[GIT PULL] Xen dom0 apic changes

[GIT PULL] Xen dom0 apic changes

[Jeremy Fitzhardinge]

This series implements the hooks into the x86 platform apic code that
Xen dom0 support requires.  This is a tidied-up repost of the series
posted a couple of weeks ago, with only a few small changes.

Thanks,
	J

The following changes since commit 089faa06184f85284ba6c4164dd7b4741ca5d5c5:
  Jeremy Fitzhardinge (1):
        x86: don't need "changed" parameter for set_io_bitmap()

are available in the git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen.git push/xen/dom0/apic

Gerd Hoffmann (2):
      xen: set pirq name to something useful.
      xen: fix legacy irq setup, make ioapic-less machines work.

Ian Campbell (1):
      xen: pre-initialize legacy irqs early

Jeremy Fitzhardinge (14):
      xen/dom0: handle acpi lapic parsing in Xen dom0
      xen: hook io_apic read/write operations
      xen: create dummy ioapic mapping
      xen: implement pirq type event channels
      x86/io_apic: add get_nr_irqs_gsi()
      xen/apic: identity map gsi->irqs
      xen: direct irq registration to pirq event channels
      xen: bind pirq to vector and event channel
      xen/apic: program the apic triggering and polarity properly
      xen: don't setup acpi interrupt unless there is one
      xen: use acpi_get_override_irq() to get triggering for legacy irqs
      xen: initialize irq 0 too
      xen: dynamically allocate irq & event structures
      xen: disable MSI

 arch/x86/include/asm/io_apic.h |    7 +
 arch/x86/include/asm/xen/pci.h |   13 ++
 arch/x86/kernel/acpi/boot.c    |   18 +++-
 arch/x86/kernel/apic/io_apic.c |   37 +++++-
 arch/x86/xen/Kconfig           |   11 ++
 arch/x86/xen/Makefile          |    3 +-
 arch/x86/xen/apic.c            |   60 +++++++++
 arch/x86/xen/enlighten.c       |    2 +
 arch/x86/xen/mmu.c             |   10 ++
 arch/x86/xen/pci.c             |   85 +++++++++++++
 arch/x86/xen/xen-ops.h         |    6 +
 drivers/pci/pci.h              |    2 -
 drivers/xen/events.c           |  273 ++++++++++++++++++++++++++++++++++++++--
 include/linux/pci.h            |    6 +
 include/xen/events.h           |   22 ++++
 15 files changed, 540 insertions(+), 15 deletions(-)
 create mode 100644 arch/x86/include/asm/xen/pci.h
 create mode 100644 arch/x86/xen/apic.c
 create mode 100644 arch/x86/xen/pci.c

[PATCH 01/17] xen/dom0: handle acpi lapic parsing in Xen dom0

[Jeremy Fitzhardinge]

When running in Xen dom0, we still want to parse the ACPI tables to
find out about local and IO apics, but we don't want to actually use
the lapics.

Put a couple of tests for Xen to prevent lapics from being mapped or
accessed.  This is very Xen-specific behaviour, so there didn't seem to
be any point in adding more indirection.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/kernel/acpi/boot.c |   10 ++++++++++
 1 files changed, 10 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a18eb7c..6a5af13 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -41,6 +41,8 @@
 #include <asm/mpspec.h>
 #include <asm/smp.h>
 
+#include <asm/xen/hypervisor.h>
+
 static int __initdata acpi_force = 0;
 u32 acpi_rsdt_forced;
 #ifdef	CONFIG_ACPI
@@ -218,6 +220,10 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled)
 {
 	unsigned int ver = 0;
 
+	/* We don't want to register lapics when in Xen dom0 */
+	if (xen_initial_domain())
+		return;
+
 	if (!enabled) {
 		++disabled_cpus;
 		return;
@@ -754,6 +760,10 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
 
 static void __init acpi_register_lapic_address(unsigned long address)
 {
+	/* Xen dom0 doesn't have usable lapics */
+	if (xen_initial_domain())
+		return;
+
 	mp_lapic_addr = address;
 
 	set_fixmap_nocache(FIX_APIC_BASE, address);
-- 
1.6.0.6

[PATCH 02/17] xen: hook io_apic read/write operations

[Jeremy Fitzhardinge]

In Xen, writes to the IO APIC are paravirtualized via hypercalls, so
implement the appropriate operations.

This version of the patch just hooks the io_apic read/write functions
directly, rather than introducing another layer of indirection.  The
xen_initial_domain() tests compile to 0 if CONFIG_XEN_DOM0 isn't set,
and are cheap if it is.

(An alternative would be to add io_apic_ops, and point them to the Xen
implementation as needed.  HPA deemed this extra level of indirection to
be excessive.)

