The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-27-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-26-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-22-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-21-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-19-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-18-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-17-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-16-u.kleine-koenig@pengutronix.de
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-15-u.kleine-koenig@pengutronix.de
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-14-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-13-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-12-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-11-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-10-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-9-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-8-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-7-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-6-u.kleine-koenig@pengutronix.de
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-5-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
xvcu_remove() is only called for a device after after xvcu_probe()
completed successfully. In that case dev_set_drvdata() was called for
that device with a non-NULL parameter, so platform_get_drvdata() won't
return NULL and the if condition is never true.
Drop the if, preparing a conversion to make platform driver's remove
callback return void.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-4-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
tegra124_dfll_fcpu_remove() calls tegra_dfll_unregister() and the former
emits an error message if the latter fails. In that case
tegra_dfll_unregister() already printed an error message. Additionally
tegra124_dfll_fcpu_remove() returns an error code which results in yet
another warning emitted by platform_remove().
So drop the error message from tegra124_dfll_fcpu_remove() and let it
return 0. (Retuning 0 has no side effect but suppressing the error
message in platform_remove().)
Also add two comments about exiting early being wrong. This is something
that needs fixing separately.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20230312161512.2715500-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
This reverts commit ce1fdb0656. It turned
out this actually introduces a race condition. netif_running() is not a
suitable check for get_stats.
Reported-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230327152112.15635-1-wsa+renesas@sang-engineering.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Thomas Gleixner says:
====================
net, refcount: Address dst_entry reference count scalability issues
This is version 3 of this series. Version 2 can be found here:
https://lore.kernel.org/lkml/20230307125358.772287565@linutronix.de
Wangyang and Arjan reported a bottleneck in the networking code related to
struct dst_entry::__refcnt. Performance tanks massively when concurrency on
a dst_entry increases.
This happens when there are a large amount of connections to or from the
same IP address. The memtier benchmark when run on the same host as
memcached amplifies this massively. But even over real network connections
this issue can be observed at an obviously smaller scale (due to the
network bandwith limitations in my setup, i.e. 1Gb). How to reproduce:
Run memcached with -t $N and memtier_benchmark with -t $M and --ratio=1:100
on the same machine. localhost connections amplify the problem.
Start with the defaults for $N and $M and increase them. Depending on
your machine this will tank at some point. But even in reasonably small
$N, $M scenarios the refcount operations and the resulting false sharing
fallout becomes visible in perf top. At some point it becomes the
dominating issue.
There are two factors which make this reference count a scalability issue:
1) False sharing
dst_entry:__refcnt is located at offset 64 of dst_entry, which puts
it into a seperate cacheline vs. the read mostly members located at
the beginning of the struct.
That prevents false sharing vs. the struct members in the first 64
bytes of the structure, but there is also
dst_entry::lwtstate
which is located after the reference count and in the same cache
line. This member is read after a reference count has been acquired.
The other problem is struct rtable, which embeds a struct dst_entry
at offset 0. struct dst_entry has a size of 112 bytes, which means
that the struct members of rtable which follow the dst member share
the same cache line as dst_entry::__refcnt. Especially
rtable::rt_genid
is also read by the contexts which have a reference count acquired
already.
When dst_entry:__refcnt is incremented or decremented via an atomic
operation these read accesses stall and contribute to the performance
problem.
2) atomic_inc_not_zero()
A reference on dst_entry:__refcnt is acquired via
atomic_inc_not_zero() and released via atomic_dec_return().
atomic_inc_not_zero() is implemted via a atomic_try_cmpxchg() loop,
which exposes O(N^2) behaviour under contention with N concurrent
operations. Contention scalability is degrading with even a small
amount of contenders and gets worse from there.
Lightweight instrumentation exposed an average of 8!! retry loops per
atomic_inc_not_zero() invocation in a inc()/dec() loop running
concurrently on 112 CPUs.
There is nothing which can be done to make atomic_inc_not_zero() more
scalable.
The following series addresses these issues:
1) Reorder and pad struct dst_entry to prevent the false sharing.
2) Implement and use a reference count implementation which avoids the
atomic_inc_not_zero() problem.
It is slightly less performant in the case of the final 0 -> -1
transition, but the deconstruction of these objects is a low
frequency event. get()/put() pairs are in the hotpath and that's
what this implementation optimizes for.
