Struct bio has a reference count that controls when it can be freed.
Most uses cases is allocating the bio, which then returns with a
single reference to it, doing IO, and then dropping that single
reference. We can remove this atomic_dec_and_test() in the completion
path, if nobody else is holding a reference to the bio.

If someone does call bio_get() on the bio, then we flag the bio as
now having valid count and that we must properly honor the reference
count when it's being put.
Tested-by: NRobert Elliott <elliott@hp.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Struct bio has an atomic ref count for chained bio's, and we use this
to know when to end IO on the bio. However, most bio's are not chained,
so we don't need to always introduce this atomic operation as part of
ending IO.

Add a helper to elevate the bi_remaining count, and flag the bio as
now actually needing the decrement at end_io time. Rename the field
to __bi_remaining to catch any current users of this doing the
incrementing manually.

For high IOPS workloads, this reduces the overhead of bio_endio()
substantially.
Tested-by: NRobert Elliott <elliott@hp.com>
Acked-by: NKent Overstreet <kent.overstreet@gmail.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Signed-off-by: NJens Axboe <axboe@fb.com>

Rewrite __bio_copy_iov using the copy_page_{from,to}_iter helpers, and
split it into two simpler functions.

This commit should contain only literal replacements, without
functional changes.

Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NDongsu Park <dongsu.park@profitbricks.com>
[hch: removed the __bio_copy_iov wrapper]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

And also remove the unused bdev argument.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

This saves a little code, and allow to simplify the error handling.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Make use of a new interface provided by iov_iter, backed by
scatter-gather list of iovec, instead of the old interface based on
sg_iovec. Also use iov_iter_advance() instead of manual iteration.

This commit should contain only literal replacements, without
functional changes.

Cc: Christoph Hellwig <hch@infradead.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Doug Gilbert <dgilbert@interlog.com>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
[dpark: add more description in commit message]
Signed-off-by: NDongsu Park <dongsu.park@profitbricks.com>
[hch: fixed to do a deep clone of the iov_iter, and to properly use
      the iov_iter direction]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The code sniplet to walk all bio_vecs and free their pages is opencoded in
way to many places, so factor it into a helper.  Also convert the slightly
more complex cases in bio_kern_endio and __bio_copy_iov where we break
the freeing from an existing loop into a separate one.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Just open code the trivial mapping from a kernel virtual address to
a bio instead of going through the complex user address mapping
machinery.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The original behaviour is to refuse to add a new page if the maximum
number of segments has been reached, regardless of the fact the page we
are going to add can be merged into the last segment or not.

Unfortunately, when the system runs under heavy memory fragmentation
conditions, a driver may try to add multiple pages to the last segment.
The original code won't accept them and EBUSY will be reported to
userspace.

This patch modifies the function so it refuses to add a page only in case
the latter starts a new segment and the maximum number of segments has
already been reached.

The bug can be easily reproduced with the st driver:

1) set CONFIG_SCSI_MPT2SAS_MAX_SGE or CONFIG_SCSI_MPT3SAS_MAX_SGE  to 16
2) modprobe st buffer_kbs=1024
3) #dd if=/dev/zero of=/dev/st0 bs=1M count=10
   dd: error writing `/dev/st0': Device or resource busy
Signed-off-by: NMaurizio Lombardi <mlombard@redhat.com>
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Cc: Jet Chen <jet.chen@intel.com>
Cc: Tomas Henzl <thenzl@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

Many block drivers accounting io stat based on bio (e.g. NVMe...),
the blk_account_io_start/end() which is based on request
does not make sense to them, so here we introduce the similar help
function named generic_start/end_io_acct base on raw sectors, and it can
simplify some driver's open io accounting code.
Signed-off-by: NGu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Users of bio_clone_fast() do not want bios with their own bvecs.
Allocating a bvec mempool as part of the bioset intended for such users
is a waste of memory.

bioset_create_nobvec() creates a bioset that doesn't have the bvec
mempool.
Signed-off-by: NJun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Various subsystems can ask the bio subsystem to create a bio slab cache
with some free space before the bio.  This free space can be used for any
purpose.  Device mapper uses this per-bio-data feature to place some
target-specific and device-mapper specific data before the bio, so that
the target-specific data doesn't have to be allocated separately.

