Commit 50926d82 authored by Marc Zyngier's avatar Marc Zyngier Committed by Christoffer Dall

KVM: arm/arm64: The GIC is dead, long live the GIC

I don't think any single piece of the KVM/ARM code ever generated
as much hatred as the GIC emulation.

It was written by someone who had zero experience in modeling
hardware (me), was riddled with design flaws, should have been
scrapped and rewritten from scratch long before having a remote
chance of reaching mainline, and yet we supported it for a good
three years. No need to mention the names of those who suffered,
the git log is singing their praises.

Thankfully, we now have a much more maintainable implementation,
and we can safely put the grumpy old GIC to rest.

Fellow hackers, please raise your glass in memory of the GIC:

	The GIC is dead, long live the GIC!
Signed-off-by: default avatarMarc Zyngier <marc.zyngier@arm.com>
Signed-off-by: default avatarChristoffer Dall <christoffer.dall@linaro.org>
parent 0996353f
......@@ -46,13 +46,6 @@ config KVM_ARM_HOST
---help---
Provides host support for ARM processors.
config KVM_NEW_VGIC
bool "New VGIC implementation"
depends on KVM
default y
---help---
uses the new VGIC implementation
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
......@@ -22,7 +22,6 @@ obj-y += kvm-arm.o init.o interrupts.o
obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
ifeq ($(CONFIG_KVM_NEW_VGIC),y)
obj-y += $(KVM)/arm/vgic/vgic.o
obj-y += $(KVM)/arm/vgic/vgic-init.o
obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
......@@ -30,9 +29,4 @@ obj-y += $(KVM)/arm/vgic/vgic-v2.o
obj-y += $(KVM)/arm/vgic/vgic-mmio.o
obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
else
obj-y += $(KVM)/arm/vgic.o
obj-y += $(KVM)/arm/vgic-v2.o
obj-y += $(KVM)/arm/vgic-v2-emul.o
endif
obj-y += $(KVM)/arm/arch_timer.o
......@@ -54,13 +54,6 @@ config KVM_ARM_PMU
Adds support for a virtual Performance Monitoring Unit (PMU) in
virtual machines.
config KVM_NEW_VGIC
bool "New VGIC implementation"
depends on KVM
default y
---help---
uses the new VGIC implementation
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
......@@ -20,7 +20,6 @@ kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o
kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
ifeq ($(CONFIG_KVM_NEW_VGIC),y)
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-irqfd.o
......@@ -30,12 +29,5 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o
else
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
endif
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
/*
* Copyright (C) 2012 ARM Ltd.
* Author: Marc Zyngier <marc.zyngier@arm.com>
* Copyright (C) 2015, 2016 ARM Ltd.
*
* 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
......@@ -12,16 +11,10 @@
* 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
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef __ASM_ARM_KVM_VGIC_H
#define __ASM_ARM_KVM_VGIC_H
#ifdef CONFIG_KVM_NEW_VGIC
#include <kvm/vgic/vgic.h>
#else
#ifndef __KVM_ARM_VGIC_H
#define __KVM_ARM_VGIC_H
#include <linux/kernel.h>
#include <linux/kvm.h>
......@@ -29,248 +22,130 @@
#include <linux/spinlock.h>
#include <linux/types.h>
#include <kvm/iodev.h>
#include <linux/irqchip/arm-gic-common.h>
#define VGIC_NR_IRQS_LEGACY 256
#define VGIC_V3_MAX_CPUS 255
#define VGIC_V2_MAX_CPUS 8
#define VGIC_NR_IRQS_LEGACY 256
#define VGIC_NR_SGIS 16
#define VGIC_NR_PPIS 16
#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
#define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1)
#define VGIC_MAX_SPI 1019
#define VGIC_MAX_RESERVED 1023
#define VGIC_MIN_LPI 8192
#define VGIC_V2_MAX_LRS (1 << 6)
#define VGIC_V3_MAX_LRS 16
#define VGIC_MAX_IRQS 1024
#define VGIC_V2_MAX_CPUS 8
#define VGIC_V3_MAX_CPUS 255
#if (VGIC_NR_IRQS_LEGACY & 31)
#error "VGIC_NR_IRQS must be a multiple of 32"
#endif
enum vgic_type {
VGIC_V2, /* Good ol' GICv2 */
VGIC_V3, /* New fancy GICv3 */
};
#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS)
#error "VGIC_NR_IRQS must be <= 1024"
#endif
/* same for all guests, as depending only on the _host's_ GIC model */
struct vgic_global {
/* type of the host GIC */
enum vgic_type type;
/*
* The GIC distributor registers describing interrupts have two parts:
* - 32 per-CPU interrupts (SGI + PPI)
* - a bunch of shared interrupts (SPI)
*/
struct vgic_bitmap {
/*
* - One UL per VCPU for private interrupts (assumes UL is at
* least 32 bits)
* - As many UL as necessary for shared interrupts.
*
* The private interrupts are accessed via the "private"
* field, one UL per vcpu (the state for vcpu n is in
* private[n]). The shared interrupts are accessed via the
* "shared" pointer (IRQn state is at bit n-32 in the bitmap).
*/
unsigned long *private;
unsigned long *shared;
};
/* Physical address of vgic virtual cpu interface */
phys_addr_t vcpu_base;
struct vgic_bytemap {
/*
* - 8 u32 per VCPU for private interrupts
* - As many u32 as necessary for shared interrupts.
*
* The private interrupts are accessed via the "private"
* field, (the state for vcpu n is in private[n*8] to
* private[n*8 + 7]). The shared interrupts are accessed via
* the "shared" pointer (IRQn state is at byte (n-32)%4 of the
* shared[(n-32)/4] word).
*/
u32 *private;
u32 *shared;
};
/* virtual control interface mapping */
void __iomem *vctrl_base;
struct kvm_vcpu;
/* Number of implemented list registers */
int nr_lr;
enum vgic_type {
VGIC_V2, /* Good ol' GICv2 */
VGIC_V3, /* New fancy GICv3 */
};
/* Maintenance IRQ number */
unsigned int maint_irq;
#define LR_STATE_PENDING (1 << 0)
#define LR_STATE_ACTIVE (1 << 1)
#define LR_STATE_MASK (3 << 0)
#define LR_EOI_INT (1 << 2)
#define LR_HW (1 << 3)
/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
int max_gic_vcpus;
struct vgic_lr {
unsigned irq:10;
union {
unsigned hwirq:10;
unsigned source:3;
};
unsigned state:4;
/* Only needed for the legacy KVM_CREATE_IRQCHIP */
bool can_emulate_gicv2;
};
struct vgic_vmcr {
u32 ctlr;
u32 abpr;
u32 bpr;
u32 pmr;
};
extern struct vgic_global kvm_vgic_global_state;
struct vgic_ops {
struct vgic_lr (*get_lr)(const struct kvm_vcpu *, int);
void (*set_lr)(struct kvm_vcpu *, int, struct vgic_lr);
u64 (*get_elrsr)(const struct kvm_vcpu *vcpu);
u64 (*get_eisr)(const struct kvm_vcpu *vcpu);
void (*clear_eisr)(struct kvm_vcpu *vcpu);
u32 (*get_interrupt_status)(const struct kvm_vcpu *vcpu);
void (*enable_underflow)(struct kvm_vcpu *vcpu);
void (*disable_underflow)(struct kvm_vcpu *vcpu);
void (*get_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
void (*set_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
void (*enable)(struct kvm_vcpu *vcpu);
};
#define VGIC_V2_MAX_LRS (1 << 6)
#define VGIC_V3_MAX_LRS 16
#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr)
struct vgic_params {
/* vgic type */
enum vgic_type type;
/* Physical address of vgic virtual cpu interface */
phys_addr_t vcpu_base;
/* Number of list registers */
u32 nr_lr;
/* Interrupt number */
unsigned int maint_irq;
/* Virtual control interface base address */
void __iomem *vctrl_base;
int max_gic_vcpus;
/* Only needed for the legacy KVM_CREATE_IRQCHIP */
bool can_emulate_gicv2;
enum vgic_irq_config {
VGIC_CONFIG_EDGE = 0,
VGIC_CONFIG_LEVEL
};
struct vgic_vm_ops {
bool (*queue_sgi)(struct kvm_vcpu *, int irq);
void (*add_sgi_source)(struct kvm_vcpu *, int irq, int source);
int (*init_model)(struct kvm *);
int (*map_resources)(struct kvm *, const struct vgic_params *);
struct vgic_irq {
spinlock_t irq_lock; /* Protects the content of the struct */
struct list_head ap_list;
struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU
* SPIs and LPIs: The VCPU whose ap_list
* this is queued on.
*/
struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should
* be sent to, as a result of the
* targets reg (v2) or the
* affinity reg (v3).
*/
u32 intid; /* Guest visible INTID */
bool pending;
bool line_level; /* Level only */
bool soft_pending; /* Level only */
bool active; /* not used for LPIs */
bool enabled;
bool hw; /* Tied to HW IRQ */
u32 hwintid; /* HW INTID number */
union {
u8 targets; /* GICv2 target VCPUs mask */
u32 mpidr; /* GICv3 target VCPU */
};
u8 source; /* GICv2 SGIs only */
u8 priority;
enum vgic_irq_config config; /* Level or edge */
};
struct vgic_register_region;
struct vgic_io_device {
gpa_t addr;
int len;
const struct vgic_io_range *reg_ranges;
gpa_t base_addr;
struct kvm_vcpu *redist_vcpu;
const struct vgic_register_region *regions;
int nr_regions;
struct kvm_io_device dev;
};
struct irq_phys_map {
u32 virt_irq;
u32 phys_irq;
};
struct irq_phys_map_entry {
struct list_head entry;
struct rcu_head rcu;
struct irq_phys_map map;
};
struct vgic_dist {
spinlock_t lock;
bool in_kernel;
bool ready;
bool initialized;
/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
u32 vgic_model;
int nr_cpus;
int nr_irqs;
int nr_spis;
/* TODO: Consider moving to global state */
/* Virtual control interface mapping */
void __iomem *vctrl_base;
/* Distributor and vcpu interface mapping in the guest */
phys_addr_t vgic_dist_base;
/* GICv2 and GICv3 use different mapped register blocks */
/* base addresses in guest physical address space: */
gpa_t vgic_dist_base; /* distributor */
union {
phys_addr_t vgic_cpu_base;
phys_addr_t vgic_redist_base;
/* either a GICv2 CPU interface */
gpa_t vgic_cpu_base;
/* or a number of GICv3 redistributor regions */
gpa_t vgic_redist_base;
};
/* Distributor enabled */
u32 enabled;
/* Interrupt enabled (one bit per IRQ) */
struct vgic_bitmap irq_enabled;
/* Level-triggered interrupt external input is asserted */
struct vgic_bitmap irq_level;
/*
* Interrupt state is pending on the distributor
*/
struct vgic_bitmap irq_pending;
/*
* Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered
* interrupts. Essentially holds the state of the flip-flop in
* Figure 4-10 on page 4-101 in ARM IHI 0048B.b.
* Once set, it is only cleared for level-triggered interrupts on
* guest ACKs (when we queue it) or writes to GICD_ICPENDRn.
*/
struct vgic_bitmap irq_soft_pend;
/* Level-triggered interrupt queued on VCPU interface */
struct vgic_bitmap irq_queued;
/* Interrupt was active when unqueue from VCPU interface */
struct vgic_bitmap irq_active;
/* distributor enabled */
bool enabled;
/* Interrupt priority. Not used yet. */
struct vgic_bytemap irq_priority;
struct vgic_irq *spis;
/* Level/edge triggered */
struct vgic_bitmap irq_cfg;
/*
* Source CPU per SGI and target CPU:
*
* Each byte represent a SGI observable on a VCPU, each bit of
* this byte indicating if the corresponding VCPU has
* generated this interrupt. This is a GICv2 feature only.
*
* For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are
* the SGIs observable on VCPUn.
*/
u8 *irq_sgi_sources;
/*
* Target CPU for each SPI:
*
* Array of available SPI, each byte indicating the target
* VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32].
*/
u8 *irq_spi_cpu;
/*
* Reverse lookup of irq_spi_cpu for faster compute pending:
*
* Array of bitmaps, one per VCPU, describing if IRQn is
* routed to a particular VCPU.
*/
struct vgic_bitmap *irq_spi_target;
/* Target MPIDR for each IRQ (needed for GICv3 IROUTERn) only */
u32 *irq_spi_mpidr;
/* Bitmap indicating which CPU has something pending */
unsigned long *irq_pending_on_cpu;
/* Bitmap indicating which CPU has active IRQs */
unsigned long *irq_active_on_cpu;
struct vgic_vm_ops vm_ops;
struct vgic_io_device dist_iodev;
struct vgic_io_device *redist_iodevs;
/* Virtual irq to hwirq mapping */
spinlock_t irq_phys_map_lock;
struct list_head irq_phys_map_list;
};
struct vgic_v2_cpu_if {
......@@ -298,78 +173,74 @@ struct vgic_v3_cpu_if {
};
struct vgic_cpu {
/* Pending/active/both interrupts on this VCPU */
DECLARE_BITMAP(pending_percpu, VGIC_NR_PRIVATE_IRQS);
DECLARE_BITMAP(active_percpu, VGIC_NR_PRIVATE_IRQS);
DECLARE_BITMAP(pend_act_percpu, VGIC_NR_PRIVATE_IRQS);
/* Pending/active/both shared interrupts, dynamically sized */
unsigned long *pending_shared;
unsigned long *active_shared;
unsigned long *pend_act_shared;
/* CPU vif control registers for world switch */
union {
struct vgic_v2_cpu_if vgic_v2;
struct vgic_v3_cpu_if vgic_v3;
};
/* Protected by the distributor's irq_phys_map_lock */
struct list_head irq_phys_map_list;
u64 live_lrs;
};
unsigned int used_lrs;
struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
#define LR_EMPTY 0xff
spinlock_t ap_list_lock; /* Protects the ap_list */
#define INT_STATUS_EOI (1 << 0)
#define INT_STATUS_UNDERFLOW (1 << 1)
/*
* List of IRQs that this VCPU should consider because they are either
* Active or Pending (hence the name; AP list), or because they recently
* were one of the two and need to be migrated off this list to another
* VCPU.
*/
struct list_head ap_list_head;
struct kvm;
struct kvm_vcpu;
u64 live_lrs;
};
int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
int kvm_vgic_hyp_init(void);
int kvm_vgic_map_resources(struct kvm *kvm);
int kvm_vgic_get_max_vcpus(void);
void kvm_vgic_early_init(struct kvm *kvm);
int kvm_vgic_create(struct kvm *kvm, u32 type);
void kvm_vgic_destroy(struct kvm *kvm);
void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
int kvm_vgic_map_resources(struct kvm *kvm);
int kvm_vgic_hyp_init(void);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level);
int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
unsigned int virt_irq, bool level);
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq);
int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level);
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
#define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus))
#define vgic_initialized(k) ((k)->arch.vgic.initialized)
#define vgic_ready(k) ((k)->arch.vgic.ready)
#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \
((i) < (k)->arch.vgic.nr_irqs))
((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params);
#ifdef CONFIG_KVM_ARM_VGIC_V3
int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params);
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
#else
static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params)
static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
{
return -ENODEV;
}
#endif
#endif /* old VGIC include */
#endif
/**
* kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
*
* The host's GIC naturally limits the maximum amount of VCPUs a guest
* can use.
*/
static inline int kvm_vgic_get_max_vcpus(void)
{
return kvm_vgic_global_state.max_gic_vcpus;
}
#endif /* __KVM_ARM_VGIC_H */
/*
* Copyright (C) 2015, 2016 ARM Ltd.
*
* 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/>.
