linux.git/arch/xtensa, branch v5.4-rc2

mm: treewide: clarify pgtable_page_{ctor,dtor}() naming

2019-09-26T17:10:44+00:00

The naming of pgtable_page_{ctor,dtor}() seems to have confused a few
people, and until recently arm64 used these erroneously/pointlessly for
other levels of page table.

To make it incredibly clear that these only apply to the PTE level, and to
align with the naming of pgtable_pmd_page_{ctor,dtor}(), let's rename them
to pgtable_pte_page_{ctor,dtor}().

These changes were generated with the following shell script:

----
git grep -lw 'pgtable_page_.tor' | while read FILE; do
    sed -i '{s/pgtable_page_ctor/pgtable_pte_page_ctor/}' $FILE;
    sed -i '{s/pgtable_page_dtor/pgtable_pte_page_dtor/}' $FILE;
done
----

... with the documentation re-flowed to remain under 80 columns, and
whitespace fixed up in macros to keep backslashes aligned.

There should be no functional change as a result of this patch.

Link: http://lkml.kernel.org/r/20190722141133.3116-1-mark.rutland@arm.com
Signed-off-by: Mark Rutland 
Reviewed-by: Mike Rapoport 
Acked-by: Geert Uytterhoeven 	[m68k]
Cc: Anshuman Khandual 
Cc: Matthew Wilcox 
Cc: Michal Hocko 
Cc: Yu Zhao 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: introduce MADV_PAGEOUT

2019-09-26T00:51:41+00:00

When a process expects no accesses to a certain memory range for a long
time, it could hint kernel that the pages can be reclaimed instantly but
data should be preserved for future use.  This could reduce workingset
eviction so it ends up increasing performance.

This patch introduces the new MADV_PAGEOUT hint to madvise(2) syscall.
MADV_PAGEOUT can be used by a process to mark a memory range as not
expected to be used for a long time so that kernel reclaims *any LRU*
pages instantly.  The hint can help kernel in deciding which pages to
evict proactively.

A note: It doesn't apply SWAP_CLUSTER_MAX LRU page isolation limit
intentionally because it's automatically bounded by PMD size.  If PMD
size(e.g., 256) makes some trouble, we could fix it later by limit it to
SWAP_CLUSTER_MAX[1].

- man-page material

MADV_PAGEOUT (since Linux x.x)

Do not expect access in the near future so pages in the specified
regions could be reclaimed instantly regardless of memory pressure.
Thus, access in the range after successful operation could cause
major page fault but never lose the up-to-date contents unlike
MADV_DONTNEED. Pages belonging to a shared mapping are only processed
if a write access is allowed for the calling process.

MADV_PAGEOUT cannot be applied to locked pages, Huge TLB pages, or
VM_PFNMAP pages.

[1] https://lore.kernel.org/lkml/20190710194719.GS29695@dhcp22.suse.cz/

[minchan@kernel.org: clear PG_active on MADV_PAGEOUT]
  Link: http://lkml.kernel.org/r/20190802200643.GA181880@google.com
[akpm@linux-foundation.org: resolve conflicts with hmm.git]
Link: http://lkml.kernel.org/r/20190726023435.214162-5-minchan@kernel.org
Signed-off-by: Minchan Kim 
Reported-by: kbuild test robot 
Acked-by: Michal Hocko 
Cc: James E.J. Bottomley 
Cc: Richard Henderson 
Cc: Ralf Baechle 
Cc: Chris Zankel 
Cc: Daniel Colascione 
Cc: Dave Hansen 
Cc: Hillf Danton 
Cc: Joel Fernandes (Google) 
Cc: Johannes Weiner 
Cc: Kirill A. Shutemov 
Cc: Oleksandr Natalenko 
Cc: Shakeel Butt 
Cc: Sonny Rao 
Cc: Suren Baghdasaryan 
Cc: Tim Murray 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: introduce MADV_COLD

2019-09-26T00:51:41+00:00

Patch series "Introduce MADV_COLD and MADV_PAGEOUT", v7.

