Commit Graph

8105 Commits

Author SHA1 Message Date
Venkatesh Pallipadi 335ef896d4 x86, pat: Add rbtree to do quick lookup in memtype tracking
PAT memtype tracking uses a linear link list to keep track of IO
(non-RAM) regions and their memtypes. The code used a last_accessed
pointer as a cache to speedup the lookup. As per discussions with
H. Peter Anvin a while back, having a rbtree here will avoid bad
performances in pathological cases where we may end up with huge
linked list. This may not add any noticable performance speedup
in normal case as the number of entires in PAT memtype list tend
to be ~20-30 range. The patch removes the "cached_entry" logic
as with rbtree we have more generic way of speeding up the lookup.

With this patch, we use rbtree to do the quick lookup. We still use
linked list as the memtype range tracked can be of different sizes
and can overlap in different ways. We also keep track of usage counts
with linked list.

Example:
Multiple ioremaps with different sizes
uncached-minus @ 0xfffff00000-0xfffff04000
uncached-minus @ 0xfffff02000-0xfffff03000

And one userlevel mmap and the thread forks a new process
uncached-minus @ 0xbf453000-0xbf454000
uncached-minus @ 0xbf453000-0xbf454000

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-08-26 15:41:19 -07:00
Venkatesh Pallipadi 9e36fda0b3 x86, pat: Add PAT reserve free to io_mapping* APIs
io_mapping_* interfaces were added, mainly for graphics drivers.
Make this interface go through the PAT reserve/free, instead of
hardcoding WC mapping. This makes sure that there are no
aliases due to unconditional WC setting.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-08-26 15:41:16 -07:00
Venkatesh Pallipadi 9fd126bc74 x86, pat: New i/f for driver to request memtype for IO regions
Add new routines to request memtype for IO regions. This will currently
be a backend for io_mapping_* routines. But, it can also be made available
to drivers directly in future, in case it is needed.

reserve interface reserves the memory, makes sure we have a compatible
memory type available and keeps the identity map in sync when needed.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-08-26 15:41:10 -07:00
Venkatesh Pallipadi 279e669b3f x86, pat: ioremap to follow same PAT restrictions as other PAT users
ioremap has this hard-coded check for new type and requested type. That
check differs from other PAT users like /dev/mem mmap, remap_pfn_range
in only one condition where requested type is UC_MINUS and new type
is WC. Under that condition, ioremap fails. But other PAT interfaces succeed
with a WC mapping.

Change to make ioremap be in sync with other PAT APIs and use the same
macro as others. Also changes the error print to KERN_ERR instead of
pr_debug.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-08-26 15:41:07 -07:00
Venkatesh Pallipadi 5fc517466d x86, pat: Keep identity maps consistent with mmaps even when pat_disabled
Make reserve_memtype internally take care of pat disabled case and fallback
to default return values.

Remove the specific pat_disabled checks in track_* routines.

Change kernel_map_sync_memtype to sync identity map even when
pat_disabled.

This change ensures that, even for pat_disabled case, we take care of
keeping identity map in sync. Before this patch, in pat disabled case,
ioremap() keeps the identity maps in sync and other APIs like pci and
/dev/mem mmap don't, which is not a very consistent behavior.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-08-26 15:40:58 -07:00
H. Peter Anvin 5400743db5 x86, mtrr: make mtrr_aps_delayed_init static bool
mtr_aps_delayed_init was declared u32 and made global, but it only
ever takes boolean values and is only ever used in
arch/x86/kernel/cpu/mtrr/main.c.  Declare it "static bool" and remove
external references.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
2009-08-21 17:00:02 -07:00
Suresh Siddha d0af9eed5a x86, pat/mtrr: Rendezvous all the cpus for MTRR/PAT init
SDM Vol 3a section titled "MTRR considerations in MP systems" specifies
the need for synchronizing the logical cpu's while initializing/updating
MTRR.

Currently Linux kernel does the synchronization of all cpu's only when
a single MTRR register is programmed/updated. During an AP online
(during boot/cpu-online/resume)  where we initialize all the MTRR/PAT registers,
we don't follow this synchronization algorithm.

This can lead to scenarios where during a dynamic cpu online, that logical cpu
is initializing MTRR/PAT with cache disabled (cr0.cd=1) etc while other logical
HT sibling continue to run (also with cache disabled because of cr0.cd=1
on its sibling).