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/include/asm/io_apic.h |    6 ++++
 arch/x86/kernel/apic/io_apic.c |   32 ++++++++++++++++++++--
 arch/x86/xen/Makefile          |    2 +-
 arch/x86/xen/apic.c            |   57 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/xen/enlighten.c       |    2 +
 arch/x86/xen/xen-ops.h         |    6 ++++
 6 files changed, 101 insertions(+), 4 deletions(-)
 create mode 100644 arch/x86/xen/apic.c

diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 59cb4a1..20b543a 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -183,4 +183,10 @@ static inline void ioapic_init_mappings(void)	{ }
 static inline void probe_nr_irqs_gsi(void)	{ }
 #endif
 
+void xen_io_apic_init(void);
+unsigned int xen_io_apic_read(unsigned apic, unsigned reg);
+void xen_io_apic_write(unsigned int apic,
+		       unsigned int reg, unsigned int value);
+
+
 #endif /* _ASM_X86_IO_APIC_H */
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 00e6071..6d14ff9 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -62,8 +62,10 @@
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/uv_irq.h>
 
+#include <asm/xen/hypervisor.h>
 #include <asm/apic.h>
 
+
 #define __apicdebuginit(type) static type __init
 
 /*
@@ -399,14 +401,26 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
 
 static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
 {
-	struct io_apic __iomem *io_apic = io_apic_base(apic);
+	struct io_apic __iomem *io_apic;
+
+	if (xen_initial_domain())
+		return xen_io_apic_read(apic, reg);
+
+	io_apic = io_apic_base(apic);
 	writel(reg, &io_apic->index);
 	return readl(&io_apic->data);
 }
 
 static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
 {
-	struct io_apic __iomem *io_apic = io_apic_base(apic);
+	struct io_apic __iomem *io_apic;
+
+	if (xen_initial_domain()) {
+		xen_io_apic_write(apic, reg, value);
+		return;
+	}
+
+	io_apic = io_apic_base(apic);
 	writel(reg, &io_apic->index);
 	writel(value, &io_apic->data);
 }
@@ -419,7 +433,14 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i
  */
 static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
 {
-	struct io_apic __iomem *io_apic = io_apic_base(apic);
+	struct io_apic __iomem *io_apic;
+
+	if (xen_initial_domain()) {
+		xen_io_apic_write(apic, reg, value);
+		return;
+	}
+
+	io_apic = io_apic_base(apic);
 
 	if (sis_apic_bug)
 		writel(reg, &io_apic->index);
@@ -4099,6 +4120,11 @@ void __init ioapic_init_mappings(void)
 	struct resource *ioapic_res;
 	int i;
 
+	if (xen_initial_domain()) {
+		xen_io_apic_init();
+		return;
+	}
+
 	ioapic_res = ioapic_setup_resources();
 	for (i = 0; i < nr_ioapics; i++) {
 		if (smp_found_config) {
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index c4cda96..73ecb74 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -11,4 +11,4 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 
 obj-$(CONFIG_SMP)		+= smp.o spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-obj-$(CONFIG_XEN_DOM0)		+= vga.o
+obj-$(CONFIG_XEN_DOM0)		+= vga.o apic.o
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
new file mode 100644
index 0000000..17736a0
--- /dev/null
+++ b/arch/x86/xen/apic.c
@@ -0,0 +1,57 @@
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/bitmap.h>
+
+#include <asm/io_apic.h>
+#include <asm/acpi.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/physdev.h>
+
+void __init xen_io_apic_init(void)
+{
+	printk("xen apic init\n");
+	dump_stack();
+}
+
+unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
+{
+	struct physdev_apic apic_op;
+	int ret;
+
+	apic_op.apic_physbase = mp_ioapics[apic].apicaddr;
+	apic_op.reg = reg;
+	ret = HYPERVISOR_physdev_op(PHYSDEVOP_apic_read, &apic_op);
+	if (ret)
+		BUG();
+	return apic_op.value;
+}
+
+
+void xen_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	struct physdev_apic apic_op;
+
+	apic_op.apic_physbase = mp_ioapics[apic].apicaddr;
+	apic_op.reg = reg;
+	apic_op.value = value;
+	if (HYPERVISOR_physdev_op(PHYSDEVOP_apic_write, &apic_op))
+		BUG();
+}
+
+void xen_init_apic(void)
+{
+	if (!xen_initial_domain())
+		return;
+
+#ifdef CONFIG_ACPI
+	/*
+	 * Pretend ACPI found our lapic even though we've disabled it,
+ 	 * to prevent MP tables from setting up lapics.
+ 	 */
+	acpi_lapic = 1;
+#endif
+}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f673cd8..a9a7d15 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1027,6 +1027,8 @@ asmlinkage void __init xen_start_kernel(void)
 		set_iopl.iopl = 1;
 		if (HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl) == -1)
 			BUG();
+
+		xen_init_apic();
 	}
 
