[PATCH v8] Xen PCI + Xen PCI frontend driver.

[PATCH v8] Xen PCI + Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

This patch set contains the supporting patches and the driver itself for
Xen Paravirtualized (PV) domains to use PCI pass-through devices (the git tree
is git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git devel/xen-pcifront-0.8).
This patch-set is also utilized in Stefano's PV on HVM MSI/MSI-X patchset [1].

Changelog since v7 [http://lwn.net/Articles/408418/] posting:
 - Added Reviewed-by/Acked-by on some of the patches.
 - Fleshed out comments.
 - Ditched the io_apic.c idea and used Thomas Gleixner idea.

The Xen PCI frontend driver can be used by PV guests on IOMMU hardware
(or IOMMU-less). Without the hardware IOMMU you have a potential security
hole wherein a guest domain can use the hardware to map pages outside its
memory range and slurp pages up. As such, this is more restricted to a
Privileged PV domain, aka - device driver domain (similar to Qubes but a
poor-man mechanism [2]).

The first set of patches are specific to the Xen subsystem, where
we introduce an IRQ chip for Physical IRQs, along with the supporting
harness code:
 xen: Don't disable the I/O space
 xen: define BIOVEC_PHYS_MERGEABLE()
 xen: implement pirq type event channels
 xen: identity map gsi->irqs
 xen: dynamically allocate irq & event structures
 xen: set pirq name to something useful.
 xen: statically initialize cpu_evtchn_mask_p
 xen: Find an unbound irq number in reverse order (high to low).
 xen: Provide a variant of xen_poll_irq with timeout.
 xen: fix shared irq device passthrough

The next set of patches expose functionality for module drivers to be able to
enumerate and iomap (using the _PAGE_IOMAP flag) PCI devices.

 x86/io_apic: add get_nr_irqs_gsi()
 x86/PCI: Clean up pci_cache_line_size
 x86/PCI: make sure _PAGE_IOMAP it set on pci mappings
 x86/PCI: Export pci_walk_bus function.

The next two patches abstract the MSI/MSI-X architecture calls so that the
default native one (used on bare-metal) can be overwritten when running
in virtualized mode (right now on Xen). The implementation is a simple
function pointer structure.

 msi: Introduce default_[teardown|setup]_msi_irqs with fallback.
 x86: Introduce x86_msi_ops

Next, the Xen PCI stub driver. I've put it in the same location
where other sub-platform PCI drivers are. It hooks up to the
PCI legacy IRQ setup ('pcibios_enable_irq'), and MSI/MSI-X
allocation/de-allocation (via the x86_msi_ops introduced in earlier patches).

 xen/x86/PCI: Add support for the Xen PCI subsystem

Lastly, the Xen PCI front-end driver which is responsible for hooking up
to the PCI configuration read/write methods via the 'pci_scan_bus_parented' call.
In essence all pci_conf_read/write in the guest will be tunneled via
pcifront_bus_[read|write] methods. The MSI/MSI-X calls will be handled
by the Xen-PCI front-end driver as well. We also need to add a new
state so updating the XenBus:

 xenbus: Xen paravirtualised PCI hotplug support.
 xenbus: prevent warnings on unhandled enumeration values
 xen-pcifront: Xen PCI frontend driver.

The last three are two bug fixes and updating the MAINTAINERs file
with my name:

 xen/pci: Request ACS when Xen-SWIOTLB is activated.
 MAINTAINERS: Add myself for Xen PCI and Xen SWIOTLB maintainer.
 swiotlb-xen: On x86-32 builts, select SWIOTLB instead of depending on it.

The shortlog and the diffstat:

Alex Nixon (3):
      xen: Don't disable the I/O space
      x86/PCI: Clean up pci_cache_line_size
      xen/x86/PCI: Add support for the Xen PCI subsystem

Gerd Hoffmann (1):
      xen: set pirq name to something useful.

Jeremy Fitzhardinge (7):
      xen: define BIOVEC_PHYS_MERGEABLE()
      xen: implement pirq type event channels
      x86/io_apic: add get_nr_irqs_gsi()
      xen: identity map gsi->irqs
      xen: dynamically allocate irq & event structures
      xen: statically initialize cpu_evtchn_mask_p
      x86/PCI: make sure _PAGE_IOMAP it set on pci mappings

Konrad Rzeszutek Wilk (7):
      xen: Find an unbound irq number in reverse order (high to low).
      xen: Provide a variant of xen_poll_irq with timeout.
      xen: fix shared irq device passthrough
      x86/PCI: Export pci_walk_bus function.
      xen/pci: Request ACS when Xen-SWIOTLB is activated.
      MAINTAINERS: Add myself for Xen PCI and Xen SWIOTLB maintainer.
      swiotlb-xen: On x86-32 builts, select SWIOTLB instead of depending on it.

Noboru Iwamatsu (1):
      xenbus: prevent warnings on unhandled enumeration values

Ryan Wilson (1):
      xen-pcifront: Xen PCI frontend driver.

Stefano Stabellini (1):
      x86: Introduce x86_msi_ops

Thomas Gleixner (1):
      msi: Introduce default_[teardown|setup]_msi_irqs with fallback.

Yosuke Iwamatsu (1):
      xenbus: Xen paravirtualised PCI hotplug support.


 MAINTAINERS                        |   14 +
 arch/x86/Kconfig                   |    5 +
 arch/x86/include/asm/io.h          |   13 +
 arch/x86/include/asm/io_apic.h     |    1 +
 arch/x86/include/asm/pci.h         |   33 +-
 arch/x86/include/asm/pci_x86.h     |    1 +
 arch/x86/include/asm/x86_init.h    |    9 +
 arch/x86/include/asm/xen/pci.h     |   53 ++
 arch/x86/kernel/apic/io_apic.c     |    9 +-
 arch/x86/kernel/x86_init.c         |    7 +
 arch/x86/pci/Makefile              |    1 +
 arch/x86/pci/common.c              |   17 +-
 arch/x86/pci/i386.c                |    2 +
 arch/x86/pci/xen.c                 |  147 +++++
 arch/x86/xen/enlighten.c           |    3 +
 arch/x86/xen/pci-swiotlb-xen.c     |    4 +
 arch/x86/xen/setup.c               |    2 -
 drivers/block/xen-blkfront.c       |    2 +
 drivers/input/xen-kbdfront.c       |    2 +
 drivers/net/xen-netfront.c         |    2 +
 drivers/pci/Kconfig                |   15 +
 drivers/pci/Makefile               |    2 +
 drivers/pci/bus.c                  |    1 +
 drivers/pci/msi.c                  |   14 +-
 drivers/pci/xen-pcifront.c         | 1157 ++++++++++++++++++++++++++++++++++++
 drivers/video/xen-fbfront.c        |    2 +
 drivers/xen/Kconfig                |    3 +-
 drivers/xen/Makefile               |    2 +-
 drivers/xen/biomerge.c             |   13 +
 drivers/xen/events.c               |  345 ++++++++++-
 drivers/xen/xenbus/xenbus_client.c |    2 +
 include/xen/events.h               |   18 +
 include/xen/interface/io/pciif.h   |  112 ++++
 include/xen/interface/io/xenbus.h  |    8 +-
 34 files changed, 1987 insertions(+), 34 deletions(-)

P.S.
[1]. git://xenbits.xen.org/people/sstabellini/linux-pvhvm.git 2.6.36-rc1-pvhvm-pirq-v3

[2]: http://qubes-os.org/ which utilizes hardware IOMMU to run seperate domains wherein
each has specific access to hardware.

[3] Some of the authors of the patches have moved on, so their e-mails
are bouncing. I am purposly making the 'From' a valid email so that the patches
do show up on LKML. The git tree contains their proper old email addresses.

[PATCH 01/23] xen: Don't disable the I/O space

[Konrad Rzeszutek Wilk]

From: Alex Nixon <alex.nixon@darnok.org>

If a guest domain wants to access PCI devices through the frontend
driver (coming later in the patch series), it will need access to the
I/O space.

[ Impact: Allow for domU IO access, preparing for pci passthrough ]

Signed-off-by: Alex Nixon <alex.nixon@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/xen/setup.c |    2 --
 1 files changed, 0 insertions(+), 2 deletions(-)

diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 328b003..c413132 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -260,7 +260,5 @@ void __init xen_arch_setup(void)
 
 	pm_idle = xen_idle;
 
-	paravirt_disable_iospace();
-
 	fiddle_vdso();
 }
-- 
1.7.0.4

[PATCH 02/23] xen: define BIOVEC_PHYS_MERGEABLE()

[Konrad Rzeszutek Wilk]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

Impact: allow Xen control of bio merging

When running in Xen domain with device access, we need to make sure
the block subsystem doesn't merge requests across pages which aren't
machine physically contiguous.  To do this, we define our own
BIOVEC_PHYS_MERGEABLE.  When CONFIG_XEN isn't enabled, or we're not
running in a Xen domain, this has identical behaviour to the normal
implementation.  When running under Xen, we also make sure the
underlying machine pages are the same or adjacent.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/include/asm/io.h |   13 +++++++++++++
 drivers/xen/Makefile      |    2 +-
 drivers/xen/biomerge.c    |   13 +++++++++++++
 3 files changed, 27 insertions(+), 1 deletions(-)
 create mode 100644 drivers/xen/biomerge.c

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 30a3e97..0ad29d4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -41,6 +41,8 @@
 #include <asm-generic/int-ll64.h>
 #include <asm/page.h>
 
+#include <xen/xen.h>
+
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
 { type ret; asm volatile("mov" size " %1,%0":reg (ret) \
@@ -349,6 +351,17 @@ extern void __iomem *early_memremap(resource_size_t phys_addr,
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 extern void fixup_early_ioremap(void);
 
+#ifdef CONFIG_XEN
+struct bio_vec;
+
+extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+				      const struct bio_vec *vec2);
+
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
+	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
+	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
+#endif	/* CONFIG_XEN */
+
 #define IO_SPACE_LIMIT 0xffff
 
 #endif /* _ASM_X86_IO_H */
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index fcaf838..b47f5da 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -1,4 +1,4 @@
-obj-y	+= grant-table.o features.o events.o manage.o
+obj-y	+= grant-table.o features.o events.o manage.o biomerge.o
 obj-y	+= xenbus/
 
 nostackp := $(call cc-option, -fno-stack-protector)
diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c
new file mode 100644
index 0000000..ba6eda4
--- /dev/null
+++ b/drivers/xen/biomerge.c
@@ -0,0 +1,13 @@
+#include <linux/bio.h>
+#include <linux/io.h>
+#include <xen/page.h>
+
+bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+			       const struct bio_vec *vec2)
+{
+	unsigned long mfn1 = pfn_to_mfn(page_to_pfn(vec1->bv_page));
+	unsigned long mfn2 = pfn_to_mfn(page_to_pfn(vec2->bv_page));
+
+	return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&
+		((mfn1 == mfn2) || ((mfn1+1) == mfn2));
+}
-- 
1.7.0.4

[PATCH 03/23] xen: implement pirq type event channels

[Konrad Rzeszutek Wilk]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

A privileged PV Xen domain can get direct access to hardware.  In
order for this to be useful, it must be able to get hardware
interrupts.

Being a PV Xen domain, all interrupts are delivered as event channels.
PIRQ event channels are bound to a pirq number and an interrupt
vector.  When a IO APIC raises a hardware interrupt on that vector, it
is delivered as an event channel, which we can deliver to the
appropriate device driver(s).

This patch simply implements the infrastructure for dealing with pirq
event channels.

[ Impact: integrate hardware interrupts into Xen's event scheme ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/events.c |  243 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/xen/events.h |   11 +++
 2 files changed, 252 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 13365ba..b8f030a 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -16,7 +16,7 @@
  *    (typically dom0).
  * 2. VIRQs, typically used for timers.  These are per-cpu events.
  * 3. IPIs.
- * 4. Hardware interrupts. Not supported at present.
+ * 4. PIRQs - Hardware interrupts.
  *
  * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
  */
@@ -46,6 +46,9 @@
 #include <xen/interface/hvm/hvm_op.h>
 #include <xen/interface/hvm/params.h>
 
+/* Leave low irqs free for identity mapping */
+#define LEGACY_IRQS	16
+
 /*
  * This lock protects updates to the following mapping and reference-count
  * arrays. The lock does not need to be acquired to read the mapping tables.
@@ -89,10 +92,12 @@ struct irq_info
 		enum ipi_vector ipi;
 		struct {
 			unsigned short gsi;
-			unsigned short vector;
+			unsigned char vector;
+			unsigned char flags;
 		} pirq;
 	} u;
 };
+#define PIRQ_NEEDS_EOI	(1 << 0)
 
 static struct irq_info irq_info[NR_IRQS];
 
@@ -113,6 +118,7 @@ static inline unsigned long *cpu_evtchn_mask(int cpu)
 
 static struct irq_chip xen_dynamic_chip;
 static struct irq_chip xen_percpu_chip;
+static struct irq_chip xen_pirq_chip;
 
 /* Constructor for packed IRQ information. */
 static struct irq_info mk_unbound_info(void)
@@ -225,6 +231,15 @@ static unsigned int cpu_from_evtchn(unsigned int evtchn)
 	return ret;
 }
 
+static bool pirq_needs_eoi(unsigned irq)
+{
+	struct irq_info *info = info_for_irq(irq);
+
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
+}
+
 static inline unsigned long active_evtchns(unsigned int cpu,
 					   struct shared_info *sh,
 					   unsigned int idx)
@@ -366,6 +381,210 @@ static int find_unbound_irq(void)
 	return irq;
 }
 
+static bool identity_mapped_irq(unsigned irq)
+{
+	/* only identity map legacy irqs */
+	return irq < LEGACY_IRQS;
+}
+
+static void pirq_unmask_notify(int irq)
+{
+	struct physdev_eoi eoi = { .irq = irq };
+
+	if (unlikely(pirq_needs_eoi(irq))) {
+		int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
+		WARN_ON(rc);
+	}
+}
+
+static void pirq_query_unmask(int irq)
+{
+	struct physdev_irq_status_query irq_status;
+	struct irq_info *info = info_for_irq(irq);
+
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	irq_status.irq = irq;
+	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
+		irq_status.flags = 0;
+
+	info->u.pirq.flags &= ~PIRQ_NEEDS_EOI;
+	if (irq_status.flags & XENIRQSTAT_needs_eoi)
+		info->u.pirq.flags |= PIRQ_NEEDS_EOI;
+}
+
+static bool probing_irq(int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	return desc && desc->action == NULL;
+}
+
+static unsigned int startup_pirq(unsigned int irq)
+{
+	struct evtchn_bind_pirq bind_pirq;
+	struct irq_info *info = info_for_irq(irq);
+	int evtchn = evtchn_from_irq(irq);
+
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	if (VALID_EVTCHN(evtchn))
+		goto out;
+
+	bind_pirq.pirq = irq;
+	/* NB. We are happy to share unless we are probing. */
+	bind_pirq.flags = probing_irq(irq) ? 0 : BIND_PIRQ__WILL_SHARE;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq) != 0) {
+		if (!probing_irq(irq))
+			printk(KERN_INFO "Failed to obtain physical IRQ %d\n",
+			       irq);
+		return 0;
+	}
+	evtchn = bind_pirq.port;
+
+	pirq_query_unmask(irq);
+
+	evtchn_to_irq[evtchn] = irq;
+	bind_evtchn_to_cpu(evtchn, 0);
+	info->evtchn = evtchn;
+
+out:
+	unmask_evtchn(evtchn);
+	pirq_unmask_notify(irq);
+
+	return 0;
+}
+
+static void shutdown_pirq(unsigned int irq)
+{
+	struct evtchn_close close;
+	struct irq_info *info = info_for_irq(irq);
+	int evtchn = evtchn_from_irq(irq);
+
+	BUG_ON(info->type != IRQT_PIRQ);
+
+	if (!VALID_EVTCHN(evtchn))
+		return;
+
+	mask_evtchn(evtchn);
+
+	close.port = evtchn;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+		BUG();
+
+	bind_evtchn_to_cpu(evtchn, 0);
+	evtchn_to_irq[evtchn] = -1;
+	info->evtchn = 0;
+}
+
+static void enable_pirq(unsigned int irq)
+{
+	startup_pirq(irq);
+}
+
+static void disable_pirq(unsigned int irq)
+{
+}
+
+static void ack_pirq(unsigned int irq)
+{
+	int evtchn = evtchn_from_irq(irq);
+
+	move_native_irq(irq);
+
+	if (VALID_EVTCHN(evtchn)) {
+		mask_evtchn(evtchn);
+		clear_evtchn(evtchn);
+	}
+}
+
+static void end_pirq(unsigned int irq)
+{
+	int evtchn = evtchn_from_irq(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (WARN_ON(!desc))
+		return;
+
+	if ((desc->status & (IRQ_DISABLED|IRQ_PENDING)) ==
+	    (IRQ_DISABLED|IRQ_PENDING)) {
+		shutdown_pirq(irq);
+	} else if (VALID_EVTCHN(evtchn)) {
+		unmask_evtchn(evtchn);
+		pirq_unmask_notify(irq);
+	}
+}
+
+static int find_irq_by_gsi(unsigned gsi)
+{
+	int irq;
+
+	for (irq = 0; irq < NR_IRQS; irq++) {
+		struct irq_info *info = info_for_irq(irq);
+
+		if (info == NULL || info->type != IRQT_PIRQ)
+			continue;
+
+		if (gsi_from_irq(irq) == gsi)
+			return irq;
+	}
+
+	return -1;
+}
+
+/*
+ * Allocate a physical irq, along with a vector.  We don't assign an
+ * event channel until the irq actually started up.  Return an
+ * existing irq if we've already got one for the gsi.
+ */
+int xen_allocate_pirq(unsigned gsi)
+{
+	int irq;
+	struct physdev_irq irq_op;
+
+	spin_lock(&irq_mapping_update_lock);
+
+	irq = find_irq_by_gsi(gsi);
+	if (irq != -1) {
+		printk(KERN_INFO "xen_allocate_pirq: returning irq %d for gsi %u\n",
+		       irq, gsi);
+		goto out;	/* XXX need refcount? */
+	}
+
+	if (identity_mapped_irq(gsi)) {
+		irq = gsi;
+		dynamic_irq_init(irq);
+	} else
+		irq = find_unbound_irq();
+
+	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
+				      handle_level_irq, "pirq");
+
+	irq_op.irq = irq;
+	if (HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
+		dynamic_irq_cleanup(irq);
+		irq = -ENOSPC;
+		goto out;
+	}
+
+	irq_info[irq] = mk_pirq_info(0, gsi, irq_op.vector);
+
+out:
+	spin_unlock(&irq_mapping_update_lock);
+
+	return irq;
+}
+
+int xen_vector_from_irq(unsigned irq)
+{
+	return vector_from_irq(irq);
+}
+
+int xen_gsi_from_irq(unsigned irq)
+{
+	return gsi_from_irq(irq);
+}
+
 int bind_evtchn_to_irq(unsigned int evtchn)
 {
 	int irq;
@@ -965,6 +1184,26 @@ static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.retrigger	= retrigger_dynirq,
 };
 
+static struct irq_chip xen_pirq_chip __read_mostly = {
+	.name		= "xen-pirq",
+
+	.startup	= startup_pirq,
+	.shutdown	= shutdown_pirq,
+
+	.enable		= enable_pirq,
+	.unmask		= enable_pirq,
+
+	.disable	= disable_pirq,
+	.mask		= disable_pirq,
+
+	.ack		= ack_pirq,
+	.end		= end_pirq,
+
+	.set_affinity	= set_affinity_irq,
+
+	.retrigger	= retrigger_dynirq,
+};
+
 static struct irq_chip xen_percpu_chip __read_mostly = {
 	.name		= "xen-percpu",
 
diff --git a/include/xen/events.h b/include/xen/events.h
index a15d932..8f62320 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -63,4 +63,15 @@ int xen_set_callback_via(uint64_t via);
 void xen_evtchn_do_upcall(struct pt_regs *regs);
 void xen_hvm_evtchn_do_upcall(void);
 
+/* Allocate an irq for a physical interrupt, given a gsi.  "Legacy"
+ * GSIs are identity mapped; others are dynamically allocated as
+ * usual. */
+int xen_allocate_pirq(unsigned gsi);
+
+/* Return vector allocated to pirq */
+int xen_vector_from_irq(unsigned pirq);
+
+/* Return gsi allocated to pirq */
+int xen_gsi_from_irq(unsigned pirq);
+
 #endif	/* _XEN_EVENTS_H */
-- 
1.7.0.4

[PATCH 04/23] x86/io_apic: add get_nr_irqs_gsi()

[Konrad Rzeszutek Wilk]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

Impact: new interface to get max GSI

Add get_nr_irqs_gsi() to return nr_irqs_gsi.  Xen will use this to
determine how many irqs it needs to reserve for hardware irqs.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: "H. Peter Anvin" <hpa@zytor.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/include/asm/io_apic.h |    1 +
 arch/x86/kernel/apic/io_apic.c |    5 +++++
 2 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 9cb2edb..f27c681 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -169,6 +169,7 @@ extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 
 extern void probe_nr_irqs_gsi(void);
+extern int get_nr_irqs_gsi(void);
 
 extern int setup_ioapic_entry(int apic, int irq,
 			      struct IO_APIC_route_entry *entry,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f1efeba..4c9b2b9 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3862,6 +3862,11 @@ void __init probe_nr_irqs_gsi(void)
 	printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
 }
 
+int get_nr_irqs_gsi(void)
+{
+	return nr_irqs_gsi;
+}
+
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
-- 
1.7.0.4

[PATCH 05/23] xen: identity map gsi->irqs

[Konrad Rzeszutek Wilk]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

Impact: preserve compat with native

Reserve the lower irq range for use for hardware interrupts so we
can identity-map them.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/events.c |   23 +++++++++++++++++------
 1 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index b8f030a..8eeb808 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -33,6 +33,7 @@
 #include <asm/ptrace.h>
 #include <asm/irq.h>
 #include <asm/idle.h>
+#include <asm/io_apic.h>
 #include <asm/sync_bitops.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -46,9 +47,6 @@
 #include <xen/interface/hvm/hvm_op.h>
 #include <xen/interface/hvm/params.h>
 
-/* Leave low irqs free for identity mapping */
-#define LEGACY_IRQS	16
-
 /*
  * This lock protects updates to the following mapping and reference-count
  * arrays. The lock does not need to be acquired to read the mapping tables.
@@ -351,12 +349,24 @@ static void unmask_evtchn(int port)
 	put_cpu();
 }
 
+static int get_nr_hw_irqs(void)
+{
+	int ret = 1;
+
+#ifdef CONFIG_X86_IO_APIC
+	ret = get_nr_irqs_gsi();
+#endif
+
+	return ret;
+}
+
 static int find_unbound_irq(void)
 {
 	int irq;
 	struct irq_desc *desc;
+	int start = get_nr_hw_irqs();
 
-	for (irq = 0; irq < nr_irqs; irq++) {
+	for (irq = start; irq < nr_irqs; irq++) {
 		desc = irq_to_desc(irq);
 		/* only 0->15 have init'd desc; handle irq > 16 */
 		if (desc == NULL)
@@ -383,8 +393,8 @@ static int find_unbound_irq(void)
 
 static bool identity_mapped_irq(unsigned irq)
 {
-	/* only identity map legacy irqs */
-	return irq < LEGACY_IRQS;
+	/* identity map all the hardware irqs */
+	return irq < get_nr_hw_irqs();
 }
 
 static void pirq_unmask_notify(int irq)
@@ -553,6 +563,7 @@ int xen_allocate_pirq(unsigned gsi)
 
 	if (identity_mapped_irq(gsi)) {
 		irq = gsi;
+		irq_to_desc_alloc_node(irq, 0);
 		dynamic_irq_init(irq);
 	} else
 		irq = find_unbound_irq();
-- 
1.7.0.4

[PATCH 06/23] xen: dynamically allocate irq & event structures

[Konrad Rzeszutek Wilk]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

Dynamically allocate the irq_info and evtchn_to_irq arrays, so that
1) the irq_info array scales to the actual number of possible irqs,
and 2) we don't needlessly increase the static size of the kernel
when we aren't running under Xen.

Derived on patch from Mike Travis <travis@sgi.com>.

[Impact: reduce memory usage ]
[v2: Conflict in drivers/xen/events.c: Replaced alloc_bootmen with kcalloc ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/events.c |   16 ++++++++++------
 1 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 8eeb808..25412ef 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -28,6 +28,7 @@
 #include <linux/string.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>
+#include <linux/irqnr.h>
 
 #include <asm/desc.h>
 #include <asm/ptrace.h>
@@ -97,11 +98,9 @@ struct irq_info
 };
 #define PIRQ_NEEDS_EOI	(1 << 0)
 
-static struct irq_info irq_info[NR_IRQS];
+static struct irq_info *irq_info;
 
-static int evtchn_to_irq[NR_EVENT_CHANNELS] = {
-	[0 ... NR_EVENT_CHANNELS-1] = -1
-};
+static int *evtchn_to_irq;
 struct cpu_evtchn_s {
 	unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG];
 };
@@ -529,7 +528,7 @@ static int find_irq_by_gsi(unsigned gsi)
 {
 	int irq;
 
-	for (irq = 0; irq < NR_IRQS; irq++) {
+	for (irq = 0; irq < nr_irqs; irq++) {
 		struct irq_info *info = info_for_irq(irq);
 
 		if (info == NULL || info->type != IRQT_PIRQ)
@@ -1269,7 +1268,12 @@ void __init xen_init_IRQ(void)
 
 	cpu_evtchn_mask_p = kcalloc(nr_cpu_ids, sizeof(struct cpu_evtchn_s),
 				    GFP_KERNEL);
-	BUG_ON(cpu_evtchn_mask_p == NULL);
+	irq_info = kcalloc(nr_irqs, sizeof(*irq_info), GFP_KERNEL);
+
+	evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
+				    GFP_KERNEL);
+	for (i = 0; i < NR_EVENT_CHANNELS; i++)
+		evtchn_to_irq[i] = -1;
 
 	init_evtchn_cpu_bindings();
 
-- 
1.7.0.4

[PATCH 07/23] xen: set pirq name to something useful.

[Konrad Rzeszutek Wilk]

From: Gerd Hoffmann <kraxel@redhat.com>

Impact: cleanup

Make pirq show useful information in /proc/interrupts

[v2: Removed the parts for arch/x86/xen/pci.c ]

Signed-off-by: Gerd Hoffmann <kraxel@xeni.home.kraxel.org>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/events.c |    4 ++--
 include/xen/events.h |    2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 25412ef..a98e720 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -546,7 +546,7 @@ static int find_irq_by_gsi(unsigned gsi)
  * event channel until the irq actually started up.  Return an
  * existing irq if we've already got one for the gsi.
  */
-int xen_allocate_pirq(unsigned gsi)
+int xen_allocate_pirq(unsigned gsi, char *name)
 {
 	int irq;
 	struct physdev_irq irq_op;
@@ -568,7 +568,7 @@ int xen_allocate_pirq(unsigned gsi)
 		irq = find_unbound_irq();
 
 	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
-				      handle_level_irq, "pirq");
+				      handle_level_irq, name);
 
 	irq_op.irq = irq;
 	if (HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
diff --git a/include/xen/events.h b/include/xen/events.h
index 8f62320..8227da8 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -66,7 +66,7 @@ void xen_hvm_evtchn_do_upcall(void);
 /* Allocate an irq for a physical interrupt, given a gsi.  "Legacy"
  * GSIs are identity mapped; others are dynamically allocated as
  * usual. */
-int xen_allocate_pirq(unsigned gsi);
+int xen_allocate_pirq(unsigned gsi, char *name);
 
 /* Return vector allocated to pirq */
 int xen_vector_from_irq(unsigned pirq);
-- 
1.7.0.4

[PATCH 08/23] xen: statically initialize cpu_evtchn_mask_p

[Konrad Rzeszutek Wilk]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

Sometimes cpu_evtchn_mask_p can get used early, before it has been
allocated.  Statically initialize it with an initdata version to catch
any early references.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/events.c |    7 ++++++-
 1 files changed, 6 insertions(+), 1 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index a98e720..e1bd0be 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -104,7 +104,12 @@ static int *evtchn_to_irq;
 struct cpu_evtchn_s {
 	unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG];
 };
-static struct cpu_evtchn_s *cpu_evtchn_mask_p;
+
+static __initdata struct cpu_evtchn_s init_evtchn_mask = {
+	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
+};
+static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
+
 static inline unsigned long *cpu_evtchn_mask(int cpu)
 {
 	return cpu_evtchn_mask_p[cpu].bits;
-- 
1.7.0.4

[PATCH 09/23] xen: Find an unbound irq number in reverse order (high to low).

[Konrad Rzeszutek Wilk]

In earlier Xen Linux kernels, the IRQ mapping was a straight 1:1 and the
find_unbound_irq started looking around 256 for open IRQs and up. IRQs
from 0 to 255 were reserved for PCI devices.  Previous to this patch,
the 'find_unbound_irq'  started looking at get_nr_hw_irqs() number.
For privileged  domain where the ACPI information is available that
returns the upper-bound of what the GSIs. For non-privileged PV domains,
where ACPI is no-existent the get_nr_hw_irqs() reports the IRQ_LEGACY (16).
With PCI passthrough enabled, and with PCI cards that have IRQs pinned
to a higher number than 16 we collide with previously allocated IRQs.
Specifically the PCI IRQs collide with the IPI's for Xen functions
(as they are allocated earlier).
For example:

00:00.11 USB Controller: ATI Technologies Inc SB700 USB OHCI1 Controller (prog-if 10 [OHCI])
	...
	Interrupt: pin A routed to IRQ 18

[root@localhost ~]# cat /proc/interrupts | head
           CPU0       CPU1       CPU2
 16:      38186          0          0   xen-dyn-virq      timer0
 17:        149          0          0   xen-dyn-ipi       spinlock0
 18:        962          0          0   xen-dyn-ipi       resched0

and when the USB controller is loaded, the kernel reports:
IRQ handler type mismatch for IRQ 18
current handler: resched0

One way to fix this is to reverse the logic when looking for un-used
IRQ numbers and start with the highest available number. With that,
we would get:

           CPU0       CPU1       CPU2
... snip ..
292:         35          0          0   xen-dyn-ipi       callfunc0
293:       3992          0          0   xen-dyn-ipi       resched0
294:        224          0          0   xen-dyn-ipi       spinlock0
295:      57183          0          0   xen-dyn-virq      timer0
NMI:          0          0          0   Non-maskable interrupts
.. snip ..

And interrupts for PCI cards are now accessible.

This patch also includes the fix, found by Ian Campbell, titled
"xen: fix off-by-one error in find_unbound_irq."

[v2: Added an explanation in the code]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 drivers/xen/events.c |   24 +++++++++++++++++++-----
 1 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index e1bd0be..8ae696f 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -370,7 +370,11 @@ static int find_unbound_irq(void)
 	struct irq_desc *desc;
 	int start = get_nr_hw_irqs();
 
-	for (irq = start; irq < nr_irqs; irq++) {
+	if (start == nr_irqs)
+		goto no_irqs;
+
+	/* nr_irqs is a magic value. Must not use it.*/
+	for (irq = nr_irqs-1; irq > start; irq--) {
 		desc = irq_to_desc(irq);
 		/* only 0->15 have init'd desc; handle irq > 16 */
 		if (desc == NULL)
@@ -383,8 +387,8 @@ static int find_unbound_irq(void)
 			break;
 	}
 
-	if (irq == nr_irqs)
-		panic("No available IRQ to bind to: increase nr_irqs!\n");
+	if (irq == start)
+		goto no_irqs;
 
 	desc = irq_to_desc_alloc_node(irq, 0);
 	if (WARN_ON(desc == NULL))
@@ -393,6 +397,9 @@ static int find_unbound_irq(void)
 	dynamic_irq_init_keep_chip_data(irq);
 
 	return irq;
+
+no_irqs:
+	panic("No available IRQ to bind to: increase nr_irqs!\n");
 }
 
 static bool identity_mapped_irq(unsigned irq)
@@ -546,8 +553,15 @@ static int find_irq_by_gsi(unsigned gsi)
 	return -1;
 }
 
-/*
- * Allocate a physical irq, along with a vector.  We don't assign an
+/* xen_allocate_irq might allocate irqs from the top down, as a
+ * consequence don't assume that the irq number returned has a low value
+ * or can be used as a pirq number unless you know otherwise.
+ *
+ * One notable exception is when xen_allocate_irq is called passing an
+ * hardware gsi as argument, in that case the irq number returned
+ * matches the gsi number passed as first argument.
+
+ * Note: We don't assign an
  * event channel until the irq actually started up.  Return an
  * existing irq if we've already got one for the gsi.
  */
-- 
1.7.0.4

[PATCH 10/23] xen: Provide a variant of xen_poll_irq with timeout.