This per-bio-data mechanism is used in place of kmalloc, so we need the
allocated slab to have the same memory alignment as memory allocated
with kmalloc.

Change bio_find_or_create_slab() so that it uses ARCH_KMALLOC_MINALIGN
alignment when creating the slab cache.  This is needed so that dm-crypt
can use per-bio-data for encryption - the crypto subsystem assumes this
data will have the same alignment as kmalloc'ed memory.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Acked-by: NJens Axboe <axboe@fb.com>

This reverts commit 254c4407.

It causes crashes with cryptsetup, even after a few iterations and
updates. Drop it for now.

The original behaviour is to refuse to add a new page if the maximum
number of segments has been reached, regardless of the fact the page we
are going to add can be merged into the last segment or not.

Unfortunately, when the system runs under heavy memory fragmentation
conditions, a driver may try to add multiple pages to the last segment.
The original code won't accept them and EBUSY will be reported to
userspace.

This patch modifies the function so it refuses to add a page only in case
the latter starts a new segment and the maximum number of segments has
already been reached.

The bug can be easily reproduced with the st driver:

1) set CONFIG_SCSI_MPT2SAS_MAX_SGE or CONFIG_SCSI_MPT3SAS_MAX_SGE  to 16
2) modprobe st buffer_kbs=1024
3) #dd if=/dev/zero of=/dev/st0 bs=1M count=10
   dd: error writing `/dev/st0': Device or resource busy

[ming.lei@canonical.com: update bi_iter.bi_size before recounting segments]
Signed-off-by: NMaurizio Lombardi <mlombard@redhat.com>
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Tested-by: NDongsu Park <dongsu.park@profitbricks.com>
Tested-by: NJet Chen <jet.chen@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

Another restriction inherited for NVMe - those devices don't support
SG lists that have "gaps" in them. Gaps refers to cases where the
previous SG entry doesn't end on a page boundary. For NVMe, all SG
entries must start at offset 0 (except the first) and end on a page
boundary (except the last).
Signed-off-by: NJens Axboe <axboe@fb.com>

With commit 762380ad added support for chunk sizes and no merging
across them, it broke the rule of always allowing adding of a single
page to an empty bio. So relax the restriction a bit to allow for that,
similarly to what we have always done.

This fixes a crash with mkfs.xfs and 512b sector sizes on NVMe.
Reported-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Some drivers have different limits on what size a request should
optimally be, depending on the offset of the request. Similar to
dividing a device into chunks. Add a setting that allows the driver
to inform the block layer of such a chunk size. The block layer will
then prevent merging across the chunks.

This is needed to optimally support NVMe with a non-zero stripe size.
Signed-off-by: NJens Axboe <axboe@fb.com>

They really belong in block/, especially now since it's not in
drivers/block/ anymore. Additionally, the get_maintainer script
gets it wrong when in fs/.
Suggested-by: NChristoph Hellwig <hch@infradead.org>
Acked-by: NAl Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: NJens Axboe <axboe@fb.com>

Unlike the more usual refcnting, what css_tryget() provides is the
distinction between online and offline csses instead of protection
against upping a refcnt which already reached zero.  cgroup is
planning to provide actual tryget which fails if the refcnt already
reached zero.  Let's rename the existing trygets so that they clearly
indicate that they're onliness.

I thought about keeping the existing names as-are and introducing new
names for the planned actual tryget; however, given that each
controller participates in the synchronization of the online state, it
seems worthwhile to make it explicit that these functions are about
on/offline state.

