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.
183 lines
6.2 KiB
C
183 lines
6.2 KiB
C
/*-
|
|
* Copyright (c) 2003 John Baldwin <jhb@FreeBSD.org>
|
|
* 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.
|
|
*
|
|
* $FreeBSD$
|
|
*/
|
|
|
|
#ifndef __MACHINE_INTR_MACHDEP_H__
|
|
#define __MACHINE_INTR_MACHDEP_H__
|
|
|
|
#ifdef _KERNEL
|
|
|
|
/*
|
|
* The maximum number of I/O interrupts we allow. This number is rather
|
|
* arbitrary as it is just the maximum IRQ resource value. The interrupt
|
|
* source for a given IRQ maps that I/O interrupt to device interrupt
|
|
* source whether it be a pin on an interrupt controller or an MSI interrupt.
|
|
* The 16 ISA IRQs are assigned fixed IDT vectors, but all other device
|
|
* interrupts allocate IDT vectors on demand. Currently we have 191 IDT
|
|
* vectors available for device interrupts. On many systems with I/O APICs,
|
|
* a lot of the IRQs are not used, so this number can be much larger than
|
|
* 191 and still be safe since only interrupt sources in actual use will
|
|
* allocate IDT vectors.
|
|
*
|
|
* The first 255 IRQs (0 - 254) are reserved for ISA IRQs and PCI intline IRQs.
|
|
* 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
|
|
#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.
|
|
*/
|
|
#define MSI_INTEL_ADDR_BASE 0xfee00000
|
|
|
|
/*
|
|
* - 1 ??? dummy counter.
|
|
* - 2 counters for each I/O interrupt.
|
|
* - 1 counter for each CPU for lapic timer.
|
|
* - 9 counters for each CPU for IPI counters for SMP.
|
|
*/
|
|
#ifdef SMP
|
|
#define INTRCNT_COUNT (1 + NUM_IO_INTS * 2 + (1 + 9) * MAXCPU)
|
|
#else
|
|
#define INTRCNT_COUNT (1 + NUM_IO_INTS * 2 + 1)
|
|
#endif
|
|
|
|
#ifndef LOCORE
|
|
|
|
typedef void inthand_t(u_int cs, u_int ef, u_int esp, u_int ss);
|
|
|
|
#define IDTVEC(name) __CONCAT(X,name)
|
|
|
|
struct intsrc;
|
|
|
|
/*
|
|
* Methods that a PIC provides to mask/unmask a given interrupt source,
|
|
* "turn on" the interrupt on the CPU side by setting up an IDT entry, and
|
|
* return the vector associated with this source.
|
|
*/
|
|
struct pic {
|
|
void (*pic_enable_source)(struct intsrc *);
|
|
void (*pic_disable_source)(struct intsrc *, int);
|
|
void (*pic_eoi_source)(struct intsrc *);
|
|
void (*pic_enable_intr)(struct intsrc *);
|
|
void (*pic_disable_intr)(struct intsrc *);
|
|
int (*pic_vector)(struct intsrc *);
|
|
int (*pic_source_pending)(struct intsrc *);
|
|
void (*pic_suspend)(struct pic *);
|
|
void (*pic_resume)(struct pic *);
|
|
int (*pic_config_intr)(struct intsrc *, enum intr_trigger,
|
|
enum intr_polarity);
|
|
int (*pic_assign_cpu)(struct intsrc *, u_int apic_id);
|
|
TAILQ_ENTRY(pic) pics;
|
|
};
|
|
|
|
/* Flags for pic_disable_source() */
|
|
enum {
|
|
PIC_EOI,
|
|
PIC_NO_EOI,
|
|
};
|
|
|
|
/*
|
|
* An interrupt source. The upper-layer code uses the PIC methods to
|
|
* control a given source. The lower-layer PIC drivers can store additional
|
|
* private data in a given interrupt source such as an interrupt pin number
|
|
* or an I/O APIC pointer.
|
|
*/
|
|
struct intsrc {
|
|
struct pic *is_pic;
|
|
struct intr_event *is_event;
|
|
u_long *is_count;
|
|
u_long *is_straycount;
|
|
u_int is_index;
|
|
u_int is_handlers;
|
|
};
|
|
|
|
struct trapframe;
|
|
|
|
extern struct mtx icu_lock;
|
|
extern int elcr_found;
|
|
|
|
#ifndef DEV_ATPIC
|
|
void atpic_reset(void);
|
|
#endif
|
|
/* XXX: The elcr_* prototypes probably belong somewhere else. */
|
|
int elcr_probe(void);
|
|
enum intr_trigger elcr_read_trigger(u_int irq);
|
|
void elcr_resume(void);
|
|
void elcr_write_trigger(u_int irq, enum intr_trigger trigger);
|
|
#ifdef SMP
|
|
void intr_add_cpu(u_int cpu);
|
|
#endif
|
|
int intr_add_handler(const char *name, int vector, driver_filter_t filter,
|
|
driver_intr_t handler, void *arg, enum intr_type flags, void **cookiep);
|
|
#ifdef SMP
|
|
int intr_bind(u_int vector, u_char cpu);
|
|
#endif
|
|
int intr_config_intr(int vector, enum intr_trigger trig,
|
|
enum intr_polarity pol);
|
|
int intr_describe(u_int vector, void *ih, const char *descr);
|
|
void intr_execute_handlers(struct intsrc *isrc, struct trapframe *frame);
|
|
u_int intr_next_cpu(void);
|
|
struct intsrc *intr_lookup_source(int vector);
|
|
int intr_register_pic(struct pic *pic);
|
|
int intr_register_source(struct intsrc *isrc);
|
|
int intr_remove_handler(void *cookie);
|
|
void intr_resume(void);
|
|
void intr_suspend(void);
|
|
void intrcnt_add(const char *name, u_long **countp);
|
|
void nexus_add_irq(u_long irq);
|
|
int msi_alloc(device_t dev, int count, int maxcount, int *irqs);
|
|
void msi_init(void);
|
|
int msi_map(int irq, uint64_t *addr, uint32_t *data);
|
|
int msi_release(int* irqs, int count);
|
|
int msix_alloc(device_t dev, int *irq);
|
|
int msix_release(int irq);
|
|
|
|
#endif /* !LOCORE */
|
|
#endif /* _KERNEL */
|
|
#endif /* !__MACHINE_INTR_MACHDEP_H__ */
|