apic_noop is used to provide dummy apic functions. It's installed
when the CPU has no APIC or when the APIC is disabled on the kernel
command line.
The apic_noop implementation of apic_write() warns when the CPU has
an APIC or when the APIC is not disabled.
That's bogus. The warning should only happen when the CPU has an
APIC _AND_ the APIC is not disabled. apic_noop.apic_read() has the
correct check.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: <stable@kernel.org> # in <= .32 this typo resides in native_apic_write_dummy()
LKML-Reference: <alpine.LFD.2.00.0912071255420.3089@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When we enter in irq, two things can happen to preserve the link
to the previous frame pointer:
- If we were in an irq already, we don't switch to the irq stack
as we are inside. We just need to save the previous frame
pointer and to link the new one to the previous.
- Otherwise we need another level of indirection. We enter the irq with
the previous stack. We save the previous bp inside and make bp
pointing to its saved address. Then we switch to the irq stack and
push bp another time but to the new stack. This makes two levels to
dereference instead of one.
In the second case, the current stacktrace code omits the second level
and loses the frame pointer accuracy. The stack that follows will then
be considered as unreliable.
Handling that makes the perf callchain happier.
Before:
43.94% [k] _raw_read_lock
|
--- _read_lock
|
|--60.53%-- send_sigio
| __kill_fasync
| kill_fasync
| evdev_pass_event
| evdev_event
| input_pass_event
| input_handle_event
| input_event
| synaptics_process_byte
| psmouse_handle_byte
| psmouse_interrupt
| serio_interrupt
| i8042_interrupt
| handle_IRQ_event
| handle_edge_irq
| handle_irq
| __irqentry_text_start
| ret_from_intr
| |
| |--30.43%-- __select
| |
| |--17.39%-- 0x454f15
| |
| |--13.04%-- __read
| |
| |--13.04%-- vread_hpet
| |
| |--13.04%-- _xcb_lock_io
| |
| --13.04%-- 0x7f630878ce8
After:
50.00% [k] _raw_read_lock
|
--- _read_lock
|
|--98.97%-- send_sigio
| __kill_fasync
| kill_fasync
| evdev_pass_event
| evdev_event
| input_pass_event
| input_handle_event
| input_event
| |
| |--96.88%-- synaptics_process_byte
| | psmouse_handle_byte
| | psmouse_interrupt
| | serio_interrupt
| | i8042_interrupt
| | handle_IRQ_event
| | handle_edge_irq
| | handle_irq
| | __irqentry_text_start
| | ret_from_intr
| | |
| | |--39.78%-- __const_udelay
| | | |
| | | |--91.89%-- ath5k_hw_register_timeout
| | | | ath5k_hw_noise_floor_calibration
| | | | ath5k_hw_reset
| | | | ath5k_reset
| | | | ath5k_config
| | | | ieee80211_hw_config
| | | | |
| | | | |--88.24%-- ieee80211_scan_work
| | | | | worker_thread
| | | | | kthread
| | | | | child_rip
| | | | |
| | | | --11.76%-- ieee80211_scan_completed
| | | | ieee80211_scan_work
| | | | worker_thread
| | | | kthread
| | | | child_rip
| | | |
| | | --8.11%-- ath5k_hw_noise_floor_calibration
| | | ath5k_hw_reset
| | | ath5k_reset
| | | ath5k_config
Note: This does not only affect perf events but also x86-64
stacktraces. They were considered as unreliable once we quit
the irq stack frame.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
While dumping a stacktrace, the end of the exception stack won't link
the frame pointer to the previous stack.
The interrupted stack will then be considered as unreliable and ignored
by perf, as the frame pointer is unreliable itself.
This happens because we overwrite the frame pointer that links to the
interrupted frame with the address of the exception stack. This is
done in order to reserve space inside.
But rbp has been chosen here only because it is not a scratch register,
so that the address of the exception stack remains in rbp after calling
do_debug(), we can then release the exception stack space without the
need to retrieve its address again.
But we can pick another non-scratch register to do that, so that we
preserve the link to the interrupted stack frame in the stacktraces.
Just randomly choose r12. Every registers are saved just before and
restored just after calling do_debug(). And r12 is not used in the
middle, which makes it a perfect candidate.
