Skip to content

R
raspberrypi-kernel

openeuler / raspberrypi-kernel

通知 13
Star 1
Fork 0
R
raspberrypi-kernel
切换分支/标签
  1. 10 6月, 2009 14 次提交
  3. 09 6月, 2009 1 次提交
  5. 06 6月, 2009 1 次提交
  7. 05 6月, 2009 1 次提交
  9. 04 6月, 2009 1 次提交
  11. 30 5月, 2009 1 次提交
  13. 29 5月, 2009 1 次提交
    • M
      x86: ignore VM_LOCKED when determining if hugetlb-backed page tables can be shared or not · 32b154c0
      由 Mel Gorman 提交于 
      Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13302

On x86 and x86-64, it is possible that page tables are shared beween
shared mappings backed by hugetlbfs.  As part of this,
page_table_shareable() checks a pair of vma->vm_flags and they must match
if they are to be shared.  All VMA flags are taken into account, including
VM_LOCKED.

The problem is that VM_LOCKED is cleared on fork().  When a process with a
shared memory segment forks() to exec() a helper, there will be shared
VMAs with different flags.  The impact is that the shared segment is
sometimes considered shareable and other times not, depending on what
process is checking.

What happens is that the segment page tables are being shared but the
count is inaccurate depending on the ordering of events.  As the page
tables are freed with put_page(), bad pmd's are found when some of the
children exit.  The hugepage counters also get corrupted and the Total and
Free count will no longer match even when all the hugepage-backed regions
are freed.  This requires a reboot of the machine to "fix".

This patch addresses the problem by comparing all flags except VM_LOCKED
when deciding if pagetables should be shared or not for hugetlbfs-backed
mapping.
Signed-off-by: NMel Gorman <mel@csn.ul.ie>
Acked-by: NHugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: <starlight@binnacle.cx>
Cc: Eric B Munson <ebmunson@us.ibm.com>
Cc: Adam Litke <agl@us.ibm.com>
Cc: Andy Whitcroft <apw@canonical.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      32b154c0
  15. 27 5月, 2009 5 次提交
  17. 26 5月, 2009 3 次提交
    • T
      x86, relocs: ignore R_386_NONE in kernel relocation entries · 46176b4f
      由 Tejun Heo 提交于 
      For relocatable 32bit kernels, boot/compressed/relocs.c processes
relocation entries in the kernel image and appends it to the kernel
image such that boot/compressed/head_32.S can relocate the kernel.
The kernel image is one statically linked object and only uses two
relocation types - R_386_PC32 and R_386_32, of the two only the latter
needs massaging during kernel relocation and thus handled by relocs.
R_386_PC32 is ignored and all other relocation types are considered
error.

When the target of a relocation resides in a discarded section,
binutils doesn't throw away the relocation record but nullifies it by
changing it to R_386_NONE, which unfortunately makes relocs fail.

The problem was triggered by yet out-of-tree x86 stack unwind patches
but given the binutils behavior, ignoring R_386_NONE is the right
thing to do.

The problem has been tracked down to binutils behavior by Jan Beulich.

[ Impact: fix build with certain binutils by ignoring R_386_NONE ]
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Jan Beulich <JBeulich@novell.com>
Cc: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <4A1B8150.40702@kernel.org>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
      46176b4f
    • A
      KVM: Fix PDPTR reloading on CR4 writes · a2edf57f
      由 Avi Kivity 提交于 
      The processor is documented to reload the PDPTRs while in PAE mode if any
of the CR4 bits PSE, PGE, or PAE change.  Linux relies on this
behaviour when zapping the low mappings of PAE kernels during boot.

The code already handled changes to CR4.PAE; augment it to also notice changes
to PSE and PGE.

This triggered while booting an F11 PAE kernel; the futex initialization code
runs before any CR3 reloads and writes to a NULL pointer; the futex subsystem
ended up uninitialized, killing PI futexes and pulseaudio which uses them.

Cc: stable@kernel.org
Signed-off-by: NAvi Kivity <avi@redhat.com>
      a2edf57f
    • A
      KVM: Make paravirt tlb flush also reload the PAE PDPTRs · a8cd0244
      由 Avi Kivity 提交于 
      The paravirt tlb flush may be used not only to flush TLBs, but also
to reload the four page-directory-pointer-table entries, as it is used
as a replacement for reloading CR3.  Change the code to do the entire
CR3 reloading dance instead of simply flushing the TLB.

Cc: stable@kernel.org
Signed-off-by: NAvi Kivity <avi@redhat.com>
      a8cd0244
  19. 25 5月, 2009 1 次提交
  21. 23 5月, 2009 4 次提交
  23. 22 5月, 2009 1 次提交
  25. 16 5月, 2009 1 次提交
    • J
      x86: Fix performance regression caused by paravirt_ops on native kernels · b4ecc126
      由 Jeremy Fitzhardinge 提交于 
      Xiaohui Xin and some other folks at Intel have been looking into what's
behind the performance hit of paravirt_ops when running native.

