xen_init_spinlocks() currently calls static_key_slow_inc() before
jump_label_init() is invoked. When CONFIG_JUMP_LABEL is set (which usually is
the case) the effect of this static_key_slow_inc() is deferred until after
jump_label_init(). This is different from when CONFIG_JUMP_LABEL is not set, in
which case the key is set immediately. Thus, depending on the value of config
option, we may observe different behavior.
In addition, when we come to __jump_label_transform() from jump_label_init(),
the key (paravirt_ticketlocks_enabled) is already enabled. On processors where
ideal_nop is not the same as default_nop this will cause a BUG() since it is
expected that before a key is enabled the latter is replaced by the former
during initialization.
To address this problem we need to move
static_key_slow_inc(¶virt_ticketlocks_enabled) so that it is called
after jump_label_init(). We also need to make sure that this is done before
other cpus start to boot. early_initcall appears to be a good place to do so.
(Note that we cannot move whole xen_init_spinlocks() there since pv_lock_ops
need to be set before alternative_instructions() runs.)
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[v2: Added extra comments in the code]
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
As we get compile warnings about .init.data being
used by non-init functions.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
This reverts commit 70dd4998cb.
Now that the bugs have been resolved we can re-enable the
PV ticketlock implementation under PVHVM Xen guests.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
There is no need to setup this kicker IPI if we are never going
to use the paravirtualized ticketlock mechanism.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Before this patch we would patch all of the pv_lock_ops sites
using alternative assembler. Then later in the bootup cycle
change the unlock_kick and lock_spinning to the Xen specific -
without re patching.
That meant that for the core of the kernel we would be running
with the baremetal version of unlock_kick and lock_spinning while
for modules we would have the proper Xen specific slowpaths.
As most of the module uses some API from the core kernel that ended
up with slowpath lockers waiting forever to be kicked (b/c they
would be using the Xen specific slowpath logic). And the
kick never came b/c the unlock path that was taken was the
baremetal one.
On PV we do not have the problem as we initialise before the
alternative code kicks in.
The fix is to make the updating of the pv_lock_ops function
be done before the alternative code starts patching.
Note that this patch fixes issues discovered by commit
f10cd522c5.
("xen: disable PV spinlocks on HVM") wherein it mentioned
PV spinlocks cannot possibly work with the current code because they are
enabled after pvops patching has already been done, and because PV
spinlocks use a different data structure than native spinlocks so we
cannot switch between them dynamically.
The first problem is solved by this patch.
The second problem has been solved by commit
816434ec4a
(Merge branch 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip)
P.S.
There is still the commit 70dd4998cb
(xen/spinlock: Disable IRQ spinlock (PV) allocation on PVHVM) to
revert but that can be done later after all other bugs have been
fixed.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
As we are using the generic ticketlock structs and these
old structures are not needed anymore.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
The xen_lock_spinning has a check for the kicker interrupts
and if it is not initialized it will spin normally (not enter
the slowpath).
But for PVHVM case we would initialize the kicker interrupt
before the CPU came online. This meant that if the booting
CPU used a spinlock and went in the slowpath - it would
enter the slowpath and block forever. The forever part because
during bootup: the spinlock would be taken _before_ the CPU
sets itself to be online (more on this further), and we enter
to poll on the event channel forever.
The bootup CPU (see commit fc78d343fa
"xen/smp: initialize IPI vectors before marking CPU online"
for details) and the CPU that started the bootup consult
the cpu_online_mask to determine whether the booting CPU should
get an IPI. The booting CPU has to set itself in this mask via:
set_cpu_online(smp_processor_id(), true);
However, if the spinlock is taken before this (and it is) and
it polls on an event channel - it will never be woken up as
the kernel will never send an IPI to an offline CPU.