 	/* set the limit of our address space */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 4dad0ad..8f4d9a8 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -85,6 +85,12 @@ static inline void xen_init_vga(const struct dom0_vga_console_info *info,
 }
 #endif
 
+#ifdef CONFIG_XEN_DOM0
+void xen_init_apic(void);
+#else
+static inline void xen_init_apic(void) {}
+#endif
+
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\
-- 
1.6.0.6

[PATCH 03/17] xen: create dummy ioapic mapping

[Jeremy Fitzhardinge]

We don't allow direct access to the IO apic, so make sure that any
request to map it just "maps" non-present pages.  We should see any
attempts at direct access explode nicely.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/mmu.c |   10 ++++++++++
 1 files changed, 10 insertions(+), 0 deletions(-)

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 0a0cd61..41d8253 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1916,6 +1916,16 @@ static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot)
 		pte = pfn_pte(phys, prot);
 		break;
 
+#ifdef CONFIG_X86_IO_APIC
+	case FIX_IO_APIC_BASE_0 ... FIX_IO_APIC_BASE_END:
+		/*
+		 * We just don't map the IO APIC - all access is via
+		 * hypercalls.  Keep the address in the pte for reference.
+		 */
+		pte = pfn_pte(phys, PAGE_NONE);
+		break;
+#endif
+
 	case FIX_PARAVIRT_BOOTMAP:
 		/* This is an MFN, but it isn't an IO mapping from the
 		   IO domain */
-- 
1.6.0.6

[PATCH 04/17] xen: implement pirq type event channels

[Jeremy Fitzhardinge]

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.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 drivers/xen/events.c |  245 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/xen/events.h |   14 +++
 2 files changed, 256 insertions(+), 3 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index f46e880..81726e8 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
  */
@@ -40,6 +40,9 @@
 #include <xen/interface/xen.h>
 #include <xen/interface/event_channel.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.
@@ -83,10 +86,12 @@ 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];
 
@@ -106,6 +111,7 @@ static inline unsigned long *cpu_evtchn_mask(int cpu)
 #define VALID_EVTCHN(chn)	((chn) != 0)
 
 static struct irq_chip xen_dynamic_chip;
+static struct irq_chip xen_pirq_chip;
 
 /* Constructor for packed IRQ information. */
 static struct irq_info mk_unbound_info(void)
@@ -212,6 +218,15 @@ 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)
@@ -328,7 +343,7 @@ static int find_unbound_irq(void)
 	int irq;
 	struct irq_desc *desc;
 
-	for (irq = 0; irq < nr_irqs; irq++)
+	for (irq = LEGACY_IRQS; irq < nr_irqs; irq++)
 		if (irq_info[irq].type == IRQT_UNBOUND)
 			break;
 
@@ -344,6 +359,210 @@ 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;
@@ -916,6 +1135,26 @@ 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,
+};
+
 void __init xen_init_IRQ(void)
 {
 	int i;
diff --git a/include/xen/events.h b/include/xen/events.h
index 0397ba1..e5b541d 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -55,4 +55,18 @@ bool xen_test_irq_pending(int irq);
    irq will be disabled so it won't deliver an interrupt. */
 void xen_poll_irq(int irq);
 
+/* Determine the IRQ which is bound to an event channel */
+unsigned irq_from_evtchn(unsigned int evtchn);
+
+/* 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 */
-- 
1.6.0.6

[PATCH 05/17] x86/io_apic: add get_nr_irqs_gsi()

[Jeremy Fitzhardinge]

From: Jeremy Fitzhardinge <jeremy@f9-builder.(none)>

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>
---
 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 20b543a..10a7a43 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -168,6 +168,7 @@ extern void reinit_intr_remapped_IO_APIC(int);
 #endif
 
 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 6d14ff9..6da6f3c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3851,6 +3851,11 @@ 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)
 {
-- 
1.6.0.6

[PATCH 06/17] xen/apic: identity map gsi->irqs

[Jeremy Fitzhardinge]

From: Jeremy Fitzhardinge <jeremy@f9-builder.(none)>

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>
---
 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 81726e8..3477998 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -31,6 +31,7 @@
 #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>
@@ -40,9 +41,6 @@
 #include <xen/interface/xen.h>
 #include <xen/interface/event_channel.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.
@@ -338,12 +336,24 @@ 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 = LEGACY_IRQS; irq < nr_irqs; irq++)
+	for (irq = start; irq < nr_irqs; irq++)
 		if (irq_info[irq].type == IRQT_UNBOUND)
 			break;
 
