fcdbf70fd9
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.
298 lines
9.9 KiB
C
298 lines
9.9 KiB
C
/******************************************************************************
|
|
* event_channel.h
|
|
*
|
|
* Event channels between domains.
|
|
*
|
|
* 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.
|
|
*
|
|
* Copyright (c) 2003-2004, K A Fraser.
|
|
*/
|
|
|
|
#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__
|
|
#define __XEN_PUBLIC_EVENT_CHANNEL_H__
|
|
|
|
#include "xen.h"
|
|
|
|
/*
|
|
* `incontents 150 evtchn Event Channels
|
|
*
|
|
* Event channels are the basic primitive provided by Xen for event
|
|
* notifications. An event is the Xen equivalent of a hardware
|
|
* interrupt. They essentially store one bit of information, the event
|
|
* of interest is signalled by transitioning this bit from 0 to 1.
|
|
*
|
|
* Notifications are received by a guest via an upcall from Xen,
|
|
* indicating when an event arrives (setting the bit). Further
|
|
* notifications are masked until the bit is cleared again (therefore,
|
|
* guests must check the value of the bit after re-enabling event
|
|
* delivery to ensure no missed notifications).
|
|
*
|
|
* Event notifications can be masked by setting a flag; this is
|
|
* equivalent to disabling interrupts and can be used to ensure
|
|
* atomicity of certain operations in the guest kernel.
|
|
*
|
|
* Event channels are represented by the evtchn_* fields in
|
|
* struct shared_info and struct vcpu_info.
|
|
*/
|
|
|
|
/*
|
|
* ` enum neg_errnoval
|
|
* ` HYPERVISOR_event_channel_op(enum event_channel_op cmd, void *args)
|
|
* `
|
|
* @cmd == EVTCHNOP_* (event-channel operation).
|
|
* @args == struct evtchn_* Operation-specific extra arguments (NULL if none).
|
|
*/
|
|
|
|
/* ` enum event_channel_op { // EVTCHNOP_* => struct evtchn_* */
|
|
#define EVTCHNOP_bind_interdomain 0
|
|
#define EVTCHNOP_bind_virq 1
|
|
#define EVTCHNOP_bind_pirq 2
|
|
#define EVTCHNOP_close 3
|
|
#define EVTCHNOP_send 4
|
|
#define EVTCHNOP_status 5
|
|
#define EVTCHNOP_alloc_unbound 6
|
|
#define EVTCHNOP_bind_ipi 7
|
|
#define EVTCHNOP_bind_vcpu 8
|
|
#define EVTCHNOP_unmask 9
|
|
#define EVTCHNOP_reset 10
|
|
/* ` } */
|
|
|
|
#ifndef __XEN_EVTCHN_PORT_DEFINED__
|
|
typedef uint32_t evtchn_port_t;
|
|
DEFINE_XEN_GUEST_HANDLE(evtchn_port_t);
|
|
#define __XEN_EVTCHN_PORT_DEFINED__ 1
|
|
#endif
|
|
|
|
/*
|
|
* EVTCHNOP_alloc_unbound: Allocate a port in domain <dom> and mark as
|
|
* accepting interdomain bindings from domain <remote_dom>. A fresh port
|
|
* is allocated in <dom> and returned as <port>.
|
|
* NOTES:
|
|
* 1. If the caller is unprivileged then <dom> must be DOMID_SELF.
|
|
* 2. <rdom> may be DOMID_SELF, allowing loopback connections.
|
|
*/
|
|
struct evtchn_alloc_unbound {
|
|
/* IN parameters */
|
|
domid_t dom, remote_dom;
|
|
/* OUT parameters */
|
|
evtchn_port_t port;
|
|
};
|
|
typedef struct evtchn_alloc_unbound evtchn_alloc_unbound_t;
|
|
|
|
/*
|
|
* EVTCHNOP_bind_interdomain: Construct an interdomain event channel between
|
|
* the calling domain and <remote_dom>. <remote_dom,remote_port> must identify
|
|
* a port that is unbound and marked as accepting bindings from the calling
|
|
* domain. A fresh port is allocated in the calling domain and returned as
|
|
* <local_port>.
|
|
* NOTES:
|
|
* 1. <remote_dom> may be DOMID_SELF, allowing loopback connections.