[Konrad Rzeszutek Wilk]

The 'xen_poll_irq_timeout' provides a method to pass in
the poll timeout for IRQs if requested. We also export
those two poll functions as Xen PCI fronted uses them.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 drivers/xen/events.c |   17 ++++++++++++-----
 include/xen/events.h |    4 ++++
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 8ae696f..427f2d8 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -1140,7 +1140,7 @@ void xen_clear_irq_pending(int irq)
 	if (VALID_EVTCHN(evtchn))
 		clear_evtchn(evtchn);
 }
-
+EXPORT_SYMBOL(xen_clear_irq_pending);
 void xen_set_irq_pending(int irq)
 {
 	int evtchn = evtchn_from_irq(irq);
@@ -1160,9 +1160,9 @@ bool xen_test_irq_pending(int irq)
 	return ret;
 }
 
-/* Poll waiting for an irq to become pending.  In the usual case, the
-   irq will be disabled so it won't deliver an interrupt. */
-void xen_poll_irq(int irq)
+/* Poll waiting for an irq to become pending with timeout.  In the usual case,
+ * the irq will be disabled so it won't deliver an interrupt. */
+void xen_poll_irq_timeout(int irq, u64 timeout)
 {
 	evtchn_port_t evtchn = evtchn_from_irq(irq);
 
@@ -1170,13 +1170,20 @@ void xen_poll_irq(int irq)
 		struct sched_poll poll;
 
 		poll.nr_ports = 1;
-		poll.timeout = 0;
+		poll.timeout = timeout;
 		set_xen_guest_handle(poll.ports, &evtchn);
 
 		if (HYPERVISOR_sched_op(SCHEDOP_poll, &poll) != 0)
 			BUG();
 	}
 }
+EXPORT_SYMBOL(xen_poll_irq_timeout);
+/* Poll waiting for an irq to become pending.  In the usual case, the
+ * irq will be disabled so it won't deliver an interrupt. */
+void xen_poll_irq(int irq)
+{
+	xen_poll_irq_timeout(irq, 0 /* no timeout */);
+}
 
 void xen_irq_resume(void)
 {
diff --git a/include/xen/events.h b/include/xen/events.h
index 8227da8..2532f8b 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -53,6 +53,10 @@ bool xen_test_irq_pending(int irq);
    irq will be disabled so it won't deliver an interrupt. */
 void xen_poll_irq(int irq);
 
+/* Poll waiting for an irq to become pending with a timeout.  In the usual case,
+ * the irq will be disabled so it won't deliver an interrupt. */
+void xen_poll_irq_timeout(int irq, u64 timeout);
+
 /* Determine the IRQ which is bound to an event channel */
 unsigned irq_from_evtchn(unsigned int evtchn);
 
-- 
1.7.0.4

[PATCH 11/23] xen: fix shared irq device passthrough

[Konrad Rzeszutek Wilk]

In driver/xen/events.c, whether bind_pirq is shareable or not is
determined by desc->action is NULL or not. But in __setup_irq,
startup(irq) is invoked before desc->action is assigned with
new action. So desc->action in startup_irq is always NULL, and
bind_pirq is always not shareable. This results in pt_irq_create_bind
failure when passthrough a device which shares irq to other devices.

This patch doesn't use probing_irq to determine if pirq is shareable
or not, instead set shareable flag in irq_info according to trigger
mode in xen_allocate_pirq. Set level triggered interrupts shareable.
Thus use this flag to set bind_pirq flag accordingly.

[v2: arch/x86/xen/pci.c no more, so file skipped]

Signed-off-by: Weidong Han <weidong.han@intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/events.c |   11 ++++++++---
 include/xen/events.h |    2 +-
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 427f2d8..bf1dde6 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -97,6 +97,7 @@ struct irq_info
 	} u;
 };
 #define PIRQ_NEEDS_EOI	(1 << 0)
+#define PIRQ_SHAREABLE	(1 << 1)
 
 static struct irq_info *irq_info;
 
@@ -446,6 +447,7 @@ static unsigned int startup_pirq(unsigned int irq)
 	struct evtchn_bind_pirq bind_pirq;
 	struct irq_info *info = info_for_irq(irq);
 	int evtchn = evtchn_from_irq(irq);
+	int rc;
 
 	BUG_ON(info->type != IRQT_PIRQ);
 
@@ -454,8 +456,10 @@ static unsigned int startup_pirq(unsigned int irq)
 
 	bind_pirq.pirq = irq;
 	/* NB. We are happy to share unless we are probing. */
-	bind_pirq.flags = probing_irq(irq) ? 0 : BIND_PIRQ__WILL_SHARE;
-	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq) != 0) {
+	bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ?
+					BIND_PIRQ__WILL_SHARE : 0;
+	rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq);
+	if (rc != 0) {
 		if (!probing_irq(irq))
 			printk(KERN_INFO "Failed to obtain physical IRQ %d\n",
 			       irq);
@@ -565,7 +569,7 @@ static int find_irq_by_gsi(unsigned gsi)
  * event channel until the irq actually started up.  Return an
  * existing irq if we've already got one for the gsi.
  */
-int xen_allocate_pirq(unsigned gsi, char *name)
+int xen_allocate_pirq(unsigned gsi, int shareable, char *name)
 {
 	int irq;
 	struct physdev_irq irq_op;
@@ -597,6 +601,7 @@ int xen_allocate_pirq(unsigned gsi, char *name)
 	}
 
 	irq_info[irq] = mk_pirq_info(0, gsi, irq_op.vector);
+	irq_info[irq].u.pirq.flags |= shareable ? PIRQ_SHAREABLE : 0;
 
 out:
 	spin_unlock(&irq_mapping_update_lock);
diff --git a/include/xen/events.h b/include/xen/events.h
index 2532f8b..d7a4ca7 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -70,7 +70,7 @@ void xen_hvm_evtchn_do_upcall(void);
 /* Allocate an irq for a physical interrupt, given a gsi.  "Legacy"
  * GSIs are identity mapped; others are dynamically allocated as
  * usual. */
-int xen_allocate_pirq(unsigned gsi, char *name);
+int xen_allocate_pirq(unsigned gsi, int shareable, char *name);
 
 /* Return vector allocated to pirq */
 int xen_vector_from_irq(unsigned pirq);
-- 
1.7.0.4

[PATCH 12/23] x86/PCI: Clean up pci_cache_line_size

[Konrad Rzeszutek Wilk]

From: Alex Nixon <alex.nixon@darnok.org>

Separate out x86 cache_line_size initialisation code into its own
function (so it can be shared by Xen later in this patch series)

[ Impact: cleanup ]

Signed-off-by: Alex Nixon <alex.nixon@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: "H. Peter Anvin" <hpa@zytor.com>
Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: x86@kernel.org
---
 arch/x86/include/asm/pci_x86.h |    1 +
 arch/x86/pci/common.c          |   17 ++++++++++-------
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 49c7219..7045267 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -47,6 +47,7 @@ enum pci_bf_sort_state {
 extern unsigned int pcibios_max_latency;
 
 void pcibios_resource_survey(void);
+void pcibios_set_cache_line_size(void);
 
 /* pci-pc.c */
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index a0772af..f7c8a39 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -421,16 +421,10 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum)
 
 	return bus;
 }
-
-int __init pcibios_init(void)
+void __init pcibios_set_cache_line_size(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	if (!raw_pci_ops) {
-		printk(KERN_WARNING "PCI: System does not support PCI\n");
-		return 0;
-	}
-
 	/*
 	 * Set PCI cacheline size to that of the CPU if the CPU has reported it.
 	 * (For older CPUs that don't support cpuid, we se it to 32 bytes
@@ -445,7 +439,16 @@ int __init pcibios_init(void)
  		pci_dfl_cache_line_size = 32 >> 2;
 		printk(KERN_DEBUG "PCI: Unknown cacheline size. Setting to 32 bytes\n");
 	}
+}
+
+int __init pcibios_init(void)
+{
+	if (!raw_pci_ops) {
+		printk(KERN_WARNING "PCI: System does not support PCI\n");
+		return 0;
+	}
 
+	pcibios_set_cache_line_size();
 	pcibios_resource_survey();
 
 	if (pci_bf_sort >= pci_force_bf)
-- 
1.7.0.4

[PATCH 13/23] x86/PCI: make sure _PAGE_IOMAP it set on pci mappings

[Konrad Rzeszutek Wilk]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

When mapping pci space via /sys or /proc, make sure we're really
doing a hardware mapping by setting _PAGE_IOMAP.

[ Impact: bugfix; make PCI mappings map the right pages ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: "H. Peter Anvin" <hpa@zytor.com>
Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
Cc: x86@kernel.org
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/pci/i386.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 5525309..8379c2c 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -311,6 +311,8 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		 */
 		prot |= _PAGE_CACHE_UC_MINUS;
 
+	prot |= _PAGE_IOMAP;	/* creating a mapping for IO */
+
 	vma->vm_page_prot = __pgprot(prot);
 
 	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-- 
1.7.0.4

[PATCH 14/23] x86/PCI: Export pci_walk_bus function.

[Konrad Rzeszutek Wilk]

In preperation of modularizing Xen-pcifront the pci_walk_bus
needs to be exported so that the xen-pcifront module can walk
call the pci subsystem to walk the PCI devices and claim them.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> [http://marc.info/?l=linux-pci&m=126149958010298&w=2]
---
 drivers/pci/bus.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 7f0af0e..69546e9 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -299,6 +299,7 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 	}
 	up_read(&pci_bus_sem);
 }
+EXPORT_SYMBOL_GPL(pci_walk_bus);
 
 EXPORT_SYMBOL(pci_bus_alloc_resource);
 EXPORT_SYMBOL_GPL(pci_bus_add_device);
-- 
1.7.0.4

[PATCH 15/23] msi: Introduce default_[teardown|setup]_msi_irqs with fallback.

[Konrad Rzeszutek Wilk]

From: Thomas Gleixner <tglx@linutronix.de>

Introduce an override for the arch_[teardown|setup]_msi_irqs
that can be utilized to fallback to the default arch_* code.

If a platform wants to utilize the code paths defined
in driver/pci/msi.c it has to define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
or HAVE_DEFAULT_MSI_SETUP_IRQS. Otherwise the old mechanism
of over-ridding the arch_* works fine.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: x86@kernel.org
---
 drivers/pci/msi.c |   14 ++++++++++++--
 1 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 69b7be3..e57bfa9 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -35,7 +35,12 @@ int arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
 #endif
 
 #ifndef arch_setup_msi_irqs
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+# define arch_setup_msi_irqs default_setup_msi_irqs
+# define HAVE_DEFAULT_MSI_SETUP_IRQS
+#endif
+
+#ifdef HAVE_DEFAULT_MSI_SETUP_IRQS
+int default_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	struct msi_desc *entry;
 	int ret;
@@ -60,7 +65,12 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 #endif
 
 #ifndef arch_teardown_msi_irqs
-void arch_teardown_msi_irqs(struct pci_dev *dev)
+# define arch_teardown_msi_irqs default_teardown_msi_irqs
+# define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+#endif
+
+#ifdef HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+void default_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct msi_desc *entry;
 
-- 
1.7.0.4

[PATCH 16/23] x86: Introduce x86_msi_ops

[Konrad Rzeszutek Wilk]

From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>

Introduce an x86 specific indirect mechanism to setup MSIs.
The MSI setup functions become function pointers in an x86_msi_ops
struct, that defaults to the implementation in io_apic.c and msi.c.

[v2: Use HAVE_DEFAULT_* knobs]
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/include/asm/pci.h      |   33 +++++++++++++++++++++++++++++++--
 arch/x86/include/asm/x86_init.h |    9 +++++++++
 arch/x86/kernel/apic/io_apic.c  |    4 ++--
 arch/x86/kernel/x86_init.c      |    7 +++++++
 4 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d395540..ca0437c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <asm/scatterlist.h>
 #include <asm/io.h>
+#include <asm/x86_init.h>
 
 #ifdef __KERNEL__
 
@@ -94,8 +95,36 @@ static inline void early_quirks(void) { }
 
 extern void pci_iommu_alloc(void);
 
-/* MSI arch hook */
-#define arch_setup_msi_irqs arch_setup_msi_irqs
+#ifdef CONFIG_PCI_MSI
+/* MSI arch specific hooks */
+static inline int x86_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	return x86_msi.setup_msi_irqs(dev, nvec, type);
+}
+
+static inline void x86_teardown_msi_irqs(struct pci_dev *dev)
+{
+	x86_msi.teardown_msi_irqs(dev);
+}
+
+static inline void x86_teardown_msi_irq(unsigned int irq)
+{
+	x86_msi.teardown_msi_irq(irq);
+}
+#define arch_setup_msi_irqs x86_setup_msi_irqs
+#define arch_teardown_msi_irqs x86_teardown_msi_irqs
+#define arch_teardown_msi_irq x86_teardown_msi_irq
+/* implemented in arch/x86/kernel/apic/io_apic. */
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
+void native_teardown_msi_irq(unsigned int irq);
+/* default to the implementation in drivers/lib/msi.c */
+#define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+void default_teardown_msi_irqs(struct pci_dev *dev);
+#else
+#define native_setup_msi_irqs		NULL
+#define native_teardown_msi_irq		NULL
+#define default_teardown_msi_irqs	NULL
+#endif
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index baa579c..64642ad 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -154,9 +154,18 @@ struct x86_platform_ops {
 	int (*i8042_detect)(void);
 };
 
+struct pci_dev;
+
+struct x86_msi_ops {
+	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
+	void (*teardown_msi_irq)(unsigned int irq);
+	void (*teardown_msi_irqs)(struct pci_dev *dev);
+};
+
 extern struct x86_init_ops x86_init;
 extern struct x86_cpuinit_ops x86_cpuinit;
 extern struct x86_platform_ops x86_platform;
+extern struct x86_msi_ops x86_msi;
 
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 4c9b2b9..1bfc6d1 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3533,7 +3533,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	return 0;
 }
 
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	unsigned int irq;
 	int ret, sub_handle;
@@ -3594,7 +3594,7 @@ error:
 	return ret;
 }
 
-void arch_teardown_msi_irq(unsigned int irq)
+void native_teardown_msi_irq(unsigned int irq)
 {
 	destroy_irq(irq);
 }
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index cd6da6b..ceb2911 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -6,10 +6,12 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <asm/bios_ebda.h>
 #include <asm/paravirt.h>
 #include <asm/pci_x86.h>
+#include <asm/pci.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/apic.h>
@@ -99,3 +101,8 @@ struct x86_platform_ops x86_platform = {
 };
 
 EXPORT_SYMBOL_GPL(x86_platform);
+struct x86_msi_ops x86_msi = {
+	.setup_msi_irqs = native_setup_msi_irqs,
+	.teardown_msi_irq = native_teardown_msi_irq,
+	.teardown_msi_irqs = default_teardown_msi_irqs,
+};
-- 
1.7.0.4

[PATCH 17/23] xen/x86/PCI: Add support for the Xen PCI subsystem

[Konrad Rzeszutek Wilk]

From: Alex Nixon <alex.nixon@darnok.org>

The frontend stub lives in arch/x86/pci/xen.c, alongside other
sub-arch PCI init code (e.g. olpc.c).

It provides a mechanism for Xen PCI frontend to setup/destroy
legacy interrupts, MSI/MSI-X, and PCI configuration operations.

[ Impact: add core of Xen PCI support ]
[ v2: Removed the IOMMU code and only focusing on PCI.]
[ v3: removed usage of pci_scan_all_fns as that does not exist]
[ v4: introduced pci_xen value to fix compile warnings]
[ v5: squished fixes+features in one patch, changed Reviewed-by to Ccs]
[ v7: added Acked-by]
Signed-off-by: Alex Nixon <alex.nixon@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Qing He <qing.he@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
---
 arch/x86/Kconfig               |    5 ++
 arch/x86/include/asm/xen/pci.h |   53 ++++++++++++++
 arch/x86/pci/Makefile          |    1 +
 arch/x86/pci/xen.c             |  147 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/xen/enlighten.c       |    3 +
 drivers/xen/events.c           |   32 ++++++++-
 include/xen/events.h           |    3 +
 7 files changed, 242 insertions(+), 2 deletions(-)
 create mode 100644 arch/x86/include/asm/xen/pci.h
 create mode 100644 arch/x86/pci/xen.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cea0cd9..05a564a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1925,6 +1925,11 @@ config PCI_OLPC
 	def_bool y
 	depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY)
 
+config PCI_XEN
+	def_bool y
+	depends on PCI && XEN
+	select SWIOTLB_XEN
+
 config PCI_DOMAINS
 	def_bool y
 	depends on PCI
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
new file mode 100644
index 0000000..449c82f
--- /dev/null
+++ b/arch/x86/include/asm/xen/pci.h
@@ -0,0 +1,53 @@
+#ifndef _ASM_X86_XEN_PCI_H
+#define _ASM_X86_XEN_PCI_H
+
+#if defined(CONFIG_PCI_XEN)
+extern int __init pci_xen_init(void);
+#define pci_xen 1
+#else
+#define pci_xen 0
+#define pci_xen_init (0)
+#endif
+
+#if defined(CONFIG_PCI_MSI)
+#if defined(CONFIG_PCI_XEN)
+/* The drivers/pci/xen-pcifront.c sets this structure to
+ * its own functions.
+ */
+struct xen_pci_frontend_ops {
+	int (*enable_msi)(struct pci_dev *dev, int **vectors);
+	void (*disable_msi)(struct pci_dev *dev);
+	int (*enable_msix)(struct pci_dev *dev, int **vectors, int nvec);
+	void (*disable_msix)(struct pci_dev *dev);
+};
+
+extern struct xen_pci_frontend_ops *xen_pci_frontend;
+
+static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
+					      int **vectors)
+{
+	if (xen_pci_frontend && xen_pci_frontend->enable_msi)
+		return xen_pci_frontend->enable_msi(dev, vectors);
+	return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	if (xen_pci_frontend && xen_pci_frontend->disable_msi)
+			xen_pci_frontend->disable_msi(dev);
+}
+static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
+					       int **vectors, int nvec)
+{
+	if (xen_pci_frontend && xen_pci_frontend->enable_msix)
+		return xen_pci_frontend->enable_msix(dev, vectors, nvec);
+	return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	if (xen_pci_frontend && xen_pci_frontend->disable_msix)
+			xen_pci_frontend->disable_msix(dev);
+}
+#endif /* CONFIG_PCI_XEN */
+#endif /* CONFIG_PCI_MSI */
+
+#endif	/* _ASM_X86_XEN_PCI_H */
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index a0207a7..effd96e 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_PCI_BIOS)		+= pcbios.o
 obj-$(CONFIG_PCI_MMCONFIG)	+= mmconfig_$(BITS).o direct.o mmconfig-shared.o
 obj-$(CONFIG_PCI_DIRECT)	+= direct.o
 obj-$(CONFIG_PCI_OLPC)		+= olpc.o
+obj-$(CONFIG_PCI_XEN)		+= xen.o
 
 obj-y				+= fixup.o
 obj-$(CONFIG_ACPI)		+= acpi.o
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
new file mode 100644
index 0000000..b19c873
--- /dev/null
+++ b/arch/x86/pci/xen.c
@@ -0,0 +1,147 @@
+/*
+ * Xen PCI Frontend Stub - puts some "dummy" functions in to the Linux
+ *			   x86 PCI core to support the Xen PCI Frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/acpi.h>
+
+#include <linux/io.h>
+#include <asm/pci_x86.h>
+
+#include <asm/xen/hypervisor.h>
+
+#include <xen/events.h>
+#include <asm/xen/pci.h>
+
+#if defined(CONFIG_PCI_MSI)
+#include <linux/msi.h>
+
+struct xen_pci_frontend_ops *xen_pci_frontend;
+EXPORT_SYMBOL_GPL(xen_pci_frontend);
+
+/*
+ * For MSI interrupts we have to use drivers/xen/event.s functions to
+ * allocate an irq_desc and setup the right */
+
+
+static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	int irq, ret, i;
+	struct msi_desc *msidesc;
+	int *v;
+
+	v = kzalloc(sizeof(int) * max(1, nvec), GFP_KERNEL);
+	if (!v)
+		return -ENOMEM;
+
+	if (!xen_initial_domain()) {
+		if (type == PCI_CAP_ID_MSIX)
+			ret = xen_pci_frontend_enable_msix(dev, &v, nvec);
+		else
+			ret = xen_pci_frontend_enable_msi(dev, &v);
+		if (ret)
+			goto error;
+	}
+	i = 0;
+	list_for_each_entry(msidesc, &dev->msi_list, list) {
+		irq = xen_allocate_pirq(v[i], 0, /* not sharable */
+			(type == PCI_CAP_ID_MSIX) ?
+			"pcifront-msi-x" : "pcifront-msi");
+		if (irq < 0)
+			return -1;
+
+		ret = set_irq_msi(irq, msidesc);
+		if (ret)
+			goto error_while;
+		i++;
+	}
+	kfree(v);
+	return 0;
+
+error_while:
+	unbind_from_irqhandler(irq, NULL);
+error:
+	if (ret == -ENODEV)
+		dev_err(&dev->dev, "Xen PCI frontend has not registered" \
+			" MSI/MSI-X support!\n");
+
+	kfree(v);
+	return ret;
+}
+
+static void xen_teardown_msi_irqs(struct pci_dev *dev)
+{
+	/* Only do this when were are in non-privileged mode.*/
+	if (!xen_initial_domain()) {
+		struct msi_desc *msidesc;
+
+		msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
+		if (msidesc->msi_attrib.is_msix)
+			xen_pci_frontend_disable_msix(dev);
+		else
+			xen_pci_frontend_disable_msi(dev);
+	}
+
+}
+
+static void xen_teardown_msi_irq(unsigned int irq)
+{
+	xen_destroy_irq(irq);
+}
+#endif
+
+static int xen_pcifront_enable_irq(struct pci_dev *dev)
+{
+	int rc;
+	int share = 1;
+
+	dev_info(&dev->dev, "Xen PCI enabling IRQ: %d\n", dev->irq);
+
+	if (dev->irq < 0)
+		return -EINVAL;
+
+	if (dev->irq < NR_IRQS_LEGACY)
+		share = 0;
+
+	rc = xen_allocate_pirq(dev->irq, share, "pcifront");
+	if (rc < 0) {
+		dev_warn(&dev->dev, "Xen PCI IRQ: %d, failed to register:%d\n",
+			 dev->irq, rc);
+		return rc;
+	}
+	return 0;
+}
+
+int __init pci_xen_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	printk(KERN_INFO "PCI: setting up Xen PCI frontend stub\n");
+
+	pcibios_set_cache_line_size();
+
+	pcibios_enable_irq = xen_pcifront_enable_irq;
+	pcibios_disable_irq = NULL;
+
+#ifdef CONFIG_ACPI
+	/* Keep ACPI out of the picture */
+	acpi_noirq = 1;
+#endif
+
+#ifdef CONFIG_ISAPNP
+	/* Stop isapnp from probing */
+	isapnp_disable = 1;
+#endif
+
+#ifdef CONFIG_PCI_MSI
+	x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
+	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+	x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
+#endif
+	return 0;
+}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 7d46c84..1ccfa1b 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -45,6 +45,7 @@
 #include <asm/paravirt.h>
 #include <asm/apic.h>
 #include <asm/page.h>
+#include <asm/xen/pci.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/fixmap.h>
@@ -1220,6 +1221,8 @@ asmlinkage void __init xen_start_kernel(void)
 		add_preferred_console("xenboot", 0, NULL);
 		add_preferred_console("tty", 0, NULL);
 		add_preferred_console("hvc", 0, NULL);
+		if (pci_xen)
+			x86_init.pci.arch_init = pci_xen_init;
 	} else {
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index bf1dde6..adad3a9 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -583,7 +583,9 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name)
 		goto out;	/* XXX need refcount? */
 	}
 
-	if (identity_mapped_irq(gsi)) {
+	/* If we are a PV guest, we don't have GSIs (no ACPI passed). Therefore
+	 * we are using the !xen_initial_domain() to drop in the function.*/
+	if (identity_mapped_irq(gsi) || !xen_initial_domain()) {
 		irq = gsi;
 		irq_to_desc_alloc_node(irq, 0);
 		dynamic_irq_init(irq);
@@ -594,7 +596,13 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name)
 				      handle_level_irq, name);
 
 	irq_op.irq = irq;
-	if (HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
+	irq_op.vector = 0;
+
+	/* Only the privileged domain can do this. For non-priv, the pcifront
+	 * driver provides a PCI bus that does the call to do exactly
+	 * this in the priv domain. */
+	if (xen_initial_domain() &&
+	    HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
 		dynamic_irq_cleanup(irq);
 		irq = -ENOSPC;
 		goto out;
@@ -609,6 +617,26 @@ out:
 	return irq;
 }
 
+int xen_destroy_irq(int irq)
+{
+	struct irq_desc *desc;
+	int rc = -ENOENT;
+
+	spin_lock(&irq_mapping_update_lock);
+
+	desc = irq_to_desc(irq);
+	if (!desc)
+		goto out;
+
+	irq_info[irq] = mk_unbound_info();
+
+	dynamic_irq_cleanup(irq);
+
+out:
+	spin_unlock(&irq_mapping_update_lock);
+	return rc;
+}
+
 int xen_vector_from_irq(unsigned irq)
 {
 	return vector_from_irq(irq);
diff --git a/include/xen/events.h b/include/xen/events.h
index d7a4ca7..c1717ca 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -72,6 +72,9 @@ void xen_hvm_evtchn_do_upcall(void);
  * usual. */
 int xen_allocate_pirq(unsigned gsi, int shareable, char *name);
 
+/* De-allocates the above mentioned physical interrupt. */
+int xen_destroy_irq(int irq);
+
 /* Return vector allocated to pirq */
 int xen_vector_from_irq(unsigned pirq);
 
-- 
1.7.0.4

[PATCH 18/23] xenbus: Xen paravirtualised PCI hotplug support.

[Konrad Rzeszutek Wilk]

From: Yosuke Iwamatsu <y-iwamatsu@darnok.org>

The Xen PCI front driver adds two new states that are utilizez
for PCI hotplug support. This is a patch pulled from the
linux-2.6-xen-sparse tree.

Signed-off-by: Noboru Iwamatsu <n_iwamatsu@jp.fujitsu.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Yosuke Iwamatsu <y-iwamatsu@ab.jp.nec.com>
---
 drivers/xen/xenbus/xenbus_client.c |    2 ++
 include/xen/interface/io/xenbus.h  |    8 +++++++-
 2 files changed, 9 insertions(+), 1 deletions(-)

diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 7e49527..cdacf92 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -50,6 +50,8 @@ const char *xenbus_strstate(enum xenbus_state state)
 		[ XenbusStateConnected    ] = "Connected",
 		[ XenbusStateClosing      ] = "Closing",
 		[ XenbusStateClosed	  ] = "Closed",
+		[XenbusStateReconfiguring] = "Reconfiguring",
+		[XenbusStateReconfigured] = "Reconfigured",
 	};
 	return (state < ARRAY_SIZE(name)) ? name[state] : "INVALID";
 }
diff --git a/include/xen/interface/io/xenbus.h b/include/xen/interface/io/xenbus.h
index 46508c7..9fda532 100644
--- a/include/xen/interface/io/xenbus.h
+++ b/include/xen/interface/io/xenbus.h
@@ -27,8 +27,14 @@ enum xenbus_state
 	XenbusStateClosing      = 5,  /* The device is being closed
 					 due to an error or an unplug
 					 event. */
-	XenbusStateClosed       = 6
+	XenbusStateClosed       = 6,
 
+	/*
+	* Reconfiguring: The device is being reconfigured.
+	*/
+	XenbusStateReconfiguring = 7,
+
+	XenbusStateReconfigured  = 8
 };
 
 #endif /* _XEN_PUBLIC_IO_XENBUS_H */
-- 
1.7.0.4

[PATCH 19/23] xenbus: prevent warnings on unhandled enumeration values

[Konrad Rzeszutek Wilk]

From: Noboru Iwamatsu <n_iwamatsu@darnok.org>

XenbusStateReconfiguring/XenbusStateReconfigured were introduced by
c/s 437, but aren't handled in many switch statements.

.. also pulled from the linux-2.6-sparse-tree tree.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 drivers/block/xen-blkfront.c |    2 ++
 drivers/input/xen-kbdfront.c |    2 ++
 drivers/net/xen-netfront.c   |    2 ++
 drivers/video/xen-fbfront.c  |    2 ++
 4 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index ab735a6..c4e9d81 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1125,6 +1125,8 @@ static void blkback_changed(struct xenbus_device *dev,
 	case XenbusStateInitialising:
 	case XenbusStateInitWait:
 	case XenbusStateInitialised:
+	case XenbusStateReconfiguring:
+	case XenbusStateReconfigured:
 	case XenbusStateUnknown:
 	case XenbusStateClosed:
 		break;
diff --git a/drivers/input/xen-kbdfront.c b/drivers/input/xen-kbdfront.c
index ebb1190..e0c024d 100644
--- a/drivers/input/xen-kbdfront.c
+++ b/drivers/input/xen-kbdfront.c
@@ -276,6 +276,8 @@ static void xenkbd_backend_changed(struct xenbus_device *dev,
 	switch (backend_state) {
 	case XenbusStateInitialising:
 	case XenbusStateInitialised:
+	case XenbusStateReconfiguring:
+	case XenbusStateReconfigured:
 	case XenbusStateUnknown:
 	case XenbusStateClosed:
 		break;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index b50fedc..cb6e112 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1610,6 +1610,8 @@ static void backend_changed(struct xenbus_device *dev,
 	switch (backend_state) {
 	case XenbusStateInitialising:
 	case XenbusStateInitialised:
+	case XenbusStateReconfiguring:
+	case XenbusStateReconfigured:
 	case XenbusStateConnected:
 	case XenbusStateUnknown:
 	case XenbusStateClosed:
diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c
index 7c7f42a..428d273 100644
--- a/drivers/video/xen-fbfront.c
+++ b/drivers/video/xen-fbfront.c
@@ -631,6 +631,8 @@ static void xenfb_backend_changed(struct xenbus_device *dev,
 	switch (backend_state) {
 	case XenbusStateInitialising:
 	case XenbusStateInitialised:
+	case XenbusStateReconfiguring:
+	case XenbusStateReconfigured:
 	case XenbusStateUnknown:
 	case XenbusStateClosed:
 		break;
-- 
1.7.0.4

[PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

From: Ryan Wilson <hap9@darnok.org>

This is a port of the 2.6.18 Xen PCI front driver with fixes
to make it build under 2.6.34 and later (for the full list of
changes: git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git
historic/xen-pcifront-0.1). It also includes the fixes
to make it work properly.

[v2: Updated Kconfig, removed crud, added Reviewed-by]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 drivers/pci/Kconfig              |   15 +
 drivers/pci/Makefile             |    2 +
 drivers/pci/xen-pcifront.c       | 1157 ++++++++++++++++++++++++++++++++++++++
 include/xen/interface/io/pciif.h |  112 ++++
 4 files changed, 1286 insertions(+), 0 deletions(-)
 create mode 100644 drivers/pci/xen-pcifront.c
 create mode 100644 include/xen/interface/io/pciif.h

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34ef70d..018fb5e 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -40,6 +40,21 @@ config PCI_STUB
 
 	  When in doubt, say N.
 