Rename css_tryget() to css_tryget_online() and css_tryget_from_dir()
to css_tryget_online_from_dir().  This is pure rename.

v2: cgroup_freezer grew new usages of css_tryget().  Update
    accordingly.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Acked-by: NMichal Hocko <mhocko@suse.cz>
Acked-by: NLi Zefan <lizefan@huawei.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>

nr_segs is no longer used in bio_alloc_map_data since c8db4448
("block: Don't save/copy bvec array anymore")
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

bs is no longer used in biovec_create_pool since 9f060e22 ("block:
Convert integrity to bvec_alloc_bs()")
Signed-off-by: NFabian Frederick <fabf@skynet.be>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: NJens Axboe <axboe@fb.com>

Fix new kernel-doc warnings in fs/bio.c:

Warning(fs/bio.c:316): No description found for parameter 'bio'
Warning(fs/bio.c:316): No description found for parameter 'parent'
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

sg_iovec array passed to it can be const
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

When using device mapper, there are many "bio: create slab" messages in
the log. Device mapper targets have different front_pad, so each time when
we load a target that wasn't loaded before, we allocate a slab with the
appropriate front_pad and there is associated "bio: create slab" message.

This patch removes these messages, there is no need for them.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Immutable biovecs changed the way bio segments are treated in such a way that
bio_for_each_segment() cannot now do what we want for discard/write same bios,
since bi_size means something completely different for them.

Fortunately discard and write same bios never have more than a single biovec, so
bio_for_each_segment() is unnecessary and not terribly meaningful for them, but
we still have to special case them in a few places.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Tested-by: NRichard W.M. Jones <rjones@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

cgroup_subsys is a bit messier than it needs to be.

* The name of a subsys can be different from its internal identifier
  defined in cgroup_subsys.h.  Most subsystems use the matching name
  but three - cpu, memory and perf_event - use different ones.

* cgroup_subsys_id enums are postfixed with _subsys_id and each
  cgroup_subsys is postfixed with _subsys.  cgroup.h is widely
  included throughout various subsystems, it doesn't and shouldn't
  have claim on such generic names which don't have any qualifier
  indicating that they belong to cgroup.

* cgroup_subsys->subsys_id should always equal the matching
  cgroup_subsys_id enum; however, we require each controller to
  initialize it and then BUG if they don't match, which is a bit
  silly.

This patch cleans up cgroup_subsys names and initialization by doing
the followings.

* cgroup_subsys_id enums are now postfixed with _cgrp_id, and each
  cgroup_subsys with _cgrp_subsys.

* With the above, renaming subsys identifiers to match the userland
  visible names doesn't cause any naming conflicts.  All non-matching
  identifiers are renamed to match the official names.

  cpu_cgroup -> cpu
  mem_cgroup -> memory
  perf -> perf_event

* controllers no longer need to initialize ->subsys_id and ->name.
  They're generated in cgroup core and set automatically during boot.

* Redundant cgroup_subsys declarations removed.

* While updating BUG_ON()s in cgroup_init_early(), convert them to
  WARN()s.  BUGging that early during boot is stupid - the kernel
  can't print anything, even through serial console and the trap
  handler doesn't even link stack frame properly for back-tracing.

This patch doesn't introduce any behavior changes.

v2: Rebased on top of fe1217c4 ("net: net_cls: move cgroupfs
    classid handling into core").
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Acked-by: N"David S. Miller" <davem@davemloft.net>
Acked-by: N"Rafael J. Wysocki" <rjw@rjwysocki.net>
Acked-by: NMichal Hocko <mhocko@suse.cz>
Acked-by: NPeter Zijlstra <peterz@infradead.org>
Acked-by: NAristeu Rozanski <aris@redhat.com>
Acked-by: NIngo Molnar <mingo@redhat.com>
Acked-by: NLi Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Thomas Graf <tgraf@suug.ch>

This reverts commit 95d44038.

The patch is broken for on-stack bios, amongst other things.

In bio_endio if bio doesn't have bi_end_io (should be an error case),
we set bio to NULL and continue silently without freeing the bio. It
would be good to have a WARN and free the bio to avoid memory leak.
Signed-off-by: NMuthukumar Ratty <muthur@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>

The new bio_split() can split arbitrary bios - it's not restricted to
single page bios, like the old bio_split() (previously renamed to
bio_pair_split()). It also has different semantics - it doesn't allocate
a struct bio_pair, leaving it up to the caller to handle completions.