It appears that the hit is entirely due to the paravirtualized
spinlocks introduced by:

 | commit 8efcbab6
 | Date:   Mon Jul 7 12:07:51 2008 -0700
 |
 |     paravirt: introduce a "lock-byte" spinlock implementation

The extra call/return in the spinlock path is somehow
causing an increase in the cycles/instruction of somewhere around 2-7%
(seems to vary quite a lot from test to test).  The working theory is
that the CPU's pipeline is getting upset about the
call->call->locked-op->return->return, and seems to be failing to
speculate (though I haven't seen anything definitive about the precise
reasons).  This doesn't entirely make sense, because the performance
hit is also visible on unlock and other operations which don't involve
locked instructions.  But spinlock operations clearly swamp all the
other pvops operations, even though I can't imagine that they're
nearly as common (there's only a .05% increase in instructions
executed).

If I disable just the pv-spinlock calls, my tests show that pvops is
identical to non-pvops performance on native (my measurements show that
it is actually about .1% faster, but Xiaohui shows a .05% slowdown).

Summary of results, averaging 10 runs of the "mmperf" test, using a
no-pvops build as baseline:

		nopv		Pv-nospin	Pv-spin
CPU cycles	100.00%		99.89%		102.18%
instructions	100.00%		100.10%		100.15%
CPI		100.00%		99.79%		102.03%
cache ref	100.00%		100.84%		100.28%
cache miss	100.00%		90.47%		88.56%
cache miss rate	100.00%		89.72%		88.31%
branches	100.00%		99.93%		100.04%
branch miss	100.00%		103.66%		107.72%
branch miss rt	100.00%		103.73%		107.67%
wallclock	100.00%		99.90%		102.20%

The clear effect here is that the 2% increase in CPI is
directly reflected in the final wallclock time.

(The other interesting effect is that the more ops are
out of line calls via pvops, the lower the cache access
and miss rates.  Not too surprising, but it suggests that
the non-pvops kernel is over-inlined.  On the flipside,
the branch misses go up correspondingly...)

So, what's the fix?

Paravirt patching turns all the pvops calls into direct calls, so
_spin_lock etc do end up having direct calls.  For example, the compiler
generated code for paravirtualized _spin_lock is:

<_spin_lock+0>:		mov    %gs:0xb4c8,%rax
<_spin_lock+9>:		incl   0xffffffffffffe044(%rax)
<_spin_lock+15>:	callq  *0xffffffff805a5b30
<_spin_lock+22>:	retq

The indirect call will get patched to:
<_spin_lock+0>:		mov    %gs:0xb4c8,%rax
<_spin_lock+9>:		incl   0xffffffffffffe044(%rax)
<_spin_lock+15>:	callq <__ticket_spin_lock>
<_spin_lock+20>:	nop; nop		/* or whatever 2-byte nop */
<_spin_lock+22>:	retq

One possibility is to inline _spin_lock, etc, when building an
optimised kernel (ie, when there's no spinlock/preempt
instrumentation/debugging enabled).  That will remove the outer
call/return pair, returning the instruction stream to a single
call/return, which will presumably execute the same as the non-pvops
case.  The downsides arel 1) it will replicate the
preempt_disable/enable code at eack lock/unlock callsite; this code is
fairly small, but not nothing; and 2) the spinlock definitions are
already a very heavily tangled mass of #ifdefs and other preprocessor
magic, and making any changes will be non-trivial.

The other obvious answer is to disable pv-spinlocks.  Making them a
separate config option is fairly easy, and it would be trivial to
enable them only when Xen is enabled (as the only non-default user).
But it doesn't really address the common case of a distro build which
is going to have Xen support enabled, and leaves the open question of
whether the native performance cost of pv-spinlocks is worth the
performance improvement on a loaded Xen system (10% saving of overall
system CPU when guests block rather than spin).  Still it is a
reasonable short-term workaround.

[ Impact: fix pvops performance regression when running native ]
Analysed-by: N"Xin Xiaohui" <xiaohui.xin@intel.com>
Analysed-by: N"Li Xin" <xin.li@intel.com>
Analysed-by: N"Nakajima Jun" <jun.nakajima@intel.com>
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: NH. Peter Anvin <hpa@zytor.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Xen-devel <xen-devel@lists.xensource.com>
LKML-Reference: <4A0B62F7.5030802@goop.org>
[ fixed the help text ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>
      b4ecc126
  27. 15 5月, 2009 1 次提交
  29. 14 5月, 2009 1 次提交
    • S
      x86/function-graph: fix constraint for recording old return value · aa512a27
      由 Steven Rostedt 提交于 
      After upgrading from gcc 4.2.2 to 4.4.0, the function graph tracer broke.
Investigating, I found that in the asm that replaces the return value,
gcc was using the same register for the old value as it was for the
new value.

	mov	(addr), old
	mov	new, (addr)

But if old and new are the same register, we clobber new with old!
I first thought this was a bug in gcc 4.4.0 and reported it:

  http://gcc.gnu.org/bugzilla/show_bug.cgi?id=40132

Andrew Pinski responded (quickly), saying that it was correct gcc behavior
and the code needed to denote old as an "early clobber".

Instead of "=r"(old), we need "=&r"(old).

[Impact: keep function graph tracer from breaking with gcc 4.4.0 ]
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
      aa512a27
  31. 13 5月, 2009 1 次提交
  33. 12 5月, 2009 1 次提交
  35. 11 5月, 2009 1 次提交