Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
大约 1 年 前同步成功

通知 158
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 29 10月, 2007 1 次提交
  3. 17 10月, 2007 2 次提交
    • P
      mm: bdi init hooks · e0bf68dd
      由 Peter Zijlstra 提交于 
      provide BDI constructor/destructor hooks

[akpm@linux-foundation.org: compile fix]
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      e0bf68dd
    • N
      remove ZERO_PAGE · 557ed1fa
      由 Nick Piggin 提交于 
      The commit b5810039 contains the note

  A last caveat: the ZERO_PAGE is now refcounted and managed with rmap
  (and thus mapcounted and count towards shared rss).  These writes to
  the struct page could cause excessive cacheline bouncing on big
  systems.  There are a number of ways this could be addressed if it is
  an issue.

And indeed this cacheline bouncing has shown up on large SGI systems.
There was a situation where an Altix system was essentially livelocked
tearing down ZERO_PAGE pagetables when an HPC app aborted during startup.
This situation can be avoided in userspace, but it does highlight the
potential scalability problem with refcounting ZERO_PAGE, and corner
cases where it can really hurt (we don't want the system to livelock!).

There are several broad ways to fix this problem:
1. add back some special casing to avoid refcounting ZERO_PAGE
2. per-node or per-cpu ZERO_PAGES
3. remove the ZERO_PAGE completely

I will argue for 3. The others should also fix the problem, but they
result in more complex code than does 3, with little or no real benefit
that I can see.

Why? Inserting a ZERO_PAGE for anonymous read faults appears to be a
false optimisation: if an application is performance critical, it would
not be doing many read faults of new memory, or at least it could be
expected to write to that memory soon afterwards. If cache or memory use
is critical, it should not be working with a significant number of
ZERO_PAGEs anyway (a more compact representation of zeroes should be
used).

As a sanity check -- mesuring on my desktop system, there are never many
mappings to the ZERO_PAGE (eg. 2 or 3), thus memory usage here should not
increase much without it.

When running a make -j4 kernel compile on my dual core system, there are
about 1,000 mappings to the ZERO_PAGE created per second, but about 1,000
ZERO_PAGE COW faults per second (less than 1 ZERO_PAGE mapping per second
is torn down without being COWed). So removing ZERO_PAGE will save 1,000
page faults per second when running kbuild, while keeping it only saves
less than 1 page clearing operation per second. 1 page clear is cheaper
than a thousand faults, presumably, so there isn't an obvious loss.

Neither the logical argument nor these basic tests give a guarantee of no
regressions. However, this is a reasonable opportunity to try to remove
the ZERO_PAGE from the pagefault path. If it is found to cause regressions,
we can reintroduce it and just avoid refcounting it.

The /dev/zero ZERO_PAGE usage and TLB tricks also get nuked.  I don't see
much use to them except on benchmarks.  All other users of ZERO_PAGE are
converted just to use ZERO_PAGE(0) for simplicity. We can look at
replacing them all and maybe ripping out ZERO_PAGE completely when we are
more satisfied with this solution.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus "snif" Torvalds <torvalds@linux-foundation.org>
      557ed1fa
  5. 11 7月, 2007 1 次提交
  7. 10 7月, 2007 1 次提交
  9. 09 5月, 2007 2 次提交
  11. 18 4月, 2007 1 次提交
  13. 23 1月, 2007 1 次提交
    • L
      Revert "[PATCH] Fix up mmap_kmem" · 6d3154cc
      由 Linus Torvalds 提交于 
      This reverts commit 99a10a60.

As per Hugh Dickins:

  "Nadia Derbey has reported that mmap of /dev/kmem no longer works with
   the kernel virtual address as offset, and Franck has confirmed that
   his patch came from a misunderstanding of what an offset means to
   /dev/kmem - whereas his patch description seems to say that he was
   correcting the offset on a few plaforms, there was no such problem to
   correct, and his patch was in fact changing its API on all platforms."
Suggested-by: NHugh Dickins <hugh@veritas.com>
Cc: Franck Bui-Huu <fbuihuu@gmail.com>
Cc: Nadia Derbey <Nadia.Derbey@bull.net>
Cc: Andi Kleen <ak@suse.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Andrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      6d3154cc
  15. 11 12月, 2006 1 次提交
    • H
      [PATCH] read_zero_pagealigned() locking fix · 5fcf7bb7
      由 Hugh Dickins 提交于 
      Ramiro Voicu hits the BUG_ON(!pte_none(*pte)) in zeromap_pte_range: kernel
bugzilla 7645.  Right: read_zero_pagealigned uses down_read of mmap_sem,
but another thread's racing read of /dev/zero, or a normal fault, can
easily set that pte again, in between zap_page_range and zeromap_page_range
getting there.  It's been wrong ever since 2.4.3.