Starting from Westmere, VMX transitions with cr0.cd=1 don't work properly
(because of some VMX performance optimizations) and the above scenario
(with one logical cpu doing VMX activity and another logical cpu coming online)
can result in system crash.

Fix the MTRR initialization by doing rendezvous of all the cpus. During
boot and resume, we delay the MTRR/PAT init for APs till all the
logical cpu's come online and the rendezvous process at the end of AP's bringup,
will initialize the MTRR/PAT for all AP's.

For dynamic single cpu online, we synchronize all the logical cpus and
do the MTRR/PAT init on the AP that is coming online.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-08-21 16:25:55 -07:00
Marcin Slusarz 9f51e24ee8 x86: Use printk_once()
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
LKML-Reference: <1249847649-11631-6-git-send-email-marcin.slusarz@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-09 22:28:34 +02:00
Alan Cox 8bdbd962ec x86/cpu: Clean up various files a bit
No code changes except printk levels (although some of the K6
mtrr code might be clearer if there were a few as would
splitting out some of the intel cache code).

Signed-off-by: Alan Cox <alan@linux.intel.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 11:24:09 +02:00
Huang Weiyi e90476d3ba x86: Remove duplicated #include
Remove duplicated #include in:

  arch/x86/kernel/dumpstack.c

Signed-off-by: Huang Weiyi <weiyi.huang@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 10:17:08 +02:00
Cyrill Gorcunov a1b4f1a5b7 x86, ipi: Clean up safe_smp_processor_id() by using the cpu_has_apic() macro helper
We already use a lot of cpu_has_ helpers.
Lets do here the same for consistency.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090705160154.GB4791@lenovo>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-10 15:58:34 +02:00
Cyrill Gorcunov 9ff8094299 x86: Clean up idt_descr and idt_tableby using NR_VECTORS instead of hardcoded number
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090708180353.GH5301@lenovo>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-10 13:57:13 +02:00
Ingo Molnar e3d0e69268 x86: Further clean up of mtrr/generic.c
Yinghai noticed that i defined BIOS_BUG_MSG but added no
usage for it. The usage is to clean up this turd in generic.c:

			printk(KERN_WARNING "WARNING: BIOS bug: VAR MTRR %d "
				"contains strange UC entry under 1M, check "
				"with your system vendor!\n", i);

Breaking printk lines in the middle looks ugly, is hard to read
and breaks 'git grep'. Use the BIOS_BUG_MSG instead.

Also complete the moving of structure definitions and variables
to the top of the file.

Reported-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 09:46:10 +02:00
Jaswinder Singh Rajput dbd51be026 x86: Clean up mtrr/main.c
Fix following trivial style problems:

  ERROR: trailing whitespace X 25
  WARNING: Use #include <linux/uaccess.h> instead of <asm/uaccess.h>
  WARNING: Use #include <linux/kvm_para.h> instead of <asm/kvm_para.h>
  ERROR: do not initialise externals to 0 or NULL X 2
  ERROR: "foo * bar" should be "foo *bar" X 5
  ERROR: do not use assignment in if condition X 2
  WARNING: line over 80 characters X 8
  ERROR: return is not a function, parentheses are not required
  WARNING: braces {} are not necessary for any arm of this statement
  ERROR: space required before the open parenthesis '(' X 2
  ERROR: open brace '{' following function declarations go on the next line
  ERROR: space required after that ',' (ctx:VxV) X 8
  ERROR: space required before the open parenthesis '(' X 3
  ERROR: else should follow close brace '}'
  WARNING: space prohibited between function name and open parenthesis '('
  WARNING: EXPORT_SYMBOL(foo); should immediately follow its function/variable X 2

Also use pr_debug and pr_warning where possible.

total: 50 errors, 14 warnings

arch/x86/kernel/cpu/mtrr/main.o:

   text	   data	    bss	    dec	    hex	filename
   3668	    116	   4156	   7940	   1f04	main.o.before
   3668	    116	   4156	   7940	   1f04	main.o.after

md5:
   e01af2fd28deef77c8d01e71acfbd365  main.o.before.asm
   e01af2fd28deef77c8d01e71acfbd365  main.o.after.asm

