aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/device-mapper/dm-crypt.txt21
-rw-r--r--Documentation/device-mapper/dm-flakey.txt48
-rw-r--r--Documentation/device-mapper/dm-raid.txt138
-rw-r--r--drivers/md/Kconfig5
-rw-r--r--drivers/md/dm-crypt.c62
-rw-r--r--drivers/md/dm-flakey.c270
-rw-r--r--drivers/md/dm-io.c29
-rw-r--r--drivers/md/dm-ioctl.c89
-rw-r--r--drivers/md/dm-kcopyd.c42
-rw-r--r--drivers/md/dm-log-userspace-base.c3
-rw-r--r--drivers/md/dm-log.c32
-rw-r--r--drivers/md/dm-mpath.c147
-rw-r--r--drivers/md/dm-raid.c621
-rw-r--r--drivers/md/dm-snap-persistent.c80
-rw-r--r--drivers/md/dm-snap.c84
-rw-r--r--drivers/md/dm-table.c155
-rw-r--r--drivers/md/dm.c75
-rw-r--r--drivers/md/dm.h2
-rw-r--r--include/linux/device-mapper.h43
-rw-r--r--include/linux/dm-ioctl.h4
-rw-r--r--include/linux/dm-kcopyd.h15
21 files changed, 1561 insertions, 404 deletions
diff --git a/Documentation/device-mapper/dm-crypt.txt b/Documentation/device-mapper/dm-crypt.txt
index 6b5c42dbbe8..2c656ae43ba 100644
--- a/Documentation/device-mapper/dm-crypt.txt
+++ b/Documentation/device-mapper/dm-crypt.txt
@@ -4,7 +4,8 @@ dm-crypt
Device-Mapper's "crypt" target provides transparent encryption of block devices
using the kernel crypto API.
-Parameters: <cipher> <key> <iv_offset> <device path> <offset>
+Parameters: <cipher> <key> <iv_offset> <device path> \
+ <offset> [<#opt_params> <opt_params>]
<cipher>
Encryption cipher and an optional IV generation mode.
@@ -37,6 +38,24 @@ Parameters: <cipher> <key> <iv_offset> <device path> <offset>
<offset>
Starting sector within the device where the encrypted data begins.
+<#opt_params>
+ Number of optional parameters. If there are no optional parameters,
+ the optional paramaters section can be skipped or #opt_params can be zero.
+ Otherwise #opt_params is the number of following arguments.
+
+ Example of optional parameters section:
+ 1 allow_discards
+
+allow_discards
+ Block discard requests (a.k.a. TRIM) are passed through the crypt device.
+ The default is to ignore discard requests.
+
+ WARNING: Assess the specific security risks carefully before enabling this
+ option. For example, allowing discards on encrypted devices may lead to
+ the leak of information about the ciphertext device (filesystem type,
+ used space etc.) if the discarded blocks can be located easily on the
+ device later.
+
Example scripts
===============
LUKS (Linux Unified Key Setup) is now the preferred way to set up disk
diff --git a/Documentation/device-mapper/dm-flakey.txt b/Documentation/device-mapper/dm-flakey.txt
index c8efdfd19a6..6ff5c232722 100644
--- a/Documentation/device-mapper/dm-flakey.txt
+++ b/Documentation/device-mapper/dm-flakey.txt
@@ -1,17 +1,53 @@
dm-flakey
=========
-This target is the same as the linear target except that it returns I/O
-errors periodically. It's been found useful in simulating failing
-devices for testing purposes.
+This target is the same as the linear target except that it exhibits
+unreliable behaviour periodically. It's been found useful in simulating
+failing devices for testing purposes.
Starting from the time the table is loaded, the device is available for
-<up interval> seconds, then returns errors for <down interval> seconds,
-and then this cycle repeats.
+<up interval> seconds, then exhibits unreliable behaviour for <down
+interval> seconds, and then this cycle repeats.
-Parameters: <dev path> <offset> <up interval> <down interval>
+Also, consider using this in combination with the dm-delay target too,
+which can delay reads and writes and/or send them to different
+underlying devices.
