Export bind_interdomain_evtchn_to_irq() so drivers can use threaded
interrupt handlers with:

 irq = bind_interdomain_evtchn_to_irq(remote_dom, remote_port);
 if (irq < 0)
     /* error */
 ret = request_threaded_irq(...);
Signed-off-by: NJuergen Gross <jgross@suse.com>
Acked-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

The cleanup loop in grow_gnttab_list() is safe from the underflow of
the unsigned 'i' since nr_glist_frames is >= 1, but refactor it
anyway.
Signed-off-by: NChen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

If a gref could not be added (perhaps because the limit has been
reached or there are no more grant references available), the undo
path may crash because __del_gref() frees the gref while it is being
used for a list iteration.

A comment suggests that using list_for_each_entry() is safe since the
gref isn't removed from the list being iterated over, but it is freed
and thus list_for_each_entry_safe() must be used.

Also, explicitly delete the gref from the local per-file list, even
though this is not strictly necessary.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>

Only set gref->gref_id if foreign access was successfully granted and
the grant ref is valid.

If gref->gref_id == -ENOSPC the test in __del_gref() would incorrectly
attempt to end foreign access (because grant_ref_t is unsigned).
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reported-by: NDave Scott <dave.scott@citrix.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>

If the balloon driver is adding additional memory regions to the
balloon and add_memory() fails it will likely continuously fail so
cancel the balloon operation.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NDaniel Kiper <daniel.kiper@oracle.com>

Always freeze processes when suspending and thaw processes when resuming
to prevent a race noticeable with HVM guests.

This prevents a deadlock where the khubd kthread (which is designed to
be freezable) acquires a usb device lock and then tries to allocate
memory which requires the disk which hasn't been resumed yet.
Meanwhile, the xenwatch thread deadlocks waiting for the usb device
lock.

Freezing processes fixes this because the khubd thread is only thawed
after the xenwatch thread finishes resuming all the devices.
Signed-off-by: NRoss Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Cc: stable@vger.kernel.org

We should prefer `struct pci_device_id` over `DEFINE_PCI_DEVICE_TABLE` to
meet kernel coding style guidelines.  This issue was reported by checkpatch.

A simplified version of the semantic patch that makes this change is as
follows (http://coccinelle.lip6.fr/):

// <smpl>

@@
identifier i;
declarer name DEFINE_PCI_DEVICE_TABLE;
initializer z;
@@

- DEFINE_PCI_DEVICE_TABLE(i)
+ const struct pci_device_id i[]
= z;

// </smpl>

[bhelgaas: add semantic patch]
Signed-off-by: NBenoit Taine <benoit.taine@lip6.fr>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Fix to return -EFAULT from the error handling case instead of 0 when
version mismatch with pcifront.
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Reviewed-by Jan Beulich <jbeulich@suse.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=80531Reported-by: NDavid Binderman <dcb314@hotmail.com>
Signed-off-by: NAndrey Utkin <andrey.krieger.utkin@gmail.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

Since 05a812ac (xen/events/fifo:
correctly align bitops), ready is an unsigned long instead of uint32_t
and the BM() macro is no longer required.
Signed-off-by: NFrediano Ziglio <frediano.ziglio@citrix.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>

When using the FIFO-based ABI on x86_64, if the last port is at the
end of an event array page then sync_test_bit() on this port's event
word will read beyond the end of the page and in certain circumstances
this may fault.

The fault requires the following page in the kernel's direct mapping
to be not present, which would mean:

a) the array page is the last page of RAM; or

b) the following page is ballooned out /and/ it has been used for a
   foreign mapping by a kernel driver (such as netback or blkback)
   /and/ the grant has been unmapped.

Use the infrastructure added for arm64 to ensure that all bitops
operating on event words are unsigned long aligned.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: stable@vger.kernel.org

When using the FIFO-based event channel ABI, if the control block or
the local HEADs are not reset after resuming the guest may see stale
HEAD values and will fail to traverse the FIFO correctly.

