diff options
-rw-r--r-- | Documentation/virtual/kvm/api.txt | 78 | ||||
-rw-r--r-- | Documentation/virtual/kvm/devices/mpic.txt | 37 | ||||
-rw-r--r-- | arch/powerpc/include/asm/kvm_host.h | 24 | ||||
-rw-r--r-- | arch/powerpc/include/asm/kvm_ppc.h | 9 | ||||
-rw-r--r-- | arch/powerpc/include/uapi/asm/kvm.h | 9 | ||||
-rw-r--r-- | arch/powerpc/kvm/Kconfig | 12 | ||||
-rw-r--r-- | arch/powerpc/kvm/Makefile | 3 | ||||
-rw-r--r-- | arch/powerpc/kvm/booke.c | 14 | ||||
-rw-r--r-- | arch/powerpc/kvm/irq.h | 17 | ||||
-rw-r--r-- | arch/powerpc/kvm/mpic.c | 1863 | ||||
-rw-r--r-- | arch/powerpc/kvm/powerpc.c | 55 | ||||
-rw-r--r-- | arch/x86/include/asm/kvm_host.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/Kconfig | 1 | ||||
-rw-r--r-- | arch/x86/kvm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 1 | ||||
-rw-r--r-- | include/linux/kvm_host.h | 53 | ||||
-rw-r--r-- | include/trace/events/kvm.h | 12 | ||||
-rw-r--r-- | include/uapi/linux/kvm.h | 33 | ||||
-rw-r--r-- | virt/kvm/Kconfig | 3 | ||||
-rw-r--r-- | virt/kvm/assigned-dev.c | 30 | ||||
-rw-r--r-- | virt/kvm/eventfd.c | 6 | ||||
-rw-r--r-- | virt/kvm/irq_comm.c | 171 | ||||
-rw-r--r-- | virt/kvm/irqchip.c | 211 | ||||
-rw-r--r-- | virt/kvm/kvm_main.c | 170 |
24 files changed, 227 insertions, 2589 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index da6b44a..f94e300 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2147,76 +2147,6 @@ header; first `n_valid' valid entries with contents from the data written, then `n_invalid' invalid entries, invalidating any previously valid entries found. -4.79 KVM_CREATE_DEVICE - -Capability: KVM_CAP_DEVICE_CTRL -Type: vm ioctl -Parameters: struct kvm_create_device (in/out) -Returns: 0 on success, -1 on error -Errors: - ENODEV: The device type is unknown or unsupported - EEXIST: Device already created, and this type of device may not - be instantiated multiple times - - Other error conditions may be defined by individual device types or - have their standard meanings. - -Creates an emulated device in the kernel. The file descriptor returned -in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR. - -If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the -device type is supported (not necessarily whether it can be created -in the current vm). - -Individual devices should not define flags. Attributes should be used -for specifying any behavior that is not implied by the device type -number. - -struct kvm_create_device { - __u32 type; /* in: KVM_DEV_TYPE_xxx */ - __u32 fd; /* out: device handle */ - __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ -}; - -4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR - -Capability: KVM_CAP_DEVICE_CTRL -Type: device ioctl -Parameters: struct kvm_device_attr -Returns: 0 on success, -1 on error -Errors: - ENXIO: The group or attribute is unknown/unsupported for this device - EPERM: The attribute cannot (currently) be accessed this way - (e.g. read-only attribute, or attribute that only makes - sense when the device is in a different state) - - Other error conditions may be defined by individual device types. - -Gets/sets a specified piece of device configuration and/or state. The -semantics are device-specific. See individual device documentation in -the "devices" directory. As with ONE_REG, the size of the data -transferred is defined by the particular attribute. - -struct kvm_device_attr { - __u32 flags; /* no flags currently defined */ - __u32 group; /* device-defined */ - __u64 attr; /* group-defined */ - __u64 addr; /* userspace address of attr data */ -}; - -4.81 KVM_HAS_DEVICE_ATTR - -Capability: KVM_CAP_DEVICE_CTRL -Type: device ioctl -Parameters: struct kvm_device_attr -Returns: 0 on success, -1 on error -Errors: - ENXIO: The group or attribute is unknown/unsupported for this device - -Tests whether a device supports a particular attribute. A successful -return indicates the attribute is implemented. It does not necessarily -indicate that the attribute can be read or written in the device's -current state. "addr" is ignored. 