md/raid1: record nonrot rdevs while adding/removing rdevs to conf

For raid1, each read will iterate all the rdevs from conf and check if
any rdev is non-rotational, then choose rdev with minimal IO inflight
if so, or rdev with closest distance otherwise.

Disk nonrot info can be changed through sysfs entry:

/sys/block/[disk_name]/queue/rotational

However, consider that this should only be used for testing, and user
really shouldn't do this in real life. Record the number of non-rotational
disks in conf, to avoid checking each rdev in IO fast path and simplify
read_balance() a little bit.

Co-developed-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240229095714.926789-4-yukuai1@huaweicloud.com

md/raid1: switch to use md_account_bio() for io accounting

Two problems can be fixed this way:

1) 'active_io' will represent inflight io instead of io that is
dispatching.

2) If io accounting is enabled or disabled while io is still inflight,
bio_start_io_acct() and bio_end_io_acct() is not balanced and io
inflight counter will be leaked.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230621165110.1498313-5-yukuai1@huaweicloud.com

md: protect md_thread with rcu

Currently, there are many places that md_thread can be accessed without
protection, following are known scenarios that can cause
null-ptr-dereference or uaf:

1) sync_thread that is allocated and started from md_start_sync()
2) mddev->thread can be accessed directly from timeout_store() and
md_bitmap_daemon_work()
3) md_unregister_thread() from action_store().

Currently, a global spinlock 'pers_lock' is borrowed to protect
'mddev->thread' in some places, this problem can be fixed likewise,
however, use a global lock for all the cases is not good.

Fix this problem by protecting all md_thread with rcu.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230523021017.3048783-6-yukuai1@huaweicloud.com

md: raid1/raid10: drop pending_cnt

Those counters are not necessary after commit 11bb45e8aaf6 ("md: drop queue
limitation for RAID1 and RAID10"). Remove them from all code (conf and
plug structs). raid1_plug_cb and raid10_plug_cb are identical, so move
definition of raid1_plug_cb to common raid1-10 definitions and use it for
RAID10 too.

Signed-off-by: Mariusz Tkaczyk <mariusz.tkaczyk@linux.intel.com>
Signed-off-by: Song Liu <song@kernel.org>

md/raid1: enable io accounting

For raid1, we record the start time between split bio and clone bio,
and finish the accounting in the final endio.

Also introduce start_time in r1bio accordingly.

Signed-off-by: Guoqing Jiang <jiangguoqing@kylinos.cn>
Signed-off-by: Song Liu <song@kernel.org>

md/raid1: Replace zero-length array with flexible-array

The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:

struct foo {
int stuff;
struct boo array[];
};

By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.

Also, notice that, dynamic memory allocations won't be affected by
this change:

"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]

sizeof(flexible-array-member) triggers a warning because flexible array
members have incomplete type[1]. There are some instances of code in
which the sizeof operator is being incorrectly/erroneously applied to
zero-length arrays and the result is zero. Such instances may be hiding
some bugs. So, this work (flexible-array member conversions) will also
help to get completely rid of those sorts of issues.

This issue was found with the help of Coccinelle.

[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour")

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Song Liu <songliubraving@fb.com>

md: convert to bioset_init()/mempool_init()

Convert md to embedded bio sets.

Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

md: document lifetime of internal rdev pointer.

The rdev pointer kept in the local 'config' for each for
raid1, raid10, raid4/5/6 has non-obvious lifetime rules.
Sometimes RCU is needed, sometimes a lock, something nothing.

Add documentation to explain this.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <sh.li@alibaba-inc.com>

License cleanup: add SPDX GPL-2.0 license identifier to files with no license

Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.

By default all files without license information are under the default
license of the kernel, which is GPL version 2.

Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.

This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.

How this work was done:

Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,

Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.

The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.

The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.

Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).

All documentation files were explicitly excluded.

The following heuristics were used to determine which SPDX license
identifiers to apply.

- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.

For non */uapi/* files that summary was:

SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139

and resulted in the first patch in this series.

If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:

SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930

and resulted in the second patch in this series.

- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:

SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1

and that resulted in the third patch in this series.

- when the two scanners agreed on the detected license(s), that became
the concluded license(s).

- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.

- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).

- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.

- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.

In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.

Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.

Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.

In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.

Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct

This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.

These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.

Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

md/raid1: Use a new variable to count flighting sync requests

In new barrier codes, raise_barrier waits if conf->nr_pending[idx] is not zero.
After all the conditions are true, the resync request can go on be handled. But
it adds conf->nr_pending[idx] again. The next resync request hit the same bucket
idx need to wait the resync request which is submitted before. The performance
of resync/recovery is degraded.
So we should use a new variable to count sync requests which are in flight.

