linux/drivers/misc
Michal Hocko 93065ac753 mm, oom: distinguish blockable mode for mmu notifiers
There are several blockable mmu notifiers which might sleep in
mmu_notifier_invalidate_range_start and that is a problem for the
oom_reaper because it needs to guarantee a forward progress so it cannot
depend on any sleepable locks.

Currently we simply back off and mark an oom victim with blockable mmu
notifiers as done after a short sleep.  That can result in selecting a new
oom victim prematurely because the previous one still hasn't torn its
memory down yet.

We can do much better though.  Even if mmu notifiers use sleepable locks
there is no reason to automatically assume those locks are held.  Moreover
majority of notifiers only care about a portion of the address space and
there is absolutely zero reason to fail when we are unmapping an unrelated
range.  Many notifiers do really block and wait for HW which is harder to
handle and we have to bail out though.

This patch handles the low hanging fruit.
__mmu_notifier_invalidate_range_start gets a blockable flag and callbacks
are not allowed to sleep if the flag is set to false.  This is achieved by
using trylock instead of the sleepable lock for most callbacks and
continue as long as we do not block down the call chain.

I think we can improve that even further because there is a common pattern
to do a range lookup first and then do something about that.  The first
part can be done without a sleeping lock in most cases AFAICS.

The oom_reaper end then simply retries if there is at least one notifier
which couldn't make any progress in !blockable mode.  A retry loop is
already implemented to wait for the mmap_sem and this is basically the
same thing.

The simplest way for driver developers to test this code path is to wrap
userspace code which uses these notifiers into a memcg and set the hard
limit to hit the oom.  This can be done e.g.  after the test faults in all
the mmu notifier managed memory and set the hard limit to something really
small.  Then we are looking for a proper process tear down.

