linux/virt/kvm/ioapic.c

441 lines
11 KiB
C
Raw Normal View History

/*
* Copyright (C) 2001 MandrakeSoft S.A.
*
* MandrakeSoft S.A.
* 43, rue d'Aboukir
* 75002 Paris - France
* http://www.linux-mandrake.com/
* http://www.mandrakesoft.com/
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Yunhong Jiang <yunhong.jiang@intel.com>
* Yaozu (Eddie) Dong <eddie.dong@intel.com>
* Based on Xen 3.1 code.
*/
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/smp.h>
#include <linux/hrtimer.h>
#include <linux/io.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/current.h>
#include <trace/events/kvm.h>
#include "ioapic.h"
#include "lapic.h"
#include "irq.h"
#if 0
#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
#else
#define ioapic_debug(fmt, arg...)
#endif
static int ioapic_deliver(struct kvm_ioapic *vioapic, int irq);
static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
unsigned long addr,
unsigned long length)
{
unsigned long result = 0;
switch (ioapic->ioregsel) {
case IOAPIC_REG_VERSION:
result = ((((IOAPIC_NUM_PINS - 1) & 0xff) << 16)
| (IOAPIC_VERSION_ID & 0xff));
break;
case IOAPIC_REG_APIC_ID:
case IOAPIC_REG_ARB_ID:
result = ((ioapic->id & 0xf) << 24);
break;
default:
{
u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
u64 redir_content;
ASSERT(redir_index < IOAPIC_NUM_PINS);
redir_content = ioapic->redirtbl[redir_index].bits;
result = (ioapic->ioregsel & 0x1) ?
(redir_content >> 32) & 0xffffffff :
redir_content & 0xffffffff;
break;
}
}
return result;
}
static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
{
union kvm_ioapic_redirect_entry *pent;
int injected = -1;
pent = &ioapic->redirtbl[idx];
if (!pent->fields.mask) {
injected = ioapic_deliver(ioapic, idx);
if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG)
pent->fields.remote_irr = 1;
}
return injected;
}
static void update_handled_vectors(struct kvm_ioapic *ioapic)
{
DECLARE_BITMAP(handled_vectors, 256);
int i;
memset(handled_vectors, 0, sizeof(handled_vectors));
for (i = 0; i < IOAPIC_NUM_PINS; ++i)
__set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors);
memcpy(ioapic->handled_vectors, handled_vectors,
sizeof(handled_vectors));
smp_wmb();
}
static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
{
unsigned index;
bool mask_before, mask_after;
union kvm_ioapic_redirect_entry *e;
switch (ioapic->ioregsel) {
case IOAPIC_REG_VERSION:
/* Writes are ignored. */
break;
case IOAPIC_REG_APIC_ID:
ioapic->id = (val >> 24) & 0xf;
break;
case IOAPIC_REG_ARB_ID:
break;
default:
index = (ioapic->ioregsel - 0x10) >> 1;
ioapic_debug("change redir index %x val %x\n", index, val);
if (index >= IOAPIC_NUM_PINS)
return;
e = &ioapic->redirtbl[index];
mask_before = e->fields.mask;
if (ioapic->ioregsel & 1) {
e->bits &= 0xffffffff;
e->bits |= (u64) val << 32;
} else {
e->bits &= ~0xffffffffULL;
e->bits |= (u32) val;
e->fields.remote_irr = 0;
}
update_handled_vectors(ioapic);
mask_after = e->fields.mask;
if (mask_before != mask_after)
kvm_fire_mask_notifiers(ioapic->kvm, index, mask_after);
if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
&& ioapic->irr & (1 << index))
ioapic_service(ioapic, index);
break;
}
}
static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
{
union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
struct kvm_lapic_irq irqe;
ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
"vector=%x trig_mode=%x\n",
entry->fields.dest, entry->fields.dest_mode,
entry->fields.delivery_mode, entry->fields.vector,
entry->fields.trig_mode);
irqe.dest_id = entry->fields.dest_id;
irqe.vector = entry->fields.vector;
irqe.dest_mode = entry->fields.dest_mode;
irqe.trig_mode = entry->fields.trig_mode;
irqe.delivery_mode = entry->fields.delivery_mode << 8;
irqe.level = 1;
irqe.shorthand = 0;
#ifdef CONFIG_X86
/* Always delivery PIT interrupt to vcpu 0 */
if (irq == 0) {
irqe.dest_mode = 0; /* Physical mode. */
/* need to read apic_id from apic regiest since
* it can be rewritten */
irqe.dest_id = ioapic->kvm->bsp_vcpu->vcpu_id;
}
#endif
return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
}
int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
{
u32 old_irr;
u32 mask = 1 << irq;
union kvm_ioapic_redirect_entry entry;
int ret = 1;
spin_lock(&ioapic->lock);
old_irr = ioapic->irr;
if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
entry = ioapic->redirtbl[irq];
level ^= entry.fields.polarity;
if (!level)
ioapic->irr &= ~mask;
else {
int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
ioapic->irr |= mask;
if ((edge && old_irr != ioapic->irr) ||
(!edge && !entry.fields.remote_irr))
ret = ioapic_service(ioapic, irq);
else
ret = 0; /* report coalesced interrupt */
}
trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
}
spin_unlock(&ioapic->lock);
return ret;
}
static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
int trigger_mode)
{
int i;
for (i = 0; i < IOAPIC_NUM_PINS; i++) {
union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
if (ent->fields.vector != vector)
continue;
/*
* We are dropping lock while calling ack notifiers because ack
* notifier callbacks for assigned devices call into IOAPIC
* recursively. Since remote_irr is cleared only after call
* to notifiers if the same vector will be delivered while lock
* is dropped it will be put into irr and will be delivered
* after ack notifier returns.