The algorithm of this reference count is only suitable for RCU
managed objects. Therefore it cannot replace the refcount_t
algorithm, which is also based on atomic_inc_not_zero(), due to a
subtle race condition related to the 0 -> -1 transition and the final
verdict to mark the reference count dead. See details in patch 2/3.
It might be just my lack of imagination which declares this to be
impossible and I'd be happy to be proven wrong.
As a bonus the new rcuref implementation provides underflow/overflow
detection and mitigation while being performance wise on par with
open coded atomic_inc_not_zero() / atomic_dec_return() pairs even in
the non-contended case.
The combination of these two changes results in performance gains in micro
benchmarks and also localhost and networked memtier benchmarks talking to
memcached. It's hard to quantify the benchmark results as they depend
heavily on the micro-architecture and the number of concurrent operations.
The overall gain of both changes for localhost memtier ranges from 1.2X to
3.2X and from +2% to %5% range for networked operations on a 1Gb connection.
A micro benchmark which enforces maximized concurrency shows a gain between
1.2X and 4.7X!!!
Obviously this is focussed on a particular problem and therefore needs to
be discussed in detail. It also requires wider testing outside of the cases
which this is focussed on.
Though the false sharing issue is obvious and should be addressed
independent of the more focussed reference count changes.
The series is also available from git:
git://git.kernel.org/pub/scm/linux/kernel/git/tglx/devel.git rcuref
Changes vs. V2:
- Rename __refcnt to __rcuref (Linus)
- Fix comments and changelogs (Mark, Qiuxu)
- Fixup kernel doc of generated atomic_add_negative() variants
I want to say thanks to Wangyang who analyzed the issue and provided the
initial fix for the false sharing problem. Further thanks go to Arjan
Peter, Marc, Will and Borislav for valuable input and providing test
results on machines which I do not have access to, and to Linus and
Eric, Qiuxu and Mark for helpful feedback.
====================
Link: https://lore.kernel.org/r/20230323102649.764958589@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Under high contention dst_entry::__refcnt becomes a significant bottleneck.
atomic_inc_not_zero() is implemented with a cmpxchg() loop, which goes into
high retry rates on contention.
Switch the reference count to rcuref_t which results in a significant
performance gain. Rename the reference count member to __rcuref to reflect
the change.
The gain depends on the micro-architecture and the number of concurrent
operations and has been measured in the range of +25% to +130% with a
localhost memtier/memcached benchmark which amplifies the problem
massively.
Running the memtier/memcached benchmark over a real (1Gb) network
connection the conversion on top of the false sharing fix for struct
dst_entry::__refcnt results in a total gain in the 2%-5% range over the
upstream baseline.
Reported-by: Wangyang Guo <wangyang.guo@intel.com>
Reported-by: Arjan Van De Ven <arjan.van.de.ven@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20230307125538.989175656@linutronix.de
Link: https://lore.kernel.org/r/20230323102800.215027837@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
dst_entry::__refcnt is highly contended in scenarios where many connections
happen from and to the same IP. The reference count is an atomic_t, so the
reference count operations have to take the cache-line exclusive.
Aside of the unavoidable reference count contention there is another
significant problem which is caused by that: False sharing.
perf top identified two affected read accesses. dst_entry::lwtstate and
rtable::rt_genid.
dst_entry:__refcnt is located at offset 64 of dst_entry, which puts it into
a seperate cacheline vs. the read mostly members located at the beginning
of the struct.
That prevents false sharing vs. the struct members in the first 64
bytes of the structure, but there is also
dst_entry::lwtstate
which is located after the reference count and in the same cache line. This
member is read after a reference count has been acquired.
struct rtable embeds a struct dst_entry at offset 0. struct dst_entry has a
size of 112 bytes, which means that the struct members of rtable which
follow the dst member share the same cache line as dst_entry::__refcnt.
Especially
rtable::rt_genid
is also read by the contexts which have a reference count acquired
already.
When dst_entry:__refcnt is incremented or decremented via an atomic
operation these read accesses stall. This was found when analysing the
memtier benchmark in 1:100 mode, which amplifies the problem extremly.
Move the rt[6i]_uncached[_list] members out of struct rtable and struct
rt6_info into struct dst_entry to provide padding and move the lwtstate
member after that so it ends up in the same cache line.