+
+Table parameters
+----------------
+ <dev path> <offset> <up interval> <down interval> \
+ [<num_features> [<feature arguments>]]
+
+Mandatory parameters:
<dev path>: Full pathname to the underlying block-device, or a
"major:minor" device-number.
<offset>: Starting sector within the device.
<up interval>: Number of seconds device is available.
<down interval>: Number of seconds device returns errors.
+
+Optional feature parameters:
+ If no feature parameters are present, during the periods of
+ unreliability, all I/O returns errors.
+
+ drop_writes:
+ All write I/O is silently ignored.
+ Read I/O is handled correctly.
+
+ corrupt_bio_byte <Nth_byte> <direction> <value> <flags>:
+ During <down interval>, replace <Nth_byte> of the data of
+ each matching bio with <value>.
+
+ <Nth_byte>: The offset of the byte to replace.
+ Counting starts at 1, to replace the first byte.
+ <direction>: Either 'r' to corrupt reads or 'w' to corrupt writes.
+ 'w' is incompatible with drop_writes.
+ <value>: The value (from 0-255) to write.
+ <flags>: Perform the replacement only if bio->bi_rw has all the
+ selected flags set.
+
+Examples:
+ corrupt_bio_byte 32 r 1 0
+ - replaces the 32nd byte of READ bios with the value 1
+
+ corrupt_bio_byte 224 w 0 32
+ - replaces the 224th byte of REQ_META (=32) bios with the value 0
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index 33b6b7071ac..2a8c11331d2 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -1,70 +1,108 @@
-Device-mapper RAID (dm-raid) is a bridge from DM to MD. It
-provides a way to use device-mapper interfaces to access the MD RAID
-drivers.
+dm-raid
+-------
-As with all device-mapper targets, the nominal public interfaces are the
-constructor (CTR) tables and the status outputs (both STATUSTYPE_INFO
-and STATUSTYPE_TABLE). The CTR table looks like the following:
+The device-mapper RAID (dm-raid) target provides a bridge from DM to MD.
+It allows the MD RAID drivers to be accessed using a device-mapper
+interface.
-1: <s> <l> raid \
-2: <raid_type> <#raid_params> <raid_params> \
-3: <#raid_devs> <meta_dev1> <dev1> .. <meta_devN> <devN>
-
-Line 1 contains the standard first three arguments to any device-mapper
-target - the start, length, and target type fields. The target type in
-this case is "raid".
-
-Line 2 contains the arguments that define the particular raid
-type/personality/level, the required arguments for that raid type, and
-any optional arguments. Possible raid types include: raid4, raid5_la,
-raid5_ls, raid5_rs, raid6_zr, raid6_nr, and raid6_nc. (raid1 is
-planned for the future.) The list of required and optional parameters
-is the same for all the current raid types. The required parameters are
-positional, while the optional parameters are given as key/value pairs.
-The possible parameters are as follows:
- <chunk_size> Chunk size in sectors.
- [[no]sync] Force/Prevent RAID initialization
- [rebuild <idx>] Rebuild the drive indicated by the index
- [daemon_sleep <ms>] Time between bitmap daemon work to clear bits
- [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization
- [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization
- [max_write_behind <sectors>] See '-write-behind=' (man mdadm)
- [stripe_cache <sectors>] Stripe cache size for higher RAIDs
-
-Line 3 contains the list of devices that compose the array in
-metadata/data device pairs. If the metadata is stored separately, a '-'
-is given for the metadata device position. If a drive has failed or is
-missing at creation time, a '-' can be given for both the metadata and
-data drives for a given position.
-
-NB. Currently all metadata devices must be specified as '-'.
-
-Examples:
-# RAID4 - 4 data drives, 1 parity
+The target is named "raid" and it accepts the following parameters:
+
+ <raid_type> <#raid_params> <raid_params> \
+ <#raid_devs> <metadata_dev0> <dev0> [.. <metadata_devN> <devN>]
+
+<raid_type>:
+ raid1 RAID1 mirroring
+ raid4 RAID4 dedicated parity disk
+ raid5_la RAID5 left asymmetric
+ - rotating parity 0 with data continuation
+ raid5_ra RAID5 right asymmetric
+ - rotating parity N with data continuation
+ raid5_ls RAID5 left symmetric
+ - rotating parity 0 with data restart
+ raid5_rs RAID5 right symmetric
+ - rotating parity N with data restart
+ raid6_zr RAID6 zero restart
+ - rotating parity zero (left-to-right) with data restart
+ raid6_nr RAID6 N restart
+ - rotating parity N (right-to-left) with data restart
+ raid6_nc RAID6 N continue
+ - rotating parity N (right-to-left) with data continuation
+
+ Refererence: Chapter 4 of
+ http://www.snia.org/sites/default/files/SNIA_DDF_Technical_Position_v2.0.pdf
+
+<#raid_params>: The number of parameters that follow.