[akpm@linux-foundation.org: coding style fixes]
[akpm@linux-foundation.org: minor code simplification]
Link: http://lkml.kernel.org/r/20180716115058.5559-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Christian König <christian.koenig@amd.com> # AMD notifiers
Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx and umem_odp
Reported-by: David Rientjes <rientjes@google.com>
Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: Dennis Dalessandro <dennis.dalessandro@intel.com>
Cc: Sudeep Dutt <sudeep.dutt@intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-22 10:52:44 -07:00
..
altera-stapl treewide: kzalloc() -> kcalloc() 2018-06-12 16:19:22 -07:00
c2port kmemcheck: remove annotations 2017-11-15 18:21:04 -08:00
cardreader misc: rtsx: make several functions static 2018-07-03 13:01:48 +02:00
cb710 treewide: Use struct_size() for devm_kmalloc() and friends 2018-06-06 11:15:43 -07:00
cxl Merge branch 'akpm' (patches from Andrew) 2018-08-17 16:49:31 -07:00
echo misc: Remove Blackfin DSP echo support 2018-03-26 15:56:37 +02:00
eeprom misc: eeprom: assignment outside the if statement 2018-08-05 16:25:10 +02:00
genwqe genwqe: card_base: Use true and false for boolean values 2018-08-05 16:29:11 +02:00
ibmasm ibmasm: don't write out of bounds in read handler 2018-07-07 09:59:35 +02:00
lis3lv02d vfs: do bulk POLL* -> EPOLL* replacement 2018-02-11 14:34:03 -08:00
lkdtm lkdtm: Add missing SPDX-License-Identifier line 2018-03-06 19:18:55 -08:00
mei mei: define dma ring buffer sizes for PCH12 HW and newer 2018-08-02 10:18:30 +02:00
mic mm, oom: distinguish blockable mode for mmu notifiers 2018-08-22 10:52:44 -07:00
ocxl Merge branch 'akpm' (patches from Andrew) 2018-08-17 16:49:31 -07:00
sgi-gru mm, oom: distinguish blockable mode for mmu notifiers 2018-08-22 10:52:44 -07:00
sgi-xp sgi-xp: xpc_partition: mark expected switch fall-throughs 2018-07-07 17:38:57 +02:00
ti-st misc: ti-st: Fix memory leak in the error path of probe() 2018-08-02 10:35:04 +02:00
vmw_vmci vmci: type promotion bug in qp_host_get_user_memory() 2018-07-07 17:32:40 +02:00
Kconfig misc: IBM Virtual Management Channel Driver (VMC) 2018-05-14 16:35:42 +02:00
Makefile misc: IBM Virtual Management Channel Driver (VMC) 2018-05-14 16:35:42 +02:00
ad525x_dpot-i2c.c
ad525x_dpot-spi.c
ad525x_dpot.c misc: ad525x_dpot: macros should not use a trailing semicolon 2017-12-18 16:02:26 +01:00
ad525x_dpot.h misc: ad525x_dpot: Unnecessary space before function pointer arguments 2017-12-18 15:59:17 +01:00
apds990x.c misc: apds990x: Missing a blank line after declarations. 2017-12-18 16:02:26 +01:00
apds9802als.c misc: apds9802als: constify i2c_device_id 2017-08-28 16:55:49 +02:00
aspeed-lpc-ctrl.c misc: aspeed-lpc-ctrl: Enable FWH and A2H bridge cycles 2018-03-15 18:20:51 +01:00
aspeed-lpc-snoop.c drivers/misc: Aspeed LPC snoop output using misc chardev 2018-07-16 13:30:47 +02:00
atmel-ssc.c
atmel_tclib.c
bh1770glc.c misc: bh1770glc: constify attribute_group structures. 2017-08-28 16:55:48 +02:00
cs5535-mfgpt.c
ds1682.c misc: ds1682: Ignore update-in-progress ETC reads 2018-01-09 17:03:57 +01:00
dummy-irq.c
enclosure.c misc: enclosure: Remove unnecessary error check 2017-12-07 18:45:31 +01:00
fsa9480.c misc: fsa9480: Add blank line after declarations. 2018-01-09 17:03:57 +01:00
hmc6352.c misc: hmc6352: constify i2c_device_id 2017-08-28 16:55:49 +02:00
hpilo.c vfs: do bulk POLL* -> EPOLL* replacement 2018-02-11 14:34:03 -08:00
hpilo.h misc: hpilo: Use SPDX-License-Identifier 2017-12-07 18:45:31 +01:00
ibmvmc.c misc: ibmvmc: Use GFP_ATOMIC under spin lock 2018-07-07 17:35:00 +02:00
ibmvmc.h misc: IBM Virtual Management Channel Driver (VMC) 2018-05-14 16:35:42 +02:00
ics932s401.c misc: ics932s401: open brace should be on the previous line 2017-12-18 16:00:57 +01:00
ioc4.c misc: ioc4: constify pci_device_id. 2017-08-28 16:55:48 +02:00
isl29003.c misc: isl29003: Missing a blank line after declarations 2017-12-07 18:45:31 +01:00
isl29020.c misc: isl29020: constify i2c_device_id 2017-08-28 16:55:49 +02:00
kgdbts.c misc: kgdbts: Display progress of asynchronous tests 2018-01-25 08:40:17 -06:00
lattice-ecp3-config.c
pch_phub.c MISC: add const to bin_attribute structures 2017-08-28 16:55:48 +02:00
pci_endpoint_test.c pci_endpoint_test: Add 2 ioctl commands 2018-07-19 11:46:57 +01:00
phantom.c vfs: do bulk POLL* -> EPOLL* replacement 2018-02-11 14:34:03 -08:00
pti.c drivers/misc/intel/pti: Rename the header file to free up the namespace 2017-12-17 12:52:34 +01:00
qcom-coincell.c
spear13xx_pcie_gadget.c
sram-exec.c
sram.c misc: sram: enable clock before registering regions 2018-07-06 16:48:15 +02:00
sram.h
tifm_7xx1.c misc: tifm: Remove VLA 2018-04-23 13:31:27 +02:00
tifm_core.c
tsl2550.c tsl2550: fix lux1_input error in low light 2018-07-07 17:44:52 +02:00
vexpress-syscfg.c misc: vexpress/syscfg: Use devm_ioremap_resource() to map memory 2018-07-16 13:32:08 +02:00
vmw_balloon.c Merge 4.18-rc5 into char-misc-next 2018-07-16 09:04:54 +02:00