Implement vector callback for PVHVM and unify event channel implementations

Re-structure Xen HVM support so that:
	- Xen is detected and hypercalls can be performed very
	  early in system startup.
	- Xen interrupt services are implemented using FreeBSD's native
	  interrupt delivery infrastructure.
	- the Xen interrupt service implementation is shared between PV
	  and HVM guests.
	- Xen interrupt handlers can optionally use a filter handler
	  in order to avoid the overhead of dispatch to an interrupt
	  thread.
	- interrupt load can be distributed among all available CPUs.
	- the overhead of accessing the emulated local and I/O apics
	  on HVM is removed for event channel port events.
	- a similar optimization can eventually, and fairly easily,
	  be used to optimize MSI.

Early Xen detection, HVM refactoring, PVHVM interrupt infrastructure,
and misc Xen cleanups:

Sponsored by: Spectra Logic Corporation

Unification of PV & HVM interrupt infrastructure, bug fixes,
and misc Xen cleanups:

Submitted by: Roger Pau Monné
Sponsored by: Citrix Systems R&D

sys/x86/x86/local_apic.c:
sys/amd64/include/apicvar.h:
sys/i386/include/apicvar.h:
sys/amd64/amd64/apic_vector.S:
sys/i386/i386/apic_vector.s:
sys/amd64/amd64/machdep.c:
sys/i386/i386/machdep.c:
sys/i386/xen/exception.s:
sys/x86/include/segments.h:
	Reserve IDT vector 0x93 for the Xen event channel upcall
	interrupt handler.  On Hypervisors that support the direct
	vector callback feature, we can request that this vector be
	called directly by an injected HVM interrupt event, instead
	of a simulated PCI interrupt on the Xen platform PCI device.
	This avoids all of the overhead of dealing with the emulated
	I/O APIC and local APIC.  It also means that the Hypervisor
	can inject these events on any CPU, allowing upcalls for
	different ports to be handled in parallel.

sys/amd64/amd64/mp_machdep.c:
sys/i386/i386/mp_machdep.c:
	Map Xen per-vcpu area during AP startup.

sys/amd64/include/intr_machdep.h:
sys/i386/include/intr_machdep.h:
	Increase the FreeBSD IRQ vector table to include space
	for event channel interrupt sources.

sys/amd64/include/pcpu.h:
sys/i386/include/pcpu.h:
	Remove Xen HVM per-cpu variable data.  These fields are now
	allocated via the dynamic per-cpu scheme.  See xen_intr.c
	for details.

sys/amd64/include/xen/hypercall.h:
sys/dev/xen/blkback/blkback.c:
sys/i386/include/xen/xenvar.h:
sys/i386/xen/clock.c:
sys/i386/xen/xen_machdep.c:
sys/xen/gnttab.c:
	Prefer FreeBSD primatives to Linux ones in Xen support code.

sys/amd64/include/xen/xen-os.h:
sys/i386/include/xen/xen-os.h:
sys/xen/xen-os.h:
sys/dev/xen/balloon/balloon.c:
sys/dev/xen/blkback/blkback.c:
sys/dev/xen/blkfront/blkfront.c:
sys/dev/xen/console/xencons_ring.c:
sys/dev/xen/control/control.c:
sys/dev/xen/netback/netback.c:
sys/dev/xen/netfront/netfront.c:
sys/dev/xen/xenpci/xenpci.c:
sys/i386/i386/machdep.c:
sys/i386/include/pmap.h:
sys/i386/include/xen/xenfunc.h:
sys/i386/isa/npx.c:
sys/i386/xen/clock.c:
sys/i386/xen/mp_machdep.c:
sys/i386/xen/mptable.c:
sys/i386/xen/xen_clock_util.c:
sys/i386/xen/xen_machdep.c:
sys/i386/xen/xen_rtc.c:
sys/xen/evtchn/evtchn_dev.c:
sys/xen/features.c:
sys/xen/gnttab.c:
sys/xen/gnttab.h:
sys/xen/hvm.h:
sys/xen/xenbus/xenbus.c:
sys/xen/xenbus/xenbus_if.m:
sys/xen/xenbus/xenbusb_front.c:
sys/xen/xenbus/xenbusvar.h:
sys/xen/xenstore/xenstore.c:
sys/xen/xenstore/xenstore_dev.c:
sys/xen/xenstore/xenstorevar.h:
	Pull common Xen OS support functions/settings into xen/xen-os.h.