This may prevent one or more VCPUs from receiving any events following
a resume.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: stable@vger.kernel.org

arch_gnttab_map_frames() and arch_gnttab_unmap_frames() are called in
atomic context but were calling alloc_vm_area() which might sleep.

Also, if a driver attempts to allocate a grant ref from an interrupt
and the table needs expanding, then the CPU may already by in lazy MMU
mode and apply_to_page_range() will BUG when it tries to re-enable
lazy MMU mode.

These two functions are only used in PV guests.

Introduce arch_gnttab_init() to allocates the virtual address space in
advance.

Avoid the use of apply_to_page_range() by using saving and using the
array of PTE addresses from the alloc_vm_area() call (which ensures
that the required page tables are pre-allocated).
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

This patch enables EFI usage under Xen dom0. Standard EFI Linux
Kernel infrastructure cannot be used because it requires direct
access to EFI data and code. However, in dom0 case it is not possible
because above mentioned EFI stuff is fully owned and controlled
by Xen hypervisor. In this case all calls from dom0 to EFI must
be requested via special hypercall which in turn executes relevant
EFI code in behalf of dom0.

When dom0 kernel boots it checks for EFI availability on a machine.
If it is detected then artificial EFI system table is filled.
Native EFI callas are replaced by functions which mimics them
by calling relevant hypercall. Later pointer to EFI system table
is passed to standard EFI machinery and it continues EFI subsystem
initialization taking into account that there is no direct access
to EFI boot services, runtime, tables, structures, etc. After that
system runs as usual.

This patch is based on Jan Beulich and Tang Liang work.
Signed-off-by: NJan Beulich <jbeulich@suse.com>
Signed-off-by: NTang Liang <liang.tang@oracle.com>
Signed-off-by: NDaniel Kiper <daniel.kiper@oracle.com>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com
Signed-off-by: NMatt Fleming <matt.fleming@intel.com>

Since 11c7ff17 (xen/grant-table: Force
to use v1 of grants.) the code for V2 grant tables is not used.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

arch_gnttab_map_frames() and arch_gnttab_unmap_frames() are called in
atomic context but were calling alloc_vm_area() which might sleep.

Also, if a driver attempts to allocate a grant ref from an interrupt
and the table needs expanding, then the CPU may already by in lazy MMU
mode and apply_to_page_range() will BUG when it tries to re-enable
lazy MMU mode.

These two functions are only used in PV guests.

Introduce arch_gnttab_init() to allocates the virtual address space in
advance.

Avoid the use of apply_to_page_range() by using saving and using the
array of PTE addresses from the alloc_vm_area() call.

N.B. 'alloc_vm_area' pre-allocates the pagetable so there is no need
to worry about having to do a PGD/PUD/PMD walk (like apply_to_page_range
does) and we can instead do set_pte.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
----
[v2: Add comment about alloc_vm_area]
[v3: Fix compile error found by 0-day bot]

Since cd9151e2 (xen/balloon: set a
mapping for ballooned out pages), a ballooned out page had its entry
in the p2m set to the MFN of one of the scratch pages.  This means
that the p2m will contain many entries pointing to the same MFN.

During a domain save, these many-to-one entries are not identified as
such and the scratch page is saved multiple times. On restore the
ballooned pages are populated with new frames and the domain may use
up its allocation before all pages can be restored.

Since the original fix only needed to keep a mapping for the ballooned
page it is safe to set ballooned out pages as INVALID_P2M_ENTRY in the
p2m (as they were before). Thus preventing them from being saved and
re-populated on restore.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reported-by: NMarek Marczykowski <marmarek@invisiblethingslab.com>
Tested-by: NMarek Marczykowski <marmarek@invisiblethingslab.com>
Acked-by: NStefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: <stable@vger.kernel.org>

Calling xen_console_resume() in xen_suspend() causes a warning because
it locks irq_mapping_update_lock (a mutex) and this may sleep.  If a
userspace process is using the evtchn device then this mutex may be
locked at the point of the stop_machine() call and
xen_console_resume() would then deadlock.