5. The kvm_run structure ------------------------ @@ -2590,11 +2520,3 @@ to receive the topmost interrupt vector. When disabled (args[0] == 0), behavior is as if this facility is unsupported. When this capability is enabled, KVM_EXIT_EPR can occur. - -6.6 KVM_CAP_IRQ_MPIC - -Architectures: ppc -Parameters: args[0] is the MPIC device fd - args[1] is the MPIC CPU number for this vcpu - -This capability connects the vcpu to an in-kernel MPIC device. diff --git a/Documentation/virtual/kvm/devices/mpic.txt b/Documentation/virtual/kvm/devices/mpic.txt deleted file mode 100644 index ce98e32..0000000 --- a/Documentation/virtual/kvm/devices/mpic.txt +++ /dev/null @@ -1,37 +0,0 @@ -MPIC interrupt controller -========================= - -Device types supported: - KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0 - KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2 - -Only one MPIC instance, of any type, may be instantiated. The created -MPIC will act as the system interrupt controller, connecting to each -vcpu's interrupt inputs. - -Groups: - KVM_DEV_MPIC_GRP_MISC - Attributes: - KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit) - Base address of the 256 KiB MPIC register space. Must be - naturally aligned. A value of zero disables the mapping. - Reset value is zero. - - KVM_DEV_MPIC_GRP_REGISTER (rw, 32-bit) - Access an MPIC register, as if the access were made from the guest. - "attr" is the byte offset into the MPIC register space. Accesses - must be 4-byte aligned. - - MSIs may be signaled by using this attribute group to write - to the relevant MSIIR. - - KVM_DEV_MPIC_GRP_IRQ_ACTIVE (rw, 32-bit) - IRQ input line for each standard openpic source. 0 is inactive and 1 - is active, regardless of interrupt sense. - - For edge-triggered interrupts: Writing 1 is considered an activating - edge, and writing 0 is ignored. Reading returns 1 if a previously - signaled edge has not been acknowledged, and 0 otherwise. - - "attr" is the IRQ number. IRQ numbers for standard sources are the - byte offset of the relevant IVPR from EIVPR0, divided by 32. diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 43ac154..19c8ac4 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -46,10 +46,6 @@ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 #endif -/* These values are internal and can be increased later */ -#define KVM_NR_IRQCHIPS 1 -#define KVM_IRQCHIP_NUM_PINS 256 - #if !defined(CONFIG_KVM_440) #include <linux/mmu_notifier.h> @@ -267,9 +263,6 @@ struct kvm_arch { #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; #endif -#ifdef CONFIG_KVM_MPIC - void *mpic; -#endif }; /* @@ -373,11 +366,6 @@ struct kvmppc_slb { #define KVMPPC_BOOKE_MAX_IAC 4 #define KVMPPC_BOOKE_MAX_DAC 2 -/* KVMPPC_EPR_USER takes precedence over KVMPPC_EPR_KERNEL */ -#define KVMPPC_EPR_NONE 0 /* EPR not supported */ -#define KVMPPC_EPR_USER 1 /* exit to userspace to fill EPR */ -#define KVMPPC_EPR_KERNEL 2 /* in-kernel irqchip */ - struct kvmppc_booke_debug_reg { u32 dbcr0; u32 dbcr1; @@ -389,11 +377,6 @@ struct kvmppc_booke_debug_reg { u64 dac[KVMPPC_BOOKE_MAX_DAC]; }; -#define KVMPPC_IRQ_DEFAULT 0 -#define KVMPPC_IRQ_MPIC 1 - -struct openpic; - struct kvm_vcpu_arch { ulong host_stack; u32 host_pid; @@ -556,7 +539,7 @@ struct kvm_vcpu_arch { u8 sane; u8 cpu_type; u8 hcall_needed; - u8 epr_flags; /* KVMPPC_EPR_xxx */ + u8 epr_enabled; u8 epr_needed; u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ @@ -583,10 +566,6 @@ struct kvm_vcpu_arch { unsigned long magic_page_pa; /* phys addr to map the magic page to */ unsigned long magic_page_ea; /* effect. addr to map the magic page to */ - int irq_type; /* one of KVM_IRQ_* */ - int irq_cpu_id; - struct openpic *mpic; /* KVM_IRQ_MPIC */ - #ifdef CONFIG_KVM_BOOK3S_64_HV struct kvm_vcpu_arch_shared shregs; @@ -627,6 +606,5 @@ struct kvm_vcpu_arch { #define KVM_MMIO_REG_FQPR 0x0060 #define __KVM_HAVE_ARCH_WQP -#define __KVM_HAVE_CREATE_DEVICE #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index f86b5a6..b20f580 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -164,8 +164,6 @@ extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *); -int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); - /* * Cuts out inst bits with ordering according to spec. * That means the leftmost bit is zero. All given bits are included. @@ -247,8 +245,6 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *); void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid); -struct openpic; - #ifdef CONFIG_KVM_BOOK3S_64_HV static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) { @@ -274,11 +270,6 @@ static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr) #endif } -void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu); -int kvmppc_mpic_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, - u32 cpu); -void kvmppc_mpic_disconnect_vcpu(struct openpic *opp, struct kvm_vcpu *vcpu); - int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, struct kvm_config_tlb *cfg); int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu, diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 449bad8..5aefeb9 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -25,8 +25,6 @@ /* Select powerpc specific features