+
+<raid_params> consists of
+ Mandatory parameters:
+ <chunk_size>: Chunk size in sectors. This parameter is often known as
+ "stripe size". It is the only mandatory parameter and
+ is placed first.
+
+ followed by optional parameters (in any order):
+ [sync|nosync] Force or prevent RAID initialization.
+
+ [rebuild <idx>] Rebuild drive number idx (first drive is 0).
+
+ [daemon_sleep <ms>]
+ Interval between runs of the bitmap daemon that
+ clear bits. A longer interval means less bitmap I/O but
+ resyncing after a failure is likely to take longer.
+
+ [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization
+ [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization
+ [write_mostly <idx>] Drive index is write-mostly
+ [max_write_behind <sectors>] See '-write-behind=' (man mdadm)
+ [stripe_cache <sectors>] Stripe cache size (higher RAIDs only)
+ [region_size <sectors>]
+ The region_size multiplied by the number of regions is the
+ logical size of the array. The bitmap records the device
+ synchronisation state for each region.
+
+<#raid_devs>: The number of devices composing the array.
+ Each device consists of two entries. The first is the device
+ containing the metadata (if any); the second is the one containing the
+ data.
+
+ If a drive has failed or is missing at creation time, a '-' can be
+ given for both the metadata and data drives for a given position.
+
+
+Example tables
+--------------
+# RAID4 - 4 data drives, 1 parity (no metadata devices)
# No metadata devices specified to hold superblock/bitmap info
# Chunk size of 1MiB
# (Lines separated for easy reading)
+
0 1960893648 raid \
raid4 1 2048 \
5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81
-# RAID4 - 4 data drives, 1 parity (no metadata devices)
+# RAID4 - 4 data drives, 1 parity (with metadata devices)
# Chunk size of 1MiB, force RAID initialization,
# min recovery rate at 20 kiB/sec/disk
+
0 1960893648 raid \
- raid4 4 2048 min_recovery_rate 20 sync\
- 5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81
+ raid4 4 2048 sync min_recovery_rate 20 \
+ 5 8:17 8:18 8:33 8:34 8:49 8:50 8:65 8:66 8:81 8:82
-Performing a 'dmsetup table' should display the CTR table used to
-construct the mapping (with possible reordering of optional
-parameters).
+'dmsetup table' displays the table used to construct the mapping.
+The optional parameters are always printed in the order listed
+above with "sync" or "nosync" always output ahead of the other
+arguments, regardless of the order used when originally loading the table.
+Arguments that can be repeated are ordered by value.
-Performing a 'dmsetup status' will yield information on the state and
-health of the array. The output is as follows:
+'dmsetup status' yields information on the state and health of the
+array.
+The output is as follows:
1: <s> <l> raid \
2: <raid_type> <#devices> <1 health char for each dev> <resync_ratio>
-Line 1 is standard DM output. Line 2 is best shown by example:
+Line 1 is the standard output produced by device-mapper.
+Line 2 is produced by the raid target, and best explained by example:
0 1960893648 raid raid4 5 AAAAA 2/490221568
Here we can see the RAID type is raid4, there are 5 devices - all of
which are 'A'live, and the array is 2/490221568 complete with recovery.
+Faulty or missing devices are marked 'D'. Devices that are out-of-sync
+are marked 'a'.
