When the frontend and the backend reside on the same domain, even if we
add pages to the m2p_override, these pages will never be returned by
mfn_to_pfn because the check "get_phys_to_machine(pfn) != mfn" will
always fail, so the pfn of the frontend will be returned instead
(resulting in a deadlock because the frontend pages are already locked).
INFO: task qemu-system-i38:1085 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
qemu-system-i38 D ffff8800cfc137c0 0 1085 1 0x00000000
ffff8800c47ed898 0000000000000282 ffff8800be4596b0 00000000000137c0
ffff8800c47edfd8 ffff8800c47ec010 00000000000137c0 00000000000137c0
ffff8800c47edfd8 00000000000137c0 ffffffff82213020 ffff8800be4596b0
Call Trace:
[<ffffffff81101ee0>] ? __lock_page+0x70/0x70
[<ffffffff81a0fdd9>] schedule+0x29/0x70
[<ffffffff81a0fe80>] io_schedule+0x60/0x80
[<ffffffff81101eee>] sleep_on_page+0xe/0x20
[<ffffffff81a0e1ca>] __wait_on_bit_lock+0x5a/0xc0
[<ffffffff81101ed7>] __lock_page+0x67/0x70
[<ffffffff8106f750>] ? autoremove_wake_function+0x40/0x40
[<ffffffff811867e6>] ? bio_add_page+0x36/0x40
[<ffffffff8110b692>] set_page_dirty_lock+0x52/0x60
[<ffffffff81186021>] bio_set_pages_dirty+0x51/0x70
[<ffffffff8118c6b4>] do_blockdev_direct_IO+0xb24/0xeb0
[<ffffffff811e71a0>] ? ext3_get_blocks_handle+0xe00/0xe00
[<ffffffff8118ca95>] __blockdev_direct_IO+0x55/0x60
[<ffffffff811e71a0>] ? ext3_get_blocks_handle+0xe00/0xe00
[<ffffffff811e91c8>] ext3_direct_IO+0xf8/0x390
[<ffffffff811e71a0>] ? ext3_get_blocks_handle+0xe00/0xe00
[<ffffffff81004b60>] ? xen_mc_flush+0xb0/0x1b0
[<ffffffff81104027>] generic_file_aio_read+0x737/0x780
[<ffffffff813bedeb>] ? gnttab_map_refs+0x15b/0x1e0
[<ffffffff811038f0>] ? find_get_pages+0x150/0x150
[<ffffffff8119736c>] aio_rw_vect_retry+0x7c/0x1d0
[<ffffffff811972f0>] ? lookup_ioctx+0x90/0x90
[<ffffffff81198856>] aio_run_iocb+0x66/0x1a0
[<ffffffff811998b8>] do_io_submit+0x708/0xb90
[<ffffffff81199d50>] sys_io_submit+0x10/0x20
[<ffffffff81a18d69>] system_call_fastpath+0x16/0x1b
The explanation is in the comment within the code:
We need to do this because the pages shared by the frontend
(xen-blkfront) can be already locked (lock_page, called by
do_read_cache_page); when the userspace backend tries to use them
with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
do_blockdev_direct_IO is going to try to lock the same pages
again resulting in a deadlock.
A simplified call graph looks like this:
pygrub QEMU
-----------------------------------------------
do_read_cache_page io_submit
| |
lock_page ext3_direct_IO
|
bio_add_page
|
lock_page
Internally the xen-blkback uses m2p_add_override to swizzle (temporarily)
a 'struct page' to have a different MFN (so that it can point to another
guest). It also can easily find out whether another pfn corresponding
to the mfn exists in the m2p, and can set the FOREIGN bit
in the p2m, making sure that mfn_to_pfn returns the pfn of the backend.
This allows the backend to perform direct_IO on these pages, but as a
side effect prevents the frontend from using get_user_pages_fast on
them while they are being shared with the backend.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Xen PV kernels allow access to the APERF/MPERF registers to read the
effective frequency. Access to the MSRs is however redirected to the
currently scheduled physical CPU, making consecutive read and
compares unreliable. In addition each rdmsr traps into the hypervisor.
So to avoid bogus readouts and expensive traps, disable the kernel
internal feature flag for APERF/MPERF if running under Xen.
This will
a) remove the aperfmperf flag from /proc/cpuinfo
b) not mislead the power scheduler (arch/x86/kernel/cpu/sched.c) to
use the feature to improve scheduling (by default disabled)
c) not mislead the cpufreq driver to use the MSRs
This does not cover userland programs which access the MSRs via the
device file interface, but this will be addressed separately.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Cc: stable@vger.kernel.org # v3.0+
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Stub out MSR methods that aren't actually needed. This fixes a crash
as Xen Dom0 on AMD Trinity systems. A bigger patch should be added to
remove the paravirt machinery completely for the methods which
apparently have no users!
Reported-by: Andre Przywara <andre.przywara@amd.com>
Link: http://lkml.kernel.org/r/20120530222356.GA28417@andromeda.dapyr.net
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: <stable@vger.kernel.org>
We did not take into account that xen_released_pages would be
used outside the initial E820 parsing code. As such we would
did not subtract from xen_released_pages the count of pages
that we had populated back (instead we just did a simple
extra_pages = released - populated).
The balloon driver uses xen_released_pages to set the initial
current_pages count. If this is wrong (too low) then when a new
(higher) target is set, the balloon driver will request too many pages
from Xen."