Example: perf record -g -a -c 1 -f -e mem:$(tasklist_lock_addr):rw
Before:
44.18% [k] _raw_read_lock
|
|
--- |--6.31%-- waitid
|
|--4.26%-- writev
|
|--3.63%-- __select
|
|--3.15%-- __waitpid
| |
| |--28.57%-- 0x8b52e00000139f
| |
| |--28.57%-- 0x8b52e0000013c6
| |
| |--14.29%-- 0x7fde786dc000
| |
| |--14.29%-- 0x62696c2f7273752f
| |
| --14.29%-- 0x1ea9df800000000
|
|--3.00%-- __poll
After:
43.94% [k] _raw_read_lock
|
--- _read_lock
|
|--60.53%-- send_sigio
| __kill_fasync
| kill_fasync
| evdev_pass_event
| evdev_event
| input_pass_event
| input_handle_event
| input_event
| synaptics_process_byte
| psmouse_handle_byte
| psmouse_interrupt
| serio_interrupt
| i8042_interrupt
| handle_IRQ_event
| handle_edge_irq
| handle_irq
| __irqentry_text_start
| ret_from_intr
| |
| |--30.43%-- __select
| |
| |--17.39%-- 0x454f15
| |
| |--13.04%-- __read
| |
| |--13.04%-- vread_hpet
| |
| |--13.04%-- _xcb_lock_io
| |
| --13.04%-- 0x7f630878ce87
Note: it does not only affect perf events but also other stacktraces in
x86-64. They were considered as unreliable once we quit the debug
stack frame.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Dumping the callchains from breakpoint events with perf gives strange
results:
3.75% perf [kernel] [k] _raw_read_unlock
|
--- _raw_read_unlock
perf_callchain
perf_prepare_sample
__perf_event_overflow
perf_swevent_overflow
perf_swevent_add
perf_bp_event
hw_breakpoint_exceptions_notify
notifier_call_chain
__atomic_notifier_call_chain
atomic_notifier_call_chain
notify_die
do_debug
debug
munmap
We are infected with all the debug stack. Like the nmi stack, the debug
stack is undesired as it is part of the profiling path, not helpful for
the user.
Ignore it.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>
struct perf_event::event callback was called when a breakpoint
triggers. But this is a rather opaque callback, pretty
tied-only to the breakpoint API and not really integrated into perf
as it triggers even when we don't overflow.
We prefer to use overflow_handler() as it fits into the perf events
rules, being called only when we overflow.
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>
Drop the callback and task parameters from modify_user_hw_breakpoint().
For now we have no user that need to modify a breakpoint to the point
of changing its handler or its task context.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>
* 'x86-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: Limit number of per cpu TSC sync messages
x86: dumpstack, 64-bit: Disable preemption when walking the IRQ/exception stacks
x86: dumpstack: Clean up the x86_stack_ids[][] initalization and other details
x86, cpu: mv display_cacheinfo -> cpu_detect_cache_sizes
x86: Suppress stack overrun message for init_task
x86: Fix cpu_devs[] initialization in early_cpu_init()
x86: Remove CPU cache size output for non-Intel too
x86: Minimise printk spew from per-vendor init code
x86: Remove the CPU cache size printk's
cpumask: Avoid cpumask_t in arch/x86/kernel/apic/nmi.c
x86: Make sure we also print a Code: line for show_regs()
* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, msr, cpumask: Use struct cpumask rather than the deprecated cpumask_t
x86, cpuid: Simplify the code in cpuid_open
x86, cpuid: Remove the bkl from cpuid_open()
x86, msr: Remove the bkl from msr_open()
x86: AMD Geode LX optimizations
x86, msr: Unify rdmsr_on_cpus/wrmsr_on_cpus
* 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: Fix a section mismatch in arch/x86/kernel/setup.c
x86: Fixup last users of irq_chip->typename
x86: Remove BKL from apm_32
x86: Remove BKL from microcode
x86: use kernel_stack_pointer() in kprobes.c
x86: use kernel_stack_pointer() in kgdb.c
x86: use kernel_stack_pointer() in dumpstack.c
x86: use kernel_stack_pointer() in process_32.c
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
include/linux/compiler-gcc4.h: Fix build bug - gcc-4.0.2 doesn't understand __builtin_object_size
x86/alternatives: No need for alternatives-asm.h to re-invent stuff already in asm.h
x86/alternatives: Check replacementlen <= instrlen at build time
x86, 64-bit: Set data segments to null after switching to 64-bit mode
x86: Clean up the loadsegment() macro
x86: Optimize loadsegment()
x86: Add missing might_fault() checks to copy_{to,from}_user()
x86-64: __copy_from_user_inatomic() adjustments
x86: Remove unused thread_return label from switch_to()
x86, 64-bit: Fix bstep_iret jump
x86: Don't use the strict copy checks when branch profiling is in use
x86, 64-bit: Move K8 B step iret fixup to fault entry asm
x86: Generate cmpxchg build failures
