aboutsummaryrefslogtreecommitdiff
path: root/virt
diff options
context:
space:
mode:
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/Kconfig7
-rw-r--r--virt/kvm/arm/arch_timer.c2
-rw-r--r--virt/kvm/arm/vgic-v2.c265
-rw-r--r--virt/kvm/arm/vgic-v3.c247
-rw-r--r--virt/kvm/arm/vgic.c390
-rw-r--r--virt/kvm/assigned-dev.c7
-rw-r--r--virt/kvm/async_pf.c39
-rw-r--r--virt/kvm/eventfd.c206
-rw-r--r--virt/kvm/ioapic.c140
-rw-r--r--virt/kvm/iommu.c19
-rw-r--r--virt/kvm/irq_comm.c41
-rw-r--r--virt/kvm/irqchip.c107
-rw-r--r--virt/kvm/kvm_main.c99
-rw-r--r--virt/kvm/vfio.c27
14 files changed, 1172 insertions, 424 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index fbe1a48bd629..fc0c5e603eb4 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -6,6 +6,9 @@ config HAVE_KVM
config HAVE_KVM_IRQCHIP
bool
+config HAVE_KVM_IRQFD
+ bool
+
config HAVE_KVM_IRQ_ROUTING
bool
@@ -22,6 +25,10 @@ config KVM_MMIO
config KVM_ASYNC_PF
bool
+# Toggle to switch between direct notification and batch job
+config KVM_ASYNC_PF_SYNC
+ bool
+
config HAVE_KVM_MSI
bool
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 5081e809821f..22fa819a9b6a 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -277,7 +277,7 @@ int kvm_timer_hyp_init(void)
host_vtimer_irq = ppi;
- err = register_cpu_notifier(&kvm_timer_cpu_nb);
+ err = __register_cpu_notifier(&kvm_timer_cpu_nb);
if (err) {
kvm_err("Cannot register timer CPU notifier\n");
goto out_free;
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
new file mode 100644
index 000000000000..416baedfc89f
--- /dev/null
+++ b/virt/kvm/arm/vgic-v2.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (C) 2012,2013 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * 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.
+ *
+ * This program 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+static struct vgic_lr vgic_v2_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+ struct vgic_lr lr_desc;
+ u32 val = vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr];
+
+ lr_desc.irq = val & GICH_LR_VIRTUALID;
+ if (lr_desc.irq <= 15)
+ lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
+ else
+ lr_desc.source = 0;
+ lr_desc.state = 0;
+
+ if (val & GICH_LR_PENDING_BIT)
+ lr_desc.state |= LR_STATE_PENDING;
+ if (val & GICH_LR_ACTIVE_BIT)
+ lr_desc.state |= LR_STATE_ACTIVE;
+ if (val & GICH_LR_EOI)
+ lr_desc.state |= LR_EOI_INT;
+
+ return lr_desc;
+}
+
+static void vgic_v2_set_lr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ u32 lr_val = (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) | lr_desc.irq;
+
+ if (lr_desc.state & LR_STATE_PENDING)
+ lr_val |= GICH_LR_PENDING_BIT;
+ if (lr_desc.state & LR_STATE_ACTIVE)
+ lr_val |= GICH_LR_ACTIVE_BIT;
+ if (lr_desc.state & LR_EOI_INT)
+ lr_val |= GICH_LR_EOI;
+
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val;
+}
+
+static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ if (!(lr_desc.state & LR_STATE_MASK))
+ __set_bit(lr, (unsigned long *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr);
+}
+
+static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
+{
+ u64 val;
+
+#if BITS_PER_LONG == 64
+ val = vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[1];
+ val <<= 32;
+ val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[0];
+#else
+ val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
+#endif
+ return val;
+}
+
+static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
+{
+ u64 val;
+
+#if BITS_PER_LONG == 64
+ val = vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[1];
+ val <<= 32;
+ val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[0];
+#else
+ val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
+#endif
+ return val;
+}
+
+static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
+{
+ u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr;
+ u32 ret = 0;
+
+ if (misr & GICH_MISR_EOI)
+ ret |= INT_STATUS_EOI;
+ if (misr & GICH_MISR_U)
+ ret |= INT_STATUS_UNDERFLOW;
+
+ return ret;
+}
+
+static void vgic_v2_enable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr |= GICH_HCR_UIE;
+}
+
+static void vgic_v2_disable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr &= ~GICH_HCR_UIE;
+}
+
+static void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr;
+
+ vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >> GICH_VMCR_CTRL_SHIFT;
+ vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >> GICH_VMCR_ALIAS_BINPOINT_SHIFT;
+ vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >> GICH_VMCR_BINPOINT_SHIFT;
+ vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >> GICH_VMCR_PRIMASK_SHIFT;
+}
+
+static void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr;
+
+ vmcr = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
+ vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) & GICH_VMCR_ALIAS_BINPOINT_MASK;
+ vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & GICH_VMCR_BINPOINT_MASK;
+ vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
+
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
+}
+
+static void vgic_v2_enable(struct kvm_vcpu *vcpu)
+{
+ /*
+ * By forcing VMCR to zero, the GIC will restore the binary
+ * points to their reset values. Anything else resets to zero
+ * anyway.
+ */
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0;
+
+ /* Get the show on the road... */
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN;
+}
+
+static const struct vgic_ops vgic_v2_ops = {
+ .get_lr = vgic_v2_get_lr,
+ .set_lr = vgic_v2_set_lr,
+ .sync_lr_elrsr = vgic_v2_sync_lr_elrsr,
+ .get_elrsr = vgic_v2_get_elrsr,
+ .get_eisr = vgic_v2_get_eisr,
+ .get_interrupt_status = vgic_v2_get_interrupt_status,
+ .enable_underflow = vgic_v2_enable_underflow,
+ .disable_underflow = vgic_v2_disable_underflow,
+ .get_vmcr = vgic_v2_get_vmcr,
+ .set_vmcr = vgic_v2_set_vmcr,
+ .enable = vgic_v2_enable,
+};
+
+static struct vgic_params vgic_v2_params;
+
+/**
+ * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
+ * @node: pointer to the DT node
+ * @ops: address of a pointer to the GICv2 operations
+ * @params: address of a pointer to HW-specific parameters
+ *
+ * Returns 0 if a GICv2 has been found, with the low level operations
+ * in *ops and the HW parameters in *params. Returns an error code
+ * otherwise.
+ */
+int vgic_v2_probe(struct device_node *vgic_node,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params)
+{
+ int ret;
+ struct resource vctrl_res;
+ struct resource vcpu_res;
+ struct vgic_params *vgic = &vgic_v2_params;
+
+ vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
+ if (!vgic->maint_irq) {
+ kvm_err("error getting vgic maintenance irq from DT\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
+ if (ret) {
+ kvm_err("Cannot obtain GICH resource\n");
+ goto out;
+ }
+
+ vgic->vctrl_base = of_iomap(vgic_node, 2);
+ if (!vgic->vctrl_base) {
+ kvm_err("Cannot ioremap GICH\n");
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ vgic->nr_lr = readl_relaxed(vgic->vctrl_base + GICH_VTR);
+ vgic->nr_lr = (vgic->nr_lr & 0x3f) + 1;
+
+ ret = create_hyp_io_mappings(vgic->vctrl_base,
+ vgic->vctrl_base + resource_size(&vctrl_res),
+ vctrl_res.start);
+ if (ret) {
+ kvm_err("Cannot map VCTRL into hyp\n");
+ goto out_unmap;
+ }
+
+ if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
+ kvm_err("Cannot obtain GICV resource\n");
+ ret = -ENXIO;
+ goto out_unmap;
+ }
+
+ if (!PAGE_ALIGNED(vcpu_res.start)) {
+ kvm_err("GICV physical address 0x%llx not page aligned\n",
+ (unsigned long long)vcpu_res.start);
+ ret = -ENXIO;
+ goto out_unmap;
+ }
+
+ if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+ kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+ (unsigned long long)resource_size(&vcpu_res),
+ PAGE_SIZE);
+ ret = -ENXIO;
+ goto out_unmap;
+ }
+
+ vgic->vcpu_base = vcpu_res.start;
+
+ kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+ vctrl_res.start, vgic->maint_irq);
+
+ vgic->type = VGIC_V2;
+ *ops = &vgic_v2_ops;
+ *params = vgic;
+ goto out;
+
+out_unmap:
+ iounmap(vgic->vctrl_base);
+out:
+ of_node_put(vgic_node);
+ return ret;
+}
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
new file mode 100644
index 000000000000..1c2c8eef0599
--- /dev/null
+++ b/virt/kvm/arm/vgic-v3.c
@@ -0,0 +1,247 @@
+/*
+ * Copyright (C) 2013 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * 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.
