NOTE: This is very heavily based on similar logic in autonuma. It should
be signed off by Andrea but because there was no standalone
patch and it's sufficiently different from what he did that
the signed-off is omitted. Will be added back if requested.
If a large number of pages are misplaced then the memory bus can be
saturated just migrating pages between nodes. This patch rate-limits
the amount of memory that can be migrating between nodes.
Signed-off-by: Mel Gorman <mgorman@suse.de>
This defines the per-node data used by Migrate On Fault in order to
rate limit the migration. The rate limiting is applied independently
to each destination node.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
To say that the PMD handling code was incorrectly transferred from autonuma
is an understatement. The intention was to handle a PMDs worth of pages
in the same fault and effectively batch the taking of the PTL and page
migration. The copied version instead has the impact of clearing a number
of pte_numa PTE entries and whether any page migration takes place depends
on racing. This just happens to work in some cases.
This patch handles pte_numa faults in batch when a pmd_numa fault is
handled. The pages are migrated if they are currently misplaced.
Essentially this is making an assumption that NUMA locality is
on a PMD boundary but that could be addressed by only setting
pmd_numa if all the pages within that PMD are on the same node
if necessary.
Signed-off-by: Mel Gorman <mgorman@suse.de>
This is the simplest possible policy that still does something of note.
When a pte_numa is faulted, it is moved immediately. Any replacement
policy must at least do better than this and in all likelihood this
policy regresses normal workloads.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
It is tricky to quantify the basic cost of automatic NUMA placement in a
meaningful manner. This patch adds some vmstats that can be used as part
of a basic costing model.
u = basic unit = sizeof(void *)
Ca = cost of struct page access = sizeof(struct page) / u
Cpte = Cost PTE access = Ca
Cupdate = Cost PTE update = (2 * Cpte) + (2 * Wlock)
where Cpte is incurred twice for a read and a write and Wlock
is a constant representing the cost of taking or releasing a
lock
Cnumahint = Cost of a minor page fault = some high constant e.g. 1000
Cpagerw = Cost to read or write a full page = Ca + PAGE_SIZE/u
Ci = Cost of page isolation = Ca + Wi
where Wi is a constant that should reflect the approximate cost
of the locking operation
Cpagecopy = Cpagerw + (Cpagerw * Wnuma) + Ci + (Ci * Wnuma)
where Wnuma is the approximate NUMA factor. 1 is local. 1.2
would imply that remote accesses are 20% more expensive
Balancing cost = Cpte * numa_pte_updates +
Cnumahint * numa_hint_faults +
Ci * numa_pages_migrated +
Cpagecopy * numa_pages_migrated
Note that numa_pages_migrated is used as a measure of how many pages
were isolated even though it would miss pages that failed to migrate. A
vmstat counter could have been added for it but the isolation cost is
pretty marginal in comparison to the overall cost so it seemed overkill.
The ideal way to measure automatic placement benefit would be to count
the number of remote accesses versus local accesses and do something like
benefit = (remote_accesses_before - remove_access_after) * Wnuma
but the information is not readily available. As a workload converges, the
expection would be that the number of remote numa hints would reduce to 0.
convergence = numa_hint_faults_local / numa_hint_faults
where this is measured for the last N number of
numa hints recorded. When the workload is fully
converged the value is 1.
This can measure if the placement policy is converging and how fast it is
doing it.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
NOTE: This patch is based on "sched, numa, mm: Add fault driven
placement and migration policy" but as it throws away all the policy
to just leave a basic foundation I had to drop the signed-offs-by.
This patch creates a bare-bones method for setting PTEs pte_numa in the
context of the scheduler that when faulted later will be faulted onto the
node the CPU is running on. In itself this does nothing useful but any
placement policy will fundamentally depend on receiving hints on placement
from fault context and doing something intelligent about it.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
The use of MPOL_NOOP and MPOL_MF_LAZY to allow an application to
explicitly request lazy migration is a good idea but the actual
API has not been well reviewed and once released we have to support it.
For now this patch prevents an application using the services. This
will need to be revisited.
Signed-off-by: Mel Gorman <mgorman@suse.de>
This patch converts change_prot_numa() to use change_protection(). As
pte_numa and friends check the PTE bits directly it is necessary for
change_protection() to use pmd_mknuma(). Hence the required
modifications to change_protection() are a little clumsy but the
end result is that most of the numa page table helpers are just one or
two instructions.
Signed-off-by: Mel Gorman <mgorman@suse.de>
NOTE: Once again there is a lot of patch stealing and the end result
is sufficiently different that I had to drop the signed-offs.
Will re-add if the original authors are ok with that.
This patch adds another mbind() flag to request "lazy migration". The
flag, MPOL_MF_LAZY, modifies MPOL_MF_MOVE* such that the selected
pages are marked PROT_NONE. The pages will be migrated in the fault
path on "first touch", if the policy dictates at that time.
"Lazy Migration" will allow testing of migrate-on-fault via mbind().
Also allows applications to specify that only subsequently touched
pages be migrated to obey new policy, instead of all pages in range.
This can be useful for multi-threaded applications working on a
large shared data area that is initialized by an initial thread
resulting in all pages on one [or a few, if overflowed] nodes.
After PROT_NONE, the pages in regions assigned to the worker threads
will be automatically migrated local to the threads on 1st touch.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Note: Based on "mm/mpol: Use special PROT_NONE to migrate pages" but
sufficiently different that the signed-off-bys were dropped
Combine our previous _PAGE_NUMA, mpol_misplaced and migrate_misplaced_page()
pieces into an effective migrate on fault scheme.
Note that (on x86) we rely on PROT_NONE pages being !present and avoid
the TLB flush from try_to_unmap(TTU_MIGRATION). This greatly improves the
page-migration performance.
Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
If we have to avoid migrating to a node that is nearly full, put page
and return zero.
Signed-off-by: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Note: This was originally based on Peter's patch "mm/migrate: Introduce
migrate_misplaced_page()" but borrows extremely heavily from Andrea's
"autonuma: memory follows CPU algorithm and task/mm_autonuma stats
collection". The end result is barely recognisable so signed-offs
had to be dropped. If original authors are ok with it, I'll
re-add the signed-off-bys.
Add migrate_misplaced_page() which deals with migrating pages from
faults.
Based-on-work-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Based-on-work-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
This patch provides a new function to test whether a page resides
on a node that is appropriate for the mempolicy for the vma and
address where the page is supposed to be mapped. This involves
looking up the node where the page belongs. So, the function
returns that node so that it may be used to allocated the page
without consulting the policy again.
A subsequent patch will call this function from the fault path.
Because of this, I don't want to go ahead and allocate the page, e.g.,
via alloc_page_vma() only to have to free it if it has the correct
policy. So, I just mimic the alloc_page_vma() node computation
logic--sort of.
Note: we could use this function to implement a MPOL_MF_STRICT
behavior when migrating pages to match mbind() mempolicy--e.g.,
to ensure that pages in an interleaved range are reinterleaved
rather than left where they are when they reside on any page in
the interleave nodemask.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
[ Added MPOL_F_LAZY to trigger migrate-on-fault;
simplified code now that we don't have to bother
with special crap for interleaved ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
This patch augments the MPOL_MF_LAZY feature by adding a "NOOP" policy
to mbind(). When the NOOP policy is used with the 'MOVE and 'LAZY
flags, mbind() will map the pages PROT_NONE so that they will be
migrated on the next touch.
This allows an application to prepare for a new phase of operation
where different regions of shared storage will be assigned to
worker threads, w/o changing policy. Note that we could just use
"default" policy in this case. However, this also allows an
application to request that pages be migrated, only if necessary,
to follow any arbitrary policy that might currently apply to a
range of pages, without knowing the policy, or without specifying
multiple mbind()s for ranges with different policies.
[ Bug in early version of mpol_parse_str() reported by Fengguang Wu. ]
Bug-Reported-by: Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Make MPOL_LOCAL a real and exposed policy such that applications that
relied on the previous default behaviour can explicitly request it.
Requested-by: Christoph Lameter <cl@linux.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Note: This patch started as "mm/mpol: Create special PROT_NONE
infrastructure" and preserves the basic idea but steals *very*
heavily from "autonuma: numa hinting page faults entry points" for
the actual fault handlers without the migration parts. The end
result is barely recognisable as either patch so all Signed-off
and Reviewed-bys are dropped. If Peter, Ingo and Andrea are ok with
this version, I will re-add the signed-offs-by to reflect the history.
In order to facilitate a lazy -- fault driven -- migration of pages, create
a special transient PAGE_NUMA variant, we can then use the 'spurious'
protection faults to drive our migrations from.
The meaning of PAGE_NUMA depends on the architecture but on x86 it is
effectively PROT_NONE. Actual PROT_NONE mappings will not generate these
NUMA faults for the reason that the page fault code checks the permission on
the VMA (and will throw a segmentation fault on actual PROT_NONE mappings),
before it ever calls handle_mm_fault.
[dhillf@gmail.com: Fix typo]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
When we split a transparent hugepage, transfer the NUMA type from the
pmd to the pte if needed.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Introduce FOLL_NUMA to tell follow_page to check
pte/pmd_numa. get_user_pages must use FOLL_NUMA, and it's safe to do
so because it always invokes handle_mm_fault and retries the
follow_page later.
KVM secondary MMU page faults will trigger the NUMA hinting page
faults through gup_fast -> get_user_pages -> follow_page ->
handle_mm_fault.
Other follow_page callers like KSM should not use FOLL_NUMA, or they
would fail to get the pages if they use follow_page instead of
get_user_pages.
[ This patch was picked up from the AutoNUMA tree. ]
Originally-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
[ ported to this tree. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Compaction already has tracepoints to count scanned and isolated pages
but it requires that ftrace be enabled and if that information has to be
written to disk then it can be disruptive. This patch adds vmstat counters
for compaction called compact_migrate_scanned, compact_free_scanned and
compact_isolated.
With these counters, it is possible to define a basic cost model for
compaction. This approximates of how much work compaction is doing and can
be compared that with an oprofile showing TLB misses and see if the cost of
compaction is being offset by THP for example. Minimally a compaction patch
can be evaluated in terms of whether it increases or decreases cost. The
basic cost model looks like this
Fundamental unit u: a word sizeof(void *)
Ca = cost of struct page access = sizeof(struct page) / u
Cmc = Cost migrate page copy = (Ca + PAGE_SIZE/u) * 2
Cmf = Cost migrate failure = Ca * 2
Ci = Cost page isolation = (Ca + Wi)
where Wi is a constant that should reflect the approximate
cost of the locking operation.
Csm = Cost migrate scanning = Ca
Csf = Cost free scanning = Ca
Overall cost = (Csm * compact_migrate_scanned) +
(Csf * compact_free_scanned) +
(Ci * compact_isolated) +
(Cmc * pgmigrate_success) +
(Cmf * pgmigrate_failed)
Where the values are read from /proc/vmstat.
This is very basic and ignores certain costs such as the allocation cost
to do a migrate page copy but any improvement to the model would still
use the same vmstat counters.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
The pgmigrate_success and pgmigrate_fail vmstat counters tells the user
about migration activity but not the type or the reason. This patch adds
a tracepoint to identify the type of page migration and why the page is
being migrated.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
The compact_pages_moved and compact_pagemigrate_failed events are
convenient for determining if compaction is active and to what
degree migration is succeeding but it's at the wrong level. Other
users of migration may also want to know if migration is working
properly and this will be particularly true for any automated
NUMA migration. This patch moves the counters down to migration
with the new events called pgmigrate_success and pgmigrate_fail.
The compact_blocks_moved counter is removed because while it was
useful for debugging initially, it's worthless now as no meaningful
conclusions can be drawn from its value.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reuse the NUMA code's 'modified page protections' count that
change_protection() computes and skip the TLB flush if there's
no changes to a range that sys_mprotect() modifies.
Given that mprotect() already optimizes the same-flags case
I expected this optimization to dominantly trigger on
CONFIG_NUMA_BALANCING=y kernels - but even with that feature
disabled it triggers rather often.
There's two reasons for that:
1)
While sys_mprotect() already optimizes the same-flag case:
if (newflags == oldflags) {
*pprev = vma;
return 0;
}
and this test works in many cases, but it is too sharp in some
others, where it differentiates between protection values that the
underlying PTE format makes no distinction about, such as
PROT_EXEC == PROT_READ on x86.
2)
Even where the pte format over vma flag changes necessiates a
modification of the pagetables, there might be no pagetables
yet to modify: they might not be instantiated yet.
During a regular desktop bootup this optimization hits a couple
of hundred times. During a Java test I measured thousands of
hits.
So this optimization improves sys_mprotect() in general, not just
CONFIG_NUMA_BALANCING=y kernels.
[ We could further increase the efficiency of this optimization if
change_pte_range() and change_huge_pmd() was a bit smarter about
recognizing exact-same-value protection masks - when the hardware
can do that safely. This would probably further speed up mprotect(). ]
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This will be used for three kinds of purposes:
- to optimize mprotect()
- to speed up working set scanning for working set areas that
have not been touched
- to more accurately scan per real working set
No change in functionality from this patch.
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
With transparent hugepage support, handle_mm_fault() has to be careful
that a normal PMD has been established before handling a PTE fault. To
achieve this, it used __pte_alloc() directly instead of pte_alloc_map
as pte_alloc_map is unsafe to run against a huge PMD. pte_offset_map()
is called once it is known the PMD is safe.
pte_alloc_map() is smart enough to check if a PTE is already present
before calling __pte_alloc but this check was lost. As a consequence,
PTEs may be allocated unnecessarily and the page table lock taken.
Thi useless PTE does get cleaned up but it's a performance hit which
is visible in page_test from aim9.
This patch simply re-adds the check normally done by pte_alloc_map to
check if the PTE needs to be allocated before taking the page table
lock. The effect is noticable in page_test from aim9.
AIM9
2.6.38-vanilla 2.6.38-checkptenone
creat-clo 446.10 ( 0.00%) 424.47 (-5.10%)
page_test 38.10 ( 0.00%) 42.04 ( 9.37%)
brk_test 52.45 ( 0.00%) 51.57 (-1.71%)
exec_test 382.00 ( 0.00%) 456.90 (16.39%)
fork_test 60.11 ( 0.00%) 67.79 (11.34%)
MMTests Statistics: duration
Total Elapsed Time (seconds) 611.90 612.22
(While this affects 2.6.38, it is a performance rather than a
functional bug and normally outside the rules -stable. While the big
performance differences are to a microbench, the difference in fork
and exec performance may be significant enough that -stable wants to
consider the patch)
Reported-by: Raz Ben Yehuda <raziebe@gmail.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rik van Riel <riel@redhat.com>
[ Picked this up from the AutoNUMA tree to help
it upstream and to allow apples-to-apples
performance comparisons. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If ptep_clear_flush() is called to clear a page table entry that is
accessible anyway by the CPU, eg. a _PAGE_PROTNONE page table entry,
there is no need to flush the TLB on remote CPUs.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-vm3rkzevahelwhejx5uwm8ex@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The function ptep_set_access_flags is only ever used to upgrade
access permissions to a page. That means the only negative side
effect of not flushing remote TLBs is that other CPUs may incur
spurious page faults, if they happen to access the same address,
and still have a PTE with the old permissions cached in their
TLB.
Having another CPU maybe incur a spurious page fault is faster
than always incurring the cost of a remote TLB flush, so replace
the remote TLB flush with a purely local one.