x86: Add a Kconfig option to turn the copy_from_user warnings into errors
x86: Turn the copy_from_user check into an (optional) compile time warning
x86: Use __builtin_memset and __builtin_memcpy for memset/memcpy
x86: Use __builtin_object_size() to validate the buffer size for copy_from_user()
* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
x86, apic: Enable lapic nmi watchdog on AMD Family 11h
x86: Remove unnecessary mdelay() from cpu_disable_common()
x86, ioapic: Document another case when level irq is seen as an edge
x86, ioapic: Fix the EOI register detection mechanism
x86, io-apic: Move the effort of clearing remoteIRR explicitly before migrating the irq
x86: SGI UV: Map low MMR ranges
x86: apic: Print out SRAT table APIC id in hex
x86: Re-get cfg_new in case reuse/move irq_desc
x86: apic: Remove not needed #ifdef
x86: io-apic: IO-APIC MMIO should not fail on resource insertion
x86: Remove asm/apicnum.h
x86: apic: Do not use stacked physid_mask_t
x86, apic: Get rid of apicid_to_cpu_present assign on 64-bit
x86, ioapic: Use snrpintf while set names for IO-APIC resourses
x86, apic: Use PAGE_SIZE instead of numbers
x86: Remove local_irq_enable()/local_irq_disable() in fixup_irqs()
x86: Use EOI register in io-apic on intel platforms
x86: Force irq complete move during cpu offline
x86: Remove move_cleanup_count from irq_cfg
x86, intr-remap: Avoid irq_chip mask/unmask in fixup_irqs() for intr-remapping
...
* 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (40 commits)
tracing: Separate raw syscall from syscall tracer
ring-buffer-benchmark: Add parameters to set produce/consumer priorities
tracing, function tracer: Clean up strstrip() usage
ring-buffer benchmark: Run producer/consumer threads at nice +19
tracing: Remove the stale include/trace/power.h
tracing: Only print objcopy version warning once from recordmcount
tracing: Prevent build warning: 'ftrace_graph_buf' defined but not used
ring-buffer: Move access to commit_page up into function used
tracing: do not disable interrupts for trace_clock_local
ring-buffer: Add multiple iterations between benchmark timestamps
kprobes: Sanitize struct kretprobe_instance allocations
tracing: Fix to use __always_unused attribute
compiler: Introduce __always_unused
tracing: Exit with error if a weak function is used in recordmcount.pl
tracing: Move conditional into update_funcs() in recordmcount.pl
tracing: Add regex for weak functions in recordmcount.pl
tracing: Move mcount section search to front of loop in recordmcount.pl
tracing: Fix objcopy revision check in recordmcount.pl
tracing: Check absolute path of input file in recordmcount.pl
tracing: Correct the check for number of arguments in recordmcount.pl
...
* 'core-iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (63 commits)
x86, Calgary IOMMU quirk: Find nearest matching Calgary while walking up the PCI tree
x86/amd-iommu: Remove amd_iommu_pd_table
x86/amd-iommu: Move reset_iommu_command_buffer out of locked code
x86/amd-iommu: Cleanup DTE flushing code
x86/amd-iommu: Introduce iommu_flush_device() function
x86/amd-iommu: Cleanup attach/detach_device code
x86/amd-iommu: Keep devices per domain in a list
x86/amd-iommu: Add device bind reference counting
x86/amd-iommu: Use dev->arch->iommu to store iommu related information
x86/amd-iommu: Remove support for domain sharing
x86/amd-iommu: Rearrange dma_ops related functions
x86/amd-iommu: Move some pte allocation functions in the right section
x86/amd-iommu: Remove iommu parameter from dma_ops_domain_alloc
x86/amd-iommu: Use get_device_id and check_device where appropriate
x86/amd-iommu: Move find_protection_domain to helper functions
x86/amd-iommu: Simplify get_device_resources()
x86/amd-iommu: Let domain_for_device handle aliases
x86/amd-iommu: Remove iommu specific handling from dma_ops path
x86/amd-iommu: Remove iommu parameter from __(un)map_single
x86/amd-iommu: Make alloc_new_range aware of multiple IOMMUs
...
Bug reporter noted their system with an ASUS P4S800 motherboard would
hang when rebooting unless reboot=b was specified. Their dmidecode
didn't contain descriptive System Information for Manufacturer or
Product Name, so I used their Base Board Information to create a
reboot quirk patch. The bug reporter confirmed this patch resolves
the reboot hang.
Handle 0x0001, DMI type 1, 25 bytes
System Information
Manufacturer: System Manufacturer
Product Name: System Name
Version: System Version
Serial Number: SYS-1234567890
UUID: E0BFCD8B-7948-D911-A953-E486B4EEB67F
Wake-up Type: Power Switch
Handle 0x0002, DMI type 2, 8 bytes
Base Board Information
Manufacturer: ASUSTeK Computer INC.
