp_buf;
};
+struct parsed_partitions *
+check_partition(struct gendisk *, struct block_device *);
+
static inline void *read_part_sector(struct parsed_partitions *state,
sector_t n, Sector *p)
{
diff --git a/fs/partitions/efi.c b/block/partitions/efi.c
similarity index 100%
rename from fs/partitions/efi.c
rename to block/partitions/efi.c
diff --git a/fs/partitions/efi.h b/block/partitions/efi.h
similarity index 100%
rename from fs/partitions/efi.h
rename to block/partitions/efi.h
diff --git a/fs/partitions/ibm.c b/block/partitions/ibm.c
similarity index 100%
rename from fs/partitions/ibm.c
rename to block/partitions/ibm.c
diff --git a/fs/partitions/ibm.h b/block/partitions/ibm.h
similarity index 100%
rename from fs/partitions/ibm.h
rename to block/partitions/ibm.h
diff --git a/fs/partitions/karma.c b/block/partitions/karma.c
similarity index 100%
rename from fs/partitions/karma.c
rename to block/partitions/karma.c
diff --git a/fs/partitions/karma.h b/block/partitions/karma.h
similarity index 100%
rename from fs/partitions/karma.h
rename to block/partitions/karma.h
diff --git a/fs/partitions/ldm.c b/block/partitions/ldm.c
similarity index 100%
rename from fs/partitions/ldm.c
rename to block/partitions/ldm.c
diff --git a/fs/partitions/ldm.h b/block/partitions/ldm.h
similarity index 100%
rename from fs/partitions/ldm.h
rename to block/partitions/ldm.h
diff --git a/fs/partitions/mac.c b/block/partitions/mac.c
similarity index 100%
rename from fs/partitions/mac.c
rename to block/partitions/mac.c
diff --git a/fs/partitions/mac.h b/block/partitions/mac.h
similarity index 100%
rename from fs/partitions/mac.h
rename to block/partitions/mac.h
diff --git a/fs/partitions/msdos.c b/block/partitions/msdos.c
similarity index 100%
rename from fs/partitions/msdos.c
rename to block/partitions/msdos.c
diff --git a/fs/partitions/msdos.h b/block/partitions/msdos.h
similarity index 100%
rename from fs/partitions/msdos.h
rename to block/partitions/msdos.h
diff --git a/fs/partitions/osf.c b/block/partitions/osf.c
similarity index 100%
rename from fs/partitions/osf.c
rename to block/partitions/osf.c
diff --git a/fs/partitions/osf.h b/block/partitions/osf.h
similarity index 100%
rename from fs/partitions/osf.h
rename to block/partitions/osf.h
diff --git a/fs/partitions/sgi.c b/block/partitions/sgi.c
similarity index 100%
rename from fs/partitions/sgi.c
rename to block/partitions/sgi.c
diff --git a/fs/partitions/sgi.h b/block/partitions/sgi.h
similarity index 100%
rename from fs/partitions/sgi.h
rename to block/partitions/sgi.h
diff --git a/fs/partitions/sun.c b/block/partitions/sun.c
similarity index 100%
rename from fs/partitions/sun.c
rename to block/partitions/sun.c
diff --git a/fs/partitions/sun.h b/block/partitions/sun.h
similarity index 100%
rename from fs/partitions/sun.h
rename to block/partitions/sun.h
diff --git a/fs/partitions/sysv68.c b/block/partitions/sysv68.c
similarity index 100%
rename from fs/partitions/sysv68.c
rename to block/partitions/sysv68.c
diff --git a/fs/partitions/sysv68.h b/block/partitions/sysv68.h
similarity index 100%
rename from fs/partitions/sysv68.h
rename to block/partitions/sysv68.h
diff --git a/fs/partitions/ultrix.c b/block/partitions/ultrix.c
similarity index 100%
rename from fs/partitions/ultrix.c
rename to block/partitions/ultrix.c
diff --git a/fs/partitions/ultrix.h b/block/partitions/ultrix.h
similarity index 100%
rename from fs/partitions/ultrix.h
rename to block/partitions/ultrix.h
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 8eba86b..386146d 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -63,7 +63,7 @@
#include <linux/mutex.h>
#include <linux/amifdreg.h>
#include <linux/amifd.h>
-#include <linux/buffer_head.h>
+#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/interrupt.h>
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index d22119d..ec24643 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -17,7 +17,7 @@
#include <linux/highmem.h>
#include <linux/mutex.h>
#include <linux/radix-tree.h>
-#include <linux/buffer_head.h> /* invalidate_bh_lrus() */
+#include <linux/fs.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
@@ -402,14 +402,13 @@
error = -EBUSY;
if (bdev->bd_openers <= 1) {
/*
- * Invalidate the cache first, so it isn't written
- * back to the device.
+ * Kill the cache first, so it isn't written back to the
+ * device.
*
* Another thread might instantiate more buffercache here,
* but there is not much we can do to close that race.
*/
- invalidate_bh_lrus();
- truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
+ kill_bdev(bdev);
brd_free_pages(brd);
error = 0;
}
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 9955a53..510fb10 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -188,7 +188,6 @@
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/mod_devicetable.h>
-#include <linux/buffer_head.h> /* for invalidate_buffers() */
#include <linux/mutex.h>
#include <linux/io.h>
#include <linux/uaccess.h>
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1e888c9..f002577 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -69,7 +69,6 @@
#include <linux/freezer.h>
#include <linux/mutex.h>
#include <linux/writeback.h>
-#include <linux/buffer_head.h> /* for invalidate_bdev() */
#include <linux/completion.h>
#include <linux/highmem.h>
#include <linux/kthread.h>
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index f997c27..2118211 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -267,7 +267,6 @@
#include <linux/module.h>
#include <linux/fs.h>
-#include <linux/buffer_head.h>
#include <linux/major.h>
#include <linux/types.h>
#include <linux/errno.h>
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4720f68..b89c548 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -14,7 +14,6 @@
#include <linux/moduleparam.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
-#include <linux/buffer_head.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/idr.h>
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f47f1f8..5d1b676 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -36,8 +36,7 @@
#include <linux/blkdev.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
-#include <linux/mutex.h>
-#include <linux/buffer_head.h> /* for invalidate_bdev */
+#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/ctype.h>
#include <linux/string.h>
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index b78f231..ebeabc7 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -14,7 +14,6 @@
#include <linux/list.h>
#include <linux/init.h>
#include <linux/mtd/mtd.h>
-#include <linux/buffer_head.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/slab.h>
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 42986d7..eef27a1 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -17,7 +17,6 @@
#include <linux/ctype.h>
#include <linux/major.h>
#include <linux/slab.h>
-#include <linux/buffer_head.h>
#include <linux/hdreg.h>
#include <linux/async.h>
#include <linux/mutex.h>
diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c
index 6803b1e..92d24d6 100644
--- a/drivers/scsi/scsicam.c
+++ b/drivers/scsi/scsicam.c
@@ -16,7 +16,6 @@
#include <linux/genhd.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
-#include <linux/buffer_head.h>
#include <asm/unaligned.h>
#include <scsi/scsicam.h>
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 43db715..7867b7c 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -32,7 +32,6 @@
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/writeback.h>
-#include <linux/buffer_head.h> /* for fsync_bdev() */
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/vt_kern.h>
@@ -41,6 +40,7 @@
#include <linux/oom.h>
#include <linux/slab.h>
#include <linux/input.h>
+#include <linux/uaccess.h>
#include <asm/ptrace.h>
#include <asm/irq_regs.h>
diff --git a/fs/Kconfig b/fs/Kconfig
index 5f4c45d..30145d8 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -266,14 +266,6 @@
endif # NETWORK_FILESYSTEMS
-if BLOCK
-menu "Partition Types"
-
-source "fs/partitions/Kconfig"
-
-endmenu
-endif
-
source "fs/nls/Kconfig"
source "fs/dlm/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index d2c3353..93804d4 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -19,6 +19,8 @@
obj-y += no-block.o
endif
+obj-$(CONFIG_PROC_FS) += proc_namespace.o
+
obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
@@ -52,7 +54,6 @@
obj-y += quota/
obj-$(CONFIG_PROC_FS) += proc/
-obj-y += partitions/
obj-$(CONFIG_SYSFS) += sysfs/
obj-$(CONFIG_CONFIGFS_FS) += configfs/
obj-y += devpts/
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7866cdd..69a5b6f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -17,6 +17,7 @@
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/buffer_head.h>
+#include <linux/swap.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
@@ -25,6 +26,7 @@
#include <linux/namei.h>
#include <linux/log2.h>
#include <linux/kmemleak.h>
+#include <linux/cleancache.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -82,13 +84,35 @@
}
/* Kill _all_ buffers and pagecache , dirty or not.. */
-static void kill_bdev(struct block_device *bdev)
+void kill_bdev(struct block_device *bdev)
{
- if (bdev->bd_inode->i_mapping->nrpages == 0)
+ struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+ if (mapping->nrpages == 0)
return;
+
invalidate_bh_lrus();
- truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
+ truncate_inode_pages(mapping, 0);
}
+EXPORT_SYMBOL(kill_bdev);
+
+/* Invalidate clean unused buffers and pagecache. */
+void invalidate_bdev(struct block_device *bdev)
+{
+ struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+ if (mapping->nrpages == 0)
+ return;
+
+ invalidate_bh_lrus();
+ lru_add_drain_all(); /* make sure all lru add caches are flushed */
+ invalidate_mapping_pages(mapping, 0, -1);
+ /* 99% of the time, we don't need to flush the cleancache on the bdev.
+ * But, for the strange corners, lets be cautious
+ */
+ cleancache_flush_inode(mapping);
+}
+EXPORT_SYMBOL(invalidate_bdev);
int set_blocksize(struct block_device *bdev, int size)
{
diff --git a/fs/buffer.c b/fs/buffer.c
index 19d8eb7..1a30db7 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -41,7 +41,6 @@
#include <linux/bitops.h>
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
-#include <linux/cleancache.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
@@ -231,55 +230,6 @@
return ret;
}
-/* If invalidate_buffers() will trash dirty buffers, it means some kind
- of fs corruption is going on. Trashing dirty data always imply losing
- information that was supposed to be just stored on the physical layer
- by the user.
-
- Thus invalidate_buffers in general usage is not allwowed to trash
- dirty buffers. For example ioctl(FLSBLKBUF) expects dirty data to
- be preserved. These buffers are simply skipped.
-
- We also skip buffers which are still in use. For example this can
- happen if a userspace program is reading the block device.
-
- NOTE: In the case where the user removed a removable-media-disk even if
- there's still dirty data not synced on disk (due a bug in the device driver
- or due an error of the user), by not destroying the dirty buffers we could
- generate corruption also on the next media inserted, thus a parameter is
- necessary to handle this case in the most safe way possible (trying
- to not corrupt also the new disk inserted with the data belonging to
- the old now corrupted disk). Also for the ramdisk the natural thing
- to do in order to release the ramdisk memory is to destroy dirty buffers.
-
- These are two special cases. Normal usage imply the device driver
- to issue a sync on the device (without waiting I/O completion) and
- then an invalidate_buffers call that doesn't trash dirty buffers.
-
- For handling cache coherency with the blkdev pagecache the 'update' case
- is been introduced. It is needed to re-read from disk any pinned
- buffer. NOTE: re-reading from disk is destructive so we can do it only
- when we assume nobody is changing the buffercache under our I/O and when
- we think the disk contains more recent information than the buffercache.
- The update == 1 pass marks the buffers we need to update, the update == 2
- pass does the actual I/O. */
-void invalidate_bdev(struct block_device *bdev)
-{
- struct address_space *mapping = bdev->bd_inode->i_mapping;
-
- if (mapping->nrpages == 0)
- return;
-
- invalidate_bh_lrus();
- lru_add_drain_all(); /* make sure all lru add caches are flushed */
- invalidate_mapping_pages(mapping, 0, -1);
- /* 99% of the time, we don't need to flush the cleancache on the bdev.
- * But, for the strange corners, lets be cautious
- */
- cleancache_flush_inode(mapping);
-}
-EXPORT_SYMBOL(invalidate_bdev);
-
/*
* Kick the writeback threads then try to free up some ZONE_NORMAL memory.
