Commit Graph

20 Commits

Author SHA1 Message Date
Kees Cook
590b5b7d86 treewide: kzalloc_node() -> kcalloc_node()
The kzalloc_node() function has a 2-factor argument form, kcalloc_node(). This
patch replaces cases of:

        kzalloc_node(a * b, gfp, node)

with:
        kcalloc_node(a * b, gfp, node)

as well as handling cases of:

        kzalloc_node(a * b * c, gfp, node)

with:

        kzalloc_node(array3_size(a, b, c), gfp, node)

as it's slightly less ugly than:

        kcalloc_node(array_size(a, b), c, gfp, node)

This does, however, attempt to ignore constant size factors like:

        kzalloc_node(4 * 1024, gfp, node)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kzalloc_node(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kzalloc_node(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kzalloc_node(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc_node(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc_node(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc_node(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc_node(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc_node(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc_node(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kzalloc_node(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kzalloc_node
+ kcalloc_node
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kzalloc_node(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc_node(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc_node(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc_node(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc_node(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc_node(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc_node(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc_node(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kzalloc_node(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc_node(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc_node(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc_node(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc_node(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kzalloc_node(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kzalloc_node(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc_node(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc_node(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc_node(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc_node(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc_node(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc_node(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc_node(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kzalloc_node(C1 * C2 * C3, ...)
|
  kzalloc_node(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc_node(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc_node(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc_node(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kzalloc_node(sizeof(THING) * C2, ...)
|
  kzalloc_node(sizeof(TYPE) * C2, ...)
|
  kzalloc_node(C1 * C2 * C3, ...)
|
  kzalloc_node(C1 * C2, ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kzalloc_node
+ kcalloc_node
  (
-	E1 * E2
+	E1, E2
  , ...)
)

Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 16:19:22 -07:00
Ming Lei
e6fc464987 blk-mq: avoid starving tag allocation after allocating process migrates
When the allocation process is scheduled back and the mapped hw queue is
changed, fake one extra wake up on previous queue for compensating wake
up miss, so other allocations on the previous queue won't be starved.

This patch fixes one request allocation hang issue, which can be
triggered easily in case of very low nr_request.

The race is as follows:

1) 2 hw queues, nr_requests are 2, and wake_batch is one

2) there are 3 waiters on hw queue 0

3) two in-flight requests in hw queue 0 are completed, and only two
   waiters of 3 are waken up because of wake_batch, but both the two
   waiters can be scheduled to another CPU and cause to switch to hw
   queue 1

4) then the 3rd waiter will wait for ever, since no in-flight request
   is in hw queue 0 any more.

5) this patch fixes it by the fake wakeup when waiter is scheduled to
   another hw queue

Cc: <stable@vger.kernel.org>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>

Modified commit message to make it clearer, and make it apply on
top of the 4.18 branch.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-05-24 11:00:39 -06:00
Jens Axboe
c854ab5773 sbitmap: fix race in wait batch accounting
If we have multiple callers of sbq_wake_up(), we can end up in a
situation where the wait_cnt will continually go more and more
negative. Consider the case where our wake batch is 1, hence
wait_cnt will start out as 1.

wait_cnt == 1

CPU0				CPU1
atomic_dec_return(), cnt == 0
				atomic_dec_return(), cnt == -1
				cmpxchg(-1, 0) (succeeds)
				[wait_cnt now 0]
cmpxchg(0, 1) (fails)

This ends up with wait_cnt being 0, we'll wakeup immediately
next time. Going through the same loop as above again, and
we'll have wait_cnt -1.

For the case where we have a larger wake batch, the only
difference is that the starting point will be higher. We'll
still end up with continually smaller batch wakeups, which
defeats the purpose of the rolling wakeups.

Always reset the wait_cnt to the batch value. Then it doesn't
matter who wins the race. But ensure that whomever does win
the race is the one that increments the ws index and wakes up
our batch count, loser gets to call __sbq_wake_up() again to
account his wakeups towards the next active wait state index.

Fixes: 6c0ca7ae29 ("sbitmap: fix wakeup hang after sbq resize")
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-05-14 12:17:31 -06:00
Omar Sandoval
61445b56d0 sbitmap: warn if using smaller shallow depth than was setup
Make sure the user passed the right value to
sbitmap_queue_min_shallow_depth().