This should be safe on every architecture that correctly
implements flush_tlb_fix_spurious_fault() to actually invalidate
the local TLB entry that caused a page fault, as well as on
architectures where the hardware invalidates TLB entries that
cause page faults.
In the unlikely event that you are hitting what appears to be
an infinite loop of page faults, and 'git bisect' took you to
this changeset, your architecture needs to implement
flush_tlb_fix_spurious_fault to actually flush the TLB entry.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Extract the code to do object alignment from the allocators.
Do the alignment calculations in slab_common so that the
__kmem_cache_create functions of the allocators do not have
to deal with alignment.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Simplify setup and reduce code in kmem_cache_init(). This allows us to
get rid of initarray_cache as well as the manual setup code for
the kmem_cache and kmem_cache_node arrays during bootstrap.
We introduce a new bootstrap state "PARTIAL" for slab that signals the
creation of a kmem_cache boot cache.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Simplify bootstrap by statically allocated two kmem_cache structures. These are
freed after bootup is complete. Allows us to no longer worry about calculations
of sizes of kmem_cache structures during bootstrap.
Reviewed-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Use a special function to create kmalloc caches and use that function in
SLAB and SLUB.
Acked-by: Joonsoo Kim <js1304@gmail.com>
Reviewed-by: Glauber Costa <glommer@parallels.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
The nodelists field in kmem_cache is pointing to the first unused
object in the array field when bootstrap is complete.
A problem with the current approach is that the statically sized
kmem_cache structure use on boot can only contain NR_CPUS entries.
If the number of nodes plus the number of cpus is greater then we
would overwrite memory following the kmem_cache_boot definition.
Increase the size of the array field to ensure that also the node
pointers fit into the array field.
Once we do that we no longer need the kmem_cache_nodelists
array and we can then also use that structure elsewhere.
Acked-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Pass a kmem_cache_cpu pointer into unfreeze partials so that a different
kmem_cache_cpu structure than the local one can be specified.
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
dmapool always calls dma_alloc_coherent() with GFP_ATOMIC flag,
regardless the flags provided by the caller. This causes excessive
pruning of emergency memory pools without any good reason. Additionaly,
on ARM architecture any driver which is using dmapools will sooner or
later trigger the following error:
"ERROR: 256 KiB atomic DMA coherent pool is too small!
Please increase it with coherent_pool= kernel parameter!".
Increasing the coherent pool size usually doesn't help much and only
delays such error, because all GFP_ATOMIC DMA allocations are always
served from the special, very limited memory pool.
This patch changes the dmapool code to correctly use gfp flags provided
by the dmapool caller.
Reported-by: Soeren Moch <smoch@web.de>
Reported-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Soeren Moch <smoch@web.de>
Cc: stable@vger.kernel.org
This reverts commits a50915394f and
d7c3b937bd.
This is a revert of a revert of a revert. In addition, it reverts the
even older i915 change to stop using the __GFP_NO_KSWAPD flag due to the
original commits in linux-next.
It turns out that the original patch really was bogus, and that the
original revert was the correct thing to do after all. We thought we
had fixed the problem, and then reverted the revert, but the problem
really is fundamental: waking up kswapd simply isn't the right thing to
do, and direct reclaim sometimes simply _is_ the right thing to do.
When certain allocations fail, we simply should try some direct reclaim,
and if that fails, fail the allocation. That's the right thing to do
for THP allocations, which can easily fail, and the GPU allocations want
to do that too.
So starting kswapd is sometimes simply wrong, and removing the flag that
said "don't start kswapd" was a mistake. Let's hope we never revisit
this mistake again - and certainly not this many times ;)
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit 782fd30406.
We are going to reinstate the __GFP_NO_KSWAPD flag that has been
removed, the removal reverted, and then removed again. Making this
commit a pointless fixup for a problem that was caused by the removal of
__GFP_NO_KSWAPD flag.
The thing is, we really don't want to wake up kswapd for THP allocations
(because they fail quite commonly under any kind of memory pressure,
including when there is tons of memory free), and these patches were
just trying to fix up the underlying bug: the original removal of
__GFP_NO_KSWAPD in commit c654345924 ("mm: remove __GFP_NO_KSWAPD")
was simply bogus.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
commit c702418f8a ("mm: vmscan: do not keep kswapd looping forever due
to individual uncompactable zones") removed zone watermark checks from
the compaction code in kswapd but left in the zone congestion clearing,
which now happens unconditionally on higher order reclaim.
This messes up the reclaim throttling logic for zones with
dirty/writeback pages, where zones should only lose their congestion
status when their watermarks have been restored.
Remove the clearing from the zone compaction section entirely. The
preliminary zone check and the reclaim loop in kswapd will clear it if
the zone is considered balanced.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This fixes a regression in 3.7-rc, which has since gone into stable.
Commit 00442ad04a ("mempolicy: fix a memory corruption by refcount
imbalance in alloc_pages_vma()") changed get_vma_policy() to raise the
refcount on a shmem shared mempolicy; whereas shmem_alloc_page() went
on expecting alloc_page_vma() to drop the refcount it had acquired.
This deserves a rework: but for now fix the leak in shmem_alloc_page().
Hugh: shmem_swapin() did not need a fix, but surely it's clearer to use
the same refcounting there as in shmem_alloc_page(), delete its onstack
mempolicy, and the strange mpol_cond_copy() and __mpol_cond_copy() -
those were invented to let swapin_readahead() make an unknown number of
calls to alloc_pages_vma() with one mempolicy; but since 00442ad04a,
alloc_pages_vma() has kept refcount in balance, so now no problem.
Reported-and-tested-by: Tommi Rantala <tt.rantala@gmail.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a zone meets its high watermark and is compactable in case of
higher order allocations, it contributes to the percentage of the node's
memory that is considered balanced.
This requirement, that a node be only partially balanced, came about
when kswapd was desparately trying to balance tiny zones when all bigger
zones in the node had plenty of free memory. Arguably, the same should
apply to compaction: if a significant part of the node is balanced
enough to run compaction, do not get hung up on that tiny zone that
might never get in shape.
When the compaction logic in kswapd is reached, we know that at least
25% of the node's memory is balanced properly for compaction (see
zone_balanced and pgdat_balanced). Remove the individual zone checks
that restart the kswapd cycle.
Otherwise, we may observe more endless looping in kswapd where the
compaction code loops back to reclaim because of a single zone and
reclaim does nothing because the node is considered balanced overall.
See for example
https://bugzilla.redhat.com/show_bug.cgi?id=866988
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-and-tested-by: Thorsten Leemhuis <fedora@leemhuis.info>
Reported-by: Jiri Slaby <jslaby@suse.cz>
Tested-by: John Ellson <john.ellson@comcast.net>
Tested-by: Zdenek Kabelac <zkabelac@redhat.com>
Tested-by: Bruno Wolff III <bruno@wolff.to>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 0bf380bc70 ("mm: compaction: check pfn_valid when entering a
new MAX_ORDER_NR_PAGES block during isolation for migration") added a
check for pfn_valid() when isolating pages for migration as the scanner
does not necessarily start pageblock-aligned.
Since commit c89511ab2f ("mm: compaction: Restart compaction from near
where it left off"), the free scanner has the same problem. This patch
makes sure that the pfn range passed to isolate_freepages_block() is
within the same block so that pfn_valid() checks are unnecessary.
In answer to Henrik's wondering why others have not reported this:
reproducing this requires a large enough hole with the right aligment to
have compaction walk into a PFN range with no memmap. Size and
alignment depends in the memory model - 4M for FLATMEM and 128M for
SPARSEMEM on x86. It needs a "lucky" machine.
Reported-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I've legally changed my name with New York State, the US Social Security
Administration, et al. This patch propagates the name change and change
in initials and login to comments in the kernel source as well.
Signed-off-by: Nadia Yvette Chambers <nyc@holomorphy.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
In realtime environments, it may be desirable to keep the per-bdi
flusher threads from running on certain cpus. This patch adds a
cpu_list file to /sys/class/bdi/* to enable this. The default is to tie
the flusher threads to the same numa node as the backing device (though
I could be convinced to make it a mask of all cpus to avoid a change in
behaviour).
Thanks to Jeremy Eder for the original idea.
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When we try to soft-offline a thp tail page, put_page() is called on the
tail page unthinkingly and VM_BUG_ON is triggered in put_compound_page().
This patch splits thp before going into the main body of soft-offlining.
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With "mm: vmscan: scale number of pages reclaimed by reclaim/compaction
based on failures" reverted, Zdenek Kabelac reported the following
Hmm, so it's just took longer to hit the problem and observe
kswapd0 spinning on my CPU again - it's not as endless like before -
but still it easily eats minutes - it helps to turn off Firefox
or TB (memory hungry apps) so kswapd0 stops soon - and restart
those apps again. (And I still have like >1GB of cached memory)
kswapd0 R running task 0 30 2 0x00000000
Call Trace:
preempt_schedule+0x42/0x60
_raw_spin_unlock+0x55/0x60
put_super+0x31/0x40
drop_super+0x22/0x30
prune_super+0x149/0x1b0
shrink_slab+0xba/0x510
The sysrq+m indicates the system has no swap so it'll never reclaim
anonymous pages as part of reclaim/compaction. That is one part of the
problem but not the root cause as file-backed pages could also be
reclaimed.
The likely underlying problem is that kswapd is woken up or kept awake
for each THP allocation request in the page allocator slow path.
If compaction fails for the requesting process then compaction will be
deferred for a time and direct reclaim is avoided. However, if there
are a storm of THP requests that are simply rejected, it will still be
the the case that kswapd is awake for a prolonged period of time as
pgdat->kswapd_max_order is updated each time. This is noticed by the
main kswapd() loop and it will not call kswapd_try_to_sleep(). Instead
it will loopp, shrinking a small number of pages and calling
shrink_slab() on each iteration.
This patch defers when kswapd gets woken up for THP allocations. For
!THP allocations, kswapd is always woken up. For THP allocations,
kswapd is woken up iff the process is willing to enter into direct
reclaim/compaction.
[akpm@linux-foundation.org: fix typo in comment]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Zdenek Kabelac <zkabelac@redhat.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robert Jennings <rcj@linux.vnet.ibm.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It apepars that this patch was innocent, and we hope that "mm: avoid
waking kswapd for THP allocations when compaction is deferred or
contended" will fix the final kswapd-spinning cause.
Cc: Zdenek Kabelac <zkabelac@redhat.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robert Jennings <rcj@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Kswapd does not in all places have the same criteria for a balanced
zone. Zones are only being reclaimed when their high watermark is
breached, but compaction checks loop over the zonelist again when the
zone does not meet the low watermark plus two times the size of the
allocation. This gets kswapd stuck in an endless loop over a small
zone, like the DMA zone, where the high watermark is smaller than the
compaction requirement.
Add a function, zone_balanced(), that checks the watermark, and, for
higher order allocations, if compaction has enough free memory. Then
use it uniformly to check for balanced zones.
This makes sure that when the compaction watermark is not met, at least
reclaim happens and progress is made - or the zone is declared
unreclaimable at some point and skipped entirely.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: George Spelvin <linux@horizon.com>
Reported-by: Johannes Hirte <johannes.hirte@fem.tu-ilmenau.de>
Reported-by: Tomas Racek <tracek@redhat.com>
Tested-by: Johannes Hirte <johannes.hirte@fem.tu-ilmenau.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit ef6c5be658 ("fix incorrect NR_FREE_PAGES accounting (appears
like memory leak)") fixes a NR_FREE_PAGE accounting leak but missed the
return value which was also missed by this reviewer until today.
That return value is used by compaction when adding pages to a list of
isolated free pages and without this follow-up fix, there is a risk of
free list corruption.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 5515061d22 ("mm: throttle direct reclaimers if PF_MEMALLOC
reserves are low and swap is backed by network storage") introduced a
check for fatal signals after a process gets throttled for network
storage. The intention was that if a process was throttled and got
killed that it should not trigger the OOM killer. As pointed out by
Minchan Kim and David Rientjes, this check is in the wrong place and too
broad. If a system is in am OOM situation and a process is exiting, it
can loop in __alloc_pages_slowpath() and calling direct reclaim in a
loop. As the fatal signal is pending it returns 1 as if it is making
forward progress and can effectively deadlock.
This patch moves the fatal_signal_pending() check after throttling to
throttle_direct_reclaim() where it belongs. If the process is killed
while throttled, it will return immediately without direct reclaim
except now it will have TIF_MEMDIE set and will use the PFMEMALLOC
reserves.
Minchan pointed out that it may be better to direct reclaim before
returning to avoid using the reserves because there may be pages that
can easily reclaim that would avoid using the reserves. However, we do
no such targetted reclaim and there is no guarantee that suitable pages
are available. As it is expected that this throttling happens when
swap-over-NFS is used there is a possibility that the process will
instead swap which may allocate network buffers from the PFMEMALLOC
reserves. Hence, in the swap-over-nfs case where a process can be
throtted and be killed it can use the reserves to exit or it can
potentially use reserves to swap a few pages and then exit. This patch
takes the option of using the reserves if necessary to allow the process
exit quickly.
If this patch passes review it should be considered a -stable candidate
for 3.6.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With "mm: vmscan: scale number of pages reclaimed by reclaim/compaction
based on failures" reverted, Zdenek Kabelac reported the following
Hmm, so it's just took longer to hit the problem and observe
kswapd0 spinning on my CPU again - it's not as endless like before -
but still it easily eats minutes - it helps to turn off Firefox
or TB (memory hungry apps) so kswapd0 stops soon - and restart
those apps again. (And I still have like >1GB of cached memory)
kswapd0 R running task 0 30 2 0x00000000
Call Trace:
preempt_schedule+0x42/0x60
_raw_spin_unlock+0x55/0x60
put_super+0x31/0x40
drop_super+0x22/0x30
prune_super+0x149/0x1b0
shrink_slab+0xba/0x510
The sysrq+m indicates the system has no swap so it'll never reclaim
anonymous pages as part of reclaim/compaction. That is one part of the
problem but not the root cause as file-backed pages could also be
reclaimed.
The likely underlying problem is that kswapd is woken up or kept awake
for each THP allocation request in the page allocator slow path.
If compaction fails for the requesting process then compaction will be
deferred for a time and direct reclaim is avoided. However, if there
are a storm of THP requests that are simply rejected, it will still be
the the case that kswapd is awake for a prolonged period of time as
pgdat->kswapd_max_order is updated each time. This is noticed by the
main kswapd() loop and it will not call kswapd_try_to_sleep(). Instead
it will loopp, shrinking a small number of pages and calling
shrink_slab() on each iteration.
The temptation is to supply a patch that checks if kswapd was woken for
THP and if so ignore pgdat->kswapd_max_order but it'll be a hack and not
backed up by proper testing. As 3.7 is very close to release and this
is not a bug we should release with, a safer path is to revert "mm:
remove __GFP_NO_KSWAPD" for now and revisit it with the view to ironing
out the balance_pgdat() logic in general.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Zdenek Kabelac <zkabelac@redhat.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robert Jennings <rcj@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There have been some 3.7-rc reports of vm issues, including some kswapd
bugs and, more importantly, some memory "leaks":
http://www.spinics.net/lists/linux-mm/msg46187.htmlhttps://bugzilla.kernel.org/show_bug.cgi?id=50181
Commit 1fb3f8ca0e ("mm: compaction: capture a suitable high-order page
immediately when it is made available") took split_free_page() and
reused it for the compaction code. It does something curious with
capture_free_page() (previously known as split_free_page()):
int capture_free_page(struct page *page, int alloc_order,
...
