aboutsummaryrefslogtreecommitdiff
path: root/drivers/iio/proximity/as3935.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iio/proximity/as3935.c')
-rw-r--r--drivers/iio/proximity/as3935.c456
1 files changed, 456 insertions, 0 deletions
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
new file mode 100644
index 00000000000..bf677bfe8eb
--- /dev/null
+++ b/drivers/iio/proximity/as3935.c
@@ -0,0 +1,456 @@
+/*
+ * as3935.c - Support for AS3935 Franklin lightning sensor
+ *
+ * Copyright (C) 2014 Matt Ranostay <mranostay@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/gpio.h>
+#include <linux/spi/spi.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/triggered_buffer.h>
+#include <linux/of_gpio.h>
+
+
+#define AS3935_AFE_GAIN 0x00
+#define AS3935_AFE_MASK 0x3F
+#define AS3935_AFE_GAIN_MAX 0x1F
+#define AS3935_AFE_PWR_BIT BIT(0)
+
+#define AS3935_INT 0x03
+#define AS3935_INT_MASK 0x07
+#define AS3935_EVENT_INT BIT(3)
+#define AS3935_NOISE_INT BIT(1)
+
+#define AS3935_DATA 0x07
+#define AS3935_DATA_MASK 0x3F
+
+#define AS3935_TUNE_CAP 0x08
+#define AS3935_CALIBRATE 0x3D
+
+#define AS3935_WRITE_DATA BIT(15)
+#define AS3935_READ_DATA BIT(14)
+#define AS3935_ADDRESS(x) ((x) << 8)
+
+#define MAX_PF_CAP 120
+#define TUNE_CAP_DIV 8
+
+struct as3935_state {
+ struct spi_device *spi;
+ struct iio_trigger *trig;
+ struct mutex lock;
+ struct delayed_work work;
+
+ u32 tune_cap;
+ u8 buf[2] ____cacheline_aligned;
+};
+
+static const struct iio_chan_spec as3935_channels[] = {
+ {
+ .type = IIO_PROXIMITY,
+ .info_mask_separate =
+ BIT(IIO_CHAN_INFO_RAW) |
+ BIT(IIO_CHAN_INFO_PROCESSED),
+ .scan_index = 0,
+ .scan_type = {
+ .sign = 'u',
+ .realbits = 6,
+ .storagebits = 8,
+ },
+ },
+ IIO_CHAN_SOFT_TIMESTAMP(1),
+};
+
+static int as3935_read(struct as3935_state *st, unsigned int reg, int *val)
+{
+ u8 cmd;
+ int ret;
+
+ cmd = (AS3935_READ_DATA | AS3935_ADDRESS(reg)) >> 8;
+ ret = spi_w8r8(st->spi, cmd);
+ if (ret < 0)
+ return ret;
+ *val = ret;
+
+ return 0;
+};
+
+static int as3935_write(struct as3935_state *st,
+ unsigned int reg,
+ unsigned int val)
+{
+ u8 *buf = st->buf;
+
+ buf[0] = (AS3935_WRITE_DATA | AS3935_ADDRESS(reg)) >> 8;
+ buf[1] = val;
+
+ return spi_write(st->spi, buf, 2);
+};
+
+static ssize_t as3935_sensor_sensitivity_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct as3935_state *st = iio_priv(dev_to_iio_dev(dev));
+ int val, ret;
+
+ ret = as3935_read(st, AS3935_AFE_GAIN, &val);
+ if (ret)
+ return ret;
+ val = (val & AS3935_AFE_MASK) >> 1;
+
+ return sprintf(buf, "%d\n", val);
+};
+
+static ssize_t as3935_sensor_sensitivity_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct as3935_state *st = iio_priv(dev_to_iio_dev(dev));
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul((const char *) buf, 10, &val);
+ if (ret)
+ return -EINVAL;
+
+ if (val > AS3935_AFE_GAIN_MAX)
+ return -EINVAL;
+
+ as3935_write(st, AS3935_AFE_GAIN, val << 1);
+
+ return len;
+};
+
+static IIO_DEVICE_ATTR(sensor_sensitivity, S_IRUGO | S_IWUSR,
+ as3935_sensor_sensitivity_show, as3935_sensor_sensitivity_store, 0);
+
+
+static struct attribute *as3935_attributes[] = {
+ &iio_dev_attr_sensor_sensitivity.dev_attr.attr,
+ NULL,
+};
+
+static struct attribute_group as3935_attribute_group = {
+ .attrs = as3935_attributes,
+};
+
+static int as3935_read_raw(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan,
+ int *val,
+ int *val2,
+ long m)
+{
+ struct as3935_state *st = iio_priv(indio_dev);
+ int ret;
+
+
+ switch (m) {
+ case IIO_CHAN_INFO_PROCESSED:
+ case IIO_CHAN_INFO_RAW:
+ *val2 = 0;
+ ret = as3935_read(st, AS3935_DATA, val);
+ if (ret)
+ return ret;
+
+ if (m == IIO_CHAN_INFO_RAW)
+ return IIO_VAL_INT;
+
+ /* storm out of range */
+ if (*val == AS3935_DATA_MASK)
+ return -EINVAL;
+ *val *= 1000;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return IIO_VAL_INT;
+}
+
+static const struct iio_info as3935_info = {
+ .driver_module = THIS_MODULE,
+ .attrs = &as3935_attribute_group,
+ .read_raw = &as3935_read_raw,
+};
+
+static irqreturn_t as3935_trigger_handler(int irq, void *private)
+{
+ struct iio_poll_func *pf = private;
+ struct iio_dev *indio_dev = pf->indio_dev;
+ struct as3935_state *st = iio_priv(indio_dev);
+ int val, ret;
+
+ ret = as3935_read(st, AS3935_DATA, &val);
+ if (ret)
+ goto err_read;
+ val &= AS3935_DATA_MASK;
+ val *= 1000;
+
+ iio_push_to_buffers_with_timestamp(indio_dev, &val, pf->timestamp);
+err_read:
+ iio_trigger_notify_done(indio_dev->trig);
+
+ return IRQ_HANDLED;
+};
+
+static const struct iio_trigger_ops iio_interrupt_trigger_ops = {
+ .owner = THIS_MODULE,
+};
+
+static void as3935_event_work(struct work_struct *work)
+{
+ struct as3935_state *st;
+ int val;
+
+ st = container_of(work, struct as3935_state, work.work);
+
+ as3935_read(st, AS3935_INT, &val);
+ val &= AS3935_INT_MASK;
+
+ switch (val) {
+ case AS3935_EVENT_INT:
+ iio_trigger_poll(st->trig, iio_get_time_ns());
+ break;
+ case AS3935_NOISE_INT:
+ dev_warn(&st->spi->dev, "noise level is too high");
+ break;
+ }
+};
+
+static irqreturn_t as3935_interrupt_handler(int irq, void *private)
+{
+ struct iio_dev *indio_dev = private;
+ struct as3935_state *st = iio_priv(indio_dev);
+
+ /*
+ * Delay work for >2 milliseconds after an interrupt to allow
+ * estimated distance to recalculated.
+ */
+
+ schedule_delayed_work(&st->work, msecs_to_jiffies(3));
+
+ return IRQ_HANDLED;
+}
+
+static void calibrate_as3935(struct as3935_state *st)
+{
+ mutex_lock(&st->lock);
+
+ /* mask disturber interrupt bit */
+ as3935_write(st, AS3935_INT, BIT(5));
+
+ as3935_write(st, AS3935_CALIBRATE, 0x96);
+ as3935_write(st, AS3935_TUNE_CAP,
+ BIT(5) | (st->tune_cap / TUNE_CAP_DIV));
+
+ mdelay(2);
+ as3935_write(st, AS3935_TUNE_CAP, (st->tune_cap / TUNE_CAP_DIV));
+
+ mutex_unlock(&st->lock);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int as3935_suspend(struct spi_device *spi, pm_message_t msg)
+{
+ struct iio_dev *indio_dev = spi_get_drvdata(spi);
+ struct as3935_state *st = iio_priv(indio_dev);
+ int val, ret;
+
+ mutex_lock(&st->lock);
+ ret = as3935_read(st, AS3935_AFE_GAIN, &val);
+ if (ret)
+ goto err_suspend;
+ val |= AS3935_AFE_PWR_BIT;
+
+ ret = as3935_write(st, AS3935_AFE_GAIN, val);
+
+err_suspend:
+ mutex_unlock(&st->lock);
+
+ return ret;
+}
+
+static int as3935_resume(struct spi_device *spi)
+{
+ struct iio_dev *indio_dev = spi_get_drvdata(spi);
+ struct as3935_state *st = iio_priv(indio_dev);
+ int val, ret;
+
+ mutex_lock(&st->lock);
+ ret = as3935_read(st, AS3935_AFE_GAIN, &val);
+ if (ret)
+ goto err_resume;
+ val &= ~AS3935_AFE_PWR_BIT;
+ ret = as3935_write(st, AS3935_AFE_GAIN, val);
+
+err_resume:
+ mutex_unlock(&st->lock);
+
+ return ret;
+}
+#else
+#define as3935_suspend NULL
+#define as3935_resume NULL
+#endif
+
+static int as3935_probe(struct spi_device *spi)
+{
+ struct iio_dev *indio_dev;
+ struct iio_trigger *trig;
+ struct as3935_state *st;
+ struct device_node *np = spi->dev.of_node;
+ int ret;
+
+ /* Be sure lightning event interrupt is specified */
+ if (!spi->irq) {
+ dev_err(&spi->dev, "unable to get event interrupt\n");
+ return -EINVAL;
+ }
+
+ indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(st));
+ if (!indio_dev)
+ return -ENOMEM;
+
+ st = iio_priv(indio_dev);
+ st->spi = spi;
+ st->tune_cap = 0;
+
+ spi_set_drvdata(spi, indio_dev);
+ mutex_init(&st->lock);
+ INIT_DELAYED_WORK(&st->work, as3935_event_work);
+
+ ret = of_property_read_u32(np,
+ "ams,tuning-capacitor-pf", &st->tune_cap);
+ if (ret) {
+ st->tune_cap = 0;
+ dev_warn(&spi->dev,
+ "no tuning-capacitor-pf set, defaulting to %d",
+ st->tune_cap);
+ }
+
+ if (st->tune_cap > MAX_PF_CAP) {
+ dev_err(&spi->dev,
+ "wrong tuning-capacitor-pf setting of %d\n",
+ st->tune_cap);
+ return -EINVAL;
+ }
+
+ indio_dev->dev.parent = &spi->dev;
+ indio_dev->name = spi_get_device_id(spi)->name;
+ indio_dev->channels = as3935_channels;
+ indio_dev->num_channels = ARRAY_SIZE(as3935_channels);
+ indio_dev->modes = INDIO_DIRECT_MODE;
+ indio_dev->info = &as3935_info;
+
+ trig = devm_iio_trigger_alloc(&spi->dev, "%s-dev%d",
+ indio_dev->name, indio_dev->id);
+
+ if (!trig)
+ return -ENOMEM;
+
+ st->trig = trig;
+ trig->dev.parent = indio_dev->dev.parent;
+ iio_trigger_set_drvdata(trig, indio_dev);
+ trig->ops = &iio_interrupt_trigger_ops;
+
+ ret = iio_trigger_register(trig);
+ if (ret) {
+ dev_err(&spi->dev, "failed to register trigger\n");
+ return ret;
+ }
+
+ ret = iio_triggered_buffer_setup(indio_dev, NULL,
+ &as3935_trigger_handler, NULL);
+
+ if (ret) {
+ dev_err(&spi->dev, "cannot setup iio trigger\n");
+ goto unregister_trigger;
+ }
+
+ calibrate_as3935(st);
+
+ ret = devm_request_irq(&spi->dev, spi->irq,
+ &as3935_interrupt_handler,
+ IRQF_TRIGGER_RISING,
+ dev_name(&spi->dev),
+ indio_dev);
+
+ if (ret) {
+ dev_err(&spi->dev, "unable to request irq\n");
+ goto unregister_buffer;
+ }
+
+ ret = iio_device_register(indio_dev);
+ if (ret < 0) {
+ dev_err(&spi->dev, "unable to register device\n");
+ goto unregister_buffer;
+ }
+ return 0;
+
+unregister_buffer:
+ iio_triggered_buffer_cleanup(indio_dev);
+
+unregister_trigger:
+ iio_trigger_unregister(st->trig);
+
+ return ret;
+};
+
+static int as3935_remove(struct spi_device *spi)
+{
+ struct iio_dev *indio_dev = spi_get_drvdata(spi);
+ struct as3935_state *st = iio_priv(indio_dev);
+
+ iio_device_unregister(indio_dev);
+ iio_triggered_buffer_cleanup(indio_dev);
+ iio_trigger_unregister(st->trig);
+
+ return 0;
+};
+
+static const struct spi_device_id as3935_id[] = {
+ {"as3935", 0},
+ {},
+};
+MODULE_DEVICE_TABLE(spi, as3935_id);
+
+static struct spi_driver as3935_driver = {
+ .driver = {
+ .name = "as3935",
+ .owner = THIS_MODULE,
+ },
+ .probe = as3935_probe,
+ .remove = as3935_remove,
+ .id_table = as3935_id,
+ .suspend = as3935_suspend,
+ .resume = as3935_resume,
+};
+module_spi_driver(as3935_driver);
+
+MODULE_AUTHOR("Matt Ranostay <mranostay@gmail.com>");
+MODULE_DESCRIPTION("AS3935 lightning sensor");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("spi:as3935");
/tr> -rw-r--r--fs/xfs/xfs_dquot.c281
-rw-r--r--fs/xfs/xfs_dquot.h27
-rw-r--r--fs/xfs/xfs_dquot_buf.c290
-rw-r--r--fs/xfs/xfs_dquot_item.c107
-rw-r--r--fs/xfs/xfs_dquot_item.h3
-rw-r--r--fs/xfs/xfs_error.c41
-rw-r--r--fs/xfs/xfs_error.h1
-rw-r--r--fs/xfs/xfs_export.c23
-rw-r--r--fs/xfs/xfs_extent_busy.c16
-rw-r--r--fs/xfs/xfs_extent_busy.h4
-rw-r--r--fs/xfs/xfs_extfree_item.c99
-rw-r--r--fs/xfs/xfs_extfree_item.h102
-rw-r--r--fs/xfs/xfs_file.c703
-rw-r--r--fs/xfs/xfs_filestream.c702
-rw-r--r--fs/xfs/xfs_filestream.h38
-rw-r--r--fs/xfs/xfs_format.h428
-rw-r--r--fs/xfs/xfs_fs.h73
-rw-r--r--fs/xfs/xfs_fs_subr.c96
-rw-r--r--fs/xfs/xfs_fsops.c288
-rw-r--r--fs/xfs/xfs_globals.c4
-rw-r--r--fs/xfs/xfs_ialloc.c1428
-rw-r--r--fs/xfs/xfs_ialloc.h38
-rw-r--r--fs/xfs/xfs_ialloc_btree.c182
-rw-r--r--fs/xfs/xfs_ialloc_btree.h57
-rw-r--r--fs/xfs/xfs_icache.c (renamed from fs/xfs/xfs_sync.c)935
-rw-r--r--fs/xfs/xfs_icache.h104
-rw-r--r--fs/xfs/xfs_icreate_item.c189
-rw-r--r--fs/xfs/xfs_icreate_item.h34
-rw-r--r--fs/xfs/xfs_iget.c720
-rw-r--r--fs/xfs/xfs_inode.c4325
-rw-r--r--fs/xfs/xfs_inode.h323
-rw-r--r--fs/xfs/xfs_inode_buf.c479
-rw-r--r--fs/xfs/xfs_inode_buf.h50
-rw-r--r--fs/xfs/xfs_inode_fork.c1906
-rw-r--r--fs/xfs/xfs_inode_fork.h171
-rw-r--r--fs/xfs/xfs_inode_item.c445
-rw-r--r--fs/xfs/xfs_inode_item.h124
-rw-r--r--fs/xfs/xfs_ioctl.c454
-rw-r--r--fs/xfs/xfs_ioctl.h10
-rw-r--r--fs/xfs/xfs_ioctl32.c41
-rw-r--r--fs/xfs/xfs_iomap.c340
-rw-r--r--fs/xfs/xfs_iomap.h8
-rw-r--r--fs/xfs/xfs_iops.c474
-rw-r--r--fs/xfs/xfs_iops.h9
-rw-r--r--fs/xfs/xfs_itable.c87
-rw-r--r--fs/xfs/xfs_linux.h89
-rw-r--r--fs/xfs/xfs_log.c774
-rw-r--r--fs/xfs/xfs_log.h152
-rw-r--r--fs/xfs/xfs_log_cil.c477
-rw-r--r--fs/xfs/xfs_log_format.h679
-rw-r--r--fs/xfs/xfs_log_priv.h191
-rw-r--r--fs/xfs/xfs_log_recover.c1493
-rw-r--r--fs/xfs/xfs_log_rlimit.c150
-rw-r--r--fs/xfs/xfs_message.c13
-rw-r--r--fs/xfs/xfs_message.h27
-rw-r--r--fs/xfs/xfs_mount.c768
-rw-r--r--fs/xfs/xfs_mount.h145
-rw-r--r--fs/xfs/xfs_mru_cache.c151
-rw-r--r--fs/xfs/xfs_mru_cache.h31
-rw-r--r--fs/xfs/xfs_qm.c922
-rw-r--r--fs/xfs/xfs_qm.h123
-rw-r--r--fs/xfs/xfs_qm_bhv.c25
-rw-r--r--fs/xfs/xfs_qm_syscalls.c312
-rw-r--r--fs/xfs/xfs_quota.h281
-rw-r--r--fs/xfs/xfs_quota_defs.h161
-rw-r--r--fs/xfs/xfs_quota_priv.h42
-rw-r--r--fs/xfs/xfs_quotaops.c67
-rw-r--r--fs/xfs/xfs_rename.c346
-rw-r--r--fs/xfs/xfs_rtalloc.c1578
-rw-r--r--fs/xfs/xfs_rtalloc.h77
-rw-r--r--fs/xfs/xfs_rtbitmap.c973
-rw-r--r--fs/xfs/xfs_sb.c836
-rw-r--r--fs/xfs/xfs_sb.h387
-rw-r--r--fs/xfs/xfs_shared.h246
-rw-r--r--fs/xfs/xfs_stats.c1
-rw-r--r--fs/xfs/xfs_stats.h18
-rw-r--r--fs/xfs/xfs_super.c513
-rw-r--r--fs/xfs/xfs_super.h3
-rw-r--r--fs/xfs/xfs_symlink.c599
-rw-r--r--fs/xfs/xfs_symlink.h27
-rw-r--r--fs/xfs/xfs_symlink_remote.c201
-rw-r--r--fs/xfs/xfs_sync.h51
-rw-r--r--fs/xfs/xfs_sysctl.c35
-rw-r--r--fs/xfs/xfs_sysctl.h1
-rw-r--r--fs/xfs/xfs_trace.c20
-rw-r--r--fs/xfs/xfs_trace.h253
-rw-r--r--fs/xfs/xfs_trans.c638
-rw-r--r--fs/xfs/xfs_trans.h370
-rw-r--r--fs/xfs/xfs_trans_ail.c82
-rw-r--r--fs/xfs/xfs_trans_buf.c233
-rw-r--r--fs/xfs/xfs_trans_dquot.c166
-rw-r--r--fs/xfs/xfs_trans_extfree.c7
-rw-r--r--fs/xfs/xfs_trans_inode.c67
-rw-r--r--fs/xfs/xfs_trans_priv.h18
-rw-r--r--fs/xfs/xfs_trans_resv.c894
-rw-r--r--fs/xfs/xfs_trans_resv.h117
-rw-r--r--fs/xfs/xfs_trans_space.h12
-rw-r--r--fs/xfs/xfs_types.h77
-rw-r--r--fs/xfs/xfs_utils.c317
-rw-r--r--fs/xfs/xfs_vnode.h17
-rw-r--r--fs/xfs/xfs_vnodeops.c2393
-rw-r--r--fs/xfs/xfs_vnodeops.h61
-rw-r--r--fs/xfs/xfs_xattr.c14
160 files changed, 37191 insertions, 26961 deletions
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 6100ec0fa1d..399e8cec6e6 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -2,6 +2,7 @@ config XFS_FS
tristate "XFS filesystem support"
depends on BLOCK
select EXPORTFS
+ select LIBCRC32C
help
XFS is a high performance journaling filesystem which originated
on the SGI IRIX platform. It is completely multi-threaded, can
@@ -68,9 +69,22 @@ config XFS_RT
If unsure, say N.
+config XFS_WARN
+ bool "XFS Verbose Warnings"
+ depends on XFS_FS && !XFS_DEBUG
+ help
+ Say Y here to get an XFS build with many additional warnings.
+ It converts ASSERT checks to WARN, so will log any out-of-bounds
+ conditions that occur that would otherwise be missed. It is much
+ lighter weight than XFS_DEBUG and does not modify algorithms and will
+ not cause the kernel to panic on non-fatal errors.
+
+ However, similar to XFS_DEBUG, it is only advisable to use this if you
+ are debugging a particular problem.
+
config XFS_DEBUG
- bool "XFS Debugging support (EXPERIMENTAL)"
- depends on XFS_FS && EXPERIMENTAL
+ bool "XFS Debugging support"
+ depends on XFS_FS
help
Say Y here to get an XFS build with many debugging features,
including ASSERT checks, function wrappers around macros,
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d2bf974b1a2..c21f4350666 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -27,9 +27,12 @@ xfs-y += xfs_trace.o
# highlevel code
xfs-y += xfs_aops.o \
+ xfs_attr_inactive.o \
+ xfs_attr_list.o \
xfs_bit.o \
+ xfs_bmap_util.o \
xfs_buf.o \
- xfs_dfrag.o \
+ xfs_dir2_readdir.o \
xfs_discard.o \
xfs_error.o \
xfs_export.o \
@@ -37,21 +40,19 @@ xfs-y += xfs_aops.o \
xfs_file.o \
xfs_filestream.o \
xfs_fsops.o \
- xfs_fs_subr.o \
xfs_globals.o \
- xfs_iget.o \
+ xfs_icache.o \
xfs_ioctl.o \
xfs_iomap.o \
xfs_iops.o \
xfs_itable.o \
xfs_message.o \
+ xfs_mount.o \
xfs_mru_cache.o \
xfs_super.o \
- xfs_sync.o \
+ xfs_symlink.o \
+ xfs_trans.o \
xfs_xattr.o \
- xfs_rename.o \
- xfs_utils.o \
- xfs_vnodeops.o \
kmem.o \
uuid.o
@@ -60,22 +61,30 @@ xfs-y += xfs_alloc.o \
xfs_alloc_btree.o \
xfs_attr.o \
xfs_attr_leaf.o \
+ xfs_attr_remote.o \
xfs_bmap.o \
xfs_bmap_btree.o \
xfs_btree.o \
xfs_da_btree.o \
+ xfs_da_format.o \
xfs_dir2.o \
xfs_dir2_block.o \
xfs_dir2_data.o \
xfs_dir2_leaf.o \
xfs_dir2_node.o \
xfs_dir2_sf.o \
+ xfs_dquot_buf.o \
xfs_ialloc.o \
xfs_ialloc_btree.o \
+ xfs_icreate_item.o \
xfs_inode.o \
+ xfs_inode_fork.o \
+ xfs_inode_buf.o \
xfs_log_recover.o \
- xfs_mount.o \
- xfs_trans.o
+ xfs_log_rlimit.o \
+ xfs_sb.o \
+ xfs_symlink_remote.o \
+ xfs_trans_resv.o
# low-level transaction/log code
xfs-y += xfs_log.o \
@@ -96,7 +105,11 @@ xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \
xfs_qm_bhv.o \
xfs_qm.o \
xfs_quotaops.o
-xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o
+
+# xfs_rtbitmap is shared with libxfs
+xfs-$(CONFIG_XFS_RT) += xfs_rtalloc.o \
+ xfs_rtbitmap.o
+
xfs-$(CONFIG_XFS_POSIX_ACL) += xfs_acl.o
xfs-$(CONFIG_PROC_FS) += xfs_stats.o
xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 4a7286c1dc8..844e288b957 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -27,8 +27,6 @@
/*
* Greedy allocation. May fail and may return vmalloced memory.
- *
- * Must be freed using kmem_free_large.
*/
void *
kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
@@ -36,7 +34,7 @@ kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
void *ptr;
size_t kmsize = maxsize;
- while (!(ptr = kmem_zalloc_large(kmsize))) {
+ while (!(ptr = vzalloc(kmsize))) {
if ((kmsize >>= 1) <= minsize)
kmsize = minsize;
}
@@ -65,13 +63,32 @@ kmem_alloc(size_t size, xfs_km_flags_t flags)
}
void *
-kmem_zalloc(size_t size, xfs_km_flags_t flags)
+kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
{
+ unsigned noio_flag = 0;
void *ptr;
+ gfp_t lflags;
- ptr = kmem_alloc(size, flags);
+ ptr = kmem_zalloc(size, flags | KM_MAYFAIL);
if (ptr)
- memset((char *)ptr, 0, (int)size);
+ return ptr;
+
+ /*
+ * __vmalloc() will allocate data pages and auxillary structures (e.g.
+ * pagetables) with GFP_KERNEL, yet we may be under GFP_NOFS context
+ * here. Hence we need to tell memory reclaim that we are in such a
+ * context via PF_MEMALLOC_NOIO to prevent memory reclaim re-entering
+ * the filesystem here and potentially deadlocking.
+ */
+ if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+ noio_flag = memalloc_noio_save();
+
+ lflags = kmem_flags_convert(flags);
+ ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
+
+ if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+ memalloc_noio_restore(noio_flag);
+
return ptr;
}
@@ -119,14 +136,3 @@ kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags)
congestion_wait(BLK_RW_ASYNC, HZ/50);
} while (1);
}
-
-void *
-kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags)
-{
- void *ptr;
-
- ptr = kmem_zone_alloc(zone, flags);
- if (ptr)
- memset((char *)ptr, 0, kmem_cache_size(zone));
- return ptr;
-}
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index b2f2620f9a8..64db0e53ede 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -32,6 +32,7 @@ typedef unsigned __bitwise xfs_km_flags_t;
#define KM_NOSLEEP ((__force xfs_km_flags_t)0x0002u)
#define KM_NOFS ((__force xfs_km_flags_t)0x0004u)
#define KM_MAYFAIL ((__force xfs_km_flags_t)0x0008u)
+#define KM_ZERO ((__force xfs_km_flags_t)0x0010u)
/*
* We use a special process flag to avoid recursive callbacks into
@@ -43,7 +44,7 @@ kmem_flags_convert(xfs_km_flags_t flags)
{
gfp_t lflags;
- BUG_ON(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL));
+ BUG_ON(flags & ~(KM_SLEEP|KM_NOSLEEP|KM_NOFS|KM_MAYFAIL|KM_ZERO));
if (flags & KM_NOSLEEP) {
lflags = GFP_ATOMIC | __GFP_NOWARN;
@@ -52,25 +53,27 @@ kmem_flags_convert(xfs_km_flags_t flags)
if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
lflags &= ~__GFP_FS;
}
+
+ if (flags & KM_ZERO)
+ lflags |= __GFP_ZERO;
+
return lflags;
}
extern void *kmem_alloc(size_t, xfs_km_flags_t);
-extern void *kmem_zalloc(size_t, xfs_km_flags_t);
+extern void *kmem_zalloc_large(size_t size, xfs_km_flags_t);
extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t);
extern void kmem_free(const void *);
-static inline void *kmem_zalloc_large(size_t size)
-{
- return vzalloc(size);
-}
-static inline void kmem_free_large(void *ptr)
-{
- vfree(ptr);
-}
extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
+static inline void *
+kmem_zalloc(size_t size, xfs_km_flags_t flags)
+{
+ return kmem_alloc(size, flags | KM_ZERO);
+}
+
/*
* Zone interfaces
*/
@@ -109,6 +112,11 @@ kmem_zone_destroy(kmem_zone_t *zone)
}
extern void *kmem_zone_alloc(kmem_zone_t *, xfs_km_flags_t);
-extern void *kmem_zone_zalloc(kmem_zone_t *, xfs_km_flags_t);
+
+static inline void *
+kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags)
+{
+ return kmem_zone_alloc(zone, flags | KM_ZERO);
+}
#endif /* __XFS_SUPPORT_KMEM_H__ */
diff --git a/fs/xfs/mrlock.h b/fs/xfs/mrlock.h
index ff6a19873e5..e3c92d19e54 100644
--- a/fs/xfs/mrlock.h
+++ b/fs/xfs/mrlock.h
@@ -22,12 +22,12 @@
typedef struct {
struct rw_semaphore mr_lock;
-#ifdef DEBUG
+#if defined(DEBUG) || defined(XFS_WARN)
int mr_writer;
#endif
} mrlock_t;
-#ifdef DEBUG
+#if defined(DEBUG) || defined(XFS_WARN)
#define mrinit(mrp, name) \
do { (mrp)->mr_writer = 0; init_rwsem(&(mrp)->mr_lock); } while (0)
#else
@@ -46,7 +46,7 @@ static inline void mraccess_nested(mrlock_t *mrp, int subclass)
static inline void mrupdate_nested(mrlock_t *mrp, int subclass)
{
down_write_nested(&mrp->mr_lock, subclass);
-#ifdef DEBUG
+#if defined(DEBUG) || defined(XFS_WARN)
mrp->mr_writer = 1;
#endif
}
@@ -60,7 +60,7 @@ static inline int mrtryupdate(mrlock_t *mrp)
{
if (!down_write_trylock(&mrp->mr_lock))
return 0;
-#ifdef DEBUG
+#if defined(DEBUG) || defined(XFS_WARN)
mrp->mr_writer = 1;
#endif
return 1;
@@ -68,7 +68,7 @@ static inline int mrtryupdate(mrlock_t *mrp)
static inline void mrunlock_excl(mrlock_t *mrp)
{
-#ifdef DEBUG
+#if defined(DEBUG) || defined(XFS_WARN)
mrp->mr_writer = 0;
#endif
up_write(&mrp->mr_lock);
@@ -81,7 +81,7 @@ static inline void mrunlock_shared(mrlock_t *mrp)
static inline void mrdemote(mrlock_t *mrp)
{
-#ifdef DEBUG
+#if defined(DEBUG) || defined(XFS_WARN)
mrp->mr_writer = 0;
#endif
downgrade_write(&mrp->mr_lock);
diff --git a/fs/xfs/uuid.h b/fs/xfs/uuid.h
index 4732d71262c..104db0f3bed 100644
--- a/fs/xfs/uuid.h
+++ b/fs/xfs/uuid.h
@@ -26,4 +26,10 @@ extern int uuid_is_nil(uuid_t *uuid);
extern int uuid_equal(uuid_t *uuid1, uuid_t *uuid2);
extern void uuid_getnodeuniq(uuid_t *uuid, int fsid [2]);
+static inline void
+uuid_copy(uuid_t *dst, uuid_t *src)
+{
+ memcpy(dst, src, sizeof(uuid_t));
+}
+
#endif /* __XFS_SUPPORT_UUID_H__ */
diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index d8b11b7f94a..a742c47f7d5 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -24,6 +24,11 @@
#define XFS_BUF_LOCK_TRACKING 1
#endif
+#ifdef CONFIG_XFS_WARN
+#define XFS_WARN 1
+#endif
+
+
#include "xfs_linux.h"
#endif /* __XFS_H__ */
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index ac702a6eab9..6888ad886ff 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -16,11 +16,15 @@
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_ag.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
#include "xfs_acl.h"
#include "xfs_attr.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_inode.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include <linux/slab.h>
#include <linux/xattr.h>
@@ -34,7 +38,9 @@
*/
STATIC struct posix_acl *
-xfs_acl_from_disk(struct xfs_acl *aclp)
+xfs_acl_from_disk(
+ struct xfs_acl *aclp,
+ int max_entries)
{
struct posix_acl_entry *acl_e;
struct posix_acl *acl;
@@ -42,7 +48,7 @@ xfs_acl_from_disk(struct xfs_acl *aclp)
unsigned int count, i;
count = be32_to_cpu(aclp->acl_cnt);
- if (count > XFS_ACL_MAX_ENTRIES)
+ if (count > max_entries)
return ERR_PTR(-EFSCORRUPTED);
acl = posix_acl_alloc(count, GFP_KERNEL);
@@ -64,14 +70,15 @@ xfs_acl_from_disk(struct xfs_acl *aclp)
switch (acl_e->e_tag) {
case ACL_USER:
+ acl_e->e_uid = xfs_uid_to_kuid(be32_to_cpu(ace->ae_id));
+ break;
case ACL_GROUP:
- acl_e->e_id = be32_to_cpu(ace->ae_id);
+ acl_e->e_gid = xfs_gid_to_kgid(be32_to_cpu(ace->ae_id));
break;
case ACL_USER_OBJ:
case ACL_GROUP_OBJ:
case ACL_MASK:
case ACL_OTHER:
- acl_e->e_id = ACL_UNDEFINED_ID;
break;
default:
goto fail;
@@ -97,7 +104,18 @@ xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl)
acl_e = &acl->a_entries[i];
ace->ae_tag = cpu_to_be32(acl_e->e_tag);
- ace->ae_id = cpu_to_be32(acl_e->e_id);
+ switch (acl_e->e_tag) {
+ case ACL_USER:
+ ace->ae_id = cpu_to_be32(xfs_kuid_to_uid(acl_e->e_uid));
+ break;
+ case ACL_GROUP:
+ ace->ae_id = cpu_to_be32(xfs_kgid_to_gid(acl_e->e_gid));
+ break;
+ default:
+ ace->ae_id = cpu_to_be32(ACL_UNDEFINED_ID);
+ break;
+ }
+
ace->ae_perm = cpu_to_be16(acl_e->e_perm);
}
}
@@ -106,15 +124,11 @@ struct posix_acl *
xfs_get_acl(struct inode *inode, int type)
{
struct xfs_inode *ip = XFS_I(inode);
- struct posix_acl *acl;
+ struct posix_acl *acl = NULL;
struct xfs_acl *xfs_acl;
- int len = sizeof(struct xfs_acl);
unsigned char *ea_name;
int error;
-
- acl = get_cached_acl(inode, type);
- if (acl != ACL_NOT_CACHED)
- return acl;
+ int len;
trace_xfs_get_acl(ip);
@@ -133,8 +147,8 @@ xfs_get_acl(struct inode *inode, int type)
* If we have a cached ACLs value just return it, not need to
* go out to the disk.
*/
-
- xfs_acl = kzalloc(sizeof(struct xfs_acl), GFP_KERNEL);
+ len = XFS_ACL_MAX_SIZE(ip->i_mount);
+ xfs_acl = kmem_zalloc_large(len, KM_SLEEP);
if (!xfs_acl)
return ERR_PTR(-ENOMEM);
@@ -146,34 +160,29 @@ xfs_get_acl(struct inode *inode, int type)
* cache entry, for any other error assume it is transient and
* leave the cache entry as ACL_NOT_CACHED.
*/
- if (error == -ENOATTR) {
- acl = NULL;
+ if (error == -ENOATTR)
goto out_update_cache;
- }
goto out;
}
- acl = xfs_acl_from_disk(xfs_acl);
+ acl = xfs_acl_from_disk(xfs_acl, XFS_ACL_MAX_ENTRIES(ip->i_mount));
if (IS_ERR(acl))
goto out;
- out_update_cache:
+out_update_cache:
set_cached_acl(inode, type, acl);
- out:
- kfree(xfs_acl);
+out:
+ kmem_free(xfs_acl);
return acl;
}
STATIC int
-xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
+__xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
{
struct xfs_inode *ip = XFS_I(inode);
unsigned char *ea_name;
int error;
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
-
switch (type) {
case ACL_TYPE_ACCESS:
ea_name = SGI_ACL_FILE;
@@ -189,21 +198,22 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
if (acl) {
struct xfs_acl *xfs_acl;
- int len;
+ int len = XFS_ACL_MAX_SIZE(ip->i_mount);
- xfs_acl = kzalloc(sizeof(struct xfs_acl), GFP_KERNEL);
+ xfs_acl = kmem_zalloc_large(len, KM_SLEEP);
if (!xfs_acl)
return -ENOMEM;
xfs_acl_to_disk(xfs_acl, acl);
- len = sizeof(struct xfs_acl) -
- (sizeof(struct xfs_acl_entry) *
- (XFS_ACL_MAX_ENTRIES - acl->a_count));
+
+ /* subtract away the unused acl entries */
+ len -= sizeof(struct xfs_acl_entry) *
+ (XFS_ACL_MAX_ENTRIES(ip->i_mount) - acl->a_count);
error = -xfs_attr_set(ip, ea_name, (unsigned char *)xfs_acl,
len, ATTR_ROOT);
- kfree(xfs_acl);
+ kmem_free(xfs_acl);
} else {
/*
* A NULL ACL argument means we want to remove the ACL.
@@ -243,7 +253,7 @@ xfs_set_mode(struct inode *inode, umode_t mode)
static int
xfs_acl_exists(struct inode *inode, unsigned char *name)
{
- int len = sizeof(struct xfs_acl);
+ int len = XFS_ACL_MAX_SIZE(XFS_M(inode->i_sb));
return (xfs_attr_get(XFS_I(inode), name, NULL, &len,
ATTR_ROOT|ATTR_KERNOVAL) == 0);
@@ -263,131 +273,23 @@ posix_acl_default_exists(struct inode *inode)
return xfs_acl_exists(inode, SGI_ACL_DEFAULT);
}
-/*
- * No need for i_mutex because the inode is not yet exposed to the VFS.
- */
-int
-xfs_inherit_acl(struct inode *inode, struct posix_acl *acl)
-{
- umode_t mode = inode->i_mode;
- int error = 0, inherit = 0;
-
- if (S_ISDIR(inode->i_mode)) {
- error = xfs_set_acl(inode, ACL_TYPE_DEFAULT, acl);
- if (error)
- goto out;
- }
-
- error = posix_acl_create(&acl, GFP_KERNEL, &mode);
- if (error < 0)
- return error;
-
- /*
- * If posix_acl_create returns a positive value we need to
- * inherit a permission that can't be represented using the Unix
- * mode bits and we actually need to set an ACL.
- */
- if (error > 0)
- inherit = 1;
-
- error = xfs_set_mode(inode, mode);
- if (error)
- goto out;
-
- if (inherit)
- error = xfs_set_acl(inode, ACL_TYPE_ACCESS, acl);
-
-out:
- posix_acl_release(acl);
- return error;
-}
-
int
-xfs_acl_chmod(struct inode *inode)
-{
- struct posix_acl *acl;
- int error;
-
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
-
- acl = xfs_get_acl(inode, ACL_TYPE_ACCESS);
- if (IS_ERR(acl) || !acl)
- return PTR_ERR(acl);
-
- error = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
- if (error)
- return error;
-
- error = xfs_set_acl(inode, ACL_TYPE_ACCESS, acl);
- posix_acl_release(acl);
- return error;
-}
-
-static int
-xfs_xattr_acl_get(struct dentry *dentry, const char *name,
- void *value, size_t size, int type)
-{
- struct posix_acl *acl;
- int error;
-
- acl = xfs_get_acl(dentry->d_inode, type);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (acl == NULL)
- return -ENODATA;
-
- error = posix_acl_to_xattr(acl, value, size);
- posix_acl_release(acl);
-
- return error;
-}
-
-static int
-xfs_xattr_acl_set(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags, int type)
+xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
- struct inode *inode = dentry->d_inode;
- struct posix_acl *acl = NULL;
int error = 0;
- if (flags & XATTR_CREATE)
- return -EINVAL;
- if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
- return value ? -EACCES : 0;
- if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
- return -EPERM;
-
- if (!value)
+ if (!acl)
goto set_acl;
- acl = posix_acl_from_xattr(value, size);
- if (!acl) {
- /*
- * acl_set_file(3) may request that we set default ACLs with
- * zero length -- defend (gracefully) against that here.
- */
- goto out;
- }
- if (IS_ERR(acl)) {
- error = PTR_ERR(acl);
- goto out;
- }
-
- error = posix_acl_valid(acl);
- if (error)
- goto out_release;
-
- error = -EINVAL;
- if (acl->a_count > XFS_ACL_MAX_ENTRIES)
- goto out_release;
+ error = -E2BIG;
+ if (acl->a_count > XFS_ACL_MAX_ENTRIES(XFS_M(inode->i_sb)))
+ return error;
if (type == ACL_TYPE_ACCESS) {
umode_t mode = inode->i_mode;
error = posix_acl_equiv_mode(acl, &mode);
if (error <= 0) {
- posix_acl_release(acl);
acl = NULL;
if (error < 0)
@@ -396,27 +298,9 @@ xfs_xattr_acl_set(struct dentry *dentry, const char *name,
error = xfs_set_mode(inode, mode);
if (error)
- goto out_release;
+ return error;
}
set_acl:
- error = xfs_set_acl(inode, type, acl);
- out_release:
- posix_acl_release(acl);
- out:
- return error;
+ return __xfs_set_acl(inode, type, acl);
}
-
-const struct xattr_handler xfs_xattr_acl_access_handler = {
- .prefix = POSIX_ACL_XATTR_ACCESS,
- .flags = ACL_TYPE_ACCESS,
- .get = xfs_xattr_acl_get,
- .set = xfs_xattr_acl_set,
-};
-
-const struct xattr_handler xfs_xattr_acl_default_handler = {
- .prefix = POSIX_ACL_XATTR_DEFAULT,
- .flags = ACL_TYPE_DEFAULT,
- .get = xfs_xattr_acl_get,
- .set = xfs_xattr_acl_set,
-};
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 39632d94135..5dc16374451 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -22,19 +22,36 @@ struct inode;
struct posix_acl;
struct xfs_inode;
-#define XFS_ACL_MAX_ENTRIES 25
#define XFS_ACL_NOT_PRESENT (-1)
/* On-disk XFS access control list structure */
+struct xfs_acl_entry {
+ __be32 ae_tag;
+ __be32 ae_id;
+ __be16 ae_perm;
+ __be16 ae_pad; /* fill the implicit hole in the structure */
+};
+
struct xfs_acl {
- __be32 acl_cnt;
- struct xfs_acl_entry {
- __be32 ae_tag;
- __be32 ae_id;
- __be16 ae_perm;
- } acl_entry[XFS_ACL_MAX_ENTRIES];
+ __be32 acl_cnt;
+ struct xfs_acl_entry acl_entry[0];
};
+/*
+ * The number of ACL entries allowed is defined by the on-disk format.
+ * For v4 superblocks, that is limited to 25 entries. For v5 superblocks, it is
+ * limited only by the maximum size of the xattr that stores the information.
+ */
+#define XFS_ACL_MAX_ENTRIES(mp) \
+ (xfs_sb_version_hascrc(&mp->m_sb) \
+ ? (XATTR_SIZE_MAX - sizeof(struct xfs_acl)) / \
+ sizeof(struct xfs_acl_entry) \
+ : 25)
+
+#define XFS_ACL_MAX_SIZE(mp) \
+ (sizeof(struct xfs_acl) + \
+ sizeof(struct xfs_acl_entry) * XFS_ACL_MAX_ENTRIES((mp)))
+
/* On-disk XFS extended attribute names */
#define SGI_ACL_FILE (unsigned char *)"SGI_ACL_FILE"
#define SGI_ACL_DEFAULT (unsigned char *)"SGI_ACL_DEFAULT"
@@ -43,20 +60,15 @@ struct xfs_acl {
#ifdef CONFIG_XFS_POSIX_ACL
extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
-extern int xfs_inherit_acl(struct inode *inode, struct posix_acl *default_acl);
-extern int xfs_acl_chmod(struct inode *inode);
+extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
extern int posix_acl_access_exists(struct inode *inode);
extern int posix_acl_default_exists(struct inode *inode);
-
-extern const struct xattr_handler xfs_xattr_acl_access_handler;
-extern const struct xattr_handler xfs_xattr_acl_default_handler;
#else
static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type)
{
return NULL;
}
-# define xfs_inherit_acl(inode, default_acl) 0
-# define xfs_acl_chmod(inode) 0
+# define xfs_set_acl NULL
# define posix_acl_access_exists(inode) 0
# define posix_acl_default_exists(inode) 0
#endif /* CONFIG_XFS_POSIX_ACL */
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 44d65c1533c..6e247a99f5d 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -30,6 +30,7 @@ struct xfs_trans;
#define XFS_AGF_MAGIC 0x58414746 /* 'XAGF' */
#define XFS_AGI_MAGIC 0x58414749 /* 'XAGI' */
+#define XFS_AGFL_MAGIC 0x5841464c /* 'XAFL' */
#define XFS_AGF_VERSION 1
#define XFS_AGI_VERSION 1
@@ -63,14 +64,33 @@ typedef struct xfs_agf {
__be32 agf_spare0; /* spare field */
__be32 agf_levels[XFS_BTNUM_AGF]; /* btree levels */
__be32 agf_spare1; /* spare field */
+
__be32 agf_flfirst; /* first freelist block's index */
__be32 agf_fllast; /* last freelist block's index */
__be32 agf_flcount; /* count of blocks in freelist */
__be32 agf_freeblks; /* total free blocks */
+
__be32 agf_longest; /* longest free space */
__be32 agf_btreeblks; /* # of blocks held in AGF btrees */
+ uuid_t agf_uuid; /* uuid of filesystem */
+
+ /*
+ * reserve some contiguous space for future logged fields before we add
+ * the unlogged fields. This makes the range logging via flags and
+ * structure offsets much simpler.
+ */
+ __be64 agf_spare64[16];
+
+ /* unlogged fields, written during buffer writeback. */
+ __be64 agf_lsn; /* last write sequence */
+ __be32 agf_crc; /* crc of agf sector */
+ __be32 agf_spare2;
+
+ /* structure must be padded to 64 bit alignment */
} xfs_agf_t;
+#define XFS_AGF_CRC_OFF offsetof(struct xfs_agf, agf_crc)
+
#define XFS_AGF_MAGICNUM 0x00000001
#define XFS_AGF_VERSIONNUM 0x00000002
#define XFS_AGF_SEQNO 0x00000004
@@ -83,7 +103,8 @@ typedef struct xfs_agf {
#define XFS_AGF_FREEBLKS 0x00000200
#define XFS_AGF_LONGEST 0x00000400
#define XFS_AGF_BTREEBLKS 0x00000800
-#define XFS_AGF_NUM_BITS 12
+#define XFS_AGF_UUID 0x00001000
+#define XFS_AGF_NUM_BITS 13
#define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1)
#define XFS_AGF_FLAGS \
@@ -98,7 +119,8 @@ typedef struct xfs_agf {
{ XFS_AGF_FLCOUNT, "FLCOUNT" }, \
{ XFS_AGF_FREEBLKS, "FREEBLKS" }, \
{ XFS_AGF_LONGEST, "LONGEST" }, \
- { XFS_AGF_BTREEBLKS, "BTREEBLKS" }
+ { XFS_AGF_BTREEBLKS, "BTREEBLKS" }, \
+ { XFS_AGF_UUID, "UUID" }
/* disk block (xfs_daddr_t) in the AG */
#define XFS_AGF_DADDR(mp) ((xfs_daddr_t)(1 << (mp)->m_sectbb_log))
@@ -130,6 +152,7 @@ typedef struct xfs_agi {
__be32 agi_root; /* root of inode btree */
__be32 agi_level; /* levels in inode btree */
__be32 agi_freecount; /* number of free inodes */
+
__be32 agi_newino; /* new inode just allocated */
__be32 agi_dirino; /* last directory inode chunk */
/*
@@ -137,21 +160,38 @@ typedef struct xfs_agi {
* still being referenced.
*/
__be32 agi_unlinked[XFS_AGI_UNLINKED_BUCKETS];
+ /*
+ * This marks the end of logging region 1 and start of logging region 2.
+ */
+ uuid_t agi_uuid; /* uuid of filesystem */
+ __be32 agi_crc; /* crc of agi sector */
+ __be32 agi_pad32;
+ __be64 agi_lsn; /* last write sequence */
+
+ __be32 agi_free_root; /* root of the free inode btree */
+ __be32 agi_free_level;/* levels in free inode btree */
+
+ /* structure must be padded to 64 bit alignment */
} xfs_agi_t;
-#define XFS_AGI_MAGICNUM 0x00000001
-#define XFS_AGI_VERSIONNUM 0x00000002
-#define XFS_AGI_SEQNO 0x00000004
-#define XFS_AGI_LENGTH 0x00000008
-#define XFS_AGI_COUNT 0x00000010
-#define XFS_AGI_ROOT 0x00000020
-#define XFS_AGI_LEVEL 0x00000040
-#define XFS_AGI_FREECOUNT 0x00000080
-#define XFS_AGI_NEWINO 0x00000100
-#define XFS_AGI_DIRINO 0x00000200
-#define XFS_AGI_UNLINKED 0x00000400
-#define XFS_AGI_NUM_BITS 11
-#define XFS_AGI_ALL_BITS ((1 << XFS_AGI_NUM_BITS) - 1)
+#define XFS_AGI_CRC_OFF offsetof(struct xfs_agi, agi_crc)
+
+#define XFS_AGI_MAGICNUM (1 << 0)
+#define XFS_AGI_VERSIONNUM (1 << 1)
+#define XFS_AGI_SEQNO (1 << 2)
+#define XFS_AGI_LENGTH (1 << 3)
+#define XFS_AGI_COUNT (1 << 4)
+#define XFS_AGI_ROOT (1 << 5)
+#define XFS_AGI_LEVEL (1 << 6)
+#define XFS_AGI_FREECOUNT (1 << 7)
+#define XFS_AGI_NEWINO (1 << 8)
+#define XFS_AGI_DIRINO (1 << 9)
+#define XFS_AGI_UNLINKED (1 << 10)
+#define XFS_AGI_NUM_BITS_R1 11 /* end of the 1st agi logging region */
+#define XFS_AGI_ALL_BITS_R1 ((1 << XFS_AGI_NUM_BITS_R1) - 1)
+#define XFS_AGI_FREE_ROOT (1 << 11)
+#define XFS_AGI_FREE_LEVEL (1 << 12)
+#define XFS_AGI_NUM_BITS_R2 13
/* disk block (xfs_daddr_t) in the AG */
#define XFS_AGI_DADDR(mp) ((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
@@ -167,65 +207,34 @@ extern int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
*/
#define XFS_AGFL_DADDR(mp) ((xfs_daddr_t)(3 << (mp)->m_sectbb_log))
#define XFS_AGFL_BLOCK(mp) XFS_HDR_BLOCK(mp, XFS_AGFL_DADDR(mp))
-#define XFS_AGFL_SIZE(mp) ((mp)->m_sb.sb_sectsize / sizeof(xfs_agblock_t))
#define XFS_BUF_TO_AGFL(bp) ((xfs_agfl_t *)((bp)->b_addr))
-typedef struct xfs_agfl {
- __be32 agfl_bno[1]; /* actually XFS_AGFL_SIZE(mp) */
-} xfs_agfl_t;
+#define XFS_BUF_TO_AGFL_BNO(mp, bp) \
+ (xfs_sb_version_hascrc(&((mp)->m_sb)) ? \
+ &(XFS_BUF_TO_AGFL(bp)->agfl_bno[0]) : \
+ (__be32 *)(bp)->b_addr)
/*
- * Per-ag incore structure, copies of information in agf and agi,
- * to improve the performance of allocation group selection.
+ * Size of the AGFL. For CRC-enabled filesystes we steal a couple of
+ * slots in the beginning of the block for a proper header with the
+ * location information and CRC.
*/
-#define XFS_PAGB_NUM_SLOTS 128
-
-typedef struct xfs_perag {
- struct xfs_mount *pag_mount; /* owner filesystem */
- xfs_agnumber_t pag_agno; /* AG this structure belongs to */
- atomic_t pag_ref; /* perag reference count */
- char pagf_init; /* this agf's entry is initialized */
- char pagi_init; /* this agi's entry is initialized */
- char pagf_metadata; /* the agf is preferred to be metadata */
- char pagi_inodeok; /* The agi is ok for inodes */
- __uint8_t pagf_levels[XFS_BTNUM_AGF];
- /* # of levels in bno & cnt btree */
- __uint32_t pagf_flcount; /* count of blocks in freelist */
- xfs_extlen_t pagf_freeblks; /* total free blocks */
- xfs_extlen_t pagf_longest; /* longest free space */
- __uint32_t pagf_btreeblks; /* # of blocks held in AGF btrees */
- xfs_agino_t pagi_freecount; /* number of free inodes */
- xfs_agino_t pagi_count; /* number of allocated inodes */
+#define XFS_AGFL_SIZE(mp) \
+ (((mp)->m_sb.sb_sectsize - \
+ (xfs_sb_version_hascrc(&((mp)->m_sb)) ? \
+ sizeof(struct xfs_agfl) : 0)) / \
+ sizeof(xfs_agblock_t))
- /*
- * Inode allocation search lookup optimisation.
- * If the pagino matches, the search for new inodes
- * doesn't need to search the near ones again straight away
- */
- xfs_agino_t pagl_pagino;
- xfs_agino_t pagl_leftrec;
- xfs_agino_t pagl_rightrec;
-#ifdef __KERNEL__
- spinlock_t pagb_lock; /* lock for pagb_tree */
- struct rb_root pagb_tree; /* ordered tree of busy extents */
-
- atomic_t pagf_fstrms; /* # of filestreams active in this AG */
-
- spinlock_t pag_ici_lock; /* incore inode cache lock */
- struct radix_tree_root pag_ici_root; /* incore inode cache root */
- int pag_ici_reclaimable; /* reclaimable inodes */
- struct mutex pag_ici_reclaim_lock; /* serialisation point */
- unsigned long pag_ici_reclaim_cursor; /* reclaim restart point */
-
- /* buffer cache index */
- spinlock_t pag_buf_lock; /* lock for pag_buf_tree */
- struct rb_root pag_buf_tree; /* ordered tree of active buffers */
-
- /* for rcu-safe freeing */
- struct rcu_head rcu_head;
-#endif
- int pagb_count; /* pagb slots in use */
-} xfs_perag_t;
+typedef struct xfs_agfl {
+ __be32 agfl_magicnum;
+ __be32 agfl_seqno;
+ uuid_t agfl_uuid;
+ __be64 agfl_lsn;
+ __be32 agfl_crc;
+ __be32 agfl_bno[]; /* actually XFS_AGFL_SIZE(mp) */
+} xfs_agfl_t;
+
+#define XFS_AGFL_CRC_OFF offsetof(struct xfs_agfl, agfl_crc)
/*
* tags for inode radix tree
@@ -233,6 +242,7 @@ typedef struct xfs_perag {
#define XFS_ICI_NO_TAG (-1) /* special flag for an untagged lookup
in xfs_inode_ag_iterator */
#define XFS_ICI_RECLAIM_TAG 0 /* inode is to be reclaimed */
+#define XFS_ICI_EOFBLOCKS_TAG 1 /* inode has blocks beyond EOF */
#define XFS_AG_MAXLEVELS(mp) ((mp)->m_ag_maxlevels)
#define XFS_MIN_FREELIST_RAW(bl,cl,mp) \
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 9d1aeb7e273..d43813267a8 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -17,23 +17,25 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_shared.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
#include "xfs_error.h"
+#include "xfs_cksum.h"
#include "xfs_trace.h"
+#include "xfs_trans.h"
+#include "xfs_buf_item.h"
+#include "xfs_log.h"
struct workqueue_struct *xfs_alloc_wq;
@@ -173,6 +175,7 @@ xfs_alloc_compute_diff(
xfs_agblock_t wantbno, /* target starting block */
xfs_extlen_t wantlen, /* target length */
xfs_extlen_t alignment, /* target alignment */
+ char userdata, /* are we allocating data? */
xfs_agblock_t freebno, /* freespace's starting block */
xfs_extlen_t freelen, /* freespace's length */
xfs_agblock_t *newbnop) /* result: best start block from free */
@@ -187,7 +190,14 @@ xfs_alloc_compute_diff(
ASSERT(freelen >= wantlen);
freeend = freebno + freelen;
wantend = wantbno + wantlen;
- if (freebno >= wantbno) {
+ /*
+ * We want to allocate from the start of a free extent if it is past
+ * the desired block or if we are allocating user data and the free
+ * extent is before desired block. The second case is there to allow
+ * for contiguous allocation from the remaining free space if the file
+ * grows in the short term.
+ */
+ if (freebno >= wantbno || (userdata && freeend < wantend)) {
if ((newbno1 = roundup(freebno, alignment)) >= freeend)
newbno1 = NULLAGBLOCK;
} else if (freeend >= wantend && alignment > 1) {
@@ -247,16 +257,14 @@ xfs_alloc_fix_len(
k = rlen % args->prod;
if (k == args->mod)
return;
- if (k > args->mod) {
- if ((int)(rlen = rlen - k - args->mod) < (int)args->minlen)
- return;
- } else {
- if ((int)(rlen = rlen - args->prod - (args->mod - k)) <
- (int)args->minlen)
- return;
- }
- ASSERT(rlen >= args->minlen);
- ASSERT(rlen <= args->maxlen);
+ if (k > args->mod)
+ rlen = rlen - (k - args->mod);
+ else
+ rlen = rlen - args->prod + (args->mod - k);
+ if ((int)rlen < (int)args->minlen)
+ return;
+ ASSERT(rlen >= args->minlen && rlen <= args->maxlen);
+ ASSERT(rlen % args->prod == args->mod);
args->len = rlen;
}
@@ -430,6 +438,87 @@ xfs_alloc_fixup_trees(
return 0;
}
+static bool
+xfs_agfl_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_agfl *agfl = XFS_BUF_TO_AGFL(bp);
+ int i;
+
+ if (!uuid_equal(&agfl->agfl_uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be32_to_cpu(agfl->agfl_magicnum) != XFS_AGFL_MAGIC)
+ return false;
+ /*
+ * during growfs operations, the perag is not fully initialised,
+ * so we can't use it for any useful checking. growfs ensures we can't
+ * use it by using uncached buffers that don't have the perag attached
+ * so we can detect and avoid this problem.
+ */
+ if (bp->b_pag && be32_to_cpu(agfl->agfl_seqno) != bp->b_pag->pag_agno)
+ return false;
+
+ for (i = 0; i < XFS_AGFL_SIZE(mp); i++) {
+ if (be32_to_cpu(agfl->agfl_bno[i]) != NULLAGBLOCK &&
+ be32_to_cpu(agfl->agfl_bno[i]) >= mp->m_sb.sb_agblocks)
+ return false;
+ }
+ return true;
+}
+
+static void
+xfs_agfl_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+
+ /*
+ * There is no verification of non-crc AGFLs because mkfs does not
+ * initialise the AGFL to zero or NULL. Hence the only valid part of the
+ * AGFL is what the AGF says is active. We can't get to the AGF, so we
+ * can't verify just those entries are valid.
+ */
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (!xfs_buf_verify_cksum(bp, XFS_AGFL_CRC_OFF))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_agfl_verify(bp))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+}
+
+static void
+xfs_agfl_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+
+ /* no verification of non-crc AGFLs */
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (!xfs_agfl_verify(bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (bip)
+ XFS_BUF_TO_AGFL(bp)->agfl_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_AGFL_CRC_OFF);
+}
+
+const struct xfs_buf_ops xfs_agfl_buf_ops = {
+ .verify_read = xfs_agfl_read_verify,
+ .verify_write = xfs_agfl_write_verify,
+};
+
/*
* Read in the allocation group free block array.
*/
@@ -447,10 +536,9 @@ xfs_alloc_read_agfl(
error = xfs_trans_read_buf(
mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, &bp);
+ XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
if (error)
return error;
- ASSERT(!xfs_buf_geterror(bp));
xfs_buf_set_ref(bp, XFS_AGFL_REF);
*bpp = bp;
return 0;
@@ -718,7 +806,8 @@ xfs_alloc_find_best_extent(
xfs_alloc_fix_len(args);
sdiff = xfs_alloc_compute_diff(args->agbno, args->len,
- args->alignment, *sbnoa,
+ args->alignment,
+ args->userdata, *sbnoa,
*slena, &new);
/*
@@ -782,13 +871,13 @@ xfs_alloc_ag_vextent_near(
xfs_agblock_t ltnew; /* useful start bno of left side */
xfs_extlen_t rlen; /* length of returned extent */
int forced = 0;
-#if defined(DEBUG) && defined(__KERNEL__)
+#ifdef DEBUG
/*
* Randomly don't execute the first algorithm.
*/
int dofirst; /* set to do first algorithm */
- dofirst = random32() & 1;
+ dofirst = prandom_u32() & 1;
#endif
restart:
@@ -842,8 +931,8 @@ restart:
xfs_extlen_t blen=0;
xfs_agblock_t bnew=0;
-#if defined(DEBUG) && defined(__KERNEL__)
- if (!dofirst)
+#ifdef DEBUG
+ if (dofirst)
break;
#endif
/*
@@ -889,7 +978,8 @@ restart:
if (args->len < blen)
continue;
ltdiff = xfs_alloc_compute_diff(args->agbno, args->len,
- args->alignment, ltbnoa, ltlena, &ltnew);
+ args->alignment, args->userdata, ltbnoa,
+ ltlena, &ltnew);
if (ltnew != NULLAGBLOCK &&
(args->len > blen || ltdiff < bdiff)) {
bdiff = ltdiff;
@@ -1041,7 +1131,8 @@ restart:
args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen);
xfs_alloc_fix_len(args);
ltdiff = xfs_alloc_compute_diff(args->agbno, args->len,
- args->alignment, ltbnoa, ltlena, &ltnew);
+ args->alignment, args->userdata, ltbnoa,
+ ltlena, &ltnew);
error = xfs_alloc_find_best_extent(args,
&bno_cur_lt, &bno_cur_gt,
@@ -1057,7 +1148,8 @@ restart:
args->len = XFS_EXTLEN_MIN(gtlena, args->maxlen);
xfs_alloc_fix_len(args);
gtdiff = xfs_alloc_compute_diff(args->agbno, args->len,
- args->alignment, gtbnoa, gtlena, &gtnew);
+ args->alignment, args->userdata, gtbnoa,
+ gtlena, &gtnew);
error = xfs_alloc_find_best_extent(args,
&bno_cur_gt, &bno_cur_lt,
@@ -1074,13 +1166,13 @@ restart:
* If we couldn't get anything, give up.
*/
if (bno_cur_lt == NULL && bno_cur_gt == NULL) {
+ xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+
if (!forced++) {
trace_xfs_alloc_near_busy(args);
xfs_log_force(args->mp, XFS_LOG_SYNC);
goto restart;
}
-
- xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
trace_xfs_alloc_size_neither(args);
args->agbno = NULLAGBLOCK;
return 0;
@@ -1116,7 +1208,7 @@ restart:
}
rlen = args->len;
(void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment,
- ltbnoa, ltlena, &ltnew);
+ args->userdata, ltbnoa, ltlena, &ltnew);
ASSERT(ltnew >= ltbno);
ASSERT(ltnew + rlen <= ltbnoa + ltlena);
ASSERT(ltnew + rlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length));
@@ -1866,12 +1958,11 @@ xfs_alloc_fix_freelist(
/*
* Initialize the args structure.
*/
+ memset(&targs, 0, sizeof(targs));
targs.tp = tp;
targs.mp = mp;
targs.agbp = agbp;
targs.agno = args->agno;
- targs.mod = targs.minleft = targs.wasdel = targs.userdata =
- targs.minalignslop = 0;
targs.alignment = targs.minlen = targs.prod = targs.isfl = 1;
targs.type = XFS_ALLOCTYPE_THIS_AG;
targs.pag = pag;
@@ -1929,18 +2020,18 @@ xfs_alloc_get_freelist(
int btreeblk) /* destination is a AGF btree */
{
xfs_agf_t *agf; /* a.g. freespace structure */
- xfs_agfl_t *agfl; /* a.g. freelist structure */
xfs_buf_t *agflbp;/* buffer for a.g. freelist structure */
xfs_agblock_t bno; /* block number returned */
+ __be32 *agfl_bno;
int error;
int logflags;
- xfs_mount_t *mp; /* mount structure */
+ xfs_mount_t *mp = tp->t_mountp;
xfs_perag_t *pag; /* per allocation group data */
- agf = XFS_BUF_TO_AGF(agbp);
/*
* Freelist is empty, give up.
*/
+ agf = XFS_BUF_TO_AGF(agbp);
if (!agf->agf_flcount) {
*bnop = NULLAGBLOCK;
return 0;
@@ -1948,15 +2039,17 @@ xfs_alloc_get_freelist(
/*
* Read the array of free blocks.
*/
- mp = tp->t_mountp;
- if ((error = xfs_alloc_read_agfl(mp, tp,
- be32_to_cpu(agf->agf_seqno), &agflbp)))
+ error = xfs_alloc_read_agfl(mp, tp, be32_to_cpu(agf->agf_seqno),
+ &agflbp);
+ if (error)
return error;
- agfl = XFS_BUF_TO_AGFL(agflbp);
+
+
/*
* Get the block number and update the data structures.
*/
- bno = be32_to_cpu(agfl->agfl_bno[be32_to_cpu(agf->agf_flfirst)]);
+ agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agflbp);
+ bno = be32_to_cpu(agfl_bno[be32_to_cpu(agf->agf_flfirst)]);
be32_add_cpu(&agf->agf_flfirst, 1);
xfs_trans_brelse(tp, agflbp);
if (be32_to_cpu(agf->agf_flfirst) == XFS_AGFL_SIZE(mp))
@@ -2005,11 +2098,14 @@ xfs_alloc_log_agf(
offsetof(xfs_agf_t, agf_freeblks),
offsetof(xfs_agf_t, agf_longest),
offsetof(xfs_agf_t, agf_btreeblks),
+ offsetof(xfs_agf_t, agf_uuid),
sizeof(xfs_agf_t)
};
trace_xfs_agf(tp->t_mountp, XFS_BUF_TO_AGF(bp), fields, _RET_IP_);
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGF_BUF);
+
xfs_btree_offsets(fields, offsets, XFS_AGF_NUM_BITS, &first, &last);
xfs_trans_log_buf(tp, bp, (uint)first, (uint)last);
}
@@ -2046,12 +2142,13 @@ xfs_alloc_put_freelist(
int btreeblk) /* block came from a AGF btree */
{
xfs_agf_t *agf; /* a.g. freespace structure */
- xfs_agfl_t *agfl; /* a.g. free block array */
__be32 *blockp;/* pointer to array entry */
int error;
int logflags;
xfs_mount_t *mp; /* mount structure */
xfs_perag_t *pag; /* per allocation group data */
+ __be32 *agfl_bno;
+ int startoff;
agf = XFS_BUF_TO_AGF(agbp);
mp = tp->t_mountp;
@@ -2059,7 +2156,6 @@ xfs_alloc_put_freelist(
if (!agflbp && (error = xfs_alloc_read_agfl(mp, tp,
be32_to_cpu(agf->agf_seqno), &agflbp)))
return error;
- agfl = XFS_BUF_TO_AGFL(agflbp);
be32_add_cpu(&agf->agf_fllast, 1);
if (be32_to_cpu(agf->agf_fllast) == XFS_AGFL_SIZE(mp))
agf->agf_fllast = 0;
@@ -2080,16 +2176,101 @@ xfs_alloc_put_freelist(
xfs_alloc_log_agf(tp, agbp, logflags);
ASSERT(be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp));
- blockp = &agfl->agfl_bno[be32_to_cpu(agf->agf_fllast)];
+
+ agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agflbp);
+ blockp = &agfl_bno[be32_to_cpu(agf->agf_fllast)];
*blockp = cpu_to_be32(bno);
+ startoff = (char *)blockp - (char *)agflbp->b_addr;
+
xfs_alloc_log_agf(tp, agbp, logflags);
- xfs_trans_log_buf(tp, agflbp,
- (int)((xfs_caddr_t)blockp - (xfs_caddr_t)agfl),
- (int)((xfs_caddr_t)blockp - (xfs_caddr_t)agfl +
- sizeof(xfs_agblock_t) - 1));
+
+ xfs_trans_buf_set_type(tp, agflbp, XFS_BLFT_AGFL_BUF);
+ xfs_trans_log_buf(tp, agflbp, startoff,
+ startoff + sizeof(xfs_agblock_t) - 1);
return 0;
}
+static bool
+xfs_agf_verify(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp)
+ {
+ struct xfs_agf *agf = XFS_BUF_TO_AGF(bp);
+
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_uuid))
+ return false;
+
+ if (!(agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
+ XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
+ be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
+ be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
+ be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
+ be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp)))
+ return false;
+
+ /*
+ * during growfs operations, the perag is not fully initialised,
+ * so we can't use it for any useful checking. growfs ensures we can't
+ * use it by using uncached buffers that don't have the perag attached
+ * so we can detect and avoid this problem.
+ */
+ if (bp->b_pag && be32_to_cpu(agf->agf_seqno) != bp->b_pag->pag_agno)
+ return false;
+
+ if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
+ be32_to_cpu(agf->agf_btreeblks) > be32_to_cpu(agf->agf_length))
+ return false;
+
+ return true;;
+
+}
+
+static void
+xfs_agf_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !xfs_buf_verify_cksum(bp, XFS_AGF_CRC_OFF))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (XFS_TEST_ERROR(!xfs_agf_verify(mp, bp), mp,
+ XFS_ERRTAG_ALLOC_READ_AGF,
+ XFS_RANDOM_ALLOC_READ_AGF))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+}
+
+static void
+xfs_agf_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+
+ if (!xfs_agf_verify(mp, bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (bip)
+ XFS_BUF_TO_AGF(bp)->agf_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_AGF_CRC_OFF);
+}
+
+const struct xfs_buf_ops xfs_agf_buf_ops = {
+ .verify_read = xfs_agf_read_verify,
+ .verify_write = xfs_agf_write_verify,
+};
+
/*
* Read in the allocation group header (free/alloc section).
*/
@@ -2101,44 +2282,21 @@ xfs_read_agf(
int flags, /* XFS_BUF_ */
struct xfs_buf **bpp) /* buffer for the ag freelist header */
{
- struct xfs_agf *agf; /* ag freelist header */
- int agf_ok; /* set if agf is consistent */
int error;
+ trace_xfs_read_agf(mp, agno);
+
ASSERT(agno != NULLAGNUMBER);
error = xfs_trans_read_buf(
mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), flags, bpp);
+ XFS_FSS_TO_BB(mp, 1), flags, bpp, &xfs_agf_buf_ops);
if (error)
return error;
if (!*bpp)
return 0;
ASSERT(!(*bpp)->b_error);
- agf = XFS_BUF_TO_AGF(*bpp);
-
- /*
- * Validate the magic number of the agf block.
- */
- agf_ok =
- agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
- XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
- be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
- be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
- be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
- be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp) &&
- be32_to_cpu(agf->agf_seqno) == agno;
- if (xfs_sb_version_haslazysbcount(&mp->m_sb))
- agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
- be32_to_cpu(agf->agf_length);
- if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
- XFS_RANDOM_ALLOC_READ_AGF))) {
- XFS_CORRUPTION_ERROR("xfs_alloc_read_agf",
- XFS_ERRLEVEL_LOW, mp, agf);
- xfs_trans_brelse(tp, *bpp);
- return XFS_ERROR(EFSCORRUPTED);
- }
xfs_buf_set_ref(*bpp, XFS_AGF_REF);
return 0;
}
@@ -2158,8 +2316,9 @@ xfs_alloc_read_agf(
struct xfs_perag *pag; /* per allocation group data */
int error;
- ASSERT(agno != NULLAGNUMBER);
+ trace_xfs_alloc_read_agf(mp, agno);
+ ASSERT(agno != NULLAGNUMBER);
error = xfs_read_agf(mp, tp, agno,
(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
bpp);
@@ -2207,7 +2366,7 @@ xfs_alloc_read_agf(
* group or loop over the allocation groups to find the result.
*/
int /* error */
-__xfs_alloc_vextent(
+xfs_alloc_vextent(
xfs_alloc_arg_t *args) /* allocation argument structure */
{
xfs_agblock_t agsize; /* allocation group size */
@@ -2417,37 +2576,6 @@ error0:
return error;
}
-static void
-xfs_alloc_vextent_worker(
- struct work_struct *work)
-{
- struct xfs_alloc_arg *args = container_of(work,
- struct xfs_alloc_arg, work);
- unsigned long pflags;
-
- /* we are in a transaction context here */
- current_set_flags_nested(&pflags, PF_FSTRANS);
-
- args->result = __xfs_alloc_vextent(args);
- complete(args->done);
-
- current_restore_flags_nested(&pflags, PF_FSTRANS);
-}
-
-
-int /* error */
-xfs_alloc_vextent(
- xfs_alloc_arg_t *args) /* allocation argument structure */
-{
- DECLARE_COMPLETION_ONSTACK(done);
-
- args->done = &done;
- INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker);
- queue_work(xfs_alloc_wq, &args->work);
- wait_for_completion(&done);
- return args->result;
-}
-
/*
* Free an extent.
* Just break up the extent address and hand off to xfs_free_ag_extent
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 93be4a667ca..feacb061bab 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -120,9 +120,6 @@ typedef struct xfs_alloc_arg {
char isfl; /* set if is freelist blocks - !acctg */
char userdata; /* set if this is user data */
xfs_fsblock_t firstblock; /* io first block allocated */
- struct completion *done;
- struct work_struct work;
- int result;
} xfs_alloc_arg_t;
/*
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index f1647caace8..8358f1ded94 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -17,22 +17,21 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_cksum.h"
+#include "xfs_trans.h"
STATIC struct xfs_btree_cur *
@@ -71,7 +70,6 @@ xfs_allocbt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
- int length,
int *stat)
{
int error;
@@ -121,6 +119,8 @@ xfs_allocbt_free_block(
xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
XFS_EXTENT_BUSY_SKIP_DISCARD);
xfs_trans_agbtree_delta(cur->bc_tp, -1);
+
+ xfs_trans_binval(cur->bc_tp, bp);
return 0;
}
@@ -270,7 +270,122 @@ xfs_allocbt_key_diff(
return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
}
-#ifdef DEBUG
+static bool
+xfs_allocbt_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ struct xfs_perag *pag = bp->b_pag;
+ unsigned int level;
+
+ /*
+ * magic number and level verification
+ *
+ * During growfs operations, we can't verify the exact level or owner as
+ * the perag is not fully initialised and hence not attached to the
+ * buffer. In this case, check against the maximum tree depth.
+ *
+ * Similarly, during log recovery we will have a perag structure
+ * attached, but the agf information will not yet have been initialised
+ * from the on disk AGF. Again, we can only check against maximum limits
+ * in this case.
+ */
+ level = be16_to_cpu(block->bb_level);
+ switch (block->bb_magic) {
+ case cpu_to_be32(XFS_ABTB_CRC_MAGIC):
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return false;
+ if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
+ return false;
+ if (pag &&
+ be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+ return false;
+ /* fall through */
+ case cpu_to_be32(XFS_ABTB_MAGIC):
+ if (pag && pag->pagf_init) {
+ if (level >= pag->pagf_levels[XFS_BTNUM_BNOi])
+ return false;
+ } else if (level >= mp->m_ag_maxlevels)
+ return false;
+ break;
+ case cpu_to_be32(XFS_ABTC_CRC_MAGIC):
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return false;
+ if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
+ return false;
+ if (pag &&
+ be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+ return false;
+ /* fall through */
+ case cpu_to_be32(XFS_ABTC_MAGIC):
+ if (pag && pag->pagf_init) {
+ if (level >= pag->pagf_levels[XFS_BTNUM_CNTi])
+ return false;
+ } else if (level >= mp->m_ag_maxlevels)
+ return false;
+ break;
+ default:
+ return false;
+ }
+
+ /* numrecs verification */
+ if (be16_to_cpu(block->bb_numrecs) > mp->m_alloc_mxr[level != 0])
+ return false;
+
+ /* sibling pointer verification */
+ if (!block->bb_u.s.bb_leftsib ||
+ (be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks &&
+ block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK)))
+ return false;
+ if (!block->bb_u.s.bb_rightsib ||
+ (be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks &&
+ block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK)))
+ return false;
+
+ return true;
+}
+
+static void
+xfs_allocbt_read_verify(
+ struct xfs_buf *bp)
+{
+ if (!xfs_btree_sblock_verify_crc(bp))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_allocbt_verify(bp))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error) {
+ trace_xfs_btree_corrupt(bp, _RET_IP_);
+ xfs_verifier_error(bp);
+ }
+}
+
+static void
+xfs_allocbt_write_verify(
+ struct xfs_buf *bp)
+{
+ if (!xfs_allocbt_verify(bp)) {
+ trace_xfs_btree_corrupt(bp, _RET_IP_);
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+ xfs_btree_sblock_calc_crc(bp);
+
+}
+
+const struct xfs_buf_ops xfs_allocbt_buf_ops = {
+ .verify_read = xfs_allocbt_read_verify,
+ .verify_write = xfs_allocbt_write_verify,
+};
+
+
+#if defined(DEBUG) || defined(XFS_WARN)
STATIC int
xfs_allocbt_keys_inorder(
struct xfs_btree_cur *cur,
@@ -325,7 +440,8 @@ static const struct xfs_btree_ops xfs_allocbt_ops = {
.init_rec_from_cur = xfs_allocbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur,
.key_diff = xfs_allocbt_key_diff,
-#ifdef DEBUG
+ .buf_ops = &xfs_allocbt_buf_ops,
+#if defined(DEBUG) || defined(XFS_WARN)
.keys_inorder = xfs_allocbt_keys_inorder,
.recs_inorder = xfs_allocbt_recs_inorder,
#endif
@@ -365,6 +481,9 @@ xfs_allocbt_init_cursor(
cur->bc_private.a.agbp = agbp;
cur->bc_private.a.agno = agno;
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
+
return cur;
}
diff --git a/fs/xfs/xfs_alloc_btree.h b/fs/xfs/xfs_alloc_btree.h
index a6caa0022c9..45e189e7e81 100644
--- a/fs/xfs/xfs_alloc_btree.h
+++ b/fs/xfs/xfs_alloc_btree.h
@@ -27,56 +27,11 @@ struct xfs_btree_cur;
struct xfs_mount;
/*
- * There are two on-disk btrees, one sorted by blockno and one sorted
- * by blockcount and blockno. All blocks look the same to make the code
- * simpler; if we have time later, we'll make the optimizations.
- */
-#define XFS_ABTB_MAGIC 0x41425442 /* 'ABTB' for bno tree */
-#define XFS_ABTC_MAGIC 0x41425443 /* 'ABTC' for cnt tree */
-
-/*
- * Data record/key structure
- */
-typedef struct xfs_alloc_rec {
- __be32 ar_startblock; /* starting block number */
- __be32 ar_blockcount; /* count of free blocks */
-} xfs_alloc_rec_t, xfs_alloc_key_t;
-
-typedef struct xfs_alloc_rec_incore {
- xfs_agblock_t ar_startblock; /* starting block number */
- xfs_extlen_t ar_blockcount; /* count of free blocks */
-} xfs_alloc_rec_incore_t;
-
-/* btree pointer type */
-typedef __be32 xfs_alloc_ptr_t;
-
-/*
- * Minimum and maximum blocksize and sectorsize.
- * The blocksize upper limit is pretty much arbitrary.
- * The sectorsize upper limit is due to sizeof(sb_sectsize).
- */
-#define XFS_MIN_BLOCKSIZE_LOG 9 /* i.e. 512 bytes */
-#define XFS_MAX_BLOCKSIZE_LOG 16 /* i.e. 65536 bytes */
-#define XFS_MIN_BLOCKSIZE (1 << XFS_MIN_BLOCKSIZE_LOG)
-#define XFS_MAX_BLOCKSIZE (1 << XFS_MAX_BLOCKSIZE_LOG)
-#define XFS_MIN_SECTORSIZE_LOG 9 /* i.e. 512 bytes */
-#define XFS_MAX_SECTORSIZE_LOG 15 /* i.e. 32768 bytes */
-#define XFS_MIN_SECTORSIZE (1 << XFS_MIN_SECTORSIZE_LOG)
-#define XFS_MAX_SECTORSIZE (1 << XFS_MAX_SECTORSIZE_LOG)
-
-/*
- * Block numbers in the AG:
- * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.
- */
-#define XFS_BNO_BLOCK(mp) ((xfs_agblock_t)(XFS_AGFL_BLOCK(mp) + 1))
-#define XFS_CNT_BLOCK(mp) ((xfs_agblock_t)(XFS_BNO_BLOCK(mp) + 1))
-
-/*
* Btree block header size depends on a superblock flag.
- *
- * (not quite yet, but soon)
*/
-#define XFS_ALLOC_BLOCK_LEN(mp) XFS_BTREE_SBLOCK_LEN
+#define XFS_ALLOC_BLOCK_LEN(mp) \
+ (xfs_sb_version_hascrc(&((mp)->m_sb)) ? \
+ XFS_BTREE_SBLOCK_CRC_LEN : XFS_BTREE_SBLOCK_LEN)
/*
* Record, key, and pointer address macros for btree blocks.
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8dad722c004..faaf716e208 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -16,21 +16,25 @@
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
-#include "xfs_log.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_trans.h"
#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_iomap.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dinode.h"
+#include <linux/aio.h>
#include <linux/gfp.h>
#include <linux/mpage.h>
#include <linux/pagevec.h>
@@ -85,14 +89,6 @@ xfs_destroy_ioend(
bh->b_end_io(bh, !ioend->io_error);
}
- if (ioend->io_iocb) {
- if (ioend->io_isasync) {
- aio_complete(ioend->io_iocb, ioend->io_error ?
- ioend->io_error : ioend->io_result, 0);
- }
- inode_dio_done(ioend->io_inode);
- }
-
mempool_free(ioend, xfs_ioend_pool);
}
@@ -115,7 +111,7 @@ xfs_setfilesize_trans_alloc(
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
- error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
@@ -124,6 +120,12 @@ xfs_setfilesize_trans_alloc(
ioend->io_append_trans = tp;
/*
+ * We may pass freeze protection with a transaction. So tell lockdep
+ * we released it.
+ */
+ rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+ 1, _THIS_IP_);
+ /*
* We hand off the transaction to the completion thread now, so
* clear the flag here.
*/
@@ -143,11 +145,13 @@ xfs_setfilesize(
xfs_fsize_t isize;
/*
- * The transaction was allocated in the I/O submission thread,
- * thus we need to mark ourselves as beeing in a transaction
- * manually.
+ * The transaction may have been allocated in the I/O submission thread,
+ * thus we need to mark ourselves as beeing in a transaction manually.
+ * Similarly for freeze protection.
*/
current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+ rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+ 0, 1, _THIS_IP_);
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size);
@@ -179,9 +183,10 @@ xfs_finish_ioend(
if (atomic_dec_and_test(&ioend->io_remaining)) {
struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount;
- if (ioend->io_type == IO_UNWRITTEN)
+ if (ioend->io_type == XFS_IO_UNWRITTEN)
queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
- else if (ioend->io_append_trans)
+ else if (ioend->io_append_trans ||
+ (ioend->io_isdirect && xfs_ioend_is_append(ioend)))
queue_work(mp->m_data_workqueue, &ioend->io_work);
else
xfs_destroy_ioend(ioend);
@@ -210,36 +215,32 @@ xfs_end_io(
* For unwritten extents we need to issue transactions to convert a
* range to normal written extens after the data I/O has finished.
*/
- if (ioend->io_type == IO_UNWRITTEN) {
+ if (ioend->io_type == XFS_IO_UNWRITTEN) {
+ error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
+ ioend->io_size);
+ } else if (ioend->io_isdirect && xfs_ioend_is_append(ioend)) {
/*
- * For buffered I/O we never preallocate a transaction when
- * doing the unwritten extent conversion, but for direct I/O
- * we do not know if we are converting an unwritten extent
- * or not at the point where we preallocate the transaction.
+ * For direct I/O we do not know if we need to allocate blocks
+ * or not so we can't preallocate an append transaction as that
+ * results in nested reservations and log space deadlocks. Hence
+ * allocate the transaction here. While this is sub-optimal and
+ * can block IO completion for some time, we're stuck with doing
+ * it this way until we can pass the ioend to the direct IO
+ * allocation callbacks and avoid nesting that way.
*/
- if (ioend->io_append_trans) {
- ASSERT(ioend->io_isdirect);
-
- current_set_flags_nested(
- &ioend->io_append_trans->t_pflags, PF_FSTRANS);
- xfs_trans_cancel(ioend->io_append_trans, 0);
- }
-
- error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
- ioend->io_size);
- if (error) {
- ioend->io_error = -error;
+ error = xfs_setfilesize_trans_alloc(ioend);
+ if (error)
goto done;
- }
+ error = xfs_setfilesize(ioend);
} else if (ioend->io_append_trans) {
error = xfs_setfilesize(ioend);
- if (error)
- ioend->io_error = -error;
} else {
ASSERT(!xfs_ioend_is_append(ioend));
}
done:
+ if (error)
+ ioend->io_error = -error;
xfs_destroy_ioend(ioend);
}
@@ -275,7 +276,6 @@ xfs_alloc_ioend(
* all the I/O from calling the completion routine too early.
*/
atomic_set(&ioend->io_remaining, 1);
- ioend->io_isasync = 0;
ioend->io_isdirect = 0;
ioend->io_error = 0;
ioend->io_list = NULL;
@@ -285,8 +285,6 @@ xfs_alloc_ioend(
ioend->io_buffer_tail = NULL;
ioend->io_offset = 0;
ioend->io_size = 0;
- ioend->io_iocb = NULL;
- ioend->io_result = 0;
ioend->io_append_trans = NULL;
INIT_WORK(&ioend->io_work, xfs_end_io);
@@ -312,7 +310,7 @@ xfs_map_blocks(
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
- if (type == IO_UNWRITTEN)
+ if (type == XFS_IO_UNWRITTEN)
bmapi_flags |= XFS_BMAPI_IGSTATE;
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
@@ -323,10 +321,10 @@ xfs_map_blocks(
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
- ASSERT(offset <= mp->m_maxioffset);
+ ASSERT(offset <= mp->m_super->s_maxbytes);
- if (offset + count > mp->m_maxioffset)
- count = mp->m_maxioffset - offset;
+ if (offset + count > mp->m_super->s_maxbytes)
+ count = mp->m_super->s_maxbytes - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
@@ -336,16 +334,16 @@ xfs_map_blocks(
if (error)
return -XFS_ERROR(error);
- if (type == IO_DELALLOC &&
+ if (type == XFS_IO_DELALLOC &&
(!nimaps || isnullstartblock(imap->br_startblock))) {
- error = xfs_iomap_write_allocate(ip, offset, count, imap);
+ error = xfs_iomap_write_allocate(ip, offset, imap);
if (!error)
trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
return -XFS_ERROR(error);
}
#ifdef DEBUG
- if (type == IO_UNWRITTEN) {
+ if (type == XFS_IO_UNWRITTEN) {
ASSERT(nimaps);
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
@@ -409,7 +407,7 @@ xfs_alloc_ioend_bio(
struct bio *bio = bio_alloc(GFP_NOIO, nvecs);
ASSERT(bio->bi_private == NULL);
- bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
return bio;
}
@@ -445,7 +443,7 @@ xfs_start_page_writeback(
end_page_writeback(page);
}
-static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
+static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
{
return bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
}
@@ -466,11 +464,17 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
*
* The fix is two passes across the ioend list - one to start writeback on the
* buffer_heads, and then submit them for I/O on the second pass.
+ *
+ * If @fail is non-zero, it means that we have a situation where some part of
+ * the submission process has failed after we have marked paged for writeback
+ * and unlocked them. In this situation, we need to fail the ioend chain rather
+ * than submit it to IO. This typically only happens on a filesystem shutdown.
*/
STATIC void
xfs_submit_ioend(
struct writeback_control *wbc,
- xfs_ioend_t *ioend)
+ xfs_ioend_t *ioend,
+ int fail)
{
xfs_ioend_t *head = ioend;
xfs_ioend_t *next;
@@ -491,6 +495,18 @@ xfs_submit_ioend(
next = ioend->io_list;
bio = NULL;
+ /*
+ * If we are failing the IO now, just mark the ioend with an
+ * error and finish it. This will run IO completion immediately
+ * as there is only one reference to the ioend at this point in
+ * time.
+ */
+ if (fail) {
+ ioend->io_error = -fail;
+ xfs_finish_ioend(ioend);
+ continue;
+ }
+
for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
if (!bio) {
@@ -501,7 +517,7 @@ xfs_submit_ioend(
goto retry;
}
- if (bio_add_buffer(bio, bh) != bh->b_size) {
+ if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
xfs_submit_ioend_bio(wbc, ioend, bio);
goto retry;
}
@@ -616,38 +632,46 @@ xfs_map_at_offset(
}
/*
- * Test if a given page is suitable for writing as part of an unwritten
- * or delayed allocate extent.
+ * Test if a given page contains at least one buffer of a given @type.
+ * If @check_all_buffers is true, then we walk all the buffers in the page to
+ * try to find one of the type passed in. If it is not set, then the caller only
+ * needs to check the first buffer on the page for a match.
*/
-STATIC int
+STATIC bool
xfs_check_page_type(
struct page *page,
- unsigned int type)
+ unsigned int type,
+ bool check_all_buffers)
{
- if (PageWriteback(page))
- return 0;
+ struct buffer_head *bh;
+ struct buffer_head *head;
- if (page->mapping && page_has_buffers(page)) {
- struct buffer_head *bh, *head;
- int acceptable = 0;
+ if (PageWriteback(page))
+ return false;
+ if (!page->mapping)
+ return false;
+ if (!page_has_buffers(page))
+ return false;
- bh = head = page_buffers(page);
- do {
- if (buffer_unwritten(bh))
- acceptable += (type == IO_UNWRITTEN);
- else if (buffer_delay(bh))
- acceptable += (type == IO_DELALLOC);
- else if (buffer_dirty(bh) && buffer_mapped(bh))
- acceptable += (type == IO_OVERWRITE);
- else
- break;
- } while ((bh = bh->b_this_page) != head);
+ bh = head = page_buffers(page);
+ do {
+ if (buffer_unwritten(bh)) {
+ if (type == XFS_IO_UNWRITTEN)
+ return true;
+ } else if (buffer_delay(bh)) {
+ if (type == XFS_IO_DELALLOC)
+ return true;
+ } else if (buffer_dirty(bh) && buffer_mapped(bh)) {
+ if (type == XFS_IO_OVERWRITE)
+ return true;
+ }
- if (acceptable)
- return 1;
- }
+ /* If we are only checking the first buffer, we are done now. */
+ if (!check_all_buffers)
+ break;
+ } while ((bh = bh->b_this_page) != head);
- return 0;
+ return false;
}
/*
@@ -681,7 +705,7 @@ xfs_convert_page(
goto fail_unlock_page;
if (page->mapping != inode->i_mapping)
goto fail_unlock_page;
- if (!xfs_check_page_type(page, (*ioendp)->io_type))
+ if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
goto fail_unlock_page;
/*
@@ -701,12 +725,40 @@ xfs_convert_page(
(xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
i_size_read(inode));
+ /*
+ * If the current map does not span the entire page we are about to try
+ * to write, then give up. The only way we can write a page that spans
+ * multiple mappings in a single writeback iteration is via the
+ * xfs_vm_writepage() function. Data integrity writeback requires the
+ * entire page to be written in a single attempt, otherwise the part of
+ * the page we don't write here doesn't get written as part of the data
+ * integrity sync.
+ *
+ * For normal writeback, we also don't attempt to write partial pages
+ * here as it simply means that write_cache_pages() will see it under
+ * writeback and ignore the page until some point in the future, at
+ * which time this will be the only page in the file that needs
+ * writeback. Hence for more optimal IO patterns, we should always
+ * avoid partial page writeback due to multiple mappings on a page here.
+ */
+ if (!xfs_imap_valid(inode, imap, end_offset))
+ goto fail_unlock_page;
+
len = 1 << inode->i_blkbits;
p_offset = min_t(unsigned long, end_offset & (PAGE_CACHE_SIZE - 1),
PAGE_CACHE_SIZE);
p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
page_dirty = p_offset / len;
+ /*
+ * The moment we find a buffer that doesn't match our current type
+ * specification or can't be written, abort the loop and start
+ * writeback. As per the above xfs_imap_valid() check, only
+ * xfs_vm_writepage() can handle partial page writeback fully - we are
+ * limited here to the buffers that are contiguous with the current
+ * ioend, and hence a buffer we can't write breaks that contiguity and
+ * we have to defer the rest of the IO to xfs_vm_writepage().
+ */
bh = head = page_buffers(page);
do {
if (offset >= end_offset)
@@ -715,25 +767,26 @@ xfs_convert_page(
uptodate = 0;
if (!(PageUptodate(page) || buffer_uptodate(bh))) {
done = 1;
- continue;
+ break;
}
if (buffer_unwritten(bh) || buffer_delay(bh) ||
buffer_mapped(bh)) {
if (buffer_unwritten(bh))
- type = IO_UNWRITTEN;
+ type = XFS_IO_UNWRITTEN;
else if (buffer_delay(bh))
- type = IO_DELALLOC;
+ type = XFS_IO_DELALLOC;
else
- type = IO_OVERWRITE;
+ type = XFS_IO_OVERWRITE;
- if (!xfs_imap_valid(inode, imap, offset)) {
- done = 1;
- continue;
- }
+ /*
+ * imap should always be valid because of the above
+ * partial page end_offset check on the imap.
+ */
+ ASSERT(xfs_imap_valid(inode, imap, offset));
lock_buffer(bh);
- if (type != IO_OVERWRITE)
+ if (type != XFS_IO_OVERWRITE)
xfs_map_at_offset(inode, bh, imap, offset);
xfs_add_to_ioend(inode, bh, offset, type,
ioendp, done);
@@ -742,6 +795,7 @@ xfs_convert_page(
count++;
} else {
done = 1;
+ break;
}
} while (offset += len, (bh = bh->b_this_page) != head);
@@ -800,10 +854,12 @@ xfs_cluster_write(
STATIC void
xfs_vm_invalidatepage(
struct page *page,
- unsigned long offset)
+ unsigned int offset,
+ unsigned int length)
{
- trace_xfs_invalidatepage(page->mapping->host, page, offset);
- block_invalidatepage(page, offset);
+ trace_xfs_invalidatepage(page->mapping->host, page, offset,
+ length);
+ block_invalidatepage(page, offset, length);
}
/*
@@ -831,7 +887,7 @@ xfs_aops_discard_page(
struct buffer_head *bh, *head;
loff_t offset = page_offset(page);
- if (!xfs_check_page_type(page, IO_DELALLOC))
+ if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
goto out_invalidate;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -867,7 +923,7 @@ next_buffer:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_invalidate:
- xfs_vm_invalidatepage(page, 0);
+ xfs_vm_invalidatepage(page, 0, PAGE_CACHE_SIZE);
return;
}
@@ -897,7 +953,7 @@ xfs_vm_writepage(
int count = 0;
int nonblocking = 0;
- trace_xfs_writepage(inode, page, 0);
+ trace_xfs_writepage(inode, page, 0, 0);
ASSERT(page_has_buffers(page));
@@ -919,29 +975,81 @@ xfs_vm_writepage(
* Given that we do not allow direct reclaim to call us, we should
* never be called while in a filesystem transaction.
*/
- if (WARN_ON(current->flags & PF_FSTRANS))
+ if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
goto redirty;
/* Is this page beyond the end of the file? */
offset = i_size_read(inode);
end_index = offset >> PAGE_CACHE_SHIFT;
last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
- if (page->index >= end_index) {
- if ((page->index >= end_index + 1) ||
- !(i_size_read(inode) & (PAGE_CACHE_SIZE - 1))) {
- unlock_page(page);
- return 0;
- }
+
+ /*
+ * The page index is less than the end_index, adjust the end_offset
+ * to the highest offset that this page should represent.
+ * -----------------------------------------------------
+ * | file mapping | <EOF> |
+ * -----------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | |
+ * ^--------------------------------^----------|--------
+ * | desired writeback range | see else |
+ * ---------------------------------^------------------|
+ */
+ if (page->index < end_index)
+ end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
+ else {
+ /*
+ * Check whether the page to write out is beyond or straddles
+ * i_size or not.
+ * -------------------------------------------------------
+ * | file mapping | <EOF> |
+ * -------------------------------------------------------
+ * | Page ... | Page N-2 | Page N-1 | Page N | Beyond |
+ * ^--------------------------------^-----------|---------
+ * | | Straddles |
+ * ---------------------------------^-----------|--------|
+ */
+ unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
+
+ /*
+ * Skip the page if it is fully outside i_size, e.g. due to a
+ * truncate operation that is in progress. We must redirty the
+ * page so that reclaim stops reclaiming it. Otherwise
+ * xfs_vm_releasepage() is called on it and gets confused.
+ *
+ * Note that the end_index is unsigned long, it would overflow
+ * if the given offset is greater than 16TB on 32-bit system
+ * and if we do check the page is fully outside i_size or not
+ * via "if (page->index >= end_index + 1)" as "end_index + 1"
+ * will be evaluated to 0. Hence this page will be redirtied
+ * and be written out repeatedly which would result in an
+ * infinite loop, the user program that perform this operation
+ * will hang. Instead, we can verify this situation by checking
+ * if the page to write is totally beyond the i_size or if it's
+ * offset is just equal to the EOF.
+ */
+ if (page->index > end_index ||
+ (page->index == end_index && offset_into_page == 0))
+ goto redirty;
+
+ /*
+ * The page straddles i_size. It must be zeroed out on each
+ * and every writepage invocation because it may be mmapped.
+ * "A file is mapped in multiples of the page size. For a file
+ * that is not a multiple of the page size, the remaining
+ * memory is zeroed when mapped, and writes to that region are
+ * not written out to the file."
+ */
+ zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
+
+ /* Adjust the end_offset to the end of file */
+ end_offset = offset;
}
- end_offset = min_t(unsigned long long,
- (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
- offset);
len = 1 << inode->i_blkbits;
bh = head = page_buffers(page);
offset = page_offset(page);
- type = IO_OVERWRITE;
+ type = XFS_IO_OVERWRITE;
if (wbc->sync_mode == WB_SYNC_NONE)
nonblocking = 1;
@@ -966,18 +1074,18 @@ xfs_vm_writepage(
}
if (buffer_unwritten(bh)) {
- if (type != IO_UNWRITTEN) {
- type = IO_UNWRITTEN;
+ if (type != XFS_IO_UNWRITTEN) {
+ type = XFS_IO_UNWRITTEN;
imap_valid = 0;
}
} else if (buffer_delay(bh)) {
- if (type != IO_DELALLOC) {
- type = IO_DELALLOC;
+ if (type != XFS_IO_DELALLOC) {
+ type = XFS_IO_DELALLOC;
imap_valid = 0;
}
} else if (buffer_uptodate(bh)) {
- if (type != IO_OVERWRITE) {
- type = IO_OVERWRITE;
+ if (type != XFS_IO_OVERWRITE) {
+ type = XFS_IO_OVERWRITE;
imap_valid = 0;
}
} else {
@@ -1013,7 +1121,7 @@ xfs_vm_writepage(
}
if (imap_valid) {
lock_buffer(bh);
- if (type != IO_OVERWRITE)
+ if (type != XFS_IO_OVERWRITE)
xfs_map_at_offset(inode, bh, &imap, offset);
xfs_add_to_ioend(inode, bh, offset, type, &ioend,
new_ioend);
@@ -1030,7 +1138,18 @@ xfs_vm_writepage(
xfs_start_page_writeback(page, 1, count);
- if (ioend && imap_valid) {
+ /* if there is no IO to be submitted for this page, we are done */
+ if (!ioend)
+ return 0;
+
+ ASSERT(iohead);
+
+ /*
+ * Any errors from this point onwards need tobe reported through the IO
+ * completion path as we have marked the initial page as under writeback
+ * and unlocked it.
+ */
+ if (imap_valid) {
xfs_off_t end_index;
end_index = imap.br_startoff + imap.br_blockcount;
@@ -1049,20 +1168,15 @@ xfs_vm_writepage(
wbc, end_index);
}
- if (iohead) {
- /*
- * Reserve log space if we might write beyond the on-disk
- * inode size.
- */
- if (ioend->io_type != IO_UNWRITTEN &&
- xfs_ioend_is_append(ioend)) {
- err = xfs_setfilesize_trans_alloc(ioend);
- if (err)
- goto error;
- }
- xfs_submit_ioend(wbc, iohead);
- }
+ /*
+ * Reserve log space if we might write beyond the on-disk inode size.
+ */
+ err = 0;
+ if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
+ err = xfs_setfilesize_trans_alloc(ioend);
+
+ xfs_submit_ioend(wbc, iohead, err);
return 0;
@@ -1107,13 +1221,13 @@ xfs_vm_releasepage(
{
int delalloc, unwritten;
- trace_xfs_releasepage(page->mapping->host, page, 0);
+ trace_xfs_releasepage(page->mapping->host, page, 0, 0);
xfs_count_page_state(page, &delalloc, &unwritten);
- if (WARN_ON(delalloc))
+ if (WARN_ON_ONCE(delalloc))
return 0;
- if (WARN_ON(unwritten))
+ if (WARN_ON_ONCE(unwritten))
return 0;
return try_to_free_buffers(page);
@@ -1159,12 +1273,12 @@ __xfs_get_blocks(
lockmode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lockmode);
} else {
- lockmode = xfs_ilock_map_shared(ip);
+ lockmode = xfs_ilock_data_map_shared(ip);
}
- ASSERT(offset <= mp->m_maxioffset);
- if (offset + size > mp->m_maxioffset)
- size = mp->m_maxioffset - offset;
+ ASSERT(offset <= mp->m_super->s_maxbytes);
+ if (offset + size > mp->m_super->s_maxbytes)
+ size = mp->m_super->s_maxbytes - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
@@ -1226,8 +1340,10 @@ __xfs_get_blocks(
if (create || !ISUNWRITTEN(&imap))
xfs_map_buffer(inode, bh_result, &imap, offset);
if (create && ISUNWRITTEN(&imap)) {
- if (direct)
+ if (direct) {
bh_result->b_private = inode;
+ set_buffer_defer_completion(bh_result);
+ }
set_buffer_unwritten(bh_result);
}
}
@@ -1265,6 +1381,14 @@ __xfs_get_blocks(
/*
* If this is O_DIRECT or the mpage code calling tell them how large
* the mapping is, so that we can avoid repeated get_blocks calls.
+ *
+ * If the mapping spans EOF, then we have to break the mapping up as the
+ * mapping for blocks beyond EOF must be marked new so that sub block
+ * regions can be correctly zeroed. We can't do this for mappings within
+ * EOF unless the mapping was just allocated or is unwritten, otherwise
+ * the callers would overwrite existing data with zeros. Hence we have
+ * to split the mapping into a range up to and including EOF, and a
+ * second mapping for beyond EOF.
*/
if (direct || size > (1 << inode->i_blkbits)) {
xfs_off_t mapping_size;
@@ -1275,6 +1399,12 @@ __xfs_get_blocks(
ASSERT(mapping_size > 0);
if (mapping_size > size)
mapping_size = size;
+ if (offset < i_size_read(inode) &&
+ offset + mapping_size >= i_size_read(inode)) {
+ /* limit mapping to block that spans EOF */
+ mapping_size = roundup_64(i_size_read(inode) - offset,
+ 1 << inode->i_blkbits);
+ }
if (mapping_size > LONG_MAX)
mapping_size = LONG_MAX;
@@ -1324,9 +1454,7 @@ xfs_end_io_direct_write(
struct kiocb *iocb,
loff_t offset,
ssize_t size,
- void *private,
- int ret,
- bool is_async)
+ void *private)
{
struct xfs_ioend *ioend = iocb->private;
@@ -1348,26 +1476,18 @@ xfs_end_io_direct_write(
ioend->io_offset = offset;
ioend->io_size = size;
- ioend->io_iocb = iocb;
- ioend->io_result = ret;
if (private && size > 0)
- ioend->io_type = IO_UNWRITTEN;
+ ioend->io_type = XFS_IO_UNWRITTEN;
- if (is_async) {
- ioend->io_isasync = 1;
- xfs_finish_ioend(ioend);
- } else {
- xfs_finish_ioend_sync(ioend);
- }
+ xfs_finish_ioend_sync(ioend);
}
STATIC ssize_t
xfs_vm_direct_IO(
int rw,
struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t offset)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
struct block_device *bdev = xfs_find_bdev_for_inode(inode);
@@ -1375,43 +1495,32 @@ xfs_vm_direct_IO(
ssize_t ret;
if (rw & WRITE) {
- size_t size = iov_length(iov, nr_segs);
+ size_t size = iov_iter_count(iter);
/*
- * We need to preallocate a transaction for a size update
- * here. In the case that this write both updates the size
- * and converts at least on unwritten extent we will cancel
- * the still clean transaction after the I/O has finished.
+ * We cannot preallocate a size update transaction here as we
+ * don't know whether allocation is necessary or not. Hence we
+ * can only tell IO completion that one is necessary if we are
+ * not doing unwritten extent conversion.
*/
- iocb->private = ioend = xfs_alloc_ioend(inode, IO_DIRECT);
- if (offset + size > XFS_I(inode)->i_d.di_size) {
- ret = xfs_setfilesize_trans_alloc(ioend);
- if (ret)
- goto out_destroy_ioend;
+ iocb->private = ioend = xfs_alloc_ioend(inode, XFS_IO_DIRECT);
+ if (offset + size > XFS_I(inode)->i_d.di_size)
ioend->io_isdirect = 1;
- }
- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
- xfs_get_blocks_direct,
- xfs_end_io_direct_write, NULL, 0);
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+ offset, xfs_get_blocks_direct,
+ xfs_end_io_direct_write, NULL,
+ DIO_ASYNC_EXTEND);
if (ret != -EIOCBQUEUED && iocb->private)
- goto out_trans_cancel;
+ goto out_destroy_ioend;
} else {
- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
- xfs_get_blocks_direct,
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+ offset, xfs_get_blocks_direct,
NULL, NULL, 0);
}
return ret;
-out_trans_cancel:
- if (ioend->io_append_trans) {
- current_set_flags_nested(&ioend->io_append_trans->t_pflags,
- PF_FSTRANS);
- xfs_trans_cancel(ioend->io_append_trans, 0);
- }
out_destroy_ioend:
xfs_destroy_ioend(ioend);
return ret;
@@ -1460,13 +1569,26 @@ xfs_vm_write_failed(
loff_t pos,
unsigned len)
{
- loff_t block_offset = pos & PAGE_MASK;
+ loff_t block_offset;
loff_t block_start;
loff_t block_end;
loff_t from = pos & (PAGE_CACHE_SIZE - 1);
loff_t to = from + len;
struct buffer_head *bh, *head;
+ /*
+ * The request pos offset might be 32 or 64 bit, this is all fine
+ * on 64-bit platform. However, for 64-bit pos request on 32-bit
+ * platform, the high 32-bit will be masked off if we evaluate the
+ * block_offset via (pos & PAGE_MASK) because the PAGE_MASK is
+ * 0xfffff000 as an unsigned long, hence the result is incorrect
+ * which could cause the following ASSERT failed in most cases.
+ * In order to avoid this, we can evaluate the block_offset of the
+ * start of the page by using shifts rather than masks the mismatch
+ * problem.
+ */
+ block_offset = (pos >> PAGE_CACHE_SHIFT) << PAGE_CACHE_SHIFT;
+
ASSERT(block_offset + from == pos);
head = page_buffers(page);
@@ -1492,6 +1614,16 @@ xfs_vm_write_failed(
xfs_vm_kill_delalloc_range(inode, block_offset,
block_offset + bh->b_size);
+
+ /*
+ * This buffer does not contain data anymore. make sure anyone
+ * who finds it knows that for certain.
+ */
+ clear_buffer_delay(bh);
+ clear_buffer_uptodate(bh);
+ clear_buffer_mapped(bh);
+ clear_buffer_new(bh);
+ clear_buffer_dirty(bh);
}
}
@@ -1518,20 +1650,28 @@ xfs_vm_write_begin(
ASSERT(len <= PAGE_CACHE_SIZE);
- page = grab_cache_page_write_begin(mapping, index,
- flags | AOP_FLAG_NOFS);
+ page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
status = __block_write_begin(page, pos, len, xfs_get_blocks);
if (unlikely(status)) {
struct inode *inode = mapping->host;
+ size_t isize = i_size_read(inode);
xfs_vm_write_failed(inode, page, pos, len);
unlock_page(page);
- if (pos + len > i_size_read(inode))
- truncate_pagecache(inode, pos + len, i_size_read(inode));
+ /*
+ * If the write is beyond EOF, we only want to kill blocks
+ * allocated in this write, not blocks that were previously
+ * written successfully.
+ */
+ if (pos + len > isize) {
+ ssize_t start = max_t(ssize_t, pos, isize);
+
+ truncate_pagecache_range(inode, start, pos + len);
+ }
page_cache_release(page);
page = NULL;
@@ -1542,9 +1682,12 @@ xfs_vm_write_begin(
}
/*
- * On failure, we only need to kill delalloc blocks beyond EOF because they
- * will never be written. For blocks within EOF, generic_write_end() zeros them
- * so they are safe to leave alone and be written with all the other valid data.
+ * On failure, we only need to kill delalloc blocks beyond EOF in the range of
+ * this specific write because they will never be written. Previous writes
+ * beyond EOF where block allocation succeeded do not need to be trashed, so
+ * only new blocks from this write should be trashed. For blocks within
+ * EOF, generic_write_end() zeros them so they are safe to leave alone and be
+ * written with all the other valid data.
*/
STATIC int
xfs_vm_write_end(
@@ -1567,8 +1710,11 @@ xfs_vm_write_end(
loff_t to = pos + len;
if (to > isize) {
- truncate_pagecache(inode, to, isize);
+ /* only kill blocks in this write beyond EOF */
+ if (pos > isize)
+ isize = pos;
xfs_vm_kill_delalloc_range(inode, isize, to);
+ truncate_pagecache_range(inode, isize, to);
}
}
return ret;
@@ -1584,7 +1730,7 @@ xfs_vm_bmap(
trace_xfs_vm_bmap(XFS_I(inode));
xfs_ilock(ip, XFS_IOLOCK_SHARED);
- xfs_flush_pages(ip, (xfs_off_t)0, -1, 0, FI_REMAPF);
+ filemap_write_and_wait(mapping);
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return generic_block_bmap(mapping, block, xfs_get_blocks);
}
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 84eafbcb0d9..f94dd459dff 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -24,17 +24,17 @@ extern mempool_t *xfs_ioend_pool;
* Types of I/O for bmap clustering and I/O completion tracking.
*/
enum {
- IO_DIRECT = 0, /* special case for direct I/O ioends */
- IO_DELALLOC, /* mapping covers delalloc region */
- IO_UNWRITTEN, /* mapping covers allocated but uninitialized data */
- IO_OVERWRITE, /* mapping covers already allocated extent */
+ XFS_IO_DIRECT = 0, /* special case for direct I/O ioends */
+ XFS_IO_DELALLOC, /* covers delalloc region */
+ XFS_IO_UNWRITTEN, /* covers allocated but uninitialized data */
+ XFS_IO_OVERWRITE, /* covers already allocated extent */
};
#define XFS_IO_TYPES \
{ 0, "" }, \
- { IO_DELALLOC, "delalloc" }, \
- { IO_UNWRITTEN, "unwritten" }, \
- { IO_OVERWRITE, "overwrite" }
+ { XFS_IO_DELALLOC, "delalloc" }, \
+ { XFS_IO_UNWRITTEN, "unwritten" }, \
+ { XFS_IO_OVERWRITE, "overwrite" }
/*
* xfs_ioend struct manages large extent writes for XFS.
@@ -45,7 +45,6 @@ typedef struct xfs_ioend {
unsigned int io_type; /* delalloc / unwritten */
int io_error; /* I/O error code */
atomic_t io_remaining; /* hold count */
- unsigned int io_isasync : 1; /* needs aio_complete */
unsigned int io_isdirect : 1;/* direct I/O */
struct inode *io_inode; /* file being written to */
struct buffer_head *io_buffer_head;/* buffer linked list head */
@@ -54,8 +53,6 @@ typedef struct xfs_ioend {
xfs_off_t io_offset; /* offset in the file */
struct work_struct io_work; /* xfsdatad work queue */
struct xfs_trans *io_append_trans;/* xact. for size update */
- struct kiocb *io_iocb;
- int io_result;
} xfs_ioend_t;
extern const struct address_space_operations xfs_address_space_operations;
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index a17ff01b5ad..bfe36fc2cdc 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -15,31 +15,34 @@
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
-
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
#include "xfs_attr_sf.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
#include "xfs_attr.h"
#include "xfs_attr_leaf.h"
+#include "xfs_attr_remote.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
+#include "xfs_dinode.h"
/*
* xfs_attr.c
@@ -62,7 +65,6 @@ STATIC int xfs_attr_shortform_addname(xfs_da_args_t *args);
STATIC int xfs_attr_leaf_get(xfs_da_args_t *args);
STATIC int xfs_attr_leaf_addname(xfs_da_args_t *args);
STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args);
-STATIC int xfs_attr_leaf_list(xfs_attr_list_context_t *context);
/*
* Internal routines when attribute list is more than one block.
@@ -70,34 +72,36 @@ STATIC int xfs_attr_leaf_list(xfs_attr_list_context_t *context);
STATIC int xfs_attr_node_get(xfs_da_args_t *args);
STATIC int xfs_attr_node_addname(xfs_da_args_t *args);
STATIC int xfs_attr_node_removename(xfs_da_args_t *args);
-STATIC int xfs_attr_node_list(xfs_attr_list_context_t *context);
STATIC int xfs_attr_fillstate(xfs_da_state_t *state);
STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
-/*
- * Routines to manipulate out-of-line attribute values.
- */
-STATIC int xfs_attr_rmtval_set(xfs_da_args_t *args);
-STATIC int xfs_attr_rmtval_remove(xfs_da_args_t *args);
-
-#define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */
STATIC int
-xfs_attr_name_to_xname(
- struct xfs_name *xname,
- const unsigned char *aname)
+xfs_attr_args_init(
+ struct xfs_da_args *args,
+ struct xfs_inode *dp,
+ const unsigned char *name,
+ int flags)
{
- if (!aname)
+
+ if (!name)
return EINVAL;
- xname->name = aname;
- xname->len = strlen((char *)aname);
- if (xname->len >= MAXNAMELEN)
+
+ memset(args, 0, sizeof(*args));
+ args->geo = dp->i_mount->m_attr_geo;
+ args->whichfork = XFS_ATTR_FORK;
+ args->dp = dp;
+ args->flags = flags;
+ args->name = name;
+ args->namelen = strlen((const char *)name);
+ if (args->namelen >= MAXNAMELEN)
return EFAULT; /* match IRIX behaviour */
+ args->hashval = xfs_da_hashname(args->name, args->namelen);
return 0;
}
-STATIC int
+int
xfs_inode_hasattr(
struct xfs_inode *ip)
{
@@ -112,78 +116,46 @@ xfs_inode_hasattr(
* Overall external interface routines.
*========================================================================*/
-STATIC int
-xfs_attr_get_int(
+int
+xfs_attr_get(
struct xfs_inode *ip,
- struct xfs_name *name,
+ const unsigned char *name,
unsigned char *value,
int *valuelenp,
int flags)
{
- xfs_da_args_t args;
- int error;
+ struct xfs_da_args args;
+ uint lock_mode;
+ int error;
+
+ XFS_STATS_INC(xs_attr_get);
+
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ return EIO;
if (!xfs_inode_hasattr(ip))
return ENOATTR;
- /*
- * Fill in the arg structure for this request.
- */
- memset((char *)&args, 0, sizeof(args));
- args.name = name->name;
- args.namelen = name->len;
+ error = xfs_attr_args_init(&args, ip, name, flags);
+ if (error)
+ return error;
+
args.value = value;
args.valuelen = *valuelenp;
- args.flags = flags;
- args.hashval = xfs_da_hashname(args.name, args.namelen);
- args.dp = ip;
- args.whichfork = XFS_ATTR_FORK;
- /*
- * Decide on what work routines to call based on the inode size.
- */
- if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+ lock_mode = xfs_ilock_attr_map_shared(ip);
+ if (!xfs_inode_hasattr(ip))
+ error = ENOATTR;
+ else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
error = xfs_attr_shortform_getvalue(&args);
- } else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK)) {
+ else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
error = xfs_attr_leaf_get(&args);
- } else {
+ else
error = xfs_attr_node_get(&args);
- }
+ xfs_iunlock(ip, lock_mode);
- /*
- * Return the number of bytes in the value to the caller.
- */
*valuelenp = args.valuelen;
-
- if (error == EEXIST)
- error = 0;
- return(error);
-}
-
-int
-xfs_attr_get(
- xfs_inode_t *ip,
- const unsigned char *name,
- unsigned char *value,
- int *valuelenp,
- int flags)
-{
- int error;
- struct xfs_name xname;
-
- XFS_STATS_INC(xs_attr_get);
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount))
- return(EIO);
-
- error = xfs_attr_name_to_xname(&xname, name);
- if (error)
- return error;
-
- xfs_ilock(ip, XFS_ILOCK_SHARED);
- error = xfs_attr_get_int(ip, &xname, value, valuelenp, flags);
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- return(error);
+ return error == EEXIST ? 0 : error;
}
/*
@@ -191,12 +163,10 @@ xfs_attr_get(
*/
STATIC int
xfs_attr_calc_size(
- struct xfs_inode *ip,
- int namelen,
- int valuelen,
+ struct xfs_da_args *args,
int *local)
{
- struct xfs_mount *mp = ip->i_mount;
+ struct xfs_mount *mp = args->dp->i_mount;
int size;
int nblks;
@@ -204,12 +174,10 @@ xfs_attr_calc_size(
* Determine space new attribute will use, and if it would be
* "local" or "remote" (note: local != inline).
*/
- size = xfs_attr_leaf_newentsize(namelen, valuelen,
- mp->m_sb.sb_blocksize, local);
-
+ size = xfs_attr_leaf_newentsize(args, local);
nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
if (*local) {
- if (size > (mp->m_sb.sb_blocksize >> 1)) {
+ if (size > (args->geo->blksize / 2)) {
/* Double split possible */
nblks *= 2;
}
@@ -218,7 +186,7 @@ xfs_attr_calc_size(
* Out of line attribute, cannot double split, but
* make room for the attribute value itself.
*/
- uint dblocks = XFS_B_TO_FSB(mp, valuelen);
+ uint dblocks = xfs_attr3_rmt_blocks(mp, args->valuelen);
nblks += dblocks;
nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK);
}
@@ -226,25 +194,38 @@ xfs_attr_calc_size(
return nblks;
}
-STATIC int
-xfs_attr_set_int(
- struct xfs_inode *dp,
- struct xfs_name *name,
- unsigned char *value,
- int valuelen,
- int flags)
+int
+xfs_attr_set(
+ struct xfs_inode *dp,
+ const unsigned char *name,
+ unsigned char *value,
+ int valuelen,
+ int flags)
{
- xfs_da_args_t args;
- xfs_fsblock_t firstblock;
- xfs_bmap_free_t flist;
- int error, err2, committed;
- xfs_mount_t *mp = dp->i_mount;
- int rsvd = (flags & ATTR_ROOT) != 0;
- int local;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_da_args args;
+ struct xfs_bmap_free flist;
+ struct xfs_trans_res tres;
+ xfs_fsblock_t firstblock;
+ int rsvd = (flags & ATTR_ROOT) != 0;
+ int error, err2, committed, local;
+
+ XFS_STATS_INC(xs_attr_set);
+
+ if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+ return EIO;
+
+ error = xfs_attr_args_init(&args, dp, name, flags);
+ if (error)
+ return error;
+
+ args.value = value;
+ args.valuelen = valuelen;
+ args.firstblock = &firstblock;
+ args.flist = &flist;
+ args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+ args.total = xfs_attr_calc_size(&args, &local);
- /*
- * Attach the dquots to the inode.
- */
error = xfs_qm_dqattach(dp, 0);
if (error)
return error;
@@ -255,32 +236,14 @@ xfs_attr_set_int(
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
- XFS_ATTR_SF_ENTSIZE_BYNAME(name->len, valuelen);
+ XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
- if ((error = xfs_bmap_add_attrfork(dp, sf_size, rsvd)))
- return(error);
+ error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
+ if (error)
+ return error;
}
/*
- * Fill in the arg structure for this request.
- */
- memset((char *)&args, 0, sizeof(args));
- args.name = name->name;
- args.namelen = name->len;
- args.value = value;
- args.valuelen = valuelen;
- args.flags = flags;
- args.hashval = xfs_da_hashname(args.name, args.namelen);
- args.dp = dp;
- args.firstblock = &firstblock;
- args.flist = &flist;
- args.whichfork = XFS_ATTR_FORK;
- args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
-
- /* Size is now blocks for attribute data */
- args.total = xfs_attr_calc_size(dp, name->len, valuelen, &local);
-
- /*
* Start our first transaction of the day.
*
* All future transactions during this code must be "chained" off
@@ -300,11 +263,14 @@ xfs_attr_set_int(
if (rsvd)
args.trans->t_flags |= XFS_TRANS_RESERVE;
- if ((error = xfs_trans_reserve(args.trans, args.total,
- XFS_ATTRSET_LOG_RES(mp, args.total), 0,
- XFS_TRANS_PERM_LOG_RES, XFS_ATTRSET_LOG_COUNT))) {
+ tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
+ M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
+ tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
+ tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
+ error = xfs_trans_reserve(args.trans, &tres, args.total, 0);
+ if (error) {
xfs_trans_cancel(args.trans, 0);
- return(error);
+ return error;
}
xfs_ilock(dp, XFS_ILOCK_EXCL);
@@ -314,7 +280,7 @@ xfs_attr_set_int(
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans, XFS_TRANS_RELEASE_LOG_RES);
- return (error);
+ return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
@@ -323,9 +289,9 @@ xfs_attr_set_int(
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
- if ((dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) ||
- ((dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS) &&
- (dp->i_d.di_anextents == 0))) {
+ if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
+ (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
+ dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
@@ -350,9 +316,8 @@ xfs_attr_set_int(
* the transaction goes to disk before returning
* to the user.
*/
- if (mp->m_flags & XFS_MOUNT_WSYNC) {
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
- }
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
@@ -362,7 +327,7 @@ xfs_attr_set_int(
XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error == 0 ? err2 : error);
+ return error ? error : err2;
}
/*
@@ -400,22 +365,19 @@ xfs_attr_set_int(
}
- if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+ if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
- } else {
+ else
error = xfs_attr_node_addname(&args);
- }
- if (error) {
+ if (error)
goto out;
- }
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
- if (mp->m_flags & XFS_MOUNT_WSYNC) {
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
- }
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
@@ -427,65 +389,47 @@ xfs_attr_set_int(
error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
+ return error;
out:
- if (args.trans)
+ if (args.trans) {
xfs_trans_cancel(args.trans,
XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
+ }
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
+ return error;
}
+/*
+ * Generic handler routine to remove a name from an attribute list.
+ * Transitions attribute list from Btree to shortform as necessary.
+ */
int
-xfs_attr_set(
- xfs_inode_t *dp,
- const unsigned char *name,
- unsigned char *value,
- int valuelen,
- int flags)
+xfs_attr_remove(
+ struct xfs_inode *dp,
+ const unsigned char *name,
+ int flags)
{
- int error;
- struct xfs_name xname;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_da_args args;
+ struct xfs_bmap_free flist;
+ xfs_fsblock_t firstblock;
+ int error;
- XFS_STATS_INC(xs_attr_set);
+ XFS_STATS_INC(xs_attr_remove);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
- return (EIO);
+ return EIO;
- error = xfs_attr_name_to_xname(&xname, name);
+ if (!xfs_inode_hasattr(dp))
+ return ENOATTR;
+
+ error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
- return xfs_attr_set_int(dp, &xname, value, valuelen, flags);
-}
-
-/*
- * Generic handler routine to remove a name from an attribute list.
- * Transitions attribute list from Btree to shortform as necessary.
- */
-STATIC int
-xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
-{
- xfs_da_args_t args;
- xfs_fsblock_t firstblock;
- xfs_bmap_free_t flist;
- int error;
- xfs_mount_t *mp = dp->i_mount;
-
- /*
- * Fill in the arg structure for this request.
- */
- memset((char *)&args, 0, sizeof(args));
- args.name = name->name;
- args.namelen = name->len;
- args.flags = flags;
- args.hashval = xfs_da_hashname(args.name, args.namelen);
- args.dp = dp;
args.firstblock = &firstblock;
args.flist = &flist;
- args.total = 0;
- args.whichfork = XFS_ATTR_FORK;
/*
* we have no control over the attribute names that userspace passes us
@@ -494,9 +438,6 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
*/
args.op_flags = XFS_DA_OP_OKNOENT;
- /*
- * Attach the dquots to the inode.
- */
error = xfs_qm_dqattach(dp, 0);
if (error)
return error;
@@ -521,13 +462,11 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
if (flags & ATTR_ROOT)
args.trans->t_flags |= XFS_TRANS_RESERVE;
- if ((error = xfs_trans_reserve(args.trans,
- XFS_ATTRRM_SPACE_RES(mp),
- XFS_ATTRRM_LOG_RES(mp),
- 0, XFS_TRANS_PERM_LOG_RES,
- XFS_ATTRRM_LOG_COUNT))) {
+ error = xfs_trans_reserve(args.trans, &M_RES(mp)->tr_attrrm,
+ XFS_ATTRRM_SPACE_RES(mp), 0);
+ if (error) {
xfs_trans_cancel(args.trans, 0);
- return(error);
+ return error;
}
xfs_ilock(dp, XFS_ILOCK_EXCL);
@@ -537,35 +476,26 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
*/
xfs_trans_ijoin(args.trans, dp, 0);
- /*
- * Decide on what work routines to call based on the inode size.
- */
if (!xfs_inode_hasattr(dp)) {
error = XFS_ERROR(ENOATTR);
- goto out;
- }
- if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+ } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
error = xfs_attr_shortform_remove(&args);
- if (error) {
- goto out;
- }
} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
error = xfs_attr_leaf_removename(&args);
} else {
error = xfs_attr_node_removename(&args);
}
- if (error) {
+
+ if (error)
goto out;
- }
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
- if (mp->m_flags & XFS_MOUNT_WSYNC) {
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
- }
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
@@ -577,267 +507,17 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
+ return error;
out:
- if (args.trans)
+ if (args.trans) {
xfs_trans_cancel(args.trans,
XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
-}
-
-int
-xfs_attr_remove(
- xfs_inode_t *dp,
- const unsigned char *name,
- int flags)
-{
- int error;
- struct xfs_name xname;
-
- XFS_STATS_INC(xs_attr_remove);
-
- if (XFS_FORCED_SHUTDOWN(dp->i_mount))
- return (EIO);
-
- error = xfs_attr_name_to_xname(&xname, name);
- if (error)
- return error;
-
- xfs_ilock(dp, XFS_ILOCK_SHARED);
- if (!xfs_inode_hasattr(dp)) {
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
- return XFS_ERROR(ENOATTR);
}
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
-
- return xfs_attr_remove_int(dp, &xname, flags);
-}
-
-int
-xfs_attr_list_int(xfs_attr_list_context_t *context)
-{
- int error;
- xfs_inode_t *dp = context->dp;
-
- XFS_STATS_INC(xs_attr_list);
-
- if (XFS_FORCED_SHUTDOWN(dp->i_mount))
- return EIO;
-
- xfs_ilock(dp, XFS_ILOCK_SHARED);
-
- /*
- * Decide on what work routines to call based on the inode size.
- */
- if (!xfs_inode_hasattr(dp)) {
- error = 0;
- } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- error = xfs_attr_shortform_list(context);
- } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
- error = xfs_attr_leaf_list(context);
- } else {
- error = xfs_attr_node_list(context);
- }
-
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
-
- return error;
-}
-
-#define ATTR_ENTBASESIZE /* minimum bytes used by an attr */ \
- (((struct attrlist_ent *) 0)->a_name - (char *) 0)
-#define ATTR_ENTSIZE(namelen) /* actual bytes used by an attr */ \
- ((ATTR_ENTBASESIZE + (namelen) + 1 + sizeof(u_int32_t)-1) \
- & ~(sizeof(u_int32_t)-1))
-
-/*
- * Format an attribute and copy it out to the user's buffer.
- * Take care to check values and protect against them changing later,
- * we may be reading them directly out of a user buffer.
- */
-/*ARGSUSED*/
-STATIC int
-xfs_attr_put_listent(
- xfs_attr_list_context_t *context,
- int flags,
- unsigned char *name,
- int namelen,
- int valuelen,
- unsigned char *value)
-{
- struct attrlist *alist = (struct attrlist *)context->alist;
- attrlist_ent_t *aep;
- int arraytop;
-
- ASSERT(!(context->flags & ATTR_KERNOVAL));
- ASSERT(context->count >= 0);
- ASSERT(context->count < (ATTR_MAX_VALUELEN/8));
- ASSERT(context->firstu >= sizeof(*alist));
- ASSERT(context->firstu <= context->bufsize);
-
- /*
- * Only list entries in the right namespace.
- */
- if (((context->flags & ATTR_SECURE) == 0) !=
- ((flags & XFS_ATTR_SECURE) == 0))
- return 0;
- if (((context->flags & ATTR_ROOT) == 0) !=
- ((flags & XFS_ATTR_ROOT) == 0))
- return 0;
-
- arraytop = sizeof(*alist) +
- context->count * sizeof(alist->al_offset[0]);
- context->firstu -= ATTR_ENTSIZE(namelen);
- if (context->firstu < arraytop) {
- trace_xfs_attr_list_full(context);
- alist->al_more = 1;
- context->seen_enough = 1;
- return 1;
- }
-
- aep = (attrlist_ent_t *)&context->alist[context->firstu];
- aep->a_valuelen = valuelen;
- memcpy(aep->a_name, name, namelen);
- aep->a_name[namelen] = 0;
- alist->al_offset[context->count++] = context->firstu;
- alist->al_count = context->count;
- trace_xfs_attr_list_add(context);
- return 0;
-}
-
-/*
- * Generate a list of extended attribute names and optionally
- * also value lengths. Positive return value follows the XFS
- * convention of being an error, zero or negative return code
- * is the length of the buffer returned (negated), indicating
- * success.
- */
-int
-xfs_attr_list(
- xfs_inode_t *dp,
- char *buffer,
- int bufsize,
- int flags,
- attrlist_cursor_kern_t *cursor)
-{
- xfs_attr_list_context_t context;
- struct attrlist *alist;
- int error;
-
- /*
- * Validate the cursor.
- */
- if (cursor->pad1 || cursor->pad2)
- return(XFS_ERROR(EINVAL));
- if ((cursor->initted == 0) &&
- (cursor->hashval || cursor->blkno || cursor->offset))
- return XFS_ERROR(EINVAL);
-
- /*
- * Check for a properly aligned buffer.
- */
- if (((long)buffer) & (sizeof(int)-1))
- return XFS_ERROR(EFAULT);
- if (flags & ATTR_KERNOVAL)
- bufsize = 0;
-
- /*
- * Initialize the output buffer.
- */
- memset(&context, 0, sizeof(context));
- context.dp = dp;
- context.cursor = cursor;
- context.resynch = 1;
- context.flags = flags;
- context.alist = buffer;
- context.bufsize = (bufsize & ~(sizeof(int)-1)); /* align */
- context.firstu = context.bufsize;
- context.put_listent = xfs_attr_put_listent;
-
- alist = (struct attrlist *)context.alist;
- alist->al_count = 0;
- alist->al_more = 0;
- alist->al_offset[0] = context.bufsize;
-
- error = xfs_attr_list_int(&context);
- ASSERT(error >= 0);
- return error;
-}
-
-int /* error */
-xfs_attr_inactive(xfs_inode_t *dp)
-{
- xfs_trans_t *trans;
- xfs_mount_t *mp;
- int error;
-
- mp = dp->i_mount;
- ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
-
- xfs_ilock(dp, XFS_ILOCK_SHARED);
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
- return 0;
- }
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
-
- /*
- * Start our first transaction of the day.
- *
- * All future transactions during this code must be "chained" off
- * this one via the trans_dup() call. All transactions will contain
- * the inode, and the inode will always be marked with trans_ihold().
- * Since the inode will be locked in all transactions, we must log
- * the inode in every transaction to let it float upward through
- * the log.
- */
- trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
- if ((error = xfs_trans_reserve(trans, 0, XFS_ATTRINVAL_LOG_RES(mp), 0,
- XFS_TRANS_PERM_LOG_RES,
- XFS_ATTRINVAL_LOG_COUNT))) {
- xfs_trans_cancel(trans, 0);
- return(error);
- }
- xfs_ilock(dp, XFS_ILOCK_EXCL);
-
- /*
- * No need to make quota reservations here. We expect to release some
- * blocks, not allocate, in the common case.
- */
- xfs_trans_ijoin(trans, dp, 0);
-
- /*
- * Decide on what work routines to call based on the inode size.
- */
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- error = 0;
- goto out;
- }
- error = xfs_attr_root_inactive(&trans, dp);
- if (error)
- goto out;
-
- error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
- if (error)
- goto out;
-
- error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
- return(error);
-
-out:
- xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
- return(error);
+ return error;
}
-
-
/*========================================================================
* External routines when attribute list is inside the inode
*========================================================================*/
@@ -893,7 +573,7 @@ STATIC int
xfs_attr_leaf_addname(xfs_da_args_t *args)
{
xfs_inode_t *dp;
- xfs_dabuf_t *bp;
+ struct xfs_buf *bp;
int retval, error, committed, forkoff;
trace_xfs_attr_leaf_addname(args);
@@ -903,41 +583,49 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
*/
dp = args->dp;
args->blkno = 0;
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1, &bp,
- XFS_ATTR_FORK);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
- return(error);
- ASSERT(bp != NULL);
+ return error;
/*
* Look up the given attribute in the leaf block. Figure out if
* the given flags produce an error or call for an atomic rename.
*/
- retval = xfs_attr_leaf_lookup_int(bp, args);
+ retval = xfs_attr3_leaf_lookup_int(bp, args);
if ((args->flags & ATTR_REPLACE) && (retval == ENOATTR)) {
- xfs_da_brelse(args->trans, bp);
- return(retval);
+ xfs_trans_brelse(args->trans, bp);
+ return retval;
} else if (retval == EEXIST) {
if (args->flags & ATTR_CREATE) { /* pure create op */
- xfs_da_brelse(args->trans, bp);
- return(retval);
+ xfs_trans_brelse(args->trans, bp);
+ return retval;
}
trace_xfs_attr_leaf_replace(args);
+ /* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* an atomic rename */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
+ args->rmtvaluelen2 = args->rmtvaluelen;
+
+ /*
+ * clear the remote attr state now that it is saved so that the
+ * values reflect the state of the attribute we are about to
+ * add, not the attribute we just found and will remove later.
+ */
+ args->rmtblkno = 0;
+ args->rmtblkcnt = 0;
+ args->rmtvaluelen = 0;
}
/*
* Add the attribute to the leaf block, transitioning to a Btree
* if required.
*/
- retval = xfs_attr_leaf_add(bp, args);
- xfs_da_buf_done(bp);
+ retval = xfs_attr3_leaf_add(bp, args);
if (retval == ENOSPC) {
/*
* Promote the attribute list to the Btree format, then
@@ -945,7 +633,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
* can manage its own transactions.
*/
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_attr_leaf_to_node(args);
+ error = xfs_attr3_leaf_to_node(args);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
@@ -1010,7 +698,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
* In a separate transaction, set the incomplete flag on the
* "old" attr and clear the incomplete flag on the "new" attr.
*/
- error = xfs_attr_leaf_flipflags(args);
+ error = xfs_attr3_leaf_flipflags(args);
if (error)
return(error);
@@ -1022,6 +710,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
+ args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
@@ -1032,19 +721,19 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
* Read in the block containing the "old" attr, then
* remove the "old" attr from that block (neat, huh!)
*/
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1,
- &bp, XFS_ATTR_FORK);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
+ -1, &bp);
if (error)
- return(error);
- ASSERT(bp != NULL);
- (void)xfs_attr_leaf_remove(bp, args);
+ return error;
+
+ xfs_attr3_leaf_remove(bp, args);
/*
* If the result is small enough, shrink it all into the inode.
*/
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_attr_leaf_to_shortform(bp, args, forkoff);
+ error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error) {
error = xfs_bmap_finish(&args->trans,
@@ -1065,8 +754,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
- } else
- xfs_da_buf_done(bp);
+ }
/*
* Commit the remove and start the next trans in series.
@@ -1077,9 +765,9 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
/*
* Added a "remote" value, just clear the incomplete flag.
*/
- error = xfs_attr_leaf_clearflag(args);
+ error = xfs_attr3_leaf_clearflag(args);
}
- return(error);
+ return error;
}
/*
@@ -1092,7 +780,7 @@ STATIC int
xfs_attr_leaf_removename(xfs_da_args_t *args)
{
xfs_inode_t *dp;
- xfs_dabuf_t *bp;
+ struct xfs_buf *bp;
int error, committed, forkoff;
trace_xfs_attr_leaf_removename(args);
@@ -1102,27 +790,24 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
*/
dp = args->dp;
args->blkno = 0;
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1, &bp,
- XFS_ATTR_FORK);
- if (error) {
- return(error);
- }
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
+ if (error)
+ return error;
- ASSERT(bp != NULL);
- error = xfs_attr_leaf_lookup_int(bp, args);
+ error = xfs_attr3_leaf_lookup_int(bp, args);
if (error == ENOATTR) {
- xfs_da_brelse(args->trans, bp);
- return(error);
+ xfs_trans_brelse(args->trans, bp);
+ return error;
}
- (void)xfs_attr_leaf_remove(bp, args);
+ xfs_attr3_leaf_remove(bp, args);
/*
* If the result is small enough, shrink it all into the inode.
*/
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_attr_leaf_to_shortform(bp, args, forkoff);
+ error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
@@ -1132,7 +817,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
- return(error);
+ return error;
}
/*
@@ -1141,9 +826,8 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
- } else
- xfs_da_buf_done(bp);
- return(0);
+ }
+ return 0;
}
/*
@@ -1155,60 +839,31 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
STATIC int
xfs_attr_leaf_get(xfs_da_args_t *args)
{
- xfs_dabuf_t *bp;
+ struct xfs_buf *bp;
int error;
+ trace_xfs_attr_leaf_get(args);
+
args->blkno = 0;
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1, &bp,
- XFS_ATTR_FORK);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
- return(error);
- ASSERT(bp != NULL);
+ return error;
- error = xfs_attr_leaf_lookup_int(bp, args);
+ error = xfs_attr3_leaf_lookup_int(bp, args);
if (error != EEXIST) {
- xfs_da_brelse(args->trans, bp);
- return(error);
+ xfs_trans_brelse(args->trans, bp);
+ return error;
}
- error = xfs_attr_leaf_getvalue(bp, args);
- xfs_da_brelse(args->trans, bp);
+ error = xfs_attr3_leaf_getvalue(bp, args);
+ xfs_trans_brelse(args->trans, bp);
if (!error && (args->rmtblkno > 0) && !(args->flags & ATTR_KERNOVAL)) {
error = xfs_attr_rmtval_get(args);
}
- return(error);
-}
-
-/*
- * Copy out attribute entries for attr_list(), for leaf attribute lists.
- */
-STATIC int
-xfs_attr_leaf_list(xfs_attr_list_context_t *context)
-{
- xfs_attr_leafblock_t *leaf;
- int error;
- xfs_dabuf_t *bp;
-
- context->cursor->blkno = 0;
- error = xfs_da_read_buf(NULL, context->dp, 0, -1, &bp, XFS_ATTR_FORK);
- if (error)
- return XFS_ERROR(error);
- ASSERT(bp != NULL);
- leaf = bp->data;
- if (unlikely(leaf->hdr.info.magic != cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
- XFS_CORRUPTION_ERROR("xfs_attr_leaf_list", XFS_ERRLEVEL_LOW,
- context->dp->i_mount, leaf);
- xfs_da_brelse(NULL, bp);
- return XFS_ERROR(EFSCORRUPTED);
- }
-
- error = xfs_attr_leaf_list_int(bp, context);
- xfs_da_brelse(NULL, bp);
- return XFS_ERROR(error);
+ return error;
}
-
/*========================================================================
- * External routines when attribute list size > XFS_LBSIZE(mp).
+ * External routines when attribute list size > geo->blksize
*========================================================================*/
/*
@@ -1241,14 +896,12 @@ restart:
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
/*
* Search to see if name already exists, and get back a pointer
* to where it should go.
*/
- error = xfs_da_node_lookup_int(state, &retval);
+ error = xfs_da3_node_lookup_int(state, &retval);
if (error)
goto out;
blk = &state->path.blk[ state->path.active-1 ];
@@ -1261,16 +914,25 @@ restart:
trace_xfs_attr_node_replace(args);
+ /* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* atomic rename op */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
+ args->rmtvaluelen2 = args->rmtvaluelen;
+
+ /*
+ * clear the remote attr state now that it is saved so that the
+ * values reflect the state of the attribute we are about to
+ * add, not the attribute we just found and will remove later.
+ */
args->rmtblkno = 0;
args->rmtblkcnt = 0;
+ args->rmtvaluelen = 0;
}
- retval = xfs_attr_leaf_add(blk->bp, state->args);
+ retval = xfs_attr3_leaf_add(blk->bp, state->args);
if (retval == ENOSPC) {
if (state->path.active == 1) {
/*
@@ -1279,8 +941,9 @@ restart:
* have been a b-tree.
*/
xfs_da_state_free(state);
+ state = NULL;
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_attr_leaf_to_node(args);
+ error = xfs_attr3_leaf_to_node(args);
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
@@ -1319,7 +982,7 @@ restart:
* in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
*/
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_da_split(state);
+ error = xfs_da3_split(state);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
@@ -1341,7 +1004,7 @@ restart:
/*
* Addition succeeded, update Btree hashvals.
*/
- xfs_da_fixhashpath(state, &state->path);
+ xfs_da3_fixhashpath(state, &state->path);
}
/*
@@ -1382,7 +1045,7 @@ restart:
* In a separate transaction, set the incomplete flag on the
* "old" attr and clear the incomplete flag on the "new" attr.
*/
- error = xfs_attr_leaf_flipflags(args);
+ error = xfs_attr3_leaf_flipflags(args);
if (error)
goto out;
@@ -1394,6 +1057,7 @@ restart:
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
+ args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
@@ -1409,10 +1073,8 @@ restart:
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
state->inleaf = 0;
- error = xfs_da_node_lookup_int(state, &retval);
+ error = xfs_da3_node_lookup_int(state, &retval);
if (error)
goto out;
@@ -1421,15 +1083,15 @@ restart:
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
- error = xfs_attr_leaf_remove(blk->bp, args);
- xfs_da_fixhashpath(state, &state->path);
+ error = xfs_attr3_leaf_remove(blk->bp, args);
+ xfs_da3_fixhashpath(state, &state->path);
/*
* Check to see if the tree needs to be collapsed.
*/
if (retval && (state->path.active > 1)) {
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_da_join(state);
+ error = xfs_da3_join(state);
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
@@ -1462,7 +1124,7 @@ restart:
/*
* Added a "remote" value, just clear the incomplete flag.
*/
- error = xfs_attr_leaf_clearflag(args);
+ error = xfs_attr3_leaf_clearflag(args);
if (error)
goto out;
}
@@ -1489,7 +1151,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
xfs_da_state_t *state;
xfs_da_state_blk_t *blk;
xfs_inode_t *dp;
- xfs_dabuf_t *bp;
+ struct xfs_buf *bp;
int retval, error, committed, forkoff;
trace_xfs_attr_node_removename(args);
@@ -1501,13 +1163,11 @@ xfs_attr_node_removename(xfs_da_args_t *args)
state = xfs_da_state_alloc();
state->args = args;
state->mp = dp->i_mount;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
/*
* Search to see if name exists, and get back a pointer to it.
*/
- error = xfs_da_node_lookup_int(state, &retval);
+ error = xfs_da3_node_lookup_int(state, &retval);
if (error || (retval != EEXIST)) {
if (error == 0)
error = retval;
@@ -1536,7 +1196,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
* Mark the attribute as INCOMPLETE, then bunmapi() the
* remote value.
*/
- error = xfs_attr_leaf_setflag(args);
+ error = xfs_attr3_leaf_setflag(args);
if (error)
goto out;
error = xfs_attr_rmtval_remove(args);
@@ -1557,15 +1217,15 @@ xfs_attr_node_removename(xfs_da_args_t *args)
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
- retval = xfs_attr_leaf_remove(blk->bp, args);
- xfs_da_fixhashpath(state, &state->path);
+ retval = xfs_attr3_leaf_remove(blk->bp, args);
+ xfs_da3_fixhashpath(state, &state->path);
/*
* Check to see if the tree needs to be collapsed.
*/
if (retval && (state->path.active > 1)) {
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_da_join(state);
+ error = xfs_da3_join(state);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
@@ -1601,19 +1261,15 @@ xfs_attr_node_removename(xfs_da_args_t *args)
*/
ASSERT(state->path.active == 1);
ASSERT(state->path.blk[0].bp);
- xfs_da_buf_done(state->path.blk[0].bp);
state->path.blk[0].bp = NULL;
- error = xfs_da_read_buf(args->trans, args->dp, 0, -1, &bp,
- XFS_ATTR_FORK);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, 0, -1, &bp);
if (error)
goto out;
- ASSERT((((xfs_attr_leafblock_t *)bp->data)->hdr.info.magic) ==
- cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_attr_leaf_to_shortform(bp, args, forkoff);
+ error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error) {
error = xfs_bmap_finish(&args->trans,
@@ -1635,7 +1291,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
} else
- xfs_da_brelse(args->trans, bp);
+ xfs_trans_brelse(args->trans, bp);
}
error = 0;
@@ -1657,6 +1313,8 @@ xfs_attr_fillstate(xfs_da_state_t *state)
xfs_da_state_blk_t *blk;
int level;
+ trace_xfs_attr_fillstate(state->args);
+
/*
* Roll down the "path" in the state structure, storing the on-disk
* block number for those buffers in the "path".
@@ -1665,8 +1323,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
if (blk->bp) {
- blk->disk_blkno = xfs_da_blkno(blk->bp);
- xfs_da_buf_done(blk->bp);
+ blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
blk->bp = NULL;
} else {
blk->disk_blkno = 0;
@@ -1681,8 +1338,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
if (blk->bp) {
- blk->disk_blkno = xfs_da_blkno(blk->bp);
- xfs_da_buf_done(blk->bp);
+ blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
blk->bp = NULL;
} else {
blk->disk_blkno = 0;
@@ -1705,6 +1361,8 @@ xfs_attr_refillstate(xfs_da_state_t *state)
xfs_da_state_blk_t *blk;
int level, error;
+ trace_xfs_attr_refillstate(state->args);
+
/*
* Roll down the "path" in the state structure, storing the on-disk
* block number for those buffers in the "path".
@@ -1713,7 +1371,7 @@ xfs_attr_refillstate(xfs_da_state_t *state)
ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
if (blk->disk_blkno) {
- error = xfs_da_read_buf(state->args->trans,
+ error = xfs_da3_node_read(state->args->trans,
state->args->dp,
blk->blkno, blk->disk_blkno,
&blk->bp, XFS_ATTR_FORK);
@@ -1732,7 +1390,7 @@ xfs_attr_refillstate(xfs_da_state_t *state)
ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
if (blk->disk_blkno) {
- error = xfs_da_read_buf(state->args->trans,
+ error = xfs_da3_node_read(state->args->trans,
state->args->dp,
blk->blkno, blk->disk_blkno,
&blk->bp, XFS_ATTR_FORK);
@@ -1761,16 +1419,16 @@ xfs_attr_node_get(xfs_da_args_t *args)
int error, retval;
int i;
+ trace_xfs_attr_node_get(args);
+
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_sb.sb_blocksize;
- state->node_ents = state->mp->m_attr_node_ents;
/*
* Search to see if name exists, and get back a pointer to it.
*/
- error = xfs_da_node_lookup_int(state, &retval);
+ error = xfs_da3_node_lookup_int(state, &retval);
if (error) {
retval = error;
} else if (retval == EEXIST) {
@@ -1781,7 +1439,7 @@ xfs_attr_node_get(xfs_da_args_t *args)
/*
* Get the value, local or "remote"
*/
- retval = xfs_attr_leaf_getvalue(blk->bp, args);
+ retval = xfs_attr3_leaf_getvalue(blk->bp, args);
if (!retval && (args->rmtblkno > 0)
&& !(args->flags & ATTR_KERNOVAL)) {
retval = xfs_attr_rmtval_get(args);
@@ -1792,439 +1450,10 @@ xfs_attr_node_get(xfs_da_args_t *args)
* If not in a transaction, we have to release all the buffers.
*/
for (i = 0; i < state->path.active; i++) {
- xfs_da_brelse(args->trans, state->path.blk[i].bp);
+ xfs_trans_brelse(args->trans, state->path.blk[i].bp);
state->path.blk[i].bp = NULL;
}
xfs_da_state_free(state);
return(retval);
}
-
-STATIC int /* error */
-xfs_attr_node_list(xfs_attr_list_context_t *context)
-{
- attrlist_cursor_kern_t *cursor;
- xfs_attr_leafblock_t *leaf;
- xfs_da_intnode_t *node;
- xfs_da_node_entry_t *btree;
- int error, i;
- xfs_dabuf_t *bp;
-
- cursor = context->cursor;
- cursor->initted = 1;
-
- /*
- * Do all sorts of validation on the passed-in cursor structure.
- * If anything is amiss, ignore the cursor and look up the hashval
- * starting from the btree root.
- */
- bp = NULL;
- if (cursor->blkno > 0) {
- error = xfs_da_read_buf(NULL, context->dp, cursor->blkno, -1,
- &bp, XFS_ATTR_FORK);
- if ((error != 0) && (error != EFSCORRUPTED))
- return(error);
- if (bp) {
- node = bp->data;
- switch (be16_to_cpu(node->hdr.info.magic)) {
- case XFS_DA_NODE_MAGIC:
- trace_xfs_attr_list_wrong_blk(context);
- xfs_da_brelse(NULL, bp);
- bp = NULL;
- break;
- case XFS_ATTR_LEAF_MAGIC:
- leaf = bp->data;
- if (cursor->hashval > be32_to_cpu(leaf->entries[
- be16_to_cpu(leaf->hdr.count)-1].hashval)) {
- trace_xfs_attr_list_wrong_blk(context);
- xfs_da_brelse(NULL, bp);
- bp = NULL;
- } else if (cursor->hashval <=
- be32_to_cpu(leaf->entries[0].hashval)) {
- trace_xfs_attr_list_wrong_blk(context);
- xfs_da_brelse(NULL, bp);
- bp = NULL;
- }
- break;
- default:
- trace_xfs_attr_list_wrong_blk(context);
- xfs_da_brelse(NULL, bp);
- bp = NULL;
- }
- }
- }
-
- /*
- * We did not find what we expected given the cursor's contents,
- * so we start from the top and work down based on the hash value.
- * Note that start of node block is same as start of leaf block.