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 8420129fc5e..f75a66e7d31 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -241,12 +241,13 @@ config DM_MIRROR
needed for live data migration tools such as 'pvmove'.
config DM_RAID
- tristate "RAID 4/5/6 target (EXPERIMENTAL)"
+ tristate "RAID 1/4/5/6 target (EXPERIMENTAL)"
depends on BLK_DEV_DM && EXPERIMENTAL
+ select MD_RAID1
select MD_RAID456
select BLK_DEV_MD
---help---
- A dm target that supports RAID4, RAID5 and RAID6 mappings
+ A dm target that supports RAID1, RAID4, RAID5 and RAID6 mappings
A RAID-5 set of N drives with a capacity of C MB per drive provides
the capacity of C * (N - 1) MB, and protects against a failure
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index bae6c4e23d3..49da55c1528 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -30,7 +30,6 @@
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "crypt"
-#define MESG_STR(x) x, sizeof(x)
/*
* context holding the current state of a multi-part conversion
@@ -239,7 +238,7 @@ static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
memset(iv, 0, cc->iv_size);
- *(u32 *)iv = cpu_to_le32(dmreq->iv_sector & 0xffffffff);
+ *(__le32 *)iv = cpu_to_le32(dmreq->iv_sector & 0xffffffff);
return 0;
}
@@ -248,7 +247,7 @@ static int crypt_iv_plain64_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
memset(iv, 0, cc->iv_size);
- *(u64 *)iv = cpu_to_le64(dmreq->iv_sector);
+ *(__le64 *)iv = cpu_to_le64(dmreq->iv_sector);
return 0;
}
@@ -415,7 +414,7 @@ static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv,
struct crypto_cipher *essiv_tfm = this_crypt_config(cc)->iv_private;
memset(iv, 0, cc->iv_size);
- *(u64 *)iv = cpu_to_le64(dmreq->iv_sector);
+ *(__le64 *)iv = cpu_to_le64(dmreq->iv_sector);
crypto_cipher_encrypt_one(essiv_tfm, iv, iv);
return 0;
@@ -1575,11 +1574,17 @@ bad_mem:
static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct crypt_config *cc;
- unsigned int key_size;
+ unsigned int key_size, opt_params;
unsigned long long tmpll;
int ret;
+ struct dm_arg_set as;
+ const char *opt_string;
+
+ static struct dm_arg _args[] = {
+ {0, 1, "Invalid number of feature args"},
+ };
- if (argc != 5) {
+ if (argc < 5) {
ti->error = "Not enough arguments";
return -EINVAL;
}
@@ -1648,6 +1653,30 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
}
cc->start = tmpll;
+ argv += 5;
+ argc -= 5;
+
+ /* Optional parameters */
+ if (argc) {
+ as.argc = argc;
+ as.argv = argv;
+
+ ret = dm_read_arg_group(_args, &as, &opt_params, &ti->error);
+ if (ret)
+ goto bad;
+
+ opt_string = dm_shift_arg(&as);
+
+ if (opt_params == 1 && opt_string &&
+ !strcasecmp(opt_string, "allow_discards"))
+ ti->num_discard_requests = 1;
+ else if (opt_params) {
+ ret = -EINVAL;
+ ti->error = "Invalid feature arguments";
+ goto bad;
+ }
+ }
+
ret = -ENOMEM;
cc->io_queue = alloc_workqueue("kcryptd_io",
WQ_NON_REENTRANT|
@@ -1682,9 +1711,16 @@ static int crypt_map(struct dm_target *ti, struct bio *bio,
struct dm_crypt_io *io;
struct crypt_config *cc;
- if (bio->bi_rw & REQ_FLUSH) {
+ /*
+ * If bio is REQ_FLUSH or REQ_DISCARD, just bypass crypt queues.