+config XEN_PCIDEV_FRONTEND
+        tristate "Xen PCI Frontend"
+        depends on PCI && X86 && XEN
+        select HOTPLUG
+        select PCI_XEN
+        default y
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
+config XEN_PCIDEV_FE_DEBUG
+        bool
+        depends on PCI_DEBUG
+        default n
+
 config HT_IRQ
 	bool "Interrupts on hypertransport devices"
 	default y
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index dc1aa09..d5e2705 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -65,6 +65,8 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
 
 obj-$(CONFIG_PCI_STUB) += pci-stub.o
 
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
 endif
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
new file mode 100644
index 0000000..d78f658
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1157 @@
+/*
+ * Xen PCI Frontend.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pciif.h>
+#include <asm/xen/pci.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <linux/time.h>
+
+
+#ifndef __init_refok
+#define __init_refok
+#endif
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN    (-1)
+
+
+struct pci_bus_entry {
+	struct list_head list;
+	struct pci_bus *bus;
+};
+
+#define _PDEVB_op_active		(0)
+#define PDEVB_op_active			(1 << (_PDEVB_op_active))
+
+struct pcifront_device {
+	struct xenbus_device *xdev;
+	struct list_head root_buses;
+
+	int evtchn;
+	int gnt_ref;
+
+	int irq;
+
+	/* Lock this when doing any operations in sh_info */
+	spinlock_t sh_info_lock;
+	struct xen_pci_sharedinfo *sh_info;
+	struct work_struct op_work;
+	unsigned long flags;
+
+};
+
+struct pcifront_sd {
+	int domain;
+	struct pcifront_device *pdev;
+};
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+	return sd->pdev;
+}
+
+static inline void pcifront_init_sd(struct pcifront_sd *sd,
+				    unsigned int domain, unsigned int bus,
+				    struct pcifront_device *pdev)
+{
+	sd->domain = domain;
+	sd->pdev = pdev;
+}
+
+static inline void pcifront_setup_root_resources(struct pci_bus *bus,
+						 struct pcifront_sd *sd)
+{
+}
+
+
+DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev;
+
+static int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static int errno_to_pcibios_err(int errno)
+{
+	switch (errno) {
+	case XEN_PCI_ERR_success:
+		return PCIBIOS_SUCCESSFUL;
+
+	case XEN_PCI_ERR_dev_not_found:
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	case XEN_PCI_ERR_invalid_offset:
+	case XEN_PCI_ERR_op_failed:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	case XEN_PCI_ERR_not_implemented:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+
+	case XEN_PCI_ERR_access_denied:
+		return PCIBIOS_SET_FAILED;
+	}
+	return errno;
+}
+
+static inline void schedule_pcifront_aer_op(struct pcifront_device *pdev)
+{
+	if (test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+		&& !test_and_set_bit(_PDEVB_op_active, &pdev->flags)) {
+		dev_dbg(&pdev->xdev->dev, "schedule aer frontend job\n");
+		schedule_work(&pdev->op_work);
+	}
+}
+
+static int do_pci_op(struct pcifront_device *pdev, struct xen_pci_op *op)
+{
+	int err = 0;
+	struct xen_pci_op *active_op = &pdev->sh_info->op;
+	unsigned long irq_flags;
+	evtchn_port_t port = pdev->evtchn;
+	unsigned irq = pdev->irq;
+	s64 ns, ns_timeout;
+	struct timeval tv;
+
+	spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
+
+	memcpy(active_op, op, sizeof(struct xen_pci_op));
+
+	/* Go */
+	wmb();
+	set_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(port);
+
+	/*
+	 * We set a poll timeout of 3 seconds but give up on return after
+	 * 2 seconds. It is better to time out too late rather than too early
+	 * (in the latter case we end up continually re-executing poll() with a
+	 * timeout in the past). 1s difference gives plenty of slack for error.
+	 */
+	do_gettimeofday(&tv);
+	ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+
+	xen_clear_irq_pending(irq);
+
+	while (test_bit(_XEN_PCIF_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		xen_poll_irq_timeout(irq, jiffies + 3*HZ);
+		xen_clear_irq_pending(irq);
+		do_gettimeofday(&tv);
+		ns = timeval_to_ns(&tv);
+		if (ns > ns_timeout) {
+			dev_err(&pdev->xdev->dev,
+				"pciback not responding!!!\n");
+			clear_bit(_XEN_PCIF_active,
+				  (unsigned long *)&pdev->sh_info->flags);
+			err = XEN_PCI_ERR_dev_not_found;
+			goto out;
+		}
+	}
+
+	/*
+	* We might lose backend service request since we
+	* reuse same evtchn with pci_conf backend response. So re-schedule
+	* aer pcifront service.
+	*/
+	if (test_bit(_XEN_PCIB_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		dev_err(&pdev->xdev->dev,
+			"schedule aer pcifront service\n");
+		schedule_pcifront_aer_op(pdev);
+	}
+
+	memcpy(op, active_op, sizeof(struct xen_pci_op));
+
+	err = op->err;
+out:
+	spin_unlock_irqrestore(&pdev->sh_info_lock, irq_flags);
+	return err;
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_read(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 *val)
+{
+	int err = 0;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_read,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+			 pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn), where, size);
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (verbose_request)
+			dev_info(&pdev->xdev->dev, "read got back value %x\n",
+				 op.value);
+
+		*val = op.value;
+	} else if (err == -ENODEV) {
+		/* No device here, pretend that it just returned 0 */
+		err = 0;
+		*val = 0;
+	}
+
+	return errno_to_pcibios_err(err);
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_write(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 val)
+{
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_write,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+		.value  = val,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "write dev=%04x:%02x:%02x.%01x - "
+			 "offset %x size %d val %x\n",
+			 pci_domain_nr(bus), bus->number,
+			 PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+
+	return errno_to_pcibios_err(do_pci_op(pdev, &op));
+}
+
+struct pci_ops pcifront_bus_ops = {
+	.read = pcifront_bus_read,
+	.write = pcifront_bus_write,
+};
+
+#ifdef CONFIG_PCI_MSI
+static int pci_frontend_enable_msix(struct pci_dev *dev,
+				    int **vector, int nvec)
+{
+	int err;
+	int i;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+		.value = nvec,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+	struct msi_desc *entry;
+
+	if (nvec > SH_INFO_MAX_VEC) {
+		dev_err(&dev->dev, "too much vector for pci frontend: %x."
+				   " Increase SH_INFO_MAX_VEC.\n", nvec);
+		return -EINVAL;
+	}
+
+	i = 0;
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+		/* Vector is useless at this point. */
+		op.msix_entries[i].vector = -1;
+		i++;
+	}
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (likely(!op.value)) {
+			/* we get the result */
+			for (i = 0; i < nvec; i++)
+				*(*vector+i) = op.msix_entries[i].vector;
+			return 0;
+		} else {
+			printk(KERN_DEBUG "enable msix get value %x\n",
+				op.value);
+			return op.value;
+		}
+	} else {
+		dev_err(&dev->dev, "enable msix get err %x\n", err);
+		return err;
+	}
+}
+
+static void pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+
+	/* What should do for error ? */
+	if (err)
+		dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
+}
+
+static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (likely(!err)) {
+		*(*vector) = op.value;
+	} else {
+		dev_err(&dev->dev, "pci frontend enable msi failed for dev "
+				    "%x:%x\n", op.bus, op.devfn);
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static void pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (err == XEN_PCI_ERR_dev_not_found) {
+		/* XXX No response from backend, what shall we do? */
+		printk(KERN_DEBUG "get no response from backend for disable MSI\n");
+		return;
+	}
+	if (err)
+		/* how can pciback notify us fail? */
+		printk(KERN_DEBUG "get fake response frombackend\n");
+}
+
+static struct xen_pci_frontend_ops pci_frontend_ops = {
+	.enable_msi = pci_frontend_enable_msi,
+	.disable_msi = pci_frontend_disable_msi,
+	.enable_msix = pci_frontend_enable_msix,
+	.disable_msix = pci_frontend_disable_msix,
+};
+
+static void pci_frontend_registrar(int enable)
+{
+	if (enable)
+		xen_pci_frontend = &pci_frontend_ops;
+	else
+		xen_pci_frontend = NULL;
+};
+#else
+static inline void pci_frontend_registrar(int enable) { };
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static int pcifront_claim_resource(struct pci_dev *dev, void *data)
+{
+	struct pcifront_device *pdev = data;
+	int i;
+	struct resource *r;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		r = &dev->resource[i];
+
+		if (!r->parent && r->start && r->flags) {
+			dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
+				pci_name(dev), i);
+			if (pci_claim_resource(dev, i)) {
+				dev_err(&pdev->xdev->dev, "Could not claim "
+					"resource %s/%d! Device offline. Try "
+					"giving less than 4GB to domain.\n",
+					pci_name(dev), i);
+			}
+		}
+	}
+
+	return 0;
+}
+
+int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+				unsigned int domain, unsigned int bus,
+				struct pci_bus *b)
+{
+	struct pci_dev *d;
+	unsigned int devfn;
+
+	/* Scan the bus for functions and add.
+	 * We omit handling of PCI bridge attachment because pciback prevents
+	 * bridges from being exported.
+	 */
+	for (devfn = 0; devfn < 0x100; devfn++) {
+		d = pci_get_slot(b, devfn);
+		if (d) {
+			/* Device is already known. */
+			pci_dev_put(d);
+			continue;
+		}
+
+		d = pci_scan_single_device(b, devfn);
+		if (d)
+			dev_info(&pdev->xdev->dev, "New device on "
+				 "%04x:%02x:%02x.%02x found.\n", domain, bus,
+				 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	}
+
+	return 0;
+}
+
+int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+				 unsigned int domain, unsigned int bus)
+{
+	struct pci_bus *b;
+	struct pcifront_sd *sd = NULL;
+	struct pci_bus_entry *bus_entry = NULL;
+	int err = 0;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		err = -EINVAL;
+		goto err_out;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	if (!bus_entry || !sd) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	pcifront_init_sd(sd, domain, bus, pdev);
+
+	b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
+				  &pcifront_bus_ops, sd);
+	if (!b) {
+		dev_err(&pdev->xdev->dev,
+			"Error creating PCI Frontend Bus!\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	pcifront_setup_root_resources(b, sd);
+	bus_entry->bus = b;
+
+	list_add(&bus_entry->list, &pdev->root_buses);
+
+	/* pci_scan_bus_parented skips devices which do not have a have
+	* devfn==0. The pcifront_scan_bus enumerates all devfn. */
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+
+err_out:
+	kfree(bus_entry);
+	kfree(sd);
+
+	return err;
+}
+
+int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+				   unsigned int domain, unsigned int bus)
+{
+	int err;
+	struct pci_bus *b;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		return -EINVAL;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Rescanning PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	b = pci_find_bus(domain, bus);
+	if (!b)
+		/* If the bus is unknown, create it. */
+		return pcifront_scan_root(pdev, domain, bus);
+
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+}
+
+static void free_root_bus_devs(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	while (!list_empty(&bus->devices)) {
+		dev = container_of(bus->devices.next, struct pci_dev,
+				   bus_list);
+		dev_dbg(&dev->dev, "removing device\n");
+		pci_remove_bus_device(dev);
+	}
+}
+
+void pcifront_free_roots(struct pcifront_device *pdev)
+{
+	struct pci_bus_entry *bus_entry, *t;
+
+	dev_dbg(&pdev->xdev->dev, "cleaning up root buses\n");
+
+	list_for_each_entry_safe(bus_entry, t, &pdev->root_buses, list) {
+		list_del(&bus_entry->list);
+
+		free_root_bus_devs(bus_entry->bus);
+
+		kfree(bus_entry->bus->sysdata);
+
+		device_unregister(bus_entry->bus->bridge);
+		pci_remove_bus(bus_entry->bus);
+
+		kfree(bus_entry);
+	}
+}
+
+static pci_ers_result_t pcifront_common_process(int cmd,
+						struct pcifront_device *pdev,
+						pci_channel_state_t state)
+{
+	pci_ers_result_t result;
+	struct pci_driver *pdrv;
+	int bus = pdev->sh_info->aer_op.bus;
+	int devfn = pdev->sh_info->aer_op.devfn;
+	struct pci_dev *pcidev;
+	int flag = 0;
+
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront AER process: cmd %x (bus:%x, devfn%x)",
+		cmd, bus, devfn);
+	result = PCI_ERS_RESULT_NONE;
+
+	pcidev = pci_get_bus_and_slot(bus, devfn);
+	if (!pcidev || !pcidev->driver) {
+		dev_err(&pcidev->dev,
+			"device or driver is NULL\n");
+		return result;
+	}
+	pdrv = pcidev->driver;
+
+	if (get_driver(&pdrv->driver)) {
+		if (pdrv->err_handler && pdrv->err_handler->error_detected) {
+			dev_dbg(&pcidev->dev,
+				"trying to call AER service\n");
+			if (pcidev) {
+				flag = 1;
+				switch (cmd) {
+				case XEN_PCI_OP_aer_detected:
+					result = pdrv->err_handler->
+						 error_detected(pcidev, state);
+					break;
+				case XEN_PCI_OP_aer_mmio:
+					result = pdrv->err_handler->
+						 mmio_enabled(pcidev);
+					break;
+				case XEN_PCI_OP_aer_slotreset:
+					result = pdrv->err_handler->
+						 slot_reset(pcidev);
+					break;
+				case XEN_PCI_OP_aer_resume:
+					pdrv->err_handler->resume(pcidev);
+					break;
+				default:
+					dev_err(&pdev->xdev->dev,
+						"bad request in aer recovery "
+						"operation!\n");
+
+				}
+			}
+		}
+		put_driver(&pdrv->driver);
+	}
+	if (!flag)
+		result = PCI_ERS_RESULT_NONE;
+
+	return result;
+}
+
+
+void pcifront_do_aer(struct work_struct *data)
+{
+	struct pcifront_device *pdev =
+		container_of(data, struct pcifront_device, op_work);
+	int cmd = pdev->sh_info->aer_op.cmd;
+	pci_channel_state_t state =
+		(pci_channel_state_t)pdev->sh_info->aer_op.err;
+
+	/*If a pci_conf op is in progress,
+		we have to wait until it is done before service aer op*/
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront service aer bus %x devfn %x\n",
+		pdev->sh_info->aer_op.bus, pdev->sh_info->aer_op.devfn);
+
+	pdev->sh_info->aer_op.err = pcifront_common_process(cmd, pdev, state);
+
+	/* Post the operation to the guest. */
+	wmb();
+	clear_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(pdev->evtchn);
+
+	/*in case of we lost an aer request in four lines time_window*/
+	smp_mb__before_clear_bit();
+	clear_bit(_PDEVB_op_active, &pdev->flags);
+	smp_mb__after_clear_bit();
+
+	schedule_pcifront_aer_op(pdev);
+
+}
+
+irqreturn_t pcifront_handler_aer(int irq, void *dev)
+{
+	struct pcifront_device *pdev = dev;
+	schedule_pcifront_aer_op(pdev);
+	return IRQ_HANDLED;
+}
+int pcifront_connect(struct pcifront_device *pdev)
+{
+	int err = 0;
+
+	spin_lock(&pcifront_dev_lock);
+
+	if (!pcifront_dev) {
+		dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
+		pcifront_dev = pdev;
+	} else {
+		dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+		err = -EEXIST;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+
+	return err;
+}
+
+void pcifront_disconnect(struct pcifront_device *pdev)
+{
+	spin_lock(&pcifront_dev_lock);
+
+	if (pdev == pcifront_dev) {
+		dev_info(&pdev->xdev->dev,
+			 "Disconnecting PCI Frontend Buses\n");
+		pcifront_dev = NULL;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+}
+static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev;
+
+	pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+
+	pdev->sh_info =
+	    (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL);
+	if (pdev->sh_info == NULL) {
+		kfree(pdev);
+		pdev = NULL;
+		goto out;
+	}
+	pdev->sh_info->flags = 0;
+
+	/*Flag for registering PV AER handler*/
+	set_bit(_XEN_PCIB_AERHANDLER, (void *)&pdev->sh_info->flags);
+
+	dev_set_drvdata(&xdev->dev, pdev);
+	pdev->xdev = xdev;
+
+	INIT_LIST_HEAD(&pdev->root_buses);
+
+	spin_lock_init(&pdev->sh_info_lock);
+
+	pdev->evtchn = INVALID_EVTCHN;
+	pdev->gnt_ref = INVALID_GRANT_REF;
+	pdev->irq = -1;
+
+	INIT_WORK(&pdev->op_work, pcifront_do_aer);
+
+	dev_dbg(&xdev->dev, "Allocated pdev @ 0x%p pdev->sh_info @ 0x%p\n",
+		pdev, pdev->sh_info);
+out:
+	return pdev;
+}
+
+static void free_pdev(struct pcifront_device *pdev)
+{
+	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
+
+	pcifront_free_roots(pdev);
+
+	/*For PCIE_AER error handling job*/
+	flush_scheduled_work();
+	unbind_from_irqhandler(pdev->irq, pdev);
+
+	if (pdev->evtchn != INVALID_EVTCHN)
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+
+	if (pdev->gnt_ref != INVALID_GRANT_REF)
+		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
+					  (unsigned long)pdev->sh_info);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+
+	kfree(pdev);
+}
+
+static int pcifront_publish_info(struct pcifront_device *pdev)
+{
+	int err = 0;
+	struct xenbus_transaction trans;
+
+	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
+	if (err < 0)
+		goto out;
+
+	pdev->gnt_ref = err;
+
+	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
+	if (err)
+		goto out;
+
+	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+		0, "pcifront", pdev);
+	if (err < 0) {
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
+				 "irqhandler.\n");
+		return err;
+	}
+	pdev->irq = err;
+
+do_publish:
+	err = xenbus_transaction_start(&trans);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend "
+				 "(start transaction)");
+		goto out;
+	}
+
+	err = xenbus_printf(trans, pdev->xdev->nodename,
+			    "pci-op-ref", "%u", pdev->gnt_ref);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "event-channel", "%u", pdev->evtchn);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "magic", XEN_PCI_MAGIC);
+
+	if (err) {
+		xenbus_transaction_end(trans, 1);
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend");
+		goto out;
+	} else {
+		err = xenbus_transaction_end(trans, 0);
+		if (err == -EAGAIN)
+			goto do_publish;
+		else if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error completing transaction "
+					 "for backend");
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+
+	dev_dbg(&pdev->xdev->dev, "publishing successful!\n");
+
+out:
+	return err;
+}
+
+static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	char str[64];
+	unsigned int domain, bus;
+
+
+	/* Only connect once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	err = pcifront_connect(pdev);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error connecting PCI Frontend");
+		goto out;
+	}
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_scan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_scan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+	int err = 0;
+	enum xenbus_state prev_state;
+
+
+	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+
+	if (prev_state >= XenbusStateClosing)
+		goto out;
+
+	if (prev_state == XenbusStateConnected) {
+		pcifront_free_roots(pdev);
+		pcifront_disconnect(pdev);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateClosed);
+
+out:
+
+	return err;
+}
+
+static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	unsigned int domain, bus;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_rescan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_rescan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_detach_devices(struct pcifront_device *pdev)
+{
+	int err = 0;
+	int i, num_devs;
+	unsigned int domain, bus, slot, func;
+	struct pci_bus *pci_bus;
+	struct pci_dev *pci_dev;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateConnected)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI devices");
+		goto out;
+	}
+
+	/* Find devices being detached and remove them. */
+	for (i = 0; i < num_devs; i++) {
+		int l, state;
+		l = snprintf(str, sizeof(str), "state-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d",
+				   &state);
+		if (err != 1)
+			state = XenbusStateUnknown;
+
+		if (state != XenbusStateClosing)
+			continue;
+
+		/* Remove device. */
+		l = snprintf(str, sizeof(str), "vdev-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err != 4) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI device %d", i);
+			goto out;
+		}
+
+		pci_bus = pci_find_bus(domain, bus);
+		if (!pci_bus) {
+			dev_dbg(&pdev->xdev->dev, "Cannot get bus %04x:%02x\n",
+				domain, bus);
+			continue;
+		}
+		pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
+		if (!pci_dev) {
+			dev_dbg(&pdev->xdev->dev,
+				"Cannot get PCI device %04x:%02x:%02x.%02x\n",
+				domain, bus, slot, func);
+			continue;
+		}
+		pci_remove_bus_device(pci_dev);
+		pci_dev_put(pci_dev);
+
+		dev_dbg(&pdev->xdev->dev,
+			"PCI device %04x:%02x:%02x.%02x removed.\n",
+			domain, bus, slot, func);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring);
+
+out:
+	return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+						  enum xenbus_state be_state)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	switch (be_state) {
+	case XenbusStateUnknown:
+	case XenbusStateInitialising:
+	case XenbusStateInitWait:
+	case XenbusStateInitialised:
+	case XenbusStateClosed:
+		break;
+
+	case XenbusStateConnected:
+		pcifront_try_connect(pdev);
+		break;
+
+	case XenbusStateClosing:
+		dev_warn(&xdev->dev, "backend going away!\n");
+		pcifront_try_disconnect(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		pcifront_detach_devices(pdev);
+		break;
+
+	case XenbusStateReconfigured:
+		pcifront_attach_devices(pdev);
+		break;
+	}
+}
+
+static int pcifront_xenbus_probe(struct xenbus_device *xdev,
+				 const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct pcifront_device *pdev = alloc_pdev(xdev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(xdev, err,
+				 "Error allocating pcifront_device struct");
+		goto out;
+	}
+
+	err = pcifront_publish_info(pdev);
+
+out:
+	return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+	if (pdev)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static struct xenbus_driver xenbus_pcifront_driver = {
+	.name			= "pcifront",
+	.owner			= THIS_MODULE,
+	.ids			= xenpci_ids,
+	.probe			= pcifront_xenbus_probe,
+	.remove			= pcifront_xenbus_remove,
+	.otherend_changed	= pcifront_backend_changed,
+};
+
+static int __init pcifront_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	pci_frontend_registrar(1 /* enable */);
+
+	return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+static void __exit pcifront_cleanup(void)
+{
+	xenbus_unregister_driver(&xenbus_pcifront_driver);
+	pci_frontend_registrar(0 /* disable */);
+}
+module_init(pcifront_init);
+module_exit(pcifront_cleanup);
+
+MODULE_DESCRIPTION("Xen PCI passthrough frontend.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:pci");
diff --git a/include/xen/interface/io/pciif.h b/include/xen/interface/io/pciif.h
new file mode 100644
index 0000000..d9922ae
--- /dev/null
+++ b/include/xen/interface/io/pciif.h
@@ -0,0 +1,112 @@
+/*
+ * PCI Backend/Frontend Common Data Structures & Macros
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCI_COMMON_H__
+#define __XEN_PCI_COMMON_H__
+
+/* Be sure to bump this number if you change this file */
+#define XEN_PCI_MAGIC "7"
+
+/* xen_pci_sharedinfo flags */
+#define	_XEN_PCIF_active		(0)
+#define	XEN_PCIF_active			(1<<_XEN_PCIF_active)
+#define	_XEN_PCIB_AERHANDLER		(1)
+#define	XEN_PCIB_AERHANDLER		(1<<_XEN_PCIB_AERHANDLER)
+#define	_XEN_PCIB_active		(2)
+#define	XEN_PCIB_active			(1<<_XEN_PCIB_active)
+
+/* xen_pci_op commands */
+#define	XEN_PCI_OP_conf_read		(0)
+#define	XEN_PCI_OP_conf_write		(1)
+#define	XEN_PCI_OP_enable_msi		(2)
+#define	XEN_PCI_OP_disable_msi		(3)
+#define	XEN_PCI_OP_enable_msix		(4)
+#define	XEN_PCI_OP_disable_msix		(5)
+#define	XEN_PCI_OP_aer_detected		(6)
+#define	XEN_PCI_OP_aer_resume		(7)
+#define	XEN_PCI_OP_aer_mmio		(8)
+#define	XEN_PCI_OP_aer_slotreset	(9)
+
+/* xen_pci_op error numbers */
+#define	XEN_PCI_ERR_success		(0)
+#define	XEN_PCI_ERR_dev_not_found	(-1)
+#define	XEN_PCI_ERR_invalid_offset	(-2)
+#define	XEN_PCI_ERR_access_denied	(-3)
+#define	XEN_PCI_ERR_not_implemented	(-4)
+/* XEN_PCI_ERR_op_failed - backend failed to complete the operation */
+#define XEN_PCI_ERR_op_failed		(-5)
+
+/*
+ * it should be PAGE_SIZE-sizeof(struct xen_pci_op))/sizeof(struct msix_entry))
+ * Should not exceed 128
+ */
+#define SH_INFO_MAX_VEC			128
+
+struct xen_msix_entry {
+	uint16_t vector;
+	uint16_t entry;
+};
+struct xen_pci_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+
+	/* OUT: will contain an error number (if any) from errno.h */
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment */
+	uint32_t bus;
+	uint32_t devfn;
+
+	/* IN: which configuration registers to touch */
+	int32_t offset;
+	int32_t size;
+
+	/* IN/OUT: Contains the result after a READ or the value to WRITE */
+	uint32_t value;
+	/* IN: Contains extra infor for this operation */
+	uint32_t info;
+	/*IN:  param for msi-x */
+	struct xen_msix_entry msix_entries[SH_INFO_MAX_VEC];
+};
+
+/*used for pcie aer handling*/
+struct xen_pcie_aer_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+	/*IN/OUT: return aer_op result or carry error_detected state as input*/
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment*/
+	uint32_t bus;
+	uint32_t devfn;
+};
+struct xen_pci_sharedinfo {
+	/* flags - XEN_PCIF_* */
+	uint32_t flags;
+	struct xen_pci_op op;
+	struct xen_pcie_aer_op aer_op;
+};
+
+#endif /* __XEN_PCI_COMMON_H__ */
-- 
1.7.0.4

[PATCH 21/23] xen/pci: Request ACS when Xen-SWIOTLB is activated.

[Konrad Rzeszutek Wilk]

It used to done in the Xen startup code but that is not really
appropiate.

[v2: Update Kconfig with PCI requirement]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/xen/pci-swiotlb-xen.c |    4 ++++
 drivers/xen/Kconfig            |    2 +-
 2 files changed, 5 insertions(+), 1 deletions(-)

diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index a013ec9..be4d80a 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -1,6 +1,7 @@
 /* Glue code to lib/swiotlb-xen.c */
 
 #include <linux/dma-mapping.h>
+#include <linux/pci.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/xen/hypervisor.h>
@@ -54,5 +55,8 @@ void __init pci_xen_swiotlb_init(void)
 	if (xen_swiotlb) {
 		xen_swiotlb_init(1);
 		dma_ops = &xen_swiotlb_dma_ops;
+
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
 	}
 }
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 60d71e9..f70a627 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -74,6 +74,6 @@ config XEN_PLATFORM_PCI
 
 config SWIOTLB_XEN
 	def_bool y
-	depends on SWIOTLB
+	depends on PCI && SWIOTLB
 
 endmenu
-- 
1.7.0.4

[PATCH 22/23] MAINTAINERS: Add myself for Xen PCI and Xen SWIOTLB maintainer.

[Konrad Rzeszutek Wilk]

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 MAINTAINERS |   14 ++++++++++++++
 1 files changed, 14 insertions(+), 0 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 668682d..662aa75 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6486,6 +6486,20 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.
 S:	Maintained
 F:	drivers/platform/x86
 
+XEN PCI SUBSYSTEM
+M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+L:	xen-devel@lists.xensource.com
+S:	Supported
+F:	arch/x86/pci/*xen*
+F:	drivers/pci/*xen*
+
+XEN SWIOTLB SUBSYSTEM
+M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+L:	xen-devel@lists.xensource.com
+S:	Supported
+F:	arch/x86/xen/*swiotlb*
+F:	drivers/xen/*swiotlb*
+
 XEN HYPERVISOR INTERFACE
 M:	Jeremy Fitzhardinge <jeremy@xensource.com>
 M:	Chris Wright <chrisw@sous-sol.org>
-- 
1.7.0.4

[PATCH 23/23] swiotlb-xen: On x86-32 builts, select SWIOTLB instead of depending on it.

[Konrad Rzeszutek Wilk]

We used to depend on CONFIG_SWIOTLB, but that is disabled by default.
So when compiling we get this compile error:

arch/x86/xen/pci-swiotlb-xen.c: In function 'pci_xen_swiotlb_detect':
arch/x86/xen/pci-swiotlb-xen.c:48: error: lvalue required as left operand of assignment

Fix it by actually activating the SWIOTLB library.

Reported-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/Kconfig |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index f70a627..6e6180c 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -74,6 +74,7 @@ config XEN_PLATFORM_PCI
 
 config SWIOTLB_XEN
 	def_bool y
-	depends on PCI && SWIOTLB
+	depends on PCI
+	select SWIOTLB
 
 endmenu
-- 
1.7.0.4

Re: [PATCH 13/23] x86/PCI: make sure _PAGE_IOMAP it set on pci mappings

[Jesse Barnes]

On Tue, 12 Oct 2010 11:44:21 -0400
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> wrote:

> From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
> 
> When mapping pci space via /sys or /proc, make sure we're really
> doing a hardware mapping by setting _PAGE_IOMAP.
> 
> [ Impact: bugfix; make PCI mappings map the right pages ]
> 
> Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> Reviewed-by: "H. Peter Anvin" <hpa@zytor.com>
> Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
> Cc: x86@kernel.org
> Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
> ---
>  arch/x86/pci/i386.c |    2 ++
>  1 files changed, 2 insertions(+), 0 deletions(-)
> 
> diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
> index 5525309..8379c2c 100644
> --- a/arch/x86/pci/i386.c
> +++ b/arch/x86/pci/i386.c
> @@ -311,6 +311,8 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
>  		 */
>  		prot |= _PAGE_CACHE_UC_MINUS;
>  
> +	prot |= _PAGE_IOMAP;	/* creating a mapping for IO */
> +
>  	vma->vm_page_prot = __pgprot(prot);
>  
>  	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,

Looks fine.

Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>

-- 
Jesse Barnes, Intel Open Source Technology Center

Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Jan Beulich]

>>> On 12.10.10 at 17:44, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> wrote:
> --- a/drivers/pci/Kconfig
> +++ b/drivers/pci/Kconfig
> @@ -40,6 +40,21 @@ config PCI_STUB
>  
>  	  When in doubt, say N.
>  
> +config XEN_PCIDEV_FRONTEND
> +        tristate "Xen PCI Frontend"
> +        depends on PCI && X86 && XEN
> +        select HOTPLUG
> +        select PCI_XEN
> +        default y
> +        help
> +          The PCI device frontend driver allows the kernel to import 
> arbitrary
> +          PCI devices from a PCI backend to support PCI driver domains.
> +
> +config XEN_PCIDEV_FE_DEBUG
> +        bool
> +        depends on PCI_DEBUG
> +        default n

A bool without prompt, (pointlessly) defaulting to 'n', and without
getting selected anywhere has no way to get set to 'y'...

> +
>  config HT_IRQ
>  	bool "Interrupts on hypertransport devices"
>  	default y
> --- /dev/null
> +++ b/drivers/pci/xen-pcifront.c
> @@ -0,0 +1,1157 @@
> +/*
> + * Xen PCI Frontend.
> + *
> + *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
> + */
> +#include <linux/module.h>
> +#include <linux/init.h>
> +#include <linux/mm.h>
> +#include <xen/xenbus.h>
> +#include <xen/events.h>
> +#include <xen/grant_table.h>
> +#include <xen/page.h>
> +#include <linux/spinlock.h>
> +#include <linux/pci.h>
> +#include <linux/msi.h>
> +#include <xen/xenbus.h>
> +#include <xen/interface/io/pciif.h>
> +#include <asm/xen/pci.h>
> +#include <linux/interrupt.h>
> +#include <asm/atomic.h>
> +#include <linux/workqueue.h>
> +#include <linux/bitops.h>
> +#include <linux/time.h>
> +
> +
> +#ifndef __init_refok
> +#define __init_refok
> +#endif

???

> +
> +#define INVALID_GRANT_REF (0)
> +#define INVALID_EVTCHN    (-1)
> +
> +
> +struct pci_bus_entry {
> +	struct list_head list;
> +	struct pci_bus *bus;
> +};
> +
> +#define _PDEVB_op_active		(0)
> +#define PDEVB_op_active			(1 << (_PDEVB_op_active))
> +
> +struct pcifront_device {
> +	struct xenbus_device *xdev;
> +	struct list_head root_buses;
> +
> +	int evtchn;
> +	int gnt_ref;
> +
> +	int irq;
> +
> +	/* Lock this when doing any operations in sh_info */
> +	spinlock_t sh_info_lock;
> +	struct xen_pci_sharedinfo *sh_info;
> +	struct work_struct op_work;
> +	unsigned long flags;
> +
> +};
> +
> +struct pcifront_sd {
> +	int domain;
> +	struct pcifront_device *pdev;
> +};
> +
> +static inline struct pcifront_device *
> +pcifront_get_pdev(struct pcifront_sd *sd)
> +{
> +	return sd->pdev;
> +}
> +
> +static inline void pcifront_init_sd(struct pcifront_sd *sd,
> +				    unsigned int domain, unsigned int bus,
> +				    struct pcifront_device *pdev)
> +{
> +	sd->domain = domain;
> +	sd->pdev = pdev;
> +}
> +
> +static inline void pcifront_setup_root_resources(struct pci_bus *bus,
> +						 struct pcifront_sd *sd)
> +{
> +}

???