*/
#ifndef __ASM_ARM_KVM_VGIC_VGIC_H
#define __ASM_ARM_KVM_VGIC_VGIC_H
#include <linux/kernel.h>
#include <linux/kvm.h>
#include <linux/irqreturn.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <kvm/iodev.h>
#define VGIC_V3_MAX_CPUS 255
#define VGIC_V2_MAX_CPUS 8
#define VGIC_NR_IRQS_LEGACY 256
#define VGIC_NR_SGIS 16
#define VGIC_NR_PPIS 16
#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
#define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1)
#define VGIC_MAX_SPI 1019
#define VGIC_MAX_RESERVED 1023
#define VGIC_MIN_LPI 8192
enum vgic_type {
VGIC_V2, /* Good ol' GICv2 */
VGIC_V3, /* New fancy GICv3 */
};
/* same for all guests, as depending only on the _host's_ GIC model */
struct vgic_global {
/* type of the host GIC */
enum vgic_type type;
/* Physical address of vgic virtual cpu interface */
phys_addr_t vcpu_base;
/* virtual control interface mapping */
void __iomem *vctrl_base;
/* Number of implemented list registers */
int nr_lr;
/* Maintenance IRQ number */
unsigned int maint_irq;
/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
int max_gic_vcpus;
/* Only needed for the legacy KVM_CREATE_IRQCHIP */
bool can_emulate_gicv2;
};
extern struct vgic_global kvm_vgic_global_state;
#define VGIC_V2_MAX_LRS (1 << 6)
#define VGIC_V3_MAX_LRS 16
#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr)
enum vgic_irq_config {
VGIC_CONFIG_EDGE = 0,
VGIC_CONFIG_LEVEL
};
struct vgic_irq {
spinlock_t irq_lock; /* Protects the content of the struct */
struct list_head ap_list;
struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU
* SPIs and LPIs: The VCPU whose ap_list
* this is queued on.
*/
struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should
* be sent to, as a result of the
* targets reg (v2) or the
* affinity reg (v3).
*/
u32 intid; /* Guest visible INTID */
bool pending;
bool line_level; /* Level only */
bool soft_pending; /* Level only */
bool active; /* not used for LPIs */
bool enabled;
bool hw; /* Tied to HW IRQ */
u32 hwintid; /* HW INTID number */
union {
u8 targets; /* GICv2 target VCPUs mask */
u32 mpidr; /* GICv3 target VCPU */
};
u8 source; /* GICv2 SGIs only */
u8 priority;
enum vgic_irq_config config; /* Level or edge */
};
struct vgic_register_region;
struct vgic_io_device {
gpa_t base_addr;
struct kvm_vcpu *redist_vcpu;
const struct vgic_register_region *regions;
int nr_regions;
struct kvm_io_device dev;
};
struct vgic_dist {
bool in_kernel;
bool ready;
bool initialized;
/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
u32 vgic_model;
int nr_spis;
/* TODO: Consider moving to global state */
/* Virtual control interface mapping */
void __iomem *vctrl_base;
/* base addresses in guest physical address space: */
gpa_t vgic_dist_base; /* distributor */
union {
/* either a GICv2 CPU interface */
gpa_t vgic_cpu_base;
/* or a number of GICv3 redistributor regions */
gpa_t vgic_redist_base;
};
/* distributor enabled */
bool enabled;
struct vgic_irq *spis;
struct vgic_io_device dist_iodev;
struct vgic_io_device *redist_iodevs;
};
struct vgic_v2_cpu_if {
u32 vgic_hcr;
u32 vgic_vmcr;
u32 vgic_misr; /* Saved only */
u64 vgic_eisr; /* Saved only */
u64 vgic_elrsr; /* Saved only */
u32 vgic_apr;
u32 vgic_lr[VGIC_V2_MAX_LRS];
};
struct vgic_v3_cpu_if {
#ifdef CONFIG_KVM_ARM_VGIC_V3
u32 vgic_hcr;
u32 vgic_vmcr;
u32 vgic_sre; /* Restored only, change ignored */
u32 vgic_misr; /* Saved only */
u32 vgic_eisr; /* Saved only */
u32 vgic_elrsr; /* Saved only */
u32 vgic_ap0r[4];
u32 vgic_ap1r[4];
u64 vgic_lr[VGIC_V3_MAX_LRS];
#endif
};
struct vgic_cpu {
/* CPU vif control registers for world switch */
union {
struct vgic_v2_cpu_if vgic_v2;
struct vgic_v3_cpu_if vgic_v3;
};
unsigned int used_lrs;
struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
spinlock_t ap_list_lock; /* Protects the ap_list */
/*
* List of IRQs that this VCPU should consider because they are either
* Active or Pending (hence the name; AP list), or because they recently
* were one of the two and need to be migrated off this list to another
* VCPU.
*/
struct list_head ap_list_head;
u64 live_lrs;
};
int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
void kvm_vgic_early_init(struct kvm *kvm);
int kvm_vgic_create(struct kvm *kvm, u32 type);
void kvm_vgic_destroy(struct kvm *kvm);
void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
int kvm_vgic_map_resources(struct kvm *kvm);
int kvm_vgic_hyp_init(void);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level);
int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level);
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
#define vgic_initialized(k) ((k)->arch.vgic.initialized)
#define vgic_ready(k) ((k)->arch.vgic.ready)
#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \
((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
#ifdef CONFIG_KVM_ARM_VGIC_V3
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
#else
static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
{
}
#endif
/**
* kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
*
* The host's GIC naturally limits the maximum amount of VCPUs a guest
* can use.
*/
static inline int kvm_vgic_get_max_vcpus(void)
{
return kvm_vgic_global_state.max_gic_vcpus;
}
#endif /* __ASM_ARM_KVM_VGIC_VGIC_H */
......@@ -21,18 +21,11 @@
#include <asm/kvm_hyp.h>
#ifdef CONFIG_KVM_NEW_VGIC
extern struct vgic_global kvm_vgic_global_state;
#define vgic_v2_params kvm_vgic_global_state
#else
extern struct vgic_params vgic_v2_params;
#endif
static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
void __iomem *base)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
u32 eisr0, eisr1;
int i;
bool expect_mi;
......@@ -74,7 +67,7 @@ static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
u32 elrsr0, elrsr1;
elrsr0 = readl_relaxed(base + GICH_ELRSR0);
......@@ -93,7 +86,7 @@ static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
int i;
for (i = 0; i < nr_lr; i++) {
......@@ -147,7 +140,7 @@ void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
struct vgic_dist *vgic = &kvm->arch.vgic;
void __iomem *base = kern_hyp_va(vgic->vctrl_base);
int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
int i;
u64 live_lrs = 0;
......
/*
* Contains GICv2 specific emulation code, was in vgic.c before.
*
* Copyright (C) 2012 ARM Ltd.
* 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/uaccess.h>
#include <linux/irqchip/arm-gic.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>
#include "vgic.h"
#define GICC_ARCH_VERSION_V2 0x2
static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi)
{
return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi;
}
static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
u32 reg;
u32 word_offset = offset & 3;
switch (offset & ~3) {
case 0: /* GICD_CTLR */
reg = vcpu->kvm->arch.vgic.enabled;
vgic_reg_access(mmio, &reg, word_offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
if (mmio->is_write) {
vcpu->kvm->arch.vgic.enabled = reg & 1;
vgic_update_state(vcpu->kvm);
return true;
}
break;
case 4: /* GICD_TYPER */
reg = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
reg |= (vcpu->kvm->arch.vgic.nr_irqs >> 5) - 1;
vgic_reg_access(mmio, &reg, word_offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
break;
case 8: /* GICD_IIDR */
reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
vgic_reg_access(mmio, &reg, word_offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
break;
}
return false;
}
static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id, ACCESS_WRITE_SETBIT);
}
static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id, ACCESS_WRITE_CLEARBIT);
}
static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
}
static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
}
static bool handle_mmio_set_active_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
}
static bool handle_mmio_clear_active_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
}
static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 *reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
vcpu->vcpu_id, offset);
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
return false;
}
#define GICD_ITARGETSR_SIZE 32
#define GICD_CPUTARGETS_BITS 8
#define GICD_IRQS_PER_ITARGETSR (GICD_ITARGETSR_SIZE / GICD_CPUTARGETS_BITS)
static u32 vgic_get_target_reg(struct kvm *kvm, int irq)
{
struct vgic_dist *dist = &kvm->arch.vgic;
int i;
u32 val = 0;
irq -= VGIC_NR_PRIVATE_IRQS;
for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++)
val |= 1 << (dist->irq_spi_cpu[irq + i] + i * 8);
return val;
}
static void vgic_set_target_reg(struct kvm *kvm, u32 val, int irq)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int i, c;
unsigned long *bmap;
u32 target;
irq -= VGIC_NR_PRIVATE_IRQS;
/*
* Pick the LSB in each byte. This ensures we target exactly
* one vcpu per IRQ. If the byte is null, assume we target
* CPU0.
*/
for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) {
int shift = i * GICD_CPUTARGETS_BITS;
target = ffs((val >> shift) & 0xffU);
target = target ? (target - 1) : 0;
dist->irq_spi_cpu[irq + i] = target;
kvm_for_each_vcpu(c, vcpu, kvm) {
bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
if (c == target)
set_bit(irq + i, bmap);
else
clear_bit(irq + i, bmap);
}
}
}
static bool handle_mmio_target_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 reg;
/* We treat the banked interrupts targets as read-only */
if (offset < 32) {
u32 roreg;
roreg = 1 << vcpu->vcpu_id;
roreg |= roreg << 8;
roreg |= roreg << 16;
vgic_reg_access(mmio, &roreg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
return false;
}
reg = vgic_get_target_reg(vcpu->kvm, offset & ~3U);
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
if (mmio->is_write) {
vgic_set_target_reg(vcpu->kvm, reg, offset & ~3U);
vgic_update_state(vcpu->kvm);
return true;
}
return false;
}
static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
u32 *reg;
reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
vcpu->vcpu_id, offset >> 1);
return vgic_handle_cfg_reg(reg, mmio, offset);
}
static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
u32 reg;
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_VALUE);
if (mmio->is_write) {
vgic_dispatch_sgi(vcpu, reg);
vgic_update_state(vcpu->kvm);
return true;
}
return false;
}
/* Handle reads of GICD_CPENDSGIRn and GICD_SPENDSGIRn */
static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
int sgi;
int min_sgi = (offset & ~0x3);
int max_sgi = min_sgi + 3;
int vcpu_id = vcpu->vcpu_id;
u32 reg = 0;
/* Copy source SGIs from distributor side */
for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
u8 sources = *vgic_get_sgi_sources(dist, vcpu_id, sgi);
reg |= ((u32)sources) << (8 * (sgi - min_sgi));
}
mmio_data_write(mmio, ~0, reg);
return false;
}
static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset, bool set)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
int sgi;
int min_sgi = (offset & ~0x3);
int max_sgi = min_sgi + 3;
int vcpu_id = vcpu->vcpu_id;
u32 reg;
bool updated = false;
reg = mmio_data_read(mmio, ~0);
/* Clear pending SGIs on the distributor */
for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
u8 mask = reg >> (8 * (sgi - min_sgi));
u8 *src = vgic_get_sgi_sources(dist, vcpu_id, sgi);
if (set) {
if ((*src & mask) != mask)
updated = true;
*src |= mask;
} else {
if (*src & mask)
updated = true;
*src &= ~mask;
}
}
if (updated)
vgic_update_state(vcpu->kvm);
return updated;
}
static bool handle_mmio_sgi_set(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (!mmio->is_write)
return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
else
return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, true);
}
static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (!mmio->is_write)
return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
else
return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false);
}
static const struct vgic_io_range vgic_dist_ranges[] = {
{
.base = GIC_DIST_SOFTINT,
.len = 4,
.handle_mmio = handle_mmio_sgi_reg,
},
{
.base = GIC_DIST_CTRL,
.len = 12,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_misc,
},
{
.base = GIC_DIST_IGROUP,
.len = VGIC_MAX_IRQS / 8,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GIC_DIST_ENABLE_SET,
.len = VGIC_MAX_IRQS / 8,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_enable_reg,
},
{
.base = GIC_DIST_ENABLE_CLEAR,
.len = VGIC_MAX_IRQS / 8,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_enable_reg,
},
{
.base = GIC_DIST_PENDING_SET,
.len = VGIC_MAX_IRQS / 8,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_pending_reg,
},
{
.base = GIC_DIST_PENDING_CLEAR,
.len = VGIC_MAX_IRQS / 8,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_pending_reg,
},
{
.base = GIC_DIST_ACTIVE_SET,
.len = VGIC_MAX_IRQS / 8,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_active_reg,
},
{
.base = GIC_DIST_ACTIVE_CLEAR,
.len = VGIC_MAX_IRQS / 8,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_active_reg,
},
{
.base = GIC_DIST_PRI,
.len = VGIC_MAX_IRQS,
.bits_per_irq = 8,
.handle_mmio = handle_mmio_priority_reg,
},
{
.base = GIC_DIST_TARGET,
.len = VGIC_MAX_IRQS,
.bits_per_irq = 8,
.handle_mmio = handle_mmio_target_reg,
},
{
.base = GIC_DIST_CONFIG,
.len = VGIC_MAX_IRQS / 4,
.bits_per_irq = 2,
.handle_mmio = handle_mmio_cfg_reg,
},
{
.base = GIC_DIST_SGI_PENDING_CLEAR,
.len = VGIC_NR_SGIS,
.handle_mmio = handle_mmio_sgi_clear,
},
{
.base = GIC_DIST_SGI_PENDING_SET,
.len = VGIC_NR_SGIS,
.handle_mmio = handle_mmio_sgi_set,
},
{}
};
static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
{
struct kvm *kvm = vcpu->kvm;
struct vgic_dist *dist = &kvm->arch.vgic;
int nrcpus = atomic_read(&kvm->online_vcpus);
u8 target_cpus;
int sgi, mode, c, vcpu_id;
vcpu_id = vcpu->vcpu_id;
sgi = reg & 0xf;
target_cpus = (reg >> 16) & 0xff;
mode = (reg >> 24) & 3;
switch (mode) {
case 0:
if (!target_cpus)
return;
break;
case 1:
target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
break;
case 2:
target_cpus = 1 << vcpu_id;
break;
}
kvm_for_each_vcpu(c, vcpu, kvm) {
if (target_cpus & 1) {
/* Flag the SGI as pending */
vgic_dist_irq_set_pending(vcpu, sgi);
*vgic_get_sgi_sources(dist, c, sgi) |= 1 << vcpu_id;
kvm_debug("SGI%d from CPU%d to CPU%d\n",
sgi, vcpu_id, c);
}
target_cpus >>= 1;
}
}
static bool vgic_v2_queue_sgi(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
unsigned long sources;
int vcpu_id = vcpu->vcpu_id;
int c;
sources = *vgic_get_sgi_sources(dist, vcpu_id, irq);
for_each_set_bit(c, &sources, dist->nr_cpus) {
if (vgic_queue_irq(vcpu, c, irq))
clear_bit(c, &sources);
}
*vgic_get_sgi_sources(dist, vcpu_id, irq) = sources;
/*
* If the sources bitmap has been cleared it means that we
* could queue all the SGIs onto link registers (see the
* clear_bit above), and therefore we are done with them in
* our emulated gic and can get rid of them.
*/
if (!sources) {
vgic_dist_irq_clear_pending(vcpu, irq);
vgic_cpu_irq_clear(vcpu, irq);
return true;
}
return false;
}
/**
* kvm_vgic_map_resources - Configure global VGIC state before running any VCPUs
* @kvm: pointer to the kvm struct
*
* Map the virtual CPU interface into the VM before running any VCPUs. We
* can't do this at creation time, because user space must first set the
* virtual CPU interface address in the guest physical address space.
