Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 161
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 25 2月, 2011 1 次提交
  3. 15 9月, 2010 1 次提交
    • T
      x86: hpet: Work around hardware stupidity · 54ff7e59
      由 Thomas Gleixner 提交于 
      This more or less reverts commits 08be9796 (x86: Force HPET
readback_cmp for all ATI chipsets) and 30a564be (x86, hpet: Restrict
read back to affected ATI chipsets) to the status of commit 8da854cb
(x86, hpet: Erratum workaround for read after write of HPET
comparator).

The delta to commit 8da854cb is mostly comments and the change from
WARN_ONCE to printk_once as we know the call path of this function
already.

This needs really in depth explanation:

First of all the HPET design is a complete failure. Having a counter
compare register which generates an interrupt on matching values
forces the software to do at least one superfluous readback of the
counter register.

While it is nice in theory to program "absolute" time events it is
practically useless because the timer runs at some absurd frequency
which can never be matched to real world units. So we are forced to
calculate a relative delta and this forces a readout of the actual
counter value, adding the delta and programming the compare
register. When the delta is small enough we run into the danger that
we program a compare value which is already in the past. Due to the
compare for equal nature of HPET we need to read back the counter
value after writing the compare rehgister (btw. this is necessary for
absolute timeouts as well) to make sure that we did not miss the timer
event. We try to work around that by setting the minimum delta to a
value which is larger than the theoretical time which elapses between
the counter readout and the compare register write, but that's only
true in theory. A NMI or SMI which hits between the readout and the
write can easily push us beyond that limit. This would result in
waiting for the next HPET timer interrupt until the 32bit wraparound
of the counter happens which takes about 306 seconds.

So we designed the next event function to look like:

   match = read_cnt() + delta;
   write_compare_ref(match);
   return read_cnt() < match ? 0 : -ETIME;

At some point we got into trouble with certain ATI chipsets. Even the
above "safe" procedure failed. The reason was that the write to the
compare register was delayed probably for performance reasons. The
theory was that they wanted to avoid the synchronization of the write
with the HPET clock, which is understandable. So the write does not
hit the compare register directly instead it goes to some intermediate
register which is copied to the real compare register in sync with the
HPET clock. That opens another window for hitting the dreaded "wait
for a wraparound" problem.

To work around that "optimization" we added a read back of the compare
register which either enforced the update of the just written value or
just delayed the readout of the counter enough to avoid the issue. We
unfortunately never got any affirmative info from ATI/AMD about this.

One thing is sure, that we nuked the performance "optimization" that
way completely and I'm pretty sure that the result is worse than
before some HW folks came up with those.

Just for paranoia reasons I added a check whether the read back
compare register value was the same as the value we wrote right
before. That paranoia check triggered a couple of years after it was
added on an Intel ICH9 chipset. Venki added a workaround (commit
8da854cb) which was reading the compare register twice when the first
check failed. We considered this to be a penalty in general and
restricted the readback (thus the wasted CPU cycles) to the known to
be affected ATI chipsets.

This turned out to be a utterly wrong decision. 2.6.35 testers
experienced massive problems and finally one of them bisected it down
to commit 30a564be which spured some further investigation.

Finally we got confirmation that the write to the compare register can
be delayed by up to two HPET clock cycles which explains the problems
nicely. All we can do about this is to go back to Venki's initial
workaround in a slightly modified version.

Just for the record I need to say, that all of this could have been
avoided if hardware designers and of course the HPET committee would
have thought about the consequences for a split second. It's out of my
comprehension why designing a working timer is so hard. There are two
ways to achieve it:

 1) Use a counter wrap around aware compare_reg <= counter_reg
    implementation instead of the easy compare_reg == counter_reg

    Downsides:

	- It needs more silicon.

	- It needs a readout of the counter to apply a relative
	  timeout. This is necessary as the counter does not run in
	  any useful (and adjustable) frequency and there is no
	  guarantee that the counter which is used for timer events is
	  the same which is used for reading the actual time (and
	  therefor for calculating the delta)

    Upsides:

	- None

  2) Use a simple down counter for relative timer events

    Downsides:

	- Absolute timeouts are not possible, which is not a problem
	  at all in the context of an OS and the expected
	  max. latencies/jitter (also see Downsides of #1)

   Upsides:

	- It needs less or equal silicon.