> +
> +
> +DEFINE_SPINLOCK(pcifront_dev_lock);

static?

>...
> +void pcifront_do_aer(struct work_struct *data)

static?

>...
> +irqreturn_t pcifront_handler_aer(int irq, void *dev)

static?

>...
> +int pcifront_connect(struct pcifront_device *pdev)

static?

>...
> +void pcifront_disconnect(struct pcifront_device *pdev)

static?

>...
> +static void free_pdev(struct pcifront_device *pdev)
> +{
> +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> +
> +	pcifront_free_roots(pdev);
> +
> +	/*For PCIE_AER error handling job*/
> +	flush_scheduled_work();

	if (pdev->irq > 0)

> +	unbind_from_irqhandler(pdev->irq, pdev);
> +
> +	if (pdev->evtchn != INVALID_EVTCHN)
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> +
> +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> +					  (unsigned long)pdev->sh_info);

	else
		free_page((unsigned long)pdev->sh_info);

> +
> +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> +
> +	kfree(pdev);
> +}
> +
> +static int pcifront_publish_info(struct pcifront_device *pdev)
> +{
> +	int err = 0;
> +	struct xenbus_transaction trans;
> +
> +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> +	if (err < 0)
> +		goto out;
> +
> +	pdev->gnt_ref = err;
> +
> +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> +	if (err)
> +		goto out;
> +
> +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> +		0, "pcifront", pdev);
> +	if (err < 0) {
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);

You're leaking the grant ref here. I think it's better to not do any
cleanup here, and instead call free_pdev() on error in
pcifront_xenbus_probe() (see below).

> +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> +				 "irqhandler.\n");
> +		return err;
> +	}
> +	pdev->irq = err;
>...
> +static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
> +{
> +	int err = -EFAULT;
> +	int i, num_roots, len;
> +	char str[64];
> +	unsigned int domain, bus;
> +

The original code had a per-device lock here and in subsequent
functions. Is this being dropped due to implicit serialization through
only running in the context of the single xenbus thread?

>...
> +static int pcifront_xenbus_probe(struct xenbus_device *xdev,
> +				 const struct xenbus_device_id *id)
> +{
> +	int err = 0;
> +	struct pcifront_device *pdev = alloc_pdev(xdev);
> +
> +	if (pdev == NULL) {
> +		err = -ENOMEM;
> +		xenbus_dev_fatal(xdev, err,
> +				 "Error allocating pcifront_device struct");
> +		goto out;
> +	}
> +
> +	err = pcifront_publish_info(pdev);

	if (err)
		free_pdev(pdev);

> +
> +out:
> +	return err;
> +}
>...

Jan

Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Jan Beulich]

>>> On 12.10.10 at 17:44, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> wrote:
> --- a/drivers/pci/Kconfig
> +++ b/drivers/pci/Kconfig
> @@ -40,6 +40,21 @@ config PCI_STUB
>  
>  	  When in doubt, say N.
>  
> +config XEN_PCIDEV_FRONTEND
> +        tristate "Xen PCI Frontend"
> +        depends on PCI && X86 && XEN
> +        select HOTPLUG
> +        select PCI_XEN
> +        default y
> +        help
> +          The PCI device frontend driver allows the kernel to import 
> arbitrary
> +          PCI devices from a PCI backend to support PCI driver domains.
> +
> +config XEN_PCIDEV_FE_DEBUG
> +        bool
> +        depends on PCI_DEBUG
> +        default n

A bool without prompt, (pointlessly) defaulting to 'n', and without
getting selected anywhere has no way to get set to 'y'...

> +
>  config HT_IRQ
>  	bool "Interrupts on hypertransport devices"
>  	default y
> --- /dev/null
> +++ b/drivers/pci/xen-pcifront.c
> @@ -0,0 +1,1157 @@
> +/*
> + * Xen PCI Frontend.
> + *
> + *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
> + */
> +#include <linux/module.h>
> +#include <linux/init.h>
> +#include <linux/mm.h>
> +#include <xen/xenbus.h>
> +#include <xen/events.h>
> +#include <xen/grant_table.h>
> +#include <xen/page.h>
> +#include <linux/spinlock.h>
> +#include <linux/pci.h>
> +#include <linux/msi.h>
> +#include <xen/xenbus.h>
> +#include <xen/interface/io/pciif.h>
> +#include <asm/xen/pci.h>
> +#include <linux/interrupt.h>
> +#include <asm/atomic.h>
> +#include <linux/workqueue.h>
> +#include <linux/bitops.h>
> +#include <linux/time.h>
> +
> +
> +#ifndef __init_refok
> +#define __init_refok
> +#endif

???

> +
> +#define INVALID_GRANT_REF (0)
> +#define INVALID_EVTCHN    (-1)
> +
> +
> +struct pci_bus_entry {
> +	struct list_head list;
> +	struct pci_bus *bus;
> +};
> +
> +#define _PDEVB_op_active		(0)
> +#define PDEVB_op_active			(1 << (_PDEVB_op_active))
> +
> +struct pcifront_device {
> +	struct xenbus_device *xdev;
> +	struct list_head root_buses;
> +
> +	int evtchn;
> +	int gnt_ref;
> +
> +	int irq;
> +
> +	/* Lock this when doing any operations in sh_info */
> +	spinlock_t sh_info_lock;
> +	struct xen_pci_sharedinfo *sh_info;
> +	struct work_struct op_work;
> +	unsigned long flags;
> +
> +};
> +
> +struct pcifront_sd {
> +	int domain;
> +	struct pcifront_device *pdev;
> +};
> +
> +static inline struct pcifront_device *
> +pcifront_get_pdev(struct pcifront_sd *sd)
> +{
> +	return sd->pdev;
> +}
> +
> +static inline void pcifront_init_sd(struct pcifront_sd *sd,
> +				    unsigned int domain, unsigned int bus,
> +				    struct pcifront_device *pdev)
> +{
> +	sd->domain = domain;
> +	sd->pdev = pdev;
> +}
> +
> +static inline void pcifront_setup_root_resources(struct pci_bus *bus,
> +						 struct pcifront_sd *sd)
> +{
> +}

???

> +
> +
> +DEFINE_SPINLOCK(pcifront_dev_lock);

static?

>...
> +void pcifront_do_aer(struct work_struct *data)

static?

>...
> +irqreturn_t pcifront_handler_aer(int irq, void *dev)

static?

>...
> +int pcifront_connect(struct pcifront_device *pdev)

static?

>...
> +void pcifront_disconnect(struct pcifront_device *pdev)

static?

>...
> +static void free_pdev(struct pcifront_device *pdev)
> +{
> +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> +
> +	pcifront_free_roots(pdev);
> +
> +	/*For PCIE_AER error handling job*/
> +	flush_scheduled_work();

	if (pdev->irq > 0)

> +	unbind_from_irqhandler(pdev->irq, pdev);
> +
> +	if (pdev->evtchn != INVALID_EVTCHN)
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> +
> +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> +					  (unsigned long)pdev->sh_info);

	else
		free_page((unsigned long)pdev->sh_info);

> +
> +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> +
> +	kfree(pdev);
> +}
> +
> +static int pcifront_publish_info(struct pcifront_device *pdev)
> +{
> +	int err = 0;
> +	struct xenbus_transaction trans;
> +
> +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> +	if (err < 0)
> +		goto out;
> +
> +	pdev->gnt_ref = err;
> +
> +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> +	if (err)
> +		goto out;
> +
> +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> +		0, "pcifront", pdev);
> +	if (err < 0) {
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);

You're leaking the grant ref here. I think it's better to not do any
cleanup here, and instead call free_pdev() on error in
pcifront_xenbus_probe() (see below).

> +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> +				 "irqhandler.\n");
> +		return err;
> +	}
> +	pdev->irq = err;
>...
> +static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
> +{
> +	int err = -EFAULT;
> +	int i, num_roots, len;
> +	char str[64];
> +	unsigned int domain, bus;
> +

The original code had a per-device lock here and in subsequent
functions. Is this being dropped due to implicit serialization through
only running in the context of the single xenbus thread?

>...
> +static int pcifront_xenbus_probe(struct xenbus_device *xdev,
> +				 const struct xenbus_device_id *id)
> +{
> +	int err = 0;
> +	struct pcifront_device *pdev = alloc_pdev(xdev);
> +
> +	if (pdev == NULL) {
> +		err = -ENOMEM;
> +		xenbus_dev_fatal(xdev, err,
> +				 "Error allocating pcifront_device struct");
> +		goto out;
> +	}
> +
> +	err = pcifront_publish_info(pdev);

	if (err)
		free_pdev(pdev);

> +
> +out:
> +	return err;
> +}
>...

Jan

Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

Hey Jan,

Thank you for taking your time to look at this patch. Will fix up, test it, 
and if there are no issues, have it ready tomorrow.

On Wednesday 13 October 2010 05:36:59 Jan Beulich wrote:
> >>> On 12.10.10 at 17:44, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> >>> wrote:
> >
> > --- a/drivers/pci/Kconfig
> > +++ b/drivers/pci/Kconfig
> > @@ -40,6 +40,21 @@ config PCI_STUB
> >
> >  	  When in doubt, say N.
> >
> > +config XEN_PCIDEV_FRONTEND
> > +        tristate "Xen PCI Frontend"
> > +        depends on PCI && X86 && XEN
> > +        select HOTPLUG
> > +        select PCI_XEN
> > +        default y
> > +        help
> > +          The PCI device frontend driver allows the kernel to import
> > arbitrary
> > +          PCI devices from a PCI backend to support PCI driver domains.
> > +
> > +config XEN_PCIDEV_FE_DEBUG
> > +        bool
> > +        depends on PCI_DEBUG
> > +        default n
>
> A bool without prompt, (pointlessly) defaulting to 'n', and without
> getting selected anywhere has no way to get set to 'y'...
>
> > +
> >  config HT_IRQ
> >  	bool "Interrupts on hypertransport devices"
> >  	default y
> > --- /dev/null
> > +++ b/drivers/pci/xen-pcifront.c
> > @@ -0,0 +1,1157 @@
> > +/*
> > + * Xen PCI Frontend.
> > + *
> > + *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
> > + */
> > +#include <linux/module.h>
> > +#include <linux/init.h>
> > +#include <linux/mm.h>
> > +#include <xen/xenbus.h>
> > +#include <xen/events.h>
> > +#include <xen/grant_table.h>
> > +#include <xen/page.h>
> > +#include <linux/spinlock.h>
> > +#include <linux/pci.h>
> > +#include <linux/msi.h>
> > +#include <xen/xenbus.h>
> > +#include <xen/interface/io/pciif.h>
> > +#include <asm/xen/pci.h>
> > +#include <linux/interrupt.h>
> > +#include <asm/atomic.h>
> > +#include <linux/workqueue.h>
> > +#include <linux/bitops.h>
> > +#include <linux/time.h>
> > +
> > +
> > +#ifndef __init_refok
> > +#define __init_refok
> > +#endif
>
> ???
>
> > +
> > +#define INVALID_GRANT_REF (0)
> > +#define INVALID_EVTCHN    (-1)
> > +
> > +
> > +struct pci_bus_entry {
> > +	struct list_head list;
> > +	struct pci_bus *bus;
> > +};
> > +
> > +#define _PDEVB_op_active		(0)
> > +#define PDEVB_op_active			(1 << (_PDEVB_op_active))
> > +
> > +struct pcifront_device {
> > +	struct xenbus_device *xdev;
> > +	struct list_head root_buses;
> > +
> > +	int evtchn;
> > +	int gnt_ref;
> > +
> > +	int irq;
> > +
> > +	/* Lock this when doing any operations in sh_info */
> > +	spinlock_t sh_info_lock;
> > +	struct xen_pci_sharedinfo *sh_info;
> > +	struct work_struct op_work;
> > +	unsigned long flags;
> > +
> > +};
> > +
> > +struct pcifront_sd {
> > +	int domain;
> > +	struct pcifront_device *pdev;
> > +};
> > +
> > +static inline struct pcifront_device *
> > +pcifront_get_pdev(struct pcifront_sd *sd)
> > +{
> > +	return sd->pdev;
> > +}
> > +
> > +static inline void pcifront_init_sd(struct pcifront_sd *sd,
> > +				    unsigned int domain, unsigned int bus,
> > +				    struct pcifront_device *pdev)
> > +{
> > +	sd->domain = domain;
> > +	sd->pdev = pdev;
> > +}
> > +
> > +static inline void pcifront_setup_root_resources(struct pci_bus *bus,
> > +						 struct pcifront_sd *sd)
> > +{
> > +}
>
> ???
>
> > +
> > +
> > +DEFINE_SPINLOCK(pcifront_dev_lock);
>
> static?
>
> >...
> > +void pcifront_do_aer(struct work_struct *data)
>
> static?
>
> >...
> > +irqreturn_t pcifront_handler_aer(int irq, void *dev)
>
> static?
>
> >...
> > +int pcifront_connect(struct pcifront_device *pdev)
>
> static?
>
> >...
> > +void pcifront_disconnect(struct pcifront_device *pdev)
>
> static?
>
> >...
> > +static void free_pdev(struct pcifront_device *pdev)
> > +{
> > +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> > +
> > +	pcifront_free_roots(pdev);
> > +
> > +	/*For PCIE_AER error handling job*/
> > +	flush_scheduled_work();
>
> 	if (pdev->irq > 0)
>
> > +	unbind_from_irqhandler(pdev->irq, pdev);
> > +
> > +	if (pdev->evtchn != INVALID_EVTCHN)
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> > +
> > +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> > +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> > +					  (unsigned long)pdev->sh_info);
>
> 	else
> 		free_page((unsigned long)pdev->sh_info);
>
> > +
> > +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> > +
> > +	kfree(pdev);
> > +}
> > +
> > +static int pcifront_publish_info(struct pcifront_device *pdev)
> > +{
> > +	int err = 0;
> > +	struct xenbus_transaction trans;
> > +
> > +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> > +	if (err < 0)
> > +		goto out;
> > +
> > +	pdev->gnt_ref = err;
> > +
> > +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> > +	if (err)
> > +		goto out;
> > +
> > +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> > +		0, "pcifront", pdev);
> > +	if (err < 0) {
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
>
> You're leaking the grant ref here. I think it's better to not do any
> cleanup here, and instead call free_pdev() on error in
> pcifront_xenbus_probe() (see below).

Excellent. Will do!
>
> > +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> > +				 "irqhandler.\n");
> > +		return err;
> > +	}
> > +	pdev->irq = err;
> >...
> > +static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
> > +{
> > +	int err = -EFAULT;
> > +	int i, num_roots, len;
> > +	char str[64];
> > +	unsigned int domain, bus;
> > +
>
> The original code had a per-device lock here and in subsequent
> functions. Is this being dropped due to implicit serialization through
> only running in the context of the single xenbus thread?

Yes!

>
> >...
> > +static int pcifront_xenbus_probe(struct xenbus_device *xdev,
> > +				 const struct xenbus_device_id *id)
> > +{
> > +	int err = 0;
> > +	struct pcifront_device *pdev = alloc_pdev(xdev);
> > +
> > +	if (pdev == NULL) {
> > +		err = -ENOMEM;
> > +		xenbus_dev_fatal(xdev, err,
> > +				 "Error allocating pcifront_device struct");
> > +		goto out;
> > +	}
> > +
> > +	err = pcifront_publish_info(pdev);
>
> 	if (err)
> 		free_pdev(pdev);
>
> > +
> > +out:
> > +	return err;
> > +}
> >...
>
> Jan

Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

Hey Jan,

Thank you for taking your time to look at this patch. Will fix up, test it, 
and if there are no issues, have it ready tomorrow.

On Wednesday 13 October 2010 05:36:59 Jan Beulich wrote:
> >>> On 12.10.10 at 17:44, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> >>> wrote:
> >
> > --- a/drivers/pci/Kconfig
> > +++ b/drivers/pci/Kconfig
> > @@ -40,6 +40,21 @@ config PCI_STUB
> >
> >  	  When in doubt, say N.
> >
> > +config XEN_PCIDEV_FRONTEND
> > +        tristate "Xen PCI Frontend"
> > +        depends on PCI && X86 && XEN
> > +        select HOTPLUG
> > +        select PCI_XEN
> > +        default y
> > +        help
> > +          The PCI device frontend driver allows the kernel to import
> > arbitrary
> > +          PCI devices from a PCI backend to support PCI driver domains.
> > +
> > +config XEN_PCIDEV_FE_DEBUG
> > +        bool
> > +        depends on PCI_DEBUG
> > +        default n
>
> A bool without prompt, (pointlessly) defaulting to 'n', and without
> getting selected anywhere has no way to get set to 'y'...
>
> > +
> >  config HT_IRQ
> >  	bool "Interrupts on hypertransport devices"
> >  	default y
> > --- /dev/null
> > +++ b/drivers/pci/xen-pcifront.c
> > @@ -0,0 +1,1157 @@
> > +/*
> > + * Xen PCI Frontend.
> > + *
> > + *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
> > + */
> > +#include <linux/module.h>
> > +#include <linux/init.h>
> > +#include <linux/mm.h>
> > +#include <xen/xenbus.h>
> > +#include <xen/events.h>
> > +#include <xen/grant_table.h>
> > +#include <xen/page.h>
> > +#include <linux/spinlock.h>
> > +#include <linux/pci.h>
> > +#include <linux/msi.h>
> > +#include <xen/xenbus.h>
> > +#include <xen/interface/io/pciif.h>
> > +#include <asm/xen/pci.h>
> > +#include <linux/interrupt.h>
> > +#include <asm/atomic.h>
> > +#include <linux/workqueue.h>
> > +#include <linux/bitops.h>
> > +#include <linux/time.h>
> > +
> > +
> > +#ifndef __init_refok
> > +#define __init_refok
> > +#endif
>
> ???
>
> > +
> > +#define INVALID_GRANT_REF (0)
> > +#define INVALID_EVTCHN    (-1)
> > +
> > +
> > +struct pci_bus_entry {
> > +	struct list_head list;
> > +	struct pci_bus *bus;
> > +};
> > +
> > +#define _PDEVB_op_active		(0)
> > +#define PDEVB_op_active			(1 << (_PDEVB_op_active))
> > +
> > +struct pcifront_device {
> > +	struct xenbus_device *xdev;
> > +	struct list_head root_buses;
> > +
> > +	int evtchn;
> > +	int gnt_ref;
> > +
> > +	int irq;
> > +
> > +	/* Lock this when doing any operations in sh_info */
> > +	spinlock_t sh_info_lock;
> > +	struct xen_pci_sharedinfo *sh_info;
> > +	struct work_struct op_work;
> > +	unsigned long flags;
> > +
> > +};
> > +
> > +struct pcifront_sd {
> > +	int domain;
> > +	struct pcifront_device *pdev;
> > +};
> > +
> > +static inline struct pcifront_device *
> > +pcifront_get_pdev(struct pcifront_sd *sd)
> > +{
> > +	return sd->pdev;
> > +}
> > +
> > +static inline void pcifront_init_sd(struct pcifront_sd *sd,
> > +				    unsigned int domain, unsigned int bus,
> > +				    struct pcifront_device *pdev)
> > +{
> > +	sd->domain = domain;
> > +	sd->pdev = pdev;
> > +}
> > +
> > +static inline void pcifront_setup_root_resources(struct pci_bus *bus,
> > +						 struct pcifront_sd *sd)
> > +{
> > +}
>
> ???
>
> > +
> > +
> > +DEFINE_SPINLOCK(pcifront_dev_lock);
>
> static?
>
> >...
> > +void pcifront_do_aer(struct work_struct *data)
>
> static?
>
> >...
> > +irqreturn_t pcifront_handler_aer(int irq, void *dev)
>
> static?
>
> >...
> > +int pcifront_connect(struct pcifront_device *pdev)
>
> static?
>
> >...
> > +void pcifront_disconnect(struct pcifront_device *pdev)
>
> static?
>
> >...
> > +static void free_pdev(struct pcifront_device *pdev)
> > +{
> > +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> > +
> > +	pcifront_free_roots(pdev);
> > +
> > +	/*For PCIE_AER error handling job*/
> > +	flush_scheduled_work();
>
> 	if (pdev->irq > 0)
>
> > +	unbind_from_irqhandler(pdev->irq, pdev);
> > +
> > +	if (pdev->evtchn != INVALID_EVTCHN)
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> > +
> > +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> > +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> > +					  (unsigned long)pdev->sh_info);
>
> 	else
> 		free_page((unsigned long)pdev->sh_info);
>
> > +
> > +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> > +
> > +	kfree(pdev);
> > +}
> > +
> > +static int pcifront_publish_info(struct pcifront_device *pdev)
> > +{
> > +	int err = 0;
> > +	struct xenbus_transaction trans;
> > +
> > +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> > +	if (err < 0)
> > +		goto out;
> > +
> > +	pdev->gnt_ref = err;
> > +
> > +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> > +	if (err)
> > +		goto out;
> > +
> > +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> > +		0, "pcifront", pdev);
> > +	if (err < 0) {
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
>
> You're leaking the grant ref here. I think it's better to not do any
> cleanup here, and instead call free_pdev() on error in
> pcifront_xenbus_probe() (see below).

Excellent. Will do!
>
> > +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> > +				 "irqhandler.\n");
> > +		return err;
> > +	}
> > +	pdev->irq = err;
> >...
> > +static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
> > +{
> > +	int err = -EFAULT;
> > +	int i, num_roots, len;
> > +	char str[64];
> > +	unsigned int domain, bus;
> > +
>
> The original code had a per-device lock here and in subsequent
> functions. Is this being dropped due to implicit serialization through
> only running in the context of the single xenbus thread?

Yes!

>
> >...
> > +static int pcifront_xenbus_probe(struct xenbus_device *xdev,
> > +				 const struct xenbus_device_id *id)
> > +{
> > +	int err = 0;
> > +	struct pcifront_device *pdev = alloc_pdev(xdev);
> > +
> > +	if (pdev == NULL) {
> > +		err = -ENOMEM;
> > +		xenbus_dev_fatal(xdev, err,
> > +				 "Error allocating pcifront_device struct");
> > +		goto out;
> > +	}
> > +
> > +	err = pcifront_publish_info(pdev);
>
> 	if (err)
> 		free_pdev(pdev);
>
> > +
> > +out:
> > +	return err;
> > +}
> >...
>
> Jan

Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

[-- Attachment #1: Type: text/plain, Size: 35309 bytes --]

On Wed, Oct 13, 2010 at 09:53:44AM -0400, Konrad Rzeszutek Wilk wrote:
> Hey Jan,
> 
> Thank you for taking your time to look at this patch. Will fix up, test it, 
> and if there are no issues, have it ready tomorrow.

Attached (and inline) is the updated version of this patch. If I missed anything
please do point it out to me! If this is to your satisfaction, can I put
a Reviewed-by tag on the patch?

Thank you.

>From 7e865c880aa5942c4c22bd67618b2e9fc1788da6 Mon Sep 17 00:00:00 2001
From: Ryan Wilson <hap9@epoch.ncsc.mil>
Date: Mon, 2 Aug 2010 21:31:05 -0400
Subject: [PATCH] xen-pcifront: Xen PCI frontend driver.

This is a port of the 2.6.18 Xen PCI front driver with fixes
to make it build under 2.6.34 and later (for the full list of
changes: git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git
historic/xen-pcifront-0.1). It also includes the fixes
to make it work properly.

[v2: Updated Kconfig, removed crud, added Reviewed-by]
[v3: Added 'static', fixed grant table leak, redid Kconfig]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Jan Beulich <JBeulich@novell.com>
---
 drivers/pci/Kconfig              |   21 +
 drivers/pci/Makefile             |    2 +
 drivers/pci/xen-pcifront.c       | 1152 ++++++++++++++++++++++++++++++++++++++
 include/xen/interface/io/pciif.h |  112 ++++
 4 files changed, 1287 insertions(+), 0 deletions(-)
 create mode 100644 drivers/pci/xen-pcifront.c
 create mode 100644 include/xen/interface/io/pciif.h

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34ef70d..5b1630e 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -40,6 +40,27 @@ config PCI_STUB
 
 	  When in doubt, say N.
 
+config XEN_PCIDEV_FRONTEND
+        tristate "Xen PCI Frontend"
+        depends on PCI && X86 && XEN
+        select HOTPLUG
+        select PCI_XEN
+        default y
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
+config XEN_PCIDEV_FE_DEBUG
+        bool "Xen PCI Frontend debugging"
+        depends on XEN_PCIDEV_FRONTEND && PCI_DEBUG
+	help
+	  Say Y here if you want the Xen PCI frontend to produce a bunch of debug
+	  messages to the system log.  Select this if you are having a
+	  problem with Xen PCI frontend support and want to see more of what is
+	  going on.
+
+	  When in doubt, say N.
+
 config HT_IRQ
 	bool "Interrupts on hypertransport devices"
 	default y
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index dc1aa09..d5e2705 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -65,6 +65,8 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
 