+ *
+ * This program 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+/* These are for GICv2 emulation only */
+#define GICH_LR_VIRTUALID (0x3ffUL << 0)
+#define GICH_LR_PHYSID_CPUID_SHIFT (10)
+#define GICH_LR_PHYSID_CPUID (7UL << GICH_LR_PHYSID_CPUID_SHIFT)
+
+/*
+ * LRs are stored in reverse order in memory. make sure we index them
+ * correctly.
+ */
+#define LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr)
+
+static u32 ich_vtr_el2;
+
+static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+ struct vgic_lr lr_desc;
+ u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)];
+
+ lr_desc.irq = val & GICH_LR_VIRTUALID;
+ if (lr_desc.irq <= 15)
+ lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
+ else
+ lr_desc.source = 0;
+ lr_desc.state = 0;
+
+ if (val & ICH_LR_PENDING_BIT)
+ lr_desc.state |= LR_STATE_PENDING;
+ if (val & ICH_LR_ACTIVE_BIT)
+ lr_desc.state |= LR_STATE_ACTIVE;
+ if (val & ICH_LR_EOI)
+ lr_desc.state |= LR_EOI_INT;
+
+ return lr_desc;
+}
+
+static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ u64 lr_val = (((u32)lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) |
+ lr_desc.irq);
+
+ if (lr_desc.state & LR_STATE_PENDING)
+ lr_val |= ICH_LR_PENDING_BIT;
+ if (lr_desc.state & LR_STATE_ACTIVE)
+ lr_val |= ICH_LR_ACTIVE_BIT;
+ if (lr_desc.state & LR_EOI_INT)
+ lr_val |= ICH_LR_EOI;
+
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)] = lr_val;
+}
+
+static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ if (!(lr_desc.state & LR_STATE_MASK))
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
+}
+
+static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr;
+}
+
+static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr;
+}
+
+static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu)
+{
+ u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr;
+ u32 ret = 0;
+
+ if (misr & ICH_MISR_EOI)
+ ret |= INT_STATUS_EOI;
+ if (misr & ICH_MISR_U)
+ ret |= INT_STATUS_UNDERFLOW;
+
+ return ret;
+}
+
+static void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr;
+
+ vmcrp->ctlr = (vmcr & ICH_VMCR_CTLR_MASK) >> ICH_VMCR_CTLR_SHIFT;
+ vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
+ vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
+ vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
+}
+
+static void vgic_v3_enable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr |= ICH_HCR_UIE;
+}
+
+static void vgic_v3_disable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr &= ~ICH_HCR_UIE;
+}
+
+static void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr;
+
+ vmcr = (vmcrp->ctlr << ICH_VMCR_CTLR_SHIFT) & ICH_VMCR_CTLR_MASK;
+ vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
+ vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
+ vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
+
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr;
+}
+
+static void vgic_v3_enable(struct kvm_vcpu *vcpu)
+{
+ /*
+ * By forcing VMCR to zero, the GIC will restore the binary
+ * points to their reset values. Anything else resets to zero
+ * anyway.
+ */
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = 0;
+
+ /* Get the show on the road... */
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr = ICH_HCR_EN;
+}
+
+static const struct vgic_ops vgic_v3_ops = {
+ .get_lr = vgic_v3_get_lr,
+ .set_lr = vgic_v3_set_lr,
+ .sync_lr_elrsr = vgic_v3_sync_lr_elrsr,
+ .get_elrsr = vgic_v3_get_elrsr,
+ .get_eisr = vgic_v3_get_eisr,
+ .get_interrupt_status = vgic_v3_get_interrupt_status,
+ .enable_underflow = vgic_v3_enable_underflow,
+ .disable_underflow = vgic_v3_disable_underflow,
+ .get_vmcr = vgic_v3_get_vmcr,
+ .set_vmcr = vgic_v3_set_vmcr,
+ .enable = vgic_v3_enable,
+};
+
+static struct vgic_params vgic_v3_params;
+
+/**
+ * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
+ * @node: pointer to the DT node
+ * @ops: address of a pointer to the GICv3 operations
+ * @params: address of a pointer to HW-specific parameters
+ *
+ * Returns 0 if a GICv3 has been found, with the low level operations
+ * in *ops and the HW parameters in *params. Returns an error code
+ * otherwise.
+ */
+int vgic_v3_probe(struct device_node *vgic_node,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params)
+{
+ int ret = 0;
+ u32 gicv_idx;
+ struct resource vcpu_res;
+ struct vgic_params *vgic = &vgic_v3_params;
+
+ vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
+ if (!vgic->maint_irq) {
+ kvm_err("error getting vgic maintenance irq from DT\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2);
+
+ /*
+ * The ListRegs field is 5 bits, but there is a architectural
+ * maximum of 16 list registers. Just ignore bit 4...
+ */
+ vgic->nr_lr = (ich_vtr_el2 & 0xf) + 1;
+
+ if (of_property_read_u32(vgic_node, "#redistributor-regions", &gicv_idx))
+ gicv_idx = 1;
+
+ gicv_idx += 3; /* Also skip GICD, GICC, GICH */
+ if (of_address_to_resource(vgic_node, gicv_idx, &vcpu_res)) {
+ kvm_err("Cannot obtain GICV region\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!PAGE_ALIGNED(vcpu_res.start)) {
+ kvm_err("GICV physical address 0x%llx not page aligned\n",
+ (unsigned long long)vcpu_res.start);
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+ kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+ (unsigned long long)resource_size(&vcpu_res),
+ PAGE_SIZE);
+ ret = -ENXIO;
+ goto out;
+ }
+
+ vgic->vcpu_base = vcpu_res.start;
+ vgic->vctrl_base = NULL;
+ vgic->type = VGIC_V3;
+
+ kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+ vcpu_res.start, vgic->maint_irq);
+
+ *ops = &vgic_v3_ops;
+ *params = vgic;
+
+out:
+ of_node_put(vgic_node);
+ return ret;
+}
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 8ca405cd7c1a..73eba793b17f 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -76,14 +76,6 @@
#define IMPLEMENTER_ARM 0x43b
#define GICC_ARCH_VERSION_V2 0x2
-/* Physical address of vgic virtual cpu interface */
-static phys_addr_t vgic_vcpu_base;
-
-/* Virtual control interface base address */
-static void __iomem *vgic_vctrl_base;
-
-static struct device_node *vgic_node;
-
#define ACCESS_READ_VALUE (1 << 0)
#define ACCESS_READ_RAZ (0 << 0)
#define ACCESS_READ_MASK(x) ((x) & (1 << 0))
@@ -94,21 +86,46 @@ static struct device_node *vgic_node;
#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1))
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
+static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
static void vgic_update_state(struct kvm *kvm);
static void vgic_kick_vcpus(struct kvm *kvm);
static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
-static u32 vgic_nr_lr;
+static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
+static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
+static void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-static unsigned int vgic_maint_irq;
+static const struct vgic_ops *vgic_ops;
+static const struct vgic_params *vgic;
+
+/*
+ * struct vgic_bitmap contains unions that provide two views of
+ * the same data. In one case it is an array of registers of
+ * u32's, and in the other case it is a bitmap of unsigned
+ * longs.
+ *
+ * This does not work on 64-bit BE systems, because the bitmap access
+ * will store two consecutive 32-bit words with the higher-addressed
+ * register's bits at the lower index and the lower-addressed register's
+ * bits at the higher index.
+ *
+ * Therefore, swizzle the register index when accessing the 32-bit word
+ * registers to access the right register's value.
+ */
+#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 64
+#define REG_OFFSET_SWIZZLE 1
+#else
+#define REG_OFFSET_SWIZZLE 0
+#endif
static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
int cpuid, u32 offset)
{
offset >>= 2;
if (!offset)
- return x->percpu[cpuid].reg;
+ return x->percpu[cpuid].reg + (offset ^ REG_OFFSET_SWIZZLE);
else
- return x->shared.reg + offset - 1;
+ return x->shared.reg + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
}
static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
@@ -241,12 +258,12 @@ static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
{
- return *((u32 *)mmio->data) & mask;
+ return le32_to_cpu(*((u32 *)mmio->data)) & mask;
}
static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
{
- *((u32 *)mmio->data) = value & mask;
+ *((u32 *)mmio->data) = cpu_to_le32(value) & mask;
}
/**
@@ -548,11 +565,10 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
u32 val;
u32 *reg;
- offset >>= 1;
reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
- vcpu->vcpu_id, offset);
+ vcpu->vcpu_id, offset >> 1);
- if (offset & 2)
+ if (offset & 4)
val = *reg >> 16;
else
val = *reg & 0xffff;
@@ -561,13 +577,13 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
vgic_reg_access(mmio, &val, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
if (mmio->is_write) {
- if (offset < 4) {
+ if (offset < 8) {
*reg = ~0U; /* Force PPIs/SGIs to 1 */
return false;
}
val = vgic_cfg_compress(val);
- if (offset & 2) {
+ if (offset & 4) {
*reg &= 0xffff;
*reg |= val << 16;
} else {
@@ -594,18 +610,6 @@ static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
return false;
}
-#define LR_CPUID(lr) \
- (((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT)
-#define LR_IRQID(lr) \
- ((lr) & GICH_LR_VIRTUALID)
-
-static void vgic_retire_lr(int lr_nr, int irq, struct vgic_cpu *vgic_cpu)
-{
- clear_bit(lr_nr, vgic_cpu->lr_used);
- vgic_cpu->vgic_lr[lr_nr] &= ~GICH_LR_STATE;
- vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
-}
-
/**
* vgic_unqueue_irqs - move pending IRQs from LRs to the distributor
* @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
@@ -623,13 +627,10 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
int vcpu_id = vcpu->vcpu_id;
- int i, irq, source_cpu;
- u32 *lr;
+ int i;
for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
- lr = &vgic_cpu->vgic_lr[i];
- irq = LR_IRQID(*lr);
- source_cpu = LR_CPUID(*lr);
+ struct vgic_lr lr = vgic_get_lr(vcpu, i);
/*
* There are three options for the state bits:
@@ -641,7 +642,7 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
* If the LR holds only an active interrupt (not pending) then
* just leave it alone.