I did a simple test:
1. Without the patch, create a raid1 with two disks. The resync speed:
Device: rrqm/s wrqm/s r/s w/s rMB/s wMB/s avgrq-sz avgqu-sz await r_await w_await svctm %util
sdb 0.00 0.00 166.00 0.00 10.38 0.00 128.00 0.03 0.20 0.20 0.00 0.19 3.20
sdc 0.00 0.00 0.00 166.00 0.00 10.38 128.00 0.96 5.77 0.00 5.77 5.75 95.50
2. With the patch, the result is:
sdb 2214.00 0.00 766.00 0.00 185.69 0.00 496.46 2.80 3.66 3.66 0.00 1.03 79.10
sdc 0.00 2205.00 0.00 769.00 0.00 186.44 496.52 5.25 6.84 0.00 6.84 1.30 100.10

Suggested-by: Shaohua Li <shli@kernel.org>
Signed-off-by: Xiao Ni <xni@redhat.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>

md/raid1: simplify the splitting of requests.

raid1 currently splits requests in two different ways for
two different reasons.

First, bio_split() is used to ensure the bio fits within a
resync accounting region.
Second, multiple r1bios are allocated for each bio to handle
the possiblity of known bad blocks on some devices.

This can be simplified to just use bio_split() once, and not
use multiple r1bios.
We delay the split until we know a maximum bio size that can
be handled with a single r1bio, and then split the bio and
queue the remainder for later handling.

This avoids all loops inside raid1.c request handling. Just
a single read, or a single set of writes, is submitted to
lower-level devices for each bio that comes from
generic_make_request().

When the bio needs to be split, generic_make_request() will
do the necessary looping and call md_make_request() multiple
times.

raid1_make_request() no longer queues request for raid1 to handle,
so we can remove that branch from the 'if'.

This patch also creates a new private bio_set
(conf->bio_split) for splitting bios. Using fs_bio_set
is wrong, as it is meant to be used by filesystems, not
block devices. Using it inside md can lead to deadlocks
under high memory pressure.

Delete unused variable in raid1_write_request() (Shaohua)
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>

md: raid1: improve write behind

This patch improve handling of write behind in the following ways:

- introduce behind master bio to hold all write behind pages
- fast clone bios from behind master bio
- avoid to change bvec table directly
- use bio_copy_data() and make code more clean

Suggested-by: Shaohua Li <shli@fb.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>

RAID1: avoid unnecessary spin locks in I/O barrier code

When I run a parallel reading performan testing on a md raid1 device with
two NVMe SSDs, I observe very bad throughput in supprise: by fio with 64KB
block size, 40 seq read I/O jobs, 128 iodepth, overall throughput is
only 2.7GB/s, this is around 50% of the idea performance number.

The perf reports locking contention happens at allow_barrier() and
wait_barrier() code,
- 41.41% fio [kernel.kallsyms] [k] _raw_spin_lock_irqsave
- _raw_spin_lock_irqsave
+ 89.92% allow_barrier
+ 9.34% __wake_up
- 37.30% fio [kernel.kallsyms] [k] _raw_spin_lock_irq
- _raw_spin_lock_irq
- 100.00% wait_barrier

The reason is, in these I/O barrier related functions,
- raise_barrier()
- lower_barrier()
- wait_barrier()
- allow_barrier()
They always hold conf->resync_lock firstly, even there are only regular
reading I/Os and no resync I/O at all. This is a huge performance penalty.

The solution is a lockless-like algorithm in I/O barrier code, and only
holding conf->resync_lock when it has to.

The original idea is from Hannes Reinecke, and Neil Brown provides
comments to improve it. I continue to work on it, and make the patch into
current form.

In the new simpler raid1 I/O barrier implementation, there are two
wait barrier functions,
- wait_barrier()
Which calls _wait_barrier(), is used for regular write I/O. If there is
resync I/O happening on the same I/O barrier bucket, or the whole
array is frozen, task will wait until no barrier on same barrier bucket,
or the whold array is unfreezed.
- wait_read_barrier()
Since regular read I/O won't interfere with resync I/O (read_balance()
will make sure only uptodate data will be read out), it is unnecessary
to wait for barrier in regular read I/Os, waiting in only necessary
when the whole array is frozen.

The operations on conf->nr_pending[idx], conf->nr_waiting[idx], conf->
barrier[idx] are very carefully designed in raise_barrier(),
lower_barrier(), _wait_barrier() and wait_read_barrier(), in order to
avoid unnecessary spin locks in these functions. Once conf->
nr_pengding[idx] is increased, a resync I/O with same barrier bucket index
has to wait in raise_barrier(). Then in _wait_barrier() if no barrier
raised in same barrier bucket index and array is not frozen, the regular
I/O doesn't need to hold conf->resync_lock, it can just increase
conf->nr_pending[idx], and return to its caller. wait_read_barrier() is
very similar to _wait_barrier(), the only difference is it only waits when
array is frozen. For heavy parallel reading I/Os, the lockless I/O barrier
code almostly gets rid of all spin lock cost.