This fixes errors such as:
(XEN) memory.c:133:d0 Could not allocate order=0 extent: id=0 memflags=0 (51 of 512)
during bootup and
free_memory : 0
where the free_memory should be 128.
Acked-by: David Vrabel <david.vrabel@citrix.com>
[v1: Per David's review made the git commit better]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
This file depends on <xen/xen.h>, but the dependency was hidden due
to: <asm/acpi.h> -> <asm/trampoline.h> -> <asm/io.h> -> <xen/xen.h>
With the removal of <asm/trampoline.h>, this exposed the missing
Cc: Len Brown <lenb@kernel.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Jarkko Sakkinen <jarkko.sakkinen@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/n/tip-7ccybvue6mw6wje3uxzzcglj@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Provide the registration callback to call in the Xen's
ACPI sleep functionality. This means that during S3/S5
we make a hypercall XENPF_enter_acpi_sleep with the
proper PM1A/PM1B registers.
Based of Ke Yu's <ke.yu@intel.com> initial idea.
[ From http://xenbits.xensource.com/linux-2.6.18-xen.hg
change c68699484a65 ]
[v1: Added Copyright and license]
[v2: Added check if PM1A/B the 16-bits MSB contain something. The spec
only uses 16-bits but might have more in future]
Signed-off-by: Liang Tang <liang.tang@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Map native ipi vector to xen vector.
Implement apic ipi interface with xen_send_IPI_one.
Tested-by: Steven Noonan <steven@uplinklabs.net>
Signed-off-by: Ben Guthro <ben@guthro.net>
Signed-off-by: Lin Ming <mlin@ss.pku.edu.cn>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
In xen_memory_setup(), if a page that is being released has a VA
mapping this must also be updated. Otherwise, the page will be not
released completely -- it will still be referenced in Xen and won't be
freed util the mapping is removed and this prevents it from being
reallocated at a different PFN.
This was already being done for the ISA memory region in
xen_ident_map_ISA() but on many systems this was omitting a few pages
as many systems marked a few pages below the ISA memory region as
reserved in the e820 map.
This fixes errors such as:
(XEN) page_alloc.c:1148:d0 Over-allocation for domain 0: 2097153 > 2097152
(XEN) memory.c:133:d0 Could not allocate order=0 extent: id=0 memflags=0 (0 of 17)
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
They use the same set of arguments, so it is just the matter
of using the proper hypercall.
Acked-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
When the Xen hypervisor boots a PV kernel it hands it two pieces
of information: nr_pages and a made up E820 entry.
The nr_pages value defines the range from zero to nr_pages of PFNs
which have a valid Machine Frame Number (MFN) underneath it. The
E820 mirrors that (with the VGA hole):
BIOS-provided physical RAM map:
Xen: 0000000000000000 - 00000000000a0000 (usable)
Xen: 00000000000a0000 - 0000000000100000 (reserved)
Xen: 0000000000100000 - 0000000080800000 (usable)
The fun comes when a PV guest that is run with a machine E820 - that
can either be the initial domain or a PCI PV guest, where the E820
looks like the normal thing:
BIOS-provided physical RAM map:
Xen: 0000000000000000 - 000000000009e000 (usable)
Xen: 000000000009ec00 - 0000000000100000 (reserved)
Xen: 0000000000100000 - 0000000020000000 (usable)
Xen: 0000000020000000 - 0000000020200000 (reserved)
Xen: 0000000020200000 - 0000000040000000 (usable)
Xen: 0000000040000000 - 0000000040200000 (reserved)
Xen: 0000000040200000 - 00000000bad80000 (usable)
Xen: 00000000bad80000 - 00000000badc9000 (ACPI NVS)
..
With that overlaying the nr_pages directly on the E820 does not
work as there are gaps and non-RAM regions that won't be used
by the memory allocator. The 'xen_release_chunk' helps with that
by punching holes in the P2M (PFN to MFN lookup tree) for those
regions and tells us that:
Freeing 20000-20200 pfn range: 512 pages freed
Freeing 40000-40200 pfn range: 512 pages freed
Freeing bad80-badf4 pfn range: 116 pages freed
Freeing badf6-bae7f pfn range: 137 pages freed
Freeing bb000-100000 pfn range: 282624 pages freed
Released 283999 pages of unused memory
Those 283999 pages are subtracted from the nr_pages and are returned
to the hypervisor. The end result is that the initial domain
boots with 1GB less memory as the nr_pages has been subtracted by
the amount of pages residing within the PCI hole. It can balloon up
to that if desired using 'xl mem-set 0 8092', but the balloon driver
is not always compiled in for the initial domain.
This patch, implements the populate hypercall (XENMEM_populate_physmap)
which increases the the domain with the same amount of pages that
were released.
The other solution (that did not work) was to transplant the MFN in
the P2M tree - the ones that were going to be freed were put in
the E820_RAM regions past the nr_pages. But the modifications to the
M2P array (the other side of creating PTEs) were not carried away.
As the hypervisor is the only one capable of modifying that and the
only two hypercalls that would do this are: the update_va_mapping
(which won't work, as during initial bootup only PFNs up to nr_pages
are mapped in the guest) or via the populate hypercall.
The end result is that the kernel can now boot with the
nr_pages without having to subtract the 283999 pages.