- Background

The Android terminology used for forking a new process and starting an app
from scratch is a cold start, while resuming an existing app is a hot
start.  While we continually try to improve the performance of cold
starts, hot starts will always be significantly less power hungry as well
as faster so we are trying to make hot start more likely than cold start.

To increase hot start, Android userspace manages the order that apps
should be killed in a process called ActivityManagerService.
ActivityManagerService tracks every Android app or service that the user
could be interacting with at any time and translates that into a ranked
list for lmkd(low memory killer daemon).  They are likely to be killed by
lmkd if the system has to reclaim memory.  In that sense they are similar
to entries in any other cache.  Those apps are kept alive for
opportunistic performance improvements but those performance improvements
will vary based on the memory requirements of individual workloads.

- Problem

Naturally, cached apps were dominant consumers of memory on the system.
However, they were not significant consumers of swap even though they are
good candidate for swap.  Under investigation, swapping out only begins
once the low zone watermark is hit and kswapd wakes up, but the overall
allocation rate in the system might trip lmkd thresholds and cause a
cached process to be killed(we measured performance swapping out vs.
zapping the memory by killing a process.  Unsurprisingly, zapping is 10x
times faster even though we use zram which is much faster than real
storage) so kill from lmkd will often satisfy the high zone watermark,
resulting in very few pages actually being moved to swap.

- Approach

The approach we chose was to use a new interface to allow userspace to
proactively reclaim entire processes by leveraging platform information.
This allowed us to bypass the inaccuracy of the kernel’s LRUs for pages
that are known to be cold from userspace and to avoid races with lmkd by
reclaiming apps as soon as they entered the cached state.  Additionally,
it could provide many chances for platform to use much information to
optimize memory efficiency.

To achieve the goal, the patchset introduce two new options for madvise.
One is MADV_COLD which will deactivate activated pages and the other is
MADV_PAGEOUT which will reclaim private pages instantly.  These new
options complement MADV_DONTNEED and MADV_FREE by adding non-destructive
ways to gain some free memory space.  MADV_PAGEOUT is similar to
MADV_DONTNEED in a way that it hints the kernel that memory region is not
currently needed and should be reclaimed immediately; MADV_COLD is similar
to MADV_FREE in a way that it hints the kernel that memory region is not
currently needed and should be reclaimed when memory pressure rises.

This patch (of 5):

When a process expects no accesses to a certain memory range, it could
give a hint to kernel that the pages can be reclaimed when memory pressure
happens but data should be preserved for future use.  This could reduce
workingset eviction so it ends up increasing performance.

This patch introduces the new MADV_COLD hint to madvise(2) syscall.
MADV_COLD can be used by a process to mark a memory range as not expected
to be used in the near future.  The hint can help kernel in deciding which
pages to evict early during memory pressure.

It works for every LRU pages like MADV_[DONTNEED|FREE]. IOW, It moves

	active file page -> inactive file LRU
	active anon page -> inacdtive anon LRU

Unlike MADV_FREE, it doesn't move active anonymous pages to inactive file
LRU's head because MADV_COLD is a little bit different symantic.
MADV_FREE means it's okay to discard when the memory pressure because the
content of the page is *garbage* so freeing such pages is almost zero
overhead since we don't need to swap out and access afterward causes just
minor fault.  Thus, it would make sense to put those freeable pages in
inactive file LRU to compete other used-once pages.  It makes sense for
implmentaion point of view, too because it's not swapbacked memory any
longer until it would be re-dirtied.  Even, it could give a bonus to make
them be reclaimed on swapless system.  However, MADV_COLD doesn't mean
garbage so reclaiming them requires swap-out/in in the end so it's bigger
cost.  Since we have designed VM LRU aging based on cost-model, anonymous
cold pages would be better to position inactive anon's LRU list, not file
LRU.  Furthermore, it would help to avoid unnecessary scanning if system
doesn't have a swap device.  Let's start simpler way without adding
complexity at this moment.  However, keep in mind, too that it's a caveat
that workloads with a lot of pages cache are likely to ignore MADV_COLD on
anonymous memory because we rarely age anonymous LRU lists.