This patch significantly improves raid1 reading peroformance. From my
testing, a raid1 device built by two NVMe SSD, runs fio with 64KB
blocksize, 40 seq read I/O jobs, 128 iodepth, overall throughput
increases from 2.7GB/s to 4.6GB/s (+70%).

Changelog
V4:
- Change conf->nr_queued[] to atomic_t.
- Define BARRIER_BUCKETS_NR_BITS by (PAGE_SHIFT - ilog2(sizeof(atomic_t)))
V3:
- Add smp_mb__after_atomic() as Shaohua and Neil suggested.
- Change conf->nr_queued[] from atomic_t to int.
- Change conf->array_frozen from atomic_t back to int, and use
READ_ONCE(conf->array_frozen) to check value of conf->array_frozen
in _wait_barrier() and wait_read_barrier().
- In _wait_barrier() and wait_read_barrier(), add a call to
wake_up(&conf->wait_barrier) after atomic_dec(&conf->nr_pending[idx]),
to fix a deadlock between _wait_barrier()/wait_read_barrier and
freeze_array().
V2:
- Remove a spin_lock/unlock pair in raid1d().
- Add more code comments to explain why there is no racy when checking two
atomic_t variables at same time.
V1:
- Original RFC patch for comments.

Signed-off-by: Coly Li <colyli@suse.de>
Cc: Shaohua Li <shli@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: Neil Brown <neilb@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>

RAID1: a new I/O barrier implementation to remove resync window

'Commit 79ef3a8aa1cb ("raid1: Rewrite the implementation of iobarrier.")'
introduces a sliding resync window for raid1 I/O barrier, this idea limits
I/O barriers to happen only inside a slidingresync window, for regular
I/Os out of this resync window they don't need to wait for barrier any
more. On large raid1 device, it helps a lot to improve parallel writing
I/O throughput when there are background resync I/Os performing at
same time.

The idea of sliding resync widow is awesome, but code complexity is a
challenge. Sliding resync window requires several variables to work
collectively, this is complexed and very hard to make it work correctly.
Just grep "Fixes: 79ef3a8aa1" in kernel git log, there are 8 more patches
to fix the original resync window patch. This is not the end, any further
related modification may easily introduce more regreassion.

Therefore I decide to implement a much simpler raid1 I/O barrier, by
removing resync window code, I believe life will be much easier.

The brief idea of the simpler barrier is,
- Do not maintain a global unique resync window
- Use multiple hash buckets to reduce I/O barrier conflicts, regular
I/O only has to wait for a resync I/O when both them have same barrier
bucket index, vice versa.
- I/O barrier can be reduced to an acceptable number if there are enough
barrier buckets

Here I explain how the barrier buckets are designed,
- BARRIER_UNIT_SECTOR_SIZE
The whole LBA address space of a raid1 device is divided into multiple
barrier units, by the size of BARRIER_UNIT_SECTOR_SIZE.
Bio requests won't go across border of barrier unit size, that means
maximum bio size is BARRIER_UNIT_SECTOR_SIZE<<9 (64MB) in bytes.
For random I/O 64MB is large enough for both read and write requests,
for sequential I/O considering underlying block layer may merge them
into larger requests, 64MB is still good enough.
Neil also points out that for resync operation, "we want the resync to
move from region to region fairly quickly so that the slowness caused
by having to synchronize with the resync is averaged out over a fairly
small time frame". For full speed resync, 64MB should take less then 1
second. When resync is competing with other I/O, it could take up a few
minutes. Therefore 64MB size is fairly good range for resync.

- BARRIER_BUCKETS_NR
There are BARRIER_BUCKETS_NR buckets in total, which is defined by,
#define BARRIER_BUCKETS_NR_BITS (PAGE_SHIFT - 2)
#define BARRIER_BUCKETS_NR (1<<BARRIER_BUCKETS_NR_BITS)
this patch makes the bellowed members of struct r1conf from integer
to array of integers,
- int nr_pending;
- int nr_waiting;
- int nr_queued;
- int barrier;
+ int *nr_pending;
+ int *nr_waiting;
+ int *nr_queued;
+ int *barrier;
number of the array elements is defined as BARRIER_BUCKETS_NR. For 4KB
kernel space page size, (PAGE_SHIFT - 2) indecates there are 1024 I/O
barrier buckets, and each array of integers occupies single memory page.
1024 means for a request which is smaller than the I/O barrier unit size
has ~0.1% chance to wait for resync to pause, which is quite a small
enough fraction. Also requesting single memory page is more friendly to
kernel page allocator than larger memory size.