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
Cc: Avi Kivity <avi@redhat.com> # Avi, please have a look at the kvm_para.h bit
[ More cleanups ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:19:55 +02:00
Jaswinder Singh Rajput 09b22c85d5 x86: Clean up mtrr/state.c
Fix:

  WARNING: Use #include <linux/io.h> instead of <asm/io.h>
  WARNING: line over 80 characters X 4

arch/x86/kernel/cpu/mtrr/state.o:

   text	   data	    bss	    dec	    hex	filename
    864	      0	      0	    864	    360	state.o.before
    864	      0	      0	    864	    360	state.o.after

md5:
   c5c4364b9aeac74d70111e1e49667a2c  state.o.before.asm
   c5c4364b9aeac74d70111e1e49667a2c  state.o.after.asm

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ More cleanups ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:19:53 +02:00
Jaswinder Singh Rajput 3ec8dbcb09 x86: Clean up mtrr/mtrr.h
Fix:

  ERROR: do not use C99 // comments
  ERROR: "foo * bar" should be "foo *bar" X 2

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ More tidyups ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:19:52 +02:00
Jaswinder Singh Rajput 26dc67eda1 x86: Clean up mtrr/if.c
Fix:

  WARNING: Use #include <linux/uaccess.h> instead of <asm/uaccess.h>
  ERROR: trailing whitespace X 7
  ERROR: trailing statements should be on next line X 3
  WARNING: line over 80 characters X 5
  ERROR: space required before the open parenthesis '('

arch/x86/kernel/cpu/mtrr/if.o:

   text	   data	    bss	    dec	    hex	filename
   2239	      4	      0	   2243	    8c3	if.o.before
   2239	      4	      0	   2243	    8c3	if.o.after

md5:
   78d1f2aa4843ec6509c18e2dee54bc7f  if.o.before.asm
   78d1f2aa4843ec6509c18e2dee54bc7f  if.o.after.asm

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ More cleanups to make the code more consistent. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:19:48 +02:00
Jaswinder Singh Rajput a1a499a399 x86: Clean up mtrr/generic.c
Fix following trivial style problems:

  ERROR: trailing whitespace X 4
  WARNING: Use #include <linux/io.h> instead of <asm/io.h>
  WARNING: braces {} are not necessary for single statement blocks X 3
  ERROR: "foo * bar" should be "foo *bar"
  WARNING: line over 80 characters X 6
  ERROR: "foo * bar" should be "foo *bar"
  ERROR: spaces required around that '=' (ctx:VxO)
  ERROR: space required before that '-' (ctx:OxV)
  WARNING: suspect code indent for conditional statements (8, 12)
  ERROR: spaces required around that '=' (ctx:VxV)
  ERROR: do not initialise statics to 0 or NULL
  ERROR: space prohibited after that open parenthesis '(' X 2
  ERROR: space prohibited before that close parenthesis ')' X 2
  ERROR: trailing statements should be on next line
  ERROR: return is not a function, parentheses are not required

Also use pr_debug and pr_warning where possible.

arch/x86/kernel/cpu/mtrr/generic.o:

   text	   data	    bss	    dec	    hex	filename
   5652	     77	   4224	   9953	   26e1	generic.o.before
   5652	     77	   4220	   9949	   26dd	generic.o.after

The md5 changed:
   b34d6c045f06daa4ed092b90cc760e8f  generic.o.before.asm
   a490c6251cfd8442fbffecc0e09a573d  generic.o.after.asm

Because mtrr_state moved from data to bss, changing its
offsets - and also because __LINE__ numbers changed.

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ Further cleanups to make the code more consistent ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:10:47 +02:00
Jaswinder Singh Rajput 2311037708 x86: Clean up mtrr/cyrix.c
Fix trivial style problems:

  WARNING: Use #include <linux/io.h> instead of <asm/io.h>
  WARNING: line over 80 characters
  ERROR: do not initialise statics to 0 or NULL
  ERROR: space prohibited after that open parenthesis '(' X 2
  ERROR: space prohibited before that close parenthesis ')' X 2
  ERROR: trailing whitespace X 2
  ERROR: trailing statements should be on next line
  ERROR: do not use C99 // comments X 2

arch/x86/kernel/cpu/mtrr/cyrix.o:

   text	   data	    bss	    dec	    hex	filename
   1637	     32	      8	   1677	    68d	cyrix.o.before
   1637	     32	      8	   1677	    68d	cyrix.o.after

md5:
   6f52abd06905be3f4cabb5239f9b0ff0  cyrix.o.before.asm
   6f52abd06905be3f4cabb5239f9b0ff0  cyrix.o.after.asm