__mod_zone_page_state(zone, NR_FREE_PAGES, -(1UL << order));
- /* Split into individual pages */
- set_page_refcounted(page);
- split_page(page, order);
+ if (alloc_order != order)
+ expand(zone, page, alloc_order, order,
+ &zone->free_area[order], migratetype);
Note that expand() puts the pages _back_ in the allocator, but it does
not bump NR_FREE_PAGES. We "return" 'alloc_order' worth of pages, but
we accounted for removing 'order' in the __mod_zone_page_state() call.
For the old split_page()-style use (order==alloc_order) the bug will not
trigger. But, when called from the compaction code where we
occasionally get a larger page out of the buddy allocator than we need,
we will run in to this.
This patch simply changes the NR_FREE_PAGES manipulation to the correct
'alloc_order' instead of 'order'.
I've been able to repeatedly trigger this in my testing environment.
The amount "leaked" very closely tracks the imbalance I see in buddy
pages vs. NR_FREE_PAGES. I have confirmed that this patch fixes the
imbalance
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rename cgroup_subsys css lifetime related callbacks to better describe
what their roles are. Also, update documentation.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
"Asynchronous" is misspelled in some comments. No code changes.
Signed-off-by: Adam Buchbinder <adam.buchbinder@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Revert commit 7f1290f2f2 ("mm: fix-up zone present pages")
That patch tried to fix a issue when calculating zone->present_pages,
but it caused a regression on 32bit systems with HIGHMEM. With that
change, reset_zone_present_pages() resets all zone->present_pages to
zero, and fixup_zone_present_pages() is called to recalculate
zone->present_pages when the boot allocator frees core memory pages into
buddy allocator. Because highmem pages are not freed by bootmem
allocator, all highmem zones' present_pages becomes zero.
Various options for improving the situation are being discussed but for
now, let's return to the 3.6 code.
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Petr Tesarik <ptesarik@suse.cz>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: Chris Clayton <chris2553@googlemail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Under a particular load on one machine, I have hit shmem_evict_inode()'s
BUG_ON(inode->i_blocks), enough times to narrow it down to a particular
race between swapout and eviction.
It comes from the "if (freed > 0)" asymmetry in shmem_recalc_inode(),
and the lack of coherent locking between mapping's nrpages and shmem's
swapped count. There's a window in shmem_writepage(), between lowering
nrpages in shmem_delete_from_page_cache() and then raising swapped
count, when the freed count appears to be +1 when it should be 0, and
then the asymmetry stops it from being corrected with -1 before hitting
the BUG.
One answer is coherent locking: using tree_lock throughout, without
info->lock; reasonable, but the raw_spin_lock in percpu_counter_add() on
used_blocks makes that messier than expected. Another answer may be a
further effort to eliminate the weird shmem_recalc_inode() altogether,
but previous attempts at that failed.
So far undecided, but for now change the BUG_ON to WARN_ON: in usual
circumstances it remains a useful consistency check.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fuzzing with trinity hit the "impossible" VM_BUG_ON(error) (which Fedora
has converted to WARNING) in shmem_getpage_gfp():
WARNING: at mm/shmem.c:1151 shmem_getpage_gfp+0xa5c/0xa70()
Pid: 29795, comm: trinity-child4 Not tainted 3.7.0-rc2+ #49
Call Trace:
warn_slowpath_common+0x7f/0xc0
warn_slowpath_null+0x1a/0x20
shmem_getpage_gfp+0xa5c/0xa70
shmem_fault+0x4f/0xa0
__do_fault+0x71/0x5c0
handle_pte_fault+0x97/0xae0
handle_mm_fault+0x289/0x350
__do_page_fault+0x18e/0x530
do_page_fault+0x2b/0x50
page_fault+0x28/0x30
tracesys+0xe1/0xe6
Thanks to Johannes for pointing to truncation: free_swap_and_cache()
only does a trylock on the page, so the page lock we've held since
before confirming swap is not enough to protect against truncation.
What cleanup is needed in this case? Just delete_from_swap_cache(),
which takes care of the memcg uncharge.
Signed-off-by: Hugh Dickins <hughd@google.com>
Reported-by: Dave Jones <davej@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
kmap_to_page returns the corresponding struct page for a virtual address
of an arbitrary mapping. This works by checking whether the address
falls in the pkmap region and using the pkmap page tables instead of the
linear mapping if appropriate.
Unfortunately, the bounds checking means that PKMAP_ADDR(LAST_PKMAP) is
incorrectly treated as a highmem address and we can end up walking off
the end of pkmap_page_table and subsequently passing junk to pte_page.
This patch fixes the bound check to stay within the pkmap tables.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Jiri Slaby reported the following:
(It's an effective revert of "mm: vmscan: scale number of pages
reclaimed by reclaim/compaction based on failures".) Given kswapd
had hours of runtime in ps/top output yesterday in the morning
and after the revert it's now 2 minutes in sum for the last 24h,
I would say, it's gone.
The intention of the patch in question was to compensate for the loss of
lumpy reclaim. Part of the reason lumpy reclaim worked is because it
aggressively reclaimed pages and this patch was meant to be a sane
compromise.
When compaction fails, it gets deferred and both compaction and
reclaim/compaction is deferred avoid excessive reclaim. However, since
commit c654345924 ("mm: remove __GFP_NO_KSWAPD"), kswapd is woken up
each time and continues reclaiming which was not taken into account when
the patch was developed.
Attempts to address the problem ended up just changing the shape of the
problem instead of fixing it. The release window gets closer and while
a THP allocation failing is not a major problem, kswapd chewing up a lot
of CPU is.
This patch reverts commit 83fde0f228 ("mm: vmscan: scale number of
pages reclaimed by reclaim/compaction based on failures") and will be
revisited in the future.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Zdenek Kabelac <zkabelac@redhat.com>
Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Johannes Hirte <johannes.hirte@fem.tu-ilmenau.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There's a name leak introduced by commit 91a27b2a75 ("vfs: define
struct filename and have getname() return it"). Add the missing
putname.
[akpm@linux-foundation.org: cleanup]
Signed-off-by: Xiaotian Feng <dannyfeng@tencent.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When MEMCG is configured on (even when it's disabled by boot option),
when adding or removing a page to/from its lru list, the zone pointer
used for stats updates is nowadays taken from the struct lruvec. (On
many configurations, calculating zone from page is slower.)
But we have no code to update all the lruvecs (per zone, per memcg) when
a memory node is hotadded. Here's an extract from the oops which
results when running numactl to bind a program to a newly onlined node:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000f60
IP: __mod_zone_page_state+0x9/0x60
Pid: 1219, comm: numactl Not tainted 3.6.0-rc5+ #180 Bochs Bochs
Process numactl (pid: 1219, threadinfo ffff880039abc000, task ffff8800383c4ce0)
Call Trace:
__pagevec_lru_add_fn+0xdf/0x140
pagevec_lru_move_fn+0xb1/0x100
__pagevec_lru_add+0x1c/0x30
lru_add_drain_cpu+0xa3/0x130
lru_add_drain+0x2f/0x40
...
The natural solution might be to use a memcg callback whenever memory is
hotadded; but that solution has not been scoped out, and it happens that
we do have an easy location at which to update lruvec->zone. The lruvec
pointer is discovered either by mem_cgroup_zone_lruvec() or by
mem_cgroup_page_lruvec(), and both of those do know the right zone.
So check and set lruvec->zone in those; and remove the inadequate
attempt to set lruvec->zone from lruvec_init(), which is called before
NODE_DATA(node) has been allocated in such cases.
Ah, there was one exceptionr. For no particularly good reason,
mem_cgroup_force_empty_list() has its own code for deciding lruvec.
Change it to use the standard mem_cgroup_zone_lruvec() and
mem_cgroup_get_lru_size() too. In fact it was already safe against such
an oops (the lru lists in danger could only be empty), but we're better
proofed against future changes this way.
I've marked this for stable (3.6) since we introduced the problem in 3.5
(now closed to stable); but I have no idea if this is the only fix
needed to get memory hotadd working with memcg in 3.6, and received no
answer when I enquired twice before.
Reported-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
oom_badness() takes a totalpages argument which says how many pages are
available and it uses it as a base for the score calculation. The value
is calculated by mem_cgroup_get_limit which considers both limit and
total_swap_pages (resp. memsw portion of it).
This is usually correct but since fe35004fbf ("mm: avoid swapping out
with swappiness==0") we do not swap when swappiness is 0 which means
that we cannot really use up all the totalpages pages. This in turn
confuses oom score calculation if the memcg limit is much smaller than
the available swap because the used memory (capped by the limit) is
negligible comparing to totalpages so the resulting score is too small
if adj!=0 (typically task with CAP_SYS_ADMIN or non zero oom_score_adj).
A wrong process might be selected as result.
The problem can be worked around by checking mem_cgroup_swappiness==0
and not considering swap at all in such a case.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
do_wp_page() sets mmun_called if mmun_start and mmun_end were
initialized and, if so, may call mmu_notifier_invalidate_range_end()
with these values. This doesn't prevent gcc from emitting a build
warning though:
mm/memory.c: In function `do_wp_page':
mm/memory.c:2530: warning: `mmun_start' may be used uninitialized in this function
mm/memory.c:2531: warning: `mmun_end' may be used uninitialized in this function
It's much easier to initialize the variables to impossible values and do
a simple comparison to determine if they were initialized to remove the
bool entirely.
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Iterating over the vma->anon_vma_chain without anon_vma_lock may cause
NULL ptr deref in anon_vma_interval_tree_verify(), because the node in the
chain might have been removed.
BUG: unable to handle kernel paging request at fffffffffffffff0
IP: [<ffffffff8122c29c>] anon_vma_interval_tree_verify+0xc/0xa0
PGD 4e28067 PUD 4e29067 PMD 0
Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
CPU 0
Pid: 9050, comm: trinity-child64 Tainted: G W 3.7.0-rc2-next-20121025-sasha-00001-g673f98e-dirty #77
RIP: 0010: anon_vma_interval_tree_verify+0xc/0xa0
Process trinity-child64 (pid: 9050, threadinfo ffff880045f80000, task ffff880048eb0000)
Call Trace:
validate_mm+0x58/0x1e0
vma_adjust+0x635/0x6b0
__split_vma.isra.22+0x161/0x220
split_vma+0x24/0x30
sys_madvise+0x5da/0x7b0
tracesys+0xe1/0xe6
RIP anon_vma_interval_tree_verify+0xc/0xa0
CR2: fffffffffffffff0
Figured out by Bob Liu.
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Bob Liu <lliubbo@gmail.com>
Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It will be useful to be able to access global memory commitment from
device drivers. On the Hyper-V platform, the host has a policy engine to
balance the available physical memory amongst all competing virtual
machines hosted on a given node. This policy engine is driven by a number
of metrics including the memory commitment reported by the guests. The
balloon driver for Linux on Hyper-V will use this function to retrieve
guest memory commitment. This function is also used in Xen self
ballooning code.
[akpm@linux-foundation.org: coding-style tweak]
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix new kernel-doc warnings in mm/slab.c:
Warning(mm/slab.c:2358): No description found for parameter 'cachep'
Warning(mm/slab.c:2358): Excess function parameter 'name' description in '__kmem_cache_create'
Warning(mm/slab.c:2358): Excess function parameter 'size' description in '__kmem_cache_create'
Warning(mm/slab.c:2358): Excess function parameter 'align' description in '__kmem_cache_create'
Warning(mm/slab.c:2358): Excess function parameter 'ctor' description in '__kmem_cache_create'
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
In kswapd(), set current->reclaim_state to NULL before returning, as
current->reclaim_state holds reference to variable on kswapd()'s stack.
In rare cases, while returning from kswapd() during memory offlining,
__free_slab() and freepages() can access the dangling pointer of
current->reclaim_state.
Signed-off-by: Takamori Yamaguchi <takamori.yamaguchi@jp.sony.com>
Signed-off-by: Aaditya Kumar <aaditya.kumar@ap.sony.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull rmdir updates into for-3.8 so that further callback updates can
be put on top. This pull created a trivial conflict between the
following two commits.
8c7f6edbda ("cgroup: mark subsystems with broken hierarchy support and whine if cgroups are nested for them")
ed95779340 ("cgroup: kill cgroup_subsys->__DEPRECATED_clear_css_refs")
The former added a field to cgroup_subsys and the latter removed one
from it. They happen to be colocated causing the conflict. Keeping
what's added and removing what's removed resolves the conflict.
Signed-off-by: Tejun Heo <tj@kernel.org>
All ->pre_destory() implementations return 0 now, which is the only
allowed return value. Make it return void.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Now that pre_destroy callbacks are called from the context where neither
any task can attach the group nor any children group can be added there
is no other way to fail from hugetlb_pre_destroy.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Glauber Costa <glommer@parallels.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Now that pre_destroy callbacks are called from the context where neither
any task can attach the group nor any children group can be added there
is no other way to fail from mem_cgroup_pre_destroy.
mem_cgroup_pre_destroy doesn't have to take a reference to memcg's css
because all css' are marked dead already.
tj: Remove now unused local variable @cgrp from
mem_cgroup_reparent_charges().
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Glauber Costa <glommer@parallels.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
CGRP_WAIT_ON_RMDIR is another kludge which was added to make cgroup
destruction rollback somewhat working. cgroup_rmdir() used to drain
CSS references and CGRP_WAIT_ON_RMDIR and the associated waitqueue and
helpers were used to allow the task performing rmdir to wait for the
next relevant event.
Unfortunately, the wait is visible to controllers too and the
mechanism got exposed to memcg by 887032670d ("cgroup avoid permanent
sleep at rmdir").
Now that the draining and retries are gone, CGRP_WAIT_ON_RMDIR is
unnecessary. Remove it and all the mechanisms supporting it. Note
that memcontrol.c changes are essentially revert of 887032670d
("cgroup avoid permanent sleep at rmdir").
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Balbir Singh <bsingharora@gmail.com>
CSS_REMOVED is one of the several contortions which were necessary to
support css reference draining on cgroup removal. All css->refcnts
which need draining should be deactivated and verified to equal zero
atomically w.r.t. css_tryget(). If any one isn't zero, all refcnts
needed to be re-activated and css_tryget() shouldn't fail in the
process.
This was achieved by letting css_tryget() busy-loop until either the
refcnt is reactivated (failed removal attempt) or CSS_REMOVED is set
(committing to removal).
Now that css refcnt draining is no longer used, there's no need for
atomic rollback mechanism. css_tryget() simply can look at the
reference count and fail if it's deactivated - it's never getting
re-activated.
This patch removes CSS_REMOVED and updates __css_tryget() to fail if
the refcnt is deactivated. As deactivation and removal are a single
step now, they no longer need to be protected against css_tryget()
happening from irq context. Remove local_irq_disable/enable() from
cgroup_rmdir().
Note that this removes css_is_removed() whose only user is VM_BUG_ON()
in memcontrol.c. We can replace it with a check on the refcnt but
given that the only use case is a debug assert, I think it's better to
simply unexport it.
v2: Comment updated and explanation on local_irq_disable/enable()
added per Michal Hocko.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
The definition of ARCH_SLAB_MINALIGN is architecture dependent
and can be either of type size_t or int. Comparing that value
with ARCH_KMALLOC_MINALIGN can cause harmless warnings on
platforms where they are different. Since both are always
small positive integer numbers, using the size_t type to compare
them is safe and gets rid of the warning.
