There's been reports of high NMI handler overhead, highlighted by
such kernel messages:
[ 3697.380195] perf samples too long (10009 > 10000), lowering kernel.perf_event_max_sample_rate to 13000
[ 3697.389509] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 9.331 msecs
Don Zickus analyzed the source of the overhead and reported:
> While there are a few places that are causing latencies, for now I focused on
> the longest one first. It seems to be 'copy_user_from_nmi'
>
> intel_pmu_handle_irq ->
> intel_pmu_drain_pebs_nhm ->
> __intel_pmu_drain_pebs_nhm ->
> __intel_pmu_pebs_event ->
> intel_pmu_pebs_fixup_ip ->
> copy_from_user_nmi
>
> In intel_pmu_pebs_fixup_ip(), if the while-loop goes over 50, the sum of
> all the copy_from_user_nmi latencies seems to go over 1,000,000 cycles
> (there are some cases where only 10 iterations are needed to go that high
> too, but in generall over 50 or so). At this point copy_user_from_nmi
> seems to account for over 90% of the nmi latency.
The solution to that is to avoid having to call copy_from_user_nmi() for
every instruction.
Since we already limit the max basic block size, we can easily
pre-allocate a piece of memory to copy the entire thing into in one
go.
Don reported this test result:
> Your patch made a huge difference in improvement. The
> copy_from_user_nmi() no longer hits the million of cycles. I still
> have a batch of 100,000-300,000 cycles. My longest NMI paths used
> to be dominated by copy_from_user_nmi, now it is not (I have to dig
> up the new hot path).
Reported-and-tested-by: Don Zickus <dzickus@redhat.com>
Cc: jmario@redhat.com
Cc: acme@infradead.org
Cc: dave.hansen@linux.intel.com
Cc: eranian@google.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131016105755.GX10651@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
A small batch of fixes this week, mostly OMAP related. Nothing stands out
as particularly controversial.
Also a fix for a 3.12-rc1 timer regression for Exynos platforms, including
the Chromebooks.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)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=HpMx
-----END PGP SIGNATURE-----
Merge tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM SoC fixes from Olof Johansson:
"A small batch of fixes this week, mostly OMAP related. Nothing stands
out as particularly controversial.
Also a fix for a 3.12-rc1 timer regression for Exynos platforms,
including the Chromebooks"
* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
ARM: exynos: dts: Update 5250 arch timer node with clock frequency
ARM: OMAP2: RX-51: Add missing max_current to rx51_lp5523_led_config
ARM: mach-omap2: board-generic: fix undefined symbol
ARM: dts: Fix pinctrl mask for omap3
ARM: OMAP3: Fix hardware detection for omap3630 when booted with device tree
ARM: OMAP2: gpmc-onenand: fix sync mode setup with DT
Without the "clock-frequency" property in arch timer node, could able
to see the below crash dump.
[<c0014e28>] (unwind_backtrace+0x0/0xf4) from [<c0011808>] (show_stack+0x10/0x14)
[<c0011808>] (show_stack+0x10/0x14) from [<c036ac1c>] (dump_stack+0x7c/0xb0)
[<c036ac1c>] (dump_stack+0x7c/0xb0) from [<c01ab760>] (Ldiv0_64+0x8/0x18)
[<c01ab760>] (Ldiv0_64+0x8/0x18) from [<c0062f60>] (clockevents_config.part.2+0x1c/0x74)
[<c0062f60>] (clockevents_config.part.2+0x1c/0x74) from [<c0062fd8>] (clockevents_config_and_register+0x20/0x2c)
[<c0062fd8>] (clockevents_config_and_register+0x20/0x2c) from [<c02b8e8c>] (arch_timer_setup+0xa8/0x134)
[<c02b8e8c>] (arch_timer_setup+0xa8/0x134) from [<c04b47b4>] (arch_timer_init+0x1f4/0x24c)
[<c04b47b4>] (arch_timer_init+0x1f4/0x24c) from [<c04b40d8>] (clocksource_of_init+0x34/0x58)
[<c04b40d8>] (clocksource_of_init+0x34/0x58) from [<c049ed8c>] (time_init+0x20/0x2c)
[<c049ed8c>] (time_init+0x20/0x2c) from [<c049b95c>] (start_kernel+0x1e0/0x39c)
THis is because the Exynos u-boot, for example on the Chromebooks, doesn't set
up the CNTFRQ register as expected by arch_timer. Instead, we have to specify
the frequency in the device tree like this.