+ * - for REQ_FLUSH device-mapper core ensures that no IO is in-flight
+ * - for REQ_DISCARD caller must use flush if IO ordering matters
+ */
+ if (unlikely(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) {
cc = ti->private;
bio->bi_bdev = cc->dev->bdev;
+ if (bio_sectors(bio))
+ bio->bi_sector = cc->start + dm_target_offset(ti, bio->bi_sector);
return DM_MAPIO_REMAPPED;
}
@@ -1727,6 +1763,10 @@ static int crypt_status(struct dm_target *ti, status_type_t type,
DMEMIT(" %llu %s %llu", (unsigned long long)cc->iv_offset,
cc->dev->name, (unsigned long long)cc->start);
+
+ if (ti->num_discard_requests)
+ DMEMIT(" 1 allow_discards");
+
break;
}
return 0;
@@ -1770,12 +1810,12 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
if (argc < 2)
goto error;
- if (!strnicmp(argv[0], MESG_STR("key"))) {
+ if (!strcasecmp(argv[0], "key")) {
if (!test_bit(DM_CRYPT_SUSPENDED, &cc->flags)) {
DMWARN("not suspended during key manipulation.");
return -EINVAL;
}
- if (argc == 3 && !strnicmp(argv[1], MESG_STR("set"))) {
+ if (argc == 3 && !strcasecmp(argv[1], "set")) {
ret = crypt_set_key(cc, argv[2]);
if (ret)
return ret;
@@ -1783,7 +1823,7 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
ret = cc->iv_gen_ops->init(cc);
return ret;
}
- if (argc == 2 && !strnicmp(argv[1], MESG_STR("wipe"))) {
+ if (argc == 2 && !strcasecmp(argv[1], "wipe")) {
if (cc->iv_gen_ops && cc->iv_gen_ops->wipe) {
ret = cc->iv_gen_ops->wipe(cc);
if (ret)
@@ -1823,7 +1863,7 @@ static int crypt_iterate_devices(struct dm_target *ti,
static struct target_type crypt_target = {
.name = "crypt",
- .version = {1, 10, 0},
+ .version = {1, 11, 0},
.module = THIS_MODULE,
.ctr = crypt_ctr,
.dtr = crypt_dtr,
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index ea790623c30..89f73ca22cf 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -1,6 +1,6 @@
/*
* Copyright (C) 2003 Sistina Software (UK) Limited.
- * Copyright (C) 2004, 2010 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2004, 2010-2011 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
@@ -15,6 +15,9 @@
#define DM_MSG_PREFIX "flakey"
+#define all_corrupt_bio_flags_match(bio, fc) \
+ (((bio)->bi_rw & (fc)->corrupt_bio_flags) == (fc)->corrupt_bio_flags)
+
/*
* Flakey: Used for testing only, simulates intermittent,
* catastrophic device failure.
@@ -25,60 +28,189 @@ struct flakey_c {
sector_t start;
unsigned up_interval;
unsigned down_interval;
+ unsigned long flags;
+ unsigned corrupt_bio_byte;
+ unsigned corrupt_bio_rw;
+ unsigned corrupt_bio_value;
+ unsigned corrupt_bio_flags;
+};
+
+enum feature_flag_bits {
+ DROP_WRITES
};
+static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
+ struct dm_target *ti)
+{
+ int r;
+ unsigned argc;
+ const char *arg_name;
+
+ static struct dm_arg _args[] = {
+ {0, 6, "Invalid number of feature args"},
+ {1, UINT_MAX, "Invalid corrupt bio byte"},
+ {0, 255, "Invalid corrupt value to write into bio byte (0-255)"},
+ {0, UINT_MAX, "Invalid corrupt bio flags mask"},
+ };
+
+ /* No feature arguments supplied. */
+ if (!as->argc)
+ return 0;
+
+ r = dm_read_arg_group(_args, as, &argc, &ti->error);
+ if (r)
+ return r;
+
+ while (argc) {
+ arg_name = dm_shift_arg(as);
+ argc--;
+
+ /*
+ * drop_writes
+ */
+ if (!strcasecmp(arg_name, "drop_writes")) {
+ if (test_and_set_bit(DROP_WRITES, &fc->flags)) {
+ ti->error = "Feature drop_writes duplicated";
+ return -EINVAL;
+ }
+
+ continue;
+ }
+
+ /*
+ * corrupt_bio_byte <Nth_byte> <direction> <value> <bio_flags>
+ */
+ if (!strcasecmp(arg_name, "corrupt_bio_byte")) {
+ if (!argc)
+ ti->error = "Feature corrupt_bio_byte requires parameters";
+
+ r = dm_read_arg(_args + 1, as, &fc->corrupt_bio_byte, &ti->error);
+ if (r)
+ return r;
+ argc--;
+
+ /*
+ * Direction r or w?