|
|
*/
|
|
struct evtchn_bind_interdomain {
|
|
/* IN parameters. */
|
|
domid_t remote_dom;
|
|
evtchn_port_t remote_port;
|
|
/* OUT parameters. */
|
|
evtchn_port_t local_port;
|
|
};
|
|
typedef struct evtchn_bind_interdomain evtchn_bind_interdomain_t;
|
|
|
|
/*
|
|
* EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified
|
|
* vcpu.
|
|
* NOTES:
|
|
* 1. Virtual IRQs are classified as per-vcpu or global. See the VIRQ list
|
|
* in xen.h for the classification of each VIRQ.
|
|
* 2. Global VIRQs must be allocated on VCPU0 but can subsequently be
|
|
* re-bound via EVTCHNOP_bind_vcpu.
|
|
* 3. Per-vcpu VIRQs may be bound to at most one event channel per vcpu.
|
|
* The allocated event channel is bound to the specified vcpu and the
|
|
* binding cannot be changed.
|
|
*/
|
|
struct evtchn_bind_virq {
|
|
/* IN parameters. */
|
|
uint32_t virq; /* enum virq */
|
|
uint32_t vcpu;
|
|
/* OUT parameters. */
|
|
evtchn_port_t port;
|
|
};
|
|
typedef struct evtchn_bind_virq evtchn_bind_virq_t;
|
|
|
|
/*
|
|
* EVTCHNOP_bind_pirq: Bind a local event channel to a real IRQ (PIRQ <irq>).
|
|
* NOTES:
|
|
* 1. A physical IRQ may be bound to at most one event channel per domain.
|
|
* 2. Only a sufficiently-privileged domain may bind to a physical IRQ.
|
|
*/
|
|
struct evtchn_bind_pirq {
|
|
/* IN parameters. */
|
|
uint32_t pirq;
|
|
#define BIND_PIRQ__WILL_SHARE 1
|
|
uint32_t flags; /* BIND_PIRQ__* */
|
|
/* OUT parameters. */
|
|
evtchn_port_t port;
|
|
};
|
|
typedef struct evtchn_bind_pirq evtchn_bind_pirq_t;
|
|
|
|
/*
|
|
* EVTCHNOP_bind_ipi: Bind a local event channel to receive events.
|
|
* NOTES:
|
|
* 1. The allocated event channel is bound to the specified vcpu. The binding
|
|
* may not be changed.
|
|
*/
|
|
struct evtchn_bind_ipi {
|
|
uint32_t vcpu;
|
|
/* OUT parameters. */
|
|
evtchn_port_t port;
|
|
};
|
|
typedef struct evtchn_bind_ipi evtchn_bind_ipi_t;
|
|
|
|
/*
|
|
* EVTCHNOP_close: Close a local event channel <port>. If the channel is
|
|
* interdomain then the remote end is placed in the unbound state
|
|
* (EVTCHNSTAT_unbound), awaiting a new connection.
|
|
*/
|
|
struct evtchn_close {
|
|
/* IN parameters. */
|
|
evtchn_port_t port;
|
|
};
|
|
typedef struct evtchn_close evtchn_close_t;
|
|
|
|
/*
|
|
* EVTCHNOP_send: Send an event to the remote end of the channel whose local
|
|
* endpoint is <port>.
|
|
*/
|
|
struct evtchn_send {
|
|
/* IN parameters. */
|
|
evtchn_port_t port;
|
|
};
|
|
typedef struct evtchn_send evtchn_send_t;
|
|
|
|
/*
|
|
* EVTCHNOP_status: Get the current status of the communication channel which
|
|
* has an endpoint at <dom, port>.
|
|
* NOTES:
|
|
* 1. <dom> may be specified as DOMID_SELF.
|
|
* 2. Only a sufficiently-privileged domain may obtain the status of an event
|
|
* channel for which <dom> is not DOMID_SELF.