Signed-off-by: Yuvaraj Kumar C D <yuvaraj.cd@samsung.com>
[olof: Changed subject, added comment, elaborated on commit message]
Signed-off-by: Olof Johansson <olof@lixom.net>
noticed now that people are actually using the device tree
based booting for omap3.
Also one regression fix for timer compile for dra7xx when
omap5 is not selected, and a LED regression fix for n900.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)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=yVzH
-----END PGP SIGNATURE-----
Merge tag 'fixes-against-v3.12-rc3-take2' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes
From Tony Lindgren:
Few fixes for omap3 related hangs and errors that people have
noticed now that people are actually using the device tree
based booting for omap3.
Also one regression fix for timer compile for dra7xx when
omap5 is not selected, and a LED regression fix for n900.
* tag 'fixes-against-v3.12-rc3-take2' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
ARM: OMAP2: RX-51: Add missing max_current to rx51_lp5523_led_config
ARM: mach-omap2: board-generic: fix undefined symbol
ARM: dts: Fix pinctrl mask for omap3
ARM: OMAP3: Fix hardware detection for omap3630 when booted with device tree
ARM: OMAP2: gpmc-onenand: fix sync mode setup with DT
Signed-off-by: Olof Johansson <olof@lixom.net>
The attached change defers the initialization of the variables tsk, mm
and flags until they are needed. As a result, the code won't crash if a
kernel probe is done with a corrupt context and the code will be better
optimized.
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
Running an "echo t > /proc/sysrq-trigger" crashes the parisc kernel. The
problem is, that in print_worker_info() we try to read the workqueue info via
the probe_kernel_read() functions which use pagefault_disable() to avoid
crashes like this:
probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq));
probe_kernel_read(&wq, &pwq->wq, sizeof(wq));
probe_kernel_read(name, wq->name, sizeof(name) - 1);
The problem here is, that the first probe_kernel_read(&pwq) might return zero
in pwq and as such the following probe_kernel_reads() try to access contents of
the page zero which is read protected and generate a kernel segfault.
With this patch we fix the interruption handler to call parisc_terminate()
directly only if pagefault_disable() was not called (in which case
preempt_count()==0). Otherwise we hand over to the pagefault handler which
will try to look up the faulting address in the fixup tables.
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v3.0+
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
Commit 9a46ad6d6d "smp: make smp_call_function_many() use logic
similar to smp_call_function_single()" has unified the way to handle
single and multiple cross-CPU function calls. Now only one interrupt
is needed for architecture specific code to support generic SMP function
call interfaces, so kill the redundant single function call interrupt.
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Jiang Liu <liuj97@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
Pull gcc "asm goto" miscompilation workaround from Ingo Molnar:
"This is the fix for the GCC miscompilation discussed in the following
lkml thread:
[x86] BUG: unable to handle kernel paging request at 00740060
The bug in GCC has been fixed by Jakub and the fix will be part of the
GCC 4.8.2 release expected to be released next week - so the quirk's
version test checks for <= 4.8.1.
The quirk is only added to compiler-gcc4.h and not to the higher level
compiler.h because all asm goto uses are behind a feature check"
* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
compiler/gcc4: Add quirk for 'asm goto' miscompilation bug
Pull x86 fixes from Ingo Molnar:
"A build fix and a reboot quirk"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/reboot: Add reboot quirk for Dell Latitude E5410
x86, build, pci: Fix PCI_MSI build on !SMP
ARCompact TRAP_S insn used for breakpoints, commits before exception is
taken (updating architectural PC). So ptregs->ret contains next-PC and
not the breakpoint PC itself. This is different from other restartable
exceptions such as TLB Miss where ptregs->ret has exact faulting PC.
gdb needs to know exact-PC hence ARC ptrace GETREGSET provides for
@stop_pc which returns ptregs->ret vs. EFA depending on the
situation.
However, writing stop_pc (SETREGSET request), which updates ptregs->ret
doesn't makes sense stop_pc doesn't always correspond to that reg as
described above.
This was not an issue so far since user_regs->ret / user_regs->stop_pc
had same value and both writing to ptregs->ret was OK, needless, but NOT
broken, hence not observed.
With gdb "jump", they diverge, and user_regs->ret updating ptregs is
overwritten immediately with stop_pc, which this patch fixes.