*/
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 1064805..67bef6d 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -11,7 +11,6 @@
#include <linux/slab.h>
#include <linux/mount.h>
-#include <linux/buffer_head.h>
#include "internal.h"
#define list_to_page(head) (list_entry((head)->prev, struct page, lru))
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 69fef5b..a2ee8f9 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -20,7 +20,6 @@
#include <linux/cramfs_fs.h>
#include <linux/slab.h>
#include <linux/cramfs_fs_sb.h>
-#include <linux/buffer_head.h>
#include <linux/vfs.h>
#include <linux/mutex.h>
diff --git a/fs/dcache.c b/fs/dcache.c
index 64c8ce4..9791b1e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2452,6 +2452,7 @@
{
struct dentry *dentry = path->dentry;
struct vfsmount *vfsmnt = path->mnt;
+ struct mount *mnt = real_mount(vfsmnt);
bool slash = false;
int error = 0;
@@ -2461,10 +2462,11 @@
if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
/* Global root? */
- if (!mnt_has_parent(vfsmnt))
+ if (!mnt_has_parent(mnt))
goto global_root;
- dentry = vfsmnt->mnt_mountpoint;
- vfsmnt = vfsmnt->mnt_parent;
+ dentry = mnt->mnt_mountpoint;
+ mnt = mnt->mnt_parent;
+ vfsmnt = &mnt->mnt;
continue;
}
parent = dentry->d_parent;
@@ -2501,7 +2503,7 @@
if (!slash)
error = prepend(buffer, buflen, "/", 1);
if (!error)
- error = vfsmnt->mnt_ns ? 1 : 2;
+ error = real_mount(vfsmnt)->mnt_ns ? 1 : 2;
goto out;
}
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 6b08864..5eff711 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -10,6 +10,7 @@
#include <linux/personality.h>
#include <asm/uaccess.h>
#include "internal.h"
+#include "mount.h"
static long do_sys_name_to_handle(struct path *path,
struct file_handle __user *ufh,
@@ -66,7 +67,8 @@
} else
retval = 0;
/* copy the mount id */
- if (copy_to_user(mnt_id, &path->mnt->mnt_id, sizeof(*mnt_id)) ||
+ if (copy_to_user(mnt_id, &real_mount(path->mnt)->mnt_id,
+ sizeof(*mnt_id)) ||
copy_to_user(ufh, handle,
sizeof(struct file_handle) + handle_bytes))
retval = -EFAULT;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 517f211..80a4574 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -25,7 +25,6 @@
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
-#include <linux/buffer_head.h>
#include <linux/tracepoint.h>
#include "internal.h"
diff --git a/fs/internal.h b/fs/internal.h
index 23599f8..2523a40 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -15,6 +15,7 @@
struct file_system_type;
struct linux_binprm;
struct path;
+struct mount;
/*
* block_dev.c
@@ -46,7 +47,6 @@
extern int copy_mount_options(const void __user *, unsigned long *);
extern int copy_mount_string(const void __user *, char **);
-extern struct vfsmount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
extern struct vfsmount *lookup_mnt(struct path *);
extern int finish_automount(struct vfsmount *, struct path *);
diff --git a/fs/libfs.c b/fs/libfs.c
index f6d411e..5b2dbb3 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -12,7 +12,7 @@
#include <linux/mutex.h>
#include <linux/exportfs.h>
#include <linux/writeback.h>
-#include <linux/buffer_head.h>
+#include <linux/buffer_head.h> /* sync_mapping_buffers */
#include <asm/uaccess.h>
diff --git a/fs/mount.h b/fs/mount.h
index 7890e49..0921b51 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -1,6 +1,75 @@
#include <linux/mount.h>
+#include <linux/seq_file.h>
+#include <linux/poll.h>
-static inline int mnt_has_parent(struct vfsmount *mnt)
+struct mnt_namespace {
+ atomic_t count;
+ struct mount * root;
+ struct list_head list;
+ wait_queue_head_t poll;
+ int event;
+};
+
+struct mnt_pcp {
+ int mnt_count;
+ int mnt_writers;
+};
+
+struct mount {
+ struct list_head mnt_hash;
+ struct mount *mnt_parent;
+ struct dentry *mnt_mountpoint;
+ struct vfsmount mnt;
+#ifdef CONFIG_SMP
+ struct mnt_pcp __percpu *mnt_pcp;
+ atomic_t mnt_longterm; /* how many of the refs are longterm */
+#else
+ int mnt_count;
+ int mnt_writers;
+#endif
+ struct list_head mnt_mounts; /* list of children, anchored here */
+ struct list_head mnt_child; /* and going through their mnt_child */
+ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */
+ struct list_head mnt_list;
+ struct list_head mnt_expire; /* link in fs-specific expiry list */
+ struct list_head mnt_share; /* circular list of shared mounts */
+ struct list_head mnt_slave_list;/* list of slave mounts */
+ struct list_head mnt_slave; /* slave list entry */
+ struct mount *mnt_master; /* slave is on master->mnt_slave_list */
+ struct mnt_namespace *mnt_ns; /* containing namespace */
+#ifdef CONFIG_FSNOTIFY
+ struct hlist_head mnt_fsnotify_marks;
+ __u32 mnt_fsnotify_mask;
+#endif
+ int mnt_id; /* mount identifier */
+ int mnt_group_id; /* peer group identifier */
+ int mnt_expiry_mark; /* true if marked for expiry */
+ int mnt_pinned;
+ int mnt_ghosts;
+};
+
+static inline struct mount *real_mount(struct vfsmount *mnt)
+{
+ return container_of(mnt, struct mount, mnt);
+}
+
+static inline int mnt_has_parent(struct mount *mnt)
{
return mnt != mnt->mnt_parent;
}
+
+extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
+
+static inline void get_mnt_ns(struct mnt_namespace *ns)
+{
+ atomic_inc(&ns->count);
+}
+
+struct proc_mounts {
+ struct seq_file m; /* must be the first element */
+ struct mnt_namespace *ns;
+ struct path root;
+ int (*show)(struct seq_file *, struct vfsmount *);
+};
+
+extern const struct seq_operations mounts_op;
diff --git a/fs/namei.c b/fs/namei.c
index afd5876..c283a1e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -36,6 +36,7 @@
#include <asm/uaccess.h>
#include "internal.h"
+#include "mount.h"
/* [Feb-1997 T. Schoebel-Theuer]
* Fundamental changes in the pathname lookup mechanisms (namei)
@@ -676,36 +677,38 @@
static int follow_up_rcu(struct path *path)
{
- struct vfsmount *parent;
+ struct mount *mnt = real_mount(path->mnt);
+ struct mount *parent;
struct dentry *mountpoint;
- parent = path->mnt->mnt_parent;
- if (parent == path->mnt)
+ parent = mnt->mnt_parent;
+ if (&parent->mnt == path->mnt)
return 0;
- mountpoint = path->mnt->mnt_mountpoint;
+ mountpoint = mnt->mnt_mountpoint;
path->dentry = mountpoint;
- path->mnt = parent;
+ path->mnt = &parent->mnt;
return 1;
}
int follow_up(struct path *path)
{
- struct vfsmount *parent;
+ struct mount *mnt = real_mount(path->mnt);
+ struct mount *parent;
struct dentry *mountpoint;
br_read_lock(vfsmount_lock);
- parent = path->mnt->mnt_parent;
- if (parent == path->mnt) {
+ parent = mnt->mnt_parent;
+ if (&parent->mnt == path->mnt) {
br_read_unlock(vfsmount_lock);
return 0;
}
- mntget(parent);
- mountpoint = dget(path->mnt->mnt_mountpoint);
+ mntget(&parent->mnt);
+ mountpoint = dget(mnt->mnt_mountpoint);
br_read_unlock(vfsmount_lock);
dput(path->dentry);
path->dentry = mountpoint;
mntput(path->mnt);
- path->mnt = parent;
+ path->mnt = &parent->mnt;
return 1;
}
@@ -884,7 +887,7 @@
struct inode **inode)
{
for (;;) {
- struct vfsmount *mounted;
+ struct mount *mounted;
/*
* Don't forget we might have a non-mountpoint managed dentry
* that wants to block transit.
@@ -898,8 +901,8 @@
mounted = __lookup_mnt(path->mnt, path->dentry, 1);
if (!mounted)
break;
- path->mnt = mounted;
- path->dentry = mounted->mnt_root;
+ path->mnt = &mounted->mnt;
+ path->dentry = mounted->mnt.mnt_root;
nd->flags |= LOOKUP_JUMPED;
nd->seq = read_seqcount_begin(&path->dentry->d_seq);
/*
@@ -915,12 +918,12 @@
static void follow_mount_rcu(struct nameidata *nd)
{
while (d_mountpoint(nd->path.dentry)) {
- struct vfsmount *mounted;
+ struct mount *mounted;
mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry, 1);
if (!mounted)
break;
- nd->path.mnt = mounted;
- nd->path.dentry = mounted->mnt_root;
+ nd->path.mnt = &mounted->mnt;
+ nd->path.dentry = mounted->mnt.mnt_root;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
}
}
diff --git a/fs/namespace.c b/fs/namespace.c
index 86b4f64..773435c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -9,30 +9,17 @@
*/
#include <linux/syscalls.h>
-#include <linux/slab.h>
-#include <linux/sched.h>
-#include <linux/spinlock.h>
-#include <linux/percpu.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/acct.h>
+#include <linux/export.h>
#include <linux/capability.h>
-#include <linux/cpumask.h>
-#include <linux/module.h>
-#include <linux/sysfs.h>
-#include <linux/seq_file.h>
#include <linux/mnt_namespace.h>
#include <linux/namei.h>
-#include <linux/nsproxy.h>
#include <linux/security.h>
-#include <linux/mount.h>
-#include <linux/ramfs.h>
-#include <linux/log2.h>
#include <linux/idr.h>
-#include <linux/fs_struct.h>
-#include <linux/fsnotify.h>
-#include <asm/uaccess.h>
-#include <asm/unistd.h>
+#include <linux/acct.h> /* acct_auto_close_mnt */
+#include <linux/ramfs.h> /* init_rootfs */
+#include <linux/fs_struct.h> /* get_fs_root et.al. */
+#include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */
+#include <linux/uaccess.h>
#include "pnode.h"
#include "internal.h"
@@ -78,7 +65,7 @@
* allocation is serialized by namespace_sem, but we need the spinlock to
* serialize with freeing.
*/
-static int mnt_alloc_id(struct vfsmount *mnt)
+static int mnt_alloc_id(struct mount *mnt)
{
int res;
@@ -95,7 +82,7 @@
return res;
}
-static void mnt_free_id(struct vfsmount *mnt)
+static void mnt_free_id(struct mount *mnt)
{
int id = mnt->mnt_id;
spin_lock(&mnt_id_lock);
@@ -110,7 +97,7 @@
*
* mnt_group_ida is protected by namespace_sem
*/
-static int mnt_alloc_group_id(struct vfsmount *mnt)
+static int mnt_alloc_group_id(struct mount *mnt)
{
int res;
@@ -129,7 +116,7 @@
/*
* Release a peer group ID
*/
-void mnt_release_group_id(struct vfsmount *mnt)
+void mnt_release_group_id(struct mount *mnt)
{
int id = mnt->mnt_group_id;
ida_remove(&mnt_group_ida, id);
@@ -141,7 +128,7 @@
/*
* vfsmount lock must be held for read
*/
-static inline void mnt_add_count(struct vfsmount *mnt, int n)
+static inline void mnt_add_count(struct mount *mnt, int n)
{
#ifdef CONFIG_SMP
this_cpu_add(mnt->mnt_pcp->mnt_count, n);
@@ -155,7 +142,7 @@
/*
* vfsmount lock must be held for write
*/
-unsigned int mnt_get_count(struct vfsmount *mnt)
+unsigned int mnt_get_count(struct mount *mnt)
{
#ifdef CONFIG_SMP
unsigned int count = 0;
@@ -171,9 +158,9 @@
#endif
}
-static struct vfsmount *alloc_vfsmnt(const char *name)
+static struct mount *alloc_vfsmnt(const char *name)
{
- struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
+ struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
if (mnt) {
int err;
@@ -252,7 +239,7 @@
}
EXPORT_SYMBOL_GPL(__mnt_is_readonly);
-static inline void mnt_inc_writers(struct vfsmount *mnt)
+static inline void mnt_inc_writers(struct mount *mnt)
{
#ifdef CONFIG_SMP
this_cpu_inc(mnt->mnt_pcp->mnt_writers);
@@ -261,7 +248,7 @@
#endif
}
-static inline void mnt_dec_writers(struct vfsmount *mnt)
+static inline void mnt_dec_writers(struct mount *mnt)
{
#ifdef CONFIG_SMP
this_cpu_dec(mnt->mnt_pcp->mnt_writers);
@@ -270,7 +257,7 @@
#endif
}
-static unsigned int mnt_get_writers(struct vfsmount *mnt)
+static unsigned int mnt_get_writers(struct mount *mnt)
{
#ifdef CONFIG_SMP
unsigned int count = 0;
@@ -296,7 +283,7 @@
*/
/**
* mnt_want_write - get write access to a mount
- * @mnt: the mount on which to take a write
+ * @m: the mount on which to take a write
*
* This tells the low-level filesystem that a write is
* about to be performed to it, and makes sure that
@@ -304,8 +291,9 @@
* the write operation is finished, mnt_drop_write()
* must be called. This is effectively a refcount.
*/
-int mnt_want_write(struct vfsmount *mnt)
+int mnt_want_write(struct vfsmount *m)
{
+ struct mount *mnt = real_mount(m);
int ret = 0;
preempt_disable();
@@ -316,7 +304,7 @@
* incremented count after it has set MNT_WRITE_HOLD.
*/
smp_mb();
- while (mnt->mnt_flags & MNT_WRITE_HOLD)
+ while (mnt->mnt.mnt_flags & MNT_WRITE_HOLD)
cpu_relax();
/*
* After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
@@ -324,7 +312,7 @@
* MNT_WRITE_HOLD is cleared.
*/
smp_rmb();
- if (__mnt_is_readonly(mnt)) {
+ if (__mnt_is_readonly(m)) {
mnt_dec_writers(mnt);
ret = -EROFS;
goto out;
@@ -353,7 +341,7 @@
if (__mnt_is_readonly(mnt))
return -EROFS;
preempt_disable();
- mnt_inc_writers(mnt);
+ mnt_inc_writers(real_mount(mnt));
preempt_enable();
return 0;
}
@@ -387,7 +375,7 @@
void mnt_drop_write(struct vfsmount *mnt)
{
preempt_disable();
- mnt_dec_writers(mnt);
+ mnt_dec_writers(real_mount(mnt));
preempt_enable();
}
EXPORT_SYMBOL_GPL(mnt_drop_write);
@@ -398,12 +386,12 @@
}
EXPORT_SYMBOL(mnt_drop_write_file);
-static int mnt_make_readonly(struct vfsmount *mnt)
+static int mnt_make_readonly(struct mount *mnt)
{
int ret = 0;
br_write_lock(vfsmount_lock);
- mnt->mnt_flags |= MNT_WRITE_HOLD;
+ mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
/*
* After storing MNT_WRITE_HOLD, we'll read the counters. This store
* should be visible before we do.