On a 8GB machine, with various dom0_mem= parameters this is what we get:
no dom0_mem
-Memory: 6485264k/9435136k available (5817k kernel code, 1136060k absent, 1813812k reserved, 2899k data, 696k init)
+Memory: 7619036k/9435136k available (5817k kernel code, 1136060k absent, 680040k reserved, 2899k data, 696k init)
dom0_mem=3G
-Memory: 2616536k/9435136k available (5817k kernel code, 1136060k absent, 5682540k reserved, 2899k data, 696k init)
+Memory: 2703776k/9435136k available (5817k kernel code, 1136060k absent, 5595300k reserved, 2899k data, 696k init)
dom0_mem=max:3G
-Memory: 2696732k/4281724k available (5817k kernel code, 1136060k absent, 448932k reserved, 2899k data, 696k init)
+Memory: 2702204k/4281724k available (5817k kernel code, 1136060k absent, 443460k reserved, 2899k data, 696k init)
And the 'xm list' or 'xl list' now reflect what the dom0_mem=
argument is.
Acked-by: David Vrabel <david.vrabel@citrix.com>
[v2: Use populate hypercall]
[v3: Remove debug printks]
[v4: Simplify code]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Otherwise we can get these meaningless:
Freeing bad80-badf4 pfn range: 0 pages freed
We also can do this for the summary ones - no point of printing
"Set 0 page(s) to 1-1 mapping"
Acked-by: David Vrabel <david.vrabel@citrix.com>
[v1: Extended to the summary printks]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
The accessing PCI configuration space with the PCI BIOS32 service does
not work in PV guests.
On systems without MMCONFIG or where the BIOS hasn't marked the
MMCONFIG region as reserved in the e820 map, the BIOS service is
probed (even though direct access is preferred) and this hangs.
CC: stable@kernel.org
Acked-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
[v1: Fixed compile error when CONFIG_PCI is not set]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
If I try to do "cat /sys/kernel/debug/kernel_page_tables"
I end up with:
BUG: unable to handle kernel paging request at ffffc7fffffff000
IP: [<ffffffff8106aa51>] ptdump_show+0x221/0x480
PGD 0
Oops: 0000 [#1] SMP
CPU 0
.. snip..
RAX: 0000000000000000 RBX: ffffc00000000fff RCX: 0000000000000000
RDX: 0000800000000000 RSI: 0000000000000000 RDI: ffffc7fffffff000
which is due to the fact we are trying to access a PFN that is not
accessible to us. The reason (at least in this case) was that
PGD[256] is set to __HYPERVISOR_VIRT_START which was setup (by the
hypervisor) to point to a read-only linear map of the MFN->PFN array.
During our parsing we would get the MFN (a valid one), try to look
it up in the MFN->PFN tree and find it invalid and return ~0 as PFN.
Then pte_mfn_to_pfn would happilly feed that in, attach the flags
and return it back to the caller. 'ptdump_show' bitshifts it and
gets and invalid value that it tries to dereference.
Instead of doing all of that, we detect the ~0 case and just
return !_PAGE_PRESENT.
This bug has been in existence .. at least until 2.6.37 (yikes!)
CC: stable@kernel.org
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
On x86_64 on AMD machines where the first APIC_ID is not zero, we get:
ACPI: LAPIC (acpi_id[0x01] lapic_id[0x10] enabled)
BIOS bug: APIC version is 0 for CPU 1/0x10, fixing up to 0x10
BIOS bug: APIC version mismatch, boot CPU: 0, CPU 1: version 10
which means that when the ACPI processor driver loads and
tries to parse the _Pxx states it fails to do as, as it
ends up calling acpi_get_cpuid which does this:
for_each_possible_cpu(i) {
if (cpu_physical_id(i) == apic_id)
return i;
}
And the bootup CPU, has not been found so it fails and returns -1
for the first CPU - which then subsequently in the loop that
"acpi_processor_get_info" does results in returning an error, which
means that "acpi_processor_add" failing and per_cpu(processor)
is never set (and is NULL).
That means that when xen-acpi-processor tries to load (much much
later on) and parse the P-states it gets -ENODEV from
acpi_processor_register_performance() (which tries to read
the per_cpu(processor)) and fails to parse the data.
Reported-by-and-Tested-by: Stefan Bader <stefan.bader@canonical.com>
Suggested-by: Boris Ostrovsky <boris.ostrovsky@amd.com>
[v2: Bit-shift APIC ID by 24 bits]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Implements xen_io_apic_read with hypercall, so it returns proper
IO-APIC information instead of fabricated one.
Fallback to return an emulated IO_APIC values if hypercall fails.
[v2: fallback to return an emulated IO_APIC values if hypercall fails]
Signed-off-by: Lin Ming <mlin@ss.pku.edu.cn>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
This reverts commit 2531d64b6f.
The two patches:
x86/apic: Replace io_apic_ops with x86_io_apic_ops.
xen/x86: Implement x86_apic_ops
take care of fixing it properly.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Or rather just implement one different function as opposed
to the native one : the read function.
We synthesize the values.
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
[v1: Rebased on top of tip/x86/urgent]
[v2: Return 0xfd instead of 0xff in the default case]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
In xen_restore_fl_direct(), xen_force_evtchn_callback() was being
called even if no events were pending. This resulted in (depending on
workload) about a 100 times as many xen_version hypercalls as
necessary.
Fix this by correcting the sense of the conditional jump.
This seems to give a significant performance benefit for some
workloads.