The simple fix is to use down_write instead, but that would serialize reads
of /dev/zero more than at present: perhaps some app would be badly
affected.  So instead let zeromap_page_range return the error instead of
BUG_ON, and read_zero_pagealigned break to the slower clear_user loop in
that case - there's no need to optimize for it.

Use -EEXIST for when a pte is found: BUG_ON in mmap_zero (the other user of
zeromap_page_range), though it really isn't interesting there.  And since
mmap_zero wants -EAGAIN for out-of-memory, the zeromaps better return that
than -ENOMEM.
Signed-off-by: NHugh Dickins <hugh@veritas.com>
Cc: Ramiro Voicu: <Ramiro.Voicu@cern.ch>
Cc: <stable@kernel.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>
      5fcf7bb7
  17. 09 12月, 2006 1 次提交
  19. 02 12月, 2006 1 次提交
  21. 13 10月, 2006 2 次提交
    • L
      Include proper header file for PFN_DOWN() · b8a3ad5b
      由 Linus Torvalds 提交于 
      The recent commit (99a10a60) to fix up
mmap_kmem() broke compiles because it used PFN_DOWN() without including
<linux/pfn.h>.
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>
      b8a3ad5b
    • F
      [PATCH] Fix up mmap_kmem · 99a10a60
      由 Franck Bui-Huu 提交于 
      vma->vm_pgoff is an pfn _offset_ relatif to the begining
of the memory start. The previous code was doing at first:

	vma->vm_pgoff << PAGE_SHIFT

which results into a wrong physical address since some
platforms have a physical mem start that can be different
from 0. After that the previous call __pa() on this
wrong physical address, however __pa() is used to convert
a _virtual_ address into a physical one.

This patch rewrites this convertion. It calculates the
pfn of PAGE_OFFSET which is the pfn of the mem start
then it adds the vma->vm_pgoff to it.

It also uses virt_to_phys() instead of __pa() since the
latter shouldn't be used by drivers.
Signed-off-by: NFranck Bui-Huu <fbuihuu@gmail.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>
      99a10a60
  23. 30 9月, 2006 1 次提交
  25. 27 9月, 2006 1 次提交
  27. 11 7月, 2006 1 次提交
    • L
      [PATCH] make valid_mmap_phys_addr_range() take a pfn · 06c67bef
      由 Lennert Buytenhek 提交于 
      Newer ARMs have a 40 bit physical address space, but mapping physical
memory above 4G needs a special page table format which we (currently?) do
not use for userspace mappings, so what happens instead is that mapping an
address >= 4G will happily discard the upper bits and wrap.

There is a valid_mmap_phys_addr_range() arch hook where we could check for
>= 4G addresses and deny the mapping, but this hook takes an unsigned long
address:

	static inline int valid_mmap_phys_addr_range(unsigned long addr, size_t size);

And drivers/char/mem.c:mmap_mem() calls it like this:

	static int mmap_mem(struct file * file, struct vm_area_struct * vma)
	{
		size_t size = vma->vm_end - vma->vm_start;

		if (!valid_mmap_phys_addr_range(vma->vm_pgoff << PAGE_SHIFT, size))

So that's not much help either.

This patch makes the hook take a pfn instead of a phys address.
Signed-off-by: NLennert Buytenhek <buytenh@wantstofly.org>
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>
      06c67bef
  29. 04 7月, 2006 1 次提交
  31. 01 7月, 2006 1 次提交
  33. 27 6月, 2006 2 次提交
  35. 26 4月, 2006 1 次提交
  37. 29 3月, 2006 1 次提交
  39. 27 3月, 2006 1 次提交
  41. 26 3月, 2006 1 次提交
  43. 12 1月, 2006 1 次提交
  45. 10 1月, 2006 1 次提交
  47. 09 1月, 2006 3 次提交
  49. 29 11月, 2005 1 次提交
    • L
      mm: re-architect the VM_UNPAGED logic · 6aab341e
      由 Linus Torvalds 提交于 
      This replaces the (in my opinion horrible) VM_UNMAPPED logic with very
explicit support for a "remapped page range" aka VM_PFNMAP.  It allows a
VM area to contain an arbitrary range of page table entries that the VM
never touches, and never considers to be normal pages.

Any user of "remap_pfn_range()" automatically gets this new
functionality, and doesn't even have to mark the pages reserved or
indeed mark them any other way.  It just works.  As a side effect, doing
mmap() on /dev/mem works for arbitrary ranges.

Sparc update from David in the next commit.
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>
      6aab341e
  51. 23 11月, 2005 1 次提交
  53. 29 10月, 2005 2 次提交
  55. 08 9月, 2005 1 次提交
  57. 14 8月, 2005 1 次提交
    • L
      Fix up mmap of /dev/kmem · 4bb82551
      由 Linus Torvalds 提交于 
      This leaves the issue of whether we should deprecate the whole thing (or
if we should check the whole mmap range, for that matter) open. Just do
the minimal fix for now.
      4bb82551
  59. 26 6月, 2005 3 次提交
  61. 22 6月, 2005 1 次提交