Product Name: P4S800
Version: REV 1.xx
Serial Number: xxxxxxxxxxx
BugLink: http://bugs.launchpad.net/bugs/366682
ASUS P4S800 will hang when rebooting unless reboot=b is specified.
Add a quirk to reboot through the bios.
Signed-off-by: Leann Ogasawara <leann.ogasawara@canonical.com>
LKML-Reference: <1259972107.4629.275.camel@emiko>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: <stable@kernel.org>
Commit ae21ee65e8 "PCI: acs p2p upsteram
forwarding enabling" doesn't actually enable ACS.
Add a function to pci core to allow an IOMMU to request that ACS
be enabled. The existing mechanism of using iommu_found() in the pci
core to know when ACS should be enabled doesn't actually work due to
initialization order; iommu has only been detected not initialized.
Have Intel and AMD IOMMUs request ACS, and Xen does as well during early
init of dom0.
Cc: Allen Kay <allen.m.kay@intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
The x86 lapic nmi watchdog does not recognize AMD Family 11h,
resulting in:
NMI watchdog: CPU not supported
As far as I can see from available documentation (the BKDM),
family 11h looks identical to family 10h as far as the PMU
is concerned.
Extending the check to accept family 11h results in:
Testing NMI watchdog ... OK.
I've been running with this change on a Turion X2 Ultra ZM-82
laptop for a couple of weeks now without problems.
Signed-off-by: Mikael Pettersson <mikpe@it.uu.se>
Cc: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Cc: <stable@kernel.org>
LKML-Reference: <19223.53436.931768.278021@pilspetsen.it.uu.se>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
pci_get_device will increase the ref count of found device.
Although we're going to reset soon, we should use pci_dev_put
to decrease the ref count for consistency.
Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <1259838400-23833-1-git-send-email-dfeng@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
On a multi-node x3950M2 system, there's a slight oddity in the
PCI device tree for all secondary nodes:
30:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1)
\-33:00.0 PCI bridge: IBM CalIOC2 PCI-E Root Port (rev 01)
\-34:00.0 RAID bus controller: LSI Logic / Symbios Logic MegaRAID SAS 1078 (rev 04)
...as compared to the primary node:
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1)
\-01:00.0 VGA compatible controller: ATI Technologies Inc ES1000 (rev 02)
03:00.0 PCI bridge: IBM CalIOC2 PCI-E Root Port (rev 01)
\-04:00.0 RAID bus controller: LSI Logic / Symbios Logic MegaRAID SAS 1078 (rev 04)
In both nodes, the LSI RAID controller hangs off a CalIOC2
device, but on the secondary nodes, the BIOS hides the VGA
device and substitutes the device tree ending with the disk
controller.
It would seem that Calgary devices don't necessarily appear at
the top of the PCI tree, which means that the current code to
find the Calgary IOMMU that goes with a particular device is
buggy.
Rather than walk all the way to the top of the PCI
device tree and try to match bus number with Calgary descriptor,
the code needs to examine each parent of the particular device;
if it encounters a Calgary with a matching bus number, simply
use that.
Otherwise, we BUG() when the bus number of the Calgary doesn't
match the bus number of whatever's at the top of the device tree.
Extra note: This patch appears to work correctly for the x3950
that came before the x3950 M2.
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Acked-by: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Jon D. Mason <jdmason@kudzu.us>
Cc: Corinna Schultz <coschult@us.ibm.com>
Cc: <stable@kernel.org>
LKML-Reference: <20091202230556.GG10295@tux1.beaverton.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Even it is in error path unlikely taken, add_timer_on() at
CPU_DOWN_FAILED* needs to be skipped if mce_timer is disabled.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: <stable@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
fixup_irqs() already has a mdelay(). Remove the extra and
unnecessary mdelay() from cpu_disable_common().
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Cc: ebiederm@xmission.com
Cc: garyhade@us.ibm.com
LKML-Reference: <20091201233335.232177348@sbs-t61.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In the case when cpu goes offline, fixup_irqs() will forward any
unhandled interrupt on the offlined cpu to the new cpu
destination that is handling the corresponding interrupt. This
interrupt forwarding is done via IPI's. Hence, in this case also
level-triggered io-apic interrupt will be seen as an edge
interrupt in the cpu's APIC IRR.
Document this scenario in the code which handles this case by doing
an explicit EOI to the io-apic to clear remote IRR of the io-apic RTE.