- I/O barrier bucket is indexed by bio start sector
If multiple I/O requests hit different I/O barrier units, they only need
to compete I/O barrier with other I/Os which hit the same I/O barrier
bucket index with each other. The index of a barrier bucket which a
bio should look for is calculated by sector_to_idx() which is defined
in raid1.h as an inline function,
static inline int sector_to_idx(sector_t sector)
{
return hash_long(sector >> BARRIER_UNIT_SECTOR_BITS,
BARRIER_BUCKETS_NR_BITS);
}
Here sector_nr is the start sector number of a bio.

- Single bio won't go across boundary of a I/O barrier unit
If a request goes across boundary of barrier unit, it will be split. A
bio may be split in raid1_make_request() or raid1_sync_request(), if
sectors returned by align_to_barrier_unit_end() is smaller than
original bio size.

Comparing to single sliding resync window,
- Currently resync I/O grows linearly, therefore regular and resync I/O
will conflict within a single barrier units. So the I/O behavior is
similar to single sliding resync window.
- But a barrier unit bucket is shared by all barrier units with identical
barrier uinit index, the probability of conflict might be higher
than single sliding resync window, in condition that writing I/Os
always hit barrier units which have identical barrier bucket indexs with
the resync I/Os. This is a very rare condition in real I/O work loads,
I cannot imagine how it could happen in practice.
- Therefore we can achieve a good enough low conflict rate with much
simpler barrier algorithm and implementation.

There are two changes should be noticed,
- In raid1d(), I change the code to decrease conf->nr_pending[idx] into
single loop, it looks like this,
spin_lock_irqsave(&conf->device_lock, flags);
conf->nr_queued[idx]--;
spin_unlock_irqrestore(&conf->device_lock, flags);
This change generates more spin lock operations, but in next patch of
this patch set, it will be replaced by a single line code,
atomic_dec(&conf->nr_queueud[idx]);
So we don't need to worry about spin lock cost here.
- Mainline raid1 code split original raid1_make_request() into
raid1_read_request() and raid1_write_request(). If the original bio
goes across an I/O barrier unit size, this bio will be split before
calling raid1_read_request() or raid1_write_request(), this change
the code logic more simple and clear.
- In this patch wait_barrier() is moved from raid1_make_request() to
raid1_write_request(). In raid_read_request(), original wait_barrier()
is replaced by raid1_read_request().
The differnece is wait_read_barrier() only waits if array is frozen,
using different barrier function in different code path makes the code
more clean and easy to read.
Changelog
V4:
- Add alloc_r1bio() to remove redundant r1bio memory allocation code.
- Fix many typos in patch comments.
- Use (PAGE_SHIFT - ilog2(sizeof(int))) to define BARRIER_BUCKETS_NR_BITS.
V3:
- Rebase the patch against latest upstream kernel code.
- Many fixes by review comments from Neil,
- Back to use pointers to replace arraries in struct r1conf
- Remove total_barriers from struct r1conf
- Add more patch comments to explain how/why the values of
BARRIER_UNIT_SECTOR_SIZE and BARRIER_BUCKETS_NR are decided.
- Use get_unqueued_pending() to replace get_all_pendings() and
get_all_queued()
- Increase bucket number from 512 to 1024
- Change code comments format by review from Shaohua.
V2:
- Use bio_split() to split the orignal bio if it goes across barrier unit
bounday, to make the code more simple, by suggestion from Shaohua and
Neil.
- Use hash_long() to replace original linear hash, to avoid a possible
confilict between resync I/O and sequential write I/O, by suggestion from
Shaohua.
- Add conf->total_barriers to record barrier depth, which is used to
control number of parallel sync I/O barriers, by suggestion from Shaohua.
- In V1 patch the bellowed barrier buckets related members in r1conf are
allocated in memory page. To make the code more simple, V2 patch moves
the memory space into struct r1conf, like this,
- int nr_pending;
- int nr_waiting;
- int nr_queued;
- int barrier;
+ int nr_pending[BARRIER_BUCKETS_NR];
+ int nr_waiting[BARRIER_BUCKETS_NR];
+ int nr_queued[BARRIER_BUCKETS_NR];
+ int barrier[BARRIER_BUCKETS_NR];
This change is by the suggestion from Shaohua.
- Remove some inrelavent code comments, by suggestion from Guoqing.
- Add a missing wait_barrier() before jumping to retry_write, in
raid1_make_write_request().
V1:
- Original RFC patch for comments

Signed-off-by: Coly Li <colyli@suse.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: Neil Brown <neilb@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>

md/raid1: add failfast handling for reads.