Acked-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-05-10 11:27:52 -06:00
Omar Sandoval
a327553965 sbitmap: fix missed wakeups caused by sbitmap_queue_get_shallow()
The sbitmap queue wake batch is calculated such that once allocations
start blocking, all of the bits which are already allocated must be
enough to fulfill the batch counters of all of the waitqueues. However,
the shallow allocation depth can break this invariant, since we block
before our full depth is being utilized. Add
sbitmap_queue_min_shallow_depth(), which saves the minimum shallow depth
the sbq will use, and update sbq_calc_wake_batch() to take it into
account.

Acked-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-05-10 11:27:36 -06:00
Omar Sandoval
4ace53f1ed sbitmap: use test_and_set_bit_lock()/clear_bit_unlock()
sbitmap_queue_get()/sbitmap_queue_clear() are used for
allocating/freeing a resource, so they should provide acquire/release
barrier semantics, respectively. sbitmap_get() currently contains a full
barrier, which is unnecessary, so use test_and_set_bit_lock() instead of
test_and_set_bit() (these are equivalent on x86_64). sbitmap_clear_bit()
does not imply any barriers, which is incorrect, as accesses of the
resource (e.g., request) could potentially get reordered to after the
clear_bit(). Introduce sbitmap_clear_bit_unlock() and use it for
sbitmap_queue_clear() (this only adds a compiler barrier on x86_64). The
other existing user of sbitmap_clear_bit() (the blk-mq software queue
pending map) is serialized through a spinlock and does not need this.

Reported-by: Tejun Heo <tj@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-28 12:23:35 -07:00
Jens Axboe
4e5dff41be blk-mq: improve heavily contended tag case
Even with a number of waitqueues, we can get into a situation where we
are heavily contended on the waitqueue lock. I got a report on spc1
where we're spending seconds doing this. Arguably the use case is nasty,
I reproduce it with one device and 1000 threads banging on the device.
But that doesn't mean we shouldn't be handling it better.

What ends up happening is that a thread will fail to get a tag, add
itself to the waitqueue, and subsequently get woken up when a tag is
freed - only to find itself going back to sleep on the waitqueue.

Instead of waking all threads, use an exclusive wait and wake up our
sbitmap batch count instead. This seems to work well for me (massive
improvement for this use case), and it survives basic testing. But I
haven't fully verified it yet.

An additional improvement is running the queue and checking for a new
tag BEFORE needing to add ourselves to the waitqueue.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-22 11:09:37 -07:00
Omar Sandoval
c05e667337 sbitmap: add sbitmap_get_shallow() operation
This operation supports the use case of limiting the number of bits that
can be allocated for a given operation. Rather than setting aside some
bits at the end of the bitmap, we can set aside bits in each word of the
bitmap. This means we can keep the allocation hints spread out and
support sbitmap_resize() nicely at the cost of lower granularity for the
allowed depth.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-14 14:06:52 -06:00
Ingo Molnar
af8601ad42 kasan, sched/headers: Uninline kasan_enable/disable_current()
<linux/kasan.h> is a low level header that is included early
in affected kernel headers. But it includes <linux/sched.h>
which complicates the cleanup of sched.h dependencies.

But kasan.h has almost no need for sched.h: its only use of
scheduler functionality is in two inline functions which are
not used very frequently - so uninline kasan_enable_current()
and kasan_disable_current().

Also add a <linux/sched.h> dependency to a .c file that depended
on kasan.h including it.

This paves the way to remove the <linux/sched.h> include from kasan.h.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 08:42:25 +01:00
Omar Sandoval
24af1ccfe1 sbitmap: add helpers for dumping to a seq_file
This is useful debugging information that will be used in the blk-mq
debugfs directory.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>

Changed 'weight' to 'busy'.

Signed-off-by: Jens Axboe <axboe@fb.com>
2017-01-27 08:17:44 -07:00
Omar Sandoval
6c0ca7ae29 sbitmap: fix wakeup hang after sbq resize
When we resize a struct sbitmap_queue, we update the wakeup batch size,
but we don't update the wait count in the struct sbq_wait_states. If we
resized down from a size which could use a bigger batch size, these
counts could be too large and cause us to miss necessary wakeups. To fix
this, update the wait counts when we resize (ensuring some careful
memory ordering so that it's safe w.r.t. concurrent clears).