The resulting improvement depends on the micro-architecture and the number
of CPUs. It ranges from +20% to +120% with a localhost memtier/memcached
benchmark.
[ tglx: Rearrange struct ]
Signed-off-by: Wangyang Guo <wangyang.guo@intel.com>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230323102800.042297517@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TRANSPARENT_HUGEPAGE_NEVER_DAX has nothing to do with DAX. It's set when
has_transparent_hugepage() returns false, checked in hugepage_vma_check()
and will disable THP completely if false. Rename it to
TRANSPARENT_HUGEPAGE_UNSUPPORTED to reflect its real purpose.
[peterx@redhat.com: fix comment, per David]
Link: https://lkml.kernel.org/r/ZBMzQW674oHQJV7F@x1n
Link: https://lkml.kernel.org/r/20230315171642.1244625-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
It's more clear and simple to just use IS_ENABLED(CONFIG_HWPOISON_INJECT)
to check whether or not to enable HWPoison injector module instead of
CONFIG_HWPOISON_INJECT/CONFIG_HWPOISON_INJECT_MODULE.
Link: https://lkml.kernel.org/r/20230313053929.84607-1-wangkefeng.wang@huawei.com
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Now there are no readers of shrinker_rwsem, so we can simply replace it
with mutex lock.
Link: https://lkml.kernel.org/r/20230313112819.38938-9-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sultan Alsawaf <sultan@kerneltoast.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Currently, the synchronize_shrinkers() is only used by TTM pool. It only
requires that no shrinkers run in parallel, and doesn't care about
registering and unregistering of shrinkers.
Since slab shrink is protected by SRCU, synchronize_srcu() is sufficient
to ensure that no shrinker is running in parallel. So the shrinker_rwsem
in synchronize_shrinkers() is no longer needed, just remove it.
Link: https://lkml.kernel.org/r/20230313112819.38938-8-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sultan Alsawaf <sultan@kerneltoast.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
For now, reparent_shrinker_deferred() is the only holder of read lock of
shrinker_rwsem. And it already holds the global cgroup_mutex, so it will
not be called in parallel.
Therefore, in order to convert shrinker_rwsem to shrinker_mutex later,
here we change to hold the write lock of shrinker_rwsem to reparent.
Link: https://lkml.kernel.org/r/20230313112819.38938-7-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sultan Alsawaf <sultan@kerneltoast.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Like global and memcg slab shrink, also use SRCU to make count and scan
operations in memory shrinker debugfs lockless.
Link: https://lkml.kernel.org/r/20230313112819.38938-6-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sultan Alsawaf <sultan@kerneltoast.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
After we make slab shrink lockless with SRCU, the longest sleep
unregister_shrinker() will be a sleep waiting for all do_shrink_slab()
calls.
To avoid long unbreakable action in the unregister_shrinker(), add
shrinker_srcu_generation to restore a check similar to the
rwsem_is_contendent() check that we had before.
And for memcg slab shrink, we unlock SRCU and continue iterations from the
next shrinker id.
Link: https://lkml.kernel.org/r/20230313112819.38938-5-zhengqi.arch@bytedance.com
Signed-off-by: Kirill Tkhai <tkhai@ya.ru>
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sultan Alsawaf <sultan@kerneltoast.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Like global slab shrink, this commit also uses SRCU to make memcg slab
shrink lockless.
We can reproduce the down_read_trylock() hotspot through the
following script:
```
DIR="/root/shrinker/memcg/mnt"
do_create()
{
mkdir -p /sys/fs/cgroup/memory/test
mkdir -p /sys/fs/cgroup/perf_event/test
echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes
for i in `seq 0 $1`;
do
mkdir -p /sys/fs/cgroup/memory/test/$i;
echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs;
echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs;
mkdir -p $DIR/$i;
done
}
do_mount()
{
for i in `seq $1 $2`;
do
mount -t tmpfs $i $DIR/$i;
done
}
do_touch()
{
for i in `seq $1 $2`;
do
echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs;
echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs;
dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 &
done
}
case "$1" in
touch)
do_touch $2 $3
;;
test)
do_create 4000
do_mount 0 4000
do_touch 0 3000
;;
*)
exit 1
;;
esac
```
Save the above script, then run test and touch commands.