 obj-$(CONFIG_PCI_STUB) += pci-stub.o
 
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
 endif
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
new file mode 100644
index 0000000..238870a
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1152 @@
+/*
+ * Xen PCI Frontend.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pciif.h>
+#include <asm/xen/pci.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <linux/time.h>
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN    (-1)
+
+struct pci_bus_entry {
+	struct list_head list;
+	struct pci_bus *bus;
+};
+
+#define _PDEVB_op_active		(0)
+#define PDEVB_op_active			(1 << (_PDEVB_op_active))
+
+struct pcifront_device {
+	struct xenbus_device *xdev;
+	struct list_head root_buses;
+
+	int evtchn;
+	int gnt_ref;
+
+	int irq;
+
+	/* Lock this when doing any operations in sh_info */
+	spinlock_t sh_info_lock;
+	struct xen_pci_sharedinfo *sh_info;
+	struct work_struct op_work;
+	unsigned long flags;
+
+};
+
+struct pcifront_sd {
+	int domain;
+	struct pcifront_device *pdev;
+};
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+	return sd->pdev;
+}
+
+static inline void pcifront_init_sd(struct pcifront_sd *sd,
+				    unsigned int domain, unsigned int bus,
+				    struct pcifront_device *pdev)
+{
+	sd->domain = domain;
+	sd->pdev = pdev;
+}
+
+static DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev;
+
+static int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static int errno_to_pcibios_err(int errno)
+{
+	switch (errno) {
+	case XEN_PCI_ERR_success:
+		return PCIBIOS_SUCCESSFUL;
+
+	case XEN_PCI_ERR_dev_not_found:
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	case XEN_PCI_ERR_invalid_offset:
+	case XEN_PCI_ERR_op_failed:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	case XEN_PCI_ERR_not_implemented:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+
+	case XEN_PCI_ERR_access_denied:
+		return PCIBIOS_SET_FAILED;
+	}
+	return errno;
+}
+
+static inline void schedule_pcifront_aer_op(struct pcifront_device *pdev)
+{
+	if (test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+		&& !test_and_set_bit(_PDEVB_op_active, &pdev->flags)) {
+		dev_dbg(&pdev->xdev->dev, "schedule aer frontend job\n");
+		schedule_work(&pdev->op_work);
+	}
+}
+
+static int do_pci_op(struct pcifront_device *pdev, struct xen_pci_op *op)
+{
+	int err = 0;
+	struct xen_pci_op *active_op = &pdev->sh_info->op;
+	unsigned long irq_flags;
+	evtchn_port_t port = pdev->evtchn;
+	unsigned irq = pdev->irq;
+	s64 ns, ns_timeout;
+	struct timeval tv;
+
+	spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
+
+	memcpy(active_op, op, sizeof(struct xen_pci_op));
+
+	/* Go */
+	wmb();
+	set_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(port);
+
+	/*
+	 * We set a poll timeout of 3 seconds but give up on return after
+	 * 2 seconds. It is better to time out too late rather than too early
+	 * (in the latter case we end up continually re-executing poll() with a
+	 * timeout in the past). 1s difference gives plenty of slack for error.
+	 */
+	do_gettimeofday(&tv);
+	ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+
+	xen_clear_irq_pending(irq);
+
+	while (test_bit(_XEN_PCIF_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		xen_poll_irq_timeout(irq, jiffies + 3*HZ);
+		xen_clear_irq_pending(irq);
+		do_gettimeofday(&tv);
+		ns = timeval_to_ns(&tv);
+		if (ns > ns_timeout) {
+			dev_err(&pdev->xdev->dev,
+				"pciback not responding!!!\n");
+			clear_bit(_XEN_PCIF_active,
+				  (unsigned long *)&pdev->sh_info->flags);
+			err = XEN_PCI_ERR_dev_not_found;
+			goto out;
+		}
+	}
+
+	/*
+	* We might lose backend service request since we
+	* reuse same evtchn with pci_conf backend response. So re-schedule
+	* aer pcifront service.
+	*/
+	if (test_bit(_XEN_PCIB_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		dev_err(&pdev->xdev->dev,
+			"schedule aer pcifront service\n");
+		schedule_pcifront_aer_op(pdev);
+	}
+
+	memcpy(op, active_op, sizeof(struct xen_pci_op));
+
+	err = op->err;
+out:
+	spin_unlock_irqrestore(&pdev->sh_info_lock, irq_flags);
+	return err;
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_read(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 *val)
+{
+	int err = 0;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_read,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+			 pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn), where, size);
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (verbose_request)
+			dev_info(&pdev->xdev->dev, "read got back value %x\n",
+				 op.value);
+
+		*val = op.value;
+	} else if (err == -ENODEV) {
+		/* No device here, pretend that it just returned 0 */
+		err = 0;
+		*val = 0;
+	}
+
+	return errno_to_pcibios_err(err);
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_write(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 val)
+{
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_write,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+		.value  = val,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "write dev=%04x:%02x:%02x.%01x - "
+			 "offset %x size %d val %x\n",
+			 pci_domain_nr(bus), bus->number,
+			 PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+
+	return errno_to_pcibios_err(do_pci_op(pdev, &op));
+}
+
+struct pci_ops pcifront_bus_ops = {
+	.read = pcifront_bus_read,
+	.write = pcifront_bus_write,
+};
+
+#ifdef CONFIG_PCI_MSI
+static int pci_frontend_enable_msix(struct pci_dev *dev,
+				    int **vector, int nvec)
+{
+	int err;
+	int i;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+		.value = nvec,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+	struct msi_desc *entry;
+
+	if (nvec > SH_INFO_MAX_VEC) {
+		dev_err(&dev->dev, "too much vector for pci frontend: %x."
+				   " Increase SH_INFO_MAX_VEC.\n", nvec);
+		return -EINVAL;
+	}
+
+	i = 0;
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+		/* Vector is useless at this point. */
+		op.msix_entries[i].vector = -1;
+		i++;
+	}
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (likely(!op.value)) {
+			/* we get the result */
+			for (i = 0; i < nvec; i++)
+				*(*vector+i) = op.msix_entries[i].vector;
+			return 0;
+		} else {
+			printk(KERN_DEBUG "enable msix get value %x\n",
+				op.value);
+			return op.value;
+		}
+	} else {
+		dev_err(&dev->dev, "enable msix get err %x\n", err);
+		return err;
+	}
+}
+
+static void pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+
+	/* What should do for error ? */
+	if (err)
+		dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
+}
+
+static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (likely(!err)) {
+		*(*vector) = op.value;
+	} else {
+		dev_err(&dev->dev, "pci frontend enable msi failed for dev "
+				    "%x:%x\n", op.bus, op.devfn);
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static void pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (err == XEN_PCI_ERR_dev_not_found) {
+		/* XXX No response from backend, what shall we do? */
+		printk(KERN_DEBUG "get no response from backend for disable MSI\n");
+		return;
+	}
+	if (err)
+		/* how can pciback notify us fail? */
+		printk(KERN_DEBUG "get fake response frombackend\n");
+}
+
+static struct xen_pci_frontend_ops pci_frontend_ops = {
+	.enable_msi = pci_frontend_enable_msi,
+	.disable_msi = pci_frontend_disable_msi,
+	.enable_msix = pci_frontend_enable_msix,
+	.disable_msix = pci_frontend_disable_msix,
+};
+
+static void pci_frontend_registrar(int enable)
+{
+	if (enable)
+		xen_pci_frontend = &pci_frontend_ops;
+	else
+		xen_pci_frontend = NULL;
+};
+#else
+static inline void pci_frontend_registrar(int enable) { };
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static int pcifront_claim_resource(struct pci_dev *dev, void *data)
+{
+	struct pcifront_device *pdev = data;
+	int i;
+	struct resource *r;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		r = &dev->resource[i];
+
+		if (!r->parent && r->start && r->flags) {
+			dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
+				pci_name(dev), i);
+			if (pci_claim_resource(dev, i)) {
+				dev_err(&pdev->xdev->dev, "Could not claim "
+					"resource %s/%d! Device offline. Try "
+					"giving less than 4GB to domain.\n",
+					pci_name(dev), i);
+			}
+		}
+	}
+
+	return 0;
+}
+
+int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+				unsigned int domain, unsigned int bus,
+				struct pci_bus *b)
+{
+	struct pci_dev *d;
+	unsigned int devfn;
+
+	/* Scan the bus for functions and add.
+	 * We omit handling of PCI bridge attachment because pciback prevents
+	 * bridges from being exported.
+	 */
+	for (devfn = 0; devfn < 0x100; devfn++) {
+		d = pci_get_slot(b, devfn);
+		if (d) {
+			/* Device is already known. */
+			pci_dev_put(d);
+			continue;
+		}
+
+		d = pci_scan_single_device(b, devfn);
+		if (d)
+			dev_info(&pdev->xdev->dev, "New device on "
+				 "%04x:%02x:%02x.%02x found.\n", domain, bus,
+				 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	}
+
+	return 0;
+}
+
+static int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+				 unsigned int domain, unsigned int bus)
+{
+	struct pci_bus *b;
+	struct pcifront_sd *sd = NULL;
+	struct pci_bus_entry *bus_entry = NULL;
+	int err = 0;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		err = -EINVAL;
+		goto err_out;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	if (!bus_entry || !sd) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	pcifront_init_sd(sd, domain, bus, pdev);
+
+	b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
+				  &pcifront_bus_ops, sd);
+	if (!b) {
+		dev_err(&pdev->xdev->dev,
+			"Error creating PCI Frontend Bus!\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	bus_entry->bus = b;
+
+	list_add(&bus_entry->list, &pdev->root_buses);
+
+	/* pci_scan_bus_parented skips devices which do not have a have
+	* devfn==0. The pcifront_scan_bus enumerates all devfn. */
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+
+err_out:
+	kfree(bus_entry);
+	kfree(sd);
+
+	return err;
+}
+
+static int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+				   unsigned int domain, unsigned int bus)
+{
+	int err;
+	struct pci_bus *b;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		return -EINVAL;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Rescanning PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	b = pci_find_bus(domain, bus);
+	if (!b)
+		/* If the bus is unknown, create it. */
+		return pcifront_scan_root(pdev, domain, bus);
+
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+}
+
+static void free_root_bus_devs(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	while (!list_empty(&bus->devices)) {
+		dev = container_of(bus->devices.next, struct pci_dev,
+				   bus_list);
+		dev_dbg(&dev->dev, "removing device\n");
+		pci_remove_bus_device(dev);
+	}
+}
+
+static void pcifront_free_roots(struct pcifront_device *pdev)
+{
+	struct pci_bus_entry *bus_entry, *t;
+
+	dev_dbg(&pdev->xdev->dev, "cleaning up root buses\n");
+
+	list_for_each_entry_safe(bus_entry, t, &pdev->root_buses, list) {
+		list_del(&bus_entry->list);
+
+		free_root_bus_devs(bus_entry->bus);
+
+		kfree(bus_entry->bus->sysdata);
+
+		device_unregister(bus_entry->bus->bridge);
+		pci_remove_bus(bus_entry->bus);
+
+		kfree(bus_entry);
+	}
+}
+
+static pci_ers_result_t pcifront_common_process(int cmd,
+						struct pcifront_device *pdev,
+						pci_channel_state_t state)
+{
+	pci_ers_result_t result;
+	struct pci_driver *pdrv;
+	int bus = pdev->sh_info->aer_op.bus;
+	int devfn = pdev->sh_info->aer_op.devfn;
+	struct pci_dev *pcidev;
+	int flag = 0;
+
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront AER process: cmd %x (bus:%x, devfn%x)",
+		cmd, bus, devfn);
+	result = PCI_ERS_RESULT_NONE;
+
+	pcidev = pci_get_bus_and_slot(bus, devfn);
+	if (!pcidev || !pcidev->driver) {
+		dev_err(&pcidev->dev,
+			"device or driver is NULL\n");
+		return result;
+	}
+	pdrv = pcidev->driver;
+
+	if (get_driver(&pdrv->driver)) {
+		if (pdrv->err_handler && pdrv->err_handler->error_detected) {
+			dev_dbg(&pcidev->dev,
+				"trying to call AER service\n");
+			if (pcidev) {
+				flag = 1;
+				switch (cmd) {
+				case XEN_PCI_OP_aer_detected:
+					result = pdrv->err_handler->
+						 error_detected(pcidev, state);
+					break;
+				case XEN_PCI_OP_aer_mmio:
+					result = pdrv->err_handler->
+						 mmio_enabled(pcidev);
+					break;
+				case XEN_PCI_OP_aer_slotreset:
+					result = pdrv->err_handler->
+						 slot_reset(pcidev);
+					break;
+				case XEN_PCI_OP_aer_resume:
+					pdrv->err_handler->resume(pcidev);
+					break;
+				default:
+					dev_err(&pdev->xdev->dev,
+						"bad request in aer recovery "
+						"operation!\n");
+
+				}
+			}
+		}
+		put_driver(&pdrv->driver);
+	}
+	if (!flag)
+		result = PCI_ERS_RESULT_NONE;
+
+	return result;
+}
+
+
+static void pcifront_do_aer(struct work_struct *data)
+{
+	struct pcifront_device *pdev =
+		container_of(data, struct pcifront_device, op_work);
+	int cmd = pdev->sh_info->aer_op.cmd;
+	pci_channel_state_t state =
+		(pci_channel_state_t)pdev->sh_info->aer_op.err;
+
+	/*If a pci_conf op is in progress,
+		we have to wait until it is done before service aer op*/
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront service aer bus %x devfn %x\n",
+		pdev->sh_info->aer_op.bus, pdev->sh_info->aer_op.devfn);
+
+	pdev->sh_info->aer_op.err = pcifront_common_process(cmd, pdev, state);
+
+	/* Post the operation to the guest. */
+	wmb();
+	clear_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(pdev->evtchn);
+
+	/*in case of we lost an aer request in four lines time_window*/
+	smp_mb__before_clear_bit();
+	clear_bit(_PDEVB_op_active, &pdev->flags);
+	smp_mb__after_clear_bit();
+
+	schedule_pcifront_aer_op(pdev);
+
+}
+
+static irqreturn_t pcifront_handler_aer(int irq, void *dev)
+{
+	struct pcifront_device *pdev = dev;
+	schedule_pcifront_aer_op(pdev);
+	return IRQ_HANDLED;
+}
+static int pcifront_connect(struct pcifront_device *pdev)
+{
+	int err = 0;
+
+	spin_lock(&pcifront_dev_lock);
+
+	if (!pcifront_dev) {
+		dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
+		pcifront_dev = pdev;
+	} else {
+		dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+		err = -EEXIST;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+
+	return err;
+}
+
+static void pcifront_disconnect(struct pcifront_device *pdev)
+{
+	spin_lock(&pcifront_dev_lock);
+
+	if (pdev == pcifront_dev) {
+		dev_info(&pdev->xdev->dev,
+			 "Disconnecting PCI Frontend Buses\n");
+		pcifront_dev = NULL;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+}
+static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev;
+
+	pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+
+	pdev->sh_info =
+	    (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL);
+	if (pdev->sh_info == NULL) {
+		kfree(pdev);
+		pdev = NULL;
+		goto out;
+	}
+	pdev->sh_info->flags = 0;
+
+	/*Flag for registering PV AER handler*/
+	set_bit(_XEN_PCIB_AERHANDLER, (void *)&pdev->sh_info->flags);
+
+	dev_set_drvdata(&xdev->dev, pdev);
+	pdev->xdev = xdev;
+
+	INIT_LIST_HEAD(&pdev->root_buses);
+
+	spin_lock_init(&pdev->sh_info_lock);
+
+	pdev->evtchn = INVALID_EVTCHN;
+	pdev->gnt_ref = INVALID_GRANT_REF;
+	pdev->irq = -1;
+
+	INIT_WORK(&pdev->op_work, pcifront_do_aer);
+
+	dev_dbg(&xdev->dev, "Allocated pdev @ 0x%p pdev->sh_info @ 0x%p\n",
+		pdev, pdev->sh_info);
+out:
+	return pdev;
+}
+
+static void free_pdev(struct pcifront_device *pdev)
+{
+	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
+
+	pcifront_free_roots(pdev);
+
+	/*For PCIE_AER error handling job*/
+	flush_scheduled_work();
+
+	if (pdev->irq)
+		unbind_from_irqhandler(pdev->irq, pdev);
+
+	if (pdev->evtchn != INVALID_EVTCHN)
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+
+	if (pdev->gnt_ref != INVALID_GRANT_REF)
+		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
+					  (unsigned long)pdev->sh_info);
+	else
+		free_page((unsigned long)pdev->sh_info);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+
+	kfree(pdev);
+}
+
+static int pcifront_publish_info(struct pcifront_device *pdev)
+{
+	int err = 0;
+	struct xenbus_transaction trans;
+
+	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
+	if (err < 0)
+		goto out;
+
+	pdev->gnt_ref = err;
+
+	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
+	if (err)
+		goto out;
+
+	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+		0, "pcifront", pdev);
+	if (err < 0) {
+		/*
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
+				 "irqhandler.\n");
+		*/
+		return err;
+	}
+	pdev->irq = err;
+
+do_publish:
+	err = xenbus_transaction_start(&trans);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend "
+				 "(start transaction)");
+		goto out;
+	}
+
+	err = xenbus_printf(trans, pdev->xdev->nodename,
+			    "pci-op-ref", "%u", pdev->gnt_ref);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "event-channel", "%u", pdev->evtchn);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "magic", XEN_PCI_MAGIC);
+
+	if (err) {
+		xenbus_transaction_end(trans, 1);
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend");
+		goto out;
+	} else {
+		err = xenbus_transaction_end(trans, 0);
+		if (err == -EAGAIN)
+			goto do_publish;
+		else if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error completing transaction "
+					 "for backend");
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+
+	dev_dbg(&pdev->xdev->dev, "publishing successful!\n");
+
+out:
+	return err;
+}
+
+static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	char str[64];
+	unsigned int domain, bus;
+
+
+	/* Only connect once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	err = pcifront_connect(pdev);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error connecting PCI Frontend");
+		goto out;
+	}
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_scan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_scan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+	int err = 0;
+	enum xenbus_state prev_state;
+
+
+	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+
+	if (prev_state >= XenbusStateClosing)
+		goto out;
+
+	if (prev_state == XenbusStateConnected) {
+		pcifront_free_roots(pdev);
+		pcifront_disconnect(pdev);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateClosed);
+
+out:
+
+	return err;
+}
+
+static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	unsigned int domain, bus;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_rescan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_rescan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_detach_devices(struct pcifront_device *pdev)
+{
+	int err = 0;
+	int i, num_devs;
+	unsigned int domain, bus, slot, func;
+	struct pci_bus *pci_bus;
+	struct pci_dev *pci_dev;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateConnected)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI devices");
+		goto out;
+	}
+
+	/* Find devices being detached and remove them. */
+	for (i = 0; i < num_devs; i++) {
+		int l, state;
+		l = snprintf(str, sizeof(str), "state-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d",
+				   &state);
+		if (err != 1)
+			state = XenbusStateUnknown;
+
+		if (state != XenbusStateClosing)
+			continue;
+
+		/* Remove device. */
+		l = snprintf(str, sizeof(str), "vdev-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err != 4) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI device %d", i);
+			goto out;
+		}
+
+		pci_bus = pci_find_bus(domain, bus);
+		if (!pci_bus) {
+			dev_dbg(&pdev->xdev->dev, "Cannot get bus %04x:%02x\n",
+				domain, bus);
+			continue;
+		}
+		pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
+		if (!pci_dev) {
+			dev_dbg(&pdev->xdev->dev,
+				"Cannot get PCI device %04x:%02x:%02x.%02x\n",
+				domain, bus, slot, func);
+			continue;
+		}
+		pci_remove_bus_device(pci_dev);
+		pci_dev_put(pci_dev);
+
+		dev_dbg(&pdev->xdev->dev,
+			"PCI device %04x:%02x:%02x.%02x removed.\n",
+			domain, bus, slot, func);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring);
+
+out:
+	return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+						  enum xenbus_state be_state)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	switch (be_state) {
+	case XenbusStateUnknown:
+	case XenbusStateInitialising:
+	case XenbusStateInitWait:
+	case XenbusStateInitialised:
+	case XenbusStateClosed:
+		break;
+
+	case XenbusStateConnected:
+		pcifront_try_connect(pdev);
+		break;
+
+	case XenbusStateClosing:
+		dev_warn(&xdev->dev, "backend going away!\n");
+		pcifront_try_disconnect(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		pcifront_detach_devices(pdev);
+		break;
+
+	case XenbusStateReconfigured:
+		pcifront_attach_devices(pdev);
+		break;
+	}
+}
+
+static int pcifront_xenbus_probe(struct xenbus_device *xdev,
+				 const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct pcifront_device *pdev = alloc_pdev(xdev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(xdev, err,
+				 "Error allocating pcifront_device struct");
+		goto out;
+	}
+
+	err = pcifront_publish_info(pdev);
+	if (err)
+		free_pdev(pdev);
+
+out:
+	return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+	if (pdev)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static struct xenbus_driver xenbus_pcifront_driver = {
+	.name			= "pcifront",
+	.owner			= THIS_MODULE,
+	.ids			= xenpci_ids,
+	.probe			= pcifront_xenbus_probe,
+	.remove			= pcifront_xenbus_remove,
+	.otherend_changed	= pcifront_backend_changed,
+};
+
+static int __init pcifront_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	pci_frontend_registrar(1 /* enable */);
+
+	return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+static void __exit pcifront_cleanup(void)
+{
+	xenbus_unregister_driver(&xenbus_pcifront_driver);
+	pci_frontend_registrar(0 /* disable */);
+}
+module_init(pcifront_init);
+module_exit(pcifront_cleanup);
+
+MODULE_DESCRIPTION("Xen PCI passthrough frontend.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:pci");
diff --git a/include/xen/interface/io/pciif.h b/include/xen/interface/io/pciif.h
new file mode 100644
index 0000000..d9922ae
--- /dev/null
+++ b/include/xen/interface/io/pciif.h
@@ -0,0 +1,112 @@
+/*
+ * PCI Backend/Frontend Common Data Structures & Macros
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCI_COMMON_H__
+#define __XEN_PCI_COMMON_H__
+
+/* Be sure to bump this number if you change this file */
+#define XEN_PCI_MAGIC "7"
+
+/* xen_pci_sharedinfo flags */
+#define	_XEN_PCIF_active		(0)
+#define	XEN_PCIF_active			(1<<_XEN_PCIF_active)
+#define	_XEN_PCIB_AERHANDLER		(1)
+#define	XEN_PCIB_AERHANDLER		(1<<_XEN_PCIB_AERHANDLER)
+#define	_XEN_PCIB_active		(2)
+#define	XEN_PCIB_active			(1<<_XEN_PCIB_active)
+
+/* xen_pci_op commands */
+#define	XEN_PCI_OP_conf_read		(0)
+#define	XEN_PCI_OP_conf_write		(1)
+#define	XEN_PCI_OP_enable_msi		(2)
+#define	XEN_PCI_OP_disable_msi		(3)
+#define	XEN_PCI_OP_enable_msix		(4)
+#define	XEN_PCI_OP_disable_msix		(5)
+#define	XEN_PCI_OP_aer_detected		(6)
+#define	XEN_PCI_OP_aer_resume		(7)
+#define	XEN_PCI_OP_aer_mmio		(8)
+#define	XEN_PCI_OP_aer_slotreset	(9)
+
+/* xen_pci_op error numbers */
+#define	XEN_PCI_ERR_success		(0)
+#define	XEN_PCI_ERR_dev_not_found	(-1)
+#define	XEN_PCI_ERR_invalid_offset	(-2)
+#define	XEN_PCI_ERR_access_denied	(-3)
+#define	XEN_PCI_ERR_not_implemented	(-4)
+/* XEN_PCI_ERR_op_failed - backend failed to complete the operation */
+#define XEN_PCI_ERR_op_failed		(-5)
+
+/*
+ * it should be PAGE_SIZE-sizeof(struct xen_pci_op))/sizeof(struct msix_entry))
+ * Should not exceed 128
+ */
+#define SH_INFO_MAX_VEC			128
+
+struct xen_msix_entry {
+	uint16_t vector;
+	uint16_t entry;
+};
+struct xen_pci_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+
+	/* OUT: will contain an error number (if any) from errno.h */
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment */
+	uint32_t bus;
+	uint32_t devfn;
+
+	/* IN: which configuration registers to touch */
+	int32_t offset;
+	int32_t size;
+
+	/* IN/OUT: Contains the result after a READ or the value to WRITE */
+	uint32_t value;
+	/* IN: Contains extra infor for this operation */
+	uint32_t info;
+	/*IN:  param for msi-x */
+	struct xen_msix_entry msix_entries[SH_INFO_MAX_VEC];
+};
+
+/*used for pcie aer handling*/
+struct xen_pcie_aer_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+	/*IN/OUT: return aer_op result or carry error_detected state as input*/
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment*/
+	uint32_t bus;
+	uint32_t devfn;
+};
+struct xen_pci_sharedinfo {
+	/* flags - XEN_PCIF_* */
+	uint32_t flags;
+	struct xen_pci_op op;
+	struct xen_pcie_aer_op aer_op;
+};
+
+#endif /* __XEN_PCI_COMMON_H__ */
-- 
1.7.1


[-- Attachment #2: 0001-xen-pcifront-Xen-PCI-frontend-driver.patch --]
[-- Type: text/x-diff, Size: 34891 bytes --]

>From 7e865c880aa5942c4c22bd67618b2e9fc1788da6 Mon Sep 17 00:00:00 2001
From: Ryan Wilson <hap9@epoch.ncsc.mil>
Date: Mon, 2 Aug 2010 21:31:05 -0400
Subject: [PATCH] xen-pcifront: Xen PCI frontend driver.

This is a port of the 2.6.18 Xen PCI front driver with fixes
to make it build under 2.6.34 and later (for the full list of
changes: git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git
historic/xen-pcifront-0.1). It also includes the fixes
to make it work properly.

[v2: Updated Kconfig, removed crud, added Reviewed-by]
[v3: Added 'static', fixed grant table leak, redid Kconfig]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Jan Beulich <JBeulich@novell.com>
---
 drivers/pci/Kconfig              |   21 +
 drivers/pci/Makefile             |    2 +
 drivers/pci/xen-pcifront.c       | 1152 ++++++++++++++++++++++++++++++++++++++
 include/xen/interface/io/pciif.h |  112 ++++
 4 files changed, 1287 insertions(+), 0 deletions(-)
 create mode 100644 drivers/pci/xen-pcifront.c
 create mode 100644 include/xen/interface/io/pciif.h

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34ef70d..5b1630e 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -40,6 +40,27 @@ config PCI_STUB
 
 	  When in doubt, say N.
 
+config XEN_PCIDEV_FRONTEND
+        tristate "Xen PCI Frontend"
+        depends on PCI && X86 && XEN
+        select HOTPLUG
+        select PCI_XEN
+        default y
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
+config XEN_PCIDEV_FE_DEBUG
+        bool "Xen PCI Frontend debugging"
+        depends on XEN_PCIDEV_FRONTEND && PCI_DEBUG
+	help
+	  Say Y here if you want the Xen PCI frontend to produce a bunch of debug
+	  messages to the system log.  Select this if you are having a
+	  problem with Xen PCI frontend support and want to see more of what is
+	  going on.
+
+	  When in doubt, say N.
+
 config HT_IRQ
 	bool "Interrupts on hypertransport devices"
 	default y
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index dc1aa09..d5e2705 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -65,6 +65,8 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
 