+ */
+ arg_name = dm_shift_arg(as);
+ if (!strcasecmp(arg_name, "w"))
+ fc->corrupt_bio_rw = WRITE;
+ else if (!strcasecmp(arg_name, "r"))
+ fc->corrupt_bio_rw = READ;
+ else {
+ ti->error = "Invalid corrupt bio direction (r or w)";
+ return -EINVAL;
+ }
+ argc--;
+
+ /*
+ * Value of byte (0-255) to write in place of correct one.
+ */
+ r = dm_read_arg(_args + 2, as, &fc->corrupt_bio_value, &ti->error);
+ if (r)
+ return r;
+ argc--;
+
+ /*
+ * Only corrupt bios with these flags set.
+ */
+ r = dm_read_arg(_args + 3, as, &fc->corrupt_bio_flags, &ti->error);
+ if (r)
+ return r;
+ argc--;
+
+ continue;
+ }
+
+ ti->error = "Unrecognised flakey feature requested";
+ return -EINVAL;
+ }
+
+ if (test_bit(DROP_WRITES, &fc->flags) && (fc->corrupt_bio_rw == WRITE)) {
+ ti->error = "drop_writes is incompatible with corrupt_bio_byte with the WRITE flag set";
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/*
- * Construct a flakey mapping: <dev_path> <offset> <up interval> <down interval>
+ * Construct a flakey mapping:
+ * <dev_path> <offset> <up interval> <down interval> [<#feature args> [<arg>]*]
+ *
+ * Feature args:
+ * [drop_writes]
+ * [corrupt_bio_byte <Nth_byte> <direction> <value> <bio_flags>]
+ *
+ * Nth_byte starts from 1 for the first byte.
+ * Direction is r for READ or w for WRITE.
+ * bio_flags is ignored if 0.
*/
static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
+ static struct dm_arg _args[] = {
+ {0, UINT_MAX, "Invalid up interval"},
+ {0, UINT_MAX, "Invalid down interval"},
+ };
+
+ int r;
struct flakey_c *fc;
- unsigned long long tmp;
+ unsigned long long tmpll;
+ struct dm_arg_set as;
+ const char *devname;
- if (argc != 4) {
- ti->error = "dm-flakey: Invalid argument count";
+ as.argc = argc;
+ as.argv = argv;
+
+ if (argc < 4) {
+ ti->error = "Invalid argument count";
return -EINVAL;
}
- fc = kmalloc(sizeof(*fc), GFP_KERNEL);
+ fc = kzalloc(sizeof(*fc), GFP_KERNEL);
if (!fc) {
- ti->error = "dm-flakey: Cannot allocate linear context";
+ ti->error = "Cannot allocate linear context";
return -ENOMEM;
}
fc->start_time = jiffies;
- if (sscanf(argv[1], "%llu", &tmp) != 1) {
- ti->error = "dm-flakey: Invalid device sector";
+ devname = dm_shift_arg(&as);
+
+ if (sscanf(dm_shift_arg(&as), "%llu", &tmpll) != 1) {
+ ti->error = "Invalid device sector";
goto bad;
}
- fc->start = tmp;
+ fc->start = tmpll;
- if (sscanf(argv[2], "%u", &fc->up_interval) != 1) {
- ti->error = "dm-flakey: Invalid up interval";
+ r = dm_read_arg(_args, &as, &fc->up_interval, &ti->error);
+ if (r)
goto bad;
- }
- if (sscanf(argv[3], "%u", &fc->down_interval) != 1) {
- ti->error = "dm-flakey: Invalid down interval";
+ r = dm_read_arg(_args, &as, &fc->down_interval, &ti->error);
+ if (r)
goto bad;
- }
if (!(fc->up_interval + fc->down_interval)) {
- ti->error = "dm-flakey: Total (up + down) interval is zero";
+ ti->error = "Total (up + down) interval is zero";
goto bad;
}
if (fc->up_interval + fc->down_interval < fc->up_interval) {
- ti->error = "dm-flakey: Interval overflow";
+ ti->error = "Interval overflow";
goto bad;
}
- if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &fc->dev)) {
- ti->error = "dm-flakey: Device lookup failed";
+ r = parse_features(&as, fc, ti);
+ if (r)
+ goto bad;
+
+ if (dm_get_device(ti, devname, dm_table_get_mode(ti->table), &fc->dev)) {
+ ti->error = "Device lookup failed";
goto bad;
}
ti->num_flush_requests = 1;
+ ti->num_discard_requests = 1;
ti->private = fc;
return 0;
@@ -99,7 +231,7 @@ static sector_t flakey_map_sector(struct dm_target *ti, sector_t bi_sector)
{
struct flakey_c *fc = ti->private;
- return fc->start + (bi_sector - ti->begin);
+ return fc->start + dm_target_offset(ti, bi_sector);
}
static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
@@ -111,6 +243,25 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
bio->bi_sector = flakey_map_sector(ti, bio->bi_sector);
}
+static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
+{
+ unsigned bio_bytes = bio_cur_bytes(bio);
+ char *data = bio_data(bio);
+
+ /*
+ * Overwrite the Nth byte of the data returned.