sys/amd64/include/xen/xen-os.h:
sys/i386/include/xen/xen-os.h:
sys/xen/xen-os.h:
	Remove constants, macros, and functions unused in FreeBSD's Xen
	support.

sys/xen/xen-os.h:
sys/i386/xen/xen_machdep.c:
sys/x86/xen/hvm.c:
	Introduce new functions xen_domain(), xen_pv_domain(), and
	xen_hvm_domain().  These are used in favor of #ifdefs so that
	FreeBSD can dynamically detect and adapt to the presence of
	a hypervisor.  The goal is to have an HVM optimized GENERIC,
	but more is necessary before this is possible.

sys/amd64/amd64/machdep.c:
sys/dev/xen/xenpci/xenpcivar.h:
sys/dev/xen/xenpci/xenpci.c:
sys/x86/xen/hvm.c:
sys/sys/kernel.h:
	Refactor magic ioport, Hypercall table and Hypervisor shared
	information page setup, and move it to a dedicated HVM support
	module.

	HVM mode initialization is now triggered during the
	SI_SUB_HYPERVISOR phase of system startup.  This currently
	occurs just after the kernel VM is fully setup which is
	just enough infrastructure to allow the hypercall table
	and shared info page to be properly mapped.

sys/xen/hvm.h:
sys/x86/xen/hvm.c:
	Add definitions and a method for configuring Hypervisor event
	delievery via a direct vector callback.

sys/amd64/include/xen/xen-os.h:
sys/x86/xen/hvm.c:

sys/conf/files:
sys/conf/files.amd64:
sys/conf/files.i386:
	Adjust kernel build to reflect the refactoring of early
	Xen startup code and Xen interrupt services.

sys/dev/xen/blkback/blkback.c:
sys/dev/xen/blkfront/blkfront.c:
sys/dev/xen/blkfront/block.h:
sys/dev/xen/control/control.c:
sys/dev/xen/evtchn/evtchn_dev.c:
sys/dev/xen/netback/netback.c:
sys/dev/xen/netfront/netfront.c:
sys/xen/xenstore/xenstore.c:
sys/xen/evtchn/evtchn_dev.c:
sys/dev/xen/console/console.c:
sys/dev/xen/console/xencons_ring.c
	Adjust drivers to use new xen_intr_*() API.

sys/dev/xen/blkback/blkback.c:
	Since blkback defers all event handling to a taskqueue,
	convert this task queue to a "fast" taskqueue, and schedule
	it via an interrupt filter.  This avoids an unnecessary
	ithread context switch.

sys/xen/xenstore/xenstore.c:
	The xenstore driver is MPSAFE.  Indicate as much when
	registering its interrupt handler.

sys/xen/xenbus/xenbus.c:
sys/xen/xenbus/xenbusvar.h:
	Remove unused event channel APIs.

sys/xen/evtchn.h:
	Remove all kernel Xen interrupt service API definitions
	from this file.  It is now only used for structure and
	ioctl definitions related to the event channel userland
	device driver.

	Update the definitions in this file to match those from
	NetBSD.  Implementing this interface will be necessary for
	Dom0 support.

sys/xen/evtchn/evtchnvar.h:
	Add a header file for implemenation internal APIs related
	to managing event channels event delivery.  This is used
	to allow, for example, the event channel userland device
	driver to access low-level routines that typical kernel
	consumers of event channel services should never access.

sys/xen/interface/event_channel.h:
sys/xen/xen_intr.h:
	Standardize on the evtchn_port_t type for referring to
	an event channel port id.  In order to prevent low-level
	event channel APIs from leaking to kernel consumers who
	should not have access to this data, the type is defined
	twice: Once in the Xen provided event_channel.h, and again
	in xen/xen_intr.h.  The double declaration is protected by
	__XEN_EVTCHN_PORT_DEFINED__ to ensure it is never declared
	twice within a given compilation unit.

sys/xen/xen_intr.h:
sys/xen/evtchn/evtchn.c:
sys/x86/xen/xen_intr.c:
sys/dev/xen/xenpci/evtchn.c:
sys/dev/xen/xenpci/xenpcivar.h:
	New implementation of Xen interrupt services.  This is
	similar in many respects to the i386 PV implementation with
	the exception that events for bound to event channel ports
	(i.e. not IPI, virtual IRQ, or physical IRQ) are further
	optimized to avoid mask/unmask operations that aren't
	necessary for these edge triggered events.