Note that the PVHVM logic in sending IPIs is using the HVM
path which has numerous checks using the cpu_online_mask
and cpu_active_mask. See above mention git commit for details.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)
iQEcBAABAgAGBQJSGqS5AAoJEHm+PkMAQRiGFxEH/3VrqF6WAkcviNiW/0DCdO8k
v6Wi7Sp5LxVkwzmOCHCV1tTHwLRlH3cB9YmJlGQ0kHCREaAuEQAB0xJXIW7dnyYj
Qq7KoRZEMe3wizmjEsj8qsrhfMLzHjBw67hBz2znwW/4P7YdgzwD7KRiEat+yRC9
ON3nNL2zIqpfk92RXvVrSVl4KMEM+WNbOfiffgBiEP24Ja1MJMFH1d4i6hNOaB0x
9Pb3Lw8let92x+8Ao5jnjKdKMgVsoZWbN/TgQR8zZOHM38AGGiDgk18vMz+L+hpS
jqfjckxj1m30jGq0qZ9ZbMZx3IGif4KccVr30MqNHJpwi6Q24qXvT3YfA3HkstM=
=nAab
-----END PGP SIGNATURE-----
Merge tag 'v3.11-rc7' into stable/for-linus-3.12
Linux 3.11-rc7
As we need the git commit 28817e9de4f039a1a8c1fe1df2fa2df524626b9e
Author: Chuck Anderson <chuck.anderson@oracle.com>
Date: Tue Aug 6 15:12:19 2013 -0700
xen/smp: initialize IPI vectors before marking CPU online
* tag 'v3.11-rc7': (443 commits)
Linux 3.11-rc7
ARC: [lib] strchr breakage in Big-endian configuration
VFS: collect_mounts() should return an ERR_PTR
bfs: iget_locked() doesn't return an ERR_PTR
efs: iget_locked() doesn't return an ERR_PTR()
proc: kill the extra proc_readfd_common()->dir_emit_dots()
cope with potentially long ->d_dname() output for shmem/hugetlb
usb: phy: fix build breakage
USB: OHCI: add missing PCI PM callbacks to ohci-pci.c
staging: comedi: bug-fix NULL pointer dereference on failed attach
lib/lz4: correct the LZ4 license
memcg: get rid of swapaccount leftovers
nilfs2: fix issue with counting number of bio requests for BIO_EOPNOTSUPP error detection
nilfs2: remove double bio_put() in nilfs_end_bio_write() for BIO_EOPNOTSUPP error
drivers/platform/olpc/olpc-ec.c: initialise earlier
ipv4: expose IPV4_DEVCONF
ipv6: handle Redirect ICMP Message with no Redirected Header option
be2net: fix disabling TX in be_close()
Revert "ACPI / video: Always call acpi_video_init_brightness() on init"
Revert "genetlink: fix family dump race"
...
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
* 'x86/spinlocks' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/kvm/guest: Fix sparse warning: "symbol 'klock_waiting' was not declared as static"
kvm: Paravirtual ticketlocks support for linux guests running on KVM hypervisor
kvm guest: Add configuration support to enable debug information for KVM Guests
kvm uapi: Add KICK_CPU and PV_UNHALT definition to uapi
xen, pvticketlock: Allow interrupts to be enabled while blocking
x86, ticketlock: Add slowpath logic
jump_label: Split jumplabel ratelimit
x86, pvticketlock: When paravirtualizing ticket locks, increment by 2
x86, pvticketlock: Use callee-save for lock_spinning
xen, pvticketlocks: Add xen_nopvspin parameter to disable xen pv ticketlocks
xen, pvticketlock: Xen implementation for PV ticket locks
xen: Defer spinlock setup until boot CPU setup
x86, ticketlock: Collapse a layer of functions
x86, ticketlock: Don't inline _spin_unlock when using paravirt spinlocks
x86, spinlock: Replace pv spinlocks with pv ticketlocks
m2p_remove_override() calls get_balloon_scratch_page() in
MULTI_update_va_mapping() even though it already has pointer to this page from
the earlier call (in scratch_page). This second call doesn't have a matching
put_balloon_scratch_page() thus not restoring preempt count back. (Also, there
is no put_balloon_scratch_page() in the error path.)
In addition, the second multicall uses __xen_mc_entry() which does not disable
interrupts. Rearrange xen_mc_* calls to keep interrupts off while performing
multicalls.
This commit fixes a regression introduced by:
commit ee0726407f
Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Tue Jul 23 17:23:54 2013 +0000
xen/m2p: use GNTTABOP_unmap_and_replace to reinstate the original mapping
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
This is the updated version of df54d6fa54 ("x86 get_unmapped_area():
use proper mmap base for bottom-up direction") that only randomizes the
mmap base address once.
Signed-off-by: Radu Caragea <sinaelgl@gmail.com>
Reported-and-tested-by: Jeff Shorey <shoreyjeff@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Adrian Sendroiu <molecula2788@gmail.com>
Cc: Greg KH <greg@kroah.com>
Cc: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit df54d6fa54.
The commit isn't necessarily wrong, but because it recalculates the
random mmap_base every time, it seems to confuse user memory allocators
that expect contiguous mmap allocations even when the mmap address isn't
specified.
In particular, the MATLAB Java runtime seems to be unhappy. See
https://bugzilla.kernel.org/show_bug.cgi?id=60774
So we'll want to apply the random offset only once, and Radu has a patch
for that. Revert this older commit in order to apply the other one.
Reported-by: Jeff Shorey <shoreyjeff@gmail.com>
Cc: Radu Caragea <sinaelgl@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
- On ARM did not have balanced calls to get/put_cpu.
- Fix to make tboot + Xen + Linux correctly.
- Fix events VCPU binding issues.