Then we can use the following perf command to view hotspots:
perf top -U -F 999
1) Before applying this patchset:
32.31% [kernel] [k] down_read_trylock
19.40% [kernel] [k] pv_native_safe_halt
16.24% [kernel] [k] up_read
15.70% [kernel] [k] shrink_slab
4.69% [kernel] [k] _find_next_bit
2.62% [kernel] [k] shrink_node
1.78% [kernel] [k] shrink_lruvec
0.76% [kernel] [k] do_shrink_slab
2) After applying this patchset:
27.83% [kernel] [k] _find_next_bit
16.97% [kernel] [k] shrink_slab
15.82% [kernel] [k] pv_native_safe_halt
9.58% [kernel] [k] shrink_node
8.31% [kernel] [k] shrink_lruvec
5.64% [kernel] [k] do_shrink_slab
3.88% [kernel] [k] mem_cgroup_iter
At the same time, we use the following perf command to capture
IPC information:
perf stat -e cycles,instructions -G test -a --repeat 5 -- sleep 10
1) Before applying this patchset:
Performance counter stats for 'system wide' (5 runs):
454187219766 cycles test ( +- 1.84% )
78896433101 instructions test # 0.17 insn per cycle ( +- 0.44% )
10.0020430 +- 0.0000366 seconds time elapsed ( +- 0.00% )
2) After applying this patchset:
Performance counter stats for 'system wide' (5 runs):
841954709443 cycles test ( +- 15.80% ) (98.69%)
527258677936 instructions test # 0.63 insn per cycle ( +- 15.11% ) (98.68%)
10.01064 +- 0.00831 seconds time elapsed ( +- 0.08% )
We can see that IPC drops very seriously when calling
down_read_trylock() at high frequency. After using SRCU,
the IPC is at a normal level.
Link: https://lkml.kernel.org/r/20230313112819.38938-4-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Vlastimil Babka <Vbabka@suse.cz>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sultan Alsawaf <sultan@kerneltoast.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The shrinker_rwsem is a global read-write lock in shrinkers subsystem,
which protects most operations such as slab shrink, registration and
unregistration of shrinkers, etc. This can easily cause problems in the
following cases.
1) When the memory pressure is high and there are many
filesystems mounted or unmounted at the same time,
slab shrink will be affected (down_read_trylock()
failed).
Such as the real workload mentioned by Kirill Tkhai:
```
One of the real workloads from my experience is start
of an overcommitted node containing many starting
containers after node crash (or many resuming containers
after reboot for kernel update). In these cases memory
pressure is huge, and the node goes round in long reclaim.
```
2) If a shrinker is blocked (such as the case mentioned
in [1]) and a writer comes in (such as mount a fs),
then this writer will be blocked and cause all
subsequent shrinker-related operations to be blocked.
Even if there is no competitor when shrinking slab, there may still be a
problem. If we have a long shrinker list and we do not reclaim enough
memory with each shrinker, then the down_read_trylock() may be called with
high frequency. Because of the poor multicore scalability of atomic
operations, this can lead to a significant drop in IPC (instructions per
cycle).
So many times in history ([2],[3],[4],[5]), some people wanted to replace
shrinker_rwsem trylock with SRCU in the slab shrink, but all these patches
were abandoned because SRCU was not unconditionally enabled.
But now, since commit 1cd0bd06093c ("rcu: Remove CONFIG_SRCU"), the SRCU
is unconditionally enabled. So it's time to use SRCU to protect readers
who previously held shrinker_rwsem.
This commit uses SRCU to make global slab shrink lockless,
the memcg slab shrink is handled in the subsequent patch.
[1]. https://lore.kernel.org/lkml/20191129214541.3110-1-ptikhomirov@virtuozzo.com/
[2]. https://lore.kernel.org/all/1437080113.3596.2.camel@stgolabs.net/
[3]. https://lore.kernel.org/lkml/1510609063-3327-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp/
[4]. https://lore.kernel.org/lkml/153365347929.19074.12509495712735843805.stgit@localhost.localdomain/
[5]. https://lore.kernel.org/lkml/20210927074823.5825-1-sultan@kerneltoast.com/
Link: https://lkml.kernel.org/r/20230313112819.38938-3-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "make slab shrink lockless", v5.
This patch series aims to make slab shrink lockless.