Reported-by: Anton Kolesov <akolesov@synopsys.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Pull MIPS fix from Ralf Baechle:
"Just one fix. The stack protector was loading the value of the canary
instead of its address"
* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
MIPS: stack protector: Fix per-task canary switch
Fengguang Wu, Oleg Nesterov and Peter Zijlstra tracked down
a kernel crash to a GCC bug: GCC miscompiles certain 'asm goto'
constructs, as outlined here:
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
Implement a workaround suggested by Jakub Jelinek.
Reported-and-tested-by: Fengguang Wu <fengguang.wu@intel.com>
Reported-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Suggested-by: Jakub Jelinek <jakub@redhat.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull kbuild fix from Michal Marek:
"Here is an ARM Makefile fix that you even acked. After nobody wanted
to take it, it ended up in the kbuild tree"
* 'rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild:
arm, kbuild: make "make install" not depend on vmlinux
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)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=O6an
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm fixes from Paolo Bonzini:
"Fixes for 3.12-rc5: two old PPC bugs and one new (3.12-rc2) x86 bug"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
kvm: ppc: booke: check range page invalidation progress on page setup
KVM: PPC: Book3S HV: Fix typo in saving DSCR
KVM: nVMX: fix shadow on EPT
When the MM code is invalidating a range of pages, it calls the KVM
kvm_mmu_notifier_invalidate_range_start() notifier function, which calls
kvm_unmap_hva_range(), which arranges to flush all the TLBs for guest pages.
However, the Linux PTEs for the range being flushed are still valid at
that point. We are not supposed to establish any new references to pages
in the range until the ...range_end() notifier gets called.
The PPC-specific KVM code doesn't get any explicit notification of that;
instead, we are supposed to use mmu_notifier_retry() to test whether we
are or have been inside a range flush notifier pair while we have been
referencing a page.
This patch calls the mmu_notifier_retry() while mapping the guest
page to ensure we are not referencing a page when in range invalidation.
This call is inside a region locked with kvm->mmu_lock, which is the
same lock that is called by the KVM MMU notifier functions, thus
ensuring that no new notification can proceed while we are in the
locked region.
Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Acked-by: Alexander Graf <agraf@suse.de>
[Backported to 3.12 - Paolo]
Reviewed-by: Bharat Bhushan <bharat.bhushan@freescale.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This fixes a typo in the code that saves the guest DSCR (Data Stream
Control Register) into the kvm_vcpu_arch struct on guest exit. The
effect of the typo was that the DSCR value was saved in the wrong place,
so changes to the DSCR by the guest didn't persist across guest exit
and entry, and some host kernel memory got corrupted.
Cc: stable@vger.kernel.org [v3.1+]
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
72f857950f broke shadow on EPT. This patch reverts it and fixes PAE
on nEPT (which reverted commit fixed) in other way.
Shadow on EPT is now broken because while L1 builds shadow page table
for L2 (which is PAE while L2 is in real mode) it never loads L2's
GUEST_PDPTR[0-3]. They do not need to be loaded because without nested
virtualization HW does this during guest entry if EPT is disabled,
but in our case L0 emulates L2's vmentry while EPT is enables, so we
cannot rely on vmcs12->guest_pdptr[0-3] to contain up-to-date values
and need to re-read PDPTEs from L2 memory. This is what kvm_set_cr3()
is doing, but by clearing cache bits during L2 vmentry we drop values
that kvm_set_cr3() read from memory.
So why the same code does not work for PAE on nEPT? kvm_set_cr3()
reads pdptes into vcpu->arch.walk_mmu->pdptrs[]. walk_mmu points to
vcpu->arch.nested_mmu while nested guest is running, but ept_load_pdptrs()
uses vcpu->arch.mmu which contain incorrect values. Fix that by using
walk_mmu in ept_(load|save)_pdptrs.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
File drivers/leds/leds-lp55xx-common.c refuse to change led_current sysfs
attribute if value is higher than max_current specified in board file. By default
global C variables are zero, so changing always failed. This patch adding missing
max_current and setting it to max safe value 100 (10 mA).
It is unclear which commit exactly caused this regression as the lp5523
driver was broken and was hiding the platform data breakage. Now
the driver is fixed so this should be fixed as well.
Signed-off-by: Pali Rohár <pali.rohar@gmail.com>
Signed-off-by: Joerg Reisenweber <joerg@openmoko.org>
[tony@atomide.com: updated comments to describe regression]
Signed-off-by: Tony Lindgren <tony@atomide.com>
Since dra7 reuses the function 'omap5_realtime_timer_init' in
arch/arm/mach-omap2/board-generic.c as timer init function, it has to be
built for this SoC as well.