Requested-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Cc: ebiederm@xmission.com
Cc: garyhade@us.ibm.com
LKML-Reference: <20091201233335.143970505@sbs-t61.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Maciej W. Rozycki reported:
> 82093AA I/O APIC has its version set to 0x11 and it
> does not support the EOI register. Similarly I/O APICs
> integrated into the 82379AB south bridge and the 82374EB/SB
> EISA component.
IO-APIC versions below 0x20 don't support EOI register.
Some of the Intel ICH Specs (ICH2 to ICH5) documents the io-apic
version as 0x2. This is an error with documentation and these
ICH chips use io-apic's of version 0x20 and indeed has a working
EOI register for the io-apic.
Fix the EOI register detection mechanism to check for version
0x20 and beyond.
And also, a platform can potentially have io-apic's with
different versions. Make the EOI register check per io-apic.
Reported-by: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: ebiederm@xmission.com
Cc: garyhade@us.ibm.com
LKML-Reference: <20091201233335.065361533@sbs-t61.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When the level-triggered interrupt is seen as an edge interrupt,
we try to clear the remoteIRR explicitly (using either an
io-apic eoi register when present or through the idea of
changing trigger mode of the io-apic RTE to edge and then back
to level). But this explicit try also needs to happen before we
try to migrate the irq. Otherwise irq migration attempt will
fail anyhow, as it postpones the irq migration to a later
attempt when it sees the remoteIRR in the io-apic RTE still set.
Signed-off-by: "Maciej W. Rozycki" <macro@linux-mips.org>
Reviewed-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: ebiederm@xmission.com
Cc: garyhade@us.ibm.com
LKML-Reference: <20091201233334.975416130@sbs-t61.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When we disable a breakpoint through dr7, we unregister it right
away, making us lose track of its corresponding address
register value.
It means that the following sequence would be unsupported:
- set address in dr0
- enable it through dr7
- disable it through dr7
- enable it through dr7
because we lost the address register value when we disabled the
breakpoint.
Don't unregister the disabled breakpoints but rather disable
them.
Reported-by: "K.Prasad" <prasad@linux.vnet.ibm.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1259735536-9236-1-git-send-regression-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The semantics the PAT code expect of is_untracked_pat_range() is "is
this range completely contained inside the untracked region." This
means that checkin 8a27138924 was
technically wrong, because the implementation needlessly confusing.
The sane interface is for it to take a semiclosed range like just
about everything else (as evidenced by the sheer number of "- 1"'s
removed by that patch) so change the actual implementation to match.
Reported-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jack Steiner <steiner@sgi.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
LKML-Reference: <20091119202341.GA4420@sgi.com>
copy_edd() should be __init.
warning msg:
WARNING: vmlinux.o(.text+0x7759): Section mismatch in reference from the
function copy_edd() to the variable .init.data:boot_params
The function copy_edd() references
the variable __initdata boot_params.
This is often because copy_edd lacks a __initdata
annotation or the annotation of boot_params is wrong.
Signed-off-by: ZhenwenXu <helight.xu@gmail.com>
LKML-Reference: <4B139F8F.4000907@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Andrew complained rightly that the WARN_ON in hpet_next_event() is
confusing and the code comment not really helpful.
Change it to WARN_ONCE and print the reason in clear text. Change the
comment to explain what kind of hardware wreckage we deal with.
Pointed-out-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com>
The data that was stored in this table is now available in
dev->archdata.iommu. So this table is not longer necessary.
This patch removes the remaining uses of that variable and
removes it from the code.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch removes the ugly contruct where the
iommu->lock must be released while before calling the
reset_iommu_command_buffer function.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch cleans up the code to flush device table entries
in the IOMMU. With this chance the driver can get rid of the
iommu_queue_inv_dev_entry() function.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch adds a function to flush a DTE entry for a given
struct device and replaces iommu_queue_inv_dev_entry calls
with this function where appropriate.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch cleans up the attach_device and detach_device
paths and fixes reference counting while at it.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch introduces a list to each protection domain which
keeps all devices associated with the domain. This can be
used later to optimize certain functions and to completly
remove the amd_iommu_pd_table.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch adds a reference count to each device to count
how often the device was bound to that domain. This is
important for single devices that act as an alias for a
number of others. These devices must stay bound to their
domains until all devices that alias to it are unbound from
the same domain.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch changes IOMMU code to use dev->archdata->iommu to
store information about the alias device and the domain the
device is attached to.