@@ -361,8 +371,8 @@ 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)
@@ -531,6 +541,7 @@ int xen_allocate_pirq(unsigned gsi)
 
 	if (identity_mapped_irq(gsi)) {
 		irq = gsi;
+		irq_to_desc_alloc_cpu(irq, 0);
 		dynamic_irq_init(irq);
 	} else
 		irq = find_unbound_irq();
-- 
1.6.0.6

[PATCH 07/17] xen: direct irq registration to pirq event channels

[Jeremy Fitzhardinge]

This patch puts the hooks into place so that when the interrupt
subsystem registers an irq, it gets routed via Xen (if we're running
under Xen).

The first step is to get a gsi for a particular device+pin.  We use
the normal acpi interrupt routing to do the mapping.

We reserve enough irq space to fit the hardware interrupt sources in,
so we can allocate the irq == gsi, as we do in the native case;
software events will get allocated irqs above that.

Having allocated an irq, we ask Xen to allocate a vector, and then
bind that pirq/vector to an event channel.  When the hardware raises
an interrupt on a vector, Xen signals us on the corresponding event
channel, which gets routed to the irq and delivered to the appropriate
device driver.

This patch does everything except set up the IO APIC pin routing to
the vector.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/include/asm/xen/pci.h |   13 +++++++++++
 arch/x86/kernel/acpi/boot.c    |    8 ++++++-
 arch/x86/xen/Kconfig           |   11 +++++++++
 arch/x86/xen/Makefile          |    1 +
 arch/x86/xen/pci.c             |   47 ++++++++++++++++++++++++++++++++++++++++
 drivers/xen/events.c           |    6 ++++-
 include/xen/events.h           |    8 ++++++
 7 files changed, 92 insertions(+), 2 deletions(-)
 create mode 100644 arch/x86/include/asm/xen/pci.h
 create mode 100644 arch/x86/xen/pci.c

diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
new file mode 100644
index 0000000..0563fc6
--- /dev/null
+++ b/arch/x86/include/asm/xen/pci.h
@@ -0,0 +1,13 @@
+#ifndef _ASM_X86_XEN_PCI_H
+#define _ASM_X86_XEN_PCI_H
+
+#ifdef CONFIG_XEN_DOM0_PCI
+int xen_register_gsi(u32 gsi, int triggering, int polarity);
+#else
+static inline int xen_register_gsi(u32 gsi, int triggering, int polarity)
+{
+	return -1;
+}
+#endif
+
+#endif	/* _ASM_X86_XEN_PCI_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 6a5af13..ad13a07 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -41,6 +41,8 @@
 #include <asm/mpspec.h>
 #include <asm/smp.h>
 
+#include <asm/xen/pci.h>
+
 #include <asm/xen/hypervisor.h>
 
 static int __initdata acpi_force = 0;
@@ -482,9 +484,13 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
  */
 int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 {
-	unsigned int irq;
+	int irq;
 	unsigned int plat_gsi = gsi;
 
+	irq = xen_register_gsi(gsi, triggering, polarity);
+	if (irq >= 0)
+		return irq;
+
 #ifdef CONFIG_PCI
 	/*
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index fe69286..42e9f0a 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -37,6 +37,17 @@ config XEN_DEBUG_FS
 	  Enable statistics output and various tuning options in debugfs.
 	  Enabling this option may incur a significant performance overhead.
 