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ Made the code more consistent ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:10:47 +02:00
Jaswinder Singh Rajput 63f9600fad x86: Clean up mtrr/cleanup.c
Fix trivial style problems:

  WARNING: Use #include <linux/uaccess.h> instead of <asm/uaccess.h>
  WARNING: Use #include <linux/kvm_para.h> instead of <asm/kvm_para.h>

Also, nr_mtrr_spare_reg should be unsigned long.

arch/x86/kernel/cpu/mtrr/cleanup.o:

   text	   data	    bss	    dec	    hex	filename
   6241	   8992	   2056	  17289	   4389	cleanup.o.before
   6241	   8992	   2056	  17289	   4389	cleanup.o.after

The md5 has changed:
   1a7a27513aef1825236daf29110fe657  cleanup.o.before.asm
   bcea358efa2532b6020e338e158447af  cleanup.o.after.asm

Because a WARN_ON()'s __LINE__ value changed by 3 lines.

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ Did lots of other cleanups to make the code look more consistent. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:10:46 +02:00
Jaswinder Singh Rajput 6c4caa1ab7 x86: Clean up mtrr/centaur.c
Remove dead code and fix trivial style problems:

  ERROR: trailing whitespace X 2
  WARNING: line over 80 characters X 3
  ROR: trailing whitespace
  ERROR: do not use C99 // comments X 2

arch/x86/kernel/cpu/mtrr/centaur.o:

   text	   data	    bss	    dec	    hex	filename
    605	     32	     68	    705	    2c1	centaur.o.before
    605	     32	     68	    705	    2c1	centaur.o.after

md5:
   a4865ea98ce3c163bb1d376a3949b3e3  centaur.o.before.asm
   a4865ea98ce3c163bb1d376a3949b3e3  centaur.o.after.asm

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ Standardized comments, DocBook, curly braces, newlines. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:10:45 +02:00
Jaswinder Singh Rajput 42204455f1 x86: Clean up mtrr/amd.c:
Fix trivial style problems :

  ERROR: trailing whitespace
  WARNING: line over 80 characters
  ERROR: do not use C99 // comments

arch/x86/kernel/cpu/mtrr/amd.o:

   text	   data	    bss	    dec	    hex	filename
    501	     32	      0	    533	    215	amd.o.before
    501	     32	      0	    533	    215	amd.o.after

md5:
   62f795eb840ee2d17b03df89e789e76c  amd.o.before.asm
   62f795eb840ee2d17b03df89e789e76c  amd.o.after.asm

Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
[ Also restructured comments to be standard, removed stray return,
  converted function description to DocBook style, etc. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:10:45 +02:00
Ingo Molnar d7e57676e3 Merge branch 'linus' into x86/cleanups
Merge reason: We were on an older pre-rc1 base, move to almost-rc2.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-04 11:00:42 +02:00
Linus Torvalds 405d7ca515 Merge git://git.infradead.org/iommu-2.6
* git://git.infradead.org/iommu-2.6: (38 commits)
  intel-iommu: Don't keep freeing page zero in dma_pte_free_pagetable()
  intel-iommu: Introduce first_pte_in_page() to simplify PTE-setting loops
  intel-iommu: Use cmpxchg64_local() for setting PTEs
  intel-iommu: Warn about unmatched unmap requests
  intel-iommu: Kill superfluous mapping_lock
  intel-iommu: Ensure that PTE writes are 64-bit atomic, even on i386
  intel-iommu: Make iommu=pt work on i386 too
  intel-iommu: Performance improvement for dma_pte_free_pagetable()
  intel-iommu: Don't free too much in dma_pte_free_pagetable()
  intel-iommu: dump mappings but don't die on pte already set
  intel-iommu: Combine domain_pfn_mapping() and domain_sg_mapping()
  intel-iommu: Introduce domain_sg_mapping() to speed up intel_map_sg()
  intel-iommu: Simplify __intel_alloc_iova()
  intel-iommu: Performance improvement for domain_pfn_mapping()
  intel-iommu: Performance improvement for dma_pte_clear_range()
  intel-iommu: Clean up iommu_domain_identity_map()
  intel-iommu: Remove last use of PHYSICAL_PAGE_MASK, for reserving PCI BARs
  intel-iommu: Make iommu_flush_iotlb_psi() take pfn as argument
  intel-iommu: Change aligned_size() to aligned_nrpages()
  intel-iommu: Clean up intel_map_sg(), remove domain_page_mapping()
  ...
2009-07-02 16:51:09 -07:00
Yinghai Lu 7c5371c403 x86: add boundary check for 32bit res before expand e820 resource to alignment
fix hang with HIGHMEM_64G and 32bit resource.  According to hpa and
Linus, use (resource_size_t)-1 to fend off big ranges.