*/
- if ((*lr & GICH_LR_STATE) == GICH_LR_ACTIVE_BIT)
+ if ((lr.state & LR_STATE_MASK) == LR_STATE_ACTIVE)
continue;
/*
@@ -650,18 +651,19 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
* is fine, then we are only setting a few bits that were
* already set.
*/
- vgic_dist_irq_set(vcpu, irq);
- if (irq < VGIC_NR_SGIS)
- dist->irq_sgi_sources[vcpu_id][irq] |= 1 << source_cpu;
- *lr &= ~GICH_LR_PENDING_BIT;
+ vgic_dist_irq_set(vcpu, lr.irq);
+ if (lr.irq < VGIC_NR_SGIS)
+ dist->irq_sgi_sources[vcpu_id][lr.irq] |= 1 << lr.source;
+ lr.state &= ~LR_STATE_PENDING;
+ vgic_set_lr(vcpu, i, lr);
/*
* If there's no state left on the LR (it could still be
* active), then the LR does not hold any useful info and can
* be marked as free for other use.
*/
- if (!(*lr & GICH_LR_STATE))
- vgic_retire_lr(i, irq, vgic_cpu);
+ if (!(lr.state & LR_STATE_MASK))
+ vgic_retire_lr(i, lr.irq, vcpu);
/* Finally update the VGIC state. */
vgic_update_state(vcpu->kvm);
@@ -916,6 +918,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
case 0:
if (!target_cpus)
return;
+ break;
case 1:
target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
@@ -989,8 +992,73 @@ static void vgic_update_state(struct kvm *kvm)
}
}
-#define MK_LR_PEND(src, irq) \
- (GICH_LR_PENDING_BIT | ((src) << GICH_LR_PHYSID_CPUID_SHIFT) | (irq))
+static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+ return vgic_ops->get_lr(vcpu, lr);
+}
+
+static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr vlr)
+{
+ vgic_ops->set_lr(vcpu, lr, vlr);
+}
+
+static void vgic_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr vlr)
+{
+ vgic_ops->sync_lr_elrsr(vcpu, lr, vlr);
+}
+
+static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu)
+{
+ return vgic_ops->get_elrsr(vcpu);
+}
+
+static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu)
+{
+ return vgic_ops->get_eisr(vcpu);
+}
+
+static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
+{
+ return vgic_ops->get_interrupt_status(vcpu);
+}
+
+static inline void vgic_enable_underflow(struct kvm_vcpu *vcpu)
+{
+ vgic_ops->enable_underflow(vcpu);
+}
+
+static inline void vgic_disable_underflow(struct kvm_vcpu *vcpu)
+{
+ vgic_ops->disable_underflow(vcpu);
+}
+
+static inline void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+ vgic_ops->get_vmcr(vcpu, vmcr);
+}
+
+static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+ vgic_ops->set_vmcr(vcpu, vmcr);
+}
+
+static inline void vgic_enable(struct kvm_vcpu *vcpu)
+{
+ vgic_ops->enable(vcpu);
+}
+
+static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr);
+
+ vlr.state = 0;
+ vgic_set_lr(vcpu, lr_nr, vlr);
+ clear_bit(lr_nr, vgic_cpu->lr_used);
+ vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+}
/*
* An interrupt may have been disabled after being made pending on the
@@ -1006,13 +1074,13 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
int lr;
- for_each_set_bit(lr, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
- int irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
+ for_each_set_bit(lr, vgic_cpu->lr_used, vgic->nr_lr) {
+ struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
- if (!vgic_irq_is_enabled(vcpu, irq)) {
- vgic_retire_lr(lr, irq, vgic_cpu);
- if (vgic_irq_is_active(vcpu, irq))
- vgic_irq_clear_active(vcpu, irq);
+ if (!vgic_irq_is_enabled(vcpu, vlr.irq)) {
+ vgic_retire_lr(lr, vlr.irq, vcpu);
+ if (vgic_irq_is_active(vcpu, vlr.irq))
+ vgic_irq_clear_active(vcpu, vlr.irq);
}
}
}
@@ -1024,6 +1092,7 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_lr vlr;
int lr;
/* Sanitize the input... */
@@ -1036,28 +1105,34 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
lr = vgic_cpu->vgic_irq_lr_map[irq];
/* Do we have an active interrupt for the same CPUID? */
- if (lr != LR_EMPTY &&
- (LR_CPUID(vgic_cpu->vgic_lr[lr]) == sgi_source_id)) {
- kvm_debug("LR%d piggyback for IRQ%d %x\n",
- lr, irq, vgic_cpu->vgic_lr[lr]);
- BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
- vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;
- return true;
+ if (lr != LR_EMPTY) {
+ vlr = vgic_get_lr(vcpu, lr);
+ if (vlr.source == sgi_source_id) {
+ kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
+ BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
+ vlr.state |= LR_STATE_PENDING;
+ vgic_set_lr(vcpu, lr, vlr);
+ return true;
+ }
}
/* Try to use another LR for this interrupt */
lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used,
- vgic_cpu->nr_lr);
- if (lr >= vgic_cpu->nr_lr)
+ vgic->nr_lr);
+ if (lr >= vgic->nr_lr)
return false;
kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id);
- vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq);
vgic_cpu->vgic_irq_lr_map[irq] = lr;
set_bit(lr, vgic_cpu->lr_used);
+ vlr.irq = irq;
+ vlr.source = sgi_source_id;
+ vlr.state = LR_STATE_PENDING;
if (!vgic_irq_is_edge(vcpu, irq))
- vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;
+ vlr.state |= LR_EOI_INT;
+
+ vgic_set_lr(vcpu, lr, vlr);
return true;
}
@@ -1155,9 +1230,9 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
epilog:
if (overflow) {
- vgic_cpu->vgic_hcr |= GICH_HCR_UIE;
+ vgic_enable_underflow(vcpu);
} else {
- vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
+ vgic_disable_underflow(vcpu);
/*
* We're about to run this VCPU, and we've consumed
* everything the distributor had in store for
@@ -1170,44 +1245,46 @@ epilog:
static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ u32 status = vgic_get_interrupt_status(vcpu);
bool level_pending = false;
- kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);
+ kvm_debug("STATUS = %08x\n", status);
- if (vgic_cpu->vgic_misr & GICH_MISR_EOI) {
+ if (status & INT_STATUS_EOI) {
/*
* Some level interrupts have been EOIed. Clear their
* active bit.
*/
- int lr, irq;
+ u64 eisr = vgic_get_eisr(vcpu);
+ unsigned long *eisr_ptr = (unsigned long *)&eisr;
+ int lr;
- for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_eisr,
- vgic_cpu->nr_lr) {
- irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
+ for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
+ struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
- vgic_irq_clear_active(vcpu, irq);
- vgic_cpu->vgic_lr[lr] &= ~GICH_LR_EOI;
+ vgic_irq_clear_active(vcpu, vlr.irq);
+ WARN_ON(vlr.state & LR_STATE_MASK);
+ vlr.state = 0;
+ vgic_set_lr(vcpu, lr, vlr);
/* Any additional pending interrupt? */
- if (vgic_dist_irq_is_pending(vcpu, irq)) {
- vgic_cpu_irq_set(vcpu, irq);
+ if (vgic_dist_irq_is_pending(vcpu, vlr.irq)) {
+ vgic_cpu_irq_set(vcpu, vlr.irq);
level_pending = true;
} else {
- vgic_cpu_irq_clear(vcpu, irq);
+ vgic_cpu_irq_clear(vcpu, vlr.irq);
}
/*
* Despite being EOIed, the LR may not have
* been marked as empty.
