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.

7 files changed, 80 insertions, 142 deletions

diff --git a/sys/i386/include/apicvar.h b/sys/i386/include/apicvar.h
index a0e622e..5d1f522 100644
--- a/sys/i386/include/apicvar.h
+++ b/sys/i386/include/apicvar.h
@@ -226,6 +226,7 @@ int	lapic_set_lvt_triggermode(u_int apic_id, u_int lvt,
 	    enum intr_trigger trigger);
 void	lapic_set_tpr(u_int vector);
 void	lapic_setup(int boot);
+void	xen_intr_handle_upcall(struct trapframe *frame);
 
 #endif /* !LOCORE */
 #endif /* _MACHINE_APICVAR_H_ */
diff --git a/sys/i386/include/intr_machdep.h b/sys/i386/include/intr_machdep.h
index b3dd122..6bbe378 100644
--- a/sys/i386/include/intr_machdep.h
+++ b/sys/i386/include/intr_machdep.h
@@ -44,12 +44,30 @@
  * allocate IDT vectors.
  *
  * The first 255 IRQs (0 - 254) are reserved for ISA IRQs and PCI intline IRQs.
- * IRQ values beyond 256 are used by MSI.  We leave 255 unused to avoid
- * confusion since 255 is used in PCI to indicate an invalid IRQ.
+ * IRQ values from 256 to 767 are used by MSI.  When running under the Xen
+ * Hypervisor, IRQ values from 768 to 4863 are available for binding to
+ * event channel events.  We leave 255 unused to avoid confusion since 255 is
+ * used in PCI to indicate an invalid IRQ.
  */
 #define	NUM_MSI_INTS	512
 #define	FIRST_MSI_INT	256
-#define	NUM_IO_INTS	(FIRST_MSI_INT + NUM_MSI_INTS)
+#ifdef XENHVM
+#include <xen/xen-os.h>
+#define	NUM_EVTCHN_INTS	NR_EVENT_CHANNELS
+#define	FIRST_EVTCHN_INT \
+    (FIRST_MSI_INT + NUM_MSI_INTS)
+#define	LAST_EVTCHN_INT \
+    (FIRST_EVTCHN_INT + NUM_EVTCHN_INTS - 1)
+#elif defined(XEN)
+#include <xen/xen-os.h>
+#define	NUM_EVTCHN_INTS	NR_EVENT_CHANNELS
+#define	FIRST_EVTCHN_INT 0
+#define	LAST_EVTCHN_INT \
+    (FIRST_EVTCHN_INT + NUM_EVTCHN_INTS - 1)
+#else /* !XEN && !XENHVM */
+#define	NUM_EVTCHN_INTS	0
+#endif
+#define	NUM_IO_INTS	(FIRST_MSI_INT + NUM_MSI_INTS + NUM_EVTCHN_INTS)
 
 /*
  * Default base address for MSI messages on x86 platforms.
diff --git a/sys/i386/include/pcpu.h b/sys/i386/include/pcpu.h
index 3606d12..3a684bf 100644
--- a/sys/i386/include/pcpu.h
+++ b/sys/i386/include/pcpu.h
@@ -71,21 +71,9 @@ struct shadow_time_info {
 	vm_paddr_t *pc_pdir_shadow;					\
 	uint64_t pc_processed_system_time;				\
 	struct shadow_time_info pc_shadow_time;				\
-	int	pc_resched_irq;						\
-	int	pc_callfunc_irq;					\
-	int	pc_virq_to_irq[NR_VIRQS];				\
-	int	pc_ipi_to_irq[NR_IPIS];					\
-	char	__pad[77]
+	char	__pad[189]
 
-#elif defined(XENHVM)
-
-#define	PCPU_XEN_FIELDS							\
-	;								\
-	unsigned int pc_last_processed_l1i;				\
-	unsigned int pc_last_processed_l2i;				\
-	char	__pad[229]
-
-#else /* !XEN && !XENHVM */
+#else /* !XEN */
 
 #define PCPU_XEN_FIELDS							\
 	;								\
diff --git a/sys/i386/include/pmap.h b/sys/i386/include/pmap.h
index 94b63ca..0303c60 100644
--- a/sys/i386/include/pmap.h
+++ b/sys/i386/include/pmap.h
@@ -213,7 +213,9 @@ extern pd_entry_t *IdlePTD;	/* physical address of "Idle" state directory */
 