+config XEN_PCI_PASSTHROUGH
+       bool #"Enable support for Xen PCI passthrough devices"
+       depends on XEN && PCI
+       help
+         Enable support for passing PCI devices through to
+	 unprivileged domains. (COMPLETELY UNTESTED)
+
+config XEN_DOM0_PCI
+       def_bool y
+       depends on XEN_DOM0 && PCI
+
 config XEN_DOM0
 	bool "Enable Xen privileged domain support"
 	depends on XEN && X86_IO_APIC && ACPI
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 73ecb74..639965a 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -12,3 +12,4 @@ obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 obj-$(CONFIG_SMP)		+= smp.o spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_XEN_DOM0)		+= vga.o apic.o
+obj-$(CONFIG_XEN_DOM0_PCI)	+= pci.o
\ No newline at end of file
diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
new file mode 100644
index 0000000..f450007
--- /dev/null
+++ b/arch/x86/xen/pci.c
@@ -0,0 +1,47 @@
+#include <linux/kernel.h>
+#include <linux/acpi.h>
+#include <linux/pci.h>
+
+#include <asm/pci_x86.h>
+
+#include <asm/xen/hypervisor.h>
+
+#include <xen/interface/xen.h>
+#include <xen/events.h>
+
+#include "xen-ops.h"
+
+int xen_register_gsi(u32 gsi, int triggering, int polarity)
+{
+	int irq;
+
+	if (!xen_domain())
+		return -1;
+
+	printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n",
+	       gsi, triggering, polarity);
+
+	irq = xen_allocate_pirq(gsi);
+
+	printk(KERN_DEBUG "xen: --> irq=%d\n", irq);
+
+	return irq;
+}
+
+void __init xen_setup_pirqs(void)
+{
+#ifdef CONFIG_ACPI
+	int irq;
+
+	/*
+	 * Set up acpi interrupt in acpi_gbl_FADT.sci_interrupt.
+	 */
+	irq = xen_allocate_pirq(acpi_gbl_FADT.sci_interrupt);
+
+	printk(KERN_INFO "xen: allocated irq %d for acpi %d\n",
+	       irq, acpi_gbl_FADT.sci_interrupt);
+
+	/* Blerk. */
+	acpi_gbl_FADT.sci_interrupt = irq;
+#endif
+}
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 3477998..3cf0a1b 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -413,6 +413,7 @@ 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);
 
@@ -422,7 +423,8 @@ 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) {
+	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);
@@ -1181,4 +1183,6 @@ void __init xen_init_IRQ(void)
 		mask_evtchn(i);
 
 	irq_ctx_init(smp_processor_id());
+
+	xen_setup_pirqs();
 }
diff --git a/include/xen/events.h b/include/xen/events.h
index e5b541d..6fe4863 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -69,4 +69,12 @@ int xen_vector_from_irq(unsigned pirq);
 /* Return gsi allocated to pirq */
 int xen_gsi_from_irq(unsigned pirq);
 
+#ifdef CONFIG_XEN_DOM0_PCI
+void xen_setup_pirqs(void);
+#else
+static inline void xen_setup_pirqs(void)
+{
+}
+#endif
+
 #endif	/* _XEN_EVENTS_H */
-- 
1.6.0.6

[PATCH 08/17] xen: bind pirq to vector and event channel

[Jeremy Fitzhardinge]

Having converting a dev+pin to a gsi, and that gsi to an irq, and
allocated a vector for the irq, we must program the IO APIC to deliver
an interrupt on a pin to the vector, so Xen can deliver it as an event
channel.

Given the pirq, we can get the gsi and vector.  We map the gsi to a
specific IO APIC's pin, and set the routing entry.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/apic.c |    4 ++--
 arch/x86/xen/pci.c  |   30 ++++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 17736a0..e9d9ea7 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -4,6 +4,7 @@
 
 #include <asm/io_apic.h>
 #include <asm/acpi.h>
+#include <asm/hw_irq.h>
 
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
@@ -13,8 +14,7 @@
 
 void __init xen_io_apic_init(void)
 {
-	printk("xen apic init\n");
-	dump_stack();
+	enable_IO_APIC();
 }
 
 unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index f450007..61f070c 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -2,6 +2,8 @@
 #include <linux/acpi.h>
 #include <linux/pci.h>
 
+#include <asm/mpspec.h>
+#include <asm/io_apic.h>
 #include <asm/pci_x86.h>
 
 #include <asm/xen/hypervisor.h>
@@ -11,6 +13,31 @@
 
 #include "xen-ops.h"
 
+static void xen_set_io_apic_routing(int irq, int trigger, int polarity)
+{
+	int ioapic, ioapic_pin;
+	int vector, gsi;
+	struct IO_APIC_route_entry entry;
+
+	gsi = xen_gsi_from_irq(irq);
+	vector = xen_vector_from_irq(irq);
+
+	ioapic = mp_find_ioapic(gsi);
+	if (ioapic == -1) {
+		printk(KERN_WARNING "xen_set_ioapic_routing: irq %d gsi %d ioapic %d\n",
+			irq, gsi, ioapic);
+		return;
+	}
+
+	ioapic_pin = mp_find_ioapic_pin(ioapic, gsi);
+
+	printk(KERN_INFO "xen_set_ioapic_routing: irq %d gsi %d vector %d ioapic %d pin %d triggering %d polarity %d\n",
+		irq, gsi, vector, ioapic, ioapic_pin, trigger, polarity);
+
+	setup_ioapic_entry(ioapic, -1, &entry, ~0, trigger, polarity, vector);
+	ioapic_write_entry(ioapic, ioapic_pin, entry);
+}
+
 int xen_register_gsi(u32 gsi, int triggering, int polarity)
 {
 	int irq;
@@ -25,6 +52,9 @@ int xen_register_gsi(u32 gsi, int triggering, int polarity)
 
 	printk(KERN_DEBUG "xen: --> irq=%d\n", irq);
 
