cgroup is trying to make interface consistent across different
controllers.  For weight based resource control, the knob should have
the range [1, 10000] and default to 100.  This patch updates
cfq-iosched so that the weight range conforms.  The internal
calculations have enough range and the widening of the weight range
shouldn't cause any problem.

* blkcg_policy->cpd_bind_fn() is added.  If present, this is invoked
  when blkcg is attached to a hierarchy.

* cfq_cpd_init() is updated to use the new default value on the
  unified hierarchy.

* cfq_cpd_bind() callback is implemented to clear per-blkg configs and
  apply the default config matching the hierarchy type.

* cfqd->root_group->[leaf_]weight initialization in cfq_init_queue()
  is moved into !CONFIG_CFQ_GROUP_IOSCHED block.  cfq_cpd_bind() is
  now responsible for initializing the initial weights when blkcg is
  enabled.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg interface grew to be the biggest of all controllers and
unfortunately most inconsistent too.  The interface files are
inconsistent with a number of cloes duplicates.  Some files have
recursive variants while others don't.  There's distinction between
normal and leaf weights which isn't intuitive and there are a lot of
stat knobs which don't make much sense outside of debugging and expose
too much implementation details to userland.

In the unified hierarchy, everything is always hierarchical and
internal nodes can't have tasks rendering the two structural issues
twisting the current interface.  The interface has to be updated in a
significant anyway and this is a good chance to revamp it as a whole.
This patch implements blkcg interface for the unified hierarchy.

* (from a previous patch) blkcg is identified by "io" instead of
  "blkio" on the unified hierarchy.  Given that the whole interface is
  updated anyway, the rename shouldn't carry noticeable conversion
  overhead.

* The original interface consisted of 27 files is replaced with the
  following three files.

  blkio.stat	: per-blkcg stats
  blkio.weight	: per-cgroup and per-cgroup-queue weight settings
  blkio.max	: per-cgroup-queue bps and iops max limits

Documentation/cgroups/unified-hierarchy.txt updated accordingly.

v2: blkcg_policy->dfl_cftypes wasn't removed on
    blkcg_policy_unregister() corrupting the cftypes list.  Fixed.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

* Export blkg_dev_name()

* Drop unnecessary @cft from __cfq_set_weight().
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

Currently, blkg_conf_prep() expects input to be of the following form

 MAJ:MIN NUM

and reads the NUM part into blkg_conf_ctx->v.  This is quite
restrictive and gets in the way in implementing blkcg interface for
the unified hierarchy.  This patch updates blkg_conf_prep() so that it
expects

 MAJ:MIN BODY_STR

where BODY_STR is an arbitrary string.  blkg_conf_ctx->v is replaced
with ->body which is a char pointer pointing to the start of BODY_STR.
Parsing of the body is moved to blkg_conf_prep()'s callers.

To allow using, for example, strsep() on blkg_conf_ctx->val, it is a
non-const pointer and to accommodate that const is dropped from @input
too.

This doesn't cause any behavior changes.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg is about to grow interface for the unified hierarchy.  Add
legacy to existing cftypes.

* blkcg_policy->cftypes -> blkcg_policy->legacy_cftypes
* blk-cgroup.c:blkcg_files -> blkcg_legacy_files
* cfq-iosched.c:cfq_blkcg_files -> cfq_blkcg_legacy_files
* blk-throttle.c:throtl_files -> throtl_legacy_files

Pure renames.  No functional change.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkio interface has become messy over time and is currently the
largest.  In addition to the inconsistent naming scheme, it has
multiple stat files which report more or less the same thing, a number
of debug stat files which expose internal details which shouldn't have
been part of the public interface in the first place, recursive and
non-recursive stats and leaf and non-leaf knobs.

Both recursive vs. non-recursive and leaf vs. non-leaf distinctions
don't make any sense on the unified hierarchy as only leaf cgroups can
contain processes.  cgroups is going through a major interface
revision with the unified hierarchy involving significant fundamental
usage changes and given that a significant portion of the interface
doesn't make sense anymore, it's a good time to reorganize the
interface.

As the first step, this patch renames the external visible subsystem
name from "blkio" to "io".  This is more concise, matches the other
two major subsystem names, "cpu" and "memory", and better suited as
blkcg will be involved in anything writeback related too whether an
actual block device is involved or not.