- */
- if (bp == NULL) {
- cursor->blkno = 0;
- for (;;) {
- error = xfs_da_read_buf(NULL, context->dp,
- cursor->blkno, -1, &bp,
- XFS_ATTR_FORK);
- if (error)
- return(error);
- if (unlikely(bp == NULL)) {
- XFS_ERROR_REPORT("xfs_attr_node_list(2)",
- XFS_ERRLEVEL_LOW,
- context->dp->i_mount);
- return(XFS_ERROR(EFSCORRUPTED));
- }
- node = bp->data;
- if (node->hdr.info.magic ==
- cpu_to_be16(XFS_ATTR_LEAF_MAGIC))
- break;
- if (unlikely(node->hdr.info.magic !=
- cpu_to_be16(XFS_DA_NODE_MAGIC))) {
- XFS_CORRUPTION_ERROR("xfs_attr_node_list(3)",
- XFS_ERRLEVEL_LOW,
- context->dp->i_mount,
- node);
- xfs_da_brelse(NULL, bp);
- return(XFS_ERROR(EFSCORRUPTED));
- }
- btree = node->btree;
- for (i = 0; i < be16_to_cpu(node->hdr.count);
- btree++, i++) {
- if (cursor->hashval
- <= be32_to_cpu(btree->hashval)) {
- cursor->blkno = be32_to_cpu(btree->before);
- trace_xfs_attr_list_node_descend(context,
- btree);
- break;
- }
- }
- if (i == be16_to_cpu(node->hdr.count)) {
- xfs_da_brelse(NULL, bp);
- return(0);
- }
- xfs_da_brelse(NULL, bp);
- }
- }
- ASSERT(bp != NULL);
-
- /*
- * Roll upward through the blocks, processing each leaf block in
- * order. As long as there is space in the result buffer, keep
- * adding the information.
- */
- for (;;) {
- leaf = bp->data;
- if (unlikely(leaf->hdr.info.magic !=
- cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
- XFS_CORRUPTION_ERROR("xfs_attr_node_list(4)",
- XFS_ERRLEVEL_LOW,
- context->dp->i_mount, leaf);
- xfs_da_brelse(NULL, bp);
- return(XFS_ERROR(EFSCORRUPTED));
- }
- error = xfs_attr_leaf_list_int(bp, context);
- if (error) {
- xfs_da_brelse(NULL, bp);
- return error;
- }
- if (context->seen_enough || leaf->hdr.info.forw == 0)
- break;
- cursor->blkno = be32_to_cpu(leaf->hdr.info.forw);
- xfs_da_brelse(NULL, bp);
- error = xfs_da_read_buf(NULL, context->dp, cursor->blkno, -1,
- &bp, XFS_ATTR_FORK);
- if (error)
- return(error);
- if (unlikely((bp == NULL))) {
- XFS_ERROR_REPORT("xfs_attr_node_list(5)",
- XFS_ERRLEVEL_LOW,
- context->dp->i_mount);
- return(XFS_ERROR(EFSCORRUPTED));
- }
- }
- xfs_da_brelse(NULL, bp);
- return(0);
-}
-
-
-/*========================================================================
- * External routines for manipulating out-of-line attribute values.
- *========================================================================*/
-
-/*
- * Read the value associated with an attribute from the out-of-line buffer
- * that we stored it in.
- */
-int
-xfs_attr_rmtval_get(xfs_da_args_t *args)
-{
- xfs_bmbt_irec_t map[ATTR_RMTVALUE_MAPSIZE];
- xfs_mount_t *mp;
- xfs_daddr_t dblkno;
- void *dst;
- xfs_buf_t *bp;
- int nmap, error, tmp, valuelen, blkcnt, i;
- xfs_dablk_t lblkno;
-
- ASSERT(!(args->flags & ATTR_KERNOVAL));
-
- mp = args->dp->i_mount;
- dst = args->value;
- valuelen = args->valuelen;
- lblkno = args->rmtblkno;
- while (valuelen > 0) {
- nmap = ATTR_RMTVALUE_MAPSIZE;
- error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
- args->rmtblkcnt, map, &nmap,
- XFS_BMAPI_ATTRFORK);
- if (error)
- return(error);
- ASSERT(nmap >= 1);
-
- for (i = 0; (i < nmap) && (valuelen > 0); i++) {
- ASSERT((map[i].br_startblock != DELAYSTARTBLOCK) &&
- (map[i].br_startblock != HOLESTARTBLOCK));
- dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
- blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
- error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
- dblkno, blkcnt, 0, &bp);
- if (error)
- return(error);
-
- tmp = min_t(int, valuelen, BBTOB(bp->b_length));
- xfs_buf_iomove(bp, 0, tmp, dst, XBRW_READ);
- xfs_buf_relse(bp);
- dst += tmp;
- valuelen -= tmp;
-
- lblkno += map[i].br_blockcount;
- }
- }
- ASSERT(valuelen == 0);
- return(0);
-}
-
-/*
- * Write the value associated with an attribute into the out-of-line buffer
- * that we have defined for it.
- */
-STATIC int
-xfs_attr_rmtval_set(xfs_da_args_t *args)
-{
- xfs_mount_t *mp;
- xfs_fileoff_t lfileoff;
- xfs_inode_t *dp;
- xfs_bmbt_irec_t map;
- xfs_daddr_t dblkno;
- void *src;
- xfs_buf_t *bp;
- xfs_dablk_t lblkno;
- int blkcnt, valuelen, nmap, error, tmp, committed;
-
- dp = args->dp;
- mp = dp->i_mount;
- src = args->value;
-
- /*
- * Find a "hole" in the attribute address space large enough for
- * us to drop the new attribute's value into.
- */
- blkcnt = XFS_B_TO_FSB(mp, args->valuelen);
- lfileoff = 0;
- error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
- XFS_ATTR_FORK);
- if (error) {
- return(error);
- }
- args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff;
- args->rmtblkcnt = blkcnt;
-
- /*
- * Roll through the "value", allocating blocks on disk as required.
- */
- while (blkcnt > 0) {
- /*
- * Allocate a single extent, up to the size of the value.
- */
- xfs_bmap_init(args->flist, args->firstblock);
- nmap = 1;
- error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
- blkcnt,
- XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
- args->firstblock, args->total, &map, &nmap,
- args->flist);
- if (!error) {
- error = xfs_bmap_finish(&args->trans, args->flist,
- &committed);
- }
- if (error) {
- ASSERT(committed);
- args->trans = NULL;
- xfs_bmap_cancel(args->flist);
- return(error);
- }
-
- /*
- * bmap_finish() may have committed the last trans and started
- * a new one. We need the inode to be in all transactions.
- */
- if (committed)
- xfs_trans_ijoin(args->trans, dp, 0);
-
- ASSERT(nmap == 1);
- ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
- (map.br_startblock != HOLESTARTBLOCK));
- lblkno += map.br_blockcount;
- blkcnt -= map.br_blockcount;
-
- /*
- * Start the next trans in the chain.
- */
- error = xfs_trans_roll(&args->trans, dp);
- if (error)
- return (error);
- }
-
- /*
- * Roll through the "value", copying the attribute value to the
- * already-allocated blocks. Blocks are written synchronously
- * so that we can know they are all on disk before we turn off
- * the INCOMPLETE flag.
- */
- lblkno = args->rmtblkno;
- valuelen = args->valuelen;
- while (valuelen > 0) {
- int buflen;
-
- /*
- * Try to remember where we decided to put the value.
- */
- xfs_bmap_init(args->flist, args->firstblock);
- nmap = 1;
- error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
- args->rmtblkcnt, &map, &nmap,
- XFS_BMAPI_ATTRFORK);
- if (error)
- return(error);
- ASSERT(nmap == 1);
- ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
- (map.br_startblock != HOLESTARTBLOCK));
-
- dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
- blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
-
- bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt, 0);
- if (!bp)
- return ENOMEM;
-
- buflen = BBTOB(bp->b_length);
- tmp = min_t(int, valuelen, buflen);
- xfs_buf_iomove(bp, 0, tmp, src, XBRW_WRITE);
- if (tmp < buflen)
- xfs_buf_zero(bp, tmp, buflen - tmp);
-
- error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */
- xfs_buf_relse(bp);
- if (error)
- return error;
- src += tmp;
- valuelen -= tmp;
-
- lblkno += map.br_blockcount;
- }
- ASSERT(valuelen == 0);
- return(0);
-}
-
-/*
- * Remove the value associated with an attribute by deleting the
- * out-of-line buffer that it is stored on.
- */
-STATIC int
-xfs_attr_rmtval_remove(xfs_da_args_t *args)
-{
- xfs_mount_t *mp;
- xfs_bmbt_irec_t map;
- xfs_buf_t *bp;
- xfs_daddr_t dblkno;
- xfs_dablk_t lblkno;
- int valuelen, blkcnt, nmap, error, done, committed;
-
- mp = args->dp->i_mount;
-
- /*
- * Roll through the "value", invalidating the attribute value's
- * blocks.
- */
- lblkno = args->rmtblkno;
- valuelen = args->rmtblkcnt;
- while (valuelen > 0) {
- /*
- * Try to remember where we decided to put the value.
- */
- nmap = 1;
- error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
- args->rmtblkcnt, &map, &nmap,
- XFS_BMAPI_ATTRFORK);
- if (error)
- return(error);
- ASSERT(nmap == 1);
- ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
- (map.br_startblock != HOLESTARTBLOCK));
-
- dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
- blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
-
- /*
- * If the "remote" value is in the cache, remove it.
- */
- bp = xfs_incore(mp->m_ddev_targp, dblkno, blkcnt, XBF_TRYLOCK);
- if (bp) {
- xfs_buf_stale(bp);
- xfs_buf_relse(bp);
- bp = NULL;
- }
-
- valuelen -= map.br_blockcount;
-
- lblkno += map.br_blockcount;
- }
-
- /*
- * Keep de-allocating extents until the remote-value region is gone.
- */
- lblkno = args->rmtblkno;
- blkcnt = args->rmtblkcnt;
- done = 0;
- while (!done) {
- xfs_bmap_init(args->flist, args->firstblock);
- error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
- XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
- 1, args->firstblock, args->flist,
- &done);
- if (!error) {
- error = xfs_bmap_finish(&args->trans, args->flist,
- &committed);
- }
- if (error) {
- ASSERT(committed);
- args->trans = NULL;
- xfs_bmap_cancel(args->flist);
- return(error);
- }
-
- /*
- * bmap_finish() may have committed the last trans and started
- * a new one. We need the inode to be in all transactions.
- */
- if (committed)
- xfs_trans_ijoin(args->trans, args->dp, 0);
-
- /*
- * Close out trans and start the next one in the chain.
- */
- error = xfs_trans_roll(&args->trans, args->dp);
- if (error)
- return (error);
- }
- return(0);
-}
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index e920d68ef50..dd482458947 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -140,7 +140,15 @@ typedef struct xfs_attr_list_context {
* Overall external interface routines.
*/
int xfs_attr_inactive(struct xfs_inode *dp);
-int xfs_attr_rmtval_get(struct xfs_da_args *args);
int xfs_attr_list_int(struct xfs_attr_list_context *);
+int xfs_inode_hasattr(struct xfs_inode *ip);
+int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
+ unsigned char *value, int *valuelenp, int flags);
+int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
+ unsigned char *value, int valuelen, int flags);
+int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
+int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
+ int flags, struct attrlist_cursor_kern *cursor);
+
#endif /* __XFS_ATTR_H__ */
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
new file mode 100644
index 00000000000..09480c57f06
--- /dev/null
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -0,0 +1,452 @@
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_attr_remote.h"
+#include "xfs_trans.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_error.h"
+#include "xfs_quota.h"
+#include "xfs_trace.h"
+#include "xfs_dinode.h"
+#include "xfs_dir2.h"
+
+/*
+ * Look at all the extents for this logical region,
+ * invalidate any buffers that are incore/in transactions.
+ */
+STATIC int
+xfs_attr3_leaf_freextent(
+ struct xfs_trans **trans,
+ struct xfs_inode *dp,
+ xfs_dablk_t blkno,
+ int blkcnt)
+{
+ struct xfs_bmbt_irec map;
+ struct xfs_buf *bp;
+ xfs_dablk_t tblkno;
+ xfs_daddr_t dblkno;
+ int tblkcnt;
+ int dblkcnt;
+ int nmap;
+ int error;
+
+ /*
+ * Roll through the "value", invalidating the attribute value's
+ * blocks.
+ */
+ tblkno = blkno;
+ tblkcnt = blkcnt;
+ while (tblkcnt > 0) {
+ /*
+ * Try to remember where we decided to put the value.
+ */
+ nmap = 1;
+ error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
+ &map, &nmap, XFS_BMAPI_ATTRFORK);
+ if (error) {
+ return(error);
+ }
+ ASSERT(nmap == 1);
+ ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+
+ /*
+ * If it's a hole, these are already unmapped
+ * so there's nothing to invalidate.
+ */
+ if (map.br_startblock != HOLESTARTBLOCK) {
+
+ dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
+ map.br_startblock);
+ dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
+ map.br_blockcount);
+ bp = xfs_trans_get_buf(*trans,
+ dp->i_mount->m_ddev_targp,
+ dblkno, dblkcnt, 0);
+ if (!bp)
+ return ENOMEM;
+ xfs_trans_binval(*trans, bp);
+ /*
+ * Roll to next transaction.
+ */
+ error = xfs_trans_roll(trans, dp);
+ if (error)
+ return (error);
+ }
+
+ tblkno += map.br_blockcount;
+ tblkcnt -= map.br_blockcount;
+ }
+
+ return(0);
+}
+
+/*
+ * Invalidate all of the "remote" value regions pointed to by a particular
+ * leaf block.
+ * Note that we must release the lock on the buffer so that we are not
+ * caught holding something that the logging code wants to flush to disk.
+ */
+STATIC int
+xfs_attr3_leaf_inactive(
+ struct xfs_trans **trans,
+ struct xfs_inode *dp,
+ struct xfs_buf *bp)
+{
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr_leaf_name_remote *name_rmt;
+ struct xfs_attr_inactive_list *list;
+ struct xfs_attr_inactive_list *lp;
+ int error;
+ int count;
+ int size;
+ int tmp;
+ int i;
+
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+
+ /*
+ * Count the number of "remote" value extents.
+ */
+ count = 0;
+ entry = xfs_attr3_leaf_entryp(leaf);
+ for (i = 0; i < ichdr.count; entry++, i++) {
+ if (be16_to_cpu(entry->nameidx) &&
+ ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+ if (name_rmt->valueblk)
+ count++;
+ }
+ }
+
+ /*
+ * If there are no "remote" values, we're done.
+ */
+ if (count == 0) {
+ xfs_trans_brelse(*trans, bp);
+ return 0;
+ }
+
+ /*
+ * Allocate storage for a list of all the "remote" value extents.
+ */
+ size = count * sizeof(xfs_attr_inactive_list_t);
+ list = kmem_alloc(size, KM_SLEEP);
+
+ /*
+ * Identify each of the "remote" value extents.
+ */
+ lp = list;
+ entry = xfs_attr3_leaf_entryp(leaf);
+ for (i = 0; i < ichdr.count; entry++, i++) {
+ if (be16_to_cpu(entry->nameidx) &&
+ ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+ if (name_rmt->valueblk) {
+ lp->valueblk = be32_to_cpu(name_rmt->valueblk);
+ lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount,
+ be32_to_cpu(name_rmt->valuelen));
+ lp++;
+ }
+ }
+ }
+ xfs_trans_brelse(*trans, bp); /* unlock for trans. in freextent() */
+
+ /*
+ * Invalidate each of the "remote" value extents.
+ */
+ error = 0;
+ for (lp = list, i = 0; i < count; i++, lp++) {
+ tmp = xfs_attr3_leaf_freextent(trans, dp,
+ lp->valueblk, lp->valuelen);
+
+ if (error == 0)
+ error = tmp; /* save only the 1st errno */
+ }
+
+ kmem_free(list);
+ return error;
+}
+
+/*
+ * Recurse (gasp!) through the attribute nodes until we find leaves.
+ * We're doing a depth-first traversal in order to invalidate everything.
+ */
+STATIC int
+xfs_attr3_node_inactive(
+ struct xfs_trans **trans,
+ struct xfs_inode *dp,
+ struct xfs_buf *bp,
+ int level)
+{
+ xfs_da_blkinfo_t *info;
+ xfs_da_intnode_t *node;
+ xfs_dablk_t child_fsb;
+ xfs_daddr_t parent_blkno, child_blkno;
+ int error, i;
+ struct xfs_buf *child_bp;
+ struct xfs_da_node_entry *btree;
+ struct xfs_da3_icnode_hdr ichdr;
+
+ /*
+ * Since this code is recursive (gasp!) we must protect ourselves.
+ */
+ if (level > XFS_DA_NODE_MAXDEPTH) {
+ xfs_trans_brelse(*trans, bp); /* no locks for later trans */
+ return XFS_ERROR(EIO);
+ }
+
+ node = bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&ichdr, node);
+ parent_blkno = bp->b_bn;
+ if (!ichdr.count) {
+ xfs_trans_brelse(*trans, bp);
+ return 0;
+ }
+ btree = dp->d_ops->node_tree_p(node);
+ child_fsb = be32_to_cpu(btree[0].before);
+ xfs_trans_brelse(*trans, bp); /* no locks for later trans */
+
+ /*
+ * If this is the node level just above the leaves, simply loop
+ * over the leaves removing all of them. If this is higher up
+ * in the tree, recurse downward.
+ */
+ for (i = 0; i < ichdr.count; i++) {
+ /*
+ * Read the subsidiary block to see what we have to work with.
+ * Don't do this in a transaction. This is a depth-first
+ * traversal of the tree so we may deal with many blocks
+ * before we come back to this one.
+ */
+ error = xfs_da3_node_read(*trans, dp, child_fsb, -2, &child_bp,
+ XFS_ATTR_FORK);
+ if (error)
+ return(error);
+ if (child_bp) {
+ /* save for re-read later */
+ child_blkno = XFS_BUF_ADDR(child_bp);
+
+ /*
+ * Invalidate the subtree, however we have to.
+ */
+ info = child_bp->b_addr;
+ switch (info->magic) {
+ case cpu_to_be16(XFS_DA_NODE_MAGIC):
+ case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+ error = xfs_attr3_node_inactive(trans, dp,
+ child_bp, level + 1);
+ break;
+ case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
+ case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
+ error = xfs_attr3_leaf_inactive(trans, dp,
+ child_bp);
+ break;
+ default:
+ error = XFS_ERROR(EIO);
+ xfs_trans_brelse(*trans, child_bp);
+ break;
+ }
+ if (error)
+ return error;
+
+ /*
+ * Remove the subsidiary block from the cache
+ * and from the log.
+ */
+ error = xfs_da_get_buf(*trans, dp, 0, child_blkno,
+ &child_bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ xfs_trans_binval(*trans, child_bp);
+ }
+
+ /*
+ * If we're not done, re-read the parent to get the next
+ * child block number.
+ */
+ if (i + 1 < ichdr.count) {
+ error = xfs_da3_node_read(*trans, dp, 0, parent_blkno,
+ &bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ child_fsb = be32_to_cpu(btree[i + 1].before);
+ xfs_trans_brelse(*trans, bp);
+ }
+ /*
+ * Atomically commit the whole invalidate stuff.
+ */
+ error = xfs_trans_roll(trans, dp);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+/*
+ * Indiscriminately delete the entire attribute fork
+ *
+ * Recurse (gasp!) through the attribute nodes until we find leaves.
+ * We're doing a depth-first traversal in order to invalidate everything.
+ */
+int
+xfs_attr3_root_inactive(
+ struct xfs_trans **trans,
+ struct xfs_inode *dp)
+{
+ struct xfs_da_blkinfo *info;
+ struct xfs_buf *bp;
+ xfs_daddr_t blkno;
+ int error;
+
+ /*
+ * Read block 0 to see what we have to work with.
+ * We only get here if we have extents, since we remove
+ * the extents in reverse order the extent containing
+ * block 0 must still be there.
+ */
+ error = xfs_da3_node_read(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ blkno = bp->b_bn;
+
+ /*
+ * Invalidate the tree, even if the "tree" is only a single leaf block.
+ * This is a depth-first traversal!
+ */
+ info = bp->b_addr;
+ switch (info->magic) {
+ case cpu_to_be16(XFS_DA_NODE_MAGIC):
+ case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+ error = xfs_attr3_node_inactive(trans, dp, bp, 1);
+ break;
+ case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
+ case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
+ error = xfs_attr3_leaf_inactive(trans, dp, bp);
+ break;
+ default:
+ error = XFS_ERROR(EIO);
+ xfs_trans_brelse(*trans, bp);
+ break;
+ }
+ if (error)
+ return error;
+
+ /*
+ * Invalidate the incore copy of the root block.
+ */
+ error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ xfs_trans_binval(*trans, bp); /* remove from cache */
+ /*
+ * Commit the invalidate and start the next transaction.
+ */
+ error = xfs_trans_roll(trans, dp);
+
+ return error;
+}
+
+int
+xfs_attr_inactive(xfs_inode_t *dp)
+{
+ xfs_trans_t *trans;
+ xfs_mount_t *mp;
+ int error;
+
+ mp = dp->i_mount;
+ ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
+
+ xfs_ilock(dp, XFS_ILOCK_SHARED);
+ if (!xfs_inode_hasattr(dp) ||
+ dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+ xfs_iunlock(dp, XFS_ILOCK_SHARED);
+ return 0;
+ }
+ xfs_iunlock(dp, XFS_ILOCK_SHARED);
+
+ /*
+ * Start our first transaction of the day.
+ *
+ * All future transactions during this code must be "chained" off
+ * this one via the trans_dup() call. All transactions will contain
+ * the inode, and the inode will always be marked with trans_ihold().
+ * Since the inode will be locked in all transactions, we must log
+ * the inode in every transaction to let it float upward through
+ * the log.
+ */
+ trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
+ error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
+ if (error) {
+ xfs_trans_cancel(trans, 0);
+ return(error);
+ }
+ xfs_ilock(dp, XFS_ILOCK_EXCL);
+
+ /*
+ * No need to make quota reservations here. We expect to release some
+ * blocks, not allocate, in the common case.
+ */
+ xfs_trans_ijoin(trans, dp, 0);
+
+ /*
+ * Decide on what work routines to call based on the inode size.
+ */
+ if (!xfs_inode_hasattr(dp) ||
+ dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+ error = 0;
+ goto out;
+ }
+ error = xfs_attr3_root_inactive(&trans, dp);
+ if (error)
+ goto out;
+
+ error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
+ if (error)
+ goto out;
+
+ error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(dp, XFS_ILOCK_EXCL);
+
+ return(error);
+
+out:
+ xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
+ xfs_iunlock(dp, XFS_ILOCK_EXCL);
+ return(error);
+}
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 7d89d800f51..28712d29e43 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -17,28 +18,32 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_alloc.h"
-#include "xfs_btree.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
+#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
#include "xfs_attr.h"
#include "xfs_attr_leaf.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_buf_item.h"
+#include "xfs_cksum.h"
+#include "xfs_dinode.h"
+#include "xfs_dir2.h"
+
/*
* xfs_attr_leaf.c
@@ -53,39 +58,219 @@
/*
* Routines used for growing the Btree.
*/
-STATIC int xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t which_block,
- xfs_dabuf_t **bpp);
-STATIC int xfs_attr_leaf_add_work(xfs_dabuf_t *leaf_buffer, xfs_da_args_t *args,
- int freemap_index);
-STATIC void xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *leaf_buffer);
-STATIC void xfs_attr_leaf_rebalance(xfs_da_state_t *state,
+STATIC int xfs_attr3_leaf_create(struct xfs_da_args *args,
+ xfs_dablk_t which_block, struct xfs_buf **bpp);
+STATIC int xfs_attr3_leaf_add_work(struct xfs_buf *leaf_buffer,
+ struct xfs_attr3_icleaf_hdr *ichdr,
+ struct xfs_da_args *args, int freemap_index);
+STATIC void xfs_attr3_leaf_compact(struct xfs_da_args *args,
+ struct xfs_attr3_icleaf_hdr *ichdr,
+ struct xfs_buf *leaf_buffer);
+STATIC void xfs_attr3_leaf_rebalance(xfs_da_state_t *state,
xfs_da_state_blk_t *blk1,
xfs_da_state_blk_t *blk2);
-STATIC int xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
- xfs_da_state_blk_t *leaf_blk_1,
- xfs_da_state_blk_t *leaf_blk_2,
- int *number_entries_in_blk1,
- int *number_usedbytes_in_blk1);
+STATIC int xfs_attr3_leaf_figure_balance(xfs_da_state_t *state,
+ xfs_da_state_blk_t *leaf_blk_1,
+ struct xfs_attr3_icleaf_hdr *ichdr1,
+ xfs_da_state_blk_t *leaf_blk_2,
+ struct xfs_attr3_icleaf_hdr *ichdr2,
+ int *number_entries_in_blk1,
+ int *number_usedbytes_in_blk1);
/*
- * Routines used for shrinking the Btree.
+ * Utility routines.
*/
-STATIC int xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
- xfs_dabuf_t *bp, int level);
-STATIC int xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
- xfs_dabuf_t *bp);
-STATIC int xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp,
- xfs_dablk_t blkno, int blkcnt);
+STATIC void xfs_attr3_leaf_moveents(struct xfs_da_args *args,
+ struct xfs_attr_leafblock *src_leaf,
+ struct xfs_attr3_icleaf_hdr *src_ichdr, int src_start,
+ struct xfs_attr_leafblock *dst_leaf,
+ struct xfs_attr3_icleaf_hdr *dst_ichdr, int dst_start,
+ int move_count);
+STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index);
+
+void
+xfs_attr3_leaf_hdr_from_disk(
+ struct xfs_attr3_icleaf_hdr *to,
+ struct xfs_attr_leafblock *from)
+{
+ int i;
+
+ ASSERT(from->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC) ||
+ from->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC));
+
+ if (from->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC)) {
+ struct xfs_attr3_leaf_hdr *hdr3 = (struct xfs_attr3_leaf_hdr *)from;
+
+ to->forw = be32_to_cpu(hdr3->info.hdr.forw);
+ to->back = be32_to_cpu(hdr3->info.hdr.back);
+ to->magic = be16_to_cpu(hdr3->info.hdr.magic);
+ to->count = be16_to_cpu(hdr3->count);
+ to->usedbytes = be16_to_cpu(hdr3->usedbytes);
+ to->firstused = be16_to_cpu(hdr3->firstused);
+ to->holes = hdr3->holes;
+
+ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+ to->freemap[i].base = be16_to_cpu(hdr3->freemap[i].base);
+ to->freemap[i].size = be16_to_cpu(hdr3->freemap[i].size);
+ }
+ return;
+ }
+ to->forw = be32_to_cpu(from->hdr.info.forw);
+ to->back = be32_to_cpu(from->hdr.info.back);
+ to->magic = be16_to_cpu(from->hdr.info.magic);
+ to->count = be16_to_cpu(from->hdr.count);
+ to->usedbytes = be16_to_cpu(from->hdr.usedbytes);
+ to->firstused = be16_to_cpu(from->hdr.firstused);
+ to->holes = from->hdr.holes;
+
+ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+ to->freemap[i].base = be16_to_cpu(from->hdr.freemap[i].base);
+ to->freemap[i].size = be16_to_cpu(from->hdr.freemap[i].size);
+ }
+}
+
+void
+xfs_attr3_leaf_hdr_to_disk(
+ struct xfs_attr_leafblock *to,
+ struct xfs_attr3_icleaf_hdr *from)
+{
+ int i;
+
+ ASSERT(from->magic == XFS_ATTR_LEAF_MAGIC ||
+ from->magic == XFS_ATTR3_LEAF_MAGIC);
+
+ if (from->magic == XFS_ATTR3_LEAF_MAGIC) {
+ struct xfs_attr3_leaf_hdr *hdr3 = (struct xfs_attr3_leaf_hdr *)to;
+
+ hdr3->info.hdr.forw = cpu_to_be32(from->forw);
+ hdr3->info.hdr.back = cpu_to_be32(from->back);
+ hdr3->info.hdr.magic = cpu_to_be16(from->magic);
+ hdr3->count = cpu_to_be16(from->count);
+ hdr3->usedbytes = cpu_to_be16(from->usedbytes);
+ hdr3->firstused = cpu_to_be16(from->firstused);
+ hdr3->holes = from->holes;
+ hdr3->pad1 = 0;
+
+ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+ hdr3->freemap[i].base = cpu_to_be16(from->freemap[i].base);
+ hdr3->freemap[i].size = cpu_to_be16(from->freemap[i].size);
+ }
+ return;
+ }
+ to->hdr.info.forw = cpu_to_be32(from->forw);
+ to->hdr.info.back = cpu_to_be32(from->back);
+ to->hdr.info.magic = cpu_to_be16(from->magic);
+ to->hdr.count = cpu_to_be16(from->count);
+ to->hdr.usedbytes = cpu_to_be16(from->usedbytes);
+ to->hdr.firstused = cpu_to_be16(from->firstused);
+ to->hdr.holes = from->holes;
+ to->hdr.pad1 = 0;
+
+ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+ to->hdr.freemap[i].base = cpu_to_be16(from->freemap[i].base);
+ to->hdr.freemap[i].size = cpu_to_be16(from->freemap[i].size);
+ }
+}
+
+static bool
+xfs_attr3_leaf_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_attr_leafblock *leaf = bp->b_addr;
+ struct xfs_attr3_icleaf_hdr ichdr;
+
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_da3_node_hdr *hdr3 = bp->b_addr;
+
+ if (ichdr.magic != XFS_ATTR3_LEAF_MAGIC)
+ return false;
+
+ if (!uuid_equal(&hdr3->info.uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(hdr3->info.blkno) != bp->b_bn)
+ return false;
+ } else {
+ if (ichdr.magic != XFS_ATTR_LEAF_MAGIC)
+ return false;
+ }
+ if (ichdr.count == 0)
+ return false;
+
+ /* XXX: need to range check rest of attr header values */
+ /* XXX: hash order check? */
+
+ return true;
+}
+
+static void
+xfs_attr3_leaf_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+ struct xfs_attr3_leaf_hdr *hdr3 = bp->b_addr;
+
+ if (!xfs_attr3_leaf_verify(bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (bip)
+ hdr3->info.lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_ATTR3_LEAF_CRC_OFF);
+}
/*
- * Utility routines.
+ * leaf/node format detection on trees is sketchy, so a node read can be done on
+ * leaf level blocks when detection identifies the tree as a node format tree
+ * incorrectly. In this case, we need to swap the verifier to match the correct
+ * format of the block being read.
*/
-STATIC void xfs_attr_leaf_moveents(xfs_attr_leafblock_t *src_leaf,
- int src_start,
- xfs_attr_leafblock_t *dst_leaf,
- int dst_start, int move_count,
- xfs_mount_t *mp);
-STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index);
+static void
+xfs_attr3_leaf_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !xfs_buf_verify_cksum(bp, XFS_ATTR3_LEAF_CRC_OFF))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_attr3_leaf_verify(bp))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+}
+
+const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = {
+ .verify_read = xfs_attr3_leaf_read_verify,
+ .verify_write = xfs_attr3_leaf_write_verify,
+};
+
+int
+xfs_attr3_leaf_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
+ xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp)
+{
+ int err;
+
+ err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
+ XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops);
+ if (!err && tp)
+ xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
+ return err;
+}
/*========================================================================
* Namespace helper routines
@@ -125,7 +310,8 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
int dsize;
xfs_mount_t *mp = dp->i_mount;
- offset = (XFS_LITINO(mp) - bytes) >> 3; /* rounded down */
+ /* rounded down */
+ offset = (XFS_LITINO(mp, dp->i_d.di_version) - bytes) >> 3;
switch (dp->i_d.di_format) {
case XFS_DINODE_FMT_DEV:
@@ -184,7 +370,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
return 0;
return dp->i_d.di_forkoff;
}
- dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
+ dsize = XFS_BMAP_BROOT_SPACE(mp, dp->i_df.if_broot);
break;
}
@@ -196,7 +382,8 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
minforkoff = roundup(minforkoff, 8) >> 3;
/* attr fork btree root can have at least this many key/ptr pairs */
- maxforkoff = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
+ maxforkoff = XFS_LITINO(mp, dp->i_d.di_version) -
+ XFS_BMDR_SPACE_CALC(MINABTPTRS);
maxforkoff = maxforkoff >> 3; /* rounded down */
if (offset >= maxforkoff)
@@ -440,7 +627,7 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args)
xfs_attr_sf_entry_t *sfe;
int i;
- ASSERT(args->dp->i_d.di_aformat == XFS_IFINLINE);
+ ASSERT(args->dp->i_afp->if_flags == XFS_IFINLINE);
sf = (xfs_attr_shortform_t *)args->dp->i_afp->if_u1.if_data;
sfe = &sf->list[0];
for (i = 0; i < sf->hdr.count;
@@ -480,7 +667,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
char *tmpbuffer;
int error, i, size;
xfs_dablk_t blkno;
- xfs_dabuf_t *bp;
+ struct xfs_buf *bp;
xfs_ifork_t *ifp;
trace_xfs_attr_sf_to_leaf(args);
@@ -495,6 +682,8 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
sf = (xfs_attr_shortform_t *)tmpbuffer;
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
+ xfs_bmap_local_to_extents_empty(dp, XFS_ATTR_FORK);
+
bp = NULL;
error = xfs_da_grow_inode(args, &blkno);
if (error) {
@@ -510,7 +699,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
}
ASSERT(blkno == 0);
- error = xfs_attr_leaf_create(args, blkno, &bp);
+ error = xfs_attr3_leaf_create(args, blkno, &bp);
if (error) {
error = xfs_da_shrink_inode(args, 0, bp);
bp = NULL;
@@ -523,6 +712,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
memset((char *)&nargs, 0, sizeof(nargs));
nargs.dp = dp;
+ nargs.geo = args->geo;
nargs.firstblock = args->firstblock;
nargs.flist = args->flist;
nargs.total = args->total;
@@ -539,9 +729,9 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
nargs.hashval = xfs_da_hashname(sfe->nameval,
sfe->namelen);
nargs.flags = XFS_ATTR_NSP_ONDISK_TO_ARGS(sfe->flags);
- error = xfs_attr_leaf_lookup_int(bp, &nargs); /* set a->index */
+ error = xfs_attr3_leaf_lookup_int(bp, &nargs); /* set a->index */
ASSERT(error == ENOATTR);
- error = xfs_attr_leaf_add(bp, &nargs);
+ error = xfs_attr3_leaf_add(bp, &nargs);
ASSERT(error != ENOSPC);
if (error)
goto out;
@@ -550,251 +740,85 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
error = 0;
out:
- if(bp)
- xfs_da_buf_done(bp);
kmem_free(tmpbuffer);
return(error);
}
-STATIC int
-xfs_attr_shortform_compare(const void *a, const void *b)
-{
- xfs_attr_sf_sort_t *sa, *sb;
-
- sa = (xfs_attr_sf_sort_t *)a;
- sb = (xfs_attr_sf_sort_t *)b;
- if (sa->hash < sb->hash) {
- return(-1);
- } else if (sa->hash > sb->hash) {
- return(1);
- } else {
- return(sa->entno - sb->entno);
- }
-}
-
-
-#define XFS_ISRESET_CURSOR(cursor) \
- (!((cursor)->initted) && !((cursor)->hashval) && \
- !((cursor)->blkno) && !((cursor)->offset))
-/*
- * Copy out entries of shortform attribute lists for attr_list().
- * Shortform attribute lists are not stored in hashval sorted order.
- * If the output buffer is not large enough to hold them all, then we
- * we have to calculate each entries' hashvalue and sort them before
- * we can begin returning them to the user.
- */
-/*ARGSUSED*/
-int
-xfs_attr_shortform_list(xfs_attr_list_context_t *context)
-{
- attrlist_cursor_kern_t *cursor;
- xfs_attr_sf_sort_t *sbuf, *sbp;
- xfs_attr_shortform_t *sf;
- xfs_attr_sf_entry_t *sfe;
- xfs_inode_t *dp;
- int sbsize, nsbuf, count, i;
- int error;
-
- ASSERT(context != NULL);
- dp = context->dp;
- ASSERT(dp != NULL);
- ASSERT(dp->i_afp != NULL);
- sf = (xfs_attr_shortform_t *)dp->i_afp->if_u1.if_data;
- ASSERT(sf != NULL);
- if (!sf->hdr.count)
- return(0);
- cursor = context->cursor;
- ASSERT(cursor != NULL);
-
- trace_xfs_attr_list_sf(context);
-
- /*
- * If the buffer is large enough and the cursor is at the start,
- * do not bother with sorting since we will return everything in
- * one buffer and another call using the cursor won't need to be
- * made.
- * Note the generous fudge factor of 16 overhead bytes per entry.
- * If bufsize is zero then put_listent must be a search function
- * and can just scan through what we have.
- */
- if (context->bufsize == 0 ||
- (XFS_ISRESET_CURSOR(cursor) &&
- (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
- for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
- error = context->put_listent(context,
- sfe->flags,
- sfe->nameval,
- (int)sfe->namelen,
- (int)sfe->valuelen,
- &sfe->nameval[sfe->namelen]);
-
- /*
- * Either search callback finished early or
- * didn't fit it all in the buffer after all.
- */
- if (context->seen_enough)
- break;
-
- if (error)
- return error;
- sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
- }
- trace_xfs_attr_list_sf_all(context);
- return(0);
- }
-
- /* do no more for a search callback */
- if (context->bufsize == 0)
- return 0;
-
- /*
- * It didn't all fit, so we have to sort everything on hashval.
- */
- sbsize = sf->hdr.count * sizeof(*sbuf);
- sbp = sbuf = kmem_alloc(sbsize, KM_SLEEP | KM_NOFS);
-
- /*
- * Scan the attribute list for the rest of the entries, storing
- * the relevant info from only those that match into a buffer.
- */
- nsbuf = 0;
- for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
- if (unlikely(
- ((char *)sfe < (char *)sf) ||
- ((char *)sfe >= ((char *)sf + dp->i_afp->if_bytes)))) {
- XFS_CORRUPTION_ERROR("xfs_attr_shortform_list",
- XFS_ERRLEVEL_LOW,
- context->dp->i_mount, sfe);
- kmem_free(sbuf);
- return XFS_ERROR(EFSCORRUPTED);
- }
-
- sbp->entno = i;
- sbp->hash = xfs_da_hashname(sfe->nameval, sfe->namelen);
- sbp->name = sfe->nameval;
- sbp->namelen = sfe->namelen;
- /* These are bytes, and both on-disk, don't endian-flip */
- sbp->valuelen = sfe->valuelen;
- sbp->flags = sfe->flags;
- sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
- sbp++;
- nsbuf++;
- }
-
- /*
- * Sort the entries on hash then entno.
- */
- xfs_sort(sbuf, nsbuf, sizeof(*sbuf), xfs_attr_shortform_compare);
-
- /*
- * Re-find our place IN THE SORTED LIST.
- */
- count = 0;
- cursor->initted = 1;
- cursor->blkno = 0;
- for (sbp = sbuf, i = 0; i < nsbuf; i++, sbp++) {
- if (sbp->hash == cursor->hashval) {
- if (cursor->offset == count) {
- break;
- }
- count++;
- } else if (sbp->hash > cursor->hashval) {
- break;
- }
- }
- if (i == nsbuf) {
- kmem_free(sbuf);
- return(0);
- }
-
- /*
- * Loop putting entries into the user buffer.
- */
- for ( ; i < nsbuf; i++, sbp++) {
- if (cursor->hashval != sbp->hash) {
- cursor->hashval = sbp->hash;
- cursor->offset = 0;
- }
- error = context->put_listent(context,
- sbp->flags,
- sbp->name,
- sbp->namelen,
- sbp->valuelen,
- &sbp->name[sbp->namelen]);
- if (error)
- return error;
- if (context->seen_enough)
- break;
- cursor->offset++;
- }
-
- kmem_free(sbuf);
- return(0);
-}
-
/*
* Check a leaf attribute block to see if all the entries would fit into
* a shortform attribute list.
*/
int
-xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
+xfs_attr_shortform_allfit(
+ struct xfs_buf *bp,
+ struct xfs_inode *dp)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr_leaf_entry *entry;
xfs_attr_leaf_name_local_t *name_loc;
- int bytes, i;
+ struct xfs_attr3_icleaf_hdr leafhdr;
+ int bytes;
+ int i;
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&leafhdr, leaf);
+ entry = xfs_attr3_leaf_entryp(leaf);
- entry = &leaf->entries[0];
bytes = sizeof(struct xfs_attr_sf_hdr);
- for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) {
+ for (i = 0; i < leafhdr.count; entry++, i++) {
if (entry->flags & XFS_ATTR_INCOMPLETE)
continue; /* don't copy partial entries */
if (!(entry->flags & XFS_ATTR_LOCAL))
return(0);
- name_loc = xfs_attr_leaf_name_local(leaf, i);
+ name_loc = xfs_attr3_leaf_name_local(leaf, i);
if (name_loc->namelen >= XFS_ATTR_SF_ENTSIZE_MAX)
return(0);
if (be16_to_cpu(name_loc->valuelen) >= XFS_ATTR_SF_ENTSIZE_MAX)
return(0);
- bytes += sizeof(struct xfs_attr_sf_entry)-1
+ bytes += sizeof(struct xfs_attr_sf_entry) - 1
+ name_loc->namelen
+ be16_to_cpu(name_loc->valuelen);
}
if ((dp->i_mount->m_flags & XFS_MOUNT_ATTR2) &&
(dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
(bytes == sizeof(struct xfs_attr_sf_hdr)))
- return(-1);
- return(xfs_attr_shortform_bytesfit(dp, bytes));
+ return -1;
+ return xfs_attr_shortform_bytesfit(dp, bytes);
}
/*
* Convert a leaf attribute list to shortform attribute list
*/
int
-xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
+xfs_attr3_leaf_to_shortform(
+ struct xfs_buf *bp,
+ struct xfs_da_args *args,
+ int forkoff)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
- xfs_attr_leaf_name_local_t *name_loc;
- xfs_da_args_t nargs;
- xfs_inode_t *dp;
- char *tmpbuffer;
- int error, i;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr_leaf_name_local *name_loc;
+ struct xfs_da_args nargs;
+ struct xfs_inode *dp = args->dp;
+ char *tmpbuffer;
+ int error;
+ int i;
trace_xfs_attr_leaf_to_sf(args);
- dp = args->dp;
- tmpbuffer = kmem_alloc(XFS_LBSIZE(dp->i_mount), KM_SLEEP);
- ASSERT(tmpbuffer != NULL);
+ tmpbuffer = kmem_alloc(args->geo->blksize, KM_SLEEP);
+ if (!tmpbuffer)
+ return ENOMEM;
+
+ memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
- ASSERT(bp != NULL);
- memcpy(tmpbuffer, bp->data, XFS_LBSIZE(dp->i_mount));
leaf = (xfs_attr_leafblock_t *)tmpbuffer;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- memset(bp->data, 0, XFS_LBSIZE(dp->i_mount));
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ entry = xfs_attr3_leaf_entryp(leaf);
+
+ /* XXX (dgc): buffer is about to be marked stale - why zero it? */
+ memset(bp->b_addr, 0, args->geo->blksize);
/*
* Clean out the prior contents of the attribute list.
@@ -816,6 +840,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
* Copy the attributes
*/
memset((char *)&nargs, 0, sizeof(nargs));
+ nargs.geo = args->geo;
nargs.dp = dp;
nargs.firstblock = args->firstblock;
nargs.flist = args->flist;
@@ -823,14 +848,14 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
nargs.whichfork = XFS_ATTR_FORK;
nargs.trans = args->trans;
nargs.op_flags = XFS_DA_OP_OKNOENT;
- entry = &leaf->entries[0];
- for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) {
+
+ for (i = 0; i < ichdr.count; entry++, i++) {
if (entry->flags & XFS_ATTR_INCOMPLETE)
continue; /* don't copy partial entries */
if (!entry->nameidx)
continue;
ASSERT(entry->flags & XFS_ATTR_LOCAL);
- name_loc = xfs_attr_leaf_name_local(leaf, i);
+ name_loc = xfs_attr3_leaf_name_local(leaf, i);
nargs.name = name_loc->nameval;
nargs.namelen = name_loc->namelen;
nargs.value = &name_loc->nameval[nargs.namelen];
@@ -843,70 +868,77 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
out:
kmem_free(tmpbuffer);
- return(error);
+ return error;
}
/*
* Convert from using a single leaf to a root node and a leaf.
*/
int
-xfs_attr_leaf_to_node(xfs_da_args_t *args)
+xfs_attr3_leaf_to_node(
+ struct xfs_da_args *args)
{
- xfs_attr_leafblock_t *leaf;
- xfs_da_intnode_t *node;
- xfs_inode_t *dp;
- xfs_dabuf_t *bp1, *bp2;
- xfs_dablk_t blkno;
- int error;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr icleafhdr;
+ struct xfs_attr_leaf_entry *entries;
+ struct xfs_da_node_entry *btree;
+ struct xfs_da3_icnode_hdr icnodehdr;
+ struct xfs_da_intnode *node;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_buf *bp1 = NULL;
+ struct xfs_buf *bp2 = NULL;
+ xfs_dablk_t blkno;
+ int error;
trace_xfs_attr_leaf_to_node(args);
- dp = args->dp;
- bp1 = bp2 = NULL;
error = xfs_da_grow_inode(args, &blkno);
if (error)
goto out;
- error = xfs_da_read_buf(args->trans, args->dp, 0, -1, &bp1,
- XFS_ATTR_FORK);
+ error = xfs_attr3_leaf_read(args->trans, dp, 0, -1, &bp1);
if (error)
goto out;
- ASSERT(bp1 != NULL);
- bp2 = NULL;
- error = xfs_da_get_buf(args->trans, args->dp, blkno, -1, &bp2,
- XFS_ATTR_FORK);
+
+ error = xfs_da_get_buf(args->trans, dp, blkno, -1, &bp2, XFS_ATTR_FORK);
if (error)
goto out;
- ASSERT(bp2 != NULL);
- memcpy(bp2->data, bp1->data, XFS_LBSIZE(dp->i_mount));
- xfs_da_buf_done(bp1);
- bp1 = NULL;
- xfs_da_log_buf(args->trans, bp2, 0, XFS_LBSIZE(dp->i_mount) - 1);
+
+ /* copy leaf to new buffer, update identifiers */
+ xfs_trans_buf_set_type(args->trans, bp2, XFS_BLFT_ATTR_LEAF_BUF);
+ bp2->b_ops = bp1->b_ops;
+ memcpy(bp2->b_addr, bp1->b_addr, args->geo->blksize);
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_da3_blkinfo *hdr3 = bp2->b_addr;
+ hdr3->blkno = cpu_to_be64(bp2->b_bn);
+ }
+ xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1);
/*
* Set up the new root node.
*/
- error = xfs_da_node_create(args, 0, 1, &bp1, XFS_ATTR_FORK);
+ error = xfs_da3_node_create(args, 0, 1, &bp1, XFS_ATTR_FORK);
if (error)
goto out;
- node = bp1->data;
- leaf = bp2->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
+ node = bp1->b_addr;
+ dp->d_ops->node_hdr_from_disk(&icnodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
+
+ leaf = bp2->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&icleafhdr, leaf);
+ entries = xfs_attr3_leaf_entryp(leaf);
+
/* both on-disk, don't endian-flip twice */
- node->btree[0].hashval =
- leaf->entries[be16_to_cpu(leaf->hdr.count)-1 ].hashval;
- node->btree[0].before = cpu_to_be32(blkno);
- node->hdr.count = cpu_to_be16(1);
- xfs_da_log_buf(args->trans, bp1, 0, XFS_LBSIZE(dp->i_mount) - 1);
+ btree[0].hashval = entries[icleafhdr.count - 1].hashval;
+ btree[0].before = cpu_to_be32(blkno);
+ icnodehdr.count = 1;
+ dp->d_ops->node_hdr_to_disk(node, &icnodehdr);
+ xfs_trans_log_buf(args->trans, bp1, 0, args->geo->blksize - 1);
error = 0;
out:
- if (bp1)
- xfs_da_buf_done(bp1);
- if (bp2)
- xfs_da_buf_done(bp2);
- return(error);
+ return error;
}
-
/*========================================================================
* Routines used for growing the Btree.
*========================================================================*/
@@ -916,49 +948,63 @@ out:
* or a leaf in a node attribute list.
*/
STATIC int
-xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
+xfs_attr3_leaf_create(
+ struct xfs_da_args *args,
+ xfs_dablk_t blkno,
+ struct xfs_buf **bpp)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_hdr_t *hdr;
- xfs_inode_t *dp;
- xfs_dabuf_t *bp;
- int error;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_buf *bp;
+ int error;
trace_xfs_attr_leaf_create(args);
- dp = args->dp;
- ASSERT(dp != NULL);
error = xfs_da_get_buf(args->trans, args->dp, blkno, -1, &bp,
XFS_ATTR_FORK);
if (error)
- return(error);
- ASSERT(bp != NULL);
- leaf = bp->data;
- memset((char *)leaf, 0, XFS_LBSIZE(dp->i_mount));
- hdr = &leaf->hdr;
- hdr->info.magic = cpu_to_be16(XFS_ATTR_LEAF_MAGIC);
- hdr->firstused = cpu_to_be16(XFS_LBSIZE(dp->i_mount));
- if (!hdr->firstused) {
- hdr->firstused = cpu_to_be16(
- XFS_LBSIZE(dp->i_mount) - XFS_ATTR_LEAF_NAME_ALIGN);
- }
+ return error;
+ bp->b_ops = &xfs_attr3_leaf_buf_ops;
+ xfs_trans_buf_set_type(args->trans, bp, XFS_BLFT_ATTR_LEAF_BUF);
+ leaf = bp->b_addr;
+ memset(leaf, 0, args->geo->blksize);
+
+ memset(&ichdr, 0, sizeof(ichdr));
+ ichdr.firstused = args->geo->blksize;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_da3_blkinfo *hdr3 = bp->b_addr;
+
+ ichdr.magic = XFS_ATTR3_LEAF_MAGIC;
- hdr->freemap[0].base = cpu_to_be16(sizeof(xfs_attr_leaf_hdr_t));
- hdr->freemap[0].size = cpu_to_be16(be16_to_cpu(hdr->firstused) -
- sizeof(xfs_attr_leaf_hdr_t));
+ hdr3->blkno = cpu_to_be64(bp->b_bn);
+ hdr3->owner = cpu_to_be64(dp->i_ino);
+ uuid_copy(&hdr3->uuid, &mp->m_sb.sb_uuid);
- xfs_da_log_buf(args->trans, bp, 0, XFS_LBSIZE(dp->i_mount) - 1);
+ ichdr.freemap[0].base = sizeof(struct xfs_attr3_leaf_hdr);
+ } else {
+ ichdr.magic = XFS_ATTR_LEAF_MAGIC;
+ ichdr.freemap[0].base = sizeof(struct xfs_attr_leaf_hdr);
+ }
+ ichdr.freemap[0].size = ichdr.firstused - ichdr.freemap[0].base;
+
+ xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr);
+ xfs_trans_log_buf(args->trans, bp, 0, args->geo->blksize - 1);
*bpp = bp;
- return(0);
+ return 0;
}
/*
* Split the leaf node, rebalance, then add the new entry.
*/
int
-xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
- xfs_da_state_blk_t *newblk)
+xfs_attr3_leaf_split(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *oldblk,
+ struct xfs_da_state_blk *newblk)
{
xfs_dablk_t blkno;
int error;
@@ -972,7 +1018,7 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
error = xfs_da_grow_inode(state->args, &blkno);
if (error)
return(error);
- error = xfs_attr_leaf_create(state->args, blkno, &newblk->bp);
+ error = xfs_attr3_leaf_create(state->args, blkno, &newblk->bp);
if (error)
return(error);
newblk->blkno = blkno;
@@ -982,8 +1028,8 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
* Rebalance the entries across the two leaves.
* NOTE: rebalance() currently depends on the 2nd block being empty.
*/
- xfs_attr_leaf_rebalance(state, oldblk, newblk);
- error = xfs_da_blk_link(state, oldblk, newblk);
+ xfs_attr3_leaf_rebalance(state, oldblk, newblk);
+ error = xfs_da3_blk_link(state, oldblk, newblk);
if (error)
return(error);
@@ -996,10 +1042,10 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
*/
if (state->inleaf) {
trace_xfs_attr_leaf_add_old(state->args);
- error = xfs_attr_leaf_add(oldblk->bp, state->args);
+ error = xfs_attr3_leaf_add(oldblk->bp, state->args);
} else {
trace_xfs_attr_leaf_add_new(state->args);
- error = xfs_attr_leaf_add(newblk->bp, state->args);
+ error = xfs_attr3_leaf_add(newblk->bp, state->args);
}
/*
@@ -1014,46 +1060,46 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
* Add a name to the leaf attribute list structure.
*/
int
-xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr3_leaf_add(
+ struct xfs_buf *bp,
+ struct xfs_da_args *args)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_hdr_t *hdr;
- xfs_attr_leaf_map_t *map;
- int tablesize, entsize, sum, tmp, i;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ int tablesize;
+ int entsize;
+ int sum;
+ int tmp;
+ int i;
trace_xfs_attr_leaf_add(args);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT((args->index >= 0)
- && (args->index <= be16_to_cpu(leaf->hdr.count)));
- hdr = &leaf->hdr;
- entsize = xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
- args->trans->t_mountp->m_sb.sb_blocksize, NULL);
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ ASSERT(args->index >= 0 && args->index <= ichdr.count);
+ entsize = xfs_attr_leaf_newentsize(args, NULL);
/*
* Search through freemap for first-fit on new name length.
* (may need to figure in size of entry struct too)
*/
- tablesize = (be16_to_cpu(hdr->count) + 1)
- * sizeof(xfs_attr_leaf_entry_t)
- + sizeof(xfs_attr_leaf_hdr_t);
- map = &hdr->freemap[XFS_ATTR_LEAF_MAPSIZE-1];
- for (sum = 0, i = XFS_ATTR_LEAF_MAPSIZE-1; i >= 0; map--, i--) {
- if (tablesize > be16_to_cpu(hdr->firstused)) {
- sum += be16_to_cpu(map->size);
+ tablesize = (ichdr.count + 1) * sizeof(xfs_attr_leaf_entry_t)
+ + xfs_attr3_leaf_hdr_size(leaf);
+ for (sum = 0, i = XFS_ATTR_LEAF_MAPSIZE - 1; i >= 0; i--) {
+ if (tablesize > ichdr.firstused) {
+ sum += ichdr.freemap[i].size;
continue;
}
- if (!map->size)
+ if (!ichdr.freemap[i].size)
continue; /* no space in this map */
tmp = entsize;
- if (be16_to_cpu(map->base) < be16_to_cpu(hdr->firstused))
+ if (ichdr.freemap[i].base < ichdr.firstused)
tmp += sizeof(xfs_attr_leaf_entry_t);
- if (be16_to_cpu(map->size) >= tmp) {
- tmp = xfs_attr_leaf_add_work(bp, args, i);
- return(tmp);
+ if (ichdr.freemap[i].size >= tmp) {
+ tmp = xfs_attr3_leaf_add_work(bp, &ichdr, args, i);
+ goto out_log_hdr;
}
- sum += be16_to_cpu(map->size);
+ sum += ichdr.freemap[i].size;
}
/*
@@ -1061,77 +1107,86 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
* and we don't have enough freespace, then compaction will do us
* no good and we should just give up.
*/
- if (!hdr->holes && (sum < entsize))
- return(XFS_ERROR(ENOSPC));
+ if (!ichdr.holes && sum < entsize)
+ return XFS_ERROR(ENOSPC);
/*
* Compact the entries to coalesce free space.
* This may change the hdr->count via dropping INCOMPLETE entries.
*/
- xfs_attr_leaf_compact(args->trans, bp);
+ xfs_attr3_leaf_compact(args, &ichdr, bp);
/*
* After compaction, the block is guaranteed to have only one
* free region, in freemap[0]. If it is not big enough, give up.
*/
- if (be16_to_cpu(hdr->freemap[0].size)
- < (entsize + sizeof(xfs_attr_leaf_entry_t)))
- return(XFS_ERROR(ENOSPC));
+ if (ichdr.freemap[0].size < (entsize + sizeof(xfs_attr_leaf_entry_t))) {
+ tmp = ENOSPC;
+ goto out_log_hdr;
+ }
- return(xfs_attr_leaf_add_work(bp, args, 0));
+ tmp = xfs_attr3_leaf_add_work(bp, &ichdr, args, 0);
+
+out_log_hdr:
+ xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr);
+ xfs_trans_log_buf(args->trans, bp,
+ XFS_DA_LOGRANGE(leaf, &leaf->hdr,
+ xfs_attr3_leaf_hdr_size(leaf)));
+ return tmp;
}
/*
* Add a name to a leaf attribute list structure.
*/
STATIC int
-xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
+xfs_attr3_leaf_add_work(
+ struct xfs_buf *bp,
+ struct xfs_attr3_icleaf_hdr *ichdr,
+ struct xfs_da_args *args,
+ int mapindex)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_hdr_t *hdr;
- xfs_attr_leaf_entry_t *entry;
- xfs_attr_leaf_name_local_t *name_loc;
- xfs_attr_leaf_name_remote_t *name_rmt;
- xfs_attr_leaf_map_t *map;
- xfs_mount_t *mp;
- int tmp, i;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr_leaf_name_local *name_loc;
+ struct xfs_attr_leaf_name_remote *name_rmt;
+ struct xfs_mount *mp;
+ int tmp;
+ int i;
+
+ trace_xfs_attr_leaf_add_work(args);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- hdr = &leaf->hdr;
- ASSERT((mapindex >= 0) && (mapindex < XFS_ATTR_LEAF_MAPSIZE));
- ASSERT((args->index >= 0) && (args->index <= be16_to_cpu(hdr->count)));
+ leaf = bp->b_addr;
+ ASSERT(mapindex >= 0 && mapindex < XFS_ATTR_LEAF_MAPSIZE);
+ ASSERT(args->index >= 0 && args->index <= ichdr->count);
/*
* Force open some space in the entry array and fill it in.
*/
- entry = &leaf->entries[args->index];
- if (args->index < be16_to_cpu(hdr->count)) {
- tmp = be16_to_cpu(hdr->count) - args->index;
+ entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
+ if (args->index < ichdr->count) {
+ tmp = ichdr->count - args->index;
tmp *= sizeof(xfs_attr_leaf_entry_t);
- memmove((char *)(entry+1), (char *)entry, tmp);
- xfs_da_log_buf(args->trans, bp,
+ memmove(entry + 1, entry, tmp);
+ xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
}
- be16_add_cpu(&hdr->count, 1);
+ ichdr->count++;
/*
* Allocate space for the new string (at the end of the run).
*/
- map = &hdr->freemap[mapindex];
mp = args->trans->t_mountp;
- ASSERT(be16_to_cpu(map->base) < XFS_LBSIZE(mp));
- ASSERT((be16_to_cpu(map->base) & 0x3) == 0);
- ASSERT(be16_to_cpu(map->size) >=
- xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
- mp->m_sb.sb_blocksize, NULL));
- ASSERT(be16_to_cpu(map->size) < XFS_LBSIZE(mp));
- ASSERT((be16_to_cpu(map->size) & 0x3) == 0);
- be16_add_cpu(&map->size,
- -xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
- mp->m_sb.sb_blocksize, &tmp));
- entry->nameidx = cpu_to_be16(be16_to_cpu(map->base) +
- be16_to_cpu(map->size));
+ ASSERT(ichdr->freemap[mapindex].base < args->geo->blksize);
+ ASSERT((ichdr->freemap[mapindex].base & 0x3) == 0);
+ ASSERT(ichdr->freemap[mapindex].size >=
+ xfs_attr_leaf_newentsize(args, NULL));
+ ASSERT(ichdr->freemap[mapindex].size < args->geo->blksize);
+ ASSERT((ichdr->freemap[mapindex].size & 0x3) == 0);
+
+ ichdr->freemap[mapindex].size -= xfs_attr_leaf_newentsize(args, &tmp);
+
+ entry->nameidx = cpu_to_be16(ichdr->freemap[mapindex].base +
+ ichdr->freemap[mapindex].size);
entry->hashval = cpu_to_be32(args->hashval);
entry->flags = tmp ? XFS_ATTR_LOCAL : 0;
entry->flags |= XFS_ATTR_NSP_ARGS_TO_ONDISK(args->flags);
@@ -1142,11 +1197,11 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
args->index2++;
}
}
- xfs_da_log_buf(args->trans, bp,
+ xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
ASSERT((args->index == 0) ||
(be32_to_cpu(entry->hashval) >= be32_to_cpu((entry-1)->hashval)));
- ASSERT((args->index == be16_to_cpu(hdr->count)-1) ||
+ ASSERT((args->index == ichdr->count - 1) ||
(be32_to_cpu(entry->hashval) <= be32_to_cpu((entry+1)->hashval)));
/*
@@ -1157,14 +1212,14 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
* as part of this transaction (a split operation for example).
*/
if (entry->flags & XFS_ATTR_LOCAL) {
- name_loc = xfs_attr_leaf_name_local(leaf, args->index);
+ name_loc = xfs_attr3_leaf_name_local(leaf, args->index);
name_loc->namelen = args->namelen;
name_loc->valuelen = cpu_to_be16(args->valuelen);
memcpy((char *)name_loc->nameval, args->name, args->namelen);
memcpy((char *)&name_loc->nameval[args->namelen], args->value,
be16_to_cpu(name_loc->valuelen));
} else {
- name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
name_rmt->namelen = args->namelen;
memcpy((char *)name_rmt->name, args->name, args->namelen);
entry->flags |= XFS_ATTR_INCOMPLETE;
@@ -1172,87 +1227,132 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
name_rmt->valuelen = 0;
name_rmt->valueblk = 0;
args->rmtblkno = 1;
- args->rmtblkcnt = XFS_B_TO_FSB(mp, args->valuelen);
+ args->rmtblkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen);
+ args->rmtvaluelen = args->valuelen;
}
- xfs_da_log_buf(args->trans, bp,
- XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
+ xfs_trans_log_buf(args->trans, bp,
+ XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index),
xfs_attr_leaf_entsize(leaf, args->index)));
/*
* Update the control info for this leaf node
*/
- if (be16_to_cpu(entry->nameidx) < be16_to_cpu(hdr->firstused)) {
- /* both on-disk, don't endian-flip twice */
- hdr->firstused = entry->nameidx;
- }
- ASSERT(be16_to_cpu(hdr->firstused) >=
- ((be16_to_cpu(hdr->count) * sizeof(*entry)) + sizeof(*hdr)));
- tmp = (be16_to_cpu(hdr->count)-1) * sizeof(xfs_attr_leaf_entry_t)
- + sizeof(xfs_attr_leaf_hdr_t);
- map = &hdr->freemap[0];
- for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; map++, i++) {
- if (be16_to_cpu(map->base) == tmp) {
- be16_add_cpu(&map->base, sizeof(xfs_attr_leaf_entry_t));
- be16_add_cpu(&map->size,
- -((int)sizeof(xfs_attr_leaf_entry_t)));
+ if (be16_to_cpu(entry->nameidx) < ichdr->firstused)
+ ichdr->firstused = be16_to_cpu(entry->nameidx);
+
+ ASSERT(ichdr->firstused >= ichdr->count * sizeof(xfs_attr_leaf_entry_t)
+ + xfs_attr3_leaf_hdr_size(leaf));
+ tmp = (ichdr->count - 1) * sizeof(xfs_attr_leaf_entry_t)
+ + xfs_attr3_leaf_hdr_size(leaf);
+
+ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+ if (ichdr->freemap[i].base == tmp) {
+ ichdr->freemap[i].base += sizeof(xfs_attr_leaf_entry_t);
+ ichdr->freemap[i].size -= sizeof(xfs_attr_leaf_entry_t);
}
}
- be16_add_cpu(&hdr->usedbytes, xfs_attr_leaf_entsize(leaf, args->index));
- xfs_da_log_buf(args->trans, bp,
- XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
- return(0);
+ ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index);
+ return 0;
}
/*
* Garbage collect a leaf attribute list block by copying it to a new buffer.
*/
STATIC void
-xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
+xfs_attr3_leaf_compact(
+ struct xfs_da_args *args,
+ struct xfs_attr3_icleaf_hdr *ichdr_dst,
+ struct xfs_buf *bp)
{
- xfs_attr_leafblock_t *leaf_s, *leaf_d;
- xfs_attr_leaf_hdr_t *hdr_s, *hdr_d;
- xfs_mount_t *mp;
- char *tmpbuffer;
+ struct xfs_attr_leafblock *leaf_src;
+ struct xfs_attr_leafblock *leaf_dst;
+ struct xfs_attr3_icleaf_hdr ichdr_src;
+ struct xfs_trans *trans = args->trans;
+ char *tmpbuffer;
- mp = trans->t_mountp;
- tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP);
- ASSERT(tmpbuffer != NULL);
- memcpy(tmpbuffer, bp->data, XFS_LBSIZE(mp));
- memset(bp->data, 0, XFS_LBSIZE(mp));
+ trace_xfs_attr_leaf_compact(args);
+
+ tmpbuffer = kmem_alloc(args->geo->blksize, KM_SLEEP);
+ memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
+ memset(bp->b_addr, 0, args->geo->blksize);
+ leaf_src = (xfs_attr_leafblock_t *)tmpbuffer;
+ leaf_dst = bp->b_addr;
/*
- * Copy basic information
+ * Copy the on-disk header back into the destination buffer to ensure
+ * all the information in the header that is not part of the incore
+ * header structure is preserved.
*/
- leaf_s = (xfs_attr_leafblock_t *)tmpbuffer;
- leaf_d = bp->data;
- hdr_s = &leaf_s->hdr;
- hdr_d = &leaf_d->hdr;
- hdr_d->info = hdr_s->info; /* struct copy */
- hdr_d->firstused = cpu_to_be16(XFS_LBSIZE(mp));
- /* handle truncation gracefully */
- if (!hdr_d->firstused) {
- hdr_d->firstused = cpu_to_be16(
- XFS_LBSIZE(mp) - XFS_ATTR_LEAF_NAME_ALIGN);
- }
- hdr_d->usedbytes = 0;
- hdr_d->count = 0;
- hdr_d->holes = 0;
- hdr_d->freemap[0].base = cpu_to_be16(sizeof(xfs_attr_leaf_hdr_t));
- hdr_d->freemap[0].size = cpu_to_be16(be16_to_cpu(hdr_d->firstused) -
- sizeof(xfs_attr_leaf_hdr_t));
+ memcpy(bp->b_addr, tmpbuffer, xfs_attr3_leaf_hdr_size(leaf_src));
+
+ /* Initialise the incore headers */
+ ichdr_src = *ichdr_dst; /* struct copy */
+ ichdr_dst->firstused = args->geo->blksize;
+ ichdr_dst->usedbytes = 0;
+ ichdr_dst->count = 0;
+ ichdr_dst->holes = 0;
+ ichdr_dst->freemap[0].base = xfs_attr3_leaf_hdr_size(leaf_src);
+ ichdr_dst->freemap[0].size = ichdr_dst->firstused -
+ ichdr_dst->freemap[0].base;
+
+ /* write the header back to initialise the underlying buffer */
+ xfs_attr3_leaf_hdr_to_disk(leaf_dst, ichdr_dst);
/*
* Copy all entry's in the same (sorted) order,
* but allocate name/value pairs packed and in sequence.
*/
- xfs_attr_leaf_moveents(leaf_s, 0, leaf_d, 0,
- be16_to_cpu(hdr_s->count), mp);
- xfs_da_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
+ xfs_attr3_leaf_moveents(args, leaf_src, &ichdr_src, 0,
+ leaf_dst, ichdr_dst, 0, ichdr_src.count);
+ /*
+ * this logs the entire buffer, but the caller must write the header
+ * back to the buffer when it is finished modifying it.
+ */
+ xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1);
kmem_free(tmpbuffer);
}
/*
+ * Compare two leaf blocks "order".
+ * Return 0 unless leaf2 should go before leaf1.
+ */
+static int
+xfs_attr3_leaf_order(
+ struct xfs_buf *leaf1_bp,
+ struct xfs_attr3_icleaf_hdr *leaf1hdr,
+ struct xfs_buf *leaf2_bp,
+ struct xfs_attr3_icleaf_hdr *leaf2hdr)
+{
+ struct xfs_attr_leaf_entry *entries1;
+ struct xfs_attr_leaf_entry *entries2;
+
+ entries1 = xfs_attr3_leaf_entryp(leaf1_bp->b_addr);
+ entries2 = xfs_attr3_leaf_entryp(leaf2_bp->b_addr);
+ if (leaf1hdr->count > 0 && leaf2hdr->count > 0 &&
+ ((be32_to_cpu(entries2[0].hashval) <
+ be32_to_cpu(entries1[0].hashval)) ||
+ (be32_to_cpu(entries2[leaf2hdr->count - 1].hashval) <
+ be32_to_cpu(entries1[leaf1hdr->count - 1].hashval)))) {
+ return 1;
+ }
+ return 0;
+}
+
+int
+xfs_attr_leaf_order(
+ struct xfs_buf *leaf1_bp,
+ struct xfs_buf *leaf2_bp)
+{
+ struct xfs_attr3_icleaf_hdr ichdr1;
+ struct xfs_attr3_icleaf_hdr ichdr2;
+
+ xfs_attr3_leaf_hdr_from_disk(&ichdr1, leaf1_bp->b_addr);
+ xfs_attr3_leaf_hdr_from_disk(&ichdr2, leaf2_bp->b_addr);
+ return xfs_attr3_leaf_order(leaf1_bp, &ichdr1, leaf2_bp, &ichdr2);
+}
+
+/*
* Redistribute the attribute list entries between two leaf nodes,
* taking into account the size of the new entry.
*
@@ -1265,24 +1365,34 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
* the "new" and "old" values can end up in different blocks.
*/
STATIC void
-xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
- xfs_da_state_blk_t *blk2)
+xfs_attr3_leaf_rebalance(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *blk1,
+ struct xfs_da_state_blk *blk2)
{
- xfs_da_args_t *args;
- xfs_da_state_blk_t *tmp_blk;
- xfs_attr_leafblock_t *leaf1, *leaf2;
- xfs_attr_leaf_hdr_t *hdr1, *hdr2;
- int count, totallen, max, space, swap;
+ struct xfs_da_args *args;
+ struct xfs_attr_leafblock *leaf1;
+ struct xfs_attr_leafblock *leaf2;
+ struct xfs_attr3_icleaf_hdr ichdr1;
+ struct xfs_attr3_icleaf_hdr ichdr2;
+ struct xfs_attr_leaf_entry *entries1;
+ struct xfs_attr_leaf_entry *entries2;
+ int count;
+ int totallen;
+ int max;
+ int space;
+ int swap;
/*
* Set up environment.
*/
ASSERT(blk1->magic == XFS_ATTR_LEAF_MAGIC);
ASSERT(blk2->magic == XFS_ATTR_LEAF_MAGIC);
- leaf1 = blk1->bp->data;
- leaf2 = blk2->bp->data;
- ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
+ leaf1 = blk1->bp->b_addr;
+ leaf2 = blk2->bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr1, leaf1);
+ xfs_attr3_leaf_hdr_from_disk(&ichdr2, leaf2);
+ ASSERT(ichdr2.count == 0);
args = state->args;
trace_xfs_attr_leaf_rebalance(args);
@@ -1294,16 +1404,23 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* second block, this code should never set "swap".
*/
swap = 0;
- if (xfs_attr_leaf_order(blk1->bp, blk2->bp)) {
+ if (xfs_attr3_leaf_order(blk1->bp, &ichdr1, blk2->bp, &ichdr2)) {
+ struct xfs_da_state_blk *tmp_blk;
+ struct xfs_attr3_icleaf_hdr tmp_ichdr;
+
tmp_blk = blk1;
blk1 = blk2;
blk2 = tmp_blk;
- leaf1 = blk1->bp->data;
- leaf2 = blk2->bp->data;
+
+ /* struct copies to swap them rather than reconverting */
+ tmp_ichdr = ichdr1;
+ ichdr1 = ichdr2;
+ ichdr2 = tmp_ichdr;
+
+ leaf1 = blk1->bp->b_addr;
+ leaf2 = blk2->bp->b_addr;
swap = 1;
}
- hdr1 = &leaf1->hdr;
- hdr2 = &leaf2->hdr;
/*
* Examine entries until we reduce the absolute difference in
@@ -1313,82 +1430,80 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* "inleaf" is true if the new entry should be inserted into blk1.
* If "swap" is also true, then reverse the sense of "inleaf".
*/
- state->inleaf = xfs_attr_leaf_figure_balance(state, blk1, blk2,
- &count, &totallen);
+ state->inleaf = xfs_attr3_leaf_figure_balance(state, blk1, &ichdr1,
+ blk2, &ichdr2,
+ &count, &totallen);
if (swap)
state->inleaf = !state->inleaf;
/*
* Move any entries required from leaf to leaf:
*/
- if (count < be16_to_cpu(hdr1->count)) {
+ if (count < ichdr1.count) {
/*
* Figure the total bytes to be added to the destination leaf.
*/
/* number entries being moved */
- count = be16_to_cpu(hdr1->count) - count;
- space = be16_to_cpu(hdr1->usedbytes) - totallen;
+ count = ichdr1.count - count;
+ space = ichdr1.usedbytes - totallen;
space += count * sizeof(xfs_attr_leaf_entry_t);
/*
* leaf2 is the destination, compact it if it looks tight.
*/
- max = be16_to_cpu(hdr2->firstused)
- - sizeof(xfs_attr_leaf_hdr_t);
- max -= be16_to_cpu(hdr2->count) * sizeof(xfs_attr_leaf_entry_t);
- if (space > max) {
- xfs_attr_leaf_compact(args->trans, blk2->bp);
- }
+ max = ichdr2.firstused - xfs_attr3_leaf_hdr_size(leaf1);
+ max -= ichdr2.count * sizeof(xfs_attr_leaf_entry_t);
+ if (space > max)
+ xfs_attr3_leaf_compact(args, &ichdr2, blk2->bp);
/*
* Move high entries from leaf1 to low end of leaf2.
*/
- xfs_attr_leaf_moveents(leaf1, be16_to_cpu(hdr1->count) - count,
- leaf2, 0, count, state->mp);
+ xfs_attr3_leaf_moveents(args, leaf1, &ichdr1,
+ ichdr1.count - count, leaf2, &ichdr2, 0, count);
- xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
- xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
- } else if (count > be16_to_cpu(hdr1->count)) {
+ } else if (count > ichdr1.count) {
/*
* I assert that since all callers pass in an empty
* second buffer, this code should never execute.
*/
+ ASSERT(0);
/*
* Figure the total bytes to be added to the destination leaf.
*/
/* number entries being moved */
- count -= be16_to_cpu(hdr1->count);
- space = totallen - be16_to_cpu(hdr1->usedbytes);
+ count -= ichdr1.count;
+ space = totallen - ichdr1.usedbytes;
space += count * sizeof(xfs_attr_leaf_entry_t);
/*
* leaf1 is the destination, compact it if it looks tight.
*/
- max = be16_to_cpu(hdr1->firstused)
- - sizeof(xfs_attr_leaf_hdr_t);
- max -= be16_to_cpu(hdr1->count) * sizeof(xfs_attr_leaf_entry_t);
- if (space > max) {
- xfs_attr_leaf_compact(args->trans, blk1->bp);
- }
+ max = ichdr1.firstused - xfs_attr3_leaf_hdr_size(leaf1);
+ max -= ichdr1.count * sizeof(xfs_attr_leaf_entry_t);
+ if (space > max)
+ xfs_attr3_leaf_compact(args, &ichdr1, blk1->bp);
/*
* Move low entries from leaf2 to high end of leaf1.
*/
- xfs_attr_leaf_moveents(leaf2, 0, leaf1,
- be16_to_cpu(hdr1->count), count, state->mp);
-
- xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
- xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+ xfs_attr3_leaf_moveents(args, leaf2, &ichdr2, 0, leaf1, &ichdr1,
+ ichdr1.count, count);
}
+ xfs_attr3_leaf_hdr_to_disk(leaf1, &ichdr1);
+ xfs_attr3_leaf_hdr_to_disk(leaf2, &ichdr2);
+ xfs_trans_log_buf(args->trans, blk1->bp, 0, args->geo->blksize - 1);
+ xfs_trans_log_buf(args->trans, blk2->bp, 0, args->geo->blksize - 1);
+
/*
* Copy out last hashval in each block for B-tree code.
*/
- blk1->hashval = be32_to_cpu(
- leaf1->entries[be16_to_cpu(leaf1->hdr.count)-1].hashval);
- blk2->hashval = be32_to_cpu(
- leaf2->entries[be16_to_cpu(leaf2->hdr.count)-1].hashval);
+ entries1 = xfs_attr3_leaf_entryp(leaf1);
+ entries2 = xfs_attr3_leaf_entryp(leaf2);
+ blk1->hashval = be32_to_cpu(entries1[ichdr1.count - 1].hashval);
+ blk2->hashval = be32_to_cpu(entries2[ichdr2.count - 1].hashval);
/*
* Adjust the expected index for insertion.
@@ -1402,22 +1517,35 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* inserting. The index/blkno fields refer to the "old" entry,
* while the index2/blkno2 fields refer to the "new" entry.
*/
- if (blk1->index > be16_to_cpu(leaf1->hdr.count)) {
+ if (blk1->index > ichdr1.count) {
ASSERT(state->inleaf == 0);
- blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count);
+ blk2->index = blk1->index - ichdr1.count;
args->index = args->index2 = blk2->index;
args->blkno = args->blkno2 = blk2->blkno;
- } else if (blk1->index == be16_to_cpu(leaf1->hdr.count)) {
+ } else if (blk1->index == ichdr1.count) {
if (state->inleaf) {
args->index = blk1->index;
args->blkno = blk1->blkno;
args->index2 = 0;
args->blkno2 = blk2->blkno;
} else {
- blk2->index = blk1->index
- - be16_to_cpu(leaf1->hdr.count);
- args->index = args->index2 = blk2->index;
- args->blkno = args->blkno2 = blk2->blkno;
+ /*
+ * On a double leaf split, the original attr location
+ * is already stored in blkno2/index2, so don't
+ * overwrite it overwise we corrupt the tree.
+ */
+ blk2->index = blk1->index - ichdr1.count;
+ args->index = blk2->index;
+ args->blkno = blk2->blkno;
+ if (!state->extravalid) {
+ /*
+ * set the new attr location to match the old
+ * one and let the higher level split code
+ * decide where in the leaf to place it.
+ */
+ args->index2 = blk2->index;
+ args->blkno2 = blk2->blkno;
+ }
}
} else {
ASSERT(state->inleaf == 1);
@@ -1434,42 +1562,38 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* GROT: Do a double-split for this case?
*/
STATIC int
-xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
- xfs_da_state_blk_t *blk1,
- xfs_da_state_blk_t *blk2,
- int *countarg, int *usedbytesarg)
+xfs_attr3_leaf_figure_balance(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *blk1,
+ struct xfs_attr3_icleaf_hdr *ichdr1,
+ struct xfs_da_state_blk *blk2,
+ struct xfs_attr3_icleaf_hdr *ichdr2,
+ int *countarg,
+ int *usedbytesarg)
{
- xfs_attr_leafblock_t *leaf1, *leaf2;
- xfs_attr_leaf_hdr_t *hdr1, *hdr2;
- xfs_attr_leaf_entry_t *entry;
- int count, max, index, totallen, half;
- int lastdelta, foundit, tmp;
-
- /*
- * Set up environment.
- */
- leaf1 = blk1->bp->data;
- leaf2 = blk2->bp->data;
- hdr1 = &leaf1->hdr;
- hdr2 = &leaf2->hdr;
- foundit = 0;
- totallen = 0;
+ struct xfs_attr_leafblock *leaf1 = blk1->bp->b_addr;
+ struct xfs_attr_leafblock *leaf2 = blk2->bp->b_addr;
+ struct xfs_attr_leaf_entry *entry;
+ int count;
+ int max;
+ int index;
+ int totallen = 0;
+ int half;
+ int lastdelta;
+ int foundit = 0;
+ int tmp;
/*
* Examine entries until we reduce the absolute difference in
* byte usage between the two blocks to a minimum.
*/
- max = be16_to_cpu(hdr1->count) + be16_to_cpu(hdr2->count);
- half = (max+1) * sizeof(*entry);
- half += be16_to_cpu(hdr1->usedbytes) +
- be16_to_cpu(hdr2->usedbytes) +
- xfs_attr_leaf_newentsize(
- state->args->namelen,
- state->args->valuelen,
- state->blocksize, NULL);
+ max = ichdr1->count + ichdr2->count;
+ half = (max + 1) * sizeof(*entry);
+ half += ichdr1->usedbytes + ichdr2->usedbytes +
+ xfs_attr_leaf_newentsize(state->args, NULL);
half /= 2;
- lastdelta = state->blocksize;
- entry = &leaf1->entries[0];
+ lastdelta = state->args->geo->blksize;
+ entry = xfs_attr3_leaf_entryp(leaf1);
for (count = index = 0; count < max; entry++, index++, count++) {
#define XFS_ATTR_ABS(A) (((A) < 0) ? -(A) : (A))
@@ -1478,10 +1602,7 @@ xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
*/
if (count == blk1->index) {
tmp = totallen + sizeof(*entry) +
- xfs_attr_leaf_newentsize(
- state->args->namelen,
- state->args->valuelen,
- state->blocksize, NULL);
+ xfs_attr_leaf_newentsize(state->args, NULL);
if (XFS_ATTR_ABS(half - tmp) > lastdelta)
break;
lastdelta = XFS_ATTR_ABS(half - tmp);
@@ -1492,9 +1613,9 @@ xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
/*
* Wrap around into the second block if necessary.
*/
- if (count == be16_to_cpu(hdr1->count)) {
+ if (count == ichdr1->count) {
leaf1 = leaf2;
- entry = &leaf1->entries[0];
+ entry = xfs_attr3_leaf_entryp(leaf1);
index = 0;
}
@@ -1517,15 +1638,12 @@ xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
totallen -= count * sizeof(*entry);
if (foundit) {
totallen -= sizeof(*entry) +
- xfs_attr_leaf_newentsize(
- state->args->namelen,
- state->args->valuelen,
- state->blocksize, NULL);
+ xfs_attr_leaf_newentsize(state->args, NULL);
}
*countarg = count;
*usedbytesarg = totallen;
- return(foundit);
+ return foundit;
}
/*========================================================================
@@ -1544,14 +1662,22 @@ xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
* GROT: allow for INCOMPLETE entries in calculation.
*/
int
-xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
+xfs_attr3_leaf_toosmall(
+ struct xfs_da_state *state,
+ int *action)
{
- xfs_attr_leafblock_t *leaf;
- xfs_da_state_blk_t *blk;
- xfs_da_blkinfo_t *info;
- int count, bytes, forward, error, retval, i;
- xfs_dablk_t blkno;
- xfs_dabuf_t *bp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_da_state_blk *blk;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_buf *bp;
+ xfs_dablk_t blkno;
+ int bytes;
+ int forward;
+ int error;
+ int retval;
+ int i;
+
+ trace_xfs_attr_leaf_toosmall(state->args);
/*
* Check for the degenerate case of the block being over 50% full.
@@ -1559,14 +1685,12 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
* to coalesce with a sibling.
*/
blk = &state->path.blk[ state->path.active-1 ];
- info = blk->bp->data;
- ASSERT(info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- leaf = (xfs_attr_leafblock_t *)info;
- count = be16_to_cpu(leaf->hdr.count);
- bytes = sizeof(xfs_attr_leaf_hdr_t) +
- count * sizeof(xfs_attr_leaf_entry_t) +
- be16_to_cpu(leaf->hdr.usedbytes);
- if (bytes > (state->blocksize >> 1)) {
+ leaf = blk->bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ bytes = xfs_attr3_leaf_hdr_size(leaf) +
+ ichdr.count * sizeof(xfs_attr_leaf_entry_t) +
+ ichdr.usedbytes;
+ if (bytes > (state->args->geo->blksize >> 1)) {
*action = 0; /* blk over 50%, don't try to join */
return(0);
}
@@ -1577,14 +1701,14 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
* coalesce it with a sibling block. We choose (arbitrarily)
* to merge with the forward block unless it is NULL.
*/
- if (count == 0) {
+ if (ichdr.count == 0) {
/*
* Make altpath point to the block we want to keep and
* path point to the block we want to drop (this one).
*/
- forward = (info->forw != 0);
+ forward = (ichdr.forw != 0);
memcpy(&state->altpath, &state->path, sizeof(state->path));
- error = xfs_da_path_shift(state, &state->altpath, forward,
+ error = xfs_da3_path_shift(state, &state->altpath, forward,
0, &retval);
if (error)
return(error);
@@ -1593,7 +1717,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
} else {
*action = 2;
}
- return(0);
+ return 0;
}
/*
@@ -1604,31 +1728,30 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
* to shrink an attribute list over time.
*/
/* start with smaller blk num */
- forward = (be32_to_cpu(info->forw) < be32_to_cpu(info->back));
+ forward = ichdr.forw < ichdr.back;
for (i = 0; i < 2; forward = !forward, i++) {
+ struct xfs_attr3_icleaf_hdr ichdr2;
if (forward)
- blkno = be32_to_cpu(info->forw);
+ blkno = ichdr.forw;
else
- blkno = be32_to_cpu(info->back);
+ blkno = ichdr.back;
if (blkno == 0)
continue;
- error = xfs_da_read_buf(state->args->trans, state->args->dp,
- blkno, -1, &bp, XFS_ATTR_FORK);
+ error = xfs_attr3_leaf_read(state->args->trans, state->args->dp,
+ blkno, -1, &bp);
if (error)
return(error);
- ASSERT(bp != NULL);
-
- leaf = (xfs_attr_leafblock_t *)info;
- count = be16_to_cpu(leaf->hdr.count);
- bytes = state->blocksize - (state->blocksize>>2);
- bytes -= be16_to_cpu(leaf->hdr.usedbytes);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- count += be16_to_cpu(leaf->hdr.count);
- bytes -= be16_to_cpu(leaf->hdr.usedbytes);
- bytes -= count * sizeof(xfs_attr_leaf_entry_t);
- bytes -= sizeof(xfs_attr_leaf_hdr_t);
- xfs_da_brelse(state->args->trans, bp);
+
+ xfs_attr3_leaf_hdr_from_disk(&ichdr2, bp->b_addr);
+
+ bytes = state->args->geo->blksize -
+ (state->args->geo->blksize >> 2) -
+ ichdr.usedbytes - ichdr2.usedbytes -
+ ((ichdr.count + ichdr2.count) *
+ sizeof(xfs_attr_leaf_entry_t)) -
+ xfs_attr3_leaf_hdr_size(leaf);
+
+ xfs_trans_brelse(state->args->trans, bp);
if (bytes >= 0)
break; /* fits with at least 25% to spare */
}
@@ -1643,10 +1766,10 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
*/
memcpy(&state->altpath, &state->path, sizeof(state->path));
if (blkno < blk->blkno) {
- error = xfs_da_path_shift(state, &state->altpath, forward,
+ error = xfs_da3_path_shift(state, &state->altpath, forward,
0, &retval);
} else {
- error = xfs_da_path_shift(state, &state->path, forward,
+ error = xfs_da3_path_shift(state, &state->path, forward,
0, &retval);
}
if (error)
@@ -1666,29 +1789,35 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
* If two leaves are 37% full, when combined they will leave 25% free.
*/
int
-xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr3_leaf_remove(
+ struct xfs_buf *bp,
+ struct xfs_da_args *args)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_hdr_t *hdr;
- xfs_attr_leaf_map_t *map;
- xfs_attr_leaf_entry_t *entry;
- int before, after, smallest, entsize;
- int tablesize, tmp, i;
- xfs_mount_t *mp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_attr_leaf_entry *entry;
+ int before;
+ int after;
+ int smallest;
+ int entsize;
+ int tablesize;
+ int tmp;
+ int i;
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- hdr = &leaf->hdr;
- mp = args->trans->t_mountp;
- ASSERT((be16_to_cpu(hdr->count) > 0)
- && (be16_to_cpu(hdr->count) < (XFS_LBSIZE(mp)/8)));
- ASSERT((args->index >= 0)
- && (args->index < be16_to_cpu(hdr->count)));
- ASSERT(be16_to_cpu(hdr->firstused) >=
- ((be16_to_cpu(hdr->count) * sizeof(*entry)) + sizeof(*hdr)));
- entry = &leaf->entries[args->index];
- ASSERT(be16_to_cpu(entry->nameidx) >= be16_to_cpu(hdr->firstused));
- ASSERT(be16_to_cpu(entry->nameidx) < XFS_LBSIZE(mp));
+ trace_xfs_attr_leaf_remove(args);
+
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+
+ ASSERT(ichdr.count > 0 && ichdr.count < args->geo->blksize / 8);
+ ASSERT(args->index >= 0 && args->index < ichdr.count);
+ ASSERT(ichdr.firstused >= ichdr.count * sizeof(*entry) +
+ xfs_attr3_leaf_hdr_size(leaf));
+
+ entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
+
+ ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused);
+ ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize);
/*
* Scan through free region table:
@@ -1696,30 +1825,28 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
* find smallest free region in case we need to replace it,
* adjust any map that borders the entry table,
*/
- tablesize = be16_to_cpu(hdr->count) * sizeof(xfs_attr_leaf_entry_t)
- + sizeof(xfs_attr_leaf_hdr_t);
- map = &hdr->freemap[0];
- tmp = be16_to_cpu(map->size);
+ tablesize = ichdr.count * sizeof(xfs_attr_leaf_entry_t)
+ + xfs_attr3_leaf_hdr_size(leaf);
+ tmp = ichdr.freemap[0].size;
before = after = -1;
smallest = XFS_ATTR_LEAF_MAPSIZE - 1;
entsize = xfs_attr_leaf_entsize(leaf, args->index);
- for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; map++, i++) {
- ASSERT(be16_to_cpu(map->base) < XFS_LBSIZE(mp));
- ASSERT(be16_to_cpu(map->size) < XFS_LBSIZE(mp));
- if (be16_to_cpu(map->base) == tablesize) {
- be16_add_cpu(&map->base,
- -((int)sizeof(xfs_attr_leaf_entry_t)));
- be16_add_cpu(&map->size, sizeof(xfs_attr_leaf_entry_t));
+ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+ ASSERT(ichdr.freemap[i].base < args->geo->blksize);
+ ASSERT(ichdr.freemap[i].size < args->geo->blksize);
+ if (ichdr.freemap[i].base == tablesize) {
+ ichdr.freemap[i].base -= sizeof(xfs_attr_leaf_entry_t);
+ ichdr.freemap[i].size += sizeof(xfs_attr_leaf_entry_t);
}
- if ((be16_to_cpu(map->base) + be16_to_cpu(map->size))
- == be16_to_cpu(entry->nameidx)) {
+ if (ichdr.freemap[i].base + ichdr.freemap[i].size ==
+ be16_to_cpu(entry->nameidx)) {
before = i;
- } else if (be16_to_cpu(map->base)
- == (be16_to_cpu(entry->nameidx) + entsize)) {
+ } else if (ichdr.freemap[i].base ==
+ (be16_to_cpu(entry->nameidx) + entsize)) {
after = i;
- } else if (be16_to_cpu(map->size) < tmp) {
- tmp = be16_to_cpu(map->size);
+ } else if (ichdr.freemap[i].size < tmp) {
+ tmp = ichdr.freemap[i].size;
smallest = i;
}
}
@@ -1730,36 +1857,30 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
*/
if ((before >= 0) || (after >= 0)) {
if ((before >= 0) && (after >= 0)) {
- map = &hdr->freemap[before];
- be16_add_cpu(&map->size, entsize);
- be16_add_cpu(&map->size,
- be16_to_cpu(hdr->freemap[after].size));
- hdr->freemap[after].base = 0;
- hdr->freemap[after].size = 0;
+ ichdr.freemap[before].size += entsize;
+ ichdr.freemap[before].size += ichdr.freemap[after].size;
+ ichdr.freemap[after].base = 0;
+ ichdr.freemap[after].size = 0;
} else if (before >= 0) {
- map = &hdr->freemap[before];
- be16_add_cpu(&map->size, entsize);
+ ichdr.freemap[before].size += entsize;
} else {
- map = &hdr->freemap[after];
- /* both on-disk, don't endian flip twice */
- map->base = entry->nameidx;
- be16_add_cpu(&map->size, entsize);
+ ichdr.freemap[after].base = be16_to_cpu(entry->nameidx);
+ ichdr.freemap[after].size += entsize;
}
} else {
/*
* Replace smallest region (if it is smaller than free'd entry)
*/
- map = &hdr->freemap[smallest];
- if (be16_to_cpu(map->size) < entsize) {
- map->base = cpu_to_be16(be16_to_cpu(entry->nameidx));
- map->size = cpu_to_be16(entsize);
+ if (ichdr.freemap[smallest].size < entsize) {
+ ichdr.freemap[smallest].base = be16_to_cpu(entry->nameidx);
+ ichdr.freemap[smallest].size = entsize;
}
}
/*
* Did we remove the first entry?
*/
- if (be16_to_cpu(entry->nameidx) == be16_to_cpu(hdr->firstused))
+ if (be16_to_cpu(entry->nameidx) == ichdr.firstused)
smallest = 1;
else
smallest = 0;
@@ -1767,20 +1888,20 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
/*
* Compress the remaining entries and zero out the removed stuff.
*/
- memset(xfs_attr_leaf_name(leaf, args->index), 0, entsize);
- be16_add_cpu(&hdr->usedbytes, -entsize);
- xfs_da_log_buf(args->trans, bp,
- XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
+ memset(xfs_attr3_leaf_name(leaf, args->index), 0, entsize);
+ ichdr.usedbytes -= entsize;
+ xfs_trans_log_buf(args->trans, bp,
+ XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index),
entsize));
- tmp = (be16_to_cpu(hdr->count) - args->index)
- * sizeof(xfs_attr_leaf_entry_t);
- memmove((char *)entry, (char *)(entry+1), tmp);
- be16_add_cpu(&hdr->count, -1);
- xfs_da_log_buf(args->trans, bp,
- XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
- entry = &leaf->entries[be16_to_cpu(hdr->count)];
- memset((char *)entry, 0, sizeof(xfs_attr_leaf_entry_t));
+ tmp = (ichdr.count - args->index) * sizeof(xfs_attr_leaf_entry_t);
+ memmove(entry, entry + 1, tmp);
+ ichdr.count--;
+ xfs_trans_log_buf(args->trans, bp,
+ XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(xfs_attr_leaf_entry_t)));
+
+ entry = &xfs_attr3_leaf_entryp(leaf)[ichdr.count];
+ memset(entry, 0, sizeof(xfs_attr_leaf_entry_t));
/*
* If we removed the first entry, re-find the first used byte
@@ -1789,131 +1910,146 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
* removing the name.
*/
if (smallest) {
- tmp = XFS_LBSIZE(mp);
- entry = &leaf->entries[0];
- for (i = be16_to_cpu(hdr->count)-1; i >= 0; entry++, i--) {
- ASSERT(be16_to_cpu(entry->nameidx) >=
- be16_to_cpu(hdr->firstused));
- ASSERT(be16_to_cpu(entry->nameidx) < XFS_LBSIZE(mp));
+ tmp = args->geo->blksize;
+ entry = xfs_attr3_leaf_entryp(leaf);
+ for (i = ichdr.count - 1; i >= 0; entry++, i--) {
+ ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused);
+ ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize);
if (be16_to_cpu(entry->nameidx) < tmp)
tmp = be16_to_cpu(entry->nameidx);
}
- hdr->firstused = cpu_to_be16(tmp);
- if (!hdr->firstused) {
- hdr->firstused = cpu_to_be16(
- tmp - XFS_ATTR_LEAF_NAME_ALIGN);
- }
+ ichdr.firstused = tmp;
+ if (!ichdr.firstused)
+ ichdr.firstused = tmp - XFS_ATTR_LEAF_NAME_ALIGN;
} else {
- hdr->holes = 1; /* mark as needing compaction */
+ ichdr.holes = 1; /* mark as needing compaction */
}
- xfs_da_log_buf(args->trans, bp,
- XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
+ xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr);
+ xfs_trans_log_buf(args->trans, bp,
+ XFS_DA_LOGRANGE(leaf, &leaf->hdr,
+ xfs_attr3_leaf_hdr_size(leaf)));
/*
* Check if leaf is less than 50% full, caller may want to
* "join" the leaf with a sibling if so.
*/
- tmp = sizeof(xfs_attr_leaf_hdr_t);
- tmp += be16_to_cpu(leaf->hdr.count) * sizeof(xfs_attr_leaf_entry_t);
- tmp += be16_to_cpu(leaf->hdr.usedbytes);
- return(tmp < mp->m_attr_magicpct); /* leaf is < 37% full */
+ tmp = ichdr.usedbytes + xfs_attr3_leaf_hdr_size(leaf) +
+ ichdr.count * sizeof(xfs_attr_leaf_entry_t);
+
+ return tmp < args->geo->magicpct; /* leaf is < 37% full */
}
/*
* Move all the attribute list entries from drop_leaf into save_leaf.
*/
void
-xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
- xfs_da_state_blk_t *save_blk)
+xfs_attr3_leaf_unbalance(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *drop_blk,
+ struct xfs_da_state_blk *save_blk)
{
- xfs_attr_leafblock_t *drop_leaf, *save_leaf, *tmp_leaf;
- xfs_attr_leaf_hdr_t *drop_hdr, *save_hdr, *tmp_hdr;
- xfs_mount_t *mp;
- char *tmpbuffer;
+ struct xfs_attr_leafblock *drop_leaf = drop_blk->bp->b_addr;
+ struct xfs_attr_leafblock *save_leaf = save_blk->bp->b_addr;
+ struct xfs_attr3_icleaf_hdr drophdr;
+ struct xfs_attr3_icleaf_hdr savehdr;
+ struct xfs_attr_leaf_entry *entry;
trace_xfs_attr_leaf_unbalance(state->args);
- /*
- * Set up environment.
- */
- mp = state->mp;
- ASSERT(drop_blk->magic == XFS_ATTR_LEAF_MAGIC);
- ASSERT(save_blk->magic == XFS_ATTR_LEAF_MAGIC);
- drop_leaf = drop_blk->bp->data;
- save_leaf = save_blk->bp->data;
- ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- drop_hdr = &drop_leaf->hdr;
- save_hdr = &save_leaf->hdr;
+ drop_leaf = drop_blk->bp->b_addr;
+ save_leaf = save_blk->bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&drophdr, drop_leaf);
+ xfs_attr3_leaf_hdr_from_disk(&savehdr, save_leaf);
+ entry = xfs_attr3_leaf_entryp(drop_leaf);
/*
* Save last hashval from dying block for later Btree fixup.
*/
- drop_blk->hashval = be32_to_cpu(
- drop_leaf->entries[be16_to_cpu(drop_leaf->hdr.count)-1].hashval);
+ drop_blk->hashval = be32_to_cpu(entry[drophdr.count - 1].hashval);
/*
* Check if we need a temp buffer, or can we do it in place.
* Note that we don't check "leaf" for holes because we will
* always be dropping it, toosmall() decided that for us already.
*/
- if (save_hdr->holes == 0) {
+ if (savehdr.holes == 0) {
/*
* dest leaf has no holes, so we add there. May need
* to make some room in the entry array.
*/
- if (xfs_attr_leaf_order(save_blk->bp, drop_blk->bp)) {
- xfs_attr_leaf_moveents(drop_leaf, 0, save_leaf, 0,
- be16_to_cpu(drop_hdr->count), mp);
+ if (xfs_attr3_leaf_order(save_blk->bp, &savehdr,
+ drop_blk->bp, &drophdr)) {
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
+ save_leaf, &savehdr, 0,
+ drophdr.count);
} else {
- xfs_attr_leaf_moveents(drop_leaf, 0, save_leaf,
- be16_to_cpu(save_hdr->count),
- be16_to_cpu(drop_hdr->count), mp);
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
+ save_leaf, &savehdr,
+ savehdr.count, drophdr.count);
}
} else {
/*
* Destination has holes, so we make a temporary copy
* of the leaf and add them both to that.
*/
- tmpbuffer = kmem_alloc(state->blocksize, KM_SLEEP);
- ASSERT(tmpbuffer != NULL);
- memset(tmpbuffer, 0, state->blocksize);
- tmp_leaf = (xfs_attr_leafblock_t *)tmpbuffer;
- tmp_hdr = &tmp_leaf->hdr;
- tmp_hdr->info = save_hdr->info; /* struct copy */
- tmp_hdr->count = 0;
- tmp_hdr->firstused = cpu_to_be16(state->blocksize);
- if (!tmp_hdr->firstused) {
- tmp_hdr->firstused = cpu_to_be16(
- state->blocksize - XFS_ATTR_LEAF_NAME_ALIGN);
- }
- tmp_hdr->usedbytes = 0;
- if (xfs_attr_leaf_order(save_blk->bp, drop_blk->bp)) {
- xfs_attr_leaf_moveents(drop_leaf, 0, tmp_leaf, 0,
- be16_to_cpu(drop_hdr->count), mp);
- xfs_attr_leaf_moveents(save_leaf, 0, tmp_leaf,
- be16_to_cpu(tmp_leaf->hdr.count),
- be16_to_cpu(save_hdr->count), mp);
+ struct xfs_attr_leafblock *tmp_leaf;
+ struct xfs_attr3_icleaf_hdr tmphdr;
+
+ tmp_leaf = kmem_zalloc(state->args->geo->blksize, KM_SLEEP);
+
+ /*
+ * Copy the header into the temp leaf so that all the stuff
+ * not in the incore header is present and gets copied back in
+ * once we've moved all the entries.
+ */
+ memcpy(tmp_leaf, save_leaf, xfs_attr3_leaf_hdr_size(save_leaf));
+
+ memset(&tmphdr, 0, sizeof(tmphdr));
+ tmphdr.magic = savehdr.magic;
+ tmphdr.forw = savehdr.forw;
+ tmphdr.back = savehdr.back;
+ tmphdr.firstused = state->args->geo->blksize;
+
+ /* write the header to the temp buffer to initialise it */
+ xfs_attr3_leaf_hdr_to_disk(tmp_leaf, &tmphdr);
+
+ if (xfs_attr3_leaf_order(save_blk->bp, &savehdr,
+ drop_blk->bp, &drophdr)) {
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
+ tmp_leaf, &tmphdr, 0,
+ drophdr.count);
+ xfs_attr3_leaf_moveents(state->args,
+ save_leaf, &savehdr, 0,
+ tmp_leaf, &tmphdr, tmphdr.count,
+ savehdr.count);
} else {
- xfs_attr_leaf_moveents(save_leaf, 0, tmp_leaf, 0,
- be16_to_cpu(save_hdr->count), mp);
- xfs_attr_leaf_moveents(drop_leaf, 0, tmp_leaf,
- be16_to_cpu(tmp_leaf->hdr.count),
- be16_to_cpu(drop_hdr->count), mp);
+ xfs_attr3_leaf_moveents(state->args,
+ save_leaf, &savehdr, 0,
+ tmp_leaf, &tmphdr, 0,
+ savehdr.count);
+ xfs_attr3_leaf_moveents(state->args,
+ drop_leaf, &drophdr, 0,
+ tmp_leaf, &tmphdr, tmphdr.count,
+ drophdr.count);
}
- memcpy((char *)save_leaf, (char *)tmp_leaf, state->blocksize);
- kmem_free(tmpbuffer);
+ memcpy(save_leaf, tmp_leaf, state->args->geo->blksize);
+ savehdr = tmphdr; /* struct copy */
+ kmem_free(tmp_leaf);
}
- xfs_da_log_buf(state->args->trans, save_blk->bp, 0,
- state->blocksize - 1);
+ xfs_attr3_leaf_hdr_to_disk(save_leaf, &savehdr);
+ xfs_trans_log_buf(state->args->trans, save_blk->bp, 0,
+ state->args->geo->blksize - 1);
/*
* Copy out last hashval in each block for B-tree code.
*/
- save_blk->hashval = be32_to_cpu(
- save_leaf->entries[be16_to_cpu(save_leaf->hdr.count)-1].hashval);
+ entry = xfs_attr3_leaf_entryp(save_leaf);
+ save_blk->hashval = be32_to_cpu(entry[savehdr.count - 1].hashval);
}
/*========================================================================
@@ -1934,29 +2070,33 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
* Don't change the args->value unless we find the attribute.
*/
int
-xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr3_leaf_lookup_int(
+ struct xfs_buf *bp,
+ struct xfs_da_args *args)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
- xfs_attr_leaf_name_local_t *name_loc;
- xfs_attr_leaf_name_remote_t *name_rmt;
- int probe, span;
- xfs_dahash_t hashval;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr_leaf_entry *entries;
+ struct xfs_attr_leaf_name_local *name_loc;
+ struct xfs_attr_leaf_name_remote *name_rmt;
+ xfs_dahash_t hashval;
+ int probe;
+ int span;
trace_xfs_attr_leaf_lookup(args);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(be16_to_cpu(leaf->hdr.count)
- < (XFS_LBSIZE(args->dp->i_mount)/8));
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ entries = xfs_attr3_leaf_entryp(leaf);
+ ASSERT(ichdr.count < args->geo->blksize / 8);
/*
* Binary search. (note: small blocks will skip this loop)
*/
hashval = args->hashval;
- probe = span = be16_to_cpu(leaf->hdr.count) / 2;
- for (entry = &leaf->entries[probe]; span > 4;
- entry = &leaf->entries[probe]) {
+ probe = span = ichdr.count / 2;
+ for (entry = &entries[probe]; span > 4; entry = &entries[probe]) {
span /= 2;
if (be32_to_cpu(entry->hashval) < hashval)
probe += span;
@@ -1965,35 +2105,31 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
else
break;
}
- ASSERT((probe >= 0) &&
- (!leaf->hdr.count
- || (probe < be16_to_cpu(leaf->hdr.count))));
- ASSERT((span <= 4) || (be32_to_cpu(entry->hashval) == hashval));
+ ASSERT(probe >= 0 && (!ichdr.count || probe < ichdr.count));
+ ASSERT(span <= 4 || be32_to_cpu(entry->hashval) == hashval);
/*
* Since we may have duplicate hashval's, find the first matching
* hashval in the leaf.
*/
- while ((probe > 0) && (be32_to_cpu(entry->hashval) >= hashval)) {
+ while (probe > 0 && be32_to_cpu(entry->hashval) >= hashval) {
entry--;
probe--;
}
- while ((probe < be16_to_cpu(leaf->hdr.count)) &&
- (be32_to_cpu(entry->hashval) < hashval)) {
+ while (probe < ichdr.count &&
+ be32_to_cpu(entry->hashval) < hashval) {
entry++;
probe++;
}
- if ((probe == be16_to_cpu(leaf->hdr.count)) ||
- (be32_to_cpu(entry->hashval) != hashval)) {
+ if (probe == ichdr.count || be32_to_cpu(entry->hashval) != hashval) {
args->index = probe;
- return(XFS_ERROR(ENOATTR));
+ return XFS_ERROR(ENOATTR);
}
/*
* Duplicate keys may be present, so search all of them for a match.
*/
- for ( ; (probe < be16_to_cpu(leaf->hdr.count)) &&
- (be32_to_cpu(entry->hashval) == hashval);
+ for (; probe < ichdr.count && (be32_to_cpu(entry->hashval) == hashval);
entry++, probe++) {
/*
* GROT: Add code to remove incomplete entries.
@@ -2007,33 +2143,36 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
continue;
}
if (entry->flags & XFS_ATTR_LOCAL) {
- name_loc = xfs_attr_leaf_name_local(leaf, probe);
+ name_loc = xfs_attr3_leaf_name_local(leaf, probe);
if (name_loc->namelen != args->namelen)
continue;
- if (memcmp(args->name, (char *)name_loc->nameval, args->namelen) != 0)
+ if (memcmp(args->name, name_loc->nameval,
+ args->namelen) != 0)
continue;
if (!xfs_attr_namesp_match(args->flags, entry->flags))
continue;
args->index = probe;
- return(XFS_ERROR(EEXIST));
+ return XFS_ERROR(EEXIST);
} else {
- name_rmt = xfs_attr_leaf_name_remote(leaf, probe);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, probe);
if (name_rmt->namelen != args->namelen)
continue;
- if (memcmp(args->name, (char *)name_rmt->name,
- args->namelen) != 0)
+ if (memcmp(args->name, name_rmt->name,
+ args->namelen) != 0)
continue;
if (!xfs_attr_namesp_match(args->flags, entry->flags))
continue;
args->index = probe;
+ args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen);
args->rmtblkno = be32_to_cpu(name_rmt->valueblk);
- args->rmtblkcnt = XFS_B_TO_FSB(args->dp->i_mount,
- be32_to_cpu(name_rmt->valuelen));
- return(XFS_ERROR(EEXIST));
+ args->rmtblkcnt = xfs_attr3_rmt_blocks(
+ args->dp->i_mount,
+ args->rmtvaluelen);
+ return XFS_ERROR(EEXIST);
}
}
args->index = probe;
- return(XFS_ERROR(ENOATTR));
+ return XFS_ERROR(ENOATTR);
}
/*
@@ -2041,54 +2180,57 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
* list structure.
*/
int
-xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr3_leaf_getvalue(
+ struct xfs_buf *bp,
+ struct xfs_da_args *args)
{
- int valuelen;
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
- xfs_attr_leaf_name_local_t *name_loc;
- xfs_attr_leaf_name_remote_t *name_rmt;
-
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(be16_to_cpu(leaf->hdr.count)
- < (XFS_LBSIZE(args->dp->i_mount)/8));
- ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
-
- entry = &leaf->entries[args->index];
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr_leaf_name_local *name_loc;
+ struct xfs_attr_leaf_name_remote *name_rmt;
+ int valuelen;
+
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ ASSERT(ichdr.count < args->geo->blksize / 8);
+ ASSERT(args->index < ichdr.count);
+
+ entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
if (entry->flags & XFS_ATTR_LOCAL) {
- name_loc = xfs_attr_leaf_name_local(leaf, args->index);
+ name_loc = xfs_attr3_leaf_name_local(leaf, args->index);
ASSERT(name_loc->namelen == args->namelen);
ASSERT(memcmp(args->name, name_loc->nameval, args->namelen) == 0);
valuelen = be16_to_cpu(name_loc->valuelen);
if (args->flags & ATTR_KERNOVAL) {
args->valuelen = valuelen;
- return(0);
+ return 0;
}
if (args->valuelen < valuelen) {
args->valuelen = valuelen;
- return(XFS_ERROR(ERANGE));
+ return XFS_ERROR(ERANGE);
}
args->valuelen = valuelen;
memcpy(args->value, &name_loc->nameval[args->namelen], valuelen);
} else {
- name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
ASSERT(name_rmt->namelen == args->namelen);
ASSERT(memcmp(args->name, name_rmt->name, args->namelen) == 0);
- valuelen = be32_to_cpu(name_rmt->valuelen);
+ args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen);
args->rmtblkno = be32_to_cpu(name_rmt->valueblk);
- args->rmtblkcnt = XFS_B_TO_FSB(args->dp->i_mount, valuelen);
+ args->rmtblkcnt = xfs_attr3_rmt_blocks(args->dp->i_mount,
+ args->rmtvaluelen);
if (args->flags & ATTR_KERNOVAL) {
- args->valuelen = valuelen;
- return(0);
+ args->valuelen = args->rmtvaluelen;
+ return 0;
}
- if (args->valuelen < valuelen) {
- args->valuelen = valuelen;
- return(XFS_ERROR(ERANGE));
+ if (args->valuelen < args->rmtvaluelen) {
+ args->valuelen = args->rmtvaluelen;
+ return XFS_ERROR(ERANGE);
}
- args->valuelen = valuelen;
+ args->valuelen = args->rmtvaluelen;
}
- return(0);
+ return 0;
}
/*========================================================================
@@ -2101,13 +2243,21 @@ xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
*/
/*ARGSUSED*/
STATIC void
-xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s,
- xfs_attr_leafblock_t *leaf_d, int start_d,
- int count, xfs_mount_t *mp)
+xfs_attr3_leaf_moveents(
+ struct xfs_da_args *args,
+ struct xfs_attr_leafblock *leaf_s,
+ struct xfs_attr3_icleaf_hdr *ichdr_s,
+ int start_s,
+ struct xfs_attr_leafblock *leaf_d,
+ struct xfs_attr3_icleaf_hdr *ichdr_d,
+ int start_d,
+ int count)
{
- xfs_attr_leaf_hdr_t *hdr_s, *hdr_d;
- xfs_attr_leaf_entry_t *entry_s, *entry_d;
- int desti, tmp, i;
+ struct xfs_attr_leaf_entry *entry_s;
+ struct xfs_attr_leaf_entry *entry_d;
+ int desti;
+ int tmp;
+ int i;
/*
* Check for nothing to do.
@@ -2118,45 +2268,41 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s,
/*
* Set up environment.
*/
- ASSERT(leaf_s->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(leaf_d->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- hdr_s = &leaf_s->hdr;
- hdr_d = &leaf_d->hdr;
- ASSERT((be16_to_cpu(hdr_s->count) > 0) &&
- (be16_to_cpu(hdr_s->count) < (XFS_LBSIZE(mp)/8)));
- ASSERT(be16_to_cpu(hdr_s->firstused) >=
- ((be16_to_cpu(hdr_s->count)
- * sizeof(*entry_s))+sizeof(*hdr_s)));
- ASSERT(be16_to_cpu(hdr_d->count) < (XFS_LBSIZE(mp)/8));
- ASSERT(be16_to_cpu(hdr_d->firstused) >=
- ((be16_to_cpu(hdr_d->count)
- * sizeof(*entry_d))+sizeof(*hdr_d)));
-
- ASSERT(start_s < be16_to_cpu(hdr_s->count));
- ASSERT(start_d <= be16_to_cpu(hdr_d->count));
- ASSERT(count <= be16_to_cpu(hdr_s->count));
+ ASSERT(ichdr_s->magic == XFS_ATTR_LEAF_MAGIC ||
+ ichdr_s->magic == XFS_ATTR3_LEAF_MAGIC);
+ ASSERT(ichdr_s->magic == ichdr_d->magic);
+ ASSERT(ichdr_s->count > 0 && ichdr_s->count < args->geo->blksize / 8);
+ ASSERT(ichdr_s->firstused >= (ichdr_s->count * sizeof(*entry_s))
+ + xfs_attr3_leaf_hdr_size(leaf_s));
+ ASSERT(ichdr_d->count < args->geo->blksize / 8);
+ ASSERT(ichdr_d->firstused >= (ichdr_d->count * sizeof(*entry_d))
+ + xfs_attr3_leaf_hdr_size(leaf_d));
+
+ ASSERT(start_s < ichdr_s->count);
+ ASSERT(start_d <= ichdr_d->count);
+ ASSERT(count <= ichdr_s->count);
+
/*
* Move the entries in the destination leaf up to make a hole?
*/
- if (start_d < be16_to_cpu(hdr_d->count)) {
- tmp = be16_to_cpu(hdr_d->count) - start_d;
+ if (start_d < ichdr_d->count) {
+ tmp = ichdr_d->count - start_d;
tmp *= sizeof(xfs_attr_leaf_entry_t);
- entry_s = &leaf_d->entries[start_d];
- entry_d = &leaf_d->entries[start_d + count];
- memmove((char *)entry_d, (char *)entry_s, tmp);
+ entry_s = &xfs_attr3_leaf_entryp(leaf_d)[start_d];
+ entry_d = &xfs_attr3_leaf_entryp(leaf_d)[start_d + count];
+ memmove(entry_d, entry_s, tmp);
}
/*
* Copy all entry's in the same (sorted) order,
* but allocate attribute info packed and in sequence.
*/
- entry_s = &leaf_s->entries[start_s];
- entry_d = &leaf_d->entries[start_d];
+ entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s];
+ entry_d = &xfs_attr3_leaf_entryp(leaf_d)[start_d];
desti = start_d;
for (i = 0; i < count; entry_s++, entry_d++, desti++, i++) {
- ASSERT(be16_to_cpu(entry_s->nameidx)
- >= be16_to_cpu(hdr_s->firstused));
+ ASSERT(be16_to_cpu(entry_s->nameidx) >= ichdr_s->firstused);
tmp = xfs_attr_leaf_entsize(leaf_s, start_s + i);
#ifdef GROT
/*
@@ -2165,36 +2311,34 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s,
* off for 6.2, should be revisited later.
*/
if (entry_s->flags & XFS_ATTR_INCOMPLETE) { /* skip partials? */
- memset(xfs_attr_leaf_name(leaf_s, start_s + i), 0, tmp);
- be16_add_cpu(&hdr_s->usedbytes, -tmp);
- be16_add_cpu(&hdr_s->count, -1);
+ memset(xfs_attr3_leaf_name(leaf_s, start_s + i), 0, tmp);
+ ichdr_s->usedbytes -= tmp;
+ ichdr_s->count -= 1;
entry_d--; /* to compensate for ++ in loop hdr */
desti--;
if ((start_s + i) < offset)
result++; /* insertion index adjustment */
} else {
#endif /* GROT */
- be16_add_cpu(&hdr_d->firstused, -tmp);
+ ichdr_d->firstused -= tmp;
/* both on-disk, don't endian flip twice */
entry_d->hashval = entry_s->hashval;
- /* both on-disk, don't endian flip twice */
- entry_d->nameidx = hdr_d->firstused;
+ entry_d->nameidx = cpu_to_be16(ichdr_d->firstused);
entry_d->flags = entry_s->flags;
ASSERT(be16_to_cpu(entry_d->nameidx) + tmp
- <= XFS_LBSIZE(mp));
- memmove(xfs_attr_leaf_name(leaf_d, desti),
- xfs_attr_leaf_name(leaf_s, start_s + i), tmp);
+ <= args->geo->blksize);
+ memmove(xfs_attr3_leaf_name(leaf_d, desti),
+ xfs_attr3_leaf_name(leaf_s, start_s + i), tmp);
ASSERT(be16_to_cpu(entry_s->nameidx) + tmp
- <= XFS_LBSIZE(mp));
- memset(xfs_attr_leaf_name(leaf_s, start_s + i), 0, tmp);
- be16_add_cpu(&hdr_s->usedbytes, -tmp);
- be16_add_cpu(&hdr_d->usedbytes, tmp);
- be16_add_cpu(&hdr_s->count, -1);
- be16_add_cpu(&hdr_d->count, 1);
- tmp = be16_to_cpu(hdr_d->count)
- * sizeof(xfs_attr_leaf_entry_t)
- + sizeof(xfs_attr_leaf_hdr_t);
- ASSERT(be16_to_cpu(hdr_d->firstused) >= tmp);
+ <= args->geo->blksize);
+ memset(xfs_attr3_leaf_name(leaf_s, start_s + i), 0, tmp);
+ ichdr_s->usedbytes -= tmp;
+ ichdr_d->usedbytes += tmp;
+ ichdr_s->count -= 1;
+ ichdr_d->count += 1;
+ tmp = ichdr_d->count * sizeof(xfs_attr_leaf_entry_t)
+ + xfs_attr3_leaf_hdr_size(leaf_d);
+ ASSERT(ichdr_d->firstused >= tmp);
#ifdef GROT
}
#endif /* GROT */
@@ -2203,86 +2347,60 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s,
/*
* Zero out the entries we just copied.
*/
- if (start_s == be16_to_cpu(hdr_s->count)) {
+ if (start_s == ichdr_s->count) {
tmp = count * sizeof(xfs_attr_leaf_entry_t);
- entry_s = &leaf_s->entries[start_s];
+ entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s];
ASSERT(((char *)entry_s + tmp) <=
- ((char *)leaf_s + XFS_LBSIZE(mp)));
- memset((char *)entry_s, 0, tmp);
+ ((char *)leaf_s + args->geo->blksize));
+ memset(entry_s, 0, tmp);
} else {
/*
* Move the remaining entries down to fill the hole,
* then zero the entries at the top.
*/
- tmp = be16_to_cpu(hdr_s->count) - count;
- tmp *= sizeof(xfs_attr_leaf_entry_t);
- entry_s = &leaf_s->entries[start_s + count];
- entry_d = &leaf_s->entries[start_s];
- memmove((char *)entry_d, (char *)entry_s, tmp);
+ tmp = (ichdr_s->count - count) * sizeof(xfs_attr_leaf_entry_t);
+ entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s + count];
+ entry_d = &xfs_attr3_leaf_entryp(leaf_s)[start_s];
+ memmove(entry_d, entry_s, tmp);
tmp = count * sizeof(xfs_attr_leaf_entry_t);
- entry_s = &leaf_s->entries[be16_to_cpu(hdr_s->count)];
+ entry_s = &xfs_attr3_leaf_entryp(leaf_s)[ichdr_s->count];
ASSERT(((char *)entry_s + tmp) <=
- ((char *)leaf_s + XFS_LBSIZE(mp)));
- memset((char *)entry_s, 0, tmp);
+ ((char *)leaf_s + args->geo->blksize));
+ memset(entry_s, 0, tmp);
}
/*
* Fill in the freemap information
*/
- hdr_d->freemap[0].base = cpu_to_be16(sizeof(xfs_attr_leaf_hdr_t));
- be16_add_cpu(&hdr_d->freemap[0].base, be16_to_cpu(hdr_d->count) *
- sizeof(xfs_attr_leaf_entry_t));
- hdr_d->freemap[0].size = cpu_to_be16(be16_to_cpu(hdr_d->firstused)
- - be16_to_cpu(hdr_d->freemap[0].base));
- hdr_d->freemap[1].base = 0;
- hdr_d->freemap[2].base = 0;
- hdr_d->freemap[1].size = 0;
- hdr_d->freemap[2].size = 0;
- hdr_s->holes = 1; /* leaf may not be compact */
-}
-
-/*
- * Compare two leaf blocks "order".
- * Return 0 unless leaf2 should go before leaf1.
- */
-int
-xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp)
-{
- xfs_attr_leafblock_t *leaf1, *leaf2;
-
- leaf1 = leaf1_bp->data;
- leaf2 = leaf2_bp->data;
- ASSERT((leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) &&
- (leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)));
- if ((be16_to_cpu(leaf1->hdr.count) > 0) &&
- (be16_to_cpu(leaf2->hdr.count) > 0) &&
- ((be32_to_cpu(leaf2->entries[0].hashval) <
- be32_to_cpu(leaf1->entries[0].hashval)) ||
- (be32_to_cpu(leaf2->entries[
- be16_to_cpu(leaf2->hdr.count)-1].hashval) <
- be32_to_cpu(leaf1->entries[
- be16_to_cpu(leaf1->hdr.count)-1].hashval)))) {
- return(1);
- }
- return(0);
+ ichdr_d->freemap[0].base = xfs_attr3_leaf_hdr_size(leaf_d);
+ ichdr_d->freemap[0].base += ichdr_d->count * sizeof(xfs_attr_leaf_entry_t);
+ ichdr_d->freemap[0].size = ichdr_d->firstused - ichdr_d->freemap[0].base;
+ ichdr_d->freemap[1].base = 0;
+ ichdr_d->freemap[2].base = 0;
+ ichdr_d->freemap[1].size = 0;
+ ichdr_d->freemap[2].size = 0;
+ ichdr_s->holes = 1; /* leaf may not be compact */
}
/*
* Pick up the last hashvalue from a leaf block.
*/
xfs_dahash_t
-xfs_attr_leaf_lasthash(xfs_dabuf_t *bp, int *count)
+xfs_attr_leaf_lasthash(
+ struct xfs_buf *bp,
+ int *count)
{
- xfs_attr_leafblock_t *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_attr_leaf_entry *entries;
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, bp->b_addr);
+ entries = xfs_attr3_leaf_entryp(bp->b_addr);
if (count)
- *count = be16_to_cpu(leaf->hdr.count);
- if (!leaf->hdr.count)
- return(0);
- return be32_to_cpu(leaf->entries[be16_to_cpu(leaf->hdr.count)-1].hashval);
+ *count = ichdr.count;
+ if (!ichdr.count)
+ return 0;
+ return be32_to_cpu(entries[ichdr.count - 1].hashval);
}
/*
@@ -2292,20 +2410,21 @@ xfs_attr_leaf_lasthash(xfs_dabuf_t *bp, int *count)
STATIC int
xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index)
{
+ struct xfs_attr_leaf_entry *entries;
xfs_attr_leaf_name_local_t *name_loc;
xfs_attr_leaf_name_remote_t *name_rmt;
int size;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- if (leaf->entries[index].flags & XFS_ATTR_LOCAL) {
- name_loc = xfs_attr_leaf_name_local(leaf, index);
+ entries = xfs_attr3_leaf_entryp(leaf);
+ if (entries[index].flags & XFS_ATTR_LOCAL) {
+ name_loc = xfs_attr3_leaf_name_local(leaf, index);
size = xfs_attr_leaf_entsize_local(name_loc->namelen,
be16_to_cpu(name_loc->valuelen));
} else {
- name_rmt = xfs_attr_leaf_name_remote(leaf, index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, index);
size = xfs_attr_leaf_entsize_remote(name_rmt->namelen);
}
- return(size);
+ return size;
}
/*
@@ -2315,138 +2434,21 @@ xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index)
* a "local" or a "remote" attribute.
*/
int
-xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize, int *local)
+xfs_attr_leaf_newentsize(
+ struct xfs_da_args *args,
+ int *local)
{
- int size;
+ int size;
- size = xfs_attr_leaf_entsize_local(namelen, valuelen);
- if (size < xfs_attr_leaf_entsize_local_max(blocksize)) {
- if (local) {
+ size = xfs_attr_leaf_entsize_local(args->namelen, args->valuelen);
+ if (size < xfs_attr_leaf_entsize_local_max(args->geo->blksize)) {
+ if (local)
*local = 1;
- }
- } else {
- size = xfs_attr_leaf_entsize_remote(namelen);
- if (local) {
- *local = 0;
- }
+ return size;
}
- return(size);
-}
-
-/*
- * Copy out attribute list entries for attr_list(), for leaf attribute lists.
- */
-int
-xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
-{
- attrlist_cursor_kern_t *cursor;
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
- int retval, i;
-
- ASSERT(bp != NULL);
- leaf = bp->data;
- cursor = context->cursor;
- cursor->initted = 1;
-
- trace_xfs_attr_list_leaf(context);
-
- /*
- * Re-find our place in the leaf block if this is a new syscall.
- */
- if (context->resynch) {
- entry = &leaf->entries[0];
- for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) {
- if (be32_to_cpu(entry->hashval) == cursor->hashval) {
- if (cursor->offset == context->dupcnt) {
- context->dupcnt = 0;
- break;
- }
- context->dupcnt++;
- } else if (be32_to_cpu(entry->hashval) >
- cursor->hashval) {
- context->dupcnt = 0;
- break;
- }
- }
- if (i == be16_to_cpu(leaf->hdr.count)) {
- trace_xfs_attr_list_notfound(context);
- return(0);
- }
- } else {
- entry = &leaf->entries[0];
- i = 0;
- }
- context->resynch = 0;
-
- /*
- * We have found our place, start copying out the new attributes.
- */
- retval = 0;
- for ( ; (i < be16_to_cpu(leaf->hdr.count)); entry++, i++) {
- if (be32_to_cpu(entry->hashval) != cursor->hashval) {
- cursor->hashval = be32_to_cpu(entry->hashval);
- cursor->offset = 0;
- }
-
- if (entry->flags & XFS_ATTR_INCOMPLETE)
- continue; /* skip incomplete entries */
-
- if (entry->flags & XFS_ATTR_LOCAL) {
- xfs_attr_leaf_name_local_t *name_loc =
- xfs_attr_leaf_name_local(leaf, i);
-
- retval = context->put_listent(context,
- entry->flags,
- name_loc->nameval,
- (int)name_loc->namelen,
- be16_to_cpu(name_loc->valuelen),
- &name_loc->nameval[name_loc->namelen]);
- if (retval)
- return retval;
- } else {
- xfs_attr_leaf_name_remote_t *name_rmt =
- xfs_attr_leaf_name_remote(leaf, i);
-
- int valuelen = be32_to_cpu(name_rmt->valuelen);
-
- if (context->put_value) {
- xfs_da_args_t args;
-
- memset((char *)&args, 0, sizeof(args));
- args.dp = context->dp;
- args.whichfork = XFS_ATTR_FORK;
- args.valuelen = valuelen;
- args.value = kmem_alloc(valuelen, KM_SLEEP | KM_NOFS);
- args.rmtblkno = be32_to_cpu(name_rmt->valueblk);
- args.rmtblkcnt = XFS_B_TO_FSB(args.dp->i_mount, valuelen);
- retval = xfs_attr_rmtval_get(&args);
- if (retval)
- return retval;
- retval = context->put_listent(context,
- entry->flags,
- name_rmt->name,
- (int)name_rmt->namelen,
- valuelen,
- args.value);
- kmem_free(args.value);
- } else {
- retval = context->put_listent(context,
- entry->flags,
- name_rmt->name,
- (int)name_rmt->namelen,
- valuelen,
- NULL);
- }
- if (retval)
- return retval;
- }
- if (context->seen_enough)
- break;
- cursor->offset++;
- }
- trace_xfs_attr_list_leaf_end(context);
- return(retval);
+ if (local)
+ *local = 0;
+ return xfs_attr_leaf_entsize_remote(args->namelen);
}
@@ -2458,14 +2460,16 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
* Clear the INCOMPLETE flag on an entry in a leaf block.
*/
int
-xfs_attr_leaf_clearflag(xfs_da_args_t *args)
+xfs_attr3_leaf_clearflag(
+ struct xfs_da_args *args)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
- xfs_attr_leaf_name_remote_t *name_rmt;
- xfs_dabuf_t *bp;
- int error;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr_leaf_name_remote *name_rmt;
+ struct xfs_buf *bp;
+ int error;
#ifdef DEBUG
+ struct xfs_attr3_icleaf_hdr ichdr;
xfs_attr_leaf_name_local_t *name_loc;
int namelen;
char *name;
@@ -2475,27 +2479,25 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
/*
* Set up the operation.
*/
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1, &bp,
- XFS_ATTR_FORK);
- if (error) {
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
+ if (error)
return(error);
- }
- ASSERT(bp != NULL);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
- ASSERT(args->index >= 0);
- entry = &leaf->entries[ args->index ];
+ leaf = bp->b_addr;
+ entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
ASSERT(entry->flags & XFS_ATTR_INCOMPLETE);
#ifdef DEBUG
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ ASSERT(args->index < ichdr.count);
+ ASSERT(args->index >= 0);
+
if (entry->flags & XFS_ATTR_LOCAL) {
- name_loc = xfs_attr_leaf_name_local(leaf, args->index);
+ name_loc = xfs_attr3_leaf_name_local(leaf, args->index);
namelen = name_loc->namelen;
name = (char *)name_loc->nameval;
} else {
- name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
namelen = name_rmt->namelen;
name = (char *)name_rmt->name;
}
@@ -2505,18 +2507,17 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
#endif /* DEBUG */
entry->flags &= ~XFS_ATTR_INCOMPLETE;
- xfs_da_log_buf(args->trans, bp,
+ xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
if (args->rmtblkno) {
ASSERT((entry->flags & XFS_ATTR_LOCAL) == 0);
- name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
- name_rmt->valuelen = cpu_to_be32(args->valuelen);
- xfs_da_log_buf(args->trans, bp,
+ name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen);
+ xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
}
- xfs_da_buf_done(bp);
/*
* Commit the flag value change and start the next trans in series.
@@ -2528,44 +2529,46 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
* Set the INCOMPLETE flag on an entry in a leaf block.
*/
int
-xfs_attr_leaf_setflag(xfs_da_args_t *args)
+xfs_attr3_leaf_setflag(
+ struct xfs_da_args *args)
{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
- xfs_attr_leaf_name_remote_t *name_rmt;
- xfs_dabuf_t *bp;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr_leaf_name_remote *name_rmt;
+ struct xfs_buf *bp;
int error;
+#ifdef DEBUG
+ struct xfs_attr3_icleaf_hdr ichdr;
+#endif
trace_xfs_attr_leaf_setflag(args);
/*
* Set up the operation.
*/
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1, &bp,
- XFS_ATTR_FORK);
- if (error) {
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
+ if (error)
return(error);
- }
- ASSERT(bp != NULL);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
+ leaf = bp->b_addr;
+#ifdef DEBUG
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ ASSERT(args->index < ichdr.count);
ASSERT(args->index >= 0);
- entry = &leaf->entries[ args->index ];
+#endif
+ entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
ASSERT((entry->flags & XFS_ATTR_INCOMPLETE) == 0);
entry->flags |= XFS_ATTR_INCOMPLETE;
- xfs_da_log_buf(args->trans, bp,
+ xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
if ((entry->flags & XFS_ATTR_LOCAL) == 0) {
- name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
name_rmt->valueblk = 0;
name_rmt->valuelen = 0;
- xfs_da_log_buf(args->trans, bp,
+ xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
}
- xfs_da_buf_done(bp);
/*
* Commit the flag value change and start the next trans in series.
@@ -2581,14 +2584,20 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
* Note that they could be in different blocks, or in the same block.
*/
int
-xfs_attr_leaf_flipflags(xfs_da_args_t *args)
+xfs_attr3_leaf_flipflags(
+ struct xfs_da_args *args)
{
- xfs_attr_leafblock_t *leaf1, *leaf2;
- xfs_attr_leaf_entry_t *entry1, *entry2;
- xfs_attr_leaf_name_remote_t *name_rmt;
- xfs_dabuf_t *bp1, *bp2;
+ struct xfs_attr_leafblock *leaf1;
+ struct xfs_attr_leafblock *leaf2;
+ struct xfs_attr_leaf_entry *entry1;
+ struct xfs_attr_leaf_entry *entry2;
+ struct xfs_attr_leaf_name_remote *name_rmt;
+ struct xfs_buf *bp1;
+ struct xfs_buf *bp2;
int error;
#ifdef DEBUG
+ struct xfs_attr3_icleaf_hdr ichdr1;
+ struct xfs_attr3_icleaf_hdr ichdr2;
xfs_attr_leaf_name_local_t *name_loc;
int namelen1, namelen2;
char *name1, *name2;
@@ -2599,55 +2608,52 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
/*
* Read the block containing the "old" attr
*/
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1, &bp1,
- XFS_ATTR_FORK);
- if (error) {
- return(error);
- }
- ASSERT(bp1 != NULL);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp1);
+ if (error)
+ return error;
/*
* Read the block containing the "new" attr, if it is different
*/
if (args->blkno2 != args->blkno) {
- error = xfs_da_read_buf(args->trans, args->dp, args->blkno2,
- -1, &bp2, XFS_ATTR_FORK);
- if (error) {
- return(error);
- }
- ASSERT(bp2 != NULL);
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno2,
+ -1, &bp2);
+ if (error)
+ return error;
} else {
bp2 = bp1;
}
- leaf1 = bp1->data;
- ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(args->index < be16_to_cpu(leaf1->hdr.count));
+ leaf1 = bp1->b_addr;
+ entry1 = &xfs_attr3_leaf_entryp(leaf1)[args->index];
+
+ leaf2 = bp2->b_addr;
+ entry2 = &xfs_attr3_leaf_entryp(leaf2)[args->index2];
+
+#ifdef DEBUG
+ xfs_attr3_leaf_hdr_from_disk(&ichdr1, leaf1);
+ ASSERT(args->index < ichdr1.count);
ASSERT(args->index >= 0);
- entry1 = &leaf1->entries[ args->index ];
- leaf2 = bp2->data;
- ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- ASSERT(args->index2 < be16_to_cpu(leaf2->hdr.count));
+ xfs_attr3_leaf_hdr_from_disk(&ichdr2, leaf2);
+ ASSERT(args->index2 < ichdr2.count);
ASSERT(args->index2 >= 0);
- entry2 = &leaf2->entries[ args->index2 ];
-#ifdef DEBUG
if (entry1->flags & XFS_ATTR_LOCAL) {
- name_loc = xfs_attr_leaf_name_local(leaf1, args->index);
+ name_loc = xfs_attr3_leaf_name_local(leaf1, args->index);
namelen1 = name_loc->namelen;
name1 = (char *)name_loc->nameval;
} else {
- name_rmt = xfs_attr_leaf_name_remote(leaf1, args->index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf1, args->index);
namelen1 = name_rmt->namelen;
name1 = (char *)name_rmt->name;
}
if (entry2->flags & XFS_ATTR_LOCAL) {
- name_loc = xfs_attr_leaf_name_local(leaf2, args->index2);
+ name_loc = xfs_attr3_leaf_name_local(leaf2, args->index2);
namelen2 = name_loc->namelen;
name2 = (char *)name_loc->nameval;
} else {
- name_rmt = xfs_attr_leaf_name_remote(leaf2, args->index2);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf2, args->index2);
namelen2 = name_rmt->namelen;
name2 = (char *)name_rmt->name;
}
@@ -2660,343 +2666,32 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
ASSERT((entry2->flags & XFS_ATTR_INCOMPLETE) == 0);
entry1->flags &= ~XFS_ATTR_INCOMPLETE;
- xfs_da_log_buf(args->trans, bp1,
+ xfs_trans_log_buf(args->trans, bp1,
XFS_DA_LOGRANGE(leaf1, entry1, sizeof(*entry1)));
if (args->rmtblkno) {
ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0);
- name_rmt = xfs_attr_leaf_name_remote(leaf1, args->index);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf1, args->index);
name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
- name_rmt->valuelen = cpu_to_be32(args->valuelen);
- xfs_da_log_buf(args->trans, bp1,
+ name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen);
+ xfs_trans_log_buf(args->trans, bp1,
XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt)));
}
entry2->flags |= XFS_ATTR_INCOMPLETE;
- xfs_da_log_buf(args->trans, bp2,
+ xfs_trans_log_buf(args->trans, bp2,
XFS_DA_LOGRANGE(leaf2, entry2, sizeof(*entry2)));
if ((entry2->flags & XFS_ATTR_LOCAL) == 0) {
- name_rmt = xfs_attr_leaf_name_remote(leaf2, args->index2);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf2, args->index2);
name_rmt->valueblk = 0;
name_rmt->valuelen = 0;
- xfs_da_log_buf(args->trans, bp2,
+ xfs_trans_log_buf(args->trans, bp2,
XFS_DA_LOGRANGE(leaf2, name_rmt, sizeof(*name_rmt)));
}
- xfs_da_buf_done(bp1);
- if (bp1 != bp2)
- xfs_da_buf_done(bp2);
/*
* Commit the flag value change and start the next trans in series.
*/
error = xfs_trans_roll(&args->trans, args->dp);
- return(error);
-}
-
-/*========================================================================
- * Indiscriminately delete the entire attribute fork
- *========================================================================*/
-
-/*
- * Recurse (gasp!) through the attribute nodes until we find leaves.
- * We're doing a depth-first traversal in order to invalidate everything.
- */
-int
-xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
-{
- xfs_da_blkinfo_t *info;
- xfs_daddr_t blkno;
- xfs_dabuf_t *bp;
- int error;
-
- /*
- * Read block 0 to see what we have to work with.
- * We only get here if we have extents, since we remove
- * the extents in reverse order the extent containing
- * block 0 must still be there.
- */
- error = xfs_da_read_buf(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
- if (error)
- return(error);
- blkno = xfs_da_blkno(bp);
-
- /*
- * Invalidate the tree, even if the "tree" is only a single leaf block.
- * This is a depth-first traversal!
- */
- info = bp->data;
- if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
- error = xfs_attr_node_inactive(trans, dp, bp, 1);
- } else if (info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) {
- error = xfs_attr_leaf_inactive(trans, dp, bp);
- } else {
- error = XFS_ERROR(EIO);
- xfs_da_brelse(*trans, bp);
- }
- if (error)
- return(error);
-
- /*
- * Invalidate the incore copy of the root block.
- */
- error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
- if (error)
- return(error);
- xfs_da_binval(*trans, bp); /* remove from cache */
- /*
- * Commit the invalidate and start the next transaction.
- */
- error = xfs_trans_roll(trans, dp);
-
- return (error);
-}
-
-/*
- * Recurse (gasp!) through the attribute nodes until we find leaves.
- * We're doing a depth-first traversal in order to invalidate everything.
- */
-STATIC int
-xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
- int level)
-{
- xfs_da_blkinfo_t *info;
- xfs_da_intnode_t *node;
- xfs_dablk_t child_fsb;
- xfs_daddr_t parent_blkno, child_blkno;
- int error, count, i;
- xfs_dabuf_t *child_bp;
-
- /*
- * Since this code is recursive (gasp!) we must protect ourselves.
- */
- if (level > XFS_DA_NODE_MAXDEPTH) {
- xfs_da_brelse(*trans, bp); /* no locks for later trans */
- return(XFS_ERROR(EIO));
- }
-
- node = bp->data;
- ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- parent_blkno = xfs_da_blkno(bp); /* save for re-read later */
- count = be16_to_cpu(node->hdr.count);
- if (!count) {
- xfs_da_brelse(*trans, bp);
- return(0);
- }
- child_fsb = be32_to_cpu(node->btree[0].before);
- xfs_da_brelse(*trans, bp); /* no locks for later trans */
-
- /*
- * If this is the node level just above the leaves, simply loop
- * over the leaves removing all of them. If this is higher up
- * in the tree, recurse downward.
- */
- for (i = 0; i < count; i++) {
- /*
- * Read the subsidiary block to see what we have to work with.
- * Don't do this in a transaction. This is a depth-first
- * traversal of the tree so we may deal with many blocks
- * before we come back to this one.
- */
- error = xfs_da_read_buf(*trans, dp, child_fsb, -2, &child_bp,
- XFS_ATTR_FORK);
- if (error)
- return(error);
- if (child_bp) {
- /* save for re-read later */
- child_blkno = xfs_da_blkno(child_bp);
-
- /*
- * Invalidate the subtree, however we have to.
- */
- info = child_bp->data;
- if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
- error = xfs_attr_node_inactive(trans, dp,
- child_bp, level+1);
- } else if (info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) {
- error = xfs_attr_leaf_inactive(trans, dp,
- child_bp);
- } else {
- error = XFS_ERROR(EIO);
- xfs_da_brelse(*trans, child_bp);
- }
- if (error)
- return(error);
-
- /*
- * Remove the subsidiary block from the cache
- * and from the log.
- */
- error = xfs_da_get_buf(*trans, dp, 0, child_blkno,
- &child_bp, XFS_ATTR_FORK);
- if (error)
- return(error);
- xfs_da_binval(*trans, child_bp);
- }
-
- /*
- * If we're not done, re-read the parent to get the next
- * child block number.
- */
- if ((i+1) < count) {
- error = xfs_da_read_buf(*trans, dp, 0, parent_blkno,
- &bp, XFS_ATTR_FORK);
- if (error)
- return(error);
- child_fsb = be32_to_cpu(node->btree[i+1].before);
- xfs_da_brelse(*trans, bp);
- }
- /*
- * Atomically commit the whole invalidate stuff.
- */
- error = xfs_trans_roll(trans, dp);
- if (error)
- return (error);
- }
-
- return(0);
-}
-
-/*
- * Invalidate all of the "remote" value regions pointed to by a particular
- * leaf block.
- * Note that we must release the lock on the buffer so that we are not
- * caught holding something that the logging code wants to flush to disk.
- */
-STATIC int
-xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
-{
- xfs_attr_leafblock_t *leaf;
- xfs_attr_leaf_entry_t *entry;
- xfs_attr_leaf_name_remote_t *name_rmt;
- xfs_attr_inactive_list_t *list, *lp;
- int error, count, size, tmp, i;
-
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
-
- /*
- * Count the number of "remote" value extents.
- */
- count = 0;
- entry = &leaf->entries[0];
- for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) {
- if (be16_to_cpu(entry->nameidx) &&
- ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
- name_rmt = xfs_attr_leaf_name_remote(leaf, i);
- if (name_rmt->valueblk)
- count++;
- }
- }
-
- /*
- * If there are no "remote" values, we're done.
- */
- if (count == 0) {
- xfs_da_brelse(*trans, bp);
- return(0);
- }
-
- /*
- * Allocate storage for a list of all the "remote" value extents.
- */
- size = count * sizeof(xfs_attr_inactive_list_t);
- list = (xfs_attr_inactive_list_t *)kmem_alloc(size, KM_SLEEP);
-
- /*
- * Identify each of the "remote" value extents.
- */
- lp = list;
- entry = &leaf->entries[0];
- for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) {
- if (be16_to_cpu(entry->nameidx) &&
- ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
- name_rmt = xfs_attr_leaf_name_remote(leaf, i);
- if (name_rmt->valueblk) {
- lp->valueblk = be32_to_cpu(name_rmt->valueblk);
- lp->valuelen = XFS_B_TO_FSB(dp->i_mount,
- be32_to_cpu(name_rmt->valuelen));
- lp++;
- }
- }
- }
- xfs_da_brelse(*trans, bp); /* unlock for trans. in freextent() */
-
- /*
- * Invalidate each of the "remote" value extents.
- */
- error = 0;
- for (lp = list, i = 0; i < count; i++, lp++) {
- tmp = xfs_attr_leaf_freextent(trans, dp,
- lp->valueblk, lp->valuelen);
-
- if (error == 0)
- error = tmp; /* save only the 1st errno */
- }
-
- kmem_free((xfs_caddr_t)list);
- return(error);
-}
-
-/*
- * Look at all the extents for this logical region,
- * invalidate any buffers that are incore/in transactions.
- */
-STATIC int
-xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp,
- xfs_dablk_t blkno, int blkcnt)
-{
- xfs_bmbt_irec_t map;
- xfs_dablk_t tblkno;
- int tblkcnt, dblkcnt, nmap, error;
- xfs_daddr_t dblkno;
- xfs_buf_t *bp;
-
- /*
- * Roll through the "value", invalidating the attribute value's
- * blocks.
- */
- tblkno = blkno;
- tblkcnt = blkcnt;
- while (tblkcnt > 0) {
- /*
- * Try to remember where we decided to put the value.
- */
- nmap = 1;
- error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
- &map, &nmap, XFS_BMAPI_ATTRFORK);
- if (error) {
- return(error);
- }
- ASSERT(nmap == 1);
- ASSERT(map.br_startblock != DELAYSTARTBLOCK);
-
- /*
- * If it's a hole, these are already unmapped
- * so there's nothing to invalidate.
- */
- if (map.br_startblock != HOLESTARTBLOCK) {
-
- dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
- map.br_startblock);
- dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
- map.br_blockcount);
- bp = xfs_trans_get_buf(*trans,
- dp->i_mount->m_ddev_targp,
- dblkno, dblkcnt, 0);
- if (!bp)
- return ENOMEM;
- xfs_trans_binval(*trans, bp);
- /*
- * Roll to next transaction.
- */
- error = xfs_trans_roll(trans, dp);
- if (error)
- return (error);
- }
-
- tblkno += map.br_blockcount;
- tblkcnt -= map.br_blockcount;
- }
-
- return(0);
+ return error;
}
diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h
index 9c7d22fdcf4..e2929da7c3b 100644
--- a/fs/xfs/xfs_attr_leaf.h
+++ b/fs/xfs/xfs_attr_leaf.h
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000,2002-2003,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -18,180 +19,15 @@
#ifndef __XFS_ATTR_LEAF_H__
#define __XFS_ATTR_LEAF_H__
-/*
- * Attribute storage layout, internal structure, access macros, etc.
- *
- * Attribute lists are structured around Btrees where all the data
- * elements are in the leaf nodes. Attribute names are hashed into an int,
- * then that int is used as the index into the Btree. Since the hashval
- * of an attribute name may not be unique, we may have duplicate keys. The
- * internal links in the Btree are logical block offsets into the file.
- */
-
struct attrlist;
struct attrlist_cursor_kern;
struct xfs_attr_list_context;
-struct xfs_dabuf;
struct xfs_da_args;
struct xfs_da_state;
struct xfs_da_state_blk;
struct xfs_inode;
struct xfs_trans;
-/*========================================================================
- * Attribute structure when equal to XFS_LBSIZE(mp) bytes.
- *========================================================================*/
-
-/*
- * This is the structure of the leaf nodes in the Btree.
- *
- * Struct leaf_entry's are packed from the top. Name/values grow from the
- * bottom but are not packed. The freemap contains run-length-encoded entries
- * for the free bytes after the leaf_entry's, but only the N largest such,
- * smaller runs are dropped. When the freemap doesn't show enough space
- * for an allocation, we compact the name/value area and try again. If we
- * still don't have enough space, then we have to split the block. The
- * name/value structs (both local and remote versions) must be 32bit aligned.
- *
- * Since we have duplicate hash keys, for each key that matches, compare
- * the actual name string. The root and intermediate node search always
- * takes the first-in-the-block key match found, so we should only have
- * to work "forw"ard. If none matches, continue with the "forw"ard leaf
- * nodes until the hash key changes or the attribute name is found.
- *
- * We store the fact that an attribute is a ROOT/USER/SECURE attribute in
- * the leaf_entry. The namespaces are independent only because we also look
- * at the namespace bit when we are looking for a matching attribute name.
- *
- * We also store an "incomplete" bit in the leaf_entry. It shows that an
- * attribute is in the middle of being created and should not be shown to
- * the user if we crash during the time that the bit is set. We clear the
- * bit when we have finished setting up the attribute. We do this because
- * we cannot create some large attributes inside a single transaction, and we
- * need some indication that we weren't finished if we crash in the middle.
- */
-#define XFS_ATTR_LEAF_MAPSIZE 3 /* how many freespace slots */
-
-typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */
- __be16 base; /* base of free region */
- __be16 size; /* length of free region */
-} xfs_attr_leaf_map_t;
-
-typedef struct xfs_attr_leaf_hdr { /* constant-structure header block */
- xfs_da_blkinfo_t info; /* block type, links, etc. */
- __be16 count; /* count of active leaf_entry's */
- __be16 usedbytes; /* num bytes of names/values stored */
- __be16 firstused; /* first used byte in name area */
- __u8 holes; /* != 0 if blk needs compaction */
- __u8 pad1;
- xfs_attr_leaf_map_t freemap[XFS_ATTR_LEAF_MAPSIZE];
- /* N largest free regions */
-} xfs_attr_leaf_hdr_t;
-
-typedef struct xfs_attr_leaf_entry { /* sorted on key, not name */
- __be32 hashval; /* hash value of name */
- __be16 nameidx; /* index into buffer of name/value */
- __u8 flags; /* LOCAL/ROOT/SECURE/INCOMPLETE flag */
- __u8 pad2; /* unused pad byte */
-} xfs_attr_leaf_entry_t;
-
-typedef struct xfs_attr_leaf_name_local {
- __be16 valuelen; /* number of bytes in value */
- __u8 namelen; /* length of name bytes */
- __u8 nameval[1]; /* name/value bytes */
-} xfs_attr_leaf_name_local_t;
-
-typedef struct xfs_attr_leaf_name_remote {
- __be32 valueblk; /* block number of value bytes */
- __be32 valuelen; /* number of bytes in value */
- __u8 namelen; /* length of name bytes */
- __u8 name[1]; /* name bytes */
-} xfs_attr_leaf_name_remote_t;
-
-typedef struct xfs_attr_leafblock {
- xfs_attr_leaf_hdr_t hdr; /* constant-structure header block */
- xfs_attr_leaf_entry_t entries[1]; /* sorted on key, not name */
- xfs_attr_leaf_name_local_t namelist; /* grows from bottom of buf */
- xfs_attr_leaf_name_remote_t valuelist; /* grows from bottom of buf */
-} xfs_attr_leafblock_t;
-
-/*
- * Flags used in the leaf_entry[i].flags field.
- * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
- * on the system call, they are "or"ed together for various operations.
- */
-#define XFS_ATTR_LOCAL_BIT 0 /* attr is stored locally */
-#define XFS_ATTR_ROOT_BIT 1 /* limit access to trusted attrs */
-#define XFS_ATTR_SECURE_BIT 2 /* limit access to secure attrs */
-#define XFS_ATTR_INCOMPLETE_BIT 7 /* attr in middle of create/delete */
-#define XFS_ATTR_LOCAL (1 << XFS_ATTR_LOCAL_BIT)
-#define XFS_ATTR_ROOT (1 << XFS_ATTR_ROOT_BIT)
-#define XFS_ATTR_SECURE (1 << XFS_ATTR_SECURE_BIT)
-#define XFS_ATTR_INCOMPLETE (1 << XFS_ATTR_INCOMPLETE_BIT)
-
-/*
- * Conversion macros for converting namespace bits from argument flags
- * to ondisk flags.