	- It works ALWAYS

	- It is way faster than a compare register based solution (One
	  write versus one write plus at least one and up to four
	  reads)

I would not be so grumpy about all of this, if I would not have been
ignored for many years when pointing out these flaws to various
hardware folks. I really hate timers (at least those which seem to be
designed by janitors).

Though finally we got a reasonable explanation plus a solution and I
want to thank all the folks involved in chasing it down and providing
valuable input to this.
Bisected-by: NNix <nix@esperi.org.uk>
Reported-by: NArtur Skawina <art.08.09@gmail.com>
Reported-by: NDamien Wyart <damien.wyart@free.fr>
Reported-by: NJohn Drescher <drescherjm@gmail.com>
Cc: Venkatesh Pallipadi <venki@google.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Borislav Petkov <borislav.petkov@amd.com>
Cc: stable@kernel.org
Acked-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
      54ff7e59
  5. 08 9月, 2010 1 次提交
  7. 15 7月, 2010 1 次提交
  9. 08 4月, 2009 1 次提交
  11. 10 1月, 2009 1 次提交
    • A
      x86: only scan the root bus in early PCI quirks · 8659c406
      由 Andi Kleen 提交于 
      We found a situation on Linus' machine that the Nvidia timer quirk hit on
a Intel chipset system.  The problem is that the system has a fancy Nvidia
card with an own PCI bridge, and the early-quirks code looking for any
NVidia bridge triggered on it incorrectly.  This didn't lead a boot
failure by luck, but the timer routing code selecting the wrong timer
first and some ugly messages.  It might lead to real problems on other
systems.

I checked all the devices which are currently checked for by early_quirks
and it turns out they are all located in the root bus zero.

So change the early-quirks loop to only scan bus 0.  This incidently also
saves quite some unnecessary scanning work, because early_quirks doesn't
go through all the non root busses.

The graphics card is not on bus 0, so it is not matched anymore.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      8659c406
  13. 28 11月, 2008 1 次提交
  15. 16 11月, 2008 1 次提交
  17. 22 10月, 2008 1 次提交
  19. 17 10月, 2008 1 次提交
  21. 07 10月, 2008 1 次提交
  23. 06 9月, 2008 1 次提交
  25. 11 7月, 2008 1 次提交
  27. 08 7月, 2008 2 次提交
  29. 17 6月, 2008 1 次提交
  31. 30 1月, 2008 3 次提交
    • S
      x86: fix section mismatch warning in early-quirks.c · 85b74d6c
      由 Sam Ravnborg 提交于 
      Fix following warnings:
WARNING: arch/x86/kernel/built-in.o(.text+0x139e1): Section mismatch: reference to .init.data:early_qrk in 'check_dev_quirk'
WARNING: arch/x86/kernel/built-in.o(.text+0x139f5): Section mismatch: reference to .init.data:early_qrk in 'check_dev_quirk'
WARNING: arch/x86/kernel/built-in.o(.text+0x13a0c): Section mismatch: reference to .init.data:early_qrk in 'check_dev_quirk'
WARNING: arch/x86/kernel/built-in.o(.text+0x13a12): Section mismatch: reference to .init.data:early_qrk in 'check_dev_quirk'
WARNING: arch/x86/kernel/built-in.o(.text+0x13a1a): Section mismatch: reference to .init.data:early_qrk in 'check_dev_quirk'
WARNING: arch/x86/kernel/built-in.o(.text+0x13a36): Section mismatch: reference to .init.data:early_qrk in 'check_dev_quirk'
WARNING: arch/x86/kernel/built-in.o(.text+0x13a42): Section mismatch: reference to .init.data:

Warning was caused by access to the __initdata annotated variable
from the non-annotated static function check_dev_quirk().
check_dev_quirk() were only used from a function annotated
__init so add __init annotation to check_dev_quirk() to fix it.
Signed-off-by: NSam Ravnborg <sam@ravnborg.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
      85b74d6c
    • N
      x86: clean up arch/x86/kernel/early-quirks.c · 7bcbc78d
      由 Neil Horman 提交于 
      clean up checkpatch errors. No code changed.