This also fixes a theoretical issue where two threads could end up
bumping the wait count up by the batch size, which could also
potentially lead to hangs.

Reported-by: Martin Raiber <martin@urbackup.org>
Fixes: e3a2b3f931 ("blk-mq: allow changing of queue depth through sysfs")
Fixes: 2971c35f35 ("blk-mq: bitmap tag: fix race on blk_mq_bitmap_tags::wake_cnt")
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-01-18 13:41:55 -07:00
Omar Sandoval
f66227de59 sbitmap: use smp_mb__after_atomic() in sbq_wake_up()
We always do an atomic clear_bit() right before we call sbq_wake_up(),
so we can use smp_mb__after_atomic(). While we're here, comment the
memory barriers in here a little more.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-01-18 13:41:49 -07:00
Colin Ian King
60658e0dc1 sbitmap: initialize weight to zero
Variable weight is not being initialized to zero before it is
used to compute the weight sum. Ensure it is initialized to zero.

Found with static analysis with cppcheck:
[lib/sbitmap.c:177]: (error) Uninitialized variable: weight

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-19 08:19:40 -06:00
Omar Sandoval
5c64a8df0c sbitmap: don't update the allocation hint on clear after resize
If we have a bunch of high-numbered bits allocated and then we resize
the struct sbitmap_queue, when those bits get cleared, we'll update the
hint and then have to re-randomize it repeatedly. Avoid that by checking
that the cleared bit is still a valid hint. No measurable performance
difference in the common case.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-17 13:39:06 -06:00
Omar Sandoval
05fd095d53 sbitmap: re-initialize allocation hints after resize
After a struct sbitmap_queue is resized smaller, the allocation hints
may still be set to bits beyond the new depth of the bitmap. This means
that, for example, if the number of blk-mq tags is reduced through
sysfs, more requests than the nominal queue depth may be in flight.

It's tempting to fix this at resize time by doing a one-time
reinitialization of the hints, but this can race with
__sbitmap_queue_get() updating the hint. Instead, check the hint before
we use it. This caused no measurable performance difference in my
synthetic benchmarks.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-17 08:39:16 -06:00
Omar Sandoval
98d95416db sbitmap: randomize initial alloc_hint values
In order to get good cache behavior from a sbitmap, we want each CPU to
stick to its own cacheline(s) as much as possible. This might happen
naturally as the bitmap gets filled up and the alloc_hint values spread
out, but we really want this behavior from the start. blk-mq apparently
intended to do this, but the code to do this was never wired up. Get rid
of the dead code and make it part of the sbitmap library.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-17 08:39:14 -06:00
Omar Sandoval
f4a644db86 sbitmap: push alloc policy into sbitmap_queue
Again, there's no point in passing this in every time. Make it part of
struct sbitmap_queue and clean up the API.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-17 08:39:12 -06:00
Omar Sandoval
40aabb6746 sbitmap: push per-cpu last_tag into sbitmap_queue
Allocating your own per-cpu allocation hint separately makes for an
awkward API. Instead, allocate the per-cpu hint as part of the struct
sbitmap_queue. There's no point for a struct sbitmap_queue without the
cache, but you can still use a bare struct sbitmap.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-17 08:39:10 -06:00
Omar Sandoval
48e28166a7 sbitmap: allocate wait queues on a specific node
The original bt_alloc() we converted from was using kzalloc(), not
kzalloc_node(), to allocate the wait queues. This was probably an
oversight, so fix it for sbitmap_queue_init_node().

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-17 08:39:08 -06:00
Omar Sandoval
88459642cb blk-mq: abstract tag allocation out into sbitmap library
This is a generally useful data structure, so make it available to
anyone else who might want to use it. It's also a nice cleanup
separating the allocation logic from the rest of the tag handling logic.

The code is behind a new Kconfig option, CONFIG_SBITMAP, which is only
selected by CONFIG_BLOCK for now.

This should be a complete noop functionality-wise.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-17 08:38:44 -06:00