- */
-#define XFS_ATTR_NSP_ARGS_MASK (ATTR_ROOT | ATTR_SECURE)
-#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | XFS_ATTR_SECURE)
-#define XFS_ATTR_NSP_ONDISK(flags) ((flags) & XFS_ATTR_NSP_ONDISK_MASK)
-#define XFS_ATTR_NSP_ARGS(flags) ((flags) & XFS_ATTR_NSP_ARGS_MASK)
-#define XFS_ATTR_NSP_ARGS_TO_ONDISK(x) (((x) & ATTR_ROOT ? XFS_ATTR_ROOT : 0) |\
- ((x) & ATTR_SECURE ? XFS_ATTR_SECURE : 0))
-#define XFS_ATTR_NSP_ONDISK_TO_ARGS(x) (((x) & XFS_ATTR_ROOT ? ATTR_ROOT : 0) |\
- ((x) & XFS_ATTR_SECURE ? ATTR_SECURE : 0))
-
-/*
- * Alignment for namelist and valuelist entries (since they are mixed
- * there can be only one alignment value)
- */
-#define XFS_ATTR_LEAF_NAME_ALIGN ((uint)sizeof(xfs_dablk_t))
-
-/*
- * Cast typed pointers for "local" and "remote" name/value structs.
- */
-static inline xfs_attr_leaf_name_remote_t *
-xfs_attr_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx)
-{
- return (xfs_attr_leaf_name_remote_t *)
- &((char *)leafp)[be16_to_cpu(leafp->entries[idx].nameidx)];
-}
-
-static inline xfs_attr_leaf_name_local_t *
-xfs_attr_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx)
-{
- return (xfs_attr_leaf_name_local_t *)
- &((char *)leafp)[be16_to_cpu(leafp->entries[idx].nameidx)];
-}
-
-static inline char *xfs_attr_leaf_name(xfs_attr_leafblock_t *leafp, int idx)
-{
- return &((char *)leafp)[be16_to_cpu(leafp->entries[idx].nameidx)];
-}
-
-/*
- * Calculate total bytes used (including trailing pad for alignment) for
- * a "local" name/value structure, a "remote" name/value structure, and
- * a pointer which might be either.
- */
-static inline int xfs_attr_leaf_entsize_remote(int nlen)
-{
- return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \
- XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
-}
-
-static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen)
-{
- return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) +
- XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
-}
-
-static inline int xfs_attr_leaf_entsize_local_max(int bsize)
-{
- return (((bsize) >> 1) + ((bsize) >> 2));
-}
-
/*
* Used to keep a list of "remote value" extents when unlinking an inode.
*/
@@ -215,51 +51,58 @@ int xfs_attr_shortform_getvalue(struct xfs_da_args *args);
int xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
int xfs_attr_shortform_remove(struct xfs_da_args *args);
int xfs_attr_shortform_list(struct xfs_attr_list_context *context);
-int xfs_attr_shortform_allfit(struct xfs_dabuf *bp, struct xfs_inode *dp);
+int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
int xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
/*
* Internal routines when attribute fork size == XFS_LBSIZE(mp).
*/
-int xfs_attr_leaf_to_node(struct xfs_da_args *args);
-int xfs_attr_leaf_to_shortform(struct xfs_dabuf *bp,
+int xfs_attr3_leaf_to_node(struct xfs_da_args *args);
+int xfs_attr3_leaf_to_shortform(struct xfs_buf *bp,
struct xfs_da_args *args, int forkoff);
-int xfs_attr_leaf_clearflag(struct xfs_da_args *args);
-int xfs_attr_leaf_setflag(struct xfs_da_args *args);
-int xfs_attr_leaf_flipflags(xfs_da_args_t *args);
+int xfs_attr3_leaf_clearflag(struct xfs_da_args *args);
+int xfs_attr3_leaf_setflag(struct xfs_da_args *args);
+int xfs_attr3_leaf_flipflags(struct xfs_da_args *args);
/*
* Routines used for growing the Btree.
*/
-int xfs_attr_leaf_split(struct xfs_da_state *state,
+int xfs_attr3_leaf_split(struct xfs_da_state *state,
struct xfs_da_state_blk *oldblk,
struct xfs_da_state_blk *newblk);
-int xfs_attr_leaf_lookup_int(struct xfs_dabuf *leaf,
+int xfs_attr3_leaf_lookup_int(struct xfs_buf *leaf,
struct xfs_da_args *args);
-int xfs_attr_leaf_getvalue(struct xfs_dabuf *bp, struct xfs_da_args *args);
-int xfs_attr_leaf_add(struct xfs_dabuf *leaf_buffer,
+int xfs_attr3_leaf_getvalue(struct xfs_buf *bp, struct xfs_da_args *args);
+int xfs_attr3_leaf_add(struct xfs_buf *leaf_buffer,
struct xfs_da_args *args);
-int xfs_attr_leaf_remove(struct xfs_dabuf *leaf_buffer,
+int xfs_attr3_leaf_remove(struct xfs_buf *leaf_buffer,
struct xfs_da_args *args);
-int xfs_attr_leaf_list_int(struct xfs_dabuf *bp,
+int xfs_attr3_leaf_list_int(struct xfs_buf *bp,
struct xfs_attr_list_context *context);
/*
* Routines used for shrinking the Btree.
*/
-int xfs_attr_leaf_toosmall(struct xfs_da_state *state, int *retval);
-void xfs_attr_leaf_unbalance(struct xfs_da_state *state,
+int xfs_attr3_leaf_toosmall(struct xfs_da_state *state, int *retval);
+void xfs_attr3_leaf_unbalance(struct xfs_da_state *state,
struct xfs_da_state_blk *drop_blk,
struct xfs_da_state_blk *save_blk);
-int xfs_attr_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
+int xfs_attr3_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
/*
* Utility routines.
*/
-xfs_dahash_t xfs_attr_leaf_lasthash(struct xfs_dabuf *bp, int *count);
-int xfs_attr_leaf_order(struct xfs_dabuf *leaf1_bp,
- struct xfs_dabuf *leaf2_bp);
-int xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize,
- int *local);
+xfs_dahash_t xfs_attr_leaf_lasthash(struct xfs_buf *bp, int *count);
+int xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
+ struct xfs_buf *leaf2_bp);
+int xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local);
+int xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
+ xfs_dablk_t bno, xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp);
+void xfs_attr3_leaf_hdr_from_disk(struct xfs_attr3_icleaf_hdr *to,
+ struct xfs_attr_leafblock *from);
+void xfs_attr3_leaf_hdr_to_disk(struct xfs_attr_leafblock *to,
+ struct xfs_attr3_icleaf_hdr *from);
+
#endif /* __XFS_ATTR_LEAF_H__ */
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
new file mode 100644
index 00000000000..90e2eeb2120
--- /dev/null
+++ b/fs/xfs/xfs_attr_list.c
@@ -0,0 +1,653 @@
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
+#include "xfs_attr.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_error.h"
+#include "xfs_trace.h"
+#include "xfs_buf_item.h"
+#include "xfs_cksum.h"
+#include "xfs_dinode.h"
+#include "xfs_dir2.h"
+
+STATIC int
+xfs_attr_shortform_compare(const void *a, const void *b)
+{
+ xfs_attr_sf_sort_t *sa, *sb;
+
+ sa = (xfs_attr_sf_sort_t *)a;
+ sb = (xfs_attr_sf_sort_t *)b;
+ if (sa->hash < sb->hash) {
+ return(-1);
+ } else if (sa->hash > sb->hash) {
+ return(1);
+ } else {
+ return(sa->entno - sb->entno);
+ }
+}
+
+#define XFS_ISRESET_CURSOR(cursor) \
+ (!((cursor)->initted) && !((cursor)->hashval) && \
+ !((cursor)->blkno) && !((cursor)->offset))
+/*
+ * Copy out entries of shortform attribute lists for attr_list().
+ * Shortform attribute lists are not stored in hashval sorted order.
+ * If the output buffer is not large enough to hold them all, then we
+ * we have to calculate each entries' hashvalue and sort them before
+ * we can begin returning them to the user.
+ */
+int
+xfs_attr_shortform_list(xfs_attr_list_context_t *context)
+{
+ attrlist_cursor_kern_t *cursor;
+ xfs_attr_sf_sort_t *sbuf, *sbp;
+ xfs_attr_shortform_t *sf;
+ xfs_attr_sf_entry_t *sfe;
+ xfs_inode_t *dp;
+ int sbsize, nsbuf, count, i;
+ int error;
+
+ ASSERT(context != NULL);
+ dp = context->dp;
+ ASSERT(dp != NULL);
+ ASSERT(dp->i_afp != NULL);
+ sf = (xfs_attr_shortform_t *)dp->i_afp->if_u1.if_data;
+ ASSERT(sf != NULL);
+ if (!sf->hdr.count)
+ return(0);
+ cursor = context->cursor;
+ ASSERT(cursor != NULL);
+
+ trace_xfs_attr_list_sf(context);
+
+ /*
+ * If the buffer is large enough and the cursor is at the start,
+ * do not bother with sorting since we will return everything in
+ * one buffer and another call using the cursor won't need to be
+ * made.
+ * Note the generous fudge factor of 16 overhead bytes per entry.
+ * If bufsize is zero then put_listent must be a search function
+ * and can just scan through what we have.
+ */
+ if (context->bufsize == 0 ||
+ (XFS_ISRESET_CURSOR(cursor) &&
+ (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
+ for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+ error = context->put_listent(context,
+ sfe->flags,
+ sfe->nameval,
+ (int)sfe->namelen,
+ (int)sfe->valuelen,
+ &sfe->nameval[sfe->namelen]);
+
+ /*
+ * Either search callback finished early or
+ * didn't fit it all in the buffer after all.
+ */
+ if (context->seen_enough)
+ break;
+
+ if (error)
+ return error;
+ sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
+ }
+ trace_xfs_attr_list_sf_all(context);
+ return(0);
+ }
+
+ /* do no more for a search callback */
+ if (context->bufsize == 0)
+ return 0;
+
+ /*
+ * It didn't all fit, so we have to sort everything on hashval.
+ */
+ sbsize = sf->hdr.count * sizeof(*sbuf);
+ sbp = sbuf = kmem_alloc(sbsize, KM_SLEEP | KM_NOFS);
+
+ /*
+ * Scan the attribute list for the rest of the entries, storing
+ * the relevant info from only those that match into a buffer.
+ */
+ nsbuf = 0;
+ for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+ if (unlikely(
+ ((char *)sfe < (char *)sf) ||
+ ((char *)sfe >= ((char *)sf + dp->i_afp->if_bytes)))) {
+ XFS_CORRUPTION_ERROR("xfs_attr_shortform_list",
+ XFS_ERRLEVEL_LOW,
+ context->dp->i_mount, sfe);
+ kmem_free(sbuf);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+
+ sbp->entno = i;
+ sbp->hash = xfs_da_hashname(sfe->nameval, sfe->namelen);
+ sbp->name = sfe->nameval;
+ sbp->namelen = sfe->namelen;
+ /* These are bytes, and both on-disk, don't endian-flip */
+ sbp->valuelen = sfe->valuelen;
+ sbp->flags = sfe->flags;
+ sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
+ sbp++;
+ nsbuf++;
+ }
+
+ /*
+ * Sort the entries on hash then entno.
+ */
+ xfs_sort(sbuf, nsbuf, sizeof(*sbuf), xfs_attr_shortform_compare);
+
+ /*
+ * Re-find our place IN THE SORTED LIST.
+ */
+ count = 0;
+ cursor->initted = 1;
+ cursor->blkno = 0;
+ for (sbp = sbuf, i = 0; i < nsbuf; i++, sbp++) {
+ if (sbp->hash == cursor->hashval) {
+ if (cursor->offset == count) {
+ break;
+ }
+ count++;
+ } else if (sbp->hash > cursor->hashval) {
+ break;
+ }
+ }
+ if (i == nsbuf) {
+ kmem_free(sbuf);
+ return(0);
+ }
+
+ /*
+ * Loop putting entries into the user buffer.
+ */
+ for ( ; i < nsbuf; i++, sbp++) {
+ if (cursor->hashval != sbp->hash) {
+ cursor->hashval = sbp->hash;
+ cursor->offset = 0;
+ }
+ error = context->put_listent(context,
+ sbp->flags,
+ sbp->name,
+ sbp->namelen,
+ sbp->valuelen,
+ &sbp->name[sbp->namelen]);
+ if (error)
+ return error;
+ if (context->seen_enough)
+ break;
+ cursor->offset++;
+ }
+
+ kmem_free(sbuf);
+ return(0);
+}
+
+STATIC int
+xfs_attr_node_list(xfs_attr_list_context_t *context)
+{
+ attrlist_cursor_kern_t *cursor;
+ xfs_attr_leafblock_t *leaf;
+ xfs_da_intnode_t *node;
+ struct xfs_attr3_icleaf_hdr leafhdr;
+ struct xfs_da3_icnode_hdr nodehdr;
+ struct xfs_da_node_entry *btree;
+ int error, i;
+ struct xfs_buf *bp;
+ struct xfs_inode *dp = context->dp;
+
+ trace_xfs_attr_node_list(context);
+
+ cursor = context->cursor;
+ cursor->initted = 1;
+
+ /*
+ * Do all sorts of validation on the passed-in cursor structure.
+ * If anything is amiss, ignore the cursor and look up the hashval
+ * starting from the btree root.
+ */
+ bp = NULL;
+ if (cursor->blkno > 0) {
+ error = xfs_da3_node_read(NULL, dp, cursor->blkno, -1,
+ &bp, XFS_ATTR_FORK);
+ if ((error != 0) && (error != EFSCORRUPTED))
+ return(error);
+ if (bp) {
+ struct xfs_attr_leaf_entry *entries;
+
+ node = bp->b_addr;
+ switch (be16_to_cpu(node->hdr.info.magic)) {
+ case XFS_DA_NODE_MAGIC:
+ case XFS_DA3_NODE_MAGIC:
+ trace_xfs_attr_list_wrong_blk(context);
+ xfs_trans_brelse(NULL, bp);
+ bp = NULL;
+ break;
+ case XFS_ATTR_LEAF_MAGIC:
+ case XFS_ATTR3_LEAF_MAGIC:
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&leafhdr, leaf);
+ entries = xfs_attr3_leaf_entryp(leaf);
+ if (cursor->hashval > be32_to_cpu(
+ entries[leafhdr.count - 1].hashval)) {
+ trace_xfs_attr_list_wrong_blk(context);
+ xfs_trans_brelse(NULL, bp);
+ bp = NULL;
+ } else if (cursor->hashval <= be32_to_cpu(
+ entries[0].hashval)) {
+ trace_xfs_attr_list_wrong_blk(context);
+ xfs_trans_brelse(NULL, bp);
+ bp = NULL;
+ }
+ break;
+ default:
+ trace_xfs_attr_list_wrong_blk(context);
+ xfs_trans_brelse(NULL, bp);
+ bp = NULL;
+ }
+ }
+ }
+
+ /*
+ * We did not find what we expected given the cursor's contents,
+ * so we start from the top and work down based on the hash value.
+ * Note that start of node block is same as start of leaf block.
+ */
+ if (bp == NULL) {
+ cursor->blkno = 0;
+ for (;;) {
+ __uint16_t magic;
+
+ error = xfs_da3_node_read(NULL, dp,
+ cursor->blkno, -1, &bp,
+ XFS_ATTR_FORK);
+ if (error)
+ return(error);
+ node = bp->b_addr;
+ magic = be16_to_cpu(node->hdr.info.magic);
+ if (magic == XFS_ATTR_LEAF_MAGIC ||
+ magic == XFS_ATTR3_LEAF_MAGIC)
+ break;
+ if (magic != XFS_DA_NODE_MAGIC &&
+ magic != XFS_DA3_NODE_MAGIC) {
+ XFS_CORRUPTION_ERROR("xfs_attr_node_list(3)",
+ XFS_ERRLEVEL_LOW,
+ context->dp->i_mount,
+ node);
+ xfs_trans_brelse(NULL, bp);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
+ for (i = 0; i < nodehdr.count; btree++, i++) {
+ if (cursor->hashval
+ <= be32_to_cpu(btree->hashval)) {
+ cursor->blkno = be32_to_cpu(btree->before);
+ trace_xfs_attr_list_node_descend(context,
+ btree);
+ break;
+ }
+ }
+ if (i == nodehdr.count) {
+ xfs_trans_brelse(NULL, bp);
+ return 0;
+ }
+ xfs_trans_brelse(NULL, bp);
+ }
+ }
+ ASSERT(bp != NULL);
+
+ /*
+ * Roll upward through the blocks, processing each leaf block in
+ * order. As long as there is space in the result buffer, keep
+ * adding the information.
+ */
+ for (;;) {
+ leaf = bp->b_addr;
+ error = xfs_attr3_leaf_list_int(bp, context);
+ if (error) {
+ xfs_trans_brelse(NULL, bp);
+ return error;
+ }
+ xfs_attr3_leaf_hdr_from_disk(&leafhdr, leaf);
+ if (context->seen_enough || leafhdr.forw == 0)
+ break;
+ cursor->blkno = leafhdr.forw;
+ xfs_trans_brelse(NULL, bp);
+ error = xfs_attr3_leaf_read(NULL, dp, cursor->blkno, -1, &bp);
+ if (error)
+ return error;
+ }
+ xfs_trans_brelse(NULL, bp);
+ return 0;
+}
+
+/*
+ * Copy out attribute list entries for attr_list(), for leaf attribute lists.
+ */
+int
+xfs_attr3_leaf_list_int(
+ struct xfs_buf *bp,
+ struct xfs_attr_list_context *context)
+{
+ struct attrlist_cursor_kern *cursor;
+ struct xfs_attr_leafblock *leaf;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_attr_leaf_entry *entries;
+ struct xfs_attr_leaf_entry *entry;
+ int retval;
+ int i;
+
+ trace_xfs_attr_list_leaf(context);
+
+ leaf = bp->b_addr;
+ xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
+ entries = xfs_attr3_leaf_entryp(leaf);
+
+ cursor = context->cursor;
+ cursor->initted = 1;
+
+ /*
+ * Re-find our place in the leaf block if this is a new syscall.
+ */
+ if (context->resynch) {
+ entry = &entries[0];
+ for (i = 0; i < ichdr.count; entry++, i++) {
+ if (be32_to_cpu(entry->hashval) == cursor->hashval) {
+ if (cursor->offset == context->dupcnt) {
+ context->dupcnt = 0;
+ break;
+ }
+ context->dupcnt++;
+ } else if (be32_to_cpu(entry->hashval) >
+ cursor->hashval) {
+ context->dupcnt = 0;
+ break;
+ }
+ }
+ if (i == ichdr.count) {
+ trace_xfs_attr_list_notfound(context);
+ return 0;
+ }
+ } else {
+ entry = &entries[0];
+ i = 0;
+ }
+ context->resynch = 0;
+
+ /*
+ * We have found our place, start copying out the new attributes.
+ */
+ retval = 0;
+ for (; i < ichdr.count; entry++, i++) {
+ if (be32_to_cpu(entry->hashval) != cursor->hashval) {
+ cursor->hashval = be32_to_cpu(entry->hashval);
+ cursor->offset = 0;
+ }
+
+ if (entry->flags & XFS_ATTR_INCOMPLETE)
+ continue; /* skip incomplete entries */
+
+ if (entry->flags & XFS_ATTR_LOCAL) {
+ xfs_attr_leaf_name_local_t *name_loc =
+ xfs_attr3_leaf_name_local(leaf, i);
+
+ retval = context->put_listent(context,
+ entry->flags,
+ name_loc->nameval,
+ (int)name_loc->namelen,
+ be16_to_cpu(name_loc->valuelen),
+ &name_loc->nameval[name_loc->namelen]);
+ if (retval)
+ return retval;
+ } else {
+ xfs_attr_leaf_name_remote_t *name_rmt =
+ xfs_attr3_leaf_name_remote(leaf, i);
+
+ int valuelen = be32_to_cpu(name_rmt->valuelen);
+
+ if (context->put_value) {
+ xfs_da_args_t args;
+
+ memset((char *)&args, 0, sizeof(args));
+ args.geo = context->dp->i_mount->m_attr_geo;
+ args.dp = context->dp;
+ args.whichfork = XFS_ATTR_FORK;
+ args.valuelen = valuelen;
+ args.rmtvaluelen = valuelen;
+ args.value = kmem_alloc(valuelen, KM_SLEEP | KM_NOFS);
+ args.rmtblkno = be32_to_cpu(name_rmt->valueblk);
+ args.rmtblkcnt = xfs_attr3_rmt_blocks(
+ args.dp->i_mount, valuelen);
+ retval = xfs_attr_rmtval_get(&args);
+ if (retval)
+ return retval;
+ retval = context->put_listent(context,
+ entry->flags,
+ name_rmt->name,
+ (int)name_rmt->namelen,
+ valuelen,
+ args.value);
+ kmem_free(args.value);
+ } else {
+ retval = context->put_listent(context,
+ entry->flags,
+ name_rmt->name,
+ (int)name_rmt->namelen,
+ valuelen,
+ NULL);
+ }
+ if (retval)
+ return retval;
+ }
+ if (context->seen_enough)
+ break;
+ cursor->offset++;
+ }
+ trace_xfs_attr_list_leaf_end(context);
+ return retval;
+}
+
+/*
+ * Copy out attribute entries for attr_list(), for leaf attribute lists.
+ */
+STATIC int
+xfs_attr_leaf_list(xfs_attr_list_context_t *context)
+{
+ int error;
+ struct xfs_buf *bp;
+
+ trace_xfs_attr_leaf_list(context);
+
+ context->cursor->blkno = 0;
+ error = xfs_attr3_leaf_read(NULL, context->dp, 0, -1, &bp);
+ if (error)
+ return XFS_ERROR(error);
+
+ error = xfs_attr3_leaf_list_int(bp, context);
+ xfs_trans_brelse(NULL, bp);
+ return XFS_ERROR(error);
+}
+
+int
+xfs_attr_list_int(
+ xfs_attr_list_context_t *context)
+{
+ int error;
+ xfs_inode_t *dp = context->dp;
+ uint lock_mode;
+
+ XFS_STATS_INC(xs_attr_list);
+
+ if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+ return EIO;
+
+ /*
+ * Decide on what work routines to call based on the inode size.
+ */
+ lock_mode = xfs_ilock_attr_map_shared(dp);
+ if (!xfs_inode_hasattr(dp)) {
+ error = 0;
+ } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+ error = xfs_attr_shortform_list(context);
+ } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+ error = xfs_attr_leaf_list(context);
+ } else {
+ error = xfs_attr_node_list(context);
+ }
+ xfs_iunlock(dp, lock_mode);
+ return error;
+}
+
+#define ATTR_ENTBASESIZE /* minimum bytes used by an attr */ \
+ (((struct attrlist_ent *) 0)->a_name - (char *) 0)
+#define ATTR_ENTSIZE(namelen) /* actual bytes used by an attr */ \
+ ((ATTR_ENTBASESIZE + (namelen) + 1 + sizeof(u_int32_t)-1) \
+ & ~(sizeof(u_int32_t)-1))
+
+/*
+ * Format an attribute and copy it out to the user's buffer.
+ * Take care to check values and protect against them changing later,
+ * we may be reading them directly out of a user buffer.
+ */
+STATIC int
+xfs_attr_put_listent(
+ xfs_attr_list_context_t *context,
+ int flags,
+ unsigned char *name,
+ int namelen,
+ int valuelen,
+ unsigned char *value)
+{
+ struct attrlist *alist = (struct attrlist *)context->alist;
+ attrlist_ent_t *aep;
+ int arraytop;
+
+ ASSERT(!(context->flags & ATTR_KERNOVAL));
+ ASSERT(context->count >= 0);
+ ASSERT(context->count < (ATTR_MAX_VALUELEN/8));
+ ASSERT(context->firstu >= sizeof(*alist));
+ ASSERT(context->firstu <= context->bufsize);
+
+ /*
+ * Only list entries in the right namespace.
+ */
+ if (((context->flags & ATTR_SECURE) == 0) !=
+ ((flags & XFS_ATTR_SECURE) == 0))
+ return 0;
+ if (((context->flags & ATTR_ROOT) == 0) !=
+ ((flags & XFS_ATTR_ROOT) == 0))
+ return 0;
+
+ arraytop = sizeof(*alist) +
+ context->count * sizeof(alist->al_offset[0]);
+ context->firstu -= ATTR_ENTSIZE(namelen);
+ if (context->firstu < arraytop) {
+ trace_xfs_attr_list_full(context);
+ alist->al_more = 1;
+ context->seen_enough = 1;
+ return 1;
+ }
+
+ aep = (attrlist_ent_t *)&context->alist[context->firstu];
+ aep->a_valuelen = valuelen;
+ memcpy(aep->a_name, name, namelen);
+ aep->a_name[namelen] = 0;
+ alist->al_offset[context->count++] = context->firstu;
+ alist->al_count = context->count;
+ trace_xfs_attr_list_add(context);
+ return 0;
+}
+
+/*
+ * Generate a list of extended attribute names and optionally
+ * also value lengths. Positive return value follows the XFS
+ * convention of being an error, zero or negative return code
+ * is the length of the buffer returned (negated), indicating
+ * success.
+ */
+int
+xfs_attr_list(
+ xfs_inode_t *dp,
+ char *buffer,
+ int bufsize,
+ int flags,
+ attrlist_cursor_kern_t *cursor)
+{
+ xfs_attr_list_context_t context;
+ struct attrlist *alist;
+ int error;
+
+ /*
+ * Validate the cursor.
+ */
+ if (cursor->pad1 || cursor->pad2)
+ return(XFS_ERROR(EINVAL));
+ if ((cursor->initted == 0) &&
+ (cursor->hashval || cursor->blkno || cursor->offset))
+ return XFS_ERROR(EINVAL);
+
+ /*
+ * Check for a properly aligned buffer.
+ */
+ if (((long)buffer) & (sizeof(int)-1))
+ return XFS_ERROR(EFAULT);
+ if (flags & ATTR_KERNOVAL)
+ bufsize = 0;
+
+ /*
+ * Initialize the output buffer.
+ */
+ memset(&context, 0, sizeof(context));
+ context.dp = dp;
+ context.cursor = cursor;
+ context.resynch = 1;
+ context.flags = flags;
+ context.alist = buffer;
+ context.bufsize = (bufsize & ~(sizeof(int)-1)); /* align */
+ context.firstu = context.bufsize;
+ context.put_listent = xfs_attr_put_listent;
+
+ alist = (struct attrlist *)context.alist;
+ alist->al_count = 0;
+ alist->al_more = 0;
+ alist->al_offset[0] = context.bufsize;
+
+ error = xfs_attr_list_int(&context);
+ ASSERT(error >= 0);
+ return error;
+}
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
new file mode 100644
index 00000000000..b5adfecbb8e
--- /dev/null
+++ b/fs/xfs/xfs_attr_remote.c
@@ -0,0 +1,628 @@
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_trans.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_remote.h"
+#include "xfs_trans_space.h"
+#include "xfs_trace.h"
+#include "xfs_cksum.h"
+#include "xfs_buf_item.h"
+#include "xfs_error.h"
+
+#define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */
+
+/*
+ * Each contiguous block has a header, so it is not just a simple attribute
+ * length to FSB conversion.
+ */
+int
+xfs_attr3_rmt_blocks(
+ struct xfs_mount *mp,
+ int attrlen)
+{
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ int buflen = XFS_ATTR3_RMT_BUF_SPACE(mp, mp->m_sb.sb_blocksize);
+ return (attrlen + buflen - 1) / buflen;
+ }
+ return XFS_B_TO_FSB(mp, attrlen);
+}
+
+/*
+ * Checking of the remote attribute header is split into two parts. The verifier
+ * does CRC, location and bounds checking, the unpacking function checks the
+ * attribute parameters and owner.
+ */
+static bool
+xfs_attr3_rmt_hdr_ok(
+ void *ptr,
+ xfs_ino_t ino,
+ uint32_t offset,
+ uint32_t size,
+ xfs_daddr_t bno)
+{
+ struct xfs_attr3_rmt_hdr *rmt = ptr;
+
+ if (bno != be64_to_cpu(rmt->rm_blkno))
+ return false;
+ if (offset != be32_to_cpu(rmt->rm_offset))
+ return false;
+ if (size != be32_to_cpu(rmt->rm_bytes))
+ return false;
+ if (ino != be64_to_cpu(rmt->rm_owner))
+ return false;
+
+ /* ok */
+ return true;
+}
+
+static bool
+xfs_attr3_rmt_verify(
+ struct xfs_mount *mp,
+ void *ptr,
+ int fsbsize,
+ xfs_daddr_t bno)
+{
+ struct xfs_attr3_rmt_hdr *rmt = ptr;
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return false;
+ if (rmt->rm_magic != cpu_to_be32(XFS_ATTR3_RMT_MAGIC))
+ return false;
+ if (!uuid_equal(&rmt->rm_uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(rmt->rm_blkno) != bno)
+ return false;
+ if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt))
+ return false;
+ if (be32_to_cpu(rmt->rm_offset) +
+ be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX)
+ return false;
+ if (rmt->rm_owner == 0)
+ return false;
+
+ return true;
+}
+
+static void
+xfs_attr3_rmt_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ char *ptr;
+ int len;
+ xfs_daddr_t bno;
+ int blksize = mp->m_attr_geo->blksize;
+
+ /* no verification of non-crc buffers */
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ ptr = bp->b_addr;
+ bno = bp->b_bn;
+ len = BBTOB(bp->b_length);
+ ASSERT(len >= blksize);
+
+ while (len > 0) {
+ if (!xfs_verify_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF)) {
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ break;
+ }
+ if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ break;
+ }
+ len -= blksize;
+ ptr += blksize;
+ bno += BTOBB(blksize);
+ }
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+ else
+ ASSERT(len == 0);
+}
+
+static void
+xfs_attr3_rmt_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+ char *ptr;
+ int len;
+ xfs_daddr_t bno;
+ int blksize = mp->m_attr_geo->blksize;
+
+ /* no verification of non-crc buffers */
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ ptr = bp->b_addr;
+ bno = bp->b_bn;
+ len = BBTOB(bp->b_length);
+ ASSERT(len >= blksize);
+
+ while (len > 0) {
+ if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+ if (bip) {
+ struct xfs_attr3_rmt_hdr *rmt;
+
+ rmt = (struct xfs_attr3_rmt_hdr *)ptr;
+ rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+ }
+ xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
+
+ len -= blksize;
+ ptr += blksize;
+ bno += BTOBB(blksize);
+ }
+ ASSERT(len == 0);
+}
+
+const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = {
+ .verify_read = xfs_attr3_rmt_read_verify,
+ .verify_write = xfs_attr3_rmt_write_verify,
+};
+
+STATIC int
+xfs_attr3_rmt_hdr_set(
+ struct xfs_mount *mp,
+ void *ptr,
+ xfs_ino_t ino,
+ uint32_t offset,
+ uint32_t size,
+ xfs_daddr_t bno)
+{
+ struct xfs_attr3_rmt_hdr *rmt = ptr;
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return 0;
+
+ rmt->rm_magic = cpu_to_be32(XFS_ATTR3_RMT_MAGIC);
+ rmt->rm_offset = cpu_to_be32(offset);
+ rmt->rm_bytes = cpu_to_be32(size);
+ uuid_copy(&rmt->rm_uuid, &mp->m_sb.sb_uuid);
+ rmt->rm_owner = cpu_to_be64(ino);
+ rmt->rm_blkno = cpu_to_be64(bno);
+
+ return sizeof(struct xfs_attr3_rmt_hdr);
+}
+
+/*
+ * Helper functions to copy attribute data in and out of the one disk extents
+ */
+STATIC int
+xfs_attr_rmtval_copyout(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ xfs_ino_t ino,
+ int *offset,
+ int *valuelen,
+ __uint8_t **dst)
+{
+ char *src = bp->b_addr;
+ xfs_daddr_t bno = bp->b_bn;
+ int len = BBTOB(bp->b_length);
+ int blksize = mp->m_attr_geo->blksize;
+
+ ASSERT(len >= blksize);
+
+ while (len > 0 && *valuelen > 0) {
+ int hdr_size = 0;
+ int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
+
+ byte_cnt = min(*valuelen, byte_cnt);
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ if (!xfs_attr3_rmt_hdr_ok(src, ino, *offset,
+ byte_cnt, bno)) {
+ xfs_alert(mp,
+"remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
+ bno, *offset, byte_cnt, ino);
+ return EFSCORRUPTED;
+ }
+ hdr_size = sizeof(struct xfs_attr3_rmt_hdr);
+ }
+
+ memcpy(*dst, src + hdr_size, byte_cnt);
+
+ /* roll buffer forwards */
+ len -= blksize;
+ src += blksize;
+ bno += BTOBB(blksize);
+
+ /* roll attribute data forwards */
+ *valuelen -= byte_cnt;
+ *dst += byte_cnt;
+ *offset += byte_cnt;
+ }
+ return 0;
+}
+
+STATIC void
+xfs_attr_rmtval_copyin(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ xfs_ino_t ino,
+ int *offset,
+ int *valuelen,
+ __uint8_t **src)
+{
+ char *dst = bp->b_addr;
+ xfs_daddr_t bno = bp->b_bn;
+ int len = BBTOB(bp->b_length);
+ int blksize = mp->m_attr_geo->blksize;
+
+ ASSERT(len >= blksize);
+
+ while (len > 0 && *valuelen > 0) {
+ int hdr_size;
+ int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
+
+ byte_cnt = min(*valuelen, byte_cnt);
+ hdr_size = xfs_attr3_rmt_hdr_set(mp, dst, ino, *offset,
+ byte_cnt, bno);
+
+ memcpy(dst + hdr_size, *src, byte_cnt);
+
+ /*
+ * If this is the last block, zero the remainder of it.
+ * Check that we are actually the last block, too.
+ */
+ if (byte_cnt + hdr_size < blksize) {
+ ASSERT(*valuelen - byte_cnt == 0);
+ ASSERT(len == blksize);
+ memset(dst + hdr_size + byte_cnt, 0,
+ blksize - hdr_size - byte_cnt);
+ }
+
+ /* roll buffer forwards */
+ len -= blksize;
+ dst += blksize;
+ bno += BTOBB(blksize);
+
+ /* roll attribute data forwards */
+ *valuelen -= byte_cnt;
+ *src += byte_cnt;
+ *offset += byte_cnt;
+ }
+}
+
+/*
+ * Read the value associated with an attribute from the out-of-line buffer
+ * that we stored it in.
+ */
+int
+xfs_attr_rmtval_get(
+ struct xfs_da_args *args)
+{
+ struct xfs_bmbt_irec map[ATTR_RMTVALUE_MAPSIZE];
+ struct xfs_mount *mp = args->dp->i_mount;
+ struct xfs_buf *bp;
+ xfs_dablk_t lblkno = args->rmtblkno;
+ __uint8_t *dst = args->value;
+ int valuelen;
+ int nmap;
+ int error;
+ int blkcnt = args->rmtblkcnt;
+ int i;
+ int offset = 0;
+
+ trace_xfs_attr_rmtval_get(args);
+
+ ASSERT(!(args->flags & ATTR_KERNOVAL));
+ ASSERT(args->rmtvaluelen == args->valuelen);
+
+ valuelen = args->rmtvaluelen;
+ while (valuelen > 0) {
+ nmap = ATTR_RMTVALUE_MAPSIZE;
+ error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
+ blkcnt, map, &nmap,
+ XFS_BMAPI_ATTRFORK);
+ if (error)
+ return error;
+ ASSERT(nmap >= 1);
+
+ for (i = 0; (i < nmap) && (valuelen > 0); i++) {
+ xfs_daddr_t dblkno;
+ int dblkcnt;
+
+ ASSERT((map[i].br_startblock != DELAYSTARTBLOCK) &&
+ (map[i].br_startblock != HOLESTARTBLOCK));
+ dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
+ dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
+ error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
+ dblkno, dblkcnt, 0, &bp,
+ &xfs_attr3_rmt_buf_ops);
+ if (error)
+ return error;
+
+ error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
+ &offset, &valuelen,
+ &dst);
+ xfs_buf_relse(bp);
+ if (error)
+ return error;
+
+ /* roll attribute extent map forwards */
+ lblkno += map[i].br_blockcount;
+ blkcnt -= map[i].br_blockcount;
+ }
+ }
+ ASSERT(valuelen == 0);
+ return 0;
+}
+
+/*
+ * Write the value associated with an attribute into the out-of-line buffer
+ * that we have defined for it.
+ */
+int
+xfs_attr_rmtval_set(
+ struct xfs_da_args *args)
+{
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_bmbt_irec map;
+ xfs_dablk_t lblkno;
+ xfs_fileoff_t lfileoff = 0;
+ __uint8_t *src = args->value;
+ int blkcnt;
+ int valuelen;
+ int nmap;
+ int error;
+ int offset = 0;
+
+ trace_xfs_attr_rmtval_set(args);
+
+ /*
+ * Find a "hole" in the attribute address space large enough for
+ * us to drop the new attribute's value into. Because CRC enable
+ * attributes have headers, we can't just do a straight byte to FSB
+ * conversion and have to take the header space into account.
+ */
+ blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen);
+ error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
+ XFS_ATTR_FORK);
+ if (error)
+ return error;
+
+ args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff;
+ args->rmtblkcnt = blkcnt;
+
+ /*
+ * Roll through the "value", allocating blocks on disk as required.
+ */
+ while (blkcnt > 0) {
+ int committed;
+
+ /*
+ * Allocate a single extent, up to the size of the value.
+ */
+ xfs_bmap_init(args->flist, args->firstblock);
+ nmap = 1;
+ error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
+ blkcnt,
+ XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
+ args->firstblock, args->total, &map, &nmap,
+ args->flist);
+ if (!error) {
+ error = xfs_bmap_finish(&args->trans, args->flist,
+ &committed);
+ }
+ if (error) {
+ ASSERT(committed);
+ args->trans = NULL;
+ xfs_bmap_cancel(args->flist);
+ return(error);
+ }
+
+ /*
+ * bmap_finish() may have committed the last trans and started
+ * a new one. We need the inode to be in all transactions.
+ */
+ if (committed)
+ xfs_trans_ijoin(args->trans, dp, 0);
+
+ ASSERT(nmap == 1);
+ ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
+ (map.br_startblock != HOLESTARTBLOCK));
+ lblkno += map.br_blockcount;
+ blkcnt -= map.br_blockcount;
+
+ /*
+ * Start the next trans in the chain.
+ */
+ error = xfs_trans_roll(&args->trans, dp);
+ if (error)
+ return (error);
+ }
+
+ /*
+ * Roll through the "value", copying the attribute value to the
+ * already-allocated blocks. Blocks are written synchronously
+ * so that we can know they are all on disk before we turn off
+ * the INCOMPLETE flag.
+ */
+ lblkno = args->rmtblkno;
+ blkcnt = args->rmtblkcnt;
+ valuelen = args->rmtvaluelen;
+ while (valuelen > 0) {
+ struct xfs_buf *bp;
+ xfs_daddr_t dblkno;
+ int dblkcnt;
+
+ ASSERT(blkcnt > 0);
+
+ xfs_bmap_init(args->flist, args->firstblock);
+ nmap = 1;
+ error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
+ blkcnt, &map, &nmap,
+ XFS_BMAPI_ATTRFORK);
+ if (error)
+ return(error);
+ ASSERT(nmap == 1);
+ ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
+ (map.br_startblock != HOLESTARTBLOCK));
+
+ dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
+ dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
+
+ bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, 0);
+ if (!bp)
+ return ENOMEM;
+ bp->b_ops = &xfs_attr3_rmt_buf_ops;
+
+ xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
+ &valuelen, &src);
+
+ error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */
+ xfs_buf_relse(bp);
+ if (error)
+ return error;
+
+
+ /* roll attribute extent map forwards */
+ lblkno += map.br_blockcount;
+ blkcnt -= map.br_blockcount;
+ }
+ ASSERT(valuelen == 0);
+ return 0;
+}
+
+/*
+ * Remove the value associated with an attribute by deleting the
+ * out-of-line buffer that it is stored on.
+ */
+int
+xfs_attr_rmtval_remove(
+ struct xfs_da_args *args)
+{
+ struct xfs_mount *mp = args->dp->i_mount;
+ xfs_dablk_t lblkno;
+ int blkcnt;
+ int error;
+ int done;
+
+ trace_xfs_attr_rmtval_remove(args);
+
+ /*
+ * Roll through the "value", invalidating the attribute value's blocks.
+ */
+ lblkno = args->rmtblkno;
+ blkcnt = args->rmtblkcnt;
+ while (blkcnt > 0) {
+ struct xfs_bmbt_irec map;
+ struct xfs_buf *bp;
+ xfs_daddr_t dblkno;
+ int dblkcnt;
+ int nmap;
+
+ /*
+ * Try to remember where we decided to put the value.
+ */
+ nmap = 1;
+ error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
+ blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
+ if (error)
+ return(error);
+ ASSERT(nmap == 1);
+ ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
+ (map.br_startblock != HOLESTARTBLOCK));
+
+ dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
+ dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
+
+ /*
+ * If the "remote" value is in the cache, remove it.
+ */
+ bp = xfs_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
+ if (bp) {
+ xfs_buf_stale(bp);
+ xfs_buf_relse(bp);
+ bp = NULL;
+ }
+
+ lblkno += map.br_blockcount;
+ blkcnt -= map.br_blockcount;
+ }
+
+ /*
+ * Keep de-allocating extents until the remote-value region is gone.
+ */
+ lblkno = args->rmtblkno;
+ blkcnt = args->rmtblkcnt;
+ done = 0;
+ while (!done) {
+ int committed;
+
+ xfs_bmap_init(args->flist, args->firstblock);
+ error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
+ XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
+ 1, args->firstblock, args->flist,
+ &done);
+ if (!error) {
+ error = xfs_bmap_finish(&args->trans, args->flist,
+ &committed);
+ }
+ if (error) {
+ ASSERT(committed);
+ args->trans = NULL;
+ xfs_bmap_cancel(args->flist);
+ return error;
+ }
+
+ /*
+ * bmap_finish() may have committed the last trans and started
+ * a new one. We need the inode to be in all transactions.
+ */
+ if (committed)
+ xfs_trans_ijoin(args->trans, args->dp, 0);
+
+ /*
+ * Close out trans and start the next one in the chain.
+ */
+ error = xfs_trans_roll(&args->trans, args->dp);
+ if (error)
+ return (error);
+ }
+ return(0);
+}
diff --git a/fs/xfs/xfs_utils.h b/fs/xfs/xfs_attr_remote.h
index 5eeab4690cf..5a9acfa156d 100644
--- a/fs/xfs/xfs_utils.h
+++ b/fs/xfs/xfs_attr_remote.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -15,13 +15,13 @@
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
-#ifndef __XFS_UTILS_H__
-#define __XFS_UTILS_H__
+#ifndef __XFS_ATTR_REMOTE_H__
+#define __XFS_ATTR_REMOTE_H__
-extern int xfs_dir_ialloc(xfs_trans_t **, xfs_inode_t *, umode_t, xfs_nlink_t,
- xfs_dev_t, prid_t, int, xfs_inode_t **, int *);
-extern int xfs_droplink(xfs_trans_t *, xfs_inode_t *);
-extern int xfs_bumplink(xfs_trans_t *, xfs_inode_t *);
-extern void xfs_bump_ino_vers2(xfs_trans_t *, xfs_inode_t *);
+int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
-#endif /* __XFS_UTILS_H__ */
+int xfs_attr_rmtval_get(struct xfs_da_args *args);
+int xfs_attr_rmtval_set(struct xfs_da_args *args);
+int xfs_attr_rmtval_remove(struct xfs_da_args *args);
+
+#endif /* __XFS_ATTR_REMOTE_H__ */
diff --git a/fs/xfs/xfs_bit.c b/fs/xfs/xfs_bit.c
index 48228848f5a..0e8885a5964 100644
--- a/fs/xfs/xfs_bit.c
+++ b/fs/xfs/xfs_bit.c
@@ -16,10 +16,8 @@
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
+#include "xfs_log_format.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_buf_item.h"
/*
* XFS bit manipulation routines, used in non-realtime code.
diff --git a/fs/xfs/xfs_bit.h b/fs/xfs/xfs_bit.h
index f1e3c907044..e1649c0d3e0 100644
--- a/fs/xfs/xfs_bit.h
+++ b/fs/xfs/xfs_bit.h
@@ -66,8 +66,11 @@ static inline int xfs_lowbit64(__uint64_t v)
n = ffs(w);
} else { /* upper bits */
w = (__uint32_t)(v >> 32);
- if (w && (n = ffs(w)))
- n += 32;
+ if (w) {
+ n = ffs(w);
+ if (n)
+ n += 32;
+ }
}
return n - 1;
}
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 58b815ec8c9..75c3fe5f3d9 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -17,207 +17,95 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
#include "xfs_inum.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir2.h"
+#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_dir2.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
-#include "xfs_mount.h"
-#include "xfs_itable.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_extfree_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
-#include "xfs_attr_leaf.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_buf_item.h"
-#include "xfs_filestream.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
+#include "xfs_symlink.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_dinode.h"
+#include "xfs_filestream.h"
kmem_zone_t *xfs_bmap_free_item_zone;
/*
- * Prototypes for internal bmap routines.
- */
-
-#ifdef DEBUG
-STATIC void
-xfs_bmap_check_leaf_extents(
- struct xfs_btree_cur *cur,
- struct xfs_inode *ip,
- int whichfork);
-#else
-#define xfs_bmap_check_leaf_extents(cur, ip, whichfork) do { } while (0)
-#endif
-
-
-/*
- * Called from xfs_bmap_add_attrfork to handle extents format files.
- */
-STATIC int /* error */
-xfs_bmap_add_attrfork_extents(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fsblock_t *firstblock, /* first block allocated */
- xfs_bmap_free_t *flist, /* blocks to free at commit */
- int *flags); /* inode logging flags */
-
-/*
- * Called from xfs_bmap_add_attrfork to handle local format files.
- */
-STATIC int /* error */
-xfs_bmap_add_attrfork_local(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fsblock_t *firstblock, /* first block allocated */
- xfs_bmap_free_t *flist, /* blocks to free at commit */
- int *flags); /* inode logging flags */
-
-/*
- * xfs_bmap_alloc is called by xfs_bmapi to allocate an extent for a file.
- * It figures out where to ask the underlying allocator to put the new extent.
- */
-STATIC int /* error */
-xfs_bmap_alloc(
- xfs_bmalloca_t *ap); /* bmap alloc argument struct */
-
-/*
- * Transform a btree format file with only one leaf node, where the
- * extents list will fit in the inode, into an extents format file.
- * Since the file extents are already in-core, all we have to do is
- * give up the space for the btree root and pitch the leaf block.
- */
-STATIC int /* error */
-xfs_bmap_btree_to_extents(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_btree_cur_t *cur, /* btree cursor */
- int *logflagsp, /* inode logging flags */
- int whichfork); /* data or attr fork */
-
-/*
- * Remove the entry "free" from the free item list. Prev points to the
- * previous entry, unless "free" is the head of the list.
+ * Miscellaneous helper functions
*/
-STATIC void
-xfs_bmap_del_free(
- xfs_bmap_free_t *flist, /* free item list header */
- xfs_bmap_free_item_t *prev, /* previous item on list, if any */
- xfs_bmap_free_item_t *free); /* list item to be freed */
/*
- * Convert an extents-format file into a btree-format file.
- * The new file will have a root block (in the inode) and a single child block.
- */
-STATIC int /* error */
-xfs_bmap_extents_to_btree(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fsblock_t *firstblock, /* first-block-allocated */
- xfs_bmap_free_t *flist, /* blocks freed in xaction */
- xfs_btree_cur_t **curp, /* cursor returned to caller */
- int wasdel, /* converting a delayed alloc */
- int *logflagsp, /* inode logging flags */
- int whichfork); /* data or attr fork */
-
-/*
- * Convert a local file to an extents file.
- * This code is sort of bogus, since the file data needs to get
- * logged so it won't be lost. The bmap-level manipulations are ok, though.
- */
-STATIC int /* error */
-xfs_bmap_local_to_extents(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fsblock_t *firstblock, /* first block allocated in xaction */
- xfs_extlen_t total, /* total blocks needed by transaction */
- int *logflagsp, /* inode logging flags */
- int whichfork); /* data or attr fork */
-
-/*
- * Search the extents list for the inode, for the extent containing bno.
- * If bno lies in a hole, point to the next entry. If bno lies past eof,
- * *eofp will be set, and *prevp will contain the last entry (null if none).
- * Else, *lastxp will be set to the index of the found
- * entry; *gotp will contain the entry.
- */
-STATIC xfs_bmbt_rec_host_t * /* pointer to found extent entry */
-xfs_bmap_search_extents(
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fileoff_t bno, /* block number searched for */
- int whichfork, /* data or attr fork */
- int *eofp, /* out: end of file found */
- xfs_extnum_t *lastxp, /* out: last extent index */
- xfs_bmbt_irec_t *gotp, /* out: extent entry found */
- xfs_bmbt_irec_t *prevp); /* out: previous extent entry found */
-
-/*
- * Compute the worst-case number of indirect blocks that will be used
- * for ip's delayed extent of length "len".
- */
-STATIC xfs_filblks_t
-xfs_bmap_worst_indlen(
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_filblks_t len); /* delayed extent length */
-
-#ifdef DEBUG
-/*
- * Perform various validation checks on the values being returned
- * from xfs_bmapi().
+ * Compute and fill in the value of the maximum depth of a bmap btree
+ * in this filesystem. Done once, during mount.
*/
-STATIC void
-xfs_bmap_validate_ret(
- xfs_fileoff_t bno,
- xfs_filblks_t len,
- int flags,
- xfs_bmbt_irec_t *mval,
- int nmap,
- int ret_nmap);
-#else
-#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap)
-#endif /* DEBUG */
-
-STATIC int
-xfs_bmap_count_tree(
- xfs_mount_t *mp,
- xfs_trans_t *tp,
- xfs_ifork_t *ifp,
- xfs_fsblock_t blockno,
- int levelin,
- int *count);
-
-STATIC void
-xfs_bmap_count_leaves(
- xfs_ifork_t *ifp,
- xfs_extnum_t idx,
- int numrecs,
- int *count);
-
-STATIC void
-xfs_bmap_disk_count_leaves(
- struct xfs_mount *mp,
- struct xfs_btree_block *block,
- int numrecs,
- int *count);
+void
+xfs_bmap_compute_maxlevels(
+ xfs_mount_t *mp, /* file system mount structure */
+ int whichfork) /* data or attr fork */
+{
+ int level; /* btree level */
+ uint maxblocks; /* max blocks at this level */
+ uint maxleafents; /* max leaf entries possible */
+ int maxrootrecs; /* max records in root block */
+ int minleafrecs; /* min records in leaf block */
+ int minnoderecs; /* min records in node block */
+ int sz; /* root block size */
-/*
- * Bmap internal routines.
- */
+ /*
+ * The maximum number of extents in a file, hence the maximum
+ * number of leaf entries, is controlled by the type of di_nextents
+ * (a signed 32-bit number, xfs_extnum_t), or by di_anextents
+ * (a signed 16-bit number, xfs_aextnum_t).
+ *
+ * Note that we can no longer assume that if we are in ATTR1 that
+ * the fork offset of all the inodes will be
+ * (xfs_default_attroffset(ip) >> 3) because we could have mounted
+ * with ATTR2 and then mounted back with ATTR1, keeping the
+ * di_forkoff's fixed but probably at various positions. Therefore,
+ * for both ATTR1 and ATTR2 we have to assume the worst case scenario
+ * of a minimum size available.
+ */
+ if (whichfork == XFS_DATA_FORK) {
+ maxleafents = MAXEXTNUM;
+ sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
+ } else {
+ maxleafents = MAXAEXTNUM;
+ sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
+ }
+ maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
+ minleafrecs = mp->m_bmap_dmnr[0];
+ minnoderecs = mp->m_bmap_dmnr[1];
+ maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
+ for (level = 1; maxblocks > 1; level++) {
+ if (maxblocks <= maxrootrecs)
+ maxblocks = 1;
+ else
+ maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
+ }
+ mp->m_bm_maxlevels[whichfork] = level;
+}
STATIC int /* error */
xfs_bmbt_lookup_eq(
@@ -287,6 +175,834 @@ xfs_bmbt_update(
}
/*
+ * Compute the worst-case number of indirect blocks that will be used
+ * for ip's delayed extent of length "len".
+ */
+STATIC xfs_filblks_t
+xfs_bmap_worst_indlen(
+ xfs_inode_t *ip, /* incore inode pointer */
+ xfs_filblks_t len) /* delayed extent length */
+{
+ int level; /* btree level number */
+ int maxrecs; /* maximum record count at this level */
+ xfs_mount_t *mp; /* mount structure */
+ xfs_filblks_t rval; /* return value */
+
+ mp = ip->i_mount;
+ maxrecs = mp->m_bmap_dmxr[0];
+ for (level = 0, rval = 0;
+ level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
+ level++) {
+ len += maxrecs - 1;
+ do_div(len, maxrecs);
+ rval += len;
+ if (len == 1)
+ return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
+ level - 1;
+ if (level == 0)
+ maxrecs = mp->m_bmap_dmxr[1];
+ }
+ return rval;
+}
+
+/*
+ * Calculate the default attribute fork offset for newly created inodes.
+ */
+uint
+xfs_default_attroffset(
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ uint offset;
+
+ if (mp->m_sb.sb_inodesize == 256) {
+ offset = XFS_LITINO(mp, ip->i_d.di_version) -
+ XFS_BMDR_SPACE_CALC(MINABTPTRS);
+ } else {
+ offset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
+ }
+
+ ASSERT(offset < XFS_LITINO(mp, ip->i_d.di_version));
+ return offset;
+}
+
+/*
+ * Helper routine to reset inode di_forkoff field when switching
+ * attribute fork from local to extent format - we reset it where
+ * possible to make space available for inline data fork extents.
+ */
+STATIC void
+xfs_bmap_forkoff_reset(
+ xfs_inode_t *ip,
+ int whichfork)
+{
+ if (whichfork == XFS_ATTR_FORK &&
+ ip->i_d.di_format != XFS_DINODE_FMT_DEV &&
+ ip->i_d.di_format != XFS_DINODE_FMT_UUID &&
+ ip->i_d.di_format != XFS_DINODE_FMT_BTREE) {
+ uint dfl_forkoff = xfs_default_attroffset(ip) >> 3;
+
+ if (dfl_forkoff > ip->i_d.di_forkoff)
+ ip->i_d.di_forkoff = dfl_forkoff;
+ }
+}
+
+/*
+ * Debug/sanity checking code
+ */
+
+STATIC int
+xfs_bmap_sanity_check(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ int level)
+{
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+
+ if (block->bb_magic != cpu_to_be32(XFS_BMAP_CRC_MAGIC) &&
+ block->bb_magic != cpu_to_be32(XFS_BMAP_MAGIC))
+ return 0;
+
+ if (be16_to_cpu(block->bb_level) != level ||
+ be16_to_cpu(block->bb_numrecs) == 0 ||
+ be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0])
+ return 0;
+
+ return 1;
+}
+
+#ifdef DEBUG
+STATIC struct xfs_buf *
+xfs_bmap_get_bp(
+ struct xfs_btree_cur *cur,
+ xfs_fsblock_t bno)
+{
+ struct xfs_log_item_desc *lidp;
+ int i;
+
+ if (!cur)
+ return NULL;
+
+ for (i = 0; i < XFS_BTREE_MAXLEVELS; i++) {
+ if (!cur->bc_bufs[i])
+ break;
+ if (XFS_BUF_ADDR(cur->bc_bufs[i]) == bno)
+ return cur->bc_bufs[i];
+ }
+
+ /* Chase down all the log items to see if the bp is there */
+ list_for_each_entry(lidp, &cur->bc_tp->t_items, lid_trans) {
+ struct xfs_buf_log_item *bip;
+ bip = (struct xfs_buf_log_item *)lidp->lid_item;
+ if (bip->bli_item.li_type == XFS_LI_BUF &&
+ XFS_BUF_ADDR(bip->bli_buf) == bno)
+ return bip->bli_buf;
+ }
+
+ return NULL;
+}
+
+STATIC void
+xfs_check_block(
+ struct xfs_btree_block *block,
+ xfs_mount_t *mp,
+ int root,
+ short sz)
+{
+ int i, j, dmxr;
+ __be64 *pp, *thispa; /* pointer to block address */
+ xfs_bmbt_key_t *prevp, *keyp;
+
+ ASSERT(be16_to_cpu(block->bb_level) > 0);
+
+ prevp = NULL;
+ for( i = 1; i <= xfs_btree_get_numrecs(block); i++) {
+ dmxr = mp->m_bmap_dmxr[0];
+ keyp = XFS_BMBT_KEY_ADDR(mp, block, i);
+
+ if (prevp) {
+ ASSERT(be64_to_cpu(prevp->br_startoff) <
+ be64_to_cpu(keyp->br_startoff));
+ }
+ prevp = keyp;
+
+ /*
+ * Compare the block numbers to see if there are dups.
+ */
+ if (root)
+ pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, i, sz);
+ else
+ pp = XFS_BMBT_PTR_ADDR(mp, block, i, dmxr);
+
+ for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) {
+ if (root)
+ thispa = XFS_BMAP_BROOT_PTR_ADDR(mp, block, j, sz);
+ else
+ thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
+ if (*thispa == *pp) {
+ xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld",
+ __func__, j, i,
+ (unsigned long long)be64_to_cpu(*thispa));
+ panic("%s: ptrs are equal in node\n",
+ __func__);
+ }
+ }
+ }
+}
+
+/*
+ * Check that the extents for the inode ip are in the right order in all
+ * btree leaves.
+ */
+
+STATIC void
+xfs_bmap_check_leaf_extents(
+ xfs_btree_cur_t *cur, /* btree cursor or null */
+ xfs_inode_t *ip, /* incore inode pointer */
+ int whichfork) /* data or attr fork */
+{
+ struct xfs_btree_block *block; /* current btree block */
+ xfs_fsblock_t bno; /* block # of "block" */
+ xfs_buf_t *bp; /* buffer for "block" */
+ int error; /* error return value */
+ xfs_extnum_t i=0, j; /* index into the extents list */
+ xfs_ifork_t *ifp; /* fork structure */
+ int level; /* btree level, for checking */
+ xfs_mount_t *mp; /* file system mount structure */
+ __be64 *pp; /* pointer to block address */
+ xfs_bmbt_rec_t *ep; /* pointer to current extent */
+ xfs_bmbt_rec_t last = {0, 0}; /* last extent in prev block */
+ xfs_bmbt_rec_t *nextp; /* pointer to next extent */
+ int bp_release = 0;
+
+ if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) {
+ return;
+ }
+
+ bno = NULLFSBLOCK;
+ mp = ip->i_mount;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ block = ifp->if_broot;
+ /*
+ * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
+ */
+ level = be16_to_cpu(block->bb_level);
+ ASSERT(level > 0);
+ xfs_check_block(block, mp, 1, ifp->if_broot_bytes);
+ pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
+ bno = be64_to_cpu(*pp);
+
+ ASSERT(bno != NULLDFSBNO);
+ ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
+ ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+
+ /*
+ * Go down the tree until leaf level is reached, following the first
+ * pointer (leftmost) at each level.
+ */
+ while (level-- > 0) {
+ /* See if buf is in cur first */
+ bp_release = 0;
+ bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
+ if (!bp) {
+ bp_release = 1;
+ error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
+ XFS_BMAP_BTREE_REF,
+ &xfs_bmbt_buf_ops);
+ if (error)
+ goto error_norelse;
+ }
+ block = XFS_BUF_TO_BLOCK(bp);
+ XFS_WANT_CORRUPTED_GOTO(
+ xfs_bmap_sanity_check(mp, bp, level),
+ error0);
+ if (level == 0)
+ break;
+
+ /*
+ * Check this block for basic sanity (increasing keys and
+ * no duplicate blocks).
+ */
+
+ xfs_check_block(block, mp, 0, 0);
+ pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
+ bno = be64_to_cpu(*pp);
+ XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
+ if (bp_release) {
+ bp_release = 0;
+ xfs_trans_brelse(NULL, bp);
+ }
+ }
+
+ /*
+ * Here with bp and block set to the leftmost leaf node in the tree.
+ */
+ i = 0;
+
+ /*
+ * Loop over all leaf nodes checking that all extents are in the right order.
+ */
+ for (;;) {
+ xfs_fsblock_t nextbno;
+ xfs_extnum_t num_recs;
+
+
+ num_recs = xfs_btree_get_numrecs(block);
+
+ /*
+ * Read-ahead the next leaf block, if any.
+ */
+
+ nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
+
+ /*
+ * Check all the extents to make sure they are OK.
+ * If we had a previous block, the last entry should
+ * conform with the first entry in this one.
+ */
+
+ ep = XFS_BMBT_REC_ADDR(mp, block, 1);
+ if (i) {
+ ASSERT(xfs_bmbt_disk_get_startoff(&last) +
+ xfs_bmbt_disk_get_blockcount(&last) <=
+ xfs_bmbt_disk_get_startoff(ep));
+ }
+ for (j = 1; j < num_recs; j++) {
+ nextp = XFS_BMBT_REC_ADDR(mp, block, j + 1);
+ ASSERT(xfs_bmbt_disk_get_startoff(ep) +
+ xfs_bmbt_disk_get_blockcount(ep) <=
+ xfs_bmbt_disk_get_startoff(nextp));
+ ep = nextp;
+ }
+
+ last = *ep;
+ i += num_recs;
+ if (bp_release) {
+ bp_release = 0;
+ xfs_trans_brelse(NULL, bp);
+ }
+ bno = nextbno;
+ /*
+ * If we've reached the end, stop.
+ */
+ if (bno == NULLFSBLOCK)
+ break;
+
+ bp_release = 0;
+ bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
+ if (!bp) {
+ bp_release = 1;
+ error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
+ XFS_BMAP_BTREE_REF,
+ &xfs_bmbt_buf_ops);
+ if (error)
+ goto error_norelse;
+ }
+ block = XFS_BUF_TO_BLOCK(bp);
+ }
+ if (bp_release) {
+ bp_release = 0;
+ xfs_trans_brelse(NULL, bp);
+ }
+ return;
+
+error0:
+ xfs_warn(mp, "%s: at error0", __func__);
+ if (bp_release)
+ xfs_trans_brelse(NULL, bp);
+error_norelse:
+ xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
+ __func__, i);
+ panic("%s: CORRUPTED BTREE OR SOMETHING", __func__);
+ return;
+}
+
+/*
+ * Add bmap trace insert entries for all the contents of the extent records.
+ */
+void
+xfs_bmap_trace_exlist(
+ xfs_inode_t *ip, /* incore inode pointer */
+ xfs_extnum_t cnt, /* count of entries in the list */
+ int whichfork, /* data or attr fork */
+ unsigned long caller_ip)
+{
+ xfs_extnum_t idx; /* extent record index */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ int state = 0;
+
+ if (whichfork == XFS_ATTR_FORK)
+ state |= BMAP_ATTRFORK;
+
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ ASSERT(cnt == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
+ for (idx = 0; idx < cnt; idx++)
+ trace_xfs_extlist(ip, idx, whichfork, caller_ip);
+}
+
+/*
+ * Validate that the bmbt_irecs being returned from bmapi are valid
+ * given the caller's original parameters. Specifically check the
+ * ranges of the returned irecs to ensure that they only extend beyond
+ * the given parameters if the XFS_BMAPI_ENTIRE flag was set.
+ */
+STATIC void
+xfs_bmap_validate_ret(
+ xfs_fileoff_t bno,
+ xfs_filblks_t len,
+ int flags,
+ xfs_bmbt_irec_t *mval,
+ int nmap,
+ int ret_nmap)
+{
+ int i; /* index to map values */
+
+ ASSERT(ret_nmap <= nmap);
+
+ for (i = 0; i < ret_nmap; i++) {
+ ASSERT(mval[i].br_blockcount > 0);
+ if (!(flags & XFS_BMAPI_ENTIRE)) {
+ ASSERT(mval[i].br_startoff >= bno);
+ ASSERT(mval[i].br_blockcount <= len);
+ ASSERT(mval[i].br_startoff + mval[i].br_blockcount <=
+ bno + len);
+ } else {
+ ASSERT(mval[i].br_startoff < bno + len);
+ ASSERT(mval[i].br_startoff + mval[i].br_blockcount >
+ bno);
+ }
+ ASSERT(i == 0 ||
+ mval[i - 1].br_startoff + mval[i - 1].br_blockcount ==
+ mval[i].br_startoff);
+ ASSERT(mval[i].br_startblock != DELAYSTARTBLOCK &&
+ mval[i].br_startblock != HOLESTARTBLOCK);
+ ASSERT(mval[i].br_state == XFS_EXT_NORM ||
+ mval[i].br_state == XFS_EXT_UNWRITTEN);
+ }
+}
+
+#else
+#define xfs_bmap_check_leaf_extents(cur, ip, whichfork) do { } while (0)
+#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap)
+#endif /* DEBUG */
+
+/*
+ * bmap free list manipulation functions
+ */
+
+/*
+ * Add the extent to the list of extents to be free at transaction end.
+ * The list is maintained sorted (by block number).
+ */
+void
+xfs_bmap_add_free(
+ xfs_fsblock_t bno, /* fs block number of extent */
+ xfs_filblks_t len, /* length of extent */
+ xfs_bmap_free_t *flist, /* list of extents */
+ xfs_mount_t *mp) /* mount point structure */
+{
+ xfs_bmap_free_item_t *cur; /* current (next) element */
+ xfs_bmap_free_item_t *new; /* new element */
+ xfs_bmap_free_item_t *prev; /* previous element */
+#ifdef DEBUG
+ xfs_agnumber_t agno;
+ xfs_agblock_t agbno;
+
+ ASSERT(bno != NULLFSBLOCK);
+ ASSERT(len > 0);
+ ASSERT(len <= MAXEXTLEN);
+ ASSERT(!isnullstartblock(bno));
+ agno = XFS_FSB_TO_AGNO(mp, bno);
+ agbno = XFS_FSB_TO_AGBNO(mp, bno);
+ ASSERT(agno < mp->m_sb.sb_agcount);
+ ASSERT(agbno < mp->m_sb.sb_agblocks);
+ ASSERT(len < mp->m_sb.sb_agblocks);
+ ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
+#endif
+ ASSERT(xfs_bmap_free_item_zone != NULL);
+ new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
+ new->xbfi_startblock = bno;
+ new->xbfi_blockcount = (xfs_extlen_t)len;
+ for (prev = NULL, cur = flist->xbf_first;
+ cur != NULL;
+ prev = cur, cur = cur->xbfi_next) {
+ if (cur->xbfi_startblock >= bno)
+ break;
+ }
+ if (prev)
+ prev->xbfi_next = new;
+ else
+ flist->xbf_first = new;
+ new->xbfi_next = cur;
+ flist->xbf_count++;
+}
+
+/*
+ * Remove the entry "free" from the free item list. Prev points to the
+ * previous entry, unless "free" is the head of the list.
+ */
+void
+xfs_bmap_del_free(
+ xfs_bmap_free_t *flist, /* free item list header */
+ xfs_bmap_free_item_t *prev, /* previous item on list, if any */
+ xfs_bmap_free_item_t *free) /* list item to be freed */
+{
+ if (prev)
+ prev->xbfi_next = free->xbfi_next;
+ else
+ flist->xbf_first = free->xbfi_next;
+ flist->xbf_count--;
+ kmem_zone_free(xfs_bmap_free_item_zone, free);
+}
+
+/*
+ * Free up any items left in the list.
+ */
+void
+xfs_bmap_cancel(
+ xfs_bmap_free_t *flist) /* list of bmap_free_items */
+{
+ xfs_bmap_free_item_t *free; /* free list item */
+ xfs_bmap_free_item_t *next;
+
+ if (flist->xbf_count == 0)
+ return;
+ ASSERT(flist->xbf_first != NULL);
+ for (free = flist->xbf_first; free; free = next) {
+ next = free->xbfi_next;
+ xfs_bmap_del_free(flist, NULL, free);
+ }
+ ASSERT(flist->xbf_count == 0);
+}
+
+/*
+ * Inode fork format manipulation functions
+ */
+
+/*
+ * Transform a btree format file with only one leaf node, where the
+ * extents list will fit in the inode, into an extents format file.
+ * Since the file extents are already in-core, all we have to do is
+ * give up the space for the btree root and pitch the leaf block.
+ */
+STATIC int /* error */
+xfs_bmap_btree_to_extents(
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_inode_t *ip, /* incore inode pointer */
+ xfs_btree_cur_t *cur, /* btree cursor */
+ int *logflagsp, /* inode logging flags */
+ int whichfork) /* data or attr fork */
+{
+ /* REFERENCED */
+ struct xfs_btree_block *cblock;/* child btree block */
+ xfs_fsblock_t cbno; /* child block number */
+ xfs_buf_t *cbp; /* child block's buffer */
+ int error; /* error return value */
+ xfs_ifork_t *ifp; /* inode fork data */
+ xfs_mount_t *mp; /* mount point structure */
+ __be64 *pp; /* ptr to block address */
+ struct xfs_btree_block *rblock;/* root btree block */
+
+ mp = ip->i_mount;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+ ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
+ rblock = ifp->if_broot;
+ ASSERT(be16_to_cpu(rblock->bb_level) == 1);
+ ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
+ ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0) == 1);
+ pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
+ cbno = be64_to_cpu(*pp);
+ *logflagsp = 0;
+#ifdef DEBUG
+ if ((error = xfs_btree_check_lptr(cur, cbno, 1)))
+ return error;
+#endif
+ error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp, XFS_BMAP_BTREE_REF,
+ &xfs_bmbt_buf_ops);
+ if (error)
+ return error;
+ cblock = XFS_BUF_TO_BLOCK(cbp);
+ if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
+ return error;
+ xfs_bmap_add_free(cbno, 1, cur->bc_private.b.flist, mp);
+ ip->i_d.di_nblocks--;
+ xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
+ xfs_trans_binval(tp, cbp);
+ if (cur->bc_bufs[0] == cbp)
+ cur->bc_bufs[0] = NULL;
+ xfs_iroot_realloc(ip, -1, whichfork);
+ ASSERT(ifp->if_broot == NULL);
+ ASSERT((ifp->if_flags & XFS_IFBROOT) == 0);
+ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+ *logflagsp = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
+ return 0;
+}
+
+/*
+ * Convert an extents-format file into a btree-format file.
+ * The new file will have a root block (in the inode) and a single child block.
+ */
+STATIC int /* error */
+xfs_bmap_extents_to_btree(
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_inode_t *ip, /* incore inode pointer */
+ xfs_fsblock_t *firstblock, /* first-block-allocated */
+ xfs_bmap_free_t *flist, /* blocks freed in xaction */
+ xfs_btree_cur_t **curp, /* cursor returned to caller */
+ int wasdel, /* converting a delayed alloc */
+ int *logflagsp, /* inode logging flags */
+ int whichfork) /* data or attr fork */
+{
+ struct xfs_btree_block *ablock; /* allocated (child) bt block */
+ xfs_buf_t *abp; /* buffer for ablock */
+ xfs_alloc_arg_t args; /* allocation arguments */
+ xfs_bmbt_rec_t *arp; /* child record pointer */
+ struct xfs_btree_block *block; /* btree root block */
+ xfs_btree_cur_t *cur; /* bmap btree cursor */
+ xfs_bmbt_rec_host_t *ep; /* extent record pointer */
+ int error; /* error return value */
+ xfs_extnum_t i, cnt; /* extent record index */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ xfs_bmbt_key_t *kp; /* root block key pointer */
+ xfs_mount_t *mp; /* mount structure */
+ xfs_extnum_t nextents; /* number of file extents */
+ xfs_bmbt_ptr_t *pp; /* root block address pointer */
+
+ mp = ip->i_mount;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS);
+
+ /*
+ * Make space in the inode incore.
+ */
+ xfs_iroot_realloc(ip, 1, whichfork);
+ ifp->if_flags |= XFS_IFBROOT;
+
+ /*
+ * Fill in the root.
+ */
+ block = ifp->if_broot;
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
+ XFS_BMAP_CRC_MAGIC, 1, 1, ip->i_ino,
+ XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
+ else
+ xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
+ XFS_BMAP_MAGIC, 1, 1, ip->i_ino,
+ XFS_BTREE_LONG_PTRS);
+
+ /*
+ * Need a cursor. Can't allocate until bb_level is filled in.
+ */
+ cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
+ cur->bc_private.b.firstblock = *firstblock;
+ cur->bc_private.b.flist = flist;
+ cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
+ /*
+ * Convert to a btree with two levels, one record in root.
+ */
+ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE);
+ memset(&args, 0, sizeof(args));
+ args.tp = tp;
+ args.mp = mp;
+ args.firstblock = *firstblock;
+ if (*firstblock == NULLFSBLOCK) {
+ args.type = XFS_ALLOCTYPE_START_BNO;
+ args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
+ } else if (flist->xbf_low) {
+ args.type = XFS_ALLOCTYPE_START_BNO;
+ args.fsbno = *firstblock;
+ } else {
+ args.type = XFS_ALLOCTYPE_NEAR_BNO;
+ args.fsbno = *firstblock;
+ }
+ args.minlen = args.maxlen = args.prod = 1;
+ args.wasdel = wasdel;
+ *logflagsp = 0;
+ if ((error = xfs_alloc_vextent(&args))) {
+ xfs_iroot_realloc(ip, -1, whichfork);
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ return error;
+ }
+ /*
+ * Allocation can't fail, the space was reserved.
+ */
+ ASSERT(args.fsbno != NULLFSBLOCK);
+ ASSERT(*firstblock == NULLFSBLOCK ||
+ args.agno == XFS_FSB_TO_AGNO(mp, *firstblock) ||
+ (flist->xbf_low &&
+ args.agno > XFS_FSB_TO_AGNO(mp, *firstblock)));
+ *firstblock = cur->bc_private.b.firstblock = args.fsbno;
+ cur->bc_private.b.allocated++;
+ ip->i_d.di_nblocks++;
+ xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
+ abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
+ /*
+ * Fill in the child block.
+ */
+ abp->b_ops = &xfs_bmbt_buf_ops;
+ ablock = XFS_BUF_TO_BLOCK(abp);
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ xfs_btree_init_block_int(mp, ablock, abp->b_bn,
+ XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino,
+ XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
+ else
+ xfs_btree_init_block_int(mp, ablock, abp->b_bn,
+ XFS_BMAP_MAGIC, 0, 0, ip->i_ino,
+ XFS_BTREE_LONG_PTRS);
+
+ arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
+ nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+ for (cnt = i = 0; i < nextents; i++) {
+ ep = xfs_iext_get_ext(ifp, i);
+ if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) {
+ arp->l0 = cpu_to_be64(ep->l0);
+ arp->l1 = cpu_to_be64(ep->l1);
+ arp++; cnt++;
+ }
+ }
+ ASSERT(cnt == XFS_IFORK_NEXTENTS(ip, whichfork));
+ xfs_btree_set_numrecs(ablock, cnt);
+
+ /*
+ * Fill in the root key and pointer.
+ */
+ kp = XFS_BMBT_KEY_ADDR(mp, block, 1);
+ arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
+ kp->br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(arp));
+ pp = XFS_BMBT_PTR_ADDR(mp, block, 1, xfs_bmbt_get_maxrecs(cur,
+ be16_to_cpu(block->bb_level)));
+ *pp = cpu_to_be64(args.fsbno);
+
+ /*
+ * Do all this logging at the end so that
+ * the root is at the right level.
+ */
+ xfs_btree_log_block(cur, abp, XFS_BB_ALL_BITS);
+ xfs_btree_log_recs(cur, abp, 1, be16_to_cpu(ablock->bb_numrecs));
+ ASSERT(*curp == NULL);
+ *curp = cur;
+ *logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
+ return 0;
+}
+
+/*
+ * Convert a local file to an extents file.
+ * This code is out of bounds for data forks of regular files,
+ * since the file data needs to get logged so things will stay consistent.
+ * (The bmap-level manipulations are ok, though).
+ */
+void
+xfs_bmap_local_to_extents_empty(
+ struct xfs_inode *ip,
+ int whichfork)
+{
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+
+ ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
+ ASSERT(ifp->if_bytes == 0);
+ ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0);
+
+ xfs_bmap_forkoff_reset(ip, whichfork);
+ ifp->if_flags &= ~XFS_IFINLINE;
+ ifp->if_flags |= XFS_IFEXTENTS;
+ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+}
+
+
+STATIC int /* error */
+xfs_bmap_local_to_extents(
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_inode_t *ip, /* incore inode pointer */
+ xfs_fsblock_t *firstblock, /* first block allocated in xaction */
+ xfs_extlen_t total, /* total blocks needed by transaction */
+ int *logflagsp, /* inode logging flags */
+ int whichfork,
+ void (*init_fn)(struct xfs_trans *tp,
+ struct xfs_buf *bp,
+ struct xfs_inode *ip,
+ struct xfs_ifork *ifp))
+{
+ int error = 0;
+ int flags; /* logging flags returned */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ xfs_alloc_arg_t args; /* allocation arguments */
+ xfs_buf_t *bp; /* buffer for extent block */
+ xfs_bmbt_rec_host_t *ep; /* extent record pointer */
+
+ /*
+ * We don't want to deal with the case of keeping inode data inline yet.
+ * So sending the data fork of a regular inode is invalid.
+ */
+ ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK));
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
+
+ if (!ifp->if_bytes) {
+ xfs_bmap_local_to_extents_empty(ip, whichfork);
+ flags = XFS_ILOG_CORE;
+ goto done;
+ }
+
+ flags = 0;
+ error = 0;
+ ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) ==
+ XFS_IFINLINE);
+ memset(&args, 0, sizeof(args));
+ args.tp = tp;
+ args.mp = ip->i_mount;
+ args.firstblock = *firstblock;
+ /*
+ * Allocate a block. We know we need only one, since the
+ * file currently fits in an inode.
+ */
+ if (*firstblock == NULLFSBLOCK) {
+ args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
+ args.type = XFS_ALLOCTYPE_START_BNO;
+ } else {
+ args.fsbno = *firstblock;
+ args.type = XFS_ALLOCTYPE_NEAR_BNO;
+ }
+ args.total = total;
+ args.minlen = args.maxlen = args.prod = 1;
+ error = xfs_alloc_vextent(&args);
+ if (error)
+ goto done;
+
+ /* Can't fail, the space was reserved. */
+ ASSERT(args.fsbno != NULLFSBLOCK);
+ ASSERT(args.len == 1);
+ *firstblock = args.fsbno;
+ bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
+
+ /* initialise the block and copy the data */
+ init_fn(tp, bp, ip, ifp);
+
+ /* account for the change in fork size and log everything */
+ xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
+ xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
+ xfs_bmap_local_to_extents_empty(ip, whichfork);
+ flags |= XFS_ILOG_CORE;
+
+ xfs_iext_add(ifp, 0, 1);
+ ep = xfs_iext_get_ext(ifp, 0);
+ xfs_bmbt_set_allf(ep, 0, args.fsbno, 1, XFS_EXT_NORM);
+ trace_xfs_bmap_post_update(ip, 0,
+ whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0,
+ _THIS_IP_);
+ XFS_IFORK_NEXT_SET(ip, whichfork, 1);
+ ip->i_d.di_nblocks = 1;
+ xfs_trans_mod_dquot_byino(tp, ip,
+ XFS_TRANS_DQ_BCOUNT, 1L);
+ flags |= xfs_ilog_fext(whichfork);
+
+done:
+ *logflagsp = flags;
+ return error;
+}
+
+/*
* Called from xfs_bmap_add_attrfork to handle btree format files.
*/
STATIC int /* error */
@@ -357,7 +1073,15 @@ xfs_bmap_add_attrfork_extents(
}
/*
- * Called from xfs_bmap_add_attrfork to handle local format files.
+ * Called from xfs_bmap_add_attrfork to handle local format files. Each
+ * different data fork content type needs a different callout to do the
+ * conversion. Some are basic and only require special block initialisation
+ * callouts for the data formating, others (directories) are so specialised they
+ * handle everything themselves.
+ *
+ * XXX (dgc): investigate whether directory conversion can use the generic
+ * formatting callout. It should be possible - it's just a very complex
+ * formatter.
*/
STATIC int /* error */
xfs_bmap_add_attrfork_local(
@@ -368,27 +1092,651 @@ xfs_bmap_add_attrfork_local(
int *flags) /* inode logging flags */
{
xfs_da_args_t dargs; /* args for dir/attr code */
- int error; /* error return value */
- xfs_mount_t *mp; /* mount structure pointer */
if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
return 0;
+
if (S_ISDIR(ip->i_d.di_mode)) {
- mp = ip->i_mount;
memset(&dargs, 0, sizeof(dargs));
+ dargs.geo = ip->i_mount->m_dir_geo;
dargs.dp = ip;
dargs.firstblock = firstblock;
dargs.flist = flist;
- dargs.total = mp->m_dirblkfsbs;
+ dargs.total = dargs.geo->fsbcount;
dargs.whichfork = XFS_DATA_FORK;
dargs.trans = tp;
- error = xfs_dir2_sf_to_block(&dargs);
- } else
- error = xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags,
- XFS_DATA_FORK);
+ return xfs_dir2_sf_to_block(&dargs);
+ }
+
+ if (S_ISLNK(ip->i_d.di_mode))
+ return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
+ flags, XFS_DATA_FORK,
+ xfs_symlink_local_to_remote);
+
+ /* should only be called for types that support local format data */
+ ASSERT(0);
+ return EFSCORRUPTED;
+}
+
+/*
+ * Convert inode from non-attributed to attributed.
+ * Must not be in a transaction, ip must not be locked.
+ */
+int /* error code */
+xfs_bmap_add_attrfork(
+ xfs_inode_t *ip, /* incore inode pointer */
+ int size, /* space new attribute needs */
+ int rsvd) /* xact may use reserved blks */
+{
+ xfs_fsblock_t firstblock; /* 1st block/ag allocated */
+ xfs_bmap_free_t flist; /* freed extent records */
+ xfs_mount_t *mp; /* mount structure */
+ xfs_trans_t *tp; /* transaction pointer */
+ int blks; /* space reservation */
+ int version = 1; /* superblock attr version */
+ int committed; /* xaction was committed */
+ int logflags; /* logging flags */
+ int error; /* error return value */
+ int cancel_flags = 0;
+
+ ASSERT(XFS_IFORK_Q(ip) == 0);
+
+ mp = ip->i_mount;
+ ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
+ tp = xfs_trans_alloc(mp, XFS_TRANS_ADDAFORK);
+ blks = XFS_ADDAFORK_SPACE_RES(mp);
+ if (rsvd)
+ tp->t_flags |= XFS_TRANS_RESERVE;
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_addafork, blks, 0);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ return error;
+ }
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
+ XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
+ XFS_QMOPT_RES_REGBLKS);
+ if (error)
+ goto trans_cancel;
+ cancel_flags |= XFS_TRANS_ABORT;
+ if (XFS_IFORK_Q(ip))
+ goto trans_cancel;
+ if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) {
+ /*
+ * For inodes coming from pre-6.2 filesystems.
+ */
+ ASSERT(ip->i_d.di_aformat == 0);
+ ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
+ }
+ ASSERT(ip->i_d.di_anextents == 0);
+
+ xfs_trans_ijoin(tp, ip, 0);
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+ switch (ip->i_d.di_format) {
+ case XFS_DINODE_FMT_DEV:
+ ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3;
+ break;
+ case XFS_DINODE_FMT_UUID:
+ ip->i_d.di_forkoff = roundup(sizeof(uuid_t), 8) >> 3;
+ break;
+ case XFS_DINODE_FMT_LOCAL:
+ case XFS_DINODE_FMT_EXTENTS:
+ case XFS_DINODE_FMT_BTREE:
+ ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size);
+ if (!ip->i_d.di_forkoff)
+ ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3;
+ else if (mp->m_flags & XFS_MOUNT_ATTR2)
+ version = 2;
+ break;
+ default:
+ ASSERT(0);
+ error = XFS_ERROR(EINVAL);
+ goto trans_cancel;
+ }
+
+ ASSERT(ip->i_afp == NULL);
+ ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
+ ip->i_afp->if_flags = XFS_IFEXTENTS;
+ logflags = 0;
+ xfs_bmap_init(&flist, &firstblock);
+ switch (ip->i_d.di_format) {
+ case XFS_DINODE_FMT_LOCAL:
+ error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &flist,
+ &logflags);
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
+ &flist, &logflags);
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &flist,
+ &logflags);
+ break;
+ default:
+ error = 0;
+ break;
+ }
+ if (logflags)
+ xfs_trans_log_inode(tp, ip, logflags);
+ if (error)
+ goto bmap_cancel;
+ if (!xfs_sb_version_hasattr(&mp->m_sb) ||
+ (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
+ __int64_t sbfields = 0;
+
+ spin_lock(&mp->m_sb_lock);
+ if (!xfs_sb_version_hasattr(&mp->m_sb)) {
+ xfs_sb_version_addattr(&mp->m_sb);
+ sbfields |= XFS_SB_VERSIONNUM;
+ }
+ if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) {
+ xfs_sb_version_addattr2(&mp->m_sb);
+ sbfields |= (XFS_SB_VERSIONNUM | XFS_SB_FEATURES2);
+ }
+ if (sbfields) {
+ spin_unlock(&mp->m_sb_lock);
+ xfs_mod_sb(tp, sbfields);
+ } else
+ spin_unlock(&mp->m_sb_lock);
+ }
+
+ error = xfs_bmap_finish(&tp, &flist, &committed);
+ if (error)
+ goto bmap_cancel;
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
+
+bmap_cancel:
+ xfs_bmap_cancel(&flist);
+trans_cancel:
+ xfs_trans_cancel(tp, cancel_flags);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+}
+
+/*
+ * Internal and external extent tree search functions.
+ */
+
+/*
+ * Read in the extents to if_extents.
+ * All inode fields are set up by caller, we just traverse the btree
+ * and copy the records in. If the file system cannot contain unwritten
+ * extents, the records are checked for no "state" flags.
+ */
+int /* error */
+xfs_bmap_read_extents(
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_inode_t *ip, /* incore inode */
+ int whichfork) /* data or attr fork */
+{
+ struct xfs_btree_block *block; /* current btree block */
+ xfs_fsblock_t bno; /* block # of "block" */
+ xfs_buf_t *bp; /* buffer for "block" */
+ int error; /* error return value */
+ xfs_exntfmt_t exntf; /* XFS_EXTFMT_NOSTATE, if checking */
+ xfs_extnum_t i, j; /* index into the extents list */
+ xfs_ifork_t *ifp; /* fork structure */
+ int level; /* btree level, for checking */
+ xfs_mount_t *mp; /* file system mount structure */
+ __be64 *pp; /* pointer to block address */
+ /* REFERENCED */
+ xfs_extnum_t room; /* number of entries there's room for */
+
+ bno = NULLFSBLOCK;
+ mp = ip->i_mount;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ exntf = (whichfork != XFS_DATA_FORK) ? XFS_EXTFMT_NOSTATE :
+ XFS_EXTFMT_INODE(ip);
+ block = ifp->if_broot;
+ /*
+ * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
+ */
+ level = be16_to_cpu(block->bb_level);
+ ASSERT(level > 0);
+ pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
+ bno = be64_to_cpu(*pp);
+ ASSERT(bno != NULLDFSBNO);
+ ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
+ ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+ /*
+ * Go down the tree until leaf level is reached, following the first
+ * pointer (leftmost) at each level.
+ */
+ while (level-- > 0) {
+ error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
+ XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops);
+ if (error)
+ return error;
+ block = XFS_BUF_TO_BLOCK(bp);
+ XFS_WANT_CORRUPTED_GOTO(
+ xfs_bmap_sanity_check(mp, bp, level),
+ error0);
+ if (level == 0)
+ break;
+ pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
+ bno = be64_to_cpu(*pp);
+ XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
+ xfs_trans_brelse(tp, bp);
+ }
+ /*
+ * Here with bp and block set to the leftmost leaf node in the tree.
+ */
+ room = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+ i = 0;
+ /*
+ * Loop over all leaf nodes. Copy information to the extent records.
+ */
+ for (;;) {
+ xfs_bmbt_rec_t *frp;
+ xfs_fsblock_t nextbno;
+ xfs_extnum_t num_recs;
+ xfs_extnum_t start;
+
+ num_recs = xfs_btree_get_numrecs(block);
+ if (unlikely(i + num_recs > room)) {
+ ASSERT(i + num_recs <= room);
+ xfs_warn(ip->i_mount,
+ "corrupt dinode %Lu, (btree extents).",
+ (unsigned long long) ip->i_ino);
+ XFS_CORRUPTION_ERROR("xfs_bmap_read_extents(1)",
+ XFS_ERRLEVEL_LOW, ip->i_mount, block);
+ goto error0;
+ }
+ XFS_WANT_CORRUPTED_GOTO(
+ xfs_bmap_sanity_check(mp, bp, 0),
+ error0);
+ /*
+ * Read-ahead the next leaf block, if any.
+ */
+ nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
+ if (nextbno != NULLFSBLOCK)
+ xfs_btree_reada_bufl(mp, nextbno, 1,
+ &xfs_bmbt_buf_ops);
+ /*
+ * Copy records into the extent records.
+ */
+ frp = XFS_BMBT_REC_ADDR(mp, block, 1);
+ start = i;
+ for (j = 0; j < num_recs; j++, i++, frp++) {
+ xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i);
+ trp->l0 = be64_to_cpu(frp->l0);
+ trp->l1 = be64_to_cpu(frp->l1);
+ }
+ if (exntf == XFS_EXTFMT_NOSTATE) {
+ /*
+ * Check all attribute bmap btree records and
+ * any "older" data bmap btree records for a
+ * set bit in the "extent flag" position.
+ */
+ if (unlikely(xfs_check_nostate_extents(ifp,
+ start, num_recs))) {
+ XFS_ERROR_REPORT("xfs_bmap_read_extents(2)",
+ XFS_ERRLEVEL_LOW,
+ ip->i_mount);
+ goto error0;
+ }
+ }
+ xfs_trans_brelse(tp, bp);
+ bno = nextbno;
+ /*
+ * If we've reached the end, stop.
+ */
+ if (bno == NULLFSBLOCK)
+ break;
+ error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
+ XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops);
+ if (error)
+ return error;
+ block = XFS_BUF_TO_BLOCK(bp);
+ }
+ ASSERT(i == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
+ ASSERT(i == XFS_IFORK_NEXTENTS(ip, whichfork));
+ XFS_BMAP_TRACE_EXLIST(ip, i, whichfork);
+ return 0;
+error0:
+ xfs_trans_brelse(tp, bp);
+ return XFS_ERROR(EFSCORRUPTED);
}
+
+/*
+ * Search the extent records for the entry containing block bno.
+ * If bno lies in a hole, point to the next entry. If bno lies
+ * past eof, *eofp will be set, and *prevp will contain the last
+ * entry (null if none). Else, *lastxp will be set to the index
+ * of the found entry; *gotp will contain the entry.
+ */
+STATIC xfs_bmbt_rec_host_t * /* pointer to found extent entry */
+xfs_bmap_search_multi_extents(
+ xfs_ifork_t *ifp, /* inode fork pointer */
+ xfs_fileoff_t bno, /* block number searched for */
+ int *eofp, /* out: end of file found */
+ xfs_extnum_t *lastxp, /* out: last extent index */
+ xfs_bmbt_irec_t *gotp, /* out: extent entry found */
+ xfs_bmbt_irec_t *prevp) /* out: previous extent entry found */
+{
+ xfs_bmbt_rec_host_t *ep; /* extent record pointer */
+ xfs_extnum_t lastx; /* last extent index */
+
+ /*
+ * Initialize the extent entry structure to catch access to
+ * uninitialized br_startblock field.
+ */
+ gotp->br_startoff = 0xffa5a5a5a5a5a5a5LL;
+ gotp->br_blockcount = 0xa55a5a5a5a5a5a5aLL;
+ gotp->br_state = XFS_EXT_INVALID;
+#if XFS_BIG_BLKNOS
+ gotp->br_startblock = 0xffffa5a5a5a5a5a5LL;
+#else
+ gotp->br_startblock = 0xffffa5a5;
+#endif
+ prevp->br_startoff = NULLFILEOFF;
+
+ ep = xfs_iext_bno_to_ext(ifp, bno, &lastx);
+ if (lastx > 0) {
+ xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx - 1), prevp);
+ }
+ if (lastx < (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))) {
+ xfs_bmbt_get_all(ep, gotp);
+ *eofp = 0;
+ } else {
+ if (lastx > 0) {
+ *gotp = *prevp;
+ }
+ *eofp = 1;
+ ep = NULL;
+ }
+ *lastxp = lastx;
+ return ep;
+}
+
+/*
+ * Search the extents list for the inode, for the extent containing bno.
+ * If bno lies in a hole, point to the next entry. If bno lies past eof,
+ * *eofp will be set, and *prevp will contain the last entry (null if none).
+ * Else, *lastxp will be set to the index of the found
+ * entry; *gotp will contain the entry.
+ */
+STATIC xfs_bmbt_rec_host_t * /* pointer to found extent entry */
+xfs_bmap_search_extents(
+ xfs_inode_t *ip, /* incore inode pointer */
+ xfs_fileoff_t bno, /* block number searched for */
+ int fork, /* data or attr fork */
+ int *eofp, /* out: end of file found */
+ xfs_extnum_t *lastxp, /* out: last extent index */
+ xfs_bmbt_irec_t *gotp, /* out: extent entry found */
+ xfs_bmbt_irec_t *prevp) /* out: previous extent entry found */
+{
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ xfs_bmbt_rec_host_t *ep; /* extent record pointer */
+
+ XFS_STATS_INC(xs_look_exlist);
+ ifp = XFS_IFORK_PTR(ip, fork);
+
+ ep = xfs_bmap_search_multi_extents(ifp, bno, eofp, lastxp, gotp, prevp);
+
+ if (unlikely(!(gotp->br_startblock) && (*lastxp != NULLEXTNUM) &&
+ !(XFS_IS_REALTIME_INODE(ip) && fork == XFS_DATA_FORK))) {
+ xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
+ "Access to block zero in inode %llu "
+ "start_block: %llx start_off: %llx "
+ "blkcnt: %llx extent-state: %x lastx: %x",
+ (unsigned long long)ip->i_ino,
+ (unsigned long long)gotp->br_startblock,
+ (unsigned long long)gotp->br_startoff,
+ (unsigned long long)gotp->br_blockcount,
+ gotp->br_state, *lastxp);
+ *lastxp = NULLEXTNUM;
+ *eofp = 1;
+ return NULL;
+ }
+ return ep;
+}
+
+/*
+ * Returns the file-relative block number of the first unused block(s)
+ * in the file with at least "len" logically contiguous blocks free.
+ * This is the lowest-address hole if the file has holes, else the first block
+ * past the end of file.
+ * Return 0 if the file is currently local (in-inode).
+ */
+int /* error */
+xfs_bmap_first_unused(
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_inode_t *ip, /* incore inode */
+ xfs_extlen_t len, /* size of hole to find */
+ xfs_fileoff_t *first_unused, /* unused block */
+ int whichfork) /* data or attr fork */
+{
+ int error; /* error return value */
+ int idx; /* extent record index */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ xfs_fileoff_t lastaddr; /* last block number seen */
+ xfs_fileoff_t lowest; /* lowest useful block */
+ xfs_fileoff_t max; /* starting useful block */
+ xfs_fileoff_t off; /* offset for this block */
+ xfs_extnum_t nextents; /* number of extent entries */
+
+ ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE ||
+ XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ||
+ XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
+ if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
+ *first_unused = 0;
+ return 0;
+ }
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ if (!(ifp->if_flags & XFS_IFEXTENTS) &&
+ (error = xfs_iread_extents(tp, ip, whichfork)))
+ return error;
+ lowest = *first_unused;
+ nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+ for (idx = 0, lastaddr = 0, max = lowest; idx < nextents; idx++) {
+ xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx);
+ off = xfs_bmbt_get_startoff(ep);
+ /*
+ * See if the hole before this extent will work.
+ */
+ if (off >= lowest + len && off - max >= len) {
+ *first_unused = max;
+ return 0;
+ }
+ lastaddr = off + xfs_bmbt_get_blockcount(ep);
+ max = XFS_FILEOFF_MAX(lastaddr, lowest);
+ }
+ *first_unused = max;
+ return 0;
+}
+
+/*
+ * Returns the file-relative block number of the last block - 1 before
+ * last_block (input value) in the file.
+ * This is not based on i_size, it is based on the extent records.
+ * Returns 0 for local files, as they do not have extent records.
+ */
+int /* error */
+xfs_bmap_last_before(
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_inode_t *ip, /* incore inode */
+ xfs_fileoff_t *last_block, /* last block */
+ int whichfork) /* data or attr fork */
+{
+ xfs_fileoff_t bno; /* input file offset */
+ int eof; /* hit end of file */
+ xfs_bmbt_rec_host_t *ep; /* pointer to last extent */
+ int error; /* error return value */
+ xfs_bmbt_irec_t got; /* current extent value */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ xfs_extnum_t lastx; /* last extent used */
+ xfs_bmbt_irec_t prev; /* previous extent value */
+
+ if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
+ XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL)
+ return XFS_ERROR(EIO);
+ if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
+ *last_block = 0;
+ return 0;
+ }
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ if (!(ifp->if_flags & XFS_IFEXTENTS) &&
+ (error = xfs_iread_extents(tp, ip, whichfork)))
+ return error;
+ bno = *last_block - 1;
+ ep = xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got,
+ &prev);
+ if (eof || xfs_bmbt_get_startoff(ep) > bno) {
+ if (prev.br_startoff == NULLFILEOFF)
+ *last_block = 0;
+ else
+ *last_block = prev.br_startoff + prev.br_blockcount;
+ }
+ /*
+ * Otherwise *last_block is already the right answer.
+ */
+ return 0;
+}
+
+int
+xfs_bmap_last_extent(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int whichfork,
+ struct xfs_bmbt_irec *rec,
+ int *is_empty)
+{
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ int error;
+ int nextents;
+
+ if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+ error = xfs_iread_extents(tp, ip, whichfork);
+ if (error)
+ return error;
+ }
+
+ nextents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+ if (nextents == 0) {
+ *is_empty = 1;
+ return 0;
+ }
+
+ xfs_bmbt_get_all(xfs_iext_get_ext(ifp, nextents - 1), rec);
+ *is_empty = 0;
+ return 0;
+}
+
+/*
+ * Check the last inode extent to determine whether this allocation will result
+ * in blocks being allocated at the end of the file. When we allocate new data
+ * blocks at the end of the file which do not start at the previous data block,
+ * we will try to align the new blocks at stripe unit boundaries.
+ *
+ * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be
+ * at, or past the EOF.
+ */
+STATIC int
+xfs_bmap_isaeof(
+ struct xfs_bmalloca *bma,
+ int whichfork)
+{
+ struct xfs_bmbt_irec rec;
+ int is_empty;
+ int error;
+
+ bma->aeof = 0;
+ error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
+ &is_empty);
+ if (error)
+ return error;
+
+ if (is_empty) {
+ bma->aeof = 1;
+ return 0;
+ }
+
+ /*
+ * Check if we are allocation or past the last extent, or at least into
+ * the last delayed allocated extent.
+ */
+ bma->aeof = bma->offset >= rec.br_startoff + rec.br_blockcount ||
+ (bma->offset >= rec.br_startoff &&
+ isnullstartblock(rec.br_startblock));
+ return 0;
+}
+
+/*
+ * Returns the file-relative block number of the first block past eof in
+ * the file. This is not based on i_size, it is based on the extent records.
+ * Returns 0 for local files, as they do not have extent records.
+ */
+int
+xfs_bmap_last_offset(
+ struct xfs_inode *ip,
+ xfs_fileoff_t *last_block,
+ int whichfork)
+{
+ struct xfs_bmbt_irec rec;
+ int is_empty;
+ int error;
+
+ *last_block = 0;
+
+ if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL)
+ return 0;
+
+ if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
+ XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS)
+ return XFS_ERROR(EIO);
+
+ error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty);
+ if (error || is_empty)
+ return error;
+
+ *last_block = rec.br_startoff + rec.br_blockcount;
+ return 0;
+}
+
+/*
+ * Returns whether the selected fork of the inode has exactly one
+ * block or not. For the data fork we check this matches di_size,
+ * implying the file's range is 0..bsize-1.
+ */
+int /* 1=>1 block, 0=>otherwise */
+xfs_bmap_one_block(
+ xfs_inode_t *ip, /* incore inode */
+ int whichfork) /* data or attr fork */
+{
+ xfs_bmbt_rec_host_t *ep; /* ptr to fork's extent */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ int rval; /* return value */
+ xfs_bmbt_irec_t s; /* internal version of extent */
+
+#ifndef DEBUG
+ if (whichfork == XFS_DATA_FORK)
+ return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize;
+#endif /* !DEBUG */
+ if (XFS_IFORK_NEXTENTS(ip, whichfork) != 1)
+ return 0;
+ if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS)
+ return 0;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+ ep = xfs_iext_get_ext(ifp, 0);
+ xfs_bmbt_get_all(ep, &s);
+ rval = s.br_startoff == 0 && s.br_blockcount == 1;
+ if (rval && whichfork == XFS_DATA_FORK)
+ ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize);
+ return rval;
+}
+
+/*
+ * Extent tree manipulation functions used during allocation.
+ */
+
/*
* Convert a delayed allocation to a real allocation.
*/
@@ -1852,9 +3200,13 @@ done:
}
/*
+ * Functions used in the extent read, allocate and remove paths
+ */
+
+/*
* Adjust the size of the new extent based on di_extsize and rt extsize.
*/
-STATIC int
+int
xfs_bmap_extsize_align(
xfs_mount_t *mp,
xfs_bmbt_irec_t *gotp, /* next extent pointer */
@@ -2016,9 +3368,9 @@ xfs_bmap_extsize_align(
#define XFS_ALLOC_GAP_UNITS 4
-STATIC void
+void
xfs_bmap_adjacent(
- xfs_bmalloca_t *ap) /* bmap alloc argument struct */
+ struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
xfs_fsblock_t adjust; /* adjustment to block numbers */
xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */
@@ -2164,107 +3516,65 @@ xfs_bmap_adjacent(
#undef ISVALID
}
-STATIC int
-xfs_bmap_rtalloc(
- xfs_bmalloca_t *ap) /* bmap alloc argument struct */
+static int
+xfs_bmap_longest_free_extent(
+ struct xfs_trans *tp,
+ xfs_agnumber_t ag,
+ xfs_extlen_t *blen,
+ int *notinit)
{
- xfs_alloctype_t atype = 0; /* type for allocation routines */
- int error; /* error return value */
- xfs_mount_t *mp; /* mount point structure */
- xfs_extlen_t prod = 0; /* product factor for allocators */
- xfs_extlen_t ralen = 0; /* realtime allocation length */
- xfs_extlen_t align; /* minimum allocation alignment */
- xfs_rtblock_t rtb;
-
- mp = ap->ip->i_mount;
- align = xfs_get_extsz_hint(ap->ip);
- prod = align / mp->m_sb.sb_rextsize;
- error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
- align, 1, ap->eof, 0,
- ap->conv, &ap->offset, &ap->length);
- if (error)
- return error;
- ASSERT(ap->length);
- ASSERT(ap->length % mp->m_sb.sb_rextsize == 0);
-
- /*
- * If the offset & length are not perfectly aligned
- * then kill prod, it will just get us in trouble.
- */
- if (do_mod(ap->offset, align) || ap->length % align)
- prod = 1;
- /*
- * Set ralen to be the actual requested length in rtextents.
- */
- ralen = ap->length / mp->m_sb.sb_rextsize;
- /*
- * If the old value was close enough to MAXEXTLEN that
- * we rounded up to it, cut it back so it's valid again.
- * Note that if it's a really large request (bigger than
- * MAXEXTLEN), we don't hear about that number, and can't
- * adjust the starting point to match it.
- */
- if (ralen * mp->m_sb.sb_rextsize >= MAXEXTLEN)
- ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
-
- /*
- * Lock out other modifications to the RT bitmap inode.
- */
- xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
-
- /*
- * If it's an allocation to an empty file at offset 0,
- * pick an extent that will space things out in the rt area.
- */
- if (ap->eof && ap->offset == 0) {
- xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_perag *pag;
+ xfs_extlen_t longest;
+ int error = 0;
- error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
+ pag = xfs_perag_get(mp, ag);
+ if (!pag->pagf_init) {
+ error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK);
if (error)
- return error;
- ap->blkno = rtx * mp->m_sb.sb_rextsize;
- } else {
- ap->blkno = 0;
+ goto out;
+
+ if (!pag->pagf_init) {
+ *notinit = 1;
+ goto out;
+ }
}
- xfs_bmap_adjacent(ap);
+ longest = xfs_alloc_longest_free_extent(mp, pag);
+ if (*blen < longest)
+ *blen = longest;
- /*
- * Realtime allocation, done through xfs_rtallocate_extent.
- */
- atype = ap->blkno == 0 ? XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO;
- do_div(ap->blkno, mp->m_sb.sb_rextsize);
- rtb = ap->blkno;
- ap->length = ralen;
- if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
- &ralen, atype, ap->wasdel, prod, &rtb)))
- return error;
- if (rtb == NULLFSBLOCK && prod > 1 &&
- (error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1,
- ap->length, &ralen, atype,
- ap->wasdel, 1, &rtb)))
- return error;
- ap->blkno = rtb;
- if (ap->blkno != NULLFSBLOCK) {
- ap->blkno *= mp->m_sb.sb_rextsize;
- ralen *= mp->m_sb.sb_rextsize;
- ap->length = ralen;
- ap->ip->i_d.di_nblocks += ralen;
- xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
- if (ap->wasdel)
- ap->ip->i_delayed_blks -= ralen;
+out:
+ xfs_perag_put(pag);
+ return error;
+}
+
+static void
+xfs_bmap_select_minlen(
+ struct xfs_bmalloca *ap,
+ struct xfs_alloc_arg *args,
+ xfs_extlen_t *blen,
+ int notinit)
+{
+ if (notinit || *blen < ap->minlen) {
/*
- * Adjust the disk quota also. This was reserved
- * earlier.
+ * Since we did a BUF_TRYLOCK above, it is possible that
+ * there is space for this request.
*/
- xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
- ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
- XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
+ args->minlen = ap->minlen;
+ } else if (*blen < args->maxlen) {
+ /*
+ * If the best seen length is less than the request length,
+ * use the best as the minimum.
+ */
+ args->minlen = *blen;
} else {
- ap->length = 0;
+ /*
+ * Otherwise we've seen an extent as big as maxlen, use that
+ * as the minimum.
+ */
+ args->minlen = args->maxlen;
}
- return 0;
}
STATIC int
@@ -2274,117 +3584,80 @@ xfs_bmap_btalloc_nullfb(
xfs_extlen_t *blen)
{
struct xfs_mount *mp = ap->ip->i_mount;
- struct xfs_perag *pag;
xfs_agnumber_t ag, startag;
int notinit = 0;
int error;
- if (ap->userdata && xfs_inode_is_filestream(ap->ip))
- args->type = XFS_ALLOCTYPE_NEAR_BNO;
- else
- args->type = XFS_ALLOCTYPE_START_BNO;
+ args->type = XFS_ALLOCTYPE_START_BNO;
args->total = ap->total;
- /*
- * Search for an allocation group with a single extent large enough
- * for the request. If one isn't found, then adjust the minimum
- * allocation size to the largest space found.
- */
startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
if (startag == NULLAGNUMBER)
startag = ag = 0;
- pag = xfs_perag_get(mp, ag);
while (*blen < args->maxlen) {
- if (!pag->pagf_init) {
- error = xfs_alloc_pagf_init(mp, args->tp, ag,
- XFS_ALLOC_FLAG_TRYLOCK);
- if (error) {
- xfs_perag_put(pag);
- return error;
- }
- }
-
- /*
- * See xfs_alloc_fix_freelist...
- */
- if (pag->pagf_init) {
- xfs_extlen_t longest;
- longest = xfs_alloc_longest_free_extent(mp, pag);
- if (*blen < longest)
- *blen = longest;
- } else
- notinit = 1;
-
- if (xfs_inode_is_filestream(ap->ip)) {
- if (*blen >= args->maxlen)
- break;
-
- if (ap->userdata) {
- /*
- * If startag is an invalid AG, we've
- * come here once before and
- * xfs_filestream_new_ag picked the
- * best currently available.
- *
- * Don't continue looping, since we
- * could loop forever.
- */
- if (startag == NULLAGNUMBER)
- break;
-
- error = xfs_filestream_new_ag(ap, &ag);
- xfs_perag_put(pag);
- if (error)
- return error;
+ error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
+ &notinit);
+ if (error)
+ return error;
- /* loop again to set 'blen'*/
- startag = NULLAGNUMBER;
- pag = xfs_perag_get(mp, ag);
- continue;
- }
- }
if (++ag == mp->m_sb.sb_agcount)
ag = 0;
if (ag == startag)
break;
- xfs_perag_put(pag);
- pag = xfs_perag_get(mp, ag);
}
- xfs_perag_put(pag);
- /*
- * Since the above loop did a BUF_TRYLOCK, it is
- * possible that there is space for this request.
- */
- if (notinit || *blen < ap->minlen)
- args->minlen = ap->minlen;
- /*
- * If the best seen length is less than the request
- * length, use the best as the minimum.
- */
- else if (*blen < args->maxlen)
- args->minlen = *blen;
- /*
- * Otherwise we've seen an extent as big as maxlen,
- * use that as the minimum.
- */
- else
- args->minlen = args->maxlen;
+ xfs_bmap_select_minlen(ap, args, blen, notinit);
+ return 0;
+}
+
+STATIC int
+xfs_bmap_btalloc_filestreams(
+ struct xfs_bmalloca *ap,
+ struct xfs_alloc_arg *args,
+ xfs_extlen_t *blen)
+{
+ struct xfs_mount *mp = ap->ip->i_mount;
+ xfs_agnumber_t ag;
+ int notinit = 0;
+ int error;
+
+ args->type = XFS_ALLOCTYPE_NEAR_BNO;
+ args->total = ap->total;
+
+ ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
+ if (ag == NULLAGNUMBER)
+ ag = 0;
+
+ error = xfs_bmap_longest_free_extent(args->tp, ag, blen, &notinit);
+ if (error)
+ return error;
+
+ if (*blen < args->maxlen) {
+ error = xfs_filestream_new_ag(ap, &ag);
+ if (error)
+ return error;
+
+ error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
+ &notinit);
+ if (error)
+ return error;
+
+ }
+
+ xfs_bmap_select_minlen(ap, args, blen, notinit);
/*
- * set the failure fallback case to look in the selected
- * AG as the stream may have moved.
+ * Set the failure fallback case to look in the selected AG as stream
+ * may have moved.
*/
- if (xfs_inode_is_filestream(ap->ip))
- ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
-
+ ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
return 0;
}
STATIC int
xfs_bmap_btalloc(
- xfs_bmalloca_t *ap) /* bmap alloc argument struct */
+ struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
xfs_mount_t *mp; /* mount point structure */
xfs_alloctype_t atype = 0; /* type for allocation routines */
@@ -2398,10 +3671,19 @@ xfs_bmap_btalloc(
int isaligned;
int tryagain;
int error;
+ int stripe_align;
ASSERT(ap->length);
mp = ap->ip->i_mount;
+
+ /* stripe alignment for allocation is determined by mount parameters */
+ stripe_align = 0;
+ if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
+ stripe_align = mp->m_swidth;
+ else if (mp->m_dalign)
+ stripe_align = mp->m_dalign;
+
align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
if (unlikely(align)) {
error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
@@ -2410,6 +3692,8 @@ xfs_bmap_btalloc(
ASSERT(!error);
ASSERT(ap->length);
}
+
+
nullfb = *ap->firstblock == NULLFSBLOCK;
fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
if (nullfb) {
@@ -2437,6 +3721,7 @@ xfs_bmap_btalloc(
* Normal allocation, done through xfs_alloc_vextent.
*/
tryagain = isaligned = 0;
+ memset(&args, 0, sizeof(args));
args.tp = ap->tp;
args.mp = mp;
args.fsbno = ap->blkno;
@@ -2446,7 +3731,15 @@ xfs_bmap_btalloc(
args.firstblock = *ap->firstblock;
blen = 0;
if (nullfb) {
- error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
+ /*
+ * Search for an allocation group with a single extent large
+ * enough for the request. If one isn't found, then adjust
+ * the minimum allocation size to the largest space found.
+ */
+ if (ap->userdata && xfs_inode_is_filestream(ap->ip))
+ error = xfs_bmap_btalloc_filestreams(ap, &args, &blen);
+ else
+ error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
if (error)
return error;
} else if (ap->flist->xbf_low) {
@@ -2484,7 +3777,7 @@ xfs_bmap_btalloc(
*/
if (!ap->flist->xbf_low && ap->aeof) {
if (!ap->offset) {
- args.alignment = mp->m_dalign;
+ args.alignment = stripe_align;
atype = args.type;
isaligned = 1;
/*
@@ -2509,13 +3802,13 @@ xfs_bmap_btalloc(
* of minlen+alignment+slop doesn't go up
* between the calls.
*/
- if (blen > mp->m_dalign && blen <= args.maxlen)
- nextminlen = blen - mp->m_dalign;
+ if (blen > stripe_align && blen <= args.maxlen)
+ nextminlen = blen - stripe_align;
else
nextminlen = args.minlen;
- if (nextminlen + mp->m_dalign > args.minlen + 1)
+ if (nextminlen + stripe_align > args.minlen + 1)
args.minalignslop =
- nextminlen + mp->m_dalign -
+ nextminlen + stripe_align -
args.minlen - 1;
else
args.minalignslop = 0;
@@ -2537,7 +3830,7 @@ xfs_bmap_btalloc(
*/
args.type = atype;
args.fsbno = ap->blkno;
- args.alignment = mp->m_dalign;
+ args.alignment = stripe_align;
args.minlen = nextminlen;
args.minalignslop = 0;
isaligned = 1;
@@ -2615,7 +3908,7 @@ xfs_bmap_btalloc(
*/
STATIC int
xfs_bmap_alloc(
- xfs_bmalloca_t *ap) /* bmap alloc argument struct */
+ struct xfs_bmalloca *ap) /* bmap alloc argument struct */
{
if (XFS_IS_REALTIME_INODE(ap->ip) && ap->userdata)
return xfs_bmap_rtalloc(ap);
@@ -2623,1618 +3916,6 @@ xfs_bmap_alloc(
}
/*
- * Transform a btree format file with only one leaf node, where the
- * extents list will fit in the inode, into an extents format file.
- * Since the file extents are already in-core, all we have to do is
- * give up the space for the btree root and pitch the leaf block.
- */
-STATIC int /* error */
-xfs_bmap_btree_to_extents(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_btree_cur_t *cur, /* btree cursor */
- int *logflagsp, /* inode logging flags */
- int whichfork) /* data or attr fork */
-{
- /* REFERENCED */
- struct xfs_btree_block *cblock;/* child btree block */
- xfs_fsblock_t cbno; /* child block number */
- xfs_buf_t *cbp; /* child block's buffer */
- int error; /* error return value */
- xfs_ifork_t *ifp; /* inode fork data */
- xfs_mount_t *mp; /* mount point structure */
- __be64 *pp; /* ptr to block address */
- struct xfs_btree_block *rblock;/* root btree block */
-
- mp = ip->i_mount;
- ifp = XFS_IFORK_PTR(ip, whichfork);
- ASSERT(ifp->if_flags & XFS_IFEXTENTS);
- ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
- rblock = ifp->if_broot;
- ASSERT(be16_to_cpu(rblock->bb_level) == 1);
- ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
- ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0) == 1);
- pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
- cbno = be64_to_cpu(*pp);
- *logflagsp = 0;
-#ifdef DEBUG
- if ((error = xfs_btree_check_lptr(cur, cbno, 1)))
- return error;
-#endif
- if ((error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp,
- XFS_BMAP_BTREE_REF)))
- return error;
- cblock = XFS_BUF_TO_BLOCK(cbp);
- if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
- return error;
- xfs_bmap_add_free(cbno, 1, cur->bc_private.b.flist, mp);
- ip->i_d.di_nblocks--;
- xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
- xfs_trans_binval(tp, cbp);
- if (cur->bc_bufs[0] == cbp)
- cur->bc_bufs[0] = NULL;
- xfs_iroot_realloc(ip, -1, whichfork);
- ASSERT(ifp->if_broot == NULL);
- ASSERT((ifp->if_flags & XFS_IFBROOT) == 0);
- XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
- *logflagsp = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
- return 0;
-}
-
-/*
- * Called by xfs_bmapi to update file extent records and the btree
- * after removing space (or undoing a delayed allocation).
- */
-STATIC int /* error */
-xfs_bmap_del_extent(
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_trans_t *tp, /* current transaction pointer */
- xfs_extnum_t *idx, /* extent number to update/delete */
- xfs_bmap_free_t *flist, /* list of extents to be freed */
- xfs_btree_cur_t *cur, /* if null, not a btree */
- xfs_bmbt_irec_t *del, /* data to remove from extents */
- int *logflagsp, /* inode logging flags */
- int whichfork) /* data or attr fork */
-{
- xfs_filblks_t da_new; /* new delay-alloc indirect blocks */
- xfs_filblks_t da_old; /* old delay-alloc indirect blocks */
- xfs_fsblock_t del_endblock=0; /* first block past del */
- xfs_fileoff_t del_endoff; /* first offset past del */
- int delay; /* current block is delayed allocated */
- int do_fx; /* free extent at end of routine */
- xfs_bmbt_rec_host_t *ep; /* current extent entry pointer */
- int error; /* error return value */
- int flags; /* inode logging flags */
- xfs_bmbt_irec_t got; /* current extent entry */
- xfs_fileoff_t got_endoff; /* first offset past got */
- int i; /* temp state */
- xfs_ifork_t *ifp; /* inode fork pointer */
- xfs_mount_t *mp; /* mount structure */
- xfs_filblks_t nblks; /* quota/sb block count */
- xfs_bmbt_irec_t new; /* new record to be inserted */
- /* REFERENCED */
- uint qfield; /* quota field to update */
- xfs_filblks_t temp; /* for indirect length calculations */
- xfs_filblks_t temp2; /* for indirect length calculations */
- int state = 0;
-
- XFS_STATS_INC(xs_del_exlist);
-
- if (whichfork == XFS_ATTR_FORK)
- state |= BMAP_ATTRFORK;
-
- mp = ip->i_mount;
- ifp = XFS_IFORK_PTR(ip, whichfork);
- ASSERT((*idx >= 0) && (*idx < ifp->if_bytes /
- (uint)sizeof(xfs_bmbt_rec_t)));
- ASSERT(del->br_blockcount > 0);
- ep = xfs_iext_get_ext(ifp, *idx);
- xfs_bmbt_get_all(ep, &got);
- ASSERT(got.br_startoff <= del->br_startoff);
- del_endoff = del->br_startoff + del->br_blockcount;
- got_endoff = got.br_startoff + got.br_blockcount;
- ASSERT(got_endoff >= del_endoff);
- delay = isnullstartblock(got.br_startblock);
- ASSERT(isnullstartblock(del->br_startblock) == delay);
- flags = 0;
- qfield = 0;
- error = 0;
- /*
- * If deleting a real allocation, must free up the disk space.
- */
- if (!delay) {
- flags = XFS_ILOG_CORE;
- /*
- * Realtime allocation. Free it and record di_nblocks update.
- */
- if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
- xfs_fsblock_t bno;
- xfs_filblks_t len;
-
- ASSERT(do_mod(del->br_blockcount,
- mp->m_sb.sb_rextsize) == 0);
- ASSERT(do_mod(del->br_startblock,
- mp->m_sb.sb_rextsize) == 0);
- bno = del->br_startblock;
- len = del->br_blockcount;
- do_div(bno, mp->m_sb.sb_rextsize);
- do_div(len, mp->m_sb.sb_rextsize);
- error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len);
- if (error)
- goto done;
- do_fx = 0;
- nblks = len * mp->m_sb.sb_rextsize;
- qfield = XFS_TRANS_DQ_RTBCOUNT;
- }
- /*
- * Ordinary allocation.
- */
- else {
- do_fx = 1;
- nblks = del->br_blockcount;
- qfield = XFS_TRANS_DQ_BCOUNT;
- }
- /*
- * Set up del_endblock and cur for later.
- */
- del_endblock = del->br_startblock + del->br_blockcount;
- if (cur) {
- if ((error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
- got.br_startblock, got.br_blockcount,
- &i)))
- goto done;
- XFS_WANT_CORRUPTED_GOTO(i == 1, done);
- }
- da_old = da_new = 0;
- } else {
- da_old = startblockval(got.br_startblock);
- da_new = 0;
- nblks = 0;
- do_fx = 0;
- }
- /*
- * Set flag value to use in switch statement.
- * Left-contig is 2, right-contig is 1.
- */
- switch (((got.br_startoff == del->br_startoff) << 1) |
- (got_endoff == del_endoff)) {
- case 3:
- /*
- * Matches the whole extent. Delete the entry.
- */
- xfs_iext_remove(ip, *idx, 1,
- whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0);
- --*idx;
- if (delay)
- break;
-
- XFS_IFORK_NEXT_SET(ip, whichfork,
- XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
- flags |= XFS_ILOG_CORE;
- if (!cur) {
- flags |= xfs_ilog_fext(whichfork);
- break;
- }
- if ((error = xfs_btree_delete(cur, &i)))
- goto done;
- XFS_WANT_CORRUPTED_GOTO(i == 1, done);
- break;
-
- case 2:
- /*
- * Deleting the first part of the extent.
- */
- trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
- xfs_bmbt_set_startoff(ep, del_endoff);
- temp = got.br_blockcount - del->br_blockcount;
- xfs_bmbt_set_blockcount(ep, temp);
- if (delay) {
- temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
- da_old);
- xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
- trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
- da_new = temp;
- break;
- }
- xfs_bmbt_set_startblock(ep, del_endblock);
- trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
- if (!cur) {
- flags |= xfs_ilog_fext(whichfork);
- break;
- }
- if ((error = xfs_bmbt_update(cur, del_endoff, del_endblock,
- got.br_blockcount - del->br_blockcount,
- got.br_state)))
- goto done;
- break;
-
- case 1:
- /*
- * Deleting the last part of the extent.
- */
- temp = got.br_blockcount - del->br_blockcount;
- trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
- xfs_bmbt_set_blockcount(ep, temp);
- if (delay) {
- temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
- da_old);
- xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
- trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
- da_new = temp;
- break;
- }
- trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
- if (!cur) {
- flags |= xfs_ilog_fext(whichfork);
- break;
- }
- if ((error = xfs_bmbt_update(cur, got.br_startoff,
- got.br_startblock,
- got.br_blockcount - del->br_blockcount,
- got.br_state)))
- goto done;
- break;
-
- case 0:
- /*
- * Deleting the middle of the extent.
- */
- temp = del->br_startoff - got.br_startoff;
- trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
- xfs_bmbt_set_blockcount(ep, temp);
- new.br_startoff = del_endoff;
- temp2 = got_endoff - del_endoff;
- new.br_blockcount = temp2;
- new.br_state = got.br_state;
- if (!delay) {
- new.br_startblock = del_endblock;
- flags |= XFS_ILOG_CORE;
- if (cur) {
- if ((error = xfs_bmbt_update(cur,
- got.br_startoff,
- got.br_startblock, temp,
- got.br_state)))
- goto done;
- if ((error = xfs_btree_increment(cur, 0, &i)))
- goto done;
- cur->bc_rec.b = new;
- error = xfs_btree_insert(cur, &i);
- if (error && error != ENOSPC)
- goto done;
- /*
- * If get no-space back from btree insert,
- * it tried a split, and we have a zero
- * block reservation.
- * Fix up our state and return the error.
- */
- if (error == ENOSPC) {
- /*
- * Reset the cursor, don't trust
- * it after any insert operation.
- */
- if ((error = xfs_bmbt_lookup_eq(cur,
- got.br_startoff,
- got.br_startblock,
- temp, &i)))
- goto done;
- XFS_WANT_CORRUPTED_GOTO(i == 1, done);
- /*
- * Update the btree record back
- * to the original value.
- */
- if ((error = xfs_bmbt_update(cur,
- got.br_startoff,
- got.br_startblock,
- got.br_blockcount,
- got.br_state)))
- goto done;
- /*
- * Reset the extent record back
- * to the original value.
- */
- xfs_bmbt_set_blockcount(ep,
- got.br_blockcount);
- flags = 0;
- error = XFS_ERROR(ENOSPC);
- goto done;
- }
- XFS_WANT_CORRUPTED_GOTO(i == 1, done);
- } else
- flags |= xfs_ilog_fext(whichfork);
- XFS_IFORK_NEXT_SET(ip, whichfork,
- XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
- } else {
- ASSERT(whichfork == XFS_DATA_FORK);
- temp = xfs_bmap_worst_indlen(ip, temp);
- xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
- temp2 = xfs_bmap_worst_indlen(ip, temp2);
- new.br_startblock = nullstartblock((int)temp2);
- da_new = temp + temp2;
- while (da_new > da_old) {
- if (temp) {
- temp--;
- da_new--;
- xfs_bmbt_set_startblock(ep,
- nullstartblock((int)temp));
- }
- if (da_new == da_old)
- break;
- if (temp2) {
- temp2--;
- da_new--;
- new.br_startblock =
- nullstartblock((int)temp2);
- }
- }
- }
- trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
- xfs_iext_insert(ip, *idx + 1, 1, &new, state);
- ++*idx;
- break;
- }
- /*
- * If we need to, add to list of extents to delete.
- */
- if (do_fx)
- xfs_bmap_add_free(del->br_startblock, del->br_blockcount, flist,
- mp);
- /*
- * Adjust inode # blocks in the file.
- */
- if (nblks)
- ip->i_d.di_nblocks -= nblks;
- /*
- * Adjust quota data.
- */
- if (qfield)
- xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks);
-
- /*
- * Account for change in delayed indirect blocks.
- * Nothing to do for disk quota accounting here.
- */
- ASSERT(da_old >= da_new);
- if (da_old > da_new) {
- xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS,
- (int64_t)(da_old - da_new), 0);
- }
-done:
- *logflagsp = flags;
- return error;
-}
-
-/*
- * Remove the entry "free" from the free item list. Prev points to the
- * previous entry, unless "free" is the head of the list.
- */
-STATIC void
-xfs_bmap_del_free(
- xfs_bmap_free_t *flist, /* free item list header */
- xfs_bmap_free_item_t *prev, /* previous item on list, if any */
- xfs_bmap_free_item_t *free) /* list item to be freed */
-{
- if (prev)
- prev->xbfi_next = free->xbfi_next;
- else
- flist->xbf_first = free->xbfi_next;
- flist->xbf_count--;
- kmem_zone_free(xfs_bmap_free_item_zone, free);
-}
-
-/*
- * Convert an extents-format file into a btree-format file.
- * The new file will have a root block (in the inode) and a single child block.
- */
-STATIC int /* error */
-xfs_bmap_extents_to_btree(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fsblock_t *firstblock, /* first-block-allocated */
- xfs_bmap_free_t *flist, /* blocks freed in xaction */
- xfs_btree_cur_t **curp, /* cursor returned to caller */
- int wasdel, /* converting a delayed alloc */
- int *logflagsp, /* inode logging flags */
- int whichfork) /* data or attr fork */
-{
- struct xfs_btree_block *ablock; /* allocated (child) bt block */
- xfs_buf_t *abp; /* buffer for ablock */
- xfs_alloc_arg_t args; /* allocation arguments */
- xfs_bmbt_rec_t *arp; /* child record pointer */
- struct xfs_btree_block *block; /* btree root block */
- xfs_btree_cur_t *cur; /* bmap btree cursor */
- xfs_bmbt_rec_host_t *ep; /* extent record pointer */
- int error; /* error return value */
- xfs_extnum_t i, cnt; /* extent record index */
- xfs_ifork_t *ifp; /* inode fork pointer */
- xfs_bmbt_key_t *kp; /* root block key pointer */
- xfs_mount_t *mp; /* mount structure */
- xfs_extnum_t nextents; /* number of file extents */
- xfs_bmbt_ptr_t *pp; /* root block address pointer */
-
- ifp = XFS_IFORK_PTR(ip, whichfork);
- ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS);
-
- /*
- * Make space in the inode incore.
- */
- xfs_iroot_realloc(ip, 1, whichfork);
- ifp->if_flags |= XFS_IFBROOT;
-
- /*
- * Fill in the root.
- */
- block = ifp->if_broot;
- block->bb_magic = cpu_to_be32(XFS_BMAP_MAGIC);
- block->bb_level = cpu_to_be16(1);
- block->bb_numrecs = cpu_to_be16(1);
- block->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
- block->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
-
- /*
- * Need a cursor. Can't allocate until bb_level is filled in.
- */
- mp = ip->i_mount;
- cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
- cur->bc_private.b.firstblock = *firstblock;
- cur->bc_private.b.flist = flist;
- cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
- /*
- * Convert to a btree with two levels, one record in root.
- */
- XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE);
- args.tp = tp;
- args.mp = mp;
- args.firstblock = *firstblock;
- if (*firstblock == NULLFSBLOCK) {
- args.type = XFS_ALLOCTYPE_START_BNO;
- args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
- } else if (flist->xbf_low) {
- args.type = XFS_ALLOCTYPE_START_BNO;
- args.fsbno = *firstblock;
- } else {
- args.type = XFS_ALLOCTYPE_NEAR_BNO;
- args.fsbno = *firstblock;
- }
- args.minlen = args.maxlen = args.prod = 1;
- args.total = args.minleft = args.alignment = args.mod = args.isfl =
- args.minalignslop = 0;
- args.wasdel = wasdel;
- *logflagsp = 0;
- if ((error = xfs_alloc_vextent(&args))) {
- xfs_iroot_realloc(ip, -1, whichfork);
- xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
- return error;
- }
- /*
- * Allocation can't fail, the space was reserved.
- */
- ASSERT(args.fsbno != NULLFSBLOCK);
- ASSERT(*firstblock == NULLFSBLOCK ||
- args.agno == XFS_FSB_TO_AGNO(mp, *firstblock) ||
- (flist->xbf_low &&
- args.agno > XFS_FSB_TO_AGNO(mp, *firstblock)));
- *firstblock = cur->bc_private.b.firstblock = args.fsbno;
- cur->bc_private.b.allocated++;
- ip->i_d.di_nblocks++;
- xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
- abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
- /*
- * Fill in the child block.
- */
- ablock = XFS_BUF_TO_BLOCK(abp);
- ablock->bb_magic = cpu_to_be32(XFS_BMAP_MAGIC);
- ablock->bb_level = 0;
- ablock->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
- ablock->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
- arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
- nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
- for (cnt = i = 0; i < nextents; i++) {
- ep = xfs_iext_get_ext(ifp, i);
- if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) {
- arp->l0 = cpu_to_be64(ep->l0);
- arp->l1 = cpu_to_be64(ep->l1);
- arp++; cnt++;
- }
- }
- ASSERT(cnt == XFS_IFORK_NEXTENTS(ip, whichfork));
- xfs_btree_set_numrecs(ablock, cnt);
-
- /*
- * Fill in the root key and pointer.
- */
- kp = XFS_BMBT_KEY_ADDR(mp, block, 1);
- arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
- kp->br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(arp));
- pp = XFS_BMBT_PTR_ADDR(mp, block, 1, xfs_bmbt_get_maxrecs(cur,
- be16_to_cpu(block->bb_level)));
- *pp = cpu_to_be64(args.fsbno);
-
- /*
- * Do all this logging at the end so that
- * the root is at the right level.
- */
- xfs_btree_log_block(cur, abp, XFS_BB_ALL_BITS);
- xfs_btree_log_recs(cur, abp, 1, be16_to_cpu(ablock->bb_numrecs));
- ASSERT(*curp == NULL);
- *curp = cur;
- *logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
- return 0;
-}
-
-/*
- * Calculate the default attribute fork offset for newly created inodes.
- */
-uint
-xfs_default_attroffset(
- struct xfs_inode *ip)
-{
- struct xfs_mount *mp = ip->i_mount;
- uint offset;
-
- if (mp->m_sb.sb_inodesize == 256) {
- offset = XFS_LITINO(mp) -
- XFS_BMDR_SPACE_CALC(MINABTPTRS);
- } else {
- offset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
- }
-
- ASSERT(offset < XFS_LITINO(mp));
- return offset;
-}
-
-/*
- * Helper routine to reset inode di_forkoff field when switching
- * attribute fork from local to extent format - we reset it where
- * possible to make space available for inline data fork extents.
- */
-STATIC void
-xfs_bmap_forkoff_reset(
- xfs_mount_t *mp,
- xfs_inode_t *ip,
- int whichfork)
-{
- if (whichfork == XFS_ATTR_FORK &&
- ip->i_d.di_format != XFS_DINODE_FMT_DEV &&
- ip->i_d.di_format != XFS_DINODE_FMT_UUID &&
- ip->i_d.di_format != XFS_DINODE_FMT_BTREE) {
- uint dfl_forkoff = xfs_default_attroffset(ip) >> 3;
-
- if (dfl_forkoff > ip->i_d.di_forkoff)
- ip->i_d.di_forkoff = dfl_forkoff;
- }
-}
-
-/*
- * Convert a local file to an extents file.
- * This code is out of bounds for data forks of regular files,
- * since the file data needs to get logged so things will stay consistent.
- * (The bmap-level manipulations are ok, though).
- */
-STATIC int /* error */
-xfs_bmap_local_to_extents(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fsblock_t *firstblock, /* first block allocated in xaction */
- xfs_extlen_t total, /* total blocks needed by transaction */
- int *logflagsp, /* inode logging flags */
- int whichfork) /* data or attr fork */
-{
- int error; /* error return value */
- int flags; /* logging flags returned */
- xfs_ifork_t *ifp; /* inode fork pointer */
-
- /*
- * We don't want to deal with the case of keeping inode data inline yet.
- * So sending the data fork of a regular inode is invalid.
- */
- ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK));
- ifp = XFS_IFORK_PTR(ip, whichfork);
- ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
- flags = 0;
- error = 0;
- if (ifp->if_bytes) {
- xfs_alloc_arg_t args; /* allocation arguments */
- xfs_buf_t *bp; /* buffer for extent block */
- xfs_bmbt_rec_host_t *ep;/* extent record pointer */
-
- args.tp = tp;
- args.mp = ip->i_mount;
- args.firstblock = *firstblock;
- ASSERT((ifp->if_flags &
- (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == XFS_IFINLINE);
- /*
- * Allocate a block. We know we need only one, since the
- * file currently fits in an inode.
- */
- if (*firstblock == NULLFSBLOCK) {
- args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
- args.type = XFS_ALLOCTYPE_START_BNO;
- } else {
- args.fsbno = *firstblock;
- args.type = XFS_ALLOCTYPE_NEAR_BNO;
- }
- args.total = total;
- args.mod = args.minleft = args.alignment = args.wasdel =
- args.isfl = args.minalignslop = 0;
- args.minlen = args.maxlen = args.prod = 1;
- if ((error = xfs_alloc_vextent(&args)))
- goto done;
- /*
- * Can't fail, the space was reserved.
- */
- ASSERT(args.fsbno != NULLFSBLOCK);
- ASSERT(args.len == 1);
- *firstblock = args.fsbno;
- bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
- memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
- xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
- xfs_bmap_forkoff_reset(args.mp, ip, whichfork);
- xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
- xfs_iext_add(ifp, 0, 1);
- ep = xfs_iext_get_ext(ifp, 0);
- xfs_bmbt_set_allf(ep, 0, args.fsbno, 1, XFS_EXT_NORM);
- trace_xfs_bmap_post_update(ip, 0,
- whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0,
- _THIS_IP_);
- XFS_IFORK_NEXT_SET(ip, whichfork, 1);
- ip->i_d.di_nblocks = 1;
- xfs_trans_mod_dquot_byino(tp, ip,
- XFS_TRANS_DQ_BCOUNT, 1L);
- flags |= xfs_ilog_fext(whichfork);
- } else {
- ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0);
- xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork);
- }
- ifp->if_flags &= ~XFS_IFINLINE;
- ifp->if_flags |= XFS_IFEXTENTS;
- XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
- flags |= XFS_ILOG_CORE;
-done:
- *logflagsp = flags;
- return error;
-}
-
-/*
- * Search the extent records for the entry containing block bno.
- * If bno lies in a hole, point to the next entry. If bno lies
- * past eof, *eofp will be set, and *prevp will contain the last
- * entry (null if none). Else, *lastxp will be set to the index
- * of the found entry; *gotp will contain the entry.
- */
-STATIC xfs_bmbt_rec_host_t * /* pointer to found extent entry */
-xfs_bmap_search_multi_extents(
- xfs_ifork_t *ifp, /* inode fork pointer */
- xfs_fileoff_t bno, /* block number searched for */
- int *eofp, /* out: end of file found */
- xfs_extnum_t *lastxp, /* out: last extent index */
- xfs_bmbt_irec_t *gotp, /* out: extent entry found */
- xfs_bmbt_irec_t *prevp) /* out: previous extent entry found */
-{
- xfs_bmbt_rec_host_t *ep; /* extent record pointer */
- xfs_extnum_t lastx; /* last extent index */
-
- /*
- * Initialize the extent entry structure to catch access to
- * uninitialized br_startblock field.
- */
- gotp->br_startoff = 0xffa5a5a5a5a5a5a5LL;
- gotp->br_blockcount = 0xa55a5a5a5a5a5a5aLL;
- gotp->br_state = XFS_EXT_INVALID;
-#if XFS_BIG_BLKNOS
- gotp->br_startblock = 0xffffa5a5a5a5a5a5LL;
-#else
- gotp->br_startblock = 0xffffa5a5;
-#endif
- prevp->br_startoff = NULLFILEOFF;
-
- ep = xfs_iext_bno_to_ext(ifp, bno, &lastx);
- if (lastx > 0) {
- xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx - 1), prevp);
- }
- if (lastx < (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))) {
- xfs_bmbt_get_all(ep, gotp);
- *eofp = 0;
- } else {
- if (lastx > 0) {
- *gotp = *prevp;
- }
- *eofp = 1;
- ep = NULL;
- }
- *lastxp = lastx;
- return ep;
-}
-
-/*
- * Search the extents list for the inode, for the extent containing bno.
- * If bno lies in a hole, point to the next entry. If bno lies past eof,
- * *eofp will be set, and *prevp will contain the last entry (null if none).
- * Else, *lastxp will be set to the index of the found
- * entry; *gotp will contain the entry.
- */
-STATIC xfs_bmbt_rec_host_t * /* pointer to found extent entry */
-xfs_bmap_search_extents(
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_fileoff_t bno, /* block number searched for */
- int fork, /* data or attr fork */
- int *eofp, /* out: end of file found */
- xfs_extnum_t *lastxp, /* out: last extent index */
- xfs_bmbt_irec_t *gotp, /* out: extent entry found */
- xfs_bmbt_irec_t *prevp) /* out: previous extent entry found */
-{
- xfs_ifork_t *ifp; /* inode fork pointer */
- xfs_bmbt_rec_host_t *ep; /* extent record pointer */
-
- XFS_STATS_INC(xs_look_exlist);
- ifp = XFS_IFORK_PTR(ip, fork);
-
- ep = xfs_bmap_search_multi_extents(ifp, bno, eofp, lastxp, gotp, prevp);
-
- if (unlikely(!(gotp->br_startblock) && (*lastxp != NULLEXTNUM) &&
- !(XFS_IS_REALTIME_INODE(ip) && fork == XFS_DATA_FORK))) {
- xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
- "Access to block zero in inode %llu "
- "start_block: %llx start_off: %llx "
- "blkcnt: %llx extent-state: %x lastx: %x\n",
- (unsigned long long)ip->i_ino,
- (unsigned long long)gotp->br_startblock,
- (unsigned long long)gotp->br_startoff,
- (unsigned long long)gotp->br_blockcount,
- gotp->br_state, *lastxp);
- *lastxp = NULLEXTNUM;
- *eofp = 1;
- return NULL;
- }
- return ep;
-}
-
-/*
- * Compute the worst-case number of indirect blocks that will be used
- * for ip's delayed extent of length "len".
- */
-STATIC xfs_filblks_t
-xfs_bmap_worst_indlen(
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_filblks_t len) /* delayed extent length */
-{
- int level; /* btree level number */
- int maxrecs; /* maximum record count at this level */
- xfs_mount_t *mp; /* mount structure */
- xfs_filblks_t rval; /* return value */
-
- mp = ip->i_mount;
- maxrecs = mp->m_bmap_dmxr[0];
- for (level = 0, rval = 0;
- level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
- level++) {
- len += maxrecs - 1;
- do_div(len, maxrecs);
- rval += len;
- if (len == 1)
- return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
- level - 1;
- if (level == 0)
- maxrecs = mp->m_bmap_dmxr[1];
- }
- return rval;
-}
-
-/*
- * Convert inode from non-attributed to attributed.
- * Must not be in a transaction, ip must not be locked.
- */
-int /* error code */
-xfs_bmap_add_attrfork(
- xfs_inode_t *ip, /* incore inode pointer */
- int size, /* space new attribute needs */
- int rsvd) /* xact may use reserved blks */
-{
- xfs_fsblock_t firstblock; /* 1st block/ag allocated */
- xfs_bmap_free_t flist; /* freed extent records */
- xfs_mount_t *mp; /* mount structure */
- xfs_trans_t *tp; /* transaction pointer */
- int blks; /* space reservation */
- int version = 1; /* superblock attr version */
- int committed; /* xaction was committed */
- int logflags; /* logging flags */
- int error; /* error return value */
-
- ASSERT(XFS_IFORK_Q(ip) == 0);
-
- mp = ip->i_mount;
- ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
- tp = xfs_trans_alloc(mp, XFS_TRANS_ADDAFORK);
- blks = XFS_ADDAFORK_SPACE_RES(mp);
- if (rsvd)
- tp->t_flags |= XFS_TRANS_RESERVE;
- if ((error = xfs_trans_reserve(tp, blks, XFS_ADDAFORK_LOG_RES(mp), 0,
- XFS_TRANS_PERM_LOG_RES, XFS_ADDAFORK_LOG_COUNT)))
- goto error0;
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
- XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
- XFS_QMOPT_RES_REGBLKS);
- if (error) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
- return error;
- }
- if (XFS_IFORK_Q(ip))
- goto error1;
- if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) {
- /*
- * For inodes coming from pre-6.2 filesystems.
- */
- ASSERT(ip->i_d.di_aformat == 0);
- ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
- }
- ASSERT(ip->i_d.di_anextents == 0);
-
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
- switch (ip->i_d.di_format) {
- case XFS_DINODE_FMT_DEV:
- ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3;
- break;
- case XFS_DINODE_FMT_UUID:
- ip->i_d.di_forkoff = roundup(sizeof(uuid_t), 8) >> 3;
- break;
- case XFS_DINODE_FMT_LOCAL:
- case XFS_DINODE_FMT_EXTENTS:
- case XFS_DINODE_FMT_BTREE:
- ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size);
- if (!ip->i_d.di_forkoff)
- ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3;
- else if (mp->m_flags & XFS_MOUNT_ATTR2)
- version = 2;
- break;
- default:
- ASSERT(0);
- error = XFS_ERROR(EINVAL);
- goto error1;
- }
-
- ASSERT(ip->i_afp == NULL);
- ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
- ip->i_afp->if_flags = XFS_IFEXTENTS;
- logflags = 0;
- xfs_bmap_init(&flist, &firstblock);
- switch (ip->i_d.di_format) {
- case XFS_DINODE_FMT_LOCAL:
- error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &flist,
- &logflags);
- break;
- case XFS_DINODE_FMT_EXTENTS:
- error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
- &flist, &logflags);
- break;
- case XFS_DINODE_FMT_BTREE:
- error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &flist,
- &logflags);
- break;
- default:
- error = 0;
- break;
- }
- if (logflags)
- xfs_trans_log_inode(tp, ip, logflags);
- if (error)
- goto error2;
- if (!xfs_sb_version_hasattr(&mp->m_sb) ||
- (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
- __int64_t sbfields = 0;
-
- spin_lock(&mp->m_sb_lock);
- if (!xfs_sb_version_hasattr(&mp->m_sb)) {
- xfs_sb_version_addattr(&mp->m_sb);
- sbfields |= XFS_SB_VERSIONNUM;
- }
- if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) {
- xfs_sb_version_addattr2(&mp->m_sb);
- sbfields |= (XFS_SB_VERSIONNUM | XFS_SB_FEATURES2);
- }
- if (sbfields) {
- spin_unlock(&mp->m_sb_lock);
- xfs_mod_sb(tp, sbfields);
- } else
- spin_unlock(&mp->m_sb_lock);
- }
-
- error = xfs_bmap_finish(&tp, &flist, &committed);
- if (error)
- goto error2;
- return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-error2:
- xfs_bmap_cancel(&flist);
-error1:
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
-error0:
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- return error;
-}
-
-/*
- * Add the extent to the list of extents to be free at transaction end.
- * The list is maintained sorted (by block number).
- */
-/* ARGSUSED */
-void
-xfs_bmap_add_free(
- xfs_fsblock_t bno, /* fs block number of extent */
- xfs_filblks_t len, /* length of extent */
- xfs_bmap_free_t *flist, /* list of extents */
- xfs_mount_t *mp) /* mount point structure */
-{
- xfs_bmap_free_item_t *cur; /* current (next) element */
- xfs_bmap_free_item_t *new; /* new element */
- xfs_bmap_free_item_t *prev; /* previous element */
-#ifdef DEBUG
- xfs_agnumber_t agno;
- xfs_agblock_t agbno;
-
- ASSERT(bno != NULLFSBLOCK);
- ASSERT(len > 0);
- ASSERT(len <= MAXEXTLEN);
- ASSERT(!isnullstartblock(bno));
- agno = XFS_FSB_TO_AGNO(mp, bno);
- agbno = XFS_FSB_TO_AGBNO(mp, bno);
- ASSERT(agno < mp->m_sb.sb_agcount);
- ASSERT(agbno < mp->m_sb.sb_agblocks);
- ASSERT(len < mp->m_sb.sb_agblocks);
- ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
-#endif
- ASSERT(xfs_bmap_free_item_zone != NULL);
- new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
- new->xbfi_startblock = bno;
- new->xbfi_blockcount = (xfs_extlen_t)len;
- for (prev = NULL, cur = flist->xbf_first;
- cur != NULL;
- prev = cur, cur = cur->xbfi_next) {
- if (cur->xbfi_startblock >= bno)
- break;
- }
- if (prev)
- prev->xbfi_next = new;
- else
- flist->xbf_first = new;
- new->xbfi_next = cur;
- flist->xbf_count++;
-}
-
-/*
- * Compute and fill in the value of the maximum depth of a bmap btree
- * in this filesystem. Done once, during mount.
- */
-void
-xfs_bmap_compute_maxlevels(
- xfs_mount_t *mp, /* file system mount structure */
- int whichfork) /* data or attr fork */
-{
- int level; /* btree level */
- uint maxblocks; /* max blocks at this level */
- uint maxleafents; /* max leaf entries possible */
- int maxrootrecs; /* max records in root block */
- int minleafrecs; /* min records in leaf block */
- int minnoderecs; /* min records in node block */
- int sz; /* root block size */
-
- /*
- * The maximum number of extents in a file, hence the maximum
- * number of leaf entries, is controlled by the type of di_nextents
- * (a signed 32-bit number, xfs_extnum_t), or by di_anextents
- * (a signed 16-bit number, xfs_aextnum_t).
- *
- * Note that we can no longer assume that if we are in ATTR1 that
- * the fork offset of all the inodes will be
- * (xfs_default_attroffset(ip) >> 3) because we could have mounted
- * with ATTR2 and then mounted back with ATTR1, keeping the
- * di_forkoff's fixed but probably at various positions. Therefore,
- * for both ATTR1 and ATTR2 we have to assume the worst case scenario
- * of a minimum size available.
- */
- if (whichfork == XFS_DATA_FORK) {
- maxleafents = MAXEXTNUM;
- sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
- } else {
- maxleafents = MAXAEXTNUM;
- sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
- }
- maxrootrecs = xfs_bmdr_maxrecs(mp, sz, 0);
- minleafrecs = mp->m_bmap_dmnr[0];
- minnoderecs = mp->m_bmap_dmnr[1];
- maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
- for (level = 1; maxblocks > 1; level++) {
- if (maxblocks <= maxrootrecs)
- maxblocks = 1;
- else
- maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
- }
- mp->m_bm_maxlevels[whichfork] = level;
-}
-
-/*
- * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
- * caller. Frees all the extents that need freeing, which must be done
- * last due to locking considerations. We never free any extents in
- * the first transaction.
- *
- * Return 1 if the given transaction was committed and a new one
- * started, and 0 otherwise in the committed parameter.
- */
-int /* error */
-xfs_bmap_finish(
- xfs_trans_t **tp, /* transaction pointer addr */
- xfs_bmap_free_t *flist, /* i/o: list extents to free */
- int *committed) /* xact committed or not */
-{
- xfs_efd_log_item_t *efd; /* extent free data */
- xfs_efi_log_item_t *efi; /* extent free intention */
- int error; /* error return value */
- xfs_bmap_free_item_t *free; /* free extent item */
- unsigned int logres; /* new log reservation */
- unsigned int logcount; /* new log count */
- xfs_mount_t *mp; /* filesystem mount structure */
- xfs_bmap_free_item_t *next; /* next item on free list */
- xfs_trans_t *ntp; /* new transaction pointer */
-
- ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
- if (flist->xbf_count == 0) {
- *committed = 0;
- return 0;
- }
- ntp = *tp;
- efi = xfs_trans_get_efi(ntp, flist->xbf_count);
- for (free = flist->xbf_first; free; free = free->xbfi_next)
- xfs_trans_log_efi_extent(ntp, efi, free->xbfi_startblock,
- free->xbfi_blockcount);
- logres = ntp->t_log_res;
- logcount = ntp->t_log_count;
- ntp = xfs_trans_dup(*tp);
- error = xfs_trans_commit(*tp, 0);
- *tp = ntp;
- *committed = 1;
- /*
- * We have a new transaction, so we should return committed=1,
- * even though we're returning an error.
- */
- if (error)
- return error;
-
- /*
- * transaction commit worked ok so we can drop the extra ticket
- * reference that we gained in xfs_trans_dup()
- */
- xfs_log_ticket_put(ntp->t_ticket);
-
- if ((error = xfs_trans_reserve(ntp, 0, logres, 0, XFS_TRANS_PERM_LOG_RES,
- logcount)))
- return error;
- efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count);
- for (free = flist->xbf_first; free != NULL; free = next) {
- next = free->xbfi_next;
- if ((error = xfs_free_extent(ntp, free->xbfi_startblock,
- free->xbfi_blockcount))) {
- /*
- * The bmap free list will be cleaned up at a
- * higher level. The EFI will be canceled when
- * this transaction is aborted.
- * Need to force shutdown here to make sure it
- * happens, since this transaction may not be
- * dirty yet.
- */
- mp = ntp->t_mountp;
- if (!XFS_FORCED_SHUTDOWN(mp))
- xfs_force_shutdown(mp,
- (error == EFSCORRUPTED) ?
- SHUTDOWN_CORRUPT_INCORE :
- SHUTDOWN_META_IO_ERROR);
- return error;
- }
- xfs_trans_log_efd_extent(ntp, efd, free->xbfi_startblock,
- free->xbfi_blockcount);
- xfs_bmap_del_free(flist, NULL, free);
- }
- return 0;
-}
-
-/*
- * Free up any items left in the list.