If a device is marked FailFast and it is not the only device
we can read from, we mark the bio with REQ_FAILFAST_* flags.

If this does fail, we don't try read repair but just allow
failure. If it was the last device it doesn't fail of
course, so the retry happens on the same device - this time
without FAILFAST. A subsequent failure will not retry but
will just pass up the error.

During resync we may use FAILFAST requests and on a failure
we will simply use the other device(s).

During recovery we will only use FAILFAST in the unusual
case were there are multiple places to read from - i.e. if
there are > 2 devices. If we get a failure we will fail the
device and complete the resync/recovery with remaining
devices.

The new R1BIO_FailFast flag is set on read reqest to suggest
the a FAILFAST request might be acceptable. The rdev needs
to have FailFast set as well for the read to actually use
REQ_FAILFAST_*.

We need to know there are at least two working devices
before we can set R1BIO_FailFast, so we mustn't stop looking
at the first device we find. So the "min_pending == 0"
handling to not exit early, but too always choose the
best_pending_disk if min_pending == 0.

The spinlocked region in raid1_error() in enlarged to ensure
that if two bios, reading from two different devices, fail
at the same time, then there is no risk that both devices
will be marked faulty, leaving zero "In_sync" devices.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>

md: define mddev flags, recovery flags and r1bio state bits using enums

This is less error prone than using individual #defines.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>

md-cluster: Use a small window for resync

Suspending the entire device for resync could take too long. Resync
in small chunks.

cluster's resync window (32M) is maintained in r1conf as
cluster_sync_low and cluster_sync_high and processed in
raid1's sync_request(). If the current resync is outside the cluster
resync window:

1. Set the cluster_sync_low to curr_resync_completed.
2. Check if the sync will fit in the new window, if not issue a
wait_barrier() and set cluster_sync_low to sector_nr.
3. Set cluster_sync_high to cluster_sync_low + resync_window.
4. Send a message to all nodes so they may add it in their suspension
list.

bitmap_cond_end_sync is modified to allow to force a sync inorder
to get the curr_resync_completed uptodate with the sector passed.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: ensure device failure recorded before write request returns.

When a write to one of the legs of a RAID1 fails, the failure is
recorded in the metadata of the other leg(s) so that after a restart
the data on the failed drive wont be trusted even if that drive seems
to be working again (maybe a cable was unplugged).

Similarly when we record a bad-block in response to a write failure,
we must not let the write complete until the bad-block update is safe.

Currently there is no interlock between the write request completing
and the metadata update. So it is possible that the write will
complete, the app will confirm success in some way, and then the
machine will crash before the metadata update completes.

This is an extremely small hole for a racy to fit in, but it is
theoretically possible and so should be closed.

So:
- set MD_CHANGE_PENDING when requesting a metadata update for a
failed device, so we can know with certainty when it completes
- queue requests that experienced an error on a new queue which
is only processed after the metadata update completes
- call raid_end_bio_io() on bios in that queue when the time comes.

Signed-off-by: NeilBrown <neilb@suse.com>

md: make ->congested robust against personality changes.

There is currently no locking around calls to the 'congested'
bdi function. If called at an awkward time while an array is
being converted from one level (or personality) to another, there
is a tiny chance of running code in an unreferenced module etc.

So add a 'congested' function to the md_personality operations
structure, and call it with appropriate locking from a central
'mddev_congested'.

When the array personality is changing the array will be 'suspended'
so no IO is processed.
If mddev_congested detects this, it simply reports that the
array is congested, which is a safe guess.
As mddev_suspend calls synchronize_rcu(), mddev_congested can
avoid races by included the whole call inside an rcu_read_lock()
region.
This require that the congested functions for all subordinate devices
can be run under rcu_lock. Fortunately this is the case.

Signed-off-by: NeilBrown <neilb@suse.de>

md: remove unwanted white space from md.c

My editor shows much of this is RED.

Signed-off-by: NeilBrown <neilb@suse.de>

raid1: Rewrite the implementation of iobarrier.

There is an iobarrier in raid1 because of contention between normal IO and
resync IO. It suspends all normal IO when resync/recovery happens.

However if normal IO is out side the resync window, there is no contention.
So this patch changes the barrier mechanism to only block IO that
could contend with the resync that is currently happening.