Analyzed by hpa

Reported-and-tested-by: Mikael Pettersson <mikpe@it.uu.se>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-07-02 12:11:12 -07:00
Linus Torvalds 43644679a1 x86: fix power-of-2 round_up/round_down macros
These macros had two bugs:
 - the type of the mask was not correctly expanded to the full size of
   the argument being expanded, resulting in possible loss of high bits
   when mixing types.
 - the alignment argument was evaluated twice, despite the macro looking
   like a fancy function (but it really does need to be a macro, since
   it works on arbitrary integer types)

Noticed by Peter Anvin, and with a fix that is a modification of his
suggestion (bug noticed by Yinghai Lu).

Cc: Peter Anvin <hpa@zytor.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-07-02 12:05:10 -07:00
David Woodhouse 788d84bba4 Fix pci_unmap_addr() et al on i386.
We can run a 32-bit kernel on boxes with an IOMMU, so we need
pci_unmap_addr() etc. to work -- without it, drivers will leak mappings.

To be honest, this whole thing looks like it's more pain than it's
worth; I'm half inclined to remove the no-op #else case altogether.

But this is the minimal fix, which just does the right thing if
CONFIG_DMAR is set.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Cc: stable@kernel.org  [ for 2.6.30 ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-07-01 11:19:29 -07:00
David Woodhouse 3238c0c4d6 intel-iommu: Make iommu=pt work on i386 too
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2009-07-01 18:56:16 +01:00
Linus Torvalds 55bcab4695 Merge branch 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (47 commits)
  perf report: Add --symbols parameter
  perf report: Add --comms parameter
  perf report: Add --dsos parameter
  perf_counter tools: Adjust only prelinked symbol's addresses
  perf_counter: Provide a way to enable counters on exec
  perf_counter tools: Reduce perf stat measurement overhead/skew
  perf stat: Use percentages for scaling output
  perf_counter, x86: Update x86_pmu after WARN()
  perf stat: Micro-optimize the code: memcpy is only required if no event is selected and !null_run
  perf stat: Improve output
  perf stat: Fix multi-run stats
  perf stat: Add -n/--null option to run without counters
  perf_counter tools: Remove dead code
  perf_counter: Complete counter swap
  perf report: Print sorted callchains per histogram entries
  perf_counter tools: Prepare a small callchain framework
  perf record: Fix unhandled io return value
  perf_counter tools: Add alias for 'l1d' and 'l1i'
  perf-report: Add bare minimum PERF_EVENT_READ parsing
  perf-report: Add modes for inherited stats and no-samples
  ...
2009-06-30 19:02:59 -07:00
Yinghai Lu 66918dcdf9 x86: only clear node_states for 64bit
Nathan reported that

| commit 73d60b7f74
| Author: Yinghai Lu <yinghai@kernel.org>
| Date:   Tue Jun 16 15:33:00 2009 -0700
|
|    page-allocator: clear N_HIGH_MEMORY map before we set it again
|
|    SRAT tables may contains nodes of very small size.  The arch code may
|    decide to not activate such a node.  However, currently the early boot
|    code sets N_HIGH_MEMORY for such nodes.  These nodes therefore seem to be
|    active although these nodes have no present pages.
|
|    For 64bit N_HIGH_MEMORY == N_NORMAL_MEMORY, so that works for 64 bit too

unintentionally and incorrectly clears the cpuset.mems cgroup attribute on
an i386 kvm guest, meaning that cpuset.mems can not be used.