There is some subtle tricksy "..since the check here is trying to
check both pending and masked in a single cmpw, but I think this is
correct. It will call check_events now only when the combined
mask+pending word is 0x0001 (aka unmasked, pending)." (Ian)
CC: stable@kernel.org
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
When we boot on a machine that can hotplug CPUs and we
are using 'dom0_max_vcpus=X' on the Xen hypervisor line
to clip the amount of CPUs available to the initial domain,
we get this:
(XEN) Command line: com1=115200,8n1 dom0_mem=8G noreboot dom0_max_vcpus=8 sync_console mce_verbosity=verbose console=com1,vga loglvl=all guest_loglvl=all
.. snip..
DMI: Intel Corporation S2600CP/S2600CP, BIOS SE5C600.86B.99.99.x032.072520111118 07/25/2011
.. snip.
SMP: Allowing 64 CPUs, 32 hotplug CPUs
installing Xen timer for CPU 7
cpu 7 spinlock event irq 361
NMI watchdog: disabled (cpu7): hardware events not enabled
Brought up 8 CPUs
.. snip..
[acpi processor finds the CPUs are not initialized and starts calling
arch_register_cpu, which creates /sys/devices/system/cpu/cpu8/online]
CPU 8 got hotplugged
CPU 9 got hotplugged
CPU 10 got hotplugged
.. snip..
initcall 1_acpi_battery_init_async+0x0/0x1b returned 0 after 406 usecs
calling erst_init+0x0/0x2bb @ 1
[and the scheduler sticks newly started tasks on the new CPUs, but
said CPUs cannot be initialized b/c the hypervisor has limited the
amount of vCPUS to 8 - as per the dom0_max_vcpus=8 flag.
The spinlock tries to kick the other CPU, but the structure for that
is not initialized and we crash.]
BUG: unable to handle kernel paging request at fffffffffffffed8
IP: [<ffffffff81035289>] xen_spin_lock+0x29/0x60
PGD 180d067 PUD 180e067 PMD 0
Oops: 0002 [#1] SMP
CPU 7
Modules linked in:
Pid: 1, comm: swapper/0 Not tainted 3.4.0-rc2upstream-00001-gf5154e8 #1 Intel Corporation S2600CP/S2600CP
RIP: e030:[<ffffffff81035289>] [<ffffffff81035289>] xen_spin_lock+0x29/0x60
RSP: e02b:ffff8801fb9b3a70 EFLAGS: 00010282
With this patch, we cap the amount of vCPUS that the initial domain
can run, to exactly what dom0_max_vcpus=X has specified.
In the future, if there is a hypercall that will allow a running
domain to expand past its initial set of vCPUS, this patch should
be re-evaluated.
CC: stable@kernel.org
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
There are exactly four users of __monitor and __mwait:
- cstate.c (which allows acpi_processor_ffh_cstate_enter to be called
when the cpuidle API drivers are used. However patch
"cpuidle: replace xen access to x86 pm_idle and default_idle"
provides a mechanism to disable the cpuidle and use safe_halt.
- smpboot (which allows mwait_play_dead to be called). However
safe_halt is always used so we skip that.
- intel_idle (same deal as above).
- acpi_pad.c. This the one that we do not want to run as we
will hit the below crash.
Why do we want to expose MWAIT_LEAF in the first place?
We want it for the xen-acpi-processor driver - which uploads
C-states to the hypervisor. If MWAIT_LEAF is set, the cstate.c
sets the proper address in the C-states so that the hypervisor
can benefit from using the MWAIT functionality. And that is
the sole reason for using it.
Without this patch, if a module performs mwait or monitor we
get this:
invalid opcode: 0000 [#1] SMP
CPU 2
.. snip..
Pid: 5036, comm: insmod Tainted: G O 3.4.0-rc2upstream-dirty #2 Intel Corporation S2600CP/S2600CP
RIP: e030:[<ffffffffa000a017>] [<ffffffffa000a017>] mwait_check_init+0x17/0x1000 [mwait_check]
RSP: e02b:ffff8801c298bf18 EFLAGS: 00010282
RAX: ffff8801c298a010 RBX: ffffffffa03b2000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff8801c29800d8 RDI: ffff8801ff097200
RBP: ffff8801c298bf18 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
R13: ffffffffa000a000 R14: 0000005148db7294 R15: 0000000000000003
FS: 00007fbb364f2700(0000) GS:ffff8801ff08c000(0000) knlGS:0000000000000000
CS: e033 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 000000000179f038 CR3: 00000001c9469000 CR4: 0000000000002660
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process insmod (pid: 5036, threadinfo ffff8801c298a000, task ffff8801c29cd7e0)
Stack:
ffff8801c298bf48 ffffffff81002124 ffffffffa03b2000 00000000000081fd
000000000178f010 000000000178f030 ffff8801c298bf78 ffffffff810c41e6
00007fff3fb30db9 00007fff3fb30db9 00000000000081fd 0000000000010000
Call Trace:
[<ffffffff81002124>] do_one_initcall+0x124/0x170
[<ffffffff810c41e6>] sys_init_module+0xc6/0x220
[<ffffffff815b15b9>] system_call_fastpath+0x16/0x1b
Code: <0f> 01 c8 31 c0 0f 01 c9 c9 c3 00 00 00 00 00 00 00 00 00 00 00 00
RIP [<ffffffffa000a017>] mwait_check_init+0x17/0x1000 [mwait_check]
RSP <ffff8801c298bf18>
---[ end trace 16582fc8a3d1e29a ]---
Kernel panic - not syncing: Fatal exception
With this module (which is what acpi_pad.c would hit):
MODULE_AUTHOR("Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>");
MODULE_DESCRIPTION("mwait_check_and_back");
MODULE_LICENSE("GPL");
MODULE_VERSION();
static int __init mwait_check_init(void)
{
__monitor((void *)¤t_thread_info()->flags, 0, 0);
__mwait(0, 0);
return 0;
}
static void __exit mwait_check_exit(void)
{
}
module_init(mwait_check_init);
module_exit(mwait_check_exit);
Reported-by: Liu, Jinsong <jinsong.liu@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: x86@kernel.org
Link: http://lkml.kernel.org/r/20120420124557.246929343@linutronix.de
Preparatory patch to use the generic idle thread allocation.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: x86@kernel.org
Link: http://lkml.kernel.org/r/20120420124557.176604405@linutronix.de
Remove open-coded exception table entries in arch/x86/xen/xen-asm_32.S,
and replace them with _ASM_EXTABLE() macros; this will allow us to
change the format and type of the exception table entries.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/CA%2B55aFyijf43qSu3N9nWHEBwaGbb7T2Oq9A=9EyR=Jtyqfq_cQ@mail.gmail.com
This reverts commit b960d6c43a.