Without this patch, building ARM collie_defconfig results in:
mm/slob.c: In function '__kmalloc_node':
mm/slob.c:431:152: warning: comparison of distinct pointer types lacks a cast [enabled by default]
mm/slob.c: In function 'kfree':
mm/slob.c:484:153: warning: comparison of distinct pointer types lacks a cast [enabled by default]
mm/slob.c: In function 'ksize':
mm/slob.c:503:153: warning: comparison of distinct pointer types lacks a cast [enabled by default]
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
[ penberg@kernel.org: updates for master ]
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Some flags are used internally by the allocators for management
purposes. One example of that is the CFLGS_OFF_SLAB flag that slab uses
to mark that the metadata for that cache is stored outside of the slab.
No cache should ever pass those as a creation flags. We can just ignore
this bit if it happens to be passed (such as when duplicating a cache in
the kmem memcg patches).
Because such flags can vary from allocator to allocator, we allow them
to make their own decisions on that, defining SLAB_AVAILABLE_FLAGS with
all flags that are valid at creation time. Allocators that doesn't have
any specific flag requirement should define that to mean all flags.
Common code will mask out all flags not belonging to that set.
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
When freeing objects, the slob allocator currently free empty pages
calling __free_pages(). However, page-size kmallocs are disposed
using put_page() instead.
It makes no sense to call put_page() for kernel pages that are provided
by the object allocator, so we shouldn't be doing this ourselves.
This is based on:
commit d9b7f22623
Author: Glauber Costa <glommer@parallels.com>
slub: use free_page instead of put_page for freeing kmalloc allocation
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Acked-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Ezequiel Garcia <elezegarcia@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
This function is identically defined in all three allocators
and it's trivial to move it to slab.h
Since now it's static, inline, header-defined function
this patch also drops the EXPORT_SYMBOL tag.
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Ezequiel Garcia <elezegarcia@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Fields object_size and size are not the same: the latter might include
slab metadata. Return object_size field in kmem_cache_size().
Also, improve trace accuracy by correctly tracing reported size.
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Ezequiel Garcia <elezegarcia@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
This field was being used to store size allocation so it could be
retrieved by ksize(). However, it is a bad practice to not mark a page
as a slab page and then use fields for special purposes.
There is no need to store the allocated size and
ksize() can simply return PAGE_SIZE << compound_order(page).
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Ezequiel Garcia <elezegarcia@gmail.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
mem_cgroup_force_empty_list currently tries to remove all pages from
the given LRU. To prevent from temoporary failures (EBUSY returned by
mem_cgroup_move_parent) it uses a margin to the current LRU pages and
returns the true if there are still some pages left on the list.
If we consider that mem_cgroup_move_parent fails only when it is racing
with somebody else removing (uncharging) the page or when the page is
migrated then it is obvious that all those failures are only temporal
and so we can safely retry later.
Let's get rid of the safety margin and make the loop really wait for
the empty LRU. The caller should still make sure that all charges have
been removed from the res_counter because mem_cgroup_replace_page_cache
might add a page to the LRU after the list_empty check (it doesn't touch
res_counter though).
This catches most of the cases except for shmem which might call
mem_cgroup_replace_page_cache with a page which is not charged and on
the LRU yet but this was the case also without this patch. In order to
fix this we need a guarantee that try_get_mem_cgroup_from_page falls
back to the current mm's cgroup so it needs css_tryget to fail. This
will be fixed up in a later patch because it needs a help from cgroup
core (pre_destroy has to be called after css is cleared).
Although mem_cgroup_pre_destroy can still fail (if a new task or a new
sub-group appears) there is no reason to retry pre_destroy callback from
the cgroup core. This means that __DEPRECATED_clear_css_refs has lost
its meaning and it can be removed.
Changes since v2
- remove __DEPRECATED_clear_css_refs
Changes since v1
- use kerndoc
- be more specific about mem_cgroup_move_parent possible failures
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The root cgroup cannot be destroyed so we never hit it down the
mem_cgroup_pre_destroy path and mem_cgroup_force_empty_write shouldn't
even try to do anything if called for the root.
This means that mem_cgroup_move_parent doesn't have to bother with the
root cgroup and it can assume it can always move charges upwards.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
mem_cgroup_force_empty did two separate things depending on free_all
parameter from the very beginning. It either reclaimed as many pages as
possible and moved the rest to the parent or just moved charges to the
parent. The first variant is used as memory.force_empty callback while
the later is used from the mem_cgroup_pre_destroy.
The whole games around gotos are far from being nice and there is no
reason to keep those two functions inside one. Let's split them and
also move the responsibility for css reference counting to their callers
to make to code easier.
This patch doesn't have any functional changes.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
commit 099a19d9('allow limited allocation before slab is online') made
pcpu_alloc_chunk() use pcpu_mem_zalloc() but forgot to update
pcpu_free_chunk() accordingly. This doesn't cause any immediate
problema, but fix it for consistency.
tj: commit message updated
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Pull x86 fixes from Ingo Molnar:
"This fixes a couple of nasty page table initialization bugs which were
causing kdump regressions. A clean rearchitecturing of the code is in
the works - meanwhile these are reverts that restore the
best-known-working state of the kernel.
There's also EFI fixes and other small fixes."
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, mm: Undo incorrect revert in arch/x86/mm/init.c
x86: efi: Turn off efi_enabled after setup on mixed fw/kernel
x86, mm: Find_early_table_space based on ranges that are actually being mapped
x86, mm: Use memblock memory loop instead of e820_RAM
x86, mm: Trim memory in memblock to be page aligned
x86/irq/ioapic: Check for valid irq_cfg pointer in smp_irq_move_cleanup_interrupt
x86/efi: Fix oops caused by incorrect set_memory_uc() usage
x86-64: Fix page table accounting
Revert "x86/mm: Fix the size calculation of mapping tables"
MAINTAINERS: Add EFI git repository location
Commit 957f822a0a ("mm, numa: reclaim from all nodes within reclaim
distance") caused zone_reclaim_mode to be set for all systems where two
nodes are within RECLAIM_DISTANCE of each other. This is the opposite
of what we actually want: zone_reclaim_mode should be set if two nodes
are sufficiently distant.
Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Julian Wollrath <jwollrath@web.de>
Tested-by: Julian Wollrath <jwollrath@web.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Patrik Kullman <patrik.kullman@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
While allocating mmu_notifier with parameter GFP_KERNEL, swap would start
to work in case of tight available memory. Eventually, that would lead to
a deadlock while the swap deamon swaps anonymous pages. It was caused by
commit e0f3c3f78d ("mm/mmu_notifier: init notifier if necessary").
=================================
[ INFO: inconsistent lock state ]
3.7.0-rc1+ #518 Not tainted
---------------------------------
inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage.
kswapd0/35 [HC0[0]:SC0[0]:HE1:SE1] takes:
(&mapping->i_mmap_mutex){+.+.?.}, at: page_referenced+0x9c/0x2e0
{RECLAIM_FS-ON-W} state was registered at:
mark_held_locks+0x86/0x150
lockdep_trace_alloc+0x67/0xc0
kmem_cache_alloc_trace+0x33/0x230
do_mmu_notifier_register+0x87/0x180
mmu_notifier_register+0x13/0x20
kvm_dev_ioctl+0x428/0x510
do_vfs_ioctl+0x98/0x570
sys_ioctl+0x91/0xb0
system_call_fastpath+0x16/0x1b
irq event stamp: 825
hardirqs last enabled at (825): _raw_spin_unlock_irq+0x30/0x60
hardirqs last disabled at (824): _raw_spin_lock_irq+0x19/0x80
softirqs last enabled at (0): copy_process+0x630/0x17c0
softirqs last disabled at (0): (null)
...
Simply back out the above commit, which was a small performance
optimization.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Reported-by: Andrea Righi <andrea@betterlinux.com>
Tested-by: Andrea Righi <andrea@betterlinux.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Sagi Grimberg <sagig@mellanox.co.il>
Cc: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If start_isolate_page_range() failed, unset_migratetype_isolate() has been
done inside it.
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On s390 any write to a page (even from kernel itself) sets architecture
specific page dirty bit. Thus when a page is written to via buffered
write, HW dirty bit gets set and when we later map and unmap the page,
page_remove_rmap() finds the dirty bit and calls set_page_dirty().
Dirtying of a page which shouldn't be dirty can cause all sorts of
problems to filesystems. The bug we observed in practice is that
buffers from the page get freed, so when the page gets later marked as
dirty and writeback writes it, XFS crashes due to an assertion
BUG_ON(!PagePrivate(page)) in page_buffers() called from
xfs_count_page_state().
Similar problem can also happen when zero_user_segment() call from
xfs_vm_writepage() (or block_write_full_page() for that matter) set the
hardware dirty bit during writeback, later buffers get freed, and then
page unmapped.
Fix the issue by ignoring s390 HW dirty bit for page cache pages of
mappings with mapping_cap_account_dirty(). This is safe because for
such mappings when a page gets marked as writeable in PTE it is also
marked dirty in do_wp_page() or do_page_fault(). When the dirty bit is
cleared by clear_page_dirty_for_io(), the page gets writeprotected in
page_mkclean(). So pagecache page is writeable if and only if it is
dirty.
Thanks to Hugh Dickins for pointing out mapping has to have
mapping_cap_account_dirty() for things to work and proposing a cleaned
up variant of the patch.
The patch has survived about two hours of running fsx-linux on tmpfs
while heavily swapping and several days of running on out build machines
where the original problem was triggered.
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: <stable@vger.kernel.org> [3.0+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We will not map partial pages, so need to make sure memblock
allocation will not allocate those bytes out.
Also we will use for_each_mem_pfn_range() to loop to map memory
range to keep them consistent.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/CAE9FiQVZirvaBMFYRfXMmWEcHbKSicQEHz4VAwUv0xFCk51ZNw@mail.gmail.com
Acked-by: Jacob Shin <jacob.shin@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org>
Right now, slab and slub have fields in struct page to derive which
cache a page belongs to, but they do it slightly differently.
slab uses a field called slab_cache, that lives in the third double
word. slub, uses a field called "slab", living outside of the
doublewords area.
Ideally, we could use the same field for this. Since slub heavily makes
use of the doubleword region, there isn't really much room to move
slub's slab_cache field around. Since slab does not have such strict
placement restrictions, we can move it outside the doubleword area.
The naming used by slab, "slab_cache", is less confusing, and it is
preferred over slub's generic "slab".
Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
With all the infrastructure in place, we can now have slabinfo_show
done from slab_common.c. A cache-specific function is called to grab
information about the cache itself, since that is still heavily
dependent on the implementation. But with the values produced by it, all
the printing and handling is done from common code.
Signed-off-by: Glauber Costa <glommer@parallels.com>
CC: Christoph Lameter <cl@linux.com>
CC: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
The header format is highly similar between slab and slub. The main
difference lays in the fact that slab may optionally have statistics
added here in case of CONFIG_SLAB_DEBUG, while the slub will stick them
somewhere else.
By making sure that information conditionally lives inside a
globally-visible CONFIG_DEBUG_SLAB switch, we can move the header
printing to a common location.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
This patch moves all the common machinery to slabinfo processing
to slab_common.c. We can do better by noticing that the output is
heavily common, and having the allocators to just provide finished
information about this. But after this first step, this can be done
easier.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Christoph Lameter <cl@linux.com>
CC: David Rientjes <rientjes@google.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
A set of fixes and some minor cleanups for -rc2:
- A series from Arnd that fixes warnings in drivers and other code
included by ARM defconfigs. Most have been acked by corresponding
maintainers (and seem quite hard to argue not picking up anyway in the
few exception cases).
- A few misc patches from the list for integrator/vt8500/i.MX
- A batch of fixes to OMAP platforms, fixing:
- boot problems on beaglebone,
- regression fixes for local timers
- clockdomain locking fixes
- a few boot/sparse warnings
- For Tegra:
- Clock rate calculation overflow fix
- Revert a change that removed timer clocks and a fix for symbol name clashes
- For Renesas:
- IO accessor / annotation cleanups to remove warnings
- For Kirkwood/Dove/mvebu:
- Fixes for device trees for Dove (some minor cleanups, some fixes)
- Fixes for the mvebu gpio driver
- Fix build problem for Feroceon due to missing ifdefs
- Fix lsxl DTS files
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)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=alOZ
-----END PGP SIGNATURE-----
Merge tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM soc fixes from Olof Johansson:
"A set of fixes and some minor cleanups for -rc2:
- A series from Arnd that fixes warnings in drivers and other code
included by ARM defconfigs. Most have been acked by corresponding
maintainers (and seem quite hard to argue not picking up anyway in
the few exception cases).
- A few misc patches from the list for integrator/vt8500/i.MX
- A batch of fixes to OMAP platforms, fixing:
- boot problems on beaglebone,
- regression fixes for local timers
- clockdomain locking fixes
- a few boot/sparse warnings
- For Tegra:
- Clock rate calculation overflow fix
- Revert a change that removed timer clocks and a fix for symbol
name clashes
- For Renesas:
- IO accessor / annotation cleanups to remove warnings
- For Kirkwood/Dove/mvebu:
- Fixes for device trees for Dove (some minor cleanups, some fixes)
- Fixes for the mvebu gpio driver
- Fix build problem for Feroceon due to missing ifdefs
- Fix lsxl DTS files"
* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (31 commits)
ARM: kirkwood: fix buttons on lsxl boards
ARM: kirkwood: fix LEDs names for lsxl boards
ARM: Kirkwood: fix disabling CACHE_FEROCEON_L2
gpio: mvebu: Add missing breaks in mvebu_gpio_irq_set_type
ARM: dove: Add crypto engine to DT
ARM: dove: Remove watchdog from DT
ARM: dove: Restructure SoC device tree descriptor
ARM: dove: Fix clock names of sata and gbe
ARM: dove: Fix tauros2 device tree init
ARM: dove: Add pcie clock support
ARM: OMAP2+: Allow kernel to boot even if GPMC fails to reserve memory
ARM: OMAP: clockdomain: Fix locking on _clkdm_clk_hwmod_enable / disable
ARM: s3c: mark s3c2440_clk_add as __init_refok
spi/s3c64xx: use correct dma_transfer_direction type
ARM: OMAP4: devices: fixup OMAP4 DMIC platform device error message
ARM: OMAP2+: clock data: Add dev-id for the omap-gpmc dummy fck
ARM: OMAP: resolve sparse warning concerning debug_card_init()
ARM: OMAP4: Fix twd_local_timer_register regression
ARM: tegra: add tegra_timer clock
ARM: tegra: rename tegra system timer
...