- */
-void
-xfs_bmap_cancel(
- xfs_bmap_free_t *flist) /* list of bmap_free_items */
-{
- xfs_bmap_free_item_t *free; /* free list item */
- xfs_bmap_free_item_t *next;
-
- if (flist->xbf_count == 0)
- return;
- ASSERT(flist->xbf_first != NULL);
- for (free = flist->xbf_first; free; free = next) {
- next = free->xbfi_next;
- xfs_bmap_del_free(flist, NULL, free);
- }
- ASSERT(flist->xbf_count == 0);
-}
-
-/*
- * Returns the file-relative block number of the first unused block(s)
- * in the file with at least "len" logically contiguous blocks free.
- * This is the lowest-address hole if the file has holes, else the first block
- * past the end of file.
- * Return 0 if the file is currently local (in-inode).
- */
-int /* error */
-xfs_bmap_first_unused(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode */
- xfs_extlen_t len, /* size of hole to find */
- xfs_fileoff_t *first_unused, /* unused block */
- int whichfork) /* data or attr fork */
-{
- int error; /* error return value */
- int idx; /* extent record index */
- xfs_ifork_t *ifp; /* inode fork pointer */
- xfs_fileoff_t lastaddr; /* last block number seen */
- xfs_fileoff_t lowest; /* lowest useful block */
- xfs_fileoff_t max; /* starting useful block */
- xfs_fileoff_t off; /* offset for this block */
- xfs_extnum_t nextents; /* number of extent entries */
-
- ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE ||
- XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ||
- XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
- if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
- *first_unused = 0;
- return 0;
- }
- ifp = XFS_IFORK_PTR(ip, whichfork);
- if (!(ifp->if_flags & XFS_IFEXTENTS) &&
- (error = xfs_iread_extents(tp, ip, whichfork)))
- return error;
- lowest = *first_unused;
- nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
- for (idx = 0, lastaddr = 0, max = lowest; idx < nextents; idx++) {
- xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx);
- off = xfs_bmbt_get_startoff(ep);
- /*
- * See if the hole before this extent will work.
- */
- if (off >= lowest + len && off - max >= len) {
- *first_unused = max;
- return 0;
- }
- lastaddr = off + xfs_bmbt_get_blockcount(ep);
- max = XFS_FILEOFF_MAX(lastaddr, lowest);
- }
- *first_unused = max;
- return 0;
-}
-
-/*
- * Returns the file-relative block number of the last block + 1 before
- * last_block (input value) in the file.
- * This is not based on i_size, it is based on the extent records.
- * Returns 0 for local files, as they do not have extent records.
- */
-int /* error */
-xfs_bmap_last_before(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode */
- xfs_fileoff_t *last_block, /* last block */
- int whichfork) /* data or attr fork */
-{
- xfs_fileoff_t bno; /* input file offset */
- int eof; /* hit end of file */
- xfs_bmbt_rec_host_t *ep; /* pointer to last extent */
- int error; /* error return value */
- xfs_bmbt_irec_t got; /* current extent value */
- xfs_ifork_t *ifp; /* inode fork pointer */
- xfs_extnum_t lastx; /* last extent used */
- xfs_bmbt_irec_t prev; /* previous extent value */
-
- if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
- XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
- XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL)
- return XFS_ERROR(EIO);
- if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
- *last_block = 0;
- return 0;
- }
- ifp = XFS_IFORK_PTR(ip, whichfork);
- if (!(ifp->if_flags & XFS_IFEXTENTS) &&
- (error = xfs_iread_extents(tp, ip, whichfork)))
- return error;
- bno = *last_block - 1;
- ep = xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got,
- &prev);
- if (eof || xfs_bmbt_get_startoff(ep) > bno) {
- if (prev.br_startoff == NULLFILEOFF)
- *last_block = 0;
- else
- *last_block = prev.br_startoff + prev.br_blockcount;
- }
- /*
- * Otherwise *last_block is already the right answer.
- */
- return 0;
-}
-
-STATIC int
-xfs_bmap_last_extent(
- struct xfs_trans *tp,
- struct xfs_inode *ip,
- int whichfork,
- struct xfs_bmbt_irec *rec,
- int *is_empty)
-{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
- int error;
- int nextents;
-
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(tp, ip, whichfork);
- if (error)
- return error;
- }
-
- nextents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
- if (nextents == 0) {
- *is_empty = 1;
- return 0;
- }
-
- xfs_bmbt_get_all(xfs_iext_get_ext(ifp, nextents - 1), rec);
- *is_empty = 0;
- return 0;
-}
-
-/*
- * Check the last inode extent to determine whether this allocation will result
- * in blocks being allocated at the end of the file. When we allocate new data
- * blocks at the end of the file which do not start at the previous data block,
- * we will try to align the new blocks at stripe unit boundaries.
- *
- * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be
- * at, or past the EOF.
- */
-STATIC int
-xfs_bmap_isaeof(
- struct xfs_bmalloca *bma,
- int whichfork)
-{
- struct xfs_bmbt_irec rec;
- int is_empty;
- int error;
-
- bma->aeof = 0;
- error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
- &is_empty);
- if (error || is_empty)
- return error;
-
- /*
- * Check if we are allocation or past the last extent, or at least into
- * the last delayed allocated extent.
- */
- bma->aeof = bma->offset >= rec.br_startoff + rec.br_blockcount ||
- (bma->offset >= rec.br_startoff &&
- isnullstartblock(rec.br_startblock));
- return 0;
-}
-
-/*
- * Check if the endoff is outside the last extent. If so the caller will grow
- * the allocation to a stripe unit boundary. All offsets are considered outside
- * the end of file for an empty fork, so 1 is returned in *eof in that case.
- */
-int
-xfs_bmap_eof(
- struct xfs_inode *ip,
- xfs_fileoff_t endoff,
- int whichfork,
- int *eof)
-{
- struct xfs_bmbt_irec rec;
- int error;
-
- error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, eof);
- if (error || *eof)
- return error;
-
- *eof = endoff >= rec.br_startoff + rec.br_blockcount;
- return 0;
-}
-
-/*
- * Returns the file-relative block number of the first block past eof in
- * the file. This is not based on i_size, it is based on the extent records.
- * Returns 0 for local files, as they do not have extent records.
- */
-int
-xfs_bmap_last_offset(
- struct xfs_trans *tp,
- struct xfs_inode *ip,
- xfs_fileoff_t *last_block,
- int whichfork)
-{
- struct xfs_bmbt_irec rec;
- int is_empty;
- int error;
-
- *last_block = 0;
-
- if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL)
- return 0;
-
- if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
- XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS)
- return XFS_ERROR(EIO);
-
- error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty);
- if (error || is_empty)
- return error;
-
- *last_block = rec.br_startoff + rec.br_blockcount;
- return 0;
-}
-
-/*
- * Returns whether the selected fork of the inode has exactly one
- * block or not. For the data fork we check this matches di_size,
- * implying the file's range is 0..bsize-1.
- */
-int /* 1=>1 block, 0=>otherwise */
-xfs_bmap_one_block(
- xfs_inode_t *ip, /* incore inode */
- int whichfork) /* data or attr fork */
-{
- xfs_bmbt_rec_host_t *ep; /* ptr to fork's extent */
- xfs_ifork_t *ifp; /* inode fork pointer */
- int rval; /* return value */
- xfs_bmbt_irec_t s; /* internal version of extent */
-
-#ifndef DEBUG
- if (whichfork == XFS_DATA_FORK)
- return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize;
-#endif /* !DEBUG */
- if (XFS_IFORK_NEXTENTS(ip, whichfork) != 1)
- return 0;
- if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS)
- return 0;
- ifp = XFS_IFORK_PTR(ip, whichfork);
- ASSERT(ifp->if_flags & XFS_IFEXTENTS);
- ep = xfs_iext_get_ext(ifp, 0);
- xfs_bmbt_get_all(ep, &s);
- rval = s.br_startoff == 0 && s.br_blockcount == 1;
- if (rval && whichfork == XFS_DATA_FORK)
- ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize);
- return rval;
-}
-
-STATIC int
-xfs_bmap_sanity_check(
- struct xfs_mount *mp,
- struct xfs_buf *bp,
- int level)
-{
- struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
-
- if (block->bb_magic != cpu_to_be32(XFS_BMAP_MAGIC) ||
- be16_to_cpu(block->bb_level) != level ||
- be16_to_cpu(block->bb_numrecs) == 0 ||
- be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0])
- return 0;
- return 1;
-}
-
-/*
- * Read in the extents to if_extents.
- * All inode fields are set up by caller, we just traverse the btree
- * and copy the records in. If the file system cannot contain unwritten
- * extents, the records are checked for no "state" flags.
- */
-int /* error */
-xfs_bmap_read_extents(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode */
- int whichfork) /* data or attr fork */
-{
- struct xfs_btree_block *block; /* current btree block */
- xfs_fsblock_t bno; /* block # of "block" */
- xfs_buf_t *bp; /* buffer for "block" */
- int error; /* error return value */
- xfs_exntfmt_t exntf; /* XFS_EXTFMT_NOSTATE, if checking */
- xfs_extnum_t i, j; /* index into the extents list */
- xfs_ifork_t *ifp; /* fork structure */
- int level; /* btree level, for checking */
- xfs_mount_t *mp; /* file system mount structure */
- __be64 *pp; /* pointer to block address */
- /* REFERENCED */
- xfs_extnum_t room; /* number of entries there's room for */
-
- bno = NULLFSBLOCK;
- mp = ip->i_mount;
- ifp = XFS_IFORK_PTR(ip, whichfork);
- exntf = (whichfork != XFS_DATA_FORK) ? XFS_EXTFMT_NOSTATE :
- XFS_EXTFMT_INODE(ip);
- block = ifp->if_broot;
- /*
- * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
- */
- level = be16_to_cpu(block->bb_level);
- ASSERT(level > 0);
- pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
- bno = be64_to_cpu(*pp);
- ASSERT(bno != NULLDFSBNO);
- ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
- ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
- /*
- * Go down the tree until leaf level is reached, following the first
- * pointer (leftmost) at each level.
- */
- while (level-- > 0) {
- if ((error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
- XFS_BMAP_BTREE_REF)))
- return error;
- block = XFS_BUF_TO_BLOCK(bp);
- XFS_WANT_CORRUPTED_GOTO(
- xfs_bmap_sanity_check(mp, bp, level),
- error0);
- if (level == 0)
- break;
- pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
- bno = be64_to_cpu(*pp);
- XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
- xfs_trans_brelse(tp, bp);
- }
- /*
- * Here with bp and block set to the leftmost leaf node in the tree.
- */
- room = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
- i = 0;
- /*
- * Loop over all leaf nodes. Copy information to the extent records.
- */
- for (;;) {
- xfs_bmbt_rec_t *frp;
- xfs_fsblock_t nextbno;
- xfs_extnum_t num_recs;
- xfs_extnum_t start;
-
- num_recs = xfs_btree_get_numrecs(block);
- if (unlikely(i + num_recs > room)) {
- ASSERT(i + num_recs <= room);
- xfs_warn(ip->i_mount,
- "corrupt dinode %Lu, (btree extents).",
- (unsigned long long) ip->i_ino);
- XFS_CORRUPTION_ERROR("xfs_bmap_read_extents(1)",
- XFS_ERRLEVEL_LOW, ip->i_mount, block);
- goto error0;
- }
- XFS_WANT_CORRUPTED_GOTO(
- xfs_bmap_sanity_check(mp, bp, 0),
- error0);
- /*
- * Read-ahead the next leaf block, if any.
- */
- nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
- if (nextbno != NULLFSBLOCK)
- xfs_btree_reada_bufl(mp, nextbno, 1);
- /*
- * Copy records into the extent records.
- */
- frp = XFS_BMBT_REC_ADDR(mp, block, 1);
- start = i;
- for (j = 0; j < num_recs; j++, i++, frp++) {
- xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i);
- trp->l0 = be64_to_cpu(frp->l0);
- trp->l1 = be64_to_cpu(frp->l1);
- }
- if (exntf == XFS_EXTFMT_NOSTATE) {
- /*
- * Check all attribute bmap btree records and
- * any "older" data bmap btree records for a
- * set bit in the "extent flag" position.
- */
- if (unlikely(xfs_check_nostate_extents(ifp,
- start, num_recs))) {
- XFS_ERROR_REPORT("xfs_bmap_read_extents(2)",
- XFS_ERRLEVEL_LOW,
- ip->i_mount);
- goto error0;
- }
- }
- xfs_trans_brelse(tp, bp);
- bno = nextbno;
- /*
- * If we've reached the end, stop.
- */
- if (bno == NULLFSBLOCK)
- break;
- if ((error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
- XFS_BMAP_BTREE_REF)))
- return error;
- block = XFS_BUF_TO_BLOCK(bp);
- }
- ASSERT(i == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
- ASSERT(i == XFS_IFORK_NEXTENTS(ip, whichfork));
- XFS_BMAP_TRACE_EXLIST(ip, i, whichfork);
- return 0;
-error0:
- xfs_trans_brelse(tp, bp);
- return XFS_ERROR(EFSCORRUPTED);
-}
-
-#ifdef DEBUG
-/*
- * Add bmap trace insert entries for all the contents of the extent records.
- */
-void
-xfs_bmap_trace_exlist(
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_extnum_t cnt, /* count of entries in the list */
- int whichfork, /* data or attr fork */
- unsigned long caller_ip)
-{
- xfs_extnum_t idx; /* extent record index */
- xfs_ifork_t *ifp; /* inode fork pointer */
- int state = 0;
-
- if (whichfork == XFS_ATTR_FORK)
- state |= BMAP_ATTRFORK;
-
- ifp = XFS_IFORK_PTR(ip, whichfork);
- ASSERT(cnt == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
- for (idx = 0; idx < cnt; idx++)
- trace_xfs_extlist(ip, idx, whichfork, caller_ip);
-}
-
-/*
- * Validate that the bmbt_irecs being returned from bmapi are valid
- * given the callers original parameters. Specifically check the
- * ranges of the returned irecs to ensure that they only extent beyond
- * the given parameters if the XFS_BMAPI_ENTIRE flag was set.
- */
-STATIC void
-xfs_bmap_validate_ret(
- xfs_fileoff_t bno,
- xfs_filblks_t len,
- int flags,
- xfs_bmbt_irec_t *mval,
- int nmap,
- int ret_nmap)
-{
- int i; /* index to map values */
-
- ASSERT(ret_nmap <= nmap);
-
- for (i = 0; i < ret_nmap; i++) {
- ASSERT(mval[i].br_blockcount > 0);
- if (!(flags & XFS_BMAPI_ENTIRE)) {
- ASSERT(mval[i].br_startoff >= bno);
- ASSERT(mval[i].br_blockcount <= len);
- ASSERT(mval[i].br_startoff + mval[i].br_blockcount <=
- bno + len);
- } else {
- ASSERT(mval[i].br_startoff < bno + len);
- ASSERT(mval[i].br_startoff + mval[i].br_blockcount >
- bno);
- }
- ASSERT(i == 0 ||
- mval[i - 1].br_startoff + mval[i - 1].br_blockcount ==
- mval[i].br_startoff);
- ASSERT(mval[i].br_startblock != DELAYSTARTBLOCK &&
- mval[i].br_startblock != HOLESTARTBLOCK);
- ASSERT(mval[i].br_state == XFS_EXT_NORM ||
- mval[i].br_state == XFS_EXT_UNWRITTEN);
- }
-}
-#endif /* DEBUG */
-
-
-/*
* Trim the returned map to the required bounds
*/
STATIC void
@@ -4363,6 +4044,7 @@ xfs_bmapi_read(
ASSERT(*nmap >= 1);
ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK|XFS_BMAPI_ENTIRE|
XFS_BMAPI_IGSTATE)));
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
@@ -4557,6 +4239,7 @@ xfs_bmapi_delay(
ASSERT(*nmap >= 1);
ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
ASSERT(!(flags & ~XFS_BMAPI_ENTIRE));
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
@@ -4615,23 +4298,19 @@ xfs_bmapi_delay(
}
-STATIC int
+static int
xfs_bmapi_allocate(
- struct xfs_bmalloca *bma,
- int flags)
+ struct xfs_bmalloca *bma)
{
struct xfs_mount *mp = bma->ip->i_mount;
- int whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
+ int whichfork = (bma->flags & XFS_BMAPI_ATTRFORK) ?
XFS_ATTR_FORK : XFS_DATA_FORK;
struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork);
int tmp_logflags = 0;
int error;
- int rt;
ASSERT(bma->length > 0);
- rt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(bma->ip);
-
/*
* For the wasdelay case, we could also just allocate the stuff asked
* for in this bmap call but that wouldn't be as good.
@@ -4654,19 +4333,19 @@ xfs_bmapi_allocate(
* Indicate if this is the first user data in the file, or just any
* user data.
*/
- if (!(flags & XFS_BMAPI_METADATA)) {
+ if (!(bma->flags & XFS_BMAPI_METADATA)) {
bma->userdata = (bma->offset == 0) ?
XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;
}
- bma->minlen = (flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
+ bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
/*
* Only want to do the alignment at the eof if it is userdata and
* allocation length is larger than a stripe unit.
*/
if (mp->m_dalign && bma->length >= mp->m_dalign &&
- !(flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {
+ !(bma->flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {
error = xfs_bmap_isaeof(bma, whichfork);
if (error)
return error;
@@ -4706,7 +4385,7 @@ xfs_bmapi_allocate(
* A wasdelay extent has been initialized, so shouldn't be flagged
* as unwritten.
*/
- if (!bma->wasdel && (flags & XFS_BMAPI_PREALLOC) &&
+ if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) &&
xfs_sb_version_hasextflgbit(&mp->m_sb))
bma->got.br_state = XFS_EXT_UNWRITTEN;
@@ -4822,7 +4501,7 @@ xfs_bmapi_write(
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp;
- struct xfs_bmalloca bma = { 0 }; /* args for xfs_bmap_alloc */
+ struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */
xfs_fileoff_t end; /* end of mapped file region */
int eof; /* after the end of extents */
int error; /* error return */
@@ -4845,20 +4524,20 @@ xfs_bmapi_write(
orig_mval = mval;
orig_nmap = *nmap;
#endif
+ whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
+ XFS_ATTR_FORK : XFS_DATA_FORK;
ASSERT(*nmap >= 1);
ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
ASSERT(!(flags & XFS_BMAPI_IGSTATE));
ASSERT(tp != NULL);
ASSERT(len > 0);
-
- whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
- XFS_ATTR_FORK : XFS_DATA_FORK;
+ ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL);
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
- XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
- XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL),
+ XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
XFS_ERROR_REPORT("xfs_bmapi_write", XFS_ERRLEVEL_LOW, mp);
return XFS_ERROR(EFSCORRUPTED);
@@ -4871,13 +4550,6 @@ xfs_bmapi_write(
XFS_STATS_INC(xs_blk_mapw);
- if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
- error = xfs_bmap_local_to_extents(tp, ip, firstblock, total,
- &bma.logflags, whichfork);
- if (error)
- goto error0;
- }
-
if (*firstblock == NULLFSBLOCK) {
if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE)
bma.minleft = be16_to_cpu(ifp->if_broot->bb_level) + 1;
@@ -4919,6 +4591,7 @@ xfs_bmapi_write(
bma.conv = !!(flags & XFS_BMAPI_CONVERT);
bma.wasdel = wasdelay;
bma.offset = bno;
+ bma.flags = flags;
/*
* There's a 32/64 bit type mismatch between the
@@ -4934,7 +4607,7 @@ xfs_bmapi_write(
ASSERT(len > 0);
ASSERT(bma.length > 0);
- error = xfs_bmapi_allocate(&bma, flags);
+ error = xfs_bmapi_allocate(&bma);
if (error)
goto error0;
if (bma.blkno == NULLFSBLOCK)
@@ -5032,6 +4705,328 @@ error0:
}
/*
+ * Called by xfs_bmapi to update file extent records and the btree
+ * after removing space (or undoing a delayed allocation).
+ */
+STATIC int /* error */
+xfs_bmap_del_extent(
+ xfs_inode_t *ip, /* incore inode pointer */
+ xfs_trans_t *tp, /* current transaction pointer */
+ xfs_extnum_t *idx, /* extent number to update/delete */
+ xfs_bmap_free_t *flist, /* list of extents to be freed */
+ xfs_btree_cur_t *cur, /* if null, not a btree */
+ xfs_bmbt_irec_t *del, /* data to remove from extents */
+ int *logflagsp, /* inode logging flags */
+ int whichfork) /* data or attr fork */
+{
+ xfs_filblks_t da_new; /* new delay-alloc indirect blocks */
+ xfs_filblks_t da_old; /* old delay-alloc indirect blocks */
+ xfs_fsblock_t del_endblock=0; /* first block past del */
+ xfs_fileoff_t del_endoff; /* first offset past del */
+ int delay; /* current block is delayed allocated */
+ int do_fx; /* free extent at end of routine */
+ xfs_bmbt_rec_host_t *ep; /* current extent entry pointer */
+ int error; /* error return value */
+ int flags; /* inode logging flags */
+ xfs_bmbt_irec_t got; /* current extent entry */
+ xfs_fileoff_t got_endoff; /* first offset past got */
+ int i; /* temp state */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ xfs_mount_t *mp; /* mount structure */
+ xfs_filblks_t nblks; /* quota/sb block count */
+ xfs_bmbt_irec_t new; /* new record to be inserted */
+ /* REFERENCED */
+ uint qfield; /* quota field to update */
+ xfs_filblks_t temp; /* for indirect length calculations */
+ xfs_filblks_t temp2; /* for indirect length calculations */
+ int state = 0;
+
+ XFS_STATS_INC(xs_del_exlist);
+
+ if (whichfork == XFS_ATTR_FORK)
+ state |= BMAP_ATTRFORK;
+
+ mp = ip->i_mount;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ ASSERT((*idx >= 0) && (*idx < ifp->if_bytes /
+ (uint)sizeof(xfs_bmbt_rec_t)));
+ ASSERT(del->br_blockcount > 0);
+ ep = xfs_iext_get_ext(ifp, *idx);
+ xfs_bmbt_get_all(ep, &got);
+ ASSERT(got.br_startoff <= del->br_startoff);
+ del_endoff = del->br_startoff + del->br_blockcount;
+ got_endoff = got.br_startoff + got.br_blockcount;
+ ASSERT(got_endoff >= del_endoff);
+ delay = isnullstartblock(got.br_startblock);
+ ASSERT(isnullstartblock(del->br_startblock) == delay);
+ flags = 0;
+ qfield = 0;
+ error = 0;
+ /*
+ * If deleting a real allocation, must free up the disk space.
+ */
+ if (!delay) {
+ flags = XFS_ILOG_CORE;
+ /*
+ * Realtime allocation. Free it and record di_nblocks update.
+ */
+ if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
+ xfs_fsblock_t bno;
+ xfs_filblks_t len;
+
+ ASSERT(do_mod(del->br_blockcount,
+ mp->m_sb.sb_rextsize) == 0);
+ ASSERT(do_mod(del->br_startblock,
+ mp->m_sb.sb_rextsize) == 0);
+ bno = del->br_startblock;
+ len = del->br_blockcount;
+ do_div(bno, mp->m_sb.sb_rextsize);
+ do_div(len, mp->m_sb.sb_rextsize);
+ error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len);
+ if (error)
+ goto done;
+ do_fx = 0;
+ nblks = len * mp->m_sb.sb_rextsize;
+ qfield = XFS_TRANS_DQ_RTBCOUNT;
+ }
+ /*
+ * Ordinary allocation.
+ */
+ else {
+ do_fx = 1;
+ nblks = del->br_blockcount;
+ qfield = XFS_TRANS_DQ_BCOUNT;
+ }
+ /*
+ * Set up del_endblock and cur for later.
+ */
+ del_endblock = del->br_startblock + del->br_blockcount;
+ if (cur) {
+ if ((error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
+ got.br_startblock, got.br_blockcount,
+ &i)))
+ goto done;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, done);
+ }
+ da_old = da_new = 0;
+ } else {
+ da_old = startblockval(got.br_startblock);
+ da_new = 0;
+ nblks = 0;
+ do_fx = 0;
+ }
+ /*
+ * Set flag value to use in switch statement.
+ * Left-contig is 2, right-contig is 1.
+ */
+ switch (((got.br_startoff == del->br_startoff) << 1) |
+ (got_endoff == del_endoff)) {
+ case 3:
+ /*
+ * Matches the whole extent. Delete the entry.
+ */
+ xfs_iext_remove(ip, *idx, 1,
+ whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0);
+ --*idx;
+ if (delay)
+ break;
+
+ XFS_IFORK_NEXT_SET(ip, whichfork,
+ XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
+ flags |= XFS_ILOG_CORE;
+ if (!cur) {
+ flags |= xfs_ilog_fext(whichfork);
+ break;
+ }
+ if ((error = xfs_btree_delete(cur, &i)))
+ goto done;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, done);
+ break;
+
+ case 2:
+ /*
+ * Deleting the first part of the extent.
+ */
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ xfs_bmbt_set_startoff(ep, del_endoff);
+ temp = got.br_blockcount - del->br_blockcount;
+ xfs_bmbt_set_blockcount(ep, temp);
+ if (delay) {
+ temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
+ da_old);
+ xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ da_new = temp;
+ break;
+ }
+ xfs_bmbt_set_startblock(ep, del_endblock);
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ if (!cur) {
+ flags |= xfs_ilog_fext(whichfork);
+ break;
+ }
+ if ((error = xfs_bmbt_update(cur, del_endoff, del_endblock,
+ got.br_blockcount - del->br_blockcount,
+ got.br_state)))
+ goto done;
+ break;
+
+ case 1:
+ /*
+ * Deleting the last part of the extent.
+ */
+ temp = got.br_blockcount - del->br_blockcount;
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ xfs_bmbt_set_blockcount(ep, temp);
+ if (delay) {
+ temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
+ da_old);
+ xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ da_new = temp;
+ break;
+ }
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ if (!cur) {
+ flags |= xfs_ilog_fext(whichfork);
+ break;
+ }
+ if ((error = xfs_bmbt_update(cur, got.br_startoff,
+ got.br_startblock,
+ got.br_blockcount - del->br_blockcount,
+ got.br_state)))
+ goto done;
+ break;
+
+ case 0:
+ /*
+ * Deleting the middle of the extent.
+ */
+ temp = del->br_startoff - got.br_startoff;
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ xfs_bmbt_set_blockcount(ep, temp);
+ new.br_startoff = del_endoff;
+ temp2 = got_endoff - del_endoff;
+ new.br_blockcount = temp2;
+ new.br_state = got.br_state;
+ if (!delay) {
+ new.br_startblock = del_endblock;
+ flags |= XFS_ILOG_CORE;
+ if (cur) {
+ if ((error = xfs_bmbt_update(cur,
+ got.br_startoff,
+ got.br_startblock, temp,
+ got.br_state)))
+ goto done;
+ if ((error = xfs_btree_increment(cur, 0, &i)))
+ goto done;
+ cur->bc_rec.b = new;
+ error = xfs_btree_insert(cur, &i);
+ if (error && error != ENOSPC)
+ goto done;
+ /*
+ * If get no-space back from btree insert,
+ * it tried a split, and we have a zero
+ * block reservation.
+ * Fix up our state and return the error.
+ */
+ if (error == ENOSPC) {
+ /*
+ * Reset the cursor, don't trust
+ * it after any insert operation.
+ */
+ if ((error = xfs_bmbt_lookup_eq(cur,
+ got.br_startoff,
+ got.br_startblock,
+ temp, &i)))
+ goto done;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, done);
+ /*
+ * Update the btree record back
+ * to the original value.
+ */
+ if ((error = xfs_bmbt_update(cur,
+ got.br_startoff,
+ got.br_startblock,
+ got.br_blockcount,
+ got.br_state)))
+ goto done;
+ /*
+ * Reset the extent record back
+ * to the original value.
+ */
+ xfs_bmbt_set_blockcount(ep,
+ got.br_blockcount);
+ flags = 0;
+ error = XFS_ERROR(ENOSPC);
+ goto done;
+ }
+ XFS_WANT_CORRUPTED_GOTO(i == 1, done);
+ } else
+ flags |= xfs_ilog_fext(whichfork);
+ XFS_IFORK_NEXT_SET(ip, whichfork,
+ XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
+ } else {
+ ASSERT(whichfork == XFS_DATA_FORK);
+ temp = xfs_bmap_worst_indlen(ip, temp);
+ xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
+ temp2 = xfs_bmap_worst_indlen(ip, temp2);
+ new.br_startblock = nullstartblock((int)temp2);
+ da_new = temp + temp2;
+ while (da_new > da_old) {
+ if (temp) {
+ temp--;
+ da_new--;
+ xfs_bmbt_set_startblock(ep,
+ nullstartblock((int)temp));
+ }
+ if (da_new == da_old)
+ break;
+ if (temp2) {
+ temp2--;
+ da_new--;
+ new.br_startblock =
+ nullstartblock((int)temp2);
+ }
+ }
+ }
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ xfs_iext_insert(ip, *idx + 1, 1, &new, state);
+ ++*idx;
+ break;
+ }
+ /*
+ * If we need to, add to list of extents to delete.
+ */
+ if (do_fx)
+ xfs_bmap_add_free(del->br_startblock, del->br_blockcount, flist,
+ mp);
+ /*
+ * Adjust inode # blocks in the file.
+ */
+ if (nblks)
+ ip->i_d.di_nblocks -= nblks;
+ /*
+ * Adjust quota data.
+ */
+ if (qfield)
+ xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks);
+
+ /*
+ * Account for change in delayed indirect blocks.
+ * Nothing to do for disk quota accounting here.
+ */
+ ASSERT(da_old >= da_new);
+ if (da_old > da_new) {
+ xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS,
+ (int64_t)(da_old - da_new), 0);
+ }
+done:
+ *logflagsp = flags;
+ return error;
+}
+
+/*
* Unmap (remove) blocks from a file.
* If nexts is nonzero then the number of extents to remove is limited to
* that value. If not all extents in the block range can be removed then
@@ -5087,6 +5082,7 @@ xfs_bunmapi(
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(len > 0);
ASSERT(nexts >= 0);
@@ -5412,772 +5408,199 @@ error0:
}
/*
- * returns 1 for success, 0 if we failed to map the extent.
- */
-STATIC int
-xfs_getbmapx_fix_eof_hole(
- xfs_inode_t *ip, /* xfs incore inode pointer */
- struct getbmapx *out, /* output structure */
- int prealloced, /* this is a file with
- * preallocated data space */
- __int64_t end, /* last block requested */
- xfs_fsblock_t startblock)
-{
- __int64_t fixlen;
- xfs_mount_t *mp; /* file system mount point */
- xfs_ifork_t *ifp; /* inode fork pointer */
- xfs_extnum_t lastx; /* last extent pointer */
- xfs_fileoff_t fileblock;
-
- if (startblock == HOLESTARTBLOCK) {
- mp = ip->i_mount;
- out->bmv_block = -1;
- fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
- fixlen -= out->bmv_offset;
- if (prealloced && out->bmv_offset + out->bmv_length == end) {
- /* Came to hole at EOF. Trim it. */
- if (fixlen <= 0)
- return 0;
- out->bmv_length = fixlen;
- }
- } else {
- if (startblock == DELAYSTARTBLOCK)
- out->bmv_block = -2;
- else
- out->bmv_block = xfs_fsb_to_db(ip, startblock);
- fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset);
- ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
- if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
- (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
- out->bmv_oflags |= BMV_OF_LAST;
- }
-
- return 1;
-}
-
-/*
- * Get inode's extents as described in bmv, and format for output.
- * Calls formatter to fill the user's buffer until all extents
- * are mapped, until the passed-in bmv->bmv_count slots have
- * been filled, or until the formatter short-circuits the loop,
- * if it is tracking filled-in extents on its own.
+ * Shift extent records to the left to cover a hole.
+ *
+ * The maximum number of extents to be shifted in a single operation
+ * is @num_exts, and @current_ext keeps track of the current extent
+ * index we have shifted. @offset_shift_fsb is the length by which each
+ * extent is shifted. If there is no hole to shift the extents
+ * into, this will be considered invalid operation and we abort immediately.
*/
-int /* error code */
-xfs_getbmap(
- xfs_inode_t *ip,
- struct getbmapx *bmv, /* user bmap structure */
- xfs_bmap_format_t formatter, /* format to user */
- void *arg) /* formatter arg */
+int
+xfs_bmap_shift_extents(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int *done,
+ xfs_fileoff_t start_fsb,
+ xfs_fileoff_t offset_shift_fsb,
+ xfs_extnum_t *current_ext,
+ xfs_fsblock_t *firstblock,
+ struct xfs_bmap_free *flist,
+ int num_exts)
{
- __int64_t bmvend; /* last block requested */
- int error = 0; /* return value */
- __int64_t fixlen; /* length for -1 case */
- int i; /* extent number */
- int lock; /* lock state */
- xfs_bmbt_irec_t *map; /* buffer for user's data */
- xfs_mount_t *mp; /* file system mount point */
- int nex; /* # of user extents can do */
- int nexleft; /* # of user extents left */
- int subnex; /* # of bmapi's can do */
- int nmap; /* number of map entries */
- struct getbmapx *out; /* output structure */
- int whichfork; /* data or attr fork */
- int prealloced; /* this is a file with
- * preallocated data space */
- int iflags; /* interface flags */
- int bmapi_flags; /* flags for xfs_bmapi */
- int cur_ext = 0;
+ struct xfs_btree_cur *cur;
+ struct xfs_bmbt_rec_host *gotp;
+ struct xfs_bmbt_irec got;
+ struct xfs_bmbt_irec left;
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *ifp;
+ xfs_extnum_t nexts = 0;
+ xfs_fileoff_t startoff;
+ int error = 0;
+ int i;
+ int whichfork = XFS_DATA_FORK;
+ int logflags;
+ xfs_filblks_t blockcount = 0;
+ int total_extents;
- mp = ip->i_mount;
- iflags = bmv->bmv_iflags;
- whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
-
- if (whichfork == XFS_ATTR_FORK) {
- if (XFS_IFORK_Q(ip)) {
- if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
- ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
- ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
- return XFS_ERROR(EINVAL);
- } else if (unlikely(
- ip->i_d.di_aformat != 0 &&
- ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
- XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
- ip->i_mount);
- return XFS_ERROR(EFSCORRUPTED);
- }
-
- prealloced = 0;
- fixlen = 1LL << 32;
- } else {
- if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
- ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
- ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
- return XFS_ERROR(EINVAL);
-
- if (xfs_get_extsz_hint(ip) ||
- ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
- prealloced = 1;
- fixlen = XFS_MAXIOFFSET(mp);
- } else {
- prealloced = 0;
- fixlen = XFS_ISIZE(ip);
- }
- }
-
- if (bmv->bmv_length == -1) {
- fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
- bmv->bmv_length =
- max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
- } else if (bmv->bmv_length == 0) {
- bmv->bmv_entries = 0;
- return 0;
- } else if (bmv->bmv_length < 0) {
- return XFS_ERROR(EINVAL);
- }
-
- nex = bmv->bmv_count - 1;
- if (nex <= 0)
- return XFS_ERROR(EINVAL);
- bmvend = bmv->bmv_offset + bmv->bmv_length;
-
-
- if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
- return XFS_ERROR(ENOMEM);
- out = kmem_zalloc(bmv->bmv_count * sizeof(struct getbmapx), KM_MAYFAIL);
- if (!out) {
- out = kmem_zalloc_large(bmv->bmv_count *
- sizeof(struct getbmapx));
- if (!out)
- return XFS_ERROR(ENOMEM);
- }
-
- xfs_ilock(ip, XFS_IOLOCK_SHARED);
- if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {
- if (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size) {
- error = xfs_flush_pages(ip, 0, -1, 0, FI_REMAPF);
- if (error)
- goto out_unlock_iolock;
- }
- /*
- * even after flushing the inode, there can still be delalloc
- * blocks on the inode beyond EOF due to speculative
- * preallocation. These are not removed until the release
- * function is called or the inode is inactivated. Hence we
- * cannot assert here that ip->i_delayed_blks == 0.
- */
+ if (unlikely(XFS_TEST_ERROR(
+ (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
+ mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+ XFS_ERROR_REPORT("xfs_bmap_shift_extents",
+ XFS_ERRLEVEL_LOW, mp);
+ return XFS_ERROR(EFSCORRUPTED);
}
- lock = xfs_ilock_map_shared(ip);
-
- /*
- * Don't let nex be bigger than the number of extents
- * we can have assuming alternating holes and real extents.
- */
- if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
- nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
-
- bmapi_flags = xfs_bmapi_aflag(whichfork);
- if (!(iflags & BMV_IF_PREALLOC))
- bmapi_flags |= XFS_BMAPI_IGSTATE;
-
- /*
- * Allocate enough space to handle "subnex" maps at a time.
- */
- error = ENOMEM;
- subnex = 16;
- map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
- if (!map)
- goto out_unlock_ilock;
-
- bmv->bmv_entries = 0;
-
- if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
- (whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
- error = 0;
- goto out_free_map;
- }
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return XFS_ERROR(EIO);
- nexleft = nex;
+ ASSERT(current_ext != NULL);
- do {
- nmap = (nexleft > subnex) ? subnex : nexleft;
- error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
- XFS_BB_TO_FSB(mp, bmv->bmv_length),
- map, &nmap, bmapi_flags);
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+ /* Read in all the extents */
+ error = xfs_iread_extents(tp, ip, whichfork);
if (error)
- goto out_free_map;
- ASSERT(nmap <= subnex);
-
- for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
- out[cur_ext].bmv_oflags = 0;
- if (map[i].br_state == XFS_EXT_UNWRITTEN)
- out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
- else if (map[i].br_startblock == DELAYSTARTBLOCK)
- out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
- out[cur_ext].bmv_offset =
- XFS_FSB_TO_BB(mp, map[i].br_startoff);
- out[cur_ext].bmv_length =
- XFS_FSB_TO_BB(mp, map[i].br_blockcount);
- out[cur_ext].bmv_unused1 = 0;
- out[cur_ext].bmv_unused2 = 0;
-
- /*
- * delayed allocation extents that start beyond EOF can
- * occur due to speculative EOF allocation when the
- * delalloc extent is larger than the largest freespace
- * extent at conversion time. These extents cannot be
- * converted by data writeback, so can exist here even
- * if we are not supposed to be finding delalloc
- * extents.
- */
- if (map[i].br_startblock == DELAYSTARTBLOCK &&
- map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
- ASSERT((iflags & BMV_IF_DELALLOC) != 0);
-
- if (map[i].br_startblock == HOLESTARTBLOCK &&
- whichfork == XFS_ATTR_FORK) {
- /* came to the end of attribute fork */
- out[cur_ext].bmv_oflags |= BMV_OF_LAST;
- goto out_free_map;
- }
-
- if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
- prealloced, bmvend,
- map[i].br_startblock))
- goto out_free_map;
-
- bmv->bmv_offset =
- out[cur_ext].bmv_offset +
- out[cur_ext].bmv_length;
- bmv->bmv_length =
- max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
-
- /*
- * In case we don't want to return the hole,
- * don't increase cur_ext so that we can reuse
- * it in the next loop.
- */
- if ((iflags & BMV_IF_NO_HOLES) &&
- map[i].br_startblock == HOLESTARTBLOCK) {
- memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
- continue;
- }
-
- nexleft--;
- bmv->bmv_entries++;
- cur_ext++;
- }
- } while (nmap && nexleft && bmv->bmv_length);
-
- out_free_map:
- kmem_free(map);
- out_unlock_ilock:
- xfs_iunlock_map_shared(ip, lock);
- out_unlock_iolock:
- xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-
- for (i = 0; i < cur_ext; i++) {
- int full = 0; /* user array is full */
-
- /* format results & advance arg */
- error = formatter(&arg, &out[i], &full);
- if (error || full)
- break;
- }
-
- if (is_vmalloc_addr(out))
- kmem_free_large(out);
- else
- kmem_free(out);
- return error;
-}
-
-#ifdef DEBUG
-STATIC struct xfs_buf *
-xfs_bmap_get_bp(
- struct xfs_btree_cur *cur,
- xfs_fsblock_t bno)
-{
- struct xfs_log_item_desc *lidp;
- int i;
-
- if (!cur)
- return NULL;
-
- for (i = 0; i < XFS_BTREE_MAXLEVELS; i++) {
- if (!cur->bc_bufs[i])
- break;
- if (XFS_BUF_ADDR(cur->bc_bufs[i]) == bno)
- return cur->bc_bufs[i];
- }
-
- /* Chase down all the log items to see if the bp is there */
- list_for_each_entry(lidp, &cur->bc_tp->t_items, lid_trans) {
- struct xfs_buf_log_item *bip;
- bip = (struct xfs_buf_log_item *)lidp->lid_item;
- if (bip->bli_item.li_type == XFS_LI_BUF &&
- XFS_BUF_ADDR(bip->bli_buf) == bno)
- return bip->bli_buf;
- }
-
- return NULL;
-}
-
-STATIC void
-xfs_check_block(
- struct xfs_btree_block *block,
- xfs_mount_t *mp,
- int root,
- short sz)
-{
- int i, j, dmxr;
- __be64 *pp, *thispa; /* pointer to block address */
- xfs_bmbt_key_t *prevp, *keyp;
-
- ASSERT(be16_to_cpu(block->bb_level) > 0);
-
- prevp = NULL;
- for( i = 1; i <= xfs_btree_get_numrecs(block); i++) {
- dmxr = mp->m_bmap_dmxr[0];
- keyp = XFS_BMBT_KEY_ADDR(mp, block, i);
-
- if (prevp) {
- ASSERT(be64_to_cpu(prevp->br_startoff) <
- be64_to_cpu(keyp->br_startoff));
- }
- prevp = keyp;
-
- /*
- * Compare the block numbers to see if there are dups.
- */
- if (root)
- pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, i, sz);
- else
- pp = XFS_BMBT_PTR_ADDR(mp, block, i, dmxr);
-
- for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) {
- if (root)
- thispa = XFS_BMAP_BROOT_PTR_ADDR(mp, block, j, sz);
- else
- thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
- if (*thispa == *pp) {
- xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld",
- __func__, j, i,
- (unsigned long long)be64_to_cpu(*thispa));
- panic("%s: ptrs are equal in node\n",
- __func__);
- }
- }
- }
-}
-
-/*
- * Check that the extents for the inode ip are in the right order in all
- * btree leaves.
- */
-
-STATIC void
-xfs_bmap_check_leaf_extents(
- xfs_btree_cur_t *cur, /* btree cursor or null */
- xfs_inode_t *ip, /* incore inode pointer */
- int whichfork) /* data or attr fork */
-{
- struct xfs_btree_block *block; /* current btree block */
- xfs_fsblock_t bno; /* block # of "block" */
- xfs_buf_t *bp; /* buffer for "block" */
- int error; /* error return value */
- xfs_extnum_t i=0, j; /* index into the extents list */
- xfs_ifork_t *ifp; /* fork structure */
- int level; /* btree level, for checking */
- xfs_mount_t *mp; /* file system mount structure */
- __be64 *pp; /* pointer to block address */
- xfs_bmbt_rec_t *ep; /* pointer to current extent */
- xfs_bmbt_rec_t last = {0, 0}; /* last extent in prev block */
- xfs_bmbt_rec_t *nextp; /* pointer to next extent */
- int bp_release = 0;
-
- if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) {
- return;
+ return error;
}
- bno = NULLFSBLOCK;
- mp = ip->i_mount;
- ifp = XFS_IFORK_PTR(ip, whichfork);
- block = ifp->if_broot;
/*
- * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
- */
- level = be16_to_cpu(block->bb_level);
- ASSERT(level > 0);
- xfs_check_block(block, mp, 1, ifp->if_broot_bytes);
- pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
- bno = be64_to_cpu(*pp);
-
- ASSERT(bno != NULLDFSBNO);
- ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
- ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
-
- /*
- * Go down the tree until leaf level is reached, following the first
- * pointer (leftmost) at each level.
+ * If *current_ext is 0, we would need to lookup the extent
+ * from where we would start shifting and store it in gotp.
*/
- while (level-- > 0) {
- /* See if buf is in cur first */
- bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
- if (bp) {
- bp_release = 0;
- } else {
- bp_release = 1;
- }
- if (!bp && (error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
- XFS_BMAP_BTREE_REF)))
- goto error_norelse;
- block = XFS_BUF_TO_BLOCK(bp);
- XFS_WANT_CORRUPTED_GOTO(
- xfs_bmap_sanity_check(mp, bp, level),
- error0);
- if (level == 0)
- break;
-
+ if (!*current_ext) {
+ gotp = xfs_iext_bno_to_ext(ifp, start_fsb, current_ext);
/*
- * Check this block for basic sanity (increasing keys and
- * no duplicate blocks).
+ * gotp can be null in 2 cases: 1) if there are no extents
+ * or 2) start_fsb lies in a hole beyond which there are
+ * no extents. Either way, we are done.
*/
-
- xfs_check_block(block, mp, 0, 0);
- pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
- bno = be64_to_cpu(*pp);
- XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
- if (bp_release) {
- bp_release = 0;
- xfs_trans_brelse(NULL, bp);
+ if (!gotp) {
+ *done = 1;
+ return 0;
}
}
- /*
- * Here with bp and block set to the leftmost leaf node in the tree.
- */
- i = 0;
+ /* We are going to change core inode */
+ logflags = XFS_ILOG_CORE;
+ if (ifp->if_flags & XFS_IFBROOT) {
+ cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
+ cur->bc_private.b.firstblock = *firstblock;
+ cur->bc_private.b.flist = flist;
+ cur->bc_private.b.flags = 0;
+ } else {
+ cur = NULL;
+ logflags |= XFS_ILOG_DEXT;
+ }
/*
- * Loop over all leaf nodes checking that all extents are in the right order.
+ * There may be delalloc extents in the data fork before the range we
+ * are collapsing out, so we cannot
+ * use the count of real extents here. Instead we have to calculate it
+ * from the incore fork.
*/
- for (;;) {
- xfs_fsblock_t nextbno;
- xfs_extnum_t num_recs;
-
+ total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+ while (nexts++ < num_exts && *current_ext < total_extents) {
- num_recs = xfs_btree_get_numrecs(block);
+ gotp = xfs_iext_get_ext(ifp, *current_ext);
+ xfs_bmbt_get_all(gotp, &got);
+ startoff = got.br_startoff - offset_shift_fsb;
/*
- * Read-ahead the next leaf block, if any.
+ * Before shifting extent into hole, make sure that the hole
+ * is large enough to accomodate the shift.
*/
+ if (*current_ext) {
+ xfs_bmbt_get_all(xfs_iext_get_ext(ifp,
+ *current_ext - 1), &left);
- nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
-
- /*
- * Check all the extents to make sure they are OK.
- * If we had a previous block, the last entry should
- * conform with the first entry in this one.
- */
-
- ep = XFS_BMBT_REC_ADDR(mp, block, 1);
- if (i) {
- ASSERT(xfs_bmbt_disk_get_startoff(&last) +
- xfs_bmbt_disk_get_blockcount(&last) <=
- xfs_bmbt_disk_get_startoff(ep));
- }
- for (j = 1; j < num_recs; j++) {
- nextp = XFS_BMBT_REC_ADDR(mp, block, j + 1);
- ASSERT(xfs_bmbt_disk_get_startoff(ep) +
- xfs_bmbt_disk_get_blockcount(ep) <=
- xfs_bmbt_disk_get_startoff(nextp));
- ep = nextp;
+ if (startoff < left.br_startoff + left.br_blockcount)
+ error = XFS_ERROR(EINVAL);
+ } else if (offset_shift_fsb > got.br_startoff) {
+ /*
+ * When first extent is shifted, offset_shift_fsb
+ * should be less than the stating offset of
+ * the first extent.
+ */
+ error = XFS_ERROR(EINVAL);
}
- last = *ep;
- i += num_recs;
- if (bp_release) {
- bp_release = 0;
- xfs_trans_brelse(NULL, bp);
- }
- bno = nextbno;
- /*
- * If we've reached the end, stop.
- */
- if (bno == NULLFSBLOCK)
- break;
+ if (error)
+ goto del_cursor;
- bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
- if (bp) {
- bp_release = 0;
- } else {
- bp_release = 1;
+ if (cur) {
+ error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
+ got.br_startblock,
+ got.br_blockcount,
+ &i);
+ if (error)
+ goto del_cursor;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
}
- if (!bp && (error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
- XFS_BMAP_BTREE_REF)))
- goto error_norelse;
- block = XFS_BUF_TO_BLOCK(bp);
- }
- if (bp_release) {
- bp_release = 0;
- xfs_trans_brelse(NULL, bp);
- }
- return;
-
-error0:
- xfs_warn(mp, "%s: at error0", __func__);
- if (bp_release)
- xfs_trans_brelse(NULL, bp);
-error_norelse:
- xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
- __func__, i);
- panic("%s: CORRUPTED BTREE OR SOMETHING", __func__);
- return;
-}
-#endif
-
-/*
- * Count fsblocks of the given fork.
- */
-int /* error */
-xfs_bmap_count_blocks(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_inode_t *ip, /* incore inode */
- int whichfork, /* data or attr fork */
- int *count) /* out: count of blocks */
-{
- struct xfs_btree_block *block; /* current btree block */
- xfs_fsblock_t bno; /* block # of "block" */
- xfs_ifork_t *ifp; /* fork structure */
- int level; /* btree level, for checking */
- xfs_mount_t *mp; /* file system mount structure */
- __be64 *pp; /* pointer to block address */
-
- bno = NULLFSBLOCK;
- mp = ip->i_mount;
- ifp = XFS_IFORK_PTR(ip, whichfork);
- if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
- xfs_bmap_count_leaves(ifp, 0,
- ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
- count);
- return 0;
- }
- /*
- * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
- */
- block = ifp->if_broot;
- level = be16_to_cpu(block->bb_level);
- ASSERT(level > 0);
- pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
- bno = be64_to_cpu(*pp);
- ASSERT(bno != NULLDFSBNO);
- ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
- ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
-
- if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
- XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
- mp);
- return XFS_ERROR(EFSCORRUPTED);
- }
-
- return 0;
-}
+ /* Check if we can merge 2 adjacent extents */
+ if (*current_ext &&
+ left.br_startoff + left.br_blockcount == startoff &&
+ left.br_startblock + left.br_blockcount ==
+ got.br_startblock &&
+ left.br_state == got.br_state &&
+ left.br_blockcount + got.br_blockcount <= MAXEXTLEN) {
+ blockcount = left.br_blockcount +
+ got.br_blockcount;
+ xfs_iext_remove(ip, *current_ext, 1, 0);
+ if (cur) {
+ error = xfs_btree_delete(cur, &i);
+ if (error)
+ goto del_cursor;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
+ }
+ XFS_IFORK_NEXT_SET(ip, whichfork,
+ XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
+ gotp = xfs_iext_get_ext(ifp, --*current_ext);
+ xfs_bmbt_get_all(gotp, &got);
-/*
- * Recursively walks each level of a btree
- * to count total fsblocks is use.
- */
-STATIC int /* error */
-xfs_bmap_count_tree(
- xfs_mount_t *mp, /* file system mount point */
- xfs_trans_t *tp, /* transaction pointer */
- xfs_ifork_t *ifp, /* inode fork pointer */
- xfs_fsblock_t blockno, /* file system block number */
- int levelin, /* level in btree */
- int *count) /* Count of blocks */
-{
- int error;
- xfs_buf_t *bp, *nbp;
- int level = levelin;
- __be64 *pp;
- xfs_fsblock_t bno = blockno;
- xfs_fsblock_t nextbno;
- struct xfs_btree_block *block, *nextblock;
- int numrecs;
-
- if ((error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF)))
- return error;
- *count += 1;
- block = XFS_BUF_TO_BLOCK(bp);
+ /* Make cursor point to the extent we will update */
+ if (cur) {
+ error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
+ got.br_startblock,
+ got.br_blockcount,
+ &i);
+ if (error)
+ goto del_cursor;
+ XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
+ }
- if (--level) {
- /* Not at node above leaves, count this level of nodes */
- nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
- while (nextbno != NULLFSBLOCK) {
- if ((error = xfs_btree_read_bufl(mp, tp, nextbno,
- 0, &nbp, XFS_BMAP_BTREE_REF)))
- return error;
- *count += 1;
- nextblock = XFS_BUF_TO_BLOCK(nbp);
- nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
- xfs_trans_brelse(tp, nbp);
+ xfs_bmbt_set_blockcount(gotp, blockcount);
+ got.br_blockcount = blockcount;
+ } else {
+ /* We have to update the startoff */
+ xfs_bmbt_set_startoff(gotp, startoff);
+ got.br_startoff = startoff;
}
- /* Dive to the next level */
- pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
- bno = be64_to_cpu(*pp);
- if (unlikely((error =
- xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
- xfs_trans_brelse(tp, bp);
- XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
- XFS_ERRLEVEL_LOW, mp);
- return XFS_ERROR(EFSCORRUPTED);
- }
- xfs_trans_brelse(tp, bp);
- } else {
- /* count all level 1 nodes and their leaves */
- for (;;) {
- nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
- numrecs = be16_to_cpu(block->bb_numrecs);
- xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
- xfs_trans_brelse(tp, bp);
- if (nextbno == NULLFSBLOCK)
- break;
- bno = nextbno;
- if ((error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
- XFS_BMAP_BTREE_REF)))
- return error;
- *count += 1;
- block = XFS_BUF_TO_BLOCK(bp);
+ if (cur) {
+ error = xfs_bmbt_update(cur, got.br_startoff,
+ got.br_startblock,
+ got.br_blockcount,
+ got.br_state);
+ if (error)
+ goto del_cursor;
}
- }
- return 0;
-}
-
-/*
- * Count leaf blocks given a range of extent records.
- */
-STATIC void
-xfs_bmap_count_leaves(
- xfs_ifork_t *ifp,
- xfs_extnum_t idx,
- int numrecs,
- int *count)
-{
- int b;
- for (b = 0; b < numrecs; b++) {
- xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b);
- *count += xfs_bmbt_get_blockcount(frp);
+ (*current_ext)++;
+ total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
}
-}
-
-/*
- * Count leaf blocks given a range of extent records originally
- * in btree format.
- */
-STATIC void
-xfs_bmap_disk_count_leaves(
- struct xfs_mount *mp,
- struct xfs_btree_block *block,
- int numrecs,
- int *count)
-{
- int b;
- xfs_bmbt_rec_t *frp;
-
- for (b = 1; b <= numrecs; b++) {
- frp = XFS_BMBT_REC_ADDR(mp, block, b);
- *count += xfs_bmbt_disk_get_blockcount(frp);
- }
-}
-
-/*
- * dead simple method of punching delalyed allocation blocks from a range in
- * the inode. Walks a block at a time so will be slow, but is only executed in
- * rare error cases so the overhead is not critical. This will alays punch out
- * both the start and end blocks, even if the ranges only partially overlap
- * them, so it is up to the caller to ensure that partial blocks are not
- * passed in.
- */
-int
-xfs_bmap_punch_delalloc_range(
- struct xfs_inode *ip,
- xfs_fileoff_t start_fsb,
- xfs_fileoff_t length)
-{
- xfs_fileoff_t remaining = length;
- int error = 0;
-
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
- do {
- int done;
- xfs_bmbt_irec_t imap;
- int nimaps = 1;
- xfs_fsblock_t firstblock;
- xfs_bmap_free_t flist;
-
- /*
- * Map the range first and check that it is a delalloc extent
- * before trying to unmap the range. Otherwise we will be
- * trying to remove a real extent (which requires a
- * transaction) or a hole, which is probably a bad idea...
- */
- error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
- XFS_BMAPI_ENTIRE);
-
- if (error) {
- /* something screwed, just bail */
- if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- xfs_alert(ip->i_mount,
- "Failed delalloc mapping lookup ino %lld fsb %lld.",
- ip->i_ino, start_fsb);
- }
- break;
- }
- if (!nimaps) {
- /* nothing there */
- goto next_block;
- }
- if (imap.br_startblock != DELAYSTARTBLOCK) {
- /* been converted, ignore */
- goto next_block;
- }
- WARN_ON(imap.br_blockcount == 0);
- /*
- * Note: while we initialise the firstblock/flist pair, they
- * should never be used because blocks should never be
- * allocated or freed for a delalloc extent and hence we need
- * don't cancel or finish them after the xfs_bunmapi() call.
- */
- xfs_bmap_init(&flist, &firstblock);
- error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
- &flist, &done);
- if (error)
- break;
+ /* Check if we are done */
+ if (*current_ext == total_extents)
+ *done = 1;
- ASSERT(!flist.xbf_count && !flist.xbf_first);
-next_block:
- start_fsb++;
- remaining--;
- } while(remaining > 0);
+del_cursor:
+ if (cur)
+ xfs_btree_del_cursor(cur,
+ error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+ xfs_trans_log_inode(tp, ip, logflags);
return error;
}
-
-/*
- * Convert the given file system block to a disk block. We have to treat it
- * differently based on whether the file is a real time file or not, because the
- * bmap code does.
- */
-xfs_daddr_t
-xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
-{
- return (XFS_IS_REALTIME_INODE(ip) ? \
- (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
- XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
-}
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 803b56d7ce1..b879ca56a64 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -106,36 +106,6 @@ static inline void xfs_bmap_init(xfs_bmap_free_t *flp, xfs_fsblock_t *fbp)
}
/*
- * Argument structure for xfs_bmap_alloc.
- */
-typedef struct xfs_bmalloca {
- xfs_fsblock_t *firstblock; /* i/o first block allocated */
- struct xfs_bmap_free *flist; /* bmap freelist */
- struct xfs_trans *tp; /* transaction pointer */
- struct xfs_inode *ip; /* incore inode pointer */
- struct xfs_bmbt_irec prev; /* extent before the new one */
- struct xfs_bmbt_irec got; /* extent after, or delayed */
-
- xfs_fileoff_t offset; /* offset in file filling in */
- xfs_extlen_t length; /* i/o length asked/allocated */
- xfs_fsblock_t blkno; /* starting block of new extent */
-
- struct xfs_btree_cur *cur; /* btree cursor */
- xfs_extnum_t idx; /* current extent index */
- int nallocs;/* number of extents alloc'd */
- int logflags;/* flags for transaction logging */
-
- xfs_extlen_t total; /* total blocks needed for xaction */
- xfs_extlen_t minlen; /* minimum allocation size (blocks) */
- xfs_extlen_t minleft; /* amount must be left after alloc */
- char eof; /* set if allocating past last extent */
- char wasdel; /* replacing a delayed allocation */
- char userdata;/* set if is user data */
- char aeof; /* allocated space at eof */
- char conv; /* overwriting unwritten extents */
-} xfs_bmalloca_t;
-
-/*
* Flags for xfs_bmap_add_extent*.
*/
#define BMAP_LEFT_CONTIG (1 << 0)
@@ -155,7 +125,17 @@ typedef struct xfs_bmalloca {
{ BMAP_RIGHT_FILLING, "RF" }, \
{ BMAP_ATTRFORK, "ATTR" }
-#if defined(__KERNEL) && defined(DEBUG)
+
+/*
+ * This macro is used to determine how many extents will be shifted
+ * in one write transaction. We could require two splits,
+ * an extent move on the first and an extent merge on the second,
+ * So it is proper that one extent is shifted inside write transaction
+ * at a time.
+ */
+#define XFS_BMAP_MAX_SHIFT_EXTENTS 1
+
+#ifdef DEBUG
void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
int whichfork, unsigned long caller_ip);
#define XFS_BMAP_TRACE_EXLIST(ip,c,w) \
@@ -165,6 +145,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
#endif
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
+void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
void xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len,
struct xfs_bmap_free *flist, struct xfs_mount *mp);
void xfs_bmap_cancel(struct xfs_bmap_free *flist);
@@ -173,8 +154,8 @@ int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
int xfs_bmap_last_before(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t *last_block, int whichfork);
-int xfs_bmap_last_offset(struct xfs_trans *tp, struct xfs_inode *ip,
- xfs_fileoff_t *unused, int whichfork);
+int xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
+ int whichfork);
int xfs_bmap_one_block(struct xfs_inode *ip, int whichfork);
int xfs_bmap_read_extents(struct xfs_trans *tp, struct xfs_inode *ip,
int whichfork);
@@ -196,24 +177,10 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
xfs_extnum_t num);
uint xfs_default_attroffset(struct xfs_inode *ip);
-
-#ifdef __KERNEL__
-/* bmap to userspace formatter - copy to user & advance pointer */
-typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *, int *);
-
-int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
- int *committed);
-int xfs_getbmap(struct xfs_inode *ip, struct getbmapx *bmv,
- xfs_bmap_format_t formatter, void *arg);
-int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
- int whichfork, int *eof);
-int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
- int whichfork, int *count);
-int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip,
- xfs_fileoff_t start_fsb, xfs_fileoff_t length);
-
-xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
-
-#endif /* __KERNEL__ */
+int xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip,
+ int *done, xfs_fileoff_t start_fsb,
+ xfs_fileoff_t offset_shift_fsb, xfs_extnum_t *current_ext,
+ xfs_fsblock_t *firstblock, struct xfs_bmap_free *flist,
+ int num_exts);
#endif /* __XFS_BMAP_H__ */
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index 862084a47a7..948836c4fd9 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -17,25 +17,26 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
-#include "xfs_itable.h"
+#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_quota.h"
+#include "xfs_trace.h"
+#include "xfs_cksum.h"
+#include "xfs_dinode.h"
/*
* Determine the extent state.
@@ -58,25 +59,32 @@ xfs_extent_state(
*/
void
xfs_bmdr_to_bmbt(
- struct xfs_mount *mp,
+ struct xfs_inode *ip,
xfs_bmdr_block_t *dblock,
int dblocklen,
struct xfs_btree_block *rblock,
int rblocklen)
{
+ struct xfs_mount *mp = ip->i_mount;
int dmxr;
xfs_bmbt_key_t *fkp;
__be64 *fpp;
xfs_bmbt_key_t *tkp;
__be64 *tpp;
- rblock->bb_magic = cpu_to_be32(XFS_BMAP_MAGIC);
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
+ XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino,
+ XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
+ else
+ xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
+ XFS_BMAP_MAGIC, 0, 0, ip->i_ino,
+ XFS_BTREE_LONG_PTRS);
+
rblock->bb_level = dblock->bb_level;
ASSERT(be16_to_cpu(rblock->bb_level) > 0);
rblock->bb_numrecs = dblock->bb_numrecs;
- rblock->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
- rblock->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
- dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+ dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
fkp = XFS_BMDR_KEY_ADDR(dblock, 1);
tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
@@ -423,13 +431,19 @@ xfs_bmbt_to_bmdr(
xfs_bmbt_key_t *tkp;
__be64 *tpp;
- ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_MAGIC));
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_CRC_MAGIC));
+ ASSERT(uuid_equal(&rblock->bb_u.l.bb_uuid, &mp->m_sb.sb_uuid));
+ ASSERT(rblock->bb_u.l.bb_blkno ==
+ cpu_to_be64(XFS_BUF_DADDR_NULL));
+ } else
+ ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_MAGIC));
ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLDFSBNO));
ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLDFSBNO));
ASSERT(rblock->bb_level != 0);
dblock->bb_level = rblock->bb_level;
dblock->bb_numrecs = rblock->bb_numrecs;
- dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+ dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
tkp = XFS_BMDR_KEY_ADDR(dblock, 1);
fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
@@ -505,7 +519,6 @@ xfs_bmbt_alloc_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *start,
union xfs_btree_ptr *new,
- int length,
int *stat)
{
xfs_alloc_arg_t args; /* block allocation args */
@@ -658,8 +671,7 @@ xfs_bmbt_get_dmaxrecs(
{
if (level != cur->bc_nlevels - 1)
return cur->bc_mp->m_bmap_dmxr[level != 0];
- return xfs_bmdr_maxrecs(cur->bc_mp, cur->bc_private.b.forksize,
- level == 0);
+ return xfs_bmdr_maxrecs(cur->bc_private.b.forksize, level == 0);
}
STATIC void
@@ -707,7 +719,96 @@ xfs_bmbt_key_diff(
cur->bc_rec.b.br_startoff;
}
-#ifdef DEBUG
+static bool
+xfs_bmbt_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ unsigned int level;
+
+ switch (block->bb_magic) {
+ case cpu_to_be32(XFS_BMAP_CRC_MAGIC):
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return false;
+ if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(block->bb_u.l.bb_blkno) != bp->b_bn)
+ return false;
+ /*
+ * XXX: need a better way of verifying the owner here. Right now
+ * just make sure there has been one set.
+ */
+ if (be64_to_cpu(block->bb_u.l.bb_owner) == 0)
+ return false;
+ /* fall through */
+ case cpu_to_be32(XFS_BMAP_MAGIC):
+ break;
+ default:
+ return false;
+ }
+
+ /*
+ * numrecs and level verification.
+ *
+ * We don't know what fork we belong to, so just verify that the level
+ * is less than the maximum of the two. Later checks will be more
+ * precise.
+ */
+ level = be16_to_cpu(block->bb_level);
+ if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1]))
+ return false;
+ if (be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0])
+ return false;
+
+ /* sibling pointer verification */
+ if (!block->bb_u.l.bb_leftsib ||
+ (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLDFSBNO) &&
+ !XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_u.l.bb_leftsib))))
+ return false;
+ if (!block->bb_u.l.bb_rightsib ||
+ (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLDFSBNO) &&
+ !XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_u.l.bb_rightsib))))
+ return false;
+
+ return true;
+}
+
+static void
+xfs_bmbt_read_verify(
+ struct xfs_buf *bp)
+{
+ if (!xfs_btree_lblock_verify_crc(bp))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_bmbt_verify(bp))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error) {
+ trace_xfs_btree_corrupt(bp, _RET_IP_);
+ xfs_verifier_error(bp);
+ }
+}
+
+static void
+xfs_bmbt_write_verify(
+ struct xfs_buf *bp)
+{
+ if (!xfs_bmbt_verify(bp)) {
+ trace_xfs_btree_corrupt(bp, _RET_IP_);
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+ xfs_btree_lblock_calc_crc(bp);
+}
+
+const struct xfs_buf_ops xfs_bmbt_buf_ops = {
+ .verify_read = xfs_bmbt_read_verify,
+ .verify_write = xfs_bmbt_write_verify,
+};
+
+
+#if defined(DEBUG) || defined(XFS_WARN)
STATIC int
xfs_bmbt_keys_inorder(
struct xfs_btree_cur *cur,
@@ -746,7 +847,8 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
.init_rec_from_cur = xfs_bmbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_bmbt_init_ptr_from_cur,
.key_diff = xfs_bmbt_key_diff,
-#ifdef DEBUG
+ .buf_ops = &xfs_bmbt_buf_ops,
+#if defined(DEBUG) || defined(XFS_WARN)
.keys_inorder = xfs_bmbt_keys_inorder,
.recs_inorder = xfs_bmbt_recs_inorder,
#endif
@@ -775,6 +877,8 @@ xfs_bmbt_init_cursor(
cur->bc_ops = &xfs_bmbt_ops;
cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
cur->bc_private.b.ip = ip;
@@ -808,7 +912,6 @@ xfs_bmbt_maxrecs(
*/
int
xfs_bmdr_maxrecs(
- struct xfs_mount *mp,
int blocklen,
int leaf)
{
@@ -818,3 +921,47 @@ xfs_bmdr_maxrecs(
return blocklen / sizeof(xfs_bmdr_rec_t);
return blocklen / (sizeof(xfs_bmdr_key_t) + sizeof(xfs_bmdr_ptr_t));
}
+
+/*
+ * Change the owner of a btree format fork fo the inode passed in. Change it to
+ * the owner of that is passed in so that we can change owners before or after
+ * we switch forks between inodes. The operation that the caller is doing will
+ * determine whether is needs to change owner before or after the switch.
+ *
+ * For demand paged transactional modification, the fork switch should be done
+ * after reading in all the blocks, modifying them and pinning them in the
+ * transaction. For modification when the buffers are already pinned in memory,
+ * the fork switch can be done before changing the owner as we won't need to
+ * validate the owner until the btree buffers are unpinned and writes can occur
+ * again.
+ *
+ * For recovery based ownership change, there is no transactional context and
+ * so a buffer list must be supplied so that we can record the buffers that we
+ * modified for the caller to issue IO on.
+ */
+int
+xfs_bmbt_change_owner(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int whichfork,
+ xfs_ino_t new_owner,
+ struct list_head *buffer_list)
+{
+ struct xfs_btree_cur *cur;
+ int error;
+
+ ASSERT(tp || buffer_list);
+ ASSERT(!(tp && buffer_list));
+ if (whichfork == XFS_DATA_FORK)
+ ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_BTREE);
+ else
+ ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE);
+
+ cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
+ if (!cur)
+ return ENOMEM;
+
+ error = xfs_btree_change_owner(cur, new_owner, buffer_list);
+ xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+ return error;
+}
diff --git a/fs/xfs/xfs_bmap_btree.h b/fs/xfs/xfs_bmap_btree.h
index 0e66c4ea0f8..819a8a4dee9 100644
--- a/fs/xfs/xfs_bmap_btree.h
+++ b/fs/xfs/xfs_bmap_btree.h
@@ -18,8 +18,6 @@
#ifndef __XFS_BMAP_BTREE_H__
#define __XFS_BMAP_BTREE_H__
-#define XFS_BMAP_MAGIC 0x424d4150 /* 'BMAP' */
-
struct xfs_btree_cur;
struct xfs_btree_block;
struct xfs_mount;
@@ -27,85 +25,6 @@ struct xfs_inode;
struct xfs_trans;
/*
- * Bmap root header, on-disk form only.
- */
-typedef struct xfs_bmdr_block {
- __be16 bb_level; /* 0 is a leaf */
- __be16 bb_numrecs; /* current # of data records */
-} xfs_bmdr_block_t;
-
-/*
- * Bmap btree record and extent descriptor.
- * l0:63 is an extent flag (value 1 indicates non-normal).
- * l0:9-62 are startoff.
- * l0:0-8 and l1:21-63 are startblock.
- * l1:0-20 are blockcount.
- */
-#define BMBT_EXNTFLAG_BITLEN 1
-#define BMBT_STARTOFF_BITLEN 54
-#define BMBT_STARTBLOCK_BITLEN 52
-#define BMBT_BLOCKCOUNT_BITLEN 21
-
-typedef struct xfs_bmbt_rec {
- __be64 l0, l1;
-} xfs_bmbt_rec_t;
-
-typedef __uint64_t xfs_bmbt_rec_base_t; /* use this for casts */
-typedef xfs_bmbt_rec_t xfs_bmdr_rec_t;
-
-typedef struct xfs_bmbt_rec_host {
- __uint64_t l0, l1;
-} xfs_bmbt_rec_host_t;
-
-/*
- * Values and macros for delayed-allocation startblock fields.
- */
-#define STARTBLOCKVALBITS 17
-#define STARTBLOCKMASKBITS (15 + XFS_BIG_BLKNOS * 20)
-#define DSTARTBLOCKMASKBITS (15 + 20)
-#define STARTBLOCKMASK \
- (((((xfs_fsblock_t)1) << STARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS)
-#define DSTARTBLOCKMASK \
- (((((xfs_dfsbno_t)1) << DSTARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS)
-
-static inline int isnullstartblock(xfs_fsblock_t x)
-{
- return ((x) & STARTBLOCKMASK) == STARTBLOCKMASK;
-}
-
-static inline int isnulldstartblock(xfs_dfsbno_t x)
-{
- return ((x) & DSTARTBLOCKMASK) == DSTARTBLOCKMASK;
-}
-
-static inline xfs_fsblock_t nullstartblock(int k)
-{
- ASSERT(k < (1 << STARTBLOCKVALBITS));
- return STARTBLOCKMASK | (k);
-}
-
-static inline xfs_filblks_t startblockval(xfs_fsblock_t x)
-{
- return (xfs_filblks_t)((x) & ~STARTBLOCKMASK);
-}
-
-/*
- * Possible extent formats.
- */
-typedef enum {
- XFS_EXTFMT_NOSTATE = 0,
- XFS_EXTFMT_HASSTATE
-} xfs_exntfmt_t;
-
-/*
- * Possible extent states.
- */
-typedef enum {
- XFS_EXT_NORM, XFS_EXT_UNWRITTEN,
- XFS_EXT_DMAPI_OFFLINE, XFS_EXT_INVALID
-} xfs_exntst_t;
-
-/*
* Extent state and extent format macros.
*/
#define XFS_EXTFMT_INODE(x) \
@@ -114,32 +33,11 @@ typedef enum {
#define ISUNWRITTEN(x) ((x)->br_state == XFS_EXT_UNWRITTEN)
/*
- * Incore version of above.
- */
-typedef struct xfs_bmbt_irec
-{
- xfs_fileoff_t br_startoff; /* starting file offset */
- xfs_fsblock_t br_startblock; /* starting block number */
- xfs_filblks_t br_blockcount; /* number of blocks */
- xfs_exntst_t br_state; /* extent state */
-} xfs_bmbt_irec_t;
-
-/*
- * Key structure for non-leaf levels of the tree.
- */
-typedef struct xfs_bmbt_key {
- __be64 br_startoff; /* starting file offset */
-} xfs_bmbt_key_t, xfs_bmdr_key_t;
-
-/* btree pointer type */
-typedef __be64 xfs_bmbt_ptr_t, xfs_bmdr_ptr_t;
-
-/*
* Btree block header size depends on a superblock flag.
- *
- * (not quite yet, but soon)
*/
-#define XFS_BMBT_BLOCK_LEN(mp) XFS_BTREE_LBLOCK_LEN
+#define XFS_BMBT_BLOCK_LEN(mp) \
+ (xfs_sb_version_hascrc(&((mp)->m_sb)) ? \
+ XFS_BTREE_LBLOCK_CRC_LEN : XFS_BTREE_LBLOCK_LEN)
#define XFS_BMBT_REC_ADDR(mp, block, index) \
((xfs_bmbt_rec_t *) \
@@ -186,15 +84,17 @@ typedef __be64 xfs_bmbt_ptr_t, xfs_bmdr_ptr_t;
#define XFS_BMAP_BROOT_PTR_ADDR(mp, bb, i, sz) \
XFS_BMBT_PTR_ADDR(mp, bb, i, xfs_bmbt_maxrecs(mp, sz, 0))
-#define XFS_BMAP_BROOT_SPACE_CALC(nrecs) \
- (int)(XFS_BTREE_LBLOCK_LEN + \
+#define XFS_BMAP_BROOT_SPACE_CALC(mp, nrecs) \
+ (int)(XFS_BMBT_BLOCK_LEN(mp) + \
((nrecs) * (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t))))
-#define XFS_BMAP_BROOT_SPACE(bb) \
- (XFS_BMAP_BROOT_SPACE_CALC(be16_to_cpu((bb)->bb_numrecs)))
+#define XFS_BMAP_BROOT_SPACE(mp, bb) \
+ (XFS_BMAP_BROOT_SPACE_CALC(mp, be16_to_cpu((bb)->bb_numrecs)))
#define XFS_BMDR_SPACE_CALC(nrecs) \
(int)(sizeof(xfs_bmdr_block_t) + \
((nrecs) * (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t))))
+#define XFS_BMAP_BMDR_SPACE(bb) \
+ (XFS_BMDR_SPACE_CALC(be16_to_cpu((bb)->bb_numrecs)))
/*
* Maximum number of bmap btree levels.
@@ -204,7 +104,7 @@ typedef __be64 xfs_bmbt_ptr_t, xfs_bmdr_ptr_t;
/*
* Prototypes for xfs_bmap.c to call.
*/
-extern void xfs_bmdr_to_bmbt(struct xfs_mount *, xfs_bmdr_block_t *, int,
+extern void xfs_bmdr_to_bmbt(struct xfs_inode *, xfs_bmdr_block_t *, int,
struct xfs_btree_block *, int);
extern void xfs_bmbt_get_all(xfs_bmbt_rec_host_t *r, xfs_bmbt_irec_t *s);
extern xfs_filblks_t xfs_bmbt_get_blockcount(xfs_bmbt_rec_host_t *r);
@@ -230,11 +130,14 @@ extern void xfs_bmbt_to_bmdr(struct xfs_mount *, struct xfs_btree_block *, int,
xfs_bmdr_block_t *, int);
extern int xfs_bmbt_get_maxrecs(struct xfs_btree_cur *, int level);
-extern int xfs_bmdr_maxrecs(struct xfs_mount *, int blocklen, int leaf);
+extern int xfs_bmdr_maxrecs(int blocklen, int leaf);
extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
+extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
+ int whichfork, xfs_ino_t new_owner,
+ struct list_head *buffer_list);
+
extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
struct xfs_trans *, struct xfs_inode *, int);
-
#endif /* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
new file mode 100644
index 00000000000..64731ef3324
--- /dev/null
+++ b/fs/xfs/xfs_bmap_util.c
@@ -0,0 +1,1897 @@
+/*
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.
+ * Copyright (c) 2012 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_inode.h"
+#include "xfs_btree.h"
+#include "xfs_trans.h"
+#include "xfs_extfree_item.h"
+#include "xfs_alloc.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_rtalloc.h"
+#include "xfs_error.h"
+#include "xfs_quota.h"
+#include "xfs_trans_space.h"
+#include "xfs_trace.h"
+#include "xfs_icache.h"
+#include "xfs_log.h"
+#include "xfs_dinode.h"
+
+/* Kernel only BMAP related definitions and functions */
+
+/*
+ * Convert the given file system block to a disk block. We have to treat it
+ * differently based on whether the file is a real time file or not, because the
+ * bmap code does.
+ */
+xfs_daddr_t
+xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
+{
+ return (XFS_IS_REALTIME_INODE(ip) ? \
+ (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
+ XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
+}
+
+/*
+ * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
+ * caller. Frees all the extents that need freeing, which must be done
+ * last due to locking considerations. We never free any extents in
+ * the first transaction.
+ *
+ * Return 1 if the given transaction was committed and a new one
+ * started, and 0 otherwise in the committed parameter.
+ */
+int /* error */
+xfs_bmap_finish(
+ xfs_trans_t **tp, /* transaction pointer addr */
+ xfs_bmap_free_t *flist, /* i/o: list extents to free */
+ int *committed) /* xact committed or not */
+{
+ xfs_efd_log_item_t *efd; /* extent free data */
+ xfs_efi_log_item_t *efi; /* extent free intention */
+ int error; /* error return value */
+ xfs_bmap_free_item_t *free; /* free extent item */
+ struct xfs_trans_res tres; /* new log reservation */
+ xfs_mount_t *mp; /* filesystem mount structure */
+ xfs_bmap_free_item_t *next; /* next item on free list */
+ xfs_trans_t *ntp; /* new transaction pointer */
+
+ ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
+ if (flist->xbf_count == 0) {
+ *committed = 0;
+ return 0;
+ }
+ ntp = *tp;
+ efi = xfs_trans_get_efi(ntp, flist->xbf_count);
+ for (free = flist->xbf_first; free; free = free->xbfi_next)
+ xfs_trans_log_efi_extent(ntp, efi, free->xbfi_startblock,
+ free->xbfi_blockcount);
+
+ tres.tr_logres = ntp->t_log_res;
+ tres.tr_logcount = ntp->t_log_count;
+ tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
+ ntp = xfs_trans_dup(*tp);
+ error = xfs_trans_commit(*tp, 0);
+ *tp = ntp;
+ *committed = 1;
+ /*
+ * We have a new transaction, so we should return committed=1,
+ * even though we're returning an error.
+ */
+ if (error)
+ return error;
+
+ /*
+ * transaction commit worked ok so we can drop the extra ticket
+ * reference that we gained in xfs_trans_dup()
+ */
+ xfs_log_ticket_put(ntp->t_ticket);
+
+ error = xfs_trans_reserve(ntp, &tres, 0, 0);
+ if (error)
+ return error;
+ efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count);
+ for (free = flist->xbf_first; free != NULL; free = next) {
+ next = free->xbfi_next;
+ if ((error = xfs_free_extent(ntp, free->xbfi_startblock,
+ free->xbfi_blockcount))) {
+ /*
+ * The bmap free list will be cleaned up at a
+ * higher level. The EFI will be canceled when
+ * this transaction is aborted.
+ * Need to force shutdown here to make sure it
+ * happens, since this transaction may not be
+ * dirty yet.
+ */
+ mp = ntp->t_mountp;
+ if (!XFS_FORCED_SHUTDOWN(mp))
+ xfs_force_shutdown(mp,
+ (error == EFSCORRUPTED) ?
+ SHUTDOWN_CORRUPT_INCORE :
+ SHUTDOWN_META_IO_ERROR);
+ return error;
+ }
+ xfs_trans_log_efd_extent(ntp, efd, free->xbfi_startblock,
+ free->xbfi_blockcount);
+ xfs_bmap_del_free(flist, NULL, free);
+ }
+ return 0;
+}
+
+int
+xfs_bmap_rtalloc(
+ struct xfs_bmalloca *ap) /* bmap alloc argument struct */
+{
+ xfs_alloctype_t atype = 0; /* type for allocation routines */
+ int error; /* error return value */
+ xfs_mount_t *mp; /* mount point structure */
+ xfs_extlen_t prod = 0; /* product factor for allocators */
+ xfs_extlen_t ralen = 0; /* realtime allocation length */
+ xfs_extlen_t align; /* minimum allocation alignment */
+ xfs_rtblock_t rtb;
+
+ mp = ap->ip->i_mount;
+ align = xfs_get_extsz_hint(ap->ip);
+ prod = align / mp->m_sb.sb_rextsize;
+ error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
+ align, 1, ap->eof, 0,
+ ap->conv, &ap->offset, &ap->length);
+ if (error)
+ return error;
+ ASSERT(ap->length);
+ ASSERT(ap->length % mp->m_sb.sb_rextsize == 0);
+
+ /*
+ * If the offset & length are not perfectly aligned
+ * then kill prod, it will just get us in trouble.
+ */
+ if (do_mod(ap->offset, align) || ap->length % align)
+ prod = 1;
+ /*
+ * Set ralen to be the actual requested length in rtextents.
+ */
+ ralen = ap->length / mp->m_sb.sb_rextsize;
+ /*
+ * If the old value was close enough to MAXEXTLEN that
+ * we rounded up to it, cut it back so it's valid again.
+ * Note that if it's a really large request (bigger than
+ * MAXEXTLEN), we don't hear about that number, and can't
+ * adjust the starting point to match it.
+ */
+ if (ralen * mp->m_sb.sb_rextsize >= MAXEXTLEN)
+ ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
+
+ /*
+ * Lock out other modifications to the RT bitmap inode.
+ */
+ xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+
+ /*
+ * If it's an allocation to an empty file at offset 0,
+ * pick an extent that will space things out in the rt area.
+ */
+ if (ap->eof && ap->offset == 0) {
+ xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */
+
+ error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
+ if (error)
+ return error;
+ ap->blkno = rtx * mp->m_sb.sb_rextsize;
+ } else {
+ ap->blkno = 0;
+ }
+
+ xfs_bmap_adjacent(ap);
+
+ /*
+ * Realtime allocation, done through xfs_rtallocate_extent.
+ */
+ atype = ap->blkno == 0 ? XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO;
+ do_div(ap->blkno, mp->m_sb.sb_rextsize);
+ rtb = ap->blkno;
+ ap->length = ralen;
+ if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
+ &ralen, atype, ap->wasdel, prod, &rtb)))
+ return error;
+ if (rtb == NULLFSBLOCK && prod > 1 &&
+ (error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1,
+ ap->length, &ralen, atype,
+ ap->wasdel, 1, &rtb)))
+ return error;
+ ap->blkno = rtb;
+ if (ap->blkno != NULLFSBLOCK) {
+ ap->blkno *= mp->m_sb.sb_rextsize;
+ ralen *= mp->m_sb.sb_rextsize;
+ ap->length = ralen;
+ ap->ip->i_d.di_nblocks += ralen;
+ xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
+ if (ap->wasdel)
+ ap->ip->i_delayed_blks -= ralen;
+ /*
+ * Adjust the disk quota also. This was reserved
+ * earlier.
+ */
+ xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
+ ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
+ XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
+ } else {
+ ap->length = 0;
+ }
+ return 0;
+}
+
+/*
+ * Check if the endoff is outside the last extent. If so the caller will grow
+ * the allocation to a stripe unit boundary. All offsets are considered outside
+ * the end of file for an empty fork, so 1 is returned in *eof in that case.
+ */
+int
+xfs_bmap_eof(
+ struct xfs_inode *ip,
+ xfs_fileoff_t endoff,
+ int whichfork,
+ int *eof)
+{
+ struct xfs_bmbt_irec rec;
+ int error;
+
+ error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, eof);
+ if (error || *eof)
+ return error;
+
+ *eof = endoff >= rec.br_startoff + rec.br_blockcount;
+ return 0;
+}
+
+/*
+ * Extent tree block counting routines.
+ */
+
+/*
+ * Count leaf blocks given a range of extent records.
+ */
+STATIC void
+xfs_bmap_count_leaves(
+ xfs_ifork_t *ifp,
+ xfs_extnum_t idx,
+ int numrecs,
+ int *count)
+{
+ int b;
+
+ for (b = 0; b < numrecs; b++) {
+ xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b);
+ *count += xfs_bmbt_get_blockcount(frp);
+ }
+}
+
+/*
+ * Count leaf blocks given a range of extent records originally
+ * in btree format.
+ */
+STATIC void
+xfs_bmap_disk_count_leaves(
+ struct xfs_mount *mp,
+ struct xfs_btree_block *block,
+ int numrecs,
+ int *count)
+{
+ int b;
+ xfs_bmbt_rec_t *frp;
+
+ for (b = 1; b <= numrecs; b++) {
+ frp = XFS_BMBT_REC_ADDR(mp, block, b);
+ *count += xfs_bmbt_disk_get_blockcount(frp);
+ }
+}
+
+/*
+ * Recursively walks each level of a btree
+ * to count total fsblocks in use.
+ */
+STATIC int /* error */
+xfs_bmap_count_tree(
+ xfs_mount_t *mp, /* file system mount point */
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_ifork_t *ifp, /* inode fork pointer */
+ xfs_fsblock_t blockno, /* file system block number */
+ int levelin, /* level in btree */
+ int *count) /* Count of blocks */
+{
+ int error;
+ xfs_buf_t *bp, *nbp;
+ int level = levelin;
+ __be64 *pp;
+ xfs_fsblock_t bno = blockno;
+ xfs_fsblock_t nextbno;
+ struct xfs_btree_block *block, *nextblock;
+ int numrecs;
+
+ error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF,
+ &xfs_bmbt_buf_ops);
+ if (error)
+ return error;
+ *count += 1;
+ block = XFS_BUF_TO_BLOCK(bp);
+
+ if (--level) {
+ /* Not at node above leaves, count this level of nodes */
+ nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
+ while (nextbno != NULLFSBLOCK) {
+ error = xfs_btree_read_bufl(mp, tp, nextbno, 0, &nbp,
+ XFS_BMAP_BTREE_REF,
+ &xfs_bmbt_buf_ops);
+ if (error)
+ return error;
+ *count += 1;
+ nextblock = XFS_BUF_TO_BLOCK(nbp);
+ nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
+ xfs_trans_brelse(tp, nbp);
+ }
+
+ /* Dive to the next level */
+ pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
+ bno = be64_to_cpu(*pp);
+ if (unlikely((error =
+ xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
+ xfs_trans_brelse(tp, bp);
+ XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
+ XFS_ERRLEVEL_LOW, mp);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+ xfs_trans_brelse(tp, bp);
+ } else {
+ /* count all level 1 nodes and their leaves */
+ for (;;) {
+ nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
+ numrecs = be16_to_cpu(block->bb_numrecs);
+ xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
+ xfs_trans_brelse(tp, bp);
+ if (nextbno == NULLFSBLOCK)
+ break;
+ bno = nextbno;
+ error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
+ XFS_BMAP_BTREE_REF,
+ &xfs_bmbt_buf_ops);
+ if (error)
+ return error;
+ *count += 1;
+ block = XFS_BUF_TO_BLOCK(bp);
+ }
+ }
+ return 0;
+}
+
+/*
+ * Count fsblocks of the given fork.
+ */
+int /* error */
+xfs_bmap_count_blocks(
+ xfs_trans_t *tp, /* transaction pointer */
+ xfs_inode_t *ip, /* incore inode */
+ int whichfork, /* data or attr fork */
+ int *count) /* out: count of blocks */
+{
+ struct xfs_btree_block *block; /* current btree block */
+ xfs_fsblock_t bno; /* block # of "block" */
+ xfs_ifork_t *ifp; /* fork structure */
+ int level; /* btree level, for checking */
+ xfs_mount_t *mp; /* file system mount structure */
+ __be64 *pp; /* pointer to block address */
+
+ bno = NULLFSBLOCK;
+ mp = ip->i_mount;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
+ if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
+ xfs_bmap_count_leaves(ifp, 0,
+ ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
+ count);
+ return 0;
+ }
+
+ /*
+ * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
+ */
+ block = ifp->if_broot;
+ level = be16_to_cpu(block->bb_level);
+ ASSERT(level > 0);
+ pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
+ bno = be64_to_cpu(*pp);
+ ASSERT(bno != NULLDFSBNO);
+ ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
+ ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+
+ if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
+ XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
+ mp);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+
+ return 0;
+}
+
+/*
+ * returns 1 for success, 0 if we failed to map the extent.
+ */
+STATIC int
+xfs_getbmapx_fix_eof_hole(
+ xfs_inode_t *ip, /* xfs incore inode pointer */
+ struct getbmapx *out, /* output structure */
+ int prealloced, /* this is a file with
+ * preallocated data space */
+ __int64_t end, /* last block requested */
+ xfs_fsblock_t startblock)
+{
+ __int64_t fixlen;
+ xfs_mount_t *mp; /* file system mount point */
+ xfs_ifork_t *ifp; /* inode fork pointer */
+ xfs_extnum_t lastx; /* last extent pointer */
+ xfs_fileoff_t fileblock;
+
+ if (startblock == HOLESTARTBLOCK) {
+ mp = ip->i_mount;
+ out->bmv_block = -1;
+ fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
+ fixlen -= out->bmv_offset;
+ if (prealloced && out->bmv_offset + out->bmv_length == end) {
+ /* Came to hole at EOF. Trim it. */
+ if (fixlen <= 0)
+ return 0;
+ out->bmv_length = fixlen;
+ }
+ } else {
+ if (startblock == DELAYSTARTBLOCK)
+ out->bmv_block = -2;
+ else
+ out->bmv_block = xfs_fsb_to_db(ip, startblock);
+ fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset);
+ ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+ if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
+ (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
+ out->bmv_oflags |= BMV_OF_LAST;
+ }
+
+ return 1;
+}
+
+/*
+ * Get inode's extents as described in bmv, and format for output.
+ * Calls formatter to fill the user's buffer until all extents
+ * are mapped, until the passed-in bmv->bmv_count slots have
+ * been filled, or until the formatter short-circuits the loop,
+ * if it is tracking filled-in extents on its own.
+ */
+int /* error code */
+xfs_getbmap(
+ xfs_inode_t *ip,
+ struct getbmapx *bmv, /* user bmap structure */
+ xfs_bmap_format_t formatter, /* format to user */
+ void *arg) /* formatter arg */
+{
+ __int64_t bmvend; /* last block requested */
+ int error = 0; /* return value */
+ __int64_t fixlen; /* length for -1 case */
+ int i; /* extent number */
+ int lock; /* lock state */
+ xfs_bmbt_irec_t *map; /* buffer for user's data */
+ xfs_mount_t *mp; /* file system mount point */
+ int nex; /* # of user extents can do */
+ int nexleft; /* # of user extents left */
+ int subnex; /* # of bmapi's can do */
+ int nmap; /* number of map entries */
+ struct getbmapx *out; /* output structure */
+ int whichfork; /* data or attr fork */
+ int prealloced; /* this is a file with
+ * preallocated data space */
+ int iflags; /* interface flags */
+ int bmapi_flags; /* flags for xfs_bmapi */
+ int cur_ext = 0;
+
+ mp = ip->i_mount;
+ iflags = bmv->bmv_iflags;
+ whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
+
+ if (whichfork == XFS_ATTR_FORK) {
+ if (XFS_IFORK_Q(ip)) {
+ if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
+ ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
+ ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
+ return XFS_ERROR(EINVAL);
+ } else if (unlikely(
+ ip->i_d.di_aformat != 0 &&
+ ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
+ XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
+ ip->i_mount);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+
+ prealloced = 0;
+ fixlen = 1LL << 32;
+ } else {
+ if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
+ ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
+ ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
+ return XFS_ERROR(EINVAL);
+
+ if (xfs_get_extsz_hint(ip) ||
+ ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
+ prealloced = 1;
+ fixlen = mp->m_super->s_maxbytes;
+ } else {
+ prealloced = 0;
+ fixlen = XFS_ISIZE(ip);
+ }
+ }
+
+ if (bmv->bmv_length == -1) {
+ fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
+ bmv->bmv_length =
+ max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
+ } else if (bmv->bmv_length == 0) {
+ bmv->bmv_entries = 0;
+ return 0;
+ } else if (bmv->bmv_length < 0) {
+ return XFS_ERROR(EINVAL);
+ }
+
+ nex = bmv->bmv_count - 1;
+ if (nex <= 0)
+ return XFS_ERROR(EINVAL);
+ bmvend = bmv->bmv_offset + bmv->bmv_length;
+
+
+ if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
+ return XFS_ERROR(ENOMEM);
+ out = kmem_zalloc_large(bmv->bmv_count * sizeof(struct getbmapx), 0);
+ if (!out)
+ return XFS_ERROR(ENOMEM);
+
+ xfs_ilock(ip, XFS_IOLOCK_SHARED);
+ if (whichfork == XFS_DATA_FORK) {
+ if (!(iflags & BMV_IF_DELALLOC) &&
+ (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
+ error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
+ if (error)
+ goto out_unlock_iolock;
+
+ /*
+ * Even after flushing the inode, there can still be
+ * delalloc blocks on the inode beyond EOF due to
+ * speculative preallocation. These are not removed
+ * until the release function is called or the inode
+ * is inactivated. Hence we cannot assert here that
+ * ip->i_delayed_blks == 0.
+ */
+ }
+
+ lock = xfs_ilock_data_map_shared(ip);
+ } else {
+ lock = xfs_ilock_attr_map_shared(ip);
+ }
+
+ /*
+ * Don't let nex be bigger than the number of extents
+ * we can have assuming alternating holes and real extents.
+ */
+ if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
+ nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
+
+ bmapi_flags = xfs_bmapi_aflag(whichfork);
+ if (!(iflags & BMV_IF_PREALLOC))
+ bmapi_flags |= XFS_BMAPI_IGSTATE;
+
+ /*
+ * Allocate enough space to handle "subnex" maps at a time.
+ */
+ error = ENOMEM;
+ subnex = 16;
+ map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
+ if (!map)
+ goto out_unlock_ilock;
+
+ bmv->bmv_entries = 0;
+
+ if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
+ (whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
+ error = 0;
+ goto out_free_map;
+ }
+
+ nexleft = nex;
+
+ do {
+ nmap = (nexleft > subnex) ? subnex : nexleft;
+ error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
+ XFS_BB_TO_FSB(mp, bmv->bmv_length),
+ map, &nmap, bmapi_flags);
+ if (error)
+ goto out_free_map;
+ ASSERT(nmap <= subnex);
+
+ for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
+ out[cur_ext].bmv_oflags = 0;
+ if (map[i].br_state == XFS_EXT_UNWRITTEN)
+ out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
+ else if (map[i].br_startblock == DELAYSTARTBLOCK)
+ out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
+ out[cur_ext].bmv_offset =
+ XFS_FSB_TO_BB(mp, map[i].br_startoff);
+ out[cur_ext].bmv_length =
+ XFS_FSB_TO_BB(mp, map[i].br_blockcount);
+ out[cur_ext].bmv_unused1 = 0;
+ out[cur_ext].bmv_unused2 = 0;
+
+ /*
+ * delayed allocation extents that start beyond EOF can
+ * occur due to speculative EOF allocation when the
+ * delalloc extent is larger than the largest freespace
+ * extent at conversion time. These extents cannot be
+ * converted by data writeback, so can exist here even
+ * if we are not supposed to be finding delalloc
+ * extents.
+ */
+ if (map[i].br_startblock == DELAYSTARTBLOCK &&
+ map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+ ASSERT((iflags & BMV_IF_DELALLOC) != 0);
+
+ if (map[i].br_startblock == HOLESTARTBLOCK &&
+ whichfork == XFS_ATTR_FORK) {
+ /* came to the end of attribute fork */
+ out[cur_ext].bmv_oflags |= BMV_OF_LAST;
+ goto out_free_map;
+ }
+
+ if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
+ prealloced, bmvend,
+ map[i].br_startblock))
+ goto out_free_map;
+
+ bmv->bmv_offset =
+ out[cur_ext].bmv_offset +
+ out[cur_ext].bmv_length;
+ bmv->bmv_length =
+ max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
+
+ /*
+ * In case we don't want to return the hole,
+ * don't increase cur_ext so that we can reuse
+ * it in the next loop.
+ */
+ if ((iflags & BMV_IF_NO_HOLES) &&
+ map[i].br_startblock == HOLESTARTBLOCK) {
+ memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
+ continue;
+ }
+
+ nexleft--;
+ bmv->bmv_entries++;
+ cur_ext++;
+ }
+ } while (nmap && nexleft && bmv->bmv_length);
+
+ out_free_map:
+ kmem_free(map);
+ out_unlock_ilock:
+ xfs_iunlock(ip, lock);
+ out_unlock_iolock:
+ xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+
+ for (i = 0; i < cur_ext; i++) {
+ int full = 0; /* user array is full */
+
+ /* format results & advance arg */
+ error = formatter(&arg, &out[i], &full);
+ if (error || full)
+ break;
+ }
+
+ kmem_free(out);
+ return error;
+}
+
+/*
+ * dead simple method of punching delalyed allocation blocks from a range in
+ * the inode. Walks a block at a time so will be slow, but is only executed in
+ * rare error cases so the overhead is not critical. This will always punch out
+ * both the start and end blocks, even if the ranges only partially overlap
+ * them, so it is up to the caller to ensure that partial blocks are not
+ * passed in.
+ */
+int
+xfs_bmap_punch_delalloc_range(
+ struct xfs_inode *ip,
+ xfs_fileoff_t start_fsb,
+ xfs_fileoff_t length)
+{
+ xfs_fileoff_t remaining = length;
+ int error = 0;
+
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+ do {
+ int done;
+ xfs_bmbt_irec_t imap;
+ int nimaps = 1;
+ xfs_fsblock_t firstblock;
+ xfs_bmap_free_t flist;
+
+ /*
+ * Map the range first and check that it is a delalloc extent
+ * before trying to unmap the range. Otherwise we will be
+ * trying to remove a real extent (which requires a
+ * transaction) or a hole, which is probably a bad idea...
+ */
+ error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
+ XFS_BMAPI_ENTIRE);
+
+ if (error) {
+ /* something screwed, just bail */
+ if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+ xfs_alert(ip->i_mount,
+ "Failed delalloc mapping lookup ino %lld fsb %lld.",
+ ip->i_ino, start_fsb);
+ }
+ break;
+ }
+ if (!nimaps) {
+ /* nothing there */
+ goto next_block;
+ }
+ if (imap.br_startblock != DELAYSTARTBLOCK) {
+ /* been converted, ignore */
+ goto next_block;
+ }
+ WARN_ON(imap.br_blockcount == 0);
+
+ /*
+ * Note: while we initialise the firstblock/flist pair, they
+ * should never be used because blocks should never be
+ * allocated or freed for a delalloc extent and hence we need
+ * don't cancel or finish them after the xfs_bunmapi() call.
+ */
+ xfs_bmap_init(&flist, &firstblock);
+ error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
+ &flist, &done);
+ if (error)
+ break;
+
+ ASSERT(!flist.xbf_count && !flist.xbf_first);
+next_block:
+ start_fsb++;
+ remaining--;
+ } while(remaining > 0);
+
+ return error;
+}
+
+/*
+ * Test whether it is appropriate to check an inode for and free post EOF
+ * blocks. The 'force' parameter determines whether we should also consider
+ * regular files that are marked preallocated or append-only.
+ */
+bool
+xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
+{
+ /* prealloc/delalloc exists only on regular files */
+ if (!S_ISREG(ip->i_d.di_mode))
+ return false;
+
+ /*
+ * Zero sized files with no cached pages and delalloc blocks will not
+ * have speculative prealloc/delalloc blocks to remove.
+ */
+ if (VFS_I(ip)->i_size == 0 &&
+ VN_CACHED(VFS_I(ip)) == 0 &&
+ ip->i_delayed_blks == 0)
+ return false;
+
+ /* If we haven't read in the extent list, then don't do it now. */
+ if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
+ return false;
+
+ /*
+ * Do not free real preallocated or append-only files unless the file
+ * has delalloc blocks and we are forced to remove them.
+ */
+ if (ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
+ if (!force || ip->i_delayed_blks == 0)
+ return false;
+
+ return true;
+}
+
+/*
+ * This is called by xfs_inactive to free any blocks beyond eof
+ * when the link count isn't zero and by xfs_dm_punch_hole() when
+ * punching a hole to EOF.
+ */
+int
+xfs_free_eofblocks(
+ xfs_mount_t *mp,
+ xfs_inode_t *ip,
+ bool need_iolock)
+{
+ xfs_trans_t *tp;
+ int error;
+ xfs_fileoff_t end_fsb;
+ xfs_fileoff_t last_fsb;
+ xfs_filblks_t map_len;
+ int nimaps;
+ xfs_bmbt_irec_t imap;
+
+ /*
+ * Figure out if there are any blocks beyond the end
+ * of the file. If not, then there is nothing to do.
+ */
+ end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
+ last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
+ if (last_fsb <= end_fsb)
+ return 0;
+ map_len = last_fsb - end_fsb;
+
+ nimaps = 1;
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+ error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+ if (!error && (nimaps != 0) &&
+ (imap.br_startblock != HOLESTARTBLOCK ||
+ ip->i_delayed_blks)) {
+ /*
+ * Attach the dquots to the inode up front.
+ */
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ return error;
+
+ /*
+ * There are blocks after the end of file.
+ * Free them up now by truncating the file to
+ * its current size.
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
+
+ if (need_iolock) {
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+ xfs_trans_cancel(tp, 0);
+ return EAGAIN;
+ }
+ }
+
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
+ if (error) {
+ ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ xfs_trans_cancel(tp, 0);
+ if (need_iolock)
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ return error;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
+
+ /*
+ * Do not update the on-disk file size. If we update the
+ * on-disk file size and then the system crashes before the
+ * contents of the file are flushed to disk then the files
+ * may be full of holes (ie NULL files bug).
+ */
+ error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
+ XFS_ISIZE(ip));
+ if (error) {
+ /*
+ * If we get an error at this point we simply don't
+ * bother truncating the file.
+ */
+ xfs_trans_cancel(tp,
+ (XFS_TRANS_RELEASE_LOG_RES |
+ XFS_TRANS_ABORT));
+ } else {
+ error = xfs_trans_commit(tp,
+ XFS_TRANS_RELEASE_LOG_RES);
+ if (!error)
+ xfs_inode_clear_eofblocks_tag(ip);
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ if (need_iolock)
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ }
+ return error;
+}
+
+int
+xfs_alloc_file_space(
+ struct xfs_inode *ip,
+ xfs_off_t offset,
+ xfs_off_t len,
+ int alloc_type)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ xfs_off_t count;
+ xfs_filblks_t allocated_fsb;
+ xfs_filblks_t allocatesize_fsb;
+ xfs_extlen_t extsz, temp;
+ xfs_fileoff_t startoffset_fsb;
+ xfs_fsblock_t firstfsb;
+ int nimaps;
+ int quota_flag;
+ int rt;
+ xfs_trans_t *tp;
+ xfs_bmbt_irec_t imaps[1], *imapp;
+ xfs_bmap_free_t free_list;
+ uint qblocks, resblks, resrtextents;
+ int committed;
+ int error;
+
+ trace_xfs_alloc_file_space(ip);
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return XFS_ERROR(EIO);
+
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ return error;
+
+ if (len <= 0)
+ return XFS_ERROR(EINVAL);
+
+ rt = XFS_IS_REALTIME_INODE(ip);
+ extsz = xfs_get_extsz_hint(ip);
+
+ count = len;
+ imapp = &imaps[0];
+ nimaps = 1;
+ startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
+ allocatesize_fsb = XFS_B_TO_FSB(mp, count);
+
+ /*
+ * Allocate file space until done or until there is an error
+ */
+ while (allocatesize_fsb && !error) {
+ xfs_fileoff_t s, e;
+
+ /*
+ * Determine space reservations for data/realtime.
+ */
+ if (unlikely(extsz)) {
+ s = startoffset_fsb;
+ do_div(s, extsz);
+ s *= extsz;
+ e = startoffset_fsb + allocatesize_fsb;
+ if ((temp = do_mod(startoffset_fsb, extsz)))
+ e += temp;
+ if ((temp = do_mod(e, extsz)))
+ e += extsz - temp;
+ } else {
+ s = 0;
+ e = allocatesize_fsb;
+ }
+
+ /*
+ * The transaction reservation is limited to a 32-bit block
+ * count, hence we need to limit the number of blocks we are
+ * trying to reserve to avoid an overflow. We can't allocate
+ * more than @nimaps extents, and an extent is limited on disk
+ * to MAXEXTLEN (21 bits), so use that to enforce the limit.
+ */
+ resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
+ if (unlikely(rt)) {
+ resrtextents = qblocks = resblks;
+ resrtextents /= mp->m_sb.sb_rextsize;
+ resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+ quota_flag = XFS_QMOPT_RES_RTBLKS;
+ } else {
+ resrtextents = 0;
+ resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
+ quota_flag = XFS_QMOPT_RES_REGBLKS;
+ }
+
+ /*
+ * Allocate and setup the transaction.
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
+ resblks, resrtextents);
+ /*
+ * Check for running out of space
+ */
+ if (error) {
+ /*
+ * Free the transaction structure.
+ */
+ ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
+ xfs_trans_cancel(tp, 0);
+ break;
+ }
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks,
+ 0, quota_flag);
+ if (error)
+ goto error1;
+
+ xfs_trans_ijoin(tp, ip, 0);
+
+ xfs_bmap_init(&free_list, &firstfsb);
+ error = xfs_bmapi_write(tp, ip, startoffset_fsb,
+ allocatesize_fsb, alloc_type, &firstfsb,
+ 0, imapp, &nimaps, &free_list);
+ if (error) {
+ goto error0;
+ }
+
+ /*
+ * Complete the transaction
+ */
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error) {
+ goto error0;
+ }
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ if (error) {
+ break;
+ }
+
+ allocated_fsb = imapp->br_blockcount;
+
+ if (nimaps == 0) {
+ error = XFS_ERROR(ENOSPC);
+ break;
+ }
+
+ startoffset_fsb += allocated_fsb;
+ allocatesize_fsb -= allocated_fsb;
+ }
+
+ return error;
+
+error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
+ xfs_bmap_cancel(&free_list);
+ xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
+
+error1: /* Just cancel transaction */
+ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+}
+
+/*
+ * Zero file bytes between startoff and endoff inclusive.
+ * The iolock is held exclusive and no blocks are buffered.
+ *
+ * This function is used by xfs_free_file_space() to zero
+ * partial blocks when the range to free is not block aligned.
+ * When unreserving space with boundaries that are not block
+ * aligned we round up the start and round down the end
+ * boundaries and then use this function to zero the parts of
+ * the blocks that got dropped during the rounding.
+ */
+STATIC int
+xfs_zero_remaining_bytes(
+ xfs_inode_t *ip,
+ xfs_off_t startoff,
+ xfs_off_t endoff)
+{
+ xfs_bmbt_irec_t imap;
+ xfs_fileoff_t offset_fsb;
+ xfs_off_t lastoffset;
+ xfs_off_t offset;
+ xfs_buf_t *bp;
+ xfs_mount_t *mp = ip->i_mount;
+ int nimap;
+ int error = 0;
+
+ /*
+ * Avoid doing I/O beyond eof - it's not necessary
+ * since nothing can read beyond eof. The space will
+ * be zeroed when the file is extended anyway.
+ */
+ if (startoff >= XFS_ISIZE(ip))
+ return 0;
+
+ if (endoff > XFS_ISIZE(ip))
+ endoff = XFS_ISIZE(ip);
+
+ bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
+ mp->m_rtdev_targp : mp->m_ddev_targp,
+ BTOBB(mp->m_sb.sb_blocksize), 0);
+ if (!bp)
+ return XFS_ERROR(ENOMEM);
+
+ xfs_buf_unlock(bp);
+
+ for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
+ uint lock_mode;
+
+ offset_fsb = XFS_B_TO_FSBT(mp, offset);
+ nimap = 1;
+
+ lock_mode = xfs_ilock_data_map_shared(ip);
+ error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
+ xfs_iunlock(ip, lock_mode);
+
+ if (error || nimap < 1)
+ break;
+ ASSERT(imap.br_blockcount >= 1);
+ ASSERT(imap.br_startoff == offset_fsb);
+ lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
+ if (lastoffset > endoff)
+ lastoffset = endoff;
+ if (imap.br_startblock == HOLESTARTBLOCK)
+ continue;
+ ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+ if (imap.br_state == XFS_EXT_UNWRITTEN)
+ continue;
+ XFS_BUF_UNDONE(bp);
+ XFS_BUF_UNWRITE(bp);
+ XFS_BUF_READ(bp);
+ XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
+
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ error = XFS_ERROR(EIO);
+ break;
+ }
+ xfs_buf_iorequest(bp);
+ error = xfs_buf_iowait(bp);
+ if (error) {
+ xfs_buf_ioerror_alert(bp,
+ "xfs_zero_remaining_bytes(read)");
+ break;
+ }
+ memset(bp->b_addr +
+ (offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
+ 0, lastoffset - offset + 1);
+ XFS_BUF_UNDONE(bp);
+ XFS_BUF_UNREAD(bp);
+ XFS_BUF_WRITE(bp);
+
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ error = XFS_ERROR(EIO);
+ break;
+ }
+ xfs_buf_iorequest(bp);
+ error = xfs_buf_iowait(bp);
+ if (error) {
+ xfs_buf_ioerror_alert(bp,
+ "xfs_zero_remaining_bytes(write)");
+ break;
+ }
+ }
+ xfs_buf_free(bp);
+ return error;
+}
+
+int
+xfs_free_file_space(
+ struct xfs_inode *ip,
+ xfs_off_t offset,
+ xfs_off_t len)
+{
+ int committed;
+ int done;
+ xfs_fileoff_t endoffset_fsb;
+ int error;
+ xfs_fsblock_t firstfsb;
+ xfs_bmap_free_t free_list;
+ xfs_bmbt_irec_t imap;
+ xfs_off_t ioffset;
+ xfs_extlen_t mod=0;
+ xfs_mount_t *mp;
+ int nimap;
+ uint resblks;
+ xfs_off_t rounding;
+ int rt;
+ xfs_fileoff_t startoffset_fsb;
+ xfs_trans_t *tp;
+
+ mp = ip->i_mount;
+
+ trace_xfs_free_file_space(ip);
+
+ error = xfs_qm_dqattach(ip, 0);
+ if (error)
+ return error;
+
+ error = 0;
+ if (len <= 0) /* if nothing being freed */
+ return error;
+ rt = XFS_IS_REALTIME_INODE(ip);
+ startoffset_fsb = XFS_B_TO_FSB(mp, offset);
+ endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
+
+ /* wait for the completion of any pending DIOs */
+ inode_dio_wait(VFS_I(ip));
+
+ rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
+ ioffset = offset & ~(rounding - 1);
+ error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+ ioffset, -1);
+ if (error)
+ goto out;
+ truncate_pagecache_range(VFS_I(ip), ioffset, -1);
+
+ /*
+ * Need to zero the stuff we're not freeing, on disk.
+ * If it's a realtime file & can't use unwritten extents then we
+ * actually need to zero the extent edges. Otherwise xfs_bunmapi
+ * will take care of it for us.
+ */
+ if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
+ nimap = 1;
+ error = xfs_bmapi_read(ip, startoffset_fsb, 1,
+ &imap, &nimap, 0);
+ if (error)
+ goto out;
+ ASSERT(nimap == 0 || nimap == 1);
+ if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
+ xfs_daddr_t block;
+
+ ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+ block = imap.br_startblock;
+ mod = do_div(block, mp->m_sb.sb_rextsize);
+ if (mod)
+ startoffset_fsb += mp->m_sb.sb_rextsize - mod;
+ }
+ nimap = 1;
+ error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
+ &imap, &nimap, 0);
+ if (error)
+ goto out;
+ ASSERT(nimap == 0 || nimap == 1);
+ if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
+ ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+ mod++;
+ if (mod && (mod != mp->m_sb.sb_rextsize))
+ endoffset_fsb -= mod;
+ }
+ }
+ if ((done = (endoffset_fsb <= startoffset_fsb)))
+ /*
+ * One contiguous piece to clear
+ */
+ error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
+ else {
+ /*
+ * Some full blocks, possibly two pieces to clear
+ */
+ if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
+ error = xfs_zero_remaining_bytes(ip, offset,
+ XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
+ if (!error &&
+ XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
+ error = xfs_zero_remaining_bytes(ip,
+ XFS_FSB_TO_B(mp, endoffset_fsb),
+ offset + len - 1);
+ }
+
+ /*
+ * free file space until done or until there is an error
+ */
+ resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+ while (!error && !done) {
+
+ /*
+ * allocate and setup the transaction. Allow this
+ * transaction to dip into the reserve blocks to ensure
+ * the freeing of the space succeeds at ENOSPC.
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);
+
+ /*
+ * check for running out of space
+ */
+ if (error) {
+ /*
+ * Free the transaction structure.
+ */
+ ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
+ xfs_trans_cancel(tp, 0);
+ break;
+ }
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_trans_reserve_quota(tp, mp,
+ ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
+ resblks, 0, XFS_QMOPT_RES_REGBLKS);
+ if (error)
+ goto error1;
+
+ xfs_trans_ijoin(tp, ip, 0);
+
+ /*
+ * issue the bunmapi() call to free the blocks
+ */
+ xfs_bmap_init(&free_list, &firstfsb);
+ error = xfs_bunmapi(tp, ip, startoffset_fsb,
+ endoffset_fsb - startoffset_fsb,
+ 0, 2, &firstfsb, &free_list, &done);
+ if (error) {
+ goto error0;
+ }
+
+ /*
+ * complete the transaction
+ */
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error) {
+ goto error0;
+ }
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ }
+
+ out:
+ return error;
+
+ error0:
+ xfs_bmap_cancel(&free_list);
+ error1:
+ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ goto out;
+}
+
+
+int
+xfs_zero_file_space(
+ struct xfs_inode *ip,
+ xfs_off_t offset,
+ xfs_off_t len)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ uint granularity;
+ xfs_off_t start_boundary;
+ xfs_off_t end_boundary;
+ int error;
+
+ trace_xfs_zero_file_space(ip);
+
+ granularity = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
+
+ /*
+ * Round the range of extents we are going to convert inwards. If the
+ * offset is aligned, then it doesn't get changed so we zero from the
+ * start of the block offset points to.
+ */
+ start_boundary = round_up(offset, granularity);
+ end_boundary = round_down(offset + len, granularity);
+
+ ASSERT(start_boundary >= offset);
+ ASSERT(end_boundary <= offset + len);
+
+ if (start_boundary < end_boundary - 1) {
+ /*
+ * punch out delayed allocation blocks and the page cache over
+ * the conversion range
+ */
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_bmap_punch_delalloc_range(ip,
+ XFS_B_TO_FSBT(mp, start_boundary),
+ XFS_B_TO_FSB(mp, end_boundary - start_boundary));
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ truncate_pagecache_range(VFS_I(ip), start_boundary,
+ end_boundary - 1);
+
+ /* convert the blocks */
+ error = xfs_alloc_file_space(ip, start_boundary,
+ end_boundary - start_boundary - 1,
+ XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT);
+ if (error)
+ goto out;
+
+ /* We've handled the interior of the range, now for the edges */
+ if (start_boundary != offset) {
+ error = xfs_iozero(ip, offset, start_boundary - offset);
+ if (error)
+ goto out;
+ }
+
+ if (end_boundary != offset + len)
+ error = xfs_iozero(ip, end_boundary,
+ offset + len - end_boundary);
+
+ } else {
+ /*
+ * It's either a sub-granularity range or the range spanned lies
+ * partially across two adjacent blocks.
+ */
+ error = xfs_iozero(ip, offset, len);
+ }
+
+out:
+ return error;
+
+}
+
+/*
+ * xfs_collapse_file_space()
+ * This routine frees disk space and shift extent for the given file.
+ * The first thing we do is to free data blocks in the specified range
+ * by calling xfs_free_file_space(). It would also sync dirty data
+ * and invalidate page cache over the region on which collapse range
+ * is working. And Shift extent records to the left to cover a hole.
+ * RETURNS:
+ * 0 on success
+ * errno on error
+ *
+ */
+int
+xfs_collapse_file_space(
+ struct xfs_inode *ip,
+ xfs_off_t offset,
+ xfs_off_t len)
+{
+ int done = 0;
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_trans *tp;
+ int error;
+ xfs_extnum_t current_ext = 0;
+ struct xfs_bmap_free free_list;
+ xfs_fsblock_t first_block;
+ int committed;
+ xfs_fileoff_t start_fsb;
+ xfs_fileoff_t shift_fsb;
+
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+ trace_xfs_collapse_file_space(ip);
+
+ start_fsb = XFS_B_TO_FSB(mp, offset + len);
+ shift_fsb = XFS_B_TO_FSB(mp, len);
+
+ error = xfs_free_file_space(ip, offset, len);
+ if (error)
+ return error;
+
+ while (!error && !done) {
+ tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+ /*
+ * We would need to reserve permanent block for transaction.
+ * This will come into picture when after shifting extent into
+ * hole we found that adjacent extents can be merged which
+ * may lead to freeing of a block during record update.
+ */
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
+ XFS_DIOSTRAT_SPACE_RES(mp, 0), 0);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ break;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
+ ip->i_gdquot, ip->i_pdquot,
+ XFS_DIOSTRAT_SPACE_RES(mp, 0), 0,
+ XFS_QMOPT_RES_REGBLKS);
+ if (error)
+ goto out;
+
+ xfs_trans_ijoin(tp, ip, 0);
+
+ xfs_bmap_init(&free_list, &first_block);
+
+ /*
+ * We are using the write transaction in which max 2 bmbt
+ * updates are allowed
+ */
+ error = xfs_bmap_shift_extents(tp, ip, &done, start_fsb,
+ shift_fsb, &current_ext,
+ &first_block, &free_list,
+ XFS_BMAP_MAX_SHIFT_EXTENTS);
+ if (error)
+ goto out;
+
+ error = xfs_bmap_finish(&tp, &free_list, &committed);
+ if (error)
+ goto out;
+
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ }
+
+ return error;
+
+out:
+ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+}
+
+/*
+ * We need to check that the format of the data fork in the temporary inode is
+ * valid for the target inode before doing the swap. This is not a problem with
+ * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
+ * data fork depending on the space the attribute fork is taking so we can get
+ * invalid formats on the target inode.
+ *
+ * E.g. target has space for 7 extents in extent format, temp inode only has
+ * space for 6. If we defragment down to 7 extents, then the tmp format is a
+ * btree, but when swapped it needs to be in extent format. Hence we can't just
+ * blindly swap data forks on attr2 filesystems.
+ *
+ * Note that we check the swap in both directions so that we don't end up with
+ * a corrupt temporary inode, either.
+ *
+ * Note that fixing the way xfs_fsr sets up the attribute fork in the source
+ * inode will prevent this situation from occurring, so all we do here is
+ * reject and log the attempt. basically we are putting the responsibility on
+ * userspace to get this right.
+ */
+static int
+xfs_swap_extents_check_format(
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip) /* tmp inode */
+{
+
+ /* Should never get a local format */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
+ tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
+ return EINVAL;
+
+ /*
+ * if the target inode has less extents that then temporary inode then
+ * why did userspace call us?
+ */
+ if (ip->i_d.di_nextents < tip->i_d.di_nextents)
+ return EINVAL;
+
+ /*
+ * if the target inode is in extent form and the temp inode is in btree
+ * form then we will end up with the target inode in the wrong format
+ * as we already know there are less extents in the temp inode.
+ */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
+ return EINVAL;
+
+ /* Check temp in extent form to max in target */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) >
+ XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+ return EINVAL;
+
+ /* Check target in extent form to max in temp */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) >
+ XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+ return EINVAL;
+
+ /*
+ * If we are in a btree format, check that the temp root block will fit
+ * in the target and that it has enough extents to be in btree format
+ * in the target.
+ *
+ * Note that we have to be careful to allow btree->extent conversions
+ * (a common defrag case) which will occur when the temp inode is in
+ * extent format...
+ */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ if (XFS_IFORK_BOFF(ip) &&
+ XFS_BMAP_BMDR_SPACE(tip->i_df.if_broot) > XFS_IFORK_BOFF(ip))
+ return EINVAL;
+ if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
+ XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+ return EINVAL;
+ }
+
+ /* Reciprocal target->temp btree format checks */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ if (XFS_IFORK_BOFF(tip) &&
+ XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip))
+ return EINVAL;
+ if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
+ XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+ return EINVAL;
+ }
+
+ return 0;
+}
+
+int
+xfs_swap_extents(
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip, /* tmp inode */
+ xfs_swapext_t *sxp)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ xfs_trans_t *tp;
+ xfs_bstat_t *sbp = &sxp->sx_stat;
+ xfs_ifork_t *tempifp, *ifp, *tifp;
+ int src_log_flags, target_log_flags;
+ int error = 0;
+ int aforkblks = 0;
+ int taforkblks = 0;
+ __uint64_t tmp;
+
+ tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
+ if (!tempifp) {
+ error = XFS_ERROR(ENOMEM);
+ goto out;
+ }
+
+ /*
+ * we have to do two separate lock calls here to keep lockdep
+ * happy. If we try to get all the locks in one call, lock will
+ * report false positives when we drop the ILOCK and regain them
+ * below.
+ */
+ xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
+ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
+
+ /* Verify that both files have the same format */
+ if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
+ error = XFS_ERROR(EINVAL);
+ goto out_unlock;
+ }
+
+ /* Verify both files are either real-time or non-realtime */
+ if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
+ error = XFS_ERROR(EINVAL);
+ goto out_unlock;
+ }
+
+ error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
+ if (error)
+ goto out_unlock;
+ truncate_pagecache_range(VFS_I(tip), 0, -1);
+
+ /* Verify O_DIRECT for ftmp */
+ if (VN_CACHED(VFS_I(tip)) != 0) {
+ error = XFS_ERROR(EINVAL);
+ goto out_unlock;
+ }
+
+ /* Verify all data are being swapped */
+ if (sxp->sx_offset != 0 ||
+ sxp->sx_length != ip->i_d.di_size ||
+ sxp->sx_length != tip->i_d.di_size) {
+ error = XFS_ERROR(EFAULT);
+ goto out_unlock;
+ }
+
+ trace_xfs_swap_extent_before(ip, 0);
+ trace_xfs_swap_extent_before(tip, 1);
+
+ /* check inode formats now that data is flushed */
+ error = xfs_swap_extents_check_format(ip, tip);
+ if (error) {
+ xfs_notice(mp,
+ "%s: inode 0x%llx format is incompatible for exchanging.",
+ __func__, ip->i_ino);
+ goto out_unlock;
+ }
+
+ /*
+ * Compare the current change & modify times with that
+ * passed in. If they differ, we abort this swap.
+ * This is the mechanism used to ensure the calling
+ * process that the file was not changed out from
+ * under it.
+ */
+ if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
+ (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
+ (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
+ (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
+ error = XFS_ERROR(EBUSY);
+ goto out_unlock;
+ }
+
+ /* We need to fail if the file is memory mapped. Once we have tossed
+ * all existing pages, the page fault will have no option
+ * but to go to the filesystem for pages. By making the page fault call
+ * vop_read (or write in the case of autogrow) they block on the iolock
+ * until we have switched the extents.
+ */
+ if (VN_MAPPED(VFS_I(ip))) {
+ error = XFS_ERROR(EBUSY);
+ goto out_unlock;
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_iunlock(tip, XFS_ILOCK_EXCL);
+
+ /*
+ * There is a race condition here since we gave up the
+ * ilock. However, the data fork will not change since
+ * we have the iolock (locked for truncation too) so we
+ * are safe. We don't really care if non-io related
+ * fields change.
+ */
+ truncate_pagecache_range(VFS_I(ip), 0, -1);
+
+ tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
+ error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+ if (error) {
+ xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ xfs_iunlock(tip, XFS_IOLOCK_EXCL);
+ xfs_trans_cancel(tp, 0);
+ goto out;
+ }
+ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
+
+ /*
+ * Count the number of extended attribute blocks
+ */
+ if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
+ (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
+ error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
+ if (error)
+ goto out_trans_cancel;
+ }
+ if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
+ (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
+ error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
+ &taforkblks);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+
+ /*
+ * Before we've swapped the forks, lets set the owners of the forks
+ * appropriately. We have to do this as we are demand paging the btree
+ * buffers, and so the validation done on read will expect the owner
+ * field to be correctly set. Once we change the owners, we can swap the
+ * inode forks.
+ *
+ * Note the trickiness in setting the log flags - we set the owner log
+ * flag on the opposite inode (i.e. the inode we are setting the new
+ * owner to be) because once we swap the forks and log that, log
+ * recovery is going to see the fork as owned by the swapped inode,
+ * not the pre-swapped inodes.
+ */
+ src_log_flags = XFS_ILOG_CORE;
+ target_log_flags = XFS_ILOG_CORE;
+ if (ip->i_d.di_version == 3 &&
+ ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ target_log_flags |= XFS_ILOG_DOWNER;
+ error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
+ tip->i_ino, NULL);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ if (tip->i_d.di_version == 3 &&
+ tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+ src_log_flags |= XFS_ILOG_DOWNER;
+ error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
+ ip->i_ino, NULL);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ /*
+ * Swap the data forks of the inodes
+ */
+ ifp = &ip->i_df;
+ tifp = &tip->i_df;
+ *tempifp = *ifp; /* struct copy */
+ *ifp = *tifp; /* struct copy */
+ *tifp = *tempifp; /* struct copy */
+
+ /*
+ * Fix the on-disk inode values
+ */
+ tmp = (__uint64_t)ip->i_d.di_nblocks;
+ ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
+ tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
+
+ tmp = (__uint64_t) ip->i_d.di_nextents;
+ ip->i_d.di_nextents = tip->i_d.di_nextents;
+ tip->i_d.di_nextents = tmp;
+
+ tmp = (__uint64_t) ip->i_d.di_format;
+ ip->i_d.di_format = tip->i_d.di_format;
+ tip->i_d.di_format = tmp;
+
+ /*
+ * The extents in the source inode could still contain speculative
+ * preallocation beyond EOF (e.g. the file is open but not modified
+ * while defrag is in progress). In that case, we need to copy over the
+ * number of delalloc blocks the data fork in the source inode is
+ * tracking beyond EOF so that when the fork is truncated away when the
+ * temporary inode is unlinked we don't underrun the i_delayed_blks
+ * counter on that inode.
+ */
+ ASSERT(tip->i_delayed_blks == 0);
+ tip->i_delayed_blks = ip->i_delayed_blks;
+ ip->i_delayed_blks = 0;
+
+ switch (ip->i_d.di_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ /* If the extents fit in the inode, fix the
+ * pointer. Otherwise it's already NULL or
+ * pointing to the extent.
+ */
+ if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
+ ifp->if_u1.if_extents =
+ ifp->if_u2.if_inline_ext;
+ }
+ src_log_flags |= XFS_ILOG_DEXT;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ ASSERT(ip->i_d.di_version < 3 ||
+ (src_log_flags & XFS_ILOG_DOWNER));
+ src_log_flags |= XFS_ILOG_DBROOT;
+ break;
+ }
+
+ switch (tip->i_d.di_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ /* If the extents fit in the inode, fix the
+ * pointer. Otherwise it's already NULL or
+ * pointing to the extent.
+ */
+ if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
+ tifp->if_u1.if_extents =
+ tifp->if_u2.if_inline_ext;
+ }
+ target_log_flags |= XFS_ILOG_DEXT;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ target_log_flags |= XFS_ILOG_DBROOT;
+ ASSERT(tip->i_d.di_version < 3 ||
+ (target_log_flags & XFS_ILOG_DOWNER));
+ break;
+ }
+
+ xfs_trans_log_inode(tp, ip, src_log_flags);
+ xfs_trans_log_inode(tp, tip, target_log_flags);
+
+ /*
+ * If this is a synchronous mount, make sure that the
+ * transaction goes to disk before returning to the user.
+ */
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
+ xfs_trans_set_sync(tp);
+
+ error = xfs_trans_commit(tp, 0);
+
+ trace_xfs_swap_extent_after(ip, 0);
+ trace_xfs_swap_extent_after(tip, 1);
+out:
+ kmem_free(tempifp);
+ return error;
+
+out_unlock:
+ xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ goto out;
+
+out_trans_cancel:
+ xfs_trans_cancel(tp, 0);
+ goto out_unlock;
+}
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
new file mode 100644
index 00000000000..2fdb72d2c90
--- /dev/null
+++ b/fs/xfs/xfs_bmap_util.h
@@ -0,0 +1,112 @@
+/*
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#ifndef __XFS_BMAP_UTIL_H__
+#define __XFS_BMAP_UTIL_H__
+
+/* Kernel only BMAP related definitions and functions */
+
+struct xfs_bmbt_irec;
+struct xfs_bmap_free_item;
+struct xfs_ifork;
+struct xfs_inode;
+struct xfs_mount;
+struct xfs_trans;
+
+/*
+ * Argument structure for xfs_bmap_alloc.
+ */
+struct xfs_bmalloca {
+ xfs_fsblock_t *firstblock; /* i/o first block allocated */
+ struct xfs_bmap_free *flist; /* bmap freelist */
+ struct xfs_trans *tp; /* transaction pointer */
+ struct xfs_inode *ip; /* incore inode pointer */
+ struct xfs_bmbt_irec prev; /* extent before the new one */
+ struct xfs_bmbt_irec got; /* extent after, or delayed */
+
+ xfs_fileoff_t offset; /* offset in file filling in */
+ xfs_extlen_t length; /* i/o length asked/allocated */
+ xfs_fsblock_t blkno; /* starting block of new extent */
+
+ struct xfs_btree_cur *cur; /* btree cursor */
+ xfs_extnum_t idx; /* current extent index */
+ int nallocs;/* number of extents alloc'd */
+ int logflags;/* flags for transaction logging */
+
+ xfs_extlen_t total; /* total blocks needed for xaction */
+ xfs_extlen_t minlen; /* minimum allocation size (blocks) */
+ xfs_extlen_t minleft; /* amount must be left after alloc */
+ bool eof; /* set if allocating past last extent */
+ bool wasdel; /* replacing a delayed allocation */
+ bool userdata;/* set if is user data */
+ bool aeof; /* allocated space at eof */
+ bool conv; /* overwriting unwritten extents */
+ int flags;
+ struct completion *done;
+ struct work_struct work;
+ int result;
+};
+
+int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
+ int *committed);
+int xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
+int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
+ int whichfork, int *eof);
+int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
+ int whichfork, int *count);
+int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip,
+ xfs_fileoff_t start_fsb, xfs_fileoff_t length);
+
+/* bmap to userspace formatter - copy to user & advance pointer */
+typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *, int *);
+int xfs_getbmap(struct xfs_inode *ip, struct getbmapx *bmv,
+ xfs_bmap_format_t formatter, void *arg);
+
+/* functions in xfs_bmap.c that are only needed by xfs_bmap_util.c */
+void xfs_bmap_del_free(struct xfs_bmap_free *flist,
+ struct xfs_bmap_free_item *prev,
+ struct xfs_bmap_free_item *free);
+int xfs_bmap_extsize_align(struct xfs_mount *mp, struct xfs_bmbt_irec *gotp,
+ struct xfs_bmbt_irec *prevp, xfs_extlen_t extsz,
+ int rt, int eof, int delay, int convert,
+ xfs_fileoff_t *offp, xfs_extlen_t *lenp);
+void xfs_bmap_adjacent(struct xfs_bmalloca *ap);
+int xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+ int whichfork, struct xfs_bmbt_irec *rec,
+ int *is_empty);
+
+/* preallocation and hole punch interface */
+int xfs_alloc_file_space(struct xfs_inode *ip, xfs_off_t offset,
+ xfs_off_t len, int alloc_type);
+int xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset,
+ xfs_off_t len);
+int xfs_zero_file_space(struct xfs_inode *ip, xfs_off_t offset,
+ xfs_off_t len);
+int xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset,
+ xfs_off_t len);
+
+/* EOF block manipulation functions */
+bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
+int xfs_free_eofblocks(struct xfs_mount *mp, struct xfs_inode *ip,
+ bool need_iolock);
+
+int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
+ struct xfs_swapext *sx);
+
+xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
+
+#endif /* __XFS_BMAP_UTIL_H__ */
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e53e317b158..cf893bc1e37 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -17,22 +17,23 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
+#include "xfs_buf_item.h"
#include "xfs_btree.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_cksum.h"
+#include "xfs_alloc.h"
/*
* Cursor allocation zone.
@@ -42,9 +43,14 @@ kmem_zone_t *xfs_btree_cur_zone;
/*
* Btree magic numbers.
*/
-const __uint32_t xfs_magics[XFS_BTNUM_MAX] = {
- XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC
+static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
+ { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
+ XFS_FIBT_MAGIC },
+ { XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC,
+ XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC }
};
+#define xfs_btree_magic(cur) \
+ xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum]
STATIC int /* error (0 or EFSCORRUPTED) */
@@ -54,30 +60,38 @@ xfs_btree_check_lblock(
int level, /* level of the btree block */
struct xfs_buf *bp) /* buffer for block, if any */
{
- int lblock_ok; /* block passes checks */
+ int lblock_ok = 1; /* block passes checks */
struct xfs_mount *mp; /* file system mount point */
mp = cur->bc_mp;
- lblock_ok =
- be32_to_cpu(block->bb_magic) == xfs_magics[cur->bc_btnum] &&
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ lblock_ok = lblock_ok &&
+ uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_uuid) &&
+ block->bb_u.l.bb_blkno == cpu_to_be64(
+ bp ? bp->b_bn : XFS_BUF_DADDR_NULL);
+ }
+
+ lblock_ok = lblock_ok &&
+ be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) &&
be16_to_cpu(block->bb_level) == level &&
be16_to_cpu(block->bb_numrecs) <=
cur->bc_ops->get_maxrecs(cur, level) &&
block->bb_u.l.bb_leftsib &&
(block->bb_u.l.bb_leftsib == cpu_to_be64(NULLDFSBNO) ||
XFS_FSB_SANITY_CHECK(mp,
- be64_to_cpu(block->bb_u.l.bb_leftsib))) &&
+ be64_to_cpu(block->bb_u.l.bb_leftsib))) &&
block->bb_u.l.bb_rightsib &&
(block->bb_u.l.bb_rightsib == cpu_to_be64(NULLDFSBNO) ||
XFS_FSB_SANITY_CHECK(mp,
- be64_to_cpu(block->bb_u.l.bb_rightsib)));
+ be64_to_cpu(block->bb_u.l.bb_rightsib)));
+
if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp,
XFS_ERRTAG_BTREE_CHECK_LBLOCK,
XFS_RANDOM_BTREE_CHECK_LBLOCK))) {
if (bp)
trace_xfs_btree_corrupt(bp, _RET_IP_);
- XFS_ERROR_REPORT("xfs_btree_check_lblock", XFS_ERRLEVEL_LOW,
- mp);
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
@@ -90,16 +104,26 @@ xfs_btree_check_sblock(
int level, /* level of the btree block */
struct xfs_buf *bp) /* buffer containing block */
{
+ struct xfs_mount *mp; /* file system mount point */
struct xfs_buf *agbp; /* buffer for ag. freespace struct */
struct xfs_agf *agf; /* ag. freespace structure */
xfs_agblock_t agflen; /* native ag. freespace length */
- int sblock_ok; /* block passes checks */
+ int sblock_ok = 1; /* block passes checks */
+ mp = cur->bc_mp;
agbp = cur->bc_private.a.agbp;
agf = XFS_BUF_TO_AGF(agbp);
agflen = be32_to_cpu(agf->agf_length);
- sblock_ok =
- be32_to_cpu(block->bb_magic) == xfs_magics[cur->bc_btnum] &&
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ sblock_ok = sblock_ok &&
+ uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid) &&
+ block->bb_u.s.bb_blkno == cpu_to_be64(
+ bp ? bp->b_bn : XFS_BUF_DADDR_NULL);
+ }
+
+ sblock_ok = sblock_ok &&
+ be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) &&
be16_to_cpu(block->bb_level) == level &&
be16_to_cpu(block->bb_numrecs) <=
cur->bc_ops->get_maxrecs(cur, level) &&
@@ -109,13 +133,13 @@ xfs_btree_check_sblock(
(block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK) ||
be32_to_cpu(block->bb_u.s.bb_rightsib) < agflen) &&
block->bb_u.s.bb_rightsib;
- if (unlikely(XFS_TEST_ERROR(!sblock_ok, cur->bc_mp,
+
+ if (unlikely(XFS_TEST_ERROR(!sblock_ok, mp,
XFS_ERRTAG_BTREE_CHECK_SBLOCK,
XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
if (bp)
trace_xfs_btree_corrupt(bp, _RET_IP_);
- XFS_CORRUPTION_ERROR("xfs_btree_check_sblock",
- XFS_ERRLEVEL_LOW, cur->bc_mp, block);
+ XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
@@ -194,6 +218,70 @@ xfs_btree_check_ptr(
#endif
/*
+ * Calculate CRC on the whole btree block and stuff it into the
+ * long-form btree header.
+ *
+ * Prior to calculting the CRC, pull the LSN out of the buffer log item and put
+ * it into the buffer so recovery knows what the last modifcation was that made
+ * it to disk.
+ */
+void
+xfs_btree_lblock_calc_crc(
+ struct xfs_buf *bp)
+{
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+
+ if (!xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
+ return;
+ if (bip)
+ block->bb_u.l.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+ xfs_buf_update_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF);
+}
+
+bool
+xfs_btree_lblock_verify_crc(
+ struct xfs_buf *bp)
+{
+ if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
+ return xfs_buf_verify_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF);
+
+ return true;
+}
+
+/*
+ * Calculate CRC on the whole btree block and stuff it into the
+ * short-form btree header.
+ *
+ * Prior to calculting the CRC, pull the LSN out of the buffer log item and put
+ * it into the buffer so recovery knows what the last modifcation was that made
+ * it to disk.
+ */
+void
+xfs_btree_sblock_calc_crc(
+ struct xfs_buf *bp)
+{
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+
+ if (!xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
+ return;
+ if (bip)
+ block->bb_u.s.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+ xfs_buf_update_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF);
+}
+
+bool
+xfs_btree_sblock_verify_crc(
+ struct xfs_buf *bp)
+{
+ if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
+ return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF);
+
+ return true;
+}
+
+/*
* Delete the btree cursor.
*/
void
@@ -266,17 +354,19 @@ xfs_btree_dup_cursor(
for (i = 0; i < new->bc_nlevels; i++) {
new->bc_ptrs[i] = cur->bc_ptrs[i];
new->bc_ra[i] = cur->bc_ra[i];
- if ((bp = cur->bc_bufs[i])) {
- if ((error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
- XFS_BUF_ADDR(bp), mp->m_bsize, 0, &bp))) {
+ bp = cur->bc_bufs[i];
+ if (bp) {
+ error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+ XFS_BUF_ADDR(bp), mp->m_bsize,
+ 0, &bp,
+ cur->bc_ops->buf_ops);
+ if (error) {
xfs_btree_del_cursor(new, error);
*ncur = NULL;
return error;
}
- new->bc_bufs[i] = bp;
- ASSERT(!xfs_buf_geterror(bp));
- } else
- new->bc_bufs[i] = NULL;
+ }
+ new->bc_bufs[i] = bp;
}
*ncur = new;
return 0;
@@ -317,9 +407,14 @@ xfs_btree_dup_cursor(
*/
static inline size_t xfs_btree_block_len(struct xfs_btree_cur *cur)
{
- return (cur->bc_flags & XFS_BTREE_LONG_PTRS) ?
- XFS_BTREE_LBLOCK_LEN :
- XFS_BTREE_SBLOCK_LEN;
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+ if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS)
+ return XFS_BTREE_LBLOCK_CRC_LEN;
+ return XFS_BTREE_LBLOCK_LEN;
+ }
+ if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS)
+ return XFS_BTREE_SBLOCK_CRC_LEN;
+ return XFS_BTREE_SBLOCK_LEN;
}
/*
@@ -413,7 +508,7 @@ xfs_btree_ptr_addr(
}
/*
- * Get a the root block which is stored in the inode.
+ * Get the root block which is stored in the inode.
*
* For now this btree implementation assumes the btree root is always
* stored in the if_broot field of an inode fork.
@@ -459,14 +554,11 @@ xfs_btree_get_bufl(
xfs_fsblock_t fsbno, /* file system block number */
uint lock) /* lock flags for get_buf */
{
- xfs_buf_t *bp; /* buffer pointer (return value) */
xfs_daddr_t d; /* real disk block address */
ASSERT(fsbno != NULLFSBLOCK);
d = XFS_FSB_TO_DADDR(mp, fsbno);
- bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
- ASSERT(!xfs_buf_geterror(bp));
- return bp;
+ return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
}
/*
@@ -481,15 +573,12 @@ xfs_btree_get_bufs(
xfs_agblock_t agbno, /* allocation group block number */
uint lock) /* lock flags for get_buf */
{
- xfs_buf_t *bp; /* buffer pointer (return value) */
xfs_daddr_t d; /* real disk block address */
ASSERT(agno != NULLAGNUMBER);
ASSERT(agbno != NULLAGBLOCK);
d = XFS_AGB_TO_DADDR(mp, agno, agbno);
- bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
- ASSERT(!xfs_buf_geterror(bp));
- return bp;
+ return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
}
/*
@@ -609,26 +698,26 @@ xfs_btree_offsets(
* Get a buffer for the block, return it read in.
* Long-form addressing.
*/
-int /* error */
+int
xfs_btree_read_bufl(
- xfs_mount_t *mp, /* file system mount point */
- xfs_trans_t *tp, /* transaction pointer */
- xfs_fsblock_t fsbno, /* file system block number */
- uint lock, /* lock flags for read_buf */
- xfs_buf_t **bpp, /* buffer for fsbno */
- int refval) /* ref count value for buffer */
-{
- xfs_buf_t *bp; /* return value */
+ struct xfs_mount *mp, /* file system mount point */
+ struct xfs_trans *tp, /* transaction pointer */
+ xfs_fsblock_t fsbno, /* file system block number */
+ uint lock, /* lock flags for read_buf */
+ struct xfs_buf **bpp, /* buffer for fsbno */
+ int refval, /* ref count value for buffer */
+ const struct xfs_buf_ops *ops)
+{
+ struct xfs_buf *bp; /* return value */
xfs_daddr_t d; /* real disk block address */
- int error;
+ int error;
ASSERT(fsbno != NULLFSBLOCK);
d = XFS_FSB_TO_DADDR(mp, fsbno);
- if ((error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d,
- mp->m_bsize, lock, &bp))) {
+ error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d,
+ mp->m_bsize, lock, &bp, ops);
+ if (error)
return error;
- }
- ASSERT(!xfs_buf_geterror(bp));
if (bp)
xfs_buf_set_ref(bp, refval);
*bpp = bp;
@@ -642,15 +731,16 @@ xfs_btree_read_bufl(
/* ARGSUSED */
void
xfs_btree_reada_bufl(
- xfs_mount_t *mp, /* file system mount point */
- xfs_fsblock_t fsbno, /* file system block number */
- xfs_extlen_t count) /* count of filesystem blocks */
+ struct xfs_mount *mp, /* file system mount point */
+ xfs_fsblock_t fsbno, /* file system block number */
+ xfs_extlen_t count, /* count of filesystem blocks */
+ const struct xfs_buf_ops *ops)
{
xfs_daddr_t d;
ASSERT(fsbno != NULLFSBLOCK);
d = XFS_FSB_TO_DADDR(mp, fsbno);
- xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count);
+ xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, ops);
}
/*
@@ -660,17 +750,18 @@ xfs_btree_reada_bufl(
/* ARGSUSED */
void
xfs_btree_reada_bufs(
- xfs_mount_t *mp, /* file system mount point */
- xfs_agnumber_t agno, /* allocation group number */
- xfs_agblock_t agbno, /* allocation group block number */
- xfs_extlen_t count) /* count of filesystem blocks */
+ struct xfs_mount *mp, /* file system mount point */
+ xfs_agnumber_t agno, /* allocation group number */
+ xfs_agblock_t agbno, /* allocation group block number */
+ xfs_extlen_t count, /* count of filesystem blocks */
+ const struct xfs_buf_ops *ops)
{
xfs_daddr_t d;
ASSERT(agno != NULLAGNUMBER);
ASSERT(agbno != NULLAGBLOCK);
d = XFS_AGB_TO_DADDR(mp, agno, agbno);
- xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count);
+ xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, ops);
}
STATIC int
@@ -684,12 +775,14 @@ xfs_btree_readahead_lblock(
xfs_dfsbno_t right = be64_to_cpu(block->bb_u.l.bb_rightsib);
if ((lr & XFS_BTCUR_LEFTRA) && left != NULLDFSBNO) {
- xfs_btree_reada_bufl(cur->bc_mp, left, 1);
+ xfs_btree_reada_bufl(cur->bc_mp, left, 1,
+ cur->bc_ops->buf_ops);
rval++;
}
if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLDFSBNO) {
- xfs_btree_reada_bufl(cur->bc_mp, right, 1);
+ xfs_btree_reada_bufl(cur->bc_mp, right, 1,
+ cur->bc_ops->buf_ops);
rval++;
}
@@ -709,13 +802,13 @@ xfs_btree_readahead_sblock(
if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
- left, 1);
+ left, 1, cur->bc_ops->buf_ops);
rval++;
}
if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) {
xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
- right, 1);
+ right, 1, cur->bc_ops->buf_ops);
rval++;
}
@@ -753,6 +846,41 @@ xfs_btree_readahead(
return xfs_btree_readahead_sblock(cur, lr, block);
}
+STATIC xfs_daddr_t
+xfs_btree_ptr_to_daddr(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr)
+{
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+ ASSERT(ptr->l != cpu_to_be64(NULLDFSBNO));
+
+ return XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l));
+ } else {
+ ASSERT(cur->bc_private.a.agno != NULLAGNUMBER);
+ ASSERT(ptr->s != cpu_to_be32(NULLAGBLOCK));
+
+ return XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_private.a.agno,
+ be32_to_cpu(ptr->s));
+ }
+}
+
+/*
+ * Readahead @count btree blocks at the given @ptr location.
+ *
+ * We don't need to care about long or short form btrees here as we have a
+ * method of converting the ptr directly to a daddr available to us.
+ */
+STATIC void
+xfs_btree_readahead_ptr(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr,
+ xfs_extlen_t count)
+{
+ xfs_buf_readahead(cur->bc_mp->m_ddev_targp,
+ xfs_btree_ptr_to_daddr(cur, ptr),
+ cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops);
+}
+
/*
* Set the buffer for level "lev" in the cursor to bp, releasing
* any previous buffer.
@@ -853,29 +981,88 @@ xfs_btree_set_sibling(
}
}
-STATIC void
+void
+xfs_btree_init_block_int(
+ struct xfs_mount *mp,
+ struct xfs_btree_block *buf,
+ xfs_daddr_t blkno,
+ __u32 magic,
+ __u16 level,
+ __u16 numrecs,
+ __u64 owner,
+ unsigned int flags)
+{
+ buf->bb_magic = cpu_to_be32(magic);
+ buf->bb_level = cpu_to_be16(level);
+ buf->bb_numrecs = cpu_to_be16(numrecs);
+
+ if (flags & XFS_BTREE_LONG_PTRS) {
+ buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
+ buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
+ if (flags & XFS_BTREE_CRC_BLOCKS) {
+ buf->bb_u.l.bb_blkno = cpu_to_be64(blkno);
+ buf->bb_u.l.bb_owner = cpu_to_be64(owner);
+ uuid_copy(&buf->bb_u.l.bb_uuid, &mp->m_sb.sb_uuid);
+ buf->bb_u.l.bb_pad = 0;
+ buf->bb_u.l.bb_lsn = 0;
+ }
+ } else {
+ /* owner is a 32 bit value on short blocks */
+ __u32 __owner = (__u32)owner;
+
+ buf->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
+ buf->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
+ if (flags & XFS_BTREE_CRC_BLOCKS) {
+ buf->bb_u.s.bb_blkno = cpu_to_be64(blkno);
+ buf->bb_u.s.bb_owner = cpu_to_be32(__owner);
+ uuid_copy(&buf->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid);
+ buf->bb_u.s.bb_lsn = 0;
+ }
+ }
+}
+
+void
xfs_btree_init_block(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ __u32 magic,
+ __u16 level,
+ __u16 numrecs,
+ __u64 owner,
+ unsigned int flags)
+{
+ xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn,
+ magic, level, numrecs, owner, flags);
+}
+
+STATIC void
+xfs_btree_init_block_cur(
struct xfs_btree_cur *cur,
+ struct xfs_buf *bp,
int level,
- int numrecs,
- struct xfs_btree_block *new) /* new block */
+ int numrecs)
{
- new->bb_magic = cpu_to_be32(xfs_magics[cur->bc_btnum]);
- new->bb_level = cpu_to_be16(level);
- new->bb_numrecs = cpu_to_be16(numrecs);
+ __u64 owner;
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- new->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
- new->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
- } else {
- new->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
- new->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
- }
+ /*
+ * we can pull the owner from the cursor right now as the different
+ * owners align directly with the pointer size of the btree. This may
+ * change in future, but is safe for current users of the generic btree
+ * code.
+ */
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ owner = cur->bc_private.b.ip->i_ino;
+ else
+ owner = cur->bc_private.a.agno;
+
+ xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn,
+ xfs_btree_magic(cur), level, numrecs,
+ owner, cur->bc_flags);
}
/*
* Return true if ptr is the last record in the btree and
- * we need to track updateѕ to this record. The decision
+ * we need to track updates to this record. The decision
* will be further refined in the update_lastrec method.