If we have another thread (very likely) touched the list, we
end up hitting a problem "that the next element is wrong because
we should be able to cope with that. The problem is that the
next->next pointer would be set LIST_POISON1. " (Stefano's
comment on the patch).
Reverting for now.
Suggested-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Use list_for_each_entry_safe and remove the spin_lock acquisition in
m2p_find_override.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Move the code from Xen to debugfs to make the code common
for other users as well.
Accked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Suzuki Poulose <suzuki@in.ibm.com>
[v1: Fixed rebase issues]
[v2: Fixed PPC compile issues]
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
During early bootup we can't use alloc_page, so to allocate
leaf pages in the P2M we need to use extend_brk. For that
we are utilizing the early_alloc_p2m and early_alloc_p2m_middle
functions to do the job for us. This function follows the
same logic as set_phys_to_machine.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
At the start of the function we were checking for idx != 0
and bailing out. And later calling extend_brk if idx != 0.
That is unnecessary so remove that checks.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
For identity cases we want to call reserve_brk only on the boundary
conditions of the middle P2M (so P2M[x][y][0] = extend_brk). This is
to work around identify regions (PCI spaces, gaps in E820) which are not
aligned on 2MB regions.
However for the case were we want to allocate P2M middle leafs at the
early bootup stage, irregardless of this alignment check we need some
means of doing that. For that we provide the new argument.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
We are going to be using the early_alloc_p2m (and
early_alloc_p2m_middle) code in follow up patches which
are not related to setting identity pages.
Hence lets move the code out in its own function and
rename them as appropiate.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
There is an extra and unnecessary call to smp_processor_id()
in cpu_bringup(). Remove it.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
The above mentioned patch checks the IOAPIC and if it contains
-1, then it unmaps said IOAPIC. But under Xen we get this:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000040
IP: [<ffffffff8134e51f>] xen_irq_init+0x1f/0xb0
PGD 0
Oops: 0002 [#1] SMP
CPU 0
Modules linked in:
Pid: 1, comm: swapper/0 Not tainted 3.2.10-3.fc16.x86_64 #1 Dell Inc. Inspiron
1525 /0U990C
RIP: e030:[<ffffffff8134e51f>] [<ffffffff8134e51f>] xen_irq_init+0x1f/0xb0
RSP: e02b: ffff8800d42cbb70 EFLAGS: 00010202
RAX: 0000000000000000 RBX: 00000000ffffffef RCX: 0000000000000001
RDX: 0000000000000040 RSI: 00000000ffffffef RDI: 0000000000000001
RBP: ffff8800d42cbb80 R08: ffff8800d6400000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 00000000ffffffef
R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000010
FS: 0000000000000000(0000) GS:ffff8800df5fe000(0000) knlGS:0000000000000000
CS: e033 DS: 0000 ES: 0000 CR0:000000008005003b
CR2: 0000000000000040 CR3: 0000000001a05000 CR4: 0000000000002660
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process swapper/0 (pid: 1, threadinfo ffff8800d42ca000, task ffff8800d42d0000)
Stack:
00000000ffffffef 0000000000000010 ffff8800d42cbbe0 ffffffff8134f157
ffffffff8100a9b2 ffffffff8182ffd1 00000000000000a0 00000000829e7384
0000000000000002 0000000000000010 00000000ffffffff 0000000000000000
Call Trace:
[<ffffffff8134f157>] xen_bind_pirq_gsi_to_irq+0x87/0x230
[<ffffffff8100a9b2>] ? check_events+0x12+0x20
[<ffffffff814bab42>] xen_register_pirq+0x82/0xe0
[<ffffffff814bac1a>] xen_register_gsi.part.2+0x4a/0xd0
[<ffffffff814bacc0>] acpi_register_gsi_xen+0x20/0x30
[<ffffffff8103036f>] acpi_register_gsi+0xf/0x20
[<ffffffff8131abdb>] acpi_pci_irq_enable+0x12e/0x202
[<ffffffff814bc849>] pcibios_enable_device+0x39/0x40
[<ffffffff812dc7ab>] do_pci_enable_device+0x4b/0x70
[<ffffffff812dc878>] __pci_enable_device_flags+0xa8/0xf0
[<ffffffff812dc8d3>] pci_enable_device+0x13/0x20
The reason we are dying is b/c the call acpi_get_override_irq() is used,
which returns the polarity and trigger for the IRQs. That function calls
mp_find_ioapics to get the 'struct ioapic' structure - which along with the
mp_irq[x] is used to figure out the default values and the polarity/trigger
overrides. Since the mp_find_ioapics now returns -1 [b/c the IOAPIC is filled
with 0xffffffff], the acpi_get_override_irq() stops trying to lookup in the
mp_irq[x] the proper INT_SRV_OVR and we can't install the SCI interrupt.