*/
- set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
- vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT;
+ vgic_sync_lr_elrsr(vcpu, lr, vlr);
}
}
- if (vgic_cpu->vgic_misr & GICH_MISR_U)
- vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
+ if (status & INT_STATUS_UNDERFLOW)
+ vgic_disable_underflow(vcpu);
return level_pending;
}
@@ -1220,29 +1297,31 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ u64 elrsr;
+ unsigned long *elrsr_ptr;
int lr, pending;
bool level_pending;
level_pending = vgic_process_maintenance(vcpu);
+ elrsr = vgic_get_elrsr(vcpu);
+ elrsr_ptr = (unsigned long *)&elrsr;
/* Clear mappings for empty LRs */
- for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr,
- vgic_cpu->nr_lr) {
- int irq;
+ for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) {
+ struct vgic_lr vlr;
if (!test_and_clear_bit(lr, vgic_cpu->lr_used))
continue;
- irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
+ vlr = vgic_get_lr(vcpu, lr);
- BUG_ON(irq >= VGIC_NR_IRQS);
- vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+ BUG_ON(vlr.irq >= VGIC_NR_IRQS);
+ vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
}
/* Check if we still have something up our sleeve... */
- pending = find_first_zero_bit((unsigned long *)vgic_cpu->vgic_elrsr,
- vgic_cpu->nr_lr);
- if (level_pending || pending < vgic_cpu->nr_lr)
+ pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
+ if (level_pending || pending < vgic->nr_lr)
set_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
}
@@ -1432,21 +1511,20 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
}
/*
- * By forcing VMCR to zero, the GIC will restore the binary
- * points to their reset values. Anything else resets to zero
- * anyway.
+ * Store the number of LRs per vcpu, so we don't have to go
+ * all the way to the distributor structure to find out. Only
+ * assembly code should use this one.
*/
- vgic_cpu->vgic_vmcr = 0;
+ vgic_cpu->nr_lr = vgic->nr_lr;
- vgic_cpu->nr_lr = vgic_nr_lr;
- vgic_cpu->vgic_hcr = GICH_HCR_EN; /* Get the show on the road... */
+ vgic_enable(vcpu);
return 0;
}
static void vgic_init_maintenance_interrupt(void *info)
{
- enable_percpu_irq(vgic_maint_irq, 0);
+ enable_percpu_irq(vgic->maint_irq, 0);
}
static int vgic_cpu_notify(struct notifier_block *self,
@@ -1459,7 +1537,7 @@ static int vgic_cpu_notify(struct notifier_block *self,
break;
case CPU_DYING:
case CPU_DYING_FROZEN:
- disable_percpu_irq(vgic_maint_irq);
+ disable_percpu_irq(vgic->maint_irq);
break;
}
@@ -1470,81 +1548,54 @@ static struct notifier_block vgic_cpu_nb = {
.notifier_call = vgic_cpu_notify,
};
+static const struct of_device_id vgic_ids[] = {
+ { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
+ { .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
+ {},
+};
+
int kvm_vgic_hyp_init(void)
{
+ const struct of_device_id *matched_id;
+ int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
+ const struct vgic_params **);
+ struct device_node *vgic_node;
int ret;
- struct resource vctrl_res;
- struct resource vcpu_res;
- vgic_node = of_find_compatible_node(NULL, NULL, "arm,cortex-a15-gic");
+ vgic_node = of_find_matching_node_and_match(NULL,
+ vgic_ids, &matched_id);
if (!vgic_node) {
- kvm_err("error: no compatible vgic node in DT\n");
+ kvm_err("error: no compatible GIC node found\n");
return -ENODEV;
}
- vgic_maint_irq = irq_of_parse_and_map(vgic_node, 0);
- if (!vgic_maint_irq) {
- kvm_err("error getting vgic maintenance irq from DT\n");
- ret = -ENXIO;
- goto out;
- }
+ vgic_probe = matched_id->data;
+ ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
+ if (ret)
+ return ret;
- ret = request_percpu_irq(vgic_maint_irq, vgic_maintenance_handler,
+ ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
"vgic", kvm_get_running_vcpus());
if (ret) {
- kvm_err("Cannot register interrupt %d\n", vgic_maint_irq);
- goto out;
+ kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
+ return ret;
}
- ret = register_cpu_notifier(&vgic_cpu_nb);
+ ret = __register_cpu_notifier(&vgic_cpu_nb);
if (ret) {
kvm_err("Cannot register vgic CPU notifier\n");
goto out_free_irq;
}
- ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
- if (ret) {
- kvm_err("Cannot obtain VCTRL resource\n");
- goto out_free_irq;
- }
-
- vgic_vctrl_base = of_iomap(vgic_node, 2);
- if (!vgic_vctrl_base) {
- kvm_err("Cannot ioremap VCTRL\n");
- ret = -ENOMEM;
- goto out_free_irq;
- }
-
- vgic_nr_lr = readl_relaxed(vgic_vctrl_base + GICH_VTR);
- vgic_nr_lr = (vgic_nr_lr & 0x3f) + 1;
-
- ret = create_hyp_io_mappings(vgic_vctrl_base,
- vgic_vctrl_base + resource_size(&vctrl_res),
- vctrl_res.start);
- if (ret) {
- kvm_err("Cannot map VCTRL into hyp\n");
- goto out_unmap;
- }
+ /* Callback into for arch code for setup */
+ vgic_arch_setup(vgic);
- kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
- vctrl_res.start, vgic_maint_irq);
on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
- if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
- kvm_err("Cannot obtain VCPU resource\n");
- ret = -ENXIO;
- goto out_unmap;
- }
- vgic_vcpu_base = vcpu_res.start;
-
- goto out;
+ return 0;
-out_unmap:
- iounmap(vgic_vctrl_base);
out_free_irq:
- free_percpu_irq(vgic_maint_irq, kvm_get_running_vcpus());
-out:
- of_node_put(vgic_node);
+ free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
return ret;
}
@@ -1577,7 +1628,7 @@ int kvm_vgic_init(struct kvm *kvm)
}
ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
- vgic_vcpu_base, KVM_VGIC_V2_CPU_SIZE);
+ vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE);
if (ret) {
kvm_err("Unable to remap VGIC CPU to VCPU\n");
goto out;
@@ -1623,7 +1674,8 @@ int kvm_vgic_create(struct kvm *kvm)
}
spin_lock_init(&kvm->arch.vgic.lock);
- kvm->arch.vgic.vctrl_base = vgic_vctrl_base;
+ kvm->arch.vgic.in_kernel = true;
+ kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
@@ -1667,10 +1719,11 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
if (addr + size < addr)
return -EINVAL;
+ *ioaddr = addr;
ret = vgic_ioaddr_overlap(kvm);
if (ret)
- return ret;
- *ioaddr = addr;
+ *ioaddr = VGIC_ADDR_UNDEF;
+
return ret;
}
@@ -1721,39 +1774,40 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
static bool handle_cpu_mmio_misc(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- u32 reg, mask = 0, shift = 0;
bool updated = false;
+ struct vgic_vmcr vmcr;
+ u32 *vmcr_field;
+ u32 reg;
+
+ vgic_get_vmcr(vcpu, &vmcr);
switch (offset & ~0x3) {
case GIC_CPU_CTRL:
- mask = GICH_VMCR_CTRL_MASK;
- shift = GICH_VMCR_CTRL_SHIFT;
+ vmcr_field = &vmcr.ctlr;
break;
case GIC_CPU_PRIMASK:
- mask = GICH_VMCR_PRIMASK_MASK;
- shift = GICH_VMCR_PRIMASK_SHIFT;
+ vmcr_field = &vmcr.pmr;
break;
case GIC_CPU_BINPOINT:
- mask = GICH_VMCR_BINPOINT_MASK;
- shift = GICH_VMCR_BINPOINT_SHIFT;
+ vmcr_field = &vmcr.bpr;
break;
case GIC_CPU_ALIAS_BINPOINT:
- mask = GICH_VMCR_ALIAS_BINPOINT_MASK;
- shift = GICH_VMCR_ALIAS_BINPOINT_SHIFT;
+ vmcr_field = &vmcr.abpr;
break;
+ default:
+ BUG();
}
if (!mmio->is_write) {
- reg = (vgic_cpu->vgic_vmcr & mask) >> shift;
+ reg = *vmcr_field;
mmio_data_write(mmio, ~0, reg);
} else {
reg = mmio_data_read(mmio, ~0);
- reg = (reg << shift) & mask;
- if (reg != (vgic_cpu->vgic_vmcr & mask))
+ if (reg != *vmcr_field) {
+ *vmcr_field = reg;
+ vgic_set_vmcr(vcpu, &vmcr);
updated = true;
- vgic_cpu->vgic_vmcr &= ~mask;
- vgic_cpu->vgic_vmcr |= reg;
+ }
}
return updated;
}
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 8db43701016f..5819a2708d7e 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -395,7 +395,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
if (dev->entries_nr == 0)
return r;
- r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
+ r = pci_enable_msix_exact(dev->dev,
+ dev->host_msix_entries, dev->entries_nr);
if (r)
return r;
@@ -525,8 +526,10 @@ static int assign_guest_irq(struct kvm *kvm,
dev->irq_requested_type |= guest_irq_type;
if (dev->ack_notifier.gsi != -1)
kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