1. Background
=============
On our servers, we often find the following system cpu hotspots:
52.22% [kernel] [k] down_read_trylock
19.60% [kernel] [k] up_read
8.86% [kernel] [k] shrink_slab
2.44% [kernel] [k] idr_find
1.25% [kernel] [k] count_shadow_nodes
1.18% [kernel] [k] shrink lruvec
0.71% [kernel] [k] mem_cgroup_iter
0.71% [kernel] [k] shrink_node
0.55% [kernel] [k] find_next_bit
And we used bpftrace to capture its calltrace as follows:
@[
down_read_trylock+1
shrink_slab+128
shrink_node+371
do_try_to_free_pages+232
try_to_free_pages+243
_alloc_pages_slowpath+771
_alloc_pages_nodemask+702
pagecache_get_page+255
filemap_fault+1361
ext4_filemap_fault+44
__do_fault+76
handle_mm_fault+3543
do_user_addr_fault+442
do_page_fault+48
page_fault+62
]: 1161690
@[
down_read_trylock+1
shrink_slab+128
shrink_node+371
balance_pgdat+690
kswapd+389
kthread+246
ret_from_fork+31
]: 8424884
@[
down_read_trylock+1
shrink_slab+128
shrink_node+371
do_try_to_free_pages+232
try_to_free_pages+243
__alloc_pages_slowpath+771
__alloc_pages_nodemask+702
__do_page_cache_readahead+244
filemap_fault+1674
ext4_filemap_fault+44
__do_fault+76
handle_mm_fault+3543
do_user_addr_fault+442
do_page_fault+48
page_fault+62
]: 20917631
We can see that down_read_trylock() of shrinker_rwsem is being called with
high frequency at that time. Because of the poor multicore scalability of
atomic operations, this can lead to a significant drop in IPC
(instructions per cycle).
And more, the shrinker_rwsem is a global read-write lock in shrinkers
subsystem, which protects most operations such as slab shrink,
registration and unregistration of shrinkers, etc. This can easily cause
problems in the following cases.
1) When the memory pressure is high and there are many filesystems
mounted or unmounted at the same time, slab shrink will be affected
(down_read_trylock() failed).
Such as the real workload mentioned by Kirill Tkhai:
```
One of the real workloads from my experience is start of an
overcommitted node containing many starting containers after node crash
(or many resuming containers after reboot for kernel update). In these
cases memory pressure is huge, and the node goes round in long reclaim.
```
2) If a shrinker is blocked (such as the case mentioned in [1]) and a
writer comes in (such as mount a fs), then this writer will be blocked
and cause all subsequent shrinker-related operations to be blocked.
[1]. https://lore.kernel.org/lkml/20191129214541.3110-1-ptikhomirov@virtuozzo.com/
All the above cases can be solved by replacing the shrinker_rwsem trylocks
with SRCU.
2. Survey
=========
Before doing the code implementation, I found that there were many similar
submissions in the community:
a. Davidlohr Bueso submitted a patch in 2015.
Subject: [PATCH -next v2] mm: srcu-ify shrinkers
Link: https://lore.kernel.org/all/1437080113.3596.2.camel@stgolabs.net/
Result: It was finally merged into the linux-next branch,
but failed on arm allnoconfig (without CONFIG_SRCU)
b. Tetsuo Handa submitted a patchset in 2017.
Subject: [PATCH 1/2] mm,vmscan: Kill global shrinker lock.
Link: https://lore.kernel.org/lkml/1510609063-3327-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp/
Result: Finally chose to use the current simple way (break
when rwsem_is_contended()). And Christoph Hellwig suggested to
using SRCU, but SRCU was not unconditionally enabled at the
time.
c. Kirill Tkhai submitted a patchset in 2018.
Subject: [PATCH RFC 00/10] Introduce lockless shrink_slab()
Link: https://lore.kernel.org/lkml/153365347929.19074.12509495712735843805.stgit@localhost.localdomain/
Result: At that time, SRCU was not unconditionally enabled,
and there were some objections to enabling SRCU. Later,
because Kirill's focus was moved to other things, this patchset
was not continued to be updated.
d. Sultan Alsawaf submitted a patch in 2021.
Subject: [PATCH] mm: vmscan: Replace shrinker_rwsem trylocks with SRCU protection
Link: https://lore.kernel.org/lkml/20210927074823.5825-1-sultan@kerneltoast.com/
Result: Rejected because SRCU was not unconditionally enabled.