      text    data     bss     dec     hex filename
       705     120       0     825     339 early-quirks.o.before
       705     120       0     825     339 early-quirks.o.after
Signed-off-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
      7bcbc78d
    • N
      x86, kexec: force x86 arches to boot kdump kernels on boot cpu · c6b48324
      由 Neil Horman 提交于 
      Recently a kdump bug was discovered in which a system would hang inside
calibrate_delay during the booting of the kdump kernel.  This was caused
by the fact that the jiffies counter was not being incremented during
timer calibration.  The root cause of this problem was found to be a
bios misconfiguration of the hypertransport bus.  On system affected by
this hang, the bios had assigned APIC ids which used extended apic bits
(more than the nominal 4 bit ids's), but failed to configure bit 17 of
the hypertransport transaction config register, which indicated that the
mask for the destination field of interrupt packets accross the ht bus
(see section 3.3.9 of
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/26094.PDF).
If a crash occurs on a cpu with an APIC id that extends beyond 4 bits,
it will not recieve interrupts during the kdump kernel boot, and this
hang will be the result.  The fix is to add this patch, whcih add an
early pci quirk check, to forcibly enable this bit in the httcfg
register.  This enables all cpus on a system to receive interrupts, and
allows kdump kernel bootup to procede normally.
Signed-off-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
      c6b48324
  33. 30 10月, 2007 3 次提交
  35. 28 10月, 2007 1 次提交
  37. 20 10月, 2007 1 次提交
  39. 11 10月, 2007 2 次提交
  41. 22 7月, 2007 1 次提交
  43. 03 5月, 2007 1 次提交
  45. 09 4月, 2007 1 次提交
    • A
      [PATCH] x86_64 early quirks: fix early_qrk[] section tag · c993c735
      由 Andrew Morton 提交于 
      WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:nvidia_bugs from .data between 'early_qrk' (at offset 0x8428) and 'enable_cpu_hotplug'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:via_bugs from .data between 'early_qrk' (at offset 0x8438) and 'enable_cpu_hotplug'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:ati_bugs from .data between 'early_qrk' (at offset 0x8448) and 'enable_cpu_hotplug'

The compiler is putting it into .data because the __initdata is in the wrong
place.

Cc: Andi Kleen <ak@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      c993c735
  47. 17 3月, 2007 1 次提交
    • S
      [PATCH] x86-64: fix section mismatch warnings · 43999d9e
      由 Sam Ravnborg 提交于 
      Fix the following section mismatch warnings on x86_64:
(build using defconfig)

WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:mtrr_bp_init from .text between 'identify_cpu' (at offset 0x65eb) and 'IRQ0x20_interrupt'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data: from .text between 'finish_e820_parsing' (at offset 0x7dc2) and 'early_panic'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:e820_print_map from .text between 'finish_e820_parsing' (at offset 0x7de1) and 'early_panic'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:num_processors from .text between 'acpi_unmap_lsapic' (at offset 0xc88f) and 'acpi_register_ioapic'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:disabled_cpus from .text between 'MP_processor_info' (at offset 0x11f35) and 'mp_register_lapic'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:num_processors from .text between 'MP_processor_info' (at offset 0x11f6e) and 'mp_register_lapic'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:num_processors from .text between 'MP_processor_info' (at offset 0x11f93) and 'mp_register_lapic'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fix_aperture from .text between 'gart_parse_options' (at offset 0x15517) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fix_aperture from .text between 'gart_parse_options' (at offset 0x1552c) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x1553d) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x15552) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x15561) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'gart_parse_options' (at offset 0x15577) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fallback_aper_force from .text between 'gart_parse_options' (at offset 0x1558a) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:fallback_aper_order from .text between 'gart_parse_options' (at offset 0x155bf) and 'iommu_full'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:timer_over_8254 from .text between 'ati_bugs' (at offset 0x16344) and 'via_bugs'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:timer_over_8254 from .text between 'ati_bugs' (at offset 0x16356) and 'via_bugs'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_allowed from .text between 'via_bugs' (at offset 0x16380) and 'nvidia_bugs'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:iommu_aperture_disabled from .text between 'via_bugs' (at offset 0x16397) and 'nvidia_bugs'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:acpi_use_timer_override from .text between 'nvidia_bugs' (at offset 0x163a7) and 'arch_unregister_cpu'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:nvidia_hpet_check from .text between 'nvidia_bugs' (at offset 0x163b1) and 'arch_unregister_cpu'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data: from .text between 'nvidia_bugs' (at offset 0x163be) and 'arch_unregister_cpu'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data: from .text between 'nvidia_bugs' (at offset 0x163d1) and 'arch_unregister_cpu'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.data:acpi_skip_timer_override from .text between 'nvidia_bugs' (at offset 0x163e1) and 'arch_unregister_cpu'
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:quirk_intel_irqbalance from .text between 'intel_bugs' (at offset 0x1633c) and 'ati_bugs'