- } else
+ } else {
kvm_free_irq_source_id(kvm, dev->irq_source_id);
+ dev->irq_source_id = -1;
+ }
return r;
}
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8631d9c14320..d6a3d0993d88 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -28,6 +28,21 @@
#include "async_pf.h"
#include <trace/events/kvm.h>
+static inline void kvm_async_page_present_sync(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+#ifdef CONFIG_KVM_ASYNC_PF_SYNC
+ kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+static inline void kvm_async_page_present_async(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+#ifndef CONFIG_KVM_ASYNC_PF_SYNC
+ kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+
static struct kmem_cache *async_pf_cache;
int kvm_async_pf_init(void)
@@ -65,11 +80,10 @@ static void async_pf_execute(struct work_struct *work)
might_sleep();
- use_mm(mm);
down_read(&mm->mmap_sem);
- get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL);
+ get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL);
up_read(&mm->mmap_sem);
- unuse_mm(mm);
+ kvm_async_page_present_sync(vcpu, apf);
spin_lock(&vcpu->async_pf.lock);
list_add_tail(&apf->link, &vcpu->async_pf.done);
@@ -85,7 +99,7 @@ static void async_pf_execute(struct work_struct *work)
if (waitqueue_active(&vcpu->wq))
wake_up_interruptible(&vcpu->wq);
- mmdrop(mm);
+ mmput(mm);
kvm_put_kvm(vcpu->kvm);
}
@@ -97,11 +111,16 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
list_entry(vcpu->async_pf.queue.next,
typeof(*work), queue);
list_del(&work->queue);
+
+#ifdef CONFIG_KVM_ASYNC_PF_SYNC
+ flush_work(&work->work);
+#else
if (cancel_work_sync(&work->work)) {
- mmdrop(work->mm);
+ mmput(work->mm);
kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
kmem_cache_free(async_pf_cache, work);
}
+#endif
}
spin_lock(&vcpu->async_pf.lock);
@@ -130,7 +149,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
spin_unlock(&vcpu->async_pf.lock);
kvm_arch_async_page_ready(vcpu, work);
- kvm_arch_async_page_present(vcpu, work);
+ kvm_async_page_present_async(vcpu, work);
list_del(&work->queue);
vcpu->async_pf.queued--;
@@ -138,7 +157,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
}
}
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
struct kvm_arch_async_pf *arch)
{
struct kvm_async_pf *work;
@@ -159,10 +178,10 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
work->wakeup_all = false;
work->vcpu = vcpu;
work->gva = gva;
- work->addr = gfn_to_hva(vcpu->kvm, gfn);
+ work->addr = hva;
work->arch = *arch;
work->mm = current->mm;
- atomic_inc(&work->mm->mm_count);
+ atomic_inc(&work->mm->mm_users);
kvm_get_kvm(work->vcpu->kvm);
/* this can't really happen otherwise gfn_to_pfn_async
@@ -180,7 +199,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
return 1;
retry_sync:
kvm_put_kvm(work->vcpu->kvm);
- mmdrop(work->mm);
+ mmput(work->mm);
kmem_cache_free(async_pf_cache, work);
return 0;
}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index abe4d6043b36..3c5981c87c3f 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -31,11 +31,15 @@
#include <linux/list.h>
#include <linux/eventfd.h>
#include <linux/kernel.h>
+#include <linux/srcu.h>
#include <linux/slab.h>
+#include <linux/seqlock.h>
+#include <trace/events/kvm.h>
+#include "irq.h"
#include "iodev.h"
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
/*
* --------------------------------------------------------------------
* irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -74,7 +78,8 @@ struct _irqfd {
struct kvm *kvm;
wait_queue_t wait;
/* Update side is protected by irqfds.lock */
- struct kvm_kernel_irq_routing_entry __rcu *irq_entry;
+ struct kvm_kernel_irq_routing_entry irq_entry;
+ seqcount_t irq_entry_sc;
/* Used for level IRQ fast-path */
int gsi;
struct work_struct inject;
@@ -118,19 +123,22 @@ static void
irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
{
struct _irqfd_resampler *resampler;
+ struct kvm *kvm;
struct _irqfd *irqfd;
+ int idx;
resampler = container_of(kian, struct _irqfd_resampler, notifier);
+ kvm = resampler->kvm;
- kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
resampler->notifier.gsi, 0, false);
- rcu_read_lock();
+ idx = srcu_read_lock(&kvm->irq_srcu);
list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
eventfd_signal(irqfd->resamplefd, 1);
- rcu_read_unlock();
+ srcu_read_unlock(&kvm->irq_srcu, idx);
}
static void
@@ -142,7 +150,7 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd)
mutex_lock(&kvm->irqfds.resampler_lock);
list_del_rcu(&irqfd->resampler_link);
- synchronize_rcu();
+ synchronize_srcu(&kvm->irq_srcu);
if (list_empty(&resampler->list)) {
list_del(&resampler->link);
@@ -219,19 +227,24 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
unsigned long flags = (unsigned long)key;
- struct kvm_kernel_irq_routing_entry *irq;
+ struct kvm_kernel_irq_routing_entry irq;
struct kvm *kvm = irqfd->kvm;
+ unsigned seq;
+ int idx;
if (flags & POLLIN) {
- rcu_read_lock();
- irq = rcu_dereference(irqfd->irq_entry);
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ do {
+ seq = read_seqcount_begin(&irqfd->irq_entry_sc);
+ irq = irqfd->irq_entry;
+ } while (read_seqcount_retry(&irqfd->irq_entry_sc, seq));
/* An event has been signaled, inject an interrupt */
- if (irq)
- kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
+ if (irq.type == KVM_IRQ_ROUTING_MSI)
+ kvm_set_msi(&irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
false);
else
schedule_work(&irqfd->inject);
- rcu_read_unlock();
+ srcu_read_unlock(&kvm->irq_srcu, idx);
}
if (flags & POLLHUP) {
@@ -267,34 +280,37 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
}
/* Must be called under irqfds.lock */
-static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
- struct kvm_irq_routing_table *irq_rt)
+static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd)
{
struct kvm_kernel_irq_routing_entry *e;
+ struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
+ int i, n_entries;
- if (irqfd->gsi >= irq_rt->nr_rt_entries) {
- rcu_assign_pointer(irqfd->irq_entry, NULL);
- return;
- }
+ n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi);
+
+ write_seqcount_begin(&irqfd->irq_entry_sc);
- hlist_for_each_entry(e, &irq_rt->map[irqfd->gsi], link) {
+ irqfd->irq_entry.type = 0;
+
+ e = entries;
+ for (i = 0; i < n_entries; ++i, ++e) {
/* Only fast-path MSI. */
if (e->type == KVM_IRQ_ROUTING_MSI)
- rcu_assign_pointer(irqfd->irq_entry, e);
- else
- rcu_assign_pointer(irqfd->irq_entry, NULL);
+ irqfd->irq_entry = *e;
}
+
+ write_seqcount_end(&irqfd->irq_entry_sc);
}
static int
kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
{
- struct kvm_irq_routing_table *irq_rt;
struct _irqfd *irqfd, *tmp;
struct fd f;
struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
int ret;
unsigned int events;
+ int idx;
irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
if (!irqfd)
@@ -305,6 +321,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
INIT_LIST_HEAD(&irqfd->list);
INIT_WORK(&irqfd->inject, irqfd_inject);
INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
+ seqcount_init(&irqfd->irq_entry_sc);
f = fdget(args->fd);
if (!f.file) {
@@ -363,7 +380,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
}
list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
- synchronize_rcu();
+ synchronize_srcu(&kvm->irq_srcu);
mutex_unlock(&kvm->irqfds.resampler_lock);
}
@@ -387,23 +404,23 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
goto fail;
}
- irq_rt = rcu_dereference_protected(kvm->irq_routing,
- lockdep_is_held(&kvm->irqfds.lock));
- irqfd_update(kvm, irqfd, irq_rt);
-
- events = f.file->f_op->poll(f.file, &irqfd->pt);
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ irqfd_update(kvm, irqfd);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
list_add_tail(&irqfd->list, &kvm->irqfds.items);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
/*
* Check if there was an event already pending on the eventfd
* before we registered, and trigger it as if we didn't miss it.