 obj-$(CONFIG_PCI_STUB) += pci-stub.o
 
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
 endif
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
new file mode 100644
index 0000000..238870a
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1152 @@
+/*
+ * Xen PCI Frontend.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pciif.h>
+#include <asm/xen/pci.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <linux/time.h>
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN    (-1)
+
+struct pci_bus_entry {
+	struct list_head list;
+	struct pci_bus *bus;
+};
+
+#define _PDEVB_op_active		(0)
+#define PDEVB_op_active			(1 << (_PDEVB_op_active))
+
+struct pcifront_device {
+	struct xenbus_device *xdev;
+	struct list_head root_buses;
+
+	int evtchn;
+	int gnt_ref;
+
+	int irq;
+
+	/* Lock this when doing any operations in sh_info */
+	spinlock_t sh_info_lock;
+	struct xen_pci_sharedinfo *sh_info;
+	struct work_struct op_work;
+	unsigned long flags;
+
+};
+
+struct pcifront_sd {
+	int domain;
+	struct pcifront_device *pdev;
+};
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+	return sd->pdev;
+}
+
+static inline void pcifront_init_sd(struct pcifront_sd *sd,
+				    unsigned int domain, unsigned int bus,
+				    struct pcifront_device *pdev)
+{
+	sd->domain = domain;
+	sd->pdev = pdev;
+}
+
+static DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev;
+
+static int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static int errno_to_pcibios_err(int errno)
+{
+	switch (errno) {
+	case XEN_PCI_ERR_success:
+		return PCIBIOS_SUCCESSFUL;
+
+	case XEN_PCI_ERR_dev_not_found:
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	case XEN_PCI_ERR_invalid_offset:
+	case XEN_PCI_ERR_op_failed:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	case XEN_PCI_ERR_not_implemented:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+
+	case XEN_PCI_ERR_access_denied:
+		return PCIBIOS_SET_FAILED;
+	}
+	return errno;
+}
+
+static inline void schedule_pcifront_aer_op(struct pcifront_device *pdev)
+{
+	if (test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+		&& !test_and_set_bit(_PDEVB_op_active, &pdev->flags)) {
+		dev_dbg(&pdev->xdev->dev, "schedule aer frontend job\n");
+		schedule_work(&pdev->op_work);
+	}
+}
+
+static int do_pci_op(struct pcifront_device *pdev, struct xen_pci_op *op)
+{
+	int err = 0;
+	struct xen_pci_op *active_op = &pdev->sh_info->op;
+	unsigned long irq_flags;
+	evtchn_port_t port = pdev->evtchn;
+	unsigned irq = pdev->irq;
+	s64 ns, ns_timeout;
+	struct timeval tv;
+
+	spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
+
+	memcpy(active_op, op, sizeof(struct xen_pci_op));
+
+	/* Go */
+	wmb();
+	set_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(port);
+
+	/*
+	 * We set a poll timeout of 3 seconds but give up on return after
+	 * 2 seconds. It is better to time out too late rather than too early
+	 * (in the latter case we end up continually re-executing poll() with a
+	 * timeout in the past). 1s difference gives plenty of slack for error.
+	 */
+	do_gettimeofday(&tv);
+	ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+
+	xen_clear_irq_pending(irq);
+
+	while (test_bit(_XEN_PCIF_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		xen_poll_irq_timeout(irq, jiffies + 3*HZ);
+		xen_clear_irq_pending(irq);
+		do_gettimeofday(&tv);
+		ns = timeval_to_ns(&tv);
+		if (ns > ns_timeout) {
+			dev_err(&pdev->xdev->dev,
+				"pciback not responding!!!\n");
+			clear_bit(_XEN_PCIF_active,
+				  (unsigned long *)&pdev->sh_info->flags);
+			err = XEN_PCI_ERR_dev_not_found;
+			goto out;
+		}
+	}
+
+	/*
+	* We might lose backend service request since we
+	* reuse same evtchn with pci_conf backend response. So re-schedule
+	* aer pcifront service.
+	*/
+	if (test_bit(_XEN_PCIB_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		dev_err(&pdev->xdev->dev,
+			"schedule aer pcifront service\n");
+		schedule_pcifront_aer_op(pdev);
+	}
+
+	memcpy(op, active_op, sizeof(struct xen_pci_op));
+
+	err = op->err;
+out:
+	spin_unlock_irqrestore(&pdev->sh_info_lock, irq_flags);
+	return err;
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_read(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 *val)
+{
+	int err = 0;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_read,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+			 pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn), where, size);
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (verbose_request)
+			dev_info(&pdev->xdev->dev, "read got back value %x\n",
+				 op.value);
+
+		*val = op.value;
+	} else if (err == -ENODEV) {
+		/* No device here, pretend that it just returned 0 */
+		err = 0;
+		*val = 0;
+	}
+
+	return errno_to_pcibios_err(err);
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_write(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 val)
+{
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_write,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+		.value  = val,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "write dev=%04x:%02x:%02x.%01x - "
+			 "offset %x size %d val %x\n",
+			 pci_domain_nr(bus), bus->number,
+			 PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+
+	return errno_to_pcibios_err(do_pci_op(pdev, &op));
+}
+
+struct pci_ops pcifront_bus_ops = {
+	.read = pcifront_bus_read,
+	.write = pcifront_bus_write,
+};
+
+#ifdef CONFIG_PCI_MSI
+static int pci_frontend_enable_msix(struct pci_dev *dev,
+				    int **vector, int nvec)
+{
+	int err;
+	int i;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+		.value = nvec,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+	struct msi_desc *entry;
+
+	if (nvec > SH_INFO_MAX_VEC) {
+		dev_err(&dev->dev, "too much vector for pci frontend: %x."
+				   " Increase SH_INFO_MAX_VEC.\n", nvec);
+		return -EINVAL;
+	}
+
+	i = 0;
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+		/* Vector is useless at this point. */
+		op.msix_entries[i].vector = -1;
+		i++;
+	}
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (likely(!op.value)) {
+			/* we get the result */
+			for (i = 0; i < nvec; i++)
+				*(*vector+i) = op.msix_entries[i].vector;
+			return 0;
+		} else {
+			printk(KERN_DEBUG "enable msix get value %x\n",
+				op.value);
+			return op.value;
+		}
+	} else {
+		dev_err(&dev->dev, "enable msix get err %x\n", err);
+		return err;
+	}
+}
+
+static void pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+
+	/* What should do for error ? */
+	if (err)
+		dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
+}
+
+static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (likely(!err)) {
+		*(*vector) = op.value;
+	} else {
+		dev_err(&dev->dev, "pci frontend enable msi failed for dev "
+				    "%x:%x\n", op.bus, op.devfn);
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static void pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (err == XEN_PCI_ERR_dev_not_found) {
+		/* XXX No response from backend, what shall we do? */
+		printk(KERN_DEBUG "get no response from backend for disable MSI\n");
+		return;
+	}
+	if (err)
+		/* how can pciback notify us fail? */
+		printk(KERN_DEBUG "get fake response frombackend\n");
+}
+
+static struct xen_pci_frontend_ops pci_frontend_ops = {
+	.enable_msi = pci_frontend_enable_msi,
+	.disable_msi = pci_frontend_disable_msi,
+	.enable_msix = pci_frontend_enable_msix,
+	.disable_msix = pci_frontend_disable_msix,
+};
+
+static void pci_frontend_registrar(int enable)
+{
+	if (enable)
+		xen_pci_frontend = &pci_frontend_ops;
+	else
+		xen_pci_frontend = NULL;
+};
+#else
+static inline void pci_frontend_registrar(int enable) { };
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static int pcifront_claim_resource(struct pci_dev *dev, void *data)
+{
+	struct pcifront_device *pdev = data;
+	int i;
+	struct resource *r;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		r = &dev->resource[i];
+
+		if (!r->parent && r->start && r->flags) {
+			dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
+				pci_name(dev), i);
+			if (pci_claim_resource(dev, i)) {
+				dev_err(&pdev->xdev->dev, "Could not claim "
+					"resource %s/%d! Device offline. Try "
+					"giving less than 4GB to domain.\n",
+					pci_name(dev), i);
+			}
+		}
+	}
+
+	return 0;
+}
+
+int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+				unsigned int domain, unsigned int bus,
+				struct pci_bus *b)
+{
+	struct pci_dev *d;
+	unsigned int devfn;
+
+	/* Scan the bus for functions and add.
+	 * We omit handling of PCI bridge attachment because pciback prevents
+	 * bridges from being exported.
+	 */
+	for (devfn = 0; devfn < 0x100; devfn++) {
+		d = pci_get_slot(b, devfn);
+		if (d) {
+			/* Device is already known. */
+			pci_dev_put(d);
+			continue;
+		}
+
+		d = pci_scan_single_device(b, devfn);
+		if (d)
+			dev_info(&pdev->xdev->dev, "New device on "
+				 "%04x:%02x:%02x.%02x found.\n", domain, bus,
+				 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	}
+
+	return 0;
+}
+
+static int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+				 unsigned int domain, unsigned int bus)
+{
+	struct pci_bus *b;
+	struct pcifront_sd *sd = NULL;
+	struct pci_bus_entry *bus_entry = NULL;
+	int err = 0;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		err = -EINVAL;
+		goto err_out;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	if (!bus_entry || !sd) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	pcifront_init_sd(sd, domain, bus, pdev);
+
+	b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
+				  &pcifront_bus_ops, sd);
+	if (!b) {
+		dev_err(&pdev->xdev->dev,
+			"Error creating PCI Frontend Bus!\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	bus_entry->bus = b;
+
+	list_add(&bus_entry->list, &pdev->root_buses);
+
+	/* pci_scan_bus_parented skips devices which do not have a have
+	* devfn==0. The pcifront_scan_bus enumerates all devfn. */
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+
+err_out:
+	kfree(bus_entry);
+	kfree(sd);
+
+	return err;
+}
+
+static int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+				   unsigned int domain, unsigned int bus)
+{
+	int err;
+	struct pci_bus *b;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		return -EINVAL;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Rescanning PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	b = pci_find_bus(domain, bus);
+	if (!b)
+		/* If the bus is unknown, create it. */
+		return pcifront_scan_root(pdev, domain, bus);
+
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+}
+
+static void free_root_bus_devs(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	while (!list_empty(&bus->devices)) {
+		dev = container_of(bus->devices.next, struct pci_dev,
+				   bus_list);
+		dev_dbg(&dev->dev, "removing device\n");
+		pci_remove_bus_device(dev);
+	}
+}
+
+static void pcifront_free_roots(struct pcifront_device *pdev)
+{
+	struct pci_bus_entry *bus_entry, *t;
+
+	dev_dbg(&pdev->xdev->dev, "cleaning up root buses\n");
+
+	list_for_each_entry_safe(bus_entry, t, &pdev->root_buses, list) {
+		list_del(&bus_entry->list);
+
+		free_root_bus_devs(bus_entry->bus);
+
+		kfree(bus_entry->bus->sysdata);
+
+		device_unregister(bus_entry->bus->bridge);
+		pci_remove_bus(bus_entry->bus);
+
+		kfree(bus_entry);
+	}
+}
+
+static pci_ers_result_t pcifront_common_process(int cmd,
+						struct pcifront_device *pdev,
+						pci_channel_state_t state)
+{
+	pci_ers_result_t result;
+	struct pci_driver *pdrv;
+	int bus = pdev->sh_info->aer_op.bus;
+	int devfn = pdev->sh_info->aer_op.devfn;
+	struct pci_dev *pcidev;
+	int flag = 0;
+
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront AER process: cmd %x (bus:%x, devfn%x)",
+		cmd, bus, devfn);
+	result = PCI_ERS_RESULT_NONE;
+
+	pcidev = pci_get_bus_and_slot(bus, devfn);
+	if (!pcidev || !pcidev->driver) {
+		dev_err(&pcidev->dev,
+			"device or driver is NULL\n");
+		return result;
+	}
+	pdrv = pcidev->driver;
+
+	if (get_driver(&pdrv->driver)) {
+		if (pdrv->err_handler && pdrv->err_handler->error_detected) {
+			dev_dbg(&pcidev->dev,
+				"trying to call AER service\n");
+			if (pcidev) {
+				flag = 1;
+				switch (cmd) {
+				case XEN_PCI_OP_aer_detected:
+					result = pdrv->err_handler->
+						 error_detected(pcidev, state);
+					break;
+				case XEN_PCI_OP_aer_mmio:
+					result = pdrv->err_handler->
+						 mmio_enabled(pcidev);
+					break;
+				case XEN_PCI_OP_aer_slotreset:
+					result = pdrv->err_handler->
+						 slot_reset(pcidev);
+					break;
+				case XEN_PCI_OP_aer_resume:
+					pdrv->err_handler->resume(pcidev);
+					break;
+				default:
+					dev_err(&pdev->xdev->dev,
+						"bad request in aer recovery "
+						"operation!\n");
+
+				}
+			}
+		}
+		put_driver(&pdrv->driver);
+	}
+	if (!flag)
+		result = PCI_ERS_RESULT_NONE;
+
+	return result;
+}
+
+
+static void pcifront_do_aer(struct work_struct *data)
+{
+	struct pcifront_device *pdev =
+		container_of(data, struct pcifront_device, op_work);
+	int cmd = pdev->sh_info->aer_op.cmd;
+	pci_channel_state_t state =
+		(pci_channel_state_t)pdev->sh_info->aer_op.err;
+
+	/*If a pci_conf op is in progress,
+		we have to wait until it is done before service aer op*/
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront service aer bus %x devfn %x\n",
+		pdev->sh_info->aer_op.bus, pdev->sh_info->aer_op.devfn);
+
+	pdev->sh_info->aer_op.err = pcifront_common_process(cmd, pdev, state);
+
+	/* Post the operation to the guest. */
+	wmb();
+	clear_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(pdev->evtchn);
+
+	/*in case of we lost an aer request in four lines time_window*/
+	smp_mb__before_clear_bit();
+	clear_bit(_PDEVB_op_active, &pdev->flags);
+	smp_mb__after_clear_bit();
+
+	schedule_pcifront_aer_op(pdev);
+
+}
+
+static irqreturn_t pcifront_handler_aer(int irq, void *dev)
+{
+	struct pcifront_device *pdev = dev;
+	schedule_pcifront_aer_op(pdev);
+	return IRQ_HANDLED;
+}
+static int pcifront_connect(struct pcifront_device *pdev)
+{
+	int err = 0;
+
+	spin_lock(&pcifront_dev_lock);
+
+	if (!pcifront_dev) {
+		dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
+		pcifront_dev = pdev;
+	} else {
+		dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+		err = -EEXIST;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+
+	return err;
+}
+
+static void pcifront_disconnect(struct pcifront_device *pdev)
+{
+	spin_lock(&pcifront_dev_lock);
+
+	if (pdev == pcifront_dev) {
+		dev_info(&pdev->xdev->dev,
+			 "Disconnecting PCI Frontend Buses\n");
+		pcifront_dev = NULL;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+}
+static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev;
+
+	pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+
+	pdev->sh_info =
+	    (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL);
+	if (pdev->sh_info == NULL) {
+		kfree(pdev);
+		pdev = NULL;
+		goto out;
+	}
+	pdev->sh_info->flags = 0;
+
+	/*Flag for registering PV AER handler*/
+	set_bit(_XEN_PCIB_AERHANDLER, (void *)&pdev->sh_info->flags);
+
+	dev_set_drvdata(&xdev->dev, pdev);
+	pdev->xdev = xdev;
+
+	INIT_LIST_HEAD(&pdev->root_buses);
+
+	spin_lock_init(&pdev->sh_info_lock);
+
+	pdev->evtchn = INVALID_EVTCHN;
+	pdev->gnt_ref = INVALID_GRANT_REF;
+	pdev->irq = -1;
+
+	INIT_WORK(&pdev->op_work, pcifront_do_aer);
+
+	dev_dbg(&xdev->dev, "Allocated pdev @ 0x%p pdev->sh_info @ 0x%p\n",
+		pdev, pdev->sh_info);
+out:
+	return pdev;
+}
+
+static void free_pdev(struct pcifront_device *pdev)
+{
+	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
+
+	pcifront_free_roots(pdev);
+
+	/*For PCIE_AER error handling job*/
+	flush_scheduled_work();
+
+	if (pdev->irq)
+		unbind_from_irqhandler(pdev->irq, pdev);
+
+	if (pdev->evtchn != INVALID_EVTCHN)
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+
+	if (pdev->gnt_ref != INVALID_GRANT_REF)
+		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
+					  (unsigned long)pdev->sh_info);
+	else
+		free_page((unsigned long)pdev->sh_info);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+
+	kfree(pdev);
+}
+
+static int pcifront_publish_info(struct pcifront_device *pdev)
+{
+	int err = 0;
+	struct xenbus_transaction trans;
+
+	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
+	if (err < 0)
+		goto out;
+
+	pdev->gnt_ref = err;
+
+	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
+	if (err)
+		goto out;
+
+	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+		0, "pcifront", pdev);
+	if (err < 0) {
+		/*
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
+				 "irqhandler.\n");
+		*/
+		return err;
+	}
+	pdev->irq = err;
+
+do_publish:
+	err = xenbus_transaction_start(&trans);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend "
+				 "(start transaction)");
+		goto out;
+	}
+
+	err = xenbus_printf(trans, pdev->xdev->nodename,
+			    "pci-op-ref", "%u", pdev->gnt_ref);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "event-channel", "%u", pdev->evtchn);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "magic", XEN_PCI_MAGIC);
+
+	if (err) {
+		xenbus_transaction_end(trans, 1);
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend");
+		goto out;
+	} else {
+		err = xenbus_transaction_end(trans, 0);
+		if (err == -EAGAIN)
+			goto do_publish;
+		else if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error completing transaction "
+					 "for backend");
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+
+	dev_dbg(&pdev->xdev->dev, "publishing successful!\n");
+
+out:
+	return err;
+}
+
+static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	char str[64];
+	unsigned int domain, bus;
+
+
+	/* Only connect once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	err = pcifront_connect(pdev);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error connecting PCI Frontend");
+		goto out;
+	}
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_scan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_scan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+	int err = 0;
+	enum xenbus_state prev_state;
+
+
+	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+
+	if (prev_state >= XenbusStateClosing)
+		goto out;
+
+	if (prev_state == XenbusStateConnected) {
+		pcifront_free_roots(pdev);
+		pcifront_disconnect(pdev);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateClosed);
+
+out:
+
+	return err;
+}
+
+static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	unsigned int domain, bus;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_rescan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_rescan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_detach_devices(struct pcifront_device *pdev)
+{
+	int err = 0;
+	int i, num_devs;
+	unsigned int domain, bus, slot, func;
+	struct pci_bus *pci_bus;
+	struct pci_dev *pci_dev;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateConnected)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI devices");
+		goto out;
+	}
+
+	/* Find devices being detached and remove them. */
+	for (i = 0; i < num_devs; i++) {
+		int l, state;
+		l = snprintf(str, sizeof(str), "state-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d",
+				   &state);
+		if (err != 1)
+			state = XenbusStateUnknown;
+
+		if (state != XenbusStateClosing)
+			continue;
+
+		/* Remove device. */
+		l = snprintf(str, sizeof(str), "vdev-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err != 4) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI device %d", i);
+			goto out;
+		}
+
+		pci_bus = pci_find_bus(domain, bus);
+		if (!pci_bus) {
+			dev_dbg(&pdev->xdev->dev, "Cannot get bus %04x:%02x\n",
+				domain, bus);
+			continue;
+		}
+		pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
+		if (!pci_dev) {
+			dev_dbg(&pdev->xdev->dev,
+				"Cannot get PCI device %04x:%02x:%02x.%02x\n",
+				domain, bus, slot, func);
+			continue;
+		}
+		pci_remove_bus_device(pci_dev);
+		pci_dev_put(pci_dev);
+
+		dev_dbg(&pdev->xdev->dev,
+			"PCI device %04x:%02x:%02x.%02x removed.\n",
+			domain, bus, slot, func);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring);
+
+out:
+	return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+						  enum xenbus_state be_state)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	switch (be_state) {
+	case XenbusStateUnknown:
+	case XenbusStateInitialising:
+	case XenbusStateInitWait:
+	case XenbusStateInitialised:
+	case XenbusStateClosed:
+		break;
+
+	case XenbusStateConnected:
+		pcifront_try_connect(pdev);
+		break;
+
+	case XenbusStateClosing:
+		dev_warn(&xdev->dev, "backend going away!\n");
+		pcifront_try_disconnect(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		pcifront_detach_devices(pdev);
+		break;
+
+	case XenbusStateReconfigured:
+		pcifront_attach_devices(pdev);
+		break;
+	}
+}
+
+static int pcifront_xenbus_probe(struct xenbus_device *xdev,
+				 const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct pcifront_device *pdev = alloc_pdev(xdev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(xdev, err,
+				 "Error allocating pcifront_device struct");
+		goto out;
+	}
+
+	err = pcifront_publish_info(pdev);
+	if (err)
+		free_pdev(pdev);
+
+out:
+	return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+	if (pdev)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static struct xenbus_driver xenbus_pcifront_driver = {
+	.name			= "pcifront",
+	.owner			= THIS_MODULE,
+	.ids			= xenpci_ids,
+	.probe			= pcifront_xenbus_probe,
+	.remove			= pcifront_xenbus_remove,
+	.otherend_changed	= pcifront_backend_changed,
+};
+
+static int __init pcifront_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	pci_frontend_registrar(1 /* enable */);
+
+	return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+static void __exit pcifront_cleanup(void)
+{
+	xenbus_unregister_driver(&xenbus_pcifront_driver);
+	pci_frontend_registrar(0 /* disable */);
+}
+module_init(pcifront_init);
+module_exit(pcifront_cleanup);
+
+MODULE_DESCRIPTION("Xen PCI passthrough frontend.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:pci");
diff --git a/include/xen/interface/io/pciif.h b/include/xen/interface/io/pciif.h
new file mode 100644
index 0000000..d9922ae
--- /dev/null
+++ b/include/xen/interface/io/pciif.h
@@ -0,0 +1,112 @@
+/*
+ * PCI Backend/Frontend Common Data Structures & Macros
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCI_COMMON_H__
+#define __XEN_PCI_COMMON_H__
+
+/* Be sure to bump this number if you change this file */
+#define XEN_PCI_MAGIC "7"
+
+/* xen_pci_sharedinfo flags */
+#define	_XEN_PCIF_active		(0)
+#define	XEN_PCIF_active			(1<<_XEN_PCIF_active)
+#define	_XEN_PCIB_AERHANDLER		(1)
+#define	XEN_PCIB_AERHANDLER		(1<<_XEN_PCIB_AERHANDLER)
+#define	_XEN_PCIB_active		(2)
+#define	XEN_PCIB_active			(1<<_XEN_PCIB_active)
+
+/* xen_pci_op commands */
+#define	XEN_PCI_OP_conf_read		(0)
+#define	XEN_PCI_OP_conf_write		(1)
+#define	XEN_PCI_OP_enable_msi		(2)
+#define	XEN_PCI_OP_disable_msi		(3)
+#define	XEN_PCI_OP_enable_msix		(4)
+#define	XEN_PCI_OP_disable_msix		(5)
+#define	XEN_PCI_OP_aer_detected		(6)
+#define	XEN_PCI_OP_aer_resume		(7)
+#define	XEN_PCI_OP_aer_mmio		(8)
+#define	XEN_PCI_OP_aer_slotreset	(9)
+
+/* xen_pci_op error numbers */
+#define	XEN_PCI_ERR_success		(0)
+#define	XEN_PCI_ERR_dev_not_found	(-1)
+#define	XEN_PCI_ERR_invalid_offset	(-2)
+#define	XEN_PCI_ERR_access_denied	(-3)
+#define	XEN_PCI_ERR_not_implemented	(-4)
+/* XEN_PCI_ERR_op_failed - backend failed to complete the operation */
+#define XEN_PCI_ERR_op_failed		(-5)
+
+/*
+ * it should be PAGE_SIZE-sizeof(struct xen_pci_op))/sizeof(struct msix_entry))
+ * Should not exceed 128
+ */
+#define SH_INFO_MAX_VEC			128
+
+struct xen_msix_entry {
+	uint16_t vector;
+	uint16_t entry;
+};
+struct xen_pci_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+
+	/* OUT: will contain an error number (if any) from errno.h */
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment */
+	uint32_t bus;
+	uint32_t devfn;
+
+	/* IN: which configuration registers to touch */
+	int32_t offset;
+	int32_t size;
+
+	/* IN/OUT: Contains the result after a READ or the value to WRITE */
+	uint32_t value;
+	/* IN: Contains extra infor for this operation */
+	uint32_t info;
+	/*IN:  param for msi-x */
+	struct xen_msix_entry msix_entries[SH_INFO_MAX_VEC];
+};
+
+/*used for pcie aer handling*/
+struct xen_pcie_aer_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+	/*IN/OUT: return aer_op result or carry error_detected state as input*/
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment*/
+	uint32_t bus;
+	uint32_t devfn;
+};
+struct xen_pci_sharedinfo {
+	/* flags - XEN_PCIF_* */
+	uint32_t flags;
+	struct xen_pci_op op;
+	struct xen_pcie_aer_op aer_op;
+};
+
+#endif /* __XEN_PCI_COMMON_H__ */
-- 
1.7.1

Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

[-- Attachment #1: Type: text/plain, Size: 35309 bytes --]

On Wed, Oct 13, 2010 at 09:53:44AM -0400, Konrad Rzeszutek Wilk wrote:
> Hey Jan,
> 
> Thank you for taking your time to look at this patch. Will fix up, test it, 
> and if there are no issues, have it ready tomorrow.

Attached (and inline) is the updated version of this patch. If I missed anything
please do point it out to me! If this is to your satisfaction, can I put
a Reviewed-by tag on the patch?

Thank you.

>From 7e865c880aa5942c4c22bd67618b2e9fc1788da6 Mon Sep 17 00:00:00 2001
From: Ryan Wilson <hap9@epoch.ncsc.mil>
Date: Mon, 2 Aug 2010 21:31:05 -0400
Subject: [PATCH] xen-pcifront: Xen PCI frontend driver.

This is a port of the 2.6.18 Xen PCI front driver with fixes
to make it build under 2.6.34 and later (for the full list of
changes: git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git
historic/xen-pcifront-0.1). It also includes the fixes
to make it work properly.

[v2: Updated Kconfig, removed crud, added Reviewed-by]
[v3: Added 'static', fixed grant table leak, redid Kconfig]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Jan Beulich <JBeulich@novell.com>
---
 drivers/pci/Kconfig              |   21 +
 drivers/pci/Makefile             |    2 +
 drivers/pci/xen-pcifront.c       | 1152 ++++++++++++++++++++++++++++++++++++++
 include/xen/interface/io/pciif.h |  112 ++++
 4 files changed, 1287 insertions(+), 0 deletions(-)
 create mode 100644 drivers/pci/xen-pcifront.c
 create mode 100644 include/xen/interface/io/pciif.h

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34ef70d..5b1630e 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -40,6 +40,27 @@ config PCI_STUB
 
 	  When in doubt, say N.
 
+config XEN_PCIDEV_FRONTEND
+        tristate "Xen PCI Frontend"
+        depends on PCI && X86 && XEN
+        select HOTPLUG
+        select PCI_XEN
+        default y
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
+config XEN_PCIDEV_FE_DEBUG
+        bool "Xen PCI Frontend debugging"
+        depends on XEN_PCIDEV_FRONTEND && PCI_DEBUG
+	help
+	  Say Y here if you want the Xen PCI frontend to produce a bunch of debug
+	  messages to the system log.  Select this if you are having a
+	  problem with Xen PCI frontend support and want to see more of what is
+	  going on.
+
+	  When in doubt, say N.
+
 config HT_IRQ
 	bool "Interrupts on hypertransport devices"
 	default y
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index dc1aa09..d5e2705 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -65,6 +65,8 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
 
 obj-$(CONFIG_PCI_STUB) += pci-stub.o
 
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
 endif
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
new file mode 100644
index 0000000..238870a
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1152 @@
+/*
+ * Xen PCI Frontend.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pciif.h>
+#include <asm/xen/pci.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <linux/time.h>
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN    (-1)
+
+struct pci_bus_entry {
+	struct list_head list;
+	struct pci_bus *bus;
+};
+
+#define _PDEVB_op_active		(0)
+#define PDEVB_op_active			(1 << (_PDEVB_op_active))
+
+struct pcifront_device {
+	struct xenbus_device *xdev;
+	struct list_head root_buses;
+
+	int evtchn;
+	int gnt_ref;
+
+	int irq;
+
+	/* Lock this when doing any operations in sh_info */
+	spinlock_t sh_info_lock;
+	struct xen_pci_sharedinfo *sh_info;
+	struct work_struct op_work;
+	unsigned long flags;
+
+};
+
+struct pcifront_sd {
+	int domain;
+	struct pcifront_device *pdev;
+};
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+	return sd->pdev;
+}
+
+static inline void pcifront_init_sd(struct pcifront_sd *sd,
+				    unsigned int domain, unsigned int bus,
+				    struct pcifront_device *pdev)
+{
+	sd->domain = domain;
+	sd->pdev = pdev;
+}
+
+static DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev;
+
+static int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static int errno_to_pcibios_err(int errno)
+{
+	switch (errno) {
+	case XEN_PCI_ERR_success:
+		return PCIBIOS_SUCCESSFUL;
+
+	case XEN_PCI_ERR_dev_not_found:
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	case XEN_PCI_ERR_invalid_offset:
+	case XEN_PCI_ERR_op_failed:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	case XEN_PCI_ERR_not_implemented:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+
+	case XEN_PCI_ERR_access_denied:
+		return PCIBIOS_SET_FAILED;
+	}
+	return errno;
+}
+
+static inline void schedule_pcifront_aer_op(struct pcifront_device *pdev)
+{
+	if (test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+		&& !test_and_set_bit(_PDEVB_op_active, &pdev->flags)) {
+		dev_dbg(&pdev->xdev->dev, "schedule aer frontend job\n");
+		schedule_work(&pdev->op_work);
+	}
+}
+
+static int do_pci_op(struct pcifront_device *pdev, struct xen_pci_op *op)
+{
+	int err = 0;
+	struct xen_pci_op *active_op = &pdev->sh_info->op;
+	unsigned long irq_flags;
+	evtchn_port_t port = pdev->evtchn;
+	unsigned irq = pdev->irq;
+	s64 ns, ns_timeout;
+	struct timeval tv;
+
+	spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
+
+	memcpy(active_op, op, sizeof(struct xen_pci_op));
+
+	/* Go */
+	wmb();
+	set_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(port);
+
+	/*
+	 * We set a poll timeout of 3 seconds but give up on return after
+	 * 2 seconds. It is better to time out too late rather than too early
+	 * (in the latter case we end up continually re-executing poll() with a
+	 * timeout in the past). 1s difference gives plenty of slack for error.
+	 */
+	do_gettimeofday(&tv);
+	ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+
+	xen_clear_irq_pending(irq);
+
+	while (test_bit(_XEN_PCIF_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		xen_poll_irq_timeout(irq, jiffies + 3*HZ);
+		xen_clear_irq_pending(irq);
+		do_gettimeofday(&tv);
+		ns = timeval_to_ns(&tv);
+		if (ns > ns_timeout) {
+			dev_err(&pdev->xdev->dev,
+				"pciback not responding!!!\n");
+			clear_bit(_XEN_PCIF_active,
+				  (unsigned long *)&pdev->sh_info->flags);
+			err = XEN_PCI_ERR_dev_not_found;
+			goto out;
+		}
+	}
+
+	/*
+	* We might lose backend service request since we
+	* reuse same evtchn with pci_conf backend response. So re-schedule
+	* aer pcifront service.
+	*/
+	if (test_bit(_XEN_PCIB_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		dev_err(&pdev->xdev->dev,
+			"schedule aer pcifront service\n");
+		schedule_pcifront_aer_op(pdev);
+	}
+
+	memcpy(op, active_op, sizeof(struct xen_pci_op));
+
+	err = op->err;
+out:
+	spin_unlock_irqrestore(&pdev->sh_info_lock, irq_flags);
+	return err;
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_read(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 *val)
+{
+	int err = 0;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_read,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+			 pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn), where, size);
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (verbose_request)
+			dev_info(&pdev->xdev->dev, "read got back value %x\n",
+				 op.value);
+
+		*val = op.value;
+	} else if (err == -ENODEV) {
+		/* No device here, pretend that it just returned 0 */
+		err = 0;
+		*val = 0;
+	}
+
+	return errno_to_pcibios_err(err);
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_write(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 val)
+{
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_write,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+		.value  = val,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "write dev=%04x:%02x:%02x.%01x - "
+			 "offset %x size %d val %x\n",
+			 pci_domain_nr(bus), bus->number,
+			 PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+
+	return errno_to_pcibios_err(do_pci_op(pdev, &op));
+}
+
+struct pci_ops pcifront_bus_ops = {
+	.read = pcifront_bus_read,
+	.write = pcifront_bus_write,
+};
+
+#ifdef CONFIG_PCI_MSI
+static int pci_frontend_enable_msix(struct pci_dev *dev,
+				    int **vector, int nvec)
+{
+	int err;
+	int i;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+		.value = nvec,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+	struct msi_desc *entry;
+
+	if (nvec > SH_INFO_MAX_VEC) {
+		dev_err(&dev->dev, "too much vector for pci frontend: %x."
+				   " Increase SH_INFO_MAX_VEC.\n", nvec);
+		return -EINVAL;
+	}
+
+	i = 0;
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+		/* Vector is useless at this point. */
+		op.msix_entries[i].vector = -1;
+		i++;
+	}
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (likely(!op.value)) {
+			/* we get the result */
+			for (i = 0; i < nvec; i++)
+				*(*vector+i) = op.msix_entries[i].vector;
+			return 0;
+		} else {
+			printk(KERN_DEBUG "enable msix get value %x\n",
+				op.value);
+			return op.value;
+		}
+	} else {
+		dev_err(&dev->dev, "enable msix get err %x\n", err);
+		return err;
+	}
+}
+
+static void pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+
+	/* What should do for error ? */
+	if (err)
+		dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
+}
+
+static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (likely(!err)) {
+		*(*vector) = op.value;
+	} else {
+		dev_err(&dev->dev, "pci frontend enable msi failed for dev "
+				    "%x:%x\n", op.bus, op.devfn);
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static void pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (err == XEN_PCI_ERR_dev_not_found) {
+		/* XXX No response from backend, what shall we do? */
+		printk(KERN_DEBUG "get no response from backend for disable MSI\n");
+		return;
+	}
+	if (err)
+		/* how can pciback notify us fail? */
+		printk(KERN_DEBUG "get fake response frombackend\n");
+}
+
+static struct xen_pci_frontend_ops pci_frontend_ops = {
+	.enable_msi = pci_frontend_enable_msi,
+	.disable_msi = pci_frontend_disable_msi,
+	.enable_msix = pci_frontend_enable_msix,
+	.disable_msix = pci_frontend_disable_msix,
+};
+
+static void pci_frontend_registrar(int enable)
+{
+	if (enable)
+		xen_pci_frontend = &pci_frontend_ops;
+	else
+		xen_pci_frontend = NULL;
+};
+#else
+static inline void pci_frontend_registrar(int enable) { };
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static int pcifront_claim_resource(struct pci_dev *dev, void *data)
+{
+	struct pcifront_device *pdev = data;
+	int i;
+	struct resource *r;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		r = &dev->resource[i];
+
+		if (!r->parent && r->start && r->flags) {
+			dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
+				pci_name(dev), i);
+			if (pci_claim_resource(dev, i)) {
+				dev_err(&pdev->xdev->dev, "Could not claim "
+					"resource %s/%d! Device offline. Try "
+					"giving less than 4GB to domain.\n",
+					pci_name(dev), i);
+			}
+		}
+	}
+
+	return 0;
+}
+
+int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+				unsigned int domain, unsigned int bus,
+				struct pci_bus *b)
+{
+	struct pci_dev *d;
+	unsigned int devfn;
+
+	/* Scan the bus for functions and add.
+	 * We omit handling of PCI bridge attachment because pciback prevents
+	 * bridges from being exported.
+	 */
+	for (devfn = 0; devfn < 0x100; devfn++) {
+		d = pci_get_slot(b, devfn);
+		if (d) {
+			/* Device is already known. */
+			pci_dev_put(d);
+			continue;
+		}
+
+		d = pci_scan_single_device(b, devfn);
+		if (d)
+			dev_info(&pdev->xdev->dev, "New device on "
+				 "%04x:%02x:%02x.%02x found.\n", domain, bus,
+				 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	}
+
+	return 0;
+}
+
+static int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+				 unsigned int domain, unsigned int bus)
+{
+	struct pci_bus *b;
+	struct pcifront_sd *sd = NULL;
+	struct pci_bus_entry *bus_entry = NULL;
+	int err = 0;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		err = -EINVAL;
+		goto err_out;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	if (!bus_entry || !sd) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	pcifront_init_sd(sd, domain, bus, pdev);
+
+	b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
+				  &pcifront_bus_ops, sd);
+	if (!b) {
+		dev_err(&pdev->xdev->dev,
+			"Error creating PCI Frontend Bus!\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	bus_entry->bus = b;
+
+	list_add(&bus_entry->list, &pdev->root_buses);
+
+	/* pci_scan_bus_parented skips devices which do not have a have
+	* devfn==0. The pcifront_scan_bus enumerates all devfn. */
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+
+err_out:
+	kfree(bus_entry);
+	kfree(sd);
+
+	return err;
+}
+
+static int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+				   unsigned int domain, unsigned int bus)
+{
+	int err;
+	struct pci_bus *b;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		return -EINVAL;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Rescanning PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	b = pci_find_bus(domain, bus);
+	if (!b)
+		/* If the bus is unknown, create it. */
+		return pcifront_scan_root(pdev, domain, bus);
+
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+}
+
+static void free_root_bus_devs(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	while (!list_empty(&bus->devices)) {
+		dev = container_of(bus->devices.next, struct pci_dev,
+				   bus_list);
+		dev_dbg(&dev->dev, "removing device\n");
+		pci_remove_bus_device(dev);
+	}
+}
+
+static void pcifront_free_roots(struct pcifront_device *pdev)
+{
+	struct pci_bus_entry *bus_entry, *t;
+
+	dev_dbg(&pdev->xdev->dev, "cleaning up root buses\n");
+
+	list_for_each_entry_safe(bus_entry, t, &pdev->root_buses, list) {
+		list_del(&bus_entry->list);
+
+		free_root_bus_devs(bus_entry->bus);
+
+		kfree(bus_entry->bus->sysdata);
+
+		device_unregister(bus_entry->bus->bridge);
+		pci_remove_bus(bus_entry->bus);
+
+		kfree(bus_entry);
+	}
+}
+
+static pci_ers_result_t pcifront_common_process(int cmd,
+						struct pcifront_device *pdev,
+						pci_channel_state_t state)
+{
+	pci_ers_result_t result;
+	struct pci_driver *pdrv;
+	int bus = pdev->sh_info->aer_op.bus;
+	int devfn = pdev->sh_info->aer_op.devfn;
+	struct pci_dev *pcidev;
+	int flag = 0;
+
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront AER process: cmd %x (bus:%x, devfn%x)",
+		cmd, bus, devfn);
+	result = PCI_ERS_RESULT_NONE;
+
+	pcidev = pci_get_bus_and_slot(bus, devfn);
+	if (!pcidev || !pcidev->driver) {
+		dev_err(&pcidev->dev,
+			"device or driver is NULL\n");
+		return result;
+	}
+	pdrv = pcidev->driver;
+
+	if (get_driver(&pdrv->driver)) {
+		if (pdrv->err_handler && pdrv->err_handler->error_detected) {
+			dev_dbg(&pcidev->dev,
+				"trying to call AER service\n");
+			if (pcidev) {
+				flag = 1;
+				switch (cmd) {
+				case XEN_PCI_OP_aer_detected:
+					result = pdrv->err_handler->
+						 error_detected(pcidev, state);
+					break;
+				case XEN_PCI_OP_aer_mmio:
+					result = pdrv->err_handler->
+						 mmio_enabled(pcidev);
+					break;
+				case XEN_PCI_OP_aer_slotreset:
+					result = pdrv->err_handler->
+						 slot_reset(pcidev);
+					break;
+				case XEN_PCI_OP_aer_resume:
+					pdrv->err_handler->resume(pcidev);
+					break;
+				default:
+					dev_err(&pdev->xdev->dev,
+						"bad request in aer recovery "
+						"operation!\n");
+
+				}
+			}
+		}
+		put_driver(&pdrv->driver);
+	}
+	if (!flag)
+		result = PCI_ERS_RESULT_NONE;
+
+	return result;
+}
+
+
+static void pcifront_do_aer(struct work_struct *data)
+{
+	struct pcifront_device *pdev =
+		container_of(data, struct pcifront_device, op_work);
+	int cmd = pdev->sh_info->aer_op.cmd;
+	pci_channel_state_t state =
+		(pci_channel_state_t)pdev->sh_info->aer_op.err;
+
+	/*If a pci_conf op is in progress,
+		we have to wait until it is done before service aer op*/
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront service aer bus %x devfn %x\n",
+		pdev->sh_info->aer_op.bus, pdev->sh_info->aer_op.devfn);
+
+	pdev->sh_info->aer_op.err = pcifront_common_process(cmd, pdev, state);
+
+	/* Post the operation to the guest. */
+	wmb();
+	clear_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(pdev->evtchn);
+
+	/*in case of we lost an aer request in four lines time_window*/
+	smp_mb__before_clear_bit();
+	clear_bit(_PDEVB_op_active, &pdev->flags);
+	smp_mb__after_clear_bit();
+
+	schedule_pcifront_aer_op(pdev);
+
+}
+
+static irqreturn_t pcifront_handler_aer(int irq, void *dev)
+{
+	struct pcifront_device *pdev = dev;
+	schedule_pcifront_aer_op(pdev);
+	return IRQ_HANDLED;
+}
+static int pcifront_connect(struct pcifront_device *pdev)
+{
+	int err = 0;
+
+	spin_lock(&pcifront_dev_lock);
+
+	if (!pcifront_dev) {
+		dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
+		pcifront_dev = pdev;
+	} else {
+		dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+		err = -EEXIST;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+
+	return err;
+}
+
+static void pcifront_disconnect(struct pcifront_device *pdev)
+{
+	spin_lock(&pcifront_dev_lock);
+
+	if (pdev == pcifront_dev) {
+		dev_info(&pdev->xdev->dev,
+			 "Disconnecting PCI Frontend Buses\n");
+		pcifront_dev = NULL;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+}
+static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev;
+
+	pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+
+	pdev->sh_info =
+	    (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL);
+	if (pdev->sh_info == NULL) {
+		kfree(pdev);
+		pdev = NULL;
+		goto out;
+	}
+	pdev->sh_info->flags = 0;
+
+	/*Flag for registering PV AER handler*/
+	set_bit(_XEN_PCIB_AERHANDLER, (void *)&pdev->sh_info->flags);
+
+	dev_set_drvdata(&xdev->dev, pdev);
+	pdev->xdev = xdev;
+
+	INIT_LIST_HEAD(&pdev->root_buses);
+
+	spin_lock_init(&pdev->sh_info_lock);
+
+	pdev->evtchn = INVALID_EVTCHN;
+	pdev->gnt_ref = INVALID_GRANT_REF;
+	pdev->irq = -1;
+
+	INIT_WORK(&pdev->op_work, pcifront_do_aer);
+
+	dev_dbg(&xdev->dev, "Allocated pdev @ 0x%p pdev->sh_info @ 0x%p\n",
+		pdev, pdev->sh_info);
+out:
+	return pdev;
+}
+
+static void free_pdev(struct pcifront_device *pdev)
+{
+	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
+
+	pcifront_free_roots(pdev);
+
+	/*For PCIE_AER error handling job*/
+	flush_scheduled_work();
+
+	if (pdev->irq)
+		unbind_from_irqhandler(pdev->irq, pdev);
+
+	if (pdev->evtchn != INVALID_EVTCHN)
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+
+	if (pdev->gnt_ref != INVALID_GRANT_REF)
+		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
+					  (unsigned long)pdev->sh_info);
+	else
+		free_page((unsigned long)pdev->sh_info);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+
+	kfree(pdev);
+}
+
+static int pcifront_publish_info(struct pcifront_device *pdev)
+{
+	int err = 0;
+	struct xenbus_transaction trans;
+
+	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
+	if (err < 0)
+		goto out;
+
+	pdev->gnt_ref = err;
+
+	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
+	if (err)
+		goto out;
+
+	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+		0, "pcifront", pdev);
+	if (err < 0) {
+		/*
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
+				 "irqhandler.\n");
+		*/
+		return err;
+	}
+	pdev->irq = err;
+
+do_publish:
+	err = xenbus_transaction_start(&trans);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend "
+				 "(start transaction)");
+		goto out;
+	}
+
+	err = xenbus_printf(trans, pdev->xdev->nodename,
+			    "pci-op-ref", "%u", pdev->gnt_ref);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "event-channel", "%u", pdev->evtchn);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "magic", XEN_PCI_MAGIC);
+
+	if (err) {
+		xenbus_transaction_end(trans, 1);
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend");
+		goto out;
+	} else {
+		err = xenbus_transaction_end(trans, 0);
+		if (err == -EAGAIN)
+			goto do_publish;
+		else if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error completing transaction "
+					 "for backend");
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+
+	dev_dbg(&pdev->xdev->dev, "publishing successful!\n");
+
+out:
+	return err;
+}
+
+static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	char str[64];
+	unsigned int domain, bus;
+
+
+	/* Only connect once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	err = pcifront_connect(pdev);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error connecting PCI Frontend");
+		goto out;
+	}
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_scan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_scan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+	int err = 0;
+	enum xenbus_state prev_state;
+
+
+	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+
+	if (prev_state >= XenbusStateClosing)
+		goto out;
+
+	if (prev_state == XenbusStateConnected) {
+		pcifront_free_roots(pdev);
+		pcifront_disconnect(pdev);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateClosed);
+
+out:
+
+	return err;
+}
+
+static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	unsigned int domain, bus;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_rescan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_rescan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_detach_devices(struct pcifront_device *pdev)
+{
+	int err = 0;
+	int i, num_devs;
+	unsigned int domain, bus, slot, func;
+	struct pci_bus *pci_bus;
+	struct pci_dev *pci_dev;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateConnected)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI devices");
+		goto out;
+	}
+
+	/* Find devices being detached and remove them. */
+	for (i = 0; i < num_devs; i++) {
+		int l, state;
+		l = snprintf(str, sizeof(str), "state-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d",
+				   &state);
+		if (err != 1)
+			state = XenbusStateUnknown;
+
+		if (state != XenbusStateClosing)
+			continue;
+
+		/* Remove device. */
+		l = snprintf(str, sizeof(str), "vdev-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err != 4) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI device %d", i);
+			goto out;
+		}
+
+		pci_bus = pci_find_bus(domain, bus);
+		if (!pci_bus) {
+			dev_dbg(&pdev->xdev->dev, "Cannot get bus %04x:%02x\n",
+				domain, bus);
+			continue;
+		}
+		pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
+		if (!pci_dev) {
+			dev_dbg(&pdev->xdev->dev,
+				"Cannot get PCI device %04x:%02x:%02x.%02x\n",
+				domain, bus, slot, func);
+			continue;
+		}
+		pci_remove_bus_device(pci_dev);
+		pci_dev_put(pci_dev);
+
+		dev_dbg(&pdev->xdev->dev,
+			"PCI device %04x:%02x:%02x.%02x removed.\n",
+			domain, bus, slot, func);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring);
+
+out:
+	return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+						  enum xenbus_state be_state)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	switch (be_state) {
+	case XenbusStateUnknown:
+	case XenbusStateInitialising:
+	case XenbusStateInitWait:
+	case XenbusStateInitialised:
+	case XenbusStateClosed:
+		break;
+
+	case XenbusStateConnected:
+		pcifront_try_connect(pdev);
+		break;
+
+	case XenbusStateClosing:
+		dev_warn(&xdev->dev, "backend going away!\n");
+		pcifront_try_disconnect(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		pcifront_detach_devices(pdev);
+		break;
+
+	case XenbusStateReconfigured:
+		pcifront_attach_devices(pdev);
+		break;
+	}
+}
+
+static int pcifront_xenbus_probe(struct xenbus_device *xdev,
+				 const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct pcifront_device *pdev = alloc_pdev(xdev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(xdev, err,
+				 "Error allocating pcifront_device struct");
+		goto out;
+	}
+
+	err = pcifront_publish_info(pdev);
+	if (err)
+		free_pdev(pdev);
+
+out:
+	return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+	if (pdev)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static struct xenbus_driver xenbus_pcifront_driver = {
+	.name			= "pcifront",
+	.owner			= THIS_MODULE,
+	.ids			= xenpci_ids,
+	.probe			= pcifront_xenbus_probe,
+	.remove			= pcifront_xenbus_remove,
+	.otherend_changed	= pcifront_backend_changed,
+};
+
+static int __init pcifront_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	pci_frontend_registrar(1 /* enable */);
+
+	return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+static void __exit pcifront_cleanup(void)
+{
+	xenbus_unregister_driver(&xenbus_pcifront_driver);
+	pci_frontend_registrar(0 /* disable */);
+}
+module_init(pcifront_init);
+module_exit(pcifront_cleanup);
+
+MODULE_DESCRIPTION("Xen PCI passthrough frontend.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:pci");
diff --git a/include/xen/interface/io/pciif.h b/include/xen/interface/io/pciif.h
new file mode 100644
index 0000000..d9922ae
--- /dev/null
+++ b/include/xen/interface/io/pciif.h
@@ -0,0 +1,112 @@
+/*
+ * PCI Backend/Frontend Common Data Structures & Macros
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCI_COMMON_H__
+#define __XEN_PCI_COMMON_H__
+
+/* Be sure to bump this number if you change this file */
+#define XEN_PCI_MAGIC "7"
+
+/* xen_pci_sharedinfo flags */
+#define	_XEN_PCIF_active		(0)
+#define	XEN_PCIF_active			(1<<_XEN_PCIF_active)
+#define	_XEN_PCIB_AERHANDLER		(1)
+#define	XEN_PCIB_AERHANDLER		(1<<_XEN_PCIB_AERHANDLER)
+#define	_XEN_PCIB_active		(2)
+#define	XEN_PCIB_active			(1<<_XEN_PCIB_active)
+
+/* xen_pci_op commands */
+#define	XEN_PCI_OP_conf_read		(0)
+#define	XEN_PCI_OP_conf_write		(1)
+#define	XEN_PCI_OP_enable_msi		(2)
+#define	XEN_PCI_OP_disable_msi		(3)
+#define	XEN_PCI_OP_enable_msix		(4)
+#define	XEN_PCI_OP_disable_msix		(5)
+#define	XEN_PCI_OP_aer_detected		(6)
+#define	XEN_PCI_OP_aer_resume		(7)
+#define	XEN_PCI_OP_aer_mmio		(8)
+#define	XEN_PCI_OP_aer_slotreset	(9)
+
+/* xen_pci_op error numbers */
+#define	XEN_PCI_ERR_success		(0)
+#define	XEN_PCI_ERR_dev_not_found	(-1)
+#define	XEN_PCI_ERR_invalid_offset	(-2)
+#define	XEN_PCI_ERR_access_denied	(-3)
+#define	XEN_PCI_ERR_not_implemented	(-4)
+/* XEN_PCI_ERR_op_failed - backend failed to complete the operation */
+#define XEN_PCI_ERR_op_failed		(-5)
+
+/*
+ * it should be PAGE_SIZE-sizeof(struct xen_pci_op))/sizeof(struct msix_entry))
+ * Should not exceed 128
+ */
+#define SH_INFO_MAX_VEC			128
+
+struct xen_msix_entry {
+	uint16_t vector;
+	uint16_t entry;
+};
+struct xen_pci_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+
+	/* OUT: will contain an error number (if any) from errno.h */
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment */
+	uint32_t bus;
+	uint32_t devfn;
+
+	/* IN: which configuration registers to touch */
+	int32_t offset;
+	int32_t size;
+
+	/* IN/OUT: Contains the result after a READ or the value to WRITE */
+	uint32_t value;
+	/* IN: Contains extra infor for this operation */
+	uint32_t info;
+	/*IN:  param for msi-x */
+	struct xen_msix_entry msix_entries[SH_INFO_MAX_VEC];
+};
+
+/*used for pcie aer handling*/
+struct xen_pcie_aer_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+	/*IN/OUT: return aer_op result or carry error_detected state as input*/
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment*/
+	uint32_t bus;
+	uint32_t devfn;
+};
+struct xen_pci_sharedinfo {
+	/* flags - XEN_PCIF_* */
+	uint32_t flags;
+	struct xen_pci_op op;
+	struct xen_pcie_aer_op aer_op;
+};
+
+#endif /* __XEN_PCI_COMMON_H__ */
-- 
1.7.1