in <linux/kvm.h> */ #define __KVM_HAVE_SPAPR_TCE #define __KVM_HAVE_PPC_SMT -#define __KVM_HAVE_IRQCHIP -#define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_GUEST_DEBUG struct kvm_regs { @@ -487,11 +485,4 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TLB3PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a) #define KVM_REG_PPC_EPTCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b) -/* Device control API: PPC-specific devices */ -#define KVM_DEV_MPIC_GRP_MISC 1 -#define KVM_DEV_MPIC_BASE_ADDR 0 /* 64-bit */ - -#define KVM_DEV_MPIC_GRP_REGISTER 2 /* 32-bit */ -#define KVM_DEV_MPIC_GRP_IRQ_ACTIVE 3 /* 32-bit */ - #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 656e0bc..4489520 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -151,18 +151,6 @@ config KVM_E500MC If unsure, say N. -config KVM_MPIC - bool "KVM in-kernel MPIC emulation" - depends on KVM && E500 - select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQ_ROUTING - select HAVE_KVM_MSI - help - Enable support for emulating MPIC devices inside the - host kernel, rather than relying on userspace to emulate. - Currently, support is limited to certain versions of - Freescale's MPIC implementation. - source drivers/vhost/Kconfig endif # VIRTUALIZATION diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 4eada0c..b772ede 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -103,9 +103,6 @@ kvm-book3s_32-objs := \ book3s_32_mmu.o kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs) -kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o -kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(addprefix ../../../virt/kvm/, irqchip.o) - kvm-objs := $(kvm-objs-m) $(kvm-objs-y) obj-$(CONFIG_KVM_440) += kvm.o diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 9731ad6..5d9383f 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -370,7 +370,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, keep_irq = true; } - if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_flags) + if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_enabled) update_epr = true; switch (priority) { @@ -451,16 +451,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, set_guest_esr(vcpu, vcpu->arch.queued_esr); if (update_dear == true) set_guest_dear(vcpu, vcpu->arch.queued_dear); - if (update_epr == true) { - if (vcpu->arch.epr_flags & KVMPPC_EPR_USER) - kvm_make_request(KVM_REQ_EPR_EXIT, vcpu); -#ifdef CONFIG_KVM_MPIC - else if (vcpu->arch.epr_flags & KVMPPC_EPR_KERNEL) { - BUG_ON(vcpu->arch.irq_type != KVMPPC_IRQ_MPIC); - kvmppc_mpic_set_epr(vcpu); - } -#endif - } + if (update_epr == true) + kvm_make_request(KVM_REQ_EPR_EXIT, vcpu); new_msr &= msr_mask; #if defined(CONFIG_64BIT) diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h deleted file mode 100644 index f1e27fd..0000000 --- a/arch/powerpc/kvm/irq.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef __IRQ_H -#define __IRQ_H - -#include <linux/kvm_host.h> - -static inline int irqchip_in_kernel(struct kvm *kvm) -{ - int ret = 0; - -#ifdef CONFIG_KVM_MPIC - ret = ret || (kvm->arch.mpic != NULL); -#endif - smp_rmb(); - return ret; -} - -#endif diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c deleted file mode 100644 index 475a98b..0000000 --- a/arch/powerpc/kvm/mpic.c +++ /dev/null @@ -1,1863 +0,0 @@ -/* - * OpenPIC emulation - * - * Copyright (c) 2004 Jocelyn Mayer - * 2011 Alexander Graf - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. - */ - -#include <linux/slab.h> -#include <linux/mutex.h> -#include <linux/kvm_host.h> -#include <linux/errno.h> -#include <linux/fs.h> -#include <linux/anon_inodes.h> -#include <asm/uaccess.h> -#include <asm/mpic.h> -#include <asm/kvm_para.h> -#include <asm/kvm_host.h> -#include <asm/kvm_ppc.h> -#include "iodev.h" - -#define MAX_CPU 32 -#define MAX_SRC 256 -#define MAX_TMR 4 -#define MAX_IPI 4 -#define MAX_MSI 8 -#define MAX_IRQ (MAX_SRC + MAX_IPI + MAX_TMR) -#define VID 0x03 /* MPIC version ID */ - -/* OpenPIC capability flags */ -#define OPENPIC_FLAG_IDR_CRIT (1 << 0) -#define OPENPIC_FLAG_ILR (2 << 0) - -/* OpenPIC address map */ -#define OPENPIC_REG_SIZE 0x40000 -#define OPENPIC_GLB_REG_START 0x0 -#define OPENPIC_GLB_REG_SIZE 0x10F0 -#define OPENPIC_TMR_REG_START 0x10F0 -#define OPENPIC_TMR_REG_SIZE 0x220 -#define OPENPIC_MSI_REG_START 0x1600 -#define OPENPIC_MSI_REG_SIZE 0x200 -#define OPENPIC_SUMMARY_REG_START 0x3800 -#define OPENPIC_SUMMARY_REG_SIZE 0x800 -#define OPENPIC_SRC_REG_START 0x10000 -#define OPENPIC_SRC_REG_SIZE (MAX_SRC * 0x20) -#define OPENPIC_CPU_REG_START 0x20000 -#define OPENPIC_CPU_REG_SIZE (0x100 + ((MAX_CPU - 1) * 0x1000)) - -struct