*/
STATIC int
@@ -912,24 +1099,6 @@ xfs_btree_buf_to_ptr(
}
}
-STATIC xfs_daddr_t
-xfs_btree_ptr_to_daddr(
- struct xfs_btree_cur *cur,
- union xfs_btree_ptr *ptr)
-{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- ASSERT(ptr->l != cpu_to_be64(NULLDFSBNO));
-
- return XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l));
- } else {
- ASSERT(cur->bc_private.a.agno != NULLAGNUMBER);
- ASSERT(ptr->s != cpu_to_be32(NULLAGBLOCK));
-
- return XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_private.a.agno,
- be32_to_cpu(ptr->s));
- }
-}
-
STATIC void
xfs_btree_set_refs(
struct xfs_btree_cur *cur,
@@ -941,6 +1110,7 @@ xfs_btree_set_refs(
xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
break;
case XFS_BTNUM_INO:
+ case XFS_BTNUM_FINO:
xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
break;
case XFS_BTNUM_BMAP:
@@ -972,6 +1142,7 @@ xfs_btree_get_buf_block(
if (!*bpp)
return ENOMEM;
+ (*bpp)->b_ops = cur->bc_ops->buf_ops;
*block = XFS_BUF_TO_BLOCK(*bpp);
return 0;
}
@@ -984,7 +1155,6 @@ STATIC int
xfs_btree_read_buf_block(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr,
- int level,
int flags,
struct xfs_btree_block **block,
struct xfs_buf **bpp)
@@ -998,19 +1168,14 @@ xfs_btree_read_buf_block(
d = xfs_btree_ptr_to_daddr(cur, ptr);
error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
- mp->m_bsize, flags, bpp);
+ mp->m_bsize, flags, bpp,
+ cur->bc_ops->buf_ops);
if (error)
return error;
- ASSERT(!xfs_buf_geterror(*bpp));
-
xfs_btree_set_refs(cur, *bpp);
*block = XFS_BUF_TO_BLOCK(*bpp);
-
- error = xfs_btree_check_block(cur, *block, level, *bpp);
- if (error)
- xfs_trans_brelse(cur->bc_tp, *bpp);
- return error;
+ return 0;
}
/*
@@ -1126,6 +1291,7 @@ xfs_btree_log_keys(
XFS_BTREE_TRACE_ARGBII(cur, bp, first, last);
if (bp) {
+ xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF);
xfs_trans_log_buf(cur->bc_tp, bp,
xfs_btree_key_offset(cur, first),
xfs_btree_key_offset(cur, last + 1) - 1);
@@ -1150,6 +1316,7 @@ xfs_btree_log_recs(
XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
XFS_BTREE_TRACE_ARGBII(cur, bp, first, last);
+ xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF);
xfs_trans_log_buf(cur->bc_tp, bp,
xfs_btree_rec_offset(cur, first),
xfs_btree_rec_offset(cur, last + 1) - 1);
@@ -1174,6 +1341,7 @@ xfs_btree_log_ptrs(
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
int level = xfs_btree_get_level(block);
+ xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF);
xfs_trans_log_buf(cur->bc_tp, bp,
xfs_btree_ptr_offset(cur, first, level),
xfs_btree_ptr_offset(cur, last + 1, level) - 1);
@@ -1202,7 +1370,12 @@ xfs_btree_log_block(
offsetof(struct xfs_btree_block, bb_numrecs),
offsetof(struct xfs_btree_block, bb_u.s.bb_leftsib),
offsetof(struct xfs_btree_block, bb_u.s.bb_rightsib),
- XFS_BTREE_SBLOCK_LEN
+ offsetof(struct xfs_btree_block, bb_u.s.bb_blkno),
+ offsetof(struct xfs_btree_block, bb_u.s.bb_lsn),
+ offsetof(struct xfs_btree_block, bb_u.s.bb_uuid),
+ offsetof(struct xfs_btree_block, bb_u.s.bb_owner),
+ offsetof(struct xfs_btree_block, bb_u.s.bb_crc),
+ XFS_BTREE_SBLOCK_CRC_LEN
};
static const short loffsets[] = { /* table of offsets (long) */
offsetof(struct xfs_btree_block, bb_magic),
@@ -1210,17 +1383,40 @@ xfs_btree_log_block(
offsetof(struct xfs_btree_block, bb_numrecs),
offsetof(struct xfs_btree_block, bb_u.l.bb_leftsib),
offsetof(struct xfs_btree_block, bb_u.l.bb_rightsib),
- XFS_BTREE_LBLOCK_LEN
+ offsetof(struct xfs_btree_block, bb_u.l.bb_blkno),
+ offsetof(struct xfs_btree_block, bb_u.l.bb_lsn),
+ offsetof(struct xfs_btree_block, bb_u.l.bb_uuid),
+ offsetof(struct xfs_btree_block, bb_u.l.bb_owner),
+ offsetof(struct xfs_btree_block, bb_u.l.bb_crc),
+ offsetof(struct xfs_btree_block, bb_u.l.bb_pad),
+ XFS_BTREE_LBLOCK_CRC_LEN
};
XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
XFS_BTREE_TRACE_ARGBI(cur, bp, fields);
if (bp) {
+ int nbits;
+
+ if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) {
+ /*
+ * We don't log the CRC when updating a btree
+ * block but instead recreate it during log
+ * recovery. As the log buffers have checksums
+ * of their own this is safe and avoids logging a crc
+ * update in a lot of places.
+ */
+ if (fields == XFS_BB_ALL_BITS)
+ fields = XFS_BB_ALL_BITS_CRC;
+ nbits = XFS_BB_NUM_BITS_CRC;
+ } else {
+ nbits = XFS_BB_NUM_BITS;
+ }
xfs_btree_offsets(fields,
(cur->bc_flags & XFS_BTREE_LONG_PTRS) ?
loffsets : soffsets,
- XFS_BB_NUM_BITS, &first, &last);
+ nbits, &first, &last);
+ xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF);
xfs_trans_log_buf(cur->bc_tp, bp, first, last);
} else {
xfs_trans_log_inode(cur->bc_tp, cur->bc_private.b.ip,
@@ -1315,8 +1511,8 @@ xfs_btree_increment(
union xfs_btree_ptr *ptrp;
ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
- error = xfs_btree_read_buf_block(cur, ptrp, --lev,
- 0, &block, &bp);
+ --lev;
+ error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
@@ -1414,8 +1610,8 @@ xfs_btree_decrement(
union xfs_btree_ptr *ptrp;
ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
- error = xfs_btree_read_buf_block(cur, ptrp, --lev,
- 0, &block, &bp);
+ --lev;
+ error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
xfs_btree_setbuf(cur, lev, bp);
@@ -1465,7 +1661,7 @@ xfs_btree_lookup_get_block(
return 0;
}
- error = xfs_btree_read_buf_block(cur, pp, level, 0, blkp, &bp);
+ error = xfs_btree_read_buf_block(cur, pp, 0, blkp, &bp);
if (error)
return error;
@@ -1497,7 +1693,7 @@ xfs_lookup_get_search_key(
/*
* Lookup the record. The cursor is made to point to it, based on dir.
- * Return 0 if can't find any such record, 1 for success.
+ * stat is set to 0 if can't find any such record, 1 for success.
*/
int /* error */
xfs_btree_lookup(
@@ -1816,7 +2012,7 @@ xfs_btree_lshift(
goto out0;
/* Set up the left neighbor as "left". */
- error = xfs_btree_read_buf_block(cur, &lptr, level, 0, &left, &lbp);
+ error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
if (error)
goto error0;
@@ -2000,7 +2196,7 @@ xfs_btree_rshift(
goto out0;
/* Set up the right neighbor as "right". */
- error = xfs_btree_read_buf_block(cur, &rptr, level, 0, &right, &rbp);
+ error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
if (error)
goto error0;
@@ -2128,7 +2324,7 @@ error1:
* record (to be inserted into parent).
*/
STATIC int /* error */
-xfs_btree_split(
+__xfs_btree_split(
struct xfs_btree_cur *cur,
int level,
union xfs_btree_ptr *ptrp,
@@ -2170,7 +2366,7 @@ xfs_btree_split(
xfs_btree_buf_to_ptr(cur, lbp, &lptr);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, 1, stat);
+ error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat);
if (error)
goto error0;
if (*stat == 0)
@@ -2183,7 +2379,7 @@ xfs_btree_split(
goto error0;
/* Fill in the btree header for the new right block. */
- xfs_btree_init_block(cur, xfs_btree_get_level(left), 0, right);
+ xfs_btree_init_block_cur(cur, rbp, xfs_btree_get_level(left), 0);
/*
* Split the entries between the old and the new block evenly.
@@ -2268,7 +2464,7 @@ xfs_btree_split(
* point back to right instead of to left.
*/
if (!xfs_btree_ptr_is_null(cur, &rrptr)) {
- error = xfs_btree_read_buf_block(cur, &rrptr, level,
+ error = xfs_btree_read_buf_block(cur, &rrptr,
0, &rrblock, &rrbp);
if (error)
goto error0;
@@ -2308,6 +2504,85 @@ error0:
return error;
}
+struct xfs_btree_split_args {
+ struct xfs_btree_cur *cur;
+ int level;
+ union xfs_btree_ptr *ptrp;
+ union xfs_btree_key *key;
+ struct xfs_btree_cur **curp;
+ int *stat; /* success/failure */
+ int result;
+ bool kswapd; /* allocation in kswapd context */
+ struct completion *done;
+ struct work_struct work;
+};
+
+/*
+ * Stack switching interfaces for allocation
+ */
+static void
+xfs_btree_split_worker(
+ struct work_struct *work)
+{
+ struct xfs_btree_split_args *args = container_of(work,
+ struct xfs_btree_split_args, work);
+ unsigned long pflags;
+ unsigned long new_pflags = PF_FSTRANS;
+
+ /*
+ * we are in a transaction context here, but may also be doing work
+ * in kswapd context, and hence we may need to inherit that state
+ * temporarily to ensure that we don't block waiting for memory reclaim
+ * in any way.
+ */
+ if (args->kswapd)
+ new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+
+ current_set_flags_nested(&pflags, new_pflags);
+
+ args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
+ args->key, args->curp, args->stat);
+ complete(args->done);
+
+ current_restore_flags_nested(&pflags, new_pflags);
+}
+
+/*
+ * BMBT split requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. For the other
+ * btree types, just call directly to avoid the context switch overhead here.
+ */
+STATIC int /* error */
+xfs_btree_split(
+ struct xfs_btree_cur *cur,
+ int level,
+ union xfs_btree_ptr *ptrp,
+ union xfs_btree_key *key,
+ struct xfs_btree_cur **curp,
+ int *stat) /* success/failure */
+{
+ struct xfs_btree_split_args args;
+ DECLARE_COMPLETION_ONSTACK(done);
+
+ if (cur->bc_btnum != XFS_BTNUM_BMAP)
+ return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
+
+ args.cur = cur;
+ args.level = level;
+ args.ptrp = ptrp;
+ args.key = key;
+ args.curp = curp;
+ args.stat = stat;
+ args.done = &done;
+ args.kswapd = current_is_kswapd();
+ INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker);
+ queue_work(xfs_alloc_wq, &args.work);
+ wait_for_completion(&done);
+ destroy_work_on_stack(&args.work);
+ return args.result;
+}
+
+
/*
* Copy the old inode root contents into a real block and make the
* broot point to it.
@@ -2343,7 +2618,7 @@ xfs_btree_new_iroot(
pp = xfs_btree_ptr_addr(cur, 1, block);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, pp, &nptr, 1, stat);
+ error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat);
if (error)
goto error0;
if (*stat == 0) {
@@ -2357,7 +2632,17 @@ xfs_btree_new_iroot(
if (error)
goto error0;
+ /*
+ * we can't just memcpy() the root in for CRC enabled btree blocks.
+ * In that case have to also ensure the blkno remains correct
+ */
memcpy(cblock, block, xfs_btree_block_len(cur));
+ if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) {
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ cblock->bb_u.l.bb_blkno = cpu_to_be64(cbp->b_bn);
+ else
+ cblock->bb_u.s.bb_blkno = cpu_to_be64(cbp->b_bn);
+ }
be16_add_cpu(&block->bb_level, 1);
xfs_btree_set_numrecs(block, 1);
@@ -2437,7 +2722,7 @@ xfs_btree_new_root(
cur->bc_ops->init_ptr_from_cur(cur, &rptr);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, 1, stat);
+ error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat);
if (error)
goto error0;
if (*stat == 0)
@@ -2472,8 +2757,7 @@ xfs_btree_new_root(
lbp = bp;
xfs_btree_buf_to_ptr(cur, lbp, &lptr);
left = block;
- error = xfs_btree_read_buf_block(cur, &rptr,
- cur->bc_nlevels - 1, 0, &right, &rbp);
+ error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
if (error)
goto error0;
bp = rbp;
@@ -2484,15 +2768,14 @@ xfs_btree_new_root(
xfs_btree_buf_to_ptr(cur, rbp, &rptr);
right = block;
xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB);
- error = xfs_btree_read_buf_block(cur, &lptr,
- cur->bc_nlevels - 1, 0, &left, &lbp);
+ error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
if (error)
goto error0;
bp = lbp;
nptr = 2;
}
/* Fill in the new block's btree header and log it. */
- xfs_btree_init_block(cur, cur->bc_nlevels, 2, new);
+ xfs_btree_init_block_cur(cur, nbp, cur->bc_nlevels, 2);
xfs_btree_log_block(cur, nbp, XFS_BB_ALL_BITS);
ASSERT(!xfs_btree_ptr_is_null(cur, &lptr) &&
!xfs_btree_ptr_is_null(cur, &rptr));
@@ -2559,7 +2842,6 @@ xfs_btree_make_block_unfull(
if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) {
/* A root block that can be made bigger. */
-
xfs_iroot_realloc(ip, 1, cur->bc_private.b.whichfork);
} else {
/* A root block that needs replacing */
@@ -3438,8 +3720,7 @@ xfs_btree_delrec(
rptr = cptr;
right = block;
rbp = bp;
- error = xfs_btree_read_buf_block(cur, &lptr, level,
- 0, &left, &lbp);
+ error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
if (error)
goto error0;
@@ -3456,8 +3737,7 @@ xfs_btree_delrec(
lptr = cptr;
left = block;
lbp = bp;
- error = xfs_btree_read_buf_block(cur, &rptr, level,
- 0, &right, &rbp);
+ error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
if (error)
goto error0;
@@ -3529,8 +3809,7 @@ xfs_btree_delrec(
/* If there is a right sibling, point it to the remaining block. */
xfs_btree_get_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB);
if (!xfs_btree_ptr_is_null(cur, &cptr)) {
- error = xfs_btree_read_buf_block(cur, &cptr, level,
- 0, &rrblock, &rrbp);
+ error = xfs_btree_read_buf_block(cur, &cptr, 0, &rrblock, &rrbp);
if (error)
goto error0;
xfs_btree_set_sibling(cur, rrblock, &lptr, XFS_BB_LEFTSIB);
@@ -3671,3 +3950,120 @@ xfs_btree_get_rec(
*stat = 1;
return 0;
}
+
+/*
+ * Change the owner of a btree.
+ *
+ * The mechanism we use here is ordered buffer logging. Because we don't know
+ * how many buffers were are going to need to modify, we don't really want to
+ * have to make transaction reservations for the worst case of every buffer in a
+ * full size btree as that may be more space that we can fit in the log....
+ *
+ * We do the btree walk in the most optimal manner possible - we have sibling
+ * pointers so we can just walk all the blocks on each level from left to right
+ * in a single pass, and then move to the next level and do the same. We can
+ * also do readahead on the sibling pointers to get IO moving more quickly,
+ * though for slow disks this is unlikely to make much difference to performance
+ * as the amount of CPU work we have to do before moving to the next block is
+ * relatively small.
+ *
+ * For each btree block that we load, modify the owner appropriately, set the
+ * buffer as an ordered buffer and log it appropriately. We need to ensure that
+ * we mark the region we change dirty so that if the buffer is relogged in
+ * a subsequent transaction the changes we make here as an ordered buffer are
+ * correctly relogged in that transaction. If we are in recovery context, then
+ * just queue the modified buffer as delayed write buffer so the transaction
+ * recovery completion writes the changes to disk.
+ */
+static int
+xfs_btree_block_change_owner(
+ struct xfs_btree_cur *cur,
+ int level,
+ __uint64_t new_owner,
+ struct list_head *buffer_list)
+{
+ struct xfs_btree_block *block;
+ struct xfs_buf *bp;
+ union xfs_btree_ptr rptr;
+
+ /* do right sibling readahead */
+ xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA);
+
+ /* modify the owner */
+ block = xfs_btree_get_block(cur, level, &bp);
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ block->bb_u.l.bb_owner = cpu_to_be64(new_owner);
+ else
+ block->bb_u.s.bb_owner = cpu_to_be32(new_owner);
+
+ /*
+ * If the block is a root block hosted in an inode, we might not have a
+ * buffer pointer here and we shouldn't attempt to log the change as the
+ * information is already held in the inode and discarded when the root
+ * block is formatted into the on-disk inode fork. We still change it,
+ * though, so everything is consistent in memory.
+ */
+ if (bp) {
+ if (cur->bc_tp) {
+ xfs_trans_ordered_buf(cur->bc_tp, bp);
+ xfs_btree_log_block(cur, bp, XFS_BB_OWNER);
+ } else {
+ xfs_buf_delwri_queue(bp, buffer_list);
+ }
+ } else {
+ ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+ ASSERT(level == cur->bc_nlevels - 1);
+ }
+
+ /* now read rh sibling block for next iteration */
+ xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB);
+ if (xfs_btree_ptr_is_null(cur, &rptr))
+ return ENOENT;
+
+ return xfs_btree_lookup_get_block(cur, level, &rptr, &block);
+}
+
+int
+xfs_btree_change_owner(
+ struct xfs_btree_cur *cur,
+ __uint64_t new_owner,
+ struct list_head *buffer_list)
+{
+ union xfs_btree_ptr lptr;
+ int level;
+ struct xfs_btree_block *block = NULL;
+ int error = 0;
+
+ cur->bc_ops->init_ptr_from_cur(cur, &lptr);
+
+ /* for each level */
+ for (level = cur->bc_nlevels - 1; level >= 0; level--) {
+ /* grab the left hand block */
+ error = xfs_btree_lookup_get_block(cur, level, &lptr, &block);
+ if (error)
+ return error;
+
+ /* readahead the left most block for the next level down */
+ if (level > 0) {
+ union xfs_btree_ptr *ptr;
+
+ ptr = xfs_btree_ptr_addr(cur, 1, block);
+ xfs_btree_readahead_ptr(cur, ptr, 1);
+
+ /* save for the next iteration of the loop */
+ lptr = *ptr;
+ }
+
+ /* for each buffer in the level */
+ do {
+ error = xfs_btree_block_change_owner(cur, level,
+ new_owner,
+ buffer_list);
+ } while (!error);
+
+ if (error != ENOENT)
+ return error;
+ }
+
+ return 0;
+}
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 5b240de104c..a04b69422f6 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -27,48 +27,6 @@ struct xfs_trans;
extern kmem_zone_t *xfs_btree_cur_zone;
/*
- * This nonsense is to make -wlint happy.
- */
-#define XFS_LOOKUP_EQ ((xfs_lookup_t)XFS_LOOKUP_EQi)
-#define XFS_LOOKUP_LE ((xfs_lookup_t)XFS_LOOKUP_LEi)
-#define XFS_LOOKUP_GE ((xfs_lookup_t)XFS_LOOKUP_GEi)
-
-#define XFS_BTNUM_BNO ((xfs_btnum_t)XFS_BTNUM_BNOi)
-#define XFS_BTNUM_CNT ((xfs_btnum_t)XFS_BTNUM_CNTi)
-#define XFS_BTNUM_BMAP ((xfs_btnum_t)XFS_BTNUM_BMAPi)
-#define XFS_BTNUM_INO ((xfs_btnum_t)XFS_BTNUM_INOi)
-
-/*
- * Generic btree header.
- *
- * This is a combination of the actual format used on disk for short and long
- * format btrees. The first three fields are shared by both format, but
- * the pointers are different and should be used with care.
- *
- * To get the size of the actual short or long form headers please use
- * the size macros below. Never use sizeof(xfs_btree_block).
- */
-struct xfs_btree_block {
- __be32 bb_magic; /* magic number for block type */
- __be16 bb_level; /* 0 is a leaf */
- __be16 bb_numrecs; /* current # of data records */
- union {
- struct {
- __be32 bb_leftsib;
- __be32 bb_rightsib;
- } s; /* short form pointers */
- struct {
- __be64 bb_leftsib;
- __be64 bb_rightsib;
- } l; /* long form pointers */
- } bb_u; /* rest */
-};
-
-#define XFS_BTREE_SBLOCK_LEN 16 /* size of a short form block */
-#define XFS_BTREE_LBLOCK_LEN 24 /* size of a long form block */
-
-
-/*
* Generic key, ptr and record wrapper structures.
*
* These are disk format structures, and are converted where necessary
@@ -94,20 +52,34 @@ union xfs_btree_rec {
};
/*
- * For logging record fields.
+ * This nonsense is to make -wlint happy.
*/
-#define XFS_BB_MAGIC 0x01
-#define XFS_BB_LEVEL 0x02
-#define XFS_BB_NUMRECS 0x04
-#define XFS_BB_LEFTSIB 0x08
-#define XFS_BB_RIGHTSIB 0x10
-#define XFS_BB_NUM_BITS 5
-#define XFS_BB_ALL_BITS ((1 << XFS_BB_NUM_BITS) - 1)
+#define XFS_LOOKUP_EQ ((xfs_lookup_t)XFS_LOOKUP_EQi)
+#define XFS_LOOKUP_LE ((xfs_lookup_t)XFS_LOOKUP_LEi)
+#define XFS_LOOKUP_GE ((xfs_lookup_t)XFS_LOOKUP_GEi)
+
+#define XFS_BTNUM_BNO ((xfs_btnum_t)XFS_BTNUM_BNOi)
+#define XFS_BTNUM_CNT ((xfs_btnum_t)XFS_BTNUM_CNTi)
+#define XFS_BTNUM_BMAP ((xfs_btnum_t)XFS_BTNUM_BMAPi)
+#define XFS_BTNUM_INO ((xfs_btnum_t)XFS_BTNUM_INOi)
+#define XFS_BTNUM_FINO ((xfs_btnum_t)XFS_BTNUM_FINOi)
/*
- * Magic numbers for btree blocks.
+ * For logging record fields.
*/
-extern const __uint32_t xfs_magics[];
+#define XFS_BB_MAGIC (1 << 0)
+#define XFS_BB_LEVEL (1 << 1)
+#define XFS_BB_NUMRECS (1 << 2)
+#define XFS_BB_LEFTSIB (1 << 3)
+#define XFS_BB_RIGHTSIB (1 << 4)
+#define XFS_BB_BLKNO (1 << 5)
+#define XFS_BB_LSN (1 << 6)
+#define XFS_BB_UUID (1 << 7)
+#define XFS_BB_OWNER (1 << 8)
+#define XFS_BB_NUM_BITS 5
+#define XFS_BB_ALL_BITS ((1 << XFS_BB_NUM_BITS) - 1)
+#define XFS_BB_NUM_BITS_CRC 9
+#define XFS_BB_ALL_BITS_CRC ((1 << XFS_BB_NUM_BITS_CRC) - 1)
/*
* Generic stats interface
@@ -121,6 +93,7 @@ do { \
case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break; \
case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break; \
case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break; \
+ case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(fibt, stat); break; \
case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \
} \
} while (0)
@@ -134,6 +107,7 @@ do { \
case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \
case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \
case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \
+ case XFS_BTNUM_FINO: __XFS_BTREE_STATS_ADD(fibt, stat, val); break; \
case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \
} \
} while (0)
@@ -158,7 +132,7 @@ struct xfs_btree_ops {
int (*alloc_block)(struct xfs_btree_cur *cur,
union xfs_btree_ptr *start_bno,
union xfs_btree_ptr *new_bno,
- int length, int *stat);
+ int *stat);
int (*free_block)(struct xfs_btree_cur *cur, struct xfs_buf *bp);
/* update last record information */
@@ -188,7 +162,9 @@ struct xfs_btree_ops {
__int64_t (*key_diff)(struct xfs_btree_cur *cur,
union xfs_btree_key *key);
-#ifdef DEBUG
+ const struct xfs_buf_ops *buf_ops;
+
+#if defined(DEBUG) || defined(XFS_WARN)
/* check that k1 is lower than k2 */
int (*keys_inorder)(struct xfs_btree_cur *cur,
union xfs_btree_key *k1,
@@ -254,6 +230,7 @@ typedef struct xfs_btree_cur
#define XFS_BTREE_LONG_PTRS (1<<0) /* pointers are 64bits long */
#define XFS_BTREE_ROOT_IN_INODE (1<<1) /* root may be variable size */
#define XFS_BTREE_LASTREC_UPDATE (1<<2) /* track last rec externally */
+#define XFS_BTREE_CRC_BLOCKS (1<<3) /* uses extended btree blocks */
#define XFS_BTREE_NOERROR 0
@@ -355,7 +332,8 @@ xfs_btree_read_bufl(
xfs_fsblock_t fsbno, /* file system block number */
uint lock, /* lock flags for read_buf */
struct xfs_buf **bpp, /* buffer for fsbno */
- int refval);/* ref count value for buffer */
+ int refval, /* ref count value for buffer */
+ const struct xfs_buf_ops *ops);
/*
* Read-ahead the block, don't wait for it, don't return a buffer.
@@ -365,7 +343,8 @@ void /* error */
xfs_btree_reada_bufl(
struct xfs_mount *mp, /* file system mount point */
xfs_fsblock_t fsbno, /* file system block number */
- xfs_extlen_t count); /* count of filesystem blocks */
+ xfs_extlen_t count, /* count of filesystem blocks */
+ const struct xfs_buf_ops *ops);
/*
* Read-ahead the block, don't wait for it, don't return a buffer.
@@ -376,8 +355,32 @@ xfs_btree_reada_bufs(
struct xfs_mount *mp, /* file system mount point */
xfs_agnumber_t agno, /* allocation group number */
xfs_agblock_t agbno, /* allocation group block number */
- xfs_extlen_t count); /* count of filesystem blocks */
+ xfs_extlen_t count, /* count of filesystem blocks */
+ const struct xfs_buf_ops *ops);
+/*
+ * Initialise a new btree block header
+ */
+void
+xfs_btree_init_block(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ __u32 magic,
+ __u16 level,
+ __u16 numrecs,
+ __u64 owner,
+ unsigned int flags);
+
+void
+xfs_btree_init_block_int(
+ struct xfs_mount *mp,
+ struct xfs_btree_block *buf,
+ xfs_daddr_t blkno,
+ __u32 magic,
+ __u16 level,
+ __u16 numrecs,
+ __u64 owner,
+ unsigned int flags);
/*
* Common btree core entry points.
@@ -390,6 +393,16 @@ int xfs_btree_new_iroot(struct xfs_btree_cur *, int *, int *);
int xfs_btree_insert(struct xfs_btree_cur *, int *);
int xfs_btree_delete(struct xfs_btree_cur *, int *);
int xfs_btree_get_rec(struct xfs_btree_cur *, union xfs_btree_rec **, int *);
+int xfs_btree_change_owner(struct xfs_btree_cur *cur, __uint64_t new_owner,
+ struct list_head *buffer_list);
+
+/*
+ * btree block CRC helpers
+ */
+void xfs_btree_lblock_calc_crc(struct xfs_buf *);
+bool xfs_btree_lblock_verify_crc(struct xfs_buf *);
+void xfs_btree_sblock_calc_crc(struct xfs_buf *);
+bool xfs_btree_sblock_verify_crc(struct xfs_buf *);
/*
* Internal btree helpers also used by xfs_bmap.c.
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a4beb421018..7a34a1ae655 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -34,11 +34,13 @@
#include <linux/backing-dev.h>
#include <linux/freezer.h>
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
-#include "xfs_log.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_trace.h"
+#include "xfs_log.h"
static kmem_zone_t *xfs_buf_zone;
@@ -80,53 +82,6 @@ xfs_buf_vmap_len(
}
/*
- * xfs_buf_lru_add - add a buffer to the LRU.
- *
- * The LRU takes a new reference to the buffer so that it will only be freed
- * once the shrinker takes the buffer off the LRU.
- */
-STATIC void
-xfs_buf_lru_add(
- struct xfs_buf *bp)
-{
- struct xfs_buftarg *btp = bp->b_target;
-
- spin_lock(&btp->bt_lru_lock);
- if (list_empty(&bp->b_lru)) {
- atomic_inc(&bp->b_hold);
- list_add_tail(&bp->b_lru, &btp->bt_lru);
- btp->bt_lru_nr++;
- }
- spin_unlock(&btp->bt_lru_lock);
-}
-
-/*
- * xfs_buf_lru_del - remove a buffer from the LRU
- *
- * The unlocked check is safe here because it only occurs when there are not
- * b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there
- * to optimise the shrinker removing the buffer from the LRU and calling
- * xfs_buf_free(). i.e. it removes an unnecessary round trip on the
- * bt_lru_lock.
- */
-STATIC void
-xfs_buf_lru_del(
- struct xfs_buf *bp)
-{
- struct xfs_buftarg *btp = bp->b_target;
-
- if (list_empty(&bp->b_lru))
- return;
-
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- }
- spin_unlock(&btp->bt_lru_lock);
-}
-
-/*
* When we mark a buffer stale, we remove the buffer from the LRU and clear the
* b_lru_ref count so that the buffer is freed immediately when the buffer
* reference count falls to zero. If the buffer is already on the LRU, we need
@@ -149,29 +104,59 @@ xfs_buf_stale(
*/
bp->b_flags &= ~_XBF_DELWRI_Q;
- atomic_set(&(bp)->b_lru_ref, 0);
- if (!list_empty(&bp->b_lru)) {
- struct xfs_buftarg *btp = bp->b_target;
+ spin_lock(&bp->b_lock);
+ atomic_set(&bp->b_lru_ref, 0);
+ if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
+ (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
+ atomic_dec(&bp->b_hold);
- spin_lock(&btp->bt_lru_lock);
- if (!list_empty(&bp->b_lru)) {
- list_del_init(&bp->b_lru);
- btp->bt_lru_nr--;
- atomic_dec(&bp->b_hold);
- }
- spin_unlock(&btp->bt_lru_lock);
- }
ASSERT(atomic_read(&bp->b_hold) >= 1);
+ spin_unlock(&bp->b_lock);
+}
+
+static int
+xfs_buf_get_maps(
+ struct xfs_buf *bp,
+ int map_count)
+{
+ ASSERT(bp->b_maps == NULL);
+ bp->b_map_count = map_count;
+
+ if (map_count == 1) {
+ bp->b_maps = &bp->__b_map;
+ return 0;
+ }
+
+ bp->b_maps = kmem_zalloc(map_count * sizeof(struct xfs_buf_map),
+ KM_NOFS);
+ if (!bp->b_maps)
+ return ENOMEM;
+ return 0;
+}
+
+/*
+ * Frees b_pages if it was allocated.
+ */
+static void
+xfs_buf_free_maps(
+ struct xfs_buf *bp)
+{
+ if (bp->b_maps != &bp->__b_map) {
+ kmem_free(bp->b_maps);
+ bp->b_maps = NULL;
+ }
}
struct xfs_buf *
-xfs_buf_alloc(
+_xfs_buf_alloc(
struct xfs_buftarg *target,
- xfs_daddr_t blkno,
- size_t numblks,
+ struct xfs_buf_map *map,
+ int nmaps,
xfs_buf_flags_t flags)
{
struct xfs_buf *bp;
+ int error;
+ int i;
bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS);
if (unlikely(!bp))
@@ -190,18 +175,31 @@ xfs_buf_alloc(
INIT_LIST_HEAD(&bp->b_list);
RB_CLEAR_NODE(&bp->b_rbnode);
sema_init(&bp->b_sema, 0); /* held, no waiters */
+ spin_lock_init(&bp->b_lock);
XB_SET_OWNER(bp);
bp->b_target = target;
+ bp->b_flags = flags;
/*
* Set length and io_length to the same value initially.
* I/O routines should use io_length, which will be the same in
* most cases but may be reset (e.g. XFS recovery).
*/
- bp->b_length = numblks;
- bp->b_io_length = numblks;
- bp->b_flags = flags;
- bp->b_bn = blkno;
+ error = xfs_buf_get_maps(bp, nmaps);
+ if (error) {
+ kmem_zone_free(xfs_buf_zone, bp);
+ return NULL;
+ }
+
+ bp->b_bn = map[0].bm_bn;
+ bp->b_length = 0;
+ for (i = 0; i < nmaps; i++) {
+ bp->b_maps[i].bm_bn = map[i].bm_bn;
+ bp->b_maps[i].bm_len = map[i].bm_len;
+ bp->b_length += map[i].bm_len;
+ }
+ bp->b_io_length = bp->b_length;
+
atomic_set(&bp->b_pin_count, 0);
init_waitqueue_head(&bp->b_waiters);
@@ -218,8 +216,7 @@ xfs_buf_alloc(
STATIC int
_xfs_buf_get_pages(
xfs_buf_t *bp,
- int page_count,
- xfs_buf_flags_t flags)
+ int page_count)
{
/* Make sure that we have a page list */
if (bp->b_pages == NULL) {
@@ -254,7 +251,7 @@ _xfs_buf_free_pages(
* Releases the specified buffer.
*
* The modification state of any associated pages is left unchanged.
- * The buffer most not be on any hash - use xfs_buf_rele instead for
+ * The buffer must not be on any hash - use xfs_buf_rele instead for
* hashed and refcounted buffers
*/
void
@@ -280,6 +277,7 @@ xfs_buf_free(
} else if (bp->b_flags & _XBF_KMEM)
kmem_free(bp->b_addr);
_xfs_buf_free_pages(bp);
+ xfs_buf_free_maps(bp);
kmem_zone_free(xfs_buf_zone, bp);
}
@@ -327,10 +325,11 @@ xfs_buf_allocate_memory(
}
use_alloc_page:
- start = BBTOB(bp->b_bn) >> PAGE_SHIFT;
- end = (BBTOB(bp->b_bn + bp->b_length) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ start = BBTOB(bp->b_maps[0].bm_bn) >> PAGE_SHIFT;
+ end = (BBTOB(bp->b_maps[0].bm_bn + bp->b_length) + PAGE_SIZE - 1)
+ >> PAGE_SHIFT;
page_count = end - start;
- error = _xfs_buf_get_pages(bp, page_count, flags);
+ error = _xfs_buf_get_pages(bp, page_count);
if (unlikely(error))
return error;
@@ -396,7 +395,17 @@ _xfs_buf_map_pages(
bp->b_addr = NULL;
} else {
int retried = 0;
+ unsigned noio_flag;
+ /*
+ * vm_map_ram() will allocate auxillary structures (e.g.
+ * pagetables) with GFP_KERNEL, yet we are likely to be under
+ * GFP_NOFS context here. Hence we need to tell memory reclaim
+ * that we are in such a context via PF_MEMALLOC_NOIO to prevent
+ * memory reclaim re-entering the filesystem here and
+ * potentially deadlocking.
+ */
+ noio_flag = memalloc_noio_save();
do {
bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
-1, PAGE_KERNEL);
@@ -404,6 +413,7 @@ _xfs_buf_map_pages(
break;
vm_unmap_aliases();
} while (retried++ <= 1);
+ memalloc_noio_restore(noio_flag);
if (!bp->b_addr)
return -ENOMEM;
@@ -425,8 +435,8 @@ _xfs_buf_map_pages(
xfs_buf_t *
_xfs_buf_find(
struct xfs_buftarg *btp,
- xfs_daddr_t blkno,
- size_t numblks,
+ struct xfs_buf_map *map,
+ int nmaps,
xfs_buf_flags_t flags,
xfs_buf_t *new_bp)
{
@@ -435,12 +445,36 @@ _xfs_buf_find(
struct rb_node **rbp;
struct rb_node *parent;
xfs_buf_t *bp;
+ xfs_daddr_t blkno = map[0].bm_bn;
+ xfs_daddr_t eofs;
+ int numblks = 0;
+ int i;
+ for (i = 0; i < nmaps; i++)
+ numblks += map[i].bm_len;
numbytes = BBTOB(numblks);
/* Check for IOs smaller than the sector size / not sector aligned */
- ASSERT(!(numbytes < (1 << btp->bt_sshift)));
- ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_smask));
+ ASSERT(!(numbytes < btp->bt_meta_sectorsize));
+ ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_meta_sectormask));
+
+ /*
+ * Corrupted block numbers can get through to here, unfortunately, so we
+ * have to check that the buffer falls within the filesystem bounds.
+ */
+ eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks);
+ if (blkno >= eofs) {
+ /*
+ * XXX (dgc): we should really be returning EFSCORRUPTED here,
+ * but none of the higher level infrastructure supports
+ * returning a specific error on buffer lookup failures.
+ */
+ xfs_alert(btp->bt_mount,
+ "%s: Block out of range: block 0x%llx, EOFS 0x%llx ",
+ __func__, blkno, eofs);
+ WARN_ON(1);
+ return NULL;
+ }
/* get tree root */
pag = xfs_perag_get(btp->bt_mount,
@@ -513,7 +547,9 @@ found:
*/
if (bp->b_flags & XBF_STALE) {
ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
+ ASSERT(bp->b_iodone == NULL);
bp->b_flags &= _XBF_KMEM | _XBF_PAGES;
+ bp->b_ops = NULL;
}
trace_xfs_buf_find(bp, flags, _RET_IP_);
@@ -527,31 +563,31 @@ found:
* more hits than misses.
*/
struct xfs_buf *
-xfs_buf_get(
- xfs_buftarg_t *target,
- xfs_daddr_t blkno,
- size_t numblks,
+xfs_buf_get_map(
+ struct xfs_buftarg *target,
+ struct xfs_buf_map *map,
+ int nmaps,
xfs_buf_flags_t flags)
{
struct xfs_buf *bp;
struct xfs_buf *new_bp;
int error = 0;
- bp = _xfs_buf_find(target, blkno, numblks, flags, NULL);
+ bp = _xfs_buf_find(target, map, nmaps, flags, NULL);
if (likely(bp))
goto found;
- new_bp = xfs_buf_alloc(target, blkno, numblks, flags);
+ new_bp = _xfs_buf_alloc(target, map, nmaps, flags);
if (unlikely(!new_bp))
return NULL;
error = xfs_buf_allocate_memory(new_bp, flags);
if (error) {
- kmem_zone_free(xfs_buf_zone, new_bp);
+ xfs_buf_free(new_bp);
return NULL;
}
- bp = _xfs_buf_find(target, blkno, numblks, flags, new_bp);
+ bp = _xfs_buf_find(target, map, nmaps, flags, new_bp);
if (!bp) {
xfs_buf_free(new_bp);
return NULL;
@@ -560,14 +596,12 @@ xfs_buf_get(
if (bp != new_bp)
xfs_buf_free(new_bp);
- bp->b_io_length = bp->b_length;
-
found:
if (!bp->b_addr) {
error = _xfs_buf_map_pages(bp, flags);
if (unlikely(error)) {
xfs_warn(target->bt_mount,
- "%s: failed to map pages\n", __func__);
+ "%s: failed to map pagesn", __func__);
xfs_buf_relse(bp);
return NULL;
}
@@ -584,7 +618,7 @@ _xfs_buf_read(
xfs_buf_flags_t flags)
{
ASSERT(!(flags & XBF_WRITE));
- ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
+ ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL);
bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
@@ -596,22 +630,24 @@ _xfs_buf_read(
}
xfs_buf_t *
-xfs_buf_read(
- xfs_buftarg_t *target,
- xfs_daddr_t blkno,
- size_t numblks,
- xfs_buf_flags_t flags)
+xfs_buf_read_map(
+ struct xfs_buftarg *target,
+ struct xfs_buf_map *map,
+ int nmaps,
+ xfs_buf_flags_t flags,
+ const struct xfs_buf_ops *ops)
{
- xfs_buf_t *bp;
+ struct xfs_buf *bp;
flags |= XBF_READ;
- bp = xfs_buf_get(target, blkno, numblks, flags);
+ bp = xfs_buf_get_map(target, map, nmaps, flags);
if (bp) {
trace_xfs_buf_read(bp, flags, _RET_IP_);
if (!XFS_BUF_ISDONE(bp)) {
XFS_STATS_INC(xb_get_read);
+ bp->b_ops = ops;
_xfs_buf_read(bp, flags);
} else if (flags & XBF_ASYNC) {
/*
@@ -634,16 +670,17 @@ xfs_buf_read(
* safe manner.
*/
void
-xfs_buf_readahead(
- xfs_buftarg_t *target,
- xfs_daddr_t blkno,
- size_t numblks)
+xfs_buf_readahead_map(
+ struct xfs_buftarg *target,
+ struct xfs_buf_map *map,
+ int nmaps,
+ const struct xfs_buf_ops *ops)
{
if (bdi_read_congested(target->bt_bdi))
return;
- xfs_buf_read(target, blkno, numblks,
- XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
+ xfs_buf_read_map(target, map, nmaps,
+ XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD, ops);
}
/*
@@ -655,25 +692,28 @@ xfs_buf_read_uncached(
struct xfs_buftarg *target,
xfs_daddr_t daddr,
size_t numblks,
- int flags)
+ int flags,
+ const struct xfs_buf_ops *ops)
{
- xfs_buf_t *bp;
- int error;
+ struct xfs_buf *bp;
bp = xfs_buf_get_uncached(target, numblks, flags);
if (!bp)
return NULL;
/* set up the buffer for a read IO */
- XFS_BUF_SET_ADDR(bp, daddr);
- XFS_BUF_READ(bp);
+ ASSERT(bp->b_map_count == 1);
+ bp->b_bn = daddr;
+ bp->b_maps[0].bm_bn = daddr;
+ bp->b_flags |= XBF_READ;
+ bp->b_ops = ops;
- xfsbdstrat(target->bt_mount, bp);
- error = xfs_buf_iowait(bp);
- if (error) {
+ if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
xfs_buf_relse(bp);
return NULL;
}
+ xfs_buf_iorequest(bp);
+ xfs_buf_iowait(bp);
return bp;
}
@@ -694,7 +734,11 @@ xfs_buf_set_empty(
bp->b_addr = NULL;
bp->b_length = numblks;
bp->b_io_length = numblks;
+
+ ASSERT(bp->b_map_count == 1);
bp->b_bn = XFS_BUF_DADDR_NULL;
+ bp->b_maps[0].bm_bn = XFS_BUF_DADDR_NULL;
+ bp->b_maps[0].bm_len = bp->b_length;
}
static inline struct page *
@@ -733,7 +777,7 @@ xfs_buf_associate_memory(
bp->b_pages = NULL;
bp->b_addr = mem;
- rval = _xfs_buf_get_pages(bp, page_count, 0);
+ rval = _xfs_buf_get_pages(bp, page_count);
if (rval)
return rval;
@@ -758,14 +802,15 @@ xfs_buf_get_uncached(
{
unsigned long page_count;
int error, i;
- xfs_buf_t *bp;
+ struct xfs_buf *bp;
+ DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
- bp = xfs_buf_alloc(target, XFS_BUF_DADDR_NULL, numblks, 0);
+ bp = _xfs_buf_alloc(target, &map, 1, 0);
if (unlikely(bp == NULL))
goto fail;
page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT;
- error = _xfs_buf_get_pages(bp, page_count, 0);
+ error = _xfs_buf_get_pages(bp, page_count);
if (error)
goto fail_free_buf;
@@ -779,7 +824,7 @@ xfs_buf_get_uncached(
error = _xfs_buf_map_pages(bp, 0);
if (unlikely(error)) {
xfs_warn(target->bt_mount,
- "%s: failed to map pages\n", __func__);
+ "%s: failed to map pages", __func__);
goto fail_free_mem;
}
@@ -791,6 +836,7 @@ xfs_buf_get_uncached(
__free_page(bp->b_pages[i]);
_xfs_buf_free_pages(bp);
fail_free_buf:
+ xfs_buf_free_maps(bp);
kmem_zone_free(xfs_buf_zone, bp);
fail:
return NULL;
@@ -833,12 +879,33 @@ xfs_buf_rele(
ASSERT(atomic_read(&bp->b_hold) > 0);
if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
- if (!(bp->b_flags & XBF_STALE) &&
- atomic_read(&bp->b_lru_ref)) {
- xfs_buf_lru_add(bp);
+ spin_lock(&bp->b_lock);
+ if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
+ /*
+ * If the buffer is added to the LRU take a new
+ * reference to the buffer for the LRU and clear the
+ * (now stale) dispose list state flag
+ */
+ if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
+ bp->b_state &= ~XFS_BSTATE_DISPOSE;
+ atomic_inc(&bp->b_hold);
+ }
+ spin_unlock(&bp->b_lock);
spin_unlock(&pag->pag_buf_lock);
} else {
- xfs_buf_lru_del(bp);
+ /*
+ * most of the time buffers will already be removed from
+ * the LRU, so optimise that case by checking for the
+ * XFS_BSTATE_DISPOSE flag indicating the last list the
+ * buffer was on was the disposal list
+ */
+ if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
+ list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
+ } else {
+ ASSERT(list_empty(&bp->b_lru));
+ }
+ spin_unlock(&bp->b_lock);
+
ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
spin_unlock(&pag->pag_buf_lock);
@@ -869,8 +936,6 @@ xfs_buf_trylock(
locked = down_trylock(&bp->b_sema) == 0;
if (locked)
XB_SET_OWNER(bp);
- else if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
- xfs_log_force(bp->b_target->bt_mount, 0);
trace_xfs_buf_trylock(bp, _RET_IP_);
return locked;
@@ -937,27 +1002,39 @@ STATIC void
xfs_buf_iodone_work(
struct work_struct *work)
{
- xfs_buf_t *bp =
+ struct xfs_buf *bp =
container_of(work, xfs_buf_t, b_iodone_work);
+ bool read = !!(bp->b_flags & XBF_READ);
+
+ bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
+
+ /* only validate buffers that were read without errors */
+ if (read && bp->b_ops && !bp->b_error && (bp->b_flags & XBF_DONE))
+ bp->b_ops->verify_read(bp);
if (bp->b_iodone)
(*(bp->b_iodone))(bp);
else if (bp->b_flags & XBF_ASYNC)
xfs_buf_relse(bp);
+ else {
+ ASSERT(read && bp->b_ops);
+ complete(&bp->b_iowait);
+ }
}
void
xfs_buf_ioend(
- xfs_buf_t *bp,
- int schedule)
+ struct xfs_buf *bp,
+ int schedule)
{
+ bool read = !!(bp->b_flags & XBF_READ);
+
trace_xfs_buf_iodone(bp, _RET_IP_);
- bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
if (bp->b_error == 0)
bp->b_flags |= XBF_DONE;
- if ((bp->b_iodone) || (bp->b_flags & XBF_ASYNC)) {
+ if (bp->b_iodone || (read && bp->b_ops) || (bp->b_flags & XBF_ASYNC)) {
if (schedule) {
INIT_WORK(&bp->b_iodone_work, xfs_buf_iodone_work);
queue_work(xfslogd_workqueue, &bp->b_iodone_work);
@@ -965,6 +1042,7 @@ xfs_buf_ioend(
xfs_buf_iodone_work(&bp->b_iodone_work);
}
} else {
+ bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
complete(&bp->b_iowait);
}
}
@@ -989,27 +1067,6 @@ xfs_buf_ioerror_alert(
(__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length);
}
-int
-xfs_bwrite(
- struct xfs_buf *bp)
-{
- int error;
-
- ASSERT(xfs_buf_islocked(bp));
-
- bp->b_flags |= XBF_WRITE;
- bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
-
- xfs_bdstrat_cb(bp);
-
- error = xfs_buf_iowait(bp);
- if (error) {
- xfs_force_shutdown(bp->b_target->bt_mount,
- SHUTDOWN_META_IO_ERROR);
- }
- return error;
-}
-
/*
* Called when we want to stop a buffer from getting written or read.
* We attach the EIO error, muck with its flags, and call xfs_buf_ioend
@@ -1046,7 +1103,7 @@ xfs_bioerror(
* This is meant for userdata errors; metadata bufs come with
* iodone functions attached, so that we can track down errors.
*/
-STATIC int
+int
xfs_bioerror_relse(
struct xfs_buf *bp)
{
@@ -1079,14 +1136,7 @@ xfs_bioerror_relse(
return EIO;
}
-
-/*
- * All xfs metadata buffers except log state machine buffers
- * get this attached as their b_bdstrat callback function.
- * This is so that we can catch a buffer
- * after prematurely unpinning it to forcibly shutdown the filesystem.
- */
-int
+STATIC int
xfs_bdstrat_cb(
struct xfs_buf *bp)
{
@@ -1107,23 +1157,25 @@ xfs_bdstrat_cb(
return 0;
}
-/*
- * Wrapper around bdstrat so that we can stop data from going to disk in case
- * we are shutting down the filesystem. Typically user data goes thru this
- * path; one of the exceptions is the superblock.
- */
-void
-xfsbdstrat(
- struct xfs_mount *mp,
+int
+xfs_bwrite(
struct xfs_buf *bp)
{
- if (XFS_FORCED_SHUTDOWN(mp)) {
- trace_xfs_bdstrat_shut(bp, _RET_IP_);
- xfs_bioerror_relse(bp);
- return;
- }
+ int error;
- xfs_buf_iorequest(bp);
+ ASSERT(xfs_buf_islocked(bp));
+
+ bp->b_flags |= XBF_WRITE;
+ bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
+
+ xfs_bdstrat_cb(bp);
+
+ error = xfs_buf_iowait(bp);
+ if (error) {
+ xfs_force_shutdown(bp->b_target->bt_mount,
+ SHUTDOWN_META_IO_ERROR);
+ }
+ return error;
}
STATIC void
@@ -1142,45 +1194,53 @@ xfs_buf_bio_end_io(
{
xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private;
- xfs_buf_ioerror(bp, -error);
+ /*
+ * don't overwrite existing errors - otherwise we can lose errors on
+ * buffers that require multiple bios to complete.
+ */
+ if (!bp->b_error)
+ xfs_buf_ioerror(bp, -error);
- if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
+ if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
_xfs_buf_ioend(bp, 1);
bio_put(bio);
}
-STATIC void
-_xfs_buf_ioapply(
- xfs_buf_t *bp)
+static void
+xfs_buf_ioapply_map(
+ struct xfs_buf *bp,
+ int map,
+ int *buf_offset,
+ int *count,
+ int rw)
{
- int rw, map_i, total_nr_pages, nr_pages;
- struct bio *bio;
- int offset = bp->b_offset;
- int size = BBTOB(bp->b_io_length);
- sector_t sector = bp->b_bn;
+ int page_index;
+ int total_nr_pages = bp->b_page_count;
+ int nr_pages;
+ struct bio *bio;
+ sector_t sector = bp->b_maps[map].bm_bn;
+ int size;
+ int offset;
total_nr_pages = bp->b_page_count;
- map_i = 0;
- if (bp->b_flags & XBF_WRITE) {
- if (bp->b_flags & XBF_SYNCIO)
- rw = WRITE_SYNC;
- else
- rw = WRITE;
- if (bp->b_flags & XBF_FUA)
- rw |= REQ_FUA;
- if (bp->b_flags & XBF_FLUSH)
- rw |= REQ_FLUSH;
- } else if (bp->b_flags & XBF_READ_AHEAD) {
- rw = READA;
- } else {
- rw = READ;
+ /* skip the pages in the buffer before the start offset */
+ page_index = 0;
+ offset = *buf_offset;
+ while (offset >= PAGE_SIZE) {
+ page_index++;
+ offset -= PAGE_SIZE;
}
- /* we only use the buffer cache for meta-data */
- rw |= REQ_META;
+ /*
+ * Limit the IO size to the length of the current vector, and update the
+ * remaining IO count for the next time around.
+ */
+ size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count);
+ *count -= size;
+ *buf_offset += size;
next_chunk:
atomic_inc(&bp->b_io_remaining);
@@ -1190,18 +1250,19 @@ next_chunk:
bio = bio_alloc(GFP_NOIO, nr_pages);
bio->bi_bdev = bp->b_target->bt_bdev;
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
bio->bi_end_io = xfs_buf_bio_end_io;
bio->bi_private = bp;
- for (; size && nr_pages; nr_pages--, map_i++) {
+ for (; size && nr_pages; nr_pages--, page_index++) {
int rbytes, nbytes = PAGE_SIZE - offset;
if (nbytes > size)
nbytes = size;
- rbytes = bio_add_page(bio, bp->b_pages[map_i], nbytes, offset);
+ rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes,
+ offset);
if (rbytes < nbytes)
break;
@@ -1211,7 +1272,7 @@ next_chunk:
total_nr_pages--;
}
- if (likely(bio->bi_size)) {
+ if (likely(bio->bi_iter.bi_size)) {
if (xfs_buf_is_vmapped(bp)) {
flush_kernel_vmap_range(bp->b_addr,
xfs_buf_vmap_len(bp));
@@ -1220,9 +1281,82 @@ next_chunk:
if (size)
goto next_chunk;
} else {
+ /*
+ * This is guaranteed not to be the last io reference count
+ * because the caller (xfs_buf_iorequest) holds a count itself.
+ */
+ atomic_dec(&bp->b_io_remaining);
xfs_buf_ioerror(bp, EIO);
bio_put(bio);
}
+
+}
+
+STATIC void
+_xfs_buf_ioapply(
+ struct xfs_buf *bp)
+{
+ struct blk_plug plug;
+ int rw;
+ int offset;
+ int size;
+ int i;
+
+ /*
+ * Make sure we capture only current IO errors rather than stale errors
+ * left over from previous use of the buffer (e.g. failed readahead).
+ */
+ bp->b_error = 0;
+
+ if (bp->b_flags & XBF_WRITE) {
+ if (bp->b_flags & XBF_SYNCIO)
+ rw = WRITE_SYNC;
+ else
+ rw = WRITE;
+ if (bp->b_flags & XBF_FUA)
+ rw |= REQ_FUA;
+ if (bp->b_flags & XBF_FLUSH)
+ rw |= REQ_FLUSH;
+
+ /*
+ * Run the write verifier callback function if it exists. If
+ * this function fails it will mark the buffer with an error and
+ * the IO should not be dispatched.
+ */
+ if (bp->b_ops) {
+ bp->b_ops->verify_write(bp);
+ if (bp->b_error) {
+ xfs_force_shutdown(bp->b_target->bt_mount,
+ SHUTDOWN_CORRUPT_INCORE);
+ return;
+ }
+ }
+ } else if (bp->b_flags & XBF_READ_AHEAD) {
+ rw = READA;
+ } else {
+ rw = READ;
+ }
+
+ /* we only use the buffer cache for meta-data */
+ rw |= REQ_META;
+
+ /*
+ * Walk all the vectors issuing IO on them. Set up the initial offset
+ * into the buffer and the desired IO size before we start -
+ * _xfs_buf_ioapply_vec() will modify them appropriately for each
+ * subsequent call.
+ */
+ offset = bp->b_offset;
+ size = BBTOB(bp->b_io_length);
+ blk_start_plug(&plug);
+ for (i = 0; i < bp->b_map_count; i++) {
+ xfs_buf_ioapply_map(bp, i, &offset, &size, rw);
+ if (bp->b_error)
+ break;
+ if (size <= 0)
+ break; /* all done */
+ }
+ blk_finish_plug(&plug);
}
void
@@ -1237,21 +1371,29 @@ xfs_buf_iorequest(
xfs_buf_wait_unpin(bp);
xfs_buf_hold(bp);
- /* Set the count to 1 initially, this will stop an I/O
+ /*
+ * Set the count to 1 initially, this will stop an I/O
* completion callout which happens before we have started
* all the I/O from calling xfs_buf_ioend too early.
*/
atomic_set(&bp->b_io_remaining, 1);
_xfs_buf_ioapply(bp);
- _xfs_buf_ioend(bp, 0);
+ /*
+ * If _xfs_buf_ioapply failed, we'll get back here with
+ * only the reference we took above. _xfs_buf_ioend will
+ * drop it to zero, so we'd better not queue it for later,
+ * or we'll free it before it's done.
+ */
+ _xfs_buf_ioend(bp, bp->b_error ? 0 : 1);
xfs_buf_rele(bp);
}
/*
* Waits for I/O to complete on the buffer supplied. It returns immediately if
- * no I/O is pending or there is already a pending error on the buffer. It
- * returns the I/O error code, if any, or 0 if there was no error.
+ * no I/O is pending or there is already a pending error on the buffer, in which
+ * case nothing will ever complete. It returns the I/O error code, if any, or
+ * 0 if there was no error.
*/
int
xfs_buf_iowait(
@@ -1332,80 +1474,127 @@ xfs_buf_iomove(
* returned. These buffers will have an elevated hold count, so wait on those
* while freeing all the buffers only held by the LRU.
*/
+static enum lru_status
+xfs_buftarg_wait_rele(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+
+{
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
+ struct list_head *dispose = arg;
+
+ if (atomic_read(&bp->b_hold) > 1) {
+ /* need to wait, so skip it this pass */
+ trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
+ return LRU_SKIP;
+ }
+ if (!spin_trylock(&bp->b_lock))
+ return LRU_SKIP;
+
+ /*
+ * clear the LRU reference count so the buffer doesn't get
+ * ignored in xfs_buf_rele().
+ */
+ atomic_set(&bp->b_lru_ref, 0);
+ bp->b_state |= XFS_BSTATE_DISPOSE;
+ list_move(item, dispose);
+ spin_unlock(&bp->b_lock);
+ return LRU_REMOVED;
+}
+
void
xfs_wait_buftarg(
struct xfs_buftarg *btp)
{
- struct xfs_buf *bp;
+ LIST_HEAD(dispose);
+ int loop = 0;
-restart:
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
- if (atomic_read(&bp->b_hold) > 1) {
- spin_unlock(&btp->bt_lru_lock);
- delay(100);
- goto restart;
+ /* loop until there is nothing left on the lru list. */
+ while (list_lru_count(&btp->bt_lru)) {
+ list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele,
+ &dispose, LONG_MAX);
+
+ while (!list_empty(&dispose)) {
+ struct xfs_buf *bp;
+ bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
+ list_del_init(&bp->b_lru);
+ if (bp->b_flags & XBF_WRITE_FAIL) {
+ xfs_alert(btp->bt_mount,
+"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n"
+"Please run xfs_repair to determine the extent of the problem.",
+ (long long)bp->b_bn);
+ }
+ xfs_buf_rele(bp);
}
- /*
- * clear the LRU reference count so the buffer doesn't get
- * ignored in xfs_buf_rele().
- */
- atomic_set(&bp->b_lru_ref, 0);
- spin_unlock(&btp->bt_lru_lock);
- xfs_buf_rele(bp);
- spin_lock(&btp->bt_lru_lock);
+ if (loop++ != 0)
+ delay(100);
}
- spin_unlock(&btp->bt_lru_lock);
}
-int
-xfs_buftarg_shrink(
+static enum lru_status
+xfs_buftarg_isolate(
+ struct list_head *item,
+ spinlock_t *lru_lock,
+ void *arg)
+{
+ struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru);
+ struct list_head *dispose = arg;
+
+ /*
+ * we are inverting the lru lock/bp->b_lock here, so use a trylock.
+ * If we fail to get the lock, just skip it.
+ */
+ if (!spin_trylock(&bp->b_lock))
+ return LRU_SKIP;
+ /*
+ * Decrement the b_lru_ref count unless the value is already
+ * zero. If the value is already zero, we need to reclaim the
+ * buffer, otherwise it gets another trip through the LRU.
+ */
+ if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
+ spin_unlock(&bp->b_lock);
+ return LRU_ROTATE;
+ }
+
+ bp->b_state |= XFS_BSTATE_DISPOSE;
+ list_move(item, dispose);
+ spin_unlock(&bp->b_lock);
+ return LRU_REMOVED;
+}
+
+static unsigned long
+xfs_buftarg_shrink_scan(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_buftarg *btp = container_of(shrink,
struct xfs_buftarg, bt_shrinker);
- struct xfs_buf *bp;
- int nr_to_scan = sc->nr_to_scan;
LIST_HEAD(dispose);
+ unsigned long freed;
+ unsigned long nr_to_scan = sc->nr_to_scan;
- if (!nr_to_scan)
- return btp->bt_lru_nr;
-
- spin_lock(&btp->bt_lru_lock);
- while (!list_empty(&btp->bt_lru)) {
- if (nr_to_scan-- <= 0)
- break;
-
- bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
-
- /*
- * Decrement the b_lru_ref count unless the value is already
- * zero. If the value is already zero, we need to reclaim the
- * buffer, otherwise it gets another trip through the LRU.
- */
- if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
- list_move_tail(&bp->b_lru, &btp->bt_lru);
- continue;
- }
-
- /*
- * remove the buffer from the LRU now to avoid needing another
- * lock round trip inside xfs_buf_rele().
- */
- list_move(&bp->b_lru, &dispose);
- btp->bt_lru_nr--;
- }
- spin_unlock(&btp->bt_lru_lock);
+ freed = list_lru_walk_node(&btp->bt_lru, sc->nid, xfs_buftarg_isolate,
+ &dispose, &nr_to_scan);
while (!list_empty(&dispose)) {
+ struct xfs_buf *bp;
bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
list_del_init(&bp->b_lru);
xfs_buf_rele(bp);
}
- return btp->bt_lru_nr;
+ return freed;
+}
+
+static unsigned long
+xfs_buftarg_shrink_count(
+ struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct xfs_buftarg *btp = container_of(shrink,
+ struct xfs_buftarg, bt_shrinker);
+ return list_lru_count_node(&btp->bt_lru, sc->nid);
}
void
@@ -1414,6 +1603,7 @@ xfs_free_buftarg(
struct xfs_buftarg *btp)
{
unregister_shrinker(&btp->bt_shrinker);
+ list_lru_destroy(&btp->bt_lru);
if (mp->m_flags & XFS_MOUNT_BARRIER)
xfs_blkdev_issue_flush(btp);
@@ -1421,16 +1611,14 @@ xfs_free_buftarg(
kmem_free(btp);
}
-STATIC int
-xfs_setsize_buftarg_flags(
+int
+xfs_setsize_buftarg(
xfs_buftarg_t *btp,
- unsigned int blocksize,
- unsigned int sectorsize,
- int verbose)
+ unsigned int sectorsize)
{
- btp->bt_bsize = blocksize;
- btp->bt_sshift = ffs(sectorsize) - 1;
- btp->bt_smask = sectorsize - 1;
+ /* Set up metadata sector size info */
+ btp->bt_meta_sectorsize = sectorsize;
+ btp->bt_meta_sectormask = sectorsize - 1;
if (set_blocksize(btp->bt_bdev, sectorsize)) {
char name[BDEVNAME_SIZE];
@@ -1438,47 +1626,39 @@ xfs_setsize_buftarg_flags(
bdevname(btp->bt_bdev, name);
xfs_warn(btp->bt_mount,
- "Cannot set_blocksize to %u on device %s\n",
+ "Cannot set_blocksize to %u on device %s",
sectorsize, name);
return EINVAL;
}
+ /* Set up device logical sector size mask */
+ btp->bt_logical_sectorsize = bdev_logical_block_size(btp->bt_bdev);
+ btp->bt_logical_sectormask = bdev_logical_block_size(btp->bt_bdev) - 1;
+
return 0;
}
/*
- * When allocating the initial buffer target we have not yet
- * read in the superblock, so don't know what sized sectors
- * are being used is at this early stage. Play safe.
+ * When allocating the initial buffer target we have not yet
+ * read in the superblock, so don't know what sized sectors
+ * are being used at this early stage. Play safe.
*/
STATIC int
xfs_setsize_buftarg_early(
xfs_buftarg_t *btp,
struct block_device *bdev)
{
- return xfs_setsize_buftarg_flags(btp,
- PAGE_SIZE, bdev_logical_block_size(bdev), 0);
-}
-
-int
-xfs_setsize_buftarg(
- xfs_buftarg_t *btp,
- unsigned int blocksize,
- unsigned int sectorsize)
-{
- return xfs_setsize_buftarg_flags(btp, blocksize, sectorsize, 1);
+ return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev));
}
xfs_buftarg_t *
xfs_alloc_buftarg(
struct xfs_mount *mp,
- struct block_device *bdev,
- int external,
- const char *fsname)
+ struct block_device *bdev)
{
xfs_buftarg_t *btp;
- btp = kmem_zalloc(sizeof(*btp), KM_SLEEP);
+ btp = kmem_zalloc(sizeof(*btp), KM_SLEEP | KM_NOFS);
btp->bt_mount = mp;
btp->bt_dev = bdev->bd_dev;
@@ -1487,12 +1667,16 @@ xfs_alloc_buftarg(
if (!btp->bt_bdi)
goto error;
- INIT_LIST_HEAD(&btp->bt_lru);
- spin_lock_init(&btp->bt_lru_lock);
if (xfs_setsize_buftarg_early(btp, bdev))
goto error;
- btp->bt_shrinker.shrink = xfs_buftarg_shrink;
+
+ if (list_lru_init(&btp->bt_lru))
+ goto error;
+
+ btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count;
+ btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
btp->bt_shrinker.seeks = DEFAULT_SEEKS;
+ btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE;
register_shrinker(&btp->bt_shrinker);
return btp;
@@ -1564,7 +1748,7 @@ xfs_buf_cmp(
struct xfs_buf *bp = container_of(b, struct xfs_buf, b_list);
xfs_daddr_t diff;
- diff = ap->b_bn - bp->b_bn;
+ diff = ap->b_maps[0].bm_bn - bp->b_maps[0].bm_bn;
if (diff < 0)
return -1;
if (diff > 0)
@@ -1614,7 +1798,7 @@ __xfs_buf_delwri_submit(
blk_start_plug(&plug);
list_for_each_entry_safe(bp, n, io_list, b_list) {
- bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
+ bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
bp->b_flags |= XBF_WRITE;
if (!wait) {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 7f1d1392ce3..3a7a5523d3d 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -25,6 +25,7 @@
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/uio.h>
+#include <linux/list_lru.h>
/*
* Base types
@@ -38,26 +39,28 @@ typedef enum {
XBRW_ZERO = 3, /* Zero target memory */
} xfs_buf_rw_t;
-#define XBF_READ (1 << 0) /* buffer intended for reading from device */
-#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */
-#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */
-#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */
-#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */
-#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */
+#define XBF_READ (1 << 0) /* buffer intended for reading from device */
+#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */
+#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */
+#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */
+#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */
+#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */
+#define XBF_WRITE_FAIL (1 << 24)/* async writes have failed on this buffer */
/* I/O hints for the BIO layer */
-#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */
-#define XBF_FUA (1 << 11)/* force cache write through mode */
-#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */
+#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */
+#define XBF_FUA (1 << 11)/* force cache write through mode */
+#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */
/* flags used only as arguments to access routines */
-#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */
-#define XBF_UNMAPPED (1 << 17)/* do not map the buffer */
+#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */
+#define XBF_UNMAPPED (1 << 17)/* do not map the buffer */
/* flags used only internally */
-#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */
-#define _XBF_KMEM (1 << 21)/* backed by heap memory */
-#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */
+#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */
+#define _XBF_KMEM (1 << 21)/* backed by heap memory */
+#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */
+#define _XBF_COMPOUND (1 << 23)/* compound buffer */
typedef unsigned int xfs_buf_flags_t;
@@ -68,36 +71,70 @@ typedef unsigned int xfs_buf_flags_t;
{ XBF_ASYNC, "ASYNC" }, \
{ XBF_DONE, "DONE" }, \
{ XBF_STALE, "STALE" }, \
+ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \
{ XBF_SYNCIO, "SYNCIO" }, \
{ XBF_FUA, "FUA" }, \
{ XBF_FLUSH, "FLUSH" }, \
- { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\
+ { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\
{ XBF_UNMAPPED, "UNMAPPED" }, /* ditto */\
{ _XBF_PAGES, "PAGES" }, \
{ _XBF_KMEM, "KMEM" }, \
- { _XBF_DELWRI_Q, "DELWRI_Q" }
+ { _XBF_DELWRI_Q, "DELWRI_Q" }, \
+ { _XBF_COMPOUND, "COMPOUND" }
+
+/*
+ * Internal state flags.
+ */
+#define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */
+
+/*
+ * The xfs_buftarg contains 2 notions of "sector size" -
+ *
+ * 1) The metadata sector size, which is the minimum unit and
+ * alignment of IO which will be performed by metadata operations.
+ * 2) The device logical sector size
+ *
+ * The first is specified at mkfs time, and is stored on-disk in the
+ * superblock's sb_sectsize.
+ *
+ * The latter is derived from the underlying device, and controls direct IO
+ * alignment constraints.
+ */
typedef struct xfs_buftarg {
dev_t bt_dev;
struct block_device *bt_bdev;
struct backing_dev_info *bt_bdi;
struct xfs_mount *bt_mount;
- unsigned int bt_bsize;
- unsigned int bt_sshift;
- size_t bt_smask;
+ unsigned int bt_meta_sectorsize;
+ size_t bt_meta_sectormask;
+ size_t bt_logical_sectorsize;
+ size_t bt_logical_sectormask;
/* LRU control structures */
struct shrinker bt_shrinker;
- struct list_head bt_lru;
- spinlock_t bt_lru_lock;
- unsigned int bt_lru_nr;
+ struct list_lru bt_lru;
} xfs_buftarg_t;
struct xfs_buf;
typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
+
#define XB_PAGES 2
+struct xfs_buf_map {
+ xfs_daddr_t bm_bn; /* block number for I/O */
+ int bm_len; /* size of I/O */
+};
+
+#define DEFINE_SINGLE_BUF_MAP(map, blkno, numblk) \
+ struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };
+
+struct xfs_buf_ops {
+ void (*verify_read)(struct xfs_buf *);
+ void (*verify_write)(struct xfs_buf *);
+};
+
typedef struct xfs_buf {
/*
* first cacheline holds all the fields needed for an uncontended cache
@@ -107,14 +144,20 @@ typedef struct xfs_buf {
* fast-path on locking.
*/
struct rb_node b_rbnode; /* rbtree node */
- xfs_daddr_t b_bn; /* block number for I/O */
+ xfs_daddr_t b_bn; /* block number of buffer */
int b_length; /* size of buffer in BBs */
atomic_t b_hold; /* reference count */
atomic_t b_lru_ref; /* lru reclaim ref count */
xfs_buf_flags_t b_flags; /* status flags */
struct semaphore b_sema; /* semaphore for lockables */
+ /*
+ * concurrent access to b_lru and b_lru_flags are protected by
+ * bt_lru_lock and not by b_sema
+ */
struct list_head b_lru; /* lru list */
+ spinlock_t b_lock; /* internal state lock */
+ unsigned int b_state; /* internal state flags */
wait_queue_head_t b_waiters; /* unpin waiters */
struct list_head b_list;
struct xfs_perag *b_pag; /* contains rbtree root */
@@ -127,42 +170,107 @@ typedef struct xfs_buf {
struct xfs_trans *b_transp;
struct page **b_pages; /* array of page pointers */
struct page *b_page_array[XB_PAGES]; /* inline pages */
+ struct xfs_buf_map *b_maps; /* compound buffer map */
+ struct xfs_buf_map __b_map; /* inline compound buffer map */
+ int b_map_count;
int b_io_length; /* IO size in BBs */
atomic_t b_pin_count; /* pin count */
atomic_t b_io_remaining; /* #outstanding I/O requests */
unsigned int b_page_count; /* size of page array */
unsigned int b_offset; /* page offset in first page */
unsigned short b_error; /* error code on I/O */
+ const struct xfs_buf_ops *b_ops;
+
#ifdef XFS_BUF_LOCK_TRACKING
int b_last_holder;
#endif
} xfs_buf_t;
-
/* Finding and Reading Buffers */
-struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target, xfs_daddr_t blkno,
- size_t numblks, xfs_buf_flags_t flags,
- struct xfs_buf *new_bp);
-#define xfs_incore(buftarg,blkno,len,lockit) \
- _xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
-
-struct xfs_buf *xfs_buf_get(struct xfs_buftarg *target, xfs_daddr_t blkno,
- size_t numblks, xfs_buf_flags_t flags);
-struct xfs_buf *xfs_buf_read(struct xfs_buftarg *target, xfs_daddr_t blkno,
- size_t numblks, xfs_buf_flags_t flags);
-void xfs_buf_readahead(struct xfs_buftarg *target, xfs_daddr_t blkno,
- size_t numblks);
+struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target,
+ struct xfs_buf_map *map, int nmaps,
+ xfs_buf_flags_t flags, struct xfs_buf *new_bp);
+
+static inline struct xfs_buf *
+xfs_incore(
+ struct xfs_buftarg *target,
+ xfs_daddr_t blkno,
+ size_t numblks,
+ xfs_buf_flags_t flags)
+{
+ DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+ return _xfs_buf_find(target, &map, 1, flags, NULL);
+}
+
+struct xfs_buf *_xfs_buf_alloc(struct xfs_buftarg *target,
+ struct xfs_buf_map *map, int nmaps,
+ xfs_buf_flags_t flags);
+
+static inline struct xfs_buf *
+xfs_buf_alloc(
+ struct xfs_buftarg *target,
+ xfs_daddr_t blkno,
+ size_t numblks,
+ xfs_buf_flags_t flags)
+{
+ DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+ return _xfs_buf_alloc(target, &map, 1, flags);
+}
+
+struct xfs_buf *xfs_buf_get_map(struct xfs_buftarg *target,
+ struct xfs_buf_map *map, int nmaps,
+ xfs_buf_flags_t flags);
+struct xfs_buf *xfs_buf_read_map(struct xfs_buftarg *target,
+ struct xfs_buf_map *map, int nmaps,
+ xfs_buf_flags_t flags,
+ const struct xfs_buf_ops *ops);
+void xfs_buf_readahead_map(struct xfs_buftarg *target,
+ struct xfs_buf_map *map, int nmaps,
+ const struct xfs_buf_ops *ops);
+
+static inline struct xfs_buf *
+xfs_buf_get(
+ struct xfs_buftarg *target,
+ xfs_daddr_t blkno,
+ size_t numblks,
+ xfs_buf_flags_t flags)
+{
+ DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+ return xfs_buf_get_map(target, &map, 1, flags);
+}
+
+static inline struct xfs_buf *
+xfs_buf_read(
+ struct xfs_buftarg *target,
+ xfs_daddr_t blkno,
+ size_t numblks,
+ xfs_buf_flags_t flags,
+ const struct xfs_buf_ops *ops)
+{
+ DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+ return xfs_buf_read_map(target, &map, 1, flags, ops);
+}
+
+static inline void
+xfs_buf_readahead(
+ struct xfs_buftarg *target,
+ xfs_daddr_t blkno,
+ size_t numblks,
+ const struct xfs_buf_ops *ops)
+{
+ DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+ return xfs_buf_readahead_map(target, &map, 1, ops);
+}
struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);
-struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *target, xfs_daddr_t blkno,
- size_t numblks, xfs_buf_flags_t flags);
void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks);
int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
int flags);
struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target,
- xfs_daddr_t daddr, size_t numblks, int flags);
+ xfs_daddr_t daddr, size_t numblks, int flags,
+ const struct xfs_buf_ops *ops);
void xfs_buf_hold(struct xfs_buf *bp);
/* Releasing Buffers */
@@ -178,10 +286,6 @@ extern void xfs_buf_unlock(xfs_buf_t *);
/* Buffer Read and Write Routines */
extern int xfs_bwrite(struct xfs_buf *bp);
-
-extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
-extern int xfs_bdstrat_cb(struct xfs_buf *);
-
extern void xfs_buf_ioend(xfs_buf_t *, int);
extern void xfs_buf_ioerror(xfs_buf_t *, int);
extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
@@ -192,10 +296,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
#define xfs_buf_zero(bp, off, len) \
xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
-static inline int xfs_buf_geterror(xfs_buf_t *bp)
-{
- return bp ? bp->b_error : ENOMEM;
-}
+extern int xfs_bioerror_relse(struct xfs_buf *);
/* Buffer Utility Routines */
extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
@@ -211,7 +312,8 @@ extern void xfs_buf_terminate(void);
#define XFS_BUF_ZEROFLAGS(bp) \
((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
- XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
+ XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
+ XBF_WRITE_FAIL))
void xfs_buf_stale(struct xfs_buf *bp);
#define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE)
@@ -233,8 +335,18 @@ void xfs_buf_stale(struct xfs_buf *bp);
#define XFS_BUF_UNWRITE(bp) ((bp)->b_flags &= ~XBF_WRITE)
#define XFS_BUF_ISWRITE(bp) ((bp)->b_flags & XBF_WRITE)
-#define XFS_BUF_ADDR(bp) ((bp)->b_bn)
-#define XFS_BUF_SET_ADDR(bp, bno) ((bp)->b_bn = (xfs_daddr_t)(bno))
+/*
+ * These macros use the IO block map rather than b_bn. b_bn is now really
+ * just for the buffer cache index for cached buffers. As IO does not use b_bn
+ * anymore, uncached buffers do not use b_bn at all and hence must modify the IO
+ * map directly. Uncached buffers are not allowed to be discontiguous, so this
+ * is safe to do.
+ *
+ * In future, uncached buffers will pass the block number directly to the io
+ * request function and hence these macros will go away at that point.
+ */
+#define XFS_BUF_ADDR(bp) ((bp)->b_maps[0].bm_bn)
+#define XFS_BUF_SET_ADDR(bp, bno) ((bp)->b_maps[0].bm_bn = (xfs_daddr_t)(bno))
static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
{
@@ -252,14 +364,28 @@ static inline void xfs_buf_relse(xfs_buf_t *bp)
xfs_buf_rele(bp);
}
+static inline int
+xfs_buf_verify_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
+{
+ return xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
+ cksum_offset);
+}
+
+static inline void
+xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
+{
+ xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length),
+ cksum_offset);
+}
+
/*
* Handling of buftargs.
*/
extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
- struct block_device *, int, const char *);
+ struct block_device *);
extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
extern void xfs_wait_buftarg(xfs_buftarg_t *);
-extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
+extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int);
#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev)
#define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 45df2b857d4..4654338b03f 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -17,17 +17,18 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_trans_priv.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_log.h"
kmem_zone_t *xfs_buf_item_zone;
@@ -37,110 +38,15 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
return container_of(lip, struct xfs_buf_log_item, bli_item);
}
+STATIC void xfs_buf_do_callbacks(struct xfs_buf *bp);
-#ifdef XFS_TRANS_DEBUG
-/*
- * This function uses an alternate strategy for tracking the bytes
- * that the user requests to be logged. This can then be used
- * in conjunction with the bli_orig array in the buf log item to
- * catch bugs in our callers' code.
- *
- * We also double check the bits set in xfs_buf_item_log using a
- * simple algorithm to check that every byte is accounted for.
- */
-STATIC void
-xfs_buf_item_log_debug(
- xfs_buf_log_item_t *bip,
- uint first,
- uint last)
-{
- uint x;
- uint byte;
- uint nbytes;
- uint chunk_num;
- uint word_num;
- uint bit_num;
- uint bit_set;
- uint *wordp;
-
- ASSERT(bip->bli_logged != NULL);
- byte = first;
- nbytes = last - first + 1;
- bfset(bip->bli_logged, first, nbytes);
- for (x = 0; x < nbytes; x++) {
- chunk_num = byte >> XFS_BLF_SHIFT;
- word_num = chunk_num >> BIT_TO_WORD_SHIFT;
- bit_num = chunk_num & (NBWORD - 1);
- wordp = &(bip->bli_format.blf_data_map[word_num]);
- bit_set = *wordp & (1 << bit_num);
- ASSERT(bit_set);
- byte++;
- }
-}
-
-/*
- * This function is called when we flush something into a buffer without
- * logging it. This happens for things like inodes which are logged
- * separately from the buffer.
- */
-void
-xfs_buf_item_flush_log_debug(
- xfs_buf_t *bp,
- uint first,
- uint last)
-{
- xfs_buf_log_item_t *bip = bp->b_fspriv;
- uint nbytes;
-
- if (bip == NULL || (bip->bli_item.li_type != XFS_LI_BUF))
- return;
-
- ASSERT(bip->bli_logged != NULL);
- nbytes = last - first + 1;
- bfset(bip->bli_logged, first, nbytes);
-}
-
-/*
- * This function is called to verify that our callers have logged
- * all the bytes that they changed.
- *
- * It does this by comparing the original copy of the buffer stored in
- * the buf log item's bli_orig array to the current copy of the buffer
- * and ensuring that all bytes which mismatch are set in the bli_logged
- * array of the buf log item.
- */
-STATIC void
-xfs_buf_item_log_check(
- xfs_buf_log_item_t *bip)
+static inline int
+xfs_buf_log_format_size(
+ struct xfs_buf_log_format *blfp)
{
- char *orig;
- char *buffer;
- int x;
- xfs_buf_t *bp;
-
- ASSERT(bip->bli_orig != NULL);
- ASSERT(bip->bli_logged != NULL);
-
- bp = bip->bli_buf;
- ASSERT(bp->b_length > 0);
- ASSERT(bp->b_addr != NULL);
- orig = bip->bli_orig;
- buffer = bp->b_addr;
- for (x = 0; x < BBTOB(bp->b_length); x++) {
- if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) {
- xfs_emerg(bp->b_mount,
- "%s: bip %x buffer %x orig %x index %d",
- __func__, bip, bp, orig, x);
- ASSERT(0);
- }
- }
+ return offsetof(struct xfs_buf_log_format, blf_data_map) +
+ (blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
}
-#else
-#define xfs_buf_item_log_debug(x,y,z)
-#define xfs_buf_item_log_check(x)
-#endif
-
-STATIC void xfs_buf_do_callbacks(struct xfs_buf *bp);
/*
* This returns the number of log iovecs needed to log the
@@ -152,34 +58,28 @@ STATIC void xfs_buf_do_callbacks(struct xfs_buf *bp);
*
* If the XFS_BLI_STALE flag has been set, then log nothing.
*/
-STATIC uint
-xfs_buf_item_size(
- struct xfs_log_item *lip)
+STATIC void
+xfs_buf_item_size_segment(
+ struct xfs_buf_log_item *bip,
+ struct xfs_buf_log_format *blfp,
+ int *nvecs,
+ int *nbytes)
{
- struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
- uint nvecs;
int next_bit;
int last_bit;
- ASSERT(atomic_read(&bip->bli_refcount) > 0);
- if (bip->bli_flags & XFS_BLI_STALE) {
- /*
- * The buffer is stale, so all we need to log
- * is the buf log format structure with the
- * cancel flag in it.
- */
- trace_xfs_buf_item_size_stale(bip);
- ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
- return 1;
- }
+ last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+ if (last_bit == -1)
+ return;
+
+ /*
+ * initial count for a dirty buffer is 2 vectors - the format structure
+ * and the first dirty region.
+ */
+ *nvecs += 2;
+ *nbytes += xfs_buf_log_format_size(blfp) + XFS_BLF_CHUNK;
- ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
- nvecs = 1;
- last_bit = xfs_next_bit(bip->bli_format.blf_data_map,
- bip->bli_format.blf_map_size, 0);
- ASSERT(last_bit != -1);
- nvecs++;
while (last_bit != -1) {
/*
* This takes the bit number to start looking from and
@@ -187,88 +87,165 @@ xfs_buf_item_size(
* if there are no more bits set or the start bit is
* beyond the end of the bitmap.
*/
- next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
- bip->bli_format.blf_map_size,
- last_bit + 1);
+ next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+ last_bit + 1);
/*
* If we run out of bits, leave the loop,
* else if we find a new set of bits bump the number of vecs,
* else keep scanning the current set of bits.
*/
if (next_bit == -1) {
- last_bit = -1;
+ break;
} else if (next_bit != last_bit + 1) {
last_bit = next_bit;
- nvecs++;
+ (*nvecs)++;
} else if (xfs_buf_offset(bp, next_bit * XFS_BLF_CHUNK) !=
(xfs_buf_offset(bp, last_bit * XFS_BLF_CHUNK) +
XFS_BLF_CHUNK)) {
last_bit = next_bit;
- nvecs++;
+ (*nvecs)++;
} else {
last_bit++;
}
+ *nbytes += XFS_BLF_CHUNK;
}
-
- trace_xfs_buf_item_size(bip);
- return nvecs;
}
/*
- * This is called to fill in the vector of log iovecs for the
- * given log buf item. It fills the first entry with a buf log
- * format structure, and the rest point to contiguous chunks
- * within the buffer.
+ * This returns the number of log iovecs needed to log the given buf log item.
+ *
+ * It calculates this as 1 iovec for the buf log format structure and 1 for each
+ * stretch of non-contiguous chunks to be logged. Contiguous chunks are logged
+ * in a single iovec.
+ *
+ * Discontiguous buffers need a format structure per region that that is being
+ * logged. This makes the changes in the buffer appear to log recovery as though
+ * they came from separate buffers, just like would occur if multiple buffers
+ * were used instead of a single discontiguous buffer. This enables
+ * discontiguous buffers to be in-memory constructs, completely transparent to
+ * what ends up on disk.
+ *
+ * If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
+ * format structures.
*/
STATIC void
-xfs_buf_item_format(
+xfs_buf_item_size(
struct xfs_log_item *lip,
- struct xfs_log_iovec *vecp)
+ int *nvecs,
+ int *nbytes)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
+ int i;
+
+ ASSERT(atomic_read(&bip->bli_refcount) > 0);
+ if (bip->bli_flags & XFS_BLI_STALE) {
+ /*
+ * The buffer is stale, so all we need to log
+ * is the buf log format structure with the
+ * cancel flag in it.
+ */
+ trace_xfs_buf_item_size_stale(bip);
+ ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
+ *nvecs += bip->bli_format_count;
+ for (i = 0; i < bip->bli_format_count; i++) {
+ *nbytes += xfs_buf_log_format_size(&bip->bli_formats[i]);
+ }
+ return;
+ }
+
+ ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
+
+ if (bip->bli_flags & XFS_BLI_ORDERED) {
+ /*
+ * The buffer has been logged just to order it.
+ * It is not being included in the transaction
+ * commit, so no vectors are used at all.
+ */
+ trace_xfs_buf_item_size_ordered(bip);
+ *nvecs = XFS_LOG_VEC_ORDERED;
+ return;
+ }
+
+ /*
+ * the vector count is based on the number of buffer vectors we have
+ * dirty bits in. This will only be greater than one when we have a
+ * compound buffer with more than one segment dirty. Hence for compound
+ * buffers we need to track which segment the dirty bits correspond to,
+ * and when we move from one segment to the next increment the vector
+ * count for the extra buf log format structure that will need to be
+ * written.
+ */
+ for (i = 0; i < bip->bli_format_count; i++) {
+ xfs_buf_item_size_segment(bip, &bip->bli_formats[i],
+ nvecs, nbytes);
+ }
+ trace_xfs_buf_item_size(bip);
+}
+
+static inline void
+xfs_buf_item_copy_iovec(
+ struct xfs_log_vec *lv,
+ struct xfs_log_iovec **vecp,
+ struct xfs_buf *bp,
+ uint offset,
+ int first_bit,
+ uint nbits)
+{
+ offset += first_bit * XFS_BLF_CHUNK;
+ xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_BCHUNK,
+ xfs_buf_offset(bp, offset),
+ nbits * XFS_BLF_CHUNK);
+}
+
+static inline bool
+xfs_buf_item_straddle(
+ struct xfs_buf *bp,
+ uint offset,
+ int next_bit,
+ int last_bit)
+{
+ return xfs_buf_offset(bp, offset + (next_bit << XFS_BLF_SHIFT)) !=
+ (xfs_buf_offset(bp, offset + (last_bit << XFS_BLF_SHIFT)) +
+ XFS_BLF_CHUNK);
+}
+
+static void
+xfs_buf_item_format_segment(
+ struct xfs_buf_log_item *bip,
+ struct xfs_log_vec *lv,
+ struct xfs_log_iovec **vecp,
+ uint offset,
+ struct xfs_buf_log_format *blfp)
+{
struct xfs_buf *bp = bip->bli_buf;
uint base_size;
- uint nvecs;
int first_bit;
int last_bit;
int next_bit;
uint nbits;
- uint buffer_offset;
- ASSERT(atomic_read(&bip->bli_refcount) > 0);
- ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
- (bip->bli_flags & XFS_BLI_STALE));
+ /* copy the flags across from the base format item */
+ blfp->blf_flags = bip->__bli_format.blf_flags;
/*
- * The size of the base structure is the size of the
- * declared structure plus the space for the extra words
- * of the bitmap. We subtract one from the map size, because
- * the first element of the bitmap is accounted for in the
- * size of the base structure.
+ * Base size is the actual size of the ondisk structure - it reflects
+ * the actual size of the dirty bitmap rather than the size of the in
+ * memory structure.
*/
- base_size =
- (uint)(sizeof(xfs_buf_log_format_t) +
- ((bip->bli_format.blf_map_size - 1) * sizeof(uint)));
- vecp->i_addr = &bip->bli_format;
- vecp->i_len = base_size;
- vecp->i_type = XLOG_REG_TYPE_BFORMAT;
- vecp++;
- nvecs = 1;
+ base_size = xfs_buf_log_format_size(blfp);
- /*
- * If it is an inode buffer, transfer the in-memory state to the
- * format flags and clear the in-memory state. We do not transfer
- * this state if the inode buffer allocation has not yet been committed
- * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
- * correct replay of the inode allocation.
- */
- if (bip->bli_flags & XFS_BLI_INODE_BUF) {
- if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
- xfs_log_item_in_current_chkpt(lip)))
- bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
- bip->bli_flags &= ~XFS_BLI_INODE_BUF;
+ first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+ if (!(bip->bli_flags & XFS_BLI_STALE) && first_bit == -1) {
+ /*
+ * If the map is not be dirty in the transaction, mark
+ * the size as zero and do not advance the vector pointer.
+ */
+ return;
}
+ blfp = xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_BFORMAT, blfp, base_size);
+ blfp->blf_size = 1;
+
if (bip->bli_flags & XFS_BLI_STALE) {
/*
* The buffer is stale, so all we need to log
@@ -276,17 +253,14 @@ xfs_buf_item_format(
* cancel flag in it.
*/
trace_xfs_buf_item_format_stale(bip);
- ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
- bip->bli_format.blf_size = nvecs;
+ ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
return;
}
+
/*
* Fill in an iovec for each set of contiguous chunks.
*/
- first_bit = xfs_next_bit(bip->bli_format.blf_data_map,
- bip->bli_format.blf_map_size, 0);
- ASSERT(first_bit != -1);
last_bit = first_bit;
nbits = 1;
for (;;) {
@@ -296,48 +270,25 @@ xfs_buf_item_format(
* if there are no more bits set or the start bit is
* beyond the end of the bitmap.
*/
- next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
- bip->bli_format.blf_map_size,
- (uint)last_bit + 1);
+ next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+ (uint)last_bit + 1);
/*
- * If we run out of bits fill in the last iovec and get
- * out of the loop.
- * Else if we start a new set of bits then fill in the
- * iovec for the series we were looking at and start
- * counting the bits in the new one.
- * Else we're still in the same set of bits so just
- * keep counting and scanning.
+ * If we run out of bits fill in the last iovec and get out of
+ * the loop. Else if we start a new set of bits then fill in
+ * the iovec for the series we were looking at and start
+ * counting the bits in the new one. Else we're still in the
+ * same set of bits so just keep counting and scanning.
*/
if (next_bit == -1) {
- buffer_offset = first_bit * XFS_BLF_CHUNK;
- vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
- vecp->i_len = nbits * XFS_BLF_CHUNK;
- vecp->i_type = XLOG_REG_TYPE_BCHUNK;
- nvecs++;
+ xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
+ first_bit, nbits);
+ blfp->blf_size++;
break;
- } else if (next_bit != last_bit + 1) {
- buffer_offset = first_bit * XFS_BLF_CHUNK;
- vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
- vecp->i_len = nbits * XFS_BLF_CHUNK;
- vecp->i_type = XLOG_REG_TYPE_BCHUNK;
- nvecs++;
- vecp++;
- first_bit = next_bit;
- last_bit = next_bit;
- nbits = 1;
- } else if (xfs_buf_offset(bp, next_bit << XFS_BLF_SHIFT) !=
- (xfs_buf_offset(bp, last_bit << XFS_BLF_SHIFT) +
- XFS_BLF_CHUNK)) {
- buffer_offset = first_bit * XFS_BLF_CHUNK;
- vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
- vecp->i_len = nbits * XFS_BLF_CHUNK;
- vecp->i_type = XLOG_REG_TYPE_BCHUNK;
-/* You would think we need to bump the nvecs here too, but we do not
- * this number is used by recovery, and it gets confused by the boundary
- * split here
- * nvecs++;
- */
- vecp++;
+ } else if (next_bit != last_bit + 1 ||
+ xfs_buf_item_straddle(bp, offset, next_bit, last_bit)) {
+ xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
+ first_bit, nbits);
+ blfp->blf_size++;
first_bit = next_bit;
last_bit = next_bit;
nbits = 1;
@@ -346,13 +297,71 @@ xfs_buf_item_format(
nbits++;
}
}
- bip->bli_format.blf_size = nvecs;
+}
+
+/*
+ * This is called to fill in the vector of log iovecs for the
+ * given log buf item. It fills the first entry with a buf log
+ * format structure, and the rest point to contiguous chunks
+ * within the buffer.
+ */
+STATIC void
+xfs_buf_item_format(
+ struct xfs_log_item *lip,
+ struct xfs_log_vec *lv)
+{
+ struct xfs_buf_log_item *bip = BUF_ITEM(lip);
+ struct xfs_buf *bp = bip->bli_buf;
+ struct xfs_log_iovec *vecp = NULL;
+ uint offset = 0;
+ int i;
+
+ ASSERT(atomic_read(&bip->bli_refcount) > 0);
+ ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
+ (bip->bli_flags & XFS_BLI_STALE));
+
+ /*
+ * If it is an inode buffer, transfer the in-memory state to the
+ * format flags and clear the in-memory state.
+ *
+ * For buffer based inode allocation, we do not transfer
+ * this state if the inode buffer allocation has not yet been committed
+ * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
+ * correct replay of the inode allocation.
+ *
+ * For icreate item based inode allocation, the buffers aren't written
+ * to the journal during allocation, and hence we should always tag the
+ * buffer as an inode buffer so that the correct unlinked list replay
+ * occurs during recovery.
+ */
+ if (bip->bli_flags & XFS_BLI_INODE_BUF) {
+ if (xfs_sb_version_hascrc(&lip->li_mountp->m_sb) ||
+ !((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
+ xfs_log_item_in_current_chkpt(lip)))
+ bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
+ bip->bli_flags &= ~XFS_BLI_INODE_BUF;
+ }
+
+ if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) ==
+ XFS_BLI_ORDERED) {
+ /*
+ * The buffer has been logged just to order it. It is not being
+ * included in the transaction commit, so don't format it.
+ */
+ trace_xfs_buf_item_format_ordered(bip);
+ return;
+ }
+
+ for (i = 0; i < bip->bli_format_count; i++) {
+ xfs_buf_item_format_segment(bip, lv, &vecp, offset,
+ &bip->bli_formats[i]);
+ offset += bp->b_maps[i].bm_len;
+ }
/*
* Check to make sure everything is consistent.
*/
trace_xfs_buf_item_format(bip);
- xfs_buf_item_log_check(bip);
}
/*
@@ -372,6 +381,7 @@ xfs_buf_item_pin(
ASSERT(atomic_read(&bip->bli_refcount) > 0);
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
+ (bip->bli_flags & XFS_BLI_ORDERED) ||
(bip->bli_flags & XFS_BLI_STALE));
trace_xfs_buf_item_pin(bip);
@@ -418,7 +428,7 @@ xfs_buf_item_unpin(
ASSERT(bip->bli_flags & XFS_BLI_STALE);
ASSERT(xfs_buf_islocked(bp));
ASSERT(XFS_BUF_ISSTALE(bp));
- ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+ ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
trace_xfs_buf_item_unpin_stale(bip);
@@ -459,7 +469,25 @@ xfs_buf_item_unpin(
}
xfs_buf_relse(bp);
} else if (freed && remove) {
+ /*
+ * There are currently two references to the buffer - the active
+ * LRU reference and the buf log item. What we are about to do
+ * here - simulate a failed IO completion - requires 3
+ * references.
+ *
+ * The LRU reference is removed by the xfs_buf_stale() call. The
+ * buf item reference is removed by the xfs_buf_iodone()
+ * callback that is run by xfs_buf_do_callbacks() during ioend
+ * processing (via the bp->b_iodone callback), and then finally
+ * the ioend processing will drop the IO reference if the buffer
+ * is marked XBF_ASYNC.
+ *
+ * Hence we need to take an additional reference here so that IO
+ * completion processing doesn't free the buffer prematurely.
+ */
xfs_buf_lock(bp);
+ xfs_buf_hold(bp);
+ bp->b_flags |= XBF_ASYNC;
xfs_buf_ioerror(bp, EIO);
XFS_BUF_UNDONE(bp);
xfs_buf_stale(bp);
@@ -467,6 +495,14 @@ xfs_buf_item_unpin(
}
}
+/*
+ * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30
+ * seconds so as to not spam logs too much on repeated detection of the same
+ * buffer being bad..
+ */
+
+DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
+
STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
@@ -478,13 +514,31 @@ xfs_buf_item_push(
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
- if (!xfs_buf_trylock(bp))
+ if (!xfs_buf_trylock(bp)) {
+ /*
+ * If we have just raced with a buffer being pinned and it has
+ * been marked stale, we could end up stalling until someone else
+ * issues a log force to unpin the stale buffer. Check for the
+ * race condition here so xfsaild recognizes the buffer is pinned
+ * and queues a log force to move it along.
+ */
+ if (xfs_buf_ispinned(bp))
+ return XFS_ITEM_PINNED;
return XFS_ITEM_LOCKED;
+ }
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
trace_xfs_buf_item_push(bip);
+ /* has a previous flush failed due to IO errors? */
+ if ((bp->b_flags & XBF_WRITE_FAIL) &&
+ ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
+ xfs_warn(bp->b_target->bt_mount,
+"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
+ (long long)bp->b_bn);
+ }
+
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_unlock(bp);
@@ -516,8 +570,9 @@ xfs_buf_item_unlock(
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
- int aborted;
- uint hold;
+ bool clean;
+ bool aborted;
+ int flags;
/* Clear the buffer's association with this transaction. */
bp->b_transp = NULL;
@@ -528,25 +583,23 @@ xfs_buf_item_unlock(
* (cancelled) buffers at unpin time, but we'll never go through the
* pin/unpin cycle if we abort inside commit.
*/
- aborted = (lip->li_flags & XFS_LI_ABORTED) != 0;
-
+ aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false;
/*
- * Before possibly freeing the buf item, determine if we should
- * release the buffer at the end of this routine.
+ * Before possibly freeing the buf item, copy the per-transaction state
+ * so we can reference it safely later after clearing it from the
+ * buffer log item.
*/
- hold = bip->bli_flags & XFS_BLI_HOLD;
-
- /* Clear the per transaction state. */
- bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD);
+ flags = bip->bli_flags;
+ bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
/*
* If the buf item is marked stale, then don't do anything. We'll
* unlock the buffer and free the buf item when the buffer is unpinned
* for the last time.
*/
- if (bip->bli_flags & XFS_BLI_STALE) {
+ if (flags & XFS_BLI_STALE) {
trace_xfs_buf_item_unlock_stale(bip);
- ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+ ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
if (!aborted) {
atomic_dec(&bip->bli_refcount);
return;
@@ -557,15 +610,49 @@ xfs_buf_item_unlock(
/*
* If the buf item isn't tracking any data, free it, otherwise drop the
- * reference we hold to it.
+ * reference we hold to it. If we are aborting the transaction, this may
+ * be the only reference to the buf item, so we free it anyway
+ * regardless of whether it is dirty or not. A dirty abort implies a
+ * shutdown, anyway.
+ *
+ * Ordered buffers are dirty but may have no recorded changes, so ensure
+ * we only release clean items here.
*/
- if (xfs_bitmap_empty(bip->bli_format.blf_data_map,
- bip->bli_format.blf_map_size))
- xfs_buf_item_relse(bp);
- else
- atomic_dec(&bip->bli_refcount);
+ clean = (flags & XFS_BLI_DIRTY) ? false : true;
+ if (clean) {
+ int i;
+ for (i = 0; i < bip->bli_format_count; i++) {
+ if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
+ bip->bli_formats[i].blf_map_size)) {
+ clean = false;
+ break;
+ }
+ }
+ }
- if (!hold)
+ /*
+ * Clean buffers, by definition, cannot be in the AIL. However, aborted
+ * buffers may be dirty and hence in the AIL. Therefore if we are
+ * aborting a buffer and we've just taken the last refernce away, we
+ * have to check if it is in the AIL before freeing it. We need to free
+ * it in this case, because an aborted transaction has already shut the
+ * filesystem down and this is the last chance we will have to do so.
+ */
+ if (atomic_dec_and_test(&bip->bli_refcount)) {
+ if (clean)
+ xfs_buf_item_relse(bp);
+ else if (aborted) {
+ ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
+ if (lip->li_flags & XFS_LI_IN_AIL) {
+ spin_lock(&lip->li_ailp->xa_lock);
+ xfs_trans_ail_delete(lip->li_ailp, lip,
+ SHUTDOWN_LOG_IO_ERROR);
+ }
+ xfs_buf_item_relse(bp);
+ }
+ }
+
+ if (!(flags & XFS_BLI_HOLD))
xfs_buf_relse(bp);
}
@@ -622,6 +709,35 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
.iop_committing = xfs_buf_item_committing
};
+STATIC int
+xfs_buf_item_get_format(
+ struct xfs_buf_log_item *bip,
+ int count)
+{
+ ASSERT(bip->bli_formats == NULL);
+ bip->bli_format_count = count;
+
+ if (count == 1) {
+ bip->bli_formats = &bip->__bli_format;
+ return 0;
+ }
+
+ bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
+ KM_SLEEP);
+ if (!bip->bli_formats)
+ return ENOMEM;
+ return 0;
+}
+
+STATIC void
+xfs_buf_item_free_format(
+ struct xfs_buf_log_item *bip)
+{
+ if (bip->bli_formats != &bip->__bli_format) {
+ kmem_free(bip->bli_formats);
+ bip->bli_formats = NULL;
+ }
+}
/*
* Allocate a new buf log item to go with the given buffer.
@@ -639,6 +755,8 @@ xfs_buf_item_init(
xfs_buf_log_item_t *bip;
int chunks;
int map_size;
+ int error;
+ int i;
/*
* Check to see if there is already a buf log item for
@@ -650,39 +768,33 @@ xfs_buf_item_init(
if (lip != NULL && lip->li_type == XFS_LI_BUF)
return;
- /*
- * chunks is the number of XFS_BLF_CHUNK size pieces
- * the buffer can be divided into. Make sure not to
- * truncate any pieces. map_size is the size of the
- * bitmap needed to describe the chunks of the buffer.
- */
- chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >>
- XFS_BLF_SHIFT);
- map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT);
-
- bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone,
- KM_SLEEP);
+ bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
bip->bli_buf = bp;
xfs_buf_hold(bp);
- bip->bli_format.blf_type = XFS_LI_BUF;
- bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
- bip->bli_format.blf_len = (ushort)bp->b_length;
- bip->bli_format.blf_map_size = map_size;
-#ifdef XFS_TRANS_DEBUG
/*
- * Allocate the arrays for tracking what needs to be logged
- * and what our callers request to be logged. bli_orig
- * holds a copy of the original, clean buffer for comparison
- * against, and bli_logged keeps a 1 bit flag per byte in
- * the buffer to indicate which bytes the callers have asked
- * to have logged.
+ * chunks is the number of XFS_BLF_CHUNK size pieces the buffer
+ * can be divided into. Make sure not to truncate any pieces.
+ * map_size is the size of the bitmap needed to describe the
+ * chunks of the buffer.
+ *
+ * Discontiguous buffer support follows the layout of the underlying
+ * buffer. This makes the implementation as simple as possible.
*/
- bip->bli_orig = kmem_alloc(BBTOB(bp->b_length), KM_SLEEP);
- memcpy(bip->bli_orig, bp->b_addr, BBTOB(bp->b_length));
- bip->bli_logged = kmem_zalloc(BBTOB(bp->b_length) / NBBY, KM_SLEEP);
-#endif
+ error = xfs_buf_item_get_format(bip, bp->b_map_count);
+ ASSERT(error == 0);
+
+ for (i = 0; i < bip->bli_format_count; i++) {
+ chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
+ XFS_BLF_CHUNK);
+ map_size = DIV_ROUND_UP(chunks, NBWORD);
+
+ bip->bli_formats[i].blf_type = XFS_LI_BUF;
+ bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
+ bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
+ bip->bli_formats[i].blf_map_size = map_size;
+ }
/*
* Put the buf item into the list of items attached to the
@@ -698,11 +810,11 @@ xfs_buf_item_init(
* Mark bytes first through last inclusive as dirty in the buf
* item's bitmap.
*/
-void
-xfs_buf_item_log(
- xfs_buf_log_item_t *bip,
+static void
+xfs_buf_item_log_segment(
uint first,
- uint last)
+ uint last,
+ uint *map)
{
uint first_bit;
uint last_bit;
@@ -715,12 +827,6 @@ xfs_buf_item_log(
uint mask;
/*
- * Mark the item as having some dirty data for
- * quick reference in xfs_buf_item_dirty.
- */
- bip->bli_flags |= XFS_BLI_DIRTY;
-
- /*
* Convert byte offsets to bit numbers.
*/
first_bit = first >> XFS_BLF_SHIFT;
@@ -736,7 +842,7 @@ xfs_buf_item_log(
* to set a bit in.
*/
word_num = first_bit >> BIT_TO_WORD_SHIFT;
- wordp = &(bip->bli_format.blf_data_map[word_num]);
+ wordp = &map[word_num];
/*
* Calculate the starting bit in the first word.
@@ -779,13 +885,50 @@ xfs_buf_item_log(
mask = (1 << end_bit) - 1;
*wordp |= mask;
}
+}
- xfs_buf_item_log_debug(bip, first, last);
+/*
+ * Mark bytes first through last inclusive as dirty in the buf
+ * item's bitmap.
+ */
+void
+xfs_buf_item_log(
+ xfs_buf_log_item_t *bip,
+ uint first,
+ uint last)
+{
+ int i;
+ uint start;
+ uint end;
+ struct xfs_buf *bp = bip->bli_buf;
+
+ /*
+ * walk each buffer segment and mark them dirty appropriately.
+ */
+ start = 0;
+ for (i = 0; i < bip->bli_format_count; i++) {
+ if (start > last)
+ break;
+ end = start + BBTOB(bp->b_maps[i].bm_len);
+ if (first > end) {
+ start += BBTOB(bp->b_maps[i].bm_len);
+ continue;
+ }
+ if (first < start)
+ first = start;
+ if (end > last)
+ end = last;
+
+ xfs_buf_item_log_segment(first, end,
+ &bip->bli_formats[i].blf_data_map[0]);
+
+ start += bp->b_maps[i].bm_len;
+ }
}
/*
- * Return 1 if the buffer has some data that has been logged (at any
+ * Return 1 if the buffer has been logged or ordered in a transaction (at any
* point, not just the current transaction) and 0 if not.
*/
uint
@@ -799,11 +942,7 @@ STATIC void
xfs_buf_item_free(
xfs_buf_log_item_t *bip)
{
-#ifdef XFS_TRANS_DEBUG
- kmem_free(bip->bli_orig);
- kmem_free(bip->bli_logged);
-#endif /* XFS_TRANS_DEBUG */
-
+ xfs_buf_item_free_format(bip);
kmem_zone_free(xfs_buf_item_zone, bip);
}
@@ -818,11 +957,11 @@ void
xfs_buf_item_relse(
xfs_buf_t *bp)
{
- xfs_buf_log_item_t *bip;
+ xfs_buf_log_item_t *bip = bp->b_fspriv;
trace_xfs_buf_item_relse(bp, _RET_IP_);
+ ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL));
- bip = bp->b_fspriv;
bp->b_fspriv = bip->bli_item.li_bio_list;
if (bp->b_fspriv == NULL)
bp->b_iodone = NULL;
@@ -913,7 +1052,7 @@ xfs_buf_iodone_callbacks(
static ulong lasttime;
static xfs_buftarg_t *lasttarg;
- if (likely(!xfs_buf_geterror(bp)))
+ if (likely(!bp->b_error))
goto do_callbacks;
/*
@@ -952,9 +1091,10 @@ xfs_buf_iodone_callbacks(
xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
- if (!XFS_BUF_ISSTALE(bp)) {
- bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
- xfs_bdstrat_cb(bp);
+ if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
+ bp->b_flags |= XBF_WRITE | XBF_ASYNC |
+ XBF_DONE | XBF_WRITE_FAIL;
+ xfs_buf_iorequest(bp);
} else {
xfs_buf_relse(bp);
}
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index b6ecd2061e7..3f3455a4151 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -18,51 +18,9 @@
#ifndef __XFS_BUF_ITEM_H__
#define __XFS_BUF_ITEM_H__
-extern kmem_zone_t *xfs_buf_item_zone;
+/* kernel only definitions */
-/*
- * This is the structure used to lay out a buf log item in the
- * log. The data map describes which 128 byte chunks of the buffer
- * have been logged.
- * For 6.2 and beyond, this is XFS_LI_BUF. We use this to log everything.
- */
-typedef struct xfs_buf_log_format {
- unsigned short blf_type; /* buf log item type indicator */
- unsigned short blf_size; /* size of this item */
- ushort blf_flags; /* misc state */
- ushort blf_len; /* number of blocks in this buf */
- __int64_t blf_blkno; /* starting blkno of this buf */
- unsigned int blf_map_size; /* size of data bitmap in words */
- unsigned int blf_data_map[1];/* variable size bitmap of */
- /* regions of buffer in this item */
-} xfs_buf_log_format_t;
-
-/*
- * This flag indicates that the buffer contains on disk inodes
- * and requires special recovery handling.
- */
-#define XFS_BLF_INODE_BUF 0x1
-/*
- * This flag indicates that the buffer should not be replayed
- * during recovery because its blocks are being freed.
- */
-#define XFS_BLF_CANCEL 0x2
-/*
- * This flag indicates that the buffer contains on disk
- * user or group dquots and may require special recovery handling.
- */
-#define XFS_BLF_UDQUOT_BUF 0x4
-#define XFS_BLF_PDQUOT_BUF 0x8
-#define XFS_BLF_GDQUOT_BUF 0x10
-
-#define XFS_BLF_CHUNK 128
-#define XFS_BLF_SHIFT 7
-#define BIT_TO_WORD_SHIFT 5
-#define NBWORD (NBBY * sizeof(unsigned int))
-
-/*
- * buf log item flags
- */
+/* buf log item flags */
#define XFS_BLI_HOLD 0x01
#define XFS_BLI_DIRTY 0x02
#define XFS_BLI_STALE 0x04
@@ -70,6 +28,7 @@ typedef struct xfs_buf_log_format {
#define XFS_BLI_INODE_ALLOC_BUF 0x10
#define XFS_BLI_STALE_INODE 0x20
#define XFS_BLI_INODE_BUF 0x40
+#define XFS_BLI_ORDERED 0x80
#define XFS_BLI_FLAGS \
{ XFS_BLI_HOLD, "HOLD" }, \
@@ -78,10 +37,9 @@ typedef struct xfs_buf_log_format {
{ XFS_BLI_LOGGED, "LOGGED" }, \
{ XFS_BLI_INODE_ALLOC_BUF, "INODE_ALLOC" }, \
{ XFS_BLI_STALE_INODE, "STALE_INODE" }, \
- { XFS_BLI_INODE_BUF, "INODE_BUF" }
-
+ { XFS_BLI_INODE_BUF, "INODE_BUF" }, \
+ { XFS_BLI_ORDERED, "ORDERED" }
-#ifdef __KERNEL__
struct xfs_buf;
struct xfs_mount;
@@ -98,11 +56,9 @@ typedef struct xfs_buf_log_item {
unsigned int bli_flags; /* misc flags */
unsigned int bli_recur; /* lock recursion count */
atomic_t bli_refcount; /* cnt of tp refs */
-#ifdef XFS_TRANS_DEBUG
- char *bli_orig; /* original buffer copy */
- char *bli_logged; /* bytes logged (bitmap) */
-#endif
- xfs_buf_log_format_t bli_format; /* in-log header */
+ int bli_format_count; /* count of headers */
+ struct xfs_buf_log_format *bli_formats; /* array of in-log header ptrs */
+ struct xfs_buf_log_format __bli_format; /* embedded in-log header */
} xfs_buf_log_item_t;
void xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
@@ -115,16 +71,6 @@ void xfs_buf_attach_iodone(struct xfs_buf *,
void xfs_buf_iodone_callbacks(struct xfs_buf *);
void xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
-#ifdef XFS_TRANS_DEBUG
-void
-xfs_buf_item_flush_log_debug(
- struct xfs_buf *bp,
- uint first,
- uint last);
-#else
-#define xfs_buf_item_flush_log_debug(bp, first, last)
-#endif
-
-#endif /* __KERNEL__ */
+extern kmem_zone_t *xfs_buf_item_zone;
#endif /* __XFS_BUF_ITEM_H__ */
diff --git a/fs/xfs/xfs_cksum.h b/fs/xfs/xfs_cksum.h
new file mode 100644
index 00000000000..fad1676ad8c
--- /dev/null
+++ b/fs/xfs/xfs_cksum.h
@@ -0,0 +1,63 @@
+#ifndef _XFS_CKSUM_H
+#define _XFS_CKSUM_H 1
+
+#define XFS_CRC_SEED (~(__uint32_t)0)
+
+/*
+ * Calculate the intermediate checksum for a buffer that has the CRC field
+ * inside it. The offset of the 32bit crc fields is passed as the
+ * cksum_offset parameter.
+ */
+static inline __uint32_t
+xfs_start_cksum(char *buffer, size_t length, unsigned long cksum_offset)
+{
+ __uint32_t zero = 0;
+ __uint32_t crc;
+
+ /* Calculate CRC up to the checksum. */
+ crc = crc32c(XFS_CRC_SEED, buffer, cksum_offset);
+
+ /* Skip checksum field */
+ crc = crc32c(crc, &zero, sizeof(__u32));
+
+ /* Calculate the rest of the CRC. */
+ return crc32c(crc, &buffer[cksum_offset + sizeof(__be32)],
+ length - (cksum_offset + sizeof(__be32)));
+}
+
+/*
+ * Convert the intermediate checksum to the final ondisk format.
+ *
+ * The CRC32c calculation uses LE format even on BE machines, but returns the
+ * result in host endian format. Hence we need to byte swap it back to LE format
+ * so that it is consistent on disk.
+ */
+static inline __le32
+xfs_end_cksum(__uint32_t crc)
+{
+ return ~cpu_to_le32(crc);
+}
+
+/*
+ * Helper to generate the checksum for a buffer.
+ */
+static inline void
+xfs_update_cksum(char *buffer, size_t length, unsigned long cksum_offset)
+{
+ __uint32_t crc = xfs_start_cksum(buffer, length, cksum_offset);
+
+ *(__le32 *)(buffer + cksum_offset) = xfs_end_cksum(crc);
+}
+
+/*
+ * Helper to verify the checksum for a buffer.
+ */
+static inline int
+xfs_verify_cksum(char *buffer, size_t length, unsigned long cksum_offset)
+{
+ __uint32_t crc = xfs_start_cksum(buffer, length, cksum_offset);
+
+ return *(__le32 *)(buffer + cksum_offset) == xfs_end_cksum(crc);
+}
+
+#endif /* _XFS_CKSUM_H */
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 015b946c580..a514ab61665 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -17,20 +18,20 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
#include "xfs_dir2.h"
-#include "xfs_dir2_format.h"
#include "xfs_dir2_priv.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
@@ -38,6 +39,8 @@
#include "xfs_attr_leaf.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_cksum.h"
+#include "xfs_buf_item.h"
/*
* xfs_da_btree.c
@@ -52,44 +55,237 @@
/*
* Routines used for growing the Btree.
*/
-STATIC int xfs_da_root_split(xfs_da_state_t *state,
+STATIC int xfs_da3_root_split(xfs_da_state_t *state,
xfs_da_state_blk_t *existing_root,
xfs_da_state_blk_t *new_child);
-STATIC int xfs_da_node_split(xfs_da_state_t *state,
+STATIC int xfs_da3_node_split(xfs_da_state_t *state,
xfs_da_state_blk_t *existing_blk,
xfs_da_state_blk_t *split_blk,
xfs_da_state_blk_t *blk_to_add,
int treelevel,
int *result);
-STATIC void xfs_da_node_rebalance(xfs_da_state_t *state,
+STATIC void xfs_da3_node_rebalance(xfs_da_state_t *state,
xfs_da_state_blk_t *node_blk_1,
xfs_da_state_blk_t *node_blk_2);
-STATIC void xfs_da_node_add(xfs_da_state_t *state,
+STATIC void xfs_da3_node_add(xfs_da_state_t *state,
xfs_da_state_blk_t *old_node_blk,
xfs_da_state_blk_t *new_node_blk);
/*
* Routines used for shrinking the Btree.
*/
-STATIC int xfs_da_root_join(xfs_da_state_t *state,
+STATIC int xfs_da3_root_join(xfs_da_state_t *state,
xfs_da_state_blk_t *root_blk);
-STATIC int xfs_da_node_toosmall(xfs_da_state_t *state, int *retval);
-STATIC void xfs_da_node_remove(xfs_da_state_t *state,
+STATIC int xfs_da3_node_toosmall(xfs_da_state_t *state, int *retval);
+STATIC void xfs_da3_node_remove(xfs_da_state_t *state,
xfs_da_state_blk_t *drop_blk);
-STATIC void xfs_da_node_unbalance(xfs_da_state_t *state,
+STATIC void xfs_da3_node_unbalance(xfs_da_state_t *state,
xfs_da_state_blk_t *src_node_blk,
xfs_da_state_blk_t *dst_node_blk);
/*
* Utility routines.
*/
-STATIC uint xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count);
-STATIC int xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp);
-STATIC xfs_dabuf_t *xfs_da_buf_make(int nbuf, xfs_buf_t **bps);
-STATIC int xfs_da_blk_unlink(xfs_da_state_t *state,
+STATIC int xfs_da3_blk_unlink(xfs_da_state_t *state,
xfs_da_state_blk_t *drop_blk,
xfs_da_state_blk_t *save_blk);
-STATIC void xfs_da_state_kill_altpath(xfs_da_state_t *state);
+
+
+kmem_zone_t *xfs_da_state_zone; /* anchor for state struct zone */
+
+/*
+ * Allocate a dir-state structure.
+ * We don't put them on the stack since they're large.
+ */
+xfs_da_state_t *
+xfs_da_state_alloc(void)
+{
+ return kmem_zone_zalloc(xfs_da_state_zone, KM_NOFS);
+}
+
+/*
+ * Kill the altpath contents of a da-state structure.
+ */
+STATIC void
+xfs_da_state_kill_altpath(xfs_da_state_t *state)
+{
+ int i;
+
+ for (i = 0; i < state->altpath.active; i++)
+ state->altpath.blk[i].bp = NULL;
+ state->altpath.active = 0;
+}
+
+/*
+ * Free a da-state structure.
+ */
+void
+xfs_da_state_free(xfs_da_state_t *state)
+{
+ xfs_da_state_kill_altpath(state);
+#ifdef DEBUG
+ memset((char *)state, 0, sizeof(*state));
+#endif /* DEBUG */
+ kmem_zone_free(xfs_da_state_zone, state);
+}
+
+static bool
+xfs_da3_node_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_da_intnode *hdr = bp->b_addr;
+ struct xfs_da3_icnode_hdr ichdr;
+ const struct xfs_dir_ops *ops;
+
+ ops = xfs_dir_get_ops(mp, NULL);
+
+ ops->node_hdr_from_disk(&ichdr, hdr);
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_da3_node_hdr *hdr3 = bp->b_addr;
+
+ if (ichdr.magic != XFS_DA3_NODE_MAGIC)
+ return false;
+
+ if (!uuid_equal(&hdr3->info.uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(hdr3->info.blkno) != bp->b_bn)
+ return false;
+ } else {
+ if (ichdr.magic != XFS_DA_NODE_MAGIC)
+ return false;
+ }
+ if (ichdr.level == 0)
+ return false;
+ if (ichdr.level > XFS_DA_NODE_MAXDEPTH)
+ return false;
+ if (ichdr.count == 0)
+ return false;
+
+ /*
+ * we don't know if the node is for and attribute or directory tree,
+ * so only fail if the count is outside both bounds
+ */
+ if (ichdr.count > mp->m_dir_geo->node_ents &&
+ ichdr.count > mp->m_attr_geo->node_ents)
+ return false;
+
+ /* XXX: hash order check? */
+
+ return true;
+}
+
+static void
+xfs_da3_node_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+ struct xfs_da3_node_hdr *hdr3 = bp->b_addr;
+
+ if (!xfs_da3_node_verify(bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (bip)
+ hdr3->info.lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_DA3_NODE_CRC_OFF);
+}
+
+/*
+ * leaf/node format detection on trees is sketchy, so a node read can be done on
+ * leaf level blocks when detection identifies the tree as a node format tree
+ * incorrectly. In this case, we need to swap the verifier to match the correct
+ * format of the block being read.
+ */
+static void
+xfs_da3_node_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_da_blkinfo *info = bp->b_addr;
+
+ switch (be16_to_cpu(info->magic)) {
+ case XFS_DA3_NODE_MAGIC:
+ if (!xfs_buf_verify_cksum(bp, XFS_DA3_NODE_CRC_OFF)) {
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ break;
+ }
+ /* fall through */
+ case XFS_DA_NODE_MAGIC:
+ if (!xfs_da3_node_verify(bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ break;
+ }
+ return;
+ case XFS_ATTR_LEAF_MAGIC:
+ case XFS_ATTR3_LEAF_MAGIC:
+ bp->b_ops = &xfs_attr3_leaf_buf_ops;
+ bp->b_ops->verify_read(bp);
+ return;
+ case XFS_DIR2_LEAFN_MAGIC:
+ case XFS_DIR3_LEAFN_MAGIC:
+ bp->b_ops = &xfs_dir3_leafn_buf_ops;
+ bp->b_ops->verify_read(bp);
+ return;
+ default:
+ break;
+ }
+
+ /* corrupt block */
+ xfs_verifier_error(bp);
+}
+
+const struct xfs_buf_ops xfs_da3_node_buf_ops = {
+ .verify_read = xfs_da3_node_read_verify,
+ .verify_write = xfs_da3_node_write_verify,
+};
+
+int
+xfs_da3_node_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
+ xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp,
+ int which_fork)
+{
+ int err;
+
+ err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
+ which_fork, &xfs_da3_node_buf_ops);
+ if (!err && tp) {
+ struct xfs_da_blkinfo *info = (*bpp)->b_addr;
+ int type;
+
+ switch (be16_to_cpu(info->magic)) {
+ case XFS_DA_NODE_MAGIC:
+ case XFS_DA3_NODE_MAGIC:
+ type = XFS_BLFT_DA_NODE_BUF;
+ break;
+ case XFS_ATTR_LEAF_MAGIC:
+ case XFS_ATTR3_LEAF_MAGIC:
+ type = XFS_BLFT_ATTR_LEAF_BUF;
+ break;
+ case XFS_DIR2_LEAFN_MAGIC:
+ case XFS_DIR3_LEAFN_MAGIC:
+ type = XFS_BLFT_DIR_LEAFN_BUF;
+ break;
+ default:
+ type = 0;
+ ASSERT(0);
+ break;
+ }
+ xfs_trans_buf_set_type(tp, *bpp, type);
+ }
+ return err;
+}
/*========================================================================
* Routines used for growing the Btree.
@@ -99,31 +295,46 @@ STATIC void xfs_da_state_kill_altpath(xfs_da_state_t *state);
* Create the initial contents of an intermediate node.
*/
int
-xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
- xfs_dabuf_t **bpp, int whichfork)
+xfs_da3_node_create(
+ struct xfs_da_args *args,
+ xfs_dablk_t blkno,
+ int level,
+ struct xfs_buf **bpp,
+ int whichfork)
{
- xfs_da_intnode_t *node;
- xfs_dabuf_t *bp;
- int error;
- xfs_trans_t *tp;
+ struct xfs_da_intnode *node;
+ struct xfs_trans *tp = args->trans;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_da3_icnode_hdr ichdr = {0};
+ struct xfs_buf *bp;
+ int error;
+ struct xfs_inode *dp = args->dp;
trace_xfs_da_node_create(args);
+ ASSERT(level <= XFS_DA_NODE_MAXDEPTH);
- tp = args->trans;
- error = xfs_da_get_buf(tp, args->dp, blkno, -1, &bp, whichfork);
+ error = xfs_da_get_buf(tp, dp, blkno, -1, &bp, whichfork);
if (error)
return(error);
- ASSERT(bp != NULL);
- node = bp->data;
- node->hdr.info.forw = 0;
- node->hdr.info.back = 0;
- node->hdr.info.magic = cpu_to_be16(XFS_DA_NODE_MAGIC);
- node->hdr.info.pad = 0;
- node->hdr.count = 0;
- node->hdr.level = cpu_to_be16(level);
-
- xfs_da_log_buf(tp, bp,
- XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
+ bp->b_ops = &xfs_da3_node_buf_ops;
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DA_NODE_BUF);
+ node = bp->b_addr;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_da3_node_hdr *hdr3 = bp->b_addr;
+
+ ichdr.magic = XFS_DA3_NODE_MAGIC;
+ hdr3->info.blkno = cpu_to_be64(bp->b_bn);
+ hdr3->info.owner = cpu_to_be64(args->dp->i_ino);
+ uuid_copy(&hdr3->info.uuid, &mp->m_sb.sb_uuid);
+ } else {
+ ichdr.magic = XFS_DA_NODE_MAGIC;
+ }
+ ichdr.level = level;
+
+ dp->d_ops->node_hdr_to_disk(node, &ichdr);
+ xfs_trans_log_buf(tp, bp,
+ XFS_DA_LOGRANGE(node, &node->hdr, dp->d_ops->node_hdr_size));
*bpp = bp;
return(0);
@@ -134,12 +345,18 @@ xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
* intermediate nodes, rebalance, etc.
*/
int /* error */
-xfs_da_split(xfs_da_state_t *state)
+xfs_da3_split(
+ struct xfs_da_state *state)
{
- xfs_da_state_blk_t *oldblk, *newblk, *addblk;
- xfs_da_intnode_t *node;
- xfs_dabuf_t *bp;
- int max, action, error, i;
+ struct xfs_da_state_blk *oldblk;
+ struct xfs_da_state_blk *newblk;
+ struct xfs_da_state_blk *addblk;
+ struct xfs_da_intnode *node;
+ struct xfs_buf *bp;
+ int max;
+ int action = 0;
+ int error;
+ int i;
trace_xfs_da_split(state->args);
@@ -167,7 +384,7 @@ xfs_da_split(xfs_da_state_t *state)
*/
switch (oldblk->magic) {
case XFS_ATTR_LEAF_MAGIC:
- error = xfs_attr_leaf_split(state, oldblk, newblk);
+ error = xfs_attr3_leaf_split(state, oldblk, newblk);
if ((error != 0) && (error != ENOSPC)) {
return(error); /* GROT: attr is inconsistent */
}
@@ -182,12 +399,12 @@ xfs_da_split(xfs_da_state_t *state)
if (state->inleaf) {
state->extraafter = 0; /* before newblk */
trace_xfs_attr_leaf_split_before(state->args);
- error = xfs_attr_leaf_split(state, oldblk,
+ error = xfs_attr3_leaf_split(state, oldblk,
&state->extrablk);
} else {
state->extraafter = 1; /* after newblk */
trace_xfs_attr_leaf_split_after(state->args);
- error = xfs_attr_leaf_split(state, newblk,
+ error = xfs_attr3_leaf_split(state, newblk,
&state->extrablk);
}
if (error)
@@ -201,9 +418,8 @@ xfs_da_split(xfs_da_state_t *state)
addblk = newblk;
break;
case XFS_DA_NODE_MAGIC:
- error = xfs_da_node_split(state, oldblk, newblk, addblk,
+ error = xfs_da3_node_split(state, oldblk, newblk, addblk,
max - i, &action);
- xfs_da_buf_done(addblk->bp);
addblk->bp = NULL;
if (error)
return(error); /* GROT: dir is inconsistent */
@@ -220,14 +436,7 @@ xfs_da_split(xfs_da_state_t *state)
/*
* Update the btree to show the new hashval for this child.
*/
- xfs_da_fixhashpath(state, &state->path);
- /*
- * If we won't need this block again, it's getting dropped
- * from the active path by the loop control, so we need
- * to mark it done now.
- */
- if (i > 0 || !addblk)
- xfs_da_buf_done(oldblk->bp);
+ xfs_da3_fixhashpath(state, &state->path);
}
if (!addblk)
return(0);
@@ -237,10 +446,8 @@ xfs_da_split(xfs_da_state_t *state)
*/
ASSERT(state->path.active == 0);
oldblk = &state->path.blk[0];
- error = xfs_da_root_split(state, oldblk, addblk);
+ error = xfs_da3_root_split(state, oldblk, addblk);
if (error) {
- xfs_da_buf_done(oldblk->bp);
- xfs_da_buf_done(addblk->bp);
addblk->bp = NULL;
return(error); /* GROT: dir is inconsistent */
}
@@ -250,9 +457,13 @@ xfs_da_split(xfs_da_state_t *state)
* just got bumped because of the addition of a new root node.
* There might be three blocks involved if a double split occurred,
* and the original block 0 could be at any position in the list.
+ *
+ * Note: the magic numbers and sibling pointers are in the same
+ * physical place for both v2 and v3 headers (by design). Hence it
+ * doesn't matter which version of the xfs_da_intnode structure we use
+ * here as the result will be the same using either structure.
*/
-
- node = oldblk->bp->data;
+ node = oldblk->bp->b_addr;
if (node->hdr.info.forw) {
if (be32_to_cpu(node->hdr.info.forw) == addblk->blkno) {
bp = addblk->bp;
@@ -260,13 +471,13 @@ xfs_da_split(xfs_da_state_t *state)
ASSERT(state->extravalid);
bp = state->extrablk.bp;
}
- node = bp->data;
+ node = bp->b_addr;
node->hdr.info.back = cpu_to_be32(oldblk->blkno);
- xfs_da_log_buf(state->args->trans, bp,
+ xfs_trans_log_buf(state->args->trans, bp,
XFS_DA_LOGRANGE(node, &node->hdr.info,
sizeof(node->hdr.info)));
}
- node = oldblk->bp->data;
+ node = oldblk->bp->b_addr;
if (node->hdr.info.back) {
if (be32_to_cpu(node->hdr.info.back) == addblk->blkno) {
bp = addblk->bp;
@@ -274,14 +485,12 @@ xfs_da_split(xfs_da_state_t *state)
ASSERT(state->extravalid);
bp = state->extrablk.bp;
}
- node = bp->data;
+ node = bp->b_addr;
node->hdr.info.forw = cpu_to_be32(oldblk->blkno);
- xfs_da_log_buf(state->args->trans, bp,
+ xfs_trans_log_buf(state->args->trans, bp,
XFS_DA_LOGRANGE(node, &node->hdr.info,
sizeof(node->hdr.info)));
}
- xfs_da_buf_done(oldblk->bp);
- xfs_da_buf_done(addblk->bp);
addblk->bp = NULL;
return(0);
}
@@ -292,18 +501,25 @@ xfs_da_split(xfs_da_state_t *state)
* the EOF, extending the inode in process.
*/
STATIC int /* error */
-xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
- xfs_da_state_blk_t *blk2)
+xfs_da3_root_split(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *blk1,
+ struct xfs_da_state_blk *blk2)
{
- xfs_da_intnode_t *node, *oldroot;
- xfs_da_args_t *args;
- xfs_dablk_t blkno;
- xfs_dabuf_t *bp;
- int error, size;
- xfs_inode_t *dp;
- xfs_trans_t *tp;
- xfs_mount_t *mp;
- xfs_dir2_leaf_t *leaf;
+ struct xfs_da_intnode *node;
+ struct xfs_da_intnode *oldroot;
+ struct xfs_da_node_entry *btree;
+ struct xfs_da3_icnode_hdr nodehdr;
+ struct xfs_da_args *args;
+ struct xfs_buf *bp;
+ struct xfs_inode *dp;
+ struct xfs_trans *tp;
+ struct xfs_mount *mp;
+ struct xfs_dir2_leaf *leaf;
+ xfs_dablk_t blkno;
+ int level;
+ int error;
+ int size;
trace_xfs_da_root_split(state->args);
@@ -312,85 +528,132 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* to a free space somewhere.
*/
args = state->args;
- ASSERT(args != NULL);
error = xfs_da_grow_inode(args, &blkno);
if (error)
- return(error);
+ return error;
+
dp = args->dp;
tp = args->trans;
mp = state->mp;
error = xfs_da_get_buf(tp, dp, blkno, -1, &bp, args->whichfork);
if (error)
- return(error);
- ASSERT(bp != NULL);
- node = bp->data;
- oldroot = blk1->bp->data;
- if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
- size = (int)((char *)&oldroot->btree[be16_to_cpu(oldroot->hdr.count)] -
- (char *)oldroot);
+ return error;
+ node = bp->b_addr;
+ oldroot = blk1->bp->b_addr;
+ if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC) ||
+ oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) {
+ struct xfs_da3_icnode_hdr nodehdr;
+
+ dp->d_ops->node_hdr_from_disk(&nodehdr, oldroot);
+ btree = dp->d_ops->node_tree_p(oldroot);
+ size = (int)((char *)&btree[nodehdr.count] - (char *)oldroot);
+ level = nodehdr.level;
+
+ /*
+ * we are about to copy oldroot to bp, so set up the type
+ * of bp while we know exactly what it will be.
+ */
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DA_NODE_BUF);
} else {
- ASSERT(oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
+ struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_dir2_leaf_entry *ents;
+
leaf = (xfs_dir2_leaf_t *)oldroot;
- size = (int)((char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] -
- (char *)leaf);
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+
+ ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
+ leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
+ size = (int)((char *)&ents[leafhdr.count] - (char *)leaf);
+ level = 0;
+
+ /*
+ * we are about to copy oldroot to bp, so set up the type
+ * of bp while we know exactly what it will be.
+ */
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAFN_BUF);
}
+
+ /*
+ * we can copy most of the information in the node from one block to
+ * another, but for CRC enabled headers we have to make sure that the
+ * block specific identifiers are kept intact. We update the buffer
+ * directly for this.
+ */
memcpy(node, oldroot, size);
- xfs_da_log_buf(tp, bp, 0, size - 1);
- xfs_da_buf_done(blk1->bp);
+ if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC) ||
+ oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
+ struct xfs_da3_intnode *node3 = (struct xfs_da3_intnode *)node;
+
+ node3->hdr.info.blkno = cpu_to_be64(bp->b_bn);
+ }
+ xfs_trans_log_buf(tp, bp, 0, size - 1);
+
+ bp->b_ops = blk1->bp->b_ops;
+ xfs_trans_buf_copy_type(bp, blk1->bp);
blk1->bp = bp;
blk1->blkno = blkno;
/*
* Set up the new root node.
*/
- error = xfs_da_node_create(args,
- (args->whichfork == XFS_DATA_FORK) ? mp->m_dirleafblk : 0,
- be16_to_cpu(node->hdr.level) + 1, &bp, args->whichfork);
+ error = xfs_da3_node_create(args,
+ (args->whichfork == XFS_DATA_FORK) ? args->geo->leafblk : 0,
+ level + 1, &bp, args->whichfork);
if (error)
- return(error);
- node = bp->data;
- node->btree[0].hashval = cpu_to_be32(blk1->hashval);
- node->btree[0].before = cpu_to_be32(blk1->blkno);
- node->btree[1].hashval = cpu_to_be32(blk2->hashval);
- node->btree[1].before = cpu_to_be32(blk2->blkno);
- node->hdr.count = cpu_to_be16(2);
+ return error;
+
+ node = bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
+ btree[0].hashval = cpu_to_be32(blk1->hashval);
+ btree[0].before = cpu_to_be32(blk1->blkno);
+ btree[1].hashval = cpu_to_be32(blk2->hashval);
+ btree[1].before = cpu_to_be32(blk2->blkno);
+ nodehdr.count = 2;
+ dp->d_ops->node_hdr_to_disk(node, &nodehdr);
#ifdef DEBUG
- if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)) {
- ASSERT(blk1->blkno >= mp->m_dirleafblk &&
- blk1->blkno < mp->m_dirfreeblk);
- ASSERT(blk2->blkno >= mp->m_dirleafblk &&
- blk2->blkno < mp->m_dirfreeblk);
+ if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
+ oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
+ ASSERT(blk1->blkno >= args->geo->leafblk &&
+ blk1->blkno < args->geo->freeblk);
+ ASSERT(blk2->blkno >= args->geo->leafblk &&
+ blk2->blkno < args->geo->freeblk);
}
#endif
/* Header is already logged by xfs_da_node_create */
- xfs_da_log_buf(tp, bp,
- XFS_DA_LOGRANGE(node, node->btree,
- sizeof(xfs_da_node_entry_t) * 2));
- xfs_da_buf_done(bp);
+ xfs_trans_log_buf(tp, bp,
+ XFS_DA_LOGRANGE(node, btree, sizeof(xfs_da_node_entry_t) * 2));
- return(0);
+ return 0;
}
/*
* Split the node, rebalance, then add the new entry.
*/
STATIC int /* error */
-xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
- xfs_da_state_blk_t *newblk,
- xfs_da_state_blk_t *addblk,
- int treelevel, int *result)
+xfs_da3_node_split(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *oldblk,
+ struct xfs_da_state_blk *newblk,
+ struct xfs_da_state_blk *addblk,
+ int treelevel,
+ int *result)
{
- xfs_da_intnode_t *node;
- xfs_dablk_t blkno;
- int newcount, error;
- int useextra;
+ struct xfs_da_intnode *node;
+ struct xfs_da3_icnode_hdr nodehdr;
+ xfs_dablk_t blkno;
+ int newcount;
+ int error;
+ int useextra;
+ struct xfs_inode *dp = state->args->dp;
trace_xfs_da_node_split(state->args);
- node = oldblk->bp->data;
- ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
+ node = oldblk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
/*
* With V2 dirs the extra block is data or freespace.
@@ -400,7 +663,7 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
/*
* Do we have to split the node?
*/
- if ((be16_to_cpu(node->hdr.count) + newcount) > state->node_ents) {
+ if (nodehdr.count + newcount > state->args->geo->node_ents) {
/*
* Allocate a new node, add to the doubly linked chain of
* nodes, then move some of our excess entries into it.
@@ -409,14 +672,14 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
if (error)
return(error); /* GROT: dir is inconsistent */
- error = xfs_da_node_create(state->args, blkno, treelevel,
+ error = xfs_da3_node_create(state->args, blkno, treelevel,
&newblk->bp, state->args->whichfork);
if (error)
return(error); /* GROT: dir is inconsistent */
newblk->blkno = blkno;
newblk->magic = XFS_DA_NODE_MAGIC;
- xfs_da_node_rebalance(state, oldblk, newblk);
- error = xfs_da_blk_link(state, oldblk, newblk);
+ xfs_da3_node_rebalance(state, oldblk, newblk);
+ error = xfs_da3_blk_link(state, oldblk, newblk);
if (error)
return(error);
*result = 1;
@@ -428,7 +691,7 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
* Insert the new entry(s) into the correct block
* (updating last hashval in the process).
*
- * xfs_da_node_add() inserts BEFORE the given index,
+ * xfs_da3_node_add() inserts BEFORE the given index,
* and as a result of using node_lookup_int() we always
* point to a valid entry (not after one), but a split
* operation always results in a new block whose hashvals
@@ -436,23 +699,24 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
*
* If we had double-split op below us, then add the extra block too.
*/
- node = oldblk->bp->data;
- if (oldblk->index <= be16_to_cpu(node->hdr.count)) {
+ node = oldblk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ if (oldblk->index <= nodehdr.count) {
oldblk->index++;
- xfs_da_node_add(state, oldblk, addblk);
+ xfs_da3_node_add(state, oldblk, addblk);
if (useextra) {
if (state->extraafter)
oldblk->index++;
- xfs_da_node_add(state, oldblk, &state->extrablk);
+ xfs_da3_node_add(state, oldblk, &state->extrablk);
state->extravalid = 0;
}
} else {
newblk->index++;
- xfs_da_node_add(state, newblk, addblk);
+ xfs_da3_node_add(state, newblk, addblk);
if (useextra) {
if (state->extraafter)
newblk->index++;
- xfs_da_node_add(state, newblk, &state->extrablk);
+ xfs_da3_node_add(state, newblk, &state->extrablk);
state->extravalid = 0;
}
}
@@ -467,33 +731,54 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
* NOTE: if blk2 is empty, then it will get the upper half of blk1.
*/
STATIC void
-xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
- xfs_da_state_blk_t *blk2)
+xfs_da3_node_rebalance(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *blk1,
+ struct xfs_da_state_blk *blk2)
{
- xfs_da_intnode_t *node1, *node2, *tmpnode;
- xfs_da_node_entry_t *btree_s, *btree_d;
- int count, tmp;
- xfs_trans_t *tp;
+ struct xfs_da_intnode *node1;
+ struct xfs_da_intnode *node2;
+ struct xfs_da_intnode *tmpnode;
+ struct xfs_da_node_entry *btree1;
+ struct xfs_da_node_entry *btree2;
+ struct xfs_da_node_entry *btree_s;
+ struct xfs_da_node_entry *btree_d;
+ struct xfs_da3_icnode_hdr nodehdr1;
+ struct xfs_da3_icnode_hdr nodehdr2;
+ struct xfs_trans *tp;
+ int count;
+ int tmp;
+ int swap = 0;
+ struct xfs_inode *dp = state->args->dp;
trace_xfs_da_node_rebalance(state->args);
- node1 = blk1->bp->data;
- node2 = blk2->bp->data;
+ node1 = blk1->bp->b_addr;
+ node2 = blk2->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr1, node1);
+ dp->d_ops->node_hdr_from_disk(&nodehdr2, node2);
+ btree1 = dp->d_ops->node_tree_p(node1);
+ btree2 = dp->d_ops->node_tree_p(node2);
+
/*
* Figure out how many entries need to move, and in which direction.
* Swap the nodes around if that makes it simpler.
*/
- if ((be16_to_cpu(node1->hdr.count) > 0) && (be16_to_cpu(node2->hdr.count) > 0) &&
- ((be32_to_cpu(node2->btree[0].hashval) < be32_to_cpu(node1->btree[0].hashval)) ||
- (be32_to_cpu(node2->btree[be16_to_cpu(node2->hdr.count)-1].hashval) <
- be32_to_cpu(node1->btree[be16_to_cpu(node1->hdr.count)-1].hashval)))) {
+ if (nodehdr1.count > 0 && nodehdr2.count > 0 &&
+ ((be32_to_cpu(btree2[0].hashval) < be32_to_cpu(btree1[0].hashval)) ||
+ (be32_to_cpu(btree2[nodehdr2.count - 1].hashval) <
+ be32_to_cpu(btree1[nodehdr1.count - 1].hashval)))) {
tmpnode = node1;
node1 = node2;
node2 = tmpnode;
+ dp->d_ops->node_hdr_from_disk(&nodehdr1, node1);
+ dp->d_ops->node_hdr_from_disk(&nodehdr2, node2);
+ btree1 = dp->d_ops->node_tree_p(node1);
+ btree2 = dp->d_ops->node_tree_p(node2);
+ swap = 1;
}
- ASSERT(node1->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- ASSERT(node2->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- count = (be16_to_cpu(node1->hdr.count) - be16_to_cpu(node2->hdr.count)) / 2;
+
+ count = (nodehdr1.count - nodehdr2.count) / 2;
if (count == 0)
return;
tp = state->args->trans;
@@ -504,10 +789,11 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
/*
* Move elements in node2 up to make a hole.
*/
- if ((tmp = be16_to_cpu(node2->hdr.count)) > 0) {
+ tmp = nodehdr2.count;
+ if (tmp > 0) {
tmp *= (uint)sizeof(xfs_da_node_entry_t);
- btree_s = &node2->btree[0];
- btree_d = &node2->btree[count];
+ btree_s = &btree2[0];
+ btree_d = &btree2[count];
memmove(btree_d, btree_s, tmp);
}
@@ -515,12 +801,12 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* Move the req'd B-tree elements from high in node1 to
* low in node2.
*/
- be16_add_cpu(&node2->hdr.count, count);
+ nodehdr2.count += count;
tmp = count * (uint)sizeof(xfs_da_node_entry_t);
- btree_s = &node1->btree[be16_to_cpu(node1->hdr.count) - count];
- btree_d = &node2->btree[0];
+ btree_s = &btree1[nodehdr1.count - count];
+ btree_d = &btree2[0];
memcpy(btree_d, btree_s, tmp);
- be16_add_cpu(&node1->hdr.count, -count);
+ nodehdr1.count -= count;
} else {
/*
* Move the req'd B-tree elements from low in node2 to
@@ -528,49 +814,59 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
*/
count = -count;
tmp = count * (uint)sizeof(xfs_da_node_entry_t);
- btree_s = &node2->btree[0];
- btree_d = &node1->btree[be16_to_cpu(node1->hdr.count)];
+ btree_s = &btree2[0];
+ btree_d = &btree1[nodehdr1.count];
memcpy(btree_d, btree_s, tmp);
- be16_add_cpu(&node1->hdr.count, count);
- xfs_da_log_buf(tp, blk1->bp,
+ nodehdr1.count += count;
+
+ xfs_trans_log_buf(tp, blk1->bp,
XFS_DA_LOGRANGE(node1, btree_d, tmp));
/*
* Move elements in node2 down to fill the hole.
*/
- tmp = be16_to_cpu(node2->hdr.count) - count;
+ tmp = nodehdr2.count - count;
tmp *= (uint)sizeof(xfs_da_node_entry_t);
- btree_s = &node2->btree[count];
- btree_d = &node2->btree[0];
+ btree_s = &btree2[count];
+ btree_d = &btree2[0];
memmove(btree_d, btree_s, tmp);
- be16_add_cpu(&node2->hdr.count, -count);
+ nodehdr2.count -= count;
}
/*
* Log header of node 1 and all current bits of node 2.
*/
- xfs_da_log_buf(tp, blk1->bp,
- XFS_DA_LOGRANGE(node1, &node1->hdr, sizeof(node1->hdr)));
- xfs_da_log_buf(tp, blk2->bp,
+ dp->d_ops->node_hdr_to_disk(node1, &nodehdr1);
+ xfs_trans_log_buf(tp, blk1->bp,
+ XFS_DA_LOGRANGE(node1, &node1->hdr, dp->d_ops->node_hdr_size));
+
+ dp->d_ops->node_hdr_to_disk(node2, &nodehdr2);
+ xfs_trans_log_buf(tp, blk2->bp,
XFS_DA_LOGRANGE(node2, &node2->hdr,
- sizeof(node2->hdr) +
- sizeof(node2->btree[0]) * be16_to_cpu(node2->hdr.count)));
+ dp->d_ops->node_hdr_size +
+ (sizeof(btree2[0]) * nodehdr2.count)));
/*
* Record the last hashval from each block for upward propagation.
* (note: don't use the swapped node pointers)
*/
- node1 = blk1->bp->data;
- node2 = blk2->bp->data;
- blk1->hashval = be32_to_cpu(node1->btree[be16_to_cpu(node1->hdr.count)-1].hashval);
- blk2->hashval = be32_to_cpu(node2->btree[be16_to_cpu(node2->hdr.count)-1].hashval);
+ if (swap) {
+ node1 = blk1->bp->b_addr;
+ node2 = blk2->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr1, node1);
+ dp->d_ops->node_hdr_from_disk(&nodehdr2, node2);
+ btree1 = dp->d_ops->node_tree_p(node1);
+ btree2 = dp->d_ops->node_tree_p(node2);
+ }
+ blk1->hashval = be32_to_cpu(btree1[nodehdr1.count - 1].hashval);
+ blk2->hashval = be32_to_cpu(btree2[nodehdr2.count - 1].hashval);
/*
* Adjust the expected index for insertion.
*/
- if (blk1->index >= be16_to_cpu(node1->hdr.count)) {
- blk2->index = blk1->index - be16_to_cpu(node1->hdr.count);
- blk1->index = be16_to_cpu(node1->hdr.count) + 1; /* make it invalid */
+ if (blk1->index >= nodehdr1.count) {
+ blk2->index = blk1->index - nodehdr1.count;
+ blk1->index = nodehdr1.count + 1; /* make it invalid */
}
}
@@ -578,44 +874,52 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* Add a new entry to an intermediate node.
*/
STATIC void
-xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
- xfs_da_state_blk_t *newblk)
+xfs_da3_node_add(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *oldblk,
+ struct xfs_da_state_blk *newblk)
{
- xfs_da_intnode_t *node;
- xfs_da_node_entry_t *btree;
- int tmp;
+ struct xfs_da_intnode *node;
+ struct xfs_da3_icnode_hdr nodehdr;
+ struct xfs_da_node_entry *btree;
+ int tmp;
+ struct xfs_inode *dp = state->args->dp;
trace_xfs_da_node_add(state->args);
- node = oldblk->bp->data;
- ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- ASSERT((oldblk->index >= 0) && (oldblk->index <= be16_to_cpu(node->hdr.count)));
+ node = oldblk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
+
+ ASSERT(oldblk->index >= 0 && oldblk->index <= nodehdr.count);
ASSERT(newblk->blkno != 0);
if (state->args->whichfork == XFS_DATA_FORK)
- ASSERT(newblk->blkno >= state->mp->m_dirleafblk &&
- newblk->blkno < state->mp->m_dirfreeblk);
+ ASSERT(newblk->blkno >= state->args->geo->leafblk &&
+ newblk->blkno < state->args->geo->freeblk);
/*
* We may need to make some room before we insert the new node.
*/
tmp = 0;
- btree = &node->btree[ oldblk->index ];
- if (oldblk->index < be16_to_cpu(node->hdr.count)) {
- tmp = (be16_to_cpu(node->hdr.count) - oldblk->index) * (uint)sizeof(*btree);
- memmove(btree + 1, btree, tmp);
+ if (oldblk->index < nodehdr.count) {
+ tmp = (nodehdr.count - oldblk->index) * (uint)sizeof(*btree);
+ memmove(&btree[oldblk->index + 1], &btree[oldblk->index], tmp);
}
- btree->hashval = cpu_to_be32(newblk->hashval);
- btree->before = cpu_to_be32(newblk->blkno);
- xfs_da_log_buf(state->args->trans, oldblk->bp,
- XFS_DA_LOGRANGE(node, btree, tmp + sizeof(*btree)));
- be16_add_cpu(&node->hdr.count, 1);
- xfs_da_log_buf(state->args->trans, oldblk->bp,
- XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
+ btree[oldblk->index].hashval = cpu_to_be32(newblk->hashval);
+ btree[oldblk->index].before = cpu_to_be32(newblk->blkno);
+ xfs_trans_log_buf(state->args->trans, oldblk->bp,
+ XFS_DA_LOGRANGE(node, &btree[oldblk->index],
+ tmp + sizeof(*btree)));
+
+ nodehdr.count += 1;
+ dp->d_ops->node_hdr_to_disk(node, &nodehdr);
+ xfs_trans_log_buf(state->args->trans, oldblk->bp,
+ XFS_DA_LOGRANGE(node, &node->hdr, dp->d_ops->node_hdr_size));
/*
* Copy the last hash value from the oldblk to propagate upwards.
*/
- oldblk->hashval = be32_to_cpu(node->btree[be16_to_cpu(node->hdr.count)-1 ].hashval);
+ oldblk->hashval = be32_to_cpu(btree[nodehdr.count - 1].hashval);
}
/*========================================================================
@@ -627,14 +931,16 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
* possibly deallocating that block, etc...
*/
int
-xfs_da_join(xfs_da_state_t *state)
+xfs_da3_join(
+ struct xfs_da_state *state)
{
- xfs_da_state_blk_t *drop_blk, *save_blk;
- int action, error;
+ struct xfs_da_state_blk *drop_blk;
+ struct xfs_da_state_blk *save_blk;
+ int action = 0;
+ int error;
trace_xfs_da_join(state->args);
- action = 0;
drop_blk = &state->path.blk[ state->path.active-1 ];
save_blk = &state->altpath.blk[ state->path.active-1 ];
ASSERT(state->path.blk[0].magic == XFS_DA_NODE_MAGIC);
@@ -655,12 +961,12 @@ xfs_da_join(xfs_da_state_t *state)
*/
switch (drop_blk->magic) {
case XFS_ATTR_LEAF_MAGIC:
- error = xfs_attr_leaf_toosmall(state, &action);
+ error = xfs_attr3_leaf_toosmall(state, &action);
if (error)
return(error);
if (action == 0)
return(0);
- xfs_attr_leaf_unbalance(state, drop_blk, save_blk);
+ xfs_attr3_leaf_unbalance(state, drop_blk, save_blk);
break;
case XFS_DIR2_LEAFN_MAGIC:
error = xfs_dir2_leafn_toosmall(state, &action);
@@ -675,18 +981,18 @@ xfs_da_join(xfs_da_state_t *state)
* Remove the offending node, fixup hashvals,
* check for a toosmall neighbor.
