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.
359 lines
7.1 KiB
C
359 lines
7.1 KiB
C
/******************************************************************************
|
|
* evtchn.c
|
|
*
|
|
* Xenolinux driver for receiving and demuxing event-channel signals.
|
|
*
|
|
* Copyright (c) 2004, K A Fraser
|
|
*/
|
|
|
|
#include <sys/cdefs.h>
|
|
__FBSDID("$FreeBSD$");
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/uio.h>
|
|
#include <sys/bus.h>
|
|
#include <sys/malloc.h>
|
|
#include <sys/kernel.h>
|
|
#include <sys/lock.h>
|
|
#include <sys/mutex.h>
|
|
#include <sys/selinfo.h>
|
|
#include <sys/poll.h>
|
|
#include <sys/conf.h>
|
|
#include <sys/fcntl.h>
|
|
#include <sys/ioccom.h>
|
|
#include <sys/rman.h>
|
|
|
|
#include <xen/xen-os.h>
|
|
#include <xen/evtchn.h>
|
|
#include <xen/xen_intr.h>
|
|
|
|
#include <machine/bus.h>
|
|
#include <machine/resource.h>
|
|
#include <machine/xen/synch_bitops.h>
|
|
|
|
#include <xen/evtchn/evtchnvar.h>
|
|
|
|
typedef struct evtchn_sotfc {
|
|
|
|
struct selinfo ev_rsel;
|
|
} evtchn_softc_t;
|
|
|
|
/* Only one process may open /dev/xen/evtchn at any time. */
|
|
static unsigned long evtchn_dev_inuse;
|
|
|
|
/* Notification ring, accessed via /dev/xen/evtchn. */
|
|
|
|
#define EVTCHN_RING_SIZE 2048 /* 2048 16-bit entries */
|
|
|
|
#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
|
|
static uint16_t *ring;
|
|
static unsigned int ring_cons, ring_prod, ring_overflow;
|
|
|
|
/* Which ports is user-space bound to? */
|
|
static uint32_t bound_ports[32];
|
|
|
|
/* Unique address for processes to sleep on */
|
|
static void *evtchn_waddr = ˚
|
|
|
|
static struct mtx lock, upcall_lock;
|
|
|
|
static d_read_t evtchn_read;
|
|
static d_write_t evtchn_write;
|
|
static d_ioctl_t evtchn_ioctl;
|
|
static d_poll_t evtchn_poll;
|
|
static d_open_t evtchn_open;
|
|
static d_close_t evtchn_close;
|
|
|
|
|
|
void
|
|
evtchn_device_upcall(evtchn_port_t port)
|
|
{
|
|
mtx_lock(&upcall_lock);
|
|
|
|
evtchn_mask_port(port);
|
|
evtchn_clear_port(port);
|
|
|
|
if ( ring != NULL ) {
|
|
if ( (ring_prod - ring_cons) < EVTCHN_RING_SIZE ) {
|
|
ring[EVTCHN_RING_MASK(ring_prod)] = (uint16_t)port;
|
|
if ( ring_cons == ring_prod++ ) {
|
|
wakeup(evtchn_waddr);
|
|
}
|
|
}
|
|
else {
|
|
ring_overflow = 1;
|
|
}
|
|
}
|
|
|
|
mtx_unlock(&upcall_lock);
|
|
}
|
|
|
|
static void
|
|
__evtchn_reset_buffer_ring(void)
|
|
{
|
|
/* Initialise the ring to empty. Clear errors. */
|
|
ring_cons = ring_prod = ring_overflow = 0;
|
|
}
|
|
|
|
static int
|
|
evtchn_read(struct cdev *dev, struct uio *uio, int ioflag)
|
|
{
|
|
int rc;
|
|
unsigned int count, c, p, sst = 0, bytes1 = 0, bytes2 = 0;
|
|
count = uio->uio_resid;
|
|
|
|
count &= ~1; /* even number of bytes */
|
|
|
|