Fix this by only clearing node_states[N_NORMAL_MEMORY] for 64bit only.
and need to do save/restore for that in find_zone_movable_pfn

Reported-by: Nathan Lynch <ntl@pobox.com>
Tested-by: Nathan Lynch <ntl@pobox.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>,
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-30 18:56:01 -07:00
Linus Torvalds e717f33e98 Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  Revert "x86: cap iomem_resource to addressable physical memory"
2009-06-29 09:42:01 -07:00
David Woodhouse c7ab48d2ac intel-iommu: Clean up identity mapping code, remove CONFIG_DMAR_GFX_WA
There's no need for the GFX workaround now we have 'iommu=pt' for the
cases where people really care about performance. There's no need to
have a special case for just one type of device.

This also speeds up the iommu=pt path and reduces memory usage by
setting up the si_domain _once_ and then using it for all devices,
rather than giving each device its own private page tables.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2009-06-29 12:37:44 +01:00
Yinghai Lu 4078c444cf perf_counter, x86: Update x86_pmu after WARN()
The print out should read the value before changing the value.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4A487017.4090007@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 10:19:25 +02:00
Linus Torvalds 9a8fb9ee7a Merge branch 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm
* 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: shut up uninit compiler warning in paging_tmpl.h
  KVM: Ignore reads to K7 EVNTSEL MSRs
  KVM: VMX: Handle vmx instruction vmexits
  KVM: s390: Allow stfle instruction in the guest
  KVM: kvm/x86_emulate.c toggle_interruptibility() should be static
  KVM: ia64: fix ia64 build due to missing kallsyms_lookup() and double export
  KVM: protect concurrent make_all_cpus_request
  KVM: MMU: Allow 4K ptes with bit 7 (PAT) set
  KVM: Fix dirty bit tracking for slots with large pages
2009-06-28 11:12:52 -07:00
Linus Torvalds 8326e284f8 Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, delay: tsc based udelay should have rdtsc_barrier
  x86, setup: correct include file in <asm/boot.h>
  x86, setup: Fix typo "CONFIG_x86_64" in <asm/boot.h>
  x86, mce: percpu mcheck_timer should be pinned
  x86: Add sysctl to allow panic on IOCK NMI error
  x86: Fix uv bau sending buffer initialization
  x86, mce: Fix mce resume on 32bit
  x86: Move init_gbpages() to setup_arch()
  x86: ensure percpu lpage doesn't consume too much vmalloc space
  x86: implement percpu_alloc kernel parameter
  x86: fix pageattr handling for lpage percpu allocator and re-enable it
  x86: reorganize cpa_process_alias()
  x86: prepare setup_pcpu_lpage() for pageattr fix
  x86: rename remap percpu first chunk allocator to lpage
  x86: fix duplicate free in setup_pcpu_remap() failure path
  percpu: fix too lazy vunmap cache flushing
  x86: Set cpu_llc_id on AMD CPUs
2009-06-28 11:05:28 -07:00
Jaswinder Singh Rajput bde8922325 KVM: shut up uninit compiler warning in paging_tmpl.h
Dixes compilation warning:
  CC      arch/x86/kernel/io_delay.o
 arch/x86/kvm/paging_tmpl.h: In function ‘paging64_fetch’:
 arch/x86/kvm/paging_tmpl.h:279: warning: ‘sptep’ may be used uninitialized in this function
 arch/x86/kvm/paging_tmpl.h: In function ‘paging32_fetch’:
 arch/x86/kvm/paging_tmpl.h:279: warning: ‘sptep’ may be used uninitialized in this function

warning is bogus (always have a least one level), but need to shut the compiler
up.

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2009-06-28 14:10:32 +03:00
Amit Shah 9e6996240a KVM: Ignore reads to K7 EVNTSEL MSRs
In commit 7fe29e0faa we ignored the
reads to the P6 EVNTSEL MSRs. That fixed crashes on Intel machines.

Ignore the reads to K7 EVNTSEL MSRs as well to fix this on AMD
hosts.

This fixes Kaspersky antivirus crashing Windows guests on AMD hosts.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2009-06-28 14:10:31 +03:00
Avi Kivity e3c7cb6ad7 KVM: VMX: Handle vmx instruction vmexits
IF a guest tries to use vmx instructions, inject a #UD to let it know the
instruction is not implemented, rather than crashing.