We can find that almost all these historical commits were abandoned
because SRCU was not unconditionally enabled. But now SRCU has been
unconditionally enable by Paul E. McKenney in 2023 [2], so it's time to
replace shrinker_rwsem trylocks with SRCU.
[2] https://lore.kernel.org/lkml/20230105003759.GA1769545@paulmck-ThinkPad-P17-Gen-1/
3. Reproduction and testing
===========================
We can reproduce the down_read_trylock() hotspot through the following script:
```
#!/bin/bash
DIR="/root/shrinker/memcg/mnt"
do_create()
{
mkdir -p /sys/fs/cgroup/memory/test
mkdir -p /sys/fs/cgroup/perf_event/test
echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes
for i in `seq 0 $1`;
do
mkdir -p /sys/fs/cgroup/memory/test/$i;
echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs;
echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs;
mkdir -p $DIR/$i;
done
}
do_mount()
{
for i in `seq $1 $2`;
do
mount -t tmpfs $i $DIR/$i;
done
}
do_touch()
{
for i in `seq $1 $2`;
do
echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs;
echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs;
dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 &
done
}
case "$1" in
touch)
do_touch $2 $3
;;
test)
do_create 4000
do_mount 0 4000
do_touch 0 3000
;;
*)
exit 1
;;
esac
```
Save the above script, then run test and touch commands. Then we can use
the following perf command to view hotspots:
perf top -U -F 999
1) Before applying this patchset:
32.31% [kernel] [k] down_read_trylock
19.40% [kernel] [k] pv_native_safe_halt
16.24% [kernel] [k] up_read
15.70% [kernel] [k] shrink_slab
4.69% [kernel] [k] _find_next_bit
2.62% [kernel] [k] shrink_node
1.78% [kernel] [k] shrink_lruvec
0.76% [kernel] [k] do_shrink_slab
2) After applying this patchset:
27.83% [kernel] [k] _find_next_bit
16.97% [kernel] [k] shrink_slab
15.82% [kernel] [k] pv_native_safe_halt
9.58% [kernel] [k] shrink_node
8.31% [kernel] [k] shrink_lruvec
5.64% [kernel] [k] do_shrink_slab
3.88% [kernel] [k] mem_cgroup_iter
At the same time, we use the following perf command to capture IPC
information:
perf stat -e cycles,instructions -G test -a --repeat 5 -- sleep 10
1) Before applying this patchset:
Performance counter stats for 'system wide' (5 runs):
454187219766 cycles test ( +- 1.84% )
78896433101 instructions test # 0.17 insn per cycle ( +- 0.44% )
10.0020430 +- 0.0000366 seconds time elapsed ( +- 0.00% )
2) After applying this patchset:
Performance counter stats for 'system wide' (5 runs):
841954709443 cycles test ( +- 15.80% ) (98.69%)
527258677936 instructions test # 0.63 insn per cycle ( +- 15.11% ) (98.68%)
10.01064 +- 0.00831 seconds time elapsed ( +- 0.08% )
We can see that IPC drops very seriously when calling down_read_trylock()
at high frequency. After using SRCU, the IPC is at a normal level.
This patch (of 8):
To prepare for the subsequent lockless memcg slab shrink, add a map_nr_max
field to struct shrinker_info to records its own real shrinker_nr_max.
Link: https://lkml.kernel.org/r/20230313112819.38938-1-zhengqi.arch@bytedance.com
Link: https://lkml.kernel.org/r/20230313112819.38938-2-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Suggested-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <tkhai@ya.ru>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sultan Alsawaf <sultan@kerneltoast.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Code inspection reveals that PG_skip_kasan_poison is redundant with
kasantag, because the former is intended to be set iff the latter is the
match-all tag. It can also be observed that it's basically pointless to
poison pages which have kasantag=0, because any pages with this tag would
have been pointed to by pointers with match-all tags, so poisoning the
pages would have little to no effect in terms of bug detection.
Therefore, change the condition in should_skip_kasan_poison() to check
kasantag instead, and remove PG_skip_kasan_poison and associated flags.