fsl_mpic_info { - int max_ext; -}; - -static struct fsl_mpic_info fsl_mpic_20 = { - .max_ext = 12, -}; - -static struct fsl_mpic_info fsl_mpic_42 = { - .max_ext = 12, -}; - -#define FRR_NIRQ_SHIFT 16 -#define FRR_NCPU_SHIFT 8 -#define FRR_VID_SHIFT 0 - -#define VID_REVISION_1_2 2 -#define VID_REVISION_1_3 3 - -#define VIR_GENERIC 0x00000000 /* Generic Vendor ID */ - -#define GCR_RESET 0x80000000 -#define GCR_MODE_PASS 0x00000000 -#define GCR_MODE_MIXED 0x20000000 -#define GCR_MODE_PROXY 0x60000000 - -#define TBCR_CI 0x80000000 /* count inhibit */ -#define TCCR_TOG 0x80000000 /* toggles when decrement to zero */ - -#define IDR_EP_SHIFT 31 -#define IDR_EP_MASK (1 << IDR_EP_SHIFT) -#define IDR_CI0_SHIFT 30 -#define IDR_CI1_SHIFT 29 -#define IDR_P1_SHIFT 1 -#define IDR_P0_SHIFT 0 - -#define ILR_INTTGT_MASK 0x000000ff -#define ILR_INTTGT_INT 0x00 -#define ILR_INTTGT_CINT 0x01 /* critical */ -#define ILR_INTTGT_MCP 0x02 /* machine check */ -#define NUM_OUTPUTS 3 - -#define MSIIR_OFFSET 0x140 -#define MSIIR_SRS_SHIFT 29 -#define MSIIR_SRS_MASK (0x7 << MSIIR_SRS_SHIFT) -#define MSIIR_IBS_SHIFT 24 -#define MSIIR_IBS_MASK (0x1f << MSIIR_IBS_SHIFT) - -static int get_current_cpu(void) -{ - struct kvm_vcpu *vcpu = current->thread.kvm_vcpu; - return vcpu ? vcpu->arch.irq_cpu_id : -1; -} - -static int openpic_cpu_write_internal(void *opaque, gpa_t addr, - u32 val, int idx); -static int openpic_cpu_read_internal(void *opaque, gpa_t addr, - u32 *ptr, int idx); - -enum irq_type { - IRQ_TYPE_NORMAL = 0, - IRQ_TYPE_FSLINT, /* FSL internal interrupt -- level only */ - IRQ_TYPE_FSLSPECIAL, /* FSL timer/IPI interrupt, edge, no polarity */ -}; - -struct irq_queue { - /* Round up to the nearest 64 IRQs so that the queue length - * won't change when moving between 32 and 64 bit hosts. - */ - unsigned long queue[BITS_TO_LONGS((MAX_IRQ + 63) & ~63)]; - int next; - int priority; -}; - -struct irq_source { - uint32_t ivpr; /* IRQ vector/priority register */ - uint32_t idr; /* IRQ destination register */ - uint32_t destmask; /* bitmap of CPU destinations */ - int last_cpu; - int output; /* IRQ level, e.g. ILR_INTTGT_INT */ - int pending; /* TRUE if IRQ is pending */ - enum irq_type type; - bool level:1; /* level-triggered */ - bool nomask:1; /* critical interrupts ignore mask on some FSL MPICs */ -}; - -#define IVPR_MASK_SHIFT 31 -#define IVPR_MASK_MASK (1 << IVPR_MASK_SHIFT) -#define IVPR_ACTIVITY_SHIFT 30 -#define IVPR_ACTIVITY_MASK (1 << IVPR_ACTIVITY_SHIFT) -#define IVPR_MODE_SHIFT 29 -#define IVPR_MODE_MASK (1 << IVPR_MODE_SHIFT) -#define IVPR_POLARITY_SHIFT 23 -#define IVPR_POLARITY_MASK (1 << IVPR_POLARITY_SHIFT) -#define IVPR_SENSE_SHIFT 22 -#define IVPR_SENSE_MASK (1 << IVPR_SENSE_SHIFT) - -#define IVPR_PRIORITY_MASK (0xF << 16) -#define IVPR_PRIORITY(_ivprr_) ((int)(((_ivprr_) & IVPR_PRIORITY_MASK) >> 16)) -#define IVPR_VECTOR(opp, _ivprr_) ((_ivprr_) & (opp)->vector_mask) - -/* IDR[EP/CI] are only for FSL MPIC prior to v4.0 */ -#define IDR_EP 0x80000000 /* external pin */ -#define IDR_CI 0x40000000 /* critical interrupt */ - -struct irq_dest { - struct kvm_vcpu *vcpu; - - int32_t ctpr; /* CPU current task priority */ - struct irq_queue raised; - struct irq_queue servicing; - - /* Count of IRQ sources asserting on non-INT outputs */ - uint32_t outputs_active[NUM_OUTPUTS]; -}; - -struct openpic { - struct kvm *kvm; - struct kvm_device *dev; - struct kvm_io_device mmio; - struct list_head mmio_regions; - atomic_t users; - bool mmio_mapped; - - gpa_t reg_base; - spinlock_t lock; - - /* Behavior control */ - struct fsl_mpic_info *fsl; - uint32_t model; - uint32_t flags; - uint32_t nb_irqs; - uint32_t vid; - uint32_t vir; /* Vendor identification register */ - uint32_t vector_mask; - uint32_t tfrr_reset; - uint32_t ivpr_reset; - uint32_t idr_reset; - uint32_t brr1; - uint32_t mpic_mode_mask; - - /* Global registers */ - uint32_t frr; /* Feature reporting register */ - uint32_t gcr; /* Global configuration register */ - uint32_t pir; /* Processor initialization register */ - uint32_t spve; /* Spurious vector register */ - uint32_t tfrr; /* Timer frequency reporting register */ - /* Source registers */ - struct irq_source src[MAX_IRQ]; - /* Local registers per output pin */ - struct irq_dest dst[MAX_CPU]; - uint32_t nb_cpus; - /* Timer registers */ - struct { - uint32_t tccr; /* Global timer current count register */ - uint32_t tbcr; /* Global timer base count register */ - } timers[MAX_TMR]; - /* Shared MSI registers */ - struct { - uint32_t msir; /* Shared Message Signaled Interrupt Register */ - } msi[MAX_MSI]; - uint32_t max_irq; - uint32_t irq_ipi0; - uint32_t irq_tim0; - uint32_t