mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
e73f61e41f
The allocation size of the kvm_irq_routing_table depends on the number of irq routing entries because they are all allocated with one kzalloc call. When the irq routing table gets bigger this requires high order allocations which fail from time to time: qemu-kvm: page allocation failure: order:4, mode:0xd0 This patch fixes this issue by breaking up the allocation of the table and its entries into individual kzalloc calls. These could all be satisfied with order-0 allocations, which are less likely to fail. The downside of this change is the lower performance, because of more calls to kzalloc. But given how often kvm_set_irq_routing is called in the lifetime of a guest, it doesn't really matter much. Signed-off-by: Joerg Roedel <jroedel@suse.de> [Avoid sparse warning through rcu_access_pointer. - Paolo] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
240 lines
5.8 KiB
C
240 lines
5.8 KiB
C
/*
|
|
* irqchip.c: Common API for in kernel interrupt controllers
|
|
* Copyright (c) 2007, Intel Corporation.
|
|
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
|
|
* Copyright (c) 2013, Alexander Graf <agraf@suse.de>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program; if not, write to the Free Software Foundation, Inc., 59 Temple
|
|
* Place - Suite 330, Boston, MA 02111-1307 USA.
|
|
*
|
|
* This file is derived from virt/kvm/irq_comm.c.
|
|
*
|
|
* Authors:
|
|
* Yaozu (Eddie) Dong <Eddie.dong@intel.com>
|
|
* Alexander Graf <agraf@suse.de>
|
|
*/
|
|
|
|
#include <linux/kvm_host.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/srcu.h>
|
|
#include <linux/export.h>
|
|
#include <trace/events/kvm.h>
|
|
#include "irq.h"
|
|
|
|
struct kvm_irq_routing_table {
|
|
int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
|
|
u32 nr_rt_entries;
|
|
/*
|
|
* Array indexed by gsi. Each entry contains list of irq chips
|
|
* the gsi is connected to.
|
|
*/
|
|
struct hlist_head map[0];
|
|
};
|
|
|
|
int kvm_irq_map_gsi(struct kvm *kvm,
|
|
struct kvm_kernel_irq_routing_entry *entries, int gsi)
|
|
{
|
|
struct kvm_irq_routing_table *irq_rt;
|
|
struct kvm_kernel_irq_routing_entry *e;
|
|
int n = 0;
|
|
|
|
irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
|
|
lockdep_is_held(&kvm->irq_lock));
|
|
if (gsi < irq_rt->nr_rt_entries) {
|
|
hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
|
|
entries[n] = *e;
|
|
++n;
|
|
}
|
|
}
|
|
|
|
return n;
|
|
}
|
|
|
|
int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
|
|
{
|
|
struct kvm_irq_routing_table *irq_rt;
|
|
|
|
irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
|
|
return irq_rt->chip[irqchip][pin];
|
|
}
|
|
|
|
int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
|
|
{
|
|
struct kvm_kernel_irq_routing_entry route;
|
|
|
|
if (!irqchip_in_kernel(kvm) || msi->flags != 0)
|
|
return -EINVAL;
|
|
|
|
route.msi.address_lo = msi->address_lo;
|
|
route.msi.address_hi = msi->address_hi;
|
|
route.msi.data = msi->data;
|
|
|
|
return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false);
|
|
}
|
|
|
|
/*
|
|
* Return value:
|
|
* < 0 Interrupt was ignored (masked or not delivered for other reasons)
|
|
* = 0 Interrupt was coalesced (previous irq is still pending)
|
|
* > 0 Number of CPUs interrupt was delivered to
|
|
*/
|
|
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
|
|
bool line_status)
|
|
{
|
|
struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS];
|
|
int ret = -1, i, idx;
|
|
|
|
trace_kvm_set_irq(irq, level, irq_source_id);
|
|
|
|
/* Not possible to detect if the guest uses the PIC or the
|
|
* IOAPIC. So set the bit in both. The guest will ignore
|
|
* writes to the unused one.