Resuming the console after stop_machine() returns avoids this
deadlock.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: <stable@vger.kernel.org>

Commit aa8532c3 (xen: refactor suspend
pre/post hooks) broke resuming PVHVM (auto-translated physmap) guests.

The gnttab_suspend() would clear the mapping for the grant table
frames, but the ->unmap_frames() call is only applicable to PV guests.
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reported-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

which is a perfectly legal error. This can be triggered if the
user has booted Xen with the no-cpuidle parameter.
Reported-by-and-Tested-by: NDon Slutz <dslutz@verizon.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

which are quite a few. It should be evident that dealing with that
many options is a bit complex.
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>

And also mention that you cannot do any pci_reset_function,
pci_reset_slot, or such calls. This is because they take the same
lock as SysFS does - and we would end up with a dead-lock if
we call those functions.
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>

When the toolstack wants us to drop or add an PCI device it
changes the XenBus state to Configuring - and as result of that
we find out which devices we should still be exporting out and
which ones not. For the ones we don't need anymore we need to
do an PCI reset so that it is ready for the next guest.
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>

We were doing the operations of freeing and reset in the wrong
order. Granted nothing broke because the reset functions just
set bar->which = 0.

But nonethless this was incorrect.
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: NJan Beulich <jbeulich@suse.com>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>

We are using 'psdev->dev','found_psdev->dev', and 'dev' at the
same time - and they all point to the same structure.

To keep it straight lets just use one - 'dev'.
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: NJan Beulich <jbeulich@suse.com>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>

No need to expose this outside of the ioapic code. The dynamic
allocations are guaranteed not to happen in the gsi space. See commit
62a08ae2.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NGrant Likely <grant.likely@linaro.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: x86@kernel.org
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/20140507154335.959870037@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

New architectures currently have to provide implementations of 5 different
functions: xen_arch_pre_suspend(), xen_arch_post_suspend(),
xen_arch_hvm_post_suspend(), xen_mm_pin_all(), and xen_mm_unpin_all().

Refactor the suspend code to only require xen_arch_pre_suspend() and
xen_arch_post_suspend().
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>

FIFO event channels require bitops on 32-bit aligned values (the event
words).  Linux's bitops require unsigned long alignment which may be
64-bits.

On arm64 an incorrectly unaligned access will fault.

Fix this by aligning the bitops along with an adjustment for bit
position and using an unsigned long for the local copy of the ready
word.

Cc: stable@vger.kernel.org
Signed-off-by: NVladimir Murzin <murzin.v@gmail.com>
Tested-by: NPranavkumar Sawargaonkar <pranavkumar@linaro.org>
Reviewed-by: NIan Campbell <ian.campbell@citrix.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

Mostly scripted conversion of the smp_mb__* barriers.
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Acked-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/n/tip-55dhyhocezdw1dg7u19hmh1u@git.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-arch@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>

The user can launch the guest in this sequence:

xl create -p /vm.cfg	[launch, but pause it]
xl shutdown latest	[sets control/shutdown=poweroff]
xl unpause latest
xl console latest	[and see that the guest has completely
ignored the shutdown request]

In reality the guest hasn't ignored it. It registers a watch
and gets a notification that there is value. It then calls
the shutdown_handler which ends up calling orderly_shutdown.

Unfortunately that is so early in the bootup that there
are no user-space. Which means that the orderly_shutdown fails.
But since the force flag was set to false it continues on without
reporting.

What we really want to is to use the force when we are in the
SYSTEM_BOOTING state and not use the 'force' when SYSTEM_RUNNING.

However, if we are in the running state - and the shutdown command
has been given before the user-space has been setup, there is nothing
we can do. Worst yet, we stop ignoring the 'xl shutdown' requests!

As such, the other part of this patch is to only stop ignoring
the 'xl shutdown' when we are truly in the power off sequence.

That means the user can do multiple 'xl shutdown' and we will try
to act on them instead of ignoring them.