The proper fix for this is going in v3.5 and adds an x86_io_apic_ops
struct so that platforms can override it. But for v3.4 lets carry this
work-around. This patch does that by providing a slightly different variant
of the fake IOAPIC entries.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Adapt core x86 and IA64 architecture code for dma_map_ops changes: replace
alloc/free_coherent with generic alloc/free methods.
Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
[removed swiotlb related changes and replaced it with wrappers,
merged with IA64 patch to avoid inter-patch dependences in intel-iommu code]
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Tony Luck <tony.luck@intel.com>
The CPU hotplug code has now a callback to help bring up the CPU.
Without the call we end up getting:
BUG: soft lockup - CPU#0 stuck for 29s! [migration/0:6]
Modules linked in:
CPU ] Pid: 6, comm: migration/0 Not tainted 3.3.0upstream-01180-ged378a5 #1 Dell Inc. PowerEdge T105 /0RR825
RIP: e030:[<ffffffff810d3b8b>] [<ffffffff810d3b8b>] stop_machine_cpu_stop+0x7b/0xf0
RSP: e02b:ffff8800ceaabdb0 EFLAGS: 00000293
.. snip..
Call Trace:
[<ffffffff810d3b10>] ? stop_one_cpu_nowait+0x50/0x50
[<ffffffff810d3841>] cpu_stopper_thread+0xf1/0x1c0
[<ffffffff815a9776>] ? __schedule+0x3c6/0x760
[<ffffffff815aa749>] ? _raw_spin_unlock_irqrestore+0x19/0x30
[<ffffffff810d3750>] ? res_counter_charge+0x150/0x150
[<ffffffff8108dc76>] kthread+0x96/0xa0
[<ffffffff815b27e4>] kernel_thread_helper+0x4/0x10
[<ffffffff815aacbc>] ? retint_restore_ar
Thix fixes it.
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
By using the functionality provided by "[CPUFREQ]: provide
disable_cpuidle() function to disable the API."
Under the Xen hypervisor we do not want the initial domain to exercise
the cpufreq scaling drivers. This is b/c the Xen hypervisor is
in charge of doing this as well and we can end up with both the
Linux kernel and the hypervisor trying to change the P-states
leading to weird performance issues.
Acked-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[v2: Fix compile error spotted by Benjamin Schweikert <b.schweikert@googlemail.com>]
For the hypervisor to take advantage of the MWAIT support it needs
to extract from the ACPI _CST the register address. But the
hypervisor does not have the support to parse DSDT so it relies on
the initial domain (dom0) to parse the ACPI Power Management information
and push it up to the hypervisor. The pushing of the data is done
by the processor_harveset_xen module which parses the information that
the ACPI parser has graciously exposed in 'struct acpi_processor'.
For the ACPI parser to also expose the Cx states for MWAIT, we need
to expose the MWAIT capability (leaf 1). Furthermore we also need to
expose the MWAIT_LEAF capability (leaf 5) for cstate.c to properly
function.
The hypervisor could expose these flags when it traps the XEN_EMULATE_PREFIX
operations, but it can't do it since it needs to be backwards compatible.
Instead we choose to use the native CPUID to figure out if the MWAIT
capability exists and use the XEN_SET_PDC query hypercall to figure out
if the hypervisor wants us to expose the MWAIT_LEAF capability or not.
Note: The XEN_SET_PDC query was implemented in c/s 23783:
"ACPI: add _PDC input override mechanism".
With this in place, instead of
C3 ACPI IOPORT 415
we get now
C3:ACPI FFH INTEL MWAIT 0x20
Note: The cpu_idle which would be calling the mwait variants for idling
never gets set b/c we set the default pm_idle to be the hypercall variant.
Acked-by: Jan Beulich <JBeulich@suse.com>
[v2: Fix missing header file include and #ifdef]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
We needed that call in the past to force the kernel to use
default_idle (which called safe_halt, which called xen_safe_halt).
But set_pm_idle_to_default() does now that, so there is no need
to use this boot option operand.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[Pls also look at https://lkml.org/lkml/2012/2/10/228]
Using of PAT to change pages from WB to WC works quite nicely.
Changing it back to WB - not so much. The crux of the matter is
that the code that does this (__page_change_att_set_clr) has only
limited information so when it tries to the change it gets
the "raw" unfiltered information instead of the properly filtered one -
and the "raw" one tell it that PSE bit is on (while infact it
is not). As a result when the PTE is set to be WB from WC, we get
tons of:
:WARNING: at arch/x86/xen/mmu.c:475 xen_make_pte+0x67/0xa0()
:Hardware name: HP xw4400 Workstation
.. snip..