+	if (irq > 0)
+		xen_set_io_apic_routing(irq, triggering, polarity);
+
 	return irq;
 }
 
-- 
1.6.0.6

[PATCH 09/17] xen: pre-initialize legacy irqs early

[Jeremy Fitzhardinge]

From: Ian Campbell <ian.campbell@citrix.com>

Various legacy devices, such as IDE, assume their legacy interrupts are
already initialized and are immediately usable.  Pre-initialize all the
legacy interrupts.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/pci.c |    6 +++++-
 1 files changed, 5 insertions(+), 1 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index 61f070c..d661c74 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -60,9 +60,9 @@ int xen_register_gsi(u32 gsi, int triggering, int polarity)
 
 void __init xen_setup_pirqs(void)
 {
-#ifdef CONFIG_ACPI
 	int irq;
 
+#ifdef CONFIG_ACPI
 	/*
 	 * Set up acpi interrupt in acpi_gbl_FADT.sci_interrupt.
 	 */
@@ -74,4 +74,8 @@ void __init xen_setup_pirqs(void)
 	/* Blerk. */
 	acpi_gbl_FADT.sci_interrupt = irq;
 #endif
+
+	/* Pre-allocate legacy irqs */
+	for (irq=0; irq < NR_IRQS_LEGACY; irq++)
+		xen_allocate_pirq(irq);
 }
-- 
1.6.0.6

[PATCH 10/17] xen/apic: program the apic triggering and polarity properly

[Jeremy Fitzhardinge]

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

We were passing the ACPI triggering and polarity levels directly into
the apic - but they have reversed values.  The result was that
all the level-triggered interrupts were edge, and vice-versa.
It's surprising that anything worked at all, but now AHCI works
for me.

Thanks for Gerd Hoffmann for noticing this.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/pci.c |    4 +++-
 1 files changed, 3 insertions(+), 1 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index d661c74..fb408ce 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -53,7 +53,9 @@ int xen_register_gsi(u32 gsi, int triggering, int polarity)
 	printk(KERN_DEBUG "xen: --> irq=%d\n", irq);
 
 	if (irq > 0)
-		xen_set_io_apic_routing(irq, triggering, polarity);
+		xen_set_io_apic_routing(irq,
+					triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
+					polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
 
 	return irq;
 }
-- 
1.6.0.6

[PATCH 11/17] xen: don't setup acpi interrupt unless there is one

[Jeremy Fitzhardinge]

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

If the SCI hasn't been set, then presumably we're not running
with acpi, don't bother setting up the interrupt.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/pci.c |   11 +++++------
 1 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index fb408ce..e88f85e 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -68,13 +68,12 @@ void __init xen_setup_pirqs(void)
 	/*
 	 * Set up acpi interrupt in acpi_gbl_FADT.sci_interrupt.
 	 */
-	irq = xen_allocate_pirq(acpi_gbl_FADT.sci_interrupt);
+	if (acpi_gbl_FADT.sci_interrupt > 0) {
+		irq = xen_allocate_pirq(acpi_gbl_FADT.sci_interrupt);
 
-	printk(KERN_INFO "xen: allocated irq %d for acpi %d\n",
-	       irq, acpi_gbl_FADT.sci_interrupt);
-
-	/* Blerk. */
-	acpi_gbl_FADT.sci_interrupt = irq;
+		printk(KERN_INFO "xen: allocated irq %d for acpi %d\n",
+		       irq, acpi_gbl_FADT.sci_interrupt);
+	}
 #endif
 
 	/* Pre-allocate legacy irqs */
-- 
1.6.0.6

[PATCH 12/17] xen: use acpi_get_override_irq() to get triggering for legacy irqs

[Jeremy Fitzhardinge]

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

We need to set up proper IO apic entries for legacy irqs, which are
not normally configured by either normal acpi interrupt routing or
PNP.

This also generalizes the acpi interrupt setup, so we can remove it
as a special case.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/pci.c |   24 ++++++++++--------------
 1 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index e88f85e..f55532d 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -64,19 +64,15 @@ void __init xen_setup_pirqs(void)
 {
 	int irq;
 