@@ -429,25 +417,25 @@
if (mnt_get_writers(mnt) > 0)
ret = -EBUSY;
else
- mnt->mnt_flags |= MNT_READONLY;
+ mnt->mnt.mnt_flags |= MNT_READONLY;
/*
* MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers
* that become unheld will see MNT_READONLY.
*/
smp_wmb();
- mnt->mnt_flags &= ~MNT_WRITE_HOLD;
+ mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
br_write_unlock(vfsmount_lock);
return ret;
}
-static void __mnt_unmake_readonly(struct vfsmount *mnt)
+static void __mnt_unmake_readonly(struct mount *mnt)
{
br_write_lock(vfsmount_lock);
- mnt->mnt_flags &= ~MNT_READONLY;
+ mnt->mnt.mnt_flags &= ~MNT_READONLY;
br_write_unlock(vfsmount_lock);
}
-static void free_vfsmnt(struct vfsmount *mnt)
+static void free_vfsmnt(struct mount *mnt)
{
kfree(mnt->mnt_devname);
mnt_free_id(mnt);
@@ -462,20 +450,20 @@
* @dir. If @dir is set return the first mount else return the last mount.
* vfsmount_lock must be held for read or write.
*/
-struct vfsmount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
+struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
int dir)
{
struct list_head *head = mount_hashtable + hash(mnt, dentry);
struct list_head *tmp = head;
- struct vfsmount *p, *found = NULL;
+ struct mount *p, *found = NULL;
for (;;) {
tmp = dir ? tmp->next : tmp->prev;
p = NULL;
if (tmp == head)
break;
- p = list_entry(tmp, struct vfsmount, mnt_hash);
- if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) {
+ p = list_entry(tmp, struct mount, mnt_hash);
+ if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) {
found = p;
break;
}
@@ -489,16 +477,21 @@
*/
struct vfsmount *lookup_mnt(struct path *path)
{
- struct vfsmount *child_mnt;
+ struct mount *child_mnt;
br_read_lock(vfsmount_lock);
- if ((child_mnt = __lookup_mnt(path->mnt, path->dentry, 1)))
- mntget(child_mnt);
- br_read_unlock(vfsmount_lock);
- return child_mnt;
+ child_mnt = __lookup_mnt(path->mnt, path->dentry, 1);
+ if (child_mnt) {
+ mnt_add_count(child_mnt, 1);
+ br_read_unlock(vfsmount_lock);
+ return &child_mnt->mnt;
+ } else {
+ br_read_unlock(vfsmount_lock);
+ return NULL;
+ }
}
-static inline int check_mnt(struct vfsmount *mnt)
+static inline int check_mnt(struct mount *mnt)
{
return mnt->mnt_ns == current->nsproxy->mnt_ns;
}
@@ -534,7 +527,7 @@
unsigned u;
for (u = 0; u < HASH_SIZE; u++) {
- struct vfsmount *p;
+ struct mount *p;
list_for_each_entry(p, &mount_hashtable[u], mnt_hash) {
if (p->mnt_mountpoint == dentry)
@@ -549,12 +542,12 @@
/*
* vfsmount lock must be held for write
*/
-static void detach_mnt(struct vfsmount *mnt, struct path *old_path)
+static void detach_mnt(struct mount *mnt, struct path *old_path)
{
old_path->dentry = mnt->mnt_mountpoint;
- old_path->mnt = mnt->mnt_parent;
+ old_path->mnt = &mnt->mnt_parent->mnt;
mnt->mnt_parent = mnt;
- mnt->mnt_mountpoint = mnt->mnt_root;
+ mnt->mnt_mountpoint = mnt->mnt.mnt_root;
list_del_init(&mnt->mnt_child);
list_del_init(&mnt->mnt_hash);
dentry_reset_mounted(old_path->dentry);
@@ -563,11 +556,12 @@
/*
* vfsmount lock must be held for write
*/
-void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
- struct vfsmount *child_mnt)
+void mnt_set_mountpoint(struct mount *mnt, struct dentry *dentry,
+ struct mount *child_mnt)
{
- child_mnt->mnt_parent = mntget(mnt);
+ mnt_add_count(mnt, 1); /* essentially, that's mntget */
child_mnt->mnt_mountpoint = dget(dentry);
+ child_mnt->mnt_parent = mnt;
spin_lock(&dentry->d_lock);
dentry->d_flags |= DCACHE_MOUNTED;
spin_unlock(&dentry->d_lock);
@@ -576,15 +570,15 @@
/*
* vfsmount lock must be held for write
*/
-static void attach_mnt(struct vfsmount *mnt, struct path *path)
+static void attach_mnt(struct mount *mnt, struct path *path)
{
- mnt_set_mountpoint(path->mnt, path->dentry, mnt);
+ mnt_set_mountpoint(real_mount(path->mnt), path->dentry, mnt);
list_add_tail(&mnt->mnt_hash, mount_hashtable +
hash(path->mnt, path->dentry));
- list_add_tail(&mnt->mnt_child, &path->mnt->mnt_mounts);
+ list_add_tail(&mnt->mnt_child, &real_mount(path->mnt)->mnt_mounts);
}
-static inline void __mnt_make_longterm(struct vfsmount *mnt)
+static inline void __mnt_make_longterm(struct mount *mnt)
{
#ifdef CONFIG_SMP
atomic_inc(&mnt->mnt_longterm);
@@ -592,7 +586,7 @@
}
/* needs vfsmount lock for write */
-static inline void __mnt_make_shortterm(struct vfsmount *mnt)
+static inline void __mnt_make_shortterm(struct mount *mnt)
{
#ifdef CONFIG_SMP
atomic_dec(&mnt->mnt_longterm);
@@ -602,10 +596,10 @@
/*
* vfsmount lock must be held for write
*/
-static void commit_tree(struct vfsmount *mnt)
+static void commit_tree(struct mount *mnt)
{
- struct vfsmount *parent = mnt->mnt_parent;
- struct vfsmount *m;
+ struct mount *parent = mnt->mnt_parent;
+ struct mount *m;
LIST_HEAD(head);
struct mnt_namespace *n = parent->mnt_ns;
@@ -620,12 +614,12 @@
list_splice(&head, n->list.prev);
list_add_tail(&mnt->mnt_hash, mount_hashtable +
- hash(parent, mnt->mnt_mountpoint));
+ hash(&parent->mnt, mnt->mnt_mountpoint));
list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
touch_mnt_namespace(n);
}
-static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root)
+static struct mount *next_mnt(struct mount *p, struct mount *root)
{
struct list_head *next = p->mnt_mounts.next;
if (next == &p->mnt_mounts) {
@@ -638,14 +632,14 @@
p = p->mnt_parent;
}
}
- return list_entry(next, struct vfsmount, mnt_child);
+ return list_entry(next, struct mount, mnt_child);
}
-static struct vfsmount *skip_mnt_tree(struct vfsmount *p)
+static struct mount *skip_mnt_tree(struct mount *p)
{
struct list_head *prev = p->mnt_mounts.prev;
while (prev != &p->mnt_mounts) {
- p = list_entry(prev, struct vfsmount, mnt_child);
+ p = list_entry(prev, struct mount, mnt_child);
prev = p->mnt_mounts.prev;
}
return p;
@@ -654,7 +648,7 @@
struct vfsmount *
vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
{
- struct vfsmount *mnt;
+ struct mount *mnt;
struct dentry *root;
if (!type)
@@ -665,7 +659,7 @@
return ERR_PTR(-ENOMEM);
if (flags & MS_KERNMOUNT)
- mnt->mnt_flags = MNT_INTERNAL;
+ mnt->mnt.mnt_flags = MNT_INTERNAL;
root = mount_fs(type, flags, name, data);
if (IS_ERR(root)) {
@@ -673,19 +667,19 @@
return ERR_CAST(root);
}
- mnt->mnt_root = root;
- mnt->mnt_sb = root->d_sb;
- mnt->mnt_mountpoint = mnt->mnt_root;
+ mnt->mnt.mnt_root = root;
+ mnt->mnt.mnt_sb = root->d_sb;
+ mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
- return mnt;
+ return &mnt->mnt;
}
EXPORT_SYMBOL_GPL(vfs_kern_mount);
-static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
+static struct mount *clone_mnt(struct mount *old, struct dentry *root,
int flag)
{
- struct super_block *sb = old->mnt_sb;
- struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname);
+ struct super_block *sb = old->mnt.mnt_sb;
+ struct mount *mnt = alloc_vfsmnt(old->mnt_devname);
if (mnt) {
if (flag & (CL_SLAVE | CL_PRIVATE))
@@ -699,11 +693,11 @@
goto out_free;
}
- mnt->mnt_flags = old->mnt_flags & ~MNT_WRITE_HOLD;
+ mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
atomic_inc(&sb->s_active);
- mnt->mnt_sb = sb;
- mnt->mnt_root = dget(root);
- mnt->mnt_mountpoint = mnt->mnt_root;
+ mnt->mnt.mnt_sb = sb;
+ mnt->mnt.mnt_root = dget(root);
+ mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
if (flag & CL_SLAVE) {
@@ -734,9 +728,10 @@
return NULL;
}
-static inline void mntfree(struct vfsmount *mnt)
+static inline void mntfree(struct mount *mnt)
{
- struct super_block *sb = mnt->mnt_sb;
+ struct vfsmount *m = &mnt->mnt;
+ struct super_block *sb = m->mnt_sb;
/*
* This probably indicates that somebody messed
@@ -749,13 +744,13 @@
* so mnt_get_writers() below is safe.