*/
+ events = f.file->f_op->poll(f.file, &irqfd->pt);
+
if (events & POLLIN)
schedule_work(&irqfd->inject);
- spin_unlock_irq(&kvm->irqfds.lock);
-
/*
* do not drop the file until the irqfd is fully initialized, otherwise
* we might race against the POLLHUP
@@ -428,12 +445,73 @@ out:
kfree(irqfd);
return ret;
}
+
+bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ struct kvm_irq_ack_notifier *kian;
+ int gsi, idx;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
+ link)
+ if (kian->gsi == gsi) {
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return true;
+ }
+
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
+
+void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ struct kvm_irq_ack_notifier *kian;
+ int gsi, idx;
+
+ trace_kvm_ack_irq(irqchip, pin);
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
+ link)
+ if (kian->gsi == gsi)
+ kian->irq_acked(kian);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+void kvm_register_irq_ack_notifier(struct kvm *kvm,
+ struct kvm_irq_ack_notifier *kian)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
+ mutex_unlock(&kvm->irq_lock);
+#ifdef __KVM_HAVE_IOAPIC
+ kvm_vcpu_request_scan_ioapic(kvm);
+#endif
+}
+
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+ struct kvm_irq_ack_notifier *kian)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_del_init_rcu(&kian->link);
+ mutex_unlock(&kvm->irq_lock);
+ synchronize_srcu(&kvm->irq_srcu);
+#ifdef __KVM_HAVE_IOAPIC
+ kvm_vcpu_request_scan_ioapic(kvm);
+#endif
+}
#endif
void
kvm_eventfd_init(struct kvm *kvm)
{
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
spin_lock_init(&kvm->irqfds.lock);
INIT_LIST_HEAD(&kvm->irqfds.items);
INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
@@ -442,7 +520,7 @@ kvm_eventfd_init(struct kvm *kvm)
INIT_LIST_HEAD(&kvm->ioeventfds);
}
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
/*
* shutdown any irqfd's that match fd+gsi
*/
@@ -461,14 +539,14 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) {
/*
- * This rcu_assign_pointer is needed for when
+ * This clearing of irq_entry.type is needed for when
* another thread calls kvm_irq_routing_update before
* we flush workqueue below (we synchronize with
* kvm_irq_routing_update using irqfds.lock).
- * It is paired with synchronize_rcu done by caller
- * of that function.
*/
- rcu_assign_pointer(irqfd->irq_entry, NULL);
+ write_seqcount_begin(&irqfd->irq_entry_sc);
+ irqfd->irq_entry.type = 0;
+ write_seqcount_end(&irqfd->irq_entry_sc);
irqfd_deactivate(irqfd);
}
}
@@ -523,20 +601,17 @@ kvm_irqfd_release(struct kvm *kvm)
}
/*
- * Change irq_routing and irqfd.
- * Caller must invoke synchronize_rcu afterwards.
+ * Take note of a change in irq routing.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
*/
-void kvm_irq_routing_update(struct kvm *kvm,
- struct kvm_irq_routing_table *irq_rt)
+void kvm_irq_routing_update(struct kvm *kvm)
{
struct _irqfd *irqfd;
spin_lock_irq(&kvm->irqfds.lock);
- rcu_assign_pointer(kvm->irq_routing, irq_rt);
-
list_for_each_entry(irqfd, &kvm->irqfds.items, list)
- irqfd_update(kvm, irqfd, irq_rt);
+ irqfd_update(kvm, irqfd);
spin_unlock_irq(&kvm->irqfds.lock);
}
@@ -600,7 +675,15 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
{
u64 _val;
- if (!(addr == p->addr && len == p->length))
+ if (addr != p->addr)
+ /* address must be precise for a hit */
+ return false;
+
+ if (!p->length)
+ /* length = 0 means only look at the address, so always a hit */
+ return true;
+
+ if (len != p->length)
/* address-range must be precise for a hit */
return false;
@@ -671,9 +754,11 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
list_for_each_entry(_p, &kvm->ioeventfds, list)
if (_p->bus_idx == p->bus_idx &&
- _p->addr == p->addr && _p->length == p->length &&
- (_p->wildcard || p->wildcard ||
- _p->datamatch == p->datamatch))
+ _p->addr == p->addr &&
+ (!_p->length || !p->length ||
+ (_p->length == p->length &&
+ (_p->wildcard || p->wildcard ||
+ _p->datamatch == p->datamatch))))
return true;
return false;
@@ -697,8 +782,9 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
int ret;
bus_idx = ioeventfd_bus_from_flags(args->flags);
- /* must be natural-word sized */
+ /* must be natural-word sized, or 0 to ignore length */
switch (args->len) {
+ case 0:
case 1:
case 2:
case 4:
@@ -716,6 +802,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
return -EINVAL;
+ /* ioeventfd with no length can't be combined with DATAMATCH */
+ if (!args->len &&
+ args->flags & (KVM_IOEVENTFD_FLAG_PIO |
+ KVM_IOEVENTFD_FLAG_DATAMATCH))
+ return -EINVAL;
+
eventfd = eventfd_ctx_fdget(args->fd);
if (IS_ERR(eventfd))
return PTR_ERR(eventfd);
@@ -753,6 +845,16 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
if (ret < 0)
goto unlock_fail;
+ /* When length is ignored, MMIO is also put on a separate bus, for
+ * faster lookups.
+ */
+ if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) {
+ ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
+ p->addr, 0, &p->dev);
+ if (ret < 0)
+ goto register_fail;
+ }
+
kvm->buses[bus_idx]->ioeventfd_count++;
list_add_tail(&p->list, &kvm->ioeventfds);
@@ -760,6 +862,8 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
return 0;
+register_fail:
+ kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
unlock_fail:
mutex_unlock(&kvm->slots_lock);
@@ -799,6 +903,10 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
continue;
kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
+ if (!p->length) {
+ kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
+ &p->dev);
+ }
kvm->buses[bus_idx]->ioeventfd_count--;
ioeventfd_release(p);
ret = 0;
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index ce9ed99ad7dc..e8ce34c9db32 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -50,7 +50,7 @@
#else
#define ioapic_debug(fmt, arg...)
#endif
-static int ioapic_deliver(struct kvm_ioapic *vioapic, int irq,
+static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
bool line_status);
static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
@@ -97,6 +97,14 @@ static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS);
}
+static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
+
+static void rtc_status_pending_eoi_check_valid(struct kvm_ioapic *ioapic)
+{
+ if (WARN_ON(ioapic->rtc_status.pending_eoi < 0))
+ kvm_rtc_eoi_tracking_restore_all(ioapic);
+}
+
static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
{
bool new_val, old_val;
@@ -120,9 +128,8 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
} else {
__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
ioapic->rtc_status.pending_eoi--;
+ rtc_status_pending_eoi_check_valid(ioapic);
}
-
- WARN_ON(ioapic->rtc_status.pending_eoi < 0);
}
void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
@@ -149,10 +156,10 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
{
- if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map))
+ if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) {
--ioapic->rtc_status.pending_eoi;
-
- WARN_ON(ioapic->rtc_status.pending_eoi < 0);
+ rtc_status_pending_eoi_check_valid(ioapic);
+ }
}
static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
@@ -163,23 +170,67 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
return false;
}
-static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx,
- bool line_status)
+static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
+ int irq_level, bool line_status)
{
- union kvm_ioapic_redirect_entry *pent;
- int injected = -1;
+ union kvm_ioapic_redirect_entry entry;
+ u32 mask = 1 << irq;
+ u32 old_irr;
+ int edge, ret;
+
+ entry = ioapic->redirtbl[irq];
+ edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
+
+ if (!irq_level) {
+ ioapic->irr &= ~mask;
+ ret = 1;
+ goto out;
+ }
- pent = &ioapic->redirtbl[idx];
+ /*
+ * Return 0 for coalesced interrupts; for edge-triggered interrupts,
+ * this only happens if a previous edge has not been delivered due
+ * do masking. For level interrupts, the remote_irr field tells
+ * us if the interrupt is waiting for an EOI.
+ *
+ * RTC is special: it is edge-triggered, but userspace likes to know
+ * if it has been already ack-ed via EOI because coalesced RTC
+ * interrupts lead to time drift in Windows guests. So we track
+ * EOI manually for the RTC interrupt.