+ */
+ if (data && bio_bytes >= fc->corrupt_bio_byte) {
+ data[fc->corrupt_bio_byte - 1] = fc->corrupt_bio_value;
+
+ DMDEBUG("Corrupting data bio=%p by writing %u to byte %u "
+ "(rw=%c bi_rw=%lu bi_sector=%llu cur_bytes=%u)\n",
+ bio, fc->corrupt_bio_value, fc->corrupt_bio_byte,
+ (bio_data_dir(bio) == WRITE) ? 'w' : 'r',
+ bio->bi_rw, (unsigned long long)bio->bi_sector, bio_bytes);
+ }
+}
+
static int flakey_map(struct dm_target *ti, struct bio *bio,
union map_info *map_context)
{
@@ -119,18 +270,71 @@ static int flakey_map(struct dm_target *ti, struct bio *bio,
/* Are we alive ? */
elapsed = (jiffies - fc->start_time) / HZ;
- if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval)
+ if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) {
+ /*
+ * Flag this bio as submitted while down.
+ */
+ map_context->ll = 1;
+
+ /*
+ * Map reads as normal.
+ */
+ if (bio_data_dir(bio) == READ)
+ goto map_bio;
+
+ /*
+ * Drop writes?
+ */
+ if (test_bit(DROP_WRITES, &fc->flags)) {
+ bio_endio(bio, 0);
+ return DM_MAPIO_SUBMITTED;
+ }
+
+ /*
+ * Corrupt matching writes.
+ */
+ if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == WRITE)) {
+ if (all_corrupt_bio_flags_match(bio, fc))
+ corrupt_bio_data(bio, fc);
+ goto map_bio;
+ }
+
+ /*
+ * By default, error all I/O.
+ */
return -EIO;
+ }
+map_bio:
flakey_map_bio(ti, bio);
return DM_MAPIO_REMAPPED;
}
+static int flakey_end_io(struct dm_target *ti, struct bio *bio,
+ int error, union map_info *map_context)
+{
+ struct flakey_c *fc = ti->private;
+ unsigned bio_submitted_while_down = map_context->ll;
+
+ /*
+ * Corrupt successful READs while in down state.
+ * If flags were specified, only corrupt those that match.