irq_msi; -}; - - -static void mpic_irq_raise(struct openpic *opp, struct irq_dest *dst, - int output) -{ - struct kvm_interrupt irq = { - .irq = KVM_INTERRUPT_SET_LEVEL, - }; - - if (!dst->vcpu) { - pr_debug("%s: destination cpu %td does not exist\n", - __func__, dst - &opp->dst[0]); - return; - } - - pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->arch.irq_cpu_id, - output); - - if (output != ILR_INTTGT_INT) /* TODO */ - return; - - kvm_vcpu_ioctl_interrupt(dst->vcpu, &irq); -} - -static void mpic_irq_lower(struct openpic *opp, struct irq_dest *dst, - int output) -{ - if (!dst->vcpu) { - pr_debug("%s: destination cpu %td does not exist\n", - __func__, dst - &opp->dst[0]); - return; - } - - pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->arch.irq_cpu_id, - output); - - if (output != ILR_INTTGT_INT) /* TODO */ - return; - - kvmppc_core_dequeue_external(dst->vcpu); -} - -static inline void IRQ_setbit(struct irq_queue *q, int n_IRQ) -{ - set_bit(n_IRQ, q->queue); -} - -static inline void IRQ_resetbit(struct irq_queue *q, int n_IRQ) -{ - clear_bit(n_IRQ, q->queue); -} - -static inline int IRQ_testbit(struct irq_queue *q, int n_IRQ) -{ - return test_bit(n_IRQ, q->queue); -} - -static void IRQ_check(struct openpic *opp, struct irq_queue *q) -{ - int irq = -1; - int next = -1; - int priority = -1; - - for (;;) { - irq = find_next_bit(q->queue, opp->max_irq, irq + 1); - if (irq == opp->max_irq) - break; - - pr_debug("IRQ_check: irq %d set ivpr_pr=%d pr=%d\n", - irq, IVPR_PRIORITY(opp->src[irq].ivpr), priority); - - if (IVPR_PRIORITY(opp->src[irq].ivpr) > priority) { - next = irq; - priority = IVPR_PRIORITY(opp->src[irq].ivpr); - } - } - - q->next = next; - q->priority = priority; -} - -static int IRQ_get_next(struct openpic *opp, struct irq_queue *q) -{ - /* XXX: optimize */ - IRQ_check(opp, q); - - return q->next; -} - -static void IRQ_local_pipe(struct openpic *opp, int n_CPU, int n_IRQ, - bool active, bool was_active) -{ - struct irq_dest *dst; - struct irq_source *src; - int priority; - - dst = &opp->dst[n_CPU]; - src = &opp->src[n_IRQ]; - - pr_debug("%s: IRQ %d active %d was %d\n", - __func__, n_IRQ, active, was_active); - - if (src->output != ILR_INTTGT_INT) { - pr_debug("%s: output %d irq %d active %d was %d count %d\n", - __func__, src->output, n_IRQ, active, was_active, - dst->outputs_active[src->output]); - - /* On Freescale MPIC, critical interrupts ignore priority, - * IACK, EOI, etc. Before MPIC v4.1 they also ignore - * masking. - */ - if (active) { - if (!was_active && - dst->outputs_active[src->output]++ == 0) { - pr_debug("%s: Raise OpenPIC output %d cpu %d irq %d\n", - __func__, src->output, n_CPU, n_IRQ); - mpic_irq_raise(opp, dst, src->output); - } - } else { - if (was_active && - --dst->outputs_active[src->output] == 0) { - pr_debug("%s: Lower OpenPIC output %d cpu %d irq %d\n", - __func__, src->output, n_CPU, n_IRQ); - mpic_irq_lower(opp, dst, src->output); - } - } - - return; - } - - priority = IVPR_PRIORITY(src->ivpr); - - /* Even if the interrupt doesn't have enough priority, - * it is still raised, in case ctpr is lowered later. - */ - if (active) - IRQ_setbit(&dst->raised, n_IRQ); - else - IRQ_resetbit(&dst->raised, n_IRQ); - - IRQ_check(opp, &dst->raised); - - if (active && priority <= dst->ctpr) { - pr_debug("%s: IRQ %d priority %d too low for ctpr %d on CPU %d\n", - __func__, n_IRQ, priority, dst->ctpr, n_CPU); - active = 0; - } - - if (active) { - if (IRQ_get_next(opp, &dst->servicing) >= 0 && - priority <= dst->servicing.priority) { - pr_debug("%s: IRQ %d is hidden by servicing IRQ %d on CPU %d\n", - __func__, n_IRQ, dst->servicing.next, n_CPU); - } else { - pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d/%d\n", - __func__, n_CPU, n_IRQ, dst->raised.next); - mpic_irq_raise(opp, dst, ILR_INTTGT_INT); - } - } else { - IRQ_get_next(opp, &dst->servicing); - if (dst->raised.priority > dst->ctpr && - dst->raised.priority > dst->servicing.priority) { - pr_debug("%s: IRQ %d inactive, IRQ %d prio %d above %d/%d, CPU %d\n", - __func__, n_IRQ, dst->raised.next, - dst->raised.priority, dst->ctpr, - dst->servicing.priority, n_CPU); - /* IRQ line stays asserted */ - } else { - pr_debug("%s: IRQ %d inactive, current prio %d/%d, CPU %d\n", - __func__, n_IRQ, dst->ctpr, - dst->servicing.priority, n_CPU); - mpic_irq_lower(opp, dst, ILR_INTTGT_INT); - } - } -} - -/* update pic state because registers for n_IRQ have changed value */ -static void openpic_update_irq(struct openpic *opp, int n_IRQ) -{ - struct irq_source *src; - bool active, was_active; - int i; - - src = &opp->src[n_IRQ]; - active = src->pending; - - if ((src->ivpr & IVPR_MASK_MASK) && !src->nomask) { - /* Interrupt source is disabled */ - pr_debug("%s: IRQ %d is disabled\n", __func__, n_IRQ); - active = false; - } - - was_active = !!