if ( count == 0 )
|
|
{
|
|
rc = 0;
|
|
goto out;
|
|
}
|
|
|
|
if ( count > PAGE_SIZE )
|
|
count = PAGE_SIZE;
|
|
|
|
for ( ; ; ) {
|
|
if ( (c = ring_cons) != (p = ring_prod) )
|
|
break;
|
|
|
|
if ( ring_overflow ) {
|
|
rc = EFBIG;
|
|
goto out;
|
|
}
|
|
|
|
if (sst != 0) {
|
|
rc = EINTR;
|
|
goto out;
|
|
}
|
|
|
|
/* PCATCH == check for signals before and after sleeping
|
|
* PWAIT == priority of waiting on resource
|
|
*/
|
|
sst = tsleep(evtchn_waddr, PWAIT|PCATCH, "evchwt", 10);
|
|
}
|
|
|
|
/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
|
|
if ( ((c ^ p) & EVTCHN_RING_SIZE) != 0 ) {
|
|
bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) * sizeof(uint16_t);
|
|
bytes2 = EVTCHN_RING_MASK(p) * sizeof(uint16_t);
|
|
}
|
|
else {
|
|
bytes1 = (p - c) * sizeof(uint16_t);
|
|
bytes2 = 0;
|
|
}
|
|
|
|
/* Truncate chunks according to caller's maximum byte count. */
|
|
if ( bytes1 > count ) {
|
|
bytes1 = count;
|
|
bytes2 = 0;
|
|
}
|
|
else if ( (bytes1 + bytes2) > count ) {
|
|
bytes2 = count - bytes1;
|
|
}
|
|
|
|
if ( uiomove(&ring[EVTCHN_RING_MASK(c)], bytes1, uio) ||
|
|
((bytes2 != 0) && uiomove(&ring[0], bytes2, uio)))
|
|
/* keeping this around as its replacement is not equivalent
|
|
* copyout(&ring[0], &buf[bytes1], bytes2)
|
|
*/
|
|
{
|
|
rc = EFAULT;
|
|
goto out;
|
|
}
|
|
|
|
ring_cons += (bytes1 + bytes2) / sizeof(uint16_t);
|
|
|
|
rc = bytes1 + bytes2;
|
|
|
|
out:
|
|
|
|
return rc;
|
|
}
|
|
|
|
static int
|
|
evtchn_write(struct cdev *dev, struct uio *uio, int ioflag)
|
|
{
|
|
int rc, i, count;
|
|
|
|
count = uio->uio_resid;
|
|
|
|
uint16_t *kbuf = (uint16_t *)malloc(PAGE_SIZE, M_DEVBUF, M_WAITOK);
|
|
|
|
|
|
if ( kbuf == NULL )
|
|
return ENOMEM;
|
|
|
|
count &= ~1; /* even number of bytes */
|
|
|
|
if ( count == 0 ) {
|
|
rc = 0;
|
|
goto out;
|
|
}
|
|
|
|
if ( count > PAGE_SIZE )
|
|
count = PAGE_SIZE;
|
|
|
|
if ( uiomove(kbuf, count, uio) != 0 ) {
|
|
rc = EFAULT;
|
|
goto out;
|
|
}
|
|
|
|
mtx_lock_spin(&lock);
|
|
for ( i = 0; i < (count/2); i++ )
|
|
if ( test_bit(kbuf[i], &bound_ports[0]) )
|
|
evtchn_unmask_port(kbuf[i]);
|
|
mtx_unlock_spin(&lock);
|
|
|
|
rc = count;
|
|
|
|
out:
|
|
free(kbuf, M_DEVBUF);
|
|
return rc;
|
|
}
|
|
|
|
static int
|
|
evtchn_ioctl(struct cdev *dev, unsigned long cmd, caddr_t arg,
|
|
int mode, struct thread *td __unused)
|
|
{
|
|
int rc = 0;
|
|
|
|
#ifdef NOTYET
|
|
mtx_lock_spin(&lock);
|
|
|
|
switch ( cmd )
|
|
{
|
|
case EVTCHN_RESET:
|
|
__evtchn_reset_buffer_ring();
|
|
break;
|
|
case EVTCHN_BIND:
|
|
if ( !synch_test_and_set_bit((uintptr_t)arg, &bound_ports[0]) )
|
|
unmask_evtchn((uintptr_t)arg);
|
|
else
|
|
rc = EINVAL;
|
|
break;
|
|
case EVTCHN_UNBIND:
|
|
if ( synch_test_and_clear_bit((uintptr_t)arg, &bound_ports[0]) )