- Fix a vCPU online race where IPIs are sent to not-yet-online vCPU.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)
iQEcBAABAgAGBQJSFMaJAAoJEFjIrFwIi8fJ+/0H/32rLj60FpKXcPDCvID+9p8T
XDGnFNttsxyhuzEzetOAd0aLKYKGnUaTDZBHfgSNipGCxjMLYgz84phRmHAYEj8u
kai1Ag1WjhZilCmImzFvdHFiUwtvKwkeBIL/cZtKr1BetpnuuFsoVnwbH9FVjMpr
TCg6sUwFq7xRyD1azo/cTLZFeiUqq0aQLw8J72YaapdS3SztHPeDHXlPpmLUdb6+
hiSYveJMYp2V0SW8g8eLKDJxVr2QdPEfl9WpBzpLlLK8GrNw8BEU6hSOSLzxB7z/
hDATAuZ5iHiIEi1uGfVjOyDws2ngUhmBKUH5x5iVIZd2P5c/ffLh2ePDVWGO5RI=
=yMuS
-----END PGP SIGNATURE-----
Merge tag 'stable/for-linus-3.11-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
Pull Xen bug-fixes from Konrad Rzeszutek Wilk:
- On ARM did not have balanced calls to get/put_cpu.
- Fix to make tboot + Xen + Linux correctly.
- Fix events VCPU binding issues.
- Fix a vCPU online race where IPIs are sent to not-yet-online vCPU.
* tag 'stable/for-linus-3.11-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
xen/smp: initialize IPI vectors before marking CPU online
xen/events: mask events when changing their VCPU binding
xen/events: initialize local per-cpu mask for all possible events
x86/xen: do not identity map UNUSABLE regions in the machine E820
xen/arm: missing put_cpu in xen_percpu_init
kernel use callback linked in panic_notifier_list to notice others when panic
happens.
NORET_TYPE void panic(const char * fmt, ...){
...
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
}
When Xen becomes aware of this, it will call xen_reboot(SHUTDOWN_crash) to
send out an event with reason code - SHUTDOWN_crash.
xen_panic_handler_init() is defined to register on panic_notifier_list but
we only call it in xen_arch_setup which only be called by PV, this patch is
necessary for PVHVM.
Without this patch, setting 'on_crash=coredump-restart' in PVHVM guest config
file won't lead a vmcore to be generate when the guest panics. It can be
reproduced with 'echo c > /proc/sysrq-trigger'.
Signed-off-by: Vaughan Cao <vaughan.cao@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Joe Jin <joe.jin@oracle.com>
GNTTABOP_unmap_grant_ref unmaps a grant and replaces it with a 0
mapping instead of reinstating the original mapping.
Doing so separately would be racy.
To unmap a grant and reinstate the original mapping atomically we use
GNTTABOP_unmap_and_replace.
GNTTABOP_unmap_and_replace doesn't work with GNTMAP_contains_pte, so
don't use it for kmaps. GNTTABOP_unmap_and_replace zeroes the mapping
passed in new_addr so we have to reinstate it, however that is a
per-cpu mapping only used for balloon scratch pages, so we can be sure that
it's not going to be accessed while the mapping is not valid.
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
CC: alex@alex.org.uk
CC: dcrisan@flexiant.com
[v1: Konrad fixed up the conflicts]
Conflicts:
arch/x86/xen/p2m.c
An older PVHVM guest (v3.0 based) crashed during vCPU hot-plug with:
kernel BUG at drivers/xen/events.c:1328!
RCU has detected that a CPU has not entered a quiescent state within the
grace period. It needs to send the CPU a reschedule IPI if it is not
offline. rcu_implicit_offline_qs() does this check:
/*
* If the CPU is offline, it is in a quiescent state. We can
* trust its state not to change because interrupts are disabled.
*/
if (cpu_is_offline(rdp->cpu)) {
rdp->offline_fqs++;
return 1;
}
Else the CPU is online. Send it a reschedule IPI.
The CPU is in the middle of being hot-plugged and has been marked online
(!cpu_is_offline()). See start_secondary():
set_cpu_online(smp_processor_id(), true);
...
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
start_secondary() then waits for the CPU bringing up the hot-plugged CPU to
mark it as active:
/*
* Wait until the cpu which brought this one up marked it
* online before enabling interrupts. If we don't do that then
* we can end up waking up the softirq thread before this cpu
* reached the active state, which makes the scheduler unhappy
* and schedule the softirq thread on the wrong cpu. This is
* only observable with forced threaded interrupts, but in
* theory it could also happen w/o them. It's just way harder
* to achieve.
*/
while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
cpu_relax();
/* enable local interrupts */
local_irq_enable();
The CPU being hot-plugged will be marked active after it has been fully
initialized by the CPU managing the hot-plug. In the Xen PVHVM case
xen_smp_intr_init() is called to set up the hot-plugged vCPU's
XEN_RESCHEDULE_VECTOR.
The hot-plugging CPU is marked online, not marked active and does not have
its IPI vectors set up. rcu_implicit_offline_qs() sees the hot-plugging
cpu is !cpu_is_offline() and tries to send it a reschedule IPI:
This will lead to:
kernel BUG at drivers/xen/events.c:1328!
xen_send_IPI_one()
xen_smp_send_reschedule()
rcu_implicit_offline_qs()
rcu_implicit_dynticks_qs()
force_qs_rnp()
force_quiescent_state()
__rcu_process_callbacks()
rcu_process_callbacks()
__do_softirq()
call_softirq()
do_softirq()
irq_exit()
xen_evtchn_do_upcall()
because xen_send_IPI_one() will attempt to use an uninitialized IRQ for
the XEN_RESCHEDULE_VECTOR.