We partition the whole space into five parts.
|---------|-----------|------------|----------------|-------|
start next_resync start_next_window end_window

start + RESYNC_WINDOW = next_resync
next_resync + NEXT_NORMALIO_DISTANCE = start_next_window
start_next_window + NEXT_NORMALIO_DISTANCE = end_window

Firstly we introduce some concepts:

1 - RESYNC_WINDOW: For resync, there are 32 resync requests at most at the
same time. A sync request is RESYNC_BLOCK_SIZE(64*1024).
So the RESYNC_WINDOW is 32 * RESYNC_BLOCK_SIZE, that is 2MB.
2 - NEXT_NORMALIO_DISTANCE: the distance between next_resync
and start_next_window. It also indicates the distance between
start_next_window and end_window.
It is currently 3 * RESYNC_WINDOW_SIZE but could be tuned if
this turned out not to be optimal.
3 - next_resync: the next sector at which we will do sync IO.
4 - start: a position which is at most RESYNC_WINDOW before
next_resync.
5 - start_next_window: a position which is NEXT_NORMALIO_DISTANCE
beyond next_resync. Normal-io after this position doesn't need to
wait for resync-io to complete.
6 - end_window: a position which is 2 * NEXT_NORMALIO_DISTANCE beyond
next_resync. This also doesn't need to wait, but is counted
differently.
7 - current_window_requests: the count of normalIO between
start_next_window and end_window.
8 - next_window_requests: the count of normalIO after end_window.

NormalIO will be partitioned into four types:

NormIO1: the end sector of bio is smaller or equal the start
NormIO2: the start sector of bio larger or equal to end_window
NormIO3: the start sector of bio larger or equal to
start_next_window.
NormIO4: the location between start_next_window and end_window

|--------|-----------|--------------------|----------------|-------------|
| start | next_resync | start_next_window | end_window |
NormIO1 NormIO4 NormIO4 NormIO3 NormIO2

For NormIO1, we don't need any io barrier.
For NormIO4, we used a similar approach to the original iobarrier
mechanism. The normalIO and resyncIO must be kept separate.
For NormIO2/3, we add two fields to struct r1conf: "current_window_requests"
and "next_window_requests". They indicate the count of active
requests in the two window.
For these, we don't wait for resync io to complete.

For resync action, if there are NormIO4s, we must wait for it.
If not, we can proceed.
But if resync action reaches start_next_window and
current_window_requests > 0 (that is there are NormIO3s), we must
wait until the current_window_requests becomes zero.
When current_window_requests becomes zero, start_next_window also
moves forward. Then current_window_requests will replaced by
next_window_requests.

There is a problem which when and how to change from NormIO2 to
NormIO3. Only then can sync action progress.

We add a field in struct r1conf "start_next_window".

A: if start_next_window == MaxSector, it means there are no NormIO2/3.
So start_next_window = next_resync + NEXT_NORMALIO_DISTANCE
B: if current_window_requests == 0 && next_window_requests != 0, it
means start_next_window move to end_window

There is another problem which how to differentiate between
old NormIO2(now it is NormIO3) and NormIO2.
For example, there are many bios which are NormIO2 and a bio which is
NormIO3. NormIO3 firstly completed, so the bios of NormIO2 became NormIO3.

We add a field in struct r1bio "start_next_window".
This is used to record the position conf->start_next_window when the call
to wait_barrier() is made in make_request().

In allow_barrier(), we check the conf->start_next_window.
If r1bio->stat_next_window == conf->start_next_window, it means
there is no transition between NormIO2 and NormIO3.
If r1bio->start_next_window != conf->start_next_window, it mean
there was a transition between NormIO2 and NormIO3. There can only
have been one transition. So it only means the bio is old NormIO2.

For one bio, there may be many r1bio's. So we make sure
all the r1bio->start_next_window are the same value.
If we met blocked_dev in make_request(), it must call allow_barrier
and wait_barrier. So the former and the later value of
conf->start_next_window will be change.
If there are many r1bio's with differnet start_next_window,
for the relevant bio, it depend on the last value of r1bio.
It will cause error. To avoid this, we must wait for previous r1bios
to complete.

Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

raid1: Add a field array_frozen to indicate whether raid in freeze state.

Because the following patch will rewrite the content between normal IO
and resync IO. So we used a parameter to indicate whether raid is in freeze
array.

Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: prevent merging too large request

For SSD, if request size exceeds specific value (optimal io size), request size
isn't important for bandwidth. In such condition, if making request size bigger
will cause some disks idle, the total throughput will actually drop. A good
example is doing a readahead in a two-disk raid1 setup.

So when should we split big requests? We absolutly don't want to split big
request to very small requests. Even in SSD, big request transfer is more
efficient. This patch only considers request with size above optimal io size.

If all disks are busy, is it worth doing a split? Say optimal io size is 16k,
two requests 32k and two disks. We can let each disk run one 32k request, or
split the requests to 4 16k requests and each disk runs two. It's hard to say
which case is better, depending on hardware.