 #if defined(XEN)
 #include <sys/param.h>
-#include <machine/xen/xen-os.h>
+
+#include <xen/xen-os.h>
+
 #include <machine/xen/xenvar.h>
 #include <machine/xen/xenpmap.h>
 
diff --git a/sys/i386/include/xen/xen-os.h b/sys/i386/include/xen/xen-os.h
index 257202e..e15d668 100644
--- a/sys/i386/include/xen/xen-os.h
+++ b/sys/i386/include/xen/xen-os.h
@@ -1,52 +1,64 @@
-/******************************************************************************
- * os.h
+/*****************************************************************************
+ * i386/xen/xen-os.h
  * 
- * random collection of macros and definition
+ * Random collection of macros and definition
+ *
+ * Copyright (c) 2003, 2004 Keir Fraser (on behalf of the Xen team)
+ * All rights reserved.
+ *
+ * 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.
+ *
+ * $FreeBSD$
  */
 
-#ifndef _XEN_OS_H_
-#define _XEN_OS_H_
-#include <machine/param.h>
+#ifndef _MACHINE_XEN_XEN_OS_H_
+#define _MACHINE_XEN_XEN_OS_H_
 
 #ifdef PAE
 #define CONFIG_X86_PAE
 #endif
 
-#ifdef LOCORE
-#define __ASSEMBLY__
-#endif
-
-#if !defined(__XEN_INTERFACE_VERSION__) 
-#define  __XEN_INTERFACE_VERSION__ 0x00030208
-#endif 
-
-#define GRANT_REF_INVALID   0xffffffff
-
-#include <xen/interface/xen.h>
-
 /* Everything below this point is not included by assembler (.S) files. */
 #ifndef __ASSEMBLY__
 
 /* Force a proper event-channel callback from Xen. */
 void force_evtchn_callback(void);
 
-#define likely(x)  __builtin_expect((x),1)
-#define unlikely(x)  __builtin_expect((x),0)
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+    __asm__ __volatile__ ( "rep;nop" : : : "memory" );
+}
+#define cpu_relax() rep_nop()
 
-#ifndef vtophys
-#include <vm/vm.h>
-#include <vm/vm_param.h>
-#include <vm/pmap.h>
-#endif
+#ifndef XENHVM
+void xc_printf(const char *fmt, ...);
 
-extern int gdtset;
 #ifdef SMP
+extern int gdtset;
+
 #include <sys/time.h> /* XXX for pcpu.h */
 #include <sys/pcpu.h> /* XXX for PCPU_GET */
 static inline int 
 smp_processor_id(void)  
 {
-    if (likely(gdtset))
+    if (__predict_true(gdtset))
 	return PCPU_GET(cpuid);
     return 0;
 }
@@ -55,50 +67,16 @@ smp_processor_id(void)
 #define smp_processor_id() 0
 #endif
 
-#ifndef NULL
-#define NULL (void *)0
-#endif
-
 #ifndef PANIC_IF
-#define PANIC_IF(exp) if (unlikely(exp)) {printk("panic - %s: %s:%d\n",#exp, __FILE__, __LINE__); panic("%s: %s:%d", #exp, __FILE__, __LINE__);} 
-#endif
-
-extern shared_info_t *HYPERVISOR_shared_info;
-
-/* Somewhere in the middle of the GCC 2.96 development cycle, we implemented
-   a mechanism by which the user can annotate likely branch directions and
-   expect the blocks to be reordered appropriately.  Define __builtin_expect
-   to nothing for earlier compilers.  */
-
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
-{
-    __asm__ __volatile__ ( "rep;nop" : : : "memory" );
-}
-#define cpu_relax() rep_nop()
-
-
-#if __GNUC__ == 2 && __GNUC_MINOR__ < 96
-#define __builtin_expect(x, expected_value) (x)
+#define PANIC_IF(exp) if (__predict_false(exp)) {printf("panic - %s: %s:%d\n",#exp, __FILE__, __LINE__); panic("%s: %s:%d", #exp, __FILE__, __LINE__);} 
 #endif
 
-#define per_cpu(var, cpu)           (pcpu_find((cpu))->pc_ ## var)
-
-/* crude memory allocator for memory allocation early in 
- *  boot
+/*
+ * Crude memory allocator for memory allocation early in boot.
  */
 void *bootmem_alloc(unsigned int size);
 void bootmem_free(void *ptr, unsigned int size);
 
-#include <sys/types.h>
-
-void printk(const char *fmt, ...);
-
-/* some function prototypes */
-void trap_init(void);
-
-#ifndef XENHVM
-
 /*
  * STI/CLI equivalents. These basically set and clear the virtual
  * event_enable flag in the shared_info structure. Note that when
@@ -106,7 +84,6 @@ void trap_init(void);
  * We may therefore call into do_hypervisor_callback() directly.
  */
 
-
 #define __cli()                                                         \
 do {                                                                    \
         vcpu_info_t *_vcpu;                                             \
@@ -122,7 +99,7 @@ do {                                                                    \
         _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
         _vcpu->evtchn_upcall_mask = 0;                                  \
         barrier(); /* unmask then check (avoid races) */                \
-        if ( unlikely(_vcpu->evtchn_upcall_pending) )                   \
+        if (__predict_false(_vcpu->evtchn_upcall_pending))              \
                 force_evtchn_callback();                                \
 } while (0)
 
@@ -133,7 +110,7 @@ do {                                                                    \
         _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \
         if ((_vcpu->evtchn_upcall_mask = (x)) == 0) {                   \
                 barrier(); /* unmask then check (avoid races) */        \
-                if ( unlikely(_vcpu->evtchn_upcall_pending) )           \
+                if (__predict_false(_vcpu->evtchn_upcall_pending))      \
                         force_evtchn_callback();                        \
         } 								\
 } while (0)
@@ -168,31 +145,7 @@ do {                                                                    \
 #define spin_lock_irqsave mtx_lock_irqsave
 #define spin_unlock_irqrestore mtx_unlock_irqrestore
 
-#endif
-
-#ifndef xen_mb
-#define xen_mb() mb()
-#endif
-#ifndef xen_rmb
-#define xen_rmb() rmb()
-#endif
-#ifndef xen_wmb
-#define xen_wmb() wmb()
-#endif
-#ifdef SMP
-#define smp_mb() mb() 
-#define smp_rmb() rmb()
-#define smp_wmb() wmb()
-#define smp_read_barrier_depends()      read_barrier_depends()
-#define set_mb(var, value) do { xchg(&var, value); } while (0)
-#else
-#define smp_mb()        barrier()
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#define smp_read_barrier_depends()      do { } while(0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
+#endif /* !XENHVM */
 
 /* This is a barrier for the compiler only, NOT the processor! */
 #define barrier() __asm__ __volatile__("": : :"memory")
@@ -207,8 +160,6 @@ do {                                                                    \
  */
 typedef struct { volatile int counter; } atomic_t;
 
-
-
 #define xen_xchg(ptr,v) \
         ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))
 struct __xchg_dummy { unsigned long a[100]; };
@@ -335,33 +286,6 @@ static __inline__ void atomic_inc(atomic_t *v)
 #define rdtscll(val) \
      __asm__ __volatile__("rdtsc" : "=A" (val))
 
-
-
-/*
- * Kernel pointers have redundant information, so we can use a
- * scheme where we can return either an error code or a dentry
- * pointer with the same return value.
- *
- * This should be a per-architecture thing, to allow different
- * error and pointer decisions.
- */
-#define IS_ERR_VALUE(x) unlikely((x) > (unsigned long)-1000L)
-
-static inline void *ERR_PTR(long error)
-{
-	return (void *) error;
-}
-
-static inline long PTR_ERR(const void *ptr)
-{
-	return (long) ptr;
-}
-
-static inline long IS_ERR(const void *ptr)
-{
-	return IS_ERR_VALUE((unsigned long)ptr);
-}
-
 #endif /* !__ASSEMBLY__ */
 
-#endif /* _OS_H_ */
+#endif /* _MACHINE_XEN_XEN_OS_H_ */
diff --git a/sys/i386/include/xen/xenfunc.h b/sys/i386/include/xen/xenfunc.h
index 47f0405..f02ee12 100644
--- a/sys/i386/include/xen/xenfunc.h
+++ b/sys/i386/include/xen/xenfunc.h
@@ -29,10 +29,14 @@
 #ifndef _XEN_XENFUNC_H_
 #define _XEN_XENFUNC_H_
 
-#include <machine/xen/xen-os.h>
+#include <xen/xen-os.h>
 #include <xen/hypervisor.h>
+
+#include <vm/pmap.h>
+
 #include <machine/xen/xenpmap.h>
 #include <machine/segments.h>
+
 #include <sys/pcpu.h>
 #define BKPT __asm__("int3");
 #define XPQ_CALL_DEPTH 5
diff --git a/sys/i386/include/xen/xenvar.h b/sys/i386/include/xen/xenvar.h
index b1a0a4d..2742613 100644
--- a/sys/i386/include/xen/xenvar.h
+++ b/sys/i386/include/xen/xenvar.h
@@ -37,7 +37,8 @@
 #define XPMAP   0x2
 extern int xendebug_flags;
 #ifndef NOXENDEBUG
-#define XENPRINTF printk
+/* Print directly to the Xen console during debugging. */
+#define XENPRINTF xc_printf
 #else
 #define XENPRINTF printf
 #endif