*/
WARN_ON(mnt_get_writers(mnt));
- fsnotify_vfsmount_delete(mnt);
- dput(mnt->mnt_root);
+ fsnotify_vfsmount_delete(m);
+ dput(m->mnt_root);
free_vfsmnt(mnt);
deactivate_super(sb);
}
-static void mntput_no_expire(struct vfsmount *mnt)
+static void mntput_no_expire(struct mount *mnt)
{
put_again:
#ifdef CONFIG_SMP
@@ -783,7 +778,7 @@
mnt_add_count(mnt, mnt->mnt_pinned + 1);
mnt->mnt_pinned = 0;
br_write_unlock(vfsmount_lock);
- acct_auto_close_mnt(mnt);
+ acct_auto_close_mnt(&mnt->mnt);
goto put_again;
}
br_write_unlock(vfsmount_lock);
@@ -793,10 +788,11 @@
void mntput(struct vfsmount *mnt)
{
if (mnt) {
+ struct mount *m = real_mount(mnt);
/* avoid cacheline pingpong, hope gcc doesn't get "smart" */
- if (unlikely(mnt->mnt_expiry_mark))
- mnt->mnt_expiry_mark = 0;
- mntput_no_expire(mnt);
+ if (unlikely(m->mnt_expiry_mark))
+ m->mnt_expiry_mark = 0;
+ mntput_no_expire(m);
}
}
EXPORT_SYMBOL(mntput);
@@ -804,7 +800,7 @@
struct vfsmount *mntget(struct vfsmount *mnt)
{
if (mnt)
- mnt_add_count(mnt, 1);
+ mnt_add_count(real_mount(mnt), 1);
return mnt;
}
EXPORT_SYMBOL(mntget);
@@ -812,13 +808,14 @@
void mnt_pin(struct vfsmount *mnt)
{
br_write_lock(vfsmount_lock);
- mnt->mnt_pinned++;
+ real_mount(mnt)->mnt_pinned++;
br_write_unlock(vfsmount_lock);
}
EXPORT_SYMBOL(mnt_pin);
-void mnt_unpin(struct vfsmount *mnt)
+void mnt_unpin(struct vfsmount *m)
{
+ struct mount *mnt = real_mount(m);
br_write_lock(vfsmount_lock);
if (mnt->mnt_pinned) {
mnt_add_count(mnt, 1);
@@ -888,10 +885,10 @@
EXPORT_SYMBOL(replace_mount_options);
#ifdef CONFIG_PROC_FS
-/* iterator */
+/* iterator; we want it to have access to namespace_sem, thus here... */
static void *m_start(struct seq_file *m, loff_t *pos)
{
- struct proc_mounts *p = m->private;
+ struct proc_mounts *p = container_of(m, struct proc_mounts, m);
down_read(&namespace_sem);
return seq_list_start(&p->ns->list, *pos);
@@ -899,7 +896,7 @@
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct proc_mounts *p = m->private;
+ struct proc_mounts *p = container_of(m, struct proc_mounts, m);
return seq_list_next(v, &p->ns->list, pos);
}
@@ -909,219 +906,18 @@
up_read(&namespace_sem);
}
-int mnt_had_events(struct proc_mounts *p)
+static int m_show(struct seq_file *m, void *v)
{
- struct mnt_namespace *ns = p->ns;
- int res = 0;
-
- br_read_lock(vfsmount_lock);
- if (p->m.poll_event != ns->event) {
- p->m.poll_event = ns->event;
- res = 1;
- }
- br_read_unlock(vfsmount_lock);
-
- return res;
-}
-
-struct proc_fs_info {
- int flag;
- const char *str;
-};
-
-static int show_sb_opts(struct seq_file *m, struct super_block *sb)
-{
- static const struct proc_fs_info fs_info[] = {
- { MS_SYNCHRONOUS, ",sync" },
- { MS_DIRSYNC, ",dirsync" },
- { MS_MANDLOCK, ",mand" },
- { 0, NULL }
- };
- const struct proc_fs_info *fs_infop;
-
- for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
- if (sb->s_flags & fs_infop->flag)
- seq_puts(m, fs_infop->str);
- }
-
- return security_sb_show_options(m, sb);
-}
-
-static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
-{
- static const struct proc_fs_info mnt_info[] = {
- { MNT_NOSUID, ",nosuid" },
- { MNT_NODEV, ",nodev" },
- { MNT_NOEXEC, ",noexec" },
- { MNT_NOATIME, ",noatime" },
- { MNT_NODIRATIME, ",nodiratime" },
- { MNT_RELATIME, ",relatime" },
- { 0, NULL }
- };
- const struct proc_fs_info *fs_infop;
-
- for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
- if (mnt->mnt_flags & fs_infop->flag)
- seq_puts(m, fs_infop->str);
- }
-}
-
-static void show_type(struct seq_file *m, struct super_block *sb)
-{
- mangle(m, sb->s_type->name);
- if (sb->s_subtype && sb->s_subtype[0]) {
- seq_putc(m, '.');
- mangle(m, sb->s_subtype);
- }
-}
-
-static int show_vfsmnt(struct seq_file *m, void *v)
-{
- struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
- int err = 0;
- struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
-
- if (mnt->mnt_sb->s_op->show_devname) {
- err = mnt->mnt_sb->s_op->show_devname(m, mnt);
- if (err)
- goto out;
- } else {
- mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
- }
- seq_putc(m, ' ');
- seq_path(m, &mnt_path, " \t\n\\");
- seq_putc(m, ' ');
- show_type(m, mnt->mnt_sb);
- seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
- err = show_sb_opts(m, mnt->mnt_sb);
- if (err)
- goto out;
- show_mnt_opts(m, mnt);
- if (mnt->mnt_sb->s_op->show_options)
- err = mnt->mnt_sb->s_op->show_options(m, mnt);
- seq_puts(m, " 0 0\n");
-out:
- return err;
+ struct proc_mounts *p = container_of(m, struct proc_mounts, m);
+ struct mount *r = list_entry(v, struct mount, mnt_list);
+ return p->show(m, &r->mnt);
}
const struct seq_operations mounts_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_vfsmnt
-};
-
-static int show_mountinfo(struct seq_file *m, void *v)
-{
- struct proc_mounts *p = m->private;
- struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
- struct super_block *sb = mnt->mnt_sb;
- struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
- struct path root = p->root;
- int err = 0;
-
- seq_printf(m, "%i %i %u:%u ", mnt->mnt_id, mnt->mnt_parent->mnt_id,
- MAJOR(sb->s_dev), MINOR(sb->s_dev));
- if (sb->s_op->show_path)
- err = sb->s_op->show_path(m, mnt);
- else
- seq_dentry(m, mnt->mnt_root, " \t\n\\");
- if (err)
- goto out;
- seq_putc(m, ' ');
-
- /* mountpoints outside of chroot jail will give SEQ_SKIP on this */
- err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
- if (err)
- goto out;
-
- seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
- show_mnt_opts(m, mnt);
-
- /* Tagged fields ("foo:X" or "bar") */
- if (IS_MNT_SHARED(mnt))
- seq_printf(m, " shared:%i", mnt->mnt_group_id);
- if (IS_MNT_SLAVE(mnt)) {
- int master = mnt->mnt_master->mnt_group_id;
- int dom = get_dominating_id(mnt, &p->root);
- seq_printf(m, " master:%i", master);
- if (dom && dom != master)
- seq_printf(m, " propagate_from:%i", dom);
- }
- if (IS_MNT_UNBINDABLE(mnt))
- seq_puts(m, " unbindable");
-
- /* Filesystem specific data */
- seq_puts(m, " - ");
- show_type(m, sb);
- seq_putc(m, ' ');
- if (sb->s_op->show_devname)
- err = sb->s_op->show_devname(m, mnt);
- else
- mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
- if (err)
- goto out;
- seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
- err = show_sb_opts(m, sb);
- if (err)
- goto out;
- if (sb->s_op->show_options)
- err = sb->s_op->show_options(m, mnt);
- seq_putc(m, '\n');
-out:
- return err;
-}
-
-const struct seq_operations mountinfo_op = {
- .start = m_start,
- .next = m_next,
- .stop = m_stop,
- .show = show_mountinfo,
-};
-
-static int show_vfsstat(struct seq_file *m, void *v)
-{
- struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
- struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
- int err = 0;
-
- /* device */
- if (mnt->mnt_sb->s_op->show_devname) {
- seq_puts(m, "device ");
- err = mnt->mnt_sb->s_op->show_devname(m, mnt);
- } else {
- if (mnt->mnt_devname) {
- seq_puts(m, "device ");
- mangle(m, mnt->mnt_devname);
- } else
- seq_puts(m, "no device");
- }
-
- /* mount point */
- seq_puts(m, " mounted on ");
- seq_path(m, &mnt_path, " \t\n\\");
- seq_putc(m, ' ');
-
- /* file system type */
- seq_puts(m, "with fstype ");
- show_type(m, mnt->mnt_sb);
-
- /* optional statistics */
- if (mnt->mnt_sb->s_op->show_stats) {
- seq_putc(m, ' ');
- if (!err)
- err = mnt->mnt_sb->s_op->show_stats(m, mnt);
- }
-
- seq_putc(m, '\n');
- return err;
-}
-
-const struct seq_operations mountstats_op = {
- .start = m_start,
- .next = m_next,
- .stop = m_stop,
- .show = show_vfsstat,
+ .show = m_show,
};
#endif /* CONFIG_PROC_FS */
@@ -1133,11 +929,13 @@
* open files, pwds, chroots or sub mounts that are
* busy.
*/
-int may_umount_tree(struct vfsmount *mnt)
+int may_umount_tree(struct vfsmount *m)
{
+ struct mount *mnt = real_mount(m);
int actual_refs = 0;
int minimum_refs = 0;
- struct vfsmount *p;
+ struct mount *p;
+ BUG_ON(!m);
/* write lock needed for mnt_get_count */
br_write_lock(vfsmount_lock);
@@ -1173,7 +971,7 @@
int ret = 1;
down_read(&namespace_sem);
br_write_lock(vfsmount_lock);
- if (propagate_mount_busy(mnt, 2))
+ if (propagate_mount_busy(real_mount(mnt), 2))
ret = 0;
br_write_unlock(vfsmount_lock);
up_read(&namespace_sem);
@@ -1184,25 +982,25 @@
void release_mounts(struct list_head *head)
{
- struct vfsmount *mnt;
+ struct mount *mnt;
while (!list_empty(head)) {
- mnt = list_first_entry(head, struct vfsmount, mnt_hash);
+ mnt = list_first_entry(head, struct mount, mnt_hash);
list_del_init(&mnt->mnt_hash);
if (mnt_has_parent(mnt)) {
struct dentry *dentry;
- struct vfsmount *m;
+ struct mount *m;
br_write_lock(vfsmount_lock);
dentry = mnt->mnt_mountpoint;
m = mnt->mnt_parent;
- mnt->mnt_mountpoint = mnt->mnt_root;
+ mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
m->mnt_ghosts--;
br_write_unlock(vfsmount_lock);
dput(dentry);
- mntput(m);
+ mntput(&m->mnt);
}
- mntput(mnt);
+ mntput(&mnt->mnt);
}
}
@@ -1210,10 +1008,10 @@
* vfsmount lock must be held for write
* namespace_sem must be held for write
*/
-void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
+void umount_tree(struct mount *mnt, int propagate, struct list_head *kill)
{
LIST_HEAD(tmp_list);
- struct vfsmount *p;
+ struct mount *p;
for (p = mnt; p; p = next_mnt(p, mnt))
list_move(&p->mnt_hash, &tmp_list);
@@ -1237,15 +1035,15 @@
list_splice(&tmp_list, kill);
}
-static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts);
+static void shrink_submounts(struct mount *mnt, struct list_head *umounts);
-static int do_umount(struct vfsmount *mnt, int flags)
+static int do_umount(struct mount *mnt, int flags)
{
- struct super_block *sb = mnt->mnt_sb;
+ struct super_block *sb = mnt->mnt.mnt_sb;
int retval;
LIST_HEAD(umount_list);
- retval = security_sb_umount(mnt, flags);
+ retval = security_sb_umount(&mnt->mnt, flags);
if (retval)
return retval;
@@ -1256,7 +1054,7 @@
* (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
*/
if (flags & MNT_EXPIRE) {
- if (mnt == current->fs->root.mnt ||
+ if (&mnt->mnt == current->fs->root.mnt ||
flags & (MNT_FORCE | MNT_DETACH))
return -EINVAL;
@@ -1298,7 +1096,7 @@
* /reboot - static binary that would close all descriptors and
* call reboot(9). Then init(8) could umount root and exec /reboot.
*/
- if (mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) {
+ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) {
/*
* Special case for "unmounting" root ...
* we just try to remount it readonly.
@@ -1340,6 +1138,7 @@
SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
{
struct path path;
+ struct mount *mnt;
int retval;
int lookup_flags = 0;
@@ -1352,21 +1151,22 @@
retval = user_path_at(AT_FDCWD, name, lookup_flags, &path);
if (retval)
goto out;
+ mnt = real_mount(path.mnt);
retval = -EINVAL;
if (path.dentry != path.mnt->mnt_root)
goto dput_and_out;
- if (!check_mnt(path.mnt))
+ if (!check_mnt(mnt))
goto dput_and_out;
retval = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto dput_and_out;
- retval = do_umount(path.mnt, flags);
+ retval = do_umount(mnt, flags);
dput_and_out:
/* we mustn't call path_put() as that would clear mnt_expiry_mark */
dput(path.dentry);
- mntput_no_expire(path.mnt);
+ mntput_no_expire(mnt);
out:
return retval;
}
@@ -1401,10 +1201,10 @@
#endif
}
-struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
+struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
int flag)
{
- struct vfsmount *res, *p, *q, *r, *s;
+ struct mount *res, *p, *q, *r;
struct path path;
if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt))
@@ -1417,6 +1217,7 @@
p = mnt;
list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) {
+ struct mount *s;
if (!is_subdir(r->mnt_mountpoint, dentry))
continue;
@@ -1430,9 +1231,9 @@
q = q->mnt_parent;
}
p = s;
- path.mnt = q;
+ path.mnt = &q->mnt;
path.dentry = p->mnt_mountpoint;
- q = clone_mnt(p, p->mnt_root, flag);
+ q = clone_mnt(p, p->mnt.mnt_root, flag);
if (!q)
goto Enomem;
br_write_lock(vfsmount_lock);
@@ -1455,11 +1256,12 @@
struct vfsmount *collect_mounts(struct path *path)
{
- struct vfsmount *tree;
+ struct mount *tree;
down_write(&namespace_sem);
- tree = copy_tree(path->mnt, path->dentry, CL_COPY_ALL | CL_PRIVATE);
+ tree = copy_tree(real_mount(path->mnt), path->dentry,
+ CL_COPY_ALL | CL_PRIVATE);
up_write(&namespace_sem);
- return tree;
+ return tree ? &tree->mnt : NULL;
}
void drop_collected_mounts(struct vfsmount *mnt)
@@ -1467,7 +1269,7 @@
LIST_HEAD(umount_list);
down_write(&namespace_sem);
br_write_lock(vfsmount_lock);
- umount_tree(mnt, 0, &umount_list);
+ umount_tree(real_mount(mnt), 0, &umount_list);
br_write_unlock(vfsmount_lock);
up_write(&namespace_sem);
release_mounts(&umount_list);
@@ -1476,21 +1278,21 @@
int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
struct vfsmount *root)
{
- struct vfsmount *mnt;
+ struct mount *mnt;
int res = f(root, arg);
if (res)
return res;
- list_for_each_entry(mnt, &root->mnt_list, mnt_list) {
- res = f(mnt, arg);
+ list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) {
+ res = f(&mnt->mnt, arg);
if (res)
return res;
}
return 0;
}
-static void cleanup_group_ids(struct vfsmount *mnt, struct vfsmount *end)
+static void cleanup_group_ids(struct mount *mnt, struct mount *end)
{
- struct vfsmount *p;
+ struct mount *p;
for (p = mnt; p != end; p = next_mnt(p, mnt)) {
if (p->mnt_group_id && !IS_MNT_SHARED(p))
@@ -1498,9 +1300,9 @@
}
}
-static int invent_group_ids(struct vfsmount *mnt, bool recurse)
+static int invent_group_ids(struct mount *mnt, bool recurse)
{
- struct vfsmount *p;
+ struct mount *p;
for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
@@ -1578,13 +1380,13 @@
* Must be called without spinlocks held, since this function can sleep
* in allocations.