+ */
+ if (irq == RTC_GSI && line_status &&
+ rtc_irq_check_coalesced(ioapic)) {
+ ret = 0;
+ goto out;
+ }
- if (!pent->fields.mask) {
- injected = ioapic_deliver(ioapic, idx, line_status);
- if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG)
- pent->fields.remote_irr = 1;
+ old_irr = ioapic->irr;
+ ioapic->irr |= mask;
+ if ((edge && old_irr == ioapic->irr) ||
+ (!edge && entry.fields.remote_irr)) {
+ ret = 0;
+ goto out;
}
- return injected;
+ ret = ioapic_service(ioapic, irq, line_status);
+
+out:
+ trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
+ return ret;
}
+static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr)
+{
+ u32 idx;
+
+ rtc_irq_eoi_tracking_reset(ioapic);
+ for_each_set_bit(idx, &irr, IOAPIC_NUM_PINS)
+ ioapic_set_irq(ioapic, idx, 1, true);
+
+ kvm_rtc_eoi_tracking_restore_all(ioapic);
+}
+
+
static void update_handled_vectors(struct kvm_ioapic *ioapic)
{
DECLARE_BITMAP(handled_vectors, 256);
@@ -203,10 +254,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
spin_lock(&ioapic->lock);
for (index = 0; index < IOAPIC_NUM_PINS; index++) {
e = &ioapic->redirtbl[index];
- if (!e->fields.mask &&
- (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
- kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
- index) || index == RTC_GSI)) {
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+ kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+ index == RTC_GSI) {
if (kvm_apic_match_dest(vcpu, NULL, 0,
e->fields.dest_id, e->fields.dest_mode)) {
__set_bit(e->fields.vector,
@@ -282,12 +332,15 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
}
}
-static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
+static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
{
union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
struct kvm_lapic_irq irqe;
int ret;
+ if (entry->fields.mask)
+ return -1;
+
ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
"vector=%x trig_mode=%x\n",
entry->fields.dest_id, entry->fields.dest_mode,
@@ -302,53 +355,41 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
irqe.level = 1;
irqe.shorthand = 0;
+ if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
+ ioapic->irr &= ~(1 << irq);
+
if (irq == RTC_GSI && line_status) {
+ /*
+ * pending_eoi cannot ever become negative (see
+ * rtc_status_pending_eoi_check_valid) and the caller
+ * ensures that it is only called if it is >= zero, namely
+ * if rtc_irq_check_coalesced returns false).
+ */
BUG_ON(ioapic->rtc_status.pending_eoi != 0);
ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
ioapic->rtc_status.dest_map);
- ioapic->rtc_status.pending_eoi = ret;
+ ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
} else
ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
+ if (ret && irqe.trig_mode == IOAPIC_LEVEL_TRIG)
+ entry->fields.remote_irr = 1;
+
return ret;
}
int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
int level, bool line_status)
{
- u32 old_irr;
- u32 mask = 1 << irq;
- union kvm_ioapic_redirect_entry entry;
int ret, irq_level;
BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS);
spin_lock(&ioapic->lock);
- old_irr = ioapic->irr;
irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
irq_source_id, level);
- entry = ioapic->redirtbl[irq];
- irq_level ^= entry.fields.polarity;
- if (!irq_level) {
- ioapic->irr &= ~mask;
- ret = 1;
- } else {
- int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
+ ret = ioapic_set_irq(ioapic, irq, irq_level, line_status);
- if (irq == RTC_GSI && line_status &&
- rtc_irq_check_coalesced(ioapic)) {
- ret = 0; /* coalesced */
- goto out;
- }
- ioapic->irr |= mask;
- if ((edge && old_irr != ioapic->irr) ||
- (!edge && !entry.fields.remote_irr))
- ret = ioapic_service(ioapic, irq, line_status);
- else
- ret = 0; /* report coalesced interrupt */
- }
-out:
- trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
spin_unlock(&ioapic->lock);
return ret;
@@ -394,7 +435,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
ent->fields.remote_irr = 0;
- if (!ent->fields.mask && (ioapic->irr & (1 << i)))
+ if (ioapic->irr & (1 << i))
ioapic_service(ioapic, i, false);
}
}
@@ -595,9 +636,10 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
spin_lock(&ioapic->lock);
memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
+ ioapic->irr = 0;
update_handled_vectors(ioapic);
kvm_vcpu_request_scan_ioapic(kvm);
- kvm_rtc_eoi_tracking_restore_all(ioapic);
+ kvm_ioapic_inject_all(ioapic, state->irr);
spin_unlock(&ioapic->lock);
return 0;
}
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 0df7d4b34dfe..714b94932312 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
return pfn;
}
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+ unsigned long i;
+
+ for (i = 0; i < npages; ++i)
+ kvm_release_pfn_clean(pfn + i);
+}
+
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
gfn_t gfn, end_gfn;
@@ -123,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
if (r) {
printk(KERN_ERR "kvm_iommu_map_address:"
"iommu failed to map pfn=%llx\n", pfn);
+ kvm_unpin_pages(kvm, pfn, page_size);
goto unmap_pages;
}
@@ -134,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
return 0;
unmap_pages:
- kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
+ kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
return r;
}
@@ -266,14 +275,6 @@ out_unlock:
return r;
}
-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
-{
- unsigned long i;
-
- for (i = 0; i < npages; ++i)
- kvm_release_pfn_clean(pfn + i);
-}
-
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages)
{
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index e2e6b4473a96..963b8995a9e8 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -160,9 +160,10 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
*/
int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
{
+ struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
struct kvm_kernel_irq_routing_entry *e;
int ret = -EINVAL;
- struct kvm_irq_routing_table *irq_rt;
+ int idx;
trace_kvm_set_irq(irq, level, irq_source_id);
@@ -174,17 +175,15 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
* Since there's no easy way to do this, we only support injecting MSI
* which is limited to 1:1 GSI mapping.
*/
- rcu_read_lock();
- irq_rt = rcu_dereference(kvm->irq_routing);
- if (irq < irq_rt->nr_rt_entries)
- hlist_for_each_entry(e, &irq_rt->map[irq], link) {
- if (likely(e->type == KVM_IRQ_ROUTING_MSI))
- ret = kvm_set_msi_inatomic(e, kvm);
- else
- ret = -EWOULDBLOCK;
- break;
- }
- rcu_read_unlock();
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
+ e = &entries[0];
+ if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+ ret = kvm_set_msi_inatomic(e, kvm);
+ else
+ ret = -EWOULDBLOCK;
+ }
+ srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
}
@@ -253,26 +252,25 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
mutex_lock(&kvm->irq_lock);
hlist_del_rcu(&kimn->link);
mutex_unlock(&kvm->irq_lock);
- synchronize_rcu();
+ synchronize_srcu(&kvm->irq_srcu);
}
void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
bool mask)
{
struct kvm_irq_mask_notifier *kimn;
- int gsi;
+ int idx, gsi;
- rcu_read_lock();
- gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
if (gsi != -1)
hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
if (kimn->irq == gsi)
kimn->func(kimn, mask);
- rcu_read_unlock();
+ srcu_read_unlock(&kvm->irq_srcu, idx);
}
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
- struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
{
int r = -EINVAL;
@@ -303,7 +301,6 @@ int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
e->irqchip.pin = ue->u.irqchip.pin + delta;
if (e->irqchip.pin >= max_pin)
goto out;
- rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
break;
case KVM_IRQ_ROUTING_MSI:
e->set = kvm_set_msi;
@@ -322,13 +319,13 @@ out:
#define IOAPIC_ROUTING_ENTRY(irq) \
{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
- .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) }
+ .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
#ifdef CONFIG_X86
# define PIC_ROUTING_ENTRY(irq) \
{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
- .u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 }
+ .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
# define ROUTING_ENTRY2(irq) \
IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
#else
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 20dc9e4a8f6c..7f256f31df10 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -26,69 +26,47 @@
#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"
-bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
- struct kvm_irq_ack_notifier *kian;
- int gsi;
-
- rcu_read_lock();
- gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
- if (gsi != -1)
- hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
- link)
- if (kian->gsi == gsi) {
- rcu_read_unlock();
- return true;
- }
-
- rcu_read_unlock();
-
- return false;
-}
-EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
+struct kvm_irq_routing_table {
+ int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
+ struct kvm_kernel_irq_routing_entry *rt_entries;
+ 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];
+};
-void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries, int gsi)
{
- struct kvm_irq_ack_notifier *kian;
- int gsi;
-
- trace_kvm_ack_irq(irqchip, pin);
-
- rcu_read_lock();
- gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
- if (gsi != -1)
- hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
- link)
- if (kian->gsi == gsi)
- kian->irq_acked(kian);
- rcu_read_unlock();
-}
+ 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;
+ }
+ }
-void kvm_register_irq_ack_notifier(struct kvm *kvm,
- struct kvm_irq_ack_notifier *kian)
-{
- mutex_lock(&kvm->irq_lock);
- hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
- mutex_unlock(&kvm->irq_lock);
-#ifdef __KVM_HAVE_IOAPIC
- kvm_vcpu_request_scan_ioapic(kvm);
-#endif
+ return n;
}
-void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
- struct kvm_irq_ack_notifier *kian)
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
- mutex_lock(&kvm->irq_lock);
- hlist_del_init_rcu(&kian->link);
- mutex_unlock(&kvm->irq_lock);
- synchronize_rcu();
-#ifdef __KVM_HAVE_IOAPIC
- kvm_vcpu_request_scan_ioapic(kvm);
-#endif
+ 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)
@@ -114,9 +92,8 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
bool line_status)
{
- struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
- int ret = -1, i = 0;
- struct kvm_irq_routing_table *irq_rt;
+ 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);
@@ -124,12 +101,9 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
* IOAPIC. So set the bit in both. The guest will ignore
* writes to the unused one.