Signed-off-by: Simon Barth <Simon.Pe.Barth@gmail.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
The wake-up interrupt bit is available on omap3/4/5 processors
unlike what we claim. Without fixing it we cannot use it on
omap3 and the system configured for wake-up events will just
hang on wake-up.
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: Benoît Cousson <bcousson@baylibre.com>
Cc: devicetree@vger.kernel.org
Signed-off-by: Tony Lindgren <tony@atomide.com>
SoC family definitions at the moment are reactive to board needs
as a result, beagle-xm would matchup with ti,omap3 which invokes
omap3430_init_early instead of omap3630_init_early. Obviously, this is
the wrong behavior.
With clock node dts conversion, we get the following warnings before
system hangs as a result and 3630 based platforms fails to boot
(uart4 clocks are only present in OMAP3630 and not present in
OMAP3430):
...
omap_hwmod: uart4: cannot clk_get main_clk uart4_fck
omap_hwmod: uart4: cannot _init_clocks
WARNING: CPU: 0 PID: 1 at arch/arm/mach-omap2/omap_hwmod.c:2434
_init+0x6c/0x80()
omap_hwmod: uart4: couldn't init clocks
...
WARNING: CPU: 0 PID: 1 at arch/arm/mach-omap2/omap_hwmod.c:2126
_enable+0x254/0x280()
omap_hwmod: timer12: enabled state can only be entered from
initialized, idle, or disabled state
...
WARNING: CPU: 0 PID: 46 at arch/arm/mach-omap2/omap_hwmod.c:2224
_idle+0xd4/0xf8()
omap_hwmod: timer12: idle state can only be entered from enabled state
WARNING: CPU: 0 PID: 1 at arch/arm/mach-omap2/omap_hwmod.c:2126
_enable+0x254/0x280()
omap_hwmod: uart4: enabled state can only be entered from
initialized, idle, or disabled state
So, add specific compatiblity for 3630 to allow match for Beagle-XM
platform.
Signed-off-by: Nishanth Menon <nm@ti.com>
[tony@atomide.com: left out ti,omap343x, updated comments]
Signed-off-by: Tony Lindgren <tony@atomide.com>
Pull perf fixes from Ingo Molnar:
"Various fixlets:
On the kernel side:
- fix a race
- fix a bug in the handling of the perf ring-buffer data page
On the tooling side:
- fix the handling of certain corrupted perf.data files
- fix a bug in 'perf probe'
- fix a bug in 'perf record + perf sched'
- fix a bug in 'make install'
- fix a bug in libaudit feature-detection on certain distros"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf session: Fix infinite loop on invalid perf.data file
perf tools: Fix installation of libexec components
perf probe: Fix to find line information for probe list
perf tools: Fix libaudit test
perf stat: Set child_pid after perf_evlist__prepare_workload()
perf tools: Add default handler for mmap2 events
perf/x86: Clean up cap_user_time* setting
perf: Fix perf_pmu_migrate_context
irq_exit() is now called on the irq stack, which can trigger a switch to
the softirq stack from the irq stack. If an interrupt happens at that
point, we will not properly detect the re-entrancy and clobber the
original return context on the irq stack.
This fixes it. The side effect is to prevent all nesting from softirq
stack to irq stack even in the "safe" case but it's simpler that way and
matches what x86_64 does.
Reported-by: Cédric Le Goater <clg@fr.ibm.com>
Tested-by: Cédric Le Goater <clg@fr.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull Tile bugfixes from Chris Metcalf:
"This fixes some serious issues with PREEMPT support, and a couple of
smaller corner-case issues fixed in the last couple of weeks"
* 'stable' of git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
arch: tile: re-use kbasename() helper
tile: use a more conservative __my_cpu_offset in CONFIG_PREEMPT
tile: ensure interrupts disabled for preempt_schedule_irq()
tile: change lock initalization in hardwall
tile: include: asm: use 'long long' instead of 'u64' for atomic64_t and its related functions
Commit 1400eb6 (MIPS: r4k,octeon,r2300: stack protector: change canary
per task) was merged in v3.11 and introduced assembly in the MIPS resume
functions to update the value of the current canary in
__stack_chk_guard. However it used PTR_L resulting in a load of the
canary value, instead of PTR_LA to construct its address. The value is
intended to be random but is then treated as an address in the
subsequent LONG_S (store).
This was observed to cause a fault and panic:
CPU 0 Unable to handle kernel paging request at virtual address 139fea20, epc == 8000cc0c, ra == 8034f2a4
Oops[#1]:
...