This prevents guest userspace from crashing the guest kernel.

Cc: stable@kernel.org
Signed-off-by: Avi Kivity <avi@redhat.com>
2009-06-28 14:10:31 +03:00
Jaswinder Singh Rajput a3f9d3981c KVM: kvm/x86_emulate.c toggle_interruptibility() should be static
toggle_interruptibility() is used only by same file, it should be static.

Fixed following sparse warning :

  arch/x86/kvm/x86_emulate.c:1364:6: warning: symbol 'toggle_interruptibility' was not declared. Should it be static?

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2009-06-28 14:10:30 +03:00
Avi Kivity 29a4b9333b KVM: MMU: Allow 4K ptes with bit 7 (PAT) set
Bit 7 is perfectly legal in the 4K page leve; it is used for the PAT.

Signed-off-by: Avi Kivity <avi@redhat.com>
2009-06-28 14:10:29 +03:00
H. Peter Anvin ff8a4bae45 Revert "x86: cap iomem_resource to addressable physical memory"
This reverts commit 95ee14e437.
Mikael Petterson <mikepe@it.uu.se> reported that at least one of his
systems will not boot as a result.  We have ruled out the detection
algorithm malfunctioning, so it is not a matter of producing the
incorrect bitmasks; rather, something in the application of them
fails.

Revert the commit until we can root cause and correct this problem.

-stable team: this means the underlying commit should be rejected.

Reported-and-isolated-by: Mikael Petterson <mikpe@it.uu.se>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
LKML-Reference: <200906261559.n5QFxJH8027336@pilspetsen.it.uu.se>
Cc: stable@kernel.org
Cc: Grant Grundler <grundler@parisc-linux.org>
2009-06-28 09:38:47 +02:00
Pallipadi, Venkatesh e888d7facd x86, delay: tsc based udelay should have rdtsc_barrier
delay_tsc needs rdtsc_barrier to provide proper delay.

Output from a test driver using hpet to cross check delay
provided by udelay().

Before:
[   86.794363] Expected delay 5us actual 4679ns
[   87.154362] Expected delay 5us actual 698ns
[   87.514162] Expected delay 5us actual 4539ns
[   88.653716] Expected delay 5us actual 4539ns
[   94.664106] Expected delay 10us actual 9638ns
[   95.049351] Expected delay 10us actual 10126ns
[   95.416110] Expected delay 10us actual 9568ns
[   95.799216] Expected delay 10us actual 9638ns
[  103.624104] Expected delay 10us actual 9707ns
[  104.020619] Expected delay 10us actual 768ns
[  104.419951] Expected delay 10us actual 9707ns

After:
[   50.983320] Expected delay 5us actual 5587ns
[   51.261807] Expected delay 5us actual 5587ns
[   51.565715] Expected delay 5us actual 5657ns
[   51.861171] Expected delay 5us actual 5587ns
[   52.164704] Expected delay 5us actual 5726ns
[   52.487457] Expected delay 5us actual 5657ns
[   52.789338] Expected delay 5us actual 5726ns
[   57.119680] Expected delay 10us actual 10755ns
[   57.893997] Expected delay 10us actual 10615ns
[   58.261287] Expected delay 10us actual 10755ns
[   58.620505] Expected delay 10us actual 10825ns
[   58.941035] Expected delay 10us actual 10755ns
[   59.320903] Expected delay 10us actual 10615ns
[   61.306311] Expected delay 10us actual 10755ns
[   61.520542] Expected delay 10us actual 10615ns

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-25 16:47:40 -07:00
H. Peter Anvin 658dbfeb5e x86, setup: correct include file in <asm/boot.h>
<asm/boot.h> needs <asm/pgtable_types.h>, not <asm/page_types.h> in
order to resolve PMD_SHIFT.  Also, correct a +1 which really should be
+ THREAD_ORDER.

This is a build error which was masked by a typoed #ifdef.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-25 15:16:06 -07:00
Robert P. J. Day 22f4319d6b x86, setup: Fix typo "CONFIG_x86_64" in <asm/boot.h>
CONFIG_X86_64 was misspelled (wrong case), which caused the x86-64
kernel to advertise itself as more relocatable than it really is.
This could in theory cause boot failures once bootloaders start
support the new relocation fields.

Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-25 13:33:11 -07:00
Hidetoshi Seto 5be6066a7f x86, mce: percpu mcheck_timer should be pinned
If CONFIG_NO_HZ + CONFIG_SMP, timer added via add_timer() might
be migrated on other cpu.  Use add_timer_on() instead.

Avoids the following failure:

Maciej Rutecki wrote:
> > After normal boot I try:
> >
> > echo 1 > /sys/devices/system/machinecheck/machinecheck0/check_interval
> >
> > I found this in dmesg:
> >
> > [  141.704025] ------------[ cut here ]------------
> > [  141.704039] WARNING: at arch/x86/kernel/cpu/mcheck/mce.c:1102
> > mcheck_timer+0xf5/0x100()

Reported-by: Maciej Rutecki <maciej.rutecki@gmail.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Tested-by: Maciej Rutecki <maciej.rutecki@gmail.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-25 13:33:02 -07:00
Kurt Garloff 5211a242d0 x86: Add sysctl to allow panic on IOCK NMI error
This patch introduces a new sysctl:

    /proc/sys/kernel/panic_on_io_nmi

which defaults to 0 (off).

When enabled, the kernel panics when the kernel receives an NMI
caused by an IO error.

The IO error triggered NMI indicates a serious system
condition, which could result in IO data corruption. Rather
than contiuing, panicing and dumping might be a better choice,
so one can figure out what's causing the IO error.

This could be especially important to companies running IO
intensive applications where corruption must be avoided, e.g. a
bank's databases.

[ SuSE has been shipping it for a while, it was done at the
  request of a large database vendor, for their users. ]

Signed-off-by: Kurt Garloff <garloff@suse.de>
Signed-off-by: Roberto Angelino <robertangelino@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
LKML-Reference: <20090624213211.GA11291@kroah.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-25 22:06:11 +02:00
Peter Zijlstra 194002b274 perf_counter, x86: Add mmap counter read support
Update the mmap control page with the needed information to
use the userspace RDPMC instruction for self monitoring.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-25 21:39:06 +02:00
Linus Torvalds 236e946b53 Revert "PCI: use ACPI _CRS data by default"
This reverts commit 9e9f46c44e.

Quoting from the commit message:

 "At this point, it seems to solve more problems than it causes, so let's
  try using it by default.  It's an easy revert if it ends up causing
  trouble."

And guess what? The _CRS code causes trouble.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-24 16:23:03 -07:00
Linus Torvalds 0c26d7cc31 Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6: (72 commits)
  asus-laptop: remove EXPERIMENTAL dependency
  asus-laptop: use pr_fmt and pr_<level>
  eeepc-laptop: cpufv updates
  eeepc-laptop: sync eeepc-laptop with asus_acpi
  asus_acpi: Deprecate in favor of asus-laptop
  acpi4asus: update MAINTAINER and KConfig links
  asus-laptop: platform dev as parent for led and backlight
  eeepc-laptop: enable camera by default
  ACPI: Rename ACPI processor device bus ID
  acerhdf: Acer Aspire One fan control
  ACPI: video: DMI workaround broken Acer 7720 BIOS enabling display brightness
  ACPI: run ACPI device hot removal in kacpi_hotplug_wq
  ACPI: Add the reference count to avoid unloading ACPI video bus twice
  ACPI: DMI to disable Vista compatibility on some Sony laptops
  ACPI: fix a deadlock in hotplug case
  Show the physical device node of backlight class device.
  ACPI: pdc init related memory leak with physical CPU hotplug
  ACPI: pci_root: remove unused dev/fn information
  ACPI: pci_root: simplify list traversals
  ACPI: pci_root: use driver data rather than list lookup
  ...
2009-06-24 10:17:07 -07:00
Cliff Wickman 9c26f52b90 x86: Fix uv bau sending buffer initialization
The initialization of the UV Broadcast Assist Unit's sending
buffers was making an invalid assumption about the
initialization of an MMR that defines its address.

The BIOS will not be providing that MMR.  So
uv_activation_descriptor_init() should unconditionally set it.

Tested on UV simulator.

Signed-off-by: Cliff Wickman <cpw@sgi.com>
Cc: <stable@kernel.org> # for v2.6.30.x
LKML-Reference: <E1MJTfj-0005i1-W8@eag09.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-24 17:33:58 +02:00