[-- Attachment #2: 0001-xen-pcifront-Xen-PCI-frontend-driver.patch --]
[-- Type: text/x-diff, Size: 34891 bytes --]

>From 7e865c880aa5942c4c22bd67618b2e9fc1788da6 Mon Sep 17 00:00:00 2001
From: Ryan Wilson <hap9@epoch.ncsc.mil>
Date: Mon, 2 Aug 2010 21:31:05 -0400
Subject: [PATCH] xen-pcifront: Xen PCI frontend driver.

This is a port of the 2.6.18 Xen PCI front driver with fixes
to make it build under 2.6.34 and later (for the full list of
changes: git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git
historic/xen-pcifront-0.1). It also includes the fixes
to make it work properly.

[v2: Updated Kconfig, removed crud, added Reviewed-by]
[v3: Added 'static', fixed grant table leak, redid Kconfig]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Jan Beulich <JBeulich@novell.com>
---
 drivers/pci/Kconfig              |   21 +
 drivers/pci/Makefile             |    2 +
 drivers/pci/xen-pcifront.c       | 1152 ++++++++++++++++++++++++++++++++++++++
 include/xen/interface/io/pciif.h |  112 ++++
 4 files changed, 1287 insertions(+), 0 deletions(-)
 create mode 100644 drivers/pci/xen-pcifront.c
 create mode 100644 include/xen/interface/io/pciif.h

diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34ef70d..5b1630e 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -40,6 +40,27 @@ config PCI_STUB
 
 	  When in doubt, say N.
 
+config XEN_PCIDEV_FRONTEND
+        tristate "Xen PCI Frontend"
+        depends on PCI && X86 && XEN
+        select HOTPLUG
+        select PCI_XEN
+        default y
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
+config XEN_PCIDEV_FE_DEBUG
+        bool "Xen PCI Frontend debugging"
+        depends on XEN_PCIDEV_FRONTEND && PCI_DEBUG
+	help
+	  Say Y here if you want the Xen PCI frontend to produce a bunch of debug
+	  messages to the system log.  Select this if you are having a
+	  problem with Xen PCI frontend support and want to see more of what is
+	  going on.
+
+	  When in doubt, say N.
+
 config HT_IRQ
 	bool "Interrupts on hypertransport devices"
 	default y
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index dc1aa09..d5e2705 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -65,6 +65,8 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
 
 obj-$(CONFIG_PCI_STUB) += pci-stub.o
 
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
 endif
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
new file mode 100644
index 0000000..238870a
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1152 @@
+/*
+ * Xen PCI Frontend.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pciif.h>
+#include <asm/xen/pci.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <linux/time.h>
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN    (-1)
+
+struct pci_bus_entry {
+	struct list_head list;
+	struct pci_bus *bus;
+};
+
+#define _PDEVB_op_active		(0)
+#define PDEVB_op_active			(1 << (_PDEVB_op_active))
+
+struct pcifront_device {
+	struct xenbus_device *xdev;
+	struct list_head root_buses;
+
+	int evtchn;
+	int gnt_ref;
+
+	int irq;
+
+	/* Lock this when doing any operations in sh_info */
+	spinlock_t sh_info_lock;
+	struct xen_pci_sharedinfo *sh_info;
+	struct work_struct op_work;
+	unsigned long flags;
+
+};
+
+struct pcifront_sd {
+	int domain;
+	struct pcifront_device *pdev;
+};
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+	return sd->pdev;
+}
+
+static inline void pcifront_init_sd(struct pcifront_sd *sd,
+				    unsigned int domain, unsigned int bus,
+				    struct pcifront_device *pdev)
+{
+	sd->domain = domain;
+	sd->pdev = pdev;
+}
+
+static DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev;
+
+static int verbose_request;
+module_param(verbose_request, int, 0644);
+
+static int errno_to_pcibios_err(int errno)
+{
+	switch (errno) {
+	case XEN_PCI_ERR_success:
+		return PCIBIOS_SUCCESSFUL;
+
+	case XEN_PCI_ERR_dev_not_found:
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	case XEN_PCI_ERR_invalid_offset:
+	case XEN_PCI_ERR_op_failed:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	case XEN_PCI_ERR_not_implemented:
+		return PCIBIOS_FUNC_NOT_SUPPORTED;
+
+	case XEN_PCI_ERR_access_denied:
+		return PCIBIOS_SET_FAILED;
+	}
+	return errno;
+}
+
+static inline void schedule_pcifront_aer_op(struct pcifront_device *pdev)
+{
+	if (test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+		&& !test_and_set_bit(_PDEVB_op_active, &pdev->flags)) {
+		dev_dbg(&pdev->xdev->dev, "schedule aer frontend job\n");
+		schedule_work(&pdev->op_work);
+	}
+}
+
+static int do_pci_op(struct pcifront_device *pdev, struct xen_pci_op *op)
+{
+	int err = 0;
+	struct xen_pci_op *active_op = &pdev->sh_info->op;
+	unsigned long irq_flags;
+	evtchn_port_t port = pdev->evtchn;
+	unsigned irq = pdev->irq;
+	s64 ns, ns_timeout;
+	struct timeval tv;
+
+	spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
+
+	memcpy(active_op, op, sizeof(struct xen_pci_op));
+
+	/* Go */
+	wmb();
+	set_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(port);
+
+	/*
+	 * We set a poll timeout of 3 seconds but give up on return after
+	 * 2 seconds. It is better to time out too late rather than too early
+	 * (in the latter case we end up continually re-executing poll() with a
+	 * timeout in the past). 1s difference gives plenty of slack for error.
+	 */
+	do_gettimeofday(&tv);
+	ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+
+	xen_clear_irq_pending(irq);
+
+	while (test_bit(_XEN_PCIF_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		xen_poll_irq_timeout(irq, jiffies + 3*HZ);
+		xen_clear_irq_pending(irq);
+		do_gettimeofday(&tv);
+		ns = timeval_to_ns(&tv);
+		if (ns > ns_timeout) {
+			dev_err(&pdev->xdev->dev,
+				"pciback not responding!!!\n");
+			clear_bit(_XEN_PCIF_active,
+				  (unsigned long *)&pdev->sh_info->flags);
+			err = XEN_PCI_ERR_dev_not_found;
+			goto out;
+		}
+	}
+
+	/*
+	* We might lose backend service request since we
+	* reuse same evtchn with pci_conf backend response. So re-schedule
+	* aer pcifront service.
+	*/
+	if (test_bit(_XEN_PCIB_active,
+			(unsigned long *)&pdev->sh_info->flags)) {
+		dev_err(&pdev->xdev->dev,
+			"schedule aer pcifront service\n");
+		schedule_pcifront_aer_op(pdev);
+	}
+
+	memcpy(op, active_op, sizeof(struct xen_pci_op));
+
+	err = op->err;
+out:
+	spin_unlock_irqrestore(&pdev->sh_info_lock, irq_flags);
+	return err;
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_read(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 *val)
+{
+	int err = 0;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_read,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+			 pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+			 PCI_FUNC(devfn), where, size);
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (verbose_request)
+			dev_info(&pdev->xdev->dev, "read got back value %x\n",
+				 op.value);
+
+		*val = op.value;
+	} else if (err == -ENODEV) {
+		/* No device here, pretend that it just returned 0 */
+		err = 0;
+		*val = 0;
+	}
+
+	return errno_to_pcibios_err(err);
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_write(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 val)
+{
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_conf_write,
+		.domain = pci_domain_nr(bus),
+		.bus    = bus->number,
+		.devfn  = devfn,
+		.offset = where,
+		.size   = size,
+		.value  = val,
+	};
+	struct pcifront_sd *sd = bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	if (verbose_request)
+		dev_info(&pdev->xdev->dev,
+			 "write dev=%04x:%02x:%02x.%01x - "
+			 "offset %x size %d val %x\n",
+			 pci_domain_nr(bus), bus->number,
+			 PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+
+	return errno_to_pcibios_err(do_pci_op(pdev, &op));
+}
+
+struct pci_ops pcifront_bus_ops = {
+	.read = pcifront_bus_read,
+	.write = pcifront_bus_write,
+};
+
+#ifdef CONFIG_PCI_MSI
+static int pci_frontend_enable_msix(struct pci_dev *dev,
+				    int **vector, int nvec)
+{
+	int err;
+	int i;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+		.value = nvec,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+	struct msi_desc *entry;
+
+	if (nvec > SH_INFO_MAX_VEC) {
+		dev_err(&dev->dev, "too much vector for pci frontend: %x."
+				   " Increase SH_INFO_MAX_VEC.\n", nvec);
+		return -EINVAL;
+	}
+
+	i = 0;
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+		/* Vector is useless at this point. */
+		op.msix_entries[i].vector = -1;
+		i++;
+	}
+
+	err = do_pci_op(pdev, &op);
+
+	if (likely(!err)) {
+		if (likely(!op.value)) {
+			/* we get the result */
+			for (i = 0; i < nvec; i++)
+				*(*vector+i) = op.msix_entries[i].vector;
+			return 0;
+		} else {
+			printk(KERN_DEBUG "enable msix get value %x\n",
+				op.value);
+			return op.value;
+		}
+	} else {
+		dev_err(&dev->dev, "enable msix get err %x\n", err);
+		return err;
+	}
+}
+
+static void pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msix,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+
+	/* What should do for error ? */
+	if (err)
+		dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
+}
+
+static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_enable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (likely(!err)) {
+		*(*vector) = op.value;
+	} else {
+		dev_err(&dev->dev, "pci frontend enable msi failed for dev "
+				    "%x:%x\n", op.bus, op.devfn);
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static void pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	int err;
+	struct xen_pci_op op = {
+		.cmd    = XEN_PCI_OP_disable_msi,
+		.domain = pci_domain_nr(dev->bus),
+		.bus = dev->bus->number,
+		.devfn = dev->devfn,
+	};
+	struct pcifront_sd *sd = dev->bus->sysdata;
+	struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+	err = do_pci_op(pdev, &op);
+	if (err == XEN_PCI_ERR_dev_not_found) {
+		/* XXX No response from backend, what shall we do? */
+		printk(KERN_DEBUG "get no response from backend for disable MSI\n");
+		return;
+	}
+	if (err)
+		/* how can pciback notify us fail? */
+		printk(KERN_DEBUG "get fake response frombackend\n");
+}
+
+static struct xen_pci_frontend_ops pci_frontend_ops = {
+	.enable_msi = pci_frontend_enable_msi,
+	.disable_msi = pci_frontend_disable_msi,
+	.enable_msix = pci_frontend_enable_msix,
+	.disable_msix = pci_frontend_disable_msix,
+};
+
+static void pci_frontend_registrar(int enable)
+{
+	if (enable)
+		xen_pci_frontend = &pci_frontend_ops;
+	else
+		xen_pci_frontend = NULL;
+};
+#else
+static inline void pci_frontend_registrar(int enable) { };
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static int pcifront_claim_resource(struct pci_dev *dev, void *data)
+{
+	struct pcifront_device *pdev = data;
+	int i;
+	struct resource *r;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		r = &dev->resource[i];
+
+		if (!r->parent && r->start && r->flags) {
+			dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
+				pci_name(dev), i);
+			if (pci_claim_resource(dev, i)) {
+				dev_err(&pdev->xdev->dev, "Could not claim "
+					"resource %s/%d! Device offline. Try "
+					"giving less than 4GB to domain.\n",
+					pci_name(dev), i);
+			}
+		}
+	}
+
+	return 0;
+}
+
+int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+				unsigned int domain, unsigned int bus,
+				struct pci_bus *b)
+{
+	struct pci_dev *d;
+	unsigned int devfn;
+
+	/* Scan the bus for functions and add.
+	 * We omit handling of PCI bridge attachment because pciback prevents
+	 * bridges from being exported.
+	 */
+	for (devfn = 0; devfn < 0x100; devfn++) {
+		d = pci_get_slot(b, devfn);
+		if (d) {
+			/* Device is already known. */
+			pci_dev_put(d);
+			continue;
+		}
+
+		d = pci_scan_single_device(b, devfn);
+		if (d)
+			dev_info(&pdev->xdev->dev, "New device on "
+				 "%04x:%02x:%02x.%02x found.\n", domain, bus,
+				 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	}
+
+	return 0;
+}
+
+static int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+				 unsigned int domain, unsigned int bus)
+{
+	struct pci_bus *b;
+	struct pcifront_sd *sd = NULL;
+	struct pci_bus_entry *bus_entry = NULL;
+	int err = 0;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		err = -EINVAL;
+		goto err_out;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	if (!bus_entry || !sd) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	pcifront_init_sd(sd, domain, bus, pdev);
+
+	b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
+				  &pcifront_bus_ops, sd);
+	if (!b) {
+		dev_err(&pdev->xdev->dev,
+			"Error creating PCI Frontend Bus!\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	bus_entry->bus = b;
+
+	list_add(&bus_entry->list, &pdev->root_buses);
+
+	/* pci_scan_bus_parented skips devices which do not have a have
+	* devfn==0. The pcifront_scan_bus enumerates all devfn. */
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+
+err_out:
+	kfree(bus_entry);
+	kfree(sd);
+
+	return err;
+}
+
+static int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+				   unsigned int domain, unsigned int bus)
+{
+	int err;
+	struct pci_bus *b;
+
+#ifndef CONFIG_PCI_DOMAINS
+	if (domain != 0) {
+		dev_err(&pdev->xdev->dev,
+			"PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+		dev_err(&pdev->xdev->dev,
+			"Please compile with CONFIG_PCI_DOMAINS\n");
+		return -EINVAL;
+	}
+#endif
+
+	dev_info(&pdev->xdev->dev, "Rescanning PCI Frontend Bus %04x:%02x\n",
+		 domain, bus);
+
+	b = pci_find_bus(domain, bus);
+	if (!b)
+		/* If the bus is unknown, create it. */
+		return pcifront_scan_root(pdev, domain, bus);
+
+	err = pcifront_scan_bus(pdev, domain, bus, b);
+
+	/* Claim resources before going "live" with our devices */
+	pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+	/* Create SysFS and notify udev of the devices. Aka: "going live" */
+	pci_bus_add_devices(b);
+
+	return err;
+}
+
+static void free_root_bus_devs(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	while (!list_empty(&bus->devices)) {
+		dev = container_of(bus->devices.next, struct pci_dev,
+				   bus_list);
+		dev_dbg(&dev->dev, "removing device\n");
+		pci_remove_bus_device(dev);
+	}
+}
+
+static void pcifront_free_roots(struct pcifront_device *pdev)
+{
+	struct pci_bus_entry *bus_entry, *t;
+
+	dev_dbg(&pdev->xdev->dev, "cleaning up root buses\n");
+
+	list_for_each_entry_safe(bus_entry, t, &pdev->root_buses, list) {
+		list_del(&bus_entry->list);
+
+		free_root_bus_devs(bus_entry->bus);
+
+		kfree(bus_entry->bus->sysdata);
+
+		device_unregister(bus_entry->bus->bridge);
+		pci_remove_bus(bus_entry->bus);
+
+		kfree(bus_entry);
+	}
+}
+
+static pci_ers_result_t pcifront_common_process(int cmd,
+						struct pcifront_device *pdev,
+						pci_channel_state_t state)
+{
+	pci_ers_result_t result;
+	struct pci_driver *pdrv;
+	int bus = pdev->sh_info->aer_op.bus;
+	int devfn = pdev->sh_info->aer_op.devfn;
+	struct pci_dev *pcidev;
+	int flag = 0;
+
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront AER process: cmd %x (bus:%x, devfn%x)",
+		cmd, bus, devfn);
+	result = PCI_ERS_RESULT_NONE;
+
+	pcidev = pci_get_bus_and_slot(bus, devfn);
+	if (!pcidev || !pcidev->driver) {
+		dev_err(&pcidev->dev,
+			"device or driver is NULL\n");
+		return result;
+	}
+	pdrv = pcidev->driver;
+
+	if (get_driver(&pdrv->driver)) {
+		if (pdrv->err_handler && pdrv->err_handler->error_detected) {
+			dev_dbg(&pcidev->dev,
+				"trying to call AER service\n");
+			if (pcidev) {
+				flag = 1;
+				switch (cmd) {
+				case XEN_PCI_OP_aer_detected:
+					result = pdrv->err_handler->
+						 error_detected(pcidev, state);
+					break;
+				case XEN_PCI_OP_aer_mmio:
+					result = pdrv->err_handler->
+						 mmio_enabled(pcidev);
+					break;
+				case XEN_PCI_OP_aer_slotreset:
+					result = pdrv->err_handler->
+						 slot_reset(pcidev);
+					break;
+				case XEN_PCI_OP_aer_resume:
+					pdrv->err_handler->resume(pcidev);
+					break;
+				default:
+					dev_err(&pdev->xdev->dev,
+						"bad request in aer recovery "
+						"operation!\n");
+
+				}
+			}
+		}
+		put_driver(&pdrv->driver);
+	}
+	if (!flag)
+		result = PCI_ERS_RESULT_NONE;
+
+	return result;
+}
+
+
+static void pcifront_do_aer(struct work_struct *data)
+{
+	struct pcifront_device *pdev =
+		container_of(data, struct pcifront_device, op_work);
+	int cmd = pdev->sh_info->aer_op.cmd;
+	pci_channel_state_t state =
+		(pci_channel_state_t)pdev->sh_info->aer_op.err;
+
+	/*If a pci_conf op is in progress,
+		we have to wait until it is done before service aer op*/
+	dev_dbg(&pdev->xdev->dev,
+		"pcifront service aer bus %x devfn %x\n",
+		pdev->sh_info->aer_op.bus, pdev->sh_info->aer_op.devfn);
+
+	pdev->sh_info->aer_op.err = pcifront_common_process(cmd, pdev, state);
+
+	/* Post the operation to the guest. */
+	wmb();
+	clear_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags);
+	notify_remote_via_evtchn(pdev->evtchn);
+
+	/*in case of we lost an aer request in four lines time_window*/
+	smp_mb__before_clear_bit();
+	clear_bit(_PDEVB_op_active, &pdev->flags);
+	smp_mb__after_clear_bit();
+
+	schedule_pcifront_aer_op(pdev);
+
+}
+
+static irqreturn_t pcifront_handler_aer(int irq, void *dev)
+{
+	struct pcifront_device *pdev = dev;
+	schedule_pcifront_aer_op(pdev);
+	return IRQ_HANDLED;
+}
+static int pcifront_connect(struct pcifront_device *pdev)
+{
+	int err = 0;
+
+	spin_lock(&pcifront_dev_lock);
+
+	if (!pcifront_dev) {
+		dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
+		pcifront_dev = pdev;
+	} else {
+		dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+		err = -EEXIST;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+
+	return err;
+}
+
+static void pcifront_disconnect(struct pcifront_device *pdev)
+{
+	spin_lock(&pcifront_dev_lock);
+
+	if (pdev == pcifront_dev) {
+		dev_info(&pdev->xdev->dev,
+			 "Disconnecting PCI Frontend Buses\n");
+		pcifront_dev = NULL;
+	}
+
+	spin_unlock(&pcifront_dev_lock);
+}
+static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev;
+
+	pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL);
+	if (pdev == NULL)
+		goto out;
+
+	pdev->sh_info =
+	    (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL);
+	if (pdev->sh_info == NULL) {
+		kfree(pdev);
+		pdev = NULL;
+		goto out;
+	}
+	pdev->sh_info->flags = 0;
+
+	/*Flag for registering PV AER handler*/
+	set_bit(_XEN_PCIB_AERHANDLER, (void *)&pdev->sh_info->flags);
+
+	dev_set_drvdata(&xdev->dev, pdev);
+	pdev->xdev = xdev;
+
+	INIT_LIST_HEAD(&pdev->root_buses);
+
+	spin_lock_init(&pdev->sh_info_lock);
+
+	pdev->evtchn = INVALID_EVTCHN;
+	pdev->gnt_ref = INVALID_GRANT_REF;
+	pdev->irq = -1;
+
+	INIT_WORK(&pdev->op_work, pcifront_do_aer);
+
+	dev_dbg(&xdev->dev, "Allocated pdev @ 0x%p pdev->sh_info @ 0x%p\n",
+		pdev, pdev->sh_info);
+out:
+	return pdev;
+}
+
+static void free_pdev(struct pcifront_device *pdev)
+{
+	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
+
+	pcifront_free_roots(pdev);
+
+	/*For PCIE_AER error handling job*/
+	flush_scheduled_work();
+
+	if (pdev->irq)
+		unbind_from_irqhandler(pdev->irq, pdev);
+
+	if (pdev->evtchn != INVALID_EVTCHN)
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+
+	if (pdev->gnt_ref != INVALID_GRANT_REF)
+		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
+					  (unsigned long)pdev->sh_info);
+	else
+		free_page((unsigned long)pdev->sh_info);
+
+	dev_set_drvdata(&pdev->xdev->dev, NULL);
+
+	kfree(pdev);
+}
+
+static int pcifront_publish_info(struct pcifront_device *pdev)
+{
+	int err = 0;
+	struct xenbus_transaction trans;
+
+	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
+	if (err < 0)
+		goto out;
+
+	pdev->gnt_ref = err;
+
+	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
+	if (err)
+		goto out;
+
+	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+		0, "pcifront", pdev);
+	if (err < 0) {
+		/*
+		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
+				 "irqhandler.\n");
+		*/
+		return err;
+	}
+	pdev->irq = err;
+
+do_publish:
+	err = xenbus_transaction_start(&trans);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend "
+				 "(start transaction)");
+		goto out;
+	}
+
+	err = xenbus_printf(trans, pdev->xdev->nodename,
+			    "pci-op-ref", "%u", pdev->gnt_ref);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "event-channel", "%u", pdev->evtchn);
+	if (!err)
+		err = xenbus_printf(trans, pdev->xdev->nodename,
+				    "magic", XEN_PCI_MAGIC);
+
+	if (err) {
+		xenbus_transaction_end(trans, 1);
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error writing configuration for backend");
+		goto out;
+	} else {
+		err = xenbus_transaction_end(trans, 0);
+		if (err == -EAGAIN)
+			goto do_publish;
+		else if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error completing transaction "
+					 "for backend");
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+
+	dev_dbg(&pdev->xdev->dev, "publishing successful!\n");
+
+out:
+	return err;
+}
+
+static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	char str[64];
+	unsigned int domain, bus;
+
+
+	/* Only connect once */
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateInitialised)
+		goto out;
+
+	err = pcifront_connect(pdev);
+	if (err) {
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error connecting PCI Frontend");
+		goto out;
+	}
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_scan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_scan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+	int err = 0;
+	enum xenbus_state prev_state;
+
+
+	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+
+	if (prev_state >= XenbusStateClosing)
+		goto out;
+
+	if (prev_state == XenbusStateConnected) {
+		pcifront_free_roots(pdev);
+		pcifront_disconnect(pdev);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateClosed);
+
+out:
+
+	return err;
+}
+
+static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+{
+	int err = -EFAULT;
+	int i, num_roots, len;
+	unsigned int domain, bus;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateReconfiguring)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+			   "root_num", "%d", &num_roots);
+	if (err == -ENOENT) {
+		xenbus_dev_error(pdev->xdev, err,
+				 "No PCI Roots found, trying 0000:00");
+		err = pcifront_rescan_root(pdev, 0, 0);
+		num_roots = 0;
+	} else if (err != 1) {
+		if (err == 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI roots");
+		goto out;
+	}
+
+	for (i = 0; i < num_roots; i++) {
+		len = snprintf(str, sizeof(str), "root-%d", i);
+		if (unlikely(len >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x", &domain, &bus);
+		if (err != 2) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI root %d", i);
+			goto out;
+		}
+
+		err = pcifront_rescan_root(pdev, domain, bus);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root %04x:%02x",
+					 domain, bus);
+			goto out;
+		}
+	}
+
+	xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+out:
+	return err;
+}
+
+static int pcifront_detach_devices(struct pcifront_device *pdev)
+{
+	int err = 0;
+	int i, num_devs;
+	unsigned int domain, bus, slot, func;
+	struct pci_bus *pci_bus;
+	struct pci_dev *pci_dev;
+	char str[64];
+
+	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	    XenbusStateConnected)
+		goto out;
+
+	err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d",
+			   &num_devs);
+	if (err != 1) {
+		if (err >= 0)
+			err = -EINVAL;
+		xenbus_dev_fatal(pdev->xdev, err,
+				 "Error reading number of PCI devices");
+		goto out;
+	}
+
+	/* Find devices being detached and remove them. */
+	for (i = 0; i < num_devs; i++) {
+		int l, state;
+		l = snprintf(str, sizeof(str), "state-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d",
+				   &state);
+		if (err != 1)
+			state = XenbusStateUnknown;
+
+		if (state != XenbusStateClosing)
+			continue;
+
+		/* Remove device. */
+		l = snprintf(str, sizeof(str), "vdev-%d", i);
+		if (unlikely(l >= (sizeof(str) - 1))) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+				   "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+		if (err != 4) {
+			if (err >= 0)
+				err = -EINVAL;
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error reading PCI device %d", i);
+			goto out;
+		}
+
+		pci_bus = pci_find_bus(domain, bus);
+		if (!pci_bus) {
+			dev_dbg(&pdev->xdev->dev, "Cannot get bus %04x:%02x\n",
+				domain, bus);
+			continue;
+		}
+		pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
+		if (!pci_dev) {
+			dev_dbg(&pdev->xdev->dev,
+				"Cannot get PCI device %04x:%02x:%02x.%02x\n",
+				domain, bus, slot, func);
+			continue;
+		}
+		pci_remove_bus_device(pci_dev);
+		pci_dev_put(pci_dev);
+
+		dev_dbg(&pdev->xdev->dev,
+			"PCI device %04x:%02x:%02x.%02x removed.\n",
+			domain, bus, slot, func);
+	}
+
+	err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring);
+
+out:
+	return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+						  enum xenbus_state be_state)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+
+	switch (be_state) {
+	case XenbusStateUnknown:
+	case XenbusStateInitialising:
+	case XenbusStateInitWait:
+	case XenbusStateInitialised:
+	case XenbusStateClosed:
+		break;
+
+	case XenbusStateConnected:
+		pcifront_try_connect(pdev);
+		break;
+
+	case XenbusStateClosing:
+		dev_warn(&xdev->dev, "backend going away!\n");
+		pcifront_try_disconnect(pdev);
+		break;
+
+	case XenbusStateReconfiguring:
+		pcifront_detach_devices(pdev);
+		break;
+
+	case XenbusStateReconfigured:
+		pcifront_attach_devices(pdev);
+		break;
+	}
+}
+
+static int pcifront_xenbus_probe(struct xenbus_device *xdev,
+				 const struct xenbus_device_id *id)
+{
+	int err = 0;
+	struct pcifront_device *pdev = alloc_pdev(xdev);
+
+	if (pdev == NULL) {
+		err = -ENOMEM;
+		xenbus_dev_fatal(xdev, err,
+				 "Error allocating pcifront_device struct");
+		goto out;
+	}
+
+	err = pcifront_publish_info(pdev);
+	if (err)
+		free_pdev(pdev);
+
+out:
+	return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+	if (pdev)
+		free_pdev(pdev);
+
+	return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+	{"pci"},
+	{""},
+};
+
+static struct xenbus_driver xenbus_pcifront_driver = {
+	.name			= "pcifront",
+	.owner			= THIS_MODULE,
+	.ids			= xenpci_ids,
+	.probe			= pcifront_xenbus_probe,
+	.remove			= pcifront_xenbus_remove,
+	.otherend_changed	= pcifront_backend_changed,
+};
+
+static int __init pcifront_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	pci_frontend_registrar(1 /* enable */);
+
+	return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+static void __exit pcifront_cleanup(void)
+{
+	xenbus_unregister_driver(&xenbus_pcifront_driver);
+	pci_frontend_registrar(0 /* disable */);
+}
+module_init(pcifront_init);
+module_exit(pcifront_cleanup);
+
+MODULE_DESCRIPTION("Xen PCI passthrough frontend.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:pci");
diff --git a/include/xen/interface/io/pciif.h b/include/xen/interface/io/pciif.h
new file mode 100644
index 0000000..d9922ae
--- /dev/null
+++ b/include/xen/interface/io/pciif.h
@@ -0,0 +1,112 @@
+/*
+ * PCI Backend/Frontend Common Data Structures & Macros
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#ifndef __XEN_PCI_COMMON_H__
+#define __XEN_PCI_COMMON_H__
+
+/* Be sure to bump this number if you change this file */
+#define XEN_PCI_MAGIC "7"
+
+/* xen_pci_sharedinfo flags */
+#define	_XEN_PCIF_active		(0)
+#define	XEN_PCIF_active			(1<<_XEN_PCIF_active)
+#define	_XEN_PCIB_AERHANDLER		(1)
+#define	XEN_PCIB_AERHANDLER		(1<<_XEN_PCIB_AERHANDLER)
+#define	_XEN_PCIB_active		(2)
+#define	XEN_PCIB_active			(1<<_XEN_PCIB_active)
+
+/* xen_pci_op commands */
+#define	XEN_PCI_OP_conf_read		(0)
+#define	XEN_PCI_OP_conf_write		(1)
+#define	XEN_PCI_OP_enable_msi		(2)
+#define	XEN_PCI_OP_disable_msi		(3)
+#define	XEN_PCI_OP_enable_msix		(4)
+#define	XEN_PCI_OP_disable_msix		(5)
+#define	XEN_PCI_OP_aer_detected		(6)
+#define	XEN_PCI_OP_aer_resume		(7)
+#define	XEN_PCI_OP_aer_mmio		(8)
+#define	XEN_PCI_OP_aer_slotreset	(9)
+
+/* xen_pci_op error numbers */
+#define	XEN_PCI_ERR_success		(0)
+#define	XEN_PCI_ERR_dev_not_found	(-1)
+#define	XEN_PCI_ERR_invalid_offset	(-2)
+#define	XEN_PCI_ERR_access_denied	(-3)
+#define	XEN_PCI_ERR_not_implemented	(-4)
+/* XEN_PCI_ERR_op_failed - backend failed to complete the operation */
+#define XEN_PCI_ERR_op_failed		(-5)
+
+/*
+ * it should be PAGE_SIZE-sizeof(struct xen_pci_op))/sizeof(struct msix_entry))
+ * Should not exceed 128
+ */
+#define SH_INFO_MAX_VEC			128
+
+struct xen_msix_entry {
+	uint16_t vector;
+	uint16_t entry;
+};
+struct xen_pci_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+
+	/* OUT: will contain an error number (if any) from errno.h */
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment */
+	uint32_t bus;
+	uint32_t devfn;
+
+	/* IN: which configuration registers to touch */
+	int32_t offset;
+	int32_t size;
+
+	/* IN/OUT: Contains the result after a READ or the value to WRITE */
+	uint32_t value;
+	/* IN: Contains extra infor for this operation */
+	uint32_t info;
+	/*IN:  param for msi-x */
+	struct xen_msix_entry msix_entries[SH_INFO_MAX_VEC];
+};
+
+/*used for pcie aer handling*/
+struct xen_pcie_aer_op {
+	/* IN: what action to perform: XEN_PCI_OP_* */
+	uint32_t cmd;
+	/*IN/OUT: return aer_op result or carry error_detected state as input*/
+	int32_t err;
+
+	/* IN: which device to touch */
+	uint32_t domain; /* PCI Domain/Segment*/
+	uint32_t bus;
+	uint32_t devfn;
+};
+struct xen_pci_sharedinfo {
+	/* flags - XEN_PCIF_* */
+	uint32_t flags;
+	struct xen_pci_op op;
+	struct xen_pcie_aer_op aer_op;
+};
+
+#endif /* __XEN_PCI_COMMON_H__ */
-- 
1.7.1