$24 : 139fea20 1e1f7cb6
...
Call Trace:
[<8000cc0c>] resume+0xac/0x118
[<8034f2a4>] __schedule+0x5f8/0x78c
[<8034f4e0>] schedule_preempt_disabled+0x20/0x2c
[<80348eec>] rest_init+0x74/0x84
[<804dc990>] start_kernel+0x43c/0x454
Code: 3c18804b 8f184030 8cb901f8 <af190000> 00c0e021 8cb002f0 8cb102f4 8cb202f8 8cb302fc
This can also be forced by modifying
arch/mips/include/asm/stackprotector.h so that the default
__stack_chk_guard value is more likely to be a bad (or unaligned)
pointer.
Fix it to use PTR_LA instead, to load the address of the canary value,
which the LONG_S can then use to write into it.
Reported-by: bobjones (via #mipslinux on IRC)
Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Gregory Fong <gregory.0xf0@gmail.com>
Cc: linux-mips@linux-mips.org
Cc: stable@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/6026/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Pull s390 fixes from Martin Schwidefsky:
"A couple of bux fixes, notable are the regression with ptrace vs
restarting system calls and the patch for kdump to be able to copy
from virtual memory"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
s390: fix system call restart after inferior call
s390: Allow vmalloc target buffers for copy_from_oldmem()
s390/sclp: properly detect line mode console
s390/kprobes: add exrl to list of prohibited opcodes
s390/3270: fix return value check in tty3270_resize_work()
MMCONFIG
Revert "x86/PCI: MMCONFIG: Check earlier for MMCONFIG region at address zero"
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)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=LqLn
-----END PGP SIGNATURE-----
Merge tag 'pci-v3.12-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci
Pull PCI fix from Bjorn Helgaas:
"We merged what was intended to be an MMCONFIG cleanup, but in fact,
for systems without _CBA (which is almost everything), it broke
extended config space for domain 0 and it broke all config space for
other domains.
This reverts the change"
* tag 'pci-v3.12-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci:
Revert "x86/PCI: MMCONFIG: Check earlier for MMCONFIG region at address zero"
This reverts commit 07f9b61c39.
07f9b61c was intended to be a cleanup that didn't change anything, but in
fact, for systems without _CBA (which is almost everything), it broke
extended config space for domain 0 and all config space for other domains.
Reference: http://lkml.kernel.org/r/20131004011806.GE20450@dangermouse.emea.sgi.com
Reported-by: Hedi Berriche <hedi@sgi.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Commit ebd97be635 ('PCI: remove ARCH_SUPPORTS_MSI kconfig option')
removed the ARCH_SUPPORTS_MSI option which architectures could select
to indicate that they support MSI. Now, all architectures are supposed
to build fine when MSI support is enabled: instead of having the
architecture tell *when* MSI support can be used, it's up to the
architecture code to ensure that MSI support can be enabled.
On x86, commit ebd97be635 removed the following line:
select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
Which meant that MSI support was only available when the local APIC
and I/O APIC were enabled. While this is always true on SMP or x86-64,
it is not necessarily the case on i386 !SMP.
The below patch makes sure that the local APIC and I/O APIC support is
always enabled when MSI support is enabled. To do so, it:
* Ensures the X86_UP_APIC option is not visible when PCI_MSI is
enabled. This is the option that allows, on UP machines, to enable
or not the APIC support. It is already not visible on SMP systems,
or x86-64 systems, for example. We're simply also making it
invisible on i386 MSI systems.
* Ensures that the X86_LOCAL_APIC and X86_IO_APIC options are 'y'
when PCI_MSI is enabled.
Notice that this change requires a change in drivers/iommu/Kconfig to
avoid a recursive Kconfig dependencey. The AMD_IOMMU option selects
PCI_MSI, but was depending on X86_IO_APIC. This dependency is no
longer needed: as soon as PCI_MSI is selected, the presence of
X86_IO_APIC is guaranteed. Moreover, the AMD_IOMMU already depended on
X86_64, which already guaranteed that X86_IO_APIC was enabled, so this
dependency was anyway redundant.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: http://lkml.kernel.org/r/1380794354-9079-1-git-send-email-thomas.petazzoni@free-electrons.com
Reported-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Pull MIPS fixes from Ralf Baechle:
"Two small fixes for 3.12 only this week. I have a few more fixes
pending but those are conceptually more complex so will have to wait
for a bit longer"
* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
MIPS: Fix forgotten preempt_enable() when CPU has inclusive pcaches
MIPS: Alchemy: MTX-1: fix incorrect placement of __initdata tag
Pull x86 fixes from Ingo Molnar:
"Two simplefb fixes"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/simplefb: Mark framebuffer mem-resources as IORESOURCE_BUSY to avoid bootup warning
x86/simplefb: Fix overflow causing bogus fall-back
Haswell always give an extra LBR record after every TSX abort.