*/
static int vgic_v2_map_resources(struct kvm *kvm,
const struct vgic_params *params)
{
struct vgic_dist *dist = &kvm->arch.vgic;
int ret = 0;
if (!irqchip_in_kernel(kvm))
return 0;
mutex_lock(&kvm->lock);
if (vgic_ready(kvm))
goto out;
if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) {
kvm_err("Need to set vgic cpu and dist addresses first\n");
ret = -ENXIO;
goto out;
}
vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base,
KVM_VGIC_V2_DIST_SIZE,
vgic_dist_ranges, -1, &dist->dist_iodev);
/*
* Initialize the vgic if this hasn't already been done on demand by
* accessing the vgic state from userspace.
*/
ret = vgic_init(kvm);
if (ret) {
kvm_err("Unable to allocate maps\n");
goto out_unregister;
}
ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base,
params->vcpu_base, KVM_VGIC_V2_CPU_SIZE,
true);
if (ret) {
kvm_err("Unable to remap VGIC CPU to VCPU\n");
goto out_unregister;
}
dist->ready = true;
goto out;
out_unregister:
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev);
out:
if (ret)
kvm_vgic_destroy(kvm);
mutex_unlock(&kvm->lock);
return ret;
}
static void vgic_v2_add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
*vgic_get_sgi_sources(dist, vcpu->vcpu_id, irq) |= 1 << source;
}
static int vgic_v2_init_model(struct kvm *kvm)
{
int i;
for (i = VGIC_NR_PRIVATE_IRQS; i < kvm->arch.vgic.nr_irqs; i += 4)
vgic_set_target_reg(kvm, 0, i);
return 0;
}
void vgic_v2_init_emulation(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
dist->vm_ops.queue_sgi = vgic_v2_queue_sgi;
dist->vm_ops.add_sgi_source = vgic_v2_add_sgi_source;
dist->vm_ops.init_model = vgic_v2_init_model;
dist->vm_ops.map_resources = vgic_v2_map_resources;
kvm->arch.max_vcpus = VGIC_V2_MAX_CPUS;
}
static bool handle_cpu_mmio_misc(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
bool updated = false;
struct vgic_vmcr vmcr;
u32 *vmcr_field;
u32 reg;
vgic_get_vmcr(vcpu, &vmcr);
switch (offset & ~0x3) {
case GIC_CPU_CTRL:
vmcr_field = &vmcr.ctlr;
break;
case GIC_CPU_PRIMASK:
vmcr_field = &vmcr.pmr;
break;
case GIC_CPU_BINPOINT:
vmcr_field = &vmcr.bpr;
break;
case GIC_CPU_ALIAS_BINPOINT:
vmcr_field = &vmcr.abpr;
break;
default:
BUG();
}
if (!mmio->is_write) {
reg = *vmcr_field;
mmio_data_write(mmio, ~0, reg);
} else {
reg = mmio_data_read(mmio, ~0);
if (reg != *vmcr_field) {
*vmcr_field = reg;
vgic_set_vmcr(vcpu, &vmcr);
updated = true;
}
}
return updated;
}
static bool handle_mmio_abpr(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
return handle_cpu_mmio_misc(vcpu, mmio, GIC_CPU_ALIAS_BINPOINT);
}
static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 reg;
if (mmio->is_write)
return false;
/* GICC_IIDR */
reg = (PRODUCT_ID_KVM << 20) |
(GICC_ARCH_VERSION_V2 << 16) |
(IMPLEMENTER_ARM << 0);
mmio_data_write(mmio, ~0, reg);
return false;
}
/*
* CPU Interface Register accesses - these are not accessed by the VM, but by
* user space for saving and restoring VGIC state.
*/
static const struct vgic_io_range vgic_cpu_ranges[] = {
{
.base = GIC_CPU_CTRL,
.len = 12,
.handle_mmio = handle_cpu_mmio_misc,
},
{
.base = GIC_CPU_ALIAS_BINPOINT,
.len = 4,
.handle_mmio = handle_mmio_abpr,
},
{
.base = GIC_CPU_ACTIVEPRIO,
.len = 16,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GIC_CPU_IDENT,
.len = 4,
.handle_mmio = handle_cpu_mmio_ident,
},
};
static int vgic_attr_regs_access(struct kvm_device *dev,
struct kvm_device_attr *attr,
u32 *reg, bool is_write)
{
const struct vgic_io_range *r = NULL, *ranges;
phys_addr_t offset;
int ret, cpuid, c;
struct kvm_vcpu *vcpu, *tmp_vcpu;
struct vgic_dist *vgic;
struct kvm_exit_mmio mmio;
u32 data;
offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >>
KVM_DEV_ARM_VGIC_CPUID_SHIFT;
mutex_lock(&dev->kvm->lock);
ret = vgic_init(dev->kvm);
if (ret)
goto out;
if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
ret = -EINVAL;
goto out;
}
vcpu = kvm_get_vcpu(dev->kvm, cpuid);
vgic = &dev->kvm->arch.vgic;
mmio.len = 4;
mmio.is_write = is_write;
mmio.data = &data;
if (is_write)
mmio_data_write(&mmio, ~0, *reg);
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
mmio.phys_addr = vgic->vgic_dist_base + offset;
ranges = vgic_dist_ranges;
break;
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
mmio.phys_addr = vgic->vgic_cpu_base + offset;
ranges = vgic_cpu_ranges;
break;
default:
BUG();
}
r = vgic_find_range(ranges, 4, offset);
if (unlikely(!r || !r->handle_mmio)) {
ret = -ENXIO;
goto out;
}
spin_lock(&vgic->lock);
/*
* Ensure that no other VCPU is running by checking the vcpu->cpu
* field. If no other VPCUs are running we can safely access the VGIC
* state, because even if another VPU is run after this point, that
* VCPU will not touch the vgic state, because it will block on
* getting the vgic->lock in kvm_vgic_sync_hwstate().
*/
kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm) {
if (unlikely(tmp_vcpu->cpu != -1)) {
ret = -EBUSY;
goto out_vgic_unlock;
}
}
/*
* Move all pending IRQs from the LRs on all VCPUs so the pending
* state can be properly represented in the register state accessible
* through this API.
*/
kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm)
vgic_unqueue_irqs(tmp_vcpu);
offset -= r->base;
r->handle_mmio(vcpu, &mmio, offset);
if (!is_write)
*reg = mmio_data_read(&mmio, ~0);
ret = 0;
out_vgic_unlock:
spin_unlock(&vgic->lock);
out:
mutex_unlock(&dev->kvm->lock);
return ret;
}
static int vgic_v2_create(struct kvm_device *dev, u32 type)
{
return kvm_vgic_create(dev->kvm, type);
}
static void vgic_v2_destroy(struct kvm_device *dev)
{
kfree(dev);
}
static int vgic_v2_set_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
int ret;
ret = vgic_set_common_attr(dev, attr);
if (ret != -ENXIO)
return ret;
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
u32 __user *uaddr = (u32 __user *)(long)attr->addr;
u32 reg;
if (get_user(reg, uaddr))
return -EFAULT;
return vgic_attr_regs_access(dev, attr, &reg, true);
}
}
return -ENXIO;
}
static int vgic_v2_get_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
int ret;
ret = vgic_get_common_attr(dev, attr);
if (ret != -ENXIO)
return ret;
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
u32 __user *uaddr = (u32 __user *)(long)attr->addr;
u32 reg = 0;
ret = vgic_attr_regs_access(dev, attr, &reg, false);
if (ret)
return ret;
return put_user(reg, uaddr);
}
}
return -ENXIO;
}
static int vgic_v2_has_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
phys_addr_t offset;
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_ADDR:
switch (attr->attr) {
case KVM_VGIC_V2_ADDR_TYPE_DIST:
case KVM_VGIC_V2_ADDR_TYPE_CPU:
return 0;
}
break;
case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
return vgic_has_attr_regs(vgic_dist_ranges, offset);
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
return vgic_has_attr_regs(vgic_cpu_ranges, offset);
case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
return 0;
case KVM_DEV_ARM_VGIC_GRP_CTRL:
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
return 0;
}
}
return -ENXIO;
}
struct kvm_device_ops kvm_arm_vgic_v2_ops = {
.name = "kvm-arm-vgic-v2",
.create = vgic_v2_create,
.destroy = vgic_v2_destroy,
.set_attr = vgic_v2_set_attr,
.get_attr = vgic_v2_get_attr,
.has_attr = vgic_v2_has_attr,
};
/*
* 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/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;
if (val & GICH_LR_HW) {
lr_desc.state |= LR_HW;
lr_desc.hwirq = (val & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT;
}
return lr_desc;
}
static void vgic_v2_set_lr(struct kvm_vcpu *vcpu, int lr,
struct vgic_lr lr_desc)
{
u32 lr_val;
lr_val = 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;
if (lr_desc.state & LR_HW) {
lr_val |= GICH_LR_HW;
lr_val |= (u32)lr_desc.hwirq << GICH_LR_PHYSID_CPUID_SHIFT;
}
if (lr_desc.irq < VGIC_NR_SGIS)
lr_val |= (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT);
vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val;
if (!(lr_desc.state & LR_STATE_MASK))
vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
else
vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr &= ~(1ULL << lr);
}
static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
{
return vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
}
static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
{
return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
}
static void vgic_v2_clear_eisr(struct kvm_vcpu *vcpu)
{
vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr = 0;
}
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;
vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr = ~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,
.get_elrsr = vgic_v2_get_elrsr,
.get_eisr = vgic_v2_get_eisr,
.clear_eisr = vgic_v2_clear_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,
};
struct vgic_params __section(.hyp.text) vgic_v2_params;
static void vgic_cpu_init_lrs(void *params)
{
struct vgic_params *vgic = params;
int i;
for (i = 0; i < vgic->nr_lr; i++)
writel_relaxed(0, vgic->vctrl_base + GICH_LR0 + (i * 4));
}
/**
* vgic_v2_probe - probe for a GICv2 compatible interrupt controller
* @gic_kvm_info: pointer to the GIC description
* @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(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params)
{
int ret;
struct vgic_params *vgic = &vgic_v2_params;
const struct resource *vctrl_res = &gic_kvm_info->vctrl;
const struct resource *vcpu_res = &gic_kvm_info->vcpu;
memset(vgic, 0, sizeof(*vgic));
if (!gic_kvm_info->maint_irq) {
kvm_err("error getting vgic maintenance irq\n");
ret = -ENXIO;
goto out;
}
vgic->maint_irq = gic_kvm_info->maint_irq;
if (!gic_kvm_info->vctrl.start) {
kvm_err("GICH not present in the firmware table\n");
ret = -ENXIO;
goto out;
}
vgic->vctrl_base = ioremap(gic_kvm_info->vctrl.start,
resource_size(&gic_kvm_info->vctrl));
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 (!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->can_emulate_gicv2 = true;
kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2);
vgic->vcpu_base = vcpu_res->start;
kvm_info("GICH base=0x%llx, GICV base=0x%llx, IRQ=%d\n",
gic_kvm_info->vctrl.start, vgic->vcpu_base, vgic->maint_irq);
vgic->type = VGIC_V2;
vgic->max_gic_vcpus = VGIC_V2_MAX_CPUS;
on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
*ops = &vgic_v2_ops;
*params = vgic;
goto out;
out_unmap:
iounmap(vgic->vctrl_base);
out:
return ret;
}
/*
* GICv3 distributor and redistributor emulation
*
* GICv3 emulation is currently only supported on a GICv3 host (because
* we rely on the hardware's CPU interface virtualization support), but
* supports both hardware with or without the optional GICv2 backwards
* compatibility features.
*
* Limitations of the emulation:
* (RAZ/WI: read as zero, write ignore, RAO/WI: read as one, write ignore)
* - We do not support LPIs (yet). TYPER.LPIS is reported as 0 and is RAZ/WI.
* - We do not support the message based interrupts (MBIs) triggered by
* writes to the GICD_{SET,CLR}SPI_* registers. TYPER.MBIS is reported as 0.
* - We do not support the (optional) backwards compatibility feature.
* GICD_CTLR.ARE resets to 1 and is RAO/WI. If the _host_ GIC supports
* the compatiblity feature, you can use a GICv2 in the guest, though.
* - We only support a single security state. GICD_CTLR.DS is 1 and is RAO/WI.
* - Priorities are not emulated (same as the GICv2 emulation). Linux
* as a guest is fine with this, because it does not use priorities.
* - We only support Group1 interrupts. Again Linux uses only those.
*
* Copyright (C) 2014 ARM Ltd.
* Author: Andre Przywara <andre.przywara@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/irqchip/arm-gic-v3.h>
#include <kvm/arm_vgic.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>
#include "vgic.h"
static bool handle_mmio_rao_wi(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
u32 reg = 0xffffffff;
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_ctlr(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
u32 reg = 0;
/*
* Force ARE and DS to 1, the guest cannot change this.
* For the time being we only support Group1 interrupts.
*/
if (vcpu->kvm->arch.vgic.enabled)
reg = GICD_CTLR_ENABLE_SS_G1;
reg |= GICD_CTLR_ARE_NS | GICD_CTLR_DS;
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
if (mmio->is_write) {
vcpu->kvm->arch.vgic.enabled = !!(reg & GICD_CTLR_ENABLE_SS_G1);
vgic_update_state(vcpu->kvm);
return true;
}
return false;
}
/*
* As this implementation does not provide compatibility
* with GICv2 (ARE==1), we report zero CPUs in bits [5..7].
* Also LPIs and MBIs are not supported, so we set the respective bits to 0.
* Also we report at most 2**10=1024 interrupt IDs (to match 1024 SPIs).
*/
#define INTERRUPT_ID_BITS 10
static bool handle_mmio_typer(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
u32 reg;
reg = (min(vcpu->kvm->arch.vgic.nr_irqs, 1024) >> 5) - 1;
reg |= (INTERRUPT_ID_BITS - 1) << 19;
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_iidr(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio, phys_addr_t offset)
{
u32 reg;
reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_set_enable_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id,
ACCESS_WRITE_SETBIT);
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_clear_enable_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id,
ACCESS_WRITE_CLEARBIT);
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_set_pending_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_clear_pending_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_set_active_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_clear_active_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
vcpu->vcpu_id);
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_priority_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 *reg;
if (unlikely(offset < VGIC_NR_PRIVATE_IRQS)) {
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
vcpu->vcpu_id, offset);
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
return false;
}
static bool handle_mmio_cfg_reg_dist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 *reg;
if (unlikely(offset < VGIC_NR_PRIVATE_IRQS / 4)) {
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
vcpu->vcpu_id, offset >> 1);
return vgic_handle_cfg_reg(reg, mmio, offset);
}
/*
* We use a compressed version of the MPIDR (all 32 bits in one 32-bit word)
* when we store the target MPIDR written by the guest.
*/
static u32 compress_mpidr(unsigned long mpidr)
{
u32 ret;
ret = MPIDR_AFFINITY_LEVEL(mpidr, 0);
ret |= MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8;
ret |= MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16;
ret |= MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24;
return ret;
}
static unsigned long uncompress_mpidr(u32 value)
{
unsigned long mpidr;
mpidr = ((value >> 0) & 0xFF) << MPIDR_LEVEL_SHIFT(0);
mpidr |= ((value >> 8) & 0xFF) << MPIDR_LEVEL_SHIFT(1);
mpidr |= ((value >> 16) & 0xFF) << MPIDR_LEVEL_SHIFT(2);
mpidr |= (u64)((value >> 24) & 0xFF) << MPIDR_LEVEL_SHIFT(3);
return mpidr;
}
/*
* Lookup the given MPIDR value to get the vcpu_id (if there is one)
* and store that in the irq_spi_cpu[] array.
* This limits the number of VCPUs to 255 for now, extending the data
* type (or storing kvm_vcpu pointers) should lift the limit.
* Store the original MPIDR value in an extra array to support read-as-written.
* Unallocated MPIDRs are translated to a special value and caught
* before any array accesses.
*/
static bool handle_mmio_route_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm *kvm = vcpu->kvm;
struct vgic_dist *dist = &kvm->arch.vgic;
int spi;
u32 reg;
int vcpu_id;
unsigned long *bmap, mpidr;
/*
* The upper 32 bits of each 64 bit register are zero,
* as we don't support Aff3.