As the subsystem legacy_name is set to "blkio", the only userland
visible change outside the unified hierarchy is that blkcg is reported
as "io" instead of "blkio" in the subsystem initialized message during
boot.  On the unified hierarchy, blkcg now appears as "io".
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: cgroups@vger.kernel.org
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg currently returns -EINVAL for most errors which can be pretty
confusing given that the failure modes are quite varied.  Update the
error returns so that

* -EINVAL only for syntactic errors.
* -ERANGE if the value is out of range.
* -ENODEV if the target device can't be found.
* -EOPNOTSUPP if the policy is not enabled on the target device.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

The recent percpu conversion of blkg_rwstat triggered the following
warning in certain configurations.

 block/blk-cgroup.c:654:1: warning: the frame size of 1360 bytes is larger than 1024 bytes

This is because blkg_rwstat now contains four percpu_counter which can
be pretty big depending on debug options although it shouldn't be a
problem in production configs.  This patch removes one of the two
local blkg_rwstat variables used by blkg_rwstat_recursive_sum() to
reduce stack usage.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Link: http://article.gmane.org/gmane.linux.kernel.cgroups/13835Signed-off-by: NJens Axboe <axboe@fb.com>

Currently, both cfq-iosched and blk-throttle keep track of
io_service_bytes and io_serviced stats.  While keeping track of them
separately may be useful during development, it doesn't make much
sense otherwise.  Also, blk-throttle was counting bio's as IOs while
cfq-iosched request's, which is more confusing than informative.

This patch adds ->stat_bytes and ->stat_ios to blkg (blkcg_gq),
removes the counterparts from cfq-iosched and blk-throttle and let
them print from the common blkg counters.  The common counters are
incremented during bio issue in blkcg_bio_issue_check().

The outputs are still filtered by whether the policy has
blkg_policy_data on a given blkg, so cfq's output won't show up if it
has never been used for a given blkg.  The only times when the outputs
would differ significantly are when policies are attached on the fly
or elevators are switched back and forth.  Those are quite exceptional
operations and I don't think they warrant keeping separate counters.

v3: Update blkio-controller.txt accordingly.

v2: Account IOs during bio issues instead of request completions so
    that bio-based drivers can be handled the same way.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Currently, blkg_[rw]stat_recursive_sum() assume that the target
counter is located in pd (blkg_policy_data); however, some counters
are planned to be moved to blkg (blkcg_gq).

This patch updates blkg_[rw]stat_recursive_sum() to take blkg and
blkg_policy pointers instead of pd.  If policy is NULL, it indexes
into blkg.  If non-NULL, into the blkg's pd of the policy.

The existing usages are updated to maintain the current behaviors.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg_[rw]stat are used as stat counters for blkcg policies.  It isn't
per-cpu by itself and blk-throttle makes it per-cpu by wrapping around
it.  This patch makes blkcg_[rw]stat per-cpu and drop the ad-hoc
per-cpu wrapping in blk-throttle.

* blkg_[rw]stat->cnt is replaced with cpu_cnt which is struct
  percpu_counter.  This makes syncp unnecessary as remote accesses are
  handled by percpu_counter itself.

* blkg_[rw]stat_init() can now fail due to percpu allocation failure
  and thus are updated to return int.

* percpu_counters need explicit freeing.  blkg_[rw]stat_exit() added.

* As blkg_rwstat->cpu_cnt[] can't be read directly anymore, reading
  and summing results are stored in ->aux_cnt[] instead.

* Custom per-cpu stat implementation in blk-throttle is removed.

This makes all blkcg stat counters per-cpu without complicating policy
implmentations.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

cgroup stats are local to each cgroup and doesn't propagate to
ancestors by default.  When recursive stats are necessary, the sum is
calculated over all the descendants.  This initially was for backward
compatibility to support both group-local and recursive stats but this
mode of operation makes general sense as stat update is much hotter
thafn reporting those stats.

This however ends up losing recursive stats when a child is removed.
To work around this, cfq-iosched adds its stats to its parent
cfq_group->dead_stats which is summed up together when calculating
recursive stats.

It's planned that the core stats will be moved to blkcg_gq, so we want
to move the mechanism for keeping track of the stats of dead children
from cfq to blkcg core.  This patch adds blkg_[rw]stat->aux_cnt which
are atomic64_t's keeping track of auxiliary counts which are excluded
when reading local counts but included for recursive.

blkg_[rw]stat_merge() which were used by cfq to implement dead_stats
are replaced by blkg_[rw]stat_add_aux(), and cfq now forwards stats of
a dead cgroup to the aux counts of parent->stats instead of separate
->dead_stats.