*/
- xfs_da_node_remove(state, drop_blk);
- xfs_da_fixhashpath(state, &state->path);
- error = xfs_da_node_toosmall(state, &action);
+ xfs_da3_node_remove(state, drop_blk);
+ xfs_da3_fixhashpath(state, &state->path);
+ error = xfs_da3_node_toosmall(state, &action);
if (error)
return(error);
if (action == 0)
return 0;
- xfs_da_node_unbalance(state, drop_blk, save_blk);
+ xfs_da3_node_unbalance(state, drop_blk, save_blk);
break;
}
- xfs_da_fixhashpath(state, &state->altpath);
- error = xfs_da_blk_unlink(state, drop_blk, save_blk);
+ xfs_da3_fixhashpath(state, &state->altpath);
+ error = xfs_da3_blk_unlink(state, drop_blk, save_blk);
xfs_da_state_kill_altpath(state);
if (error)
return(error);
@@ -701,9 +1007,9 @@ xfs_da_join(xfs_da_state_t *state)
* we only have one entry in the root, make the child block
* the new root.
*/
- xfs_da_node_remove(state, drop_blk);
- xfs_da_fixhashpath(state, &state->path);
- error = xfs_da_root_join(state, &state->path.blk[0]);
+ xfs_da3_node_remove(state, drop_blk);
+ xfs_da3_fixhashpath(state, &state->path);
+ error = xfs_da3_root_join(state, &state->path.blk[0]);
return(error);
}
@@ -715,9 +1021,13 @@ xfs_da_blkinfo_onlychild_validate(struct xfs_da_blkinfo *blkinfo, __u16 level)
if (level == 1) {
ASSERT(magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
- magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- } else
- ASSERT(magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
+ magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC) ||
+ magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC) ||
+ magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC));
+ } else {
+ ASSERT(magic == cpu_to_be16(XFS_DA_NODE_MAGIC) ||
+ magic == cpu_to_be16(XFS_DA3_NODE_MAGIC));
+ }
ASSERT(!blkinfo->forw);
ASSERT(!blkinfo->back);
}
@@ -730,46 +1040,64 @@ xfs_da_blkinfo_onlychild_validate(struct xfs_da_blkinfo *blkinfo, __u16 level)
* the old root to block 0 as the new root node.
*/
STATIC int
-xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
+xfs_da3_root_join(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *root_blk)
{
- xfs_da_intnode_t *oldroot;
- xfs_da_args_t *args;
- xfs_dablk_t child;
- xfs_dabuf_t *bp;
- int error;
+ struct xfs_da_intnode *oldroot;
+ struct xfs_da_args *args;
+ xfs_dablk_t child;
+ struct xfs_buf *bp;
+ struct xfs_da3_icnode_hdr oldroothdr;
+ struct xfs_da_node_entry *btree;
+ int error;
+ struct xfs_inode *dp = state->args->dp;
trace_xfs_da_root_join(state->args);
- args = state->args;
- ASSERT(args != NULL);
ASSERT(root_blk->magic == XFS_DA_NODE_MAGIC);
- oldroot = root_blk->bp->data;
- ASSERT(oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- ASSERT(!oldroot->hdr.info.forw);
- ASSERT(!oldroot->hdr.info.back);
+
+ args = state->args;
+ oldroot = root_blk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&oldroothdr, oldroot);
+ ASSERT(oldroothdr.forw == 0);
+ ASSERT(oldroothdr.back == 0);
/*
* If the root has more than one child, then don't do anything.
*/
- if (be16_to_cpu(oldroot->hdr.count) > 1)
- return(0);
+ if (oldroothdr.count > 1)
+ return 0;
/*
* Read in the (only) child block, then copy those bytes into
* the root block's buffer and free the original child block.
*/
- child = be32_to_cpu(oldroot->btree[0].before);
+ btree = dp->d_ops->node_tree_p(oldroot);
+ child = be32_to_cpu(btree[0].before);
ASSERT(child != 0);
- error = xfs_da_read_buf(args->trans, args->dp, child, -1, &bp,
+ error = xfs_da3_node_read(args->trans, dp, child, -1, &bp,
args->whichfork);
if (error)
- return(error);
- ASSERT(bp != NULL);
- xfs_da_blkinfo_onlychild_validate(bp->data,
- be16_to_cpu(oldroot->hdr.level));
+ return error;
+ xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level);
- memcpy(root_blk->bp->data, bp->data, state->blocksize);
- xfs_da_log_buf(args->trans, root_blk->bp, 0, state->blocksize - 1);
+ /*
+ * This could be copying a leaf back into the root block in the case of
+ * there only being a single leaf block left in the tree. Hence we have
+ * to update the b_ops pointer as well to match the buffer type change
+ * that could occur. For dir3 blocks we also need to update the block
+ * number in the buffer header.
+ */
+ memcpy(root_blk->bp->b_addr, bp->b_addr, args->geo->blksize);
+ root_blk->bp->b_ops = bp->b_ops;
+ xfs_trans_buf_copy_type(root_blk->bp, bp);
+ if (oldroothdr.magic == XFS_DA3_NODE_MAGIC) {
+ struct xfs_da3_blkinfo *da3 = root_blk->bp->b_addr;
+ da3->blkno = cpu_to_be64(root_blk->bp->b_bn);
+ }
+ xfs_trans_log_buf(args->trans, root_blk->bp, 0,
+ args->geo->blksize - 1);
error = xfs_da_shrink_inode(args, child, bp);
return(error);
}
@@ -784,14 +1112,24 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
* If nothing can be done, return 0.
*/
STATIC int
-xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
+xfs_da3_node_toosmall(
+ struct xfs_da_state *state,
+ int *action)
{
- xfs_da_intnode_t *node;
- xfs_da_state_blk_t *blk;
- xfs_da_blkinfo_t *info;
- int count, forward, error, retval, i;
- xfs_dablk_t blkno;
- xfs_dabuf_t *bp;
+ struct xfs_da_intnode *node;
+ struct xfs_da_state_blk *blk;
+ struct xfs_da_blkinfo *info;
+ xfs_dablk_t blkno;
+ struct xfs_buf *bp;
+ struct xfs_da3_icnode_hdr nodehdr;
+ int count;
+ int forward;
+ int error;
+ int retval;
+ int i;
+ struct xfs_inode *dp = state->args->dp;
+
+ trace_xfs_da_node_toosmall(state->args);
/*
* Check for the degenerate case of the block being over 50% full.
@@ -799,11 +1137,10 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
* to coalesce with a sibling.
*/
blk = &state->path.blk[ state->path.active-1 ];
- info = blk->bp->data;
- ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
+ info = blk->bp->b_addr;
node = (xfs_da_intnode_t *)info;
- count = be16_to_cpu(node->hdr.count);
- if (count > (state->node_ents >> 1)) {
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ if (nodehdr.count > (state->args->geo->node_ents >> 1)) {
*action = 0; /* blk over 50%, don't try to join */
return(0); /* blk over 50%, don't try to join */
}
@@ -814,14 +1151,14 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
* coalesce it with a sibling block. We choose (arbitrarily)
* to merge with the forward block unless it is NULL.
*/
- if (count == 0) {
+ if (nodehdr.count == 0) {
/*
* Make altpath point to the block we want to keep and
* path point to the block we want to drop (this one).
*/
forward = (info->forw != 0);
memcpy(&state->altpath, &state->path, sizeof(state->path));
- error = xfs_da_path_shift(state, &state->altpath, forward,
+ error = xfs_da3_path_shift(state, &state->altpath, forward,
0, &retval);
if (error)
return(error);
@@ -840,35 +1177,35 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
* We prefer coalescing with the lower numbered sibling so as
* to shrink a directory over time.
*/
+ count = state->args->geo->node_ents;
+ count -= state->args->geo->node_ents >> 2;
+ count -= nodehdr.count;
+
/* start with smaller blk num */
- forward = (be32_to_cpu(info->forw) < be32_to_cpu(info->back));
+ forward = nodehdr.forw < nodehdr.back;
for (i = 0; i < 2; forward = !forward, i++) {
+ struct xfs_da3_icnode_hdr thdr;
if (forward)
- blkno = be32_to_cpu(info->forw);
+ blkno = nodehdr.forw;
else
- blkno = be32_to_cpu(info->back);
+ blkno = nodehdr.back;
if (blkno == 0)
continue;
- error = xfs_da_read_buf(state->args->trans, state->args->dp,
+ error = xfs_da3_node_read(state->args->trans, dp,
blkno, -1, &bp, state->args->whichfork);
if (error)
return(error);
- ASSERT(bp != NULL);
-
- node = (xfs_da_intnode_t *)info;
- count = state->node_ents;
- count -= state->node_ents >> 2;
- count -= be16_to_cpu(node->hdr.count);
- node = bp->data;
- ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- count -= be16_to_cpu(node->hdr.count);
- xfs_da_brelse(state->args->trans, bp);
- if (count >= 0)
+
+ node = bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&thdr, node);
+ xfs_trans_brelse(state->args->trans, bp);
+
+ if (count - thdr.count >= 0)
break; /* fits with at least 25% to spare */
}
if (i >= 2) {
*action = 0;
- return(0);
+ return 0;
}
/*
@@ -877,28 +1214,43 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
*/
memcpy(&state->altpath, &state->path, sizeof(state->path));
if (blkno < blk->blkno) {
- error = xfs_da_path_shift(state, &state->altpath, forward,
+ error = xfs_da3_path_shift(state, &state->altpath, forward,
0, &retval);
- if (error) {
- return(error);
- }
- if (retval) {
- *action = 0;
- return(0);
- }
} else {
- error = xfs_da_path_shift(state, &state->path, forward,
+ error = xfs_da3_path_shift(state, &state->path, forward,
0, &retval);
- if (error) {
- return(error);
- }
- if (retval) {
- *action = 0;
- return(0);
- }
+ }
+ if (error)
+ return error;
+ if (retval) {
+ *action = 0;
+ return 0;
}
*action = 1;
- return(0);
+ return 0;
+}
+
+/*
+ * Pick up the last hashvalue from an intermediate node.
+ */
+STATIC uint
+xfs_da3_node_lasthash(
+ struct xfs_inode *dp,
+ struct xfs_buf *bp,
+ int *count)
+{
+ struct xfs_da_intnode *node;
+ struct xfs_da_node_entry *btree;
+ struct xfs_da3_icnode_hdr nodehdr;
+
+ node = bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ if (count)
+ *count = nodehdr.count;
+ if (!nodehdr.count)
+ return 0;
+ btree = dp->d_ops->node_tree_p(node);
+ return be32_to_cpu(btree[nodehdr.count - 1].hashval);
}
/*
@@ -906,13 +1258,19 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
* when we stop making changes, return.
*/
void
-xfs_da_fixhashpath(xfs_da_state_t *state, xfs_da_state_path_t *path)
+xfs_da3_fixhashpath(
+ struct xfs_da_state *state,
+ struct xfs_da_state_path *path)
{
- xfs_da_state_blk_t *blk;
- xfs_da_intnode_t *node;
- xfs_da_node_entry_t *btree;
- xfs_dahash_t lasthash=0;
- int level, count;
+ struct xfs_da_state_blk *blk;
+ struct xfs_da_intnode *node;
+ struct xfs_da_node_entry *btree;
+ xfs_dahash_t lasthash=0;
+ int level;
+ int count;
+ struct xfs_inode *dp = state->args->dp;
+
+ trace_xfs_da_fixhashpath(state->args);
level = path->active-1;
blk = &path->blk[ level ];
@@ -923,28 +1281,31 @@ xfs_da_fixhashpath(xfs_da_state_t *state, xfs_da_state_path_t *path)
return;
break;
case XFS_DIR2_LEAFN_MAGIC:
- lasthash = xfs_dir2_leafn_lasthash(blk->bp, &count);
+ lasthash = xfs_dir2_leafn_lasthash(dp, blk->bp, &count);
if (count == 0)
return;
break;
case XFS_DA_NODE_MAGIC:
- lasthash = xfs_da_node_lasthash(blk->bp, &count);
+ lasthash = xfs_da3_node_lasthash(dp, blk->bp, &count);
if (count == 0)
return;
break;
}
for (blk--, level--; level >= 0; blk--, level--) {
- node = blk->bp->data;
- ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- btree = &node->btree[ blk->index ];
- if (be32_to_cpu(btree->hashval) == lasthash)
+ struct xfs_da3_icnode_hdr nodehdr;
+
+ node = blk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
+ if (be32_to_cpu(btree[blk->index].hashval) == lasthash)
break;
blk->hashval = lasthash;
- btree->hashval = cpu_to_be32(lasthash);
- xfs_da_log_buf(state->args->trans, blk->bp,
- XFS_DA_LOGRANGE(node, btree, sizeof(*btree)));
+ btree[blk->index].hashval = cpu_to_be32(lasthash);
+ xfs_trans_log_buf(state->args->trans, blk->bp,
+ XFS_DA_LOGRANGE(node, &btree[blk->index],
+ sizeof(*btree)));
- lasthash = be32_to_cpu(node->btree[be16_to_cpu(node->hdr.count)-1].hashval);
+ lasthash = be32_to_cpu(btree[nodehdr.count - 1].hashval);
}
}
@@ -952,104 +1313,122 @@ xfs_da_fixhashpath(xfs_da_state_t *state, xfs_da_state_path_t *path)
* Remove an entry from an intermediate node.
*/
STATIC void
-xfs_da_node_remove(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk)
+xfs_da3_node_remove(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *drop_blk)
{
- xfs_da_intnode_t *node;
- xfs_da_node_entry_t *btree;
- int tmp;
+ struct xfs_da_intnode *node;
+ struct xfs_da3_icnode_hdr nodehdr;
+ struct xfs_da_node_entry *btree;
+ int index;
+ int tmp;
+ struct xfs_inode *dp = state->args->dp;
trace_xfs_da_node_remove(state->args);
- node = drop_blk->bp->data;
- ASSERT(drop_blk->index < be16_to_cpu(node->hdr.count));
+ node = drop_blk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ ASSERT(drop_blk->index < nodehdr.count);
ASSERT(drop_blk->index >= 0);
/*
* Copy over the offending entry, or just zero it out.
*/
- btree = &node->btree[drop_blk->index];
- if (drop_blk->index < (be16_to_cpu(node->hdr.count)-1)) {
- tmp = be16_to_cpu(node->hdr.count) - drop_blk->index - 1;
+ index = drop_blk->index;
+ btree = dp->d_ops->node_tree_p(node);
+ if (index < nodehdr.count - 1) {
+ tmp = nodehdr.count - index - 1;
tmp *= (uint)sizeof(xfs_da_node_entry_t);
- memmove(btree, btree + 1, tmp);
- xfs_da_log_buf(state->args->trans, drop_blk->bp,
- XFS_DA_LOGRANGE(node, btree, tmp));
- btree = &node->btree[be16_to_cpu(node->hdr.count)-1];
+ memmove(&btree[index], &btree[index + 1], tmp);
+ xfs_trans_log_buf(state->args->trans, drop_blk->bp,
+ XFS_DA_LOGRANGE(node, &btree[index], tmp));
+ index = nodehdr.count - 1;
}
- memset((char *)btree, 0, sizeof(xfs_da_node_entry_t));
- xfs_da_log_buf(state->args->trans, drop_blk->bp,
- XFS_DA_LOGRANGE(node, btree, sizeof(*btree)));
- be16_add_cpu(&node->hdr.count, -1);
- xfs_da_log_buf(state->args->trans, drop_blk->bp,
- XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
+ memset(&btree[index], 0, sizeof(xfs_da_node_entry_t));
+ xfs_trans_log_buf(state->args->trans, drop_blk->bp,
+ XFS_DA_LOGRANGE(node, &btree[index], sizeof(btree[index])));
+ nodehdr.count -= 1;
+ dp->d_ops->node_hdr_to_disk(node, &nodehdr);
+ xfs_trans_log_buf(state->args->trans, drop_blk->bp,
+ XFS_DA_LOGRANGE(node, &node->hdr, dp->d_ops->node_hdr_size));
/*
* Copy the last hash value from the block to propagate upwards.
*/
- btree--;
- drop_blk->hashval = be32_to_cpu(btree->hashval);
+ drop_blk->hashval = be32_to_cpu(btree[index - 1].hashval);
}
/*
- * Unbalance the btree elements between two intermediate nodes,
+ * Unbalance the elements between two intermediate nodes,
* move all Btree elements from one node into another.
*/
STATIC void
-xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
- xfs_da_state_blk_t *save_blk)
+xfs_da3_node_unbalance(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *drop_blk,
+ struct xfs_da_state_blk *save_blk)
{
- xfs_da_intnode_t *drop_node, *save_node;
- xfs_da_node_entry_t *btree;
- int tmp;
- xfs_trans_t *tp;
+ struct xfs_da_intnode *drop_node;
+ struct xfs_da_intnode *save_node;
+ struct xfs_da_node_entry *drop_btree;
+ struct xfs_da_node_entry *save_btree;
+ struct xfs_da3_icnode_hdr drop_hdr;
+ struct xfs_da3_icnode_hdr save_hdr;
+ struct xfs_trans *tp;
+ int sindex;
+ int tmp;
+ struct xfs_inode *dp = state->args->dp;
trace_xfs_da_node_unbalance(state->args);
- drop_node = drop_blk->bp->data;
- save_node = save_blk->bp->data;
- ASSERT(drop_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- ASSERT(save_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
+ drop_node = drop_blk->bp->b_addr;
+ save_node = save_blk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&drop_hdr, drop_node);
+ dp->d_ops->node_hdr_from_disk(&save_hdr, save_node);
+ drop_btree = dp->d_ops->node_tree_p(drop_node);
+ save_btree = dp->d_ops->node_tree_p(save_node);
tp = state->args->trans;
/*
* If the dying block has lower hashvals, then move all the
* elements in the remaining block up to make a hole.
*/
- if ((be32_to_cpu(drop_node->btree[0].hashval) < be32_to_cpu(save_node->btree[ 0 ].hashval)) ||
- (be32_to_cpu(drop_node->btree[be16_to_cpu(drop_node->hdr.count)-1].hashval) <
- be32_to_cpu(save_node->btree[be16_to_cpu(save_node->hdr.count)-1].hashval)))
- {
- btree = &save_node->btree[be16_to_cpu(drop_node->hdr.count)];
- tmp = be16_to_cpu(save_node->hdr.count) * (uint)sizeof(xfs_da_node_entry_t);
- memmove(btree, &save_node->btree[0], tmp);
- btree = &save_node->btree[0];
- xfs_da_log_buf(tp, save_blk->bp,
- XFS_DA_LOGRANGE(save_node, btree,
- (be16_to_cpu(save_node->hdr.count) + be16_to_cpu(drop_node->hdr.count)) *
- sizeof(xfs_da_node_entry_t)));
+ if ((be32_to_cpu(drop_btree[0].hashval) <
+ be32_to_cpu(save_btree[0].hashval)) ||
+ (be32_to_cpu(drop_btree[drop_hdr.count - 1].hashval) <
+ be32_to_cpu(save_btree[save_hdr.count - 1].hashval))) {
+ /* XXX: check this - is memmove dst correct? */
+ tmp = save_hdr.count * sizeof(xfs_da_node_entry_t);
+ memmove(&save_btree[drop_hdr.count], &save_btree[0], tmp);
+
+ sindex = 0;
+ xfs_trans_log_buf(tp, save_blk->bp,
+ XFS_DA_LOGRANGE(save_node, &save_btree[0],
+ (save_hdr.count + drop_hdr.count) *
+ sizeof(xfs_da_node_entry_t)));
} else {
- btree = &save_node->btree[be16_to_cpu(save_node->hdr.count)];
- xfs_da_log_buf(tp, save_blk->bp,
- XFS_DA_LOGRANGE(save_node, btree,
- be16_to_cpu(drop_node->hdr.count) *
- sizeof(xfs_da_node_entry_t)));
+ sindex = save_hdr.count;
+ xfs_trans_log_buf(tp, save_blk->bp,
+ XFS_DA_LOGRANGE(save_node, &save_btree[sindex],
+ drop_hdr.count * sizeof(xfs_da_node_entry_t)));
}
/*
* Move all the B-tree elements from drop_blk to save_blk.
*/
- tmp = be16_to_cpu(drop_node->hdr.count) * (uint)sizeof(xfs_da_node_entry_t);
- memcpy(btree, &drop_node->btree[0], tmp);
- be16_add_cpu(&save_node->hdr.count, be16_to_cpu(drop_node->hdr.count));
+ tmp = drop_hdr.count * (uint)sizeof(xfs_da_node_entry_t);
+ memcpy(&save_btree[sindex], &drop_btree[0], tmp);
+ save_hdr.count += drop_hdr.count;
- xfs_da_log_buf(tp, save_blk->bp,
+ dp->d_ops->node_hdr_to_disk(save_node, &save_hdr);
+ xfs_trans_log_buf(tp, save_blk->bp,
XFS_DA_LOGRANGE(save_node, &save_node->hdr,
- sizeof(save_node->hdr)));
+ dp->d_ops->node_hdr_size));
/*
* Save the last hashval in the remaining block for upward propagation.
*/
- save_blk->hashval = be32_to_cpu(save_node->btree[be16_to_cpu(save_node->hdr.count)-1].hashval);
+ save_blk->hashval = be32_to_cpu(save_btree[save_hdr.count - 1].hashval);
}
/*========================================================================
@@ -1068,16 +1447,25 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
* pruned depth-first tree search.
*/
int /* error */
-xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
+xfs_da3_node_lookup_int(
+ struct xfs_da_state *state,
+ int *result)
{
- xfs_da_state_blk_t *blk;
- xfs_da_blkinfo_t *curr;
- xfs_da_intnode_t *node;
- xfs_da_node_entry_t *btree;
- xfs_dablk_t blkno;
- int probe, span, max, error, retval;
- xfs_dahash_t hashval, btreehashval;
- xfs_da_args_t *args;
+ struct xfs_da_state_blk *blk;
+ struct xfs_da_blkinfo *curr;
+ struct xfs_da_intnode *node;
+ struct xfs_da_node_entry *btree;
+ struct xfs_da3_icnode_hdr nodehdr;
+ struct xfs_da_args *args;
+ xfs_dablk_t blkno;
+ xfs_dahash_t hashval;
+ xfs_dahash_t btreehashval;
+ int probe;
+ int span;
+ int max;
+ int error;
+ int retval;
+ struct xfs_inode *dp = state->args->dp;
args = state->args;
@@ -1085,7 +1473,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
* Descend thru the B-tree searching each level for the right
* node to use, until the right hashval is found.
*/
- blkno = (args->whichfork == XFS_DATA_FORK)? state->mp->m_dirleafblk : 0;
+ blkno = (args->whichfork == XFS_DATA_FORK)? args->geo->leafblk : 0;
for (blk = &state->path.blk[0], state->path.active = 1;
state->path.active <= XFS_DA_NODE_MAXDEPTH;
blk++, state->path.active++) {
@@ -1093,75 +1481,85 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
* Read the next node down in the tree.
*/
blk->blkno = blkno;
- error = xfs_da_read_buf(args->trans, args->dp, blkno,
+ error = xfs_da3_node_read(args->trans, args->dp, blkno,
-1, &blk->bp, args->whichfork);
if (error) {
blk->blkno = 0;
state->path.active--;
return(error);
}
- curr = blk->bp->data;
+ curr = blk->bp->b_addr;
blk->magic = be16_to_cpu(curr->magic);
- ASSERT(blk->magic == XFS_DA_NODE_MAGIC ||
- blk->magic == XFS_DIR2_LEAFN_MAGIC ||
- blk->magic == XFS_ATTR_LEAF_MAGIC);
+
+ if (blk->magic == XFS_ATTR_LEAF_MAGIC ||
+ blk->magic == XFS_ATTR3_LEAF_MAGIC) {
+ blk->magic = XFS_ATTR_LEAF_MAGIC;
+ blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
+ break;
+ }
+
+ if (blk->magic == XFS_DIR2_LEAFN_MAGIC ||
+ blk->magic == XFS_DIR3_LEAFN_MAGIC) {
+ blk->magic = XFS_DIR2_LEAFN_MAGIC;
+ blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
+ blk->bp, NULL);
+ break;
+ }
+
+ blk->magic = XFS_DA_NODE_MAGIC;
+
/*
* Search an intermediate node for a match.
*/
- if (blk->magic == XFS_DA_NODE_MAGIC) {
- node = blk->bp->data;
- max = be16_to_cpu(node->hdr.count);
- blk->hashval = be32_to_cpu(node->btree[max-1].hashval);
+ node = blk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
- /*
- * Binary search. (note: small blocks will skip loop)
- */
- probe = span = max / 2;
- hashval = args->hashval;
- for (btree = &node->btree[probe]; span > 4;
- btree = &node->btree[probe]) {
- span /= 2;
- btreehashval = be32_to_cpu(btree->hashval);
- if (btreehashval < hashval)
- probe += span;
- else if (btreehashval > hashval)
- probe -= span;
- else
- break;
- }
- ASSERT((probe >= 0) && (probe < max));
- ASSERT((span <= 4) || (be32_to_cpu(btree->hashval) == hashval));
+ max = nodehdr.count;
+ blk->hashval = be32_to_cpu(btree[max - 1].hashval);
- /*
- * Since we may have duplicate hashval's, find the first
- * matching hashval in the node.
- */
- while ((probe > 0) && (be32_to_cpu(btree->hashval) >= hashval)) {
- btree--;
- probe--;
- }
- while ((probe < max) && (be32_to_cpu(btree->hashval) < hashval)) {
- btree++;
- probe++;
- }
+ /*
+ * Binary search. (note: small blocks will skip loop)
+ */
+ probe = span = max / 2;
+ hashval = args->hashval;
+ while (span > 4) {
+ span /= 2;
+ btreehashval = be32_to_cpu(btree[probe].hashval);
+ if (btreehashval < hashval)
+ probe += span;
+ else if (btreehashval > hashval)
+ probe -= span;
+ else
+ break;
+ }
+ ASSERT((probe >= 0) && (probe < max));
+ ASSERT((span <= 4) ||
+ (be32_to_cpu(btree[probe].hashval) == hashval));
- /*
- * Pick the right block to descend on.
- */
- if (probe == max) {
- blk->index = max-1;
- blkno = be32_to_cpu(node->btree[max-1].before);
- } else {
- blk->index = probe;
- blkno = be32_to_cpu(btree->before);
- }
- } else if (blk->magic == XFS_ATTR_LEAF_MAGIC) {
- blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
- break;
- } else if (blk->magic == XFS_DIR2_LEAFN_MAGIC) {
- blk->hashval = xfs_dir2_leafn_lasthash(blk->bp, NULL);
- break;
+ /*
+ * Since we may have duplicate hashval's, find the first
+ * matching hashval in the node.
+ */
+ while (probe > 0 &&
+ be32_to_cpu(btree[probe].hashval) >= hashval) {
+ probe--;
+ }
+ while (probe < max &&
+ be32_to_cpu(btree[probe].hashval) < hashval) {
+ probe++;
+ }
+
+ /*
+ * Pick the right block to descend on.
+ */
+ if (probe == max) {
+ blk->index = max - 1;
+ blkno = be32_to_cpu(btree[max - 1].before);
+ } else {
+ blk->index = probe;
+ blkno = be32_to_cpu(btree[probe].before);
}
}
@@ -1176,7 +1574,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
retval = xfs_dir2_leafn_lookup_int(blk->bp, args,
&blk->index, state);
} else if (blk->magic == XFS_ATTR_LEAF_MAGIC) {
- retval = xfs_attr_leaf_lookup_int(blk->bp, args);
+ retval = xfs_attr3_leaf_lookup_int(blk->bp, args);
blk->index = args->index;
args->blkno = blk->blkno;
} else {
@@ -1185,7 +1583,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
}
if (((retval == ENOENT) || (retval == ENOATTR)) &&
(blk->hashval == args->hashval)) {
- error = xfs_da_path_shift(state, &state->path, 1, 1,
+ error = xfs_da3_path_shift(state, &state->path, 1, 1,
&retval);
if (error)
return(error);
@@ -1207,40 +1605,75 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
*========================================================================*/
/*
+ * Compare two intermediate nodes for "order".
+ */
+STATIC int
+xfs_da3_node_order(
+ struct xfs_inode *dp,
+ struct xfs_buf *node1_bp,
+ struct xfs_buf *node2_bp)
+{
+ struct xfs_da_intnode *node1;
+ struct xfs_da_intnode *node2;
+ struct xfs_da_node_entry *btree1;
+ struct xfs_da_node_entry *btree2;
+ struct xfs_da3_icnode_hdr node1hdr;
+ struct xfs_da3_icnode_hdr node2hdr;
+
+ node1 = node1_bp->b_addr;
+ node2 = node2_bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&node1hdr, node1);
+ dp->d_ops->node_hdr_from_disk(&node2hdr, node2);
+ btree1 = dp->d_ops->node_tree_p(node1);
+ btree2 = dp->d_ops->node_tree_p(node2);
+
+ if (node1hdr.count > 0 && node2hdr.count > 0 &&
+ ((be32_to_cpu(btree2[0].hashval) < be32_to_cpu(btree1[0].hashval)) ||
+ (be32_to_cpu(btree2[node2hdr.count - 1].hashval) <
+ be32_to_cpu(btree1[node1hdr.count - 1].hashval)))) {
+ return 1;
+ }
+ return 0;
+}
+
+/*
* Link a new block into a doubly linked list of blocks (of whatever type).
*/
int /* error */
-xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
- xfs_da_state_blk_t *new_blk)
+xfs_da3_blk_link(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *old_blk,
+ struct xfs_da_state_blk *new_blk)
{
- xfs_da_blkinfo_t *old_info, *new_info, *tmp_info;
- xfs_da_args_t *args;
- int before=0, error;
- xfs_dabuf_t *bp;
+ struct xfs_da_blkinfo *old_info;
+ struct xfs_da_blkinfo *new_info;
+ struct xfs_da_blkinfo *tmp_info;
+ struct xfs_da_args *args;
+ struct xfs_buf *bp;
+ int before = 0;
+ int error;
+ struct xfs_inode *dp = state->args->dp;
/*
* Set up environment.
*/
args = state->args;
ASSERT(args != NULL);
- old_info = old_blk->bp->data;
- new_info = new_blk->bp->data;
+ old_info = old_blk->bp->b_addr;
+ new_info = new_blk->bp->b_addr;
ASSERT(old_blk->magic == XFS_DA_NODE_MAGIC ||
old_blk->magic == XFS_DIR2_LEAFN_MAGIC ||
old_blk->magic == XFS_ATTR_LEAF_MAGIC);
- ASSERT(old_blk->magic == be16_to_cpu(old_info->magic));
- ASSERT(new_blk->magic == be16_to_cpu(new_info->magic));
- ASSERT(old_blk->magic == new_blk->magic);
switch (old_blk->magic) {
case XFS_ATTR_LEAF_MAGIC:
before = xfs_attr_leaf_order(old_blk->bp, new_blk->bp);
break;
case XFS_DIR2_LEAFN_MAGIC:
- before = xfs_dir2_leafn_order(old_blk->bp, new_blk->bp);
+ before = xfs_dir2_leafn_order(dp, old_blk->bp, new_blk->bp);
break;
case XFS_DA_NODE_MAGIC:
- before = xfs_da_node_order(old_blk->bp, new_blk->bp);
+ before = xfs_da3_node_order(dp, old_blk->bp, new_blk->bp);
break;
}
@@ -1255,18 +1688,17 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
new_info->forw = cpu_to_be32(old_blk->blkno);
new_info->back = old_info->back;
if (old_info->back) {
- error = xfs_da_read_buf(args->trans, args->dp,
+ error = xfs_da3_node_read(args->trans, dp,
be32_to_cpu(old_info->back),
-1, &bp, args->whichfork);
if (error)
return(error);
ASSERT(bp != NULL);
- tmp_info = bp->data;
- ASSERT(be16_to_cpu(tmp_info->magic) == be16_to_cpu(old_info->magic));
+ tmp_info = bp->b_addr;
+ ASSERT(tmp_info->magic == old_info->magic);
ASSERT(be32_to_cpu(tmp_info->forw) == old_blk->blkno);
tmp_info->forw = cpu_to_be32(new_blk->blkno);
- xfs_da_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
- xfs_da_buf_done(bp);
+ xfs_trans_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
}
old_info->back = cpu_to_be32(new_blk->blkno);
} else {
@@ -1277,90 +1709,52 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
new_info->forw = old_info->forw;
new_info->back = cpu_to_be32(old_blk->blkno);
if (old_info->forw) {
- error = xfs_da_read_buf(args->trans, args->dp,
+ error = xfs_da3_node_read(args->trans, dp,
be32_to_cpu(old_info->forw),
-1, &bp, args->whichfork);
if (error)
return(error);
ASSERT(bp != NULL);
- tmp_info = bp->data;
+ tmp_info = bp->b_addr;
ASSERT(tmp_info->magic == old_info->magic);
ASSERT(be32_to_cpu(tmp_info->back) == old_blk->blkno);
tmp_info->back = cpu_to_be32(new_blk->blkno);
- xfs_da_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
- xfs_da_buf_done(bp);
+ xfs_trans_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
}
old_info->forw = cpu_to_be32(new_blk->blkno);
}
- xfs_da_log_buf(args->trans, old_blk->bp, 0, sizeof(*tmp_info) - 1);
- xfs_da_log_buf(args->trans, new_blk->bp, 0, sizeof(*tmp_info) - 1);
+ xfs_trans_log_buf(args->trans, old_blk->bp, 0, sizeof(*tmp_info) - 1);
+ xfs_trans_log_buf(args->trans, new_blk->bp, 0, sizeof(*tmp_info) - 1);
return(0);
}
/*
- * Compare two intermediate nodes for "order".
- */
-STATIC int
-xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp)
-{
- xfs_da_intnode_t *node1, *node2;
-
- node1 = node1_bp->data;
- node2 = node2_bp->data;
- ASSERT(node1->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC) &&
- node2->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- if ((be16_to_cpu(node1->hdr.count) > 0) && (be16_to_cpu(node2->hdr.count) > 0) &&
- ((be32_to_cpu(node2->btree[0].hashval) <
- be32_to_cpu(node1->btree[0].hashval)) ||
- (be32_to_cpu(node2->btree[be16_to_cpu(node2->hdr.count)-1].hashval) <
- be32_to_cpu(node1->btree[be16_to_cpu(node1->hdr.count)-1].hashval)))) {
- return(1);
- }
- return(0);
-}
-
-/*
- * Pick up the last hashvalue from an intermediate node.
- */
-STATIC uint
-xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count)
-{
- xfs_da_intnode_t *node;
-
- node = bp->data;
- ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- if (count)
- *count = be16_to_cpu(node->hdr.count);
- if (!node->hdr.count)
- return(0);
- return be32_to_cpu(node->btree[be16_to_cpu(node->hdr.count)-1].hashval);
-}
-
-/*
* Unlink a block from a doubly linked list of blocks.
*/
STATIC int /* error */
-xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
- xfs_da_state_blk_t *save_blk)
+xfs_da3_blk_unlink(
+ struct xfs_da_state *state,
+ struct xfs_da_state_blk *drop_blk,
+ struct xfs_da_state_blk *save_blk)
{
- xfs_da_blkinfo_t *drop_info, *save_info, *tmp_info;
- xfs_da_args_t *args;
- xfs_dabuf_t *bp;
- int error;
+ struct xfs_da_blkinfo *drop_info;
+ struct xfs_da_blkinfo *save_info;
+ struct xfs_da_blkinfo *tmp_info;
+ struct xfs_da_args *args;
+ struct xfs_buf *bp;
+ int error;
/*
* Set up environment.
*/
args = state->args;
ASSERT(args != NULL);
- save_info = save_blk->bp->data;
- drop_info = drop_blk->bp->data;
+ save_info = save_blk->bp->b_addr;
+ drop_info = drop_blk->bp->b_addr;
ASSERT(save_blk->magic == XFS_DA_NODE_MAGIC ||
save_blk->magic == XFS_DIR2_LEAFN_MAGIC ||
save_blk->magic == XFS_ATTR_LEAF_MAGIC);
- ASSERT(save_blk->magic == be16_to_cpu(save_info->magic));
- ASSERT(drop_blk->magic == be16_to_cpu(drop_info->magic));
ASSERT(save_blk->magic == drop_blk->magic);
ASSERT((be32_to_cpu(save_info->forw) == drop_blk->blkno) ||
(be32_to_cpu(save_info->back) == drop_blk->blkno));
@@ -1374,41 +1768,39 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
trace_xfs_da_unlink_back(args);
save_info->back = drop_info->back;
if (drop_info->back) {
- error = xfs_da_read_buf(args->trans, args->dp,
+ error = xfs_da3_node_read(args->trans, args->dp,
be32_to_cpu(drop_info->back),
-1, &bp, args->whichfork);
if (error)
return(error);
ASSERT(bp != NULL);
- tmp_info = bp->data;
+ tmp_info = bp->b_addr;
ASSERT(tmp_info->magic == save_info->magic);
ASSERT(be32_to_cpu(tmp_info->forw) == drop_blk->blkno);
tmp_info->forw = cpu_to_be32(save_blk->blkno);
- xfs_da_log_buf(args->trans, bp, 0,
+ xfs_trans_log_buf(args->trans, bp, 0,
sizeof(*tmp_info) - 1);
- xfs_da_buf_done(bp);
}
} else {
trace_xfs_da_unlink_forward(args);
save_info->forw = drop_info->forw;
if (drop_info->forw) {
- error = xfs_da_read_buf(args->trans, args->dp,
+ error = xfs_da3_node_read(args->trans, args->dp,
be32_to_cpu(drop_info->forw),
-1, &bp, args->whichfork);
if (error)
return(error);
ASSERT(bp != NULL);
- tmp_info = bp->data;
+ tmp_info = bp->b_addr;
ASSERT(tmp_info->magic == save_info->magic);
ASSERT(be32_to_cpu(tmp_info->back) == drop_blk->blkno);
tmp_info->back = cpu_to_be32(save_blk->blkno);
- xfs_da_log_buf(args->trans, bp, 0,
+ xfs_trans_log_buf(args->trans, bp, 0,
sizeof(*tmp_info) - 1);
- xfs_da_buf_done(bp);
}
}
- xfs_da_log_buf(args->trans, save_blk->bp, 0, sizeof(*save_info) - 1);
+ xfs_trans_log_buf(args->trans, save_blk->bp, 0, sizeof(*save_info) - 1);
return(0);
}
@@ -1421,15 +1813,25 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
* the new bottom and the root.
*/
int /* error */
-xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
- int forward, int release, int *result)
+xfs_da3_path_shift(
+ struct xfs_da_state *state,
+ struct xfs_da_state_path *path,
+ int forward,
+ int release,
+ int *result)
{
- xfs_da_state_blk_t *blk;
- xfs_da_blkinfo_t *info;
- xfs_da_intnode_t *node;
- xfs_da_args_t *args;
- xfs_dablk_t blkno=0;
- int level, error;
+ struct xfs_da_state_blk *blk;
+ struct xfs_da_blkinfo *info;
+ struct xfs_da_intnode *node;
+ struct xfs_da_args *args;
+ struct xfs_da_node_entry *btree;
+ struct xfs_da3_icnode_hdr nodehdr;
+ xfs_dablk_t blkno = 0;
+ int level;
+ int error;
+ struct xfs_inode *dp = state->args->dp;
+
+ trace_xfs_da_path_shift(state->args);
/*
* Roll up the Btree looking for the first block where our
@@ -1442,16 +1844,17 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
ASSERT((path->active > 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
level = (path->active-1) - 1; /* skip bottom layer in path */
for (blk = &path->blk[level]; level >= 0; blk--, level--) {
- ASSERT(blk->bp != NULL);
- node = blk->bp->data;
- ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
- if (forward && (blk->index < be16_to_cpu(node->hdr.count)-1)) {
+ node = blk->bp->b_addr;
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
+
+ if (forward && (blk->index < nodehdr.count - 1)) {
blk->index++;
- blkno = be32_to_cpu(node->btree[blk->index].before);
+ blkno = be32_to_cpu(btree[blk->index].before);
break;
} else if (!forward && (blk->index > 0)) {
blk->index--;
- blkno = be32_to_cpu(node->btree[blk->index].before);
+ blkno = be32_to_cpu(btree[blk->index].before);
break;
}
}
@@ -1471,51 +1874,65 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
* (if it's dirty, trans won't actually let go)
*/
if (release)
- xfs_da_brelse(args->trans, blk->bp);
+ xfs_trans_brelse(args->trans, blk->bp);
/*
* Read the next child block.
*/
blk->blkno = blkno;
- error = xfs_da_read_buf(args->trans, args->dp, blkno, -1,
- &blk->bp, args->whichfork);
+ error = xfs_da3_node_read(args->trans, dp, blkno, -1,
+ &blk->bp, args->whichfork);
if (error)
return(error);
- ASSERT(blk->bp != NULL);
- info = blk->bp->data;
+ info = blk->bp->b_addr;
ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC) ||
+ info->magic == cpu_to_be16(XFS_DA3_NODE_MAGIC) ||
info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
- info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
- blk->magic = be16_to_cpu(info->magic);
- if (blk->magic == XFS_DA_NODE_MAGIC) {
+ info->magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC) ||
+ info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC) ||
+ info->magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC));
+
+
+ /*
+ * Note: we flatten the magic number to a single type so we
+ * don't have to compare against crc/non-crc types elsewhere.
+ */
+ switch (be16_to_cpu(info->magic)) {
+ case XFS_DA_NODE_MAGIC:
+ case XFS_DA3_NODE_MAGIC:
+ blk->magic = XFS_DA_NODE_MAGIC;
node = (xfs_da_intnode_t *)info;
- blk->hashval = be32_to_cpu(node->btree[be16_to_cpu(node->hdr.count)-1].hashval);
+ dp->d_ops->node_hdr_from_disk(&nodehdr, node);
+ btree = dp->d_ops->node_tree_p(node);
+ blk->hashval = be32_to_cpu(btree[nodehdr.count - 1].hashval);
if (forward)
blk->index = 0;
else
- blk->index = be16_to_cpu(node->hdr.count)-1;
- blkno = be32_to_cpu(node->btree[blk->index].before);
- } else {
+ blk->index = nodehdr.count - 1;
+ blkno = be32_to_cpu(btree[blk->index].before);
+ break;
+ case XFS_ATTR_LEAF_MAGIC:
+ case XFS_ATTR3_LEAF_MAGIC:
+ blk->magic = XFS_ATTR_LEAF_MAGIC;
ASSERT(level == path->active-1);
blk->index = 0;
- switch(blk->magic) {
- case XFS_ATTR_LEAF_MAGIC:
- blk->hashval = xfs_attr_leaf_lasthash(blk->bp,
- NULL);
- break;
- case XFS_DIR2_LEAFN_MAGIC:
- blk->hashval = xfs_dir2_leafn_lasthash(blk->bp,
- NULL);
- break;
- default:
- ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC ||
- blk->magic == XFS_DIR2_LEAFN_MAGIC);
- break;
- }
+ blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
+ break;
+ case XFS_DIR2_LEAFN_MAGIC:
+ case XFS_DIR3_LEAFN_MAGIC:
+ blk->magic = XFS_DIR2_LEAFN_MAGIC;
+ ASSERT(level == path->active-1);
+ blk->index = 0;
+ blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
+ blk->bp, NULL);
+ break;
+ default:
+ ASSERT(0);
+ break;
}
}
*result = 0;
- return(0);
+ return 0;
}
@@ -1674,20 +2091,12 @@ xfs_da_grow_inode(
xfs_dablk_t *new_blkno)
{
xfs_fileoff_t bno;
- int count;
int error;
trace_xfs_da_grow_inode(args);
- if (args->whichfork == XFS_DATA_FORK) {
- bno = args->dp->i_mount->m_dirleafblk;
- count = args->dp->i_mount->m_dirblkfsbs;
- } else {
- bno = 0;
- count = 1;
- }
-
- error = xfs_da_grow_inode_int(args, &bno, count);
+ bno = args->geo->leafblk;
+ error = xfs_da_grow_inode_int(args, &bno, args->geo->fsbcount);
if (!error)
*new_blkno = (xfs_dablk_t)bno;
return error;
@@ -1702,32 +2111,48 @@ xfs_da_grow_inode(
* a bmap btree split to do that.
*/
STATIC int
-xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
- xfs_dabuf_t **dead_bufp)
+xfs_da3_swap_lastblock(
+ struct xfs_da_args *args,
+ xfs_dablk_t *dead_blknop,
+ struct xfs_buf **dead_bufp)
{
- xfs_dablk_t dead_blkno, last_blkno, sib_blkno, par_blkno;
- xfs_dabuf_t *dead_buf, *last_buf, *sib_buf, *par_buf;
- xfs_fileoff_t lastoff;
- xfs_inode_t *ip;
- xfs_trans_t *tp;
- xfs_mount_t *mp;
- int error, w, entno, level, dead_level;
- xfs_da_blkinfo_t *dead_info, *sib_info;
- xfs_da_intnode_t *par_node, *dead_node;
- xfs_dir2_leaf_t *dead_leaf2;
- xfs_dahash_t dead_hash;
+ struct xfs_da_blkinfo *dead_info;
+ struct xfs_da_blkinfo *sib_info;
+ struct xfs_da_intnode *par_node;
+ struct xfs_da_intnode *dead_node;
+ struct xfs_dir2_leaf *dead_leaf2;
+ struct xfs_da_node_entry *btree;
+ struct xfs_da3_icnode_hdr par_hdr;
+ struct xfs_inode *dp;
+ struct xfs_trans *tp;
+ struct xfs_mount *mp;
+ struct xfs_buf *dead_buf;
+ struct xfs_buf *last_buf;
+ struct xfs_buf *sib_buf;
+ struct xfs_buf *par_buf;
+ xfs_dahash_t dead_hash;
+ xfs_fileoff_t lastoff;
+ xfs_dablk_t dead_blkno;
+ xfs_dablk_t last_blkno;
+ xfs_dablk_t sib_blkno;
+ xfs_dablk_t par_blkno;
+ int error;
+ int w;
+ int entno;
+ int level;
+ int dead_level;
trace_xfs_da_swap_lastblock(args);
dead_buf = *dead_bufp;
dead_blkno = *dead_blknop;
tp = args->trans;
- ip = args->dp;
+ dp = args->dp;
w = args->whichfork;
ASSERT(w == XFS_DATA_FORK);
- mp = ip->i_mount;
- lastoff = mp->m_dirfreeblk;
- error = xfs_bmap_last_before(tp, ip, &lastoff, w);
+ mp = dp->i_mount;
+ lastoff = args->geo->freeblk;
+ error = xfs_bmap_last_before(tp, dp, &lastoff, w);
if (error)
return error;
if (unlikely(lastoff == 0)) {
@@ -1738,36 +2163,47 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
/*
* Read the last block in the btree space.
*/
- last_blkno = (xfs_dablk_t)lastoff - mp->m_dirblkfsbs;
- if ((error = xfs_da_read_buf(tp, ip, last_blkno, -1, &last_buf, w)))
+ last_blkno = (xfs_dablk_t)lastoff - args->geo->fsbcount;
+ error = xfs_da3_node_read(tp, dp, last_blkno, -1, &last_buf, w);
+ if (error)
return error;
/*
* Copy the last block into the dead buffer and log it.
*/
- memcpy(dead_buf->data, last_buf->data, mp->m_dirblksize);
- xfs_da_log_buf(tp, dead_buf, 0, mp->m_dirblksize - 1);
- dead_info = dead_buf->data;
+ memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize);
+ xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1);
+ dead_info = dead_buf->b_addr;
/*
* Get values from the moved block.
*/
- if (dead_info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)) {
+ if (dead_info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
+ dead_info->magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
+ struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_dir2_leaf_entry *ents;
+
dead_leaf2 = (xfs_dir2_leaf_t *)dead_info;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, dead_leaf2);
+ ents = dp->d_ops->leaf_ents_p(dead_leaf2);
dead_level = 0;
- dead_hash = be32_to_cpu(dead_leaf2->ents[be16_to_cpu(dead_leaf2->hdr.count) - 1].hashval);
+ dead_hash = be32_to_cpu(ents[leafhdr.count - 1].hashval);
} else {
- ASSERT(dead_info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
+ struct xfs_da3_icnode_hdr deadhdr;
+
dead_node = (xfs_da_intnode_t *)dead_info;
- dead_level = be16_to_cpu(dead_node->hdr.level);
- dead_hash = be32_to_cpu(dead_node->btree[be16_to_cpu(dead_node->hdr.count) - 1].hashval);
+ dp->d_ops->node_hdr_from_disk(&deadhdr, dead_node);
+ btree = dp->d_ops->node_tree_p(dead_node);
+ dead_level = deadhdr.level;
+ dead_hash = be32_to_cpu(btree[deadhdr.count - 1].hashval);
}
sib_buf = par_buf = NULL;
/*
* If the moved block has a left sibling, fix up the pointers.
*/
if ((sib_blkno = be32_to_cpu(dead_info->back))) {
- if ((error = xfs_da_read_buf(tp, ip, sib_blkno, -1, &sib_buf, w)))
+ error = xfs_da3_node_read(tp, dp, sib_blkno, -1, &sib_buf, w);
+ if (error)
goto done;
- sib_info = sib_buf->data;
+ sib_info = sib_buf->b_addr;
if (unlikely(
be32_to_cpu(sib_info->forw) != last_blkno ||
sib_info->magic != dead_info->magic)) {
@@ -1777,19 +2213,19 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
goto done;
}
sib_info->forw = cpu_to_be32(dead_blkno);
- xfs_da_log_buf(tp, sib_buf,
+ xfs_trans_log_buf(tp, sib_buf,
XFS_DA_LOGRANGE(sib_info, &sib_info->forw,
sizeof(sib_info->forw)));
- xfs_da_buf_done(sib_buf);
sib_buf = NULL;
}
/*
* If the moved block has a right sibling, fix up the pointers.
*/
if ((sib_blkno = be32_to_cpu(dead_info->forw))) {
- if ((error = xfs_da_read_buf(tp, ip, sib_blkno, -1, &sib_buf, w)))
+ error = xfs_da3_node_read(tp, dp, sib_blkno, -1, &sib_buf, w);
+ if (error)
goto done;
- sib_info = sib_buf->data;
+ sib_info = sib_buf->b_addr;
if (unlikely(
be32_to_cpu(sib_info->back) != last_blkno ||
sib_info->magic != dead_info->magic)) {
@@ -1799,45 +2235,45 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
goto done;
}
sib_info->back = cpu_to_be32(dead_blkno);
- xfs_da_log_buf(tp, sib_buf,
+ xfs_trans_log_buf(tp, sib_buf,
XFS_DA_LOGRANGE(sib_info, &sib_info->back,
sizeof(sib_info->back)));
- xfs_da_buf_done(sib_buf);
sib_buf = NULL;
}
- par_blkno = mp->m_dirleafblk;
+ par_blkno = args->geo->leafblk;
level = -1;
/*
* Walk down the tree looking for the parent of the moved block.
*/
for (;;) {
- if ((error = xfs_da_read_buf(tp, ip, par_blkno, -1, &par_buf, w)))
+ error = xfs_da3_node_read(tp, dp, par_blkno, -1, &par_buf, w);
+ if (error)
goto done;
- par_node = par_buf->data;
- if (unlikely(par_node->hdr.info.magic !=
- cpu_to_be16(XFS_DA_NODE_MAGIC) ||
- (level >= 0 && level != be16_to_cpu(par_node->hdr.level) + 1))) {
+ par_node = par_buf->b_addr;
+ dp->d_ops->node_hdr_from_disk(&par_hdr, par_node);
+ if (level >= 0 && level != par_hdr.level + 1) {
XFS_ERROR_REPORT("xfs_da_swap_lastblock(4)",
XFS_ERRLEVEL_LOW, mp);
error = XFS_ERROR(EFSCORRUPTED);
goto done;
}
- level = be16_to_cpu(par_node->hdr.level);
+ level = par_hdr.level;
+ btree = dp->d_ops->node_tree_p(par_node);
for (entno = 0;
- entno < be16_to_cpu(par_node->hdr.count) &&
- be32_to_cpu(par_node->btree[entno].hashval) < dead_hash;
+ entno < par_hdr.count &&
+ be32_to_cpu(btree[entno].hashval) < dead_hash;
entno++)
continue;
- if (unlikely(entno == be16_to_cpu(par_node->hdr.count))) {
+ if (entno == par_hdr.count) {
XFS_ERROR_REPORT("xfs_da_swap_lastblock(5)",
XFS_ERRLEVEL_LOW, mp);
error = XFS_ERROR(EFSCORRUPTED);
goto done;
}
- par_blkno = be32_to_cpu(par_node->btree[entno].before);
+ par_blkno = be32_to_cpu(btree[entno].before);
if (level == dead_level + 1)
break;
- xfs_da_brelse(tp, par_buf);
+ xfs_trans_brelse(tp, par_buf);
par_buf = NULL;
}
/*
@@ -1846,14 +2282,14 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
*/
for (;;) {
for (;
- entno < be16_to_cpu(par_node->hdr.count) &&
- be32_to_cpu(par_node->btree[entno].before) != last_blkno;
+ entno < par_hdr.count &&
+ be32_to_cpu(btree[entno].before) != last_blkno;
entno++)
continue;
- if (entno < be16_to_cpu(par_node->hdr.count))
+ if (entno < par_hdr.count)
break;
- par_blkno = be32_to_cpu(par_node->hdr.info.forw);
- xfs_da_brelse(tp, par_buf);
+ par_blkno = par_hdr.forw;
+ xfs_trans_brelse(tp, par_buf);
par_buf = NULL;
if (unlikely(par_blkno == 0)) {
XFS_ERROR_REPORT("xfs_da_swap_lastblock(6)",
@@ -1861,37 +2297,36 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
error = XFS_ERROR(EFSCORRUPTED);
goto done;
}
- if ((error = xfs_da_read_buf(tp, ip, par_blkno, -1, &par_buf, w)))
+ error = xfs_da3_node_read(tp, dp, par_blkno, -1, &par_buf, w);
+ if (error)
goto done;
- par_node = par_buf->data;
- if (unlikely(
- be16_to_cpu(par_node->hdr.level) != level ||
- par_node->hdr.info.magic != cpu_to_be16(XFS_DA_NODE_MAGIC))) {
+ par_node = par_buf->b_addr;
+ dp->d_ops->node_hdr_from_disk(&par_hdr, par_node);
+ if (par_hdr.level != level) {
XFS_ERROR_REPORT("xfs_da_swap_lastblock(7)",
XFS_ERRLEVEL_LOW, mp);
error = XFS_ERROR(EFSCORRUPTED);
goto done;
}
+ btree = dp->d_ops->node_tree_p(par_node);
entno = 0;
}
/*
* Update the parent entry pointing to the moved block.
*/
- par_node->btree[entno].before = cpu_to_be32(dead_blkno);
- xfs_da_log_buf(tp, par_buf,
- XFS_DA_LOGRANGE(par_node, &par_node->btree[entno].before,
- sizeof(par_node->btree[entno].before)));
- xfs_da_buf_done(par_buf);
- xfs_da_buf_done(dead_buf);
+ btree[entno].before = cpu_to_be32(dead_blkno);
+ xfs_trans_log_buf(tp, par_buf,
+ XFS_DA_LOGRANGE(par_node, &btree[entno].before,
+ sizeof(btree[entno].before)));
*dead_blknop = last_blkno;
*dead_bufp = last_buf;
return 0;
done:
if (par_buf)
- xfs_da_brelse(tp, par_buf);
+ xfs_trans_brelse(tp, par_buf);
if (sib_buf)
- xfs_da_brelse(tp, sib_buf);
- xfs_da_brelse(tp, last_buf);
+ xfs_trans_brelse(tp, sib_buf);
+ xfs_trans_brelse(tp, last_buf);
return error;
}
@@ -1899,8 +2334,10 @@ done:
* Remove a btree block from a directory or attribute.
*/
int
-xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
- xfs_dabuf_t *dead_buf)
+xfs_da_shrink_inode(
+ xfs_da_args_t *args,
+ xfs_dablk_t dead_blkno,
+ struct xfs_buf *dead_buf)
{
xfs_inode_t *dp;
int done, error, w, count;
@@ -1913,29 +2350,27 @@ xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
w = args->whichfork;
tp = args->trans;
mp = dp->i_mount;
- if (w == XFS_DATA_FORK)
- count = mp->m_dirblkfsbs;
- else
- count = 1;
+ count = args->geo->fsbcount;
for (;;) {
/*
* Remove extents. If we get ENOSPC for a dir we have to move
* the last block to the place we want to kill.
*/
- if ((error = xfs_bunmapi(tp, dp, dead_blkno, count,
- xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
- 0, args->firstblock, args->flist,
- &done)) == ENOSPC) {
+ error = xfs_bunmapi(tp, dp, dead_blkno, count,
+ xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
+ 0, args->firstblock, args->flist, &done);
+ if (error == ENOSPC) {
if (w != XFS_DATA_FORK)
break;
- if ((error = xfs_da_swap_lastblock(args, &dead_blkno,
- &dead_buf)))
+ error = xfs_da3_swap_lastblock(args, &dead_blkno,
+ &dead_buf);
+ if (error)
break;
} else {
break;
}
}
- xfs_da_binval(tp, dead_buf);
+ xfs_trans_binval(tp, dead_buf);
return error;
}
@@ -1967,35 +2402,78 @@ xfs_da_map_covers_blocks(
}
/*
- * Make a dabuf.
- * Used for get_buf, read_buf, read_bufr, and reada_buf.
+ * Convert a struct xfs_bmbt_irec to a struct xfs_buf_map.
+ *
+ * For the single map case, it is assumed that the caller has provided a pointer
+ * to a valid xfs_buf_map. For the multiple map case, this function will
+ * allocate the xfs_buf_map to hold all the maps and replace the caller's single
+ * map pointer with the allocated map.
*/
-STATIC int
-xfs_da_do_buf(
- xfs_trans_t *trans,
- xfs_inode_t *dp,
- xfs_dablk_t bno,
- xfs_daddr_t *mappedbnop,
- xfs_dabuf_t **bpp,
- int whichfork,
- int caller)
+static int
+xfs_buf_map_from_irec(
+ struct xfs_mount *mp,
+ struct xfs_buf_map **mapp,
+ int *nmaps,
+ struct xfs_bmbt_irec *irecs,
+ int nirecs)
{
- xfs_buf_t *bp = NULL;
- xfs_buf_t **bplist;
- int error=0;
- int i;
- xfs_bmbt_irec_t map;
- xfs_bmbt_irec_t *mapp;
- xfs_daddr_t mappedbno;
- xfs_mount_t *mp;
- int nbplist=0;
- int nfsb;
- int nmap;
- xfs_dabuf_t *rbp;
+ struct xfs_buf_map *map;
+ int i;
+
+ ASSERT(*nmaps == 1);
+ ASSERT(nirecs >= 1);
+
+ if (nirecs > 1) {
+ map = kmem_zalloc(nirecs * sizeof(struct xfs_buf_map),
+ KM_SLEEP | KM_NOFS);
+ if (!map)
+ return ENOMEM;
+ *mapp = map;
+ }
+
+ *nmaps = nirecs;
+ map = *mapp;
+ for (i = 0; i < *nmaps; i++) {
+ ASSERT(irecs[i].br_startblock != DELAYSTARTBLOCK &&
+ irecs[i].br_startblock != HOLESTARTBLOCK);
+ map[i].bm_bn = XFS_FSB_TO_DADDR(mp, irecs[i].br_startblock);
+ map[i].bm_len = XFS_FSB_TO_BB(mp, irecs[i].br_blockcount);
+ }
+ return 0;
+}
+
+/*
+ * Map the block we are given ready for reading. There are three possible return
+ * values:
+ * -1 - will be returned if we land in a hole and mappedbno == -2 so the
+ * caller knows not to execute a subsequent read.
+ * 0 - if we mapped the block successfully
+ * >0 - positive error number if there was an error.
+ */
+static int
+xfs_dabuf_map(
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
+ xfs_daddr_t mappedbno,
+ int whichfork,
+ struct xfs_buf_map **map,
+ int *nmaps)
+{
+ struct xfs_mount *mp = dp->i_mount;
+ int nfsb;
+ int error = 0;
+ struct xfs_bmbt_irec irec;
+ struct xfs_bmbt_irec *irecs = &irec;
+ int nirecs;
+
+ ASSERT(map && *map);
+ ASSERT(*nmaps == 1);
+
+ if (whichfork == XFS_DATA_FORK)
+ nfsb = mp->m_dir_geo->fsbcount;
+ else
+ nfsb = mp->m_attr_geo->fsbcount;
- mp = dp->i_mount;
- nfsb = (whichfork == XFS_DATA_FORK) ? mp->m_dirblkfsbs : 1;
- mappedbno = *mappedbnop;
/*
* Caller doesn't have a mapping. -2 means don't complain
* if we land in a hole.
@@ -2004,154 +2482,50 @@ xfs_da_do_buf(
/*
* Optimize the one-block case.
*/
- if (nfsb == 1)
- mapp = &map;
- else
- mapp = kmem_alloc(sizeof(*mapp) * nfsb, KM_SLEEP);
+ if (nfsb != 1)
+ irecs = kmem_zalloc(sizeof(irec) * nfsb,
+ KM_SLEEP | KM_NOFS);
- nmap = nfsb;
- error = xfs_bmapi_read(dp, (xfs_fileoff_t)bno, nfsb, mapp,
- &nmap, xfs_bmapi_aflag(whichfork));
+ nirecs = nfsb;
+ error = xfs_bmapi_read(dp, (xfs_fileoff_t)bno, nfsb, irecs,
+ &nirecs, xfs_bmapi_aflag(whichfork));
if (error)
- goto exit0;
+ goto out;
} else {
- map.br_startblock = XFS_DADDR_TO_FSB(mp, mappedbno);
- map.br_startoff = (xfs_fileoff_t)bno;
- map.br_blockcount = nfsb;
- mapp = &map;
- nmap = 1;
+ irecs->br_startblock = XFS_DADDR_TO_FSB(mp, mappedbno);
+ irecs->br_startoff = (xfs_fileoff_t)bno;
+ irecs->br_blockcount = nfsb;
+ irecs->br_state = 0;
+ nirecs = 1;
}
- if (!xfs_da_map_covers_blocks(nmap, mapp, bno, nfsb)) {
- error = mappedbno == -2 ? 0 : XFS_ERROR(EFSCORRUPTED);
+
+ if (!xfs_da_map_covers_blocks(nirecs, irecs, bno, nfsb)) {
+ error = mappedbno == -2 ? -1 : XFS_ERROR(EFSCORRUPTED);
if (unlikely(error == EFSCORRUPTED)) {
if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
+ int i;
xfs_alert(mp, "%s: bno %lld dir: inode %lld",
__func__, (long long)bno,
(long long)dp->i_ino);
- for (i = 0; i < nmap; i++) {
+ for (i = 0; i < *nmaps; i++) {
xfs_alert(mp,
"[%02d] br_startoff %lld br_startblock %lld br_blockcount %lld br_state %d",
i,
- (long long)mapp[i].br_startoff,
- (long long)mapp[i].br_startblock,
- (long long)mapp[i].br_blockcount,
- mapp[i].br_state);
+ (long long)irecs[i].br_startoff,
+ (long long)irecs[i].br_startblock,
+ (long long)irecs[i].br_blockcount,
+ irecs[i].br_state);
}
}
XFS_ERROR_REPORT("xfs_da_do_buf(1)",
XFS_ERRLEVEL_LOW, mp);
}
- goto exit0;
- }
- if (caller != 3 && nmap > 1) {
- bplist = kmem_alloc(sizeof(*bplist) * nmap, KM_SLEEP);
- nbplist = 0;
- } else
- bplist = NULL;
- /*
- * Turn the mapping(s) into buffer(s).
- */
- for (i = 0; i < nmap; i++) {
- int nmapped;
-
- mappedbno = XFS_FSB_TO_DADDR(mp, mapp[i].br_startblock);
- if (i == 0)
- *mappedbnop = mappedbno;
- nmapped = (int)XFS_FSB_TO_BB(mp, mapp[i].br_blockcount);
- switch (caller) {
- case 0:
- bp = xfs_trans_get_buf(trans, mp->m_ddev_targp,
- mappedbno, nmapped, 0);
- error = bp ? bp->b_error : XFS_ERROR(EIO);
- break;
- case 1:
- case 2:
- bp = NULL;
- error = xfs_trans_read_buf(mp, trans, mp->m_ddev_targp,
- mappedbno, nmapped, 0, &bp);
- break;
- case 3:
- xfs_buf_readahead(mp->m_ddev_targp, mappedbno, nmapped);
- error = 0;
- bp = NULL;
- break;
- }
- if (error) {
- if (bp)
- xfs_trans_brelse(trans, bp);
- goto exit1;
- }
- if (!bp)
- continue;
- if (caller == 1) {
- if (whichfork == XFS_ATTR_FORK)
- xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
- else
- xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
- }
- if (bplist) {
- bplist[nbplist++] = bp;
- }
- }
- /*
- * Build a dabuf structure.
- */
- if (bplist) {
- rbp = xfs_da_buf_make(nbplist, bplist);
- } else if (bp)
- rbp = xfs_da_buf_make(1, &bp);
- else
- rbp = NULL;
- /*
- * For read_buf, check the magic number.
- */
- if (caller == 1) {
- xfs_dir2_data_hdr_t *hdr = rbp->data;
- xfs_dir2_free_t *free = rbp->data;
- xfs_da_blkinfo_t *info = rbp->data;
- uint magic, magic1;
-
- magic = be16_to_cpu(info->magic);
- magic1 = be32_to_cpu(hdr->magic);
- if (unlikely(
- XFS_TEST_ERROR((magic != XFS_DA_NODE_MAGIC) &&
- (magic != XFS_ATTR_LEAF_MAGIC) &&
- (magic != XFS_DIR2_LEAF1_MAGIC) &&
- (magic != XFS_DIR2_LEAFN_MAGIC) &&
- (magic1 != XFS_DIR2_BLOCK_MAGIC) &&
- (magic1 != XFS_DIR2_DATA_MAGIC) &&
- (free->hdr.magic != cpu_to_be32(XFS_DIR2_FREE_MAGIC)),
- mp, XFS_ERRTAG_DA_READ_BUF,
- XFS_RANDOM_DA_READ_BUF))) {
- trace_xfs_da_btree_corrupt(rbp->bps[0], _RET_IP_);
- XFS_CORRUPTION_ERROR("xfs_da_do_buf(2)",
- XFS_ERRLEVEL_LOW, mp, info);
- error = XFS_ERROR(EFSCORRUPTED);
- xfs_da_brelse(trans, rbp);
- nbplist = 0;
- goto exit1;
- }
- }
- if (bplist) {
- kmem_free(bplist);
- }
- if (mapp != &map) {
- kmem_free(mapp);
- }
- if (bpp)
- *bpp = rbp;
- return 0;
-exit1:
- if (bplist) {
- for (i = 0; i < nbplist; i++)
- xfs_trans_brelse(trans, bplist[i]);
- kmem_free(bplist);
+ goto out;
}
-exit0:
- if (mapp != &map)
- kmem_free(mapp);
- if (bpp)
- *bpp = NULL;
+ error = xfs_buf_map_from_irec(mp, map, nmaps, irecs, nirecs);
+out:
+ if (irecs != &irec)
+ kmem_free(irecs);
return error;
}
@@ -2160,285 +2534,132 @@ exit0:
*/
int
xfs_da_get_buf(
- xfs_trans_t *trans,
- xfs_inode_t *dp,
- xfs_dablk_t bno,
- xfs_daddr_t mappedbno,
- xfs_dabuf_t **bpp,
- int whichfork)
-{
- return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 0);
-}
-
-/*
- * Get a buffer for the dir/attr block, fill in the contents.
- */
-int
-xfs_da_read_buf(
- xfs_trans_t *trans,
- xfs_inode_t *dp,
- xfs_dablk_t bno,
+ struct xfs_trans *trans,
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
xfs_daddr_t mappedbno,
- xfs_dabuf_t **bpp,
- int whichfork)
-{
- return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 1);
-}
-
-/*
- * Readahead the dir/attr block.
- */
-xfs_daddr_t
-xfs_da_reada_buf(
- xfs_trans_t *trans,
- xfs_inode_t *dp,
- xfs_dablk_t bno,
- int whichfork)
+ struct xfs_buf **bpp,
+ int whichfork)
{
- xfs_daddr_t rval;
+ struct xfs_buf *bp;
+ struct xfs_buf_map map;
+ struct xfs_buf_map *mapp;
+ int nmap;
+ int error;
- rval = -1;
- if (xfs_da_do_buf(trans, dp, bno, &rval, NULL, whichfork, 3))
- return -1;
- else
- return rval;
-}
+ *bpp = NULL;
+ mapp = &map;
+ nmap = 1;
+ error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
+ &mapp, &nmap);
+ if (error) {
+ /* mapping a hole is not an error, but we don't continue */
+ if (error == -1)
+ error = 0;
+ goto out_free;
+ }
-kmem_zone_t *xfs_da_state_zone; /* anchor for state struct zone */
-kmem_zone_t *xfs_dabuf_zone; /* dabuf zone */
+ bp = xfs_trans_get_buf_map(trans, dp->i_mount->m_ddev_targp,
+ mapp, nmap, 0);
+ error = bp ? bp->b_error : XFS_ERROR(EIO);
+ if (error) {
+ xfs_trans_brelse(trans, bp);
+ goto out_free;
+ }
-/*
- * Allocate a dir-state structure.
- * We don't put them on the stack since they're large.
- */
-xfs_da_state_t *
-xfs_da_state_alloc(void)
-{
- return kmem_zone_zalloc(xfs_da_state_zone, KM_NOFS);
-}
+ *bpp = bp;
-/*
- * Kill the altpath contents of a da-state structure.
- */
-STATIC void
-xfs_da_state_kill_altpath(xfs_da_state_t *state)
-{
- int i;
+out_free:
+ if (mapp != &map)
+ kmem_free(mapp);
- for (i = 0; i < state->altpath.active; i++) {
- if (state->altpath.blk[i].bp) {
- if (state->altpath.blk[i].bp != state->path.blk[i].bp)
- xfs_da_buf_done(state->altpath.blk[i].bp);
- state->altpath.blk[i].bp = NULL;
- }
- }
- state->altpath.active = 0;
+ return error;
}
/*
- * Free a da-state structure.
+ * Get a buffer for the dir/attr block, fill in the contents.
*/
-void
-xfs_da_state_free(xfs_da_state_t *state)
+int
+xfs_da_read_buf(
+ struct xfs_trans *trans,
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
+ xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp,
+ int whichfork,
+ const struct xfs_buf_ops *ops)
{
- int i;
+ struct xfs_buf *bp;
+ struct xfs_buf_map map;
+ struct xfs_buf_map *mapp;
+ int nmap;
+ int error;
- xfs_da_state_kill_altpath(state);
- for (i = 0; i < state->path.active; i++) {
- if (state->path.blk[i].bp)
- xfs_da_buf_done(state->path.blk[i].bp);
+ *bpp = NULL;
+ mapp = &map;
+ nmap = 1;
+ error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
+ &mapp, &nmap);
+ if (error) {
+ /* mapping a hole is not an error, but we don't continue */
+ if (error == -1)
+ error = 0;
+ goto out_free;
}
- if (state->extravalid && state->extrablk.bp)
- xfs_da_buf_done(state->extrablk.bp);
-#ifdef DEBUG
- memset((char *)state, 0, sizeof(*state));
-#endif /* DEBUG */
- kmem_zone_free(xfs_da_state_zone, state);
-}
-/*
- * Create a dabuf.
- */
-/* ARGSUSED */
-STATIC xfs_dabuf_t *
-xfs_da_buf_make(int nbuf, xfs_buf_t **bps)
-{
- xfs_buf_t *bp;
- xfs_dabuf_t *dabuf;
- int i;
- int off;
+ error = xfs_trans_read_buf_map(dp->i_mount, trans,
+ dp->i_mount->m_ddev_targp,
+ mapp, nmap, 0, &bp, ops);
+ if (error)
+ goto out_free;
- if (nbuf == 1)
- dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
+ if (whichfork == XFS_ATTR_FORK)
+ xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
else
- dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS);
- dabuf->dirty = 0;
- if (nbuf == 1) {
- dabuf->nbuf = 1;
- bp = bps[0];
- dabuf->bbcount = bp->b_length;
- dabuf->data = bp->b_addr;
- dabuf->bps[0] = bp;
- } else {
- dabuf->nbuf = nbuf;
- for (i = 0, dabuf->bbcount = 0; i < nbuf; i++) {
- dabuf->bps[i] = bp = bps[i];
- dabuf->bbcount += bp->b_length;
- }
- dabuf->data = kmem_alloc(BBTOB(dabuf->bbcount), KM_SLEEP);
- for (i = off = 0; i < nbuf; i++, off += BBTOB(bp->b_length)) {
- bp = bps[i];
- memcpy((char *)dabuf->data + off, bp->b_addr,
- BBTOB(bp->b_length));
- }
- }
- return dabuf;
-}
-
-/*
- * Un-dirty a dabuf.
- */
-STATIC void
-xfs_da_buf_clean(xfs_dabuf_t *dabuf)
-{
- xfs_buf_t *bp;
- int i;
- int off;
-
- if (dabuf->dirty) {
- ASSERT(dabuf->nbuf > 1);
- dabuf->dirty = 0;
- for (i = off = 0; i < dabuf->nbuf;
- i++, off += BBTOB(bp->b_length)) {
- bp = dabuf->bps[i];
- memcpy(bp->b_addr, dabuf->data + off,
- BBTOB(bp->b_length));
- }
- }
-}
-
-/*
- * Release a dabuf.
- */
-void
-xfs_da_buf_done(xfs_dabuf_t *dabuf)
-{
- ASSERT(dabuf);
- ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
- if (dabuf->dirty)
- xfs_da_buf_clean(dabuf);
- if (dabuf->nbuf > 1) {
- kmem_free(dabuf->data);
- kmem_free(dabuf);
- } else {
- kmem_zone_free(xfs_dabuf_zone, dabuf);
- }
-}
-
-/*
- * Log transaction from a dabuf.
- */
-void
-xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last)
-{
- xfs_buf_t *bp;
- uint f;
- int i;
- uint l;
- int off;
+ xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
+ *bpp = bp;
+out_free:
+ if (mapp != &map)
+ kmem_free(mapp);
- ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
- if (dabuf->nbuf == 1) {
- ASSERT(dabuf->data == dabuf->bps[0]->b_addr);
- xfs_trans_log_buf(tp, dabuf->bps[0], first, last);
- return;
- }
- dabuf->dirty = 1;
- ASSERT(first <= last);
- for (i = off = 0; i < dabuf->nbuf; i++, off += BBTOB(bp->b_length)) {
- bp = dabuf->bps[i];
- f = off;
- l = f + BBTOB(bp->b_length) - 1;
- if (f < first)
- f = first;
- if (l > last)
- l = last;
- if (f <= l)
- xfs_trans_log_buf(tp, bp, f - off, l - off);
- /*
- * B_DONE is set by xfs_trans_log buf.
- * If we don't set it on a new buffer (get not read)
- * then if we don't put anything in the buffer it won't
- * be set, and at commit it it released into the cache,
- * and then a read will fail.
- */
- else if (!(XFS_BUF_ISDONE(bp)))
- XFS_BUF_DONE(bp);
- }
- ASSERT(last < off);
+ return error;
}
/*
- * Release dabuf from a transaction.
- * Have to free up the dabuf before the buffers are released,
- * since the synchronization on the dabuf is really the lock on the buffer.
+ * Readahead the dir/attr block.
*/
-void
-xfs_da_brelse(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
+xfs_daddr_t
+xfs_da_reada_buf(
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
+ xfs_daddr_t mappedbno,
+ int whichfork,
+ const struct xfs_buf_ops *ops)
{
- xfs_buf_t *bp;
- xfs_buf_t **bplist;
- int i;
- int nbuf;
+ struct xfs_buf_map map;
+ struct xfs_buf_map *mapp;
+ int nmap;
+ int error;
- ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
- if ((nbuf = dabuf->nbuf) == 1) {
- bplist = &bp;
- bp = dabuf->bps[0];
- } else {
- bplist = kmem_alloc(nbuf * sizeof(*bplist), KM_SLEEP);
- memcpy(bplist, dabuf->bps, nbuf * sizeof(*bplist));
+ mapp = &map;
+ nmap = 1;
+ error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
+ &mapp, &nmap);
+ if (error) {
+ /* mapping a hole is not an error, but we don't continue */
+ if (error == -1)
+ error = 0;
+ goto out_free;
}
- xfs_da_buf_done(dabuf);
- for (i = 0; i < nbuf; i++)
- xfs_trans_brelse(tp, bplist[i]);
- if (bplist != &bp)
- kmem_free(bplist);
-}
-/*
- * Invalidate dabuf from a transaction.
- */
-void
-xfs_da_binval(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
-{
- xfs_buf_t *bp;
- xfs_buf_t **bplist;
- int i;
- int nbuf;
+ mappedbno = mapp[0].bm_bn;
+ xfs_buf_readahead_map(dp->i_mount->m_ddev_targp, mapp, nmap, ops);
- ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
- if ((nbuf = dabuf->nbuf) == 1) {
- bplist = &bp;
- bp = dabuf->bps[0];
- } else {
- bplist = kmem_alloc(nbuf * sizeof(*bplist), KM_SLEEP);
- memcpy(bplist, dabuf->bps, nbuf * sizeof(*bplist));
- }
- xfs_da_buf_done(dabuf);
- for (i = 0; i < nbuf; i++)
- xfs_trans_binval(tp, bplist[i]);
- if (bplist != &bp)
- kmem_free(bplist);
-}
+out_free:
+ if (mapp != &map)
+ kmem_free(mapp);
-/*
- * Get the first daddr from a dabuf.
- */
-xfs_daddr_t
-xfs_da_blkno(xfs_dabuf_t *dabuf)
-{
- ASSERT(dabuf->nbuf);
- ASSERT(dabuf->data);
- return XFS_BUF_ADDR(dabuf->bps[0]);
+ if (error)
+ return -1;
+ return mappedbno;
}
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index dbf7c074ae7..6e153e399a7 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -18,61 +19,28 @@
#ifndef __XFS_DA_BTREE_H__
#define __XFS_DA_BTREE_H__
-struct xfs_buf;
struct xfs_bmap_free;
struct xfs_inode;
-struct xfs_mount;
struct xfs_trans;
struct zone;
-
-/*========================================================================
- * Directory Structure when greater than XFS_LBSIZE(mp) bytes.
- *========================================================================*/
+struct xfs_dir_ops;
/*
- * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
- *
- * Is is used to manage a doubly linked list of all blocks at the same
- * level in the Btree, and to identify which type of block this is.
+ * Directory/attribute geometry information. There will be one of these for each
+ * data fork type, and it will be passed around via the xfs_da_args. Global
+ * structures will be attached to the xfs_mount.
*/
-#define XFS_DA_NODE_MAGIC 0xfebe /* magic number: non-leaf blocks */
-#define XFS_ATTR_LEAF_MAGIC 0xfbee /* magic number: attribute leaf blks */
-#define XFS_DIR2_LEAF1_MAGIC 0xd2f1 /* magic number: v2 dirlf single blks */
-#define XFS_DIR2_LEAFN_MAGIC 0xd2ff /* magic number: v2 dirlf multi blks */
-
-typedef struct xfs_da_blkinfo {
- __be32 forw; /* previous block in list */
- __be32 back; /* following block in list */
- __be16 magic; /* validity check on block */
- __be16 pad; /* unused */
-} xfs_da_blkinfo_t;
-
-/*
- * This is the structure of the root and intermediate nodes in the Btree.
- * The leaf nodes are defined above.
- *
- * Entries are not packed.
- *
- * Since we have duplicate keys, use a binary search but always follow
- * all match in the block, not just the first match found.
- */
-#define XFS_DA_NODE_MAXDEPTH 5 /* max depth of Btree */
-
-typedef struct xfs_da_intnode {
- struct xfs_da_node_hdr { /* constant-structure header block */
- xfs_da_blkinfo_t info; /* block type, links, etc. */
- __be16 count; /* count of active entries */
- __be16 level; /* level above leaves (leaf == 0) */
- } hdr;
- struct xfs_da_node_entry {
- __be32 hashval; /* hash value for this descendant */
- __be32 before; /* Btree block before this key */
- } btree[1]; /* variable sized array of keys */
-} xfs_da_intnode_t;
-typedef struct xfs_da_node_hdr xfs_da_node_hdr_t;
-typedef struct xfs_da_node_entry xfs_da_node_entry_t;
-
-#define XFS_LBSIZE(mp) (mp)->m_sb.sb_blocksize
+struct xfs_da_geometry {
+ int blksize; /* da block size in bytes */
+ int fsbcount; /* da block size in filesystem blocks */
+ uint8_t fsblog; /* log2 of _filesystem_ block size */
+ uint8_t blklog; /* log2 of da block size */
+ uint node_ents; /* # of entries in a danode */
+ int magicpct; /* 37% of block size in bytes */
+ xfs_dablk_t datablk; /* blockno of dir data v2 */
+ xfs_dablk_t leafblk; /* blockno of leaf data v2 */
+ xfs_dablk_t freeblk; /* blockno of free data v2 */
+};
/*========================================================================
* Btree searching and modification structure definitions.
@@ -91,8 +59,10 @@ enum xfs_dacmp {
* Structure to ease passing around component names.
*/
typedef struct xfs_da_args {
+ struct xfs_da_geometry *geo; /* da block geometry */
const __uint8_t *name; /* string (maybe not NULL terminated) */
int namelen; /* length of string (maybe no NULL) */
+ __uint8_t filetype; /* filetype of inode for directories */
__uint8_t *value; /* set of bytes (maybe contain NULLs) */
int valuelen; /* length of value */
int flags; /* argument flags (eg: ATTR_NOCREATE) */
@@ -108,10 +78,12 @@ typedef struct xfs_da_args {
int index; /* index of attr of interest in blk */
xfs_dablk_t rmtblkno; /* remote attr value starting blkno */
int rmtblkcnt; /* remote attr value block count */
+ int rmtvaluelen; /* remote attr value length in bytes */
xfs_dablk_t blkno2; /* blkno of 2nd attr leaf of interest */
int index2; /* index of 2nd attr in blk */
xfs_dablk_t rmtblkno2; /* remote attr value starting blkno */
int rmtblkcnt2; /* remote attr value block count */
+ int rmtvaluelen2; /* remote attr value length in bytes */
int op_flags; /* operation flags */
enum xfs_dacmp cmpresult; /* name compare result for lookups */
} xfs_da_args_t;
@@ -133,24 +105,6 @@ typedef struct xfs_da_args {
{ XFS_DA_OP_CILOOKUP, "CILOOKUP" }
/*
- * Structure to describe buffer(s) for a block.
- * This is needed in the directory version 2 format case, when
- * multiple non-contiguous fsblocks might be needed to cover one
- * logical directory block.
- * If the buffer count is 1 then the data pointer points to the
- * same place as the b_addr field for the buffer, else to kmem_alloced memory.
- */
-typedef struct xfs_dabuf {
- int nbuf; /* number of buffer pointers present */
- short dirty; /* data needs to be copied back */
- short bbcount; /* how large is data in bbs */
- void *data; /* pointer for buffers' data */
- struct xfs_buf *bps[1]; /* actually nbuf of these */
-} xfs_dabuf_t;
-#define XFS_DA_BUF_SIZE(n) \
- (sizeof(xfs_dabuf_t) + sizeof(struct xfs_buf *) * ((n) - 1))
-
-/*
* Storage for holding state during Btree searches and split/join ops.
*
* Only need space for 5 intermediate nodes. With a minimum of 62-way
@@ -158,7 +112,7 @@ typedef struct xfs_dabuf {
* which is slightly more than enough.
*/
typedef struct xfs_da_state_blk {
- xfs_dabuf_t *bp; /* buffer containing block */
+ struct xfs_buf *bp; /* buffer containing block */
xfs_dablk_t blkno; /* filesystem blkno of buffer */
xfs_daddr_t disk_blkno; /* on-disk blkno (in BBs) of buffer */
int index; /* relevant index into block */
@@ -174,8 +128,6 @@ typedef struct xfs_da_state_path {
typedef struct xfs_da_state {
xfs_da_args_t *args; /* filename arguments */
struct xfs_mount *mp; /* filesystem mount point */
- unsigned int blocksize; /* logical block size */
- unsigned int node_ents; /* how many entries in danode */
xfs_da_state_path_t path; /* search/split paths */
xfs_da_state_path_t altpath; /* alternate path for join */
unsigned char inleaf; /* insert into 1->lf, 0->splf */
@@ -210,28 +162,31 @@ struct xfs_nameops {
/*
* Routines used for growing the Btree.
*/
-int xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
- xfs_dabuf_t **bpp, int whichfork);
-int xfs_da_split(xfs_da_state_t *state);
+int xfs_da3_node_create(struct xfs_da_args *args, xfs_dablk_t blkno,
+ int level, struct xfs_buf **bpp, int whichfork);
+int xfs_da3_split(xfs_da_state_t *state);
/*
* Routines used for shrinking the Btree.
*/
-int xfs_da_join(xfs_da_state_t *state);
-void xfs_da_fixhashpath(xfs_da_state_t *state,
- xfs_da_state_path_t *path_to_to_fix);
+int xfs_da3_join(xfs_da_state_t *state);
+void xfs_da3_fixhashpath(struct xfs_da_state *state,
+ struct xfs_da_state_path *path_to_to_fix);
/*
* Routines used for finding things in the Btree.
*/
-int xfs_da_node_lookup_int(xfs_da_state_t *state, int *result);
-int xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
+int xfs_da3_node_lookup_int(xfs_da_state_t *state, int *result);
+int xfs_da3_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
int forward, int release, int *result);
/*
* Utility routines.
*/
-int xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
+int xfs_da3_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
xfs_da_state_blk_t *new_blk);
+int xfs_da3_node_read(struct xfs_trans *tp, struct xfs_inode *dp,
+ xfs_dablk_t bno, xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp, int which_fork);
/*
* Utility routines.
@@ -241,14 +196,16 @@ int xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno,
int count);
int xfs_da_get_buf(struct xfs_trans *trans, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mappedbno,
- xfs_dabuf_t **bp, int whichfork);
+ struct xfs_buf **bp, int whichfork);
int xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
xfs_dablk_t bno, xfs_daddr_t mappedbno,
- xfs_dabuf_t **bpp, int whichfork);
-xfs_daddr_t xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
- xfs_dablk_t bno, int whichfork);
+ struct xfs_buf **bpp, int whichfork,
+ const struct xfs_buf_ops *ops);
+xfs_daddr_t xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
+ xfs_daddr_t mapped_bno, int whichfork,
+ const struct xfs_buf_ops *ops);
int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
- xfs_dabuf_t *dead_buf);
+ struct xfs_buf *dead_buf);
uint xfs_da_hashname(const __uint8_t *name_string, int name_length);
enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
@@ -258,15 +215,7 @@ enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
xfs_da_state_t *xfs_da_state_alloc(void);
void xfs_da_state_free(xfs_da_state_t *state);
-void xfs_da_buf_done(xfs_dabuf_t *dabuf);
-void xfs_da_log_buf(struct xfs_trans *tp, xfs_dabuf_t *dabuf, uint first,
- uint last);
-void xfs_da_brelse(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-void xfs_da_binval(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-xfs_daddr_t xfs_da_blkno(xfs_dabuf_t *dabuf);
-
extern struct kmem_zone *xfs_da_state_zone;
-extern struct kmem_zone *xfs_dabuf_zone;
extern const struct xfs_nameops xfs_default_nameops;
#endif /* __XFS_DA_BTREE_H__ */
diff --git a/fs/xfs/xfs_da_format.c b/fs/xfs/xfs_da_format.c
new file mode 100644
index 00000000000..c9aee52a37e
--- /dev/null
+++ b/fs/xfs/xfs_da_format.c
@@ -0,0 +1,911 @@
+/*
+ * Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_inode.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+
+/*
+ * Shortform directory ops
+ */
+static int
+xfs_dir2_sf_entsize(
+ struct xfs_dir2_sf_hdr *hdr,
+ int len)
+{
+ int count = sizeof(struct xfs_dir2_sf_entry); /* namelen + offset */
+
+ count += len; /* name */
+ count += hdr->i8count ? sizeof(xfs_dir2_ino8_t) :
+ sizeof(xfs_dir2_ino4_t); /* ino # */
+ return count;
+}
+
+static int
+xfs_dir3_sf_entsize(
+ struct xfs_dir2_sf_hdr *hdr,
+ int len)
+{
+ return xfs_dir2_sf_entsize(hdr, len) + sizeof(__uint8_t);
+}
+
+static struct xfs_dir2_sf_entry *
+xfs_dir2_sf_nextentry(
+ struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep)
+{
+ return (struct xfs_dir2_sf_entry *)
+ ((char *)sfep + xfs_dir2_sf_entsize(hdr, sfep->namelen));
+}
+
+static struct xfs_dir2_sf_entry *
+xfs_dir3_sf_nextentry(
+ struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep)
+{
+ return (struct xfs_dir2_sf_entry *)
+ ((char *)sfep + xfs_dir3_sf_entsize(hdr, sfep->namelen));
+}
+
+
+/*
+ * For filetype enabled shortform directories, the file type field is stored at
+ * the end of the name. Because it's only a single byte, endian conversion is
+ * not necessary. For non-filetype enable directories, the type is always
+ * unknown and we never store the value.
+ */
+static __uint8_t
+xfs_dir2_sfe_get_ftype(
+ struct xfs_dir2_sf_entry *sfep)
+{
+ return XFS_DIR3_FT_UNKNOWN;
+}
+
+static void
+xfs_dir2_sfe_put_ftype(
+ struct xfs_dir2_sf_entry *sfep,
+ __uint8_t ftype)
+{
+ ASSERT(ftype < XFS_DIR3_FT_MAX);
+}
+
+static __uint8_t
+xfs_dir3_sfe_get_ftype(
+ struct xfs_dir2_sf_entry *sfep)
+{
+ __uint8_t ftype;
+
+ ftype = sfep->name[sfep->namelen];
+ if (ftype >= XFS_DIR3_FT_MAX)
+ return XFS_DIR3_FT_UNKNOWN;
+ return ftype;
+}
+
+static void
+xfs_dir3_sfe_put_ftype(
+ struct xfs_dir2_sf_entry *sfep,
+ __uint8_t ftype)
+{
+ ASSERT(ftype < XFS_DIR3_FT_MAX);
+
+ sfep->name[sfep->namelen] = ftype;
+}
+
+/*
+ * Inode numbers in short-form directories can come in two versions,
+ * either 4 bytes or 8 bytes wide. These helpers deal with the
+ * two forms transparently by looking at the headers i8count field.
+ *
+ * For 64-bit inode number the most significant byte must be zero.
+ */
+static xfs_ino_t
+xfs_dir2_sf_get_ino(
+ struct xfs_dir2_sf_hdr *hdr,
+ xfs_dir2_inou_t *from)
+{
+ if (hdr->i8count)
+ return get_unaligned_be64(&from->i8.i) & 0x00ffffffffffffffULL;
+ else
+ return get_unaligned_be32(&from->i4.i);
+}
+
+static void
+xfs_dir2_sf_put_ino(
+ struct xfs_dir2_sf_hdr *hdr,
+ xfs_dir2_inou_t *to,
+ xfs_ino_t ino)
+{
+ ASSERT((ino & 0xff00000000000000ULL) == 0);
+
+ if (hdr->i8count)
+ put_unaligned_be64(ino, &to->i8.i);
+ else
+ put_unaligned_be32(ino, &to->i4.i);
+}
+
+static xfs_ino_t
+xfs_dir2_sf_get_parent_ino(
+ struct xfs_dir2_sf_hdr *hdr)
+{
+ return xfs_dir2_sf_get_ino(hdr, &hdr->parent);
+}
+
+static void
+xfs_dir2_sf_put_parent_ino(
+ struct xfs_dir2_sf_hdr *hdr,
+ xfs_ino_t ino)
+{
+ xfs_dir2_sf_put_ino(hdr, &hdr->parent, ino);
+}
+
+/*
+ * In short-form directory entries the inode numbers are stored at variable
+ * offset behind the entry name. If the entry stores a filetype value, then it
+ * sits between the name and the inode number. Hence the inode numbers may only
+ * be accessed through the helpers below.
+ */
+static xfs_ino_t
+xfs_dir2_sfe_get_ino(
+ struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep)
+{
+ return xfs_dir2_sf_get_ino(hdr,
+ (xfs_dir2_inou_t *)&sfep->name[sfep->namelen]);
+}
+
+static void
+xfs_dir2_sfe_put_ino(
+ struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep,
+ xfs_ino_t ino)
+{
+ xfs_dir2_sf_put_ino(hdr,
+ (xfs_dir2_inou_t *)&sfep->name[sfep->namelen], ino);
+}
+
+static xfs_ino_t
+xfs_dir3_sfe_get_ino(
+ struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep)
+{
+ return xfs_dir2_sf_get_ino(hdr,
+ (xfs_dir2_inou_t *)&sfep->name[sfep->namelen + 1]);
+}
+
+static void
+xfs_dir3_sfe_put_ino(
+ struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep,
+ xfs_ino_t ino)
+{
+ xfs_dir2_sf_put_ino(hdr,
+ (xfs_dir2_inou_t *)&sfep->name[sfep->namelen + 1], ino);
+}
+
+
+/*
+ * Directory data block operations
+ */
+
+/*
+ * For special situations, the dirent size ends up fixed because we always know
+ * what the size of the entry is. That's true for the "." and "..", and
+ * therefore we know that they are a fixed size and hence their offsets are
+ * constant, as is the first entry.
+ *
+ * Hence, this calculation is written as a macro to be able to be calculated at
+ * compile time and so certain offsets can be calculated directly in the
+ * structure initaliser via the macro. There are two macros - one for dirents
+ * with ftype and without so there are no unresolvable conditionals in the
+ * calculations. We also use round_up() as XFS_DIR2_DATA_ALIGN is always a power
+ * of 2 and the compiler doesn't reject it (unlike roundup()).
+ */
+#define XFS_DIR2_DATA_ENTSIZE(n) \
+ round_up((offsetof(struct xfs_dir2_data_entry, name[0]) + (n) + \
+ sizeof(xfs_dir2_data_off_t)), XFS_DIR2_DATA_ALIGN)
+
+#define XFS_DIR3_DATA_ENTSIZE(n) \
+ round_up((offsetof(struct xfs_dir2_data_entry, name[0]) + (n) + \
+ sizeof(xfs_dir2_data_off_t) + sizeof(__uint8_t)), \
+ XFS_DIR2_DATA_ALIGN)
+
+static int
+xfs_dir2_data_entsize(
+ int n)
+{
+ return XFS_DIR2_DATA_ENTSIZE(n);
+}
+
+static int
+xfs_dir3_data_entsize(
+ int n)
+{
+ return XFS_DIR3_DATA_ENTSIZE(n);
+}
+
+static __uint8_t
+xfs_dir2_data_get_ftype(
+ struct xfs_dir2_data_entry *dep)
+{
+ return XFS_DIR3_FT_UNKNOWN;
+}
+
+static void
+xfs_dir2_data_put_ftype(
+ struct xfs_dir2_data_entry *dep,
+ __uint8_t ftype)
+{
+ ASSERT(ftype < XFS_DIR3_FT_MAX);
+}
+
+static __uint8_t
+xfs_dir3_data_get_ftype(
+ struct xfs_dir2_data_entry *dep)
+{
+ __uint8_t ftype = dep->name[dep->namelen];
+
+ ASSERT(ftype < XFS_DIR3_FT_MAX);
+ if (ftype >= XFS_DIR3_FT_MAX)
+ return XFS_DIR3_FT_UNKNOWN;
+ return ftype;
+}
+
+static void
+xfs_dir3_data_put_ftype(
+ struct xfs_dir2_data_entry *dep,
+ __uint8_t type)
+{
+ ASSERT(type < XFS_DIR3_FT_MAX);
+ ASSERT(dep->namelen != 0);
+
+ dep->name[dep->namelen] = type;
+}
+
+/*
+ * Pointer to an entry's tag word.
+ */
+static __be16 *
+xfs_dir2_data_entry_tag_p(
+ struct xfs_dir2_data_entry *dep)
+{
+ return (__be16 *)((char *)dep +
+ xfs_dir2_data_entsize(dep->namelen) - sizeof(__be16));
+}
+
+static __be16 *
+xfs_dir3_data_entry_tag_p(
+ struct xfs_dir2_data_entry *dep)
+{
+ return (__be16 *)((char *)dep +
+ xfs_dir3_data_entsize(dep->namelen) - sizeof(__be16));
+}
+
+/*
+ * location of . and .. in data space (always block 0)
+ */
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_dot_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir2_data_hdr));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_dotdot_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR2_DATA_ENTSIZE(1));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_first_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR2_DATA_ENTSIZE(1) +
+ XFS_DIR2_DATA_ENTSIZE(2));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_ftype_data_dotdot_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_ftype_data_first_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1) +
+ XFS_DIR3_DATA_ENTSIZE(2));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_dot_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir3_data_hdr));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_dotdot_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir3_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_first_entry_p(
+ struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir3_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1) +
+ XFS_DIR3_DATA_ENTSIZE(2));
+}
+
+static struct xfs_dir2_data_free *
+xfs_dir2_data_bestfree_p(struct xfs_dir2_data_hdr *hdr)
+{
+ return hdr->bestfree;
+}
+
+static struct xfs_dir2_data_free *
+xfs_dir3_data_bestfree_p(struct xfs_dir2_data_hdr *hdr)
+{
+ return ((struct xfs_dir3_data_hdr *)hdr)->best_free;
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir2_data_entry_p(struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir2_data_hdr));
+}
+
+static struct xfs_dir2_data_unused *
+xfs_dir2_data_unused_p(struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_unused *)
+ ((char *)hdr + sizeof(struct xfs_dir2_data_hdr));
+}
+
+static struct xfs_dir2_data_entry *
+xfs_dir3_data_entry_p(struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_entry *)
+ ((char *)hdr + sizeof(struct xfs_dir3_data_hdr));
+}
+
+static struct xfs_dir2_data_unused *
+xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
+{
+ return (struct xfs_dir2_data_unused *)
+ ((char *)hdr + sizeof(struct xfs_dir3_data_hdr));
+}
+
+
+/*
+ * Directory Leaf block operations
+ */
+static int
+xfs_dir2_max_leaf_ents(struct xfs_da_geometry *geo)
+{
+ return (geo->blksize - sizeof(struct xfs_dir2_leaf_hdr)) /
+ (uint)sizeof(struct xfs_dir2_leaf_entry);
+}
+
+static struct xfs_dir2_leaf_entry *
+xfs_dir2_leaf_ents_p(struct xfs_dir2_leaf *lp)
+{
+ return lp->__ents;
+}
+
+static int
+xfs_dir3_max_leaf_ents(struct xfs_da_geometry *geo)
+{
+ return (geo->blksize - sizeof(struct xfs_dir3_leaf_hdr)) /
+ (uint)sizeof(struct xfs_dir2_leaf_entry);
+}
+
+static struct xfs_dir2_leaf_entry *
+xfs_dir3_leaf_ents_p(struct xfs_dir2_leaf *lp)
+{
+ return ((struct xfs_dir3_leaf *)lp)->__ents;
+}
+
+static void
+xfs_dir2_leaf_hdr_from_disk(
+ struct xfs_dir3_icleaf_hdr *to,
+ struct xfs_dir2_leaf *from)
+{
+ to->forw = be32_to_cpu(from->hdr.info.forw);
+ to->back = be32_to_cpu(from->hdr.info.back);
+ to->magic = be16_to_cpu(from->hdr.info.magic);
+ to->count = be16_to_cpu(from->hdr.count);
+ to->stale = be16_to_cpu(from->hdr.stale);
+
+ ASSERT(to->magic == XFS_DIR2_LEAF1_MAGIC ||
+ to->magic == XFS_DIR2_LEAFN_MAGIC);
+}
+
+static void
+xfs_dir2_leaf_hdr_to_disk(
+ struct xfs_dir2_leaf *to,
+ struct xfs_dir3_icleaf_hdr *from)
+{
+ ASSERT(from->magic == XFS_DIR2_LEAF1_MAGIC ||
+ from->magic == XFS_DIR2_LEAFN_MAGIC);
+
+ to->hdr.info.forw = cpu_to_be32(from->forw);
+ to->hdr.info.back = cpu_to_be32(from->back);
+ to->hdr.info.magic = cpu_to_be16(from->magic);
+ to->hdr.count = cpu_to_be16(from->count);
+ to->hdr.stale = cpu_to_be16(from->stale);
+}
+
+static void
+xfs_dir3_leaf_hdr_from_disk(
+ struct xfs_dir3_icleaf_hdr *to,
+ struct xfs_dir2_leaf *from)
+{
+ struct xfs_dir3_leaf_hdr *hdr3 = (struct xfs_dir3_leaf_hdr *)from;
+
+ to->forw = be32_to_cpu(hdr3->info.hdr.forw);
+ to->back = be32_to_cpu(hdr3->info.hdr.back);
+ to->magic = be16_to_cpu(hdr3->info.hdr.magic);
+ to->count = be16_to_cpu(hdr3->count);
+ to->stale = be16_to_cpu(hdr3->stale);
+
+ ASSERT(to->magic == XFS_DIR3_LEAF1_MAGIC ||
+ to->magic == XFS_DIR3_LEAFN_MAGIC);
+}
+
+static void
+xfs_dir3_leaf_hdr_to_disk(
+ struct xfs_dir2_leaf *to,
+ struct xfs_dir3_icleaf_hdr *from)
+{
+ struct xfs_dir3_leaf_hdr *hdr3 = (struct xfs_dir3_leaf_hdr *)to;
+
+ ASSERT(from->magic == XFS_DIR3_LEAF1_MAGIC ||
+ from->magic == XFS_DIR3_LEAFN_MAGIC);
+
+ hdr3->info.hdr.forw = cpu_to_be32(from->forw);
+ hdr3->info.hdr.back = cpu_to_be32(from->back);
+ hdr3->info.hdr.magic = cpu_to_be16(from->magic);
+ hdr3->count = cpu_to_be16(from->count);
+ hdr3->stale = cpu_to_be16(from->stale);
+}
+
+
+/*
+ * Directory/Attribute Node block operations
+ */
+static struct xfs_da_node_entry *
+xfs_da2_node_tree_p(struct xfs_da_intnode *dap)
+{
+ return dap->__btree;
+}
+
+static struct xfs_da_node_entry *
+xfs_da3_node_tree_p(struct xfs_da_intnode *dap)
+{
+ return ((struct xfs_da3_intnode *)dap)->__btree;
+}
+
+static void
+xfs_da2_node_hdr_from_disk(
+ struct xfs_da3_icnode_hdr *to,
+ struct xfs_da_intnode *from)
+{
+ ASSERT(from->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
+ to->forw = be32_to_cpu(from->hdr.info.forw);
+ to->back = be32_to_cpu(from->hdr.info.back);
+ to->magic = be16_to_cpu(from->hdr.info.magic);
+ to->count = be16_to_cpu(from->hdr.__count);
+ to->level = be16_to_cpu(from->hdr.__level);
+}
+
+static void
+xfs_da2_node_hdr_to_disk(
+ struct xfs_da_intnode *to,
+ struct xfs_da3_icnode_hdr *from)
+{
+ ASSERT(from->magic == XFS_DA_NODE_MAGIC);
+ to->hdr.info.forw = cpu_to_be32(from->forw);
+ to->hdr.info.back = cpu_to_be32(from->back);
+ to->hdr.info.magic = cpu_to_be16(from->magic);
+ to->hdr.__count = cpu_to_be16(from->count);
+ to->hdr.__level = cpu_to_be16(from->level);
+}
+
+static void
+xfs_da3_node_hdr_from_disk(
+ struct xfs_da3_icnode_hdr *to,
+ struct xfs_da_intnode *from)
+{
+ struct xfs_da3_node_hdr *hdr3 = (struct xfs_da3_node_hdr *)from;
+
+ ASSERT(from->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC));
+ to->forw = be32_to_cpu(hdr3->info.hdr.forw);
+ to->back = be32_to_cpu(hdr3->info.hdr.back);
+ to->magic = be16_to_cpu(hdr3->info.hdr.magic);
+ to->count = be16_to_cpu(hdr3->__count);
+ to->level = be16_to_cpu(hdr3->__level);
+}
+
+static void
+xfs_da3_node_hdr_to_disk(
+ struct xfs_da_intnode *to,
+ struct xfs_da3_icnode_hdr *from)
+{
+ struct xfs_da3_node_hdr *hdr3 = (struct xfs_da3_node_hdr *)to;
+
+ ASSERT(from->magic == XFS_DA3_NODE_MAGIC);
+ hdr3->info.hdr.forw = cpu_to_be32(from->forw);
+ hdr3->info.hdr.back = cpu_to_be32(from->back);
+ hdr3->info.hdr.magic = cpu_to_be16(from->magic);
+ hdr3->__count = cpu_to_be16(from->count);
+ hdr3->__level = cpu_to_be16(from->level);
+}
+
+
+/*
+ * Directory free space block operations
+ */
+static int
+xfs_dir2_free_max_bests(struct xfs_da_geometry *geo)
+{
+ return (geo->blksize - sizeof(struct xfs_dir2_free_hdr)) /
+ sizeof(xfs_dir2_data_off_t);
+}
+
+static __be16 *
+xfs_dir2_free_bests_p(struct xfs_dir2_free *free)
+{
+ return (__be16 *)((char *)free + sizeof(struct xfs_dir2_free_hdr));
+}
+
+/*
+ * Convert data space db to the corresponding free db.
+ */
+static xfs_dir2_db_t
+xfs_dir2_db_to_fdb(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
+{
+ return xfs_dir2_byte_to_db(geo, XFS_DIR2_FREE_OFFSET) +
+ (db / xfs_dir2_free_max_bests(geo));
+}
+
+/*
+ * Convert data space db to the corresponding index in a free db.
+ */
+static int
+xfs_dir2_db_to_fdindex(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
+{
+ return db % xfs_dir2_free_max_bests(geo);
+}
+
+static int
+xfs_dir3_free_max_bests(struct xfs_da_geometry *geo)
+{
+ return (geo->blksize - sizeof(struct xfs_dir3_free_hdr)) /
+ sizeof(xfs_dir2_data_off_t);
+}
+
+static __be16 *
+xfs_dir3_free_bests_p(struct xfs_dir2_free *free)
+{
+ return (__be16 *)((char *)free + sizeof(struct xfs_dir3_free_hdr));
+}
+
+/*
+ * Convert data space db to the corresponding free db.
+ */
+static xfs_dir2_db_t
+xfs_dir3_db_to_fdb(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
+{
+ return xfs_dir2_byte_to_db(geo, XFS_DIR2_FREE_OFFSET) +
+ (db / xfs_dir3_free_max_bests(geo));
+}
+
+/*
+ * Convert data space db to the corresponding index in a free db.
+ */
+static int
+xfs_dir3_db_to_fdindex(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
+{
+ return db % xfs_dir3_free_max_bests(geo);
+}
+
+static void
+xfs_dir2_free_hdr_from_disk(
+ struct xfs_dir3_icfree_hdr *to,
+ struct xfs_dir2_free *from)
+{
+ to->magic = be32_to_cpu(from->hdr.magic);
+ to->firstdb = be32_to_cpu(from->hdr.firstdb);
+ to->nvalid = be32_to_cpu(from->hdr.nvalid);
+ to->nused = be32_to_cpu(from->hdr.nused);
+ ASSERT(to->magic == XFS_DIR2_FREE_MAGIC);
+}
+
+static void
+xfs_dir2_free_hdr_to_disk(
+ struct xfs_dir2_free *to,
+ struct xfs_dir3_icfree_hdr *from)
+{
+ ASSERT(from->magic == XFS_DIR2_FREE_MAGIC);
+
+ to->hdr.magic = cpu_to_be32(from->magic);
+ to->hdr.firstdb = cpu_to_be32(from->firstdb);
+ to->hdr.nvalid = cpu_to_be32(from->nvalid);
+ to->hdr.nused = cpu_to_be32(from->nused);
+}
+
+static void
+xfs_dir3_free_hdr_from_disk(
+ struct xfs_dir3_icfree_hdr *to,
+ struct xfs_dir2_free *from)
+{
+ struct xfs_dir3_free_hdr *hdr3 = (struct xfs_dir3_free_hdr *)from;
+
+ to->magic = be32_to_cpu(hdr3->hdr.magic);
+ to->firstdb = be32_to_cpu(hdr3->firstdb);
+ to->nvalid = be32_to_cpu(hdr3->nvalid);
+ to->nused = be32_to_cpu(hdr3->nused);
+
+ ASSERT(to->magic == XFS_DIR3_FREE_MAGIC);
+}
+
+static void
+xfs_dir3_free_hdr_to_disk(
+ struct xfs_dir2_free *to,
+ struct xfs_dir3_icfree_hdr *from)
+{
+ struct xfs_dir3_free_hdr *hdr3 = (struct xfs_dir3_free_hdr *)to;
+
+ ASSERT(from->magic == XFS_DIR3_FREE_MAGIC);
+
+ hdr3->hdr.magic = cpu_to_be32(from->magic);
+ hdr3->firstdb = cpu_to_be32(from->firstdb);
+ hdr3->nvalid = cpu_to_be32(from->nvalid);
+ hdr3->nused = cpu_to_be32(from->nused);
+}
+
+static const struct xfs_dir_ops xfs_dir2_ops = {
+ .sf_entsize = xfs_dir2_sf_entsize,
+ .sf_nextentry = xfs_dir2_sf_nextentry,
+ .sf_get_ftype = xfs_dir2_sfe_get_ftype,
+ .sf_put_ftype = xfs_dir2_sfe_put_ftype,
+ .sf_get_ino = xfs_dir2_sfe_get_ino,
+ .sf_put_ino = xfs_dir2_sfe_put_ino,
+ .sf_get_parent_ino = xfs_dir2_sf_get_parent_ino,
+ .sf_put_parent_ino = xfs_dir2_sf_put_parent_ino,
+
+ .data_entsize = xfs_dir2_data_entsize,
+ .data_get_ftype = xfs_dir2_data_get_ftype,
+ .data_put_ftype = xfs_dir2_data_put_ftype,
+ .data_entry_tag_p = xfs_dir2_data_entry_tag_p,
+ .data_bestfree_p = xfs_dir2_data_bestfree_p,
+
+ .data_dot_offset = sizeof(struct xfs_dir2_data_hdr),
+ .data_dotdot_offset = sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR2_DATA_ENTSIZE(1),
+ .data_first_offset = sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR2_DATA_ENTSIZE(1) +
+ XFS_DIR2_DATA_ENTSIZE(2),
+ .data_entry_offset = sizeof(struct xfs_dir2_data_hdr),
+
+ .data_dot_entry_p = xfs_dir2_data_dot_entry_p,
+ .data_dotdot_entry_p = xfs_dir2_data_dotdot_entry_p,
+ .data_first_entry_p = xfs_dir2_data_first_entry_p,
+ .data_entry_p = xfs_dir2_data_entry_p,
+ .data_unused_p = xfs_dir2_data_unused_p,
+
+ .leaf_hdr_size = sizeof(struct xfs_dir2_leaf_hdr),
+ .leaf_hdr_to_disk = xfs_dir2_leaf_hdr_to_disk,
+ .leaf_hdr_from_disk = xfs_dir2_leaf_hdr_from_disk,
+ .leaf_max_ents = xfs_dir2_max_leaf_ents,
+ .leaf_ents_p = xfs_dir2_leaf_ents_p,
+
+ .node_hdr_size = sizeof(struct xfs_da_node_hdr),
+ .node_hdr_to_disk = xfs_da2_node_hdr_to_disk,
+ .node_hdr_from_disk = xfs_da2_node_hdr_from_disk,
+ .node_tree_p = xfs_da2_node_tree_p,
+
+ .free_hdr_size = sizeof(struct xfs_dir2_free_hdr),
+ .free_hdr_to_disk = xfs_dir2_free_hdr_to_disk,
+ .free_hdr_from_disk = xfs_dir2_free_hdr_from_disk,
+ .free_max_bests = xfs_dir2_free_max_bests,
+ .free_bests_p = xfs_dir2_free_bests_p,
+ .db_to_fdb = xfs_dir2_db_to_fdb,
+ .db_to_fdindex = xfs_dir2_db_to_fdindex,
+};
+
+static const struct xfs_dir_ops xfs_dir2_ftype_ops = {
+ .sf_entsize = xfs_dir3_sf_entsize,
+ .sf_nextentry = xfs_dir3_sf_nextentry,
+ .sf_get_ftype = xfs_dir3_sfe_get_ftype,
+ .sf_put_ftype = xfs_dir3_sfe_put_ftype,
+ .sf_get_ino = xfs_dir3_sfe_get_ino,
+ .sf_put_ino = xfs_dir3_sfe_put_ino,
+ .sf_get_parent_ino = xfs_dir2_sf_get_parent_ino,
+ .sf_put_parent_ino = xfs_dir2_sf_put_parent_ino,
+
+ .data_entsize = xfs_dir3_data_entsize,
+ .data_get_ftype = xfs_dir3_data_get_ftype,
+ .data_put_ftype = xfs_dir3_data_put_ftype,
+ .data_entry_tag_p = xfs_dir3_data_entry_tag_p,
+ .data_bestfree_p = xfs_dir2_data_bestfree_p,
+
+ .data_dot_offset = sizeof(struct xfs_dir2_data_hdr),
+ .data_dotdot_offset = sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1),
+ .data_first_offset = sizeof(struct xfs_dir2_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1) +
+ XFS_DIR3_DATA_ENTSIZE(2),
+ .data_entry_offset = sizeof(struct xfs_dir2_data_hdr),
+
+ .data_dot_entry_p = xfs_dir2_data_dot_entry_p,
+ .data_dotdot_entry_p = xfs_dir2_ftype_data_dotdot_entry_p,
+ .data_first_entry_p = xfs_dir2_ftype_data_first_entry_p,
+ .data_entry_p = xfs_dir2_data_entry_p,
+ .data_unused_p = xfs_dir2_data_unused_p,
+
+ .leaf_hdr_size = sizeof(struct xfs_dir2_leaf_hdr),
+ .leaf_hdr_to_disk = xfs_dir2_leaf_hdr_to_disk,
+ .leaf_hdr_from_disk = xfs_dir2_leaf_hdr_from_disk,
+ .leaf_max_ents = xfs_dir2_max_leaf_ents,
+ .leaf_ents_p = xfs_dir2_leaf_ents_p,
+
+ .node_hdr_size = sizeof(struct xfs_da_node_hdr),
+ .node_hdr_to_disk = xfs_da2_node_hdr_to_disk,
+ .node_hdr_from_disk = xfs_da2_node_hdr_from_disk,
+ .node_tree_p = xfs_da2_node_tree_p,
+
+ .free_hdr_size = sizeof(struct xfs_dir2_free_hdr),
+ .free_hdr_to_disk = xfs_dir2_free_hdr_to_disk,
+ .free_hdr_from_disk = xfs_dir2_free_hdr_from_disk,
+ .free_max_bests = xfs_dir2_free_max_bests,
+ .free_bests_p = xfs_dir2_free_bests_p,
+ .db_to_fdb = xfs_dir2_db_to_fdb,
+ .db_to_fdindex = xfs_dir2_db_to_fdindex,
+};
+
+static const struct xfs_dir_ops xfs_dir3_ops = {
+ .sf_entsize = xfs_dir3_sf_entsize,
+ .sf_nextentry = xfs_dir3_sf_nextentry,
+ .sf_get_ftype = xfs_dir3_sfe_get_ftype,
+ .sf_put_ftype = xfs_dir3_sfe_put_ftype,
+ .sf_get_ino = xfs_dir3_sfe_get_ino,
+ .sf_put_ino = xfs_dir3_sfe_put_ino,
+ .sf_get_parent_ino = xfs_dir2_sf_get_parent_ino,
+ .sf_put_parent_ino = xfs_dir2_sf_put_parent_ino,
+
+ .data_entsize = xfs_dir3_data_entsize,
+ .data_get_ftype = xfs_dir3_data_get_ftype,
+ .data_put_ftype = xfs_dir3_data_put_ftype,
+ .data_entry_tag_p = xfs_dir3_data_entry_tag_p,
+ .data_bestfree_p = xfs_dir3_data_bestfree_p,
+
+ .data_dot_offset = sizeof(struct xfs_dir3_data_hdr),
+ .data_dotdot_offset = sizeof(struct xfs_dir3_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1),
+ .data_first_offset = sizeof(struct xfs_dir3_data_hdr) +
+ XFS_DIR3_DATA_ENTSIZE(1) +
+ XFS_DIR3_DATA_ENTSIZE(2),
+ .data_entry_offset = sizeof(struct xfs_dir3_data_hdr),
+
+ .data_dot_entry_p = xfs_dir3_data_dot_entry_p,
+ .data_dotdot_entry_p = xfs_dir3_data_dotdot_entry_p,
+ .data_first_entry_p = xfs_dir3_data_first_entry_p,
+ .data_entry_p = xfs_dir3_data_entry_p,
+ .data_unused_p = xfs_dir3_data_unused_p,
+
+ .leaf_hdr_size = sizeof(struct xfs_dir3_leaf_hdr),
+ .leaf_hdr_to_disk = xfs_dir3_leaf_hdr_to_disk,
+ .leaf_hdr_from_disk = xfs_dir3_leaf_hdr_from_disk,
+ .leaf_max_ents = xfs_dir3_max_leaf_ents,
+ .leaf_ents_p = xfs_dir3_leaf_ents_p,
+
+ .node_hdr_size = sizeof(struct xfs_da3_node_hdr),
+ .node_hdr_to_disk = xfs_da3_node_hdr_to_disk,
+ .node_hdr_from_disk = xfs_da3_node_hdr_from_disk,
+ .node_tree_p = xfs_da3_node_tree_p,
+
+ .free_hdr_size = sizeof(struct xfs_dir3_free_hdr),
+ .free_hdr_to_disk = xfs_dir3_free_hdr_to_disk,
+ .free_hdr_from_disk = xfs_dir3_free_hdr_from_disk,
+ .free_max_bests = xfs_dir3_free_max_bests,
+ .free_bests_p = xfs_dir3_free_bests_p,
+ .db_to_fdb = xfs_dir3_db_to_fdb,
+ .db_to_fdindex = xfs_dir3_db_to_fdindex,
+};
+
+static const struct xfs_dir_ops xfs_dir2_nondir_ops = {
+ .node_hdr_size = sizeof(struct xfs_da_node_hdr),
+ .node_hdr_to_disk = xfs_da2_node_hdr_to_disk,
+ .node_hdr_from_disk = xfs_da2_node_hdr_from_disk,
+ .node_tree_p = xfs_da2_node_tree_p,
+};
+
+static const struct xfs_dir_ops xfs_dir3_nondir_ops = {
+ .node_hdr_size = sizeof(struct xfs_da3_node_hdr),
+ .node_hdr_to_disk = xfs_da3_node_hdr_to_disk,
+ .node_hdr_from_disk = xfs_da3_node_hdr_from_disk,
+ .node_tree_p = xfs_da3_node_tree_p,
+};
+
+/*
+ * Return the ops structure according to the current config. If we are passed
+ * an inode, then that overrides the default config we use which is based on
+ * feature bits.
+ */
+const struct xfs_dir_ops *
+xfs_dir_get_ops(
+ struct xfs_mount *mp,
+ struct xfs_inode *dp)
+{
+ if (dp)
+ return dp->d_ops;
+ if (mp->m_dir_inode_ops)
+ return mp->m_dir_inode_ops;
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ return &xfs_dir3_ops;
+ if (xfs_sb_version_hasftype(&mp->m_sb))
+ return &xfs_dir2_ftype_ops;
+ return &xfs_dir2_ops;
+}
+
+const struct xfs_dir_ops *
+xfs_nondir_get_ops(
+ struct xfs_mount *mp,
+ struct xfs_inode *dp)
+{
+ if (dp)
+ return dp->d_ops;
+ if (mp->m_nondir_inode_ops)
+ return mp->m_nondir_inode_ops;
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ return &xfs_dir3_nondir_ops;
+ return &xfs_dir2_nondir_ops;
+}
diff --git a/fs/xfs/xfs_da_format.h b/fs/xfs/xfs_da_format.h
new file mode 100644
index 00000000000..0a49b028637
--- /dev/null
+++ b/fs/xfs/xfs_da_format.h
@@ -0,0 +1,861 @@
+/*
+ * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#ifndef __XFS_DA_FORMAT_H__
+#define __XFS_DA_FORMAT_H__
+
+/*
+ * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
+ *
+ * It is used to manage a doubly linked list of all blocks at the same
+ * level in the Btree, and to identify which type of block this is.
+ */
+#define XFS_DA_NODE_MAGIC 0xfebe /* magic number: non-leaf blocks */
+#define XFS_ATTR_LEAF_MAGIC 0xfbee /* magic number: attribute leaf blks */
+#define XFS_DIR2_LEAF1_MAGIC 0xd2f1 /* magic number: v2 dirlf single blks */
+#define XFS_DIR2_LEAFN_MAGIC 0xd2ff /* magic number: v2 dirlf multi blks */
+
+typedef struct xfs_da_blkinfo {
+ __be32 forw; /* previous block in list */
+ __be32 back; /* following block in list */
+ __be16 magic; /* validity check on block */
+ __be16 pad; /* unused */
+} xfs_da_blkinfo_t;
+
+/*
+ * CRC enabled directory structure types
+ *
+ * The headers change size for the additional verification information, but
+ * otherwise the tree layouts and contents are unchanged. Hence the da btree
+ * code can use the struct xfs_da_blkinfo for manipulating the tree links and
+ * magic numbers without modification for both v2 and v3 nodes.
+ */
+#define XFS_DA3_NODE_MAGIC 0x3ebe /* magic number: non-leaf blocks */
+#define XFS_ATTR3_LEAF_MAGIC 0x3bee /* magic number: attribute leaf blks */
+#define XFS_DIR3_LEAF1_MAGIC 0x3df1 /* magic number: v2 dirlf single blks */
+#define XFS_DIR3_LEAFN_MAGIC 0x3dff /* magic number: v2 dirlf multi blks */
+
+struct xfs_da3_blkinfo {
+ /*
+ * the node link manipulation code relies on the fact that the first
+ * element of this structure is the struct xfs_da_blkinfo so it can
+ * ignore the differences in the rest of the structures.
+ */
+ struct xfs_da_blkinfo hdr;
+ __be32 crc; /* CRC of block */
+ __be64 blkno; /* first block of the buffer */
+ __be64 lsn; /* sequence number of last write */
+ uuid_t uuid; /* filesystem we belong to */
+ __be64 owner; /* inode that owns the block */
+};
+
+/*
+ * This is the structure of the root and intermediate nodes in the Btree.
+ * The leaf nodes are defined above.
+ *
+ * Entries are not packed.
+ *
+ * Since we have duplicate keys, use a binary search but always follow
+ * all match in the block, not just the first match found.
+ */
+#define XFS_DA_NODE_MAXDEPTH 5 /* max depth of Btree */
+
+typedef struct xfs_da_node_hdr {
+ struct xfs_da_blkinfo info; /* block type, links, etc. */
+ __be16 __count; /* count of active entries */
+ __be16 __level; /* level above leaves (leaf == 0) */
+} xfs_da_node_hdr_t;
+
+struct xfs_da3_node_hdr {
+ struct xfs_da3_blkinfo info; /* block type, links, etc. */
+ __be16 __count; /* count of active entries */
+ __be16 __level; /* level above leaves (leaf == 0) */
+ __be32 __pad32;
+};
+
+#define XFS_DA3_NODE_CRC_OFF (offsetof(struct xfs_da3_node_hdr, info.crc))
+
+typedef struct xfs_da_node_entry {
+ __be32 hashval; /* hash value for this descendant */
+ __be32 before; /* Btree block before this key */
+} xfs_da_node_entry_t;
+
+typedef struct xfs_da_intnode {
+ struct xfs_da_node_hdr hdr;
+ struct xfs_da_node_entry __btree[];
+} xfs_da_intnode_t;
+
+struct xfs_da3_intnode {
+ struct xfs_da3_node_hdr hdr;
+ struct xfs_da_node_entry __btree[];
+};
+
+/*
+ * In-core version of the node header to abstract the differences in the v2 and
+ * v3 disk format of the headers. Callers need to convert to/from disk format as
+ * appropriate.
+ */
+struct xfs_da3_icnode_hdr {
+ __uint32_t forw;
+ __uint32_t back;
+ __uint16_t magic;
+ __uint16_t count;
+ __uint16_t level;
+};
+
+/*
+ * Directory version 2.
+ *
+ * There are 4 possible formats:
+ * - shortform - embedded into the inode
+ * - single block - data with embedded leaf at the end
+ * - multiple data blocks, single leaf+freeindex block
+ * - data blocks, node and leaf blocks (btree), freeindex blocks
+ *
+ * Note: many node blocks structures and constants are shared with the attr
+ * code and defined in xfs_da_btree.h.
+ */
+
+#define XFS_DIR2_BLOCK_MAGIC 0x58443242 /* XD2B: single block dirs */
+#define XFS_DIR2_DATA_MAGIC 0x58443244 /* XD2D: multiblock dirs */
+#define XFS_DIR2_FREE_MAGIC 0x58443246 /* XD2F: free index blocks */
+
+/*
+ * Directory Version 3 With CRCs.
+ *
+ * The tree formats are the same as for version 2 directories. The difference
+ * is in the block header and dirent formats. In many cases the v3 structures
+ * use v2 definitions as they are no different and this makes code sharing much
+ * easier.
+ *
+ * Also, the xfs_dir3_*() functions handle both v2 and v3 formats - if the
+ * format is v2 then they switch to the existing v2 code, or the format is v3
+ * they implement the v3 functionality. This means the existing dir2 is a mix of
+ * xfs_dir2/xfs_dir3 calls and functions. The xfs_dir3 functions are called
+ * where there is a difference in the formats, otherwise the code is unchanged.
+ *
+ * Where it is possible, the code decides what to do based on the magic numbers
+ * in the blocks rather than feature bits in the superblock. This means the code
+ * is as independent of the external XFS code as possible as doesn't require
+ * passing struct xfs_mount pointers into places where it isn't really
+ * necessary.
+ *
+ * Version 3 includes:
+ *
+ * - a larger block header for CRC and identification purposes and so the
+ * offsets of all the structures inside the blocks are different.
+ *
+ * - new magic numbers to be able to detect the v2/v3 types on the fly.
+ */
+
+#define XFS_DIR3_BLOCK_MAGIC 0x58444233 /* XDB3: single block dirs */
+#define XFS_DIR3_DATA_MAGIC 0x58444433 /* XDD3: multiblock dirs */
+#define XFS_DIR3_FREE_MAGIC 0x58444633 /* XDF3: free index blocks */
+
+/*
+ * Dirents in version 3 directories have a file type field. Additions to this
+ * list are an on-disk format change, requiring feature bits. Valid values
+ * are as follows:
+ */
+#define XFS_DIR3_FT_UNKNOWN 0
+#define XFS_DIR3_FT_REG_FILE 1
+#define XFS_DIR3_FT_DIR 2
+#define XFS_DIR3_FT_CHRDEV 3
+#define XFS_DIR3_FT_BLKDEV 4
+#define XFS_DIR3_FT_FIFO 5
+#define XFS_DIR3_FT_SOCK 6
+#define XFS_DIR3_FT_SYMLINK 7
+#define XFS_DIR3_FT_WHT 8
+
+#define XFS_DIR3_FT_MAX 9
+
+/*
+ * Byte offset in data block and shortform entry.
+ */
+typedef __uint16_t xfs_dir2_data_off_t;
+#define NULLDATAOFF 0xffffU
+typedef uint xfs_dir2_data_aoff_t; /* argument form */
+
+/*
+ * Normalized offset (in a data block) of the entry, really xfs_dir2_data_off_t.
+ * Only need 16 bits, this is the byte offset into the single block form.
+ */
+typedef struct { __uint8_t i[2]; } __arch_pack xfs_dir2_sf_off_t;
+
+/*
+ * Offset in data space of a data entry.
+ */
+typedef __uint32_t xfs_dir2_dataptr_t;
+#define XFS_DIR2_MAX_DATAPTR ((xfs_dir2_dataptr_t)0xffffffff)
+#define XFS_DIR2_NULL_DATAPTR ((xfs_dir2_dataptr_t)0)
+
+/*
+ * Byte offset in a directory.
+ */
+typedef xfs_off_t xfs_dir2_off_t;
+
+/*
+ * Directory block number (logical dirblk in file)
+ */
+typedef __uint32_t xfs_dir2_db_t;
+
+/*
+ * Inode number stored as 8 8-bit values.
+ */
+typedef struct { __uint8_t i[8]; } xfs_dir2_ino8_t;
+
+/*
+ * Inode number stored as 4 8-bit values.
+ * Works a lot of the time, when all the inode numbers in a directory
+ * fit in 32 bits.
+ */
+typedef struct { __uint8_t i[4]; } xfs_dir2_ino4_t;
+
+typedef union {
+ xfs_dir2_ino8_t i8;
+ xfs_dir2_ino4_t i4;
+} xfs_dir2_inou_t;
+#define XFS_DIR2_MAX_SHORT_INUM ((xfs_ino_t)0xffffffffULL)
+
+/*
+ * Directory layout when stored internal to an inode.
+ *
+ * Small directories are packed as tightly as possible so as to fit into the
+ * literal area of the inode. These "shortform" directories consist of a
+ * single xfs_dir2_sf_hdr header followed by zero or more xfs_dir2_sf_entry
+ * structures. Due the different inode number storage size and the variable
+ * length name field in the xfs_dir2_sf_entry all these structure are
+ * variable length, and the accessors in this file should be used to iterate
+ * over them.
+ */
+typedef struct xfs_dir2_sf_hdr {
+ __uint8_t count; /* count of entries */
+ __uint8_t i8count; /* count of 8-byte inode #s */
+ xfs_dir2_inou_t parent; /* parent dir inode number */
+} __arch_pack xfs_dir2_sf_hdr_t;
+
+typedef struct xfs_dir2_sf_entry {
+ __u8 namelen; /* actual name length */
+ xfs_dir2_sf_off_t offset; /* saved offset */
+ __u8 name[]; /* name, variable size */
+ /*
+ * A single byte containing the file type field follows the inode
+ * number for version 3 directory entries.
+ *
+ * A xfs_dir2_ino8_t or xfs_dir2_ino4_t follows here, at a
+ * variable offset after the name.
+ */
+} __arch_pack xfs_dir2_sf_entry_t;
+
+static inline int xfs_dir2_sf_hdr_size(int i8count)
+{
+ return sizeof(struct xfs_dir2_sf_hdr) -
+ (i8count == 0) *
+ (sizeof(xfs_dir2_ino8_t) - sizeof(xfs_dir2_ino4_t));
+}
+
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_sf_get_offset(xfs_dir2_sf_entry_t *sfep)
+{
+ return get_unaligned_be16(&sfep->offset.i);
+}
+
+static inline void
+xfs_dir2_sf_put_offset(xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t off)
+{
+ put_unaligned_be16(off, &sfep->offset.i);
+}
+
+static inline struct xfs_dir2_sf_entry *
+xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
+{
+ return (struct xfs_dir2_sf_entry *)
+ ((char *)hdr + xfs_dir2_sf_hdr_size(hdr->i8count));
+}
+
+/*
+ * Data block structures.
+ *
+ * A pure data block looks like the following drawing on disk:
+ *
+ * +-------------------------------------------------+
+ * | xfs_dir2_data_hdr_t |
+ * +-------------------------------------------------+
+ * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ * | ... |
+ * +-------------------------------------------------+
+ * | unused space |
+ * +-------------------------------------------------+
+ *
+ * As all the entries are variable size structures the accessors below should
+ * be used to iterate over them.
+ *
+ * In addition to the pure data blocks for the data and node formats,
+ * most structures are also used for the combined data/freespace "block"
+ * format below.
+ */
+
+#define XFS_DIR2_DATA_ALIGN_LOG 3 /* i.e., 8 bytes */
+#define XFS_DIR2_DATA_ALIGN (1 << XFS_DIR2_DATA_ALIGN_LOG)
+#define XFS_DIR2_DATA_FREE_TAG 0xffff
+#define XFS_DIR2_DATA_FD_COUNT 3
+
+/*
+ * Directory address space divided into sections,
+ * spaces separated by 32GB.
+ */
+#define XFS_DIR2_SPACE_SIZE (1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
+#define XFS_DIR2_DATA_SPACE 0
+#define XFS_DIR2_DATA_OFFSET (XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
+
+/*
+ * Describe a free area in the data block.
+ *
+ * The freespace will be formatted as a xfs_dir2_data_unused_t.
+ */
+typedef struct xfs_dir2_data_free {
+ __be16 offset; /* start of freespace */
+ __be16 length; /* length of freespace */
+} xfs_dir2_data_free_t;
+
+/*
+ * Header for the data blocks.
+ *
+ * The code knows that XFS_DIR2_DATA_FD_COUNT is 3.
+ */
+typedef struct xfs_dir2_data_hdr {
+ __be32 magic; /* XFS_DIR2_DATA_MAGIC or */
+ /* XFS_DIR2_BLOCK_MAGIC */
+ xfs_dir2_data_free_t bestfree[XFS_DIR2_DATA_FD_COUNT];
+} xfs_dir2_data_hdr_t;
+
+/*
+ * define a structure for all the verification fields we are adding to the
+ * directory block structures. This will be used in several structures.
+ * The magic number must be the first entry to align with all the dir2
+ * structures so we determine how to decode them just by the magic number.
+ */
+struct xfs_dir3_blk_hdr {
+ __be32 magic; /* magic number */
+ __be32 crc; /* CRC of block */
+ __be64 blkno; /* first block of the buffer */
+ __be64 lsn; /* sequence number of last write */
+ uuid_t uuid; /* filesystem we belong to */
+ __be64 owner; /* inode that owns the block */
+};
+
+struct xfs_dir3_data_hdr {
+ struct xfs_dir3_blk_hdr hdr;
+ xfs_dir2_data_free_t best_free[XFS_DIR2_DATA_FD_COUNT];
+ __be32 pad; /* 64 bit alignment */
+};
+
+#define XFS_DIR3_DATA_CRC_OFF offsetof(struct xfs_dir3_data_hdr, hdr.crc)
+
+/*
+ * Active entry in a data block.
+ *
+ * Aligned to 8 bytes. After the variable length name field there is a
+ * 2 byte tag field, which can be accessed using xfs_dir3_data_entry_tag_p.
+ *
+ * For dir3 structures, there is file type field between the name and the tag.
+ * This can only be manipulated by helper functions. It is packed hard against
+ * the end of the name so any padding for rounding is between the file type and
+ * the tag.
+ */
+typedef struct xfs_dir2_data_entry {
+ __be64 inumber; /* inode number */
+ __u8 namelen; /* name length */
+ __u8 name[]; /* name bytes, no null */
+ /* __u8 filetype; */ /* type of inode we point to */
+ /* __be16 tag; */ /* starting offset of us */
+} xfs_dir2_data_entry_t;
+
+/*
+ * Unused entry in a data block.
+ *
+ * Aligned to 8 bytes. Tag appears as the last 2 bytes and must be accessed
+ * using xfs_dir2_data_unused_tag_p.
+ */
+typedef struct xfs_dir2_data_unused {
+ __be16 freetag; /* XFS_DIR2_DATA_FREE_TAG */
+ __be16 length; /* total free length */
+ /* variable offset */
+ __be16 tag; /* starting offset of us */
+} xfs_dir2_data_unused_t;
+
+/*
+ * Pointer to a freespace's tag word.
+ */
+static inline __be16 *
+xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup)
+{
+ return (__be16 *)((char *)dup +
+ be16_to_cpu(dup->length) - sizeof(__be16));
+}
+
+/*
+ * Leaf block structures.
+ *
+ * A pure leaf block looks like the following drawing on disk:
+ *
+ * +---------------------------+
+ * | xfs_dir2_leaf_hdr_t |
+ * +---------------------------+
+ * | xfs_dir2_leaf_entry_t |
+ * | xfs_dir2_leaf_entry_t |
+ * | xfs_dir2_leaf_entry_t |
+ * | xfs_dir2_leaf_entry_t |
+ * | ... |
+ * +---------------------------+
+ * | xfs_dir2_data_off_t |
+ * | xfs_dir2_data_off_t |
+ * | xfs_dir2_data_off_t |
+ * | ... |
+ * +---------------------------+
+ * | xfs_dir2_leaf_tail_t |
+ * +---------------------------+
+ *
+ * The xfs_dir2_data_off_t members (bests) and tail are at the end of the block
+ * for single-leaf (magic = XFS_DIR2_LEAF1_MAGIC) blocks only, but not present
+ * for directories with separate leaf nodes and free space blocks
+ * (magic = XFS_DIR2_LEAFN_MAGIC).
+ *
+ * As all the entries are variable size structures the accessors below should
+ * be used to iterate over them.
+ */
+
+/*
+ * Offset of the leaf/node space. First block in this space
+ * is the btree root.
+ */
+#define XFS_DIR2_LEAF_SPACE 1
+#define XFS_DIR2_LEAF_OFFSET (XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE)
+
+/*
+ * Leaf block header.
+ */
+typedef struct xfs_dir2_leaf_hdr {
+ xfs_da_blkinfo_t info; /* header for da routines */
+ __be16 count; /* count of entries */
+ __be16 stale; /* count of stale entries */
+} xfs_dir2_leaf_hdr_t;
+
+struct xfs_dir3_leaf_hdr {
+ struct xfs_da3_blkinfo info; /* header for da routines */
+ __be16 count; /* count of entries */
+ __be16 stale; /* count of stale entries */
+ __be32 pad; /* 64 bit alignment */
+};
+
+struct xfs_dir3_icleaf_hdr {
+ __uint32_t forw;
+ __uint32_t back;
+ __uint16_t magic;
+ __uint16_t count;
+ __uint16_t stale;
+};
+
+/*
+ * Leaf block entry.
+ */
+typedef struct xfs_dir2_leaf_entry {
+ __be32 hashval; /* hash value of name */
+ __be32 address; /* address of data entry */
+} xfs_dir2_leaf_entry_t;
+
+/*
+ * Leaf block tail.
+ */
+typedef struct xfs_dir2_leaf_tail {
+ __be32 bestcount;
+} xfs_dir2_leaf_tail_t;
+
+/*
+ * Leaf block.
+ */
+typedef struct xfs_dir2_leaf {
+ xfs_dir2_leaf_hdr_t hdr; /* leaf header */
+ xfs_dir2_leaf_entry_t __ents[]; /* entries */
+} xfs_dir2_leaf_t;
+
+struct xfs_dir3_leaf {
+ struct xfs_dir3_leaf_hdr hdr; /* leaf header */
+ struct xfs_dir2_leaf_entry __ents[]; /* entries */
+};
+
+#define XFS_DIR3_LEAF_CRC_OFF offsetof(struct xfs_dir3_leaf_hdr, info.crc)
+
+/*
+ * Get address of the bests array in the single-leaf block.
+ */
+static inline __be16 *
+xfs_dir2_leaf_bests_p(struct xfs_dir2_leaf_tail *ltp)
+{
+ return (__be16 *)ltp - be32_to_cpu(ltp->bestcount);
+}
+
+/*
+ * Free space block defintions for the node format.
+ */
+
+/*
+ * Offset of the freespace index.
+ */
+#define XFS_DIR2_FREE_SPACE 2
+#define XFS_DIR2_FREE_OFFSET (XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE)
+
+typedef struct xfs_dir2_free_hdr {
+ __be32 magic; /* XFS_DIR2_FREE_MAGIC */
+ __be32 firstdb; /* db of first entry */
+ __be32 nvalid; /* count of valid entries */
+ __be32 nused; /* count of used entries */
+} xfs_dir2_free_hdr_t;
+
+typedef struct xfs_dir2_free {
+ xfs_dir2_free_hdr_t hdr; /* block header */
+ __be16 bests[]; /* best free counts */
+ /* unused entries are -1 */
+} xfs_dir2_free_t;
+
+struct xfs_dir3_free_hdr {
+ struct xfs_dir3_blk_hdr hdr;
+ __be32 firstdb; /* db of first entry */
+ __be32 nvalid; /* count of valid entries */
+ __be32 nused; /* count of used entries */
+ __be32 pad; /* 64 bit alignment */
+};
+
+struct xfs_dir3_free {
+ struct xfs_dir3_free_hdr hdr;
+ __be16 bests[]; /* best free counts */
+ /* unused entries are -1 */
+};
+
+#define XFS_DIR3_FREE_CRC_OFF offsetof(struct xfs_dir3_free, hdr.hdr.crc)
+
+/*
+ * In core version of the free block header, abstracted away from on-disk format
+ * differences. Use this in the code, and convert to/from the disk version using
+ * xfs_dir3_free_hdr_from_disk/xfs_dir3_free_hdr_to_disk.
+ */
+struct xfs_dir3_icfree_hdr {
+ __uint32_t magic;
+ __uint32_t firstdb;
+ __uint32_t nvalid;
+ __uint32_t nused;
+
+};
+
+/*
+ * Single block format.
+ *
+ * The single block format looks like the following drawing on disk:
+ *
+ * +-------------------------------------------------+
+ * | xfs_dir2_data_hdr_t |
+ * +-------------------------------------------------+
+ * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t :
+ * | ... |
+ * +-------------------------------------------------+
+ * | unused space |
+ * +-------------------------------------------------+
+ * | ... |
+ * | xfs_dir2_leaf_entry_t |
+ * | xfs_dir2_leaf_entry_t |
+ * +-------------------------------------------------+
+ * | xfs_dir2_block_tail_t |
+ * +-------------------------------------------------+
+ *
+ * As all the entries are variable size structures the accessors below should
+ * be used to iterate over them.
+ */
+
+typedef struct xfs_dir2_block_tail {
+ __be32 count; /* count of leaf entries */
+ __be32 stale; /* count of stale lf entries */
+} xfs_dir2_block_tail_t;
+
+/*
+ * Pointer to the leaf entries embedded in a data block (1-block format)
+ */
+static inline struct xfs_dir2_leaf_entry *
+xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
+{
+ return ((struct xfs_dir2_leaf_entry *)btp) - be32_to_cpu(btp->count);
+}
+
+
+/*
+ * Attribute storage layout
+ *
+ * Attribute lists are structured around Btrees where all the data
+ * elements are in the leaf nodes. Attribute names are hashed into an int,
+ * then that int is used as the index into the Btree. Since the hashval
+ * of an attribute name may not be unique, we may have duplicate keys. The
+ * internal links in the Btree are logical block offsets into the file.
+ *
+ * Struct leaf_entry's are packed from the top. Name/values grow from the
+ * bottom but are not packed. The freemap contains run-length-encoded entries
+ * for the free bytes after the leaf_entry's, but only the N largest such,
+ * smaller runs are dropped. When the freemap doesn't show enough space
+ * for an allocation, we compact the name/value area and try again. If we
+ * still don't have enough space, then we have to split the block. The
+ * name/value structs (both local and remote versions) must be 32bit aligned.
+ *
+ * Since we have duplicate hash keys, for each key that matches, compare
+ * the actual name string. The root and intermediate node search always
+ * takes the first-in-the-block key match found, so we should only have
+ * to work "forw"ard. If none matches, continue with the "forw"ard leaf
+ * nodes until the hash key changes or the attribute name is found.
+ *
+ * We store the fact that an attribute is a ROOT/USER/SECURE attribute in
+ * the leaf_entry. The namespaces are independent only because we also look
+ * at the namespace bit when we are looking for a matching attribute name.
+ *
+ * We also store an "incomplete" bit in the leaf_entry. It shows that an
+ * attribute is in the middle of being created and should not be shown to
+ * the user if we crash during the time that the bit is set. We clear the
+ * bit when we have finished setting up the attribute. We do this because
+ * we cannot create some large attributes inside a single transaction, and we
+ * need some indication that we weren't finished if we crash in the middle.
+ */
+#define XFS_ATTR_LEAF_MAPSIZE 3 /* how many freespace slots */
+
+typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */
+ __be16 base; /* base of free region */
+ __be16 size; /* length of free region */
+} xfs_attr_leaf_map_t;
+
+typedef struct xfs_attr_leaf_hdr { /* constant-structure header block */
+ xfs_da_blkinfo_t info; /* block type, links, etc. */
+ __be16 count; /* count of active leaf_entry's */
+ __be16 usedbytes; /* num bytes of names/values stored */
+ __be16 firstused; /* first used byte in name area */
+ __u8 holes; /* != 0 if blk needs compaction */
+ __u8 pad1;
+ xfs_attr_leaf_map_t freemap[XFS_ATTR_LEAF_MAPSIZE];
+ /* N largest free regions */
+} xfs_attr_leaf_hdr_t;
+
+typedef struct xfs_attr_leaf_entry { /* sorted on key, not name */
+ __be32 hashval; /* hash value of name */
+ __be16 nameidx; /* index into buffer of name/value */
+ __u8 flags; /* LOCAL/ROOT/SECURE/INCOMPLETE flag */
+ __u8 pad2; /* unused pad byte */
+} xfs_attr_leaf_entry_t;
+
+typedef struct xfs_attr_leaf_name_local {
+ __be16 valuelen; /* number of bytes in value */
+ __u8 namelen; /* length of name bytes */
+ __u8 nameval[1]; /* name/value bytes */
+} xfs_attr_leaf_name_local_t;
+
+typedef struct xfs_attr_leaf_name_remote {
+ __be32 valueblk; /* block number of value bytes */
+ __be32 valuelen; /* number of bytes in value */
+ __u8 namelen; /* length of name bytes */
+ __u8 name[1]; /* name bytes */
+} xfs_attr_leaf_name_remote_t;
+
+typedef struct xfs_attr_leafblock {
+ xfs_attr_leaf_hdr_t hdr; /* constant-structure header block */
+ xfs_attr_leaf_entry_t entries[1]; /* sorted on key, not name */
+ xfs_attr_leaf_name_local_t namelist; /* grows from bottom of buf */
+ xfs_attr_leaf_name_remote_t valuelist; /* grows from bottom of buf */
+} xfs_attr_leafblock_t;
+
+/*
+ * CRC enabled leaf structures. Called "version 3" structures to match the
+ * version number of the directory and dablk structures for this feature, and
+ * attr2 is already taken by the variable inode attribute fork size feature.
+ */
+struct xfs_attr3_leaf_hdr {
+ struct xfs_da3_blkinfo info;
+ __be16 count;
+ __be16 usedbytes;
+ __be16 firstused;
+ __u8 holes;
+ __u8 pad1;
+ struct xfs_attr_leaf_map freemap[XFS_ATTR_LEAF_MAPSIZE];
+ __be32 pad2; /* 64 bit alignment */
+};
+
+#define XFS_ATTR3_LEAF_CRC_OFF (offsetof(struct xfs_attr3_leaf_hdr, info.crc))
+
+struct xfs_attr3_leafblock {
+ struct xfs_attr3_leaf_hdr hdr;
+ struct xfs_attr_leaf_entry entries[1];
+
+ /*
+ * The rest of the block contains the following structures after the
+ * leaf entries, growing from the bottom up. The variables are never
+ * referenced, the locations accessed purely from helper functions.
+ *
+ * struct xfs_attr_leaf_name_local
+ * struct xfs_attr_leaf_name_remote
+ */
+};
+
+/*
+ * incore, neutral version of the attribute leaf header
+ */
+struct xfs_attr3_icleaf_hdr {
+ __uint32_t forw;
+ __uint32_t back;
+ __uint16_t magic;
+ __uint16_t count;
+ __uint16_t usedbytes;
+ __uint16_t firstused;
+ __u8 holes;
+ struct {
+ __uint16_t base;
+ __uint16_t size;
+ } freemap[XFS_ATTR_LEAF_MAPSIZE];
+};
+
+/*
+ * Flags used in the leaf_entry[i].flags field.
+ * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
+ * on the system call, they are "or"ed together for various operations.
+ */
+#define XFS_ATTR_LOCAL_BIT 0 /* attr is stored locally */
+#define XFS_ATTR_ROOT_BIT 1 /* limit access to trusted attrs */
+#define XFS_ATTR_SECURE_BIT 2 /* limit access to secure attrs */
+#define XFS_ATTR_INCOMPLETE_BIT 7 /* attr in middle of create/delete */
+#define XFS_ATTR_LOCAL (1 << XFS_ATTR_LOCAL_BIT)
+#define XFS_ATTR_ROOT (1 << XFS_ATTR_ROOT_BIT)
+#define XFS_ATTR_SECURE (1 << XFS_ATTR_SECURE_BIT)
+#define XFS_ATTR_INCOMPLETE (1 << XFS_ATTR_INCOMPLETE_BIT)
+
+/*
+ * Conversion macros for converting namespace bits from argument flags
+ * to ondisk flags.
+ */
+#define XFS_ATTR_NSP_ARGS_MASK (ATTR_ROOT | ATTR_SECURE)
+#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | XFS_ATTR_SECURE)
+#define XFS_ATTR_NSP_ONDISK(flags) ((flags) & XFS_ATTR_NSP_ONDISK_MASK)
+#define XFS_ATTR_NSP_ARGS(flags) ((flags) & XFS_ATTR_NSP_ARGS_MASK)
+#define XFS_ATTR_NSP_ARGS_TO_ONDISK(x) (((x) & ATTR_ROOT ? XFS_ATTR_ROOT : 0) |\
+ ((x) & ATTR_SECURE ? XFS_ATTR_SECURE : 0))
+#define XFS_ATTR_NSP_ONDISK_TO_ARGS(x) (((x) & XFS_ATTR_ROOT ? ATTR_ROOT : 0) |\
+ ((x) & XFS_ATTR_SECURE ? ATTR_SECURE : 0))
+
+/*
+ * Alignment for namelist and valuelist entries (since they are mixed
+ * there can be only one alignment value)
+ */
+#define XFS_ATTR_LEAF_NAME_ALIGN ((uint)sizeof(xfs_dablk_t))
+
+static inline int
+xfs_attr3_leaf_hdr_size(struct xfs_attr_leafblock *leafp)
+{
+ if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
+ return sizeof(struct xfs_attr3_leaf_hdr);
+ return sizeof(struct xfs_attr_leaf_hdr);
+}
+
+static inline struct xfs_attr_leaf_entry *
+xfs_attr3_leaf_entryp(xfs_attr_leafblock_t *leafp)
+{
+ if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
+ return &((struct xfs_attr3_leafblock *)leafp)->entries[0];
+ return &leafp->entries[0];
+}
+
+/*
+ * Cast typed pointers for "local" and "remote" name/value structs.
+ */
+static inline char *
+xfs_attr3_leaf_name(xfs_attr_leafblock_t *leafp, int idx)
+{
+ struct xfs_attr_leaf_entry *entries = xfs_attr3_leaf_entryp(leafp);
+
+ return &((char *)leafp)[be16_to_cpu(entries[idx].nameidx)];
+}
+
+static inline xfs_attr_leaf_name_remote_t *
+xfs_attr3_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx)
+{
+ return (xfs_attr_leaf_name_remote_t *)xfs_attr3_leaf_name(leafp, idx);
+}
+
+static inline xfs_attr_leaf_name_local_t *
+xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx)
+{
+ return (xfs_attr_leaf_name_local_t *)xfs_attr3_leaf_name(leafp, idx);
+}
+
+/*
+ * Calculate total bytes used (including trailing pad for alignment) for
+ * a "local" name/value structure, a "remote" name/value structure, and
+ * a pointer which might be either.