*/
if ((offset & 4)) {
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
/* This region only covers SPIs, so no handling of private IRQs here. */
spi = offset / 8;
/* get the stored MPIDR for this IRQ */
mpidr = uncompress_mpidr(dist->irq_spi_mpidr[spi]);
reg = mpidr;
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
if (!mmio->is_write)
return false;
/*
* Now clear the currently assigned vCPU from the map, making room
* for the new one to be written below
*/
vcpu = kvm_mpidr_to_vcpu(kvm, mpidr);
if (likely(vcpu)) {
vcpu_id = vcpu->vcpu_id;
bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]);
__clear_bit(spi, bmap);
}
dist->irq_spi_mpidr[spi] = compress_mpidr(reg);
vcpu = kvm_mpidr_to_vcpu(kvm, reg & MPIDR_HWID_BITMASK);
/*
* The spec says that non-existent MPIDR values should not be
* forwarded to any existent (v)CPU, but should be able to become
* pending anyway. We simply keep the irq_spi_target[] array empty, so
* the interrupt will never be injected.
* irq_spi_cpu[irq] gets a magic value in this case.
*/
if (likely(vcpu)) {
vcpu_id = vcpu->vcpu_id;
dist->irq_spi_cpu[spi] = vcpu_id;
bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]);
__set_bit(spi, bmap);
} else {
dist->irq_spi_cpu[spi] = VCPU_NOT_ALLOCATED;
}
vgic_update_state(kvm);
return true;
}
/*
* We should be careful about promising too much when a guest reads
* this register. Don't claim to be like any hardware implementation,
* but just report the GIC as version 3 - which is what a Linux guest
* would check.
*/
static bool handle_mmio_idregs(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 reg = 0;
switch (offset + GICD_IDREGS) {
case GICD_PIDR2:
reg = 0x3b;
break;
}
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
return false;
}
static const struct vgic_io_range vgic_v3_dist_ranges[] = {
{
.base = GICD_CTLR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_ctlr,
},
{
.base = GICD_TYPER,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_typer,
},
{
.base = GICD_IIDR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_iidr,
},
{
/* this register is optional, it is RAZ/WI if not implemented */
.base = GICD_STATUSR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this write only register is WI when TYPER.MBIS=0 */
.base = GICD_SETSPI_NSR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this write only register is WI when TYPER.MBIS=0 */
.base = GICD_CLRSPI_NSR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this is RAZ/WI when DS=1 */
.base = GICD_SETSPI_SR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this is RAZ/WI when DS=1 */
.base = GICD_CLRSPI_SR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GICD_IGROUPR,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_rao_wi,
},
{
.base = GICD_ISENABLER,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_enable_reg_dist,
},
{
.base = GICD_ICENABLER,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_enable_reg_dist,
},
{
.base = GICD_ISPENDR,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_pending_reg_dist,
},
{
.base = GICD_ICPENDR,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_pending_reg_dist,
},
{
.base = GICD_ISACTIVER,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_active_reg_dist,
},
{
.base = GICD_ICACTIVER,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_active_reg_dist,
},
{
.base = GICD_IPRIORITYR,
.len = 0x400,
.bits_per_irq = 8,
.handle_mmio = handle_mmio_priority_reg_dist,
},
{
/* TARGETSRn is RES0 when ARE=1 */
.base = GICD_ITARGETSR,
.len = 0x400,
.bits_per_irq = 8,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GICD_ICFGR,
.len = 0x100,
.bits_per_irq = 2,
.handle_mmio = handle_mmio_cfg_reg_dist,
},
{
/* this is RAZ/WI when DS=1 */
.base = GICD_IGRPMODR,
.len = 0x80,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this is RAZ/WI when DS=1 */
.base = GICD_NSACR,
.len = 0x100,
.bits_per_irq = 2,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this is RAZ/WI when ARE=1 */
.base = GICD_SGIR,
.len = 0x04,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this is RAZ/WI when ARE=1 */
.base = GICD_CPENDSGIR,
.len = 0x10,
.handle_mmio = handle_mmio_raz_wi,
},
{
/* this is RAZ/WI when ARE=1 */
.base = GICD_SPENDSGIR,
.len = 0x10,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GICD_IROUTER + 0x100,
.len = 0x1ee0,
.bits_per_irq = 64,
.handle_mmio = handle_mmio_route_reg,
},
{
.base = GICD_IDREGS,
.len = 0x30,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_idregs,
},
{},
};
static bool handle_mmio_ctlr_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
/* since we don't support LPIs, this register is zero for now */
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_typer_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 reg;
u64 mpidr;
struct kvm_vcpu *redist_vcpu = mmio->private;
int target_vcpu_id = redist_vcpu->vcpu_id;
/* the upper 32 bits contain the affinity value */
if ((offset & ~3) == 4) {
mpidr = kvm_vcpu_get_mpidr_aff(redist_vcpu);
reg = compress_mpidr(mpidr);
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
return false;
}
reg = redist_vcpu->vcpu_id << 8;
if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
reg |= GICR_TYPER_LAST;
vgic_reg_access(mmio, &reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
return false;
}
static bool handle_mmio_set_enable_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
redist_vcpu->vcpu_id,
ACCESS_WRITE_SETBIT);
}
static bool handle_mmio_clear_enable_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
redist_vcpu->vcpu_id,
ACCESS_WRITE_CLEARBIT);
}
static bool handle_mmio_set_active_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
redist_vcpu->vcpu_id);
}
static bool handle_mmio_clear_active_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
redist_vcpu->vcpu_id);
}
static bool handle_mmio_set_pending_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset,
redist_vcpu->vcpu_id);
}
static bool handle_mmio_clear_pending_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset,
redist_vcpu->vcpu_id);
}
static bool handle_mmio_priority_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
u32 *reg;
reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
redist_vcpu->vcpu_id, offset);
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
return false;
}
static bool handle_mmio_cfg_reg_redist(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
struct kvm_vcpu *redist_vcpu = mmio->private;
u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
redist_vcpu->vcpu_id, offset >> 1);
return vgic_handle_cfg_reg(reg, mmio, offset);
}
#define SGI_base(x) ((x) + SZ_64K)
static const struct vgic_io_range vgic_redist_ranges[] = {
{
.base = GICR_CTLR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_ctlr_redist,
},
{
.base = GICR_TYPER,
.len = 0x08,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_typer_redist,
},
{
.base = GICR_IIDR,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_iidr,
},
{
.base = GICR_WAKER,
.len = 0x04,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GICR_IDREGS,
.len = 0x30,
.bits_per_irq = 0,
.handle_mmio = handle_mmio_idregs,
},
{
.base = SGI_base(GICR_IGROUPR0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_rao_wi,
},
{
.base = SGI_base(GICR_ISENABLER0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_enable_reg_redist,
},
{
.base = SGI_base(GICR_ICENABLER0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_enable_reg_redist,
},
{
.base = SGI_base(GICR_ISPENDR0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_pending_reg_redist,
},
{
.base = SGI_base(GICR_ICPENDR0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_pending_reg_redist,
},
{
.base = SGI_base(GICR_ISACTIVER0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_set_active_reg_redist,
},
{
.base = SGI_base(GICR_ICACTIVER0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_active_reg_redist,
},
{
.base = SGI_base(GICR_IPRIORITYR0),
.len = 0x20,
.bits_per_irq = 8,
.handle_mmio = handle_mmio_priority_reg_redist,
},
{
.base = SGI_base(GICR_ICFGR0),
.len = 0x08,
.bits_per_irq = 2,
.handle_mmio = handle_mmio_cfg_reg_redist,
},
{
.base = SGI_base(GICR_IGRPMODR0),
.len = 0x04,
.bits_per_irq = 1,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = SGI_base(GICR_NSACR),
.len = 0x04,
.handle_mmio = handle_mmio_raz_wi,
},
{},
};
static bool vgic_v3_queue_sgi(struct kvm_vcpu *vcpu, int irq)
{
if (vgic_queue_irq(vcpu, 0, irq)) {
vgic_dist_irq_clear_pending(vcpu, irq);
vgic_cpu_irq_clear(vcpu, irq);
return true;
}
return false;
}
static int vgic_v3_map_resources(struct kvm *kvm,
const struct vgic_params *params)
{
int ret = 0;
struct vgic_dist *dist = &kvm->arch.vgic;
gpa_t rdbase = dist->vgic_redist_base;
struct vgic_io_device *iodevs = NULL;
int i;
if (!irqchip_in_kernel(kvm))
return 0;
mutex_lock(&kvm->lock);
if (vgic_ready(kvm))
goto out;
if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) {
kvm_err("Need to set vgic distributor addresses first\n");
ret = -ENXIO;
goto out;
}
/*
* For a VGICv3 we require the userland to explicitly initialize
* the VGIC before we need to use it.
*/
if (!vgic_initialized(kvm)) {
ret = -EBUSY;
goto out;
}
ret = vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base,
GIC_V3_DIST_SIZE, vgic_v3_dist_ranges,
-1, &dist->dist_iodev);
if (ret)
goto out;
iodevs = kcalloc(dist->nr_cpus, sizeof(iodevs[0]), GFP_KERNEL);
if (!iodevs) {
ret = -ENOMEM;
goto out_unregister;
}
for (i = 0; i < dist->nr_cpus; i++) {
ret = vgic_register_kvm_io_dev(kvm, rdbase,
SZ_128K, vgic_redist_ranges,
i, &iodevs[i]);
if (ret)
goto out_unregister;
rdbase += GIC_V3_REDIST_SIZE;
}
dist->redist_iodevs = iodevs;
dist->ready = true;
goto out;
out_unregister:
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev);
if (iodevs) {
for (i = 0; i < dist->nr_cpus; i++) {
if (iodevs[i].dev.ops)
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
&iodevs[i].dev);
}
}
out:
if (ret)
kvm_vgic_destroy(kvm);
mutex_unlock(&kvm->lock);
return ret;
}
static int vgic_v3_init_model(struct kvm *kvm)
{
int i;
u32 mpidr;
struct vgic_dist *dist = &kvm->arch.vgic;
int nr_spis = dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
dist->irq_spi_mpidr = kcalloc(nr_spis, sizeof(dist->irq_spi_mpidr[0]),
GFP_KERNEL);
if (!dist->irq_spi_mpidr)
return -ENOMEM;
/* Initialize the target VCPUs for each IRQ to VCPU 0 */
mpidr = compress_mpidr(kvm_vcpu_get_mpidr_aff(kvm_get_vcpu(kvm, 0)));
for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i++) {
dist->irq_spi_cpu[i - VGIC_NR_PRIVATE_IRQS] = 0;
dist->irq_spi_mpidr[i - VGIC_NR_PRIVATE_IRQS] = mpidr;
vgic_bitmap_set_irq_val(dist->irq_spi_target, 0, i, 1);
}
return 0;
}
/* GICv3 does not keep track of SGI sources anymore. */
static void vgic_v3_add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
{
}
void vgic_v3_init_emulation(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
dist->vm_ops.queue_sgi = vgic_v3_queue_sgi;
dist->vm_ops.add_sgi_source = vgic_v3_add_sgi_source;
dist->vm_ops.init_model = vgic_v3_init_model;
dist->vm_ops.map_resources = vgic_v3_map_resources;
kvm->arch.max_vcpus = KVM_MAX_VCPUS;
}
/*
* Compare a given affinity (level 1-3 and a level 0 mask, from the SGI
* generation register ICC_SGI1R_EL1) with a given VCPU.
* If the VCPU's MPIDR matches, return the level0 affinity, otherwise
* return -1.
*/
static int match_mpidr(u64 sgi_aff, u16 sgi_cpu_mask, struct kvm_vcpu *vcpu)
{
unsigned long affinity;
int level0;
/*
* Split the current VCPU's MPIDR into affinity level 0 and the
* rest as this is what we have to compare against.
*/
affinity = kvm_vcpu_get_mpidr_aff(vcpu);
level0 = MPIDR_AFFINITY_LEVEL(affinity, 0);
affinity &= ~MPIDR_LEVEL_MASK;
/* bail out if the upper three levels don't match */
if (sgi_aff != affinity)
return -1;
/* Is this VCPU's bit set in the mask ? */
if (!(sgi_cpu_mask & BIT(level0)))
return -1;
return level0;
}
#define SGI_AFFINITY_LEVEL(reg, level) \
((((reg) & ICC_SGI1R_AFFINITY_## level ##_MASK) \
>> ICC_SGI1R_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level))
/**
* vgic_v3_dispatch_sgi - handle SGI requests from VCPUs
* @vcpu: The VCPU requesting a SGI
* @reg: The value written into the ICC_SGI1R_EL1 register by that VCPU
*
* With GICv3 (and ARE=1) CPUs trigger SGIs by writing to a system register.
* This will trap in sys_regs.c and call this function.
* This ICC_SGI1R_EL1 register contains the upper three affinity levels of the
* target processors as well as a bitmask of 16 Aff0 CPUs.
* If the interrupt routing mode bit is not set, we iterate over all VCPUs to
* check for matching ones. If this bit is set, we signal all, but not the
* calling VCPU.
*/
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *c_vcpu;
struct vgic_dist *dist = &kvm->arch.vgic;
u16 target_cpus;
u64 mpidr;
int sgi, c;
int vcpu_id = vcpu->vcpu_id;
bool broadcast;
int updated = 0;
sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT;
broadcast = reg & BIT(ICC_SGI1R_IRQ_ROUTING_MODE_BIT);
target_cpus = (reg & ICC_SGI1R_TARGET_LIST_MASK) >> ICC_SGI1R_TARGET_LIST_SHIFT;
mpidr = SGI_AFFINITY_LEVEL(reg, 3);
mpidr |= SGI_AFFINITY_LEVEL(reg, 2);
mpidr |= SGI_AFFINITY_LEVEL(reg, 1);
/*
* We take the dist lock here, because we come from the sysregs
* code path and not from the MMIO one (which already takes the lock).
*/
spin_lock(&dist->lock);
/*
* We iterate over all VCPUs to find the MPIDRs matching the request.
* If we have handled one CPU, we clear it's bit to detect early
* if we are already finished. This avoids iterating through all
* VCPUs when most of the times we just signal a single VCPU.
*/
kvm_for_each_vcpu(c, c_vcpu, kvm) {
/* Exit early if we have dealt with all requested CPUs */
if (!broadcast && target_cpus == 0)
break;
/* Don't signal the calling VCPU */
if (broadcast && c == vcpu_id)
continue;
if (!broadcast) {
int level0;
level0 = match_mpidr(mpidr, target_cpus, c_vcpu);
if (level0 == -1)
continue;
/* remove this matching VCPU from the mask */
target_cpus &= ~BIT(level0);
}
/* Flag the SGI as pending */
vgic_dist_irq_set_pending(c_vcpu, sgi);
updated = 1;
kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
}
if (updated)
vgic_update_state(vcpu->kvm);
spin_unlock(&dist->lock);
if (updated)
vgic_kick_vcpus(vcpu->kvm);
}
static int vgic_v3_create(struct kvm_device *dev, u32 type)
{
return kvm_vgic_create(dev->kvm, type);
}
static void vgic_v3_destroy(struct kvm_device *dev)
{
kfree(dev);
}
static int vgic_v3_set_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
int ret;
ret = vgic_set_common_attr(dev, attr);
if (ret != -ENXIO)
return ret;
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
return -ENXIO;
}
return -ENXIO;
}
static int vgic_v3_get_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
int ret;
ret = vgic_get_common_attr(dev, attr);
if (ret != -ENXIO)
return ret;
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
return -ENXIO;
}
return -ENXIO;
}
static int vgic_v3_has_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_ADDR:
switch (attr->attr) {
case KVM_VGIC_V2_ADDR_TYPE_DIST:
case KVM_VGIC_V2_ADDR_TYPE_CPU:
return -ENXIO;
case KVM_VGIC_V3_ADDR_TYPE_DIST:
case KVM_VGIC_V3_ADDR_TYPE_REDIST:
return 0;
}
break;
case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
return -ENXIO;
case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
return 0;
case KVM_DEV_ARM_VGIC_GRP_CTRL:
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
return 0;
}
}
return -ENXIO;
}
struct kvm_device_ops kvm_arm_vgic_v3_ops = {
.name = "kvm-arm-vgic-v3",
.create = vgic_v3_create,
.destroy = vgic_v3_destroy,
.set_attr = vgic_v3_set_attr,
.get_attr = vgic_v3_get_attr,
.has_attr = vgic_v3_has_attr,
};
/*
* 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/irqchip/arm-gic-v3.h>
#include <linux/irqchip/arm-gic-common.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
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];
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
lr_desc.irq = val & ICH_LR_VIRTUAL_ID_MASK;
else
lr_desc.irq = val & GICH_LR_VIRTUALID;
lr_desc.source = 0;
if (lr_desc.irq <= 15 &&
vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2)
lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
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;
if (val & ICH_LR_HW) {
lr_desc.state |= LR_HW;
lr_desc.hwirq = (val >> ICH_LR_PHYS_ID_SHIFT) & GENMASK(9, 0);
}
return lr_desc;
}
static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
struct vgic_lr lr_desc)
{
u64 lr_val;
lr_val = lr_desc.irq;
/*
* Currently all guest IRQs are Group1, as Group0 would result
* in a FIQ in the guest, which it wouldn't expect.