*/
-static int attach_recursive_mnt(struct vfsmount *source_mnt,
+static int attach_recursive_mnt(struct mount *source_mnt,
struct path *path, struct path *parent_path)
{
LIST_HEAD(tree_list);
- struct vfsmount *dest_mnt = path->mnt;
+ struct mount *dest_mnt = real_mount(path->mnt);
struct dentry *dest_dentry = path->dentry;
- struct vfsmount *child, *p;
+ struct mount *child, *p;
int err;
if (IS_MNT_SHARED(dest_mnt)) {
@@ -1605,7 +1407,7 @@
if (parent_path) {
detach_mnt(source_mnt, parent_path);
attach_mnt(source_mnt, path);
- touch_mnt_namespace(parent_path->mnt->mnt_ns);
+ touch_mnt_namespace(source_mnt->mnt_ns);
} else {
mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt);
commit_tree(source_mnt);
@@ -1653,13 +1455,13 @@
mutex_unlock(&path->dentry->d_inode->i_mutex);
}
-static int graft_tree(struct vfsmount *mnt, struct path *path)
+static int graft_tree(struct mount *mnt, struct path *path)
{
- if (mnt->mnt_sb->s_flags & MS_NOUSER)
+ if (mnt->mnt.mnt_sb->s_flags & MS_NOUSER)
return -EINVAL;
if (S_ISDIR(path->dentry->d_inode->i_mode) !=
- S_ISDIR(mnt->mnt_root->d_inode->i_mode))
+ S_ISDIR(mnt->mnt.mnt_root->d_inode->i_mode))
return -ENOTDIR;
if (d_unlinked(path->dentry))
@@ -1690,7 +1492,8 @@
*/
static int do_change_type(struct path *path, int flag)
{
- struct vfsmount *m, *mnt = path->mnt;
+ struct mount *m;
+ struct mount *mnt = real_mount(path->mnt);
int recurse = flag & MS_REC;
int type;
int err = 0;
@@ -1730,7 +1533,7 @@
{
LIST_HEAD(umount_list);
struct path old_path;
- struct vfsmount *mnt = NULL;
+ struct mount *mnt = NULL, *old;
int err = mount_is_safe(path);
if (err)
return err;
@@ -1744,18 +1547,20 @@
if (err)
goto out;
+ old = real_mount(old_path.mnt);
+
err = -EINVAL;
- if (IS_MNT_UNBINDABLE(old_path.mnt))
+ if (IS_MNT_UNBINDABLE(old))
goto out2;
- if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
+ if (!check_mnt(real_mount(path->mnt)) || !check_mnt(old))
goto out2;
err = -ENOMEM;
if (recurse)
- mnt = copy_tree(old_path.mnt, old_path.dentry, 0);
+ mnt = copy_tree(old, old_path.dentry, 0);
else
- mnt = clone_mnt(old_path.mnt, old_path.dentry, 0);
+ mnt = clone_mnt(old, old_path.dentry, 0);
if (!mnt)
goto out2;
@@ -1785,9 +1590,9 @@
return 0;
if (readonly_request)
- error = mnt_make_readonly(mnt);
+ error = mnt_make_readonly(real_mount(mnt));
else
- __mnt_unmake_readonly(mnt);
+ __mnt_unmake_readonly(real_mount(mnt));
return error;
}
@@ -1801,11 +1606,12 @@
{
int err;
struct super_block *sb = path->mnt->mnt_sb;
+ struct mount *mnt = real_mount(path->mnt);
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!check_mnt(path->mnt))
+ if (!check_mnt(mnt))
return -EINVAL;
if (path->dentry != path->mnt->mnt_root)
@@ -1822,22 +1628,22 @@
err = do_remount_sb(sb, flags, data, 0);
if (!err) {
br_write_lock(vfsmount_lock);
- mnt_flags |= path->mnt->mnt_flags & MNT_PROPAGATION_MASK;
- path->mnt->mnt_flags = mnt_flags;
+ mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
+ mnt->mnt.mnt_flags = mnt_flags;
br_write_unlock(vfsmount_lock);
}
up_write(&sb->s_umount);
if (!err) {
br_write_lock(vfsmount_lock);
- touch_mnt_namespace(path->mnt->mnt_ns);
+ touch_mnt_namespace(mnt->mnt_ns);
br_write_unlock(vfsmount_lock);
}
return err;
}
-static inline int tree_contains_unbindable(struct vfsmount *mnt)
+static inline int tree_contains_unbindable(struct mount *mnt)
{
- struct vfsmount *p;
+ struct mount *p;
for (p = mnt; p; p = next_mnt(p, mnt)) {
if (IS_MNT_UNBINDABLE(p))
return 1;
@@ -1848,7 +1654,8 @@
static int do_move_mount(struct path *path, char *old_name)
{
struct path old_path, parent_path;
- struct vfsmount *p;
+ struct mount *p;
+ struct mount *old;
int err = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1862,8 +1669,11 @@
if (err < 0)
goto out;
+ old = real_mount(old_path.mnt);
+ p = real_mount(path->mnt);
+
err = -EINVAL;
- if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
+ if (!check_mnt(p) || !check_mnt(old))
goto out1;
if (d_unlinked(path->dentry))
@@ -1873,7 +1683,7 @@
if (old_path.dentry != old_path.mnt->mnt_root)
goto out1;
- if (!mnt_has_parent(old_path.mnt))
+ if (!mnt_has_parent(old))
goto out1;
if (S_ISDIR(path->dentry->d_inode->i_mode) !=
@@ -1882,27 +1692,26 @@
/*
* Don't move a mount residing in a shared parent.
*/
- if (IS_MNT_SHARED(old_path.mnt->mnt_parent))
+ if (IS_MNT_SHARED(old->mnt_parent))
goto out1;
/*
* Don't move a mount tree containing unbindable mounts to a destination
* mount which is shared.
*/
- if (IS_MNT_SHARED(path->mnt) &&
- tree_contains_unbindable(old_path.mnt))
+ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old))
goto out1;
err = -ELOOP;
- for (p = path->mnt; mnt_has_parent(p); p = p->mnt_parent)
- if (p == old_path.mnt)
+ for (; mnt_has_parent(p); p = p->mnt_parent)
+ if (p == old)
goto out1;
- err = attach_recursive_mnt(old_path.mnt, path, &parent_path);
+ err = attach_recursive_mnt(old, path, &parent_path);
if (err)
goto out1;
/* if the mount is moved, it should no longer be expire
* automatically */
- list_del_init(&old_path.mnt->mnt_expire);
+ list_del_init(&old->mnt_expire);
out1:
unlock_mount(path);
out:
@@ -1953,7 +1762,7 @@
/*
* add a mount into a namespace's mount tree
*/
-static int do_add_mount(struct vfsmount *newmnt, struct path *path, int mnt_flags)
+static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
{
int err;
@@ -1964,20 +1773,20 @@
return err;
err = -EINVAL;
- if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
+ if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(real_mount(path->mnt)))
goto unlock;
/* Refuse the same filesystem on the same mount point */
err = -EBUSY;
- if (path->mnt->mnt_sb == newmnt->mnt_sb &&
+ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb &&
path->mnt->mnt_root == path->dentry)
goto unlock;
err = -EINVAL;
- if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode))
+ if (S_ISLNK(newmnt->mnt.mnt_root->d_inode->i_mode))
goto unlock;
- newmnt->mnt_flags = mnt_flags;
+ newmnt->mnt.mnt_flags = mnt_flags;
err = graft_tree(newmnt, path);
unlock:
@@ -2006,7 +1815,7 @@
if (IS_ERR(mnt))
return PTR_ERR(mnt);
- err = do_add_mount(mnt, path, mnt_flags);
+ err = do_add_mount(real_mount(mnt), path, mnt_flags);
if (err)
mntput(mnt);
return err;
@@ -2014,11 +1823,12 @@
int finish_automount(struct vfsmount *m, struct path *path)
{
+ struct mount *mnt = real_mount(m);
int err;
/* The new mount record should have at least 2 refs to prevent it being
* expired before we get a chance to add it
*/
- BUG_ON(mnt_get_count(m) < 2);
+ BUG_ON(mnt_get_count(mnt) < 2);
if (m->mnt_sb == path->mnt->mnt_sb &&
m->mnt_root == path->dentry) {
@@ -2026,15 +1836,15 @@
goto fail;
}
- err = do_add_mount(m, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
+ err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
if (!err)
return 0;
fail:
/* remove m from any expiration list it may be on */
- if (!list_empty(&m->mnt_expire)) {
+ if (!list_empty(&mnt->mnt_expire)) {
down_write(&namespace_sem);
br_write_lock(vfsmount_lock);
- list_del_init(&m->mnt_expire);
+ list_del_init(&mnt->mnt_expire);
br_write_unlock(vfsmount_lock);
up_write(&namespace_sem);
}
@@ -2053,7 +1863,7 @@
down_write(&namespace_sem);
br_write_lock(vfsmount_lock);
- list_add_tail(&mnt->mnt_expire, expiry_list);
+ list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list);
br_write_unlock(vfsmount_lock);
up_write(&namespace_sem);
@@ -2067,7 +1877,7 @@
*/
void mark_mounts_for_expiry(struct list_head *mounts)
{
- struct vfsmount *mnt, *next;
+ struct mount *mnt, *next;
LIST_HEAD(graveyard);
LIST_HEAD(umounts);
@@ -2090,7 +1900,7 @@
list_move(&mnt->mnt_expire, &graveyard);
}
while (!list_empty(&graveyard)) {
- mnt = list_first_entry(&graveyard, struct vfsmount, mnt_expire);
+ mnt = list_first_entry(&graveyard, struct mount, mnt_expire);
touch_mnt_namespace(mnt->mnt_ns);
umount_tree(mnt, 1, &umounts);
}
@@ -2108,9 +1918,9 @@
* search the list of submounts for a given mountpoint, and move any
* shrinkable submounts to the 'graveyard' list.
*/
-static int select_submounts(struct vfsmount *parent, struct list_head *graveyard)
+static int select_submounts(struct mount *parent, struct list_head *graveyard)
{
- struct vfsmount *this_parent = parent;
+ struct mount *this_parent = parent;
struct list_head *next;
int found = 0;
@@ -2119,10 +1929,10 @@
resume:
while (next != &this_parent->mnt_mounts) {
struct list_head *tmp = next;
- struct vfsmount *mnt = list_entry(tmp, struct vfsmount, mnt_child);
+ struct mount *mnt = list_entry(tmp, struct mount, mnt_child);
next = tmp->next;
- if (!(mnt->mnt_flags & MNT_SHRINKABLE))
+ if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE))
continue;
/*
* Descend a level if the d_mounts list is non-empty.
@@ -2154,15 +1964,15 @@
*
* vfsmount_lock must be held for write
*/
-static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts)
+static void shrink_submounts(struct mount *mnt, struct list_head *umounts)
{
LIST_HEAD(graveyard);
- struct vfsmount *m;
+ struct mount *m;
/* extract submounts of 'mountpoint' from the expiration list */
while (select_submounts(mnt, &graveyard)) {
while (!list_empty(&graveyard)) {
- m = list_first_entry(&graveyard, struct vfsmount,
+ m = list_first_entry(&graveyard, struct mount,
mnt_expire);
touch_mnt_namespace(m->mnt_ns);
umount_tree(m, 1, umounts);
@@ -2349,12 +2159,13 @@
void mnt_make_longterm(struct vfsmount *mnt)
{
- __mnt_make_longterm(mnt);
+ __mnt_make_longterm(real_mount(mnt));
}
-void mnt_make_shortterm(struct vfsmount *mnt)
+void mnt_make_shortterm(struct vfsmount *m)
{
#ifdef CONFIG_SMP
+ struct mount *mnt = real_mount(m);
if (atomic_add_unless(&mnt->mnt_longterm, -1, 1))
return;
br_write_lock(vfsmount_lock);
@@ -2372,7 +2183,9 @@
{
struct mnt_namespace *new_ns;
struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
- struct vfsmount *p, *q;
+ struct mount *p, *q;
+ struct mount *old = mnt_ns->root;
+ struct mount *new;
new_ns = alloc_mnt_ns();
if (IS_ERR(new_ns))
@@ -2380,15 +2193,15 @@
down_write(&namespace_sem);
/* First pass: copy the tree topology */
- new_ns->root = copy_tree(mnt_ns->root, mnt_ns->root->mnt_root,
- CL_COPY_ALL | CL_EXPIRE);
- if (!new_ns->root) {
+ new = copy_tree(old, old->mnt.mnt_root, CL_COPY_ALL | CL_EXPIRE);
+ if (!new) {
up_write(&namespace_sem);
kfree(new_ns);
return ERR_PTR(-ENOMEM);
}
+ new_ns->root = new;
br_write_lock(vfsmount_lock);
- list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
+ list_add_tail(&new_ns->list, &new->mnt_list);
br_write_unlock(vfsmount_lock);
/*
@@ -2396,27 +2209,27 @@
* as belonging to new namespace. We have already acquired a private
* fs_struct, so tsk->fs->lock is not needed.