A collection of warning fixes on non-ARM code from Arnd Bergmann:
* 'testing/driver-warnings' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
ARM: s3c: mark s3c2440_clk_add as __init_refok
spi/s3c64xx: use correct dma_transfer_direction type
pcmcia: sharpsl: don't discard sharpsl_pcmcia_ops
USB: EHCI: mark ehci_orion_conf_mbus_windows __devinit
mm/slob: use min_t() to compare ARCH_SLAB_MINALIGN
SCSI: ARM: make fas216_dumpinfo function conditional
SCSI: ARM: ncr5380/oak uses no interrupts
Merge misc fixes from Andrew Morton:
"Seven fixes"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (7 patches)
lib/dma-debug.c: fix __hash_bucket_find()
mm: compaction: correct the nr_strict va isolated check for CMA
firmware/memmap: avoid type conflicts with the generic memmap_init()
pidns: remove recursion from free_pid_ns()
drivers/video/backlight/lm3639_bl.c: return proper error in lm3639_bled_mode_store() error paths
kernel/sys.c: fix stack memory content leak via UNAME26
linux/coredump.h needs asm/siginfo.h
Thierry reported that the "iron out" patch for isolate_freepages_block()
had problems due to the strict check being too strict with "mm:
compaction: Iron out isolate_freepages_block() and
isolate_freepages_range() -fix1". It's possible that more pages than
necessary are isolated but the check still fails and I missed that this
fix was not picked up before RC1. This same problem has been identified
in 3.7-RC1 by Tony Prisk and should be addressed by the following patch.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Tested-by: Tony Prisk <linux@prisktech.co.nz>
Reported-by: Thierry Reding <thierry.reding@avionic-design.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Richard Davies <richard@arachsys.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In commit 0b173bc4da ("mm: kill vma flag VM_CAN_NONLINEAR") we
replaced the VM_CAN_NONLINEAR test with checking whether the mapping has
a '->remap_pages()' vm operation, but there is no guarantee that there
it even has a vm_ops pointer at all.
Add the appropriate test for NULL vm_ops.
Reported-by: Sasha Levin <levinsasha928@gmail.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When we try to free object, there is some of case that we need
to take a node lock. This is the necessary step for preventing a race.
After taking a lock, then we try to cmpxchg_double_slab().
But, there is a possible scenario that cmpxchg_double_slab() is failed
with taking a lock. Following example explains it.
CPU A CPU B
need lock
... need lock
... lock!!
lock..but spin free success
spin... unlock
lock!!
free fail
In this case, retry with taking a lock is occured in CPU A.
I think that in this case for CPU A,
"release a lock first, and re-take a lock if necessary" is preferable way.
There are two reasons for this.
First, this makes __slab_free()'s logic somehow simple.
With this patch, 'was_frozen = 1' is "always" handled without taking a lock.
So we can remove one code path.
Second, it may reduce lock contention.
When we do retrying, status of slab is already changed,
so we don't need a lock anymore in almost every case.
"release a lock first, and re-take a lock if necessary" policy is
helpful to this.
Signed-off-by: Joonsoo Kim <js1304@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
When reading /proc/pid/numa_maps, it's possible to return the contents of
the stack where the mempolicy string should be printed if the policy gets
freed from beneath us.
This happens because mpol_to_str() may return an error the
stack-allocated buffer is then printed without ever being stored.
There are two possible error conditions in mpol_to_str():
- if the buffer allocated is insufficient for the string to be stored,
and
- if the mempolicy has an invalid mode.
The first error condition is not triggered in any of the callers to
mpol_to_str(): at least 50 bytes is always allocated on the stack and this
is sufficient for the string to be written. A future patch should convert
this into BUILD_BUG_ON() since we know the maximum strlen possible, but
that's not -rc material.
The second error condition is possible if a race occurs in dropping a
reference to a task's mempolicy causing it to be freed during the read().
The slab poison value is then used for the mode and mpol_to_str() returns
-EINVAL.
This race is only possible because get_vma_policy() believes that
mm->mmap_sem protects task->mempolicy, which isn't true. The exit path
does not hold mm->mmap_sem when dropping the reference or setting
task->mempolicy to NULL: it uses task_lock(task) instead.
Thus, it's required for the caller of a task mempolicy to hold
task_lock(task) while grabbing the mempolicy and reading it. Callers with
a vma policy store their mempolicy earlier and can simply increment the
reference count so it's guaranteed not to be freed.
Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It should say "@new_size" and not "@size". Correct that.
Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
Cc: trivial@kernel.org
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Certain configurations won't implicitly pull in <linux/pagemap.h> resulting
in the following build error:
mm/huge_memory.c: In function 'release_pte_page':
mm/huge_memory.c:1697:2: error: implicit declaration of function 'unlock_page' [-Werror=implicit-function-declaration]
mm/huge_memory.c: In function '__collapse_huge_page_isolate':
mm/huge_memory.c:1757:3: error: implicit declaration of function 'trylock_page' [-Werror=implicit-function-declaration]
cc1: some warnings being treated as errors
Reported-by: David Daney <david.daney@cavium.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull third pile of VFS updates from Al Viro:
"Stuff from Jeff Layton, mostly. Sanitizing interplay between audit
and namei, removing a lot of insanity from audit_inode() mess and
getting things ready for his ESTALE patchset."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
procfs: don't need a PATH_MAX allocation to hold a string representation of an int
vfs: embed struct filename inside of names_cache allocation if possible
audit: make audit_inode take struct filename
vfs: make path_openat take a struct filename pointer
vfs: turn do_path_lookup into wrapper around struct filename variant
audit: allow audit code to satisfy getname requests from its names_list
vfs: define struct filename and have getname() return it
vfs: unexport getname and putname symbols
acct: constify the name arg to acct_on
vfs: allocate page instead of names_cache buffer in mount_block_root
audit: overhaul __audit_inode_child to accomodate retrying
audit: optimize audit_compare_dname_path
audit: make audit_compare_dname_path use parent_len helper
audit: remove dirlen argument to audit_compare_dname_path
audit: set the name_len in audit_inode for parent lookups
audit: add a new "type" field to audit_names struct
audit: reverse arguments to audit_inode_child
audit: no need to walk list in audit_inode if name is NULL
audit: pass in dentry to audit_copy_inode wherever possible
audit: remove unnecessary NULL ptr checks from do_path_lookup
...and fix up the callers. For do_file_open_root, just declare a
struct filename on the stack and fill out the .name field. For
do_filp_open, make it also take a struct filename pointer, and fix up its
callers to call it appropriately.
For filp_open, add a variant that takes a struct filename pointer and turn
filp_open into a wrapper around it.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
getname() is intended to copy pathname strings from userspace into a
kernel buffer. The result is just a string in kernel space. It would
however be quite helpful to be able to attach some ancillary info to
the string.
For instance, we could attach some audit-related info to reduce the
amount of audit-related processing needed. When auditing is enabled,
we could also call getname() on the string more than once and not
need to recopy it from userspace.
This patchset converts the getname()/putname() interfaces to return
a struct instead of a string. For now, the struct just tracks the
string in kernel space and the original userland pointer for it.
Later, we'll add other information to the struct as it becomes
convenient.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull SLAB fix from Pekka Enberg:
"This contains a lockdep false positive fix from Jiri Kosina I missed
from the previous pull request."
* 'slab/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux:
mm, slab: release slab_mutex earlier in kmem_cache_destroy()
Pull pile 2 of vfs updates from Al Viro:
"Stuff in this one - assorted fixes, lglock tidy-up, death to
lock_super().
There'll be a VFS pile tomorrow (with patches from Jeff Layton,
sanitizing getname() and related parts of audit and preparing for
ESTALE fixes), but I'd rather push the stuff in this one ASAP - some
of the bugs closed here are quite unpleasant."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
vfs: bogus warnings in fs/namei.c
consitify do_mount() arguments
lglock: add DEFINE_STATIC_LGLOCK()
lglock: make the per_cpu locks static
lglock: remove unused DEFINE_LGLOCK_LOCKDEP()
MAX_LFS_FILESIZE definition for 64bit needs LL...
tmpfs,ceph,gfs2,isofs,reiserfs,xfs: fix fh_len checking
vfs: drop lock/unlock super
ufs: drop lock/unlock super
sysv: drop lock/unlock super
hpfs: drop lock/unlock super
fat: drop lock/unlock super
ext3: drop lock/unlock super
exofs: drop lock/unlock super
dup3: Return an error when oldfd == newfd.
fs: handle failed audit_log_start properly
fs: prevent use after free in auditing when symlink following was denied
Pull writeback fixes from Fengguang Wu:
"Three trivial writeback fixes"
* 'writeback-for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux:
CPU hotplug, writeback: Don't call writeback_set_ratelimit() too often during hotplug
writeback: correct comment for move_expired_inodes()
backing-dev: use kstrto* in preference to simple_strtoul
Commit 1331e7a1bb ("rcu: Remove _rcu_barrier() dependency on
__stop_machine()") introduced slab_mutex -> cpu_hotplug.lock dependency
through kmem_cache_destroy() -> rcu_barrier() -> _rcu_barrier() ->
get_online_cpus().
Lockdep thinks that this might actually result in ABBA deadlock,
and reports it as below:
=== [ cut here ] ===
======================================================
[ INFO: possible circular locking dependency detected ]
3.6.0-rc5-00004-g0d8ee37 #143 Not tainted
-------------------------------------------------------
kworker/u:2/40 is trying to acquire lock:
(rcu_sched_state.barrier_mutex){+.+...}, at: [<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0
but task is already holding lock:
(slab_mutex){+.+.+.}, at: [<ffffffff81176e15>] kmem_cache_destroy+0x45/0xe0
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (slab_mutex){+.+.+.}:
[<ffffffff810ae1e2>] validate_chain+0x632/0x720
[<ffffffff810ae5d9>] __lock_acquire+0x309/0x530
[<ffffffff810ae921>] lock_acquire+0x121/0x190
[<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450
[<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50
[<ffffffff81558cb5>] cpuup_callback+0x2f/0xbe
[<ffffffff81564b83>] notifier_call_chain+0x93/0x140
[<ffffffff81076f89>] __raw_notifier_call_chain+0x9/0x10
[<ffffffff8155719d>] _cpu_up+0xba/0x14e
[<ffffffff815572ed>] cpu_up+0xbc/0x117
[<ffffffff81ae05e3>] smp_init+0x6b/0x9f
[<ffffffff81ac47d6>] kernel_init+0x147/0x1dc
[<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10
-> #1 (cpu_hotplug.lock){+.+.+.}:
[<ffffffff810ae1e2>] validate_chain+0x632/0x720
[<ffffffff810ae5d9>] __lock_acquire+0x309/0x530
[<ffffffff810ae921>] lock_acquire+0x121/0x190
[<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450
[<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50
[<ffffffff81049197>] get_online_cpus+0x37/0x50
[<ffffffff810f21bb>] _rcu_barrier+0xbb/0x1e0
[<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20
[<ffffffff810f2309>] rcu_barrier+0x9/0x10
[<ffffffff8118c129>] deactivate_locked_super+0x49/0x90
[<ffffffff8118cc01>] deactivate_super+0x61/0x70
[<ffffffff811aaaa7>] mntput_no_expire+0x127/0x180
[<ffffffff811ab49e>] sys_umount+0x6e/0xd0
[<ffffffff81569979>] system_call_fastpath+0x16/0x1b
-> #0 (rcu_sched_state.barrier_mutex){+.+...}:
[<ffffffff810adb4e>] check_prev_add+0x3de/0x440
[<ffffffff810ae1e2>] validate_chain+0x632/0x720
[<ffffffff810ae5d9>] __lock_acquire+0x309/0x530
[<ffffffff810ae921>] lock_acquire+0x121/0x190
[<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450
[<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50
[<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0
[<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20
[<ffffffff810f2309>] rcu_barrier+0x9/0x10
[<ffffffff81176ea1>] kmem_cache_destroy+0xd1/0xe0
[<ffffffffa04c3154>] nf_conntrack_cleanup_net+0xe4/0x110 [nf_conntrack]
[<ffffffffa04c31aa>] nf_conntrack_cleanup+0x2a/0x70 [nf_conntrack]
[<ffffffffa04c42ce>] nf_conntrack_net_exit+0x5e/0x80 [nf_conntrack]
[<ffffffff81454b79>] ops_exit_list+0x39/0x60
[<ffffffff814551ab>] cleanup_net+0xfb/0x1b0
[<ffffffff8106917b>] process_one_work+0x26b/0x4c0
[<ffffffff81069f3e>] worker_thread+0x12e/0x320
[<ffffffff8106f73e>] kthread+0x9e/0xb0
[<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10
other info that might help us debug this:
Chain exists of:
rcu_sched_state.barrier_mutex --> cpu_hotplug.lock --> slab_mutex
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(slab_mutex);
lock(cpu_hotplug.lock);
lock(slab_mutex);
lock(rcu_sched_state.barrier_mutex);
*** DEADLOCK ***
=== [ cut here ] ===
This is actually a false positive. Lockdep has no way of knowing the fact
that the ABBA can actually never happen, because of special semantics of
cpu_hotplug.refcount and its handling in cpu_hotplug_begin(); the mutual
exclusion there is not achieved through mutex, but through
cpu_hotplug.refcount.
The "neither cpu_up() nor cpu_down() will proceed past cpu_hotplug_begin()
until everyone who called get_online_cpus() will call put_online_cpus()"
semantics is totally invisible to lockdep.
This patch therefore moves the unlock of slab_mutex so that rcu_barrier()
is being called with it unlocked. It has two advantages:
- it slightly reduces hold time of slab_mutex; as it's used to protect
the cachep list, it's not necessary to hold it over kmem_cache_free()
call any more
- it silences the lockdep false positive warning, as it avoids lockdep ever
learning about slab_mutex -> cpu_hotplug.lock dependency
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Fuzzing with trinity oopsed on the 1st instruction of shmem_fh_to_dentry(),
u64 inum = fid->raw[2];
which is unhelpfully reported as at the end of shmem_alloc_inode():
BUG: unable to handle kernel paging request at ffff880061cd3000
IP: [<ffffffff812190d0>] shmem_alloc_inode+0x40/0x40
Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
Call Trace:
[<ffffffff81488649>] ? exportfs_decode_fh+0x79/0x2d0
[<ffffffff812d77c3>] do_handle_open+0x163/0x2c0
[<ffffffff812d792c>] sys_open_by_handle_at+0xc/0x10
[<ffffffff83a5f3f8>] tracesys+0xe1/0xe6
Right, tmpfs is being stupid to access fid->raw[2] before validating that
fh_len includes it: the buffer kmalloc'ed by do_sys_name_to_handle() may
fall at the end of a page, and the next page not be present.
But some other filesystems (ceph, gfs2, isofs, reiserfs, xfs) are being
careless about fh_len too, in fh_to_dentry() and/or fh_to_parent(), and
could oops in the same way: add the missing fh_len checks to those.
Reported-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Sage Weil <sage@inktank.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
The definition of ARCH_SLAB_MINALIGN is architecture dependent
and can be either of type size_t or int. Comparing that value
with ARCH_KMALLOC_MINALIGN can cause harmless warnings on
platforms where they are different. Since both are always
small positive integer numbers, using the size_t type to compare
them is safe and gets rid of the warning.
Without this patch, building ARM collie_defconfig results in:
mm/slob.c: In function '__kmalloc_node':
mm/slob.c:431:152: warning: comparison of distinct pointer types lacks a cast [enabled by default]
mm/slob.c: In function 'kfree':
mm/slob.c:484:153: warning: comparison of distinct pointer types lacks a cast [enabled by default]
mm/slob.c: In function 'ksize':
mm/slob.c:503:153: warning: comparison of distinct pointer types lacks a cast [enabled by default]
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Invalidation sequences are handled in various ways on various
architectures.
One way, which sparc64 uses, is to let the set_*_at() functions accumulate
pending flushes into a per-cpu array. Then the flush_tlb_range() et al.
calls process the pending TLB flushes.
In this regime, the __tlb_remove_*tlb_entry() implementations are
essentially NOPs.
The canonical PTE zap in mm/memory.c is:
ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
tlb_remove_tlb_entry(tlb, pte, addr);
With a subsequent tlb_flush_mmu() if needed.