* Eventually we want to make this configurable, so we may revisit
* this in the future.
*/
switch (vcpu->kvm->arch.vgic.vgic_model) {
case KVM_DEV_TYPE_ARM_VGIC_V3:
lr_val |= ICH_LR_GROUP;
break;
case KVM_DEV_TYPE_ARM_VGIC_V2:
if (lr_desc.irq < VGIC_NR_SGIS)
lr_val |= (u32)lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT;
break;
default:
BUG();
}
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;
if (lr_desc.state & LR_HW) {
lr_val |= ICH_LR_HW;
lr_val |= ((u64)lr_desc.hwirq) << ICH_LR_PHYS_ID_SHIFT;
}
vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = lr_val;
if (!(lr_desc.state & LR_STATE_MASK))
vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
else
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 void vgic_v3_clear_eisr(struct kvm_vcpu *vcpu)
{
vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr = 0;
}
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)
{
struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3;
/*
* By forcing VMCR to zero, the GIC will restore the binary
* points to their reset values. Anything else resets to zero
* anyway.
*/
vgic_v3->vgic_vmcr = 0;
vgic_v3->vgic_elrsr = ~0;
/*
* If we are emulating a GICv3, we do it in an non-GICv2-compatible
* way, so we force SRE to 1 to demonstrate this to the guest.
* This goes with the spec allowing the value to be RAO/WI.
*/
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
vgic_v3->vgic_sre = ICC_SRE_EL1_SRE;
else
vgic_v3->vgic_sre = 0;
/* Get the show on the road... */
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,
.get_elrsr = vgic_v3_get_elrsr,
.get_eisr = vgic_v3_get_eisr,
.clear_eisr = vgic_v3_clear_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;
static void vgic_cpu_init_lrs(void *params)
{
kvm_call_hyp(__vgic_v3_init_lrs);
}
/**
* vgic_v3_probe - probe for a GICv3 compatible interrupt controller
* @gic_kvm_info: pointer to the GIC description
* @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(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
const struct vgic_params **params)
{
int ret = 0;
struct vgic_params *vgic = &vgic_v3_params;
const struct resource *vcpu_res = &gic_kvm_info->vcpu;
vgic->maint_irq = gic_kvm_info->maint_irq;
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;
vgic->can_emulate_gicv2 = false;
if (!vcpu_res->start) {
kvm_info("GICv3: no GICV resource entry\n");
vgic->vcpu_base = 0;
} else if (!PAGE_ALIGNED(vcpu_res->start)) {
pr_warn("GICV physical address 0x%llx not page aligned\n",
(unsigned long long)vcpu_res->start);
vgic->vcpu_base = 0;
} else if (!PAGE_ALIGNED(resource_size(vcpu_res))) {
pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n",
(unsigned long long)resource_size(vcpu_res),
PAGE_SIZE);
} else {
vgic->vcpu_base = vcpu_res->start;
vgic->can_emulate_gicv2 = true;
kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
KVM_DEV_TYPE_ARM_VGIC_V2);
}
if (vgic->vcpu_base == 0)
kvm_info("disabling GICv2 emulation\n");
kvm_register_device_ops(&kvm_arm_vgic_v3_ops, KVM_DEV_TYPE_ARM_VGIC_V3);
vgic->vctrl_base = NULL;
vgic->type = VGIC_V3;
vgic->max_gic_vcpus = VGIC_V3_MAX_CPUS;
kvm_info("GICV base=0x%llx, IRQ=%d\n",
vgic->vcpu_base, vgic->maint_irq);
on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
*ops = &vgic_v3_ops;
*params = vgic;
return ret;
}
/*
* Copyright (C) 2012 ARM Ltd.
* 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, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/irq.h>
#include <linux/rculist.h>
#include <linux/uaccess.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>
#include <trace/events/kvm.h>
#include <asm/kvm.h>
#include <kvm/iodev.h>
#include <linux/irqchip/arm-gic-common.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
/*
* How the whole thing works (courtesy of Christoffer Dall):
*
* - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
* something is pending on the CPU interface.
* - Interrupts that are pending on the distributor are stored on the
* vgic.irq_pending vgic bitmap (this bitmap is updated by both user land
* ioctls and guest mmio ops, and other in-kernel peripherals such as the
* arch. timers).
* - Every time the bitmap changes, the irq_pending_on_cpu oracle is
* recalculated
* - To calculate the oracle, we need info for each cpu from
* compute_pending_for_cpu, which considers:
* - PPI: dist->irq_pending & dist->irq_enable
* - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target
* - irq_spi_target is a 'formatted' version of the GICD_ITARGETSRn
* registers, stored on each vcpu. We only keep one bit of
* information per interrupt, making sure that only one vcpu can
* accept the interrupt.
* - If any of the above state changes, we must recalculate the oracle.
* - The same is true when injecting an interrupt, except that we only
* consider a single interrupt at a time. The irq_spi_cpu array
* contains the target CPU for each SPI.
*
* The handling of level interrupts adds some extra complexity. We
* need to track when the interrupt has been EOIed, so we can sample
* the 'line' again. This is achieved as such:
*
* - When a level interrupt is moved onto a vcpu, the corresponding
* bit in irq_queued is set. As long as this bit is set, the line
* will be ignored for further interrupts. The interrupt is injected
* into the vcpu with the GICH_LR_EOI bit set (generate a
* maintenance interrupt on EOI).
* - When the interrupt is EOIed, the maintenance interrupt fires,
* and clears the corresponding bit in irq_queued. This allows the
* interrupt line to be sampled again.
* - Note that level-triggered interrupts can also be set to pending from
* writes to GICD_ISPENDRn and lowering the external input line does not
* cause the interrupt to become inactive in such a situation.
* Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become
* inactive as long as the external input line is held high.
*
*
* Initialization rules: there are multiple stages to the vgic
* initialization, both for the distributor and the CPU interfaces.
*
* Distributor:
*
* - kvm_vgic_early_init(): initialization of static data that doesn't
* depend on any sizing information or emulation type. No allocation
* is allowed there.
*
* - vgic_init(): allocation and initialization of the generic data
* structures that depend on sizing information (number of CPUs,
* number of interrupts). Also initializes the vcpu specific data
* structures. Can be executed lazily for GICv2.
* [to be renamed to kvm_vgic_init??]
*
* CPU Interface:
*
* - kvm_vgic_cpu_early_init(): initialization of static data that
* doesn't depend on any sizing information or emulation type. No
* allocation is allowed there.
*/
#include "vgic.h"
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu);
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 u64 vgic_get_elrsr(struct kvm_vcpu *vcpu);
static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
int virt_irq);
static int compute_pending_for_cpu(struct kvm_vcpu *vcpu);
static const struct vgic_ops *vgic_ops;
static const struct vgic_params *vgic;
static void add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
{
vcpu->kvm->arch.vgic.vm_ops.add_sgi_source(vcpu, irq, source);
}
static bool queue_sgi(struct kvm_vcpu *vcpu, int irq)
{
return vcpu->kvm->arch.vgic.vm_ops.queue_sgi(vcpu, irq);
}
int kvm_vgic_map_resources(struct kvm *kvm)
{
return kvm->arch.vgic.vm_ops.map_resources(kvm, vgic);
}
/*
* struct vgic_bitmap contains a bitmap made of unsigned longs, but
* extracts u32s out of them.
*
* 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 int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs)
{
int nr_longs;
nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL);
if (!b->private)
return -ENOMEM;
b->shared = b->private + nr_cpus;
return 0;
}
static void vgic_free_bitmap(struct vgic_bitmap *b)
{
kfree(b->private);
b->private = NULL;
b->shared = NULL;
}
/*
* Call this function to convert a u64 value to an unsigned long * bitmask
* in a way that works on both 32-bit and 64-bit LE and BE platforms.
*
* Warning: Calling this function may modify *val.
*/
static unsigned long *u64_to_bitmask(u64 *val)
{
#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
*val = (*val >> 32) | (*val << 32);
#endif
return (unsigned long *)val;
}
u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, int cpuid, u32 offset)
{
offset >>= 2;
if (!offset)
return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE;
else
return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
}
static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
int cpuid, int irq)
{
if (irq < VGIC_NR_PRIVATE_IRQS)
return test_bit(irq, x->private + cpuid);
return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
}
void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
int irq, int val)
{
unsigned long *reg;
if (irq < VGIC_NR_PRIVATE_IRQS) {
reg = x->private + cpuid;
} else {
reg = x->shared;
irq -= VGIC_NR_PRIVATE_IRQS;
}
if (val)
set_bit(irq, reg);
else
clear_bit(irq, reg);
}
static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
{
return x->private + cpuid;
}
unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
{
return x->shared;
}
static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs)
{
int size;
size = nr_cpus * VGIC_NR_PRIVATE_IRQS;
size += nr_irqs - VGIC_NR_PRIVATE_IRQS;
x->private = kzalloc(size, GFP_KERNEL);
if (!x->private)
return -ENOMEM;
x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32);
return 0;
}
static void vgic_free_bytemap(struct vgic_bytemap *b)
{
kfree(b->private);
b->private = NULL;
b->shared = NULL;
}
u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
{
u32 *reg;
if (offset < VGIC_NR_PRIVATE_IRQS) {
reg = x->private;
offset += cpuid * VGIC_NR_PRIVATE_IRQS;
} else {
reg = x->shared;
offset -= VGIC_NR_PRIVATE_IRQS;
}
return reg + (offset / sizeof(u32));
}
#define VGIC_CFG_LEVEL 0
#define VGIC_CFG_EDGE 1
static bool vgic_irq_is_edge(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
int irq_val;
irq_val = vgic_bitmap_get_irq_val(&dist->irq_cfg, vcpu->vcpu_id, irq);
return irq_val == VGIC_CFG_EDGE;
}
static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
}
static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
}
static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq);
}
static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1);
}
static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
}
static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1);
}
static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0);
}
static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq);
}
static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1);
}
static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0);
}
static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq);
}
static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
if (!vgic_dist_irq_get_level(vcpu, irq)) {
vgic_dist_irq_clear_pending(vcpu, irq);
if (!compute_pending_for_cpu(vcpu))
clear_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
}
}
static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
}
void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
}
void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0);
}
static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
{
if (irq < VGIC_NR_PRIVATE_IRQS)
set_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
else
set_bit(irq - VGIC_NR_PRIVATE_IRQS,
vcpu->arch.vgic_cpu.pending_shared);
}
void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
{
if (irq < VGIC_NR_PRIVATE_IRQS)
clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
else
clear_bit(irq - VGIC_NR_PRIVATE_IRQS,
vcpu->arch.vgic_cpu.pending_shared);
}
static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
{
return !vgic_irq_is_queued(vcpu, irq);
}
/**
* vgic_reg_access - access vgic register
* @mmio: pointer to the data describing the mmio access
* @reg: pointer to the virtual backing of vgic distributor data
* @offset: least significant 2 bits used for word offset
* @mode: ACCESS_ mode (see defines above)
*
* Helper to make vgic register access easier using one of the access
* modes defined for vgic register access
* (read,raz,write-ignored,setbit,clearbit,write)
*/
void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
phys_addr_t offset, int mode)
{
int word_offset = (offset & 3) * 8;
u32 mask = (1UL << (mmio->len * 8)) - 1;
u32 regval;
/*
* Any alignment fault should have been delivered to the guest
* directly (ARM ARM B3.12.7 "Prioritization of aborts").
*/
if (reg) {
regval = *reg;
} else {
BUG_ON(mode != (ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED));
regval = 0;
}
if (mmio->is_write) {
u32 data = mmio_data_read(mmio, mask) << word_offset;
switch (ACCESS_WRITE_MASK(mode)) {
case ACCESS_WRITE_IGNORED:
return;
case ACCESS_WRITE_SETBIT:
regval |= data;
break;
case ACCESS_WRITE_CLEARBIT:
regval &= ~data;
break;
case ACCESS_WRITE_VALUE:
regval = (regval & ~(mask << word_offset)) | data;
break;
}
*reg = regval;
} else {
switch (ACCESS_READ_MASK(mode)) {
case ACCESS_READ_RAZ:
regval = 0;
/* fall through */
case ACCESS_READ_VALUE:
mmio_data_write(mmio, mask, regval >> word_offset);
}
}
}
bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
vgic_reg_access(mmio, NULL, offset,
ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
return false;
}
bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id, int access)
{
u32 *reg;
int mode = ACCESS_READ_VALUE | access;
struct kvm_vcpu *target_vcpu = kvm_get_vcpu(kvm, vcpu_id);
reg = vgic_bitmap_get_reg(&kvm->arch.vgic.irq_enabled, vcpu_id, offset);
vgic_reg_access(mmio, reg, offset, mode);
if (mmio->is_write) {
if (access & ACCESS_WRITE_CLEARBIT) {
if (offset < 4) /* Force SGI enabled */
*reg |= 0xffff;
vgic_retire_disabled_irqs(target_vcpu);
}
vgic_update_state(kvm);
return true;
}
return false;
}
bool vgic_handle_set_pending_reg(struct kvm *kvm,
struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id)
{
u32 *reg, orig;
u32 level_mask;
int mode = ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT;
struct vgic_dist *dist = &kvm->arch.vgic;
reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu_id, offset);
level_mask = (~(*reg));
/* Mark both level and edge triggered irqs as pending */
reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
orig = *reg;
vgic_reg_access(mmio, reg, offset, mode);
if (mmio->is_write) {
/* Set the soft-pending flag only for level-triggered irqs */
reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
vcpu_id, offset);
vgic_reg_access(mmio, reg, offset, mode);
*reg &= level_mask;
/* Ignore writes to SGIs */
if (offset < 2) {
*reg &= ~0xffff;
*reg |= orig & 0xffff;
}
vgic_update_state(kvm);
return true;
}
return false;
}
bool vgic_handle_clear_pending_reg(struct kvm *kvm,
struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id)
{
u32 *level_active;
u32 *reg, orig;
int mode = ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT;
struct vgic_dist *dist = &kvm->arch.vgic;
reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
orig = *reg;
vgic_reg_access(mmio, reg, offset, mode);
if (mmio->is_write) {
/* Re-set level triggered level-active interrupts */
level_active = vgic_bitmap_get_reg(&dist->irq_level,
vcpu_id, offset);
reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
*reg |= *level_active;
/* Ignore writes to SGIs */
if (offset < 2) {
*reg &= ~0xffff;
*reg |= orig & 0xffff;
}
/* Clear soft-pending flags */
reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
vcpu_id, offset);
vgic_reg_access(mmio, reg, offset, mode);
vgic_update_state(kvm);
return true;
}
return false;
}
bool vgic_handle_set_active_reg(struct kvm *kvm,
struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id)
{
u32 *reg;
struct vgic_dist *dist = &kvm->arch.vgic;
reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset);
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
if (mmio->is_write) {
vgic_update_state(kvm);
return true;
}
return false;
}
bool vgic_handle_clear_active_reg(struct kvm *kvm,
struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id)
{
u32 *reg;
struct vgic_dist *dist = &kvm->arch.vgic;
reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset);
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
if (mmio->is_write) {
vgic_update_state(kvm);
return true;
}
return false;
}
static u32 vgic_cfg_expand(u16 val)
{
u32 res = 0;
int i;
/*
* Turn a 16bit value like abcd...mnop into a 32bit word
* a0b0c0d0...m0n0o0p0, which is what the HW cfg register is.