This will also help making blkg_[rw]stats per-cpu.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkg (blkcg_gq) currently is created by blkcg policies invoking
blkg_lookup_create() which ends up repeating about the same code in
different policies.  Theoretically, this can avoid the overhead of
looking and/or creating blkg's if blkcg is enabled but no policy is in
use; however, the cost of blkg lookup / creation is very low
especially if only the root blkcg is in use which is highly likely if
no blkcg policy is in active use - it boils down to a single very
predictable conditional and surrounding RCU protection.

This patch consolidates blkg creation to a new function
blkcg_bio_issue_check() which is called during bio issue from
generic_make_request_checks().  blkcg_bio_issue_check() is now the
only function which tries to create missing blkg's.  The subsequent
policy and request_list operations just perform blkg_lookup() and if
missing falls back to the root.

* blk_get_rl() no longer tries to create blkg.  It uses blkg_lookup()
  instead of blkg_lookup_create().

* blk_throtl_bio() is now called from blkcg_bio_issue_check() with rcu
  read locked and blkg already looked up.  Both throtl_lookup_tg() and
  throtl_lookup_create_tg() are dropped.

* cfq is similarly updated.  cfq_lookup_create_cfqg() is replaced with
  cfq_lookup_cfqg()which uses blkg_lookup().

This consolidates blkg handling and avoids unnecessary blkg creation
retries under memory pressure.  In addition, this provides a common
bio entry point into blkcg where things like common accounting can be
performed.

v2: Build fixes for !CONFIG_CFQ_GROUP_IOSCHED and
    !CONFIG_BLK_DEV_THROTTLING.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkg_lookup() checks whether the target queue is bypassing and, if
not, calls __blkg_lookup() which first checks the lookup hint and then
performs radix tree walk.  The operations upto hint checking are
trivial and there are many users of this function.  This patch inlines
blkg_lookup() and the fast path part of __blkg_lookup().  The radix
tree lookup and hint update are now in blkg_lookup_slowpath().

This will help consolidating blkg handling by easing moving root blkcg
short-circuit to inlined lookup fast path.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Each active policy has a cpd (blkcg_policy_data) on each blkcg.  The
cpd's were allocated by blkcg core and each policy could request to
allocate extra space at the end by setting blkcg_policy->cpd_size
larger than the size of cpd.

This is a bit unusual but blkg (blkcg_gq) policy data used to be
handled this way too so it made sense to be consistent; however, blkg
policy data switched to alloc/free callbacks.

This patch makes similar changes to cpd handling.
blkcg_policy->cpd_alloc/free_fn() are added to replace ->cpd_size.  As
cpd allocation is now done from policy side, it can simply allocate a
larger area which embeds cpd at the beginning.

As ->cpd_alloc_fn() may be able to perform all necessary
initializations, this patch makes ->cpd_init_fn() optional.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

* Rename blkcg->pd[] to blkcg->cpd[] so that cpd is consistently used
  for blkcg_policy_data.

* Make blkcg_policy->cpd_init_fn() take blkcg_policy_data instead of
  blkcg.  This makes it consistent with blkg_policy_data methods and
  to-be-added cpd alloc/free methods.

* blkcg_policy_data->blkcg and cpd_to_blkcg() added so that
  cpd_init_fn() can determine the associated blkcg from
  blkcg_policy_data.

v2: blkcg_policy_data->blkcg initializations were missing.  Added.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

The newly added ->pd_alloc_fn() and ->pd_free_fn() deal with pd
(blkg_policy_data) while the older ones use blkg (blkcg_gq).  As using
blkg doesn't make sense for ->pd_alloc_fn() and after allocation pd
can always be mapped to blkg and given that these are policy-specific
methods, it makes sense to converge on pd.

This patch makes all methods deal with pd instead of blkg.  Most
conversions are trivial.  In blk-cgroup.c, a couple method invocation
sites now test whether pd exists instead of policy state for
consistency.  This shouldn't cause any behavioral differences.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

With the recent addition of alloc and free methods, things became
messier.  This patch reorganizes them according to the followings.

* ->pd_alloc_fn()

  Responsible for allocation and static initializations - the ones
  which can be done independent of where the pd might be attached.

* ->pd_init_fn()

  Initializations which require the knowledge of where the pd is
  attached.