|
|
mask_evtchn((uintptr_t)arg);
|
|
else
|
|
rc = EINVAL;
|
|
break;
|
|
default:
|
|
rc = ENOSYS;
|
|
break;
|
|
}
|
|
|
|
mtx_unlock_spin(&lock);
|
|
#endif
|
|
|
|
return rc;
|
|
}
|
|
|
|
static int
|
|
evtchn_poll(struct cdev *dev, int poll_events, struct thread *td)
|
|
{
|
|
|
|
evtchn_softc_t *sc;
|
|
unsigned int mask = POLLOUT | POLLWRNORM;
|
|
|
|
sc = dev->si_drv1;
|
|
|
|
if ( ring_cons != ring_prod )
|
|
mask |= POLLIN | POLLRDNORM;
|
|
else if ( ring_overflow )
|
|
mask = POLLERR;
|
|
else
|
|
selrecord(td, &sc->ev_rsel);
|
|
|
|
|
|
return mask;
|
|
}
|
|
|
|
|
|
static int
|
|
evtchn_open(struct cdev *dev, int flag, int otyp, struct thread *td)
|
|
{
|
|
uint16_t *_ring;
|
|
|
|
if (flag & O_NONBLOCK)
|
|
return EBUSY;
|
|
|
|
if ( synch_test_and_set_bit(0, &evtchn_dev_inuse) )
|
|
return EBUSY;
|
|
|
|
if ( (_ring = (uint16_t *)malloc(PAGE_SIZE, M_DEVBUF, M_WAITOK)) == NULL )
|
|
return ENOMEM;
|
|
|
|
mtx_lock_spin(&lock);
|
|
ring = _ring;
|
|
__evtchn_reset_buffer_ring();
|
|
mtx_unlock_spin(&lock);
|
|
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
evtchn_close(struct cdev *dev, int flag, int otyp, struct thread *td __unused)
|
|
{
|
|
int i;
|
|
|
|
if (ring != NULL) {
|
|
free(ring, M_DEVBUF);
|
|
ring = NULL;
|
|
}
|
|
mtx_lock_spin(&lock);
|
|
for ( i = 0; i < NR_EVENT_CHANNELS; i++ )
|
|
if ( synch_test_and_clear_bit(i, &bound_ports[0]) )
|
|
evtchn_mask_port(i);
|
|
mtx_unlock_spin(&lock);
|
|
|
|
evtchn_dev_inuse = 0;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static struct cdevsw evtchn_devsw = {
|
|
.d_version = D_VERSION,
|
|
.d_open = evtchn_open,
|
|
.d_close = evtchn_close,
|
|
.d_read = evtchn_read,
|
|
.d_write = evtchn_write,
|
|
.d_ioctl = evtchn_ioctl,
|
|
.d_poll = evtchn_poll,
|
|
.d_name = "evtchn",
|
|
};
|
|
|
|
|
|
/* XXX - if this device is ever supposed to support use by more than one process
|
|
* this global static will have to go away
|
|
*/
|
|
static struct cdev *evtchn_dev;
|
|
|
|
|
|
|
|
static int
|
|
evtchn_dev_init(void *dummy __unused)
|
|
{
|
|
/* XXX I believe we don't need these leaving them here for now until we
|
|
* have some semblance of it working
|
|
*/
|
|
mtx_init(&upcall_lock, "evtchup", NULL, MTX_DEF);
|
|
|
|
/* (DEVFS) create '/dev/misc/evtchn'. */
|
|
evtchn_dev = make_dev(&evtchn_devsw, 0, UID_ROOT, GID_WHEEL, 0600, "xen/evtchn");
|
|
|
|
mtx_init(&lock, "evch", NULL, MTX_SPIN | MTX_NOWITNESS);
|
|
|
|
evtchn_dev->si_drv1 = malloc(sizeof(evtchn_softc_t), M_DEVBUF, M_WAITOK);
|
|
bzero(evtchn_dev->si_drv1, sizeof(evtchn_softc_t));
|
|
|
|
if (bootverbose)
|
|
printf("Event-channel device installed.\n");
|
|
|
|
return 0;
|
|
}
|
|
|
|
SYSINIT(evtchn_dev_init, SI_SUB_DRIVERS, SI_ORDER_FIRST, evtchn_dev_init, NULL);
|