* man-page material

MADV_COLD (since Linux x.x)

Pages in the specified regions will be treated as less-recently-accessed
compared to pages in the system with similar access frequencies.  In
contrast to MADV_FREE, the contents of the region are preserved regardless
of subsequent writes to pages.

MADV_COLD cannot be applied to locked pages, Huge TLB pages, or VM_PFNMAP
pages.

[akpm@linux-foundation.org: resolve conflicts with hmm.git]
Link: http://lkml.kernel.org/r/20190726023435.214162-2-minchan@kernel.org
Signed-off-by: Minchan Kim 
Reported-by: kbuild test robot 
Acked-by: Michal Hocko 
Acked-by: Johannes Weiner 
Cc: James E.J. Bottomley 
Cc: Richard Henderson 
Cc: Ralf Baechle 
Cc: Chris Zankel 
Cc: Johannes Weiner 
Cc: Daniel Colascione 
Cc: Dave Hansen 
Cc: Hillf Danton 
Cc: Joel Fernandes (Google) 
Cc: Kirill A. Shutemov 
Cc: Oleksandr Natalenko 
Cc: Shakeel Butt 
Cc: Sonny Rao 
Cc: Suren Baghdasaryan 
Cc: Tim Murray 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: consolidate pgtable_cache_init() and pgd_cache_init()

2019-09-24T22:54:09+00:00

Both pgtable_cache_init() and pgd_cache_init() are used to initialize kmem
cache for page table allocations on several architectures that do not use
PAGE_SIZE tables for one or more levels of the page table hierarchy.

Most architectures do not implement these functions and use __weak default
NOP implementation of pgd_cache_init().  Since there is no such default
for pgtable_cache_init(), its empty stub is duplicated among most
architectures.

Rename the definitions of pgd_cache_init() to pgtable_cache_init() and
drop empty stubs of pgtable_cache_init().

Link: http://lkml.kernel.org/r/1566457046-22637-1-git-send-email-rppt@linux.ibm.com
Signed-off-by: Mike Rapoport 
Acked-by: Will Deacon 		[arm64]
Acked-by: Thomas Gleixner 	[x86]
Cc: Catalin Marinas 
Cc: Ingo Molnar 
Cc: Borislav Petkov 
Cc: Matthew Wilcox 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: remove quicklist page table caches

2019-09-24T22:54:09+00:00

Patch series "mm: remove quicklist page table caches".

A while ago Nicholas proposed to remove quicklist page table caches [1].

I've rebased his patch on the curren upstream and switched ia64 and sh to
use generic versions of PTE allocation.

[1] https://lore.kernel.org/linux-mm/20190711030339.20892-1-npiggin@gmail.com

This patch (of 3):

Remove page table allocator "quicklists".  These have been around for a
long time, but have not got much traction in the last decade and are only
used on ia64 and sh architectures.

The numbers in the initial commit look interesting but probably don't
apply anymore.  If anybody wants to resurrect this it's in the git
history, but it's unhelpful to have this code and divergent allocator
behaviour for minor archs.

Also it might be better to instead make more general improvements to page
allocator if this is still so slow.