Fixes-Bug: http://bugs.xenproject.org/xen/bug/6Reported-by: NAlex Bligh <alex@alex.org.uk>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

The 'read_reply' works with 'process_msg' to read of a reply in XenBus.
'process_msg' is running from within the 'xenbus' thread. Whenever
a message shows up in XenBus it is put on a xs_state.reply_list list
and 'read_reply' picks it up.

The problem is if the backend domain or the xenstored process is killed.
In which case 'xenbus' is still awaiting - and 'read_reply' if called -
stuck forever waiting for the reply_list to have some contents.

This is normally not a problem - as the backend domain can come back
or the xenstored process can be restarted. However if the domain
is in process of being powered off/restarted/halted - there is no
point of waiting on it coming back - as we are effectively being
terminated and should not impede the progress.

This patch solves this problem by checking whether the guest is the
right domain. If it is an initial domain and hurtling towards death -
there is no point of continuing the wait. All other type of guests
continue with their behavior (as Xenstore is expected to still be
running in another domain).

Fixes-Bug: http://bugs.xenproject.org/xen/bug/8Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

There is a missing curly brace here so we might print some extra debug
information.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

It need to free dev_entry when it failed to assign to a new
slot on the virtual PCI bus.

smatch says:
 drivers/xen/xen-pciback/vpci.c:142 __xen_pcibk_add_pci_dev() warn:
possible memory leak of 'dev_entry'
Signed-off-by: NDaeseok Youn <daeseok.youn@gmail.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>

Patch 99c8b79d "xen: Add proper irq accounting for HYPERCALL vector"
added a call to inc_irq_stat(irq_hv_callback_count) in common Xen code,
however both the inc_irq_stat function and the irq_hv_callback_count
counter are architecture specific.

This makes the code build again on ARM by moving the call into the
existing #ifdef CONFIG_X86. We may want to later do the same implementation
on ARM that x86 has though.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xen <xen-devel@lists.xenproject.org>

Xen balloon driver will update ballooned out pages' P2M entries to point
to scratch page for PV guests. In 24f69373 ("xen/balloon: don't alloc
page while non-preemptible", kmap_flush_unused was moved after updating
P2M table. In that case for 32 bit PV guest we might end up with

  P2M    X -----> S  (S is mfn of balloon scratch page)
  M2P    Y -----> X  (Y is mfn in persistent kmap entry)

kmap_flush_unused() iterates through all the PTEs in the kmap address
space, using pte_to_page() to obtain the page. If the p2m and the m2p
are inconsistent the incorrect page is returned.  This will clear
page->address on the wrong page which may cause subsequent oopses if
that page is currently kmap'ed.

Move the flush back between get_page and __set_phys_to_machine to fix
this.
Signed-off-by: NWei Liu <wei.liu2@citrix.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Cc: stable@vger.kernel.org # 3.12+

Subsystems that want to register CPU hotplug callbacks, as well as perform
initialization for the CPUs that are already online, often do it as shown
below:

	get_online_cpus();

	for_each_online_cpu(cpu)
		init_cpu(cpu);

	register_cpu_notifier(&foobar_cpu_notifier);

	put_online_cpus();

This is wrong, since it is prone to ABBA deadlocks involving the
cpu_add_remove_lock and the cpu_hotplug.lock (when running concurrently
with CPU hotplug operations).

The xen balloon driver doesn't take get/put_online_cpus() around this code,
but that is also buggy, since it can miss CPU hotplug events in between the
initialization and callback registration:

	for_each_online_cpu(cpu)
		init_cpu(cpu);
		   ^
		   |  Race window; Can miss CPU hotplug events here.
		   v
	register_cpu_notifier(&foobar_cpu_notifier);

Interestingly, the balloon code in xen can simply be reorganized as shown
below, to have a race-free method to register hotplug callbacks, without even
taking get/put_online_cpus(). This is because the initialization performed for
already online CPUs is exactly the same as that performed for CPUs that come
online later. Moreover, the code has checks in place to avoid double
initialization.

	register_cpu_notifier(&foobar_cpu_notifier);

	get_online_cpus();

	for_each_online_cpu(cpu)
		init_cpu(cpu);

	put_online_cpus();

A hotplug operation that occurs between registering the notifier and calling
get_online_cpus(), won't disrupt anything, because the code takes care to
perform the memory allocations only once.