+ */
+static inline int xfs_attr_leaf_entsize_remote(int nlen)
+{
+ return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \
+ XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+}
+
+static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen)
+{
+ return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) +
+ XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+}
+
+static inline int xfs_attr_leaf_entsize_local_max(int bsize)
+{
+ return (((bsize) >> 1) + ((bsize) >> 2));
+}
+
+
+
+/*
+ * Remote attribute block format definition
+ *
+ * There is one of these headers per filesystem block in a remote attribute.
+ * This is done to ensure there is a 1:1 mapping between the attribute value
+ * length and the number of blocks needed to store the attribute. This makes the
+ * verification of a buffer a little more complex, but greatly simplifies the
+ * allocation, reading and writing of these attributes as we don't have to guess
+ * the number of blocks needed to store the attribute data.
+ */
+#define XFS_ATTR3_RMT_MAGIC 0x5841524d /* XARM */
+
+struct xfs_attr3_rmt_hdr {
+ __be32 rm_magic;
+ __be32 rm_offset;
+ __be32 rm_bytes;
+ __be32 rm_crc;
+ uuid_t rm_uuid;
+ __be64 rm_owner;
+ __be64 rm_blkno;
+ __be64 rm_lsn;
+};
+
+#define XFS_ATTR3_RMT_CRC_OFF offsetof(struct xfs_attr3_rmt_hdr, rm_crc)
+
+#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize) \
+ ((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
+ sizeof(struct xfs_attr3_rmt_hdr) : 0))
+
+#endif /* __XFS_DA_FORMAT_H__ */
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
deleted file mode 100644
index e00de08dc8a..00000000000
--- a/fs/xfs/xfs_dfrag.c
+++ /dev/null
@@ -1,452 +0,0 @@
-/*
- * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-#include "xfs.h"
-#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_sb.h"
-#include "xfs_ag.h"
-#include "xfs_mount.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
-#include "xfs_inode_item.h"
-#include "xfs_bmap.h"
-#include "xfs_itable.h"
-#include "xfs_dfrag.h"
-#include "xfs_error.h"
-#include "xfs_vnodeops.h"
-#include "xfs_trace.h"
-
-
-static int xfs_swap_extents(
- xfs_inode_t *ip, /* target inode */
- xfs_inode_t *tip, /* tmp inode */
- xfs_swapext_t *sxp);
-
-/*
- * ioctl interface for swapext
- */
-int
-xfs_swapext(
- xfs_swapext_t *sxp)
-{
- xfs_inode_t *ip, *tip;
- struct file *file, *tmp_file;
- int error = 0;
-
- /* Pull information for the target fd */
- file = fget((int)sxp->sx_fdtarget);
- if (!file) {
- error = XFS_ERROR(EINVAL);
- goto out;
- }
-
- if (!(file->f_mode & FMODE_WRITE) ||
- !(file->f_mode & FMODE_READ) ||
- (file->f_flags & O_APPEND)) {
- error = XFS_ERROR(EBADF);
- goto out_put_file;
- }
-
- tmp_file = fget((int)sxp->sx_fdtmp);
- if (!tmp_file) {
- error = XFS_ERROR(EINVAL);
- goto out_put_file;
- }
-
- if (!(tmp_file->f_mode & FMODE_WRITE) ||
- !(tmp_file->f_mode & FMODE_READ) ||
- (tmp_file->f_flags & O_APPEND)) {
- error = XFS_ERROR(EBADF);
- goto out_put_tmp_file;
- }
-
- if (IS_SWAPFILE(file->f_path.dentry->d_inode) ||
- IS_SWAPFILE(tmp_file->f_path.dentry->d_inode)) {
- error = XFS_ERROR(EINVAL);
- goto out_put_tmp_file;
- }
-
- ip = XFS_I(file->f_path.dentry->d_inode);
- tip = XFS_I(tmp_file->f_path.dentry->d_inode);
-
- if (ip->i_mount != tip->i_mount) {
- error = XFS_ERROR(EINVAL);
- goto out_put_tmp_file;
- }
-
- if (ip->i_ino == tip->i_ino) {
- error = XFS_ERROR(EINVAL);
- goto out_put_tmp_file;
- }
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- error = XFS_ERROR(EIO);
- goto out_put_tmp_file;
- }
-
- error = xfs_swap_extents(ip, tip, sxp);
-
- out_put_tmp_file:
- fput(tmp_file);
- out_put_file:
- fput(file);
- out:
- return error;
-}
-
-/*
- * We need to check that the format of the data fork in the temporary inode is
- * valid for the target inode before doing the swap. This is not a problem with
- * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
- * data fork depending on the space the attribute fork is taking so we can get
- * invalid formats on the target inode.
- *
- * E.g. target has space for 7 extents in extent format, temp inode only has
- * space for 6. If we defragment down to 7 extents, then the tmp format is a
- * btree, but when swapped it needs to be in extent format. Hence we can't just
- * blindly swap data forks on attr2 filesystems.
- *
- * Note that we check the swap in both directions so that we don't end up with
- * a corrupt temporary inode, either.
- *
- * Note that fixing the way xfs_fsr sets up the attribute fork in the source
- * inode will prevent this situation from occurring, so all we do here is
- * reject and log the attempt. basically we are putting the responsibility on
- * userspace to get this right.
- */
-static int
-xfs_swap_extents_check_format(
- xfs_inode_t *ip, /* target inode */
- xfs_inode_t *tip) /* tmp inode */
-{
-
- /* Should never get a local format */
- if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
- tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- return EINVAL;
-
- /*
- * if the target inode has less extents that then temporary inode then
- * why did userspace call us?
- */
- if (ip->i_d.di_nextents < tip->i_d.di_nextents)
- return EINVAL;
-
- /*
- * if the target inode is in extent form and the temp inode is in btree
- * form then we will end up with the target inode in the wrong format
- * as we already know there are less extents in the temp inode.
- */
- if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
- tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
- return EINVAL;
-
- /* Check temp in extent form to max in target */
- if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
- XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) >
- XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
- return EINVAL;
-
- /* Check target in extent form to max in temp */
- if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
- XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) >
- XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
- return EINVAL;
-
- /*
- * If we are in a btree format, check that the temp root block will fit
- * in the target and that it has enough extents to be in btree format
- * in the target.
- *
- * Note that we have to be careful to allow btree->extent conversions
- * (a common defrag case) which will occur when the temp inode is in
- * extent format...
- */
- if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
- if (XFS_IFORK_BOFF(ip) &&
- tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip))
- return EINVAL;
- if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
- XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
- return EINVAL;
- }
-
- /* Reciprocal target->temp btree format checks */
- if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
- if (XFS_IFORK_BOFF(tip) &&
- ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip))
- return EINVAL;
-
- if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
- XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
- return EINVAL;
- }
-
- return 0;
-}
-
-static int
-xfs_swap_extents(
- xfs_inode_t *ip, /* target inode */
- xfs_inode_t *tip, /* tmp inode */
- xfs_swapext_t *sxp)
-{
- xfs_mount_t *mp = ip->i_mount;
- xfs_trans_t *tp;
- xfs_bstat_t *sbp = &sxp->sx_stat;
- xfs_ifork_t *tempifp, *ifp, *tifp;
- int src_log_flags, target_log_flags;
- int error = 0;
- int aforkblks = 0;
- int taforkblks = 0;
- __uint64_t tmp;
-
- tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
- if (!tempifp) {
- error = XFS_ERROR(ENOMEM);
- goto out;
- }
-
- /*
- * we have to do two separate lock calls here to keep lockdep
- * happy. If we try to get all the locks in one call, lock will
- * report false positives when we drop the ILOCK and regain them
- * below.
- */
- xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
- xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
-
- /* Verify that both files have the same format */
- if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
- error = XFS_ERROR(EINVAL);
- goto out_unlock;
- }
-
- /* Verify both files are either real-time or non-realtime */
- if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
- error = XFS_ERROR(EINVAL);
- goto out_unlock;
- }
-
- if (VN_CACHED(VFS_I(tip)) != 0) {
- error = xfs_flushinval_pages(tip, 0, -1,
- FI_REMAPF_LOCKED);
- if (error)
- goto out_unlock;
- }
-
- /* Verify O_DIRECT for ftmp */
- if (VN_CACHED(VFS_I(tip)) != 0) {
- error = XFS_ERROR(EINVAL);
- goto out_unlock;
- }
-
- /* Verify all data are being swapped */
- if (sxp->sx_offset != 0 ||
- sxp->sx_length != ip->i_d.di_size ||
- sxp->sx_length != tip->i_d.di_size) {
- error = XFS_ERROR(EFAULT);
- goto out_unlock;
- }
-
- trace_xfs_swap_extent_before(ip, 0);
- trace_xfs_swap_extent_before(tip, 1);
-
- /* check inode formats now that data is flushed */
- error = xfs_swap_extents_check_format(ip, tip);
- if (error) {
- xfs_notice(mp,
- "%s: inode 0x%llx format is incompatible for exchanging.",
- __func__, ip->i_ino);
- goto out_unlock;
- }
-
- /*
- * Compare the current change & modify times with that
- * passed in. If they differ, we abort this swap.
- * This is the mechanism used to ensure the calling
- * process that the file was not changed out from
- * under it.
- */
- if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
- (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
- (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
- (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
- error = XFS_ERROR(EBUSY);
- goto out_unlock;
- }
-
- /* We need to fail if the file is memory mapped. Once we have tossed
- * all existing pages, the page fault will have no option
- * but to go to the filesystem for pages. By making the page fault call
- * vop_read (or write in the case of autogrow) they block on the iolock
- * until we have switched the extents.
- */
- if (VN_MAPPED(VFS_I(ip))) {
- error = XFS_ERROR(EBUSY);
- goto out_unlock;
- }
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_iunlock(tip, XFS_ILOCK_EXCL);
-
- /*
- * There is a race condition here since we gave up the
- * ilock. However, the data fork will not change since
- * we have the iolock (locked for truncation too) so we
- * are safe. We don't really care if non-io related
- * fields change.
- */
-
- xfs_tosspages(ip, 0, -1, FI_REMAPF);
-
- tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
- if ((error = xfs_trans_reserve(tp, 0,
- XFS_ICHANGE_LOG_RES(mp), 0,
- 0, 0))) {
- xfs_iunlock(ip, XFS_IOLOCK_EXCL);
- xfs_iunlock(tip, XFS_IOLOCK_EXCL);
- xfs_trans_cancel(tp, 0);
- goto out;
- }
- xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
-
- /*
- * Count the number of extended attribute blocks
- */
- if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
- (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
- error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
- if (error)
- goto out_trans_cancel;
- }
- if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
- (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
- error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
- &taforkblks);
- if (error)
- goto out_trans_cancel;
- }
-
- /*
- * Swap the data forks of the inodes
- */
- ifp = &ip->i_df;
- tifp = &tip->i_df;
- *tempifp = *ifp; /* struct copy */
- *ifp = *tifp; /* struct copy */
- *tifp = *tempifp; /* struct copy */
-
- /*
- * Fix the on-disk inode values
- */
- tmp = (__uint64_t)ip->i_d.di_nblocks;
- ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
- tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
-
- tmp = (__uint64_t) ip->i_d.di_nextents;
- ip->i_d.di_nextents = tip->i_d.di_nextents;
- tip->i_d.di_nextents = tmp;
-
- tmp = (__uint64_t) ip->i_d.di_format;
- ip->i_d.di_format = tip->i_d.di_format;
- tip->i_d.di_format = tmp;
-
- /*
- * The extents in the source inode could still contain speculative
- * preallocation beyond EOF (e.g. the file is open but not modified
- * while defrag is in progress). In that case, we need to copy over the
- * number of delalloc blocks the data fork in the source inode is
- * tracking beyond EOF so that when the fork is truncated away when the
- * temporary inode is unlinked we don't underrun the i_delayed_blks
- * counter on that inode.
- */
- ASSERT(tip->i_delayed_blks == 0);
- tip->i_delayed_blks = ip->i_delayed_blks;
- ip->i_delayed_blks = 0;
-
- src_log_flags = XFS_ILOG_CORE;
- switch (ip->i_d.di_format) {
- case XFS_DINODE_FMT_EXTENTS:
- /* If the extents fit in the inode, fix the
- * pointer. Otherwise it's already NULL or
- * pointing to the extent.
- */
- if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
- ifp->if_u1.if_extents =
- ifp->if_u2.if_inline_ext;
- }
- src_log_flags |= XFS_ILOG_DEXT;
- break;
- case XFS_DINODE_FMT_BTREE:
- src_log_flags |= XFS_ILOG_DBROOT;
- break;
- }
-
- target_log_flags = XFS_ILOG_CORE;
- switch (tip->i_d.di_format) {
- case XFS_DINODE_FMT_EXTENTS:
- /* If the extents fit in the inode, fix the
- * pointer. Otherwise it's already NULL or
- * pointing to the extent.
- */
- if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
- tifp->if_u1.if_extents =
- tifp->if_u2.if_inline_ext;
- }
- target_log_flags |= XFS_ILOG_DEXT;
- break;
- case XFS_DINODE_FMT_BTREE:
- target_log_flags |= XFS_ILOG_DBROOT;
- break;
- }
-
-
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-
- xfs_trans_log_inode(tp, ip, src_log_flags);
- xfs_trans_log_inode(tp, tip, target_log_flags);
-
- /*
- * If this is a synchronous mount, make sure that the
- * transaction goes to disk before returning to the user.
- */
- if (mp->m_flags & XFS_MOUNT_WSYNC)
- xfs_trans_set_sync(tp);
-
- error = xfs_trans_commit(tp, 0);
-
- trace_xfs_swap_extent_after(ip, 0);
- trace_xfs_swap_extent_after(tip, 1);
-out:
- kmem_free(tempifp);
- return error;
-
-out_unlock:
- xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- goto out;
-
-out_trans_cancel:
- xfs_trans_cancel(tp, 0);
- goto out_unlock;
-}
diff --git a/fs/xfs/xfs_dfrag.h b/fs/xfs/xfs_dfrag.h
deleted file mode 100644
index 20bdd935c12..00000000000
--- a/fs/xfs/xfs_dfrag.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * Copyright (c) 2000,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-#ifndef __XFS_DFRAG_H__
-#define __XFS_DFRAG_H__
-
-/*
- * Structure passed to xfs_swapext
- */
-
-typedef struct xfs_swapext
-{
- __int64_t sx_version; /* version */
- __int64_t sx_fdtarget; /* fd of target file */
- __int64_t sx_fdtmp; /* fd of tmp file */
- xfs_off_t sx_offset; /* offset into file */
- xfs_off_t sx_length; /* leng from offset */
- char sx_pad[16]; /* pad space, unused */
- xfs_bstat_t sx_stat; /* stat of target b4 copy */
-} xfs_swapext_t;
-
-/*
- * Version flag
- */
-#define XFS_SX_VERSION 0
-
-#ifdef __KERNEL__
-/*
- * Prototypes for visible xfs_dfrag.c routines.
- */
-
-/*
- * Syscall interface for xfs_swapext
- */
-int xfs_swapext(struct xfs_swapext *sx);
-
-#endif /* __KERNEL__ */
-
-#endif /* __XFS_DFRAG_H__ */
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index a3721633abc..623bbe8fd92 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -19,7 +19,7 @@
#define __XFS_DINODE_H__
#define XFS_DINODE_MAGIC 0x494e /* 'IN' */
-#define XFS_DINODE_GOOD_VERSION(v) (((v) == 1 || (v) == 2))
+#define XFS_DINODE_GOOD_VERSION(v) ((v) >= 1 && (v) <= 3)
typedef struct xfs_timestamp {
__be32 t_sec; /* timestamp seconds */
@@ -33,12 +33,15 @@ typedef struct xfs_timestamp {
* variable size the leftover area split into a data and an attribute fork.
* The format of the data and attribute fork depends on the format of the
* inode as indicated by di_format and di_aformat. To access the data and
- * attribute use the XFS_DFORK_PTR, XFS_DFORK_DPTR, and XFS_DFORK_PTR macros
+ * attribute use the XFS_DFORK_DPTR, XFS_DFORK_APTR, and XFS_DFORK_PTR macros
* below.
*
* There is a very similar struct icdinode in xfs_inode which matches the
* layout of the first 96 bytes of this structure, but is kept in native
* format instead of big endian.
+ *
+ * Note: di_flushiter is only used by v1/2 inodes - it's effectively a zeroed
+ * padding field for v3 inodes.
*/
typedef struct xfs_dinode {
__be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */
@@ -70,11 +73,38 @@ typedef struct xfs_dinode {
/* di_next_unlinked is the only non-core field in the old dinode */
__be32 di_next_unlinked;/* agi unlinked list ptr */
-} __attribute__((packed)) xfs_dinode_t;
+
+ /* start of the extended dinode, writable fields */
+ __le32 di_crc; /* CRC of the inode */
+ __be64 di_changecount; /* number of attribute changes */
+ __be64 di_lsn; /* flush sequence */
+ __be64 di_flags2; /* more random flags */
+ __u8 di_pad2[16]; /* more padding for future expansion */
+
+ /* fields only written to during inode creation */
+ xfs_timestamp_t di_crtime; /* time created */
+ __be64 di_ino; /* inode number */
+ uuid_t di_uuid; /* UUID of the filesystem */
+
+ /* structure must be padded to 64 bit alignment */
+} xfs_dinode_t;
+
+#define XFS_DINODE_CRC_OFF offsetof(struct xfs_dinode, di_crc)
#define DI_MAX_FLUSH 0xffff
/*
+ * Size of the core inode on disk. Version 1 and 2 inodes have
+ * the same size, but version 3 has grown a few additional fields.
+ */
+static inline uint xfs_dinode_size(int version)
+{
+ if (version == 3)
+ return sizeof(struct xfs_dinode);
+ return offsetof(struct xfs_dinode, di_crc);
+}
+
+/*
* The 32 bit link count in the inode theoretically maxes out at UINT_MAX.
* Since the pathconf interface is signed, we use 2^31 - 1 instead.
* The old inode format had a 16 bit link count, so its maximum is USHRT_MAX.
@@ -104,11 +134,8 @@ typedef enum xfs_dinode_fmt {
/*
* Inode size for given fs.
*/
-#define XFS_LITINO(mp) \
- ((int)(((mp)->m_sb.sb_inodesize) - sizeof(struct xfs_dinode)))
-
-#define XFS_BROOT_SIZE_ADJ \
- (XFS_BTREE_LBLOCK_LEN - sizeof(xfs_bmdr_block_t))
+#define XFS_LITINO(mp, version) \
+ ((int)(((mp)->m_sb.sb_inodesize) - xfs_dinode_size(version)))
/*
* Inode data & attribute fork sizes, per inode.
@@ -119,10 +146,10 @@ typedef enum xfs_dinode_fmt {
#define XFS_DFORK_DSIZE(dip,mp) \
(XFS_DFORK_Q(dip) ? \
XFS_DFORK_BOFF(dip) : \
- XFS_LITINO(mp))
+ XFS_LITINO(mp, (dip)->di_version))
#define XFS_DFORK_ASIZE(dip,mp) \
(XFS_DFORK_Q(dip) ? \
- XFS_LITINO(mp) - XFS_DFORK_BOFF(dip) : \
+ XFS_LITINO(mp, (dip)->di_version) - XFS_DFORK_BOFF(dip) : \
0)
#define XFS_DFORK_SIZE(dip,mp,w) \
((w) == XFS_DATA_FORK ? \
@@ -133,7 +160,7 @@ typedef enum xfs_dinode_fmt {
* Return pointers to the data or attribute forks.
*/
#define XFS_DFORK_DPTR(dip) \
- ((char *)(dip) + sizeof(struct xfs_dinode))
+ ((char *)dip + xfs_dinode_size(dip->di_version))
#define XFS_DFORK_APTR(dip) \
(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
#define XFS_DFORK_PTR(dip,w) \
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index 67a250c36d4..79670cda48a 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -17,28 +17,27 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_inum.h"
-#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_dir2.h"
-#include "xfs_dir2_format.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
-#include "xfs_vnodeops.h"
#include "xfs_trace.h"
+#include "xfs_dinode.h"
+
+struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2, XFS_DIR3_FT_DIR };
-struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2};
/*
* ASCII case-insensitive (ie. A-Z) support for directories that was
@@ -86,29 +85,74 @@ static struct xfs_nameops xfs_ascii_ci_nameops = {
.compname = xfs_ascii_ci_compname,
};
-void
-xfs_dir_mount(
- xfs_mount_t *mp)
+int
+xfs_da_mount(
+ struct xfs_mount *mp)
{
- ASSERT(xfs_sb_version_hasdirv2(&mp->m_sb));
+ struct xfs_da_geometry *dageo;
+ int nodehdr_size;
+
+
+ ASSERT(mp->m_sb.sb_versionnum & XFS_SB_VERSION_DIRV2BIT);
ASSERT((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) <=
XFS_MAX_BLOCKSIZE);
- mp->m_dirblksize = 1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog);
- mp->m_dirblkfsbs = 1 << mp->m_sb.sb_dirblklog;
- mp->m_dirdatablk = xfs_dir2_db_to_da(mp, XFS_DIR2_DATA_FIRSTDB(mp));
- mp->m_dirleafblk = xfs_dir2_db_to_da(mp, XFS_DIR2_LEAF_FIRSTDB(mp));
- mp->m_dirfreeblk = xfs_dir2_db_to_da(mp, XFS_DIR2_FREE_FIRSTDB(mp));
- mp->m_attr_node_ents =
- (mp->m_sb.sb_blocksize - (uint)sizeof(xfs_da_node_hdr_t)) /
- (uint)sizeof(xfs_da_node_entry_t);
- mp->m_dir_node_ents =
- (mp->m_dirblksize - (uint)sizeof(xfs_da_node_hdr_t)) /
- (uint)sizeof(xfs_da_node_entry_t);
- mp->m_dir_magicpct = (mp->m_dirblksize * 37) / 100;
+
+ mp->m_dir_inode_ops = xfs_dir_get_ops(mp, NULL);
+ mp->m_nondir_inode_ops = xfs_nondir_get_ops(mp, NULL);
+
+ nodehdr_size = mp->m_dir_inode_ops->node_hdr_size;
+ mp->m_dir_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
+ KM_SLEEP | KM_MAYFAIL);
+ mp->m_attr_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
+ KM_SLEEP | KM_MAYFAIL);
+ if (!mp->m_dir_geo || !mp->m_attr_geo) {
+ kmem_free(mp->m_dir_geo);
+ kmem_free(mp->m_attr_geo);
+ return ENOMEM;
+ }
+
+ /* set up directory geometry */
+ dageo = mp->m_dir_geo;
+ dageo->blklog = mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog;
+ dageo->fsblog = mp->m_sb.sb_blocklog;
+ dageo->blksize = 1 << dageo->blklog;
+ dageo->fsbcount = 1 << mp->m_sb.sb_dirblklog;
+
+ /*
+ * Now we've set up the block conversion variables, we can calculate the
+ * segment block constants using the geometry structure.
+ */
+ dageo->datablk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_DATA_OFFSET);
+ dageo->leafblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_LEAF_OFFSET);
+ dageo->freeblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_FREE_OFFSET);
+ dageo->node_ents = (dageo->blksize - nodehdr_size) /
+ (uint)sizeof(xfs_da_node_entry_t);
+ dageo->magicpct = (dageo->blksize * 37) / 100;
+
+ /* set up attribute geometry - single fsb only */
+ dageo = mp->m_attr_geo;
+ dageo->blklog = mp->m_sb.sb_blocklog;
+ dageo->fsblog = mp->m_sb.sb_blocklog;
+ dageo->blksize = 1 << dageo->blklog;
+ dageo->fsbcount = 1;
+ dageo->node_ents = (dageo->blksize - nodehdr_size) /
+ (uint)sizeof(xfs_da_node_entry_t);
+ dageo->magicpct = (dageo->blksize * 37) / 100;
+
if (xfs_sb_version_hasasciici(&mp->m_sb))
mp->m_dirnameops = &xfs_ascii_ci_nameops;
else
mp->m_dirnameops = &xfs_default_nameops;
+
+ return 0;
+}
+
+void
+xfs_da_unmount(
+ struct xfs_mount *mp)
+{
+ kmem_free(mp->m_dir_geo);
+ kmem_free(mp->m_attr_geo);
}
/*
@@ -172,16 +216,24 @@ xfs_dir_init(
xfs_inode_t *dp,
xfs_inode_t *pdp)
{
- xfs_da_args_t args;
+ struct xfs_da_args *args;
int error;
- memset((char *)&args, 0, sizeof(args));
- args.dp = dp;
- args.trans = tp;
ASSERT(S_ISDIR(dp->i_d.di_mode));
- if ((error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino)))
+ error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino);
+ if (error)
return error;
- return xfs_dir2_sf_create(&args, pdp->i_ino);
+
+ args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+ if (!args)
+ return ENOMEM;
+
+ args->geo = dp->i_mount->m_dir_geo;
+ args->dp = dp;
+ args->trans = tp;
+ error = xfs_dir2_sf_create(args, pdp->i_ino);
+ kmem_free(args);
+ return error;
}
/*
@@ -197,40 +249,57 @@ xfs_dir_createname(
xfs_bmap_free_t *flist, /* bmap's freeblock list */
xfs_extlen_t total) /* bmap's total block count */
{
- xfs_da_args_t args;
+ struct xfs_da_args *args;
int rval;
int v; /* type-checking value */
ASSERT(S_ISDIR(dp->i_d.di_mode));
- if ((rval = xfs_dir_ino_validate(tp->t_mountp, inum)))
+ rval = xfs_dir_ino_validate(tp->t_mountp, inum);
+ if (rval)
return rval;
XFS_STATS_INC(xs_dir_create);
- memset(&args, 0, sizeof(xfs_da_args_t));
- args.name = name->name;
- args.namelen = name->len;
- args.hashval = dp->i_mount->m_dirnameops->hashname(name);
- args.inumber = inum;
- args.dp = dp;
- args.firstblock = first;
- args.flist = flist;
- args.total = total;
- args.whichfork = XFS_DATA_FORK;
- args.trans = tp;
- args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
-
- if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- rval = xfs_dir2_sf_addname(&args);
- else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_block_addname(&args);
- else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_leaf_addname(&args);
+ args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+ if (!args)
+ return ENOMEM;
+
+ args->geo = dp->i_mount->m_dir_geo;
+ args->name = name->name;
+ args->namelen = name->len;
+ args->filetype = name->type;
+ args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+ args->inumber = inum;
+ args->dp = dp;
+ args->firstblock = first;
+ args->flist = flist;
+ args->total = total;
+ args->whichfork = XFS_DATA_FORK;
+ args->trans = tp;
+ args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+
+ if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+ rval = xfs_dir2_sf_addname(args);
+ goto out_free;
+ }
+
+ rval = xfs_dir2_isblock(args, &v);
+ if (rval)
+ goto out_free;
+ if (v) {
+ rval = xfs_dir2_block_addname(args);
+ goto out_free;
+ }
+
+ rval = xfs_dir2_isleaf(args, &v);
+ if (rval)
+ goto out_free;
+ if (v)
+ rval = xfs_dir2_leaf_addname(args);
else
- rval = xfs_dir2_node_addname(&args);
+ rval = xfs_dir2_node_addname(args);
+
+out_free:
+ kmem_free(args);
return rval;
}
@@ -273,45 +342,67 @@ xfs_dir_lookup(
xfs_ino_t *inum, /* out: inode number */
struct xfs_name *ci_name) /* out: actual name if CI match */
{
- xfs_da_args_t args;
+ struct xfs_da_args *args;
int rval;
int v; /* type-checking value */
ASSERT(S_ISDIR(dp->i_d.di_mode));
XFS_STATS_INC(xs_dir_lookup);
- memset(&args, 0, sizeof(xfs_da_args_t));
- args.name = name->name;
- args.namelen = name->len;
- args.hashval = dp->i_mount->m_dirnameops->hashname(name);
- args.dp = dp;
- args.whichfork = XFS_DATA_FORK;
- args.trans = tp;
- args.op_flags = XFS_DA_OP_OKNOENT;
+ /*
+ * We need to use KM_NOFS here so that lockdep will not throw false
+ * positive deadlock warnings on a non-transactional lookup path. It is
+ * safe to recurse into inode recalim in that case, but lockdep can't
+ * easily be taught about it. Hence KM_NOFS avoids having to add more
+ * lockdep Doing this avoids having to add a bunch of lockdep class
+ * annotations into the reclaim path for the ilock.
+ */
+ args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+ args->geo = dp->i_mount->m_dir_geo;
+ args->name = name->name;
+ args->namelen = name->len;
+ args->filetype = name->type;
+ args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+ args->dp = dp;
+ args->whichfork = XFS_DATA_FORK;
+ args->trans = tp;
+ args->op_flags = XFS_DA_OP_OKNOENT;
if (ci_name)
- args.op_flags |= XFS_DA_OP_CILOOKUP;
+ args->op_flags |= XFS_DA_OP_CILOOKUP;
- if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- rval = xfs_dir2_sf_lookup(&args);
- else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_block_lookup(&args);
- else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_leaf_lookup(&args);
+ if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+ rval = xfs_dir2_sf_lookup(args);
+ goto out_check_rval;
+ }
+
+ rval = xfs_dir2_isblock(args, &v);
+ if (rval)
+ goto out_free;
+ if (v) {
+ rval = xfs_dir2_block_lookup(args);
+ goto out_check_rval;
+ }
+
+ rval = xfs_dir2_isleaf(args, &v);
+ if (rval)
+ goto out_free;
+ if (v)
+ rval = xfs_dir2_leaf_lookup(args);
else
- rval = xfs_dir2_node_lookup(&args);
+ rval = xfs_dir2_node_lookup(args);
+
+out_check_rval:
if (rval == EEXIST)
rval = 0;
if (!rval) {
- *inum = args.inumber;
+ *inum = args->inumber;
if (ci_name) {
- ci_name->name = args.value;
- ci_name->len = args.valuelen;
+ ci_name->name = args->value;
+ ci_name->len = args->valuelen;
}
}
+out_free:
+ kmem_free(args);
return rval;
}
@@ -328,71 +419,52 @@ xfs_dir_removename(
xfs_bmap_free_t *flist, /* bmap's freeblock list */
xfs_extlen_t total) /* bmap's total block count */
{
- xfs_da_args_t args;
+ struct xfs_da_args *args;
int rval;
int v; /* type-checking value */
ASSERT(S_ISDIR(dp->i_d.di_mode));
XFS_STATS_INC(xs_dir_remove);
- memset(&args, 0, sizeof(xfs_da_args_t));
- args.name = name->name;
- args.namelen = name->len;
- args.hashval = dp->i_mount->m_dirnameops->hashname(name);
- args.inumber = ino;
- args.dp = dp;
- args.firstblock = first;
- args.flist = flist;
- args.total = total;
- args.whichfork = XFS_DATA_FORK;
- args.trans = tp;
-
- if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- rval = xfs_dir2_sf_removename(&args);
- else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_block_removename(&args);
- else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_leaf_removename(&args);
- else
- rval = xfs_dir2_node_removename(&args);
- return rval;
-}
-
-/*
- * Read a directory.
- */
-int
-xfs_readdir(
- xfs_inode_t *dp,
- void *dirent,
- size_t bufsize,
- xfs_off_t *offset,
- filldir_t filldir)
-{
- int rval; /* return value */
- int v; /* type-checking value */
+ args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+ if (!args)
+ return ENOMEM;
- trace_xfs_readdir(dp);
+ args->geo = dp->i_mount->m_dir_geo;
+ args->name = name->name;
+ args->namelen = name->len;
+ args->filetype = name->type;
+ args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+ args->inumber = ino;
+ args->dp = dp;
+ args->firstblock = first;
+ args->flist = flist;
+ args->total = total;
+ args->whichfork = XFS_DATA_FORK;
+ args->trans = tp;
+
+ if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+ rval = xfs_dir2_sf_removename(args);
+ goto out_free;
+ }
- if (XFS_FORCED_SHUTDOWN(dp->i_mount))
- return XFS_ERROR(EIO);
+ rval = xfs_dir2_isblock(args, &v);
+ if (rval)
+ goto out_free;
+ if (v) {
+ rval = xfs_dir2_block_removename(args);
+ goto out_free;
+ }
- ASSERT(S_ISDIR(dp->i_d.di_mode));
- XFS_STATS_INC(xs_dir_getdents);
-
- if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- rval = xfs_dir2_sf_getdents(dp, dirent, offset, filldir);
- else if ((rval = xfs_dir2_isblock(NULL, dp, &v)))
- ;
- else if (v)
- rval = xfs_dir2_block_getdents(dp, dirent, offset, filldir);
+ rval = xfs_dir2_isleaf(args, &v);
+ if (rval)
+ goto out_free;
+ if (v)
+ rval = xfs_dir2_leaf_removename(args);
else
- rval = xfs_dir2_leaf_getdents(dp, dirent, bufsize, offset,
- filldir);
+ rval = xfs_dir2_node_removename(args);
+out_free:
+ kmem_free(args);
return rval;
}
@@ -409,39 +481,55 @@ xfs_dir_replace(
xfs_bmap_free_t *flist, /* bmap's freeblock list */
xfs_extlen_t total) /* bmap's total block count */
{
- xfs_da_args_t args;
+ struct xfs_da_args *args;
int rval;
int v; /* type-checking value */
ASSERT(S_ISDIR(dp->i_d.di_mode));
- if ((rval = xfs_dir_ino_validate(tp->t_mountp, inum)))
+ rval = xfs_dir_ino_validate(tp->t_mountp, inum);
+ if (rval)
return rval;
- memset(&args, 0, sizeof(xfs_da_args_t));
- args.name = name->name;
- args.namelen = name->len;
- args.hashval = dp->i_mount->m_dirnameops->hashname(name);
- args.inumber = inum;
- args.dp = dp;
- args.firstblock = first;
- args.flist = flist;
- args.total = total;
- args.whichfork = XFS_DATA_FORK;
- args.trans = tp;
-
- if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- rval = xfs_dir2_sf_replace(&args);
- else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_block_replace(&args);
- else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_leaf_replace(&args);
+ args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+ if (!args)
+ return ENOMEM;
+
+ args->geo = dp->i_mount->m_dir_geo;
+ args->name = name->name;
+ args->namelen = name->len;
+ args->filetype = name->type;
+ args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+ args->inumber = inum;
+ args->dp = dp;
+ args->firstblock = first;
+ args->flist = flist;
+ args->total = total;
+ args->whichfork = XFS_DATA_FORK;
+ args->trans = tp;
+
+ if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+ rval = xfs_dir2_sf_replace(args);
+ goto out_free;
+ }
+
+ rval = xfs_dir2_isblock(args, &v);
+ if (rval)
+ goto out_free;
+ if (v) {
+ rval = xfs_dir2_block_replace(args);
+ goto out_free;
+ }
+
+ rval = xfs_dir2_isleaf(args, &v);
+ if (rval)
+ goto out_free;
+ if (v)
+ rval = xfs_dir2_leaf_replace(args);
else
- rval = xfs_dir2_node_replace(&args);
+ rval = xfs_dir2_node_replace(args);
+out_free:
+ kmem_free(args);
return rval;
}
@@ -456,7 +544,7 @@ xfs_dir_canenter(
struct xfs_name *name, /* name of entry to add */
uint resblks)
{
- xfs_da_args_t args;
+ struct xfs_da_args *args;
int rval;
int v; /* type-checking value */
@@ -465,28 +553,43 @@ xfs_dir_canenter(
ASSERT(S_ISDIR(dp->i_d.di_mode));
- memset(&args, 0, sizeof(xfs_da_args_t));
- args.name = name->name;
- args.namelen = name->len;
- args.hashval = dp->i_mount->m_dirnameops->hashname(name);
- args.dp = dp;
- args.whichfork = XFS_DATA_FORK;
- args.trans = tp;
- args.op_flags = XFS_DA_OP_JUSTCHECK | XFS_DA_OP_ADDNAME |
+ args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+ if (!args)
+ return ENOMEM;
+
+ args->geo = dp->i_mount->m_dir_geo;
+ args->name = name->name;
+ args->namelen = name->len;
+ args->filetype = name->type;
+ args->hashval = dp->i_mount->m_dirnameops->hashname(name);
+ args->dp = dp;
+ args->whichfork = XFS_DATA_FORK;
+ args->trans = tp;
+ args->op_flags = XFS_DA_OP_JUSTCHECK | XFS_DA_OP_ADDNAME |
XFS_DA_OP_OKNOENT;
- if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
- rval = xfs_dir2_sf_addname(&args);
- else if ((rval = xfs_dir2_isblock(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_block_addname(&args);
- else if ((rval = xfs_dir2_isleaf(tp, dp, &v)))
- return rval;
- else if (v)
- rval = xfs_dir2_leaf_addname(&args);
+ if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+ rval = xfs_dir2_sf_addname(args);
+ goto out_free;
+ }
+
+ rval = xfs_dir2_isblock(args, &v);
+ if (rval)
+ goto out_free;
+ if (v) {
+ rval = xfs_dir2_block_addname(args);
+ goto out_free;
+ }
+
+ rval = xfs_dir2_isleaf(args, &v);
+ if (rval)
+ goto out_free;
+ if (v)
+ rval = xfs_dir2_leaf_addname(args);
else
- rval = xfs_dir2_node_addname(&args);
+ rval = xfs_dir2_node_addname(args);
+out_free:
+ kmem_free(args);
return rval;
}
@@ -518,13 +621,13 @@ xfs_dir2_grow_inode(
* Set lowest possible block in the space requested.
*/
bno = XFS_B_TO_FSBT(mp, space * XFS_DIR2_SPACE_SIZE);
- count = mp->m_dirblkfsbs;
+ count = args->geo->fsbcount;
error = xfs_da_grow_inode_int(args, &bno, count);
if (error)
return error;
- *dbp = xfs_dir2_da_to_db(mp, (xfs_dablk_t)bno);
+ *dbp = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)bno);
/*
* Update file's size if this is the data space and it grew.
@@ -546,19 +649,16 @@ xfs_dir2_grow_inode(
*/
int
xfs_dir2_isblock(
- xfs_trans_t *tp,
- xfs_inode_t *dp,
- int *vp) /* out: 1 is block, 0 is not block */
+ struct xfs_da_args *args,
+ int *vp) /* out: 1 is block, 0 is not block */
{
- xfs_fileoff_t last; /* last file offset */
- xfs_mount_t *mp;
- int rval;
+ xfs_fileoff_t last; /* last file offset */
+ int rval;
- mp = dp->i_mount;
- if ((rval = xfs_bmap_last_offset(tp, dp, &last, XFS_DATA_FORK)))
+ if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
return rval;
- rval = XFS_FSB_TO_B(mp, last) == mp->m_dirblksize;
- ASSERT(rval == 0 || dp->i_d.di_size == mp->m_dirblksize);
+ rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
+ ASSERT(rval == 0 || args->dp->i_d.di_size == args->geo->blksize);
*vp = rval;
return 0;
}
@@ -568,18 +668,15 @@ xfs_dir2_isblock(
*/
int
xfs_dir2_isleaf(
- xfs_trans_t *tp,
- xfs_inode_t *dp,
- int *vp) /* out: 1 is leaf, 0 is not leaf */
+ struct xfs_da_args *args,
+ int *vp) /* out: 1 is block, 0 is not block */
{
- xfs_fileoff_t last; /* last file offset */
- xfs_mount_t *mp;
- int rval;
+ xfs_fileoff_t last; /* last file offset */
+ int rval;
- mp = dp->i_mount;
- if ((rval = xfs_bmap_last_offset(tp, dp, &last, XFS_DATA_FORK)))
+ if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
return rval;
- *vp = last == mp->m_dirleafblk + (1 << mp->m_sb.sb_dirblklog);
+ *vp = last == args->geo->leafblk + args->geo->fsbcount;
return 0;
}
@@ -592,7 +689,7 @@ int
xfs_dir2_shrink_inode(
xfs_da_args_t *args,
xfs_dir2_db_t db,
- xfs_dabuf_t *bp)
+ struct xfs_buf *bp)
{
xfs_fileoff_t bno; /* directory file offset */
xfs_dablk_t da; /* directory file offset */
@@ -607,11 +704,11 @@ xfs_dir2_shrink_inode(
dp = args->dp;
mp = dp->i_mount;
tp = args->trans;
- da = xfs_dir2_db_to_da(mp, db);
+ da = xfs_dir2_db_to_da(args->geo, db);
/*
* Unmap the fsblock(s).
*/
- if ((error = xfs_bunmapi(tp, dp, da, mp->m_dirblkfsbs,
+ if ((error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount,
XFS_BMAPI_METADATA, 0, args->firstblock, args->flist,
&done))) {
/*
@@ -634,16 +731,16 @@ xfs_dir2_shrink_inode(
/*
* Invalidate the buffer from the transaction.
*/
- xfs_da_binval(tp, bp);
+ xfs_trans_binval(tp, bp);
/*
* If it's not a data block, we're done.
*/
- if (db >= XFS_DIR2_LEAF_FIRSTDB(mp))
+ if (db >= xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET))
return 0;
/*
* If the block isn't the last one in the directory, we're done.
*/
- if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(mp, db + 1, 0))
+ if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(args->geo, db + 1, 0))
return 0;
bno = da;
if ((error = xfs_bmap_last_before(tp, dp, &bno, XFS_DATA_FORK))) {
@@ -652,7 +749,7 @@ xfs_dir2_shrink_inode(
*/
return error;
}
- if (db == mp->m_dirdatablk)
+ if (db == args->geo->datablk)
ASSERT(bno == 0);
else
ASSERT(bno > 0);
diff --git a/fs/xfs/xfs_dir2.h b/fs/xfs/xfs_dir2.h
index e937d9991c1..c8e86b0b5e9 100644
--- a/fs/xfs/xfs_dir2.h
+++ b/fs/xfs/xfs_dir2.h
@@ -23,14 +23,100 @@ struct xfs_da_args;
struct xfs_inode;
struct xfs_mount;
struct xfs_trans;
+struct xfs_dir2_sf_hdr;
+struct xfs_dir2_sf_entry;
+struct xfs_dir2_data_hdr;
+struct xfs_dir2_data_entry;
+struct xfs_dir2_data_unused;
extern struct xfs_name xfs_name_dotdot;
/*
+ * directory operations vector for encode/decode routines
+ */
+struct xfs_dir_ops {
+ int (*sf_entsize)(struct xfs_dir2_sf_hdr *hdr, int len);
+ struct xfs_dir2_sf_entry *
+ (*sf_nextentry)(struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep);
+ __uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep);
+ void (*sf_put_ftype)(struct xfs_dir2_sf_entry *sfep,
+ __uint8_t ftype);
+ xfs_ino_t (*sf_get_ino)(struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep);
+ void (*sf_put_ino)(struct xfs_dir2_sf_hdr *hdr,
+ struct xfs_dir2_sf_entry *sfep,
+ xfs_ino_t ino);
+ xfs_ino_t (*sf_get_parent_ino)(struct xfs_dir2_sf_hdr *hdr);
+ void (*sf_put_parent_ino)(struct xfs_dir2_sf_hdr *hdr,
+ xfs_ino_t ino);
+
+ int (*data_entsize)(int len);
+ __uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep);
+ void (*data_put_ftype)(struct xfs_dir2_data_entry *dep,
+ __uint8_t ftype);
+ __be16 * (*data_entry_tag_p)(struct xfs_dir2_data_entry *dep);
+ struct xfs_dir2_data_free *
+ (*data_bestfree_p)(struct xfs_dir2_data_hdr *hdr);
+
+ xfs_dir2_data_aoff_t data_dot_offset;
+ xfs_dir2_data_aoff_t data_dotdot_offset;
+ xfs_dir2_data_aoff_t data_first_offset;
+ size_t data_entry_offset;
+
+ struct xfs_dir2_data_entry *
+ (*data_dot_entry_p)(struct xfs_dir2_data_hdr *hdr);
+ struct xfs_dir2_data_entry *
+ (*data_dotdot_entry_p)(struct xfs_dir2_data_hdr *hdr);
+ struct xfs_dir2_data_entry *
+ (*data_first_entry_p)(struct xfs_dir2_data_hdr *hdr);
+ struct xfs_dir2_data_entry *
+ (*data_entry_p)(struct xfs_dir2_data_hdr *hdr);
+ struct xfs_dir2_data_unused *
+ (*data_unused_p)(struct xfs_dir2_data_hdr *hdr);
+
+ int leaf_hdr_size;
+ void (*leaf_hdr_to_disk)(struct xfs_dir2_leaf *to,
+ struct xfs_dir3_icleaf_hdr *from);
+ void (*leaf_hdr_from_disk)(struct xfs_dir3_icleaf_hdr *to,
+ struct xfs_dir2_leaf *from);
+ int (*leaf_max_ents)(struct xfs_da_geometry *geo);
+ struct xfs_dir2_leaf_entry *
+ (*leaf_ents_p)(struct xfs_dir2_leaf *lp);
+
+ int node_hdr_size;
+ void (*node_hdr_to_disk)(struct xfs_da_intnode *to,
+ struct xfs_da3_icnode_hdr *from);
+ void (*node_hdr_from_disk)(struct xfs_da3_icnode_hdr *to,
+ struct xfs_da_intnode *from);
+ struct xfs_da_node_entry *
+ (*node_tree_p)(struct xfs_da_intnode *dap);
+
+ int free_hdr_size;
+ void (*free_hdr_to_disk)(struct xfs_dir2_free *to,
+ struct xfs_dir3_icfree_hdr *from);
+ void (*free_hdr_from_disk)(struct xfs_dir3_icfree_hdr *to,
+ struct xfs_dir2_free *from);
+ int (*free_max_bests)(struct xfs_da_geometry *geo);
+ __be16 * (*free_bests_p)(struct xfs_dir2_free *free);
+ xfs_dir2_db_t (*db_to_fdb)(struct xfs_da_geometry *geo,
+ xfs_dir2_db_t db);
+ int (*db_to_fdindex)(struct xfs_da_geometry *geo,
+ xfs_dir2_db_t db);
+};
+
+extern const struct xfs_dir_ops *
+ xfs_dir_get_ops(struct xfs_mount *mp, struct xfs_inode *dp);
+extern const struct xfs_dir_ops *
+ xfs_nondir_get_ops(struct xfs_mount *mp, struct xfs_inode *dp);
+
+/*
* Generic directory interface routines
*/
extern void xfs_dir_startup(void);
-extern void xfs_dir_mount(struct xfs_mount *mp);
+extern int xfs_da_mount(struct xfs_mount *mp);
+extern void xfs_da_unmount(struct xfs_mount *mp);
+
extern int xfs_dir_isempty(struct xfs_inode *dp);
extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
struct xfs_inode *pdp);
@@ -57,4 +143,38 @@ extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
*/
extern int xfs_dir2_sf_to_block(struct xfs_da_args *args);
+/*
+ * Interface routines used by userspace utilities
+ */
+extern int xfs_dir2_isblock(struct xfs_da_args *args, int *r);
+extern int xfs_dir2_isleaf(struct xfs_da_args *args, int *r);
+extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
+ struct xfs_buf *bp);
+
+extern void xfs_dir2_data_freescan(struct xfs_inode *dp,
+ struct xfs_dir2_data_hdr *hdr, int *loghead);
+extern void xfs_dir2_data_log_entry(struct xfs_da_args *args,
+ struct xfs_buf *bp, struct xfs_dir2_data_entry *dep);
+extern void xfs_dir2_data_log_header(struct xfs_da_args *args,
+ struct xfs_buf *bp);
+extern void xfs_dir2_data_log_unused(struct xfs_da_args *args,
+ struct xfs_buf *bp, struct xfs_dir2_data_unused *dup);
+extern void xfs_dir2_data_make_free(struct xfs_da_args *args,
+ struct xfs_buf *bp, xfs_dir2_data_aoff_t offset,
+ xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp);
+extern void xfs_dir2_data_use_free(struct xfs_da_args *args,
+ struct xfs_buf *bp, struct xfs_dir2_data_unused *dup,
+ xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len,
+ int *needlogp, int *needscanp);
+
+extern struct xfs_dir2_data_free *xfs_dir2_data_freefind(
+ struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_free *bf,
+ struct xfs_dir2_data_unused *dup);
+
+extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
+extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
+extern const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops;
+extern const struct xfs_buf_ops xfs_dir3_free_buf_ops;
+extern const struct xfs_buf_ops xfs_dir3_data_buf_ops;
+
#endif /* __XFS_DIR2_H__ */
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 586732f2d80..c7cd3154026 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -17,30 +18,33 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
+#include "xfs_trans.h"
#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
+#include "xfs_buf_item.h"
#include "xfs_dir2.h"
-#include "xfs_dir2_format.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_cksum.h"
+#include "xfs_dinode.h"
/*
* Local function prototypes.
*/
-static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, xfs_dabuf_t *bp, int first,
- int last);
-static void xfs_dir2_block_log_tail(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **bpp,
+static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, struct xfs_buf *bp,
+ int first, int last);
+static void xfs_dir2_block_log_tail(xfs_trans_t *tp, struct xfs_buf *bp);
+static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, struct xfs_buf **bpp,
int *entno);
static int xfs_dir2_block_sort(const void *a, const void *b);
@@ -56,6 +60,273 @@ xfs_dir_startup(void)
xfs_dir_hash_dotdot = xfs_da_hashname((unsigned char *)"..", 2);
}
+static bool
+xfs_dir3_block_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ if (hdr3->magic != cpu_to_be32(XFS_DIR3_BLOCK_MAGIC))
+ return false;
+ if (!uuid_equal(&hdr3->uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
+ return false;
+ } else {
+ if (hdr3->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))
+ return false;
+ }
+ if (__xfs_dir3_data_check(NULL, bp))
+ return false;
+ return true;
+}
+
+static void
+xfs_dir3_block_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_dir3_block_verify(bp))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+}
+
+static void
+xfs_dir3_block_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ if (!xfs_dir3_block_verify(bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (bip)
+ hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF);
+}
+
+const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
+ .verify_read = xfs_dir3_block_read_verify,
+ .verify_write = xfs_dir3_block_write_verify,
+};
+
+int
+xfs_dir3_block_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ struct xfs_buf **bpp)
+{
+ struct xfs_mount *mp = dp->i_mount;
+ int err;
+
+ err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp,
+ XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
+ if (!err && tp)
+ xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF);
+ return err;
+}
+
+static void
+xfs_dir3_block_init(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_buf *bp,
+ struct xfs_inode *dp)
+{
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ bp->b_ops = &xfs_dir3_block_buf_ops;
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_BLOCK_BUF);
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ memset(hdr3, 0, sizeof(*hdr3));
+ hdr3->magic = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
+ hdr3->blkno = cpu_to_be64(bp->b_bn);
+ hdr3->owner = cpu_to_be64(dp->i_ino);
+ uuid_copy(&hdr3->uuid, &mp->m_sb.sb_uuid);
+ return;
+
+ }
+ hdr3->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
+}
+
+static void
+xfs_dir2_block_need_space(
+ struct xfs_inode *dp,
+ struct xfs_dir2_data_hdr *hdr,
+ struct xfs_dir2_block_tail *btp,
+ struct xfs_dir2_leaf_entry *blp,
+ __be16 **tagpp,
+ struct xfs_dir2_data_unused **dupp,
+ struct xfs_dir2_data_unused **enddupp,
+ int *compact,
+ int len)
+{
+ struct xfs_dir2_data_free *bf;
+ __be16 *tagp = NULL;
+ struct xfs_dir2_data_unused *dup = NULL;
+ struct xfs_dir2_data_unused *enddup = NULL;
+
+ *compact = 0;
+ bf = dp->d_ops->data_bestfree_p(hdr);
+
+ /*
+ * If there are stale entries we'll use one for the leaf.
+ */
+ if (btp->stale) {
+ if (be16_to_cpu(bf[0].length) >= len) {
+ /*
+ * The biggest entry enough to avoid compaction.
+ */
+ dup = (xfs_dir2_data_unused_t *)
+ ((char *)hdr + be16_to_cpu(bf[0].offset));
+ goto out;
+ }
+
+ /*
+ * Will need to compact to make this work.
+ * Tag just before the first leaf entry.
+ */
+ *compact = 1;
+ tagp = (__be16 *)blp - 1;
+
+ /* Data object just before the first leaf entry. */
+ dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
+
+ /*
+ * If it's not free then the data will go where the
+ * leaf data starts now, if it works at all.
+ */
+ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
+ if (be16_to_cpu(dup->length) + (be32_to_cpu(btp->stale) - 1) *
+ (uint)sizeof(*blp) < len)
+ dup = NULL;
+ } else if ((be32_to_cpu(btp->stale) - 1) * (uint)sizeof(*blp) < len)
+ dup = NULL;
+ else
+ dup = (xfs_dir2_data_unused_t *)blp;
+ goto out;
+ }
+
+ /*
+ * no stale entries, so just use free space.
+ * Tag just before the first leaf entry.
+ */
+ tagp = (__be16 *)blp - 1;
+
+ /* Data object just before the first leaf entry. */
+ enddup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
+
+ /*
+ * If it's not free then can't do this add without cleaning up:
+ * the space before the first leaf entry needs to be free so it
+ * can be expanded to hold the pointer to the new entry.
+ */
+ if (be16_to_cpu(enddup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
+ /*
+ * Check out the biggest freespace and see if it's the same one.
+ */
+ dup = (xfs_dir2_data_unused_t *)
+ ((char *)hdr + be16_to_cpu(bf[0].offset));
+ if (dup != enddup) {
+ /*
+ * Not the same free entry, just check its length.
+ */
+ if (be16_to_cpu(dup->length) < len)
+ dup = NULL;
+ goto out;
+ }
+
+ /*
+ * It is the biggest freespace, can it hold the leaf too?
+ */
+ if (be16_to_cpu(dup->length) < len + (uint)sizeof(*blp)) {
+ /*
+ * Yes, use the second-largest entry instead if it works.
+ */
+ if (be16_to_cpu(bf[1].length) >= len)
+ dup = (xfs_dir2_data_unused_t *)
+ ((char *)hdr + be16_to_cpu(bf[1].offset));
+ else
+ dup = NULL;
+ }
+ }
+out:
+ *tagpp = tagp;
+ *dupp = dup;
+ *enddupp = enddup;
+}
+
+/*
+ * compact the leaf entries.
+ * Leave the highest-numbered stale entry stale.
+ * XXX should be the one closest to mid but mid is not yet computed.
+ */
+static void
+xfs_dir2_block_compact(
+ struct xfs_da_args *args,
+ struct xfs_buf *bp,
+ struct xfs_dir2_data_hdr *hdr,
+ struct xfs_dir2_block_tail *btp,
+ struct xfs_dir2_leaf_entry *blp,
+ int *needlog,
+ int *lfloghigh,
+ int *lfloglow)
+{
+ int fromidx; /* source leaf index */
+ int toidx; /* target leaf index */
+ int needscan = 0;
+ int highstale; /* high stale index */
+
+ fromidx = toidx = be32_to_cpu(btp->count) - 1;
+ highstale = *lfloghigh = -1;
+ for (; fromidx >= 0; fromidx--) {
+ if (blp[fromidx].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) {
+ if (highstale == -1)
+ highstale = toidx;
+ else {
+ if (*lfloghigh == -1)
+ *lfloghigh = toidx;
+ continue;
+ }
+ }
+ if (fromidx < toidx)
+ blp[toidx] = blp[fromidx];
+ toidx--;
+ }
+ *lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1);
+ *lfloghigh -= be32_to_cpu(btp->stale) - 1;
+ be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1));
+ xfs_dir2_data_make_free(args, bp,
+ (xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
+ (xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)),
+ needlog, &needscan);
+ btp->stale = cpu_to_be32(1);
+ /*
+ * If we now need to rebuild the bestfree map, do so.
+ * This needs to happen before the next call to use_free.
+ */
+ if (needscan)
+ xfs_dir2_data_freescan(args->dp, hdr, needlog);
+}
+
/*
* Add an entry to a block directory.
*/
@@ -63,10 +334,9 @@ int /* error */
xfs_dir2_block_addname(
xfs_da_args_t *args) /* directory op arguments */
{
- xfs_dir2_data_free_t *bf; /* bestfree table in block */
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
- xfs_dabuf_t *bp; /* buffer for block */
+ struct xfs_buf *bp; /* buffer for block */
xfs_dir2_block_tail_t *btp; /* block tail */
int compact; /* need to compact leaf ents */
xfs_dir2_data_entry_t *dep; /* block data entry */
@@ -94,204 +364,74 @@ xfs_dir2_block_addname(
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- /*
- * Read the (one and only) directory block into dabuf bp.
- */
- if ((error =
- xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, &bp, XFS_DATA_FORK))) {
+
+ /* Read the (one and only) directory block into bp. */
+ error = xfs_dir3_block_read(tp, dp, &bp);
+ if (error)
return error;
- }
- ASSERT(bp != NULL);
- hdr = bp->data;
- /*
- * Check the magic number, corrupted if wrong.
- */
- if (unlikely(hdr->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))) {
- XFS_CORRUPTION_ERROR("xfs_dir2_block_addname",
- XFS_ERRLEVEL_LOW, mp, hdr);
- xfs_da_brelse(tp, bp);
- return XFS_ERROR(EFSCORRUPTED);
- }
- len = xfs_dir2_data_entsize(args->namelen);
+
+ len = dp->d_ops->data_entsize(args->namelen);
+
/*
* Set up pointers to parts of the block.
*/
- bf = hdr->bestfree;
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ hdr = bp->b_addr;
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
+
/*
- * No stale entries? Need space for entry and new leaf.
- */
- if (!btp->stale) {
- /*
- * Tag just before the first leaf entry.
- */
- tagp = (__be16 *)blp - 1;
- /*
- * Data object just before the first leaf entry.
- */
- enddup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
- /*
- * If it's not free then can't do this add without cleaning up:
- * the space before the first leaf entry needs to be free so it
- * can be expanded to hold the pointer to the new entry.
- */
- if (be16_to_cpu(enddup->freetag) != XFS_DIR2_DATA_FREE_TAG)
- dup = enddup = NULL;
- /*
- * Check out the biggest freespace and see if it's the same one.
- */
- else {
- dup = (xfs_dir2_data_unused_t *)
- ((char *)hdr + be16_to_cpu(bf[0].offset));
- if (dup == enddup) {
- /*
- * It is the biggest freespace, is it too small
- * to hold the new leaf too?
- */
- if (be16_to_cpu(dup->length) < len + (uint)sizeof(*blp)) {
- /*
- * Yes, we use the second-largest
- * entry instead if it works.
- */
- if (be16_to_cpu(bf[1].length) >= len)
- dup = (xfs_dir2_data_unused_t *)
- ((char *)hdr +
- be16_to_cpu(bf[1].offset));
- else
- dup = NULL;
- }
- } else {
- /*
- * Not the same free entry,
- * just check its length.
- */
- if (be16_to_cpu(dup->length) < len) {
- dup = NULL;
- }
- }
- }
- compact = 0;
- }
- /*
- * If there are stale entries we'll use one for the leaf.
- * Is the biggest entry enough to avoid compaction?
+ * Find out if we can reuse stale entries or whether we need extra
+ * space for entry and new leaf.
*/
- else if (be16_to_cpu(bf[0].length) >= len) {
- dup = (xfs_dir2_data_unused_t *)
- ((char *)hdr + be16_to_cpu(bf[0].offset));
- compact = 0;
- }
+ xfs_dir2_block_need_space(dp, hdr, btp, blp, &tagp, &dup,
+ &enddup, &compact, len);
+
/*
- * Will need to compact to make this work.
+ * Done everything we need for a space check now.
*/
- else {
- /*
- * Tag just before the first leaf entry.
- */
- tagp = (__be16 *)blp - 1;
- /*
- * Data object just before the first leaf entry.
- */
- dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
- /*
- * If it's not free then the data will go where the
- * leaf data starts now, if it works at all.
- */
- if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
- if (be16_to_cpu(dup->length) + (be32_to_cpu(btp->stale) - 1) *
- (uint)sizeof(*blp) < len)
- dup = NULL;
- } else if ((be32_to_cpu(btp->stale) - 1) * (uint)sizeof(*blp) < len)
- dup = NULL;
- else
- dup = (xfs_dir2_data_unused_t *)blp;
- compact = 1;
+ if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
+ xfs_trans_brelse(tp, bp);
+ if (!dup)
+ return XFS_ERROR(ENOSPC);
+ return 0;
}
- /*
- * If this isn't a real add, we're done with the buffer.
- */
- if (args->op_flags & XFS_DA_OP_JUSTCHECK)
- xfs_da_brelse(tp, bp);
+
/*
* If we don't have space for the new entry & leaf ...
*/
if (!dup) {
- /*
- * Not trying to actually do anything, or don't have
- * a space reservation: return no-space.
- */
- if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
+ /* Don't have a space reservation: return no-space. */
+ if (args->total == 0)
return XFS_ERROR(ENOSPC);
/*
* Convert to the next larger format.
* Then add the new entry in that format.
*/
error = xfs_dir2_block_to_leaf(args, bp);
- xfs_da_buf_done(bp);
if (error)
return error;
return xfs_dir2_leaf_addname(args);
}
- /*
- * Just checking, and it would work, so say so.
- */
- if (args->op_flags & XFS_DA_OP_JUSTCHECK)
- return 0;
+
needlog = needscan = 0;
+
/*
* If need to compact the leaf entries, do it now.
- * Leave the highest-numbered stale entry stale.
- * XXX should be the one closest to mid but mid is not yet computed.
*/
if (compact) {
- int fromidx; /* source leaf index */
- int toidx; /* target leaf index */
-
- for (fromidx = toidx = be32_to_cpu(btp->count) - 1,
- highstale = lfloghigh = -1;
- fromidx >= 0;
- fromidx--) {
- if (blp[fromidx].address ==
- cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) {
- if (highstale == -1)
- highstale = toidx;
- else {
- if (lfloghigh == -1)
- lfloghigh = toidx;
- continue;
- }
- }
- if (fromidx < toidx)
- blp[toidx] = blp[fromidx];
- toidx--;
- }
- lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1);
- lfloghigh -= be32_to_cpu(btp->stale) - 1;
- be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1));
- xfs_dir2_data_make_free(tp, bp,
- (xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
- (xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)),
- &needlog, &needscan);
- blp += be32_to_cpu(btp->stale) - 1;
- btp->stale = cpu_to_be32(1);
+ xfs_dir2_block_compact(args, bp, hdr, btp, blp, &needlog,
+ &lfloghigh, &lfloglow);
+ /* recalculate blp post-compaction */
+ blp = xfs_dir2_block_leaf_p(btp);
+ } else if (btp->stale) {
/*
- * If we now need to rebuild the bestfree map, do so.
- * This needs to happen before the next call to use_free.
+ * Set leaf logging boundaries to impossible state.
+ * For the no-stale case they're set explicitly.
*/
- if (needscan) {
- xfs_dir2_data_freescan(mp, hdr, &needlog);
- needscan = 0;
- }
- }
- /*
- * Set leaf logging boundaries to impossible state.
- * For the no-stale case they're set explicitly.
- */
- else if (btp->stale) {
lfloglow = be32_to_cpu(btp->count);
lfloghigh = -1;
}
+
/*
* Find the slot that's first lower than our hash value, -1 if none.
*/
@@ -314,7 +454,7 @@ xfs_dir2_block_addname(
/*
* Mark the space needed for the new leaf entry, now in use.
*/
- xfs_dir2_data_use_free(tp, bp, enddup,
+ xfs_dir2_data_use_free(args, bp, enddup,
(xfs_dir2_data_aoff_t)
((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) -
sizeof(*blp)),
@@ -329,7 +469,7 @@ xfs_dir2_block_addname(
* This needs to happen before the next call to use_free.
*/
if (needscan) {
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
needscan = 0;
}
/*
@@ -395,13 +535,13 @@ xfs_dir2_block_addname(
* Fill in the leaf entry.
*/
blp[mid].hashval = cpu_to_be32(args->hashval);
- blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh);
/*
* Mark space for the data entry used.
*/
- xfs_dir2_data_use_free(tp, bp, dup,
+ xfs_dir2_data_use_free(args, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
(xfs_dir2_data_aoff_t)len, &needlog, &needscan);
/*
@@ -410,122 +550,19 @@ xfs_dir2_block_addname(
dep->inumber = cpu_to_be64(args->inumber);
dep->namelen = args->namelen;
memcpy(dep->name, args->name, args->namelen);
- tagp = xfs_dir2_data_entry_tag_p(dep);
+ dp->d_ops->data_put_ftype(dep, args->filetype);
+ tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
/*
* Clean up the bestfree array and log the header, tail, and entry.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, bp);
+ xfs_dir2_data_log_header(args, bp);
xfs_dir2_block_log_tail(tp, bp);
- xfs_dir2_data_log_entry(tp, bp, dep);
- xfs_dir2_data_check(dp, bp);
- xfs_da_buf_done(bp);
- return 0;
-}
-
-/*
- * Readdir for block directories.
- */
-int /* error */
-xfs_dir2_block_getdents(
- xfs_inode_t *dp, /* incore inode */
- void *dirent,
- xfs_off_t *offset,
- filldir_t filldir)
-{
- xfs_dir2_data_hdr_t *hdr; /* block header */
- xfs_dabuf_t *bp; /* buffer for block */
- xfs_dir2_block_tail_t *btp; /* block tail */
- xfs_dir2_data_entry_t *dep; /* block data entry */
- xfs_dir2_data_unused_t *dup; /* block unused entry */
- char *endptr; /* end of the data entries */
- int error; /* error return value */
- xfs_mount_t *mp; /* filesystem mount point */
- char *ptr; /* current data entry */
- int wantoff; /* starting block offset */
- xfs_off_t cook;
-
- mp = dp->i_mount;
- /*
- * If the block number in the offset is out of range, we're done.
- */
- if (xfs_dir2_dataptr_to_db(mp, *offset) > mp->m_dirdatablk) {
- return 0;
- }
- /*
- * Can't read the block, give up, else get dabuf in bp.
- */
- error = xfs_da_read_buf(NULL, dp, mp->m_dirdatablk, -1,
- &bp, XFS_DATA_FORK);
- if (error)
- return error;
-
- ASSERT(bp != NULL);
- /*
- * Extract the byte offset we start at from the seek pointer.
- * We'll skip entries before this.
- */
- wantoff = xfs_dir2_dataptr_to_off(mp, *offset);
- hdr = bp->data;
- xfs_dir2_data_check(dp, bp);
- /*
- * Set up values for the loop.
- */
- btp = xfs_dir2_block_tail_p(mp, hdr);
- ptr = (char *)(hdr + 1);
- endptr = (char *)xfs_dir2_block_leaf_p(btp);
-
- /*
- * Loop over the data portion of the block.
- * Each object is a real entry (dep) or an unused one (dup).
- */
- while (ptr < endptr) {
- dup = (xfs_dir2_data_unused_t *)ptr;
- /*
- * Unused, skip it.
- */
- if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
- ptr += be16_to_cpu(dup->length);
- continue;
- }
-
- dep = (xfs_dir2_data_entry_t *)ptr;
-
- /*
- * Bump pointer for the next iteration.
- */
- ptr += xfs_dir2_data_entsize(dep->namelen);
- /*
- * The entry is before the desired starting point, skip it.
- */
- if ((char *)dep - (char *)hdr < wantoff)
- continue;
-
- cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
- (char *)dep - (char *)hdr);
-
- /*
- * If it didn't fit, set the final offset to here & return.
- */
- if (filldir(dirent, (char *)dep->name, dep->namelen,
- cook & 0x7fffffff, be64_to_cpu(dep->inumber),
- DT_UNKNOWN)) {
- *offset = cook & 0x7fffffff;
- xfs_da_brelse(NULL, bp);
- return 0;
- }
- }
-
- /*
- * Reached the end of the block.
- * Set the offset to a non-existent block 1 and return.
- */
- *offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
- 0x7fffffff;
- xfs_da_brelse(NULL, bp);
+ xfs_dir2_data_log_entry(args, bp, dep);
+ xfs_dir3_data_check(dp, bp);
return 0;
}
@@ -535,17 +572,17 @@ xfs_dir2_block_getdents(
static void
xfs_dir2_block_log_leaf(
xfs_trans_t *tp, /* transaction structure */
- xfs_dabuf_t *bp, /* block buffer */
+ struct xfs_buf *bp, /* block buffer */
int first, /* index of first logged leaf */
int last) /* index of last logged leaf */
{
- xfs_dir2_data_hdr_t *hdr = bp->data;
+ xfs_dir2_data_hdr_t *hdr = bp->b_addr;
xfs_dir2_leaf_entry_t *blp;
xfs_dir2_block_tail_t *btp;
- btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
+ btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
- xfs_da_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
+ xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
(uint)((char *)&blp[last + 1] - (char *)hdr - 1));
}
@@ -555,13 +592,13 @@ xfs_dir2_block_log_leaf(
static void
xfs_dir2_block_log_tail(
xfs_trans_t *tp, /* transaction structure */
- xfs_dabuf_t *bp) /* block buffer */
+ struct xfs_buf *bp) /* block buffer */
{
- xfs_dir2_data_hdr_t *hdr = bp->data;
+ xfs_dir2_data_hdr_t *hdr = bp->b_addr;
xfs_dir2_block_tail_t *btp;
- btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
- xfs_da_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
+ btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr);
+ xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
(uint)((char *)(btp + 1) - (char *)hdr - 1));
}
@@ -575,7 +612,7 @@ xfs_dir2_block_lookup(
{
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
- xfs_dabuf_t *bp; /* block buffer */
+ struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_inode_t *dp; /* incore inode */
@@ -593,21 +630,23 @@ xfs_dir2_block_lookup(
return error;
dp = args->dp;
mp = dp->i_mount;
- hdr = bp->data;
- xfs_dir2_data_check(dp, bp);
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ hdr = bp->b_addr;
+ xfs_dir3_data_check(dp, bp);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Get the offset from the leaf entry, to point to the data.
*/
dep = (xfs_dir2_data_entry_t *)((char *)hdr +
- xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(blp[ent].address)));
/*
* Fill in inode number, CI name if appropriate, release the block.
*/
args->inumber = be64_to_cpu(dep->inumber);
+ args->filetype = dp->d_ops->data_get_ftype(dep);
error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
- xfs_da_brelse(args->trans, bp);
+ xfs_trans_brelse(args->trans, bp);
return XFS_ERROR(error);
}
@@ -617,13 +656,13 @@ xfs_dir2_block_lookup(
static int /* error */
xfs_dir2_block_lookup_int(
xfs_da_args_t *args, /* dir lookup arguments */
- xfs_dabuf_t **bpp, /* returned block buffer */
+ struct xfs_buf **bpp, /* returned block buffer */
int *entno) /* returned entry number */
{
xfs_dir2_dataptr_t addr; /* data entry address */
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
- xfs_dabuf_t *bp; /* block buffer */
+ struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_inode_t *dp; /* incore inode */
@@ -639,17 +678,14 @@ xfs_dir2_block_lookup_int(
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- /*
- * Read the buffer, return error if we can't get it.
- */
- if ((error =
- xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, &bp, XFS_DATA_FORK))) {
+
+ error = xfs_dir3_block_read(tp, dp, &bp);
+ if (error)
return error;
- }
- ASSERT(bp != NULL);
- hdr = bp->data;
- xfs_dir2_data_check(dp, bp);
- btp = xfs_dir2_block_tail_p(mp, hdr);
+
+ hdr = bp->b_addr;
+ xfs_dir3_data_check(dp, bp);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Loop doing a binary search for our hash value.
@@ -666,7 +702,7 @@ xfs_dir2_block_lookup_int(
high = mid - 1;
if (low > high) {
ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
- xfs_da_brelse(tp, bp);
+ xfs_trans_brelse(tp, bp);
return XFS_ERROR(ENOENT);
}
}
@@ -687,7 +723,7 @@ xfs_dir2_block_lookup_int(
* Get pointer to the entry from the leaf.
*/
dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr));
+ ((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, addr));
/*
* Compare name and if it's an exact match, return the index
* and buffer. If it's the first case-insensitive match, store
@@ -714,7 +750,7 @@ xfs_dir2_block_lookup_int(
/*
* No match, release the buffer and return ENOENT.
*/
- xfs_da_brelse(tp, bp);
+ xfs_trans_brelse(tp, bp);
return XFS_ERROR(ENOENT);
}
@@ -728,7 +764,7 @@ xfs_dir2_block_removename(
{
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf pointer */
- xfs_dabuf_t *bp; /* block buffer */
+ struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_inode_t *dp; /* incore inode */
@@ -753,21 +789,22 @@ xfs_dir2_block_removename(
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- hdr = bp->data;
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ hdr = bp->b_addr;
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Point to the data entry using the leaf entry.
*/
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+ dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(blp[ent].address)));
/*
* Mark the data entry's space free.
*/
needlog = needscan = 0;
- xfs_dir2_data_make_free(tp, bp,
+ xfs_dir2_data_make_free(args, bp,
(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
- xfs_dir2_data_entsize(dep->namelen), &needlog, &needscan);
+ dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
/*
* Fix up the block tail.
*/
@@ -782,18 +819,17 @@ xfs_dir2_block_removename(
* Fix up bestfree, log the header if necessary.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, bp);
- xfs_dir2_data_check(dp, bp);
+ xfs_dir2_data_log_header(args, bp);
+ xfs_dir3_data_check(dp, bp);
/*
* See if the size as a shortform is good enough.
*/
size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
- if (size > XFS_IFORK_DSIZE(dp)) {
- xfs_da_buf_done(bp);
+ if (size > XFS_IFORK_DSIZE(dp))
return 0;
- }
+
/*
* If it works, do the conversion.
*/
@@ -810,7 +846,7 @@ xfs_dir2_block_replace(
{
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
- xfs_dabuf_t *bp; /* block buffer */
+ struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_inode_t *dp; /* incore inode */
@@ -829,22 +865,23 @@ xfs_dir2_block_replace(
}
dp = args->dp;
mp = dp->i_mount;
- hdr = bp->data;
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ hdr = bp->b_addr;
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Point to the data entry we need to change.
*/
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+ dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(blp[ent].address)));
ASSERT(be64_to_cpu(dep->inumber) != args->inumber);
/*
* Change the inode number to the new value.
*/
dep->inumber = cpu_to_be64(args->inumber);
- xfs_dir2_data_log_entry(args->trans, bp, dep);
- xfs_dir2_data_check(dp, bp);
- xfs_da_buf_done(bp);
+ dp->d_ops->data_put_ftype(dep, args->filetype);
+ xfs_dir2_data_log_entry(args, bp, dep);
+ xfs_dir3_data_check(dp, bp);
return 0;
}
@@ -871,8 +908,8 @@ xfs_dir2_block_sort(
int /* error */
xfs_dir2_leaf_to_block(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *lbp, /* leaf buffer */
- xfs_dabuf_t *dbp) /* data buffer */
+ struct xfs_buf *lbp, /* leaf buffer */
+ struct xfs_buf *dbp) /* data buffer */
{
__be16 *bestsp; /* leaf bests table */
xfs_dir2_data_hdr_t *hdr; /* block header */
@@ -892,89 +929,97 @@ xfs_dir2_leaf_to_block(
__be16 *tagp; /* end of entry (tag) */
int to; /* block/leaf to index */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
trace_xfs_dir2_leaf_to_block(args);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- leaf = lbp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ leaf = lbp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
+
+ ASSERT(leafhdr.magic == XFS_DIR2_LEAF1_MAGIC ||
+ leafhdr.magic == XFS_DIR3_LEAF1_MAGIC);
/*
* If there are data blocks other than the first one, take this
* opportunity to remove trailing empty data blocks that may have
* been left behind during no-space-reservation operations.
* These will show up in the leaf bests table.
*/
- while (dp->i_d.di_size > mp->m_dirblksize) {
+ while (dp->i_d.di_size > args->geo->blksize) {
+ int hdrsz;
+
+ hdrsz = dp->d_ops->data_entry_offset;
bestsp = xfs_dir2_leaf_bests_p(ltp);
if (be16_to_cpu(bestsp[be32_to_cpu(ltp->bestcount) - 1]) ==
- mp->m_dirblksize - (uint)sizeof(*hdr)) {
+ args->geo->blksize - hdrsz) {
if ((error =
xfs_dir2_leaf_trim_data(args, lbp,
(xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1))))
- goto out;
- } else {
- error = 0;
- goto out;
- }
+ return error;
+ } else
+ return 0;
}
/*
* Read the data block if we don't already have it, give up if it fails.
*/
- if (dbp == NULL &&
- (error = xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, &dbp,
- XFS_DATA_FORK))) {
- goto out;
+ if (!dbp) {
+ error = xfs_dir3_data_read(tp, dp, args->geo->datablk, -1, &dbp);
+ if (error)
+ return error;
}
- hdr = dbp->data;
- ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
+ hdr = dbp->b_addr;
+ ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
+
/*
* Size of the "leaf" area in the block.
*/
size = (uint)sizeof(xfs_dir2_block_tail_t) +
- (uint)sizeof(*lep) * (be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale));
+ (uint)sizeof(*lep) * (leafhdr.count - leafhdr.stale);
/*
* Look at the last data entry.
*/
- tagp = (__be16 *)((char *)hdr + mp->m_dirblksize) - 1;
+ tagp = (__be16 *)((char *)hdr + args->geo->blksize) - 1;
dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
/*
* If it's not free or is too short we can't do it.
*/
if (be16_to_cpu(dup->freetag) != XFS_DIR2_DATA_FREE_TAG ||
- be16_to_cpu(dup->length) < size) {
- error = 0;
- goto out;
- }
+ be16_to_cpu(dup->length) < size)
+ return 0;
+
/*
* Start converting it to block form.
*/
- hdr->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
+ xfs_dir3_block_init(mp, tp, dbp, dp);
+
needlog = 1;
needscan = 0;
/*
* Use up the space at the end of the block (blp/btp).
*/
- xfs_dir2_data_use_free(tp, dbp, dup, mp->m_dirblksize - size, size,
+ xfs_dir2_data_use_free(args, dbp, dup, args->geo->blksize - size, size,
&needlog, &needscan);
/*
* Initialize the block tail.
*/
- btp = xfs_dir2_block_tail_p(mp, hdr);
- btp->count = cpu_to_be32(be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale));
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
+ btp->count = cpu_to_be32(leafhdr.count - leafhdr.stale);
btp->stale = 0;
xfs_dir2_block_log_tail(tp, dbp);
/*
* Initialize the block leaf area. We compact out stale entries.
*/
lep = xfs_dir2_block_leaf_p(btp);
- for (from = to = 0; from < be16_to_cpu(leaf->hdr.count); from++) {
- if (leaf->ents[from].address ==
- cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
+ for (from = to = 0; from < leafhdr.count; from++) {
+ if (ents[from].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
continue;
- lep[to++] = leaf->ents[from];
+ lep[to++] = ents[from];
}
ASSERT(to == be32_to_cpu(btp->count));
xfs_dir2_block_log_leaf(tp, dbp, 0, be32_to_cpu(btp->count) - 1);
@@ -982,32 +1027,24 @@ xfs_dir2_leaf_to_block(
* Scan the bestfree if we need it and log the data block header.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
/*
* Pitch the old leaf block.
*/
- error = xfs_da_shrink_inode(args, mp->m_dirleafblk, lbp);
- lbp = NULL;
- if (error) {
- goto out;
- }
+ error = xfs_da_shrink_inode(args, args->geo->leafblk, lbp);
+ if (error)
+ return error;
+
/*
* Now see if the resulting block can be shrunken to shortform.
*/
size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
- if (size > XFS_IFORK_DSIZE(dp)) {
- error = 0;
- goto out;
- }
+ if (size > XFS_IFORK_DSIZE(dp))
+ return 0;
+
return xfs_dir2_block_to_sf(args, dbp, size, &sfh);
-out:
- if (lbp)
- xfs_da_buf_done(lbp);
- if (dbp)
- xfs_da_buf_done(dbp);
- return error;
}
/*
@@ -1020,7 +1057,7 @@ xfs_dir2_sf_to_block(
xfs_dir2_db_t blkno; /* dir-relative block # (0) */
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
- xfs_dabuf_t *bp; /* block buffer */
+ struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail pointer */
xfs_dir2_data_entry_t *dep; /* data entry pointer */
xfs_inode_t *dp; /* incore directory inode */
@@ -1040,13 +1077,15 @@ xfs_dir2_sf_to_block(
__be16 *tagp; /* end of data entry */
xfs_trans_t *tp; /* transaction pointer */
struct xfs_name name;
+ struct xfs_ifork *ifp;
trace_xfs_dir2_sf_to_block(args);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
+ ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
+ ASSERT(ifp->if_flags & XFS_IFINLINE);
/*
* Bomb out if the shortform directory is way too short.
*/
@@ -1055,22 +1094,23 @@ xfs_dir2_sf_to_block(
return XFS_ERROR(EIO);
}
- oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+ oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
- ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
- ASSERT(dp->i_df.if_u1.if_data != NULL);
+ ASSERT(ifp->if_bytes == dp->i_d.di_size);
+ ASSERT(ifp->if_u1.if_data != NULL);
ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
+ ASSERT(dp->i_d.di_nextents == 0);
/*
* Copy the directory into a temporary buffer.
* Then pitch the incore inode data so we can make extents.
*/
- sfp = kmem_alloc(dp->i_df.if_bytes, KM_SLEEP);
- memcpy(sfp, oldsfp, dp->i_df.if_bytes);
+ sfp = kmem_alloc(ifp->if_bytes, KM_SLEEP);
+ memcpy(sfp, oldsfp, ifp->if_bytes);
- xfs_idata_realloc(dp, -dp->i_df.if_bytes, XFS_DATA_FORK);
+ xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
+ xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK);
dp->i_d.di_size = 0;
- xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
/*
* Add block 0 to the inode.
@@ -1081,15 +1121,16 @@ xfs_dir2_sf_to_block(
return error;
}
/*
- * Initialize the data block.
+ * Initialize the data block, then convert it to block format.
*/
- error = xfs_dir2_data_init(args, blkno, &bp);
+ error = xfs_dir3_data_init(args, blkno, &bp);
if (error) {
kmem_free(sfp);
return error;
}
- hdr = bp->data;
- hdr->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
+ xfs_dir3_block_init(mp, tp, bp, dp);
+ hdr = bp->b_addr;
+
/*
* Compute size of block "tail" area.
*/
@@ -1099,15 +1140,15 @@ xfs_dir2_sf_to_block(
* The whole thing is initialized to free by the init routine.
* Say we're using the leaf and tail area.
*/
- dup = (xfs_dir2_data_unused_t *)(hdr + 1);
+ dup = dp->d_ops->data_unused_p(hdr);
needlog = needscan = 0;
- xfs_dir2_data_use_free(tp, bp, dup, mp->m_dirblksize - i, i, &needlog,
- &needscan);
+ xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i,
+ i, &needlog, &needscan);
ASSERT(needscan == 0);
/*
* Fill in the tail.
*/
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
btp->count = cpu_to_be32(sfp->count + 2); /* ., .. */
btp->stale = 0;
blp = xfs_dir2_block_leaf_p(btp);
@@ -1115,38 +1156,38 @@ xfs_dir2_sf_to_block(
/*
* Remove the freespace, we'll manage it.
*/
- xfs_dir2_data_use_free(tp, bp, dup,
+ xfs_dir2_data_use_free(args, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
be16_to_cpu(dup->length), &needlog, &needscan);
/*
* Create entry for .
*/
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + XFS_DIR2_DATA_DOT_OFFSET);
+ dep = dp->d_ops->data_dot_entry_p(hdr);
dep->inumber = cpu_to_be64(dp->i_ino);
dep->namelen = 1;
dep->name[0] = '.';
- tagp = xfs_dir2_data_entry_tag_p(dep);
+ dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
+ tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
- blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
/*
* Create entry for ..
*/
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + XFS_DIR2_DATA_DOTDOT_OFFSET);
- dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp));
+ dep = dp->d_ops->data_dotdot_entry_p(hdr);
+ dep->inumber = cpu_to_be64(dp->d_ops->sf_get_parent_ino(sfp));
dep->namelen = 2;
dep->name[0] = dep->name[1] = '.';
- tagp = xfs_dir2_data_entry_tag_p(dep);
+ dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
+ tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
- blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
- offset = XFS_DIR2_DATA_FIRST_OFFSET;
+ offset = dp->d_ops->data_first_offset;
/*
* Loop over existing entries, stuff them in.
*/
@@ -1176,8 +1217,10 @@ xfs_dir2_sf_to_block(
dup->length = cpu_to_be16(newoffset - offset);
*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
((char *)dup - (char *)hdr));
- xfs_dir2_data_log_unused(tp, bp, dup);
- xfs_dir2_data_freeinsert(hdr, dup, &dummy);
+ xfs_dir2_data_log_unused(args, bp, dup);
+ xfs_dir2_data_freeinsert(hdr,
+ dp->d_ops->data_bestfree_p(hdr),
+ dup, &dummy);
offset += be16_to_cpu(dup->length);
continue;
}
@@ -1185,23 +1228,24 @@ xfs_dir2_sf_to_block(
* Copy a real entry.
*/
dep = (xfs_dir2_data_entry_t *)((char *)hdr + newoffset);
- dep->inumber = cpu_to_be64(xfs_dir2_sfe_get_ino(sfp, sfep));
+ dep->inumber = cpu_to_be64(dp->d_ops->sf_get_ino(sfp, sfep));
dep->namelen = sfep->namelen;
+ dp->d_ops->data_put_ftype(dep, dp->d_ops->sf_get_ftype(sfep));
memcpy(dep->name, sfep->name, dep->namelen);
- tagp = xfs_dir2_data_entry_tag_p(dep);
+ tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, bp, dep);
+ xfs_dir2_data_log_entry(args, bp, dep);
name.name = sfep->name;
name.len = sfep->namelen;
blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
hashname(&name));
- blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+ blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
offset = (int)((char *)(tagp + 1) - (char *)hdr);
if (++i == sfp->count)
sfep = NULL;
else
- sfep = xfs_dir2_sf_nextentry(sfp, sfep);
+ sfep = dp->d_ops->sf_nextentry(sfp, sfep);
}
/* Done with the temporary buffer */
kmem_free(sfp);
@@ -1216,7 +1260,6 @@ xfs_dir2_sf_to_block(
ASSERT(needscan == 0);
xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
xfs_dir2_block_log_tail(tp, bp);
- xfs_dir2_data_check(dp, bp);
- xfs_da_buf_done(bp);
+ xfs_dir3_data_check(dp, bp);
return 0;
}
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index 2046988e9eb..8c2f6422648 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -17,33 +18,31 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
-#include "xfs_dir2_format.h"
+#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
+#include "xfs_trans.h"
+#include "xfs_buf_item.h"
+#include "xfs_cksum.h"
-STATIC xfs_dir2_data_free_t *
-xfs_dir2_data_freefind(xfs_dir2_data_hdr_t *hdr, xfs_dir2_data_unused_t *dup);
-
-#ifdef DEBUG
/*
* Check the consistency of the data block.
* The input can also be a block-format directory.
- * Pop an assert if we find anything bad.
+ * Return 0 is the buffer is good, otherwise an error.
*/
-void
-xfs_dir2_data_check(
- xfs_inode_t *dp, /* incore inode pointer */
- xfs_dabuf_t *bp) /* data block's buffer */
+int
+__xfs_dir3_data_check(
+ struct xfs_inode *dp, /* incore inode pointer */
+ struct xfs_buf *bp) /* data block's buffer */
{
xfs_dir2_dataptr_t addr; /* addr for leaf lookup */
xfs_dir2_data_free_t *bf; /* bestfree table */
@@ -63,39 +62,69 @@ xfs_dir2_data_check(
char *p; /* current data position */
int stale; /* count of stale leaves */
struct xfs_name name;
+ const struct xfs_dir_ops *ops;
+ struct xfs_da_geometry *geo;
- mp = dp->i_mount;
- hdr = bp->data;
- bf = hdr->bestfree;
- p = (char *)(hdr + 1);
+ mp = bp->b_target->bt_mount;
+ geo = mp->m_dir_geo;
+
+ /*
+ * We can be passed a null dp here from a verifier, so we need to go the
+ * hard way to get them.
+ */
+ ops = xfs_dir_get_ops(mp, dp);
+
+ hdr = bp->b_addr;
+ p = (char *)ops->data_entry_p(hdr);
- if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) {
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ switch (hdr->magic) {
+ case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
+ case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
+ btp = xfs_dir2_block_tail_p(geo, hdr);
lep = xfs_dir2_block_leaf_p(btp);
endp = (char *)lep;
- } else {
- ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
- endp = (char *)hdr + mp->m_dirblksize;
+
+ /*
+ * The number of leaf entries is limited by the size of the
+ * block and the amount of space used by the data entries.
+ * We don't know how much space is used by the data entries yet,
+ * so just ensure that the count falls somewhere inside the
+ * block right now.
+ */
+ XFS_WANT_CORRUPTED_RETURN(be32_to_cpu(btp->count) <
+ ((char *)btp - p) / sizeof(struct xfs_dir2_leaf_entry));
+ break;
+ case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
+ case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
+ endp = (char *)hdr + geo->blksize;
+ break;
+ default:
+ XFS_ERROR_REPORT("Bad Magic", XFS_ERRLEVEL_LOW, mp);
+ return EFSCORRUPTED;
}
- count = lastfree = freeseen = 0;
/*
* Account for zero bestfree entries.
*/
+ bf = ops->data_bestfree_p(hdr);
+ count = lastfree = freeseen = 0;
if (!bf[0].length) {
- ASSERT(!bf[0].offset);
+ XFS_WANT_CORRUPTED_RETURN(!bf[0].offset);
freeseen |= 1 << 0;
}
if (!bf[1].length) {
- ASSERT(!bf[1].offset);
+ XFS_WANT_CORRUPTED_RETURN(!bf[1].offset);
freeseen |= 1 << 1;
}
if (!bf[2].length) {
- ASSERT(!bf[2].offset);
+ XFS_WANT_CORRUPTED_RETURN(!bf[2].offset);
freeseen |= 1 << 2;
}
- ASSERT(be16_to_cpu(bf[0].length) >= be16_to_cpu(bf[1].length));
- ASSERT(be16_to_cpu(bf[1].length) >= be16_to_cpu(bf[2].length));
+
+ XFS_WANT_CORRUPTED_RETURN(be16_to_cpu(bf[0].length) >=
+ be16_to_cpu(bf[1].length));
+ XFS_WANT_CORRUPTED_RETURN(be16_to_cpu(bf[1].length) >=
+ be16_to_cpu(bf[2].length));
/*
* Loop over the data/unused entries.
*/
@@ -107,17 +136,20 @@ xfs_dir2_data_check(
* doesn't need to be there.
*/
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
- ASSERT(lastfree == 0);
- ASSERT(be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) ==
- (char *)dup - (char *)hdr);
- dfp = xfs_dir2_data_freefind(hdr, dup);
+ XFS_WANT_CORRUPTED_RETURN(lastfree == 0);
+ XFS_WANT_CORRUPTED_RETURN(
+ be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) ==
+ (char *)dup - (char *)hdr);
+ dfp = xfs_dir2_data_freefind(hdr, bf, dup);
if (dfp) {
i = (int)(dfp - bf);
- ASSERT((freeseen & (1 << i)) == 0);
+ XFS_WANT_CORRUPTED_RETURN(
+ (freeseen & (1 << i)) == 0);
freeseen |= 1 << i;
} else {
- ASSERT(be16_to_cpu(dup->length) <=
- be16_to_cpu(bf[2].length));
+ XFS_WANT_CORRUPTED_RETURN(
+ be16_to_cpu(dup->length) <=
+ be16_to_cpu(bf[2].length));
}
p += be16_to_cpu(dup->length);
lastfree = 1;
@@ -130,16 +162,21 @@ xfs_dir2_data_check(
* The linear search is crude but this is DEBUG code.
*/
dep = (xfs_dir2_data_entry_t *)p;
- ASSERT(dep->namelen != 0);
- ASSERT(xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)) == 0);
- ASSERT(be16_to_cpu(*xfs_dir2_data_entry_tag_p(dep)) ==
- (char *)dep - (char *)hdr);
+ XFS_WANT_CORRUPTED_RETURN(dep->namelen != 0);
+ XFS_WANT_CORRUPTED_RETURN(
+ !xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)));
+ XFS_WANT_CORRUPTED_RETURN(
+ be16_to_cpu(*ops->data_entry_tag_p(dep)) ==
+ (char *)dep - (char *)hdr);
+ XFS_WANT_CORRUPTED_RETURN(
+ ops->data_get_ftype(dep) < XFS_DIR3_FT_MAX);
count++;
lastfree = 0;
- if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) {
- addr = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
- (xfs_dir2_data_aoff_t)
- ((char *)dep - (char *)hdr));
+ if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
+ addr = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
+ (xfs_dir2_data_aoff_t)
+ ((char *)dep - (char *)hdr));
name.name = dep->name;
name.len = dep->namelen;
hash = mp->m_dirnameops->hashname(&name);
@@ -148,55 +185,191 @@ xfs_dir2_data_check(
be32_to_cpu(lep[i].hashval) == hash)
break;
}
- ASSERT(i < be32_to_cpu(btp->count));
+ XFS_WANT_CORRUPTED_RETURN(i < be32_to_cpu(btp->count));
}
- p += xfs_dir2_data_entsize(dep->namelen);
+ p += ops->data_entsize(dep->namelen);
}
/*
* Need to have seen all the entries and all the bestfree slots.
*/
- ASSERT(freeseen == 7);
- if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) {
+ XFS_WANT_CORRUPTED_RETURN(freeseen == 7);
+ if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
for (i = stale = 0; i < be32_to_cpu(btp->count); i++) {
if (lep[i].address ==
cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
stale++;
if (i > 0)
- ASSERT(be32_to_cpu(lep[i].hashval) >= be32_to_cpu(lep[i - 1].hashval));
+ XFS_WANT_CORRUPTED_RETURN(
+ be32_to_cpu(lep[i].hashval) >=
+ be32_to_cpu(lep[i - 1].hashval));
}
- ASSERT(count == be32_to_cpu(btp->count) - be32_to_cpu(btp->stale));
- ASSERT(stale == be32_to_cpu(btp->stale));
+ XFS_WANT_CORRUPTED_RETURN(count ==
+ be32_to_cpu(btp->count) - be32_to_cpu(btp->stale));
+ XFS_WANT_CORRUPTED_RETURN(stale == be32_to_cpu(btp->stale));
}
+ return 0;
+}
+
+static bool
+xfs_dir3_data_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ if (hdr3->magic != cpu_to_be32(XFS_DIR3_DATA_MAGIC))
+ return false;
+ if (!uuid_equal(&hdr3->uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
+ return false;
+ } else {
+ if (hdr3->magic != cpu_to_be32(XFS_DIR2_DATA_MAGIC))
+ return false;
+ }
+ if (__xfs_dir3_data_check(NULL, bp))
+ return false;
+ return true;
+}
+
+/*
+ * Readahead of the first block of the directory when it is opened is completely
+ * oblivious to the format of the directory. Hence we can either get a block
+ * format buffer or a data format buffer on readahead.
+ */
+static void
+xfs_dir3_data_reada_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_dir2_data_hdr *hdr = bp->b_addr;
+
+ switch (hdr->magic) {
+ case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
+ case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
+ bp->b_ops = &xfs_dir3_block_buf_ops;
+ bp->b_ops->verify_read(bp);
+ return;
+ case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
+ case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
+ xfs_dir3_data_verify(bp);
+ return;
+ default:
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ break;
+ }
+}
+
+static void
+xfs_dir3_data_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_dir3_data_verify(bp))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+}
+
+static void
+xfs_dir3_data_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ if (!xfs_dir3_data_verify(bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (bip)
+ hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF);
+}
+
+const struct xfs_buf_ops xfs_dir3_data_buf_ops = {
+ .verify_read = xfs_dir3_data_read_verify,
+ .verify_write = xfs_dir3_data_write_verify,
+};
+
+static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
+ .verify_read = xfs_dir3_data_reada_verify,
+ .verify_write = xfs_dir3_data_write_verify,
+};
+
+
+int
+xfs_dir3_data_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
+ xfs_daddr_t mapped_bno,
+ struct xfs_buf **bpp)
+{
+ int err;
+
+ err = xfs_da_read_buf(tp, dp, bno, mapped_bno, bpp,
+ XFS_DATA_FORK, &xfs_dir3_data_buf_ops);
+ if (!err && tp)
+ xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_DATA_BUF);
+ return err;
+}
+
+int
+xfs_dir3_data_readahead(
+ struct xfs_inode *dp,
+ xfs_dablk_t bno,
+ xfs_daddr_t mapped_bno)
+{
+ return xfs_da_reada_buf(dp, bno, mapped_bno,
+ XFS_DATA_FORK, &xfs_dir3_data_reada_buf_ops);
}
-#endif
/*
* Given a data block and an unused entry from that block,
* return the bestfree entry if any that corresponds to it.
*/
-STATIC xfs_dir2_data_free_t *
+xfs_dir2_data_free_t *
xfs_dir2_data_freefind(
- xfs_dir2_data_hdr_t *hdr, /* data block */
- xfs_dir2_data_unused_t *dup) /* data unused entry */
+ struct xfs_dir2_data_hdr *hdr, /* data block header */
+ struct xfs_dir2_data_free *bf, /* bestfree table pointer */
+ struct xfs_dir2_data_unused *dup) /* unused space */
{
xfs_dir2_data_free_t *dfp; /* bestfree entry */
xfs_dir2_data_aoff_t off; /* offset value needed */
-#if defined(DEBUG) && defined(__KERNEL__)
+#ifdef DEBUG
int matched; /* matched the value */
int seenzero; /* saw a 0 bestfree entry */
#endif
off = (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr);
-#if defined(DEBUG) && defined(__KERNEL__)
+
+#ifdef DEBUG
/*
* Validate some consistency in the bestfree table.
* Check order, non-overlapping entries, and if we find the
* one we're looking for it has to be exact.
*/
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
- for (dfp = &hdr->bestfree[0], seenzero = matched = 0;
- dfp < &hdr->bestfree[XFS_DIR2_DATA_FD_COUNT];
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+ for (dfp = &bf[0], seenzero = matched = 0;
+ dfp < &bf[XFS_DIR2_DATA_FD_COUNT];
dfp++) {
if (!dfp->offset) {
ASSERT(!dfp->length);
@@ -212,7 +385,7 @@ xfs_dir2_data_freefind(
else
ASSERT(be16_to_cpu(dfp->offset) + be16_to_cpu(dfp->length) <= off);
ASSERT(matched || be16_to_cpu(dfp->length) >= be16_to_cpu(dup->length));
- if (dfp > &hdr->bestfree[0])
+ if (dfp > &bf[0])
ASSERT(be16_to_cpu(dfp[-1].length) >= be16_to_cpu(dfp[0].length));
}
#endif
@@ -221,14 +394,12 @@ xfs_dir2_data_freefind(
* it can't be there since they're sorted.
*/
if (be16_to_cpu(dup->length) <
- be16_to_cpu(hdr->bestfree[XFS_DIR2_DATA_FD_COUNT - 1].length))
+ be16_to_cpu(bf[XFS_DIR2_DATA_FD_COUNT - 1].length))
return NULL;
/*
* Look at the three bestfree entries for our guy.
*/
- for (dfp = &hdr->bestfree[0];
- dfp < &hdr->bestfree[XFS_DIR2_DATA_FD_COUNT];
- dfp++) {
+ for (dfp = &bf[0]; dfp < &bf[XFS_DIR2_DATA_FD_COUNT]; dfp++) {
if (!dfp->offset)
return NULL;
if (be16_to_cpu(dfp->offset) == off)
@@ -245,18 +416,18 @@ xfs_dir2_data_freefind(
*/
xfs_dir2_data_free_t * /* entry inserted */
xfs_dir2_data_freeinsert(
- xfs_dir2_data_hdr_t *hdr, /* data block pointer */
- xfs_dir2_data_unused_t *dup, /* unused space */
+ struct xfs_dir2_data_hdr *hdr, /* data block pointer */
+ struct xfs_dir2_data_free *dfp, /* bestfree table pointer */
+ struct xfs_dir2_data_unused *dup, /* unused space */
int *loghead) /* log the data header (out) */
{
- xfs_dir2_data_free_t *dfp; /* bestfree table pointer */
xfs_dir2_data_free_t new; /* new bestfree entry */
-#ifdef __KERNEL__
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
-#endif
- dfp = hdr->bestfree;
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+
new.length = dup->length;
new.offset = cpu_to_be16((char *)dup - (char *)hdr);
@@ -289,36 +460,39 @@ xfs_dir2_data_freeinsert(
*/
STATIC void
xfs_dir2_data_freeremove(
- xfs_dir2_data_hdr_t *hdr, /* data block header */
- xfs_dir2_data_free_t *dfp, /* bestfree entry pointer */
+ struct xfs_dir2_data_hdr *hdr, /* data block header */
+ struct xfs_dir2_data_free *bf, /* bestfree table pointer */
+ struct xfs_dir2_data_free *dfp, /* bestfree entry pointer */
int *loghead) /* out: log data header */
{
-#ifdef __KERNEL__
+
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
-#endif
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+
/*
* It's the first entry, slide the next 2 up.
*/
- if (dfp == &hdr->bestfree[0]) {
- hdr->bestfree[0] = hdr->bestfree[1];
- hdr->bestfree[1] = hdr->bestfree[2];
+ if (dfp == &bf[0]) {
+ bf[0] = bf[1];
+ bf[1] = bf[2];
}
/*
* It's the second entry, slide the 3rd entry up.
*/
- else if (dfp == &hdr->bestfree[1])
- hdr->bestfree[1] = hdr->bestfree[2];
+ else if (dfp == &bf[1])
+ bf[1] = bf[2];
/*
* Must be the last entry.
*/
else
- ASSERT(dfp == &hdr->bestfree[2]);
+ ASSERT(dfp == &bf[2]);
/*
* Clear the 3rd entry, must be zero now.
*/
- hdr->bestfree[2].length = 0;
- hdr->bestfree[2].offset = 0;
+ bf[2].length = 0;
+ bf[2].offset = 0;
*loghead = 1;
}
@@ -327,34 +501,39 @@ xfs_dir2_data_freeremove(
*/
void
xfs_dir2_data_freescan(
- xfs_mount_t *mp, /* filesystem mount point */
- xfs_dir2_data_hdr_t *hdr, /* data block header */
- int *loghead) /* out: log data header */
+ struct xfs_inode *dp,
+ struct xfs_dir2_data_hdr *hdr,
+ int *loghead)
{
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* active data entry */
xfs_dir2_data_unused_t *dup; /* unused data entry */
+ struct xfs_dir2_data_free *bf;
char *endp; /* end of block's data */
char *p; /* current entry pointer */
+ struct xfs_da_geometry *geo = dp->i_mount->m_dir_geo;
-#ifdef __KERNEL__
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
-#endif
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+
/*
* Start by clearing the table.
*/
- memset(hdr->bestfree, 0, sizeof(hdr->bestfree));
+ bf = dp->d_ops->data_bestfree_p(hdr);
+ memset(bf, 0, sizeof(*bf) * XFS_DIR2_DATA_FD_COUNT);
*loghead = 1;
/*
* Set up pointers.
*/
- p = (char *)(hdr + 1);
- if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) {
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ p = (char *)dp->d_ops->data_entry_p(hdr);
+ if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
+ btp = xfs_dir2_block_tail_p(geo, hdr);
endp = (char *)xfs_dir2_block_leaf_p(btp);
} else
- endp = (char *)hdr + mp->m_dirblksize;
+ endp = (char *)hdr + geo->blksize;
/*
* Loop over the block's entries.
*/
@@ -366,7 +545,7 @@ xfs_dir2_data_freescan(
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
ASSERT((char *)dup - (char *)hdr ==
be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)));
- xfs_dir2_data_freeinsert(hdr, dup, loghead);
+ xfs_dir2_data_freeinsert(hdr, bf, dup, loghead);
p += be16_to_cpu(dup->length);
}
/*
@@ -375,8 +554,8 @@ xfs_dir2_data_freescan(
else {
dep = (xfs_dir2_data_entry_t *)p;
ASSERT((char *)dep - (char *)hdr ==
- be16_to_cpu(*xfs_dir2_data_entry_tag_p(dep)));
- p += xfs_dir2_data_entsize(dep->namelen);
+ be16_to_cpu(*dp->d_ops->data_entry_tag_p(dep)));
+ p += dp->d_ops->data_entsize(dep->namelen);
}
}
}
@@ -386,15 +565,16 @@ xfs_dir2_data_freescan(
* Give back the buffer for the created block.
*/
int /* error */
-xfs_dir2_data_init(
+xfs_dir3_data_init(
xfs_da_args_t *args, /* directory operation args */
xfs_dir2_db_t blkno, /* logical dir block number */
- xfs_dabuf_t **bpp) /* output block buffer */
+ struct xfs_buf **bpp) /* output block buffer */
{
- xfs_dabuf_t *bp; /* block buffer */
+ struct xfs_buf *bp; /* block buffer */
xfs_dir2_data_hdr_t *hdr; /* data block header */
xfs_inode_t *dp; /* incore directory inode */
xfs_dir2_data_unused_t *dup; /* unused entry pointer */
+ struct xfs_dir2_data_free *bf;
int error; /* error return value */
int i; /* bestfree index */
xfs_mount_t *mp; /* filesystem mount point */
@@ -407,39 +587,51 @@ xfs_dir2_data_init(
/*
* Get the buffer set up for the block.
*/
- error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, blkno), -1, &bp,
- XFS_DATA_FORK);
- if (error) {
+ error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, blkno),
+ -1, &bp, XFS_DATA_FORK);
+ if (error)
return error;
- }
- ASSERT(bp != NULL);
+ bp->b_ops = &xfs_dir3_data_buf_ops;
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_DATA_BUF);
/*
* Initialize the header.
*/
- hdr = bp->data;
- hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
- hdr->bestfree[0].offset = cpu_to_be16(sizeof(*hdr));
+ hdr = bp->b_addr;
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ memset(hdr3, 0, sizeof(*hdr3));
+ hdr3->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
+ hdr3->blkno = cpu_to_be64(bp->b_bn);
+ hdr3->owner = cpu_to_be64(dp->i_ino);
+ uuid_copy(&hdr3->uuid, &mp->m_sb.sb_uuid);
+
+ } else
+ hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
+
+ bf = dp->d_ops->data_bestfree_p(hdr);
+ bf[0].offset = cpu_to_be16(dp->d_ops->data_entry_offset);
for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) {
- hdr->bestfree[i].length = 0;
- hdr->bestfree[i].offset = 0;
+ bf[i].length = 0;
+ bf[i].offset = 0;
}
/*
* Set up an unused entry for the block's body.
*/
- dup = (xfs_dir2_data_unused_t *)(hdr + 1);
+ dup = dp->d_ops->data_unused_p(hdr);
dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
- t = mp->m_dirblksize - (uint)sizeof(*hdr);
- hdr->bestfree[0].length = cpu_to_be16(t);
+ t = args->geo->blksize - (uint)dp->d_ops->data_entry_offset;
+ bf[0].length = cpu_to_be16(t);
dup->length = cpu_to_be16(t);
*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16((char *)dup - (char *)hdr);
/*
* Log it and return it.
*/
- xfs_dir2_data_log_header(tp, bp);
- xfs_dir2_data_log_unused(tp, bp, dup);
+ xfs_dir2_data_log_header(args, bp);
+ xfs_dir2_data_log_unused(args, bp, dup);
*bpp = bp;
return 0;
}
@@ -449,17 +641,19 @@ xfs_dir2_data_init(
*/
void
xfs_dir2_data_log_entry(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp, /* block buffer */
+ struct xfs_da_args *args,
+ struct xfs_buf *bp,
xfs_dir2_data_entry_t *dep) /* data entry pointer */
{
- xfs_dir2_data_hdr_t *hdr = bp->data;
+ struct xfs_dir2_data_hdr *hdr = bp->b_addr;
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
- xfs_da_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
- (uint)((char *)(xfs_dir2_data_entry_tag_p(dep) + 1) -
+ xfs_trans_log_buf(args->trans, bp, (uint)((char *)dep - (char *)hdr),
+ (uint)((char *)(args->dp->d_ops->data_entry_tag_p(dep) + 1) -
(char *)hdr - 1));
}
@@ -468,15 +662,20 @@ xfs_dir2_data_log_entry(
*/
void
xfs_dir2_data_log_header(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp) /* block buffer */
+ struct xfs_da_args *args,
+ struct xfs_buf *bp)
{
- xfs_dir2_data_hdr_t *hdr = bp->data;
+#ifdef DEBUG
+ struct xfs_dir2_data_hdr *hdr = bp->b_addr;
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+#endif
- xfs_da_log_buf(tp, bp, 0, sizeof(*hdr) - 1);
+ xfs_trans_log_buf(args->trans, bp, 0,
+ args->dp->d_ops->data_entry_offset - 1);
}
/*
@@ -484,25 +683,27 @@ xfs_dir2_data_log_header(
*/
void
xfs_dir2_data_log_unused(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp, /* block buffer */
+ struct xfs_da_args *args,
+ struct xfs_buf *bp,
xfs_dir2_data_unused_t *dup) /* data unused pointer */
{
- xfs_dir2_data_hdr_t *hdr = bp->data;
+ xfs_dir2_data_hdr_t *hdr = bp->b_addr;
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
/*
* Log the first part of the unused entry.
*/
- xfs_da_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
+ xfs_trans_log_buf(args->trans, bp, (uint)((char *)dup - (char *)hdr),
(uint)((char *)&dup->length + sizeof(dup->length) -
1 - (char *)hdr));
/*
* Log the end (tag) of the unused entry.
*/
- xfs_da_log_buf(tp, bp,
+ xfs_trans_log_buf(args->trans, bp,
(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr),
(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr +
sizeof(xfs_dir2_data_off_t) - 1));
@@ -514,8 +715,8 @@ xfs_dir2_data_log_unused(
*/
void
xfs_dir2_data_make_free(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp, /* block buffer */
+ struct xfs_da_args *args,
+ struct xfs_buf *bp,
xfs_dir2_data_aoff_t offset, /* starting byte offset */
xfs_dir2_data_aoff_t len, /* length in bytes */
int *needlogp, /* out: log header */
@@ -524,32 +725,33 @@ xfs_dir2_data_make_free(
xfs_dir2_data_hdr_t *hdr; /* data block pointer */
xfs_dir2_data_free_t *dfp; /* bestfree pointer */
char *endptr; /* end of data area */
- xfs_mount_t *mp; /* filesystem mount point */
int needscan; /* need to regen bestfree */
xfs_dir2_data_unused_t *newdup; /* new unused entry */
xfs_dir2_data_unused_t *postdup; /* unused entry after us */
xfs_dir2_data_unused_t *prevdup; /* unused entry before us */
+ struct xfs_dir2_data_free *bf;
- mp = tp->t_mountp;
- hdr = bp->data;
+ hdr = bp->b_addr;
/*
* Figure out where the end of the data area is.
*/
- if (hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC))
- endptr = (char *)hdr + mp->m_dirblksize;
+ if (hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC))
+ endptr = (char *)hdr + args->geo->blksize;
else {
xfs_dir2_block_tail_t *btp; /* block tail */
- ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
- btp = xfs_dir2_block_tail_p(mp, hdr);
+ ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
endptr = (char *)xfs_dir2_block_leaf_p(btp);
}
/*
* If this isn't the start of the block, then back up to
* the previous entry and see if it's free.
*/
- if (offset > sizeof(*hdr)) {
+ if (offset > args->dp->d_ops->data_entry_offset) {
__be16 *tagp; /* tag just before us */
tagp = (__be16 *)((char *)hdr + offset) - 1;
@@ -575,28 +777,29 @@ xfs_dir2_data_make_free(
* Previous and following entries are both free,
* merge everything into a single free entry.
*/
+ bf = args->dp->d_ops->data_bestfree_p(hdr);
if (prevdup && postdup) {
xfs_dir2_data_free_t *dfp2; /* another bestfree pointer */
/*
* See if prevdup and/or postdup are in bestfree table.
*/
- dfp = xfs_dir2_data_freefind(hdr, prevdup);
- dfp2 = xfs_dir2_data_freefind(hdr, postdup);
+ dfp = xfs_dir2_data_freefind(hdr, bf, prevdup);
+ dfp2 = xfs_dir2_data_freefind(hdr, bf, postdup);
/*
* We need a rescan unless there are exactly 2 free entries
* namely our two. Then we know what's happening, otherwise
* since the third bestfree is there, there might be more
* entries.
*/
- needscan = (hdr->bestfree[2].length != 0);
+ needscan = (bf[2].length != 0);
/*
* Fix up the new big freespace.
*/
be16_add_cpu(&prevdup->length, len + be16_to_cpu(postdup->length));
*xfs_dir2_data_unused_tag_p(prevdup) =
cpu_to_be16((char *)prevdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, prevdup);
+ xfs_dir2_data_log_unused(args, bp, prevdup);
if (!needscan) {
/*
* Has to be the case that entries 0 and 1 are
@@ -605,18 +808,19 @@ xfs_dir2_data_make_free(
* Remove entry 1 first then entry 0.
*/
ASSERT(dfp && dfp2);
- if (dfp == &hdr->bestfree[1]) {
- dfp = &hdr->bestfree[0];
+ if (dfp == &bf[1]) {
+ dfp = &bf[0];
ASSERT(dfp2 == dfp);
- dfp2 = &hdr->bestfree[1];
+ dfp2 = &bf[1];
}
- xfs_dir2_data_freeremove(hdr, dfp2, needlogp);
- xfs_dir2_data_freeremove(hdr, dfp, needlogp);
+ xfs_dir2_data_freeremove(hdr, bf, dfp2, needlogp);
+ xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
/*
* Now insert the new entry.
*/
- dfp = xfs_dir2_data_freeinsert(hdr, prevdup, needlogp);
- ASSERT(dfp == &hdr->bestfree[0]);
+ dfp = xfs_dir2_data_freeinsert(hdr, bf, prevdup,
+ needlogp);
+ ASSERT(dfp == &bf[0]);
ASSERT(dfp->length == prevdup->length);
ASSERT(!dfp[1].length);
ASSERT(!dfp[2].length);
@@ -626,54 +830,54 @@ xfs_dir2_data_make_free(
* The entry before us is free, merge with it.
*/
else if (prevdup) {
- dfp = xfs_dir2_data_freefind(hdr, prevdup);
+ dfp = xfs_dir2_data_freefind(hdr, bf, prevdup);
be16_add_cpu(&prevdup->length, len);
*xfs_dir2_data_unused_tag_p(prevdup) =
cpu_to_be16((char *)prevdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, prevdup);
+ xfs_dir2_data_log_unused(args, bp, prevdup);
/*
* If the previous entry was in the table, the new entry
* is longer, so it will be in the table too. Remove
* the old one and add the new one.
*/
if (dfp) {
- xfs_dir2_data_freeremove(hdr, dfp, needlogp);
- xfs_dir2_data_freeinsert(hdr, prevdup, needlogp);
+ xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+ xfs_dir2_data_freeinsert(hdr, bf, prevdup, needlogp);
}
/*
* Otherwise we need a scan if the new entry is big enough.
*/
else {
needscan = be16_to_cpu(prevdup->length) >
- be16_to_cpu(hdr->bestfree[2].length);
+ be16_to_cpu(bf[2].length);
}
}
/*
* The following entry is free, merge with it.
*/
else if (postdup) {
- dfp = xfs_dir2_data_freefind(hdr, postdup);
+ dfp = xfs_dir2_data_freefind(hdr, bf, postdup);
newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset);
newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
newdup->length = cpu_to_be16(len + be16_to_cpu(postdup->length));
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
/*
* If the following entry was in the table, the new entry
* is longer, so it will be in the table too. Remove
* the old one and add the new one.
*/
if (dfp) {
- xfs_dir2_data_freeremove(hdr, dfp, needlogp);
- xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+ xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+ xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
}
/*
* Otherwise we need a scan if the new entry is big enough.
*/
else {
needscan = be16_to_cpu(newdup->length) >
- be16_to_cpu(hdr->bestfree[2].length);
+ be16_to_cpu(bf[2].length);
}
}
/*
@@ -685,8 +889,8 @@ xfs_dir2_data_make_free(
newdup->length = cpu_to_be16(len);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
- xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+ xfs_dir2_data_log_unused(args, bp, newdup);
+ xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
}
*needscanp = needscan;
}
@@ -696,8 +900,8 @@ xfs_dir2_data_make_free(
*/
void
xfs_dir2_data_use_free(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp, /* data block buffer */
+ struct xfs_da_args *args,
+ struct xfs_buf *bp,
xfs_dir2_data_unused_t *dup, /* unused entry */
xfs_dir2_data_aoff_t offset, /* starting offset to use */
xfs_dir2_data_aoff_t len, /* length to use */
@@ -712,10 +916,13 @@ xfs_dir2_data_use_free(
xfs_dir2_data_unused_t *newdup; /* new unused entry */
xfs_dir2_data_unused_t *newdup2; /* another new unused entry */
int oldlen; /* old unused entry's length */
+ struct xfs_dir2_data_free *bf;
- hdr = bp->data;
+ hdr = bp->b_addr;
ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
ASSERT(be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG);
ASSERT(offset >= (char *)dup - (char *)hdr);
ASSERT(offset + len <= (char *)dup + be16_to_cpu(dup->length) - (char *)hdr);
@@ -723,9 +930,10 @@ xfs_dir2_data_use_free(
/*
* Look up the entry in the bestfree table.
*/
- dfp = xfs_dir2_data_freefind(hdr, dup);
oldlen = be16_to_cpu(dup->length);
- ASSERT(dfp || oldlen <= be16_to_cpu(hdr->bestfree[2].length));
+ bf = args->dp->d_ops->data_bestfree_p(hdr);
+ dfp = xfs_dir2_data_freefind(hdr, bf, dup);
+ ASSERT(dfp || oldlen <= be16_to_cpu(bf[2].length));
/*
* Check for alignment with front and back of the entry.
*/
@@ -739,9 +947,10 @@ xfs_dir2_data_use_free(
*/
if (matchfront && matchback) {
if (dfp) {
- needscan = (hdr->bestfree[2].offset != 0);
+ needscan = (bf[2].offset != 0);
if (!needscan)
- xfs_dir2_data_freeremove(hdr, dfp, needlogp);
+ xfs_dir2_data_freeremove(hdr, bf, dfp,
+ needlogp);
}
}
/*
@@ -754,13 +963,14 @@ xfs_dir2_data_use_free(
newdup->length = cpu_to_be16(oldlen - len);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
/*
* If it was in the table, remove it and add the new one.
*/
if (dfp) {
- xfs_dir2_data_freeremove(hdr, dfp, needlogp);
- dfp = xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+ xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+ dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
+ needlogp);
ASSERT(dfp != NULL);
ASSERT(dfp->length == newdup->length);
ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
@@ -769,7 +979,7 @@ xfs_dir2_data_use_free(
* that means we don't know if there was a better
* choice for the last slot, or not. Rescan.
*/
- needscan = dfp == &hdr->bestfree[2];
+ needscan = dfp == &bf[2];
}
}
/*
@@ -781,13 +991,14 @@ xfs_dir2_data_use_free(
newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
/*
* If it was in the table, remove it and add the new one.
*/
if (dfp) {
- xfs_dir2_data_freeremove(hdr, dfp, needlogp);
- dfp = xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
+ xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
+ dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
+ needlogp);
ASSERT(dfp != NULL);
ASSERT(dfp->length == newdup->length);
ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
@@ -796,7 +1007,7 @@ xfs_dir2_data_use_free(
* that means we don't know if there was a better
* choice for the last slot, or not. Rescan.
*/
- needscan = dfp == &hdr->bestfree[2];
+ needscan = dfp == &bf[2];
}
}
/*
@@ -808,13 +1019,13 @@ xfs_dir2_data_use_free(
newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
*xfs_dir2_data_unused_tag_p(newdup) =
cpu_to_be16((char *)newdup - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup);
+ xfs_dir2_data_log_unused(args, bp, newdup);
newdup2 = (xfs_dir2_data_unused_t *)((char *)hdr + offset + len);
newdup2->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
newdup2->length = cpu_to_be16(oldlen - len - be16_to_cpu(newdup->length));
*xfs_dir2_data_unused_tag_p(newdup2) =
cpu_to_be16((char *)newdup2 - (char *)hdr);
- xfs_dir2_data_log_unused(tp, bp, newdup2);
+ xfs_dir2_data_log_unused(args, bp, newdup2);
/*
* If the old entry was in the table, we need to scan
* if the 3rd entry was valid, since these entries
@@ -824,11 +1035,13 @@ xfs_dir2_data_use_free(
* the 2 new will work.
*/
if (dfp) {
- needscan = (hdr->bestfree[2].length != 0);
+ needscan = (bf[2].length != 0);
if (!needscan) {
- xfs_dir2_data_freeremove(hdr, dfp, needlogp);
- xfs_dir2_data_freeinsert(hdr, newdup, needlogp);
- xfs_dir2_data_freeinsert(hdr, newdup2,
+ xfs_dir2_data_freeremove(hdr, bf, dfp,
+ needlogp);
+ xfs_dir2_data_freeinsert(hdr, bf, newdup,
+ needlogp);
+ xfs_dir2_data_freeinsert(hdr, bf, newdup2,
needlogp);
}
}
diff --git a/fs/xfs/xfs_dir2_format.h b/fs/xfs/xfs_dir2_format.h
deleted file mode 100644
index 07270981f48..00000000000
--- a/fs/xfs/xfs_dir2_format.h
+++ /dev/null
@@ -1,597 +0,0 @@
-/*
- * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-#ifndef __XFS_DIR2_FORMAT_H__
-#define __XFS_DIR2_FORMAT_H__
-
-/*
- * Directory version 2.
- *
- * There are 4 possible formats:
- * - shortform - embedded into the inode
- * - single block - data with embedded leaf at the end
- * - multiple data blocks, single leaf+freeindex block
- * - data blocks, node and leaf blocks (btree), freeindex blocks
- *
- * Note: many node blocks structures and constants are shared with the attr
- * code and defined in xfs_da_btree.h.
- */
-
-#define XFS_DIR2_BLOCK_MAGIC 0x58443242 /* XD2B: single block dirs */
-#define XFS_DIR2_DATA_MAGIC 0x58443244 /* XD2D: multiblock dirs */
-#define XFS_DIR2_FREE_MAGIC 0x58443246 /* XD2F: free index blocks */
-
-/*
- * Byte offset in data block and shortform entry.
- */
-typedef __uint16_t xfs_dir2_data_off_t;
-#define NULLDATAOFF 0xffffU
-typedef uint xfs_dir2_data_aoff_t; /* argument form */
-
-/*
- * Normalized offset (in a data block) of the entry, really xfs_dir2_data_off_t.
- * Only need 16 bits, this is the byte offset into the single block form.
- */
-typedef struct { __uint8_t i[2]; } __arch_pack xfs_dir2_sf_off_t;
-
-/*
- * Offset in data space of a data entry.
- */
-typedef __uint32_t xfs_dir2_dataptr_t;
-#define XFS_DIR2_MAX_DATAPTR ((xfs_dir2_dataptr_t)0xffffffff)
-#define XFS_DIR2_NULL_DATAPTR ((xfs_dir2_dataptr_t)0)
-
-/*
- * Byte offset in a directory.
- */
-typedef xfs_off_t xfs_dir2_off_t;
-
-/*
- * Directory block number (logical dirblk in file)
- */
-typedef __uint32_t xfs_dir2_db_t;
-
-/*
- * Inode number stored as 8 8-bit values.
- */
-typedef struct { __uint8_t i[8]; } xfs_dir2_ino8_t;
-
-/*
- * Inode number stored as 4 8-bit values.
- * Works a lot of the time, when all the inode numbers in a directory
- * fit in 32 bits.
- */
-typedef struct { __uint8_t i[4]; } xfs_dir2_ino4_t;
-
-typedef union {
- xfs_dir2_ino8_t i8;
- xfs_dir2_ino4_t i4;
-} xfs_dir2_inou_t;
-#define XFS_DIR2_MAX_SHORT_INUM ((xfs_ino_t)0xffffffffULL)
-
-/*
- * Directory layout when stored internal to an inode.
- *
- * Small directories are packed as tightly as possible so as to fit into the
- * literal area of the inode. These "shortform" directories consist of a
- * single xfs_dir2_sf_hdr header followed by zero or more xfs_dir2_sf_entry
- * structures. Due the different inode number storage size and the variable
- * length name field in the xfs_dir2_sf_entry all these structure are
- * variable length, and the accessors in this file should be used to iterate
- * over them.
- */
-typedef struct xfs_dir2_sf_hdr {
- __uint8_t count; /* count of entries */
- __uint8_t i8count; /* count of 8-byte inode #s */
- xfs_dir2_inou_t parent; /* parent dir inode number */
-} __arch_pack xfs_dir2_sf_hdr_t;
-
-typedef struct xfs_dir2_sf_entry {
- __u8 namelen; /* actual name length */
- xfs_dir2_sf_off_t offset; /* saved offset */
- __u8 name[]; /* name, variable size */
- /*
- * A xfs_dir2_ino8_t or xfs_dir2_ino4_t follows here, at a
- * variable offset after the name.
- */
-} __arch_pack xfs_dir2_sf_entry_t;
-
-static inline int xfs_dir2_sf_hdr_size(int i8count)
-{
- return sizeof(struct xfs_dir2_sf_hdr) -
- (i8count == 0) *
- (sizeof(xfs_dir2_ino8_t) - sizeof(xfs_dir2_ino4_t));
-}
-
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_sf_get_offset(xfs_dir2_sf_entry_t *sfep)
-{
- return get_unaligned_be16(&sfep->offset.i);
-}
-
-static inline void
-xfs_dir2_sf_put_offset(xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t off)
-{
- put_unaligned_be16(off, &sfep->offset.i);
-}
-
-static inline int
-xfs_dir2_sf_entsize(struct xfs_dir2_sf_hdr *hdr, int len)
-{
- return sizeof(struct xfs_dir2_sf_entry) + /* namelen + offset */
- len + /* name */
- (hdr->i8count ? /* ino */
- sizeof(xfs_dir2_ino8_t) :
- sizeof(xfs_dir2_ino4_t));
-}
-
-static inline struct xfs_dir2_sf_entry *
-xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
-{
- return (struct xfs_dir2_sf_entry *)
- ((char *)hdr + xfs_dir2_sf_hdr_size(hdr->i8count));
-}
-
-static inline struct xfs_dir2_sf_entry *
-xfs_dir2_sf_nextentry(struct xfs_dir2_sf_hdr *hdr,
- struct xfs_dir2_sf_entry *sfep)
-{
- return (struct xfs_dir2_sf_entry *)
- ((char *)sfep + xfs_dir2_sf_entsize(hdr, sfep->namelen));
-}
-
-
-/*
- * Data block structures.
- *
- * A pure data block looks like the following drawing on disk:
- *
- * +-------------------------------------------------+
- * | xfs_dir2_data_hdr_t |
- * +-------------------------------------------------+
- * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- * | ... |
- * +-------------------------------------------------+
- * | unused space |
- * +-------------------------------------------------+
- *
- * As all the entries are variable size structures the accessors below should
- * be used to iterate over them.
- *
- * In addition to the pure data blocks for the data and node formats,
- * most structures are also used for the combined data/freespace "block"
- * format below.
- */
-
-#define XFS_DIR2_DATA_ALIGN_LOG 3 /* i.e., 8 bytes */
-#define XFS_DIR2_DATA_ALIGN (1 << XFS_DIR2_DATA_ALIGN_LOG)
-#define XFS_DIR2_DATA_FREE_TAG 0xffff
-#define XFS_DIR2_DATA_FD_COUNT 3
-
-/*
- * Directory address space divided into sections,
- * spaces separated by 32GB.
- */
-#define XFS_DIR2_SPACE_SIZE (1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
-#define XFS_DIR2_DATA_SPACE 0
-#define XFS_DIR2_DATA_OFFSET (XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
-#define XFS_DIR2_DATA_FIRSTDB(mp) \
- xfs_dir2_byte_to_db(mp, XFS_DIR2_DATA_OFFSET)
-
-/*
- * Offsets of . and .. in data space (always block 0)
- */
-#define XFS_DIR2_DATA_DOT_OFFSET \
- ((xfs_dir2_data_aoff_t)sizeof(struct xfs_dir2_data_hdr))
-#define XFS_DIR2_DATA_DOTDOT_OFFSET \
- (XFS_DIR2_DATA_DOT_OFFSET + xfs_dir2_data_entsize(1))
-#define XFS_DIR2_DATA_FIRST_OFFSET \
- (XFS_DIR2_DATA_DOTDOT_OFFSET + xfs_dir2_data_entsize(2))
-
-/*
- * Describe a free area in the data block.
- *
- * The freespace will be formatted as a xfs_dir2_data_unused_t.
- */
-typedef struct xfs_dir2_data_free {
- __be16 offset; /* start of freespace */
- __be16 length; /* length of freespace */
-} xfs_dir2_data_free_t;
-
-/*
- * Header for the data blocks.
- *
- * The code knows that XFS_DIR2_DATA_FD_COUNT is 3.
- */
-typedef struct xfs_dir2_data_hdr {
- __be32 magic; /* XFS_DIR2_DATA_MAGIC or */
- /* XFS_DIR2_BLOCK_MAGIC */
- xfs_dir2_data_free_t bestfree[XFS_DIR2_DATA_FD_COUNT];
-} xfs_dir2_data_hdr_t;
-
-/*
- * Active entry in a data block.
- *
- * Aligned to 8 bytes. After the variable length name field there is a
- * 2 byte tag field, which can be accessed using xfs_dir2_data_entry_tag_p.
- */
-typedef struct xfs_dir2_data_entry {
- __be64 inumber; /* inode number */
- __u8 namelen; /* name length */
- __u8 name[]; /* name bytes, no null */
- /* __be16 tag; */ /* starting offset of us */
-} xfs_dir2_data_entry_t;
-
-/*
- * Unused entry in a data block.
- *
- * Aligned to 8 bytes. Tag appears as the last 2 bytes and must be accessed
- * using xfs_dir2_data_unused_tag_p.
- */
-typedef struct xfs_dir2_data_unused {
- __be16 freetag; /* XFS_DIR2_DATA_FREE_TAG */
- __be16 length; /* total free length */
- /* variable offset */
- __be16 tag; /* starting offset of us */
-} xfs_dir2_data_unused_t;
-
-/*
- * Size of a data entry.
- */
-static inline int xfs_dir2_data_entsize(int n)
-{
- return (int)roundup(offsetof(struct xfs_dir2_data_entry, name[0]) + n +
- (uint)sizeof(xfs_dir2_data_off_t), XFS_DIR2_DATA_ALIGN);
-}
-
-/*
- * Pointer to an entry's tag word.
- */
-static inline __be16 *
-xfs_dir2_data_entry_tag_p(struct xfs_dir2_data_entry *dep)
-{
- return (__be16 *)((char *)dep +
- xfs_dir2_data_entsize(dep->namelen) - sizeof(__be16));
-}
-
-/*
- * Pointer to a freespace's tag word.
- */
-static inline __be16 *
-xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup)
-{
- return (__be16 *)((char *)dup +
- be16_to_cpu(dup->length) - sizeof(__be16));
-}
-
-/*
- * Leaf block structures.
- *
- * A pure leaf block looks like the following drawing on disk:
- *
- * +---------------------------+
- * | xfs_dir2_leaf_hdr_t |
- * +---------------------------+
- * | xfs_dir2_leaf_entry_t |
- * | xfs_dir2_leaf_entry_t |
- * | xfs_dir2_leaf_entry_t |
- * | xfs_dir2_leaf_entry_t |
- * | ... |
- * +---------------------------+
- * | xfs_dir2_data_off_t |
- * | xfs_dir2_data_off_t |
- * | xfs_dir2_data_off_t |
- * | ... |
- * +---------------------------+
- * | xfs_dir2_leaf_tail_t |
- * +---------------------------+
- *
- * The xfs_dir2_data_off_t members (bests) and tail are at the end of the block
- * for single-leaf (magic = XFS_DIR2_LEAF1_MAGIC) blocks only, but not present
- * for directories with separate leaf nodes and free space blocks
- * (magic = XFS_DIR2_LEAFN_MAGIC).
- *
- * As all the entries are variable size structures the accessors below should
- * be used to iterate over them.
- */
-
-/*
- * Offset of the leaf/node space. First block in this space
- * is the btree root.
- */
-#define XFS_DIR2_LEAF_SPACE 1
-#define XFS_DIR2_LEAF_OFFSET (XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE)
-#define XFS_DIR2_LEAF_FIRSTDB(mp) \
- xfs_dir2_byte_to_db(mp, XFS_DIR2_LEAF_OFFSET)
-
-/*
- * Leaf block header.
- */
-typedef struct xfs_dir2_leaf_hdr {
- xfs_da_blkinfo_t info; /* header for da routines */
- __be16 count; /* count of entries */
- __be16 stale; /* count of stale entries */
-} xfs_dir2_leaf_hdr_t;
-
-/*
- * Leaf block entry.
- */
-typedef struct xfs_dir2_leaf_entry {
- __be32 hashval; /* hash value of name */
- __be32 address; /* address of data entry */
-} xfs_dir2_leaf_entry_t;
-
-/*
- * Leaf block tail.
- */
-typedef struct xfs_dir2_leaf_tail {
- __be32 bestcount;
-} xfs_dir2_leaf_tail_t;
-
-/*
- * Leaf block.
- */
-typedef struct xfs_dir2_leaf {
- xfs_dir2_leaf_hdr_t hdr; /* leaf header */
- xfs_dir2_leaf_entry_t ents[]; /* entries */
-} xfs_dir2_leaf_t;
-
-/*
- * DB blocks here are logical directory block numbers, not filesystem blocks.
- */
-
-static inline int xfs_dir2_max_leaf_ents(struct xfs_mount *mp)
-{
- return (mp->m_dirblksize - (uint)sizeof(struct xfs_dir2_leaf_hdr)) /
- (uint)sizeof(struct xfs_dir2_leaf_entry);
-}
-
-/*
- * Get address of the bestcount field in the single-leaf block.
- */
-static inline struct xfs_dir2_leaf_tail *
-xfs_dir2_leaf_tail_p(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
-{
- return (struct xfs_dir2_leaf_tail *)
- ((char *)lp + mp->m_dirblksize -
- sizeof(struct xfs_dir2_leaf_tail));
-}
-
-/*
- * Get address of the bests array in the single-leaf block.
- */
-static inline __be16 *
-xfs_dir2_leaf_bests_p(struct xfs_dir2_leaf_tail *ltp)
-{
- return (__be16 *)ltp - be32_to_cpu(ltp->bestcount);
-}
-
-/*
- * Convert dataptr to byte in file space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_dataptr_to_byte(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
- return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG;
-}
-
-/*
- * Convert byte in file space to dataptr. It had better be aligned.
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_byte_to_dataptr(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG);
-}
-
-/*
- * Convert byte in space to (DB) block
- */
-static inline xfs_dir2_db_t
-xfs_dir2_byte_to_db(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return (xfs_dir2_db_t)
- (by >> (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog));
-}
-
-/*
- * Convert dataptr to a block number
- */
-static inline xfs_dir2_db_t
-xfs_dir2_dataptr_to_db(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
- return xfs_dir2_byte_to_db(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert byte in space to offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_byte_to_off(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return (xfs_dir2_data_aoff_t)(by &
- ((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) - 1));
-}
-
-/*
- * Convert dataptr to a byte offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_dataptr_to_off(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
- return xfs_dir2_byte_to_off(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert block and offset to byte in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_db_off_to_byte(struct xfs_mount *mp, xfs_dir2_db_t db,
- xfs_dir2_data_aoff_t o)
-{
- return ((xfs_dir2_off_t)db <<
- (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) + o;
-}
-
-/*
- * Convert block (DB) to block (dablk)
- */
-static inline xfs_dablk_t
-xfs_dir2_db_to_da(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
- return (xfs_dablk_t)(db << mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert byte in space to (DA) block
- */
-static inline xfs_dablk_t
-xfs_dir2_byte_to_da(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
- return xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, by));
-}
-
-/*
- * Convert block and offset to dataptr
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_db_off_to_dataptr(struct xfs_mount *mp, xfs_dir2_db_t db,
- xfs_dir2_data_aoff_t o)
-{
- return xfs_dir2_byte_to_dataptr(mp, xfs_dir2_db_off_to_byte(mp, db, o));
-}
-
-/*
- * Convert block (dablk) to block (DB)
- */
-static inline xfs_dir2_db_t
-xfs_dir2_da_to_db(struct xfs_mount *mp, xfs_dablk_t da)
-{
- return (xfs_dir2_db_t)(da >> mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert block (dablk) to byte offset in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da)
-{
- return xfs_dir2_db_off_to_byte(mp, xfs_dir2_da_to_db(mp, da), 0);
-}
-
-/*
- * Free space block defintions for the node format.
- */
-
-/*
- * Offset of the freespace index.
- */
-#define XFS_DIR2_FREE_SPACE 2
-#define XFS_DIR2_FREE_OFFSET (XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE)
-#define XFS_DIR2_FREE_FIRSTDB(mp) \
- xfs_dir2_byte_to_db(mp, XFS_DIR2_FREE_OFFSET)
-
-typedef struct xfs_dir2_free_hdr {
- __be32 magic; /* XFS_DIR2_FREE_MAGIC */
- __be32 firstdb; /* db of first entry */
- __be32 nvalid; /* count of valid entries */
- __be32 nused; /* count of used entries */
-} xfs_dir2_free_hdr_t;
-
-typedef struct xfs_dir2_free {
- xfs_dir2_free_hdr_t hdr; /* block header */
- __be16 bests[]; /* best free counts */
- /* unused entries are -1 */
-} xfs_dir2_free_t;
-
-static inline int xfs_dir2_free_max_bests(struct xfs_mount *mp)
-{
- return (mp->m_dirblksize - sizeof(struct xfs_dir2_free_hdr)) /
- sizeof(xfs_dir2_data_off_t);
-}
-
-/*
- * Convert data space db to the corresponding free db.
- */
-static inline xfs_dir2_db_t
-xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
- return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir2_free_max_bests(mp);
-}
-
-/*
- * Convert data space db to the corresponding index in a free db.
- */
-static inline int
-xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
- return db % xfs_dir2_free_max_bests(mp);
-}
-
-/*
- * Single block format.
- *
- * The single block format looks like the following drawing on disk:
- *
- * +-------------------------------------------------+
- * | xfs_dir2_data_hdr_t |
- * +-------------------------------------------------+
- * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t :
- * | ... |
- * +-------------------------------------------------+
- * | unused space |
- * +-------------------------------------------------+
- * | ... |
- * | xfs_dir2_leaf_entry_t |
- * | xfs_dir2_leaf_entry_t |
- * +-------------------------------------------------+
- * | xfs_dir2_block_tail_t |
- * +-------------------------------------------------+
- *
- * As all the entries are variable size structures the accessors below should
- * be used to iterate over them.
- */
-
-typedef struct xfs_dir2_block_tail {
- __be32 count; /* count of leaf entries */
- __be32 stale; /* count of stale lf entries */
-} xfs_dir2_block_tail_t;
-
-/*
- * Pointer to the leaf header embedded in a data block (1-block format)
- */
-static inline struct xfs_dir2_block_tail *
-xfs_dir2_block_tail_p(struct xfs_mount *mp, struct xfs_dir2_data_hdr *hdr)
-{
- return ((struct xfs_dir2_block_tail *)
- ((char *)hdr + mp->m_dirblksize)) - 1;
-}
-
-/*
- * Pointer to the leaf entries embedded in a data block (1-block format)
- */
-static inline struct xfs_dir2_leaf_entry *
-xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
-{
- return ((struct xfs_dir2_leaf_entry *)btp) - be32_to_cpu(btp->count);
-}
-
-#endif /* __XFS_DIR2_FORMAT_H__ */
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index 397ffbcbab1..fb0aad4440c 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -17,37 +18,352 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
-#include "xfs_dir2_format.h"
+#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_trans.h"
+#include "xfs_buf_item.h"
+#include "xfs_cksum.h"
/*
* Local function declarations.
*/
+static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, struct xfs_buf **lbpp,
+ int *indexp, struct xfs_buf **dbpp);
+static void xfs_dir3_leaf_log_bests(struct xfs_da_args *args,
+ struct xfs_buf *bp, int first, int last);
+static void xfs_dir3_leaf_log_tail(struct xfs_da_args *args,
+ struct xfs_buf *bp);
+
+/*
+ * Check the internal consistency of a leaf1 block.
+ * Pop an assert if something is wrong.
+ */
#ifdef DEBUG
-static void xfs_dir2_leaf_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
+#define xfs_dir3_leaf_check(dp, bp) \
+do { \
+ if (!xfs_dir3_leaf1_check((dp), (bp))) \
+ ASSERT(0); \
+} while (0);
+
+STATIC bool
+xfs_dir3_leaf1_check(
+ struct xfs_inode *dp,
+ struct xfs_buf *bp)
+{
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
+ struct xfs_dir3_icleaf_hdr leafhdr;
+
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+
+ if (leafhdr.magic == XFS_DIR3_LEAF1_MAGIC) {
+ struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
+ if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn)
+ return false;
+ } else if (leafhdr.magic != XFS_DIR2_LEAF1_MAGIC)
+ return false;
+
+ return xfs_dir3_leaf_check_int(dp->i_mount, dp, &leafhdr, leaf);
+}
#else
-#define xfs_dir2_leaf_check(dp, bp)
+#define xfs_dir3_leaf_check(dp, bp)
#endif
-static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **lbpp,
- int *indexp, xfs_dabuf_t **dbpp);
-static void xfs_dir2_leaf_log_bests(struct xfs_trans *tp, struct xfs_dabuf *bp,
- int first, int last);
-static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_dabuf *bp);
+bool
+xfs_dir3_leaf_check_int(
+ struct xfs_mount *mp,
+ struct xfs_inode *dp,
+ struct xfs_dir3_icleaf_hdr *hdr,
+ struct xfs_dir2_leaf *leaf)
+{
+ struct xfs_dir2_leaf_entry *ents;
+ xfs_dir2_leaf_tail_t *ltp;
+ int stale;
+ int i;
+ const struct xfs_dir_ops *ops;
+ struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_da_geometry *geo = mp->m_dir_geo;
+
+ /*
+ * we can be passed a null dp here from a verifier, so we need to go the
+ * hard way to get them.
+ */
+ ops = xfs_dir_get_ops(mp, dp);
+
+ if (!hdr) {
+ ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ hdr = &leafhdr;
+ }
+
+ ents = ops->leaf_ents_p(leaf);
+ ltp = xfs_dir2_leaf_tail_p(geo, leaf);
+
+ /*
+ * XXX (dgc): This value is not restrictive enough.
+ * Should factor in the size of the bests table as well.
+ * We can deduce a value for that from di_size.
+ */
+ if (hdr->count > ops->leaf_max_ents(geo))
+ return false;
+
+ /* Leaves and bests don't overlap in leaf format. */
+ if ((hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
+ hdr->magic == XFS_DIR3_LEAF1_MAGIC) &&
+ (char *)&ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp))
+ return false;
+
+ /* Check hash value order, count stale entries. */
+ for (i = stale = 0; i < hdr->count; i++) {
+ if (i + 1 < hdr->count) {
+ if (be32_to_cpu(ents[i].hashval) >
+ be32_to_cpu(ents[i + 1].hashval))
+ return false;
+ }
+ if (ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
+ stale++;
+ }
+ if (hdr->stale != stale)
+ return false;
+ return true;
+}
+
+/*
+ * We verify the magic numbers before decoding the leaf header so that on debug
+ * kernels we don't get assertion failures in xfs_dir3_leaf_hdr_from_disk() due
+ * to incorrect magic numbers.
+ */
+static bool
+xfs_dir3_leaf_verify(
+ struct xfs_buf *bp,
+ __uint16_t magic)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
+
+ ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
+ __uint16_t magic3;
+
+ magic3 = (magic == XFS_DIR2_LEAF1_MAGIC) ? XFS_DIR3_LEAF1_MAGIC
+ : XFS_DIR3_LEAFN_MAGIC;
+
+ if (leaf3->info.hdr.magic != cpu_to_be16(magic3))
+ return false;
+ if (!uuid_equal(&leaf3->info.uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn)
+ return false;
+ } else {
+ if (leaf->hdr.info.magic != cpu_to_be16(magic))
+ return false;
+ }
+
+ return xfs_dir3_leaf_check_int(mp, NULL, NULL, leaf);
+}
+
+static void
+__read_verify(
+ struct xfs_buf *bp,
+ __uint16_t magic)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !xfs_buf_verify_cksum(bp, XFS_DIR3_LEAF_CRC_OFF))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_dir3_leaf_verify(bp, magic))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+}
+
+static void
+__write_verify(
+ struct xfs_buf *bp,
+ __uint16_t magic)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+ struct xfs_dir3_leaf_hdr *hdr3 = bp->b_addr;
+
+ if (!xfs_dir3_leaf_verify(bp, magic)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (bip)
+ hdr3->info.lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_DIR3_LEAF_CRC_OFF);
+}
+
+static void
+xfs_dir3_leaf1_read_verify(
+ struct xfs_buf *bp)
+{
+ __read_verify(bp, XFS_DIR2_LEAF1_MAGIC);
+}
+
+static void
+xfs_dir3_leaf1_write_verify(
+ struct xfs_buf *bp)
+{
+ __write_verify(bp, XFS_DIR2_LEAF1_MAGIC);
+}
+
+static void
+xfs_dir3_leafn_read_verify(
+ struct xfs_buf *bp)
+{
+ __read_verify(bp, XFS_DIR2_LEAFN_MAGIC);
+}
+
+static void
+xfs_dir3_leafn_write_verify(
+ struct xfs_buf *bp)
+{
+ __write_verify(bp, XFS_DIR2_LEAFN_MAGIC);
+}
+
+const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops = {
+ .verify_read = xfs_dir3_leaf1_read_verify,
+ .verify_write = xfs_dir3_leaf1_write_verify,
+};
+
+const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = {
+ .verify_read = xfs_dir3_leafn_read_verify,
+ .verify_write = xfs_dir3_leafn_write_verify,
+};
+
+static int
+xfs_dir3_leaf_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t fbno,
+ xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp)
+{
+ int err;
+
+ err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
+ XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops);
+ if (!err && tp)
+ xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
+ return err;
+}
+
+int
+xfs_dir3_leafn_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t fbno,
+ xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp)
+{
+ int err;
+
+ err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
+ XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops);
+ if (!err && tp)
+ xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
+ return err;
+}
+
+/*
+ * Initialize a new leaf block, leaf1 or leafn magic accepted.
+ */
+static void
+xfs_dir3_leaf_init(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_buf *bp,
+ xfs_ino_t owner,
+ __uint16_t type)
+{
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
+
+ ASSERT(type == XFS_DIR2_LEAF1_MAGIC || type == XFS_DIR2_LEAFN_MAGIC);
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
+
+ memset(leaf3, 0, sizeof(*leaf3));
+
+ leaf3->info.hdr.magic = (type == XFS_DIR2_LEAF1_MAGIC)
+ ? cpu_to_be16(XFS_DIR3_LEAF1_MAGIC)
+ : cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
+ leaf3->info.blkno = cpu_to_be64(bp->b_bn);
+ leaf3->info.owner = cpu_to_be64(owner);
+ uuid_copy(&leaf3->info.uuid, &mp->m_sb.sb_uuid);
+ } else {
+ memset(leaf, 0, sizeof(*leaf));
+ leaf->hdr.info.magic = cpu_to_be16(type);
+ }
+
+ /*
+ * If it's a leaf-format directory initialize the tail.
+ * Caller is responsible for initialising the bests table.
+ */
+ if (type == XFS_DIR2_LEAF1_MAGIC) {
+ struct xfs_dir2_leaf_tail *ltp;
+
+ ltp = xfs_dir2_leaf_tail_p(mp->m_dir_geo, leaf);
+ ltp->bestcount = 0;
+ bp->b_ops = &xfs_dir3_leaf1_buf_ops;
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAF1_BUF);
+ } else {
+ bp->b_ops = &xfs_dir3_leafn_buf_ops;
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAFN_BUF);
+ }
+}
+
+int
+xfs_dir3_leaf_get_buf(
+ xfs_da_args_t *args,
+ xfs_dir2_db_t bno,
+ struct xfs_buf **bpp,
+ __uint16_t magic)
+{
+ struct xfs_inode *dp = args->dp;
+ struct xfs_trans *tp = args->trans;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_buf *bp;
+ int error;
+
+ ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
+ ASSERT(bno >= xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET) &&
+ bno < xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET));
+
+ error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, bno),
+ -1, &bp, XFS_DATA_FORK);
+ if (error)
+ return error;
+
+ xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic);
+ xfs_dir3_leaf_log_header(args, bp);
+ if (magic == XFS_DIR2_LEAF1_MAGIC)
+ xfs_dir3_leaf_log_tail(args, bp);
+ *bpp = bp;
+ return 0;
+}
/*
* Convert a block form directory to a leaf form directory.
@@ -55,7 +371,7 @@ static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_dabuf *bp);
int /* error */
xfs_dir2_block_to_leaf(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *dbp) /* input block's buffer */
+ struct xfs_buf *dbp) /* input block's buffer */
{
__be16 *bestsp; /* leaf's bestsp entries */
xfs_dablk_t blkno; /* leaf block's bno */
@@ -64,7 +380,7 @@ xfs_dir2_block_to_leaf(
xfs_dir2_block_tail_t *btp; /* block's tail */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
- xfs_dabuf_t *lbp; /* leaf block's buffer */
+ struct xfs_buf *lbp; /* leaf block's buffer */
xfs_dir2_db_t ldb; /* leaf block's bno */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_tail_t *ltp; /* leaf's tail */
@@ -72,6 +388,9 @@ xfs_dir2_block_to_leaf(
int needlog; /* need to log block header */
int needscan; /* need to rescan bestfree */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir2_data_free *bf;
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
trace_xfs_dir2_block_to_leaf(args);
@@ -86,70 +405,83 @@ xfs_dir2_block_to_leaf(
if ((error = xfs_da_grow_inode(args, &blkno))) {
return error;
}
- ldb = xfs_dir2_da_to_db(mp, blkno);
- ASSERT(ldb == XFS_DIR2_LEAF_FIRSTDB(mp));
+ ldb = xfs_dir2_da_to_db(args->geo, blkno);
+ ASSERT(ldb == xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET));
/*
* Initialize the leaf block, get a buffer for it.
*/
- if ((error = xfs_dir2_leaf_init(args, ldb, &lbp, XFS_DIR2_LEAF1_MAGIC))) {
+ error = xfs_dir3_leaf_get_buf(args, ldb, &lbp, XFS_DIR2_LEAF1_MAGIC);
+ if (error)
return error;
- }
- ASSERT(lbp != NULL);
- leaf = lbp->data;
- hdr = dbp->data;
- xfs_dir2_data_check(dp, dbp);
- btp = xfs_dir2_block_tail_p(mp, hdr);
+
+ leaf = lbp->b_addr;
+ hdr = dbp->b_addr;
+ xfs_dir3_data_check(dp, dbp);
+ btp = xfs_dir2_block_tail_p(args->geo, hdr);
blp = xfs_dir2_block_leaf_p(btp);
+ bf = dp->d_ops->data_bestfree_p(hdr);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+
/*
* Set the counts in the leaf header.
*/
- leaf->hdr.count = cpu_to_be16(be32_to_cpu(btp->count));
- leaf->hdr.stale = cpu_to_be16(be32_to_cpu(btp->stale));
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ leafhdr.count = be32_to_cpu(btp->count);
+ leafhdr.stale = be32_to_cpu(btp->stale);
+ dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+ xfs_dir3_leaf_log_header(args, lbp);
+
/*
* Could compact these but I think we always do the conversion
* after squeezing out stale entries.