-#ifdef CONFIG_ACPI
-	/*
-	 * Set up acpi interrupt in acpi_gbl_FADT.sci_interrupt.
-	 */
-	if (acpi_gbl_FADT.sci_interrupt > 0) {
-		irq = xen_allocate_pirq(acpi_gbl_FADT.sci_interrupt);
-
-		printk(KERN_INFO "xen: allocated irq %d for acpi %d\n",
-		       irq, acpi_gbl_FADT.sci_interrupt);
-	}
-#endif
-
 	/* Pre-allocate legacy irqs */
-	for (irq=0; irq < NR_IRQS_LEGACY; irq++)
-		xen_allocate_pirq(irq);
+	for (irq=0; irq < NR_IRQS_LEGACY; irq++) {
+		int trigger, polarity;
+
+		if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
+			continue;
+
+		xen_register_gsi(irq,
+			trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE,
+			polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH);
+	}
 }
-- 
1.6.0.6

[PATCH 13/17] xen: initialize irq 0 too

[Jeremy Fitzhardinge]

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

IRQ 0 is valid, so make sure it gets initialized properly too.
(Though in practice it doesn't matter, because its the timer
interrupt we don't use.)

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/pci.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index f55532d..502ff5f 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -52,7 +52,7 @@ int xen_register_gsi(u32 gsi, int triggering, int polarity)
 
 	printk(KERN_DEBUG "xen: --> irq=%d\n", irq);
 
-	if (irq > 0)
+	if (irq >= 0)
 		xen_set_io_apic_routing(irq,
 					triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
 					polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
-- 
1.6.0.6

[PATCH 14/17] xen: dynamically allocate irq & event structures

[Jeremy Fitzhardinge]

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

Impact: reduce memory usage

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>.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 drivers/xen/events.c |   15 +++++++++------
 1 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 3cf0a1b..e8f08c0 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/bootmem.h>
+#include <linux/irqnr.h>
 
 #include <asm/ptrace.h>
 #include <asm/irq.h>
@@ -91,11 +92,9 @@ 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];
 };
@@ -509,7 +508,7 @@ 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)
@@ -1174,7 +1173,11 @@ void __init xen_init_IRQ(void)
 	size_t size = nr_cpu_ids * sizeof(struct cpu_evtchn_s);
 
 	cpu_evtchn_mask_p = alloc_bootmem(size);
-	BUG_ON(cpu_evtchn_mask_p == NULL);
+	irq_info = alloc_bootmem(nr_irqs * sizeof(*irq_info));
+
+	evtchn_to_irq = alloc_bootmem(NR_EVENT_CHANNELS * sizeof(*evtchn_to_irq));
+	for(i = 0; i < NR_EVENT_CHANNELS; i++)
+		evtchn_to_irq[i] = -1;
 
 	init_evtchn_cpu_bindings();
 
-- 
1.6.0.6

[PATCH 15/17] xen: set pirq name to something useful.

[Jeremy Fitzhardinge]

From: Gerd Hoffmann <kraxel@xeni.home.kraxel.org>

Signed-off-by: Gerd Hoffmann <kraxel@xeni.home.kraxel.org>
---
 arch/x86/xen/pci.c   |    3 ++-
 drivers/xen/events.c |    4 ++--
 include/xen/events.h |    2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index 502ff5f..fb3ada9 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -48,7 +48,8 @@ int xen_register_gsi(u32 gsi, int triggering, int polarity)
 	printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n",
 	       gsi, triggering, polarity);
 
-	irq = xen_allocate_pirq(gsi);
+	irq = xen_allocate_pirq(gsi, (triggering == ACPI_EDGE_SENSITIVE)
+				     ? "ioapic-edge" : "ioapic-level");
 
 	printk(KERN_DEBUG "xen: --> irq=%d\n", irq);
 
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index e8f08c0..52e5208 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -526,7 +526,7 @@ 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;
@@ -548,7 +548,7 @@ 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 6fe4863..4b19b9c 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -61,7 +61,7 @@ unsigned irq_from_evtchn(unsigned int evtchn);
 /* 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);
-- 
1.6.0.6

[PATCH 16/17] xen: fix legacy irq setup, make ioapic-less machines work.

[Jeremy Fitzhardinge]

From: Gerd Hoffmann <kraxel@xeni.home.kraxel.org>

Signed-off-by: Gerd Hoffmann <kraxel@xeni.home.kraxel.org>
---
 arch/x86/xen/pci.c |    6 ++++++
 1 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index fb3ada9..69b475b 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -65,6 +65,12 @@ void __init xen_setup_pirqs(void)
 {
 	int irq;
 
+	if (0 == nr_ioapics) {
+		for (irq=0; irq < NR_IRQS_LEGACY; irq++)
+			xen_allocate_pirq(irq, "xt-pic");
+		return;
+	}
+
 	/* Pre-allocate legacy irqs */
 	for (irq=0; irq < NR_IRQS_LEGACY; irq++) {
 		int trigger, polarity;
-- 
1.6.0.6

[PATCH 17/17] xen: disable MSI

[Jeremy Fitzhardinge]