:Pid: 27, comm: kswapd0 Tainted: G W 3.2.2-1.fc16.x86_64 #1
:Call Trace:
: [<ffffffff8106dd1f>] warn_slowpath_common+0x7f/0xc0
: [<ffffffff8106dd7a>] warn_slowpath_null+0x1a/0x20
: [<ffffffff81005a17>] xen_make_pte+0x67/0xa0
: [<ffffffff810051bd>] __raw_callee_save_xen_make_pte+0x11/0x1e
: [<ffffffff81040e15>] ? __change_page_attr_set_clr+0x9d5/0xc00
: [<ffffffff8114c2e8>] ? __purge_vmap_area_lazy+0x158/0x1d0
: [<ffffffff8114cca5>] ? vm_unmap_aliases+0x175/0x190
: [<ffffffff81041168>] change_page_attr_set_clr+0x128/0x4c0
: [<ffffffff81041542>] set_pages_array_wb+0x42/0xa0
: [<ffffffff8100a9b2>] ? check_events+0x12/0x20
: [<ffffffffa0074d4c>] ttm_pages_put+0x1c/0x70 [ttm]
: [<ffffffffa0074e98>] ttm_page_pool_free+0xf8/0x180 [ttm]
: [<ffffffffa0074f78>] ttm_pool_mm_shrink+0x58/0x90 [ttm]
: [<ffffffff8112ba04>] shrink_slab+0x154/0x310
: [<ffffffff8112f17a>] balance_pgdat+0x4fa/0x6c0
: [<ffffffff8112f4b8>] kswapd+0x178/0x3d0
: [<ffffffff815df134>] ? __schedule+0x3d4/0x8c0
: [<ffffffff81090410>] ? remove_wait_queue+0x50/0x50
: [<ffffffff8112f340>] ? balance_pgdat+0x6c0/0x6c0
: [<ffffffff8108fb6c>] kthread+0x8c/0xa0
for every page. The proper fix for this is has been posted
and is https://lkml.org/lkml/2012/2/10/228
"x86/cpa: Use pte_attrs instead of pte_flags on CPA/set_p.._wb/wc operations."
along with a detailed description of the problem and solution.
But since that posting has gone nowhere I am proposing
this band-aid solution so that at least users don't get
the page corruption (the pages that are WC don't get changed to WB
and end up being recycled for filesystem or other things causing
mysterious crashes).
The negative impact of this patch is that users of WC flag
(which are InfiniBand, radeon, nouveau drivers) won't be able
to set that flag - so they are going to see performance degradation.
But stability is more important here.
Fixes RH BZ# 742032, 787403, and 745574
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
commit 7347b4082e "xen: Allow
unprivileged Xen domains to create iomap pages" added a redundant
line in the early bootup code to filter out the PTE. That
filtering is already done a bit earlier so this extra processing
is not required.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
When a user offlines a VCPU and then onlines it, we get:
NMI watchdog disabled (cpu2): hardware events not enabled
BUG: scheduling while atomic: swapper/2/0/0x00000002
Modules linked in: dm_multipath dm_mod xen_evtchn iscsi_boot_sysfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi scsi_mod libcrc32c crc32c radeon fbco
ttm bitblit softcursor drm_kms_helper xen_blkfront xen_netfront xen_fbfront fb_sys_fops sysimgblt sysfillrect syscopyarea xen_kbdfront xenfs [last unloaded:
Pid: 0, comm: swapper/2 Tainted: G O 3.2.0phase15.1-00003-gd6f7f5b-dirty #4
Call Trace:
[<ffffffff81070571>] __schedule_bug+0x61/0x70
[<ffffffff8158eb78>] __schedule+0x798/0x850
[<ffffffff8158ed6a>] schedule+0x3a/0x50
[<ffffffff810349be>] cpu_idle+0xbe/0xe0
[<ffffffff81583599>] cpu_bringup_and_idle+0xe/0x10
The reason for this should be obvious from this call-chain:
cpu_bringup_and_idle:
\- cpu_bringup
| \-[preempt_disable]
|
|- cpu_idle
\- play_dead [assuming the user offlined the VCPU]
| \
| +- (xen_play_dead)
| \- HYPERVISOR_VCPU_off [so VCPU is dead, once user
| | onlines it starts from here]
| \- cpu_bringup [preempt_disable]
|
+- preempt_enable_no_reschedule()
+- schedule()
\- preempt_enable()
So we have two preempt_disble() and one preempt_enable(). Calling
preempt_enable() after the cpu_bringup() in the xen_play_dead
fixes the imbalance.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
percpu_xxx funcs are duplicated with this_cpu_xxx funcs, so replace them
for further code clean up.
I don't know much of xen code. But, since the code is in x86 architecture,
the percpu_xxx is exactly same as this_cpu_xxx serials functions. So, the
change is safe.
Signed-off-by: Alex Shi <alex.shi@intel.com>
Acked-by: Christoph Lameter <cl@gentwo.org>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
If NR_CPUS < 256 then arch_spinlock_t is only 16 bits wide but struct
xen_spinlock is 32 bits. When a spin lock is contended and
xl->spinners is modified the two bytes immediately after the spin lock
would be corrupted.
This is a regression caused by 84eb950db1
(x86, ticketlock: Clean up types and accessors) which reduced the size
of arch_spinlock_t.
Fix this by making xl->spinners a u8 if NR_CPUS < 256. A
BUILD_BUG_ON() is also added to check the sizes of the two structures
are compatible.
In many cases this was not noticable as there would often be padding
bytes after the lock (e.g., if any of CONFIG_GENERIC_LOCKBREAK,
CONFIG_DEBUG_SPINLOCK, or CONFIG_DEBUG_LOCK_ALLOC were enabled).