*/
- memcpy(leaf->ents, blp, be32_to_cpu(btp->count) * sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir2_leaf_log_ents(tp, lbp, 0, be16_to_cpu(leaf->hdr.count) - 1);
+ memcpy(ents, blp, be32_to_cpu(btp->count) * sizeof(xfs_dir2_leaf_entry_t));
+ xfs_dir3_leaf_log_ents(args, lbp, 0, leafhdr.count - 1);
needscan = 0;
needlog = 1;
/*
* Make the space formerly occupied by the leaf entries and block
* tail be free.
*/
- xfs_dir2_data_make_free(tp, dbp,
+ xfs_dir2_data_make_free(args, dbp,
(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
- (xfs_dir2_data_aoff_t)((char *)hdr + mp->m_dirblksize -
+ (xfs_dir2_data_aoff_t)((char *)hdr + args->geo->blksize -
(char *)blp),
&needlog, &needscan);
/*
* Fix up the block header, make it a data block.
*/
- hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
+ dbp->b_ops = &xfs_dir3_data_buf_ops;
+ xfs_trans_buf_set_type(tp, dbp, XFS_BLFT_DIR_DATA_BUF);
+ if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))
+ hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
+ else
+ hdr->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
+
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
/*
* Set up leaf tail and bests table.
*/
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
ltp->bestcount = cpu_to_be32(1);
bestsp = xfs_dir2_leaf_bests_p(ltp);
- bestsp[0] = hdr->bestfree[0].length;
+ bestsp[0] = bf[0].length;
/*
* Log the data header and leaf bests table.
*/
if (needlog)
- xfs_dir2_data_log_header(tp, dbp);
- xfs_dir2_leaf_check(dp, lbp);
- xfs_dir2_data_check(dp, dbp);
- xfs_dir2_leaf_log_bests(tp, lbp, 0, 0);
- xfs_da_buf_done(lbp);
+ xfs_dir2_data_log_header(args, dbp);
+ xfs_dir3_leaf_check(dp, lbp);
+ xfs_dir3_data_check(dp, dbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0, 0);
return 0;
}
STATIC void
-xfs_dir2_leaf_find_stale(
- struct xfs_dir2_leaf *leaf,
+xfs_dir3_leaf_find_stale(
+ struct xfs_dir3_icleaf_hdr *leafhdr,
+ struct xfs_dir2_leaf_entry *ents,
int index,
int *lowstale,
int *highstale)
@@ -158,7 +490,7 @@ xfs_dir2_leaf_find_stale(
* Find the first stale entry before our index, if any.
*/
for (*lowstale = index - 1; *lowstale >= 0; --*lowstale) {
- if (leaf->ents[*lowstale].address ==
+ if (ents[*lowstale].address ==
cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
break;
}
@@ -168,10 +500,8 @@ xfs_dir2_leaf_find_stale(
* Stop if the result would require moving more entries than using
* lowstale.
*/
- for (*highstale = index;
- *highstale < be16_to_cpu(leaf->hdr.count);
- ++*highstale) {
- if (leaf->ents[*highstale].address ==
+ for (*highstale = index; *highstale < leafhdr->count; ++*highstale) {
+ if (ents[*highstale].address ==
cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
break;
if (*lowstale >= 0 && index - *lowstale <= *highstale - index)
@@ -180,8 +510,9 @@ xfs_dir2_leaf_find_stale(
}
struct xfs_dir2_leaf_entry *
-xfs_dir2_leaf_find_entry(
- xfs_dir2_leaf_t *leaf, /* leaf structure */
+xfs_dir3_leaf_find_entry(
+ struct xfs_dir3_icleaf_hdr *leafhdr,
+ struct xfs_dir2_leaf_entry *ents,
int index, /* leaf table position */
int compact, /* need to compact leaves */
int lowstale, /* index of prev stale leaf */
@@ -189,7 +520,7 @@ xfs_dir2_leaf_find_entry(
int *lfloglow, /* low leaf logging index */
int *lfloghigh) /* high leaf logging index */
{
- if (!leaf->hdr.stale) {
+ if (!leafhdr->stale) {
xfs_dir2_leaf_entry_t *lep; /* leaf entry table pointer */
/*
@@ -197,18 +528,16 @@ xfs_dir2_leaf_find_entry(
*
* If there are no stale entries, just insert a hole at index.
*/
- lep = &leaf->ents[index];
- if (index < be16_to_cpu(leaf->hdr.count))
+ lep = &ents[index];
+ if (index < leafhdr->count)
memmove(lep + 1, lep,
- (be16_to_cpu(leaf->hdr.count) - index) *
- sizeof(*lep));
+ (leafhdr->count - index) * sizeof(*lep));
/*
* Record low and high logging indices for the leaf.
*/
*lfloglow = index;
- *lfloghigh = be16_to_cpu(leaf->hdr.count);
- be16_add_cpu(&leaf->hdr.count, 1);
+ *lfloghigh = leafhdr->count++;
return lep;
}
@@ -222,16 +551,17 @@ xfs_dir2_leaf_find_entry(
* entries before and after our insertion point.
*/
if (compact == 0)
- xfs_dir2_leaf_find_stale(leaf, index, &lowstale, &highstale);
+ xfs_dir3_leaf_find_stale(leafhdr, ents, index,
+ &lowstale, &highstale);
/*
* If the low one is better, use it.
*/
if (lowstale >= 0 &&
- (highstale == be16_to_cpu(leaf->hdr.count) ||
+ (highstale == leafhdr->count ||
index - lowstale - 1 < highstale - index)) {
ASSERT(index - lowstale - 1 >= 0);
- ASSERT(leaf->ents[lowstale].address ==
+ ASSERT(ents[lowstale].address ==
cpu_to_be32(XFS_DIR2_NULL_DATAPTR));
/*
@@ -239,37 +569,34 @@ xfs_dir2_leaf_find_entry(
* for the new entry.
*/
if (index - lowstale - 1 > 0) {
- memmove(&leaf->ents[lowstale],
- &leaf->ents[lowstale + 1],
+ memmove(&ents[lowstale], &ents[lowstale + 1],
(index - lowstale - 1) *
- sizeof(xfs_dir2_leaf_entry_t));
+ sizeof(xfs_dir2_leaf_entry_t));
}
*lfloglow = MIN(lowstale, *lfloglow);
*lfloghigh = MAX(index - 1, *lfloghigh);
- be16_add_cpu(&leaf->hdr.stale, -1);
- return &leaf->ents[index - 1];
+ leafhdr->stale--;
+ return &ents[index - 1];
}
/*
* The high one is better, so use that one.
*/
ASSERT(highstale - index >= 0);
- ASSERT(leaf->ents[highstale].address ==
- cpu_to_be32(XFS_DIR2_NULL_DATAPTR));
+ ASSERT(ents[highstale].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR));
/*
* Copy entries down to cover the stale entry and make room for the
* new entry.
*/
if (highstale - index > 0) {
- memmove(&leaf->ents[index + 1],
- &leaf->ents[index],
+ memmove(&ents[index + 1], &ents[index],
(highstale - index) * sizeof(xfs_dir2_leaf_entry_t));
}
*lfloglow = MIN(index, *lfloglow);
*lfloghigh = MAX(highstale, *lfloghigh);
- be16_add_cpu(&leaf->hdr.stale, -1);
- return &leaf->ents[index];
+ leafhdr->stale--;
+ return &ents[index];
}
/*
@@ -282,7 +609,7 @@ xfs_dir2_leaf_addname(
__be16 *bestsp; /* freespace table in leaf */
int compact; /* need to compact leaves */
xfs_dir2_data_hdr_t *hdr; /* data block header */
- xfs_dabuf_t *dbp; /* data block buffer */
+ struct xfs_buf *dbp; /* data block buffer */
xfs_dir2_data_entry_t *dep; /* data block entry */
xfs_inode_t *dp; /* incore directory inode */
xfs_dir2_data_unused_t *dup; /* data unused entry */
@@ -291,7 +618,7 @@ xfs_dir2_leaf_addname(
int highstale; /* index of next stale leaf */
int i; /* temporary, index */
int index; /* leaf table position */
- xfs_dabuf_t *lbp; /* leaf's buffer */
+ struct xfs_buf *lbp; /* leaf's buffer */
xfs_dir2_leaf_t *leaf; /* leaf structure */
int length; /* length of new entry */
xfs_dir2_leaf_entry_t *lep; /* leaf entry table pointer */
@@ -306,21 +633,20 @@ xfs_dir2_leaf_addname(
__be16 *tagp; /* end of data entry */
xfs_trans_t *tp; /* transaction pointer */
xfs_dir2_db_t use_block; /* data block number */
+ struct xfs_dir2_data_free *bf; /* bestfree table */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
trace_xfs_dir2_leaf_addname(args);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- /*
- * Read the leaf block.
- */
- error = xfs_da_read_buf(tp, dp, mp->m_dirleafblk, -1, &lbp,
- XFS_DATA_FORK);
- if (error) {
+
+ error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, -1, &lbp);
+ if (error)
return error;
- }
- ASSERT(lbp != NULL);
+
/*
* Look up the entry by hash value and name.
* We know it's not there, our caller has already done a lookup.
@@ -328,22 +654,25 @@ xfs_dir2_leaf_addname(
* But if there are dup hash values the index is of the first of those.
*/
index = xfs_dir2_leaf_search_hash(args, lbp);
- leaf = lbp->data;
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ leaf = lbp->b_addr;
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
bestsp = xfs_dir2_leaf_bests_p(ltp);
- length = xfs_dir2_data_entsize(args->namelen);
+ length = dp->d_ops->data_entsize(args->namelen);
+
/*
* See if there are any entries with the same hash value
* and space in their block for the new entry.
* This is good because it puts multiple same-hash value entries
* in a data block, improving the lookup of those entries.
*/
- for (use_block = -1, lep = &leaf->ents[index];
- index < be16_to_cpu(leaf->hdr.count) && be32_to_cpu(lep->hashval) == args->hashval;
+ for (use_block = -1, lep = &ents[index];
+ index < leafhdr.count && be32_to_cpu(lep->hashval) == args->hashval;
index++, lep++) {
if (be32_to_cpu(lep->address) == XFS_DIR2_NULL_DATAPTR)
continue;
- i = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ i = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
ASSERT(i < be32_to_cpu(ltp->bestcount));
ASSERT(bestsp[i] != cpu_to_be16(NULLDATAOFF));
if (be16_to_cpu(bestsp[i]) >= length) {
@@ -372,7 +701,7 @@ xfs_dir2_leaf_addname(
* How many bytes do we need in the leaf block?
*/
needbytes = 0;
- if (!leaf->hdr.stale)
+ if (!leafhdr.stale)
needbytes += sizeof(xfs_dir2_leaf_entry_t);
if (use_block == -1)
needbytes += sizeof(xfs_dir2_data_off_t);
@@ -387,29 +716,27 @@ xfs_dir2_leaf_addname(
* If we don't have enough free bytes but we can make enough
* by compacting out stale entries, we'll do that.
*/
- if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] <
- needbytes && be16_to_cpu(leaf->hdr.stale) > 1) {
+ if ((char *)bestsp - (char *)&ents[leafhdr.count] < needbytes &&
+ leafhdr.stale > 1)
compact = 1;
- }
+
/*
* Otherwise if we don't have enough free bytes we need to
* convert to node form.
*/
- else if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(
- leaf->hdr.count)] < needbytes) {
+ else if ((char *)bestsp - (char *)&ents[leafhdr.count] < needbytes) {
/*
* Just checking or no space reservation, give up.
*/
if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
args->total == 0) {
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, lbp);
return XFS_ERROR(ENOSPC);
}
/*
* Convert to node form.
*/
error = xfs_dir2_leaf_to_node(args, lbp);
- xfs_da_buf_done(lbp);
if (error)
return error;
/*
@@ -427,7 +754,7 @@ xfs_dir2_leaf_addname(
* a new data block.
*/
if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, lbp);
return use_block == -1 ? XFS_ERROR(ENOSPC) : 0;
}
/*
@@ -435,7 +762,7 @@ xfs_dir2_leaf_addname(
* changed anything.
*/
if (args->total == 0 && use_block == -1) {
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, lbp);
return XFS_ERROR(ENOSPC);
}
/*
@@ -445,15 +772,15 @@ xfs_dir2_leaf_addname(
* point later.
*/
if (compact) {
- xfs_dir2_leaf_compact_x1(lbp, &index, &lowstale, &highstale,
- &lfloglow, &lfloghigh);
+ xfs_dir3_leaf_compact_x1(&leafhdr, ents, &index, &lowstale,
+ &highstale, &lfloglow, &lfloghigh);
}
/*
* There are stale entries, so we'll need log-low and log-high
* impossibly bad values later.
*/
- else if (be16_to_cpu(leaf->hdr.stale)) {
- lfloglow = be16_to_cpu(leaf->hdr.count);
+ else if (leafhdr.stale) {
+ lfloglow = leafhdr.count;
lfloghigh = -1;
}
/*
@@ -466,14 +793,14 @@ xfs_dir2_leaf_addname(
*/
if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE,
&use_block))) {
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, lbp);
return error;
}
/*
* Initialize the block.
*/
- if ((error = xfs_dir2_data_init(args, use_block, &dbp))) {
- xfs_da_brelse(tp, lbp);
+ if ((error = xfs_dir3_data_init(args, use_block, &dbp))) {
+ xfs_trans_brelse(tp, lbp);
return error;
}
/*
@@ -485,44 +812,46 @@ xfs_dir2_leaf_addname(
memmove(&bestsp[0], &bestsp[1],
be32_to_cpu(ltp->bestcount) * sizeof(bestsp[0]));
be32_add_cpu(&ltp->bestcount, 1);
- xfs_dir2_leaf_log_tail(tp, lbp);
- xfs_dir2_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0,
+ be32_to_cpu(ltp->bestcount) - 1);
}
/*
* If we're filling in a previously empty block just log it.
*/
else
- xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block);
- hdr = dbp->data;
- bestsp[use_block] = hdr->bestfree[0].length;
+ xfs_dir3_leaf_log_bests(args, lbp, use_block, use_block);
+ hdr = dbp->b_addr;
+ bf = dp->d_ops->data_bestfree_p(hdr);
+ bestsp[use_block] = bf[0].length;
grown = 1;
- }
- /*
- * Already had space in some data block.
- * Just read that one in.
- */
- else {
- if ((error =
- xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, use_block),
- -1, &dbp, XFS_DATA_FORK))) {
- xfs_da_brelse(tp, lbp);
+ } else {
+ /*
+ * Already had space in some data block.
+ * Just read that one in.
+ */
+ error = xfs_dir3_data_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, use_block),
+ -1, &dbp);
+ if (error) {
+ xfs_trans_brelse(tp, lbp);
return error;
}
- hdr = dbp->data;
+ hdr = dbp->b_addr;
+ bf = dp->d_ops->data_bestfree_p(hdr);
grown = 0;
}
- xfs_dir2_data_check(dp, dbp);
/*
* Point to the biggest freespace in our data block.
*/
dup = (xfs_dir2_data_unused_t *)
- ((char *)hdr + be16_to_cpu(hdr->bestfree[0].offset));
+ ((char *)hdr + be16_to_cpu(bf[0].offset));
ASSERT(be16_to_cpu(dup->length) >= length);
needscan = needlog = 0;
/*
* Mark the initial part of our freespace in use for the new entry.
*/
- xfs_dir2_data_use_free(tp, dbp, dup,
+ xfs_dir2_data_use_free(args, dbp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
&needlog, &needscan);
/*
@@ -532,119 +861,78 @@ xfs_dir2_leaf_addname(
dep->inumber = cpu_to_be64(args->inumber);
dep->namelen = args->namelen;
memcpy(dep->name, args->name, dep->namelen);
- tagp = xfs_dir2_data_entry_tag_p(dep);
+ dp->d_ops->data_put_ftype(dep, args->filetype);
+ tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
/*
* Need to scan fix up the bestfree table.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
/*
* Need to log the data block's header.
*/
if (needlog)
- xfs_dir2_data_log_header(tp, dbp);
- xfs_dir2_data_log_entry(tp, dbp, dep);
+ xfs_dir2_data_log_header(args, dbp);
+ xfs_dir2_data_log_entry(args, dbp, dep);
/*
* If the bests table needs to be changed, do it.
* Log the change unless we've already done that.
*/
- if (be16_to_cpu(bestsp[use_block]) != be16_to_cpu(hdr->bestfree[0].length)) {
- bestsp[use_block] = hdr->bestfree[0].length;
+ if (be16_to_cpu(bestsp[use_block]) != be16_to_cpu(bf[0].length)) {
+ bestsp[use_block] = bf[0].length;
if (!grown)
- xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block);
+ xfs_dir3_leaf_log_bests(args, lbp, use_block, use_block);
}
- lep = xfs_dir2_leaf_find_entry(leaf, index, compact, lowstale,
+ lep = xfs_dir3_leaf_find_entry(&leafhdr, ents, index, compact, lowstale,
highstale, &lfloglow, &lfloghigh);
/*
* Fill in the new leaf entry.
*/
lep->hashval = cpu_to_be32(args->hashval);
- lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp, use_block,
+ lep->address = cpu_to_be32(
+ xfs_dir2_db_off_to_dataptr(args->geo, use_block,
be16_to_cpu(*tagp)));
/*
* Log the leaf fields and give up the buffers.
*/
- xfs_dir2_leaf_log_header(tp, lbp);
- xfs_dir2_leaf_log_ents(tp, lbp, lfloglow, lfloghigh);
- xfs_dir2_leaf_check(dp, lbp);
- xfs_da_buf_done(lbp);
- xfs_dir2_data_check(dp, dbp);
- xfs_da_buf_done(dbp);
+ dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+ xfs_dir3_leaf_log_header(args, lbp);
+ xfs_dir3_leaf_log_ents(args, lbp, lfloglow, lfloghigh);
+ xfs_dir3_leaf_check(dp, lbp);
+ xfs_dir3_data_check(dp, dbp);
return 0;
}
-#ifdef DEBUG
-/*
- * Check the internal consistency of a leaf1 block.
- * Pop an assert if something is wrong.
- */
-STATIC void
-xfs_dir2_leaf_check(
- xfs_inode_t *dp, /* incore directory inode */
- xfs_dabuf_t *bp) /* leaf's buffer */
-{
- int i; /* leaf index */
- xfs_dir2_leaf_t *leaf; /* leaf structure */
- xfs_dir2_leaf_tail_t *ltp; /* leaf tail pointer */
- xfs_mount_t *mp; /* filesystem mount point */
- int stale; /* count of stale leaves */
-
- leaf = bp->data;
- mp = dp->i_mount;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
- /*
- * This value is not restrictive enough.
- * Should factor in the size of the bests table as well.
- * We can deduce a value for that from di_size.
- */
- ASSERT(be16_to_cpu(leaf->hdr.count) <= xfs_dir2_max_leaf_ents(mp));
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
- /*
- * Leaves and bests don't overlap.
- */
- ASSERT((char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] <=
- (char *)xfs_dir2_leaf_bests_p(ltp));
- /*
- * Check hash value order, count stale entries.
- */
- for (i = stale = 0; i < be16_to_cpu(leaf->hdr.count); i++) {
- if (i + 1 < be16_to_cpu(leaf->hdr.count))
- ASSERT(be32_to_cpu(leaf->ents[i].hashval) <=
- be32_to_cpu(leaf->ents[i + 1].hashval));
- if (leaf->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
- stale++;
- }
- ASSERT(be16_to_cpu(leaf->hdr.stale) == stale);
-}
-#endif /* DEBUG */
-
/*
* Compact out any stale entries in the leaf.
* Log the header and changed leaf entries, if any.
*/
void
-xfs_dir2_leaf_compact(
+xfs_dir3_leaf_compact(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *bp) /* leaf buffer */
+ struct xfs_dir3_icleaf_hdr *leafhdr,
+ struct xfs_buf *bp) /* leaf buffer */
{
int from; /* source leaf index */
xfs_dir2_leaf_t *leaf; /* leaf structure */
int loglow; /* first leaf entry to log */
int to; /* target leaf index */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_inode *dp = args->dp;
- leaf = bp->data;
- if (!leaf->hdr.stale) {
+ leaf = bp->b_addr;
+ if (!leafhdr->stale)
return;
- }
+
/*
* Compress out the stale entries in place.
*/
- for (from = to = 0, loglow = -1; from < be16_to_cpu(leaf->hdr.count); from++) {
- if (leaf->ents[from].address ==
- cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
+ ents = dp->d_ops->leaf_ents_p(leaf);
+ for (from = to = 0, loglow = -1; from < leafhdr->count; from++) {
+ if (ents[from].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
continue;
/*
* Only actually copy the entries that are different.
@@ -652,19 +940,21 @@ xfs_dir2_leaf_compact(
if (from > to) {
if (loglow == -1)
loglow = to;
- leaf->ents[to] = leaf->ents[from];
+ ents[to] = ents[from];
}
to++;
}
/*
* Update and log the header, log the leaf entries.
*/
- ASSERT(be16_to_cpu(leaf->hdr.stale) == from - to);
- be16_add_cpu(&leaf->hdr.count, -(be16_to_cpu(leaf->hdr.stale)));
- leaf->hdr.stale = 0;
- xfs_dir2_leaf_log_header(args->trans, bp);
+ ASSERT(leafhdr->stale == from - to);
+ leafhdr->count -= leafhdr->stale;
+ leafhdr->stale = 0;
+
+ dp->d_ops->leaf_hdr_to_disk(leaf, leafhdr);
+ xfs_dir3_leaf_log_header(args, bp);
if (loglow != -1)
- xfs_dir2_leaf_log_ents(args->trans, bp, loglow, to - 1);
+ xfs_dir3_leaf_log_ents(args, bp, loglow, to - 1);
}
/*
@@ -676,8 +966,9 @@ xfs_dir2_leaf_compact(
* and leaf logging indices.
*/
void
-xfs_dir2_leaf_compact_x1(
- xfs_dabuf_t *bp, /* leaf buffer */
+xfs_dir3_leaf_compact_x1(
+ struct xfs_dir3_icleaf_hdr *leafhdr,
+ struct xfs_dir2_leaf_entry *ents,
int *indexp, /* insertion index */
int *lowstalep, /* out: stale entry before us */
int *highstalep, /* out: stale entry after us */
@@ -688,22 +979,20 @@ xfs_dir2_leaf_compact_x1(
int highstale; /* stale entry at/after index */
int index; /* insertion index */
int keepstale; /* source index of kept stale */
- xfs_dir2_leaf_t *leaf; /* leaf structure */
int lowstale; /* stale entry before index */
int newindex=0; /* new insertion index */
int to; /* destination copy index */
- leaf = bp->data;
- ASSERT(be16_to_cpu(leaf->hdr.stale) > 1);
+ ASSERT(leafhdr->stale > 1);
index = *indexp;
- xfs_dir2_leaf_find_stale(leaf, index, &lowstale, &highstale);
+ xfs_dir3_leaf_find_stale(leafhdr, ents, index, &lowstale, &highstale);
/*
* Pick the better of lowstale and highstale.
*/
if (lowstale >= 0 &&
- (highstale == be16_to_cpu(leaf->hdr.count) ||
+ (highstale == leafhdr->count ||
index - lowstale <= highstale - index))
keepstale = lowstale;
else
@@ -712,15 +1001,14 @@ xfs_dir2_leaf_compact_x1(
* Copy the entries in place, removing all the stale entries
* except keepstale.
*/
- for (from = to = 0; from < be16_to_cpu(leaf->hdr.count); from++) {
+ for (from = to = 0; from < leafhdr->count; from++) {
/*
* Notice the new value of index.
*/
if (index == from)
newindex = to;
if (from != keepstale &&
- leaf->ents[from].address ==
- cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) {
+ ents[from].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) {
if (from == to)
*lowlogp = to;
continue;
@@ -734,7 +1022,7 @@ xfs_dir2_leaf_compact_x1(
* Copy only the entries that have moved.
*/
if (from > to)
- leaf->ents[to] = leaf->ents[from];
+ ents[to] = ents[from];
to++;
}
ASSERT(from > to);
@@ -748,8 +1036,8 @@ xfs_dir2_leaf_compact_x1(
/*
* Adjust the leaf header values.
*/
- be16_add_cpu(&leaf->hdr.count, -(from - to));
- leaf->hdr.stale = cpu_to_be16(1);
+ leafhdr->count -= from - to;
+ leafhdr->stale = 1;
/*
* Remember the low/high stale value only in the "right"
* direction.
@@ -757,450 +1045,35 @@ xfs_dir2_leaf_compact_x1(
if (lowstale >= newindex)
lowstale = -1;
else
- highstale = be16_to_cpu(leaf->hdr.count);
- *highlogp = be16_to_cpu(leaf->hdr.count) - 1;
+ highstale = leafhdr->count;
+ *highlogp = leafhdr->count - 1;
*lowstalep = lowstale;
*highstalep = highstale;
}
/*
- * Getdents (readdir) for leaf and node directories.
- * This reads the data blocks only, so is the same for both forms.
- */
-int /* error */
-xfs_dir2_leaf_getdents(
- xfs_inode_t *dp, /* incore directory inode */
- void *dirent,
- size_t bufsize,
- xfs_off_t *offset,
- filldir_t filldir)
-{
- xfs_dabuf_t *bp; /* data block buffer */
- int byteoff; /* offset in current block */
- xfs_dir2_db_t curdb; /* db for current block */
- xfs_dir2_off_t curoff; /* current overall offset */
- xfs_dir2_data_hdr_t *hdr; /* data block header */
- xfs_dir2_data_entry_t *dep; /* data entry */
- xfs_dir2_data_unused_t *dup; /* unused entry */
- int error = 0; /* error return value */
- int i; /* temporary loop index */
- int j; /* temporary loop index */
- int length; /* temporary length value */
- xfs_bmbt_irec_t *map; /* map vector for blocks */
- xfs_extlen_t map_blocks; /* number of fsbs in map */
- xfs_dablk_t map_off; /* last mapped file offset */
- int map_size; /* total entries in *map */
- int map_valid; /* valid entries in *map */
- xfs_mount_t *mp; /* filesystem mount point */
- xfs_dir2_off_t newoff; /* new curoff after new blk */
- int nmap; /* mappings to ask xfs_bmapi */
- char *ptr = NULL; /* pointer to current data */
- int ra_current; /* number of read-ahead blks */
- int ra_index; /* *map index for read-ahead */
- int ra_offset; /* map entry offset for ra */
- int ra_want; /* readahead count wanted */
-
- /*
- * If the offset is at or past the largest allowed value,
- * give up right away.
- */
- if (*offset >= XFS_DIR2_MAX_DATAPTR)
- return 0;
-
- mp = dp->i_mount;
-
- /*
- * Set up to bmap a number of blocks based on the caller's
- * buffer size, the directory block size, and the filesystem
- * block size.
- */
- map_size = howmany(bufsize + mp->m_dirblksize, mp->m_sb.sb_blocksize);
- map = kmem_alloc(map_size * sizeof(*map), KM_SLEEP);
- map_valid = ra_index = ra_offset = ra_current = map_blocks = 0;
- bp = NULL;
-
- /*
- * Inside the loop we keep the main offset value as a byte offset
- * in the directory file.
- */
- curoff = xfs_dir2_dataptr_to_byte(mp, *offset);
-
- /*
- * Force this conversion through db so we truncate the offset
- * down to get the start of the data block.
- */
- map_off = xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, curoff));
- /*
- * Loop over directory entries until we reach the end offset.
- * Get more blocks and readahead as necessary.
- */
- while (curoff < XFS_DIR2_LEAF_OFFSET) {
- /*
- * If we have no buffer, or we're off the end of the
- * current buffer, need to get another one.
- */
- if (!bp || ptr >= (char *)bp->data + mp->m_dirblksize) {
- /*
- * If we have a buffer, we need to release it and
- * take it out of the mapping.
- */
- if (bp) {
- xfs_da_brelse(NULL, bp);
- bp = NULL;
- map_blocks -= mp->m_dirblkfsbs;
- /*
- * Loop to get rid of the extents for the
- * directory block.
- */
- for (i = mp->m_dirblkfsbs; i > 0; ) {
- j = MIN((int)map->br_blockcount, i);
- map->br_blockcount -= j;
- map->br_startblock += j;
- map->br_startoff += j;
- /*
- * If mapping is done, pitch it from
- * the table.
- */
- if (!map->br_blockcount && --map_valid)
- memmove(&map[0], &map[1],
- sizeof(map[0]) *
- map_valid);
- i -= j;
- }
- }
- /*
- * Recalculate the readahead blocks wanted.
- */
- ra_want = howmany(bufsize + mp->m_dirblksize,
- mp->m_sb.sb_blocksize) - 1;
- ASSERT(ra_want >= 0);
-
- /*
- * If we don't have as many as we want, and we haven't
- * run out of data blocks, get some more mappings.
- */
- if (1 + ra_want > map_blocks &&
- map_off <
- xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
- /*
- * Get more bmaps, fill in after the ones
- * we already have in the table.
- */
- nmap = map_size - map_valid;
- error = xfs_bmapi_read(dp, map_off,
- xfs_dir2_byte_to_da(mp,
- XFS_DIR2_LEAF_OFFSET) - map_off,
- &map[map_valid], &nmap, 0);
- /*
- * Don't know if we should ignore this or
- * try to return an error.
- * The trouble with returning errors
- * is that readdir will just stop without
- * actually passing the error through.
- */
- if (error)
- break; /* XXX */
- /*
- * If we got all the mappings we asked for,
- * set the final map offset based on the
- * last bmap value received.
- * Otherwise, we've reached the end.
- */
- if (nmap == map_size - map_valid)
- map_off =
- map[map_valid + nmap - 1].br_startoff +
- map[map_valid + nmap - 1].br_blockcount;
- else
- map_off =
- xfs_dir2_byte_to_da(mp,
- XFS_DIR2_LEAF_OFFSET);
- /*
- * Look for holes in the mapping, and
- * eliminate them. Count up the valid blocks.
- */
- for (i = map_valid; i < map_valid + nmap; ) {
- if (map[i].br_startblock ==
- HOLESTARTBLOCK) {
- nmap--;
- length = map_valid + nmap - i;
- if (length)
- memmove(&map[i],
- &map[i + 1],
- sizeof(map[i]) *
- length);
- } else {
- map_blocks +=
- map[i].br_blockcount;
- i++;
- }
- }
- map_valid += nmap;
- }
- /*
- * No valid mappings, so no more data blocks.
- */
- if (!map_valid) {
- curoff = xfs_dir2_da_to_byte(mp, map_off);
- break;
- }
- /*
- * Read the directory block starting at the first
- * mapping.
- */
- curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
- error = xfs_da_read_buf(NULL, dp, map->br_startoff,
- map->br_blockcount >= mp->m_dirblkfsbs ?
- XFS_FSB_TO_DADDR(mp, map->br_startblock) :
- -1,
- &bp, XFS_DATA_FORK);
- /*
- * Should just skip over the data block instead
- * of giving up.
- */
- if (error)
- break; /* XXX */
- /*
- * Adjust the current amount of read-ahead: we just
- * read a block that was previously ra.
- */
- if (ra_current)
- ra_current -= mp->m_dirblkfsbs;
- /*
- * Do we need more readahead?
- */
- for (ra_index = ra_offset = i = 0;
- ra_want > ra_current && i < map_blocks;
- i += mp->m_dirblkfsbs) {
- ASSERT(ra_index < map_valid);
- /*
- * Read-ahead a contiguous directory block.
- */
- if (i > ra_current &&
- map[ra_index].br_blockcount >=
- mp->m_dirblkfsbs) {
- xfs_buf_readahead(mp->m_ddev_targp,
- XFS_FSB_TO_DADDR(mp,
- map[ra_index].br_startblock +
- ra_offset),
- (int)BTOBB(mp->m_dirblksize));
- ra_current = i;
- }
- /*
- * Read-ahead a non-contiguous directory block.
- * This doesn't use our mapping, but this
- * is a very rare case.
- */
- else if (i > ra_current) {
- (void)xfs_da_reada_buf(NULL, dp,
- map[ra_index].br_startoff +
- ra_offset, XFS_DATA_FORK);
- ra_current = i;
- }
- /*
- * Advance offset through the mapping table.
- */
- for (j = 0; j < mp->m_dirblkfsbs; j++) {
- /*
- * The rest of this extent but not
- * more than a dir block.
- */
- length = MIN(mp->m_dirblkfsbs,
- (int)(map[ra_index].br_blockcount -
- ra_offset));
- j += length;
- ra_offset += length;
- /*
- * Advance to the next mapping if
- * this one is used up.
- */
- if (ra_offset ==
- map[ra_index].br_blockcount) {
- ra_offset = 0;
- ra_index++;
- }
- }
- }
- /*
- * Having done a read, we need to set a new offset.
- */
- newoff = xfs_dir2_db_off_to_byte(mp, curdb, 0);
- /*
- * Start of the current block.
- */
- if (curoff < newoff)
- curoff = newoff;
- /*
- * Make sure we're in the right block.
- */
- else if (curoff > newoff)
- ASSERT(xfs_dir2_byte_to_db(mp, curoff) ==
- curdb);
- hdr = bp->data;
- xfs_dir2_data_check(dp, bp);
- /*
- * Find our position in the block.
- */
- ptr = (char *)(hdr + 1);
- byteoff = xfs_dir2_byte_to_off(mp, curoff);
- /*
- * Skip past the header.
- */
- if (byteoff == 0)
- curoff += (uint)sizeof(*hdr);
- /*
- * Skip past entries until we reach our offset.
- */
- else {
- while ((char *)ptr - (char *)hdr < byteoff) {
- dup = (xfs_dir2_data_unused_t *)ptr;
-
- if (be16_to_cpu(dup->freetag)
- == XFS_DIR2_DATA_FREE_TAG) {
-
- length = be16_to_cpu(dup->length);
- ptr += length;
- continue;
- }
- dep = (xfs_dir2_data_entry_t *)ptr;
- length =
- xfs_dir2_data_entsize(dep->namelen);
- ptr += length;
- }
- /*
- * Now set our real offset.
- */
- curoff =
- xfs_dir2_db_off_to_byte(mp,
- xfs_dir2_byte_to_db(mp, curoff),
- (char *)ptr - (char *)hdr);
- if (ptr >= (char *)hdr + mp->m_dirblksize) {
- continue;
- }
- }
- }
- /*
- * We have a pointer to an entry.
- * Is it a live one?
- */
- dup = (xfs_dir2_data_unused_t *)ptr;
- /*
- * No, it's unused, skip over it.
- */
- if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
- length = be16_to_cpu(dup->length);
- ptr += length;
- curoff += length;
- continue;
- }
-
- dep = (xfs_dir2_data_entry_t *)ptr;
- length = xfs_dir2_data_entsize(dep->namelen);
-
- if (filldir(dirent, (char *)dep->name, dep->namelen,
- xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff,
- be64_to_cpu(dep->inumber), DT_UNKNOWN))
- break;
-
- /*
- * Advance to next entry in the block.
- */
- ptr += length;
- curoff += length;
- /* bufsize may have just been a guess; don't go negative */
- bufsize = bufsize > length ? bufsize - length : 0;
- }
-
- /*
- * All done. Set output offset value to current offset.
- */
- if (curoff > xfs_dir2_dataptr_to_byte(mp, XFS_DIR2_MAX_DATAPTR))
- *offset = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
- else
- *offset = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
- kmem_free(map);
- if (bp)
- xfs_da_brelse(NULL, bp);
- return error;
-}
-
-/*
- * Initialize a new leaf block, leaf1 or leafn magic accepted.
- */
-int
-xfs_dir2_leaf_init(
- xfs_da_args_t *args, /* operation arguments */
- xfs_dir2_db_t bno, /* directory block number */
- xfs_dabuf_t **bpp, /* out: leaf buffer */
- int magic) /* magic number for block */
-{
- xfs_dabuf_t *bp; /* leaf buffer */
- xfs_inode_t *dp; /* incore directory inode */
- int error; /* error return code */
- xfs_dir2_leaf_t *leaf; /* leaf structure */
- xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */
- xfs_mount_t *mp; /* filesystem mount point */
- xfs_trans_t *tp; /* transaction pointer */
-
- dp = args->dp;
- ASSERT(dp != NULL);
- tp = args->trans;
- mp = dp->i_mount;
- ASSERT(bno >= XFS_DIR2_LEAF_FIRSTDB(mp) &&
- bno < XFS_DIR2_FREE_FIRSTDB(mp));
- /*
- * Get the buffer for the block.
- */
- error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, bno), -1, &bp,
- XFS_DATA_FORK);
- if (error) {
- return error;
- }
- ASSERT(bp != NULL);
- leaf = bp->data;
- /*
- * Initialize the header.
- */
- leaf->hdr.info.magic = cpu_to_be16(magic);
- leaf->hdr.info.forw = 0;
- leaf->hdr.info.back = 0;
- leaf->hdr.count = 0;
- leaf->hdr.stale = 0;
- xfs_dir2_leaf_log_header(tp, bp);
- /*
- * If it's a leaf-format directory initialize the tail.
- * In this case our caller has the real bests table to copy into
- * the block.
- */
- if (magic == XFS_DIR2_LEAF1_MAGIC) {
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
- ltp->bestcount = 0;
- xfs_dir2_leaf_log_tail(tp, bp);
- }
- *bpp = bp;
- return 0;
-}
-
-/*
* Log the bests entries indicated from a leaf1 block.
*/
static void
-xfs_dir2_leaf_log_bests(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp, /* leaf buffer */
+xfs_dir3_leaf_log_bests(
+ struct xfs_da_args *args,
+ struct xfs_buf *bp, /* leaf buffer */
int first, /* first entry to log */
int last) /* last entry to log */
{
__be16 *firstb; /* pointer to first entry */
__be16 *lastb; /* pointer to last entry */
- xfs_dir2_leaf_t *leaf; /* leaf structure */
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
- ltp = xfs_dir2_leaf_tail_p(tp->t_mountp, leaf);
+ ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC));
+
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
firstb = xfs_dir2_leaf_bests_p(ltp) + first;
lastb = xfs_dir2_leaf_bests_p(ltp) + last;
- xfs_da_log_buf(tp, bp, (uint)((char *)firstb - (char *)leaf),
+ xfs_trans_log_buf(args->trans, bp,
+ (uint)((char *)firstb - (char *)leaf),
(uint)((char *)lastb - (char *)leaf + sizeof(*lastb) - 1));
}
@@ -1208,22 +1081,27 @@ xfs_dir2_leaf_log_bests(
* Log the leaf entries indicated from a leaf1 or leafn block.
*/
void
-xfs_dir2_leaf_log_ents(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp, /* leaf buffer */
- int first, /* first entry to log */
- int last) /* last entry to log */
+xfs_dir3_leaf_log_ents(
+ struct xfs_da_args *args,
+ struct xfs_buf *bp,
+ int first,
+ int last)
{
xfs_dir2_leaf_entry_t *firstlep; /* pointer to first entry */
xfs_dir2_leaf_entry_t *lastlep; /* pointer to last entry */
- xfs_dir2_leaf_t *leaf; /* leaf structure */
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
+ struct xfs_dir2_leaf_entry *ents;
- leaf = bp->data;
ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
- leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- firstlep = &leaf->ents[first];
- lastlep = &leaf->ents[last];
- xfs_da_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
+
+ ents = args->dp->d_ops->leaf_ents_p(leaf);
+ firstlep = &ents[first];
+ lastlep = &ents[last];
+ xfs_trans_log_buf(args->trans, bp,
+ (uint)((char *)firstlep - (char *)leaf),
(uint)((char *)lastlep - (char *)leaf + sizeof(*lastlep) - 1));
}
@@ -1231,37 +1109,41 @@ xfs_dir2_leaf_log_ents(
* Log the header of the leaf1 or leafn block.
*/
void
-xfs_dir2_leaf_log_header(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp) /* leaf buffer */
+xfs_dir3_leaf_log_header(
+ struct xfs_da_args *args,
+ struct xfs_buf *bp)
{
- xfs_dir2_leaf_t *leaf; /* leaf structure */
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
- leaf = bp->data;
ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
- leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- xfs_da_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
- (uint)(sizeof(leaf->hdr) - 1));
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
+
+ xfs_trans_log_buf(args->trans, bp,
+ (uint)((char *)&leaf->hdr - (char *)leaf),
+ args->dp->d_ops->leaf_hdr_size - 1);
}
/*
* Log the tail of the leaf1 block.
*/
STATIC void
-xfs_dir2_leaf_log_tail(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp) /* leaf buffer */
+xfs_dir3_leaf_log_tail(
+ struct xfs_da_args *args,
+ struct xfs_buf *bp)
{
- xfs_dir2_leaf_t *leaf; /* leaf structure */
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */
- xfs_mount_t *mp; /* filesystem mount point */
- mp = tp->t_mountp;
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
- xfs_da_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf),
- (uint)(mp->m_dirblksize - 1));
+ ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
+ leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
+
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
+ xfs_trans_log_buf(args->trans, bp, (uint)((char *)ltp - (char *)leaf),
+ (uint)(args->geo->blksize - 1));
}
/*
@@ -1273,15 +1155,16 @@ int
xfs_dir2_leaf_lookup(
xfs_da_args_t *args) /* operation arguments */
{
- xfs_dabuf_t *dbp; /* data block buffer */
+ struct xfs_buf *dbp; /* data block buffer */
xfs_dir2_data_entry_t *dep; /* data block entry */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
int index; /* found entry index */
- xfs_dabuf_t *lbp; /* leaf buffer */
+ struct xfs_buf *lbp; /* leaf buffer */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir2_leaf_entry *ents;
trace_xfs_dir2_leaf_lookup(args);
@@ -1293,25 +1176,28 @@ xfs_dir2_leaf_lookup(
}
tp = args->trans;
dp = args->dp;
- xfs_dir2_leaf_check(dp, lbp);
- leaf = lbp->data;
+ xfs_dir3_leaf_check(dp, lbp);
+ leaf = lbp->b_addr;
+ ents = dp->d_ops->leaf_ents_p(leaf);
/*
* Get to the leaf entry and contained data entry address.
*/
- lep = &leaf->ents[index];
+ lep = &ents[index];
+
/*
* Point to the data entry.
*/
dep = (xfs_dir2_data_entry_t *)
- ((char *)dbp->data +
- xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
+ ((char *)dbp->b_addr +
+ xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
/*
* Return the found inode number & CI name if appropriate
*/
args->inumber = be64_to_cpu(dep->inumber);
+ args->filetype = dp->d_ops->data_get_ftype(dep);
error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
- xfs_da_brelse(tp, dbp);
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, dbp);
+ xfs_trans_brelse(tp, lbp);
return XFS_ERROR(error);
}
@@ -1324,17 +1210,17 @@ xfs_dir2_leaf_lookup(
static int /* error */
xfs_dir2_leaf_lookup_int(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t **lbpp, /* out: leaf buffer */
+ struct xfs_buf **lbpp, /* out: leaf buffer */
int *indexp, /* out: index in leaf block */
- xfs_dabuf_t **dbpp) /* out: data buffer */
+ struct xfs_buf **dbpp) /* out: data buffer */
{
xfs_dir2_db_t curdb = -1; /* current data block number */
- xfs_dabuf_t *dbp = NULL; /* data buffer */
+ struct xfs_buf *dbp = NULL; /* data buffer */
xfs_dir2_data_entry_t *dep; /* data entry */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
int index; /* index in leaf block */
- xfs_dabuf_t *lbp; /* leaf buffer */
+ struct xfs_buf *lbp; /* leaf buffer */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_mount_t *mp; /* filesystem mount point */
@@ -1342,20 +1228,23 @@ xfs_dir2_leaf_lookup_int(
xfs_trans_t *tp; /* transaction pointer */
xfs_dir2_db_t cidb = -1; /* case match data block no. */
enum xfs_dacmp cmp; /* name compare result */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- /*
- * Read the leaf block into the buffer.
- */
- error = xfs_da_read_buf(tp, dp, mp->m_dirleafblk, -1, &lbp,
- XFS_DATA_FORK);
+
+ error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, -1, &lbp);
if (error)
return error;
+
*lbpp = lbp;
- leaf = lbp->data;
- xfs_dir2_leaf_check(dp, lbp);
+ leaf = lbp->b_addr;
+ xfs_dir3_leaf_check(dp, lbp);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+
/*
* Look for the first leaf entry with our hash value.
*/
@@ -1364,9 +1253,9 @@ xfs_dir2_leaf_lookup_int(
* Loop over all the entries with the right hash value
* looking to match the name.
*/
- for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) &&
- be32_to_cpu(lep->hashval) == args->hashval;
- lep++, index++) {
+ for (lep = &ents[index];
+ index < leafhdr.count && be32_to_cpu(lep->hashval) == args->hashval;
+ lep++, index++) {
/*
* Skip over stale leaf entries.
*/
@@ -1375,29 +1264,30 @@ xfs_dir2_leaf_lookup_int(
/*
* Get the new data block number.
*/
- newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ newdb = xfs_dir2_dataptr_to_db(args->geo,
+ be32_to_cpu(lep->address));
/*
* If it's not the same as the old data block number,
* need to pitch the old one and read the new one.
*/
if (newdb != curdb) {
if (dbp)
- xfs_da_brelse(tp, dbp);
- error = xfs_da_read_buf(tp, dp,
- xfs_dir2_db_to_da(mp, newdb),
- -1, &dbp, XFS_DATA_FORK);
+ xfs_trans_brelse(tp, dbp);
+ error = xfs_dir3_data_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, newdb),
+ -1, &dbp);
if (error) {
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, lbp);
return error;
}
- xfs_dir2_data_check(dp, dbp);
curdb = newdb;
}
/*
* Point to the data entry.
*/
- dep = (xfs_dir2_data_entry_t *)((char *)dbp->data +
- xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+ dep = (xfs_dir2_data_entry_t *)((char *)dbp->b_addr +
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(lep->address)));
/*
* Compare name and if it's an exact match, return the index
* and buffer. If it's the first case-insensitive match, store
@@ -1424,12 +1314,12 @@ xfs_dir2_leaf_lookup_int(
if (args->cmpresult == XFS_CMP_CASE) {
ASSERT(cidb != -1);
if (cidb != curdb) {
- xfs_da_brelse(tp, dbp);
- error = xfs_da_read_buf(tp, dp,
- xfs_dir2_db_to_da(mp, cidb),
- -1, &dbp, XFS_DATA_FORK);
+ xfs_trans_brelse(tp, dbp);
+ error = xfs_dir3_data_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, cidb),
+ -1, &dbp);
if (error) {
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, lbp);
return error;
}
}
@@ -1441,8 +1331,8 @@ xfs_dir2_leaf_lookup_int(
*/
ASSERT(cidb == -1);
if (dbp)
- xfs_da_brelse(tp, dbp);
- xfs_da_brelse(tp, lbp);
+ xfs_trans_brelse(tp, dbp);
+ xfs_trans_brelse(tp, lbp);
return XFS_ERROR(ENOENT);
}
@@ -1456,13 +1346,13 @@ xfs_dir2_leaf_removename(
__be16 *bestsp; /* leaf block best freespace */
xfs_dir2_data_hdr_t *hdr; /* data block header */
xfs_dir2_db_t db; /* data block number */
- xfs_dabuf_t *dbp; /* data block buffer */
+ struct xfs_buf *dbp; /* data block buffer */
xfs_dir2_data_entry_t *dep; /* data entry structure */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
xfs_dir2_db_t i; /* temporary data block # */
int index; /* index into leaf entries */
- xfs_dabuf_t *lbp; /* leaf buffer */
+ struct xfs_buf *lbp; /* leaf buffer */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */
@@ -1471,6 +1361,9 @@ xfs_dir2_leaf_removename(
int needscan; /* need to rescan data frees */
xfs_dir2_data_off_t oldbest; /* old value of best free */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir2_data_free *bf; /* bestfree table */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
trace_xfs_dir2_leaf_removename(args);
@@ -1483,57 +1376,63 @@ xfs_dir2_leaf_removename(
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- leaf = lbp->data;
- hdr = dbp->data;
- xfs_dir2_data_check(dp, dbp);
+ leaf = lbp->b_addr;
+ hdr = dbp->b_addr;
+ xfs_dir3_data_check(dp, dbp);
+ bf = dp->d_ops->data_bestfree_p(hdr);
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
/*
* Point to the leaf entry, use that to point to the data entry.
*/
- lep = &leaf->ents[index];
- db = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
- dep = (xfs_dir2_data_entry_t *)
- ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+ lep = &ents[index];
+ db = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
+ dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+ xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
needscan = needlog = 0;
- oldbest = be16_to_cpu(hdr->bestfree[0].length);
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ oldbest = be16_to_cpu(bf[0].length);
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
bestsp = xfs_dir2_leaf_bests_p(ltp);
ASSERT(be16_to_cpu(bestsp[db]) == oldbest);
/*
* Mark the former data entry unused.
*/
- xfs_dir2_data_make_free(tp, dbp,
+ xfs_dir2_data_make_free(args, dbp,
(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
- xfs_dir2_data_entsize(dep->namelen), &needlog, &needscan);
+ dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
/*
* We just mark the leaf entry stale by putting a null in it.
*/
- be16_add_cpu(&leaf->hdr.stale, 1);
- xfs_dir2_leaf_log_header(tp, lbp);
+ leafhdr.stale++;
+ dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+ xfs_dir3_leaf_log_header(args, lbp);
+
lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
- xfs_dir2_leaf_log_ents(tp, lbp, index, index);
+ xfs_dir3_leaf_log_ents(args, lbp, index, index);
+
/*
* Scan the freespace in the data block again if necessary,
* log the data block header if necessary.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
/*
* If the longest freespace in the data block has changed,
* put the new value in the bests table and log that.
*/
- if (be16_to_cpu(hdr->bestfree[0].length) != oldbest) {
- bestsp[db] = hdr->bestfree[0].length;
- xfs_dir2_leaf_log_bests(tp, lbp, db, db);
+ if (be16_to_cpu(bf[0].length) != oldbest) {
+ bestsp[db] = bf[0].length;
+ xfs_dir3_leaf_log_bests(args, lbp, db, db);
}
- xfs_dir2_data_check(dp, dbp);
+ xfs_dir3_data_check(dp, dbp);
/*
* If the data block is now empty then get rid of the data block.
*/
- if (be16_to_cpu(hdr->bestfree[0].length) ==
- mp->m_dirblksize - (uint)sizeof(*hdr)) {
- ASSERT(db != mp->m_dirdatablk);
+ if (be16_to_cpu(bf[0].length) ==
+ args->geo->blksize - dp->d_ops->data_entry_offset) {
+ ASSERT(db != args->geo->datablk);
if ((error = xfs_dir2_shrink_inode(args, db, dbp))) {
/*
* Nope, can't get rid of it because it caused
@@ -1541,12 +1440,9 @@ xfs_dir2_leaf_removename(
* Just go on, returning success, leaving the
* empty block in place.
*/
- if (error == ENOSPC && args->total == 0) {
- xfs_da_buf_done(dbp);
+ if (error == ENOSPC && args->total == 0)
error = 0;
- }
- xfs_dir2_leaf_check(dp, lbp);
- xfs_da_buf_done(lbp);
+ xfs_dir3_leaf_check(dp, lbp);
return error;
}
dbp = NULL;
@@ -1569,19 +1465,19 @@ xfs_dir2_leaf_removename(
memmove(&bestsp[db - i], bestsp,
(be32_to_cpu(ltp->bestcount) - (db - i)) * sizeof(*bestsp));
be32_add_cpu(&ltp->bestcount, -(db - i));
- xfs_dir2_leaf_log_tail(tp, lbp);
- xfs_dir2_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0,
+ be32_to_cpu(ltp->bestcount) - 1);
} else
bestsp[db] = cpu_to_be16(NULLDATAOFF);
}
/*
* If the data block was not the first one, drop it.
*/
- else if (db != mp->m_dirdatablk && dbp != NULL) {
- xfs_da_buf_done(dbp);
+ else if (db != args->geo->datablk)
dbp = NULL;
- }
- xfs_dir2_leaf_check(dp, lbp);
+
+ xfs_dir3_leaf_check(dp, lbp);
/*
* See if we can convert to block form.
*/
@@ -1595,15 +1491,16 @@ int /* error */
xfs_dir2_leaf_replace(
xfs_da_args_t *args) /* operation arguments */
{
- xfs_dabuf_t *dbp; /* data block buffer */
+ struct xfs_buf *dbp; /* data block buffer */
xfs_dir2_data_entry_t *dep; /* data block entry */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
int index; /* index of leaf entry */
- xfs_dabuf_t *lbp; /* leaf buffer */
+ struct xfs_buf *lbp; /* leaf buffer */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir2_leaf_entry *ents;
trace_xfs_dir2_leaf_replace(args);
@@ -1614,27 +1511,28 @@ xfs_dir2_leaf_replace(
return error;
}
dp = args->dp;
- leaf = lbp->data;
+ leaf = lbp->b_addr;
+ ents = dp->d_ops->leaf_ents_p(leaf);
/*
* Point to the leaf entry, get data address from it.
*/
- lep = &leaf->ents[index];
+ lep = &ents[index];
/*
* Point to the data entry.
*/
dep = (xfs_dir2_data_entry_t *)
- ((char *)dbp->data +
- xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
+ ((char *)dbp->b_addr +
+ xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
ASSERT(args->inumber != be64_to_cpu(dep->inumber));
/*
* Put the new inode number in, log it.
*/
dep->inumber = cpu_to_be64(args->inumber);
+ dp->d_ops->data_put_ftype(dep, args->filetype);
tp = args->trans;
- xfs_dir2_data_log_entry(tp, dbp, dep);
- xfs_da_buf_done(dbp);
- xfs_dir2_leaf_check(dp, lbp);
- xfs_da_brelse(tp, lbp);
+ xfs_dir2_data_log_entry(args, dbp, dep);
+ xfs_dir3_leaf_check(dp, lbp);
+ xfs_trans_brelse(tp, lbp);
return 0;
}
@@ -1646,7 +1544,7 @@ xfs_dir2_leaf_replace(
int /* index value */
xfs_dir2_leaf_search_hash(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *lbp) /* leaf buffer */
+ struct xfs_buf *lbp) /* leaf buffer */
{
xfs_dahash_t hash=0; /* hash from this entry */
xfs_dahash_t hashwant; /* hash value looking for */
@@ -1655,17 +1553,18 @@ xfs_dir2_leaf_search_hash(
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
int mid=0; /* current leaf index */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
+
+ leaf = lbp->b_addr;
+ ents = args->dp->d_ops->leaf_ents_p(leaf);
+ args->dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
- leaf = lbp->data;
-#ifndef __KERNEL__
- if (!leaf->hdr.count)
- return 0;
-#endif
/*
* Note, the table cannot be empty, so we have to go through the loop.
* Binary search the leaf entries looking for our hash value.
*/
- for (lep = leaf->ents, low = 0, high = be16_to_cpu(leaf->hdr.count) - 1,
+ for (lep = ents, low = 0, high = leafhdr.count - 1,
hashwant = args->hashval;
low <= high; ) {
mid = (low + high) >> 1;
@@ -1699,11 +1598,11 @@ xfs_dir2_leaf_search_hash(
int /* error */
xfs_dir2_leaf_trim_data(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *lbp, /* leaf buffer */
+ struct xfs_buf *lbp, /* leaf buffer */
xfs_dir2_db_t db) /* data block number */
{
__be16 *bestsp; /* leaf bests table */
- xfs_dabuf_t *dbp; /* data block buffer */
+ struct xfs_buf *dbp; /* data block buffer */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return value */
xfs_dir2_leaf_t *leaf; /* leaf structure */
@@ -1717,21 +1616,23 @@ xfs_dir2_leaf_trim_data(
/*
* Read the offending data block. We need its buffer.
*/
- if ((error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, db), -1, &dbp,
- XFS_DATA_FORK))) {
+ error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(args->geo, db),
+ -1, &dbp);
+ if (error)
return error;
- }
- leaf = lbp->data;
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+ leaf = lbp->b_addr;
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
#ifdef DEBUG
{
- struct xfs_dir2_data_hdr *hdr = dbp->data;
+ struct xfs_dir2_data_hdr *hdr = dbp->b_addr;
+ struct xfs_dir2_data_free *bf = dp->d_ops->data_bestfree_p(hdr);
- ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
- ASSERT(be16_to_cpu(hdr->bestfree[0].length) ==
- mp->m_dirblksize - (uint)sizeof(*hdr));
+ ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
+ ASSERT(be16_to_cpu(bf[0].length) ==
+ args->geo->blksize - dp->d_ops->data_entry_offset);
ASSERT(db == be32_to_cpu(ltp->bestcount) - 1);
}
#endif
@@ -1741,7 +1642,7 @@ xfs_dir2_leaf_trim_data(
*/
if ((error = xfs_dir2_shrink_inode(args, db, dbp))) {
ASSERT(error != ENOSPC);
- xfs_da_brelse(tp, dbp);
+ xfs_trans_brelse(tp, dbp);
return error;
}
/*
@@ -1750,23 +1651,29 @@ xfs_dir2_leaf_trim_data(
bestsp = xfs_dir2_leaf_bests_p(ltp);
be32_add_cpu(&ltp->bestcount, -1);
memmove(&bestsp[1], &bestsp[0], be32_to_cpu(ltp->bestcount) * sizeof(*bestsp));
- xfs_dir2_leaf_log_tail(tp, lbp);
- xfs_dir2_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
return 0;
}
static inline size_t
-xfs_dir2_leaf_size(
- struct xfs_dir2_leaf_hdr *hdr,
+xfs_dir3_leaf_size(
+ struct xfs_dir3_icleaf_hdr *hdr,
int counts)
{
- int entries;
+ int entries;
+ int hdrsize;
+
+ entries = hdr->count - hdr->stale;
+ if (hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
+ hdr->magic == XFS_DIR2_LEAFN_MAGIC)
+ hdrsize = sizeof(struct xfs_dir2_leaf_hdr);
+ else
+ hdrsize = sizeof(struct xfs_dir3_leaf_hdr);
- entries = be16_to_cpu(hdr->count) - be16_to_cpu(hdr->stale);
- return sizeof(xfs_dir2_leaf_hdr_t) +
- entries * sizeof(xfs_dir2_leaf_entry_t) +
- counts * sizeof(xfs_dir2_data_off_t) +
- sizeof(xfs_dir2_leaf_tail_t);
+ return hdrsize + entries * sizeof(xfs_dir2_leaf_entry_t)
+ + counts * sizeof(xfs_dir2_data_off_t)
+ + sizeof(xfs_dir2_leaf_tail_t);
}
/*
@@ -1781,15 +1688,17 @@ xfs_dir2_node_to_leaf(
xfs_da_args_t *args; /* operation arguments */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
- xfs_dabuf_t *fbp; /* buffer for freespace block */
+ struct xfs_buf *fbp; /* buffer for freespace block */
xfs_fileoff_t fo; /* freespace file offset */
xfs_dir2_free_t *free; /* freespace structure */
- xfs_dabuf_t *lbp; /* buffer for leaf block */
+ struct xfs_buf *lbp; /* buffer for leaf block */
xfs_dir2_leaf_tail_t *ltp; /* tail of leaf structure */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_mount_t *mp; /* filesystem mount point */
int rval; /* successful free trim? */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_dir3_icfree_hdr freehdr;
/*
* There's more than a leaf level in the btree, so there must
@@ -1807,22 +1716,22 @@ xfs_dir2_node_to_leaf(
/*
* Get the last offset in the file.
*/
- if ((error = xfs_bmap_last_offset(tp, dp, &fo, XFS_DATA_FORK))) {
+ if ((error = xfs_bmap_last_offset(dp, &fo, XFS_DATA_FORK))) {
return error;
}
- fo -= mp->m_dirblkfsbs;
+ fo -= args->geo->fsbcount;
/*
* If there are freespace blocks other than the first one,
* take this opportunity to remove trailing empty freespace blocks
* that may have been left behind during no-space-reservation
* operations.
*/
- while (fo > mp->m_dirfreeblk) {
+ while (fo > args->geo->freeblk) {
if ((error = xfs_dir2_node_trim_free(args, fo, &rval))) {
return error;
}
if (rval)
- fo -= mp->m_dirblkfsbs;
+ fo -= args->geo->fsbcount;
else
return 0;
}
@@ -1835,58 +1744,71 @@ xfs_dir2_node_to_leaf(
/*
* If it's not the single leaf block, give up.
*/
- if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + mp->m_dirblksize)
+ if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + args->geo->blksize)
return 0;
lbp = state->path.blk[0].bp;
- leaf = lbp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
+ leaf = lbp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+
+ ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
+ leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
+
/*
* Read the freespace block.
*/
- if ((error = xfs_da_read_buf(tp, dp, mp->m_dirfreeblk, -1, &fbp,
- XFS_DATA_FORK))) {
+ error = xfs_dir2_free_read(tp, dp, args->geo->freeblk, &fbp);
+ if (error)
return error;
- }
- free = fbp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
- ASSERT(!free->hdr.firstdb);
+ free = fbp->b_addr;
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
+
+ ASSERT(!freehdr.firstdb);
/*
* Now see if the leafn and free data will fit in a leaf1.
* If not, release the buffer and give up.
*/
- if (xfs_dir2_leaf_size(&leaf->hdr, be32_to_cpu(free->hdr.nvalid)) >
- mp->m_dirblksize) {
- xfs_da_brelse(tp, fbp);
+ if (xfs_dir3_leaf_size(&leafhdr, freehdr.nvalid) > args->geo->blksize) {
+ xfs_trans_brelse(tp, fbp);
return 0;
}
/*
* If the leaf has any stale entries in it, compress them out.
- * The compact routine will log the header.
*/
- if (be16_to_cpu(leaf->hdr.stale))
- xfs_dir2_leaf_compact(args, lbp);
- else
- xfs_dir2_leaf_log_header(tp, lbp);
- leaf->hdr.info.magic = cpu_to_be16(XFS_DIR2_LEAF1_MAGIC);
+ if (leafhdr.stale)
+ xfs_dir3_leaf_compact(args, &leafhdr, lbp);
+
+ lbp->b_ops = &xfs_dir3_leaf1_buf_ops;
+ xfs_trans_buf_set_type(tp, lbp, XFS_BLFT_DIR_LEAF1_BUF);
+ leafhdr.magic = (leafhdr.magic == XFS_DIR2_LEAFN_MAGIC)
+ ? XFS_DIR2_LEAF1_MAGIC
+ : XFS_DIR3_LEAF1_MAGIC;
+
/*
* Set up the leaf tail from the freespace block.
*/
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
- ltp->bestcount = free->hdr.nvalid;
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
+ ltp->bestcount = cpu_to_be32(freehdr.nvalid);
+
/*
* Set up the leaf bests table.
*/
- memcpy(xfs_dir2_leaf_bests_p(ltp), free->bests,
- be32_to_cpu(ltp->bestcount) * sizeof(xfs_dir2_data_off_t));
- xfs_dir2_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
- xfs_dir2_leaf_log_tail(tp, lbp);
- xfs_dir2_leaf_check(dp, lbp);
+ memcpy(xfs_dir2_leaf_bests_p(ltp), dp->d_ops->free_bests_p(free),
+ freehdr.nvalid * sizeof(xfs_dir2_data_off_t));
+
+ dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+ xfs_dir3_leaf_log_header(args, lbp);
+ xfs_dir3_leaf_log_bests(args, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+ xfs_dir3_leaf_log_tail(args, lbp);
+ xfs_dir3_leaf_check(dp, lbp);
+
/*
* Get rid of the freespace block.
*/
- error = xfs_dir2_shrink_inode(args, XFS_DIR2_FREE_FIRSTDB(mp), fbp);
+ error = xfs_dir2_shrink_inode(args,
+ xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET),
+ fbp);
if (error) {
/*
* This can't fail here because it can only happen when
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index b0f26780449..da43d304fca 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
@@ -17,62 +18,245 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_log.h"
-#include "xfs_trans.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
+#include "xfs_da_format.h"
#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
-#include "xfs_dir2_format.h"
+#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_trans.h"
+#include "xfs_buf_item.h"
+#include "xfs_cksum.h"
/*
* Function declarations.
*/
-static void xfs_dir2_free_log_header(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_leafn_add(xfs_dabuf_t *bp, xfs_da_args_t *args, int index);
-#ifdef DEBUG
-static void xfs_dir2_leafn_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
-#else
-#define xfs_dir2_leafn_check(dp, bp)
-#endif
-static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, xfs_dabuf_t *bp_s,
- int start_s, xfs_dabuf_t *bp_d, int start_d,
- int count);
+static int xfs_dir2_leafn_add(struct xfs_buf *bp, xfs_da_args_t *args,
+ int index);
static void xfs_dir2_leafn_rebalance(xfs_da_state_t *state,
xfs_da_state_blk_t *blk1,
xfs_da_state_blk_t *blk2);
-static int xfs_dir2_leafn_remove(xfs_da_args_t *args, xfs_dabuf_t *bp,
+static int xfs_dir2_leafn_remove(xfs_da_args_t *args, struct xfs_buf *bp,
int index, xfs_da_state_blk_t *dblk,
int *rval);
static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
xfs_da_state_blk_t *fblk);
/*
+ * Check internal consistency of a leafn block.
+ */
+#ifdef DEBUG
+#define xfs_dir3_leaf_check(dp, bp) \
+do { \
+ if (!xfs_dir3_leafn_check((dp), (bp))) \
+ ASSERT(0); \
+} while (0);
+
+static bool
+xfs_dir3_leafn_check(
+ struct xfs_inode *dp,
+ struct xfs_buf *bp)
+{
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
+ struct xfs_dir3_icleaf_hdr leafhdr;
+
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+
+ if (leafhdr.magic == XFS_DIR3_LEAFN_MAGIC) {
+ struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
+ if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn)
+ return false;
+ } else if (leafhdr.magic != XFS_DIR2_LEAFN_MAGIC)
+ return false;
+
+ return xfs_dir3_leaf_check_int(dp->i_mount, dp, &leafhdr, leaf);
+}
+#else
+#define xfs_dir3_leaf_check(dp, bp)
+#endif
+
+static bool
+xfs_dir3_free_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_dir2_free_hdr *hdr = bp->b_addr;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ if (hdr3->magic != cpu_to_be32(XFS_DIR3_FREE_MAGIC))
+ return false;
+ if (!uuid_equal(&hdr3->uuid, &mp->m_sb.sb_uuid))
+ return false;
+ if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
+ return false;
+ } else {
+ if (hdr->magic != cpu_to_be32(XFS_DIR2_FREE_MAGIC))
+ return false;
+ }
+
+ /* XXX: should bounds check the xfs_dir3_icfree_hdr here */
+
+ return true;
+}
+
+static void
+xfs_dir3_free_read_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !xfs_buf_verify_cksum(bp, XFS_DIR3_FREE_CRC_OFF))
+ xfs_buf_ioerror(bp, EFSBADCRC);
+ else if (!xfs_dir3_free_verify(bp))
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+
+ if (bp->b_error)
+ xfs_verifier_error(bp);
+}
+
+static void
+xfs_dir3_free_write_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_buf_log_item *bip = bp->b_fspriv;
+ struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+
+ if (!xfs_dir3_free_verify(bp)) {
+ xfs_buf_ioerror(bp, EFSCORRUPTED);
+ xfs_verifier_error(bp);
+ return;
+ }
+
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return;
+
+ if (bip)
+ hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
+
+ xfs_buf_update_cksum(bp, XFS_DIR3_FREE_CRC_OFF);
+}
+
+const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
+ .verify_read = xfs_dir3_free_read_verify,
+ .verify_write = xfs_dir3_free_write_verify,
+};
+
+
+static int
+__xfs_dir3_free_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t fbno,
+ xfs_daddr_t mappedbno,
+ struct xfs_buf **bpp)
+{
+ int err;
+
+ err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
+ XFS_DATA_FORK, &xfs_dir3_free_buf_ops);
+
+ /* try read returns without an error or *bpp if it lands in a hole */
+ if (!err && tp && *bpp)
+ xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_FREE_BUF);
+ return err;
+}
+
+int
+xfs_dir2_free_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t fbno,
+ struct xfs_buf **bpp)
+{
+ return __xfs_dir3_free_read(tp, dp, fbno, -1, bpp);
+}
+
+static int
+xfs_dir2_free_try_read(
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ xfs_dablk_t fbno,
+ struct xfs_buf **bpp)
+{
+ return __xfs_dir3_free_read(tp, dp, fbno, -2, bpp);
+}
+
+static int
+xfs_dir3_free_get_buf(
+ xfs_da_args_t *args,
+ xfs_dir2_db_t fbno,
+ struct xfs_buf **bpp)
+{
+ struct xfs_trans *tp = args->trans;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_mount *mp = dp->i_mount;
+ struct xfs_buf *bp;
+ int error;
+ struct xfs_dir3_icfree_hdr hdr;
+
+ error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, fbno),
+ -1, &bp, XFS_DATA_FORK);
+ if (error)
+ return error;
+
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_FREE_BUF);
+ bp->b_ops = &xfs_dir3_free_buf_ops;
+
+ /*
+ * Initialize the new block to be empty, and remember
+ * its first slot as our empty slot.
+ */
+ memset(bp->b_addr, 0, sizeof(struct xfs_dir3_free_hdr));
+ memset(&hdr, 0, sizeof(hdr));
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ struct xfs_dir3_free_hdr *hdr3 = bp->b_addr;
+
+ hdr.magic = XFS_DIR3_FREE_MAGIC;
+
+ hdr3->hdr.blkno = cpu_to_be64(bp->b_bn);
+ hdr3->hdr.owner = cpu_to_be64(dp->i_ino);
+ uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_uuid);
+ } else
+ hdr.magic = XFS_DIR2_FREE_MAGIC;
+ dp->d_ops->free_hdr_to_disk(bp->b_addr, &hdr);
+ *bpp = bp;
+ return 0;
+}
+
+/*
* Log entries from a freespace block.
*/
STATIC void
xfs_dir2_free_log_bests(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp, /* freespace buffer */
+ struct xfs_da_args *args,
+ struct xfs_buf *bp,
int first, /* first entry to log */
int last) /* last entry to log */
{
xfs_dir2_free_t *free; /* freespace structure */
-
- free = bp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
- xfs_da_log_buf(tp, bp,
- (uint)((char *)&free->bests[first] - (char *)free),
- (uint)((char *)&free->bests[last] - (char *)free +
- sizeof(free->bests[0]) - 1));
+ __be16 *bests;
+
+ free = bp->b_addr;
+ bests = args->dp->d_ops->free_bests_p(free);
+ ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
+ free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
+ xfs_trans_log_buf(args->trans, bp,
+ (uint)((char *)&bests[first] - (char *)free),
+ (uint)((char *)&bests[last] - (char *)free +
+ sizeof(bests[0]) - 1));
}
/*
@@ -80,15 +264,18 @@ xfs_dir2_free_log_bests(
*/
static void
xfs_dir2_free_log_header(
- xfs_trans_t *tp, /* transaction pointer */
- xfs_dabuf_t *bp) /* freespace buffer */
+ struct xfs_da_args *args,
+ struct xfs_buf *bp)
{
+#ifdef DEBUG
xfs_dir2_free_t *free; /* freespace structure */
- free = bp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
- xfs_da_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
- (uint)(sizeof(xfs_dir2_free_hdr_t) - 1));
+ free = bp->b_addr;
+ ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
+ free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
+#endif
+ xfs_trans_log_buf(args->trans, bp, 0,
+ args->dp->d_ops->free_hdr_size - 1);
}
/*
@@ -99,11 +286,11 @@ xfs_dir2_free_log_header(
int /* error */
xfs_dir2_leaf_to_node(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *lbp) /* leaf buffer */
+ struct xfs_buf *lbp) /* leaf buffer */
{
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return value */
- xfs_dabuf_t *fbp; /* freespace buffer */
+ struct xfs_buf *fbp; /* freespace buffer */
xfs_dir2_db_t fdb; /* freespace block number */
xfs_dir2_free_t *free; /* freespace structure */
__be16 *from; /* pointer to freespace entry */
@@ -115,6 +302,7 @@ xfs_dir2_leaf_to_node(
xfs_dir2_data_off_t off; /* freespace entry value */
__be16 *to; /* pointer to freespace entry */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir3_icfree_hdr freehdr;
trace_xfs_dir2_leaf_to_node(args);
@@ -127,45 +315,57 @@ xfs_dir2_leaf_to_node(
if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_FREE_SPACE, &fdb))) {
return error;
}
- ASSERT(fdb == XFS_DIR2_FREE_FIRSTDB(mp));
+ ASSERT(fdb == xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET));
/*
* Get the buffer for the new freespace block.
*/
- if ((error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, fdb), -1, &fbp,
- XFS_DATA_FORK))) {
+ error = xfs_dir3_free_get_buf(args, fdb, &fbp);
+ if (error)
return error;
- }
- ASSERT(fbp != NULL);
- free = fbp->data;
- leaf = lbp->data;
- ltp = xfs_dir2_leaf_tail_p(mp, leaf);
- /*
- * Initialize the freespace block header.
- */
- free->hdr.magic = cpu_to_be32(XFS_DIR2_FREE_MAGIC);
- free->hdr.firstdb = 0;
- ASSERT(be32_to_cpu(ltp->bestcount) <= (uint)dp->i_d.di_size / mp->m_dirblksize);
- free->hdr.nvalid = ltp->bestcount;
+
+ free = fbp->b_addr;
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
+ leaf = lbp->b_addr;
+ ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
+ ASSERT(be32_to_cpu(ltp->bestcount) <=
+ (uint)dp->i_d.di_size / args->geo->blksize);
+
/*
* Copy freespace entries from the leaf block to the new block.
* Count active entries.
*/
- for (i = n = 0, from = xfs_dir2_leaf_bests_p(ltp), to = free->bests;
- i < be32_to_cpu(ltp->bestcount); i++, from++, to++) {
+ from = xfs_dir2_leaf_bests_p(ltp);
+ to = dp->d_ops->free_bests_p(free);
+ for (i = n = 0; i < be32_to_cpu(ltp->bestcount); i++, from++, to++) {
if ((off = be16_to_cpu(*from)) != NULLDATAOFF)
n++;
*to = cpu_to_be16(off);
}
- free->hdr.nused = cpu_to_be32(n);
- leaf->hdr.info.magic = cpu_to_be16(XFS_DIR2_LEAFN_MAGIC);
+
+ /*
+ * Now initialize the freespace block header.
+ */
+ freehdr.nused = n;
+ freehdr.nvalid = be32_to_cpu(ltp->bestcount);
+
+ dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
+ xfs_dir2_free_log_bests(args, fbp, 0, freehdr.nvalid - 1);
+ xfs_dir2_free_log_header(args, fbp);
+
/*
- * Log everything.
+ * Converting the leaf to a leafnode is just a matter of changing the
+ * magic number and the ops. Do the change directly to the buffer as
+ * it's less work (and less code) than decoding the header to host
+ * format and back again.
*/
- xfs_dir2_leaf_log_header(tp, lbp);
- xfs_dir2_free_log_header(tp, fbp);
- xfs_dir2_free_log_bests(tp, fbp, 0, be32_to_cpu(free->hdr.nvalid) - 1);
- xfs_da_buf_done(fbp);
- xfs_dir2_leafn_check(dp, lbp);
+ if (leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC))
+ leaf->hdr.info.magic = cpu_to_be16(XFS_DIR2_LEAFN_MAGIC);
+ else
+ leaf->hdr.info.magic = cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
+ lbp->b_ops = &xfs_dir3_leafn_buf_ops;
+ xfs_trans_buf_set_type(tp, lbp, XFS_BLFT_DIR_LEAFN_BUF);
+ xfs_dir3_leaf_log_header(args, lbp);
+ xfs_dir3_leaf_check(dp, lbp);
return 0;
}
@@ -175,7 +375,7 @@ xfs_dir2_leaf_to_node(
*/
static int /* error */
xfs_dir2_leafn_add(
- xfs_dabuf_t *bp, /* leaf buffer */
+ struct xfs_buf *bp, /* leaf buffer */
xfs_da_args_t *args, /* operation arguments */
int index) /* insertion pt for new entry */
{
@@ -189,13 +389,17 @@ xfs_dir2_leafn_add(
int lowstale; /* previous stale entry */
xfs_mount_t *mp; /* filesystem mount point */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_dir2_leaf_entry *ents;
trace_xfs_dir2_leafn_add(args, index);
dp = args->dp;
mp = dp->i_mount;
tp = args->trans;
- leaf = bp->data;
+ leaf = bp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
/*
* Quick check just to make sure we are not going to index
@@ -211,15 +415,15 @@ xfs_dir2_leafn_add(
* a compact.
*/
- if (be16_to_cpu(leaf->hdr.count) == xfs_dir2_max_leaf_ents(mp)) {
- if (!leaf->hdr.stale)
+ if (leafhdr.count == dp->d_ops->leaf_max_ents(args->geo)) {
+ if (!leafhdr.stale)
return XFS_ERROR(ENOSPC);
- compact = be16_to_cpu(leaf->hdr.stale) > 1;
+ compact = leafhdr.stale > 1;
} else
compact = 0;
- ASSERT(index == 0 || be32_to_cpu(leaf->ents[index - 1].hashval) <= args->hashval);
- ASSERT(index == be16_to_cpu(leaf->hdr.count) ||
- be32_to_cpu(leaf->ents[index].hashval) >= args->hashval);
+ ASSERT(index == 0 || be32_to_cpu(ents[index - 1].hashval) <= args->hashval);
+ ASSERT(index == leafhdr.count ||
+ be32_to_cpu(ents[index].hashval) >= args->hashval);
if (args->op_flags & XFS_DA_OP_JUSTCHECK)
return 0;
@@ -228,61 +432,52 @@ xfs_dir2_leafn_add(
* Compact out all but one stale leaf entry. Leaves behind
* the entry closest to index.
*/
- if (compact) {
- xfs_dir2_leaf_compact_x1(bp, &index, &lowstale, &highstale,
- &lfloglow, &lfloghigh);
- }
- /*
- * Set impossible logging indices for this case.
- */
- else if (leaf->hdr.stale) {
- lfloglow = be16_to_cpu(leaf->hdr.count);
+ if (compact)
+ xfs_dir3_leaf_compact_x1(&leafhdr, ents, &index, &lowstale,
+ &highstale, &lfloglow, &lfloghigh);
+ else if (leafhdr.stale) {
+ /*
+ * Set impossible logging indices for this case.
+ */
+ lfloglow = leafhdr.count;
lfloghigh = -1;
}
/*
* Insert the new entry, log everything.
*/
- lep = xfs_dir2_leaf_find_entry(leaf, index, compact, lowstale,
+ lep = xfs_dir3_leaf_find_entry(&leafhdr, ents, index, compact, lowstale,
highstale, &lfloglow, &lfloghigh);
lep->hashval = cpu_to_be32(args->hashval);
- lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp,
+ lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(args->geo,
args->blkno, args->index));
- xfs_dir2_leaf_log_header(tp, bp);
- xfs_dir2_leaf_log_ents(tp, bp, lfloglow, lfloghigh);
- xfs_dir2_leafn_check(dp, bp);
+
+ dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+ xfs_dir3_leaf_log_header(args, bp);
+ xfs_dir3_leaf_log_ents(args, bp, lfloglow, lfloghigh);
+ xfs_dir3_leaf_check(dp, bp);
return 0;
}
#ifdef DEBUG
-/*
- * Check internal consistency of a leafn block.
- */
-void
-xfs_dir2_leafn_check(
- xfs_inode_t *dp, /* incore directory inode */
- xfs_dabuf_t *bp) /* leaf buffer */
+static void
+xfs_dir2_free_hdr_check(
+ struct xfs_inode *dp,
+ struct xfs_buf *bp,
+ xfs_dir2_db_t db)
{
- int i; /* leaf index */
- xfs_dir2_leaf_t *leaf; /* leaf structure */
- xfs_mount_t *mp; /* filesystem mount point */
- int stale; /* count of stale leaves */
+ struct xfs_dir3_icfree_hdr hdr;
- leaf = bp->data;
- mp = dp->i_mount;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- ASSERT(be16_to_cpu(leaf->hdr.count) <= xfs_dir2_max_leaf_ents(mp));
- for (i = stale = 0; i < be16_to_cpu(leaf->hdr.count); i++) {
- if (i + 1 < be16_to_cpu(leaf->hdr.count)) {
- ASSERT(be32_to_cpu(leaf->ents[i].hashval) <=
- be32_to_cpu(leaf->ents[i + 1].hashval));
- }
- if (leaf->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
- stale++;
- }
- ASSERT(be16_to_cpu(leaf->hdr.stale) == stale);
+ dp->d_ops->free_hdr_from_disk(&hdr, bp->b_addr);
+
+ ASSERT((hdr.firstdb %
+ dp->d_ops->free_max_bests(dp->i_mount->m_dir_geo)) == 0);
+ ASSERT(hdr.firstdb <= db);
+ ASSERT(db < hdr.firstdb + hdr.nvalid);
}
+#else
+#define xfs_dir2_free_hdr_check(dp, bp, db)
#endif /* DEBUG */
/*
@@ -291,18 +486,26 @@ xfs_dir2_leafn_check(
*/
xfs_dahash_t /* hash value */
xfs_dir2_leafn_lasthash(
- xfs_dabuf_t *bp, /* leaf buffer */
+ struct xfs_inode *dp,
+ struct xfs_buf *bp, /* leaf buffer */
int *count) /* count of entries in leaf */
{
- xfs_dir2_leaf_t *leaf; /* leaf structure */
+ struct xfs_dir2_leaf *leaf = bp->b_addr;
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
+
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+
+ ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
+ leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
if (count)
- *count = be16_to_cpu(leaf->hdr.count);
- if (!leaf->hdr.count)
+ *count = leafhdr.count;
+ if (!leafhdr.count)
return 0;
- return be32_to_cpu(leaf->ents[be16_to_cpu(leaf->hdr.count) - 1].hashval);
+
+ ents = dp->d_ops->leaf_ents_p(leaf);
+ return be32_to_cpu(ents[leafhdr.count - 1].hashval);
}
/*
@@ -311,12 +514,12 @@ xfs_dir2_leafn_lasthash(
*/
STATIC int
xfs_dir2_leafn_lookup_for_addname(
- xfs_dabuf_t *bp, /* leaf buffer */
+ struct xfs_buf *bp, /* leaf buffer */
xfs_da_args_t *args, /* operation arguments */
int *indexp, /* out: leaf entry index */
xfs_da_state_t *state) /* state to fill in */
{
- xfs_dabuf_t *curbp = NULL; /* current data/free buffer */
+ struct xfs_buf *curbp = NULL; /* current data/free buffer */
xfs_dir2_db_t curdb = -1; /* current data block number */
xfs_dir2_db_t curfdb = -1; /* current free block number */
xfs_inode_t *dp; /* incore directory inode */
@@ -331,16 +534,19 @@ xfs_dir2_leafn_lookup_for_addname(
xfs_dir2_db_t newdb; /* new data block number */
xfs_dir2_db_t newfdb; /* new free block number */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
-#ifdef __KERNEL__
- ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
-#endif
- xfs_dir2_leafn_check(dp, bp);
+ leaf = bp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+
+ xfs_dir3_leaf_check(dp, bp);
+ ASSERT(leafhdr.count > 0);
+
/*
* Look up the hash value in the leaf entries.
*/
@@ -352,16 +558,17 @@ xfs_dir2_leafn_lookup_for_addname(
/* If so, it's a free block buffer, get the block number. */
curbp = state->extrablk.bp;
curfdb = state->extrablk.blkno;
- free = curbp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
+ free = curbp->b_addr;
+ ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
+ free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
}
- length = xfs_dir2_data_entsize(args->namelen);
+ length = dp->d_ops->data_entsize(args->namelen);
/*
* Loop over leaf entries with the right hash value.
*/
- for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) &&
- be32_to_cpu(lep->hashval) == args->hashval;
- lep++, index++) {
+ for (lep = &ents[index];
+ index < leafhdr.count && be32_to_cpu(lep->hashval) == args->hashval;
+ lep++, index++) {
/*
* Skip stale leaf entries.
*/
@@ -370,7 +577,8 @@ xfs_dir2_leafn_lookup_for_addname(
/*
* Pull the data block number from the entry.
*/
- newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ newdb = xfs_dir2_dataptr_to_db(args->geo,
+ be32_to_cpu(lep->address));
/*
* For addname, we're looking for a place to put the new entry.
* We want to use a data block with an entry of equal
@@ -380,12 +588,14 @@ xfs_dir2_leafn_lookup_for_addname(
* in hand, take a look at it.
*/
if (newdb != curdb) {
+ __be16 *bests;
+
curdb = newdb;
/*
* Convert the data block to the free block
* holding its freespace information.
*/
- newfdb = xfs_dir2_db_to_fdb(mp, newdb);
+ newfdb = dp->d_ops->db_to_fdb(args->geo, newdb);
/*
* If it's not the one we have in hand, read it in.
*/
@@ -394,41 +604,35 @@ xfs_dir2_leafn_lookup_for_addname(
* If we had one before, drop it.
*/
if (curbp)
- xfs_da_brelse(tp, curbp);
- /*
- * Read the free block.
- */
- error = xfs_da_read_buf(tp, dp,
- xfs_dir2_db_to_da(mp, newfdb),
- -1, &curbp, XFS_DATA_FORK);
+ xfs_trans_brelse(tp, curbp);
+
+ error = xfs_dir2_free_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo,
+ newfdb),
+ &curbp);
if (error)
return error;
- free = curbp->data;
- ASSERT(be32_to_cpu(free->hdr.magic) ==
- XFS_DIR2_FREE_MAGIC);
- ASSERT((be32_to_cpu(free->hdr.firstdb) %
- xfs_dir2_free_max_bests(mp)) == 0);
- ASSERT(be32_to_cpu(free->hdr.firstdb) <= curdb);
- ASSERT(curdb < be32_to_cpu(free->hdr.firstdb) +
- be32_to_cpu(free->hdr.nvalid));
+ free = curbp->b_addr;
+
+ xfs_dir2_free_hdr_check(dp, curbp, curdb);
}
/*
* Get the index for our entry.
*/
- fi = xfs_dir2_db_to_fdindex(mp, curdb);
+ fi = dp->d_ops->db_to_fdindex(args->geo, curdb);
/*
* If it has room, return it.
*/
- if (unlikely(free->bests[fi] ==
- cpu_to_be16(NULLDATAOFF))) {
+ bests = dp->d_ops->free_bests_p(free);
+ if (unlikely(bests[fi] == cpu_to_be16(NULLDATAOFF))) {
XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
XFS_ERRLEVEL_LOW, mp);
if (curfdb != newfdb)
- xfs_da_brelse(tp, curbp);
+ xfs_trans_brelse(tp, curbp);
return XFS_ERROR(EFSCORRUPTED);
}
curfdb = newfdb;
- if (be16_to_cpu(free->bests[fi]) >= length)
+ if (be16_to_cpu(bests[fi]) >= length)
goto out;
}
}
@@ -442,6 +646,12 @@ out:
state->extrablk.bp = curbp;
state->extrablk.index = fi;
state->extrablk.blkno = curfdb;
+
+ /*
+ * Important: this magic number is not in the buffer - it's for
+ * buffer type information and therefore only the free/data type
+ * matters here, not whether CRCs are enabled or not.
+ */
state->extrablk.magic = XFS_DIR2_FREE_MAGIC;
} else {
state->extravalid = 0;
@@ -459,12 +669,12 @@ out:
*/
STATIC int
xfs_dir2_leafn_lookup_for_entry(
- xfs_dabuf_t *bp, /* leaf buffer */
+ struct xfs_buf *bp, /* leaf buffer */
xfs_da_args_t *args, /* operation arguments */
int *indexp, /* out: leaf entry index */
xfs_da_state_t *state) /* state to fill in */
{
- xfs_dabuf_t *curbp = NULL; /* current data/free buffer */
+ struct xfs_buf *curbp = NULL; /* current data/free buffer */
xfs_dir2_db_t curdb = -1; /* current data block number */
xfs_dir2_data_entry_t *dep; /* data block entry */
xfs_inode_t *dp; /* incore directory inode */
@@ -476,16 +686,19 @@ xfs_dir2_leafn_lookup_for_entry(
xfs_dir2_db_t newdb; /* new data block number */
xfs_trans_t *tp; /* transaction pointer */
enum xfs_dacmp cmp; /* comparison result */
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_dir3_icleaf_hdr leafhdr;
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
-#ifdef __KERNEL__
- ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
-#endif
- xfs_dir2_leafn_check(dp, bp);
+ leaf = bp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+
+ xfs_dir3_leaf_check(dp, bp);
+ ASSERT(leafhdr.count > 0);
+
/*
* Look up the hash value in the leaf entries.
*/
@@ -500,9 +713,9 @@ xfs_dir2_leafn_lookup_for_entry(
/*
* Loop over leaf entries with the right hash value.
*/
- for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) &&
- be32_to_cpu(lep->hashval) == args->hashval;
- lep++, index++) {
+ for (lep = &ents[index];
+ index < leafhdr.count && be32_to_cpu(lep->hashval) == args->hashval;
+ lep++, index++) {
/*
* Skip stale leaf entries.
*/
@@ -511,7 +724,8 @@ xfs_dir2_leafn_lookup_for_entry(
/*
* Pull the data block number from the entry.
*/
- newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ newdb = xfs_dir2_dataptr_to_db(args->geo,
+ be32_to_cpu(lep->address));
/*
* Not adding a new entry, so we really want to find
* the name given to us.
@@ -525,7 +739,7 @@ xfs_dir2_leafn_lookup_for_entry(
*/
if (curbp && (args->cmpresult == XFS_CMP_DIFFERENT ||
curdb != state->extrablk.blkno))
- xfs_da_brelse(tp, curbp);
+ xfs_trans_brelse(tp, curbp);
/*
* If needing the block that is saved with a CI match,
* use it otherwise read in the new data block.
@@ -535,20 +749,22 @@ xfs_dir2_leafn_lookup_for_entry(
ASSERT(state->extravalid);
curbp = state->extrablk.bp;
} else {
- error = xfs_da_read_buf(tp, dp,
- xfs_dir2_db_to_da(mp, newdb),
- -1, &curbp, XFS_DATA_FORK);
+ error = xfs_dir3_data_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo,
+ newdb),
+ -1, &curbp);
if (error)
return error;
}
- xfs_dir2_data_check(dp, curbp);
+ xfs_dir3_data_check(dp, curbp);
curdb = newdb;
}
/*
* Point to the data entry.
*/
- dep = (xfs_dir2_data_entry_t *)((char *)curbp->data +
- xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+ dep = (xfs_dir2_data_entry_t *)((char *)curbp->b_addr +
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(lep->address)));
/*
* Compare the entry and if it's an exact match, return
* EEXIST immediately. If it's the first case-insensitive
@@ -559,22 +775,24 @@ xfs_dir2_leafn_lookup_for_entry(
/* If there is a CI match block, drop it */
if (args->cmpresult != XFS_CMP_DIFFERENT &&
curdb != state->extrablk.blkno)
- xfs_da_brelse(tp, state->extrablk.bp);
+ xfs_trans_brelse(tp, state->extrablk.bp);
args->cmpresult = cmp;
args->inumber = be64_to_cpu(dep->inumber);
+ args->filetype = dp->d_ops->data_get_ftype(dep);
*indexp = index;
state->extravalid = 1;
state->extrablk.bp = curbp;
state->extrablk.blkno = curdb;
state->extrablk.index = (int)((char *)dep -
- (char *)curbp->data);
+ (char *)curbp->b_addr);
state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
+ curbp->b_ops = &xfs_dir3_data_buf_ops;
+ xfs_trans_buf_set_type(tp, curbp, XFS_BLFT_DIR_DATA_BUF);
if (cmp == XFS_CMP_EXACT)
return XFS_ERROR(EEXIST);
}
}
- ASSERT(index == be16_to_cpu(leaf->hdr.count) ||
- (args->op_flags & XFS_DA_OP_OKNOENT));
+ ASSERT(index == leafhdr.count || (args->op_flags & XFS_DA_OP_OKNOENT));
if (curbp) {
if (args->cmpresult == XFS_CMP_DIFFERENT) {
/* Giving back last used data block. */
@@ -583,10 +801,12 @@ xfs_dir2_leafn_lookup_for_entry(
state->extrablk.index = -1;
state->extrablk.blkno = curdb;
state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
+ curbp->b_ops = &xfs_dir3_data_buf_ops;
+ xfs_trans_buf_set_type(tp, curbp, XFS_BLFT_DIR_DATA_BUF);
} else {
/* If the curbp is not the CI match block, drop it */
if (state->extrablk.bp != curbp)
- xfs_da_brelse(tp, curbp);
+ xfs_trans_brelse(tp, curbp);
}
} else {
state->extravalid = 0;
@@ -602,7 +822,7 @@ xfs_dir2_leafn_lookup_for_entry(
*/
int
xfs_dir2_leafn_lookup_int(
- xfs_dabuf_t *bp, /* leaf buffer */
+ struct xfs_buf *bp, /* leaf buffer */
xfs_da_args_t *args, /* operation arguments */
int *indexp, /* out: leaf entry index */
xfs_da_state_t *state) /* state to fill in */
@@ -618,52 +838,49 @@ xfs_dir2_leafn_lookup_int(
* Log entries and headers. Stale entries are preserved.
*/
static void
-xfs_dir2_leafn_moveents(
- xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *bp_s, /* source leaf buffer */
- int start_s, /* source leaf index */
- xfs_dabuf_t *bp_d, /* destination leaf buffer */
- int start_d, /* destination leaf index */
- int count) /* count of leaves to copy */
+xfs_dir3_leafn_moveents(
+ xfs_da_args_t *args, /* operation arguments */
+ struct xfs_buf *bp_s, /* source */
+ struct xfs_dir3_icleaf_hdr *shdr,
+ struct xfs_dir2_leaf_entry *sents,
+ int start_s,/* source leaf index */
+ struct xfs_buf *bp_d, /* destination */
+ struct xfs_dir3_icleaf_hdr *dhdr,
+ struct xfs_dir2_leaf_entry *dents,
+ int start_d,/* destination leaf index */
+ int count) /* count of leaves to copy */
{
- xfs_dir2_leaf_t *leaf_d; /* destination leaf structure */
- xfs_dir2_leaf_t *leaf_s; /* source leaf structure */
- int stale; /* count stale leaves copied */
- xfs_trans_t *tp; /* transaction pointer */
+ int stale; /* count stale leaves copied */
trace_xfs_dir2_leafn_moveents(args, start_s, start_d, count);
/*
* Silently return if nothing to do.
*/
- if (count == 0) {
+ if (count == 0)
return;
- }
- tp = args->trans;
- leaf_s = bp_s->data;
- leaf_d = bp_d->data;
+
/*
* If the destination index is not the end of the current
* destination leaf entries, open up a hole in the destination
* to hold the new entries.
*/
- if (start_d < be16_to_cpu(leaf_d->hdr.count)) {
- memmove(&leaf_d->ents[start_d + count], &leaf_d->ents[start_d],
- (be16_to_cpu(leaf_d->hdr.count) - start_d) *
- sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir2_leaf_log_ents(tp, bp_d, start_d + count,
- count + be16_to_cpu(leaf_d->hdr.count) - 1);
+ if (start_d < dhdr->count) {
+ memmove(&dents[start_d + count], &dents[start_d],
+ (dhdr->count - start_d) * sizeof(xfs_dir2_leaf_entry_t));
+ xfs_dir3_leaf_log_ents(args, bp_d, start_d + count,
+ count + dhdr->count - 1);
}
/*
* If the source has stale leaves, count the ones in the copy range
* so we can update the header correctly.
*/
- if (leaf_s->hdr.stale) {
+ if (shdr->stale) {
int i; /* temp leaf index */
for (i = start_s, stale = 0; i < start_s + count; i++) {
- if (leaf_s->ents[i].address ==
- cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
+ if (sents[i].address ==
+ cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
stale++;
}
} else
@@ -671,29 +888,27 @@ xfs_dir2_leafn_moveents(
/*
* Copy the leaf entries from source to destination.
*/
- memcpy(&leaf_d->ents[start_d], &leaf_s->ents[start_s],
+ memcpy(&dents[start_d], &sents[start_s],
count * sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir2_leaf_log_ents(tp, bp_d, start_d, start_d + count - 1);
+ xfs_dir3_leaf_log_ents(args, bp_d, start_d, start_d + count - 1);
+
/*
* If there are source entries after the ones we copied,
* delete the ones we copied by sliding the next ones down.
*/
- if (start_s + count < be16_to_cpu(leaf_s->hdr.count)) {
- memmove(&leaf_s->ents[start_s], &leaf_s->ents[start_s + count],
+ if (start_s + count < shdr->count) {
+ memmove(&sents[start_s], &sents[start_s + count],
count * sizeof(xfs_dir2_leaf_entry_t));
- xfs_dir2_leaf_log_ents(tp, bp_s, start_s, start_s + count - 1);
+ xfs_dir3_leaf_log_ents(args, bp_s, start_s, start_s + count - 1);
}
+
/*
* Update the headers and log them.
*/
- be16_add_cpu(&leaf_s->hdr.count, -(count));
- be16_add_cpu(&leaf_s->hdr.stale, -(stale));
- be16_add_cpu(&leaf_d->hdr.count, count);
- be16_add_cpu(&leaf_d->hdr.stale, stale);
- xfs_dir2_leaf_log_header(tp, bp_s);
- xfs_dir2_leaf_log_header(tp, bp_d);
- xfs_dir2_leafn_check(args->dp, bp_s);
- xfs_dir2_leafn_check(args->dp, bp_d);
+ shdr->count -= count;
+ shdr->stale -= stale;
+ dhdr->count += count;
+ dhdr->stale += stale;
}
/*
@@ -702,21 +917,26 @@ xfs_dir2_leafn_moveents(
*/
int /* sort order */
xfs_dir2_leafn_order(
- xfs_dabuf_t *leaf1_bp, /* leaf1 buffer */
- xfs_dabuf_t *leaf2_bp) /* leaf2 buffer */
+ struct xfs_inode *dp,
+ struct xfs_buf *leaf1_bp, /* leaf1 buffer */
+ struct xfs_buf *leaf2_bp) /* leaf2 buffer */
{
- xfs_dir2_leaf_t *leaf1; /* leaf1 structure */
- xfs_dir2_leaf_t *leaf2; /* leaf2 structure */
-
- leaf1 = leaf1_bp->data;
- leaf2 = leaf2_bp->data;
- ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- if (be16_to_cpu(leaf1->hdr.count) > 0 &&
- be16_to_cpu(leaf2->hdr.count) > 0 &&
- (be32_to_cpu(leaf2->ents[0].hashval) < be32_to_cpu(leaf1->ents[0].hashval) ||
- be32_to_cpu(leaf2->ents[be16_to_cpu(leaf2->hdr.count) - 1].hashval) <
- be32_to_cpu(leaf1->ents[be16_to_cpu(leaf1->hdr.count) - 1].hashval)))
+ struct xfs_dir2_leaf *leaf1 = leaf1_bp->b_addr;
+ struct xfs_dir2_leaf *leaf2 = leaf2_bp->b_addr;
+ struct xfs_dir2_leaf_entry *ents1;
+ struct xfs_dir2_leaf_entry *ents2;
+ struct xfs_dir3_icleaf_hdr hdr1;
+ struct xfs_dir3_icleaf_hdr hdr2;
+
+ dp->d_ops->leaf_hdr_from_disk(&hdr1, leaf1);
+ dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf2);
+ ents1 = dp->d_ops->leaf_ents_p(leaf1);
+ ents2 = dp->d_ops->leaf_ents_p(leaf2);
+
+ if (hdr1.count > 0 && hdr2.count > 0 &&
+ (be32_to_cpu(ents2[0].hashval) < be32_to_cpu(ents1[0].hashval) ||
+ be32_to_cpu(ents2[hdr2.count - 1].hashval) <
+ be32_to_cpu(ents1[hdr1.count - 1].hashval)))
return 1;
return 0;
}
@@ -740,30 +960,41 @@ xfs_dir2_leafn_rebalance(
xfs_dir2_leaf_t *leaf1; /* first leaf structure */
xfs_dir2_leaf_t *leaf2; /* second leaf structure */
int mid; /* midpoint leaf index */
-#ifdef DEBUG
+#if defined(DEBUG) || defined(XFS_WARN)
int oldstale; /* old count of stale leaves */
#endif
int oldsum; /* old total leaf count */
int swap; /* swapped leaf blocks */
+ struct xfs_dir2_leaf_entry *ents1;
+ struct xfs_dir2_leaf_entry *ents2;
+ struct xfs_dir3_icleaf_hdr hdr1;
+ struct xfs_dir3_icleaf_hdr hdr2;
+ struct xfs_inode *dp = state->args->dp;
args = state->args;
/*
* If the block order is wrong, swap the arguments.
*/
- if ((swap = xfs_dir2_leafn_order(blk1->bp, blk2->bp))) {
+ if ((swap = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp))) {
xfs_da_state_blk_t *tmp; /* temp for block swap */
tmp = blk1;
blk1 = blk2;
blk2 = tmp;
}
- leaf1 = blk1->bp->data;
- leaf2 = blk2->bp->data;
- oldsum = be16_to_cpu(leaf1->hdr.count) + be16_to_cpu(leaf2->hdr.count);
-#ifdef DEBUG
- oldstale = be16_to_cpu(leaf1->hdr.stale) + be16_to_cpu(leaf2->hdr.stale);
+ leaf1 = blk1->bp->b_addr;
+ leaf2 = blk2->bp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&hdr1, leaf1);
+ dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf2);
+ ents1 = dp->d_ops->leaf_ents_p(leaf1);
+ ents2 = dp->d_ops->leaf_ents_p(leaf2);
+
+ oldsum = hdr1.count + hdr2.count;
+#if defined(DEBUG) || defined(XFS_WARN)
+ oldstale = hdr1.stale + hdr2.stale;
#endif
mid = oldsum >> 1;
+
/*
* If the old leaf count was odd then the new one will be even,
* so we need to divide the new count evenly.
@@ -771,10 +1002,10 @@ xfs_dir2_leafn_rebalance(
if (oldsum & 1) {
xfs_dahash_t midhash; /* middle entry hash value */
- if (mid >= be16_to_cpu(leaf1->hdr.count))
- midhash = be32_to_cpu(leaf2->ents[mid - be16_to_cpu(leaf1->hdr.count)].hashval);
+ if (mid >= hdr1.count)
+ midhash = be32_to_cpu(ents2[mid - hdr1.count].hashval);
else
- midhash = be32_to_cpu(leaf1->ents[mid].hashval);
+ midhash = be32_to_cpu(ents1[mid].hashval);
isleft = args->hashval <= midhash;
}
/*
@@ -788,44 +1019,135 @@ xfs_dir2_leafn_rebalance(
* Calculate moved entry count. Positive means left-to-right,
* negative means right-to-left. Then move the entries.
*/
- count = be16_to_cpu(leaf1->hdr.count) - mid + (isleft == 0);
+ count = hdr1.count - mid + (isleft == 0);
if (count > 0)
- xfs_dir2_leafn_moveents(args, blk1->bp,
- be16_to_cpu(leaf1->hdr.count) - count, blk2->bp, 0, count);
+ xfs_dir3_leafn_moveents(args, blk1->bp, &hdr1, ents1,
+ hdr1.count - count, blk2->bp,
+ &hdr2, ents2, 0, count);
else if (count < 0)
- xfs_dir2_leafn_moveents(args, blk2->bp, 0, blk1->bp,
- be16_to_cpu(leaf1->hdr.count), count);
- ASSERT(be16_to_cpu(leaf1->hdr.count) + be16_to_cpu(leaf2->hdr.count) == oldsum);
- ASSERT(be16_to_cpu(leaf1->hdr.stale) + be16_to_cpu(leaf2->hdr.stale) == oldstale);
+ xfs_dir3_leafn_moveents(args, blk2->bp, &hdr2, ents2, 0,
+ blk1->bp, &hdr1, ents1,
+ hdr1.count, count);
+
+ ASSERT(hdr1.count + hdr2.count == oldsum);
+ ASSERT(hdr1.stale + hdr2.stale == oldstale);
+
+ /* log the changes made when moving the entries */
+ dp->d_ops->leaf_hdr_to_disk(leaf1, &hdr1);
+ dp->d_ops->leaf_hdr_to_disk(leaf2, &hdr2);
+ xfs_dir3_leaf_log_header(args, blk1->bp);
+ xfs_dir3_leaf_log_header(args, blk2->bp);
+
+ xfs_dir3_leaf_check(dp, blk1->bp);
+ xfs_dir3_leaf_check(dp, blk2->bp);
+
/*
* Mark whether we're inserting into the old or new leaf.
*/
- if (be16_to_cpu(leaf1->hdr.count) < be16_to_cpu(leaf2->hdr.count))
+ if (hdr1.count < hdr2.count)
state->inleaf = swap;
- else if (be16_to_cpu(leaf1->hdr.count) > be16_to_cpu(leaf2->hdr.count))
+ else if (hdr1.count > hdr2.count)
state->inleaf = !swap;
else
- state->inleaf =
- swap ^ (blk1->index <= be16_to_cpu(leaf1->hdr.count));
+ state->inleaf = swap ^ (blk1->index <= hdr1.count);
/*
* Adjust the expected index for insertion.
*/
if (!state->inleaf)
- blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count);
+ blk2->index = blk1->index - hdr1.count;
/*
* Finally sanity check just to make sure we are not returning a
* negative index
*/
- if(blk2->index < 0) {
+ if (blk2->index < 0) {
state->inleaf = 1;
blk2->index = 0;
- xfs_alert(args->dp->i_mount,
- "%s: picked the wrong leaf? reverting original leaf: blk1->index %d\n",
+ xfs_alert(dp->i_mount,
+ "%s: picked the wrong leaf? reverting original leaf: blk1->index %d",
__func__, blk1->index);
}
}
+static int
+xfs_dir3_data_block_free(
+ xfs_da_args_t *args,
+ struct xfs_dir2_data_hdr *hdr,
+ struct xfs_dir2_free *free,
+ xfs_dir2_db_t fdb,
+ int findex,
+ struct xfs_buf *fbp,
+ int longest)
+{
+ int logfree = 0;
+ __be16 *bests;
+ struct xfs_dir3_icfree_hdr freehdr;
+ struct xfs_inode *dp = args->dp;
+
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
+ bests = dp->d_ops->free_bests_p(free);
+ if (hdr) {
+ /*
+ * Data block is not empty, just set the free entry to the new
+ * value.
+ */
+ bests[findex] = cpu_to_be16(longest);
+ xfs_dir2_free_log_bests(args, fbp, findex, findex);
+ return 0;
+ }
+
+ /* One less used entry in the free table. */
+ freehdr.nused--;
+
+ /*
+ * If this was the last entry in the table, we can trim the table size
+ * back. There might be other entries at the end referring to
+ * non-existent data blocks, get those too.
+ */
+ if (findex == freehdr.nvalid - 1) {
+ int i; /* free entry index */
+
+ for (i = findex - 1; i >= 0; i--) {
+ if (bests[i] != cpu_to_be16(NULLDATAOFF))
+ break;
+ }
+ freehdr.nvalid = i + 1;
+ logfree = 0;
+ } else {
+ /* Not the last entry, just punch it out. */
+ bests[findex] = cpu_to_be16(NULLDATAOFF);
+ logfree = 1;
+ }
+
+ dp->d_ops->free_hdr_to_disk(free, &freehdr);
+ xfs_dir2_free_log_header(args, fbp);
+
+ /*
+ * If there are no useful entries left in the block, get rid of the
+ * block if we can.
+ */
+ if (!freehdr.nused) {
+ int error;
+
+ error = xfs_dir2_shrink_inode(args, fdb, fbp);
+ if (error == 0) {
+ fbp = NULL;
+ logfree = 0;
+ } else if (error != ENOSPC || args->total != 0)
+ return error;
+ /*
+ * It's possible to get ENOSPC if there is no
+ * space reservation. In this case some one
+ * else will eventually get rid of this block.
+ */
+ }
+
+ /* Log the free entry that changed, unless we got rid of it. */
+ if (logfree)
+ xfs_dir2_free_log_bests(args, fbp, findex, findex);
+ return 0;
+}
+
/*
* Remove an entry from a node directory.
* This removes the leaf entry and the data entry,
@@ -834,14 +1156,14 @@ xfs_dir2_leafn_rebalance(
static int /* error */
xfs_dir2_leafn_remove(
xfs_da_args_t *args, /* operation arguments */
- xfs_dabuf_t *bp, /* leaf buffer */
+ struct xfs_buf *bp, /* leaf buffer */
int index, /* leaf entry index */
xfs_da_state_blk_t *dblk, /* data block */
int *rval) /* resulting block needs join */
{
xfs_dir2_data_hdr_t *hdr; /* data block header */
xfs_dir2_db_t db; /* data block number */
- xfs_dabuf_t *dbp; /* data block buffer */
+ struct xfs_buf *dbp; /* data block buffer */
xfs_dir2_data_entry_t *dep; /* data block entry */
xfs_inode_t *dp; /* incore directory inode */
xfs_dir2_leaf_t *leaf; /* leaf structure */
@@ -852,89 +1174,106 @@ xfs_dir2_leafn_remove(
int needlog; /* need to log data header */
int needscan; /* need to rescan data frees */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir2_data_free *bf; /* bestfree table */
+ struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_dir2_leaf_entry *ents;
trace_xfs_dir2_leafn_remove(args, index);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
+ leaf = bp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+
/*
* Point to the entry we're removing.
*/
- lep = &leaf->ents[index];
+ lep = &ents[index];
+
/*
* Extract the data block and offset from the entry.
*/
- db = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+ db = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
ASSERT(dblk->blkno == db);
- off = xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address));
+ off = xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address));
ASSERT(dblk->index == off);
+
/*
* Kill the leaf entry by marking it stale.
* Log the leaf block changes.
*/
- be16_add_cpu(&leaf->hdr.stale, 1);
- xfs_dir2_leaf_log_header(tp, bp);
+ leafhdr.stale++;
+ dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
+ xfs_dir3_leaf_log_header(args, bp);
+
lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
- xfs_dir2_leaf_log_ents(tp, bp, index, index);
+ xfs_dir3_leaf_log_ents(args, bp, index, index);
+
/*
* Make the data entry free. Keep track of the longest freespace
* in the data block in case it changes.
*/
dbp = dblk->bp;
- hdr = dbp->data;
+ hdr = dbp->b_addr;
dep = (xfs_dir2_data_entry_t *)((char *)hdr + off);
- longest = be16_to_cpu(hdr->bestfree[0].length);
+ bf = dp->d_ops->data_bestfree_p(hdr);
+ longest = be16_to_cpu(bf[0].length);
needlog = needscan = 0;
- xfs_dir2_data_make_free(tp, dbp, off,
- xfs_dir2_data_entsize(dep->namelen), &needlog, &needscan);
+ xfs_dir2_data_make_free(args, dbp, off,
+ dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
/*
* Rescan the data block freespaces for bestfree.
* Log the data block header if needed.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
if (needlog)
- xfs_dir2_data_log_header(tp, dbp);
- xfs_dir2_data_check(dp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
+ xfs_dir3_data_check(dp, dbp);
/*
* If the longest data block freespace changes, need to update
* the corresponding freeblock entry.
*/
- if (longest < be16_to_cpu(hdr->bestfree[0].length)) {
+ if (longest < be16_to_cpu(bf[0].length)) {
int error; /* error return value */
- xfs_dabuf_t *fbp; /* freeblock buffer */
+ struct xfs_buf *fbp; /* freeblock buffer */
xfs_dir2_db_t fdb; /* freeblock block number */
int findex; /* index in freeblock entries */
xfs_dir2_free_t *free; /* freeblock structure */
- int logfree; /* need to log free entry */
/*
* Convert the data block number to a free block,
* read in the free block.
*/
- fdb = xfs_dir2_db_to_fdb(mp, db);
- if ((error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, fdb),
- -1, &fbp, XFS_DATA_FORK))) {
+ fdb = dp->d_ops->db_to_fdb(args->geo, db);
+ error = xfs_dir2_free_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, fdb),
+ &fbp);
+ if (error)
return error;
- }
- free = fbp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
- ASSERT(be32_to_cpu(free->hdr.firstdb) ==
- xfs_dir2_free_max_bests(mp) *
- (fdb - XFS_DIR2_FREE_FIRSTDB(mp)));
+ free = fbp->b_addr;
+#ifdef DEBUG
+ {
+ struct xfs_dir3_icfree_hdr freehdr;
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
+ ASSERT(freehdr.firstdb == dp->d_ops->free_max_bests(args->geo) *
+ (fdb - xfs_dir2_byte_to_db(args->geo,
+ XFS_DIR2_FREE_OFFSET)));
+ }
+#endif
/*
* Calculate which entry we need to fix.
*/
- findex = xfs_dir2_db_to_fdindex(mp, db);
- longest = be16_to_cpu(hdr->bestfree[0].length);
+ findex = dp->d_ops->db_to_fdindex(args->geo, db);
+ longest = be16_to_cpu(bf[0].length);
/*
* If the data block is now empty we can get rid of it
* (usually).
*/
- if (longest == mp->m_dirblksize - (uint)sizeof(*hdr)) {
+ if (longest == args->geo->blksize -
+ dp->d_ops->data_entry_offset) {
/*
* Try to punch out the data block.
*/
@@ -948,92 +1287,27 @@ xfs_dir2_leafn_remove(
* In this case just drop the buffer and some one else
* will eventually get rid of the empty block.
*/
- else if (error == ENOSPC && args->total == 0)
- xfs_da_buf_done(dbp);
- else
+ else if (!(error == ENOSPC && args->total == 0))
return error;
}
/*
* If we got rid of the data block, we can eliminate that entry
* in the free block.
*/
- if (hdr == NULL) {
- /*
- * One less used entry in the free table.
- */
- be32_add_cpu(&free->hdr.nused, -1);
- xfs_dir2_free_log_header(tp, fbp);
- /*
- * If this was the last entry in the table, we can
- * trim the table size back. There might be other
- * entries at the end referring to non-existent
- * data blocks, get those too.
- */
- if (findex == be32_to_cpu(free->hdr.nvalid) - 1) {
- int i; /* free entry index */
-
- for (i = findex - 1;
- i >= 0 &&
- free->bests[i] == cpu_to_be16(NULLDATAOFF);
- i--)
- continue;
- free->hdr.nvalid = cpu_to_be32(i + 1);
- logfree = 0;
- }
- /*
- * Not the last entry, just punch it out.
- */
- else {
- free->bests[findex] = cpu_to_be16(NULLDATAOFF);
- logfree = 1;
- }
- /*
- * If there are no useful entries left in the block,
- * get rid of the block if we can.
- */
- if (!free->hdr.nused) {
- error = xfs_dir2_shrink_inode(args, fdb, fbp);
- if (error == 0) {
- fbp = NULL;
- logfree = 0;
- } else if (error != ENOSPC || args->total != 0)
- return error;
- /*
- * It's possible to get ENOSPC if there is no
- * space reservation. In this case some one
- * else will eventually get rid of this block.
- */
- }
- }
- /*
- * Data block is not empty, just set the free entry to
- * the new value.
- */
- else {
- free->bests[findex] = cpu_to_be16(longest);
- logfree = 1;
- }
- /*
- * Log the free entry that changed, unless we got rid of it.
- */
- if (logfree)
- xfs_dir2_free_log_bests(tp, fbp, findex, findex);
- /*
- * Drop the buffer if we still have it.
- */
- if (fbp)
- xfs_da_buf_done(fbp);
+ error = xfs_dir3_data_block_free(args, hdr, free,
+ fdb, findex, fbp, longest);
+ if (error)
+ return error;
}
- xfs_dir2_leafn_check(dp, bp);
+
+ xfs_dir3_leaf_check(dp, bp);
/*
* Return indication of whether this leaf block is empty enough
* to justify trying to join it with a neighbor.
*/
- *rval =
- ((uint)sizeof(leaf->hdr) +
- (uint)sizeof(leaf->ents[0]) *
- (be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale))) <
- mp->m_dir_magicpct;
+ *rval = (dp->d_ops->leaf_hdr_size +
+ (uint)sizeof(ents[0]) * (leafhdr.count - leafhdr.stale)) <
+ args->geo->magicpct;
return 0;
}
@@ -1050,13 +1324,14 @@ xfs_dir2_leafn_split(
xfs_dablk_t blkno; /* new leaf block number */
int error; /* error return value */
xfs_mount_t *mp; /* filesystem mount point */
+ struct xfs_inode *dp;
/*
* Allocate space for a new leaf node.
*/
args = state->args;
- mp = args->dp->i_mount;
- ASSERT(args != NULL);
+ dp = args->dp;
+ mp = dp->i_mount;
ASSERT(oldblk->magic == XFS_DIR2_LEAFN_MAGIC);
error = xfs_da_grow_inode(args, &blkno);
if (error) {
@@ -1065,11 +1340,11 @@ xfs_dir2_leafn_split(
/*
* Initialize the new leaf block.
*/
- error = xfs_dir2_leaf_init(args, xfs_dir2_da_to_db(mp, blkno),
- &newblk->bp, XFS_DIR2_LEAFN_MAGIC);
- if (error) {
+ error = xfs_dir3_leaf_get_buf(args, xfs_dir2_da_to_db(args->geo, blkno),
+ &newblk->bp, XFS_DIR2_LEAFN_MAGIC);
+ if (error)
return error;
- }
+
newblk->blkno = blkno;
newblk->magic = XFS_DIR2_LEAFN_MAGIC;
/*
@@ -1077,7 +1352,7 @@ xfs_dir2_leafn_split(
* block into the leaves.
*/
xfs_dir2_leafn_rebalance(state, oldblk, newblk);
- error = xfs_da_blk_link(state, oldblk, newblk);
+ error = xfs_da3_blk_link(state, oldblk, newblk);
if (error) {
return error;
}
@@ -1091,10 +1366,10 @@ xfs_dir2_leafn_split(
/*
* Update last hashval in each block since we added the name.
*/
- oldblk->hashval = xfs_dir2_leafn_lasthash(oldblk->bp, NULL);
- newblk->hashval = xfs_dir2_leafn_lasthash(newblk->bp, NULL);
- xfs_dir2_leafn_check(args->dp, oldblk->bp);
- xfs_dir2_leafn_check(args->dp, newblk->bp);
+ oldblk->hashval = xfs_dir2_leafn_lasthash(dp, oldblk->bp, NULL);
+ newblk->hashval = xfs_dir2_leafn_lasthash(dp, newblk->bp, NULL);
+ xfs_dir3_leaf_check(dp, oldblk->bp);
+ xfs_dir3_leaf_check(dp, newblk->bp);
return error;
}
@@ -1114,15 +1389,17 @@ xfs_dir2_leafn_toosmall(
{
xfs_da_state_blk_t *blk; /* leaf block */
xfs_dablk_t blkno; /* leaf block number */
- xfs_dabuf_t *bp; /* leaf buffer */
+ struct xfs_buf *bp; /* leaf buffer */
int bytes; /* bytes in use */
int count; /* leaf live entry count */
int error; /* error return value */
int forward; /* sibling block direction */
int i; /* sibling counter */
- xfs_da_blkinfo_t *info; /* leaf block header */
xfs_dir2_leaf_t *leaf; /* leaf structure */
int rval; /* result from path_shift */
+ struct xfs_dir3_icleaf_hdr leafhdr;
+ struct xfs_dir2_leaf_entry *ents;
+ struct xfs_inode *dp = state->args->dp;
/*
* Check for the degenerate case of the block being over 50% full.
@@ -1130,12 +1407,14 @@ xfs_dir2_leafn_toosmall(
* to coalesce with a sibling.
*/
blk = &state->path.blk[state->path.active - 1];
- info = blk->bp->data;
- ASSERT(info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- leaf = (xfs_dir2_leaf_t *)info;
- count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
- bytes = (uint)sizeof(leaf->hdr) + count * (uint)sizeof(leaf->ents[0]);
- if (bytes > (state->blocksize >> 1)) {
+ leaf = blk->bp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+ xfs_dir3_leaf_check(dp, blk->bp);
+
+ count = leafhdr.count - leafhdr.stale;
+ bytes = dp->d_ops->leaf_hdr_size + count * sizeof(ents[0]);
+ if (bytes > (state->args->geo->blksize >> 1)) {
/*
* Blk over 50%, don't try to join.
*/
@@ -1153,9 +1432,9 @@ xfs_dir2_leafn_toosmall(
* Make altpath point to the block we want to keep and
* path point to the block we want to drop (this one).
*/
- forward = (info->forw != 0);
+ forward = (leafhdr.forw != 0);
memcpy(&state->altpath, &state->path, sizeof(state->path));
- error = xfs_da_path_shift(state, &state->altpath, forward, 0,
+ error = xfs_da3_path_shift(state, &state->altpath, forward, 0,
&rval);
if (error)
return error;
@@ -1169,36 +1448,40 @@ xfs_dir2_leafn_toosmall(
* We prefer coalescing with the lower numbered sibling so as
* to shrink a directory over time.
*/
- forward = be32_to_cpu(info->forw) < be32_to_cpu(info->back);
+ forward = leafhdr.forw < leafhdr.back;
for (i = 0, bp = NULL; i < 2; forward = !forward, i++) {
- blkno = forward ? be32_to_cpu(info->forw) : be32_to_cpu(info->back);
+ struct xfs_dir3_icleaf_hdr hdr2;
+
+ blkno = forward ? leafhdr.forw : leafhdr.back;
if (blkno == 0)
continue;
/*
* Read the sibling leaf block.
*/
- if ((error =
- xfs_da_read_buf(state->args->trans, state->args->dp, blkno,
- -1, &bp, XFS_DATA_FORK))) {
+ error = xfs_dir3_leafn_read(state->args->trans, dp,
+ blkno, -1, &bp);
+ if (error)
return error;
- }
- ASSERT(bp != NULL);
+
/*
* Count bytes in the two blocks combined.
*/
- leaf = (xfs_dir2_leaf_t *)info;
- count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
- bytes = state->blocksize - (state->blocksize >> 2);
- leaf = bp->data;
- ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- count += be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
- bytes -= count * (uint)sizeof(leaf->ents[0]);
+ count = leafhdr.count - leafhdr.stale;
+ bytes = state->args->geo->blksize -
+ (state->args->geo->blksize >> 2);
+
+ leaf = bp->b_addr;
+ dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf);
+ ents = dp->d_ops->leaf_ents_p(leaf);
+ count += hdr2.count - hdr2.stale;
+ bytes -= count * sizeof(ents[0]);
+
/*
* Fits with at least 25% to spare.
*/
if (bytes >= 0)
break;
- xfs_da_brelse(state->args->trans, bp);
+ xfs_trans_brelse(state->args->trans, bp);
}
/*
* Didn't like either block, give up.
@@ -1207,21 +1490,17 @@ xfs_dir2_leafn_toosmall(
*action = 0;
return 0;
}
- /*
- * Done with the sibling leaf block here, drop the dabuf
- * so path_shift can get it.
- */
- xfs_da_buf_done(bp);
+
/*
* Make altpath point to the block we want to keep (the lower
* numbered block) and path point to the block we want to drop.
*/
memcpy(&state->altpath, &state->path, sizeof(state->path));
if (blkno < blk->blkno)
- error = xfs_da_path_shift(state, &state->altpath, forward, 0,
+ error = xfs_da3_path_shift(state, &state->altpath, forward, 0,
&rval);
else
- error = xfs_da_path_shift(state, &state->path, forward, 0,
+ error = xfs_da3_path_shift(state, &state->path, forward, 0,
&rval);
if (error) {
return error;
@@ -1243,34 +1522,54 @@ xfs_dir2_leafn_unbalance(
xfs_da_args_t *args; /* operation arguments */
xfs_dir2_leaf_t *drop_leaf; /* dead leaf structure */
xfs_dir2_leaf_t *save_leaf; /* surviving leaf structure */
+ struct xfs_dir3_icleaf_hdr savehdr;
+ struct xfs_dir3_icleaf_hdr drophdr;
+ struct xfs_dir2_leaf_entry *sents;
+ struct xfs_dir2_leaf_entry *dents;
+ struct xfs_inode *dp = state->args->dp;
args = state->args;
ASSERT(drop_blk->magic == XFS_DIR2_LEAFN_MAGIC);
ASSERT(save_blk->magic == XFS_DIR2_LEAFN_MAGIC);
- drop_leaf = drop_blk->bp->data;
- save_leaf = save_blk->bp->data;
- ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
- ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
+ drop_leaf = drop_blk->bp->b_addr;
+ save_leaf = save_blk->bp->b_addr;
+
+ dp->d_ops->leaf_hdr_from_disk(&savehdr, save_leaf);
+ dp->d_ops->leaf_hdr_from_disk(&drophdr, drop_leaf);
+ sents = dp->d_ops->leaf_ents_p(save_leaf);
+ dents = dp->d_ops->leaf_ents_p(drop_leaf);
+
/*
* If there are any stale leaf entries, take this opportunity
* to purge them.
*/
- if (drop_leaf->hdr.stale)
- xfs_dir2_leaf_compact(args, drop_blk->bp);
- if (save_leaf->hdr.stale)
- xfs_dir2_leaf_compact(args, save_blk->bp);
+ if (drophdr.stale)
+ xfs_dir3_leaf_compact(args, &drophdr, drop_blk->bp);
+ if (savehdr.stale)
+ xfs_dir3_leaf_compact(args, &savehdr, save_blk->bp);
+
/*
* Move the entries from drop to the appropriate end of save.
*/
- drop_blk->hashval = be32_to_cpu(drop_leaf->ents[be16_to_cpu(drop_leaf->hdr.count) - 1].hashval);
- if (xfs_dir2_leafn_order(save_blk->bp, drop_blk->bp))
- xfs_dir2_leafn_moveents(args, drop_blk->bp, 0, save_blk->bp, 0,
- be16_to_cpu(drop_leaf->hdr.count));
+ drop_blk->hashval = be32_to_cpu(dents[drophdr.count - 1].hashval);
+ if (xfs_dir2_leafn_order(dp, save_blk->bp, drop_blk->bp))
+ xfs_dir3_leafn_moveents(args, drop_blk->bp, &drophdr, dents, 0,
+ save_blk->bp, &savehdr, sents, 0,
+ drophdr.count);
else
- xfs_dir2_leafn_moveents(args, drop_blk->bp, 0, save_blk->bp,
- be16_to_cpu(save_leaf->hdr.count), be16_to_cpu(drop_leaf->hdr.count));
- save_blk->hashval = be32_to_cpu(save_leaf->ents[be16_to_cpu(save_leaf->hdr.count) - 1].hashval);
- xfs_dir2_leafn_check(args->dp, save_blk->bp);
+ xfs_dir3_leafn_moveents(args, drop_blk->bp, &drophdr, dents, 0,
+ save_blk->bp, &savehdr, sents,
+ savehdr.count, drophdr.count);
+ save_blk->hashval = be32_to_cpu(sents[savehdr.count - 1].hashval);
+
+ /* log the changes made when moving the entries */
+ dp->d_ops->leaf_hdr_to_disk(save_leaf, &savehdr);
+ dp->d_ops->leaf_hdr_to_disk(drop_leaf, &drophdr);
+ xfs_dir3_leaf_log_header(args, save_blk->bp);
+ xfs_dir3_leaf_log_header(args, drop_blk->bp);
+
+ xfs_dir3_leaf_check(dp, save_blk->bp);
+ xfs_dir3_leaf_check(dp, drop_blk->bp);
}
/*
@@ -1293,13 +1592,11 @@ xfs_dir2_node_addname(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
/*
* Look up the name. We're not supposed to find it, but
* this gives us the insertion point.
*/
- error = xfs_da_node_lookup_int(state, &rval);
+ error = xfs_da3_node_lookup_int(state, &rval);
if (error)
rval = error;
if (rval != ENOENT) {
@@ -1325,7 +1622,7 @@ xfs_dir2_node_addname(
* It worked, fix the hash values up the btree.
*/
if (!(args->op_flags & XFS_DA_OP_JUSTCHECK))
- xfs_da_fixhashpath(state, &state->path);
+ xfs_da3_fixhashpath(state, &state->path);
} else {
/*
* It didn't work, we need to split the leaf block.
@@ -1337,7 +1634,7 @@ xfs_dir2_node_addname(
/*
* Split the leaf block and insert the new entry.
*/
- rval = xfs_da_split(state);
+ rval = xfs_da3_split(state);
}
done:
xfs_da_state_free(state);
@@ -1356,13 +1653,13 @@ xfs_dir2_node_addname_int(
{
xfs_dir2_data_hdr_t *hdr; /* data block header */
xfs_dir2_db_t dbno; /* data block number */
- xfs_dabuf_t *dbp; /* data block buffer */
+ struct xfs_buf *dbp; /* data block buffer */
xfs_dir2_data_entry_t *dep; /* data entry pointer */
xfs_inode_t *dp; /* incore directory inode */
xfs_dir2_data_unused_t *dup; /* data unused entry pointer */
int error; /* error return value */
xfs_dir2_db_t fbno; /* freespace block number */
- xfs_dabuf_t *fbp; /* freespace buffer */
+ struct xfs_buf *fbp; /* freespace buffer */
int findex; /* freespace entry index */
xfs_dir2_free_t *free=NULL; /* freespace block structure */
xfs_dir2_db_t ifbno; /* initial freespace block no */
@@ -1374,11 +1671,14 @@ xfs_dir2_node_addname_int(
int needscan; /* need to rescan data frees */
__be16 *tagp; /* data entry tag pointer */
xfs_trans_t *tp; /* transaction pointer */
+ __be16 *bests;
+ struct xfs_dir3_icfree_hdr freehdr;
+ struct xfs_dir2_data_free *bf;
dp = args->dp;
mp = dp->i_mount;
tp = args->trans;
- length = xfs_dir2_data_entsize(args->namelen);
+ length = dp->d_ops->data_entsize(args->namelen);
/*
* If we came in with a freespace block that means that lookup
* found an entry with our hash value. This is the freespace
@@ -1390,37 +1690,38 @@ xfs_dir2_node_addname_int(
* Remember initial freespace block number.
*/
ifbno = fblk->blkno;
- free = fbp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
+ free = fbp->b_addr;
findex = fblk->index;
+ bests = dp->d_ops->free_bests_p(free);
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
+
/*
* This means the free entry showed that the data block had
* space for our entry, so we remembered it.
* Use that data block.
*/
if (findex >= 0) {
- ASSERT(findex < be32_to_cpu(free->hdr.nvalid));
- ASSERT(be16_to_cpu(free->bests[findex]) != NULLDATAOFF);
- ASSERT(be16_to_cpu(free->bests[findex]) >= length);
- dbno = be32_to_cpu(free->hdr.firstdb) + findex;
- }
- /*
- * The data block looked at didn't have enough room.
- * We'll start at the beginning of the freespace entries.
- */
- else {
+ ASSERT(findex < freehdr.nvalid);
+ ASSERT(be16_to_cpu(bests[findex]) != NULLDATAOFF);
+ ASSERT(be16_to_cpu(bests[findex]) >= length);
+ dbno = freehdr.firstdb + findex;
+ } else {
+ /*
+ * The data block looked at didn't have enough room.
+ * We'll start at the beginning of the freespace entries.
+ */
dbno = -1;
findex = 0;
}
- }
- /*
- * Didn't come in with a freespace block, so don't have a data block.
- */
- else {
+ } else {
+ /*
+ * Didn't come in with a freespace block, so no data block.
+ */
ifbno = dbno = -1;
fbp = NULL;
findex = 0;
}
+
/*
* If we don't have a data block yet, we're going to scan the
* freespace blocks looking for one. Figure out what the
@@ -1429,9 +1730,9 @@ xfs_dir2_node_addname_int(
if (dbno == -1) {
xfs_fileoff_t fo; /* freespace block number */
- if ((error = xfs_bmap_last_offset(tp, dp, &fo, XFS_DATA_FORK)))
+ if ((error = xfs_bmap_last_offset(dp, &fo, XFS_DATA_FORK)))
return error;
- lastfbno = xfs_dir2_da_to_db(mp, (xfs_dablk_t)fo);
+ lastfbno = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)fo);
fbno = ifbno;
}
/*
@@ -1449,7 +1750,8 @@ xfs_dir2_node_addname_int(
* us a freespace block to start with.
*/
if (++fbno == 0)
- fbno = XFS_DIR2_FREE_FIRSTDB(mp);
+ fbno = xfs_dir2_byte_to_db(args->geo,
+ XFS_DIR2_FREE_OFFSET);
/*
* If it's ifbno we already looked at it.
*/
@@ -1466,33 +1768,38 @@ xfs_dir2_node_addname_int(
* This should be really rare, so there's no reason
* to avoid it.
*/
- if ((error = xfs_da_read_buf(tp, dp,
- xfs_dir2_db_to_da(mp, fbno), -2, &fbp,
- XFS_DATA_FORK))) {
+ error = xfs_dir2_free_try_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, fbno),
+ &fbp);
+ if (error)
return error;
- }
- if (unlikely(fbp == NULL)) {
+ if (!fbp)
continue;
- }
- free = fbp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
+ free = fbp->b_addr;
findex = 0;
}
/*
* Look at the current free entry. Is it good enough?
+ *
+ * The bests initialisation should be where the bufer is read in
+ * the above branch. But gcc is too stupid to realise that bests
+ * and the freehdr are actually initialised if they are placed
+ * there, so we have to do it here to avoid warnings. Blech.
*/
- if (be16_to_cpu(free->bests[findex]) != NULLDATAOFF &&
- be16_to_cpu(free->bests[findex]) >= length)
- dbno = be32_to_cpu(free->hdr.firstdb) + findex;
+ bests = dp->d_ops->free_bests_p(free);
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
+ if (be16_to_cpu(bests[findex]) != NULLDATAOFF &&
+ be16_to_cpu(bests[findex]) >= length)
+ dbno = freehdr.firstdb + findex;
else {
/*
* Are we done with the freeblock?
*/
- if (++findex == be32_to_cpu(free->hdr.nvalid)) {
+ if (++findex == freehdr.nvalid) {
/*
* Drop the block.
*/
- xfs_da_brelse(tp, fbp);
+ xfs_trans_brelse(tp, fbp);
fbp = NULL;
if (fblk && fblk->bp)
fblk->bp = NULL;
@@ -1507,36 +1814,23 @@ xfs_dir2_node_addname_int(
/*
* Not allowed to allocate, return failure.
*/
- if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
- args->total == 0) {
- /*
- * Drop the freespace buffer unless it came from our
- * caller.
- */
- if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
- xfs_da_buf_done(fbp);
+ if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
return XFS_ERROR(ENOSPC);
- }
+
/*
* Allocate and initialize the new data block.
*/
if (unlikely((error = xfs_dir2_grow_inode(args,
XFS_DIR2_DATA_SPACE,
&dbno)) ||
- (error = xfs_dir2_data_init(args, dbno, &dbp)))) {
- /*
- * Drop the freespace buffer unless it came from our
- * caller.
- */
- if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
- xfs_da_buf_done(fbp);
+ (error = xfs_dir3_data_init(args, dbno, &dbp))))
return error;
- }
+
/*
* If (somehow) we have a freespace block, get rid of it.
*/
if (fbp)
- xfs_da_brelse(tp, fbp);
+ xfs_trans_brelse(tp, fbp);
if (fblk && fblk->bp)
fblk->bp = NULL;
@@ -1544,29 +1838,30 @@ xfs_dir2_node_addname_int(
* Get the freespace block corresponding to the data block
* that was just allocated.
*/
- fbno = xfs_dir2_db_to_fdb(mp, dbno);
- if (unlikely(error = xfs_da_read_buf(tp, dp,
- xfs_dir2_db_to_da(mp, fbno), -2, &fbp,
- XFS_DATA_FORK))) {
- xfs_da_buf_done(dbp);
+ fbno = dp->d_ops->db_to_fdb(args->geo, dbno);
+ error = xfs_dir2_free_try_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, fbno),
+ &fbp);
+ if (error)
return error;
- }
+
/*
* If there wasn't a freespace block, the read will
* return a NULL fbp. Allocate and initialize a new one.
*/
- if( fbp == NULL ) {
- if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_FREE_SPACE,
- &fbno))) {
+ if (!fbp) {
+ error = xfs_dir2_grow_inode(args, XFS_DIR2_FREE_SPACE,
+ &fbno);
+ if (error)
return error;
- }
- if (unlikely(xfs_dir2_db_to_fdb(mp, dbno) != fbno)) {
+ if (dp->d_ops->db_to_fdb(args->geo, dbno) != fbno) {
xfs_alert(mp,
"%s: dir ino %llu needed freesp block %lld for\n"
" data block %lld, got %lld ifbno %llu lastfbno %d",
__func__, (unsigned long long)dp->i_ino,
- (long long)xfs_dir2_db_to_fdb(mp, dbno),
+ (long long)dp->d_ops->db_to_fdb(
+ args->geo, dbno),
(long long)dbno, (long long)fbno,
(unsigned long long)ifbno, lastfbno);
if (fblk) {
@@ -1587,60 +1882,59 @@ xfs_dir2_node_addname_int(
/*
* Get a buffer for the new block.
*/
- if ((error = xfs_da_get_buf(tp, dp,
- xfs_dir2_db_to_da(mp, fbno),
- -1, &fbp, XFS_DATA_FORK))) {
+ error = xfs_dir3_free_get_buf(args, fbno, &fbp);
+ if (error)
return error;
- }
- ASSERT(fbp != NULL);
+ free = fbp->b_addr;
+ bests = dp->d_ops->free_bests_p(free);
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
/*
- * Initialize the new block to be empty, and remember
- * its first slot as our empty slot.
+ * Remember the first slot as our empty slot.
*/
- free = fbp->data;
- free->hdr.magic = cpu_to_be32(XFS_DIR2_FREE_MAGIC);
- free->hdr.firstdb = cpu_to_be32(
- (fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
- xfs_dir2_free_max_bests(mp));
- free->hdr.nvalid = 0;
- free->hdr.nused = 0;
+ freehdr.firstdb =
+ (fbno - xfs_dir2_byte_to_db(args->geo,
+ XFS_DIR2_FREE_OFFSET)) *
+ dp->d_ops->free_max_bests(args->geo);
} else {
- free = fbp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
+ free = fbp->b_addr;
+ bests = dp->d_ops->free_bests_p(free);
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
}
/*
* Set the freespace block index from the data block number.
*/
- findex = xfs_dir2_db_to_fdindex(mp, dbno);
+ findex = dp->d_ops->db_to_fdindex(args->geo, dbno);
/*
* If it's after the end of the current entries in the
* freespace block, extend that table.
*/
- if (findex >= be32_to_cpu(free->hdr.nvalid)) {
- ASSERT(findex < xfs_dir2_free_max_bests(mp));
- free->hdr.nvalid = cpu_to_be32(findex + 1);
+ if (findex >= freehdr.nvalid) {
+ ASSERT(findex < dp->d_ops->free_max_bests(args->geo));
+ freehdr.nvalid = findex + 1;
/*
* Tag new entry so nused will go up.
*/
- free->bests[findex] = cpu_to_be16(NULLDATAOFF);
+ bests[findex] = cpu_to_be16(NULLDATAOFF);
}
/*
* If this entry was for an empty data block
* (this should always be true) then update the header.
*/
- if (free->bests[findex] == cpu_to_be16(NULLDATAOFF)) {
- be32_add_cpu(&free->hdr.nused, 1);
- xfs_dir2_free_log_header(tp, fbp);
+ if (bests[findex] == cpu_to_be16(NULLDATAOFF)) {
+ freehdr.nused++;
+ dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
+ xfs_dir2_free_log_header(args, fbp);
}
/*
* Update the real value in the table.
* We haven't allocated the data entry yet so this will
* change again.
*/
- hdr = dbp->data;
- free->bests[findex] = hdr->bestfree[0].length;
+ hdr = dbp->b_addr;
+ bf = dp->d_ops->data_bestfree_p(hdr);
+ bests[findex] = bf[0].length;
logfree = 1;
}
/*
@@ -1650,35 +1944,32 @@ xfs_dir2_node_addname_int(
/*
* If just checking, we succeeded.
*/
- if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
- if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
- xfs_da_buf_done(fbp);
+ if (args->op_flags & XFS_DA_OP_JUSTCHECK)
return 0;
- }
+
/*
* Read the data block in.
*/
- if (unlikely(
- error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, dbno),
- -1, &dbp, XFS_DATA_FORK))) {
- if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
- xfs_da_buf_done(fbp);
+ error = xfs_dir3_data_read(tp, dp,
+ xfs_dir2_db_to_da(args->geo, dbno),
+ -1, &dbp);
+ if (error)
return error;
- }
- hdr = dbp->data;
+ hdr = dbp->b_addr;
+ bf = dp->d_ops->data_bestfree_p(hdr);
logfree = 0;
}
- ASSERT(be16_to_cpu(hdr->bestfree[0].length) >= length);
+ ASSERT(be16_to_cpu(bf[0].length) >= length);
/*
* Point to the existing unused space.
*/
dup = (xfs_dir2_data_unused_t *)
- ((char *)hdr + be16_to_cpu(hdr->bestfree[0].offset));
+ ((char *)hdr + be16_to_cpu(bf[0].offset));
needscan = needlog = 0;
/*
* Mark the first part of the unused space, inuse for us.
*/
- xfs_dir2_data_use_free(tp, dbp, dup,
+ xfs_dir2_data_use_free(args, dbp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
&needlog, &needscan);
/*
@@ -1688,48 +1979,44 @@ xfs_dir2_node_addname_int(
dep->inumber = cpu_to_be64(args->inumber);
dep->namelen = args->namelen;
memcpy(dep->name, args->name, dep->namelen);
- tagp = xfs_dir2_data_entry_tag_p(dep);
+ dp->d_ops->data_put_ftype(dep, args->filetype);
+ tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
- xfs_dir2_data_log_entry(tp, dbp, dep);
+ xfs_dir2_data_log_entry(args, dbp, dep);
/*
* Rescan the block for bestfree if needed.
*/
if (needscan)
- xfs_dir2_data_freescan(mp, hdr, &needlog);
+ xfs_dir2_data_freescan(dp, hdr, &needlog);
/*
* Log the data block header if needed.
*/
if (needlog)
- xfs_dir2_data_log_header(tp, dbp);
+ xfs_dir2_data_log_header(args, dbp);
/*
* If the freespace entry is now wrong, update it.
*/
- if (be16_to_cpu(free->bests[findex]) != be16_to_cpu(hdr->bestfree[0].length)) {
- free->bests[findex] = hdr->bestfree[0].length;
+ bests = dp->d_ops->free_bests_p(free); /* gcc is so stupid */
+ if (be16_to_cpu(bests[findex]) != be16_to_cpu(bf[0].length)) {
+ bests[findex] = bf[0].length;
logfree = 1;
}
/*
* Log the freespace entry if needed.
*/
if (logfree)
- xfs_dir2_free_log_bests(tp, fbp, findex, findex);
- /*
- * If the caller didn't hand us the freespace block, drop it.
- */
- if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
- xfs_da_buf_done(fbp);
+ xfs_dir2_free_log_bests(args, fbp, findex, findex);
/*
* Return the data block and offset in args, then drop the data block.
*/
args->blkno = (xfs_dablk_t)dbno;
args->index = be16_to_cpu(*tagp);
- xfs_da_buf_done(dbp);
return 0;
}
/*
* Lookup an entry in a node-format directory.
- * All the real work happens in xfs_da_node_lookup_int.
+ * All the real work happens in xfs_da3_node_lookup_int.
* The only real output is the inode number of the entry.
*/
int /* error */
@@ -1749,34 +2036,33 @@ xfs_dir2_node_lookup(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
/*
* Fill in the path to the entry in the cursor.
*/
- error = xfs_da_node_lookup_int(state, &rval);
+ error = xfs_da3_node_lookup_int(state, &rval);
if (error)
rval = error;
else if (rval == ENOENT && args->cmpresult == XFS_CMP_CASE) {
/* If a CI match, dup the actual name and return EEXIST */
xfs_dir2_data_entry_t *dep;
- dep = (xfs_dir2_data_entry_t *)((char *)state->extrablk.bp->
- data + state->extrablk.index);
+ dep = (xfs_dir2_data_entry_t *)
+ ((char *)state->extrablk.bp->b_addr +
+ state->extrablk.index);
rval = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
}
/*
* Release the btree blocks and leaf block.
*/
for (i = 0; i < state->path.active; i++) {
- xfs_da_brelse(args->trans, state->path.blk[i].bp);
+ xfs_trans_brelse(args->trans, state->path.blk[i].bp);
state->path.blk[i].bp = NULL;
}
/*
* Release the data block if we have it.
*/
if (state->extravalid && state->extrablk.bp) {
- xfs_da_brelse(args->trans, state->extrablk.bp);
+ xfs_trans_brelse(args->trans, state->extrablk.bp);
state->extrablk.bp = NULL;
}
xfs_da_state_free(state);
@@ -1788,12 +2074,12 @@ xfs_dir2_node_lookup(
*/
int /* error */
xfs_dir2_node_removename(
- xfs_da_args_t *args) /* operation arguments */
+ struct xfs_da_args *args) /* operation arguments */
{
- xfs_da_state_blk_t *blk; /* leaf block */
+ struct xfs_da_state_blk *blk; /* leaf block */
int error; /* error return value */
int rval; /* operation return value */
- xfs_da_state_t *state; /* btree cursor */
+ struct xfs_da_state *state; /* btree cursor */
trace_xfs_dir2_node_removename(args);
@@ -1803,21 +2089,18 @@ xfs_dir2_node_removename(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
- /*
- * Look up the entry we're deleting, set up the cursor.
- */
- error = xfs_da_node_lookup_int(state, &rval);
+
+ /* Look up the entry we're deleting, set up the cursor. */
+ error = xfs_da3_node_lookup_int(state, &rval);
if (error)
- rval = error;
- /*
- * Didn't find it, upper layer screwed up.
- */
+ goto out_free;
+
+ /* Didn't find it, upper layer screwed up. */
if (rval != EEXIST) {
- xfs_da_state_free(state);
- return rval;
+ error = rval;
+ goto out_free;
}
+
blk = &state->path.blk[state->path.active - 1];
ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
ASSERT(state->extravalid);
@@ -1828,21 +2111,22 @@ xfs_dir2_node_removename(
error = xfs_dir2_leafn_remove(args, blk->bp, blk->index,
&state->extrablk, &rval);
if (error)
- return error;
+ goto out_free;
/*
* Fix the hash values up the btree.
*/
- xfs_da_fixhashpath(state, &state->path);
+ xfs_da3_fixhashpath(state, &state->path);
/*
* If we need to join leaf blocks, do it.
*/
if (rval && state->path.active > 1)
- error = xfs_da_join(state);
+ error = xfs_da3_join(state);
/*
* If no errors so far, try conversion to leaf format.
*/
if (!error)
error = xfs_dir2_node_to_leaf(state);
+out_free:
xfs_da_state_free(state);
return error;
}
@@ -1873,13 +2157,11 @@ xfs_dir2_node_replace(
state = xfs_da_state_alloc();
state->args = args;
state->mp = args->dp->i_mount;
- state->blocksize = state->mp->m_dirblksize;
- state->node_ents = state->mp->m_dir_node_ents;
inum = args->inumber;
/*
* Lookup the entry to change in the btree.
*/
- error = xfs_da_node_lookup_int(state, &rval);
+ error = xfs_da3_node_lookup_int(state, &rval);
if (error) {
rval = error;
}
@@ -1888,42 +2170,47 @@ xfs_dir2_node_replace(
* and locked it. But paranoia is good.
*/
if (rval == EEXIST) {
+ struct xfs_dir2_leaf_entry *ents;
/*
* Find the leaf entry.
*/
blk = &state->path.blk[state->path.active - 1];
ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
- leaf = blk->bp->data;
- lep = &leaf->ents[blk->index];
+ leaf = blk->bp->b_addr;
+ ents = args->dp->d_ops->leaf_ents_p(leaf);
+ lep = &ents[blk->index];
ASSERT(state->extravalid);
/*
* Point to the data entry.
*/
- hdr = state->extrablk.bp->data;
- ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
+ hdr = state->extrablk.bp->b_addr;
+ ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
+ hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
dep = (xfs_dir2_data_entry_t *)
((char *)hdr +
- xfs_dir2_dataptr_to_off(state->mp, be32_to_cpu(lep->address)));
+ xfs_dir2_dataptr_to_off(args->geo,
+ be32_to_cpu(lep->address)));
ASSERT(inum != be64_to_cpu(dep->inumber));
/*
* Fill in the new inode number and log the entry.
*/
dep->inumber = cpu_to_be64(inum);
- xfs_dir2_data_log_entry(args->trans, state->extrablk.bp, dep);
+ args->dp->d_ops->data_put_ftype(dep, args->filetype);
+ xfs_dir2_data_log_entry(args, state->extrablk.bp, dep);
rval = 0;
}
/*
* Didn't find it, and we're holding a data block. Drop it.
*/
else if (state->extravalid) {
- xfs_da_brelse(args->trans, state->extrablk.bp);
+ xfs_trans_brelse(args->trans, state->extrablk.bp);
state->extrablk.bp = NULL;
}
/*
* Release all the buffers in the cursor.
*/
for (i = 0; i < state->path.active; i++) {
- xfs_da_brelse(args->trans, state->path.blk[i].bp);
+ xfs_trans_brelse(args->trans, state->path.blk[i].bp);
state->path.blk[i].bp = NULL;
}
xfs_da_state_free(state);
@@ -1940,12 +2227,13 @@ xfs_dir2_node_trim_free(
xfs_fileoff_t fo, /* free block number */
int *rvalp) /* out: did something */
{
- xfs_dabuf_t *bp; /* freespace buffer */
+ struct xfs_buf *bp; /* freespace buffer */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
xfs_dir2_free_t *free; /* freespace structure */
xfs_mount_t *mp; /* filesystem mount point */
xfs_trans_t *tp; /* transaction pointer */
+ struct xfs_dir3_icfree_hdr freehdr;
dp = args->dp;
mp = dp->i_mount;
@@ -1953,41 +2241,39 @@ xfs_dir2_node_trim_free(
/*
* Read the freespace block.
*/
- if (unlikely(error = xfs_da_read_buf(tp, dp, (xfs_dablk_t)fo, -2, &bp,
- XFS_DATA_FORK))) {
+ error = xfs_dir2_free_try_read(tp, dp, fo, &bp);
+ if (error)
return error;
- }
-
/*
* There can be holes in freespace. If fo is a hole, there's
* nothing to do.
*/
- if (bp == NULL) {
+ if (!bp)
return 0;
- }
- free = bp->data;
- ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
+ free = bp->b_addr;
+ dp->d_ops->free_hdr_from_disk(&freehdr, free);
+
/*
* If there are used entries, there's nothing to do.
*/
- if (be32_to_cpu(free->hdr.nused) > 0) {
- xfs_da_brelse(tp, bp);
+ if (freehdr.nused > 0) {
+ xfs_trans_brelse(tp, bp);
*rvalp = 0;
return 0;
}
/*
* Blow the block away.
*/
- if ((error =
- xfs_dir2_shrink_inode(args, xfs_dir2_da_to_db(mp, (xfs_dablk_t)fo),
- bp))) {
+ error = xfs_dir2_shrink_inode(args,
+ xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)fo), bp);
+ if (error) {
/*
* Can't fail with ENOSPC since that only happens with no
* space reservation, when breaking up an extent into two
* pieces. This is the last block of an extent.
*/
ASSERT(error != ENOSPC);
- xfs_da_brelse(tp, bp);
+ xfs_trans_brelse(tp, bp);
return error;
}
/*
diff --git a/fs/xfs/xfs_dir2_priv.h b/fs/xfs/xfs_dir2_priv.h