Mirror this in the THP PMD zapping using:
orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
page = pmd_page(orig_pmd);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
And we properly accomodate TLB flush mechanims like the one described
above.
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The transparent huge page code passes a PMD pointer in as the third
argument of update_mmu_cache(), which expects a PTE pointer.
This never got noticed because X86 implements update_mmu_cache() as a
macro and thus we don't get any type checking, and X86 is the only
architecture which supports transparent huge pages currently.
Before other architectures can support transparent huge pages properly we
need to add a new interface which will take a PMD pointer as the third
argument rather than a PTE pointer.
[akpm@linux-foundation.org: implement update_mm_cache_pmd() for s390]
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When our x86 box calls __remove_pages(), release_mem_region() shows many
warnings. And x86 box cannot unregister iomem_resource.
"Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>"
release_mem_region() has been changed to be called in each
PAGES_PER_SECTION by commit de7f0cba96 ("memory hotplug: release
memory regions in PAGES_PER_SECTION chunks"). Because powerpc registers
iomem_resource in each PAGES_PER_SECTION chunk. But when I hot add
memory on x86 box, iomem_resource is register in each _CRS not
PAGES_PER_SECTION chunk. So x86 box unregisters iomem_resource.
The patch fixes the problem.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Nathan Fontenot <nfont@austin.ibm.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In the paranoid case of sysctl kernel.kptr_restrict=2, mask the kernel
virtual addresses in /proc/vmallocinfo too.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reported-by: Brad Spengler <spender@grsecurity.net>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a transparent hugepage is mapped and it is included in an mlock()
range, follow_page() incorrectly avoids setting the page's mlock bit and
moving it to the unevictable lru.
This is evident if you try to mlock(), munlock(), and then mlock() a
range again. Currently:
#define MAP_SIZE (4 << 30) /* 4GB */
void *ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
mlock(ptr, MAP_SIZE);
$ grep -E "Unevictable|Inactive\(anon" /proc/meminfo
Inactive(anon): 6304 kB
Unevictable: 4213924 kB
munlock(ptr, MAP_SIZE);
Inactive(anon): 4186252 kB
Unevictable: 19652 kB
mlock(ptr, MAP_SIZE);
Inactive(anon): 4198556 kB
Unevictable: 21684 kB
Notice that less than 2MB was added to the unevictable list; this is
because these pages in the range are not transparent hugepages since the
4GB range was allocated with mmap() and has no specific alignment. If
posix_memalign() were used instead, unevictable would not have grown at
all on the second mlock().
The fix is to call mlock_vma_page() so that the mlock bit is set and the
page is added to the unevictable list. With this patch:
mlock(ptr, MAP_SIZE);
Inactive(anon): 4056 kB
Unevictable: 4213940 kB
munlock(ptr, MAP_SIZE);
Inactive(anon): 4198268 kB
Unevictable: 19636 kB
mlock(ptr, MAP_SIZE);
Inactive(anon): 4008 kB
Unevictable: 4213940 kB
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
remove_memory() will be called when hot removing a memory device. But
even if offlining memory, we cannot notice it. So the patch updates the
memory block's state and sends notification to userspace.
Additionally, the memory device may contain more than one memory block.
If the memory block has been offlined, __offline_pages() will fail. So we
should try to offline one memory block at a time.
Thus remove_memory() also check each memory block's state. So there is no
need to check the memory block's state before calling remove_memory().
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
remove_memory() is called in two cases:
1. echo offline >/sys/devices/system/memory/memoryXX/state
2. hot remove a memory device
In the 1st case, the memory block's state is changed and the notification
that memory block's state changed is sent to userland after calling
remove_memory(). So user can notice memory block is changed.
But in the 2nd case, the memory block's state is not changed and the
notification is not also sent to userspcae even if calling
remove_memory(). So user cannot notice memory block is changed.
For adding the notification at memory hot remove, the patch just prepare
as follows:
1st case uses offline_pages() for offlining memory.
2nd case uses remove_memory() for offlining memory and changing memory block's
state and notifing the information.
The patch does not implement notification to remove_memory().
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Following section mismatch warning is thrown during build;
WARNING: vmlinux.o(.text+0x32408f): Section mismatch in reference from the function memblock_type_name() to the variable .meminit.data:memblock
The function memblock_type_name() references
the variable __meminitdata memblock.
This is often because memblock_type_name lacks a __meminitdata
annotation or the annotation of memblock is wrong.
This is because memblock_type_name makes reference to memblock variable
with attribute __meminitdata. Hence, the warning (even if the function is
inline).
[akpm@linux-foundation.org: remove inline]
Signed-off-by: Raghavendra D Prabhu <rprabhu@wnohang.net>
Cc: Tejun Heo <tj@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
reclaim_clean_pages_from_list() reclaims clean pages before migration so
cc.nr_migratepages should be updated. Currently, there is no problem but
it can be wrong if we try to use the value in future.
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Presently CMA cannot migrate mlocked pages so it ends up failing to allocate
contiguous memory space.
This patch makes mlocked pages be migrated out. Of course, it can affect
realtime processes but in CMA usecase, contiguous memory allocation failing
is far worse than access latency to an mlocked page being variable while
CMA is running. If someone wants to make the system realtime, he shouldn't
enable CMA because stalls can still happen at random times.
[akpm@linux-foundation.org: tweak comment text, per Mel]
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Simply remove UNEVICTABLE_MLOCKFREED and unevictable_pgs_mlockfreed line
from /proc/vmstat: Johannes and Mel point out that it was very unlikely to
have been used by any tool, and of course we can restore it easily enough
if that turns out to be wrong.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ying Han <yinghan@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing,
causing the kernel to hang. When the system doesn't have enough free
pages, it enters reclaim but never reclaim any pages due to
too_many_isolated()==true and loops forever.
The cause is that when we do memory-hotadd after memory-remove,
__zone_pcp_update() clears a zone's ZONE_STAT_ITEMS in setup_pageset()
although the vm_stat_diff of all CPUs still have values.
In addtion, when we offline all pages of the zone, we reset them in
zone_pcp_reset without draining so we loss some zone stat item.
Reviewed-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Revert commit 0def08e3ac because check_range can't fail in
migrate_to_node with considering current usecases.
Quote from Johannes
: I think it makes sense to revert. Not because of the semantics, but I
: just don't see how check_range() could even fail for this callsite:
:
: 1. we pass mm->mmap->vm_start in there, so we should not fail due to
: find_vma()
:
: 2. we pass MPOL_MF_DISCONTIG_OK, so the discontig checks do not apply
: and so can not fail
:
: 3. we pass MPOL_MF_MOVE | MPOL_MF_MOVE_ALL, the page table loops will
: continue until addr == end, so we never fail with -EIO
And I added a new VM_BUG_ON for checking migrate_to_node's future usecase
which might pass to MPOL_MF_STRICT.
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vasiliy Kulikov <segooon@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In order to allow sleeping during invalidate_page mmu notifier calls, we
need to avoid calling when holding the PT lock. In addition to its direct
calls, invalidate_page can also be called as a substitute for a change_pte
call, in case the notifier client hasn't implemented change_pte.
This patch drops the invalidate_page call from change_pte, and instead
wraps all calls to change_pte with invalidate_range_start and
invalidate_range_end calls.
Note that change_pte still cannot sleep after this patch, and that clients
implementing change_pte should not take action on it in case the number of
outstanding invalidate_range_start calls is larger than one, otherwise
they might miss a later invalidation.
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Cc: Andrea Arcangeli <andrea@qumranet.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Haggai Eran <haggaie@mellanox.com>
Cc: Shachar Raindel <raindel@mellanox.com>
Cc: Liran Liss <liranl@mellanox.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In order to allow sleeping during mmu notifier calls, we need to avoid
invoking them under the page table spinlock. This patch solves the
problem by calling invalidate_page notification after releasing the lock
(but before freeing the page itself), or by wrapping the page invalidation
with calls to invalidate_range_begin and invalidate_range_end.
To prevent accidental changes to the invalidate_range_end arguments after
the call to invalidate_range_begin, the patch introduces a convention of
saving the arguments in consistently named locals:
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
...
mmun_start = ...
mmun_end = ...
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
...
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
The patch changes code to use this convention for all calls to
mmu_notifier_invalidate_range_start/end, except those where the calls are
close enough so that anyone who glances at the code can see the values
aren't changing.
This patchset is a preliminary step towards on-demand paging design to be
added to the RDMA stack.
Why do we want on-demand paging for Infiniband?
Applications register memory with an RDMA adapter using system calls,
and subsequently post IO operations that refer to the corresponding
virtual addresses directly to HW. Until now, this was achieved by
pinning the memory during the registration calls. The goal of on demand
paging is to avoid pinning the pages of registered memory regions (MRs).
This will allow users the same flexibility they get when swapping any
other part of their processes address spaces. Instead of requiring the
entire MR to fit in physical memory, we can allow the MR to be larger,
and only fit the current working set in physical memory.
Why should anyone care? What problems are users currently experiencing?
This can make programming with RDMA much simpler. Today, developers
that are working with more data than their RAM can hold need either to
deregister and reregister memory regions throughout their process's
life, or keep a single memory region and copy the data to it. On demand
paging will allow these developers to register a single MR at the
beginning of their process's life, and let the operating system manage
which pages needs to be fetched at a given time. In the future, we
might be able to provide a single memory access key for each process
that would provide the entire process's address as one large memory
region, and the developers wouldn't need to register memory regions at
all.
Is there any prospect that any other subsystems will utilise these
infrastructural changes? If so, which and how, etc?
As for other subsystems, I understand that XPMEM wanted to sleep in
MMU notifiers, as Christoph Lameter wrote at
http://lkml.indiana.edu/hypermail/linux/kernel/0802.1/0460.html and
perhaps Andrea knows about other use cases.
Scheduling in mmu notifications is required since we need to sync the
hardware with the secondary page tables change. A TLB flush of an IO
device is inherently slower than a CPU TLB flush, so our design works by
sending the invalidation request to the device, and waiting for an
interrupt before exiting the mmu notifier handler.
Avi said:
kvm may be a buyer. kvm::mmu_lock, which serializes guest page
faults, also protects long operations such as destroying large ranges.
It would be good to convert it into a spinlock, but as it is used inside
mmu notifiers, this cannot be done.
(there are alternatives, such as keeping the spinlock and using a
generation counter to do the teardown in O(1), which is what the "may"
is doing up there).
[akpm@linux-foundation.orgpossible speed tweak in hugetlb_cow(), cleanups]
Signed-off-by: Andrea Arcangeli <andrea@qumranet.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Haggai Eran <haggaie@mellanox.com>
Cc: Shachar Raindel <raindel@mellanox.com>
Cc: Liran Liss <liranl@mellanox.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 0c176d52b0 ("mm: hugetlb: fix pgoff computation when unmapping
page from vma") fixed pgoff calculation but it has replaced it by
vma_hugecache_offset() which is not approapriate for offsets used for
vma_prio_tree_foreach() because that one expects index in page units
rather than in huge_page_shift.
Johannes said:
: The resulting index may not be too big, but it can be too small: assume
: hpage size of 2M and the address to unmap to be 0x200000. This is regular
: page index 512 and hpage index 1. If you have a VMA that maps the file
: only starting at the second huge page, that VMAs vm_pgoff will be 512 but
: you ask for offset 1 and miss it even though it does map the page of
: interest. hugetlb_cow() will try to unmap, miss the vma, and retry the
: cow until the allocation succeeds or the skipped vma(s) go away.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Hillf Danton <dhillf@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
RECLAIM_DISTANCE represents the distance between nodes at which it is
deemed too costly to allocate from; it's preferred to try to reclaim from
a local zone before falling back to allocating on a remote node with such
a distance.
To do this, zone_reclaim_mode is set if the distance between any two
nodes on the system is greather than this distance. This, however, ends
up causing the page allocator to reclaim from every zone regardless of
its affinity.
What we really want is to reclaim only from zones that are closer than
RECLAIM_DISTANCE. This patch adds a nodemask to each node that
represents the set of nodes that are within this distance. During the
zone iteration, if the bit for a zone's node is set for the local node,
then reclaim is attempted; otherwise, the zone is skipped.
[akpm@linux-foundation.org: fix CONFIG_NUMA=n build]
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We should not be seeing non-0 unevictable_pgs_mlockfreed any longer. So
remove free_page_mlock() from the page freeing paths: __PG_MLOCKED is
already in PAGE_FLAGS_CHECK_AT_FREE, so free_pages_check() will now be
checking it, reporting "BUG: Bad page state" if it's ever found set.
Comment UNEVICTABLE_MLOCKFREED and unevictable_pgs_mlockfreed always 0.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We had thought that pages could no longer get freed while still marked as
mlocked; but Johannes Weiner posted this program to demonstrate that
truncating an mlocked private file mapping containing COWed pages is still
mishandled:
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <stdio.h>
int main(void)
{
char *map;
int fd;
system("grep mlockfreed /proc/vmstat");
fd = open("chigurh", O_CREAT|O_EXCL|O_RDWR);
unlink("chigurh");
ftruncate(fd, 4096);
map = mmap(NULL, 4096, PROT_WRITE, MAP_PRIVATE, fd, 0);
map[0] = 11;
mlock(map, sizeof(fd));
ftruncate(fd, 0);
close(fd);
munlock(map, sizeof(fd));
munmap(map, 4096);
system("grep mlockfreed /proc/vmstat");
return 0;
}
The anon COWed pages are not caught by truncation's clear_page_mlock() of
the pagecache pages; but unmap_mapping_range() unmaps them, so we ought to
look out for them there in page_remove_rmap(). Indeed, why should
truncation or invalidation be doing the clear_page_mlock() when removing
from pagecache? mlock is a property of mapping in userspace, not a
property of pagecache: an mlocked unmapped page is nonsensical.
Reported-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ying Han <yinghan@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
page_evictable(page, vma) is an irritant: almost all its callers pass
NULL for vma. Remove the vma arg and use mlocked_vma_newpage(vma, page)
explicitly in the couple of places it's needed. But in those places we
don't even need page_evictable() itself! They're dealing with a freshly
allocated anonymous page, which has no "mapping" and cannot be mlocked yet.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In fuzzing with trinity, lockdep protested "possible irq lock inversion
dependency detected" when isolate_lru_page() reenabled interrupts while
still holding the supposedly irq-safe tree_lock:
invalidate_inode_pages2
invalidate_complete_page2
spin_lock_irq(&mapping->tree_lock)
clear_page_mlock
isolate_lru_page
spin_unlock_irq(&zone->lru_lock)
isolate_lru_page() is correct to enable interrupts unconditionally:
invalidate_complete_page2() is incorrect to call clear_page_mlock() while
holding tree_lock, which is supposed to nest inside lru_lock.
Both truncate_complete_page() and invalidate_complete_page() call
clear_page_mlock() before taking tree_lock to remove page from radix_tree.
I guess invalidate_complete_page2() preferred to test PageDirty (again)
under tree_lock before committing to the munlock; but since the page has
already been unmapped, its state is already somewhat inconsistent, and no
worse if clear_page_mlock() moved up.
Reported-by: Sasha Levin <levinsasha928@gmail.com>
Deciphered-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ying Han <yinghan@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
kmem code uses this function and it is better to not use forward
declarations for static inline functions as some (older) compilers don't
like it:
gcc version 4.3.4 [gcc-4_3-branch revision 152973] (SUSE Linux)
mm/memcontrol.c:421: warning: `mem_cgroup_is_root' declared inline after being called
mm/memcontrol.c:421: warning: previous declaration of `mem_cgroup_is_root' was here
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
TCP kmem accounting is currently guarded by CONFIG_MEMCG_KMEM ifdefs but
the code is not used if !CONFIG_INET so we should rather test for both.