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

Disable MSI until we support it properly.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/apic.c |    3 +++
 drivers/pci/pci.h   |    2 --
 include/linux/pci.h |    6 ++++++
 3 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index e9d9ea7..3f890c4 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 #include <linux/threads.h>
 #include <linux/bitmap.h>
+#include <linux/pci.h>
 
 #include <asm/io_apic.h>
 #include <asm/acpi.h>
@@ -47,6 +48,8 @@ void xen_init_apic(void)
 	if (!xen_initial_domain())
 		return;
 
+	pci_no_msi();
+
 #ifdef CONFIG_ACPI
 	/*
 	 * Pretend ACPI found our lapic even though we've disabled it,
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 07c0aa5..ac1d4ca 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -110,10 +110,8 @@ extern struct rw_semaphore pci_bus_sem;
 extern unsigned int pci_pm_d3_delay;
 
 #ifdef CONFIG_PCI_MSI
-void pci_no_msi(void);
 extern void pci_msi_init_pci_dev(struct pci_dev *dev);
 #else
-static inline void pci_no_msi(void) { }
 static inline void pci_msi_init_pci_dev(struct pci_dev *dev) { }
 #endif
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 3085ea4..e2bcd27 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1197,5 +1197,11 @@ int pci_ext_cfg_avail(struct pci_dev *dev);
 
 void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
 
+#ifdef CONFIG_PCI_MSI
+void pci_no_msi(void);
+#else
+static inline void pci_no_msi(void) { }
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* LINUX_PCI_H */
-- 
1.6.0.6

[PATCH 12/17] xen: use acpi_get_override_irq() to get triggering for legacy irqs

[Jeremy Fitzhardinge]

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

We need to set up proper IO apic entries for legacy irqs, which are
not normally configured by either normal acpi interrupt routing or
PNP.

This also generalizes the acpi interrupt setup, so we can remove it
as a special case.

[ Impact: compatibility with legacy/ISA hardware ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/pci.c |   24 ++++++++++--------------
 1 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index 00ad6df..db0c74c 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -65,19 +65,15 @@ void __init xen_setup_pirqs(void)
 {
 	int irq;
 
-#ifdef CONFIG_ACPI
-	/*
-	 * Set up acpi interrupt in acpi_gbl_FADT.sci_interrupt.
-	 */
-	if (acpi_gbl_FADT.sci_interrupt > 0) {
-		irq = xen_allocate_pirq(acpi_gbl_FADT.sci_interrupt);
-
-		printk(KERN_INFO "xen: allocated irq %d for acpi %d\n",
-		       irq, acpi_gbl_FADT.sci_interrupt);
-	}
-#endif
-
 	/* Pre-allocate legacy irqs */
-	for (irq = 0; irq < NR_IRQS_LEGACY; irq++)
-		xen_allocate_pirq(irq);
+	for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
+		int trigger, polarity;
+
+		if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
+			continue;
+
+		xen_register_gsi(irq,
+			trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE,
+			polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH);
+	}
 }
-- 
1.6.0.6

[PATCH 12/17] xen: use acpi_get_override_irq() to get triggering for legacy irqs

[Jeremy Fitzhardinge]

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

We need to set up proper IO apic entries for legacy irqs, which are
not normally configured by either normal acpi interrupt routing or
PNP.

This also generalizes the acpi interrupt setup, so we can remove it
as a special case.

[ Impact: compatibility with legacy/ISA hardware ]

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/pci.c |   24 ++++++++++--------------
 1 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/arch/x86/xen/pci.c b/arch/x86/xen/pci.c
index 00ad6df..db0c74c 100644
--- a/arch/x86/xen/pci.c
+++ b/arch/x86/xen/pci.c
@@ -65,19 +65,15 @@ void __init xen_setup_pirqs(void)
 {
 	int irq;
 
-#ifdef CONFIG_ACPI
-	/*
-	 * Set up acpi interrupt in acpi_gbl_FADT.sci_interrupt.
-	 */
-	if (acpi_gbl_FADT.sci_interrupt > 0) {
-		irq = xen_allocate_pirq(acpi_gbl_FADT.sci_interrupt);
-
-		printk(KERN_INFO "xen: allocated irq %d for acpi %d\n",
-		       irq, acpi_gbl_FADT.sci_interrupt);
-	}
-#endif
-
 	/* Pre-allocate legacy irqs */
-	for (irq = 0; irq < NR_IRQS_LEGACY; irq++)
-		xen_allocate_pirq(irq);
+	for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
+		int trigger, polarity;
+
+		if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
+			continue;
+
+		xen_register_gsi(irq,
+			trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE,
+			polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH);
+	}
 }
-- 
1.6.0.6