*/
- rcu_read_lock();
- irq_rt = rcu_dereference(kvm->irq_routing);
- if (irq < irq_rt->nr_rt_entries)
- hlist_for_each_entry(e, &irq_rt->map[irq], link)
- irq_set[i++] = *e;
- rcu_read_unlock();
+ 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;
@@ -170,9 +144,11 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt,
e->gsi = ue->gsi;
e->type = ue->type;
- r = kvm_set_routing_entry(rt, e, ue);
+ 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;
@@ -223,10 +199,11 @@ int kvm_set_irq_routing(struct kvm *kvm,
mutex_lock(&kvm->irq_lock);
old = kvm->irq_routing;
- kvm_irq_routing_update(kvm, new);
+ rcu_assign_pointer(kvm->irq_routing, new);
+ kvm_irq_routing_update(kvm);
mutex_unlock(&kvm->irq_lock);
- synchronize_rcu();
+ synchronize_srcu_expedited(&kvm->irq_srcu);
new = old;
r = 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 03a0381b1cb7..95519bc959ed 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -102,7 +102,7 @@ static void kvm_release_pfn_dirty(pfn_t pfn);
static void mark_page_dirty_in_slot(struct kvm *kvm,
struct kvm_memory_slot *memslot, gfn_t gfn);
-bool kvm_rebooting;
+__visible bool kvm_rebooting;
EXPORT_SYMBOL_GPL(kvm_rebooting);
static bool largepages_enabled = true;
@@ -110,7 +110,7 @@ static bool largepages_enabled = true;
bool kvm_is_mmio_pfn(pfn_t pfn)
{
if (pfn_valid(pfn))
- return PageReserved(pfn_to_page(pfn));
+ return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
return true;
}
@@ -457,14 +457,16 @@ static struct kvm *kvm_create_vm(unsigned long type)
r = kvm_arch_init_vm(kvm, type);
if (r)
- goto out_err_nodisable;
+ goto out_err_no_disable;
r = hardware_enable_all();
if (r)
- goto out_err_nodisable;
+ goto out_err_no_disable;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
INIT_HLIST_HEAD(&kvm->mask_notifier_list);
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
#endif
@@ -473,10 +475,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
r = -ENOMEM;
kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!kvm->memslots)
- goto out_err_nosrcu;
+ goto out_err_no_srcu;
kvm_init_memslots_id(kvm);
if (init_srcu_struct(&kvm->srcu))
- goto out_err_nosrcu;
+ goto out_err_no_srcu;
+ if (init_srcu_struct(&kvm->irq_srcu))
+ goto out_err_no_irq_srcu;
for (i = 0; i < KVM_NR_BUSES; i++) {
kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
GFP_KERNEL);
@@ -505,10 +509,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
return kvm;
out_err:
+ cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);
-out_err_nosrcu:
+out_err_no_srcu:
hardware_disable_all();
-out_err_nodisable:
+out_err_no_disable:
for (i = 0; i < KVM_NR_BUSES; i++)
kfree(kvm->buses[i]);
kfree(kvm->memslots);
@@ -604,6 +610,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
kvm_arch_destroy_vm(kvm);
kvm_destroy_devices(kvm);
kvm_free_physmem(kvm);
+ cleanup_srcu_struct(&kvm->irq_srcu);
cleanup_srcu_struct(&kvm->srcu);
kvm_arch_free_vm(kvm);
hardware_disable_all();
@@ -640,14 +647,12 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
*/
static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
{
-#ifndef CONFIG_S390
unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes);
if (!memslot->dirty_bitmap)
return -ENOMEM;
-#endif /* !CONFIG_S390 */
return 0;
}
@@ -1711,16 +1716,16 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
#endif /* !CONFIG_S390 */
-bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
+int kvm_vcpu_yield_to(struct kvm_vcpu *target)
{
struct pid *pid;
struct task_struct *task = NULL;
- bool ret = false;
+ int ret = 0;
rcu_read_lock();
pid = rcu_dereference(target->pid);
if (pid)
- task = get_pid_task(target->pid, PIDTYPE_PID);
+ task = get_pid_task(pid, PIDTYPE_PID);
rcu_read_unlock();
if (!task)
return ret;
@@ -1804,7 +1809,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
continue;
if (vcpu == me)
continue;
- if (waitqueue_active(&vcpu->wq))
+ if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;
@@ -2284,6 +2289,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
ops = &kvm_arm_vgic_v2_ops;
break;
#endif
+#ifdef CONFIG_S390
+ case KVM_DEV_TYPE_FLIC:
+ ops = &kvm_flic_ops;
+ break;
+#endif
default:
return -ENODEV;
}
@@ -2316,6 +2326,34 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
return 0;
}
+static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
+{
+ switch (arg) {
+ case KVM_CAP_USER_MEMORY:
+ case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
+ case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+ case KVM_CAP_SET_BOOT_CPU_ID:
+#endif
+ case KVM_CAP_INTERNAL_ERROR_DATA:
+#ifdef CONFIG_HAVE_KVM_MSI
+ case KVM_CAP_SIGNAL_MSI:
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
+ case KVM_CAP_IRQFD_RESAMPLE:
+#endif
+ case KVM_CAP_CHECK_EXTENSION_VM:
+ return 1;
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+ case KVM_CAP_IRQ_ROUTING:
+ return KVM_MAX_IRQ_ROUTES;
+#endif
+ default:
+ break;
+ }
+ return kvm_vm_ioctl_check_extension(kvm, arg);
+}
+
static long kvm_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2479,6 +2517,9 @@ static long kvm_vm_ioctl(struct file *filp,
r = 0;
break;
}
+ case KVM_CHECK_EXTENSION:
+ r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
+ break;
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
if (r == -ENOTTY)
@@ -2563,33 +2604,6 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
return r;
}
-static long kvm_dev_ioctl_check_extension_generic(long arg)
-{
- switch (arg) {
- case KVM_CAP_USER_MEMORY:
- case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
- case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
- case KVM_CAP_SET_BOOT_CPU_ID:
-#endif
- case KVM_CAP_INTERNAL_ERROR_DATA:
-#ifdef CONFIG_HAVE_KVM_MSI
- case KVM_CAP_SIGNAL_MSI:
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
- case KVM_CAP_IRQFD_RESAMPLE:
-#endif
- return 1;
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
- case KVM_CAP_IRQ_ROUTING:
- return KVM_MAX_IRQ_ROUTES;
-#endif
- default:
- break;
- }
- return kvm_dev_ioctl_check_extension(arg);
-}
-
static long kvm_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2606,7 +2620,7 @@ static long kvm_dev_ioctl(struct file *filp,
r = kvm_dev_ioctl_create_vm(arg);
break;
case KVM_CHECK_EXTENSION:
- r = kvm_dev_ioctl_check_extension_generic(arg);
+ r = kvm_vm_ioctl_check_extension_generic(NULL, arg);
break;
case KVM_GET_VCPU_MMAP_SIZE:
r = -EINVAL;
@@ -2920,6 +2934,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
return -EOPNOTSUPP;
}
+EXPORT_SYMBOL_GPL(kvm_io_bus_write);
/* kvm_io_bus_read - called under kvm->slots_lock */
int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index b4f9507ae650..ba1a93f935c7 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -59,6 +59,22 @@ static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
symbol_put(vfio_group_put_external_user);
}
+static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
+{
+ long (*fn)(struct vfio_group *, unsigned long);
+ long ret;
+
+ fn = symbol_get(vfio_external_check_extension);
+ if (!fn)
+ return false;
+
+ ret = fn(vfio_group, VFIO_DMA_CC_IOMMU);
+
+ symbol_put(vfio_external_check_extension);
+
+ return ret > 0;
+}
+
/*
* Groups can use the same or different IOMMU domains. If the same then
* adding a new group may change the coherency of groups we've previously
@@ -75,13 +91,10 @@ static void kvm_vfio_update_coherency(struct kvm_device *dev)
mutex_lock(&kv->lock);
list_for_each_entry(kvg, &kv->group_list, node) {
- /*
- * TODO: We need an interface to check the coherency of
- * the IOMMU domain this group is using. For now, assume
- * it's always noncoherent.
- */
- noncoherent = true;
- break;
+ if (!kvm_vfio_group_is_coherent(kvg->vfio_group)) {
+ noncoherent = true;
+ break;
+ }
}
if (noncoherent != kv->noncoherent) {
Powered by cgit, Gruvboxed by Blaster4385.