+ */
+ if (!error && bio_submitted_while_down &&
+ (bio_data_dir(bio) == READ) && (fc->corrupt_bio_rw == READ) &&
+ all_corrupt_bio_flags_match(bio, fc))
+ corrupt_bio_data(bio, fc);
+
+ return error;
+}
+
static int flakey_status(struct dm_target *ti, status_type_t type,
char *result, unsigned int maxlen)
{
+ unsigned sz = 0;
struct flakey_c *fc = ti->private;
+ unsigned drop_writes;
switch (type) {
case STATUSTYPE_INFO:
@@ -138,9 +342,22 @@ static int flakey_status(struct dm_target *ti, status_type_t type,
break;
case STATUSTYPE_TABLE:
- snprintf(result, maxlen, "%s %llu %u %u", fc->dev->name,
- (unsigned long long)fc->start, fc->up_interval,
- fc->down_interval);
+ DMEMIT("%s %llu %u %u ", fc->dev->name,
+ (unsigned long long)fc->start, fc->up_interval,
+ fc->down_interval);
+
+ drop_writes = test_bit(DROP_WRITES, &fc->flags);
+ DMEMIT("%u ", drop_writes + (fc->corrupt_bio_byte > 0) * 5);
+
+ if (drop_writes)
+ DMEMIT("drop_writes ");
+
+ if (fc->corrupt_bio_byte)
+ DMEMIT("corrupt_bio_byte %u %c %u %u ",
+ fc->corrupt_bio_byte,
+ (fc->corrupt_bio_rw == WRITE) ? 'w' : 'r',
+ fc->corrupt_bio_value, fc->corrupt_bio_flags);
+
break;
}
return 0;
@@ -177,11 +394,12 @@ static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_
static struct target_type flakey_target = {
.name = "flakey",
- .version = {1, 1, 0},
+ .version = {1, 2, 0},
.module = THIS_MODULE,
.ctr = flakey_ctr,
.dtr = flakey_dtr,
.map = flakey_map,
+ .end_io = flakey_end_io,
.status = flakey_status,
.ioctl = flakey_ioctl,
.merge = flakey_merge,
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 2067288f61f..ad2eba40e31 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -38,6 +38,8 @@ struct io {
struct dm_io_client *client;
io_notify_fn callback;
void *context;
+ void *vma_invalidate_address;
+ unsigned long vma_invalidate_size;
} __attribute__((aligned(DM_IO_MAX_REGIONS)));
static struct kmem_cache *_dm_io_cache;
@@ -116,6 +118,10 @@ static void dec_count(struct io *io, unsigned int region, int error)
set_bit(region, &io->error_bits);
if (atomic_dec_and_test(&io->count)) {
+ if (io->vma_invalidate_size)
+ invalidate_kernel_vmap_range(io->vma_invalidate_address,
+ io->vma_invalidate_size);
+
if (io->sleeper)
wake_up_process(io->sleeper);
@@ -159,6 +165,9 @@ struct dpages {
unsigned context_u;
void *context_ptr;
+
+ void *vma_invalidate_address;
+ unsigned long vma_invalidate_size;
};
/*
@@ -377,6 +386,9 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
io->sleeper = current;
io->client = client;
+ io->vma_invalidate_address = dp->vma_invalidate_address;
+ io->vma_invalidate_size = dp->vma_invalidate_size;
+
dispatch_io(rw, num_regions, where, dp, io, 1);
while (1) {
@@ -415,13 +427,21 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
io->callback = fn;
io->context = context;
+ io->vma_invalidate_address = dp->vma_invalidate_address;
+ io->vma_invalidate_size = dp->vma_invalidate_size;
+
dispatch_io(rw, num_regions, where, dp, io, 0);
return 0;
}
-static int dp_init(struct dm_io_request *io_req, struct dpages *dp)
+static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
+ unsigned long size)
{
/* Set up dpages based on memory type */
+
+ dp->vma_invalidate_address = NULL;
+ dp->vma_invalidate_size = 0;
+
switch (io_req->mem.type) {
case DM_IO_PAGE_LIST:
list_dp_init(dp, io_req->mem.ptr.pl, io_req->mem.offset);
@@ -432,6 +452,11 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp)
break;
case DM_IO_VMA:
+ flush_kernel_vmap_range(io_req->mem.ptr.vma, size);
+ if ((io_req->bi_rw & RW_MASK) == READ) {
+ dp->vma_invalidate_address = io_req->mem.ptr.vma;
+ dp->vma_invalidate_size = size;
+ }
vm_dp_init(dp, io_req->mem.ptr.vma);
break;
@@ -460,7 +485,7 @@ int dm_io(struct dm_io_request *io_req, unsigned num_regions,
int r;
struct dpages dp;
- r = dp_init(io_req, &dp);
+ r = dp_init(io_req, &dp, (unsigned long)where->count << SECTOR_SHIFT);
if (r)
return r;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 4cacdad2270..2e9a3ca37bd 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -128,6 +128,24 @@ static struct hash_cell *__get_uuid_cell(const char *str)
return NULL;
}
+static struct hash_cell *__get_dev_cell(uint64_t dev)
+{
+ struct mapped_device *md;