So only consider case where there are idle disks. For readahead, split is
always better in this case. And in my test, below patch can improve > 30%
thoughput. Hmm, not 100%, because disk isn't 100% busy.

Such case can happen not just in readahead, for example, in directio. But I
suppose directio usually will have bigger IO depth and make all disks busy, so
I ignored it.

Note: if the raid uses any hard disk, we don't prevent merging. That will make
performace worse.

Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: make sequential read detection per disk based

Currently the sequential read detection is global wide. It's natural to make it
per disk based, which can improve the detection for concurrent multiple
sequential reads. And next patch will make SSD read balance not use distance
based algorithm, where this change help detect truly sequential read for SSD.

Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>

MD: Move macros from raid1*.h to raid1*.c

MD RAID1/RAID10: Move some macros from .h file to .c file

There are three macros (IO_BLOCKED,IO_MADE_GOOD,BIO_SPECIAL) which are defined
in both raid1.h and raid10.h. They are only used in there respective .c files.
However, if we wish to make RAID10 accessible to the device-mapper RAID
target (dm-raid.c), then we need to move these macros into the .c files where
they are used so that they do not conflict with each other.

The macros from the two files are identical and could be moved into md.h, but
I chose to leave the duplication and have them remain in the personality
files.

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>

MD RAID1: rename mirror_info structure

MD RAID1: Rename the structure 'mirror_info' to 'raid1_info'

The same structure name ('mirror_info') is used by raid10. Each of these
structures are defined in there respective header files. If dm-raid is
to support both RAID1 and RAID10, the header files will be included and
the structure names must not collide. While only one of these structure
names needs to change, this patch adds consistency to the naming of the
structure.

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: Allocate spare to store replacement devices and their bios.

In RAID1, a replacement is much like a normal device, so we just
double the size of the relevant arrays and look at all possible
devices for reads and writes.

This means that the array looks like it is now double the size in some
way - we need to be careful about that.
In particular, we checking if the array is still degraded while
creating a recovery request we need to only consider the first 'half'
- i.e. the real (non-replacement) devices.

Signed-off-by: NeilBrown <neilb@suse.de>

md: add proper write-congestion reporting to RAID1 and RAID10.

RAID1 and RAID10 handle write requests by queuing them for handling by
a separate thread. This is because when a write-intent-bitmap is
active we might need to update the bitmap first, so it is good to
queue a lot of writes, then do one big bitmap update for them all.

However writeback request devices to appear to be congested after a
while so it can make some guesstimate of throughput. The infinite
queue defeats that (note that RAID5 has already has a finite queue so
it doesn't suffer from this problem).

So impose a limit on the number of pending write requests. By default
it is 1024 which seems to be generally suitable. Make it configurable
via module option just in case someone finds a regression.

Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: typedef removal: conf_t -> struct r1conf

Signed-off-by: NeilBrown <neilb@suse.de>

md: remove typedefs: mirror_info_t -> struct mirror_info

Signed-off-by: NeilBrown <neilb@suse.de>

md: remove typedefs: r10bio_t -> struct r10bio and r1bio_t -> struct r1bio

Signed-off-by: NeilBrown <neilb@suse.de>

md: remove typedefs: mdk_thread_t -> struct md_thread

Signed-off-by: NeilBrown <neilb@suse.de>

md: remove typedefs: mddev_t -> struct mddev

Having mddev_t and 'struct mddev_s' is ugly and not preferred

Signed-off-by: NeilBrown <neilb@suse.de>

md: removing typedefs: mdk_rdev_t -> struct md_rdev

The typedefs are just annoying. 'mdk' probably refers to 'md_k.h'
which used to be an include file that defined this thing.

Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: add documentation to r1_private_data_s data structure.

There wasn't much and it is inconsistent.
Also rearrange fields to keep related fields together.

Reported-by: Aapo Laine <aapo.laine@shiftmail.org>
Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: Handle write errors by updating badblock log.

When we get a write error (in the data area, not in metadata),
update the badblock log rather than failing the whole device.

As the write may well be many blocks, we trying writing each
block individually and only log the ones which fail.

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>

md/raid1: store behind-write pages in bi_vecs.

When performing write-behind we allocate pages to store the data
during write.
Previously we just keep a list of pages. Now we keep a list of
bi_vec which includes offset and size.
This means that the r1bio has complete information to create a new
bio which will be needed for retrying after write errors.

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>

md/raid1: clear bad-block record when write succeeds.

If we succeed in writing to a block that was recorded as
being bad, we clear the bad-block record.

This requires some delayed handling as the bad-block-list update has
to happen in process-context.

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>

md/raid1: avoid reading from known bad blocks.