	Stubs exist for supporting physical IRQ binding, but will
	need additional work before this implementation can be
	fully shared between PV and HVM.

sys/amd64/amd64/mp_machdep.c:
sys/i386/i386/mp_machdep.c:
sys/i386/xen/mp_machdep.c
sys/x86/xen/hvm.c:
	Add support for placing vcpu_info into an arbritary memory
	page instead of using HYPERVISOR_shared_info->vcpu_info.
	This allows the creation of domains with more than 32 vcpus.

sys/i386/i386/machdep.c:
sys/i386/xen/clock.c:
sys/i386/xen/xen_machdep.c:
sys/i386/xen/exception.s:
	Add support for new event channle implementation.

1 files changed, 256 insertions, 0 deletions

diff --git a/sys/x86/xen/hvm.c b/sys/x86/xen/hvm.c
new file mode 100644
index 0000000..0730d94
--- /dev/null
+++ b/sys/x86/xen/hvm.c
@@ -0,0 +1,256 @@
+/*
+ * Copyright (c) 2008 Citrix Systems, Inc.
+ * Copyright (c) 2012 Spectra Logic Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD$");
+
+#include <sys/param.h>
+#include <sys/bus.h>
+#include <sys/kernel.h>
+#include <sys/malloc.h>
+#include <sys/proc.h>
+
+#include <dev/pci/pcivar.h>
+#include <machine/cpufunc.h>
+
+#include <xen/xen-os.h>
+#include <xen/features.h>
+#include <xen/gnttab.h>
+#include <xen/hypervisor.h>
+#include <xen/hvm.h>
+#include <xen/xen_intr.h>
+
+#include <vm/vm.h>
+#include <vm/pmap.h>
+
+#include <xen/interface/hvm/params.h>
+#include <xen/interface/vcpu.h>
+
+static MALLOC_DEFINE(M_XENHVM, "xen_hvm", "Xen HVM PV Support");
+
+DPCPU_DEFINE(struct vcpu_info, vcpu_local_info);
+DPCPU_DEFINE(struct vcpu_info *, vcpu_info);
+
+/*-------------------------------- Global Data -------------------------------*/
+/**
+ * If non-zero, the hypervisor has been configured to use a direct
+ * IDT event callback for interrupt injection.
+ */
+int xen_vector_callback_enabled;
+
+/*------------------ Hypervisor Access Shared Memory Regions -----------------*/
+/** Hypercall table accessed via HYPERVISOR_*_op() methods. */
+char *hypercall_stubs;
+shared_info_t *HYPERVISOR_shared_info;
+enum xen_domain_type xen_domain_type = XEN_NATIVE;
+
+static uint32_t
+xen_hvm_cpuid_base(void)
+{
+	uint32_t base, regs[4];
+
+	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+		do_cpuid(base, regs);
+		if (!memcmp("XenVMMXenVMM", &regs[1], 12)
+		    && (regs[0] - base) >= 2)
+			return (base);
+	}
+	return (0);
+}
+
+/*
+ * Allocate and fill in the hypcall page.
+ */
+static int
+xen_hvm_init_hypercall_stubs(void)
+{
+	uint32_t base, regs[4];
+	int i;
+
+	base = xen_hvm_cpuid_base();
+	if (!base)
+		return (ENXIO);
+
+	if (hypercall_stubs == NULL) {
+		do_cpuid(base + 1, regs);
+		printf("XEN: Hypervisor version %d.%d detected.\n",
+		    regs[0] >> 16, regs[0] & 0xffff);
+	}
+
+	/*
+	 * Find the hypercall pages.
+	 */
+	do_cpuid(base + 2, regs);
+	
+	if (hypercall_stubs == NULL) {
+		size_t call_region_size;
+
+		call_region_size = regs[0] * PAGE_SIZE;
+		hypercall_stubs = malloc(call_region_size, M_XENHVM, M_NOWAIT);
+		if (hypercall_stubs == NULL)
+			panic("Unable to allocate Xen hypercall region");
+	}
+
+	for (i = 0; i < regs[0]; i++)
+		wrmsr(regs[1], vtophys(hypercall_stubs + i * PAGE_SIZE) + i);
+
+	return (0);
+}
+
+static void