* ->pd_free_fn()

  The counter part of pd_alloc_fn().  Static de-init and freeing.

This leaves ->pd_exit_fn() without any users.  Removed.

While at it, collapse an one liner function throtl_pd_exit(), which
has only one user, into its user.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

A blkg (blkcg_gq) represents the relationship between a cgroup and
request_queue.  Each active policy has a pd (blkg_policy_data) on each
blkg.  The pd's were allocated by blkcg core and each policy could
request to allocate extra space at the end by setting
blkcg_policy->pd_size larger than the size of pd.

This is a bit unusual but was done this way mostly to simplify error
handling and all the existing use cases could be handled this way;
however, this is becoming too restrictive now that percpu memory can
be allocated without blocking.

This introduces two new mandatory blkcg_policy methods - pd_alloc_fn()
and pd_free_fn() - which are used to allocate and release pd for a
given policy.  As pd allocation is now done from policy side, it can
simply allocate a larger area which embeds pd at the beginning.  This
change makes ->pd_size pointless.  Removed.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkg_create() allows NULL ->pd_init_fn() but blkcg_activate_policy()
doesn't.  As both in-kernel policies implement ->pd_init_fn, it
currently doesn't break anything.  Update blkcg_activate_policy() so
that its behavior is consistent with blkg_create().
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

When a policy gets activated, it needs to allocate and install its
policy data on all existing blkg's (blkcg_gq's).  Because blkg
iteration is protected by a spinlock, it currently counts the total
number of blkg's in the system, allocates the matching number of
policy data on a list and installs them during a single iteration.

This can be simplified by using speculative GFP_NOWAIT allocations
while iterating and falling back to a preallocated policy data on
failure.  If the preallocated one has already been consumed, it
releases the lock, preallocate with GFP_KERNEL and then restarts the
iteration.  This can be a bit more expensive than before but policy
activation is a very cold path and shouldn't matter.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg_css_alloc() bypasses policy data allocation and blkcg_css_free()
bypasses policy data and blkcg freeing for blkcg_root.  There's no
reason to to treat policy data any differently for blkcg_root.  If the
root css gets allocated after policies are registered, policy
registration path will add policy data; otherwise, the alloc path
will.  The free path isn't never invoked for root csses.

This patch removes the unnecessary special handling of blkcg_root from
css_alloc/free paths.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

When blkcg_init_queue() fails midway after creating a new blkg, it
performs kfree() directly; however, this doesn't free the policy data
areas.  Make it use blkg_free() instead.  In turn, blkg_free() is
updated to handle root request_list special case.

While this fixes a possible memory leak, it's on an unlikely failure
path of an already cold path and the size leaked per occurrence is
miniscule too.  I don't think it needs to be tagged for -stable.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg performs several allocations to track IOs per cgroup and enforce
resource control.  Most of these allocations are performed lazily on
demand in the IO path and thus can't involve reclaim path.  Currently,
these allocations use GFP_ATOMIC; however, blkcg can gracefully deal
with occassional failures of these allocations by punting IOs to the
root cgroup and there's no reason to reach into the emergency reserve.

This patch replaces GFP_ATOMIC with GFP_NOWAIT for the following
allocations.

* bdi_writeback_congested and blkcg_gq allocations in blkg_create().

* radix tree node allocations for blkcg->blkg_tree.

* cfq_queue allocation on ioprio changes.
Signed-off-by: NTejun Heo <tj@kernel.org>
Suggested-and-Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Suggested-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

When a blkcg configuration is targeted to a partition rather than a
whole device, blkg_conf_prep fails with -EINVAL; unfortunately, it
forgets to put the gendisk ref in that case.  Fix it.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: NJens Axboe <axboe@fb.com>

e48453c3 ("block, cgroup: implement policy-specific per-blkcg
data") updated per-blkcg policy data to be dynamically allocated.
When a policy is registered, its policy data aren't created.  Instead,
when the policy is activated on a queue, the policy data are allocated
if there are blkg's (blkcg_gq's) which are attached to a given blkcg.
This is buggy.  Consider the following scenario.

1. A blkcg is created.  No blkg's attached yet.

2. The policy is registered.  No policy data is allocated.

3. The policy is activated on a queue.  As the above blkcg doesn't
   have any blkg's, it won't allocate the matching blkcg_policy_data.

4. An IO is issued from the blkcg and blkg is created and the blkcg
   still doesn't have the matching policy data allocated.

With cfq-iosched, this leads to an oops.