The same applies to net/sock.h, net/ip.h and net/tcp_memcontrol.h but
let's keep those outside of any ifdefs because it is considered safer wrt.
future maintainability.
Tested with
- CONFIG_INET && CONFIG_MEMCG_KMEM
- !CONFIG_INET && CONFIG_MEMCG_KMEM
- CONFIG_INET && !CONFIG_MEMCG_KMEM
- !CONFIG_INET && !CONFIG_MEMCG_KMEM
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Glauber Costa <glommer@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I think zone->present_pages indicates pages that buddy system can management,
it should be:
zone->present_pages = spanned pages - absent pages - bootmem pages,
but is now:
zone->present_pages = spanned pages - absent pages - memmap pages.
spanned pages: total size, including holes.
absent pages: holes.
bootmem pages: pages used in system boot, managed by bootmem allocator.
memmap pages: pages used by page structs.
This may cause zone->present_pages less than it should be. For example,
numa node 1 has ZONE_NORMAL and ZONE_MOVABLE, it's memmap and other
bootmem will be allocated from ZONE_MOVABLE, so ZONE_NORMAL's
present_pages should be spanned pages - absent pages, but now it also
minus memmap pages(free_area_init_core), which are actually allocated from
ZONE_MOVABLE. When offlining all memory of a zone, this will cause
zone->present_pages less than 0, because present_pages is unsigned long
type, it is actually a very large integer, it indirectly caused
zone->watermark[WMARK_MIN] becomes a large
integer(setup_per_zone_wmarks()), than cause totalreserve_pages become a
large integer(calculate_totalreserve_pages()), and finally cause memory
allocating failure when fork process(__vm_enough_memory()).
[root@localhost ~]# dmesg
-bash: fork: Cannot allocate memory
I think the bug described in
http://marc.info/?l=linux-mm&m=134502182714186&w=2
is also caused by wrong zone present pages.
This patch intends to fix-up zone->present_pages when memory are freed to
buddy system on x86_64 and IA64 platforms.
Signed-off-by: Jianguo Wu <wujianguo@huawei.com>
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Reported-by: Petr Tesarik <ptesarik@suse.cz>
Tested-by: Petr Tesarik <ptesarik@suse.cz>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that lumpy reclaim has been removed, compaction is the only way left
to free up contiguous memory areas. It is time to just enable
CONFIG_COMPACTION by default.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The update_mmu_cache() takes a pointer (to pte_t by default) as the last
argument but the huge_memory.c passes a pmd_t value. The patch changes
the argument to the pmd_t * pointer.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If NUMA is enabled, the indicator is not reset if the previous page
request failed, ausing us to trigger the BUG_ON() in
khugepaged_alloc_page().
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The changelog for commit 6a6dccba2f ("mm: cma: don't replace lowmem
pages with highmem") mentioned that lowmem pages can be replaced by
highmem pages during CMA migration. 6a6dccba2f fixed that issue.
Quote from that changelog:
: The filesystem layer expects pages in the block device's mapping to not
: be in highmem (the mapping's gfp mask is set in bdget()), but CMA can
: currently replace lowmem pages with highmem pages, leading to crashes in
: filesystem code such as the one below:
:
: Unable to handle kernel NULL pointer dereference at virtual address 00000400
: pgd = c0c98000
: [00000400] *pgd=00c91831, *pte=00000000, *ppte=00000000
: Internal error: Oops: 817 [#1] PREEMPT SMP ARM
: CPU: 0 Not tainted (3.5.0-rc5+ #80)
: PC is at __memzero+0x24/0x80
: ...
: Process fsstress (pid: 323, stack limit = 0xc0cbc2f0)
: Backtrace:
: [<c010e3f0>] (ext4_getblk+0x0/0x180) from [<c010e58c>] (ext4_bread+0x1c/0x98)
: [<c010e570>] (ext4_bread+0x0/0x98) from [<c0117944>] (ext4_mkdir+0x160/0x3bc)
: r4:c15337f0
: [<c01177e4>] (ext4_mkdir+0x0/0x3bc) from [<c00c29e0>] (vfs_mkdir+0x8c/0x98)
: [<c00c2954>] (vfs_mkdir+0x0/0x98) from [<c00c2a60>] (sys_mkdirat+0x74/0xac)
: r6:00000000 r5:c152eb40 r4:000001ff r3:c14b43f0
: [<c00c29ec>] (sys_mkdirat+0x0/0xac) from [<c00c2ab8>] (sys_mkdir+0x20/0x24)
: r6:beccdcf0 r5:00074000 r4:beccdbbc
: [<c00c2a98>] (sys_mkdir+0x0/0x24) from [<c000e3c0>] (ret_fast_syscall+0x0/0x30)
Memory-hotplug has same problem as CMA has so the same fix can be applied
to memory-hotplug as well.
Fix it by reusing.
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__alloc_contig_migrate_alloc() can be used by memory-hotplug so refactor
it out (move + rename as a common name) into page_isolation.c.
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Compaction caches if a pageblock was scanned and no pages were isolated so
that the pageblocks can be skipped in the future to reduce scanning. This
information is not cleared by the page allocator based on activity due to
the impact it would have to the page allocator fast paths. Hence there is
a requirement that something clear the cache or pageblocks will be skipped
forever. Currently the cache is cleared if there were a number of recent
allocation failures and it has not been cleared within the last 5 seconds.
Time-based decisions like this are terrible as they have no relationship
to VM activity and is basically a big hammer.
Unfortunately, accurate heuristics would add cost to some hot paths so
this patch implements a rough heuristic. There are two cases where the
cache is cleared.
1. If a !kswapd process completes a compaction cycle (migrate and free
scanner meet), the zone is marked compact_blockskip_flush. When kswapd
goes to sleep, it will clear the cache. This is expected to be the
common case where the cache is cleared. It does not really matter if
kswapd happens to be asleep or going to sleep when the flag is set as
it will be woken on the next allocation request.
2. If there have been multiple failures recently and compaction just
finished being deferred then a process will clear the cache and start a
full scan. This situation happens if there are multiple high-order
allocation requests under heavy memory pressure.
The clearing of the PG_migrate_skip bits and other scans is inherently
racy but the race is harmless. For allocations that can fail such as THP,
they will simply fail. For requests that cannot fail, they will retry the
allocation. Tests indicated that scanning rates were roughly similar to
when the time-based heuristic was used and the allocation success rates
were similar.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Richard Davies <richard@arachsys.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is almost entirely based on Rik's previous patches and discussions
with him about how this might be implemented.
Order > 0 compaction stops when enough free pages of the correct page
order have been coalesced. When doing subsequent higher order
allocations, it is possible for compaction to be invoked many times.
However, the compaction code always starts out looking for things to
compact at the start of the zone, and for free pages to compact things to
at the end of the zone.
This can cause quadratic behaviour, with isolate_freepages starting at the
end of the zone each time, even though previous invocations of the
compaction code already filled up all free memory on that end of the zone.
This can cause isolate_freepages to take enormous amounts of CPU with
certain workloads on larger memory systems.
This patch caches where the migration and free scanner should start from
on subsequent compaction invocations using the pageblock-skip information.
When compaction starts it begins from the cached restart points and will
update the cached restart points until a page is isolated or a pageblock
is skipped that would have been scanned by synchronous compaction.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Richard Davies <richard@arachsys.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When compaction was implemented it was known that scanning could
potentially be excessive. The ideal was that a counter be maintained for
each pageblock but maintaining this information would incur a severe
penalty due to a shared writable cache line. It has reached the point
where the scanning costs are a serious problem, particularly on
long-lived systems where a large process starts and allocates a large
number of THPs at the same time.
Instead of using a shared counter, this patch adds another bit to the
pageblock flags called PG_migrate_skip. If a pageblock is scanned by
either migrate or free scanner and 0 pages were isolated, the pageblock is
marked to be skipped in the future. When scanning, this bit is checked
before any scanning takes place and the block skipped if set.
The main difficulty with a patch like this is "when to ignore the cached
information?" If it's ignored too often, the scanning rates will still be
excessive. If the information is too stale then allocations will fail
that might have otherwise succeeded. In this patch
o CMA always ignores the information
o If the migrate and free scanner meet then the cached information will
be discarded if it's at least 5 seconds since the last time the cache
was discarded
o If there are a large number of allocation failures, discard the cache.
The time-based heuristic is very clumsy but there are few choices for a
better event. Depending solely on multiple allocation failures still
allows excessive scanning when THP allocations are failing in quick
succession due to memory pressure. Waiting until memory pressure is
relieved would cause compaction to continually fail instead of using
reclaim/compaction to try allocate the page. The time-based mechanism is
clumsy but a better option is not obvious.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Richard Davies <richard@arachsys.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit 7db8889ab0 ("mm: have order > 0 compaction start
off where it left") and commit de74f1cc ("mm: have order > 0 compaction
start near a pageblock with free pages"). These patches were a good
idea and tests confirmed that they massively reduced the amount of
scanning but the implementation is complex and tricky to understand. A
later patch will cache what pageblocks should be skipped and
reimplements the concept of compact_cached_free_pfn on top for both
migration and free scanners.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Richard Davies <richard@arachsys.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Compaction's free scanner acquires the zone->lock when checking for
PageBuddy pages and isolating them. It does this even if there are no
PageBuddy pages in the range.
This patch defers acquiring the zone lock for as long as possible. In the
event there are no free pages in the pageblock then the lock will not be
acquired at all which reduces contention on zone->lock.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Richard Davies <richard@arachsys.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Tested-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Richard Davies and Shaohua Li have both reported lock contention problems
in compaction on the zone and LRU locks as well as significant amounts of
time being spent in compaction. This series aims to reduce lock
contention and scanning rates to reduce that CPU usage. Richard reported
at https://lkml.org/lkml/2012/9/21/91 that this series made a big
different to a problem he reported in August:
http://marc.info/?l=kvm&m=134511507015614&w=2
Patch 1 defers acquiring the zone->lru_lock as long as possible.
Patch 2 defers acquiring the zone->lock as lock as possible.
Patch 3 reverts Rik's "skip-free" patches as the core concept gets
reimplemented later and the remaining patches are easier to
understand if this is reverted first.
Patch 4 adds a pageblock-skip bit to the pageblock flags to cache what
pageblocks should be skipped by the migrate and free scanners.
This drastically reduces the amount of scanning compaction has
to do.
Patch 5 reimplements something similar to Rik's idea except it uses the
pageblock-skip information to decide where the scanners should
restart from and does not need to wrap around.
I tested this on 3.6-rc6 + linux-next/akpm. Kernels tested were
akpm-20120920 3.6-rc6 + linux-next/akpm as of Septeber 20th, 2012
lesslock Patches 1-6
revert Patches 1-7
cachefail Patches 1-8
skipuseless Patches 1-9
Stress high-order allocation tests looked ok. Success rates are more or
less the same with the full series applied but there is an expectation
that there is less opportunity to race with other allocation requests if
there is less scanning. The time to complete the tests did not vary that
much and are uninteresting as were the vmstat statistics so I will not
present them here.
Using ftrace I recorded how much scanning was done by compaction and got this
3.6.0-rc6 3.6.0-rc6 3.6.0-rc6 3.6.0-rc6 3.6.0-rc6
akpm-20120920 lockless revert-v2r2 cachefail skipuseless
Total free scanned 360753976 515414028 565479007 17103281 18916589
Total free isolated 28524293597369 4048601 670493 727840
Total free efficiency 0.0079% 0.0070% 0.0072% 0.0392% 0.0385%
Total migrate scanned 247728664 822729112 1004645830 17946827 14118903
Total migrate isolated 2555324 3245937 3437501 616359 658616
Total migrate efficiency 0.0103% 0.0039% 0.0034% 0.0343% 0.0466%
The efficiency is worthless because of the nature of the test and the
number of failures. The really interesting point as far as this patch
series is concerned is the number of pages scanned. Note that reverting
Rik's patches massively increases the number of pages scanned indicating
that those patches really did make a difference to CPU usage.
However, caching what pageblocks should be skipped has a much higher
impact. With patches 1-8 applied, free page and migrate page scanning are
both reduced by 95% in comparison to the akpm kernel. If the basic
concept of Rik's patches are implemened on top then scanning then the free
scanner barely changed but migrate scanning was further reduced. That
said, tests on 3.6-rc5 indicated that the last patch had greater impact
than what was measured here so it is a bit variable.
One way or the other, this series has a large impact on the amount of
scanning compaction does when there is a storm of THP allocations.
This patch:
Compaction's migrate scanner acquires the zone->lru_lock when scanning a
range of pages looking for LRU pages to acquire. It does this even if
there are no LRU pages in the range. If multiple processes are compacting
then this can cause severe locking contention. To make matters worse
commit b2eef8c0 ("mm: compaction: minimise the time IRQs are disabled
while isolating pages for migration") releases the lru_lock every
SWAP_CLUSTER_MAX pages that are scanned.
This patch makes two changes to how the migrate scanner acquires the LRU
lock. First, it only releases the LRU lock every SWAP_CLUSTER_MAX pages
if the lock is contended. This reduces the number of times it
unnecessarily disables and re-enables IRQs. The second is that it defers
acquiring the LRU lock for as long as possible. If there are no LRU pages
or the only LRU pages are transhuge then the LRU lock will not be acquired
at all which reduces contention on zone->lru_lock.
[minchan@kernel.org: augment comment]
[akpm@linux-foundation.org: tweak comment text]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Richard Davies <richard@arachsys.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit c67fe3752a ("mm: compaction: Abort async compaction if locks
are contended or taking too long") addressed a lock contention problem
in compaction by introducing compact_checklock_irqsave() that effecively
aborting async compaction in the event of compaction.
To preserve existing behaviour it also moved a fatal_signal_pending()
check into compact_checklock_irqsave() but that is very misleading. It
"hides" the check within a locking function but has nothing to do with
locking as such. It just happens to work in a desirable fashion.
This patch moves the fatal_signal_pending() check to
isolate_migratepages_range() where it belongs. Arguably the same check
should also happen when isolating pages for freeing but it's overkill.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
isolate_migratepages_range() might isolate no pages if for example when
zone->lru_lock is contended and running asynchronous compaction. In this
case, we should abort compaction, otherwise, compact_zone will run a
useless loop and make zone->lru_lock is even contended.
An additional check is added to ensure that cc.migratepages and
cc.freepages get properly drained whan compaction is aborted.
[minchan@kernel.org: Putback pages isolated for migration if aborting]
[akpm@linux-foundation.org: compact_zone_order requires non-NULL arg contended]
[akpm@linux-foundation.org: make compact_zone_order() require non-NULL arg `contended']
[minchan@kernel.org: Putback pages isolated for migration if aborting]
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 0ee332c145 ("memblock: Kill early_node_map[]") removed
early_node_map[]. Clean up the comments to comply with that change.
Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Gavin Shan <shangw@linux.vnet.ibm.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use the existing interface function to set the NUMA node ID (NID) for the
regions, either memory or reserved region.
Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Gavin Shan <shangw@linux.vnet.ibm.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
.fault now can retry. The retry can break state machine of .fault. In
filemap_fault, if page is miss, ra->mmap_miss is increased. In the second
try, since the page is in page cache now, ra->mmap_miss is decreased. And
these are done in one fault, so we can't detect random mmap file access.