+xen_hvm_init_shared_info_page(void)
+{
+	struct xen_add_to_physmap xatp;
+
+	if (HYPERVISOR_shared_info == NULL) {
+		HYPERVISOR_shared_info = malloc(PAGE_SIZE, M_XENHVM, M_NOWAIT);
+		if (HYPERVISOR_shared_info == NULL)
+			panic("Unable to allocate Xen shared info page");
+	}
+
+	xatp.domid = DOMID_SELF;
+	xatp.idx = 0;
+	xatp.space = XENMAPSPACE_shared_info;
+	xatp.gpfn = vtophys(HYPERVISOR_shared_info) >> PAGE_SHIFT;
+	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
+		panic("HYPERVISOR_memory_op failed");
+}
+
+/*
+ * Tell the hypervisor how to contact us for event channel callbacks.
+ */
+void
+xen_hvm_set_callback(device_t dev)
+{
+	struct xen_hvm_param xhp;
+	int irq;
+
+	xhp.domid = DOMID_SELF;
+	xhp.index = HVM_PARAM_CALLBACK_IRQ;
+	if (xen_feature(XENFEAT_hvm_callback_vector)) {
+		int error;
+
+		xhp.value = HVM_CALLBACK_VECTOR(IDT_EVTCHN);
+		error = HYPERVISOR_hvm_op(HVMOP_set_param, &xhp);
+		if (error == 0) {
+			xen_vector_callback_enabled = 1;
+			return;
+		}
+		printf("Xen HVM callback vector registration failed (%d). "
+		       "Falling back to emulated device interrupt\n",
+		       error);
+	}
+	xen_vector_callback_enabled = 0;
+	if (dev == NULL) {
+		/*
+		 * Called from early boot or resume.
+		 * xenpci will invoke us again later.
+		 */
+		return;
+	}
+
+	irq = pci_get_irq(dev);
+	if (irq < 16) {
+		xhp.value = HVM_CALLBACK_GSI(irq);
+	} else {
+		u_int slot;
+		u_int pin;
+
+		slot = pci_get_slot(dev);
+		pin = pci_get_intpin(dev) - 1;
+		xhp.value = HVM_CALLBACK_PCI_INTX(slot, pin);
+	}
+
+	if (HYPERVISOR_hvm_op(HVMOP_set_param, &xhp))
+		panic("Can't set evtchn callback");
+}
+
+#define	XEN_MAGIC_IOPORT 0x10
+enum {
+	XMI_MAGIC			 = 0x49d2,
+	XMI_UNPLUG_IDE_DISKS		 = 0x01,
+	XMI_UNPLUG_NICS			 = 0x02,
+	XMI_UNPLUG_IDE_EXCEPT_PRI_MASTER = 0x04
+};
+
+static void
+xen_hvm_disable_emulated_devices(void)
+{
+	if (inw(XEN_MAGIC_IOPORT) != XMI_MAGIC)
+		return;
+
+	if (bootverbose)
+		printf("XEN: Disabling emulated block and network devices\n");
+	outw(XEN_MAGIC_IOPORT, XMI_UNPLUG_IDE_DISKS|XMI_UNPLUG_NICS);
+}
+
+void
+xen_hvm_suspend(void)
+{
+}
+
+void
+xen_hvm_resume(void)
+{
+	xen_hvm_init_hypercall_stubs();
+	xen_hvm_init_shared_info_page();
+}
+ 
+static void
+xen_hvm_init(void *dummy __unused)
+{
+	if (xen_hvm_init_hypercall_stubs() != 0)
+		return;
+
+	xen_domain_type = XEN_HVM_DOMAIN;
+	setup_xen_features();
+	xen_hvm_init_shared_info_page();
+	xen_hvm_set_callback(NULL);
+	xen_hvm_disable_emulated_devices();
+} 
+
+void xen_hvm_init_cpu(void)
+{
+	int cpu = PCPU_GET(acpi_id);
+	struct vcpu_info *vcpu_info;
+	struct vcpu_register_vcpu_info info;
+	int rc;
+
+	vcpu_info = DPCPU_PTR(vcpu_local_info);
+	info.mfn = vtophys(vcpu_info) >> PAGE_SHIFT;
+	info.offset = vtophys(vcpu_info) - trunc_page(vtophys(vcpu_info));
+
+	rc = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
+	if (rc) {
+		DPCPU_SET(vcpu_info, &HYPERVISOR_shared_info->vcpu_info[cpu]);
+	} else {
+		DPCPU_SET(vcpu_info, vcpu_info);
+	}
+}
+
+SYSINIT(xen_hvm_init, SI_SUB_HYPERVISOR, SI_ORDER_FIRST, xen_hvm_init, NULL);
+SYSINIT(xen_hvm_init_cpu, SI_SUB_INTR, SI_ORDER_FIRST, xen_hvm_init_cpu, NULL);