Then convert the existing bio_pair_split() users to the new bio_split()
- and also nvme, which was open coding bio splitting.

(We have to take that BUG_ON() out of bio_integrity_trim() because this
bio_split() needs to use it, and there's no reason it has to be used on
bios marked as cloned; BIO_CLONED doesn't seem to have clearly
documented semantics anyways.)
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Neil Brown <neilb@suse.de>

This is prep work for introducing a more general bio_split().
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: NeilBrown <neilb@suse.de>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Peter Osterlund <petero2@telia.com>
Cc: Sage Weil <sage@inktank.com>

This adds a generic mechanism for chaining bio completions. This is
going to be used for a bio_split() replacement, and it turns out to be
very useful in a fair amount of driver code - a fair number of drivers
were implementing this in their own roundabout ways, often painfully.

Note that this means it's no longer to call bio_endio() more than once
on the same bio! This can cause problems for drivers that save/restore
bi_end_io. Arguably they shouldn't be saving/restoring bi_end_io at all
- in all but the simplest cases they'd be better off just cloning the
bio, and immutable biovecs is making bio cloning cheaper. But for now,
we add a bio_endio_nodec() for these cases.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>

Now that drivers have been converted to the new bvec_iter primitives,
there's no need to trim the bvec before we submit it; and we can't trim
it once we start sharing bvecs.

It used to be that passing a partially completed bio (i.e. one with
nonzero bi_idx) to generic_make_request() was a dangerous thing -
various drivers would choke on such things. But with immutable biovecs
and our new bio splitting that shares the biovecs, submitting partially
completed bios has to work (and should work, now that all the drivers
have been completed to the new primitives)
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>

Now that drivers have been converted to the bvec_iter primitives, they
shouldn't be modifying the biovec anymore and thus saving it is
unnecessary - code that was previously making a backup of the bvec array
can now just save bio->bi_iter.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>

We need to convert the dm code to the new bvec_iter primitives which
respect bi_bvec_done; they also allow us to drastically simplify dm's
bio splitting code.

Also, it's no longer necessary to save/restore the bvec array anymore -
driver conversions for immutable bvecs are done, so drivers should never
be modifying it.

Also kill bio_sector_offset(), dm was the only user and it doesn't make
much sense anymore.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: dm-devel@redhat.com
Reviewed-by: NMike Snitzer <snitzer@redhat.com>

bio_clone() just got more expensive - however, most users of bio_clone()
don't actually need to modify the biovec. If they aren't modifying the
biovec, and they can guarantee that the original bio isn't freed before
the clone (also true in most cases), we can just point the clone at the
original bio's biovec.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>

bio_clone() needs to produce a bio that's suitable for the caller to
munge with the biovec. Part of the immutable biovec patch series is
fixing stuff up so that submitting partially completed bios is safe and
works: thus, we now need bio_clone() on a partially completed bio to
produce a bio for which bi_idx and bi_bvec done are 0 - like they would
be if the caller had just allocated a new bio.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>

Now that we've got a mechanism for immutable biovecs -
bi_iter.bi_bvec_done - we need to convert drivers to use primitives that
respect it instead of using the bvec array directly.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: NeilBrown <neilb@suse.de>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: dm-devel@redhat.com

When we start sharing biovecs, keeping bi_vcnt accurate for splits is
going to be error prone - and unnecessary, if we refactor some code.

So bio_segments() has to go - but most of the existing users just needed
to know if the bio had multiple segments, which is easier - add a
bio_multiple_segments() for them.

(Two of the current uses of bio_segments() are going to go away in a
couple patches, but the current implementation of bio_segments() is
unsafe as soon as we start doing driver conversions for immutable
biovecs - so implement a dumb version for bisectability, it'll go away
in a couple patches)
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com>
Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>