*/
- p = mnt_ns->root;
- q = new_ns->root;
+ p = old;
+ q = new;
while (p) {
q->mnt_ns = new_ns;
__mnt_make_longterm(q);
if (fs) {
- if (p == fs->root.mnt) {
- fs->root.mnt = mntget(q);
+ if (&p->mnt == fs->root.mnt) {
+ fs->root.mnt = mntget(&q->mnt);
__mnt_make_longterm(q);
- mnt_make_shortterm(p);
- rootmnt = p;
+ mnt_make_shortterm(&p->mnt);
+ rootmnt = &p->mnt;
}
- if (p == fs->pwd.mnt) {
- fs->pwd.mnt = mntget(q);
+ if (&p->mnt == fs->pwd.mnt) {
+ fs->pwd.mnt = mntget(&q->mnt);
__mnt_make_longterm(q);
- mnt_make_shortterm(p);
- pwdmnt = p;
+ mnt_make_shortterm(&p->mnt);
+ pwdmnt = &p->mnt;
}
}
- p = next_mnt(p, mnt_ns->root);
- q = next_mnt(q, new_ns->root);
+ p = next_mnt(p, old);
+ q = next_mnt(q, new);
}
up_write(&namespace_sem);
@@ -2449,18 +2262,17 @@
* create_mnt_ns - creates a private namespace and adds a root filesystem
* @mnt: pointer to the new root filesystem mountpoint
*/
-static struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
+static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
{
- struct mnt_namespace *new_ns;
-
- new_ns = alloc_mnt_ns();
+ struct mnt_namespace *new_ns = alloc_mnt_ns();
if (!IS_ERR(new_ns)) {
+ struct mount *mnt = real_mount(m);
mnt->mnt_ns = new_ns;
__mnt_make_longterm(mnt);
new_ns->root = mnt;
- list_add(&new_ns->list, &new_ns->root->mnt_list);
+ list_add(&new_ns->list, &mnt->mnt_list);
} else {
- mntput(mnt);
+ mntput(m);
}
return new_ns;
}
@@ -2541,21 +2353,21 @@
*
* namespace_sem or vfsmount_lock is held
*/
-bool is_path_reachable(struct vfsmount *mnt, struct dentry *dentry,
+bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
const struct path *root)
{
- while (mnt != root->mnt && mnt_has_parent(mnt)) {
+ while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) {
dentry = mnt->mnt_mountpoint;
mnt = mnt->mnt_parent;
}
- return mnt == root->mnt && is_subdir(dentry, root->dentry);
+ return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry);
}
int path_is_under(struct path *path1, struct path *path2)
{
int res;
br_read_lock(vfsmount_lock);
- res = is_path_reachable(path1->mnt, path1->dentry, path2);
+ res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2);
br_read_unlock(vfsmount_lock);
return res;
}
@@ -2590,6 +2402,7 @@
const char __user *, put_old)
{
struct path new, old, parent_path, root_parent, root;
+ struct mount *new_mnt, *root_mnt;
int error;
if (!capable(CAP_SYS_ADMIN))
@@ -2613,11 +2426,13 @@
goto out3;
error = -EINVAL;
- if (IS_MNT_SHARED(old.mnt) ||
- IS_MNT_SHARED(new.mnt->mnt_parent) ||
- IS_MNT_SHARED(root.mnt->mnt_parent))
+ new_mnt = real_mount(new.mnt);
+ root_mnt = real_mount(root.mnt);
+ if (IS_MNT_SHARED(real_mount(old.mnt)) ||
+ IS_MNT_SHARED(new_mnt->mnt_parent) ||
+ IS_MNT_SHARED(root_mnt->mnt_parent))
goto out4;
- if (!check_mnt(root.mnt) || !check_mnt(new.mnt))
+ if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
goto out4;
error = -ENOENT;
if (d_unlinked(new.dentry))
@@ -2631,22 +2446,22 @@
error = -EINVAL;
if (root.mnt->mnt_root != root.dentry)
goto out4; /* not a mountpoint */
- if (!mnt_has_parent(root.mnt))
+ if (!mnt_has_parent(root_mnt))
goto out4; /* not attached */
if (new.mnt->mnt_root != new.dentry)
goto out4; /* not a mountpoint */
- if (!mnt_has_parent(new.mnt))
+ if (!mnt_has_parent(new_mnt))
goto out4; /* not attached */
/* make sure we can reach put_old from new_root */
- if (!is_path_reachable(old.mnt, old.dentry, &new))
+ if (!is_path_reachable(real_mount(old.mnt), old.dentry, &new))
goto out4;
br_write_lock(vfsmount_lock);
- detach_mnt(new.mnt, &parent_path);
- detach_mnt(root.mnt, &root_parent);
+ detach_mnt(new_mnt, &parent_path);
+ detach_mnt(root_mnt, &root_parent);
/* mount old root on put_old */
- attach_mnt(root.mnt, &old);
+ attach_mnt(root_mnt, &old);
/* mount new_root on / */
- attach_mnt(new.mnt, &root_parent);
+ attach_mnt(new_mnt, &root_parent);
touch_mnt_namespace(current->nsproxy->mnt_ns);
br_write_unlock(vfsmount_lock);
chroot_fs_refs(&root, &new);
@@ -2684,8 +2499,8 @@
init_task.nsproxy->mnt_ns = ns;
get_mnt_ns(ns);
- root.mnt = ns->root;
- root.dentry = ns->root->mnt_root;
+ root.mnt = mnt;
+ root.dentry = mnt->mnt_root;
set_fs_pwd(current->fs, &root);
set_fs_root(current->fs, &root);
@@ -2698,7 +2513,7 @@
init_rwsem(&namespace_sem);
- mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount),
+ mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
@@ -2766,5 +2581,5 @@
bool our_mnt(struct vfsmount *mnt)
{
- return check_mnt(mnt);
+ return check_mnt(real_mount(mnt));
}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 9fde1c0..3568c8a 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -16,6 +16,8 @@
#include <asm/ioctls.h>
+#include "../../mount.h"
+
#define FANOTIFY_DEFAULT_MAX_EVENTS 16384
#define FANOTIFY_DEFAULT_MAX_MARKS 8192
#define FANOTIFY_DEFAULT_MAX_LISTENERS 128
@@ -546,7 +548,7 @@
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags);
fsnotify_put_mark(fsn_mark);
- if (removed & mnt->mnt_fsnotify_mask)
+ if (removed & real_mount(mnt)->mnt_fsnotify_mask)
fsnotify_recalc_vfsmount_mask(mnt);
return 0;
@@ -623,7 +625,7 @@
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
- if (added & ~mnt->mnt_fsnotify_mask)
+ if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
fsnotify_recalc_vfsmount_mask(mnt);
err:
fsnotify_put_mark(fsn_mark);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 79b47cb..ccb14d3 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -26,6 +26,7 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
+#include "../mount.h"
/*
* Clear all of the marks on an inode when it is being evicted from core
@@ -205,13 +206,13 @@
struct fsnotify_mark *inode_mark = NULL, *vfsmount_mark = NULL;
struct fsnotify_group *inode_group, *vfsmount_group;
struct fsnotify_event *event = NULL;
- struct vfsmount *mnt;
+ struct mount *mnt;
int idx, ret = 0;
/* global tests shouldn't care about events on child only the specific event */
__u32 test_mask = (mask & ~FS_EVENT_ON_CHILD);
if (data_is == FSNOTIFY_EVENT_PATH)
- mnt = ((struct path *)data)->mnt;
+ mnt = real_mount(((struct path *)data)->mnt);
else
mnt = NULL;
@@ -262,11 +263,11 @@
/* we didn't use the vfsmount_mark */
vfsmount_group = NULL;
} else if (vfsmount_group > inode_group) {
- ret = send_to_group(to_tell, mnt, NULL, vfsmount_mark, mask, data,
+ ret = send_to_group(to_tell, &mnt->mnt, NULL, vfsmount_mark, mask, data,
data_is, cookie, file_name, &event);
inode_group = NULL;
} else {
- ret = send_to_group(to_tell, mnt, inode_mark, vfsmount_mark,
+ ret = send_to_group(to_tell, &mnt->mnt, inode_mark, vfsmount_mark,
mask, data, data_is, cookie, file_name,
&event);
}
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index 778fe6c..b7b4b0e 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -28,15 +28,17 @@
#include <linux/fsnotify_backend.h>
#include "fsnotify.h"
+#include "../mount.h"
void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
{
struct fsnotify_mark *mark, *lmark;
struct hlist_node *pos, *n;
+ struct mount *m = real_mount(mnt);
LIST_HEAD(free_list);
spin_lock(&mnt->mnt_root->d_lock);
- hlist_for_each_entry_safe(mark, pos, n, &mnt->mnt_fsnotify_marks, m.m_list) {
+ hlist_for_each_entry_safe(mark, pos, n, &m->mnt_fsnotify_marks, m.m_list) {
list_add(&mark->m.free_m_list, &free_list);
hlist_del_init_rcu(&mark->m.m_list);
fsnotify_get_mark(mark);
@@ -59,15 +61,16 @@
*/
static void fsnotify_recalc_vfsmount_mask_locked(struct vfsmount *mnt)
{
+ struct mount *m = real_mount(mnt);
struct fsnotify_mark *mark;
struct hlist_node *pos;
__u32 new_mask = 0;
assert_spin_locked(&mnt->mnt_root->d_lock);
- hlist_for_each_entry(mark, pos, &mnt->mnt_fsnotify_marks, m.m_list)
+ hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list)
new_mask |= mark->mask;
- mnt->mnt_fsnotify_mask = new_mask;
+ m->mnt_fsnotify_mask = new_mask;
}
/*
@@ -101,12 +104,13 @@
static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_group *group,
struct vfsmount *mnt)
{
+ struct mount *m = real_mount(mnt);
struct fsnotify_mark *mark;
struct hlist_node *pos;
assert_spin_locked(&mnt->mnt_root->d_lock);
- hlist_for_each_entry(mark, pos, &mnt->mnt_fsnotify_marks, m.m_list) {
+ hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list) {
if (mark->group == group) {
fsnotify_get_mark(mark);
return mark;
@@ -140,6 +144,7 @@
struct fsnotify_group *group, struct vfsmount *mnt,
int allow_dups)
{
+ struct mount *m = real_mount(mnt);
struct fsnotify_mark *lmark;
struct hlist_node *node, *last = NULL;
int ret = 0;
@@ -154,13 +159,13 @@
mark->m.mnt = mnt;
/* is mark the first mark? */
- if (hlist_empty(&mnt->mnt_fsnotify_marks)) {
- hlist_add_head_rcu(&mark->m.m_list, &mnt->mnt_fsnotify_marks);
+ if (hlist_empty(&m->mnt_fsnotify_marks)) {
+ hlist_add_head_rcu(&mark->m.m_list, &m->mnt_fsnotify_marks);
goto out;
}
/* should mark be in the middle of the current list? */
- hlist_for_each_entry(lmark, node, &mnt->mnt_fsnotify_marks, m.m_list) {
+ hlist_for_each_entry(lmark, node, &m->mnt_fsnotify_marks, m.m_list) {
last = node;
if ((lmark->group == group) && !allow_dups) {
diff --git a/fs/pnode.c b/fs/pnode.c
index 4d5a06e..ab5fa9e 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -13,30 +13,30 @@
#include "pnode.h"
/* return the next shared peer mount of @p */
-static inline struct vfsmount *next_peer(struct vfsmount *p)
+static inline struct mount *next_peer(struct mount *p)
{
- return list_entry(p->mnt_share.next, struct vfsmount, mnt_share);
+ return list_entry(p->mnt_share.next, struct mount, mnt_share);
}
-static inline struct vfsmount *first_slave(struct vfsmount *p)
+static inline struct mount *first_slave(struct mount *p)
{
- return list_entry(p->mnt_slave_list.next, struct vfsmount, mnt_slave);
+ return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
}
-static inline struct vfsmount *next_slave(struct vfsmount *p)
+static inline struct mount *next_slave(struct mount *p)
{
- return list_entry(p->mnt_slave.next, struct vfsmount, mnt_slave);
+ return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
}
-static struct vfsmount *get_peer_under_root(struct vfsmount *mnt,
- struct mnt_namespace *ns,
- const struct path *root)
+static struct mount *get_peer_under_root(struct mount *mnt,
+ struct mnt_namespace *ns,
+ const struct path *root)
{
- struct vfsmount *m = mnt;
+ struct mount *m = mnt;
do {
/* Check the namespace first for optimization */
- if (m->mnt_ns == ns && is_path_reachable(m, m->mnt_root, root))
+ if (m->mnt_ns == ns && is_path_reachable(m, m->mnt.mnt_root, root))
return m;
m = next_peer(m);
@@ -51,12 +51,12 @@
*
* Caller must hold namespace_sem
*/
-int get_dominating_id(struct vfsmount *mnt, const struct path *root)
+int get_dominating_id(struct mount *mnt, const struct path *root)
{
- struct vfsmount *m;
+ struct mount *m;
for (m = mnt->mnt_master; m != NULL; m = m->mnt_master) {
- struct vfsmount *d = get_peer_under_root(m, mnt->mnt_ns, root);
+ struct mount *d = get_peer_under_root(m, mnt->mnt_ns, root);
if (d)
return d->mnt_group_id;
}
@@ -64,10 +64,10 @@
return 0;
}
-static int do_make_slave(struct vfsmount *mnt)
+static int do_make_slave(struct mount *mnt)
{
- struct vfsmount *peer_mnt = mnt, *master = mnt->mnt_master;
- struct vfsmount *slave_mnt;
+ struct mount *peer_mnt = mnt, *master = mnt->mnt_master;
+ struct mount *slave_mnt;
/*
* slave 'mnt' to a peer mount that has the
@@ -75,7 +75,7 @@
* slave it to anything that is available.
*/
while ((peer_mnt = next_peer(peer_mnt)) != mnt &&
- peer_mnt->mnt_root != mnt->mnt_root) ;
+ peer_mnt->mnt.mnt_root != mnt->mnt.mnt_root) ;
if (peer_mnt == mnt) {
peer_mnt = next_peer(mnt);
@@ -101,7 +101,7 @@
struct list_head *p = &mnt->mnt_slave_list;
while (!list_empty(p)) {
slave_mnt = list_first_entry(p,
- struct vfsmount, mnt_slave);
+ struct mount, mnt_slave);
list_del_init(&slave_mnt->mnt_slave);
slave_mnt->mnt_master = NULL;
}
@@ -114,7 +114,7 @@
/*
* vfsmount lock must be held for write
*/
-void change_mnt_propagation(struct vfsmount *mnt, int type)
+void change_mnt_propagation(struct mount *mnt, int type)
{
if (type == MS_SHARED) {
set_mnt_shared(mnt);
@@ -125,9 +125,9 @@
list_del_init(&mnt->mnt_slave);
mnt->mnt_master = NULL;
if (type == MS_UNBINDABLE)
- mnt->mnt_flags |= MNT_UNBINDABLE;
+ mnt->mnt.mnt_flags |= MNT_UNBINDABLE;
else
- mnt->mnt_flags &= ~MNT_UNBINDABLE;
+ mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE;
}
}
@@ -141,20 +141,19 @@
* vfsmount found while iterating with propagation_next() is
* a peer of one we'd found earlier.