Add a new flag to indicate .fault is tried once. In the second try, skip
ra->mmap_miss decreasing. The filemap_fault state machine is ok with it.
I only tested x86, didn't test other archs, but looks the change for other
archs is obvious, but who knows :)
Signed-off-by: Shaohua Li <shaohua.li@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If race between allocation and isolation in memory-hotplug offline
happens, some pages could be in MIGRATE_MOVABLE of free_list although the
pageblock's migratetype of the page is MIGRATE_ISOLATE.
The race could be detected by get_freepage_migratetype in
__test_page_isolated_in_pageblock. If it is detected, now EBUSY gets
bubbled all the way up and the hotplug operations fails.
But better idea is instead of returning and failing memory-hotremove, move
the free page to the correct list at the time it is detected. It could
enhance memory-hotremove operation success ratio although the race is
really rare.
Suggested by Mel Gorman.
[akpm@linux-foundation.org: small cleanup]
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Like below, memory-hotplug makes race between page-isolation
and page-allocation so it can hit BUG_ON in __offline_isolated_pages.
CPU A CPU B
start_isolate_page_range
set_migratetype_isolate
spin_lock_irqsave(zone->lock)
free_hot_cold_page(Page A)
/* without zone->lock */
migratetype = get_pageblock_migratetype(Page A);
/*
* Page could be moved into MIGRATE_MOVABLE
* of per_cpu_pages
*/
list_add_tail(&page->lru, &pcp->lists[migratetype]);
set_pageblock_isolate
move_freepages_block
drain_all_pages
/* Page A could be in MIGRATE_MOVABLE of free_list. */
check_pages_isolated
__test_page_isolated_in_pageblock
/*
* We can't catch freed page which
* is free_list[MIGRATE_MOVABLE]
*/
if (PageBuddy(page A))
pfn += 1 << page_order(page A);
/* So, Page A could be allocated */
__offline_isolated_pages
/*
* BUG_ON hit or offline page
* which is used by someone
*/
BUG_ON(!PageBuddy(page A));
This patch checks page's migratetype in freelist in
__test_page_isolated_in_pageblock. So now
__test_page_isolated_in_pageblock can check the page caused by above race
and can fail of memory offlining.
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The page allocator caches the pageblock information in page->private while
it is in the PCP freelists but this is overwritten with the order of the
page when freed to the buddy allocator. This patch stores the migratetype
of the page in the page->index field so that it is available at all times
when the page remain in free_list.
This patch adds a new call site in __free_pages_ok so it might be overhead
a bit but it's for high order allocation. So I believe damage isn't hurt.
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The page allocator uses set_page_private and page_private for handling
migratetype when it frees page. Let's replace them with [set|get]
_freepage_migratetype to make it more clear.
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Add ALLOC_CMA alloc flag and pass it to [__]zone_watermark_ok()
(from Minchan Kim).
* During watermark check decrease available free pages number by
free CMA pages number if necessary (unmovable allocations cannot
use pages from CMA areas).
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add NR_FREE_CMA_PAGES counter to be later used for checking watermark in
__zone_watermark_ok(). For simplicity and to avoid #ifdef hell make this
counter always available (not only when CONFIG_CMA=y).
[akpm@linux-foundation.org: use conventional migratetype naming]
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Isolated free pages shouldn't be accounted to NR_FREE_PAGES counter. Fix
it by properly decreasing/increasing NR_FREE_PAGES counter in
set_migratetype_isolate()/unset_migratetype_isolate() and removing counter
adjustment for isolated pages from free_one_page() and split_free_page().
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
page->private gets re-used in __free_one_page() to store page order
(so trace_mm_page_pcpu_drain() may print order instead of migratetype)
thus migratetype value must be cached locally.
Fixes regression introduced in commit a7016235a6 ("mm: fix migratetype
bug which slowed swapping"). This caused incorrect data to be attached
to the mm_page_pcpu_drain trace event.
[akpm@linux-foundation.org: add comment]
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Drop clean cache pages instead of migration during alloc_contig_range() to
minimise allocation latency by reducing the amount of migration that is
necessary. It's useful for CMA because latency of migration is more
important than evicting the background process's working set. In
addition, as pages are reclaimed then fewer free pages for migration
targets are required so it avoids memory reclaiming to get free pages,
which is a contributory factor to increased latency.
I measured elapsed time of __alloc_contig_migrate_range() which migrates
10M in 40M movable zone in QEMU machine.
Before - 146ms, After - 7ms
[akpm@linux-foundation.org: fix nommu build]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Mel Gorman <mgorman@suse.de>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Rik van Riel <riel@redhat.com>
Tested-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The variable must be static especially given the variable name.
s/RCU/SRCU/ over a few comments.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
online_pages() does build_all_zonelists() and zone_pcp_update(), I think
offline_pages() should do it too.
When the zone has no memory to allocate, remove it from other nodes'
zonelists. zone_batchsize() depends on zone's present pages, if zone's
present pages are changed, zone's pcp should be updated.
Signed-off-by: Xishi Qiu <qiuxishi@huawei.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During mremap(), the destination VMA is generally placed after the
original vma in rmap traversal order: in move_vma(), we always have
new_pgoff >= vma->vm_pgoff, and as a result new_vma->vm_pgoff >=
vma->vm_pgoff unless vma_merge() merged the new vma with an adjacent one.
When the destination VMA is placed after the original in rmap traversal
order, we can avoid taking the rmap locks in move_ptes().
Essentially, this reintroduces the optimization that had been disabled in
"mm anon rmap: remove anon_vma_moveto_tail". The difference is that we
don't try to impose the rmap traversal order; instead we just rely on
things being in the desired order in the common case and fall back to
taking locks in the uncommon case. Also we skip the i_mmap_mutex in
addition to the anon_vma lock: in both cases, the vmas are traversed in
increasing vm_pgoff order with ties resolved in tree insertion order.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
anon_vma_clone() expects new_vma->vm_{start,end,pgoff} to be correctly set
so that the new vma can be indexed on the anon interval tree.
copy_vma() was failing to do that, which broke mremap().
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Tested-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a CONFIG_DEBUG_VM_RB build option for the previously existing
DEBUG_MM_RB code. Now that Andi Kleen modified it to avoid using
recursive algorithms, we can expose it a bit more.
Also extend this code to validate_mm() after stack expansion, and to check
that the vma's start and last pgoffs have not changed since the nodes were
inserted on the anon vma interval tree (as it is important that the nodes
be reindexed after each such update).
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In file and anon rmap, we use interval trees to find potentially relevant
vmas and then call vma_address() to find the virtual address the given
page might be found at in these vmas. vma_address() used to include a
check that the returned address falls within the limits of the vma, but
this check isn't necessary now that we always use interval trees in rmap:
the interval tree just doesn't return any vmas which this check would find
to be irrelevant. As a result, we can replace the use of -EFAULT error
code (which then needed to be checked in every call site) with a
VM_BUG_ON().
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a large VMA (anon or private file mapping) is first touched, which
will populate its anon_vma field, and then split into many regions through
the use of mprotect(), the original anon_vma ends up linking all of the
vmas on a linked list. This can cause rmap to become inefficient, as we
have to walk potentially thousands of irrelevent vmas before finding the
one a given anon page might fall into.
By replacing the same_anon_vma linked list with an interval tree (where
each avc's interval is determined by its vma's start and last pgoffs), we
can make rmap efficient for this use case again.
While the change is large, all of its pieces are fairly simple.
Most places that were walking the same_anon_vma list were looking for a
known pgoff, so they can just use the anon_vma_interval_tree_foreach()
interval tree iterator instead. The exception here is ksm, where the
page's index is not known. It would probably be possible to rework ksm so
that the index would be known, but for now I have decided to keep things
simple and just walk the entirety of the interval tree there.
When updating vma's that already have an anon_vma assigned, we must take
care to re-index the corresponding avc's on their interval tree. This is
done through the use of anon_vma_interval_tree_pre_update_vma() and
anon_vma_interval_tree_post_update_vma(), which remove the avc's from
their interval tree before the update and re-insert them after the update.
The anon_vma stays locked during the update, so there is no chance that
rmap would miss the vmas that are being updated.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mremap() had a clever optimization where move_ptes() did not take the
anon_vma lock to avoid a race with anon rmap users such as page migration.
Instead, the avc's were ordered in such a way that the origin vma was
always visited by rmap before the destination. This ordering and the use
of page table locks rmap usage safe. However, we want to replace the use
of linked lists in anon rmap with an interval tree, and this will make it
harder to impose such ordering as the interval tree will always be sorted
by the avc->vma->vm_pgoff value. For now, let's replace the
anon_vma_moveto_tail() ordering function with proper anon_vma locking in
move_ptes(). Once we have the anon interval tree in place, we will
re-introduce an optimization to avoid taking these locks in the most
common cases.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Update the generic interval tree code that was introduced in "mm: replace
vma prio_tree with an interval tree".
Changes:
- fixed 'endpoing' typo noticed by Andrew Morton
- replaced include/linux/interval_tree_tmpl.h, which was used as a
template (including it automatically defined the interval tree
functions) with include/linux/interval_tree_generic.h, which only
defines a preprocessor macro INTERVAL_TREE_DEFINE(), which itself
defines the interval tree functions when invoked. Now that is a very
long macro which is unfortunate, but it does make the usage sites
(lib/interval_tree.c and mm/interval_tree.c) a bit nicer than previously.
- make use of RB_DECLARE_CALLBACKS() in the INTERVAL_TREE_DEFINE() macro,
instead of duplicating that code in the interval tree template.
- replaced vma_interval_tree_add(), which was actually handling the
nonlinear and interval tree cases, with vma_interval_tree_insert_after()
which handles only the interval tree case and has an API that is more
consistent with the other interval tree handling functions.
The nonlinear case is now handled explicitly in kernel/fork.c dup_mmap().
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
kmemleak uses a tree where each node represents an allocated memory object
in order to quickly find out what object a given address is part of.
However, the objects don't overlap, so rbtrees are a better choice than
prio tree for this use. They are both faster and have lower memory
overhead.
Tested by booting a kernel with kmemleak enabled, loading the
kmemleak_test module, and looking for the expected messages.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Implement an interval tree as a replacement for the VMA prio_tree. The
algorithms are similar to lib/interval_tree.c; however that code can't be
directly reused as the interval endpoints are not explicitly stored in the
VMA. So instead, the common algorithm is moved into a template and the
details (node type, how to get interval endpoints from the node, etc) are
filled in using the C preprocessor.
Once the interval tree functions are available, using them as a
replacement to the VMA prio tree is a relatively simple, mechanical job.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds a check to hugepage_madvise(), to refuse MADV_HUGEPAGE if
VM_NOHUGEPAGE is set in mm->def_flags. On s390, the VM_NOHUGEPAGE flag
will be set in mm->def_flags for kvm processes, to prevent any future thp
mappings. In order to also prevent MADV_HUGEPAGE on such an mm,
hugepage_madvise() should check mm->def_flags.
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On s390, a valid page table entry must not be changed while it is attached
to any CPU. So instead of pmd_mknotpresent() and set_pmd_at(), an IDTE
operation would be necessary there. This patch introduces the
pmdp_invalidate() function, to allow architecture-specific
implementations.
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The thp page table pre-allocation code currently assumes that pgtable_t is
of type "struct page *". This may not be true for all architectures, so
this patch removes that assumption by replacing the functions
prepare_pmd_huge_pte() and get_pmd_huge_pte() with two new functions that
can be defined architecture-specific.
It also removes two VM_BUG_ON checks for page_count() and page_mapcount()
operating on a pgtable_t. Apart from the VM_BUG_ON removal, there will be
no functional change introduced by this patch.
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cleanup patch in preparation for transparent hugepage support on s390.
Adding new architectures to the TRANSPARENT_HUGEPAGE config option can
make the "depends" line rather ugly, like "depends on (X86 || (S390 &&
64BIT)) && MMU".
This patch adds a HAVE_ARCH_TRANSPARENT_HUGEPAGE instead. x86 already has
MMU "def_bool y", so the MMU check is superfluous there and
HAVE_ARCH_TRANSPARENT_HUGEPAGE can be selected in arch/x86/Kconfig.
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix an anon_vma locking issue in the following situation:
- vma has no anon_vma
- next has an anon_vma
- vma is being shrunk / next is being expanded, due to an mprotect call
We need to take next's anon_vma lock to avoid races with rmap users (such
as page migration) while next is being expanded.
Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since it is called in start_khugepaged
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use khugepaged_enabled to see whether thp is enabled
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
They are used to abstract the difference between NUMA enabled and NUMA
disabled to make the code more readable
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If NUMA is enabled, we can release the page in the page pre-alloc
operation, then the CONFIG_NUMA dependent code can be reduced
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There are two pre-alloc operations in these two function, the different is:
- it allows to sleep if page alloc fail in khugepaged_loop
- it exits immediately if page alloc fail in khugepaged_do_scan
Actually, in khugepaged_do_scan, we can allow the pre-alloc to sleep on
the first failure, then the operation in khugepaged_loop can be removed
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If NUMA is disabled, hpage is used as page pre-alloc, so there are two
cases for hpage:
- it is !NULL, means the page is not consumed otherwise,
- the page has been consumed
If NUMA is enabled, hpage is just used as alloc-fail indicator which is
not a real page, NULL means not fail triggered.
So, we can release the page only if !IS_ERR_OR_NULL
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add the check of kthread_should_stop() to the conditions which are used to
wakeup on khugepaged_wait, then kthread_stop is enough to let the thread
exit
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now, khugepaged creation and cancel are completely serial under the
protection of khugepaged_mutex, it is impossible that many khugepaged
entities are running
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently, hugepaged_mutex is used really complexly and hard to
understand, actually, it is just used to serialize start_khugepaged and
khugepaged for these reasons:
- khugepaged_thread is shared between them
- the thp disable path (echo never > transparent_hugepage/enabled) is
nonblocking, so we need to protect khugepaged_thread to get a stable
running state
These can be avoided by:
- use the lock to serialize the thread creation and cancel
- thp disable path can not finised until the thread exits
Then khugepaged_thread is fully controlled by start_khugepaged, khugepaged
will be happy without the lock
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The check is unnecessary since if mm_slot_cache or mm_slots_hash
initialize failed, no sysfs interface will be created
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
THP_COLLAPSE_ALLOC is double counted if NUMA is disabled since it has
already been calculated in khugepaged_alloc_hugepage
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make sure the #endif that terminates the standard #ifndef / #define /
#endif construct gets labeled, and gets positioned at the end of the file
as is normally the case.
Signed-off-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The core page allocator ensures that page flags are zeroed when freeing
pages via free_pages_check. A number of architectures (ARM, PPC, MIPS)
rely on this property to treat new pages as dirty with respect to the data
cache and perform the appropriate flushing before mapping the pages into
userspace.
This can lead to cache synchronisation problems when using hugepages,
since the allocator keeps its own pool of pages above the usual page
allocator and does not reset the page flags when freeing a page into the
pool.
This patch adds a new architecture hook, arch_clear_hugepage_flags, so
that architectures which rely on the page flags being in a particular
state for fresh allocations can adjust the flags accordingly when a page
is freed into the pool.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The deprecated /proc/<pid>/oom_adj is scheduled for removal this month.
Signed-off-by: Davidlohr Bueso <dave@gnu.org>
Acked-by: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix the return value while failing to create the kswapd kernel thread.
Also, the error message is prioritized as KERN_ERR.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