It also doesn't free policy data on policy unregistration assuming
that freeing of all policy data on blkcg destruction should take care
of it; however, this also is incorrect.

1. A blkcg has policy data.

2. The policy gets unregistered but the policy data remains.

3. Another policy gets registered on the same slot.

4. Later, the new policy tries to allocate policy data on the previous
   blkcg but the slot is already occupied and gets skipped.  The
   policy ends up operating on the policy data of the previous policy.

There's no reason to manage blkcg_policy_data lazily.  The reason we
do lazy allocation of blkg's is that the number of all possible blkg's
is the product of cgroups and block devices which can reach a
surprising level.  blkcg_policy_data is contrained by the number of
cgroups and shouldn't be a problem.

This patch makes blkcg_policy_data to be allocated for all existing
blkcg's on policy registration and freed on unregistration and removes
blkcg_policy_data handling from policy [de]activation paths.  This
makes that blkcg_policy_data are created and removed with the policy
they belong to and fixes the above described problems.
Signed-off-by: NTejun Heo <tj@kernel.org>
Fixes: e48453c3 ("block, cgroup: implement policy-specific per-blkcg data")
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add all_blkcgs list goes through blkcg->all_blkcgs_node and is
protected by blkcg_pol_mutex.  This will be used to fix
blkcg_policy_data allocation bug.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

An entry in blkcg_policy[] is stable while there are non-bypassing
in-flight IOs on a request_queue which has the policy activated.  This
is why most derefs of blkcg_policy[] don't need explicit locking;
however, blkcg_css_alloc() isn't invoked from IO path and thus doesn't
have this protection and may race policies being added and removed.

Fix it by adding explicit blkcg_pol_mutex protection around
blkcg_policy[] iteration in blkcg_css_alloc().
Signed-off-by: NTejun Heo <tj@kernel.org>
Fixes: e48453c3 ("block, cgroup: implement policy-specific per-blkcg data")
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg_pol_mutex primarily protects the blkcg_policy array.  It also
protects cgroup file type [un]registration during policy addition /
removal.  This puts blkcg_pol_mutex outside cgroup internal
synchronization and in turn makes it impossible to grab from blkcg's
cgroup methods as that leads to cyclic dependency.

Another problematic dependency arising from this is through cgroup
interface file deactivation.  Removing a cftype requires removing all
files of the type which in turn involves draining all on-going
invocations of the file methods.  This means that an interface file
implementation can't grab blkcg_pol_mutex as draining can lead to AA
deadlock.

blkcg_reset_stats() is already in this situation.  It currently
trylocks blkcg_pol_mutex and then unwinds and retries the whole
operation on failure, which is cumbersome at best.  It has a lengthy
comment explaining how cgroup internal synchronization is involved and
expected to be updated but as explained above this doesn't need cgroup
internal locking to deadlock.  It's a self-contained AA deadlock.

The described circular dependencies can be easily broken by moving
cftype [un]registration out of blkcg_pol_mutex and protect them with
an outer mutex.  This patch introduces blkcg_pol_register_mutex which
wraps entire policy [un]registration including cftype operations and
shrinks blkcg_pol_mutex critical section.  This also makes the trylock
dancing in blkcg_reset_stats() unnecessary.  Removed.

This patch is necessary for the following blkcg_policy_data allocation
bug fixes.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Currently, per-blkcg data is freed each time a policy is deactivated,
that is also upon scheduler switch. However, when switching from a
scheduler implementing a policy which requires per-blkcg data to
another one, that same policy might be active on other devices, and
therefore those same per-blkcg data could be still in use.
This commit lets per-blkcg data be freed when the blkcg is freed
instead of on policy deactivation.
Signed-off-by: NArianna Avanzini <avanzini.arianna@gmail.com>
Reported-and-tested-by: NMichael Kaminsky <kaminsky@cs.cmu.edu>
Fixes: e48453c3 ("block, cgroup: implement policy-specific per-blkcg data")
Signed-off-by: NJens Axboe <axboe@fb.com>

The block IO (blkio) controller enables the block layer to provide service
guarantees in a hierarchical fashion. Specifically, service guarantees
are provided by registered request-accounting policies. As of now, a
proportional-share and a throttling policy are available. They are
implemented, respectively, by the CFQ I/O scheduler and the blk-throttle
subsystem. Unfortunately, as for adding new policies, the current
implementation of the block IO controller is only halfway ready to allow
new policies to be plugged in. This commit provides a solution to make
the block IO controller fully ready to handle new policies.
In what follows, we first describe briefly the current state, and then
list the changes made by this commit.