But adds:
WARNING: arch/x86_64/kernel/built-in.o - Section mismatch: reference to .init.text:get_mtrr_state from .text between 'mtrr_bp_init' (at offset 0xb887) and 'ipi_handler'

The warnings does not show up during a normal build due to kbuild
failing to check for section mismatch in vmlinux.
To see these warnings run:
scripts/mod/modpost arch/x86_64/kernel/built-in.o

kbuild will be fixed but the 'noise-level' had to be decresed first.
There remains a few section mismatch warnigns for x86_64 for areas where I did
not feel confident.
Signed-off-by: NSam Ravnborg <sam@ravnborg.org>
Signed-off-by: NAndi Kleen <ak@suse.de>
      43999d9e
  49. 09 3月, 2007 2 次提交
  51. 13 2月, 2007 1 次提交
  53. 03 2月, 2007 1 次提交
  55. 09 1月, 2007 1 次提交
  57. 07 12月, 2006 2 次提交
  59. 14 11月, 2006 1 次提交
    • A
      [PATCH] x86: Add acpi_user_timer_override option for Asus boards · fa18f477
      由 Andi Kleen 提交于 
      Timer overrides are normally disabled on Nvidia board because
they are commonly wrong, except on new ones with HPET support.
Unfortunately there are quite some Asus boards around that
don't have HPET, but need a timer override.

We don't know yet how to handle this transparently,
but at least add a command line option to force the timer override
and let them boot.

Cc: len.brown@intel.com
Signed-off-by: NAndi Kleen <ak@suse.de>
      fa18f477
  61. 22 10月, 2006 1 次提交
    • A
      [PATCH] x86-64: Revert timer routing behaviour back to 2.6.16 state · e70ea8c0
      由 Andi Kleen 提交于 
      By default route the 8254 over the 8259 and only disable
it on ATI boards where this causes double timer interrupts.

This should unbreak some Nvidia boards where the timer doesn't
seem to tick of it isn't enabled in the 8259. At least one
VIA board also seemed to have a little trouble with the disabled
8259.

For 2.6.20 we'll try both dynamically without black listing, but I think
for .19 this is the safer approach because it has been already well tested
in earlier kernels. This also makes the x86-64 behaviour the same
as i386.

Command line options can change all this of course.
Signed-off-by: NAndi Kleen <ak@suse.de>
      e70ea8c0
  63. 26 9月, 2006 1 次提交
    • A
      [PATCH] x86: Allow disabling early pci scans with pci=noearly or disallowing conf1 · 0637a70a
      由 Andi Kleen 提交于 
      Some buggy systems can machine check when config space accesses
happen for some non existent devices.  i386/x86-64 do some early
device scans that might trigger this. Allow pci=noearly to disable
this. Also when type 1 is disabling also don't do any early
accesses which are always type1.

This moves the pci= configuration parsing to be a early parameter.
I don't think this can break anything because it only changes
a single global that is only used by PCI.

Cc: gregkh@suse.de
Cc: Trammell Hudson <hudson@osresearch.net>
Signed-off-by: NAndi Kleen <ak@suse.de>
      0637a70a