There is at least one other place that has caused the same crash:
xen_smp_send_reschedule()
wake_up_idle_cpu()
add_timer_on()
clocksource_watchdog()
call_timer_fn()
run_timer_softirq()
__do_softirq()
call_softirq()
do_softirq()
irq_exit()
xen_evtchn_do_upcall()
xen_hvm_callback_vector()
clocksource_watchdog() uses cpu_online_mask to pick the next CPU to handle
a watchdog timer:
/*
* Cycle through CPUs to check if the CPUs stay synchronized
* to each other.
*/
next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(cpu_online_mask);
watchdog_timer.expires += WATCHDOG_INTERVAL;
add_timer_on(&watchdog_timer, next_cpu);
This resulted in an attempt to send an IPI to a hot-plugging CPU that
had not initialized its reschedule vector. One option would be to make
the RCU code check to not check for CPU offline but for CPU active.
As becoming active is done after a CPU is online (in older kernels).
But Srivatsa pointed out that "the cpu_active vs cpu_online ordering has been
completely reworked - in the online path, cpu_active is set *before* cpu_online,
and also, in the cpu offline path, the cpu_active bit is reset in the CPU_DYING
notification instead of CPU_DOWN_PREPARE." Drilling in this the bring-up
path: "[brought up CPU].. send out a CPU_STARTING notification, and in response
to that, the scheduler sets the CPU in the cpu_active_mask. Again, this mask
is better left to the scheduler alone, since it has the intelligence to use it
judiciously."
The conclusion was that:
"
1. At the IPI sender side:
It is incorrect to send an IPI to an offline CPU (cpu not present in
the cpu_online_mask). There are numerous places where we check this
and warn/complain.
2. At the IPI receiver side:
It is incorrect to let the world know of our presence (by setting
ourselves in global bitmasks) until our initialization steps are complete
to such an extent that we can handle the consequences (such as
receiving interrupts without crashing the sender etc.)
" (from Srivatsa)
As the native code enables the interrupts at some point we need to be
able to service them. In other words a CPU must have valid IPI vectors
if it has been marked online.
It doesn't need to handle the IPI (interrupts may be disabled) but needs
to have valid IPI vectors because another CPU may find it in cpu_online_mask
and attempt to send it an IPI.
This patch will change the order of the Xen vCPU bring-up functions so that
Xen vectors have been set up before start_secondary() is called.
It also will not continue to bring up a Xen vCPU if xen_smp_intr_init() fails
to initialize it.
Orabug 13823853
Signed-off-by Chuck Anderson <chuck.anderson@oracle.com>
Acked-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
During early setup, when the reserved regions and MMIO holes are being
setup as 1:1 in the p2m, clear any mappings instead of making them 1:1
(execept for the ISA region which is expected to be mapped).
This fixes a regression introduced in 3.5 by 83d51ab473 (xen/setup:
update VA mapping when releasing memory during setup) which caused
hosts with tboot to fail to boot.
tboot marks a region in the e820 map as unusable and the dom0 kernel
would attempt to map this region and Xen does not permit unusable
regions to be mapped by guests.
(XEN) 0000000000000000 - 0000000000060000 (usable)
(XEN) 0000000000060000 - 0000000000068000 (reserved)
(XEN) 0000000000068000 - 000000000009e000 (usable)
(XEN) 0000000000100000 - 0000000000800000 (usable)
(XEN) 0000000000800000 - 0000000000972000 (unusable)
tboot marked this region as unusable.
(XEN) 0000000000972000 - 00000000cf200000 (usable)
(XEN) 00000000cf200000 - 00000000cf38f000 (reserved)
(XEN) 00000000cf38f000 - 00000000cf3ce000 (ACPI data)
(XEN) 00000000cf3ce000 - 00000000d0000000 (reserved)
(XEN) 00000000e0000000 - 00000000f0000000 (reserved)
(XEN) 00000000fe000000 - 0000000100000000 (reserved)
(XEN) 0000000100000000 - 0000000630000000 (usable)
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
If CONFIG_PREEMPT is enabled then xen_enable_irq() (and
xen_restore_fl()) could be preempted and rescheduled on a different
VCPU in between the clear of the mask and the check for pending
events. This may result in events being lost as the upcall will check
for pending events on the wrong VCPU.
Fix this by disabling preemption around the unmask and check for
events.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
If there are UNUSABLE regions in the machine memory map, dom0 will
attempt to map them 1:1 which is not permitted by Xen and the kernel
will crash.
There isn't anything interesting in the UNUSABLE region that the dom0
kernel needs access to so we can avoid making the 1:1 mapping and
treat it as RAM.
We only do this for dom0, as that is where tboot case shows up.
A PV domU could have an UNUSABLE region in its pseudo-physical map
and would need to be handled in another patch.