The bnx2 driver is affected. In struct bnx2, phy_lock and
indirect_lock may have no padding after them. Contention on phy_lock
would corrupt indirect_lock making it appear locked and the driver
would deadlock.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
CC: stable@kernel.org #only 3.2
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
d312ae878b "xen: use maximum reservation to limit amount of usable RAM"
clamped the total amount of RAM to the current maximum reservation. This is
correct for dom0 but is not correct for guest domains. In order to boot a guest
"pre-ballooned" (e.g. with memory=1G but maxmem=2G) in order to allow for
future memory expansion the guest must derive max_pfn from the e820 provided by
the toolstack and not the current maximum reservation (which can reflect only
the current maximum, not the guest lifetime max). The existing algorithm
already behaves this correctly if we do not artificially limit the maximum
number of pages for the guest case.
For a guest booted with maxmem=512, memory=128 this results in:
[ 0.000000] BIOS-provided physical RAM map:
[ 0.000000] Xen: 0000000000000000 - 00000000000a0000 (usable)
[ 0.000000] Xen: 00000000000a0000 - 0000000000100000 (reserved)
-[ 0.000000] Xen: 0000000000100000 - 0000000008100000 (usable)
-[ 0.000000] Xen: 0000000008100000 - 0000000020800000 (unusable)
+[ 0.000000] Xen: 0000000000100000 - 0000000020800000 (usable)
...
[ 0.000000] NX (Execute Disable) protection: active
[ 0.000000] DMI not present or invalid.
[ 0.000000] e820 update range: 0000000000000000 - 0000000000010000 (usable) ==> (reserved)
[ 0.000000] e820 remove range: 00000000000a0000 - 0000000000100000 (usable)
-[ 0.000000] last_pfn = 0x8100 max_arch_pfn = 0x1000000
+[ 0.000000] last_pfn = 0x20800 max_arch_pfn = 0x1000000
[ 0.000000] initial memory mapped : 0 - 027ff000
[ 0.000000] Base memory trampoline at [c009f000] 9f000 size 4096
-[ 0.000000] init_memory_mapping: 0000000000000000-0000000008100000
-[ 0.000000] 0000000000 - 0008100000 page 4k
-[ 0.000000] kernel direct mapping tables up to 8100000 @ 27bb000-27ff000
+[ 0.000000] init_memory_mapping: 0000000000000000-0000000020800000
+[ 0.000000] 0000000000 - 0020800000 page 4k
+[ 0.000000] kernel direct mapping tables up to 20800000 @ 26f8000-27ff000
[ 0.000000] xen: setting RW the range 27e8000 - 27ff000
[ 0.000000] 0MB HIGHMEM available.
-[ 0.000000] 129MB LOWMEM available.
-[ 0.000000] mapped low ram: 0 - 08100000
-[ 0.000000] low ram: 0 - 08100000
+[ 0.000000] 520MB LOWMEM available.
+[ 0.000000] mapped low ram: 0 - 20800000
+[ 0.000000] low ram: 0 - 20800000
With this change "xl mem-set <domain> 512M" will successfully increase the
guest RAM (by reducing the balloon).
There is no change for dom0.
Reported-and-Tested-by: George Shuklin <george.shuklin@gmail.com>
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Cc: stable@kernel.org
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
memblock_init() initializes arrays for regions and memblock itself;
however, all these can be done with struct initializers and
memblock_init() can be removed. This patch kills memblock_init() and
initializes memblock with struct initializer.
The only difference is that the first dummy entries don't have .nid
set to MAX_NUMNODES initially. This doesn't cause any behavior
difference.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: "H. Peter Anvin" <hpa@zytor.com>
The idea behind commit d91ee5863b ("cpuidle: replace xen access to x86
pm_idle and default_idle") was to have one call - disable_cpuidle()
which would make pm_idle not be molested by other code. It disallows
cpuidle_idle_call to be set to pm_idle (which is excellent).
But in the select_idle_routine() and idle_setup(), the pm_idle can still
be set to either: amd_e400_idle, mwait_idle or default_idle. This
depends on some CPU flags (MWAIT) and in AMD case on the type of CPU.
In case of mwait_idle we can hit some instances where the hypervisor
(Amazon EC2 specifically) sets the MWAIT and we get:
Brought up 2 CPUs
invalid opcode: 0000 [#1] SMP
Pid: 0, comm: swapper Not tainted 3.1.0-0.rc6.git0.3.fc16.x86_64 #1
RIP: e030:[<ffffffff81015d1d>] [<ffffffff81015d1d>] mwait_idle+0x6f/0xb4
...
Call Trace:
[<ffffffff8100e2ed>] cpu_idle+0xae/0xe8
[<ffffffff8149ee78>] cpu_bringup_and_idle+0xe/0x10
RIP [<ffffffff81015d1d>] mwait_idle+0x6f/0xb4
RSP <ffff8801d28ddf10>
In the case of amd_e400_idle we don't get so spectacular crashes, but we
do end up making an MSR which is trapped in the hypervisor, and then
follow it up with a yield hypercall. Meaning we end up going to
hypervisor twice instead of just once.
The previous behavior before v3.0 was that pm_idle was set to
default_idle regardless of select_idle_routine/idle_setup.
We want to do that, but only for one specific case: Xen. This patch
does that.
Fixes RH BZ #739499 and Ubuntu #881076
Reported-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Stefano Stabellini