So reorganize the balloon code in xen this way to fix the issues with CPU
hotplug callback registration.

Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Ingo Molnar <mingo@kernel.org>
Reviewed-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: NSrivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

syscore->resume() callback is expected to do not enable interrupts,
it generates warning like below otherwise:

[ 9386.365390] WARNING: CPU: 0 PID: 6733 at drivers/base/syscore.c:104 syscore_resume+0x9a/0xe0()
[ 9386.365403] Interrupts enabled after xen_acpi_processor_resume+0x0/0x34 [xen_acpi_processor]
...
[ 9386.365429] Call Trace:
[ 9386.365434]  [<ffffffff81667a8b>] dump_stack+0x45/0x56
[ 9386.365437]  [<ffffffff8106921d>] warn_slowpath_common+0x7d/0xa0
[ 9386.365439]  [<ffffffff8106928c>] warn_slowpath_fmt+0x4c/0x50
[ 9386.365442]  [<ffffffffa0261bb0>] ? xen_upload_processor_pm_data+0x300/0x300 [xen_acpi_processor]
[ 9386.365443]  [<ffffffff814055fa>] syscore_resume+0x9a/0xe0
[ 9386.365445]  [<ffffffff810aef42>] suspend_devices_and_enter+0x402/0x470
[ 9386.365447]  [<ffffffff810af128>] pm_suspend+0x178/0x260

On xen_acpi_processor_resume() we call various procedures, which are
non atomic and can enable interrupts. To prevent the issue introduce
separate resume notify called after we enable interrupts on resume
and before we call other drivers resume callbacks.
Signed-off-by: NStanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

The grant mapping API does m2p_override unnecessarily: only gntdev needs it,
for blkback and future netback patches it just cause a lock contention, as
those pages never go to userspace. Therefore this series does the following:
- the bulk of the original function (everything after the mapping hypercall)
  is moved to arch-dependent set/clear_foreign_p2m_mapping
- the "if (xen_feature(XENFEAT_auto_translated_physmap))" branch goes to ARM
- therefore the ARM function could be much smaller, the m2p_override stubs
  could be also removed
- on x86 the set_phys_to_machine calls were moved up to this new funcion
  from m2p_override functions
- and m2p_override functions are only called when there is a kmap_ops param

It also removes a stray space from arch/x86/include/asm/xen/page.h.
Signed-off-by: NZoltan Kiss <zoltan.kiss@citrix.com>
Suggested-by: NAnthony Liguori <aliguori@amazon.com>
Suggested-by: NDavid Vrabel <david.vrabel@citrix.com>
Suggested-by: NStefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Signed-off-by: NStefano Stabellini <stefano.stabellini@eu.citrix.com>

Add support for MSI message groups for Xen Dom0 using the
MAP_PIRQ_TYPE_MULTI_MSI pirq map type.

In order to keep track of which pirq is the first one in the group all
pirqs in the MSI group except for the first one have the newly
introduced PIRQ_MSI_GROUP flag set. This prevents calling
PHYSDEVOP_unmap_pirq on them, since the unmap must be done with the
first pirq in the group.
Signed-off-by: NRoger Pau Monné <roger.pau@citrix.com>
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>

The user space interface does not filter out offline cpus. It merily
verifies that the mask contains at least one online cpu. So the
selector in the irq chip implementation needs to make sure to pick
only an online cpu because otherwise:

     Offline Core 1
     Set affinity to 0xe
     Selector will pick first set bit, i.e. core 1
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NDavid Vrabel <david.vrabel@citrix.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xen <xen-devel@lists.xenproject.org>
Link: http://lkml.kernel.org/r/20140304203100.978031089@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>