This fixes a boot failure on hosts with tboot.
tboot marks a region in the e820 map as unusable and the dom0 kernel
would attempt to map this region and Xen does not permit unusable
regions to be mapped by guests.
(XEN) 0000000000000000 - 0000000000060000 (usable)
(XEN) 0000000000060000 - 0000000000068000 (reserved)
(XEN) 0000000000068000 - 000000000009e000 (usable)
(XEN) 0000000000100000 - 0000000000800000 (usable)
(XEN) 0000000000800000 - 0000000000972000 (unusable)
tboot marked this region as unusable.
(XEN) 0000000000972000 - 00000000cf200000 (usable)
(XEN) 00000000cf200000 - 00000000cf38f000 (reserved)
(XEN) 00000000cf38f000 - 00000000cf3ce000 (ACPI data)
(XEN) 00000000cf3ce000 - 00000000d0000000 (reserved)
(XEN) 00000000e0000000 - 00000000f0000000 (reserved)
(XEN) 00000000fe000000 - 0000000100000000 (reserved)
(XEN) 0000000100000000 - 0000000630000000 (usable)
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
[v1: Altered the patch and description with domU's with UNUSABLE regions]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Pull x86 fixes from Ingo Molnar:
"Two AMD microcode loader fixes and an OLPC firmware support fix"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, microcode, AMD: Fix early microcode loading
x86, microcode, AMD: Make cpu_has_amd_erratum() use the correct struct cpuinfo_x86
x86: Don't clear olpc_ofw_header when sentinel is detected
It was not declared as static since it was thought to be used by
pv-flushtlb earlier.
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: <gleb@redhat.com>
Cc: <pbonzini@redhat.com>
Cc: Jiri Kosina <trivial@kernel.org>
Link: http://lkml.kernel.org/r/1376645921-8056-1-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Merge a bunch of fixes from Andrew Morton.
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
fs/proc/task_mmu.c: fix buffer overflow in add_page_map()
arch: *: Kconfig: add "kernel/Kconfig.freezer" to "arch/*/Kconfig"
ocfs2: fix null pointer dereference in ocfs2_dir_foreach_blk_id()
x86 get_unmapped_area(): use proper mmap base for bottom-up direction
ocfs2: fix NULL pointer dereference in ocfs2_duplicate_clusters_by_page
ocfs2: Revert 40bd62e to avoid regression in extended allocation
drivers/rtc/rtc-stmp3xxx.c: provide timeout for potentially endless loop polling a HW bit
hugetlb: fix lockdep splat caused by pmd sharing
aoe: adjust ref of head for compound page tails
microblaze: fix clone syscall
mm: save soft-dirty bits on file pages
mm: save soft-dirty bits on swapped pages
memcg: don't initialize kmem-cache destroying work for root caches
During smp_boot_cpus paravirtualied KVM guest detects if the hypervisor has
required feature (KVM_FEATURE_PV_UNHALT) to support pv-ticketlocks. If so,
support for pv-ticketlocks is registered via pv_lock_ops.
Use KVM_HC_KICK_CPU hypercall to wakeup waiting/halted vcpu.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20130810193849.GA25260@linux.vnet.ibm.com
Signed-off-by: Suzuki Poulose <suzuki@in.ibm.com>
[Raghu: check_zero race fix, enum for kvm_contention_stat, jumplabel related changes,
addition of safe_halt for irq enabled case, bailout spinning in nmi case(Gleb)]
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Gleb Natapov <gleb@redhat.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
from accessing cpu_data too early, i.e. before smp_store_cpu_info()
has copied the boot_cpu_data ontop and overwritten an already empty
structure (which we shouldn't access that early in the first place
anyway).
The second patch is kinda largish for that late in the game but it
shouldn't be problematic because we're simply switching from using
cpu_data to use the CPU family number directly and thus again, not use
uninitialized cpu_data structure.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)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=cxbY
-----END PGP SIGNATURE-----
Merge tag 'amd_ucode_fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp into x86/urgent
Pull AMD microcode fixes from Borislav Petkov:
" Those are basically two fixes which correct the AMD early ucode loader
from accessing cpu_data too early, i.e. before smp_store_cpu_info()
has copied the boot_cpu_data ontop and overwritten an already empty
structure (which we shouldn't access that early in the first place
anyway).
The second patch is kinda largish for that late in the game but it
shouldn't be problematic because we're simply switching from using
cpu_data to use the CPU family number directly and thus again, not use
uninitialized cpu_data structure. "
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When the stack is set to unlimited, the bottomup direction is used for
mmap-ings but the mmap_base is not used and thus effectively renders
ASLR for mmapings along with PIE useless.
Cc: Michel Lespinasse <walken@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Sendroiu <molecula2788@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andy reported that if file page get reclaimed we lose the soft-dirty bit
if it was there, so save _PAGE_BIT_SOFT_DIRTY bit when page address get
encoded into pte entry. Thus when #pf happens on such non-present pte
we can restore it back.