This allows the driver to get rid of the amd_iommu_pd_table
in the future.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch makes device isolation mandatory and removes
support for the amd_iommu=share option. This simplifies the
code in several places.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch rearranges two dma_ops related functions so that
their forward declarations are not longer necessary.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch moves alloc_pte() and fetch_pte() into the page
table handling code section so that the forward declarations
for them could be removed.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The logic of these two functions is reimplemented (at least
in parts) in places in the code. This patch removes these
code duplications and uses the functions instead. As a side
effect it moves check_device() to the helper function code
section.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This is a helper function and when its placed in the helper
function section we can remove its forward declaration.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
With the previous changes the get_device_resources function
can be simplified even more. The only important information
for the callers is the protection domain.
This patch renames the function to get_domain() and let it
only return the protection domain for a device.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
If there is no domain associated to a device yet and the
device has an alias device which already has a domain, the
original device needs to have the same domain as the alias
device.
This patch changes domain_for_device to handle this
situation and directly assigns the alias device domain to
the device in this situation.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
With the prior changes this parameter is not longer
required. This patch removes it from the function and all
callers.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Since the assumption that an dma_ops domain is only bound to
one IOMMU was given up we need to make alloc_new_range aware
of it.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Every call-place of get_device_resources calls check_device
before it. So call it from get_device_resources directly and
simplify the code.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The check_device logic needs to include the dma_supported
checks to be really sure. Merge the dma_supported logic into
check_device and use it to implement dma_supported.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The non-present cache flag was IOMMU local until now which
doesn't make sense. Make this a global flag so we can remove
the lase user of 'struct iommu' in the map/unmap path.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch reimplements the function
flush_all_domains_on_iommu to use the global protection
domain list.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch reimplementes the amd_iommu_flush_all_domains
function to use the global protection domain list instead
of flushing every domain on every IOMMU.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch adds code to keep a global list of all protection
domains. This allows to simplify the resume code.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This iommu_flush_tlb_pde function does essentially the same.
So the iommu_flush_domain function is redundant and can be
removed.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch extends the iommu_flush_pages function to flush
the TLB entries on all IOMMUs the domain has devices on.
This basically gives up the former assumption that dma_ops
domains are only bound to one IOMMU in the system.
For dma_ops domains this is still true but not for
IOMMU-API managed domains. Giving this assumption up for
dma_ops domains too allows code simplification.
Further it splits out the main logic into a generic function
which can be used by iommu_flush_tlb too.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch adds a function to the AMD IOMMU driver which
completes all queued commands an all IOMMUs a specific
domain has devices attached on. This is required in a later
patch when per-domain flushing is implemented.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch adds reference counting for protection domains
per IOMMU. This allows a smarter TLB flushing strategy.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch adds an index field to struct amd_iommu which can
be used to lookup it up in an array. This index will be used
in struct protection_domain to keep track which protection
domain has devices behind which IOMMU.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch updates the copyright headers in the relevant AMD
IOMMU driver files to match the date of the latest changes.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch moves all function declarations which are only
used inside the driver code to a seperate header file.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
In-kernel user breakpoints are created using functions in which
we pass breakpoint parameters as individual variables: address,
length and type.
Although it fits well for x86, this just does not scale across
archictectures that may support this api later as these may have
more or different needs. Pass in a perf_event_attr structure
instead because it is meant to evolve as much as possible into
a generic hardware breakpoint parameter structure.
Reported-by: K.Prasad <prasad@linux.vnet.ibm.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1259294154-5197-1-git-send-regression-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Explicitly mmap the UV chipset MMR address ranges used to
access blade-local registers. Although these same MMRs are also
mmaped at higher addresses, the low range is more
convenient when accessing blade-local registers.
The low range addresses always alias to the local blade
regardless of the blade id.
Signed-off-by: Jack Steiner <steiner@sgi.com>
LKML-Reference: <20091125162018.GA25445@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This prevents kernel threads from inheriting non-null segment
selectors, and causing optimizations in __switch_to() to be
ineffective.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Cc: Tim Blechmann <tim@klingt.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Jan Beulich <JBeulich@novell.com>
LKML-Reference: <1259165856-3512-1-git-send-email-brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The mce_disable_cpu() and mce_reenable_cpu() are called only
from mce_cpu_callback() which is marked as __cpuinit.
So these functions can be __cpuinit too.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Andi Kleen <ak@linux.intel.com>
LKML-Reference: <4B0E3C4E.4090809@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Limit the number of per cpu TSC sync messages by only printing
to the console if an error occurs, otherwise print as a DEBUG
message.
The info message "Skipping synchronization ..." is only printed
after the last cpu has booted.
Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: Randy Dunlap <rdunlap@xenotime.net>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20091118002222.181053000@alcatraz.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When we schedule out a breakpoint from the cpu, we also
incidentally remove the "Global exact breakpoint" flag from the
breakpoint control register. It makes us losing the fine grained
precision about the origin of the instructions that may trigger
breakpoint exceptions for the other breakpoints running in this
cpu.