*/
-static struct vfsmount *propagation_next(struct vfsmount *m,
- struct vfsmount *origin)
+static struct mount *propagation_next(struct mount *m,
+ struct mount *origin)
{
/* are there any slaves of this mount? */
if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
return first_slave(m);
while (1) {
- struct vfsmount *next;
- struct vfsmount *master = m->mnt_master;
+ struct mount *master = m->mnt_master;
if (master == origin->mnt_master) {
- next = next_peer(m);
- return ((next == origin) ? NULL : next);
+ struct mount *next = next_peer(m);
+ return (next == origin) ? NULL : next;
} else if (m->mnt_slave.next != &master->mnt_slave_list)
return next_slave(m);
@@ -172,13 +171,13 @@
* @type return CL_SLAVE if the new mount has to be
* cloned as a slave.
*/
-static struct vfsmount *get_source(struct vfsmount *dest,
- struct vfsmount *last_dest,
- struct vfsmount *last_src,
- int *type)
+static struct mount *get_source(struct mount *dest,
+ struct mount *last_dest,
+ struct mount *last_src,
+ int *type)
{
- struct vfsmount *p_last_src = NULL;
- struct vfsmount *p_last_dest = NULL;
+ struct mount *p_last_src = NULL;
+ struct mount *p_last_dest = NULL;
while (last_dest != dest->mnt_master) {
p_last_dest = last_dest;
@@ -218,33 +217,33 @@
* @source_mnt: source mount.
* @tree_list : list of heads of trees to be attached.
*/
-int propagate_mnt(struct vfsmount *dest_mnt, struct dentry *dest_dentry,
- struct vfsmount *source_mnt, struct list_head *tree_list)
+int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry,
+ struct mount *source_mnt, struct list_head *tree_list)
{
- struct vfsmount *m, *child;
+ struct mount *m, *child;
int ret = 0;
- struct vfsmount *prev_dest_mnt = dest_mnt;
- struct vfsmount *prev_src_mnt = source_mnt;
+ struct mount *prev_dest_mnt = dest_mnt;
+ struct mount *prev_src_mnt = source_mnt;
LIST_HEAD(tmp_list);
LIST_HEAD(umount_list);
for (m = propagation_next(dest_mnt, dest_mnt); m;
m = propagation_next(m, dest_mnt)) {
int type;
- struct vfsmount *source;
+ struct mount *source;
if (IS_MNT_NEW(m))
continue;
source = get_source(m, prev_dest_mnt, prev_src_mnt, &type);
- if (!(child = copy_tree(source, source->mnt_root, type))) {
+ if (!(child = copy_tree(source, source->mnt.mnt_root, type))) {
ret = -ENOMEM;
list_splice(tree_list, tmp_list.prev);
goto out;
}
- if (is_subdir(dest_dentry, m->mnt_root)) {
+ if (is_subdir(dest_dentry, m->mnt.mnt_root)) {
mnt_set_mountpoint(m, dest_dentry, child);
list_add_tail(&child->mnt_hash, tree_list);
} else {
@@ -260,7 +259,7 @@
out:
br_write_lock(vfsmount_lock);
while (!list_empty(&tmp_list)) {
- child = list_first_entry(&tmp_list, struct vfsmount, mnt_hash);
+ child = list_first_entry(&tmp_list, struct mount, mnt_hash);
umount_tree(child, 0, &umount_list);
}
br_write_unlock(vfsmount_lock);
@@ -271,7 +270,7 @@
/*
* return true if the refcount is greater than count
*/
-static inline int do_refcount_check(struct vfsmount *mnt, int count)
+static inline int do_refcount_check(struct mount *mnt, int count)
{
int mycount = mnt_get_count(mnt) - mnt->mnt_ghosts;
return (mycount > count);
@@ -287,10 +286,10 @@
*
* vfsmount lock must be held for write
*/
-int propagate_mount_busy(struct vfsmount *mnt, int refcnt)
+int propagate_mount_busy(struct mount *mnt, int refcnt)
{
- struct vfsmount *m, *child;
- struct vfsmount *parent = mnt->mnt_parent;
+ struct mount *m, *child;
+ struct mount *parent = mnt->mnt_parent;
int ret = 0;
if (mnt == parent)
@@ -306,7 +305,7 @@
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
- child = __lookup_mnt(m, mnt->mnt_mountpoint, 0);
+ child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint, 0);
if (child && list_empty(&child->mnt_mounts) &&
(ret = do_refcount_check(child, 1)))
break;
@@ -318,17 +317,17 @@
* NOTE: unmounting 'mnt' naturally propagates to all other mounts its
* parent propagates to.
*/
-static void __propagate_umount(struct vfsmount *mnt)
+static void __propagate_umount(struct mount *mnt)
{
- struct vfsmount *parent = mnt->mnt_parent;
- struct vfsmount *m;
+ struct mount *parent = mnt->mnt_parent;
+ struct mount *m;
BUG_ON(parent == mnt);
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
- struct vfsmount *child = __lookup_mnt(m,
+ struct mount *child = __lookup_mnt(&m->mnt,
mnt->mnt_mountpoint, 0);
/*
* umount the child only if the child has no
@@ -348,7 +347,7 @@
*/
int propagate_umount(struct list_head *list)
{
- struct vfsmount *mnt;
+ struct mount *mnt;
list_for_each_entry(mnt, list, mnt_hash)
__propagate_umount(mnt);
diff --git a/fs/pnode.h b/fs/pnode.h
index 5c234e7..65c6097 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -11,11 +11,11 @@
#include <linux/list.h>
#include "mount.h"
-#define IS_MNT_SHARED(mnt) ((mnt)->mnt_flags & MNT_SHARED)
-#define IS_MNT_SLAVE(mnt) ((mnt)->mnt_master)
-#define IS_MNT_NEW(mnt) (!(mnt)->mnt_ns)
-#define CLEAR_MNT_SHARED(mnt) ((mnt)->mnt_flags &= ~MNT_SHARED)
-#define IS_MNT_UNBINDABLE(mnt) ((mnt)->mnt_flags & MNT_UNBINDABLE)
+#define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
+#define IS_MNT_SLAVE(m) ((m)->mnt_master)
+#define IS_MNT_NEW(m) (!(m)->mnt_ns)
+#define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
+#define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
#define CL_EXPIRE 0x01
#define CL_SLAVE 0x02
@@ -23,25 +23,25 @@
#define CL_MAKE_SHARED 0x08
#define CL_PRIVATE 0x10
-static inline void set_mnt_shared(struct vfsmount *mnt)
+static inline void set_mnt_shared(struct mount *mnt)
{
- mnt->mnt_flags &= ~MNT_SHARED_MASK;
- mnt->mnt_flags |= MNT_SHARED;
+ mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
+ mnt->mnt.mnt_flags |= MNT_SHARED;
}
-void change_mnt_propagation(struct vfsmount *, int);
-int propagate_mnt(struct vfsmount *, struct dentry *, struct vfsmount *,
+void change_mnt_propagation(struct mount *, int);
+int propagate_mnt(struct mount *, struct dentry *, struct mount *,
struct list_head *);
int propagate_umount(struct list_head *);
-int propagate_mount_busy(struct vfsmount *, int);
-void mnt_release_group_id(struct vfsmount *);
-int get_dominating_id(struct vfsmount *mnt, const struct path *root);
-unsigned int mnt_get_count(struct vfsmount *mnt);
-void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
- struct vfsmount *);
+int propagate_mount_busy(struct mount *, int);
+void mnt_release_group_id(struct mount *);
+int get_dominating_id(struct mount *mnt, const struct path *root);
+unsigned int mnt_get_count(struct mount *mnt);
+void mnt_set_mountpoint(struct mount *, struct dentry *,
+ struct mount *);
void release_mounts(struct list_head *);
-void umount_tree(struct vfsmount *, int, struct list_head *);
-struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
-bool is_path_reachable(struct vfsmount *, struct dentry *,
+void umount_tree(struct mount *, int, struct list_head *);
+struct mount *copy_tree(struct mount *, struct dentry *, int);
+bool is_path_reachable(struct mount *, struct dentry *,
const struct path *root);
#endif /* _LINUX_PNODE_H */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 65054d3..a1dddda 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -631,120 +631,6 @@
.setattr = proc_setattr,
};
-static int mounts_open_common(struct inode *inode, struct file *file,
- const struct seq_operations *op)
-{
- struct task_struct *task = get_proc_task(inode);
- struct nsproxy *nsp;
- struct mnt_namespace *ns = NULL;
- struct path root;
- struct proc_mounts *p;
- int ret = -EINVAL;
-
- if (task) {
- rcu_read_lock();
- nsp = task_nsproxy(task);
- if (nsp) {
- ns = nsp->mnt_ns;
- if (ns)
- get_mnt_ns(ns);
- }
- rcu_read_unlock();
- if (ns && get_task_root(task, &root) == 0)
- ret = 0;
- put_task_struct(task);
- }
-
- if (!ns)
- goto err;
- if (ret)
- goto err_put_ns;
-
- ret = -ENOMEM;
- p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
- if (!p)
- goto err_put_path;
-
- file->private_data = &p->m;
- ret = seq_open(file, op);
- if (ret)
- goto err_free;
-
- p->m.private = p;
- p->ns = ns;
- p->root = root;
- p->m.poll_event = ns->event;
-
- return 0;
-
- err_free:
- kfree(p);
- err_put_path:
- path_put(&root);
- err_put_ns:
- put_mnt_ns(ns);
- err:
- return ret;
-}
-
-static int mounts_release(struct inode *inode, struct file *file)
-{
- struct proc_mounts *p = file->private_data;
- path_put(&p->root);
- put_mnt_ns(p->ns);
- return seq_release(inode, file);
-}
-
-static unsigned mounts_poll(struct file *file, poll_table *wait)
-{
- struct proc_mounts *p = file->private_data;
- unsigned res = POLLIN | POLLRDNORM;
-
- poll_wait(file, &p->ns->poll, wait);
- if (mnt_had_events(p))
- res |= POLLERR | POLLPRI;
-
- return res;
-}
-
-static int mounts_open(struct inode *inode, struct file *file)
-{
- return mounts_open_common(inode, file, &mounts_op);
-}
-
-static const struct file_operations proc_mounts_operations = {
- .open = mounts_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = mounts_release,
- .poll = mounts_poll,
-};
-
-static int mountinfo_open(struct inode *inode, struct file *file)
-{
- return mounts_open_common(inode, file, &mountinfo_op);
-}
-
-static const struct file_operations proc_mountinfo_operations = {
- .open = mountinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = mounts_release,
- .poll = mounts_poll,
-};
-
-static int mountstats_open(struct inode *inode, struct file *file)
-{
- return mounts_open_common(inode, file, &mountstats_op);
-}
-
-static const struct file_operations proc_mountstats_operations = {
- .open = mountstats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = mounts_release,
-};
-
#define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */
static ssize_t proc_info_read(struct file * file, char __user * buf,
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index be177f7..27da860 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -9,7 +9,6 @@
#include <linux/file.h>
#include <linux/utsname.h>
#include <net/net_namespace.h>
-#include <linux/mnt_namespace.h>
#include <linux/ipc_namespace.h>
#include <linux/pid_namespace.h>
#include "internal.h"
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
new file mode 100644
index 0000000..9dcd954
--- /dev/null
+++ b/fs/proc_namespace.c
@@ -0,0 +1,331 @@
+/*
+ * fs/proc_namespace.c - handling of /proc/<pid>/{mounts,mountinfo,mountstats}
+ *
+ * In fact, that's a piece of procfs; it's *almost* isolated from
+ * the rest of fs/proc, but has rather close relationships with
+ * fs/namespace.c, thus here instead of fs/proc
+ *
+ */
+#include <linux/mnt_namespace.h>
+#include <linux/nsproxy.h>
+#include <linux/security.h>
+#include <linux/fs_struct.h>
+#include "proc/internal.h" /* only for get_proc_task() in ->open() */
+
+#include "pnode.h"
+#include "internal.h"
+
+static unsigned mounts_poll(struct file *file, poll_table *wait)
+{
+ struct proc_mounts *p = file->private_data;
+ struct mnt_namespace *ns = p->ns;
+ unsigned res = POLLIN | POLLRDNORM;
+
+ poll_wait(file, &p->ns->poll, wait);
+
+ br_read_lock(vfsmount_lock);
+ if (p->m.poll_event != ns->event) {
+ p->m.poll_event = ns->event;
+ res |= POLLERR | POLLPRI;
+ }
+ br_read_unlock(vfsmount_lock);
+
+ return res;
+}
+
+struct proc_fs_info {
+ int flag;
+ const char *str;
+};
+
+static int show_sb_opts(struct seq_file *m, struct super_block *sb)
+{
+ static const struct proc_fs_info fs_info[] = {
+ { MS_SYNCHRONOUS, ",sync" },
+ { MS_DIRSYNC, ",dirsync" },
+ { MS_MANDLOCK, ",mand" },
+ { 0, NULL }
+ };
+ const struct proc_fs_info *fs_infop;
+
+ for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
+ if (sb->s_flags & fs_infop->flag)
+ seq_puts(m, fs_infop->str);
+ }
+
+ return security_sb_show_options(m, sb);
+}
+
+static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
+{
+ static const struct proc_fs_info mnt_info[] = {
+ { MNT_NOSUID, ",nosuid" },
+ { MNT_NODEV, ",nodev" },
+ { MNT_NOEXEC, ",noexec" },
+ { MNT_NOATIME, ",noatime" },
+ { MNT_NODIRATIME, ",nodiratime" },
+ { MNT_RELATIME, ",relatime" },
+ { 0, NULL }
+ };
+ const struct proc_fs_info *fs_infop;
+
+ for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
+ if (mnt->mnt_flags & fs_infop->flag)
+ seq_puts(m, fs_infop->str);
+ }
+}
+