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andy Lutomirski reported that if a page with _PAGE_SOFT_DIRTY bit set
get swapped out, the bit is getting lost and no longer available when
pte read back.
To resolve this we introduce _PTE_SWP_SOFT_DIRTY bit which is saved in
pte entry for the page being swapped out. When such page is to be read
back from a swap cache we check for bit presence and if it's there we
clear it and restore the former _PAGE_SOFT_DIRTY bit back.
One of the problem was to find a place in pte entry where we can save
the _PTE_SWP_SOFT_DIRTY bit while page is in swap. The _PAGE_PSE was
chosen for that, it doesn't intersect with swap entry format stored in
pte.
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull perf fixes from Ingo Molnar:
"Two small fixlets"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86: Add Haswell ULT model number used in Macbook Air and other systems
perf/x86: Fix intel QPI uncore event definitions
This is only theoretical, but after try_to_wake_up(p) was changed
to check p->state under p->pi_lock the code like
__set_current_state(TASK_INTERRUPTIBLE);
schedule();
can miss a signal. This is the special case of wait-for-condition,
it relies on try_to_wake_up/schedule interaction and thus it does
not need mb() between __set_current_state() and if(signal_pending).
However, this __set_current_state() can move into the critical
section protected by rq->lock, now that try_to_wake_up() takes
another lock we need to ensure that it can't be reordered with
"if (signal_pending(current))" check inside that section.
The patch is actually one-liner, it simply adds smp_wmb() before
spin_lock_irq(rq->lock). This is what try_to_wake_up() already
does by the same reason.
We turn this wmb() into the new helper, smp_mb__before_spinlock(),
for better documentation and to allow the architectures to change
the default implementation.
While at it, kill smp_mb__after_lock(), it has no callers.
Perhaps we can also add smp_mb__before/after_spinunlock() for
prepare_to_wait().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
load_microcode_amd() (and the helper it is using) should not have an
cpu parameter. The microcode loading does not depend on the CPU wrt the
patches loaded since they will end up in a global list for all CPUs
anyway.
The change from cpu to x86family in load_microcode_amd()
now allows to drop the code messing with cpu_data(cpu) from
collect_cpu_info_amd_early(), which is wrong anyway because at that
point the per-cpu cpu_info is not yet setup (These values would later be
overwritten by smp_store_boot_cpu_info() / smp_store_cpu_info()).
Fold the rest of collect_cpu_info_amd_early() into load_ucode_amd_ap(),
because its only used at one place and without the cpuinfo_x86 accesses
it was not much left.
Signed-off-by: Torsten Kaiser <just.for.lkml@googlemail.com>
[ Fengguang: build fix ]
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
[ Boris: adapt it to current tree. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
cpu_has_amd_erratum() is buggy, because it uses the per-cpu cpu_info
before it is filled by smp_store_boot_cpu_info() / smp_store_cpu_info().
If early microcode loading is enabled its collect_cpu_info_amd_early()
will fill ->x86 and so the fallback to boot_cpu_data is not used. But
->x86_vendor was not filled and is still X86_VENDOR_INTEL resulting in
no errata fixes getting applied and my system hangs on boot.
Using cpu_info in cpu_has_amd_erratum() is wrong anyway: its only
caller init_amd() will have a struct cpuinfo_x86 as parameter and the
set_cpu_bug() that is controlled by cpu_has_amd_erratum() also only uses
that struct.
So pass the struct cpuinfo_x86 from init_amd() to cpu_has_amd_erratum()
and the broken fallback can be dropped.
[ Boris: Drop WARN_ON() since we're called only from init_amd() ]
Signed-off-by: Torsten Kaiser <just.for.lkml@googlemail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
OpenFirmware wasn't quite following the protocol described in boot.txt
and the kernel has detected this through use of the sentinel value
in boot_params. OFW does zero out almost all of the stuff that it should
do, but not the sentinel.
This causes the kernel to clear olpc_ofw_header, which breaks x86 OLPC
support.
OpenFirmware has now been fixed. However, it would be nice if we could
maintain Linux compatibility with old firmware versions. To do that, we just
have to avoid zeroing out olpc_ofw_header.
OFW does not write to any other parts of the header that are being zapped
by the sentinel-detection code, and all users of olpc_ofw_header are
somewhat protected through checking for the OLPC_OFW_SIG magic value
before using it. So this should not cause any problems for anyone.
Signed-off-by: Daniel Drake <dsd@laptop.org>
Link: http://lkml.kernel.org/r/20130809221420.618E6FAB03@dev.laptop.org
Acked-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org> # v3.9+
In m2p_remove_override() when removing the grant map from the kernel
mapping and replacing with a mapping to the original page, the grant
unmap will already have flushed the TLB and it is not necessary to do
it again after updating the mapping.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
This is based on a patch that Zhenzhong Duan had sent - which
was missing some of the remaining pieces. The kernel has the
logic to handle Xen-type-exceptions using the paravirt interface
in the assembler code (see PARAVIRT_ADJUST_EXCEPTION_FRAME -
pv_irq_ops.adjust_exception_frame and and INTERRUPT_RETURN -
pv_cpu_ops.iret).