Reported-by: Prasad <prasad@linux.vnet.ibm.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1259211878-6013-1-git-send-regression-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This simplifies the error handling when we create a breakpoint.
We don't need to check the NULL return value corner case anymore
since we have improved perf_event_create_kernel_counter() to
always return an error code in the failure case.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Prasad <prasad@linux.vnet.ibm.com>
LKML-Reference: <1259210142-5714-3-git-send-regression-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Make the initialization more readable, plus tidy up a few small
visual details as well.
No change in functionality.
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Percpu symbols now occupy the same namespace as other global
symbols and as such short global symbols without subsystem
prefix tend to collide with local variables. dr7 percpu
variable used by x86 was hit by this. Rename it to cpu_dr7.
The rename also makes it more consistent with its fellow
cpu_debugreg percpu variable.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <20091125115856.GA17856@elte.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
iommu=soft boot option forces the kernel to use swiotlb.
( This has the side-effect of enabling the swiotlb over the
GART if this boot option is provided. This is the desired
behavior of the swiotlb boot option and works like that
for all other hw-IOMMU drivers. )
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: yinghai@kernel.org
LKML-Reference: <20091125084611O.fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The existing interface only has a pre-order callback. This change
adds an additional parameter for a post-order callback which will
be more useful for bus scans. ACPICA BZ 779.
Also update the external calls to acpi_walk_namespace.
http://www.acpica.org/bugzilla/show_bug.cgi?id=779
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
In some cases we can coalesce MTRR entries after cleanup; this may
allow us to have more entries. As such, introduce clean_sort_range to
to sort and coaelsce the MTRR entries.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4B0BB9A3.5020908@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
This interface is mainly intended (and implemented) for ACPI _PPC BIOS
frequency limitations, but other cpufreq drivers can also use it for
similar use-cases.
Why is this needed:
Currently it's not obvious why cpufreq got limited.
People see cpufreq/scaling_max_freq reduced, but this could have
happened by:
- any userspace prog writing to scaling_max_freq
- thermal limitations
- hardware (_PPC in ACPI case) limitiations
Therefore export bios_limit (in kHz) to:
- Point the user that it's the BIOS (broken or intended) which limits
frequency
- Export it as a sysfs interface for userspace progs.
While this was a rarely used feature on laptops, there will appear
more and more server implemenations providing "Green IT" features like
allowing the service processor to limit the frequency. People want
to know about HW/BIOS frequency limitations.
All ACPI P-state driven cpufreq drivers are covered with this patch:
- powernow-k8
- powernow-k7
- acpi-cpufreq
Tested with a patched DSDT which limits the first two cores (_PPC returns 1)
via _PPC, exposed by bios_limit:
# echo 2200000 >cpu2/cpufreq/scaling_max_freq
# cat cpu*/cpufreq/scaling_max_freq
2600000
2600000
2200000
2200000
# #scaling_max_freq shows general user/thermal/BIOS limitations
# cat cpu*/cpufreq/bios_limit
2600000
2600000
2800000
2800000
# #bios_limit only shows the HW/BIOS limitation
CC: Pallipadi Venkatesh <venkatesh.pallipadi@intel.com>
CC: Len Brown <lenb@kernel.org>
CC: davej@codemonkey.org.uk
CC: linux@dominikbrodowski.net
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Dave Jones <davej@redhat.com>
The "unsigned int processor" everywhere confused Rusty, leading to
breakage when he passed in smp_processor_id().
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dave Jones <davej@redhat.com>
Set the transition latency to value smaller than CPUFREQ_ETERNAL so
governors other than "performance" work (like the "ondemand" one).
The value is found in "AMD PowerNow! Technology Platform Design Guide for
Embedded Processors" dated December 2000 (AMD doc #24267A). There is the
answer to one of FAQs on page 40 which states that suggested complete transition
period is 200 us.
Tested on K6-2+ CPU with K6-3 core (model 13, stepping 4).
Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl>
Signed-off-by: Dave Jones <davej@redhat.com>
It's still mugging the current process's cpumask, but as comment in
1ff6e97f1d says, it's not a trivial fix.
So, at least we can use a cpumask_var_t to do the Wrong Thing the Right Way :)
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
To: cpufreq@vger.kernel.org
Cc: Mark Langsdorf <mark.langsdorf@amd.com>
Signed-off-by: Dave Jones <davej@redhat.com>
In commit 0de51088e6, we introduced the
use of acpi-cpufreq on VIA/Centaur CPU's by removing a vendor check for
VENDOR_INTEL. However, as it turns out, at least the Nano CPU's also
need the PDC (processor driver capabilities) handshake in order to
activate the methods required for acpi-cpufreq.