+static inline void mangle(struct seq_file *m, const char *s)
+{
+ seq_escape(m, s, " \t\n\\");
+}
+
+static void show_type(struct seq_file *m, struct super_block *sb)
+{
+ mangle(m, sb->s_type->name);
+ if (sb->s_subtype && sb->s_subtype[0]) {
+ seq_putc(m, '.');
+ mangle(m, sb->s_subtype);
+ }
+}
+
+static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
+{
+ struct mount *r = real_mount(mnt);
+ int err = 0;
+ struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
+
+ if (mnt->mnt_sb->s_op->show_devname) {
+ err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+ if (err)
+ goto out;
+ } else {
+ mangle(m, r->mnt_devname ? r->mnt_devname : "none");
+ }
+ seq_putc(m, ' ');
+ seq_path(m, &mnt_path, " \t\n\\");
+ seq_putc(m, ' ');
+ show_type(m, mnt->mnt_sb);
+ seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
+ err = show_sb_opts(m, mnt->mnt_sb);
+ if (err)
+ goto out;
+ show_mnt_opts(m, mnt);
+ if (mnt->mnt_sb->s_op->show_options)
+ err = mnt->mnt_sb->s_op->show_options(m, mnt);
+ seq_puts(m, " 0 0\n");
+out:
+ return err;
+}
+
+static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
+{
+ struct proc_mounts *p = m->private;
+ struct mount *r = real_mount(mnt);
+ struct super_block *sb = mnt->mnt_sb;
+ struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
+ struct path root = p->root;
+ int err = 0;
+
+ seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
+ MAJOR(sb->s_dev), MINOR(sb->s_dev));
+ if (sb->s_op->show_path)
+ err = sb->s_op->show_path(m, mnt);
+ else
+ seq_dentry(m, mnt->mnt_root, " \t\n\\");
+ if (err)
+ goto out;
+ seq_putc(m, ' ');
+
+ /* mountpoints outside of chroot jail will give SEQ_SKIP on this */
+ err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
+ if (err)
+ goto out;
+
+ seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
+ show_mnt_opts(m, mnt);
+
+ /* Tagged fields ("foo:X" or "bar") */
+ if (IS_MNT_SHARED(r))
+ seq_printf(m, " shared:%i", r->mnt_group_id);
+ if (IS_MNT_SLAVE(r)) {
+ int master = r->mnt_master->mnt_group_id;
+ int dom = get_dominating_id(r, &p->root);
+ seq_printf(m, " master:%i", master);
+ if (dom && dom != master)
+ seq_printf(m, " propagate_from:%i", dom);
+ }
+ if (IS_MNT_UNBINDABLE(r))
+ seq_puts(m, " unbindable");
+
+ /* Filesystem specific data */
+ seq_puts(m, " - ");
+ show_type(m, sb);
+ seq_putc(m, ' ');
+ if (sb->s_op->show_devname)
+ err = sb->s_op->show_devname(m, mnt);
+ else
+ mangle(m, r->mnt_devname ? r->mnt_devname : "none");
+ if (err)
+ goto out;
+ seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
+ err = show_sb_opts(m, sb);
+ if (err)
+ goto out;
+ if (sb->s_op->show_options)
+ err = sb->s_op->show_options(m, mnt);
+ seq_putc(m, '\n');
+out:
+ return err;
+}
+
+static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
+{
+ struct mount *r = real_mount(mnt);
+ struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
+ int err = 0;
+
+ /* device */
+ if (mnt->mnt_sb->s_op->show_devname) {
+ seq_puts(m, "device ");
+ err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+ } else {
+ if (r->mnt_devname) {
+ seq_puts(m, "device ");
+ mangle(m, r->mnt_devname);
+ } else
+ seq_puts(m, "no device");
+ }
+
+ /* mount point */
+ seq_puts(m, " mounted on ");
+ seq_path(m, &mnt_path, " \t\n\\");
+ seq_putc(m, ' ');
+
+ /* file system type */
+ seq_puts(m, "with fstype ");
+ show_type(m, mnt->mnt_sb);
+
+ /* optional statistics */
+ if (mnt->mnt_sb->s_op->show_stats) {
+ seq_putc(m, ' ');
+ if (!err)
+ err = mnt->mnt_sb->s_op->show_stats(m, mnt);
+ }
+
+ seq_putc(m, '\n');
+ return err;
+}
+
+static int mounts_open_common(struct inode *inode, struct file *file,
+ int (*show)(struct seq_file *, struct vfsmount *))
+{
+ struct task_struct *task = get_proc_task(inode);
+ struct nsproxy *nsp;
+ struct mnt_namespace *ns = NULL;
+ struct path root;
+ struct proc_mounts *p;
+ int ret = -EINVAL;
+
+ if (!task)
+ goto err;
+
+ rcu_read_lock();
+ nsp = task_nsproxy(task);
+ if (!nsp) {
+ rcu_read_unlock();
+ put_task_struct(task);
+ goto err;
+ }
+ ns = nsp->mnt_ns;
+ if (!ns) {
+ rcu_read_unlock();
+ put_task_struct(task);
+ goto err;
+ }
+ get_mnt_ns(ns);
+ rcu_read_unlock();
+ task_lock(task);
+ if (!task->fs) {
+ task_unlock(task);
+ put_task_struct(task);
+ ret = -ENOENT;
+ goto err_put_ns;
+ }
+ get_fs_root(task->fs, &root);
+ task_unlock(task);
+ put_task_struct(task);
+
+ ret = -ENOMEM;
+ p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
+ if (!p)
+ goto err_put_path;
+
+ file->private_data = &p->m;
+ ret = seq_open(file, &mounts_op);
+ if (ret)
+ goto err_free;
+
+ p->m.private = p;
+ p->ns = ns;
+ p->root = root;
+ p->m.poll_event = ns->event;
+ p->show = show;
+
+ return 0;
+
+ err_free:
+ kfree(p);
+ err_put_path:
+ path_put(&root);
+ err_put_ns:
+ put_mnt_ns(ns);
+ err:
+ return ret;
+}
+
+static int mounts_release(struct inode *inode, struct file *file)
+{
+ struct proc_mounts *p = file->private_data;
+ path_put(&p->root);
+ put_mnt_ns(p->ns);
+ return seq_release(inode, file);
+}
+
+static int mounts_open(struct inode *inode, struct file *file)
+{
+ return mounts_open_common(inode, file, show_vfsmnt);
+}
+
+static int mountinfo_open(struct inode *inode, struct file *file)
+{
+ return mounts_open_common(inode, file, show_mountinfo);
+}
+
+static int mountstats_open(struct inode *inode, struct file *file)
+{
+ return mounts_open_common(inode, file, show_vfsstat);
+}
+
+const struct file_operations proc_mounts_operations = {
+ .open = mounts_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = mounts_release,
+ .poll = mounts_poll,
+};
+
+const struct file_operations proc_mountinfo_operations = {
+ .open = mountinfo_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = mounts_release,
+ .poll = mounts_poll,
+};
+
+const struct file_operations proc_mountstats_operations = {
+ .open = mountstats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = mounts_release,
+};
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 5b572c8..5d81e92 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -73,7 +73,6 @@
#include <linux/security.h>
#include <linux/kmod.h>
#include <linux/namei.h>
-#include <linux/buffer_head.h>
#include <linux/capability.h>
#include <linux/quotaops.h>
#include "../internal.h" /* ugh */
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 35f4b0e..7898cd6 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -13,7 +13,6 @@
#include <linux/kernel.h>
#include <linux/security.h>
#include <linux/syscalls.h>
-#include <linux/buffer_head.h>
#include <linux/capability.h>
#include <linux/quotaops.h>
#include <linux/types.h>
diff --git a/fs/splice.c b/fs/splice.c
index fa2defa..1ec0493 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -25,7 +25,6 @@
#include <linux/mm_inline.h>
#include <linux/swap.h>
#include <linux/writeback.h>
-#include <linux/buffer_head.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/uio.h>
diff --git a/fs/sync.c b/fs/sync.c
index 101b8ef..f3501ef 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -14,7 +14,6 @@
#include <linux/linkage.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
-#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include "internal.h"
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f0e57b7..659be7d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2092,6 +2092,7 @@
extern void bdput(struct block_device *);
extern void invalidate_bdev(struct block_device *);
extern int sync_blockdev(struct block_device *bdev);
+extern void kill_bdev(struct block_device *);
extern struct super_block *freeze_bdev(struct block_device *);
extern void emergency_thaw_all(void);
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
@@ -2099,6 +2100,7 @@
#else
static inline void bd_forget(struct inode *inode) {}
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline void kill_bdev(struct block_device *bdev) {}
static inline void invalidate_bdev(struct block_device *bdev) {}
static inline struct super_block *freeze_bdev(struct block_device *sb)
@@ -2415,6 +2417,7 @@
unsigned long nr_segs, loff_t pos);
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
int datasync);
+extern void block_sync_page(struct page *page);
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index e87ec01..5a8e390 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -2,38 +2,16 @@
#define _NAMESPACE_H_
#ifdef __KERNEL__
-#include <linux/path.h>
-#include <linux/seq_file.h>
-#include <linux/wait.h>
-
-struct mnt_namespace {
- atomic_t count;
- struct vfsmount * root;
- struct list_head list;
- wait_queue_head_t poll;
- int event;
-};
-
-struct proc_mounts {
- struct seq_file m; /* must be the first element */
- struct mnt_namespace *ns;
- struct path root;
-};
-
+struct mnt_namespace;
struct fs_struct;
extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
struct fs_struct *);
extern void put_mnt_ns(struct mnt_namespace *ns);
-static inline void get_mnt_ns(struct mnt_namespace *ns)
-{
- atomic_inc(&ns->count);
-}
-extern const struct seq_operations mounts_op;
-extern const struct seq_operations mountinfo_op;
-extern const struct seq_operations mountstats_op;
-extern int mnt_had_events(struct proc_mounts *);
+extern const struct file_operations proc_mounts_operations;
+extern const struct file_operations proc_mountinfo_operations;
+extern const struct file_operations proc_mountstats_operations;
#endif
#endif
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 00f5c4f..d7029f4 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -47,45 +47,10 @@
#define MNT_INTERNAL 0x4000
-struct mnt_pcp {
- int mnt_count;
- int mnt_writers;
-};
-
struct vfsmount {
- struct list_head mnt_hash;
- struct vfsmount *mnt_parent; /* fs we are mounted on */
- struct dentry *mnt_mountpoint; /* dentry of mountpoint */
struct dentry *mnt_root; /* root of the mounted tree */
struct super_block *mnt_sb; /* pointer to superblock */
-#ifdef CONFIG_SMP
- struct mnt_pcp __percpu *mnt_pcp;
- atomic_t mnt_longterm; /* how many of the refs are longterm */
-#else
- int mnt_count;
- int mnt_writers;
-#endif
- struct list_head mnt_mounts; /* list of children, anchored here */
- struct list_head mnt_child; /* and going through their mnt_child */
int mnt_flags;
- /* 4 bytes hole on 64bits arches without fsnotify */
-#ifdef CONFIG_FSNOTIFY
- __u32 mnt_fsnotify_mask;
- struct hlist_head mnt_fsnotify_marks;
-#endif
- const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */
- struct list_head mnt_list;
- struct list_head mnt_expire; /* link in fs-specific expiry list */
- struct list_head mnt_share; /* circular list of shared mounts */
- struct list_head mnt_slave_list;/* list of slave mounts */
- struct list_head mnt_slave; /* slave list entry */
- struct vfsmount *mnt_master; /* slave is on master->mnt_slave_list */
- struct mnt_namespace *mnt_ns; /* containing namespace */
- int mnt_id; /* mount identifier */
- int mnt_group_id; /* peer group identifier */
- int mnt_expiry_mark; /* true if marked for expiry */
- int mnt_pinned;
- int mnt_ghosts;
};
struct file; /* forward dec */
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 11a594c..3739ecc 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -18,7 +18,6 @@
#include <linux/bitops.h>
#include <linux/genhd.h>
#include <linux/device.h>
-#include <linux/buffer_head.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 50f0824..8616ef3 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -32,7 +32,7 @@
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
-#include <linux/buffer_head.h>
+#include <linux/buffer_head.h> /* __set_page_dirty_buffers */
#include <linux/pagevec.h>
#include <trace/events/writeback.h>
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 78cc4d1..ea6b32d 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -13,7 +13,6 @@
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
-#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/migrate.h>
diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c
index 2cb5db5..80a09c3 100644
--- a/security/tomoyo/realpath.c
+++ b/security/tomoyo/realpath.c
@@ -5,6 +5,7 @@
*/
#include "common.h"
+#include <linux/magic.h>
/**
* tomoyo_encode2 - Encode binary string to ascii string.