Link: https://lkml.kernel.org/r/20230310042914.3805818-3-pcc@google.com
Link: https://linux-review.googlesource.com/id/I57f825f2eaeaf7e8389d6cf4597c8a5821359838
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
io_mapping_map_atomic_wc() disables preemption and pagefaults for
historical reasons. The conversion to io_mapping_map_local_wc(), which
only disables migration, cannot be done wholesale because quite some call
sites need to be updated to accommodate with the changed semantics.
On PREEMPT_RT enabled kernels the io_mapping_map_atomic_wc() semantics are
problematic due to the implicit disabling of preemption which makes it
impossible to acquire 'sleeping' spinlocks within the mapped atomic
sections.
PREEMPT_RT replaces the preempt_disable() with a migrate_disable() for
more than a decade. It could be argued that this is a justification to do
this unconditionally, but PREEMPT_RT covers only a limited number of
architectures and it disables some functionality which limits the coverage
further.
Limit the replacement to PREEMPT_RT for now. This is also done
kmap_atomic().
Link: https://lkml.kernel.org/r/20230310162905.O57Pj7hh@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Richard Weinberger <richard.weinberger@gmail.com>
Link: https://lore.kernel.org/CAFLxGvw0WMxaMqYqJ5WgvVSbKHq2D2xcXTOgMCpgq9nDC-MWTQ@mail.gmail.com
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
In doing experimentations with shmem having the option to avoid swap
becomes a useful mechanism. One of the *raves* about brd over shmem is
you can avoid swap, but that's not really a good reason to use brd if we
can instead use shmem. Using brd has its own good reasons to exist, but
just because "tmpfs" doesn't let you do that is not a great reason to
avoid it if we can easily add support for it.
I don't add support for reconfiguring incompatible options, but if we
really wanted to we can add support for that.
To avoid swap we use mapping_set_unevictable() upon inode creation, and
put a WARN_ON_ONCE() stop-gap on writepages() for reclaim.
Link: https://lkml.kernel.org/r/20230309230545.2930737-7-mcgrof@kernel.org
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Christian Brauner <brauner@kernel.org>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Update the docs to reflect a bit better why some folks prefer tmpfs over
ramfs and clarify a bit more about the difference between brd ramdisks.
While at it, add THP docs for tmpfs, both the mount options and the sysfs
file.
Link: https://lkml.kernel.org/r/20230309230545.2930737-6-mcgrof@kernel.org
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
In theory when info->flags & VM_LOCKED we should not be getting
shem_writepage() called so we should be verifying this with a
WARN_ON_ONCE(). Since we should not be swapping then best to ensure we
also don't do the folio split earlier too. So just move the check early
to avoid folio splits in case its a dubious call.
We also have a similar early bail when !total_swap_pages so just move that
earlier to avoid the possible folio split in the same situation.
Link: https://lkml.kernel.org/r/20230309230545.2930737-5-mcgrof@kernel.org
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
i915_gem requires huge folios to be split when swapping. However we have
check for usage of writepages() to ensure it used only for swap purposes
later. Avoid the splits if we're not being called for reclaim, even if
they should in theory not happen.
This makes the conditions easier to follow on shem_writepage().
Link: https://lkml.kernel.org/r/20230309230545.2930737-4-mcgrof@kernel.org
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
shmem_writepage() sets up variables typically used *after* a possible huge
page split. However even if that does happen the address space mapping
should not change, and the inode does not change either. So it should be
safe to set that from the very beginning.
This commit makes no functional changes.
Link: https://lkml.kernel.org/r/20230309230545.2930737-3-mcgrof@kernel.org
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "tmpfs: add the option to disable swap", v2.
I'm doing this work as part of future experimentation with tmpfs and the
page cache, but given a common complaint found about tmpfs is the
innability to work without the page cache I figured this might be useful
to others. It turns out it is -- at least Christian Brauner indicates
systemd uses ramfs for a few use-cases because they don't want to use swap
and so having this option would let them move over to using tmpfs for
those small use cases, see systemd-creds(1).