*/
spin_unlock(&ioapic->lock);
kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
spin_lock(&ioapic->lock);
if (trigger_mode != IOAPIC_LEVEL_TRIG)
continue;
ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
ent->fields.remote_irr = 0;
if (!ent->fields.mask && (ioapic->irr & (1 << i)))
ioapic_service(ioapic, i);
}
}
void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
smp_rmb();
if (!test_bit(vector, ioapic->handled_vectors))
return;
spin_lock(&ioapic->lock);
__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
spin_unlock(&ioapic->lock);
}
static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
{
return container_of(dev, struct kvm_ioapic, dev);
}
static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr)
{
return ((addr >= ioapic->base_address &&
(addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));
}
static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
void *val)
{
struct kvm_ioapic *ioapic = to_ioapic(this);
u32 result;
if (!ioapic_in_range(ioapic, addr))
return -EOPNOTSUPP;
ioapic_debug("addr %lx\n", (unsigned long)addr);
ASSERT(!(addr & 0xf)); /* check alignment */
addr &= 0xff;
spin_lock(&ioapic->lock);
switch (addr) {
case IOAPIC_REG_SELECT:
result = ioapic->ioregsel;
break;
case IOAPIC_REG_WINDOW:
result = ioapic_read_indirect(ioapic, addr, len);
break;
default:
result = 0;
break;
}
spin_unlock(&ioapic->lock);
switch (len) {
case 8:
*(u64 *) val = result;
break;
case 1:
case 2:
case 4:
memcpy(val, (char *)&result, len);
break;
default:
printk(KERN_WARNING "ioapic: wrong length %d\n", len);
}
return 0;
}
static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
const void *val)
{
struct kvm_ioapic *ioapic = to_ioapic(this);
u32 data;
if (!ioapic_in_range(ioapic, addr))
return -EOPNOTSUPP;
ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
(void*)addr, len, val);
ASSERT(!(addr & 0xf)); /* check alignment */
if (len == 4 || len == 8)
data = *(u32 *) val;
else {
printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
return 0;
}
addr &= 0xff;
spin_lock(&ioapic->lock);
switch (addr) {
case IOAPIC_REG_SELECT:
ioapic->ioregsel = data;
break;
case IOAPIC_REG_WINDOW:
ioapic_write_indirect(ioapic, data);
break;
#ifdef CONFIG_IA64
case IOAPIC_REG_EOI:
__kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG);
break;
#endif
default:
break;
}
spin_unlock(&ioapic->lock);
return 0;
}
void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
{
int i;
for (i = 0; i < IOAPIC_NUM_PINS; i++)
ioapic->redirtbl[i].fields.mask = 1;
ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
ioapic->ioregsel = 0;
ioapic->irr = 0;
ioapic->id = 0;
update_handled_vectors(ioapic);
}
static const struct kvm_io_device_ops ioapic_mmio_ops = {
.read = ioapic_mmio_read,
.write = ioapic_mmio_write,
};
int kvm_ioapic_init(struct kvm *kvm)
{
struct kvm_ioapic *ioapic;
int ret;
ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
if (!ioapic)
return -ENOMEM;
spin_lock_init(&ioapic->lock);
kvm->arch.vioapic = ioapic;
kvm_ioapic_reset(ioapic);
kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
ioapic->kvm = kvm;
mutex_lock(&kvm->slots_lock);
ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
mutex_unlock(&kvm->slots_lock);
if (ret < 0) {
kvm->arch.vioapic = NULL;
kfree(ioapic);
}
return ret;
}
void kvm_ioapic_destroy(struct kvm *kvm)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
if (ioapic) {
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
kvm->arch.vioapic = NULL;
kfree(ioapic);
}
}
int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
{
struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
if (!ioapic)
return -EINVAL;
spin_lock(&ioapic->lock);
memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
spin_unlock(&ioapic->lock);
return 0;
}
int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
{
struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
if (!ioapic)
return -EINVAL;
spin_lock(&ioapic->lock);
memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
update_handled_vectors(ioapic);
spin_unlock(&ioapic->lock);
return 0;
}