That means the nmi handler (and other exception handlers) use
the hypervisor iret.
The other changes that would be neccessary for this would
be to translate the NMI_VECTOR to one of the entries on the
ipi_vector and make xen_send_IPI_mask_allbutself use different
events.
Fortunately for us commit 1db01b4903
(xen: Clean up apic ipi interface) implemented this and we piggyback
on the cleanup such that the apic IPI interface will pass the right
vector value for NMI.
With this patch we can trigger NMIs within a PV guest (only tested
x86_64).
For this to work with normal PV guests (not initial domain)
we need the domain to be able to use the APIC ops - they are
already implemented to use the Xen event channels. For that
to be turned on in a PV domU we need to remove the masking
of X86_FEATURE_APIC.
Incidentally that means kgdb will also now work within
a PV guest without using the 'nokgdbroundup' workaround.
Note that the 32-bit version is different and this patch
does not enable that.
CC: Lisa Nguyen <lisa@xenapiadmin.com>
CC: Ben Guthro <benjamin.guthro@citrix.com>
CC: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[v1: Fixed up per David Vrabel comments]
Reviewed-by: Ben Guthro <benjamin.guthro@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
These are needed by both guest and host.
Originally-from: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1376058122-8248-13-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Acked-by: Gleb Natapov <gleb@redhat.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
If interrupts were enabled when taking the spinlock, we can leave them
enabled while blocking to get the lock.
If we can enable interrupts while waiting for the lock to become
available, and we take an interrupt before entering the poll,
and the handler takes a spinlock which ends up going into
the slow state (invalidating the per-cpu "lock" and "want" values),
then when the interrupt handler returns the event channel will
remain pending so the poll will return immediately, causing it to
return out to the main spinlock loop.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-12-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Maintain a flag in the LSB of the ticket lock tail which indicates
whether anyone is in the lock slowpath and may need kicking when
the current holder unlocks. The flags are set when the first locker
enters the slowpath, and cleared when unlocking to an empty queue (ie,
no contention).
In the specific implementation of lock_spinning(), make sure to set
the slowpath flags on the lock just before blocking. We must do
this before the last-chance pickup test to prevent a deadlock
with the unlocker:
Unlocker Locker
test for lock pickup
-> fail
unlock
test slowpath
-> false
set slowpath flags
block
Whereas this works in any ordering:
Unlocker Locker
set slowpath flags
test for lock pickup
-> fail
block
unlock
test slowpath
-> true, kick
If the unlocker finds that the lock has the slowpath flag set but it is
actually uncontended (ie, head == tail, so nobody is waiting), then it
clears the slowpath flag.
The unlock code uses a locked add to update the head counter. This also
acts as a full memory barrier so that its safe to subsequently
read back the slowflag state, knowing that the updated lock is visible
to the other CPUs. If it were an unlocked add, then the flag read may
just be forwarded from the store buffer before it was visible to the other
CPUs, which could result in a deadlock.
Unfortunately this means we need to do a locked instruction when
unlocking with PV ticketlocks. However, if PV ticketlocks are not
enabled, then the old non-locked "add" is the only unlocking code.
Note: this code relies on gcc making sure that unlikely() code is out of
line of the fastpath, which only happens when OPTIMIZE_SIZE=n. If it
doesn't the generated code isn't too bad, but its definitely suboptimal.
Thanks to Srivatsa Vaddagiri for providing a bugfix to the original
version of this change, which has been folded in.
Thanks to Stephan Diestelhorst for commenting on some code which relied
on an inaccurate reading of the x86 memory ordering rules.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-11-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stephan Diestelhorst <stephan.diestelhorst@amd.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Increment ticket head/tails by 2 rather than 1 to leave the LSB free
to store a "is in slowpath state" bit. This halves the number
of possible CPUs for a given ticket size, but this shouldn't matter
in practice - kernels built for 32k+ CPU systems are probably
specially built for the hardware rather than a generic distro
kernel.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-9-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Although the lock_spinning calls in the spinlock code are on the
uncommon path, their presence can cause the compiler to generate many
more register save/restores in the function pre/postamble, which is in
the fast path. To avoid this, convert it to using the pvops callee-save
calling convention, which defers all the save/restores until the actual
function is called, keeping the fastpath clean.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-8-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-7-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Replace the old Xen implementation of PV spinlocks with and implementation
of xen_lock_spinning and xen_unlock_kick.
xen_lock_spinning simply registers the cpu in its entry in lock_waiting,
adds itself to the waiting_cpus set, and blocks on an event channel
until the channel becomes pending.
xen_unlock_kick searches the cpus in waiting_cpus looking for the one
which next wants this lock with the next ticket, if any. If found,
it kicks it by making its event channel pending, which wakes it up.