[-- Attachment #3: Type: text/plain, Size: 138 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel

[Xen-devel] Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Jan Beulich]

>>> On 13.10.10 at 18:16, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> wrote:
> On Wed, Oct 13, 2010 at 09:53:44AM -0400, Konrad Rzeszutek Wilk wrote:
>> Hey Jan,
>> 
>> Thank you for taking your time to look at this patch. Will fix up, test it, 
>> and if there are no issues, have it ready tomorrow.
> 
> Attached (and inline) is the updated version of this patch. If I missed 
> anything
> please do point it out to me!

There's one more missing "static", and one incorrect change to
free_pdev() you did.

Also, any word on the pdev_lock you dropped from the original
implementation?

> If this is to your satisfaction, can I put a Reviewed-by tag on the patch?

Feel free to do so.

> --- /dev/null
> +++ b/drivers/pci/xen-pcifront.c
>...
> +int __devinit pcifront_scan_bus(struct pcifront_device *pdev,

static?

>...
> +static void free_pdev(struct pcifront_device *pdev)
> +{
> +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> +
> +	pcifront_free_roots(pdev);
> +
> +	/*For PCIE_AER error handling job*/
> +	flush_scheduled_work();
> +
> +	if (pdev->irq)

	if (pdev->irq > 0)

It gets initialized to -1 in alloc_pdev(). It may be debatable whether
it should be >= 0 - I'm not sure if the pv-ops code allows IRQ 0 to
be used. If it doesn't, initializing to 0 in alloc_pdev() would be an
alternative.

> +		unbind_from_irqhandler(pdev->irq, pdev);
> +
> +	if (pdev->evtchn != INVALID_EVTCHN)
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> +
> +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> +					  (unsigned long)pdev->sh_info);
> +	else
> +		free_page((unsigned long)pdev->sh_info);
> +
> +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> +
> +	kfree(pdev);
> +}
> +
> +static int pcifront_publish_info(struct pcifront_device *pdev)
> +{
> +	int err = 0;
> +	struct xenbus_transaction trans;
> +
> +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> +	if (err < 0)
> +		goto out;
> +
> +	pdev->gnt_ref = err;
> +
> +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> +	if (err)
> +		goto out;
> +
> +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> +		0, "pcifront", pdev);
> +	if (err < 0) {
> +		/*
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> +				 "irqhandler.\n");
> +		*/

Why are you commenting it out rather than removing it?

Jan

[Xen-devel] Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Jan Beulich]

>>> On 13.10.10 at 18:16, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> wrote:
> On Wed, Oct 13, 2010 at 09:53:44AM -0400, Konrad Rzeszutek Wilk wrote:
>> Hey Jan,
>> 
>> Thank you for taking your time to look at this patch. Will fix up, test it, 
>> and if there are no issues, have it ready tomorrow.
> 
> Attached (and inline) is the updated version of this patch. If I missed 
> anything
> please do point it out to me!

There's one more missing "static", and one incorrect change to
free_pdev() you did.

Also, any word on the pdev_lock you dropped from the original
implementation?

> If this is to your satisfaction, can I put a Reviewed-by tag on the patch?

Feel free to do so.

> --- /dev/null
> +++ b/drivers/pci/xen-pcifront.c
>...
> +int __devinit pcifront_scan_bus(struct pcifront_device *pdev,

static?

>...
> +static void free_pdev(struct pcifront_device *pdev)
> +{
> +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> +
> +	pcifront_free_roots(pdev);
> +
> +	/*For PCIE_AER error handling job*/
> +	flush_scheduled_work();
> +
> +	if (pdev->irq)

	if (pdev->irq > 0)

It gets initialized to -1 in alloc_pdev(). It may be debatable whether
it should be >= 0 - I'm not sure if the pv-ops code allows IRQ 0 to
be used. If it doesn't, initializing to 0 in alloc_pdev() would be an
alternative.

> +		unbind_from_irqhandler(pdev->irq, pdev);
> +
> +	if (pdev->evtchn != INVALID_EVTCHN)
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> +
> +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> +					  (unsigned long)pdev->sh_info);
> +	else
> +		free_page((unsigned long)pdev->sh_info);
> +
> +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> +
> +	kfree(pdev);
> +}
> +
> +static int pcifront_publish_info(struct pcifront_device *pdev)
> +{
> +	int err = 0;
> +	struct xenbus_transaction trans;
> +
> +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> +	if (err < 0)
> +		goto out;
> +
> +	pdev->gnt_ref = err;
> +
> +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> +	if (err)
> +		goto out;
> +
> +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> +		0, "pcifront", pdev);
> +	if (err < 0) {
> +		/*
> +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> +				 "irqhandler.\n");
> +		*/

Why are you commenting it out rather than removing it?

Jan

Re: [Xen-devel] Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

On Thu, Oct 14, 2010 at 08:15:06AM +0100, Jan Beulich wrote:
> >>> On 13.10.10 at 18:16, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> wrote:
> > On Wed, Oct 13, 2010 at 09:53:44AM -0400, Konrad Rzeszutek Wilk wrote:
> >> Hey Jan,
> >> 
> >> Thank you for taking your time to look at this patch. Will fix up, test it, 
> >> and if there are no issues, have it ready tomorrow.
> > 
> > Attached (and inline) is the updated version of this patch. If I missed 
> > anything
> > please do point it out to me!
> 
> There's one more missing "static", and one incorrect change to
> free_pdev() you did.

Fixed.
> 
> Also, any word on the pdev_lock you dropped from the original
> implementation?

Yes. The reason for dropping it was that the xenwatch thread provides
the neccessary locking for the states. So no more need for this
spin_lock.

> 
> > If this is to your satisfaction, can I put a Reviewed-by tag on the patch?
> 
> Feel free to do so.

Thank you.
> 
> > --- /dev/null
> > +++ b/drivers/pci/xen-pcifront.c
> >...
> > +int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
> 
> static?

Yup, done.
> 
> >...
> > +static void free_pdev(struct pcifront_device *pdev)
> > +{
> > +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> > +
> > +	pcifront_free_roots(pdev);
> > +
> > +	/*For PCIE_AER error handling job*/
> > +	flush_scheduled_work();
> > +
> > +	if (pdev->irq)
> 
> 	if (pdev->irq > 0)
> 
> It gets initialized to -1 in alloc_pdev(). It may be debatable whether
> it should be >= 0 - I'm not sure if the pv-ops code allows IRQ 0 to
> be used. If it doesn't, initializing to 0 in alloc_pdev() would be an
> alternative.

I made it '>=' The Xen PCI (arch/x86/pci/xen.c) and Xen Events (riers/xen/events.c)
are both OK with an IRQ of zero. So lets be uniform and be OK here too.

> 
> > +		unbind_from_irqhandler(pdev->irq, pdev);
> > +
> > +	if (pdev->evtchn != INVALID_EVTCHN)
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> > +
> > +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> > +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> > +					  (unsigned long)pdev->sh_info);
> > +	else
> > +		free_page((unsigned long)pdev->sh_info);
> > +
> > +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> > +
> > +	kfree(pdev);
> > +}
> > +
> > +static int pcifront_publish_info(struct pcifront_device *pdev)
> > +{
> > +	int err = 0;
> > +	struct xenbus_transaction trans;
> > +
> > +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> > +	if (err < 0)
> > +		goto out;
> > +
> > +	pdev->gnt_ref = err;
> > +
> > +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> > +	if (err)
> > +		goto out;
> > +
> > +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> > +		0, "pcifront", pdev);
> > +	if (err < 0) {
> > +		/*
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> > +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> > +				 "irqhandler.\n");
> > +		*/
> 
> Why are you commenting it out rather than removing it?

Umm. I was in a hurry to test it out and just in case it would fail I
made it a comment. And then forgot about it. Removed that comented out
section of code.
> 
> Jan
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel

Re: Re: [PATCH 20/23] xen-pcifront: Xen PCI frontend driver.

[Konrad Rzeszutek Wilk]

On Thu, Oct 14, 2010 at 08:15:06AM +0100, Jan Beulich wrote:
> >>> On 13.10.10 at 18:16, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> wrote:
> > On Wed, Oct 13, 2010 at 09:53:44AM -0400, Konrad Rzeszutek Wilk wrote:
> >> Hey Jan,
> >> 
> >> Thank you for taking your time to look at this patch. Will fix up, test it, 
> >> and if there are no issues, have it ready tomorrow.
> > 
> > Attached (and inline) is the updated version of this patch. If I missed 
> > anything
> > please do point it out to me!
> 
> There's one more missing "static", and one incorrect change to
> free_pdev() you did.

Fixed.
> 
> Also, any word on the pdev_lock you dropped from the original
> implementation?

Yes. The reason for dropping it was that the xenwatch thread provides
the neccessary locking for the states. So no more need for this
spin_lock.

> 
> > If this is to your satisfaction, can I put a Reviewed-by tag on the patch?
> 
> Feel free to do so.

Thank you.
> 
> > --- /dev/null
> > +++ b/drivers/pci/xen-pcifront.c
> >...
> > +int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
> 
> static?

Yup, done.
> 
> >...
> > +static void free_pdev(struct pcifront_device *pdev)
> > +{
> > +	dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
> > +
> > +	pcifront_free_roots(pdev);
> > +
> > +	/*For PCIE_AER error handling job*/
> > +	flush_scheduled_work();
> > +
> > +	if (pdev->irq)
> 
> 	if (pdev->irq > 0)
> 
> It gets initialized to -1 in alloc_pdev(). It may be debatable whether
> it should be >= 0 - I'm not sure if the pv-ops code allows IRQ 0 to
> be used. If it doesn't, initializing to 0 in alloc_pdev() would be an
> alternative.

I made it '>=' The Xen PCI (arch/x86/pci/xen.c) and Xen Events (riers/xen/events.c)
are both OK with an IRQ of zero. So lets be uniform and be OK here too.

> 
> > +		unbind_from_irqhandler(pdev->irq, pdev);
> > +
> > +	if (pdev->evtchn != INVALID_EVTCHN)
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> > +
> > +	if (pdev->gnt_ref != INVALID_GRANT_REF)
> > +		gnttab_end_foreign_access(pdev->gnt_ref, 0 /* r/w page */,
> > +					  (unsigned long)pdev->sh_info);
> > +	else
> > +		free_page((unsigned long)pdev->sh_info);
> > +
> > +	dev_set_drvdata(&pdev->xdev->dev, NULL);
> > +
> > +	kfree(pdev);
> > +}
> > +
> > +static int pcifront_publish_info(struct pcifront_device *pdev)
> > +{
> > +	int err = 0;
> > +	struct xenbus_transaction trans;
> > +
> > +	err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
> > +	if (err < 0)
> > +		goto out;
> > +
> > +	pdev->gnt_ref = err;
> > +
> > +	err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
> > +	if (err)
> > +		goto out;
> > +
> > +	err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
> > +		0, "pcifront", pdev);
> > +	if (err < 0) {
> > +		/*
> > +		xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
> > +		xenbus_dev_fatal(pdev->xdev, err, "Failed to bind evtchn to "
> > +				 "irqhandler.\n");
> > +		*/
> 
> Why are you commenting it out rather than removing it?

Umm. I was in a hurry to test it out and just in case it would fail I
made it a comment. And then forgot about it. Removed that comented out
section of code.
> 
> Jan
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel

Re: [PATCH 08/23] xen: statically initialize cpu_evtchn_mask_p

[Paolo Bonzini]

On 10/12/2010 05:44 PM, Konrad Rzeszutek Wilk wrote:
> -static struct cpu_evtchn_s *cpu_evtchn_mask_p;
> +
> +static __initdata struct cpu_evtchn_s init_evtchn_mask = {
> +	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
> +};
> +static struct cpu_evtchn_s *cpu_evtchn_mask_p =&init_evtchn_mask;
> +
>   static inline unsigned long *cpu_evtchn_mask(int cpu)
>   {
>   	return cpu_evtchn_mask_p[cpu].bits;

This causes a modpost warning:

    WARNING: drivers/xen/built-in.o(.data+0x0): Section mismatch in
    reference from the variable cpu_evtchn_mask_p to the variable
    .init.data:init_evtchn_mask

    The variable cpu_evtchn_mask_p references
    the variable __initdata init_evtchn_mask

    If the reference is valid then annotate the
    variable with __init* or __refdata (see linux/init.h) or name the variable:
    *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, 

This is harmless, the variable is initialized to non-init data
in an __init function.  The added noise is ugly, though.

Paolo

Re: [Xen-devel] Re: [PATCH 08/23] xen: statically initialize cpu_evtchn_mask_p

[Ian Campbell]

On Mon, 2011-01-24 at 17:44 +0000, Paolo Bonzini wrote:
> On 10/12/2010 05:44 PM, Konrad Rzeszutek Wilk wrote:
> > -static struct cpu_evtchn_s *cpu_evtchn_mask_p;
> > +
> > +static __initdata struct cpu_evtchn_s init_evtchn_mask = {
> > +	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
> > +};
> > +static struct cpu_evtchn_s *cpu_evtchn_mask_p =&init_evtchn_mask;
> > +
> >   static inline unsigned long *cpu_evtchn_mask(int cpu)
> >   {
> >   	return cpu_evtchn_mask_p[cpu].bits;
> 
> This causes a modpost warning:
> 
>     WARNING: drivers/xen/built-in.o(.data+0x0): Section mismatch in
>     reference from the variable cpu_evtchn_mask_p to the variable
>     .init.data:init_evtchn_mask
> 
>     The variable cpu_evtchn_mask_p references
>     the variable __initdata init_evtchn_mask
> 
>     If the reference is valid then annotate the
>     variable with __init* or __refdata (see linux/init.h) or name the variable:
>     *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, 
> 
> This is harmless, the variable is initialized to non-init data
> in an __init function.  The added noise is ugly, though.

Does this help? If I understand the comment which precedes  __initref
correctly it is intended to address precisely this situation.

Ian.
8<---------

xen: events: mark cpu_evtchn_mask_p as __refdata

This variable starts out pointing at init_evtchn_mask which is marked
__initdata but is set to point to a non-init data region in xen_init_IRQ
which is itself an __init function so this is safe.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 31af0ac..5061af0 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -114,7 +114,7 @@ struct cpu_evtchn_s {
 static __initdata struct cpu_evtchn_s init_evtchn_mask = {
 	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
 };
-static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
+static struct __refdata cpu_evtchn_s *cpu_evtchn_mask_p =
&init_evtchn_mask;
 
 static inline unsigned long *cpu_evtchn_mask(int cpu)
 {

Re: Re: [PATCH 08/23] xen: statically initialize cpu_evtchn_mask_p

[Andrew Jones]

On 01/25/2011 03:02 PM, Ian Campbell wrote:
> On Mon, 2011-01-24 at 17:44 +0000, Paolo Bonzini wrote:
>> On 10/12/2010 05:44 PM, Konrad Rzeszutek Wilk wrote:
>>> -static struct cpu_evtchn_s *cpu_evtchn_mask_p;
>>> +
>>> +static __initdata struct cpu_evtchn_s init_evtchn_mask = {
>>> +	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
>>> +};
>>> +static struct cpu_evtchn_s *cpu_evtchn_mask_p =&init_evtchn_mask;
>>> +
>>>   static inline unsigned long *cpu_evtchn_mask(int cpu)
>>>   {
>>>   	return cpu_evtchn_mask_p[cpu].bits;
>>
>> This causes a modpost warning:
>>
>>     WARNING: drivers/xen/built-in.o(.data+0x0): Section mismatch in
>>     reference from the variable cpu_evtchn_mask_p to the variable
>>     .init.data:init_evtchn_mask
>>
>>     The variable cpu_evtchn_mask_p references
>>     the variable __initdata init_evtchn_mask
>>
>>     If the reference is valid then annotate the
>>     variable with __init* or __refdata (see linux/init.h) or name the variable:
>>     *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, 
>>
>> This is harmless, the variable is initialized to non-init data
>> in an __init function.  The added noise is ugly, though.
> 
> Does this help? If I understand the comment which precedes  __initref
> correctly it is intended to address precisely this situation.
> 
> Ian.
> 8<---------
> 
> xen: events: mark cpu_evtchn_mask_p as __refdata
> 
> This variable starts out pointing at init_evtchn_mask which is marked
> __initdata but is set to point to a non-init data region in xen_init_IRQ
> which is itself an __init function so this is safe.
> 
> Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
> 
> diff --git a/drivers/xen/events.c b/drivers/xen/events.c
> index 31af0ac..5061af0 100644
> --- a/drivers/xen/events.c
> +++ b/drivers/xen/events.c
> @@ -114,7 +114,7 @@ struct cpu_evtchn_s {
>  static __initdata struct cpu_evtchn_s init_evtchn_mask = {
>  	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
>  };
> -static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
> +static struct __refdata cpu_evtchn_s *cpu_evtchn_mask_p =
> &init_evtchn_mask;
>  
>  static inline unsigned long *cpu_evtchn_mask(int cpu)
>  {
> 

This does indeed fix it. Although you need __refdata to follow the
complete struct name 'struct cpu_evtchn_s' rather than just 'struct', i.e.

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 7468147..a313890 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -114,7 +114,7 @@ struct cpu_evtchn_s {
 static __initdata struct cpu_evtchn_s init_evtchn_mask = {
        .bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
 };
-static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
+static struct cpu_evtchn_s __refdata *cpu_evtchn_mask_p =
&init_evtchn_mask;

 static inline unsigned long *cpu_evtchn_mask(int cpu)
 {


Ian, are you going to push this to lkml in one of your batches?

Drew

Re: Re: [PATCH 08/23] xen: statically initialize cpu_evtchn_mask_p

[Ian Campbell]

On Wed, 2011-02-09 at 13:42 +0000, Andrew Jones wrote:
> On 01/25/2011 03:02 PM, Ian Campbell wrote:
> > On Mon, 2011-01-24 at 17:44 +0000, Paolo Bonzini wrote:
> >> On 10/12/2010 05:44 PM, Konrad Rzeszutek Wilk wrote:
> >>> -static struct cpu_evtchn_s *cpu_evtchn_mask_p;
> >>> +
> >>> +static __initdata struct cpu_evtchn_s init_evtchn_mask = {
> >>> +	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
> >>> +};
> >>> +static struct cpu_evtchn_s *cpu_evtchn_mask_p =&init_evtchn_mask;
> >>> +
> >>>   static inline unsigned long *cpu_evtchn_mask(int cpu)
> >>>   {
> >>>   	return cpu_evtchn_mask_p[cpu].bits;
> >>
> >> This causes a modpost warning:
> >>
> >>     WARNING: drivers/xen/built-in.o(.data+0x0): Section mismatch in
> >>     reference from the variable cpu_evtchn_mask_p to the variable
> >>     .init.data:init_evtchn_mask
> >>
> >>     The variable cpu_evtchn_mask_p references
> >>     the variable __initdata init_evtchn_mask
> >>
> >>     If the reference is valid then annotate the
> >>     variable with __init* or __refdata (see linux/init.h) or name the variable:
> >>     *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, 
> >>
> >> This is harmless, the variable is initialized to non-init data
> >> in an __init function.  The added noise is ugly, though.
> > 
> > Does this help? If I understand the comment which precedes  __initref
> > correctly it is intended to address precisely this situation.
> > 
> > Ian.
> > 8<---------
> > 
> > xen: events: mark cpu_evtchn_mask_p as __refdata
> > 
> > This variable starts out pointing at init_evtchn_mask which is marked
> > __initdata but is set to point to a non-init data region in xen_init_IRQ
> > which is itself an __init function so this is safe.
> > 
> > Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
> > 
> > diff --git a/drivers/xen/events.c b/drivers/xen/events.c
> > index 31af0ac..5061af0 100644
> > --- a/drivers/xen/events.c
> > +++ b/drivers/xen/events.c
> > @@ -114,7 +114,7 @@ struct cpu_evtchn_s {
> >  static __initdata struct cpu_evtchn_s init_evtchn_mask = {
> >  	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
> >  };
> > -static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
> > +static struct __refdata cpu_evtchn_s *cpu_evtchn_mask_p =
> > &init_evtchn_mask;
> >  
> >  static inline unsigned long *cpu_evtchn_mask(int cpu)
> >  {
> > 
> 
> This does indeed fix it. Although you need __refdata to follow the
> complete struct name 'struct cpu_evtchn_s' rather than just 'struct', i.e.
> 
> diff --git a/drivers/xen/events.c b/drivers/xen/events.c
> index 7468147..a313890 100644
> --- a/drivers/xen/events.c
> +++ b/drivers/xen/events.c
> @@ -114,7 +114,7 @@ struct cpu_evtchn_s {
>  static __initdata struct cpu_evtchn_s init_evtchn_mask = {
>         .bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
>  };
> -static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
> +static struct cpu_evtchn_s __refdata *cpu_evtchn_mask_p =
> &init_evtchn_mask;
> 
>  static inline unsigned long *cpu_evtchn_mask(int cpu)
>  {
> 
> 
> Ian, are you going to push this to lkml in one of your batches?

Sure.

Can I add an Acked- and/or Tested-by from you?

Ian.

Re: Re: [PATCH 08/23] xen: statically initialize cpu_evtchn_mask_p

[Andrew Jones]

On 02/09/2011 03:08 PM, Ian Campbell wrote:
> On Wed, 2011-02-09 at 13:42 +0000, Andrew Jones wrote:
>> On 01/25/2011 03:02 PM, Ian Campbell wrote:
>>> On Mon, 2011-01-24 at 17:44 +0000, Paolo Bonzini wrote:
>>>> On 10/12/2010 05:44 PM, Konrad Rzeszutek Wilk wrote:
>>>>> -static struct cpu_evtchn_s *cpu_evtchn_mask_p;
>>>>> +
>>>>> +static __initdata struct cpu_evtchn_s init_evtchn_mask = {
>>>>> +	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
>>>>> +};
>>>>> +static struct cpu_evtchn_s *cpu_evtchn_mask_p =&init_evtchn_mask;
>>>>> +
>>>>>   static inline unsigned long *cpu_evtchn_mask(int cpu)
>>>>>   {
>>>>>   	return cpu_evtchn_mask_p[cpu].bits;
>>>>
>>>> This causes a modpost warning:
>>>>
>>>>     WARNING: drivers/xen/built-in.o(.data+0x0): Section mismatch in
>>>>     reference from the variable cpu_evtchn_mask_p to the variable
>>>>     .init.data:init_evtchn_mask
>>>>
>>>>     The variable cpu_evtchn_mask_p references
>>>>     the variable __initdata init_evtchn_mask
>>>>
>>>>     If the reference is valid then annotate the
>>>>     variable with __init* or __refdata (see linux/init.h) or name the variable:
>>>>     *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, 
>>>>
>>>> This is harmless, the variable is initialized to non-init data
>>>> in an __init function.  The added noise is ugly, though.
>>>
>>> Does this help? If I understand the comment which precedes  __initref
>>> correctly it is intended to address precisely this situation.
>>>
>>> Ian.
>>> 8<---------
>>>
>>> xen: events: mark cpu_evtchn_mask_p as __refdata
>>>
>>> This variable starts out pointing at init_evtchn_mask which is marked
>>> __initdata but is set to point to a non-init data region in xen_init_IRQ
>>> which is itself an __init function so this is safe.
>>>
>>> Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
>>>
>>> diff --git a/drivers/xen/events.c b/drivers/xen/events.c
>>> index 31af0ac..5061af0 100644
>>> --- a/drivers/xen/events.c
>>> +++ b/drivers/xen/events.c
>>> @@ -114,7 +114,7 @@ struct cpu_evtchn_s {
>>>  static __initdata struct cpu_evtchn_s init_evtchn_mask = {
>>>  	.bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
>>>  };
>>> -static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
>>> +static struct __refdata cpu_evtchn_s *cpu_evtchn_mask_p =
>>> &init_evtchn_mask;
>>>  
>>>  static inline unsigned long *cpu_evtchn_mask(int cpu)
>>>  {
>>>
>>
>> This does indeed fix it. Although you need __refdata to follow the
>> complete struct name 'struct cpu_evtchn_s' rather than just 'struct', i.e.
>>
>> diff --git a/drivers/xen/events.c b/drivers/xen/events.c
>> index 7468147..a313890 100644
>> --- a/drivers/xen/events.c
>> +++ b/drivers/xen/events.c
>> @@ -114,7 +114,7 @@ struct cpu_evtchn_s {
>>  static __initdata struct cpu_evtchn_s init_evtchn_mask = {
>>         .bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
>>  };
>> -static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
>> +static struct cpu_evtchn_s __refdata *cpu_evtchn_mask_p =
>> &init_evtchn_mask;
>>
>>  static inline unsigned long *cpu_evtchn_mask(int cpu)
>>  {
>>
>>
>> Ian, are you going to push this to lkml in one of your batches?
> 
> Sure.
> 
> Can I add an Acked- and/or Tested-by from you?
> 

Sure. Either-or or both. I ack it and have tested it.

Drew