To see if you hit swap:
mkswap /dev/nvme2n1
swapon /dev/nvme2n1
free -h
With swap - what we see today
=============================
mount -t tmpfs -o size=5G tmpfs /data-tmpfs/
dd if=/dev/urandom of=/data-tmpfs/5g-rand2 bs=1G count=5
free -h
total used free shared buff/cache available
Mem: 3.7Gi 2.6Gi 1.2Gi 2.2Gi 2.2Gi 1.2Gi
Swap: 99Gi 2.8Gi 97Gi
Without swap
=============
free -h
total used free shared buff/cache available
Mem: 3.7Gi 387Mi 3.4Gi 2.1Mi 57Mi 3.3Gi
Swap: 99Gi 0B 99Gi
mount -t tmpfs -o size=5G -o noswap tmpfs /data-tmpfs/
dd if=/dev/urandom of=/data-tmpfs/5g-rand2 bs=1G count=5
free -h
total used free shared buff/cache available
Mem: 3.7Gi 2.6Gi 1.2Gi 2.3Gi 2.3Gi 1.1Gi
Swap: 99Gi 21Mi 99Gi
The mix and match remount testing
=================================
# Cannot disable swap after it was first enabled:
mount -t tmpfs -o size=5G tmpfs /data-tmpfs/
mount -t tmpfs -o remount -o size=5G -o noswap tmpfs /data-tmpfs/
mount: /data-tmpfs: mount point not mounted or bad option.
dmesg(1) may have more information after failed mount system call.
dmesg -c
tmpfs: Cannot disable swap on remount
# Remount with the same noswap option is OK:
mount -t tmpfs -o size=5G -o noswap tmpfs /data-tmpfs/
mount -t tmpfs -o remount -o size=5G -o noswap tmpfs /data-tmpfs/
dmesg -c
# Trying to enable swap with a remount after it first disabled:
mount -t tmpfs -o size=5G -o noswap tmpfs /data-tmpfs/
mount -t tmpfs -o remount -o size=5G tmpfs /data-tmpfs/
mount: /data-tmpfs: mount point not mounted or bad option.
dmesg(1) may have more information after failed mount system call.
dmesg -c
tmpfs: Cannot enable swap on remount if it was disabled on first mount
This patch (of 6):
Matthew notes we should not need to check the folio lock on the
writepage() callback so remove it. This sanity check has been lingering
since linux-history days. We remove this as we tidy up the writepage()
callback to make things a bit clearer.
Link: https://lkml.kernel.org/r/20230309230545.2930737-1-mcgrof@kernel.org
Link: https://lkml.kernel.org/r/20230309230545.2930737-2-mcgrof@kernel.org
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Fix missing EXPORT_SYMBOL_GPL() statement for mas_preallocate().
It isn't actually used by anything yet, but mas_preallocate() is part of
the maple tree's 'Advanced API'. All other functions of this API are
exported already.
Link: https://lkml.kernel.org/r/20230302011035.4928-1-dakr@redhat.com
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The last remaining user of folio_write_one through the write_one_page
wrapper is jfs, so move the functionality there and hard code the call to
metapage_writepage.
Note that the use of the pagecache by the JFS 'metapage' buffer cache is a
bit odd, and we could probably do without VM-level dirty tracking at all,
but that's a change for another time.
Link: https://lkml.kernel.org/r/20230307143125.27778-4-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Evgeniy Dushistov <dushistov@mail.ru>
Cc: Gang He <ghe@suse.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jan Kara via Ocfs2-devel <ocfs2-devel@oss.oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Jun Piao <piaojun@huawei.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Use filemap_write_and_wait_range to write back the range of the dirty page
instead of write_one_page in preparation of removing write_one_page and
eventually ->writepage.
Link: https://lkml.kernel.org/r/20230307143125.27778-3-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Evgeniy Dushistov <dushistov@mail.ru>
Cc: Gang He <ghe@suse.com>
Cc: Jan Kara via Ocfs2-devel <ocfs2-devel@oss.oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Jun Piao <piaojun@huawei.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "remove most callers of write_one_page", v4.
This series removes most users of the write_one_page API. These helpers
internally call ->writepage which we are gradually removing from the
kernel.
This patch (of 3):
We do not need to writeout modified directory blocks immediately when
modifying them while the page is locked. It is enough to do the flush
somewhat later which has the added benefit that inode times can be flushed
as well. It also allows us to stop depending on write_one_page()
function.
Ported from an ext2 patch by Jan Kara.
Link: https://lkml.kernel.org/r/20230307143125.27778-1-hch@lst.de
Link: https://lkml.kernel.org/r/20230307143125.27778-2-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Evgeniy Dushistov <dushistov@mail.ru>
Cc: Jan Kara via Ocfs2-devel <ocfs2-devel@oss.oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