*/
for (i = 0; i < 16; i++)
res |= ((val >> i) & VGIC_CFG_EDGE) << (2 * i + 1);
return res;
}
static u16 vgic_cfg_compress(u32 val)
{
u16 res = 0;
int i;
/*
* Turn a 32bit word a0b0c0d0...m0n0o0p0 into 16bit value like
* abcd...mnop which is what we really care about.
*/
for (i = 0; i < 16; i++)
res |= ((val >> (i * 2 + 1)) & VGIC_CFG_EDGE) << i;
return res;
}
/*
* The distributor uses 2 bits per IRQ for the CFG register, but the
* LSB is always 0. As such, we only keep the upper bit, and use the
* two above functions to compress/expand the bits
*/
bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
u32 val;
if (offset & 4)
val = *reg >> 16;
else
val = *reg & 0xffff;
val = vgic_cfg_expand(val);
vgic_reg_access(mmio, &val, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
if (mmio->is_write) {
/* Ignore writes to read-only SGI and PPI bits */
if (offset < 8)
return false;
val = vgic_cfg_compress(val);
if (offset & 4) {
*reg &= 0xffff;
*reg |= val << 16;
} else {
*reg &= 0xffff << 16;
*reg |= val;
}
}
return false;
}
/**
* vgic_unqueue_irqs - move pending/active IRQs from LRs to the distributor
* @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
*
* Move any IRQs that have already been assigned to LRs back to the
* emulated distributor state so that the complete emulated state can be read
* from the main emulation structures without investigating the LRs.
*/
void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
{
u64 elrsr = vgic_get_elrsr(vcpu);
unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
int i;
for_each_clear_bit(i, elrsr_ptr, vgic->nr_lr) {
struct vgic_lr lr = vgic_get_lr(vcpu, i);
/*
* There are three options for the state bits:
*
* 01: pending
* 10: active
* 11: pending and active
*/
BUG_ON(!(lr.state & LR_STATE_MASK));
/* Reestablish SGI source for pending and active IRQs */
if (lr.irq < VGIC_NR_SGIS)
add_sgi_source(vcpu, lr.irq, lr.source);
/*
* If the LR holds an active (10) or a pending and active (11)
* interrupt then move the active state to the
* distributor tracking bit.
*/
if (lr.state & LR_STATE_ACTIVE)
vgic_irq_set_active(vcpu, lr.irq);
/*
* Reestablish the pending state on the distributor and the
* CPU interface and mark the LR as free for other use.
*/
vgic_retire_lr(i, vcpu);
/* Finally update the VGIC state. */
vgic_update_state(vcpu->kvm);
}
}
const
struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges,
int len, gpa_t offset)
{
while (ranges->len) {
if (offset >= ranges->base &&
(offset + len) <= (ranges->base + ranges->len))
return ranges;
ranges++;
}
return NULL;
}
static bool vgic_validate_access(const struct vgic_dist *dist,
const struct vgic_io_range *range,
unsigned long offset)
{
int irq;
if (!range->bits_per_irq)
return true; /* Not an irq-based access */
irq = offset * 8 / range->bits_per_irq;
if (irq >= dist->nr_irqs)
return false;
return true;
}
/*
* Call the respective handler function for the given range.
* We split up any 64 bit accesses into two consecutive 32 bit
* handler calls and merge the result afterwards.
* We do this in a little endian fashion regardless of the host's
* or guest's endianness, because the GIC is always LE and the rest of
* the code (vgic_reg_access) also puts it in a LE fashion already.
* At this point we have already identified the handle function, so
* range points to that one entry and offset is relative to this.
*/
static bool call_range_handler(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
unsigned long offset,
const struct vgic_io_range *range)
{
struct kvm_exit_mmio mmio32;
bool ret;
if (likely(mmio->len <= 4))
return range->handle_mmio(vcpu, mmio, offset);
/*
* Any access bigger than 4 bytes (that we currently handle in KVM)
* is actually 8 bytes long, caused by a 64-bit access
*/
mmio32.len = 4;
mmio32.is_write = mmio->is_write;
mmio32.private = mmio->private;
mmio32.phys_addr = mmio->phys_addr + 4;
mmio32.data = &((u32 *)mmio->data)[1];
ret = range->handle_mmio(vcpu, &mmio32, offset + 4);
mmio32.phys_addr = mmio->phys_addr;
mmio32.data = &((u32 *)mmio->data)[0];
ret |= range->handle_mmio(vcpu, &mmio32, offset);
return ret;
}
/**
* vgic_handle_mmio_access - handle an in-kernel MMIO access
* This is called by the read/write KVM IO device wrappers below.
* @vcpu: pointer to the vcpu performing the access
* @this: pointer to the KVM IO device in charge
* @addr: guest physical address of the access
* @len: size of the access
* @val: pointer to the data region
* @is_write: read or write access
*
* returns true if the MMIO access could be performed
*/
static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu,
struct kvm_io_device *this, gpa_t addr,
int len, void *val, bool is_write)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_io_device *iodev = container_of(this,
struct vgic_io_device, dev);
const struct vgic_io_range *range;
struct kvm_exit_mmio mmio;
bool updated_state;
gpa_t offset;
offset = addr - iodev->addr;
range = vgic_find_range(iodev->reg_ranges, len, offset);
if (unlikely(!range || !range->handle_mmio)) {
pr_warn("Unhandled access %d %08llx %d\n", is_write, addr, len);
return -ENXIO;
}
mmio.phys_addr = addr;
mmio.len = len;
mmio.is_write = is_write;
mmio.data = val;
mmio.private = iodev->redist_vcpu;
spin_lock(&dist->lock);
offset -= range->base;
if (vgic_validate_access(dist, range, offset)) {
updated_state = call_range_handler(vcpu, &mmio, offset, range);
} else {
if (!is_write)
memset(val, 0, len);
updated_state = false;
}
spin_unlock(&dist->lock);
if (updated_state)
vgic_kick_vcpus(vcpu->kvm);
return 0;
}
static int vgic_handle_mmio_read(struct kvm_vcpu *vcpu,
struct kvm_io_device *this,
gpa_t addr, int len, void *val)
{
return vgic_handle_mmio_access(vcpu, this, addr, len, val, false);
}
static int vgic_handle_mmio_write(struct kvm_vcpu *vcpu,
struct kvm_io_device *this,
gpa_t addr, int len, const void *val)
{
return vgic_handle_mmio_access(vcpu, this, addr, len, (void *)val,
true);
}
static struct kvm_io_device_ops vgic_io_ops = {
.read = vgic_handle_mmio_read,
.write = vgic_handle_mmio_write,
};
/**
* vgic_register_kvm_io_dev - register VGIC register frame on the KVM I/O bus
* @kvm: The VM structure pointer
* @base: The (guest) base address for the register frame
* @len: Length of the register frame window
* @ranges: Describing the handler functions for each register
* @redist_vcpu_id: The VCPU ID to pass on to the handlers on call
* @iodev: Points to memory to be passed on to the handler
*
* @iodev stores the parameters of this function to be usable by the handler
* respectively the dispatcher function (since the KVM I/O bus framework lacks
* an opaque parameter). Initialization is done in this function, but the
* reference should be valid and unique for the whole VGIC lifetime.
* If the register frame is not mapped for a specific VCPU, pass -1 to
* @redist_vcpu_id.
*/
int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len,
const struct vgic_io_range *ranges,
int redist_vcpu_id,
struct vgic_io_device *iodev)
{
struct kvm_vcpu *vcpu = NULL;
int ret;
if (redist_vcpu_id >= 0)
vcpu = kvm_get_vcpu(kvm, redist_vcpu_id);
iodev->addr = base;
iodev->len = len;
iodev->reg_ranges = ranges;
iodev->redist_vcpu = vcpu;
kvm_iodevice_init(&iodev->dev, &vgic_io_ops);
mutex_lock(&kvm->slots_lock);
ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, base, len,
&iodev->dev);
mutex_unlock(&kvm->slots_lock);
/* Mark the iodev as invalid if registration fails. */
if (ret)
iodev->dev.ops = NULL;
return ret;
}
static int vgic_nr_shared_irqs(struct vgic_dist *dist)
{
return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
}
static int compute_active_for_cpu(struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
unsigned long *active, *enabled, *act_percpu, *act_shared;
unsigned long active_private, active_shared;
int nr_shared = vgic_nr_shared_irqs(dist);
int vcpu_id;
vcpu_id = vcpu->vcpu_id;
act_percpu = vcpu->arch.vgic_cpu.active_percpu;
act_shared = vcpu->arch.vgic_cpu.active_shared;
active = vgic_bitmap_get_cpu_map(&dist->irq_active, vcpu_id);
enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
bitmap_and(act_percpu, active, enabled, VGIC_NR_PRIVATE_IRQS);
active = vgic_bitmap_get_shared_map(&dist->irq_active);
enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
bitmap_and(act_shared, active, enabled, nr_shared);
bitmap_and(act_shared, act_shared,
vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
nr_shared);
active_private = find_first_bit(act_percpu, VGIC_NR_PRIVATE_IRQS);
active_shared = find_first_bit(act_shared, nr_shared);
return (active_private < VGIC_NR_PRIVATE_IRQS ||
active_shared < nr_shared);
}
static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
unsigned long pending_private, pending_shared;
int nr_shared = vgic_nr_shared_irqs(dist);
int vcpu_id;
vcpu_id = vcpu->vcpu_id;
pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
pend_shared = vcpu->arch.vgic_cpu.pending_shared;
if (!dist->enabled) {
bitmap_zero(pend_percpu, VGIC_NR_PRIVATE_IRQS);
bitmap_zero(pend_shared, nr_shared);
return 0;
}
pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
bitmap_and(pend_shared, pending, enabled, nr_shared);
bitmap_and(pend_shared, pend_shared,
vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
nr_shared);
pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
pending_shared = find_first_bit(pend_shared, nr_shared);
return (pending_private < VGIC_NR_PRIVATE_IRQS ||
pending_shared < vgic_nr_shared_irqs(dist));
}
/*
* Update the interrupt state and determine which CPUs have pending
* or active interrupts. Must be called with distributor lock held.
*/
void vgic_update_state(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int c;
kvm_for_each_vcpu(c, vcpu, kvm) {
if (compute_pending_for_cpu(vcpu))
set_bit(c, dist->irq_pending_on_cpu);
if (compute_active_for_cpu(vcpu))
set_bit(c, dist->irq_active_on_cpu);
else
clear_bit(c, dist->irq_active_on_cpu);
}
}
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 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 void vgic_clear_eisr(struct kvm_vcpu *vcpu)
{
vgic_ops->clear_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);
}
void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
{
vgic_ops->get_vmcr(vcpu, vmcr);
}
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, struct kvm_vcpu *vcpu)
{
struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr);
vgic_irq_clear_queued(vcpu, vlr.irq);
/*
* We must transfer the pending state back to the distributor before
* retiring the LR, otherwise we may loose edge-triggered interrupts.
*/
if (vlr.state & LR_STATE_PENDING) {
vgic_dist_irq_set_pending(vcpu, vlr.irq);
vlr.hwirq = 0;
}
vlr.state = 0;
vgic_set_lr(vcpu, lr_nr, vlr);
}
static bool dist_active_irq(struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu);
}
bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq)
{
int i;
for (i = 0; i < vgic->nr_lr; i++) {
struct vgic_lr vlr = vgic_get_lr(vcpu, i);
if (vlr.irq == virt_irq && vlr.state & LR_STATE_ACTIVE)
return true;
}
return vgic_irq_is_active(vcpu, virt_irq);
}
/*
* An interrupt may have been disabled after being made pending on the
* CPU interface (the classic case is a timer running while we're
* rebooting the guest - the interrupt would kick as soon as the CPU
* interface gets enabled, with deadly consequences).
*
* The solution is to examine already active LRs, and check the
* interrupt is still enabled. If not, just retire it.
*/
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
{
u64 elrsr = vgic_get_elrsr(vcpu);
unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
int lr;
for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) {
struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
if (!vgic_irq_is_enabled(vcpu, vlr.irq))
vgic_retire_lr(lr, vcpu);
}
}
static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq,
int lr_nr, struct vgic_lr vlr)
{
if (vgic_irq_is_active(vcpu, irq)) {
vlr.state |= LR_STATE_ACTIVE;
kvm_debug("Set active, clear distributor: 0x%x\n", vlr.state);
vgic_irq_clear_active(vcpu, irq);
vgic_update_state(vcpu->kvm);
} else {
WARN_ON(!vgic_dist_irq_is_pending(vcpu, irq));
vlr.state |= LR_STATE_PENDING;
kvm_debug("Set pending: 0x%x\n", vlr.state);
}
if (!vgic_irq_is_edge(vcpu, irq))
vlr.state |= LR_EOI_INT;
if (vlr.irq >= VGIC_NR_SGIS) {
struct irq_phys_map *map;
map = vgic_irq_map_search(vcpu, irq);
if (map) {
vlr.hwirq = map->phys_irq;
vlr.state |= LR_HW;
vlr.state &= ~LR_EOI_INT;
/*
* Make sure we're not going to sample this
* again, as a HW-backed interrupt cannot be
* in the PENDING_ACTIVE stage.
*/
vgic_irq_set_queued(vcpu, irq);
}
}
vgic_set_lr(vcpu, lr_nr, vlr);
}
/*
* Queue an interrupt to a CPU virtual interface. Return true on success,
* or false if it wasn't possible to queue it.
* sgi_source must be zero for any non-SGI interrupts.
*/
bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
u64 elrsr = vgic_get_elrsr(vcpu);
unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
struct vgic_lr vlr;
int lr;
/* Sanitize the input... */
BUG_ON(sgi_source_id & ~7);
BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
BUG_ON(irq >= dist->nr_irqs);
kvm_debug("Queue IRQ%d\n", irq);
/* Do we have an active interrupt for the same CPUID? */
for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) {
vlr = vgic_get_lr(vcpu, lr);
if (vlr.irq == irq && vlr.source == sgi_source_id) {
kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
vgic_queue_irq_to_lr(vcpu, irq, lr, vlr);
return true;
}
}
/* Try to use another LR for this interrupt */
lr = find_first_bit(elrsr_ptr, 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);
vlr.irq = irq;
vlr.source = sgi_source_id;
vlr.state = 0;
vgic_queue_irq_to_lr(vcpu, irq, lr, vlr);
return true;
}
static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
{
if (!vgic_can_sample_irq(vcpu, irq))
return true; /* level interrupt, already queued */
if (vgic_queue_irq(vcpu, 0, irq)) {
if (vgic_irq_is_edge(vcpu, irq)) {
vgic_dist_irq_clear_pending(vcpu, irq);
vgic_cpu_irq_clear(vcpu, irq);
} else {
vgic_irq_set_queued(vcpu, irq);
}
return true;
}
return false;
}
/*
* Fill the list registers with pending interrupts before running the
* guest.