Now that we have a bad block list, we should not read from those
blocks.
There are several main parts to this:
1/ read_balance needs to check for bad blocks, and return not only
the chosen device, but also how many good blocks are available
there.
2/ fix_read_error needs to avoid trying to read from bad blocks.
3/ read submission must be ready to issue multiple reads to
different devices as different bad blocks on different devices
could mean that a single large read cannot be served by any one
device, but can still be served by the array.
This requires keeping count of the number of outstanding requests
per bio. This count is stored in 'bi_phys_segments'
4/ retrying a read needs to also be ready to submit a smaller read
and queue another request for the rest.

This does not yet handle bad blocks when reading to perform resync,
recovery, or check.

'md_trim_bio' will also be used for RAID10, so put it in md.c and
export it.

Signed-off-by: NeilBrown <neilb@suse.de>

md: change managed of recovery_disabled.

If we hit a read error while recovering a mirror, we want to abort the
recovery without necessarily failing the disk - as having a disk this
a read error is better than not having an array at all.

Currently this is managed with a per-array flag "recovery_disabled"
and is only implemented for RAID1. For RAID10 we will need finer
grained control as we might want to disable recovery for individual
devices separately.

So push more of the decision making into the personality.
'recovery_disabled' is now a 'cookie' which is copied when the
personality want to disable recovery and is changed when a device is
added to the array as this is used as a trigger to 'try recovery
again'.

This will allow RAID10 to get the control that it needs.

Signed-off-by: NeilBrown <neilb@suse.de>

MD: raid1 changes to allow use by device mapper

MD RAID1: Changes to allow RAID1 to be used by device-mapper (dm-raid.c)

Added the necessary congestion function and conditionalize calls requiring an
array 'queue' or 'gendisk'.

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: improve handling of pages allocated for write-behind.

The current handling and freeing of these pages is a bit fragile.
We only keep the list of allocated pages in each bio, so we need to
still have a valid bio when freeing the pages, which is a bit clumsy.

So simply store the allocated page list in the r1_bio so it can easily
be found and freed when we are finished with the r1_bio.

Signed-off-by: NeilBrown <neilb@suse.de>

md/raid1: discard unused variable.

This structure field (flushing_bio_list) is never used, so remove it.

Signed-off-by: NeilBrown <neilb@suse.de>

md: implment REQ_FLUSH/FUA support

This patch converts md to support REQ_FLUSH/FUA instead of now
deprecated REQ_HARDBARRIER. In the core part (md.c), the following
changes are notable.

* Unlike REQ_HARDBARRIER, REQ_FLUSH/FUA don't interfere with
processing of other requests and thus there is no reason to mark the
queue congested while FLUSH/FUA is in progress.

* REQ_FLUSH/FUA failures are final and its users don't need retry
logic. Retry logic is removed.

* Preflush needs to be issued to all member devices but FUA writes can
be handled the same way as other writes - their processing can be
deferred to request_queue of member devices. md_barrier_request()
is renamed to md_flush_request() and simplified accordingly.

For linear, raid0 and multipath, the core changes are enough. raid1,
5 and 10 need the following conversions.

* raid1: Handling of FLUSH/FUA bio's can simply be deferred to
request_queues of member devices. Barrier related logic removed.

* raid5: Queue draining logic dropped. FUA bit is propagated through
biodrain and stripe resconstruction such that all the updated parts
of the stripe are written out with FUA writes if any of the dirtying
writes was FUA. preread_active_stripes handling in make_request()
is updated as suggested by Neil Brown.

* raid10: FUA bit needs to be propagated to write clones.

linear, raid0, 1, 5 and 10 tested.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Neil Brown <neilb@suse.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

md/raid1: add takeover support for raid5->raid1

A 2-device raid5 array can now be converted to raid1.

Signed-off-by: NeilBrown <neilb@suse.de>

md: remove mddev_to_conf "helper" macro

Having a macro just to cast a void* isn't really helpful.
I would must rather see that we are simply de-referencing ->private,
than have to know what the macro does.

So open code the macro everywhere and remove the pointless cast.

Signed-off-by: NeilBrown <neilb@suse.de>

md: move lots of #include lines out of .h files and into .c

This makes the includes more explicit, and is preparation for moving
md_k.h to drivers/md/md.h

Remove include/raid/md.h as its only remaining use was to #include
other files.

Signed-off-by: NeilBrown <neilb@suse.de>

md: move headers out of include/linux/raid/

Move the headers with the local structures for the disciplines and
bitmap.h into drivers/md/ so that they are more easily grepable for
hacking and not far away. md.h is left where it is for now as there
are some uses from the outside.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: NeilBrown <neilb@suse.de>