The throttling policy does not need any per-cgroup information to perform
its task. In contrast, the proportional share policy uses, for each cgroup,
both the weight assigned by the user to the cgroup, and a set of dynamically-
computed weights, one for each device.

The first, user-defined weight is stored in the blkcg data structure: the
block IO controller allocates a private blkcg data structure for each
cgroup in the blkio cgroups hierarchy (regardless of which policy is active).
In other words, the block IO controller internally mirrors the blkio cgroups
with private blkcg data structures.

On the other hand, for each cgroup and device, the corresponding dynamically-
computed weight is maintained in the following, different way. For each device,
the block IO controller keeps a private blkcg_gq structure for each cgroup in
blkio. In other words, block IO also keeps one private mirror copy of the blkio
cgroups hierarchy for each device, made of blkcg_gq structures.
Each blkcg_gq structure keeps per-policy information in a generic array of
dynamically-allocated 'dedicated' data structures, one for each registered
policy (so currently the array contains two elements). To be inserted into the
generic array, each dedicated data structure embeds a generic blkg_policy_data
structure. Consider now the array contained in the blkcg_gq structure
corresponding to a given pair of cgroup and device: one of the elements
of the array contains the dedicated data structure for the proportional-share
policy, and this dedicated data structure contains the dynamically-computed
weight for that pair of cgroup and device.

The generic strategy adopted for storing per-policy data in blkcg_gq structures
is already capable of handling new policies, whereas the one adopted with blkcg
structures is not, because per-policy data are hard-coded in the blkcg
structures themselves (currently only data related to the proportional-
share policy).

This commit addresses the above issues through the following changes:
. It generalizes blkcg structures so that per-policy data are stored in the same
  way as in blkcg_gq structures.
  Specifically, it lets also the blkcg structure store per-policy data in a
  generic array of dynamically-allocated dedicated data structures. We will
  refer to these data structures as blkcg dedicated data structures, to
  distinguish them from the dedicated data structures inserted in the generic
  arrays kept by blkcg_gq structures.
  To allow blkcg dedicated data structures to be inserted in the generic array
  inside a blkcg structure, this commit also introduces a new blkcg_policy_data
  structure, which is the equivalent of blkg_policy_data for blkcg dedicated
  data structures.
. It adds to the blkcg_policy structure, i.e., to the descriptor of a policy, a
  cpd_size field and a cpd_init field, to be initialized by the policy with,
  respectively, the size of the blkcg dedicated data structures, and the
  address of a constructor function for blkcg dedicated data structures.
. It moves the CFQ-specific fields embedded in the blkcg data structure (i.e.,
  the fields related to the proportional-share policy), into a new blkcg
  dedicated data structure called cfq_group_data.
Signed-off-by: NPaolo Valente <paolo.valente@unimore.it>
Signed-off-by: NArianna Avanzini <avanzini.arianna@gmail.com>
Acked-by: NTejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

A blkg (blkcg_gq) can be congested and decongested independently from
other blkgs on the same request_queue.  Accordingly, for cgroup
writeback support, the congestion status at bdi (backing_dev_info)
should be split and updated separately from matching blkg's.

This patch prepares by adding blkg->wb_congested and associating a
blkg with its matching per-blkcg bdi_writeback_congested on creation.

v2: Updated to associate bdi_writeback_congested instead of
    bdi_writeback.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

For the planned cgroup writeback support, on each bdi
(backing_dev_info), each memcg will be served by a separate wb
(bdi_writeback).  This patch updates bdi so that a bdi can host
multiple wbs (bdi_writebacks).

On the default hierarchy, blkcg implicitly enables memcg.  This allows
using memcg's page ownership for attributing writeback IOs, and every
memcg - blkcg combination can be served by its own wb by assigning a
dedicated wb to each memcg.  This means that there may be multiple
wb's of a bdi mapped to the same blkcg.  As congested state is per
blkcg - bdi combination, those wb's should share the same congested
state.  This is achieved by tracking congested state via
bdi_writeback_congested structs which are keyed by blkcg.

bdi->wb remains unchanged and will keep serving the root cgroup.
cgwb's (cgroup wb's) for non-root cgroups are created on-demand or
looked up while dirtying an inode according to the memcg of the page
being dirtied or current task.  Each cgwb is indexed on bdi->cgwb_tree
by its memcg id.  Once an inode is associated with its wb, it can be
retrieved using inode_to_wb().