Suppress the extra record.
This only works when the abort is visible in the LBR
If the original abort has already left the 16 LBR entries
the extra entry will will stay.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1379688044-14173-7-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In the PEBS handler report the transaction flags using the new
generic transaction flags facility. Most of them come from
the "tsx_tuning" field in PEBSv2, but the abort code is derived
from the RAX register reported in the PEBS record.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1379688044-14173-3-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently the cap_user_time_zero capability has different tests than
cap_user_time; even though they expose the exact same data.
Switch from CONSTANT && NONSTOP to sched_clock_stable to also deal
with multi cabinet machines and drop the tsc_disabled() check.. non of
this will work sanely without tsc anyway.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-nmgn0j0muo1r4c94vlfh23xy@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull ARC fix from Vineet Gupta:
"Chrisitian found/fixed issue with SA_SIGINFO based signal handler
corrupting the user space registers post after signal handling"
* 'for-curr' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
ARC: Fix signal frame management for SA_SIGINFO
Pull powerpc fixes from Ben Herrenschmidt:
"Here are a few powerpc fixes, all aimed at -stable, found in part
thanks to the ramping up of a major distro testing and in part thanks
to the LE guys hitting all sort interesting corner cases.
The most scary are probably the register clobber issues in
csum_partial_copy_generic(), especially since Anton even had a test
case for that thing, which didn't manage to hit the bugs :-)
Another highlight is that memory hotplug should work again with these
fixes.
Oh and the vio modalias one is worse than the cset implies as it
upsets distro installers, so I've been told at least, which is why I'm
shooting it to stable"
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
powerpc/tm: Switch out userspace PPR and DSCR sooner
powerpc/tm: Turn interrupts hard off in tm_reclaim()
powerpc/perf: Fix handling of FAB events
powerpc/vio: Fix modalias_show return values
powerpc/iommu: Use GFP_KERNEL instead of GFP_ATOMIC in iommu_init_table()
powerpc/sysfs: Disable writing to PURR in guest mode
powerpc: Restore registers on error exit from csum_partial_copy_generic()
powerpc: Fix parameter clobber in csum_partial_copy_generic()
powerpc: Fix memory hotplug with sparse vmemmap
When we do a treclaim or trecheckpoint we end up running with userspace
PPR and DSCR values. Currently we don't do anything special to avoid
running with user values which could cause a severe performance
degradation.
This patch moves the PPR and DSCR save and restore around treclaim and
trecheckpoint so that we run with user values for a much shorter period.
More care is taken with the PPR as it's impact is greater than the DSCR.
This is similar to user exceptions, where we run HTM_MEDIUM early to
ensure that we don't run with a userspace PPR values in the kernel.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Cc: <stable@vger.kernel.org> # 3.9+
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We can't take IRQs in tm_reclaim as we might have a bogus r13 and r1.
This turns IRQs hard off in this function.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Cc: <stable@vger.kernel.org> # 3.9+
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit 4df4899 "Add power8 EBB support" included a bug in the handling
of the FAB_CRESP_MATCH and FAB_TYPE_MATCH fields.
These values are pulled out of the event code using EVENT_THR_CTL_SHIFT,
however we were then or'ing that value directly into MMCR1.
This meant we were failing to set the FAB fields correctly, and also
potentially corrupting the value for PMC4SEL. Leading to no counts for
the FAB events and incorrect counts for PMC4.
The fix is simply to shift left the FAB value correctly before or'ing it
with MMCR1.
Reported-by: Sooraj Ravindran Nair <soonair3@in.ibm.com>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
modalias_show() should return an empty string on error, not -ENODEV.
This causes the following false and annoying error:
> find /sys/devices -name modalias -print0 | xargs -0 cat >/dev/null
cat: /sys/devices/vio/4000/modalias: No such device
cat: /sys/devices/vio/4001/modalias: No such device
cat: /sys/devices/vio/4002/modalias: No such device
cat: /sys/devices/vio/4004/modalias: No such device
cat: /sys/devices/vio/modalias: No such device
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org>