We need to make sure interrupts are disabled while we're relying on the
contents of the per-cpu lock_waiting values, otherwise an interrupt
handler could come in, try to take some other lock, block, and overwrite
our values.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-6-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[ Raghavendra: use function + enum instead of macro, cmpxchg for zero status reset
Reintroduce break since we know the exact vCPU to send IPI as suggested by Konrad.]
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
There's no need to do it at very early init, and doing it there
makes it impossible to use the jump_label machinery.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-5-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Now that the paravirtualization layer doesn't exist at the spinlock
level any more, we can collapse the __ticket_ functions into the arch_
functions.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-4-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The code size expands somewhat, and its better to just call
a function rather than inline it.
Thanks Jeremy for original version of ARCH_NOINLINE_SPIN_UNLOCK config patch,
which is simplified.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1376058122-8248-3-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Rather than outright replacing the entire spinlock implementation in
order to paravirtualize it, keep the ticket lock implementation but add
a couple of pvops hooks on the slow patch (long spin on lock, unlocking
a contended lock).
Ticket locks have a number of nice properties, but they also have some
surprising behaviours in virtual environments. They enforce a strict
FIFO ordering on cpus trying to take a lock; however, if the hypervisor
scheduler does not schedule the cpus in the correct order, the system can
waste a huge amount of time spinning until the next cpu can take the lock.
(See Thomas Friebel's talk "Prevent Guests from Spinning Around"
http://www.xen.org/files/xensummitboston08/LHP.pdf for more details.)
To address this, we add two hooks:
- __ticket_spin_lock which is called after the cpu has been
spinning on the lock for a significant number of iterations but has
failed to take the lock (presumably because the cpu holding the lock
has been descheduled). The lock_spinning pvop is expected to block
the cpu until it has been kicked by the current lock holder.
- __ticket_spin_unlock, which on releasing a contended lock
(there are more cpus with tail tickets), it looks to see if the next
cpu is blocked and wakes it if so.
When compiled with CONFIG_PARAVIRT_SPINLOCKS disabled, a set of stub
functions causes all the extra code to go away.
Results:
=======
setup: 32 core machine with 32 vcpu KVM guest (HT off) with 8GB RAM
base = 3.11-rc
patched = base + pvspinlock V12
+-----------------+----------------+--------+
dbench (Throughput in MB/sec. Higher is better)
+-----------------+----------------+--------+
| base (stdev %)|patched(stdev%) | %gain |
+-----------------+----------------+--------+
| 15035.3 (0.3) |15150.0 (0.6) | 0.8 |
| 1470.0 (2.2) | 1713.7 (1.9) | 16.6 |
| 848.6 (4.3) | 967.8 (4.3) | 14.0 |
| 652.9 (3.5) | 685.3 (3.7) | 5.0 |
+-----------------+----------------+--------+
pvspinlock shows benefits for overcommit ratio > 1 for PLE enabled cases,
and undercommits results are flat
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-2-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
[ Raghavendra: Changed SPIN_THRESHOLD, fixed redefinition of arch_spinlock_t]
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Pull misc x86 fixes from Peter Anvin.
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, amd, microcode: Fix error path in apply_microcode_amd()
x86, fpu: correct the asm constraints for fxsave, unbreak mxcsr.daz
x86, efi: correct call to free_pages
x86/iommu/vt-d: Expand interrupt remapping quirk to cover x58 chipset
John McCalpin reports that the "drs_data" and "ncb_data" QPI
uncore events are missing the "extra bit" and always return zero
values unless the bit is properly set.
More details from him:
According to the Xeon E5-2600 Product Family Uncore Performance
Monitoring Guide, Table 2-94, about 1/2 of the QPI Link Layer events
(including the ones that "perf" calls "drs_data" and "ncb_data") require
that the "extra bit" be set.
This was confusing for a while -- a note at the bottom of page 94 says
that the "extra bit" is bit 16 of the control register.
Unfortunately, Table 2-86 clearly says that bit 16 is reserved and must
be zero. Looking around a bit, I found that bit 21 appears to be the
correct "extra bit", and further investigation shows that "perf" actually
agrees with me:
[root@c560-003.stampede]# cat /sys/bus/event_source/devices/uncore_qpi_0/format/event
config:0-7,21
So the command
# perf -e "uncore_qpi_0/event=drs_data/"
Is the same as
# perf -e "uncore_qpi_0/event=0x02,umask=0x08/"
While it should be
# perf -e "uncore_qpi_0/event=0x102,umask=0x08/"
I confirmed that this last version gives results that agree with the
amount of data that I expected the STREAM benchmark to move across the QPI
link in the second (cross-chip) test of the original script.
Reported-by: John McCalpin <mccalpin@tacc.utexas.edu>
Signed-off-by: Vince Weaver <vincent.weaver@maine.edu>
Cc: zheng.z.yan@intel.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Paul Mackerras <paulus@samba.org>
Cc: <stable@kernel.org>
Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1308021037280.26119@vincent-weaver-1.um.maine.edu
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Konrad Rzeszutek Wilk