Currently, none of the filesystems has FS_CGROUP_WRITEBACK and all
pages will keep being associated with bdi->wb.

v3: inode_attach_wb() in account_page_dirtied() moved inside
    mapping_cap_account_dirty() block where it's known to be !NULL.
    Also, an unnecessary NULL check before kfree() removed.  Both
    detected by the kbuild bot.

v2: Updated so that wb association is per inode and wb is per memcg
    rather than blkcg.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: kbuild test robot <fengguang.wu@intel.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add global constant blkcg_root_css which points to &blkcg_root.css.
This will be used by cgroup writeback support.  If blkcg is disabled,
it's defined as ERR_PTR(-EINVAL).

v2: The declarations moved to include/linux/blk-cgroup.h as suggested
    by Vivek.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: NJens Axboe <axboe@fb.com>

Currently, blkcg does a minor optimization where the root blkcg is
created when the first blkcg policy is activated on a queue and
destroyed on the deactivation of the last.  On systems where blkcg is
configured but not used, this saves one blkcg_gq struct per queue.  On
systems where blkcg is actually used, there's no difference.  The only
case where this can lead to any meaninful, albeit still minute, save
in memory consumption is when all blkcg policies are deactivated after
being widely used in the system, which is a hihgly unlikely scenario.

The conditional existence of root blkcg_gq has already created several
bugs in blkcg and became an issue once again for the new per-cgroup
wb_congested mechanism for cgroup writeback support leading to a NULL
dereference when no blkcg policy is active.  This is really not worth
bothering with.  This patch makes blkcg always allocate and link the
root blkcg_gq and release it only on queue destruction.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

cgroup aware writeback support will require exposing some of blkcg
details.  In preprataion, move block/blk-cgroup.h to
include/linux/blk-cgroup.h.  This patch is pure file move.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blkcg->id is a unique id given to each blkcg; however, the
cgroup_subsys_state which each blkcg embeds already has ->serial_nr
which can be used for the same purpose.  Drop blkcg->id and replace
its uses with blkcg->css.serial_nr.  Rename cfq_cgroup->blkcg_id to
->blkcg_serial_nr and @id in check_blkcg_changed() to @serial_nr for
consistency.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

While a queue is being destroyed, all the blkgs are destroyed and its
->root_blkg pointer is set to NULL.  If someone else starts to drain
while the queue is in this state, the following oops happens.

  NULL pointer dereference at 0000000000000028
  IP: [<ffffffff8144e944>] blk_throtl_drain+0x84/0x230
  PGD e4a1067 PUD b773067 PMD 0
  Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
  Modules linked in: cfq_iosched(-) [last unloaded: cfq_iosched]
  CPU: 1 PID: 537 Comm: bash Not tainted 3.16.0-rc3-work+ #2
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  task: ffff88000e222250 ti: ffff88000efd4000 task.ti: ffff88000efd4000
  RIP: 0010:[<ffffffff8144e944>]  [<ffffffff8144e944>] blk_throtl_drain+0x84/0x230
  RSP: 0018:ffff88000efd7bf0  EFLAGS: 00010046
  RAX: 0000000000000000 RBX: ffff880015091450 RCX: 0000000000000001
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
  RBP: ffff88000efd7c10 R08: 0000000000000000 R09: 0000000000000001
  R10: ffff88000e222250 R11: 0000000000000000 R12: ffff880015091450
  R13: ffff880015092e00 R14: ffff880015091d70 R15: ffff88001508fc28
  FS:  00007f1332650740(0000) GS:ffff88001fa80000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
  CR2: 0000000000000028 CR3: 0000000009446000 CR4: 00000000000006e0
  Stack:
   ffffffff8144e8f6 ffff880015091450 0000000000000000 ffff880015091d80
   ffff88000efd7c28 ffffffff8144ae2f ffff880015091450 ffff88000efd7c58
   ffffffff81427641 ffff880015091450 ffffffff82401f00 ffff880015091450
  Call Trace:
   [<ffffffff8144ae2f>] blkcg_drain_queue+0x1f/0x60
   [<ffffffff81427641>] __blk_drain_queue+0x71/0x180
   [<ffffffff81429b3e>] blk_queue_bypass_start+0x6e/0xb0
   [<ffffffff814498b8>] blkcg_deactivate_policy+0x38/0x120
   [<ffffffff8144ec44>] blk_throtl_exit+0x34/0x50
   [<ffffffff8144aea5>] blkcg_exit_queue+0x35/0x40
   [<ffffffff8142d476>] blk_release_queue+0x26/0xd0
   [<ffffffff81454968>] kobject_cleanup+0x38/0x70
   [<ffffffff81454848>] kobject_put+0x28/0x60
   [<ffffffff81427505>] blk_put_queue+0x15/0x20
   [<ffffffff817d07bb>] scsi_device_dev_release_usercontext+0x16b/0x1c0
   [<ffffffff810bc339>] execute_in_process_context+0x89/0xa0
   [<ffffffff817d064c>] scsi_device_dev_release+0x1c/0x20
   [<ffffffff817930e2>] device_release+0x32/0xa0
   [<ffffffff81454968>] kobject_cleanup+0x38/0x70
   [<ffffffff81454848>] kobject_put+0x28/0x60
   [<ffffffff817934d7>] put_device+0x17/0x20
   [<ffffffff817d11b9>] __scsi_remove_device+0xa9/0xe0
   [<ffffffff817d121b>] scsi_remove_device+0x2b/0x40
   [<ffffffff817d1257>] sdev_store_delete+0x27/0x30
   [<ffffffff81792ca8>] dev_attr_store+0x18/0x30
   [<ffffffff8126f75e>] sysfs_kf_write+0x3e/0x50
   [<ffffffff8126ea87>] kernfs_fop_write+0xe7/0x170
   [<ffffffff811f5e9f>] vfs_write+0xaf/0x1d0
   [<ffffffff811f69bd>] SyS_write+0x4d/0xc0
   [<ffffffff81d24692>] system_call_fastpath+0x16/0x1b