Since arch_acpi_processor_init_pdc() contains another vendor check for
Intel, the PDC is not initialized on VIA CPU's. The resulting behavior
of a current mainline kernel on such systems is: acpi-cpufreq
loads and it indicates CPU frequency changes. However, the CPU stays at
a single frequency
This trivial patch ensures that init_intel_pdc() is called on Intel and
VIA/Centaur CPU's alike.
Signed-off-by: Harald Welte <HaraldWelte@viatech.com>
Signed-off-by: Dave Jones <davej@redhat.com>
The validate_event() was failing on valid event combinations. The
function was assuming that if x86_schedule_event() returned 0, it
meant error. But x86_schedule_event() returns the counter index and
0 is a perfectly valid value. An error is returned if the function
returns a negative value.
Furthermore, validate_event() was also failing for event groups
because the event->pmu was not set until after
hw_perf_event_init().
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: paulus@samba.org
Cc: perfmon2-devel@lists.sourceforge.net
Cc: eranian@gmail.com
LKML-Reference: <4b0bdf36.1818d00a.07cc.25ae@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
--
arch/x86/kernel/cpu/perf_event.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
Move the find_smp_config() call to before bootmem is initialized.
Use reserve_early() instead of reserve_bootmem() in it.
This simplifies the code, we only need to call find_smp_config()
once and can remove the now unneeded reserve parameter from
x86_init_mpparse::find_smp_config.
We thus also reduce x86's dependency on bootmem allocations.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4B0BB9F2.70907@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
- Change is_untracked_pat_range() to return bool.
- Clean up the initialization of is_untracked_pat_range() -- by default,
we simply point it at is_ISA_range() directly.
- Move is_untracked_pat_range to the end of struct x86_platform, since
it is the newest field.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Jack Steiner <steiner@sgi.com>
LKML-Reference: <20091119202341.GA4420@sgi.com>
display_cacheinfo() doesn't display anything anymore and it is used to
detect CPU cache sizes. Rename it accordingly.
Signed-off-by: Borislav Petkov <petkovbb@gmail.com>
LKML-Reference: <20091121130145.GA31357@liondog.tnic>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
GRU space is always mapped as WB in the page table. There is
no need to track the mappings in the PAT. This also eliminates
the "freeing invalid memtype" messages when the GRU space is
unmapped.
Signed-off-by: Jack Steiner <steiner@sgi.com>
LKML-Reference: <20091119202341.GA4420@sgi.com>
[ v2: fix build failure ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
irq_thermal_count is only being maintained when
X86_THERMAL_VECTOR, and both X86_THERMAL_VECTOR and
X86_MCE_THRESHOLD don't need extra wrapping in X86_MCE
conditionals.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Cc: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Yong Wang <yong.y.wang@intel.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <borislav.petkov@amd.com>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <4B06AFA902000078000211F8@vpn.id2.novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
A memory mapped register that affects the SGI UV Broadcast
Assist Unit's interrupt handling may sometimes be unintialized.
Remove the condition on its initialization, as that condition
can be randomly satisfied by a hardware reset.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Cc: <stable@kernel.org>
LKML-Reference: <E1NBGB9-0005nU-Dp@eag09.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Attribute authorship to developers of hw-breakpoint related
files.
Signed-off-by: K.Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20091123154713.GA5593@in.ibm.com>
[ v2: moved it to latest -tip ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For some devices the ACPI table may define unity map
requirements which must me met when the IOMMU is enabled. So
we need to attach devices to their domains as early as
possible so that these mappings are in place when needed.
This patch assigns the domains right after they are
allocated. Otherwise this can result in I/O page faults
before a driver binds to a device and BIOS is still using
it.
Cc: stable@kernel.org
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This function may be called on the resume path and can not
be dropped after booting.
Cc: stable@kernel.org
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Decreases perf overhead when function tracing is enabled,
by about 50%.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
CPU to node mapping is set via the following sequence:
1. numa_init_array(): Set up roundrobin from cpu to online node
2. init_cpu_to_node(): Set that according to apicid_to_node[]
according to srat only handle the node that
is online, and leave other cpu on node
without ram (aka not online) to still
roundrobin.
3. later call srat_detect_node for Intel/AMD, will use first_online
node or nearby node.
Problem is that setup_per_cpu_areas() is not called between 2 and 3,
the per_cpu for cpu on node with ram is on different node, and could
put that on node with two hops away.
So try to optimize this and add find_near_online_node() and call
init_cpu_to_node().
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: David Rientjes <rientjes@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <4B07A739.3030104@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