*/
static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
unsigned long *pa_percpu, *pa_shared;
int i, vcpu_id;
int overflow = 0;
int nr_shared = vgic_nr_shared_irqs(dist);
vcpu_id = vcpu->vcpu_id;
pa_percpu = vcpu->arch.vgic_cpu.pend_act_percpu;
pa_shared = vcpu->arch.vgic_cpu.pend_act_shared;
bitmap_or(pa_percpu, vgic_cpu->pending_percpu, vgic_cpu->active_percpu,
VGIC_NR_PRIVATE_IRQS);
bitmap_or(pa_shared, vgic_cpu->pending_shared, vgic_cpu->active_shared,
nr_shared);
/*
* We may not have any pending interrupt, or the interrupts
* may have been serviced from another vcpu. In all cases,
* move along.
*/
if (!kvm_vgic_vcpu_pending_irq(vcpu) && !dist_active_irq(vcpu))
goto epilog;
/* SGIs */
for_each_set_bit(i, pa_percpu, VGIC_NR_SGIS) {
if (!queue_sgi(vcpu, i))
overflow = 1;
}
/* PPIs */
for_each_set_bit_from(i, pa_percpu, VGIC_NR_PRIVATE_IRQS) {
if (!vgic_queue_hwirq(vcpu, i))
overflow = 1;
}
/* SPIs */
for_each_set_bit(i, pa_shared, nr_shared) {
if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
overflow = 1;
}
epilog:
if (overflow) {
vgic_enable_underflow(vcpu);
} else {
vgic_disable_underflow(vcpu);
/*
* We're about to run this VCPU, and we've consumed
* everything the distributor had in store for
* us. Claim we don't have anything pending. We'll
* adjust that if needed while exiting.
*/
clear_bit(vcpu_id, dist->irq_pending_on_cpu);
}
}
static int process_queued_irq(struct kvm_vcpu *vcpu,
int lr, struct vgic_lr vlr)
{
int pending = 0;
/*
* If the IRQ was EOIed (called from vgic_process_maintenance) or it
* went from active to non-active (called from vgic_sync_hwirq) it was
* also ACKed and we we therefore assume we can clear the soft pending
* state (should it had been set) for this interrupt.
*
* Note: if the IRQ soft pending state was set after the IRQ was
* acked, it actually shouldn't be cleared, but we have no way of
* knowing that unless we start trapping ACKs when the soft-pending
* state is set.
*/
vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
/*
* Tell the gic to start sampling this interrupt again.
*/
vgic_irq_clear_queued(vcpu, vlr.irq);
/* Any additional pending interrupt? */
if (vgic_irq_is_edge(vcpu, vlr.irq)) {
BUG_ON(!(vlr.state & LR_HW));
pending = vgic_dist_irq_is_pending(vcpu, vlr.irq);
} else {
if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
vgic_cpu_irq_set(vcpu, vlr.irq);
pending = 1;
} else {
vgic_dist_irq_clear_pending(vcpu, vlr.irq);
vgic_cpu_irq_clear(vcpu, vlr.irq);
}
}
/*
* Despite being EOIed, the LR may not have
* been marked as empty.
*/
vlr.state = 0;
vlr.hwirq = 0;
vgic_set_lr(vcpu, lr, vlr);
return pending;
}
static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
{
u32 status = vgic_get_interrupt_status(vcpu);
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct kvm *kvm = vcpu->kvm;
int level_pending = 0;
kvm_debug("STATUS = %08x\n", status);
if (status & INT_STATUS_EOI) {
/*
* Some level interrupts have been EOIed. Clear their
* active bit.
*/
u64 eisr = vgic_get_eisr(vcpu);
unsigned long *eisr_ptr = u64_to_bitmask(&eisr);
int lr;
for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
WARN_ON(vlr.state & LR_STATE_MASK);
/*
* kvm_notify_acked_irq calls kvm_set_irq()
* to reset the IRQ level, which grabs the dist->lock
* so we call this before taking the dist->lock.
*/
kvm_notify_acked_irq(kvm, 0,
vlr.irq - VGIC_NR_PRIVATE_IRQS);
spin_lock(&dist->lock);
level_pending |= process_queued_irq(vcpu, lr, vlr);
spin_unlock(&dist->lock);
}
}
if (status & INT_STATUS_UNDERFLOW)
vgic_disable_underflow(vcpu);
/*
* In the next iterations of the vcpu loop, if we sync the vgic state
* after flushing it, but before entering the guest (this happens for
* pending signals and vmid rollovers), then make sure we don't pick
* up any old maintenance interrupts here.
*/
vgic_clear_eisr(vcpu);
return level_pending;
}
/*
* Save the physical active state, and reset it to inactive.
*
* Return true if there's a pending forwarded interrupt to queue.
*/
static bool vgic_sync_hwirq(struct kvm_vcpu *vcpu, int lr, struct vgic_lr vlr)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
bool level_pending;
if (!(vlr.state & LR_HW))
return false;
if (vlr.state & LR_STATE_ACTIVE)
return false;
spin_lock(&dist->lock);
level_pending = process_queued_irq(vcpu, lr, vlr);
spin_unlock(&dist->lock);
return level_pending;
}
/* Sync back the VGIC state after a guest run */
static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
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);
/* Deal with HW interrupts, and clear mappings for empty LRs */
for (lr = 0; lr < vgic->nr_lr; lr++) {
struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
level_pending |= vgic_sync_hwirq(vcpu, lr, vlr);
BUG_ON(vlr.irq >= dist->nr_irqs);
}
/* Check if we still have something up our sleeve... */
elrsr = vgic_get_elrsr(vcpu);
elrsr_ptr = u64_to_bitmask(&elrsr);
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);
}
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
if (!irqchip_in_kernel(vcpu->kvm))
return;
spin_lock(&dist->lock);
__kvm_vgic_flush_hwstate(vcpu);
spin_unlock(&dist->lock);
}
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
if (!irqchip_in_kernel(vcpu->kvm))
return;
__kvm_vgic_sync_hwstate(vcpu);
}
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
if (!irqchip_in_kernel(vcpu->kvm))
return 0;
return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
}
void vgic_kick_vcpus(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
int c;
/*
* We've injected an interrupt, time to find out who deserves
* a good kick...
*/
kvm_for_each_vcpu(c, vcpu, kvm) {
if (kvm_vgic_vcpu_pending_irq(vcpu))
kvm_vcpu_kick(vcpu);
}
}
static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
{
int edge_triggered = vgic_irq_is_edge(vcpu, irq);
/*
* Only inject an interrupt if:
* - edge triggered and we have a rising edge
* - level triggered and we change level
*/
if (edge_triggered) {
int state = vgic_dist_irq_is_pending(vcpu, irq);
return level > state;
} else {
int state = vgic_dist_irq_get_level(vcpu, irq);
return level != state;
}
}
static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
unsigned int irq_num, bool level)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int edge_triggered, level_triggered;
int enabled;
bool ret = true, can_inject = true;
trace_vgic_update_irq_pending(cpuid, irq_num, level);
if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020))
return -EINVAL;
spin_lock(&dist->lock);
vcpu = kvm_get_vcpu(kvm, cpuid);
edge_triggered = vgic_irq_is_edge(vcpu, irq_num);
level_triggered = !edge_triggered;
if (!vgic_validate_injection(vcpu, irq_num, level)) {
ret = false;
goto out;
}
if (irq_num >= VGIC_NR_PRIVATE_IRQS) {
cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS];
if (cpuid == VCPU_NOT_ALLOCATED) {
/* Pretend we use CPU0, and prevent injection */
cpuid = 0;
can_inject = false;
}
vcpu = kvm_get_vcpu(kvm, cpuid);
}
kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
if (level) {
if (level_triggered)
vgic_dist_irq_set_level(vcpu, irq_num);
vgic_dist_irq_set_pending(vcpu, irq_num);
} else {
if (level_triggered) {
vgic_dist_irq_clear_level(vcpu, irq_num);
if (!vgic_dist_irq_soft_pend(vcpu, irq_num)) {
vgic_dist_irq_clear_pending(vcpu, irq_num);
vgic_cpu_irq_clear(vcpu, irq_num);
if (!compute_pending_for_cpu(vcpu))
clear_bit(cpuid, dist->irq_pending_on_cpu);
}
}
ret = false;
goto out;
}
enabled = vgic_irq_is_enabled(vcpu, irq_num);
if (!enabled || !can_inject) {
ret = false;
goto out;
}
if (!vgic_can_sample_irq(vcpu, irq_num)) {
/*
* Level interrupt in progress, will be picked up
* when EOId.
*/
ret = false;
goto out;
}
if (level) {
vgic_cpu_irq_set(vcpu, irq_num);
set_bit(cpuid, dist->irq_pending_on_cpu);
}
out:
spin_unlock(&dist->lock);
if (ret) {
/* kick the specified vcpu */
kvm_vcpu_kick(kvm_get_vcpu(kvm, cpuid));
}
return 0;
}
static int vgic_lazy_init(struct kvm *kvm)
{
int ret = 0;
if (unlikely(!vgic_initialized(kvm))) {
/*
* We only provide the automatic initialization of the VGIC
* for the legacy case of a GICv2. Any other type must
* be explicitly initialized once setup with the respective
* KVM device call.
*/
if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2)
return -EBUSY;
mutex_lock(&kvm->lock);
ret = vgic_init(kvm);
mutex_unlock(&kvm->lock);
}
return ret;
}
/**
* kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
* @kvm: The VM structure pointer
* @cpuid: The CPU for PPIs
* @irq_num: The IRQ number that is assigned to the device. This IRQ
* must not be mapped to a HW interrupt.
* @level: Edge-triggered: true: to trigger the interrupt
* false: to ignore the call
* Level-sensitive true: raise the input signal
* false: lower the input signal
*
* The GIC is not concerned with devices being active-LOW or active-HIGH for
* level-sensitive interrupts. You can think of the level parameter as 1
* being HIGH and 0 being LOW and all devices being active-HIGH.
*/
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
bool level)
{
struct irq_phys_map *map;
int ret;
ret = vgic_lazy_init(kvm);
if (ret)
return ret;
map = vgic_irq_map_search(kvm_get_vcpu(kvm, cpuid), irq_num);
if (map)
return -EINVAL;
return vgic_update_irq_pending(kvm, cpuid, irq_num, level);
}
/**
* kvm_vgic_inject_mapped_irq - Inject a physically mapped IRQ to the vgic
* @kvm: The VM structure pointer
* @cpuid: The CPU for PPIs
* @virt_irq: The virtual IRQ to be injected
* @level: Edge-triggered: true: to trigger the interrupt
* false: to ignore the call
* Level-sensitive true: raise the input signal
* false: lower the input signal
*
* The GIC is not concerned with devices being active-LOW or active-HIGH for
* level-sensitive interrupts. You can think of the level parameter as 1
* being HIGH and 0 being LOW and all devices being active-HIGH.
*/
int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
unsigned int virt_irq, bool level)
{
int ret;
ret = vgic_lazy_init(kvm);
if (ret)
return ret;
return vgic_update_irq_pending(kvm, cpuid, virt_irq, level);
}
static irqreturn_t vgic_maintenance_handler(int irq, void *data)
{
/*
* We cannot rely on the vgic maintenance interrupt to be
* delivered synchronously. This means we can only use it to
* exit the VM, and we perform the handling of EOIed
* interrupts on the exit path (see vgic_process_maintenance).
*/
return IRQ_HANDLED;
}
static struct list_head *vgic_get_irq_phys_map_list(struct kvm_vcpu *vcpu,
int virt_irq)
{
if (virt_irq < VGIC_NR_PRIVATE_IRQS)
return &vcpu->arch.vgic_cpu.irq_phys_map_list;
else
return &vcpu->kvm->arch.vgic.irq_phys_map_list;
}
/**
* kvm_vgic_map_phys_irq - map a virtual IRQ to a physical IRQ
* @vcpu: The VCPU pointer
* @virt_irq: The virtual IRQ number for the guest
* @phys_irq: The hardware IRQ number of the host
*
* Establish a mapping between a guest visible irq (@virt_irq) and a
* hardware irq (@phys_irq). On injection, @virt_irq will be associated with
* the physical interrupt represented by @phys_irq. This mapping can be
* established multiple times as long as the parameters are the same.
*
* Returns 0 on success or an error value otherwise.
*/
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct list_head *root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
struct irq_phys_map *map;
struct irq_phys_map_entry *entry;
int ret = 0;
/* Create a new mapping */
entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return -ENOMEM;
spin_lock(&dist->irq_phys_map_lock);
/* Try to match an existing mapping */
map = vgic_irq_map_search(vcpu, virt_irq);
if (map) {
/* Make sure this mapping matches */
if (map->phys_irq != phys_irq)
ret = -EINVAL;
/* Found an existing, valid mapping */
goto out;
}
map = &entry->map;
map->virt_irq = virt_irq;
map->phys_irq = phys_irq;
list_add_tail_rcu(&entry->entry, root);
out:
spin_unlock(&dist->irq_phys_map_lock);
/* If we've found a hit in the existing list, free the useless
* entry */
if (ret || map != &entry->map)
kfree(entry);
return ret;
}
static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
int virt_irq)
{
struct list_head *root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
struct irq_phys_map_entry *entry;
struct irq_phys_map *map;
rcu_read_lock();
list_for_each_entry_rcu(entry, root, entry) {
map = &entry->map;
if (map->virt_irq == virt_irq) {
rcu_read_unlock();
return map;
}
}
rcu_read_unlock();
return NULL;
}
static void vgic_free_phys_irq_map_rcu(struct rcu_head *rcu)
{
struct irq_phys_map_entry *entry;
entry = container_of(rcu, struct irq_phys_map_entry, rcu);
kfree(entry);
}
/**
* kvm_vgic_unmap_phys_irq - Remove a virtual to physical IRQ mapping
* @vcpu: The VCPU pointer
* @virt_irq: The virtual IRQ number to be unmapped
*
* Remove an existing mapping between virtual and physical interrupts.
*/
int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct irq_phys_map_entry *entry;
struct list_head *root;
root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
spin_lock(&dist->irq_phys_map_lock);
list_for_each_entry(entry, root, entry) {
if (entry->map.virt_irq == virt_irq) {
list_del_rcu(&entry->entry);
call_rcu(&entry->rcu, vgic_free_phys_irq_map_rcu);
break;
}
}
spin_unlock(&dist->irq_phys_map_lock);
return 0;
}
static void vgic_destroy_irq_phys_map(struct kvm *kvm, struct list_head *root)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct irq_phys_map_entry *entry;
spin_lock(&dist->irq_phys_map_lock);
list_for_each_entry(entry, root, entry) {
list_del_rcu(&entry->entry);
call_rcu(&entry->rcu, vgic_free_phys_irq_map_rcu);
}
spin_unlock(&dist->irq_phys_map_lock);
}
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
kfree(vgic_cpu->pending_shared);
kfree(vgic_cpu->active_shared);
kfree(vgic_cpu->pend_act_shared);
vgic_destroy_irq_phys_map(vcpu->kvm, &vgic_cpu->irq_phys_map_list);
vgic_cpu->pending_shared = NULL;
vgic_cpu->active_shared = NULL;
vgic_cpu->pend_act_shared = NULL;
}
static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
int sz = nr_longs * sizeof(unsigned long);
vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL);
vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL);
if (!vgic_cpu->pending_shared
|| !vgic_cpu->active_shared
|| !vgic_cpu->pend_act_shared) {
kvm_vgic_vcpu_destroy(vcpu);
return -ENOMEM;
}
return 0;
}
/**
* kvm_vgic_vcpu_early_init - Earliest possible per-vcpu vgic init stage
*
* No memory allocation should be performed here, only static init.
*/
void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
INIT_LIST_HEAD(&vgic_cpu->irq_phys_map_list);
}
/**
* kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
*
* The host's GIC naturally limits the maximum amount of VCPUs a guest
* can use.