Link: http://lkml.kernel.org/r/1565250728-21721-2-git-send-email-rppt@linux.ibm.com
Signed-off-by: Nicholas Piggin 
Signed-off-by: Mike Rapoport 
Cc: Tony Luck 
Cc: Yoshinori Sato 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

Merge tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping

2019-09-19T20:27:23+00:00

Pull dma-mapping updates from Christoph Hellwig:

 - add dma-mapping and block layer helpers to take care of IOMMU merging
   for mmc plus subsequent fixups (Yoshihiro Shimoda)

 - rework handling of the pgprot bits for remapping (me)

 - take care of the dma direct infrastructure for swiotlb-xen (me)

 - improve the dma noncoherent remapping infrastructure (me)

 - better defaults for ->mmap, ->get_sgtable and ->get_required_mask
   (me)

 - cleanup mmaping of coherent DMA allocations (me)

 - various misc cleanups (Andy Shevchenko, me)

* tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping: (41 commits)
  mmc: renesas_sdhi_internal_dmac: Add MMC_CAP2_MERGE_CAPABLE
  mmc: queue: Fix bigger segments usage
  arm64: use asm-generic/dma-mapping.h
  swiotlb-xen: merge xen_unmap_single into xen_swiotlb_unmap_page
  swiotlb-xen: simplify cache maintainance
  swiotlb-xen: use the same foreign page check everywhere
  swiotlb-xen: remove xen_swiotlb_dma_mmap and xen_swiotlb_dma_get_sgtable
  xen: remove the exports for xen_{create,destroy}_contiguous_region
  xen/arm: remove xen_dma_ops
  xen/arm: simplify dma_cache_maint
  xen/arm: use dev_is_dma_coherent
  xen/arm: consolidate page-coherent.h
  xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance
  arm: remove wrappers for the generic dma remap helpers
  dma-mapping: introduce a dma_common_find_pages helper
  dma-mapping: always use VM_DMA_COHERENT for generic DMA remap
  vmalloc: lift the arm flag for coherent mappings to common code
  dma-mapping: provide a better default ->get_required_mask
  dma-mapping: remove the dma_declare_coherent_memory export
  remoteproc: don't allow modular build
  ...

dma-mapping: always use VM_DMA_COHERENT for generic DMA remap

2019-09-04T09:13:20+00:00

Currently the generic dma remap allocator gets a vm_flags passed by
the caller that is a little confusing.  We just introduced a generic
vmalloc-level flag to identify the dma coherent allocations, so use
that everywhere and remove the now pointless argument.

Signed-off-by: Christoph Hellwig

dma-mapping: remove CONFIG_ARCH_NO_COHERENT_DMA_MMAP

2019-09-04T09:13:18+00:00

CONFIG_ARCH_NO_COHERENT_DMA_MMAP is now functionally identical to
!CONFIG_MMU, so remove the separate symbol.  The only difference is that
arm did not set it for !CONFIG_MMU, but arm uses a separate dma mapping
implementation including its own mmap method, which is handled by moving
the CONFIG_MMU check in dma_can_mmap so that is only applies to the
dma-direct case, just as the other ifdefs for it.

Signed-off-by: Christoph Hellwig 
Acked-by: Geert Uytterhoeven 	# m68k

xtensa: virt: move PCI root complex to KIO range

2019-09-02T07:09:30+00:00

Move PCI configuration space, MMIO and memory to the KIO range to free
vmalloc area and use static TLB to access them. Move MMIO to the
beginning of KIO and define PCI_IOBASE as XCHAL_KIO_BYPASS_VADDR to
match it. Reduce number of supported PCI buses to 0x3f so that ECAM
window fits into first 64MB of the KIO. Reduce size of the PCI memory
window to 128MB so that it fits into KIO.

Signed-off-by: Max Filippov

xtensa: add support for call0 ABI in userspace

2019-09-01T20:11:57+00:00

Provide a Kconfig choice to select whether only the default ABI, only
call0 ABI or both are supported. The default for XEA2 is windowed, but
it may change for XEA3. Call0 only runs userspace with PS.WOE disabled.
Supporting both windowed and call0 ABIs is tricky, as there's no
indication in the ELF binaries which ABI they use. So it is done by
probing: each process is started with PS.WOE disabled, but the handler
of an illegal instruction exception taken with PS.WOE retries faulting
instruction after enabling PS.WOE. It must happen before any signal is
delivered to the process, otherwise it may be delivered incorrectly.

Signed-off-by: Max Filippov