776687bc ("block, blk-mq: draining can't be skipped even if
bypass_depth was non-zero") made it easier to trigger this bug by
making blk_queue_bypass_start() drain even when it loses the first
bypass test to blk_cleanup_queue(); however, the bug has always been
there even before the commit as blk_queue_bypass_start() could race
against queue destruction, win the initial bypass test but perform the
actual draining after blk_cleanup_queue() already destroyed all blkgs.

Fix it by skippping calling into policy draining if all the blkgs are
already gone.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NShirish Pargaonkar <spargaonkar@suse.com>
Reported-by: NSasha Levin <sasha.levin@oracle.com>
Reported-by: NJet Chen <jet.chen@intel.com>
Cc: stable@vger.kernel.org
Tested-by: NShirish Pargaonkar <spargaonkar@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Currently, cftypes added by cgroup_add_cftypes() are used for both the
unified default hierarchy and legacy ones and subsystems can mark each
file with either CFTYPE_ONLY_ON_DFL or CFTYPE_INSANE if it has to
appear only on one of them.  This is quite hairy and error-prone.
Also, we may end up exposing interface files to the default hierarchy
without thinking it through.

cgroup_subsys will grow two separate cftype addition functions and
apply each only on the hierarchies of the matching type.  This will
allow organizing cftypes in a lot clearer way and encourage subsystems
to scrutinize the interface which is being exposed in the new default
hierarchy.

In preparation, this patch adds cgroup_add_legacy_cftypes() which
currently is a simple wrapper around cgroup_add_cftypes() and replaces
all cgroup_add_cftypes() usages with it.

While at it, this patch drops a completely spurious return from
__hugetlb_cgroup_file_init().

This patch doesn't introduce any functional differences.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Acked-by: NLi Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Currently, cgroup_subsys->base_cftypes is used for both the unified
default hierarchy and legacy ones and subsystems can mark each file
with either CFTYPE_ONLY_ON_DFL or CFTYPE_INSANE if it has to appear
only on one of them.  This is quite hairy and error-prone.  Also, we
may end up exposing interface files to the default hierarchy without
thinking it through.

cgroup_subsys will grow two separate cftype arrays and apply each only
on the hierarchies of the matching type.  This will allow organizing
cftypes in a lot clearer way and encourage subsystems to scrutinize
the interface which is being exposed in the new default hierarchy.

In preparation, this patch renames cgroup_subsys->base_cftypes to
cgroup_subsys->legacy_cftypes.  This patch is pure rename.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Acked-by: NLi Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vivek Goyal <vgoyal@redhat.com>
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>
Cc: Aristeu Rozanski <aris@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>