*/
int kvm_vgic_get_max_vcpus(void)
{
return vgic->max_gic_vcpus;
}
void kvm_vgic_destroy(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int i;
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_vgic_vcpu_destroy(vcpu);
vgic_free_bitmap(&dist->irq_enabled);
vgic_free_bitmap(&dist->irq_level);
vgic_free_bitmap(&dist->irq_pending);
vgic_free_bitmap(&dist->irq_soft_pend);
vgic_free_bitmap(&dist->irq_queued);
vgic_free_bitmap(&dist->irq_cfg);
vgic_free_bytemap(&dist->irq_priority);
if (dist->irq_spi_target) {
for (i = 0; i < dist->nr_cpus; i++)
vgic_free_bitmap(&dist->irq_spi_target[i]);
}
kfree(dist->irq_sgi_sources);
kfree(dist->irq_spi_cpu);
kfree(dist->irq_spi_mpidr);
kfree(dist->irq_spi_target);
kfree(dist->irq_pending_on_cpu);
kfree(dist->irq_active_on_cpu);
vgic_destroy_irq_phys_map(kvm, &dist->irq_phys_map_list);
dist->irq_sgi_sources = NULL;
dist->irq_spi_cpu = NULL;
dist->irq_spi_target = NULL;
dist->irq_pending_on_cpu = NULL;
dist->irq_active_on_cpu = NULL;
dist->nr_cpus = 0;
}
/*
* Allocate and initialize the various data structures. Must be called
* with kvm->lock held!
*/
int vgic_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int nr_cpus, nr_irqs;
int ret, i, vcpu_id;
if (vgic_initialized(kvm))
return 0;
nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
if (!nr_cpus) /* No vcpus? Can't be good... */
return -ENODEV;
/*
* If nobody configured the number of interrupts, use the
* legacy one.
*/
if (!dist->nr_irqs)
dist->nr_irqs = VGIC_NR_IRQS_LEGACY;
nr_irqs = dist->nr_irqs;
ret = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
ret |= vgic_init_bitmap(&dist->irq_active, nr_cpus, nr_irqs);
ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);
if (ret)
goto out;
dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL);
dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL);
dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus,
GFP_KERNEL);
dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
GFP_KERNEL);
dist->irq_active_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
GFP_KERNEL);
if (!dist->irq_sgi_sources ||
!dist->irq_spi_cpu ||
!dist->irq_spi_target ||
!dist->irq_pending_on_cpu ||
!dist->irq_active_on_cpu) {
ret = -ENOMEM;
goto out;
}
for (i = 0; i < nr_cpus; i++)
ret |= vgic_init_bitmap(&dist->irq_spi_target[i],
nr_cpus, nr_irqs);
if (ret)
goto out;
ret = kvm->arch.vgic.vm_ops.init_model(kvm);
if (ret)
goto out;
kvm_for_each_vcpu(vcpu_id, vcpu, kvm) {
ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
if (ret) {
kvm_err("VGIC: Failed to allocate vcpu memory\n");
break;
}
/*
* Enable and configure all SGIs to be edge-triggere and
* configure all PPIs as level-triggered.
*/
for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
if (i < VGIC_NR_SGIS) {
/* SGIs */
vgic_bitmap_set_irq_val(&dist->irq_enabled,
vcpu->vcpu_id, i, 1);
vgic_bitmap_set_irq_val(&dist->irq_cfg,
vcpu->vcpu_id, i,
VGIC_CFG_EDGE);
} else if (i < VGIC_NR_PRIVATE_IRQS) {
/* PPIs */
vgic_bitmap_set_irq_val(&dist->irq_cfg,
vcpu->vcpu_id, i,
VGIC_CFG_LEVEL);
}
}
vgic_enable(vcpu);
}
out:
if (ret)
kvm_vgic_destroy(kvm);
return ret;
}
static int init_vgic_model(struct kvm *kvm, int type)
{
switch (type) {
case KVM_DEV_TYPE_ARM_VGIC_V2:
vgic_v2_init_emulation(kvm);
break;
#ifdef CONFIG_KVM_ARM_VGIC_V3
case KVM_DEV_TYPE_ARM_VGIC_V3:
vgic_v3_init_emulation(kvm);
break;
#endif
default:
return -ENODEV;
}
if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus)
return -E2BIG;
return 0;
}
/**
* kvm_vgic_early_init - Earliest possible vgic initialization stage
*
* No memory allocation should be performed here, only static init.
*/
void kvm_vgic_early_init(struct kvm *kvm)
{
spin_lock_init(&kvm->arch.vgic.lock);
spin_lock_init(&kvm->arch.vgic.irq_phys_map_lock);
INIT_LIST_HEAD(&kvm->arch.vgic.irq_phys_map_list);
}
int kvm_vgic_create(struct kvm *kvm, u32 type)
{
int i, vcpu_lock_idx = -1, ret;
struct kvm_vcpu *vcpu;
mutex_lock(&kvm->lock);
if (irqchip_in_kernel(kvm)) {
ret = -EEXIST;
goto out;
}
/*
* This function is also called by the KVM_CREATE_IRQCHIP handler,
* which had no chance yet to check the availability of the GICv2
* emulation. So check this here again. KVM_CREATE_DEVICE does
* the proper checks already.
*/
if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2) {
ret = -ENODEV;
goto out;
}
/*
* Any time a vcpu is run, vcpu_load is called which tries to grab the
* vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure
* that no other VCPUs are run while we create the vgic.
*/
ret = -EBUSY;
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!mutex_trylock(&vcpu->mutex))
goto out_unlock;
vcpu_lock_idx = i;
}
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->arch.has_run_once)
goto out_unlock;
}
ret = 0;
ret = init_vgic_model(kvm, type);
if (ret)
goto out_unlock;
kvm->arch.vgic.in_kernel = true;
kvm->arch.vgic.vgic_model = type;
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;
kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF;
out_unlock:
for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
mutex_unlock(&vcpu->mutex);
}
out:
mutex_unlock(&kvm->lock);
return ret;
}
static int vgic_ioaddr_overlap(struct kvm *kvm)
{
phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;
if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu))
return 0;
if ((dist <= cpu && dist + KVM_VGIC_V2_DIST_SIZE > cpu) ||
(cpu <= dist && cpu + KVM_VGIC_V2_CPU_SIZE > dist))
return -EBUSY;
return 0;
}
static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
phys_addr_t addr, phys_addr_t size)
{
int ret;
if (addr & ~KVM_PHYS_MASK)
return -E2BIG;
if (addr & (SZ_4K - 1))
return -EINVAL;
if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
return -EEXIST;
if (addr + size < addr)
return -EINVAL;
*ioaddr = addr;
ret = vgic_ioaddr_overlap(kvm);
if (ret)
*ioaddr = VGIC_ADDR_UNDEF;
return ret;
}
/**
* kvm_vgic_addr - set or get vgic VM base addresses
* @kvm: pointer to the vm struct
* @type: the VGIC addr type, one of KVM_VGIC_V[23]_ADDR_TYPE_XXX
* @addr: pointer to address value
* @write: if true set the address in the VM address space, if false read the
* address
*
* Set or get the vgic base addresses for the distributor and the virtual CPU
* interface in the VM physical address space. These addresses are properties
* of the emulated core/SoC and therefore user space initially knows this
* information.
*/
int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
{
int r = 0;
struct vgic_dist *vgic = &kvm->arch.vgic;
int type_needed;
phys_addr_t *addr_ptr, block_size;
phys_addr_t alignment;
mutex_lock(&kvm->lock);
switch (type) {
case KVM_VGIC_V2_ADDR_TYPE_DIST:
type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
addr_ptr = &vgic->vgic_dist_base;
block_size = KVM_VGIC_V2_DIST_SIZE;
alignment = SZ_4K;
break;
case KVM_VGIC_V2_ADDR_TYPE_CPU:
type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
addr_ptr = &vgic->vgic_cpu_base;
block_size = KVM_VGIC_V2_CPU_SIZE;
alignment = SZ_4K;
break;
#ifdef CONFIG_KVM_ARM_VGIC_V3
case KVM_VGIC_V3_ADDR_TYPE_DIST:
type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
addr_ptr = &vgic->vgic_dist_base;
block_size = KVM_VGIC_V3_DIST_SIZE;
alignment = SZ_64K;
break;
case KVM_VGIC_V3_ADDR_TYPE_REDIST:
type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
addr_ptr = &vgic->vgic_redist_base;
block_size = KVM_VGIC_V3_REDIST_SIZE;
alignment = SZ_64K;
break;
#endif
default:
r = -ENODEV;
goto out;
}
if (vgic->vgic_model != type_needed) {
r = -ENODEV;
goto out;
}
if (write) {
if (!IS_ALIGNED(*addr, alignment))
r = -EINVAL;
else
r = vgic_ioaddr_assign(kvm, addr_ptr, *addr,
block_size);
} else {
*addr = *addr_ptr;
}
out:
mutex_unlock(&kvm->lock);
return r;
}
int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
int r;
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_ADDR: {
u64 __user *uaddr = (u64 __user *)(long)attr->addr;
u64 addr;
unsigned long type = (unsigned long)attr->attr;
if (copy_from_user(&addr, uaddr, sizeof(addr)))
return -EFAULT;
r = kvm_vgic_addr(dev->kvm, type, &addr, true);
return (r == -ENODEV) ? -ENXIO : r;
}
case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
u32 __user *uaddr = (u32 __user *)(long)attr->addr;
u32 val;
int ret = 0;
if (get_user(val, uaddr))
return -EFAULT;
/*
* We require:
* - at least 32 SPIs on top of the 16 SGIs and 16 PPIs
* - at most 1024 interrupts
* - a multiple of 32 interrupts
*/
if (val < (VGIC_NR_PRIVATE_IRQS + 32) ||
val > VGIC_MAX_IRQS ||
(val & 31))
return -EINVAL;
mutex_lock(&dev->kvm->lock);
if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
ret = -EBUSY;
else
dev->kvm->arch.vgic.nr_irqs = val;
mutex_unlock(&dev->kvm->lock);
return ret;
}
case KVM_DEV_ARM_VGIC_GRP_CTRL: {
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
r = vgic_init(dev->kvm);
return r;
}
break;
}
}
return -ENXIO;
}
int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
int r = -ENXIO;
switch (attr->group) {
case KVM_DEV_ARM_VGIC_GRP_ADDR: {
u64 __user *uaddr = (u64 __user *)(long)attr->addr;
u64 addr;
unsigned long type = (unsigned long)attr->attr;
r = kvm_vgic_addr(dev->kvm, type, &addr, false);
if (r)
return (r == -ENODEV) ? -ENXIO : r;
if (copy_to_user(uaddr, &addr, sizeof(addr)))
return -EFAULT;
break;
}
case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
u32 __user *uaddr = (u32 __user *)(long)attr->addr;
r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
break;
}
}
return r;
}
int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset)
{
if (vgic_find_range(ranges, 4, offset))
return 0;
else
return -ENXIO;
}
static void vgic_init_maintenance_interrupt(void *info)
{
enable_percpu_irq(vgic->maint_irq, 0);
}
static int vgic_cpu_notify(struct notifier_block *self,
unsigned long action, void *cpu)
{
switch (action) {
case CPU_STARTING:
case CPU_STARTING_FROZEN:
vgic_init_maintenance_interrupt(NULL);
break;
case CPU_DYING:
case CPU_DYING_FROZEN:
disable_percpu_irq(vgic->maint_irq);
break;
}
return NOTIFY_OK;
}
static struct notifier_block vgic_cpu_nb = {
.notifier_call = vgic_cpu_notify,
};
static int kvm_vgic_probe(void)
{
const struct gic_kvm_info *gic_kvm_info;
int ret;
gic_kvm_info = gic_get_kvm_info();
if (!gic_kvm_info)
return -ENODEV;
switch (gic_kvm_info->type) {
case GIC_V2:
ret = vgic_v2_probe(gic_kvm_info, &vgic_ops, &vgic);
break;
case GIC_V3:
ret = vgic_v3_probe(gic_kvm_info, &vgic_ops, &vgic);
break;
default:
ret = -ENODEV;
}
return ret;
}
int kvm_vgic_hyp_init(void)
{
int ret;
ret = kvm_vgic_probe();
if (ret) {
kvm_err("error: KVM vGIC probing failed\n");
return ret;
}
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);
return ret;
}
ret = __register_cpu_notifier(&vgic_cpu_nb);
if (ret) {
kvm_err("Cannot register vgic CPU notifier\n");
goto out_free_irq;
}
on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
return 0;
out_free_irq:
free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
return ret;
}
int kvm_irq_map_gsi(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *entries,
int gsi)
{
return 0;
}
int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
return pin;
}
int kvm_set_irq(struct kvm *kvm, int irq_source_id,
u32 irq, int level, bool line_status)
{
unsigned int spi = irq + VGIC_NR_PRIVATE_IRQS;
trace_kvm_set_irq(irq, level, irq_source_id);
BUG_ON(!vgic_initialized(kvm));
return kvm_vgic_inject_irq(kvm, 0, spi, level);
}
/* MSI not implemented yet */
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id,
int level, bool line_status)
{
return 0;
}
/*
* Copyright (C) 2012-2014 ARM Ltd.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Derived from virt/kvm/arm/vgic.c
*
* 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/>.
*/
#ifndef __KVM_VGIC_H__
#define __KVM_VGIC_H__
#include <kvm/iodev.h>
#define VGIC_ADDR_UNDEF (-1)
#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF)
#define PRODUCT_ID_KVM 0x4b /* ASCII code K */
#define IMPLEMENTER_ARM 0x43b
#define ACCESS_READ_VALUE (1 << 0)
#define ACCESS_READ_RAZ (0 << 0)
#define ACCESS_READ_MASK(x) ((x) & (1 << 0))
#define ACCESS_WRITE_IGNORED (0 << 1)
#define ACCESS_WRITE_SETBIT (1 << 1)
#define ACCESS_WRITE_CLEARBIT (2 << 1)
#define ACCESS_WRITE_VALUE (3 << 1)
#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1))
#define VCPU_NOT_ALLOCATED ((u8)-1)
unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x);
void vgic_update_state(struct kvm *kvm);
int vgic_init_common_maps(struct kvm *kvm);
u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, int cpuid, u32 offset);
u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset);
void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq);
void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq);
void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq);
void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
int irq, int val);
void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq);
void vgic_unqueue_irqs(struct kvm_vcpu *vcpu);
struct kvm_exit_mmio {
phys_addr_t phys_addr;
void *data;
u32 len;
bool is_write;
void *private;
};
void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
phys_addr_t offset, int mode);
bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
phys_addr_t offset);
static inline
u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
{
return le32_to_cpu(*((u32 *)mmio->data)) & mask;
}
static inline
void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
{
*((u32 *)mmio->data) = cpu_to_le32(value) & mask;
}
struct vgic_io_range {
phys_addr_t base;
unsigned long len;
int bits_per_irq;
bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
phys_addr_t offset);
};
int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len,
const struct vgic_io_range *ranges,
int redist_id,
struct vgic_io_device *iodev);
static inline bool is_in_range(phys_addr_t addr, unsigned long len,
phys_addr_t baseaddr, unsigned long size)
{
return (addr >= baseaddr) && (addr + len <= baseaddr + size);
}
const
struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges,
int len, gpa_t offset);
bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id, int access);
bool vgic_handle_set_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id);
bool vgic_handle_clear_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id);
bool vgic_handle_set_active_reg(struct kvm *kvm,
struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id);
bool vgic_handle_clear_active_reg(struct kvm *kvm,
struct kvm_exit_mmio *mmio,
phys_addr_t offset, int vcpu_id);
bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
phys_addr_t offset);
void vgic_kick_vcpus(struct kvm *kvm);
int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset);
int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr);
int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr);
int vgic_init(struct kvm *kvm);
void vgic_v2_init_emulation(struct kvm *kvm);
void vgic_v3_init_emulation(struct kvm *kvm);
#endif
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment