76acc41fb7
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.
173 lines
5.5 KiB
C
173 lines
5.5 KiB
C
/******************************************************************************
|
|
* gnttab.h
|
|
*
|
|
* Two sets of functionality:
|
|
* 1. Granting foreign access to our memory reservation.
|
|
* 2. Accessing others' memory reservations via grant references.
|
|
* (i.e., mechanisms for both sender and recipient of grant references)
|
|
*
|
|
* Copyright (c) 2004-2005, K A Fraser
|
|
* Copyright (c) 2005, Christopher Clark
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License version 2
|
|
* as published by the Free Software Foundation; or, when distributed
|
|
* separately from the Linux kernel or incorporated into other
|
|
* software packages, subject to the following license:
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
* of this source file (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.
|
|
*/
|
|
|
|
#ifndef __ASM_GNTTAB_H__
|
|
|
|
#include <xen/xen-os.h>
|
|
#include <xen/hypervisor.h>
|
|
#include <xen/features.h>
|
|
|
|
#include <xen/interface/grant_table.h>
|
|
|
|
#define GNTTAB_LIST_END GRANT_REF_INVALID
|
|
|
|
struct gnttab_free_callback {
|
|
struct gnttab_free_callback *next;
|
|
void (*fn)(void *);
|
|
void *arg;
|
|
uint16_t count;
|
|
};
|
|
|
|
int gnttab_init(void);
|
|
|
|
/*
|
|
* Allocate a grant table reference and return it in *result. Returns
|
|
* zero on success or errno on error.
|
|
*/
|
|
int gnttab_grant_foreign_access(domid_t domid, unsigned long frame,
|
|
int flags, grant_ref_t *result);
|
|
|
|
/*
|
|
* End access through the given grant reference, iff the grant entry is no
|
|
* longer in use. Return 1 if the grant entry was freed, 0 if it is still in
|
|
* use.
|
|
*/
|
|
int gnttab_end_foreign_access_ref(grant_ref_t ref);
|
|
|
|
/*
|
|
* Eventually end access through the given grant reference, and once that
|
|
* access has been ended, free the given page too. Access will be ended
|
|
* immediately iff the grant entry is not in use, otherwise it will happen
|
|
* some time later. page may be 0, in which case no freeing will occur.
|
|
*/
|
|
void gnttab_end_foreign_access(grant_ref_t ref, void *page);
|
|
|
|
/*
|
|
* Eventually end access through the given array of grant references.
|
|
* Access will be ended immediately iff the grant entry is not in use,
|
|
* otherwise it will happen some time later
|
|
*/
|
|
void gnttab_end_foreign_access_references(u_int count, grant_ref_t *refs);
|
|
|
|
int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn, grant_ref_t *result);
|
|
|
|
unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref);
|
|
unsigned long gnttab_end_foreign_transfer(grant_ref_t ref);
|
|
|
|
int gnttab_query_foreign_access(grant_ref_t ref);
|
|
|
|
/*
|
|
* operations on reserved batches of grant references
|
|
*/
|
|
int gnttab_alloc_grant_references(uint16_t count, grant_ref_t *pprivate_head);
|
|
|
|
void gnttab_free_grant_reference(grant_ref_t ref);
|
|
|
|
void gnttab_free_grant_references(grant_ref_t head);
|
|
|
|
int gnttab_empty_grant_references(const grant_ref_t *pprivate_head);
|
|
|
|
int gnttab_claim_grant_reference(grant_ref_t *pprivate_head);
|
|
|
|
void gnttab_release_grant_reference(grant_ref_t *private_head,
|
|
grant_ref_t release);
|
|
|
|
void gnttab_request_free_callback(struct gnttab_free_callback *callback,
|
|
void (*fn)(void *), void *arg, uint16_t count);
|
|
void gnttab_cancel_free_callback(struct gnttab_free_callback *callback);
|
|
|
|
void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid,
|
|
unsigned long frame, int flags);
|
|
|
|
void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid,
|
|
unsigned long pfn);
|
|
|
|
int gnttab_suspend(void);
|
|
int gnttab_resume(void);
|
|
|
|
#if 0
|
|
|
|
#include <xen/features.h>
|
|
|
|
static inline void
|
|
gnttab_set_map_op(struct gnttab_map_grant_ref *map, vm_paddr_t addr,
|
|
uint32_t flags, grant_ref_t ref, domid_t domid)
|
|
{
|
|
if (flags & GNTMAP_contains_pte)
|
|
map->host_addr = addr;
|
|
else if (xen_feature(XENFEAT_auto_translated_physmap))
|
|
map->host_addr = vtophys(addr);
|
|
else
|
|
map->host_addr = addr;
|
|
|
|
map->flags = flags;
|
|
map->ref = ref;
|
|
map->dom = domid;
|
|
}
|
|
|
|
static inline void
|
|
gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, vm_paddr_t addr,
|
|
uint32_t flags, grant_handle_t handle)
|
|
{
|
|
if (flags & GNTMAP_contains_pte)
|
|
unmap->host_addr = addr;
|
|
else if (xen_feature(XENFEAT_auto_translated_physmap))
|
|
unmap->host_addr = vtophys(addr);
|
|
else
|
|
unmap->host_addr = addr;
|
|
|
|
unmap->handle = handle;
|
|
unmap->dev_bus_addr = 0;
|
|
}
|
|
|
|
static inline void
|
|
gnttab_set_replace_op(struct gnttab_unmap_and_replace *unmap, vm_paddr_t addr,
|
|
vm_paddr_t new_addr, grant_handle_t handle)
|
|
{
|
|
if (xen_feature(XENFEAT_auto_translated_physmap)) {
|
|
unmap->host_addr = vtophys(addr);
|
|
unmap->new_addr = vtophys(new_addr);
|
|
} else {
|
|
unmap->host_addr = addr;
|
|
unmap->new_addr = new_addr;
|
|
}
|
|
|
|
unmap->handle = handle;
|
|
}
|
|
#endif
|
|
|
|
#endif /* __ASM_GNTTAB_H__ */
|