|
|
*/
|
|
struct evtchn_status {
|
|
/* IN parameters */
|
|
domid_t dom;
|
|
evtchn_port_t port;
|
|
/* OUT parameters */
|
|
#define EVTCHNSTAT_closed 0 /* Channel is not in use. */
|
|
#define EVTCHNSTAT_unbound 1 /* Channel is waiting interdom connection.*/
|
|
#define EVTCHNSTAT_interdomain 2 /* Channel is connected to remote domain. */
|
|
#define EVTCHNSTAT_pirq 3 /* Channel is bound to a phys IRQ line. */
|
|
#define EVTCHNSTAT_virq 4 /* Channel is bound to a virtual IRQ line */
|
|
#define EVTCHNSTAT_ipi 5 /* Channel is bound to a virtual IPI line */
|
|
uint32_t status;
|
|
uint32_t vcpu; /* VCPU to which this channel is bound. */
|
|
union {
|
|
struct {
|
|
domid_t dom;
|
|
} unbound; /* EVTCHNSTAT_unbound */
|
|
struct {
|
|
domid_t dom;
|
|
evtchn_port_t port;
|
|
} interdomain; /* EVTCHNSTAT_interdomain */
|
|
uint32_t pirq; /* EVTCHNSTAT_pirq */
|
|
uint32_t virq; /* EVTCHNSTAT_virq */
|
|
} u;
|
|
};
|
|
typedef struct evtchn_status evtchn_status_t;
|
|
|
|
/*
|
|
* EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an
|
|
* event is pending.
|
|
* NOTES:
|
|
* 1. IPI-bound channels always notify the vcpu specified at bind time.
|
|
* This binding cannot be changed.
|
|
* 2. Per-VCPU VIRQ channels always notify the vcpu specified at bind time.
|
|
* This binding cannot be changed.
|
|
* 3. All other channels notify vcpu0 by default. This default is set when
|
|
* the channel is allocated (a port that is freed and subsequently reused
|
|
* has its binding reset to vcpu0).
|
|
*/
|
|
struct evtchn_bind_vcpu {
|
|
/* IN parameters. */
|
|
evtchn_port_t port;
|
|
uint32_t vcpu;
|
|
};
|
|
typedef struct evtchn_bind_vcpu evtchn_bind_vcpu_t;
|
|
|
|
/*
|
|
* EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver
|
|
* a notification to the appropriate VCPU if an event is pending.
|
|
*/
|
|
struct evtchn_unmask {
|
|
/* IN parameters. */
|
|
evtchn_port_t port;
|
|
};
|
|
typedef struct evtchn_unmask evtchn_unmask_t;
|
|
|
|
/*
|
|
* EVTCHNOP_reset: Close all event channels associated with specified domain.
|
|
* NOTES:
|
|
* 1. <dom> may be specified as DOMID_SELF.
|
|
* 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF.
|
|
*/
|
|
struct evtchn_reset {
|
|
/* IN parameters. */
|
|
domid_t dom;
|
|
};
|
|
typedef struct evtchn_reset evtchn_reset_t;
|
|
|
|
/*
|
|
* ` enum neg_errnoval
|
|
* ` HYPERVISOR_event_channel_op_compat(struct evtchn_op *op)
|
|
* `
|
|
* Superceded by new event_channel_op() hypercall since 0x00030202.
|
|
*/
|
|
struct evtchn_op {
|
|
uint32_t cmd; /* enum event_channel_op */
|
|
union {
|
|
struct evtchn_alloc_unbound alloc_unbound;
|
|
struct evtchn_bind_interdomain bind_interdomain;
|
|
struct evtchn_bind_virq bind_virq;
|
|
struct evtchn_bind_pirq bind_pirq;
|
|
struct evtchn_bind_ipi bind_ipi;
|
|
struct evtchn_close close;
|
|
struct evtchn_send send;
|
|
struct evtchn_status status;
|
|
struct evtchn_bind_vcpu bind_vcpu;
|
|
struct evtchn_unmask unmask;
|
|
} u;
|
|
};
|
|
typedef struct evtchn_op evtchn_op_t;
|
|
DEFINE_XEN_GUEST_HANDLE(evtchn_op_t);
|
|
|
|
#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */
|
|
|
|
/*
|
|
* Local variables:
|
|
* mode: C
|
|
* c-set-style: "BSD"
|
|
* c-basic-offset: 4
|
|
* tab-width: 4
|
|
* indent-tabs-mode: nil
|
|
* End:
|
|
*/
|