|
|
*/
|
|
idx = srcu_read_lock(&kvm->irq_srcu);
|
|
i = kvm_irq_map_gsi(kvm, irq_set, irq);
|
|
srcu_read_unlock(&kvm->irq_srcu, idx);
|
|
|
|
while (i--) {
|
|
int r;
|
|
r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level,
|
|
line_status);
|
|
if (r < 0)
|
|
continue;
|
|
|
|
ret = r + ((ret < 0) ? 0 : ret);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void free_irq_routing_table(struct kvm_irq_routing_table *rt)
|
|
{
|
|
int i;
|
|
|
|
if (!rt)
|
|
return;
|
|
|
|
for (i = 0; i < rt->nr_rt_entries; ++i) {
|
|
struct kvm_kernel_irq_routing_entry *e;
|
|
struct hlist_node *n;
|
|
|
|
hlist_for_each_entry_safe(e, n, &rt->map[i], link) {
|
|
hlist_del(&e->link);
|
|
kfree(e);
|
|
}
|
|
}
|
|
|
|
kfree(rt);
|
|
}
|
|
|
|
void kvm_free_irq_routing(struct kvm *kvm)
|
|
{
|
|
/* Called only during vm destruction. Nobody can use the pointer
|
|
at this stage */
|
|
struct kvm_irq_routing_table *rt = rcu_access_pointer(kvm->irq_routing);
|
|
free_irq_routing_table(rt);
|
|
}
|
|
|
|
static int setup_routing_entry(struct kvm_irq_routing_table *rt,
|
|
struct kvm_kernel_irq_routing_entry *e,
|
|
const struct kvm_irq_routing_entry *ue)
|
|
{
|
|
int r = -EINVAL;
|
|
struct kvm_kernel_irq_routing_entry *ei;
|
|
|
|
/*
|
|
* Do not allow GSI to be mapped to the same irqchip more than once.
|
|
* Allow only one to one mapping between GSI and MSI.
|
|
*/
|
|
hlist_for_each_entry(ei, &rt->map[ue->gsi], link)
|
|
if (ei->type == KVM_IRQ_ROUTING_MSI ||
|
|
ue->type == KVM_IRQ_ROUTING_MSI ||
|
|
ue->u.irqchip.irqchip == ei->irqchip.irqchip)
|
|
return r;
|
|
|
|
e->gsi = ue->gsi;
|
|
e->type = ue->type;
|
|
r = kvm_set_routing_entry(e, ue);
|
|
if (r)
|
|
goto out;
|
|
if (e->type == KVM_IRQ_ROUTING_IRQCHIP)
|
|
rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi;
|
|
|
|
hlist_add_head(&e->link, &rt->map[e->gsi]);
|
|
r = 0;
|
|
out:
|
|
return r;
|
|
}
|
|
|
|
int kvm_set_irq_routing(struct kvm *kvm,
|
|
const struct kvm_irq_routing_entry *ue,
|
|
unsigned nr,
|
|
unsigned flags)
|
|
{
|
|
struct kvm_irq_routing_table *new, *old;
|
|
u32 i, j, nr_rt_entries = 0;
|
|
int r;
|
|
|
|
for (i = 0; i < nr; ++i) {
|
|
if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES)
|
|
return -EINVAL;
|
|
nr_rt_entries = max(nr_rt_entries, ue[i].gsi);
|
|
}
|
|
|
|
nr_rt_entries += 1;
|
|
|
|
new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)),
|
|
GFP_KERNEL);
|
|
|
|
if (!new)
|
|
return -ENOMEM;
|
|
|
|
new->nr_rt_entries = nr_rt_entries;
|
|
for (i = 0; i < KVM_NR_IRQCHIPS; i++)
|
|
for (j = 0; j < KVM_IRQCHIP_NUM_PINS; j++)
|
|
new->chip[i][j] = -1;
|
|
|
|
for (i = 0; i < nr; ++i) {
|
|
struct kvm_kernel_irq_routing_entry *e;
|
|
|
|
r = -ENOMEM;
|
|
e = kzalloc(sizeof(*e), GFP_KERNEL);
|
|
if (!e)
|
|
goto out;
|
|
|
|
r = -EINVAL;
|
|
if (ue->flags)
|
|
goto out;
|
|
r = setup_routing_entry(new, e, ue);
|
|
if (r)
|
|
goto out;
|
|
++ue;
|
|
}
|
|
|
|
mutex_lock(&kvm->irq_lock);
|
|
old = kvm->irq_routing;
|
|
rcu_assign_pointer(kvm->irq_routing, new);
|
|
kvm_irq_routing_update(kvm);
|
|
mutex_unlock(&kvm->irq_lock);
|
|
|
|
synchronize_srcu_expedited(&kvm->irq_srcu);
|
|
|
|
new = old;
|
|
r = 0;
|
|
|
|
out:
|
|
free_irq_routing_table(new);
|
|
|
|
return r;
|
|
}
|