(src->ivpr & IVPR_ACTIVITY_MASK); - - /* - * We don't have a similar check for already-active because - * ctpr may have changed and we need to withdraw the interrupt. - */ - if (!active && !was_active) { - pr_debug("%s: IRQ %d is already inactive\n", __func__, n_IRQ); - return; - } - - if (active) - src->ivpr |= IVPR_ACTIVITY_MASK; - else - src->ivpr &= ~IVPR_ACTIVITY_MASK; - - if (src->destmask == 0) { - /* No target */ - pr_debug("%s: IRQ %d has no target\n", __func__, n_IRQ); - return; - } - - if (src->destmask == (1 << src->last_cpu)) { - /* Only one CPU is allowed to receive this IRQ */ - IRQ_local_pipe(opp, src->last_cpu, n_IRQ, active, was_active); - } else if (!(src->ivpr & IVPR_MODE_MASK)) { - /* Directed delivery mode */ - for (i = 0; i < opp->nb_cpus; i++) { - if (src->destmask & (1 << i)) { - IRQ_local_pipe(opp, i, n_IRQ, active, - was_active); - } - } - } else { - /* Distributed delivery mode */ - for (i = src->last_cpu + 1; i != src->last_cpu; i++) { - if (i == opp->nb_cpus) - i = 0; - - if (src->destmask & (1 << i)) { - IRQ_local_pipe(opp, i, n_IRQ, active, - was_active); - src->last_cpu = i; - break; - } - } - } -} - -static void openpic_set_irq(void *opaque, int n_IRQ, int level) -{ - struct openpic *opp = opaque; - struct irq_source *src; - - if (n_IRQ >= MAX_IRQ) { - WARN_ONCE(1, "%s: IRQ %d out of range\n", __func__, n_IRQ); - return; - } - - src = &opp->src[n_IRQ]; - pr_debug("openpic: set irq %d = %d ivpr=0x%08x\n", - n_IRQ, level, src->ivpr); - if (src->level) { - /* level-sensitive irq */ - src->pending = level; - openpic_update_irq(opp, n_IRQ); - } else { - /* edge-sensitive irq */ - if (level) { - src->pending = 1; - openpic_update_irq(opp, n_IRQ); - } - - if (src->output != ILR_INTTGT_INT) { - /* Edge-triggered interrupts shouldn't be used - * with non-INT delivery, but just in case, - * try to make it do something sane rather than - * cause an interrupt storm. This is close to - * what you'd probably see happen in real hardware. - */ - src->pending = 0; - openpic_update_irq(opp, n_IRQ); - } - } -} - -static void openpic_reset(struct openpic *opp) -{ - int i; - - opp->gcr = GCR_RESET; - /* Initialise controller registers */ - opp->frr = ((opp->nb_irqs - 1) << FRR_NIRQ_SHIFT) | - (opp->vid << FRR_VID_SHIFT); - - opp->pir = 0; - opp->spve = -1 & opp->vector_mask; - opp->tfrr = opp->tfrr_reset; - /* Initialise IRQ sources */ - for (i = 0; i < opp->max_irq; i++) { - opp->src[i].ivpr = opp->ivpr_reset; - opp->src[i].idr = opp->idr_reset; - - switch (opp->src[i].type) { - case IRQ_TYPE_NORMAL: - opp->src[i].level = - !!(opp->ivpr_reset & IVPR_SENSE_MASK); - break; - - case IRQ_TYPE_FSLINT: - opp->src[i].ivpr |= IVPR_POLARITY_MASK; - break; - - case IRQ_TYPE_FSLSPECIAL: - break; - } - } - /* Initialise IRQ destinations */ - for (i = 0; i < MAX_CPU; i++) { - opp->dst[i].ctpr = 15; - memset(&opp->dst[i].raised, 0, sizeof(struct irq_queue)); - opp->dst[i].raised.next = -1; - memset(&opp->dst[i].servicing, 0, sizeof(struct irq_queue)); - opp->dst[i].servicing.next = -1; - } - /* Initialise timers */ - for (i = 0; i < MAX_TMR; i++) { - opp->timers[i].tccr = 0; - opp->timers[i].tbcr = TBCR_CI; - } - /* Go out of RESET state */ - opp->gcr = 0; -} - -static inline uint32_t read_IRQreg_idr(struct openpic *opp, int n_IRQ) -{ - return opp->src[n_IRQ].idr; -} - -static inline uint32_t read_IRQreg_ilr(struct openpic *opp, int n_IRQ) -{ - if (opp->flags & OPENPIC_FLAG_ILR) - return opp->src[n_IRQ].output; - - return 0xffffffff; -} - -static inline uint32_t read_IRQreg_ivpr(struct openpic *opp, int n_IRQ) -{ - return opp->src[n_IRQ].ivpr; -} - -static inline void write_IRQreg_idr(struct openpic *opp, int n_IRQ, - uint32_t val) -{ - struct irq_source *src = &opp->src[n_IRQ]; - uint32_t normal_mask = (1UL << opp->nb_cpus) - 1; - uint32_t crit_mask = 0; - uint32_t mask = normal_mask; - int crit_shift = IDR_EP_SHIFT - opp->nb_cpus; - int i; - - if (opp->flags & OPENPIC_FLAG_IDR_CRIT) { - crit_mask = mask << crit_shift; - mask |= crit_mask | IDR_EP; - } - - src->idr = val & mask; - pr_debug("Set IDR %d to 0x%08x\n", n_IRQ, src->idr); - - if (opp->flags & OPENPIC_FLAG_IDR_CRIT) { - if (src->idr & crit_mask) { - if (src->idr & normal_mask) { - pr_debug("%s: IRQ configured for multiple output types, using critical\n", - __func__); - } - - src->output = ILR_INTTGT_CINT; - src->nomask = true; - src->destmask = 0; - - for (i = 0; i < opp->nb_cpus; i++) { - int n_ci = IDR_CI0_SHIFT - i; - - if (src->idr & (1UL << n_ci)) - src->destmask |= 1UL << i; - } - } else { - src->output = ILR_INTTGT_INT; - src->nomask = false; - src->destmask = src->idr & normal_mask; - } - } else { - src->destmask = src->idr; - } -} - -static inline void write_IRQreg_ilr(struct openpic *opp, int n_IRQ, - uint32_t val) -{ - if (opp->flags & OPENPIC_FLAG_ILR) { - struct irq_source *src = &opp->src[n_IRQ]; - - src->output = val & ILR_INTTGT_MASK; - pr_debug("Set ILR %d to 0x%08x, output %d\n", n_IRQ, src->idr, - src->output); - - /* TODO: on MPIC v4.0 only, set nomask for non-INT */ - } -} - -static inline void write_IRQreg_ivpr(struct openpic *opp, int n_IRQ, - uint32_t val) -{ - uint32_t mask; - - /* NOTE when implementing newer FSL MPIC models: starting with v4.0, - * the polarity bit is read-only on internal interrupts. - */ - mask = IVPR_MASK_MASK | IVPR_PRIORITY_MASK | IVPR_SENSE_MASK | - IVPR_POLARITY_MASK | opp->vector_mask; - - /* ACTIVITY bit is read-only */ - opp->src[n_IRQ].ivpr = - (opp->src[n_IRQ].ivpr & IVPR_ACTIVITY_MASK) | (val & mask); - - /* For FSL internal interrupts, The sense bit is reserved and zero, - * and the interrupt is always level-triggered. Timers and IPIs - * have no sense or polarity bits, and are edge-triggered. - */ - switch (opp->src[n_IRQ].type) { - case IRQ_TYPE_NORMAL: - opp->src[n_IRQ].level = - !!(opp->src[n_IRQ].ivpr & IVPR_SENSE_MASK); - break; - - case IRQ_TYPE_FSLINT: - opp->src[n_IRQ].ivpr &= ~IVPR_SENSE_MASK; - break; - - case IRQ_TYPE_FSLSPECIAL: - opp->src[n_IRQ].ivpr &= ~(IVPR_POLARITY_MASK | IVPR_SENSE_MASK); - break; - } - - openpic_update_irq(opp, n_IRQ); - pr_debug("Set IVPR %d to 0x%08x -> 0x%08x\n", n_IRQ, val, - opp->src[n_IRQ].ivpr); -} - -static void openpic_gcr_write(struct openpic *opp, uint64_t val) -{ - if (val & GCR_RESET) { - openpic_reset(opp); - return; - } - - opp->gcr &= ~opp->mpic_mode_mask; - opp->gcr |= val & opp->mpic_mode_mask; -} - -static int openpic_gbl_write(void *opaque, gpa_t addr, u32 val) -{ - struct openpic *opp = opaque; - int err = 0; - - pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val); - if (addr & 0xF) - return 0; - - switch (addr) { - case 0x00: /* Block Revision Register1 (BRR1) is Readonly */ - break; - case 0x40: - case 0x50: - case 0x60: - case 0x70: - case 0x80: - case 0x90: - case 0xA0: - case 0xB0: - err = openpic_cpu_write_internal(opp, addr, val, - get_current_cpu()); - break; - case 0x1000: /* FRR */ - break; - case 0x1020: /* GCR */ - openpic_gcr_write(opp, val); - break; - case 0x1080: /* VIR */ - break; - case 0x1090: /* PIR */ - /* - * This register is used to reset a CPU core -- - * let userspace handle it. - */ - err = -ENXIO; - break; - case 0x10A0: /* IPI_IVPR */ - case 0x10B0: - case 0x10C0: - case 0x10D0: { - int idx; - idx = (addr - 0x10A0) >> 4; - write_IRQreg_ivpr(opp, opp->irq_ipi0 + idx, val); - break; - } - case 0x10E0: /* SPVE */ - opp->spve = val & opp->vector_mask; - break; - default: - break; - } - - return err; -} - -static int openpic_gbl_read(void *opaque, gpa_t addr, u32 *ptr) -{ - struct openpic *opp = opaque; - u32 retval; - int err = 0; - - pr_debug("%s: addr %#llx\n", __func__, addr); - retval = 0xFFFFFFFF; - if (addr & 0xF) - goto out; - - switch (addr) { - case 0x1000: /* FRR */ - retval = opp->frr; - retval |= (opp->nb_cpus - 1) << FRR_NCPU_SHIFT; - break; - case 0x1020: /* GCR */ - retval = opp->gcr; - break; - case 0x1080: /* VIR */ - retval = opp->vir; - break; - case 0x1090: /* PIR */ - retval = 0x00000000; - break; - case 0x00: /* Block Revision Register1 (BRR1) */ - retval = opp->brr1; - break; - case 0x40: - case 0x50: - case 0x60: - case 0x70: - case 0x80: - case 0x90: - case 0xA0: - case 0xB0: - err = openpic_cpu_read_internal(opp, addr, - &retval, get_current_cpu()); - break; - case 0x10A0: /* IPI_IVPR */ - case 0x10B0: - case 0x10C0: - case 0x10D0: - { - int idx; - idx = (addr - 0x10A0) >> 4; - retval = read_IRQreg_ivpr(opp, opp->irq_ipi0 + idx); - } - break; - case 0x10E0: /* SPVE */ - retval = opp->spve; - break; - default: - break; - } - -out: - pr_debug("%s: => 0x%08x\n", __func__, retval); - *ptr = retval; - return err; -} - -static int openpic_tmr_write(void *opaque, gpa_t addr, u32 val) -{ - struct openpic *opp = opaque; - int idx; - - addr += 0x10f0; - - pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val); - if (addr & 0xF) - return 0; - - if (addr == 0x10f0) { - /* TFRR */ - opp->tfrr = val; - return 0; - } - - idx = (addr >> 6) & 0x3; - addr = addr & 0x30; - - switch (addr & 0x30) { - case 0x00: /* TCCR */ - break; - case 0x10: /* TBCR */ - if ((opp->timers[idx].tccr & TCCR_TOG) != 0 && - (val & TBCR_CI) == 0 && - (opp->timers[idx].tbcr & TBCR_CI) != 0) - opp->timers[idx].tccr &= ~TCCR_TOG; - - opp->timers[idx].tbcr = val; - break; - case 0x20: /* TVPR */ - write_IRQreg_ivpr(opp, opp->irq_tim0 + idx, val); - break; - case 0x30: /* TDR */ - write_IRQreg_idr(opp, opp->irq_tim0 + idx, val); - break; - } - - return 0; -} - -static int openpic_tmr_read(void *opaque, gpa_t addr, u32 *ptr) -{ - struct openpic *opp = opaque; - uint32_t retval = -1; - int idx; - - pr_debug("%s: addr %#llx\n", __func__, addr); - if (addr & 0xF) - goto out; - - idx = (addr >> 6) & 0x3; - if (addr == 0x0) { - /* TFRR */ - retval = opp->tfrr; - goto out; - } - - switch (addr & 0x30) { - case 0x00: /* TCCR */ - retval = opp->timers[idx].tccr; - break; - case 0x10: /* TBCR */ - retval = opp->timers[idx].tbcr; - break; - case 0x20: /* TIPV */ - retval = read_IRQreg_ivpr(opp, opp->irq_tim0 + idx); - break; - case 0x30: /* TIDE (TIDR) */ - retval = read_IRQreg_idr(opp, opp->irq_tim0 + idx); - break; - } - -out: - pr_debug("%s: => 0x%08x\n", __func__, retval); - *ptr = retval; - return 0; -} - -static int openpic_src_write(void *opaque, gpa_t addr, u32 val) -{ - struct openpic *opp = opaque; - int idx; - - pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val); - - addr = addr & 0xffff; - idx = addr >> 5; - - switch (addr & 0x1f) { - case 0x00: - write_IRQreg_ivpr(opp, idx, val); - break; - case 0x10: - write_IRQreg_idr(opp, idx, val); - break; - case 0x18: - write_IRQreg_ilr(opp, idx, val); - break; - } - - return 0; -} - -static int openpic_src_read(void *opaque, gpa_t addr, u32 *ptr) -{ - struct openpic *opp = opaque; - uint32_t retval; - int idx; - - pr_debug("%s: addr %#llx\n", __func__, addr); - retval = 0xFFFFFFFF; - - addr = addr & 0xffff; - idx = addr >> 5; - - switch (addr & 0x1f) { - case 0x00: - retval = read_IRQreg_ivpr(opp, idx); - break; - case 0x10: - retval = read_IRQreg_idr(opp, idx); - break; - case 0x18: - retval = read_IRQreg_ilr(opp, idx); - break; - } - - pr_debug("%s: => 0x%08x\n", __func__, retval); - *ptr = retval; - return 0; -} - -static int openpic_msi_write(void *opaque, gpa_t addr, u32 val) -{ - struct openpic *opp = opaque; - int idx = opp->irq_msi; - int srs, ibs; - - pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val); - if (addr & 0xF) - return 0; - - switch (addr) { - case MSIIR_OFFSET: - srs = val >> MSIIR_SRS_SHIFT; - idx += srs; - ibs = (val & MSIIR_IBS_MASK) >> MSIIR_IBS_SHIFT; - opp->msi[srs].msir |= 1 << ibs; - openpic_set_irq(opp, idx, 1); - break; - default: - /* most registers are read-only, thus ignored */ - break; - } - - return 0; -} - -static int openpic_msi_read(void *opaque, gpa_t addr, u32 *ptr) -{ - struct openpic *opp = opaque; - uint32_t r = 0; - int i, srs; - - pr_debug("%s: addr %#llx\n", __func__, addr); - if (addr & 0xF) - return -ENXIO; - - srs = addr >> 4; - - switch (addr) { - case 0x00: - case 0x10: - case 0x20: - case 0x30: - case 0x40: - case 0x50: - case 0x60: - case 0x70: /* MSIRs */ - r = opp->msi[srs].msir; - /* Clear on read */ - opp->msi[srs].msir = 0; - openpic_set_irq(opp, opp->irq_msi + srs, 0); - break; - case 0x120: /* MSISR */ - for (i = 0; i < MAX_MSI; i++) - r |= (opp->msi[i].msir ? 1 : 0) << i; - break; - } - - pr_debug("%s: => 0x%08x\n", __func__, r); - *ptr = r; - return 0; -} - -static int openpic_summary_read(void *opaque, gpa_t addr, u32 *ptr) -{ - uint32_t r = 0; - - pr_debug("%s: addr %#llx\n", __func__, addr); - - /* TODO: EISR/EIMR */ - - *ptr = r; - return 0; -} - -static int openpic_summary_write(void *opaque, gpa_t addr, u32 val) -{ - pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val); - - /* TODO: EISR/EIMR */ - return 0; -} - -static int openpic_cpu_write_internal(void *opaque, gpa_t addr, - u32 val, int idx) -{ - struct openpic *opp = opaque; - struct irq_source *src; - struct irq_dest *dst; - int s_IRQ, n_IRQ; - - pr_debug("%s: cpu %d addr %#llx <= 0x%08x\n", __func__, idx, - addr, val); - - if (idx < 0) - return 0; - - if (addr & 0xF) - return 0; - - dst = &opp->dst[idx]; - addr &= 0xFF0; - switch (addr) { - case 0x40: /* IPIDR */ - case 0x50: - case 0x60: - case 0x70: - idx = (addr - 0x40) >> 4; - /* we use IDE as mask which CPUs to deliver the IPI to still. */ - opp->src[opp->irq_ipi0 + idx].destmask |= val; - openpic_set_irq(opp, opp->irq_ipi0 + idx, 1); - openpic_set_irq(opp, opp->irq_ipi0 + idx, 0); - break; - case 0x80: /* CTPR */ - dst->ctpr = val & 0x0000000F; - - pr_debug("%s: set CPU %d ctpr to %d, raised %d servicing %d\n", - __func__, idx, dst->ctpr, dst->raised.priority, - dst->servicing.priority); - - if (dst->raised.priority <= dst->ctpr) { - pr_debug("%s: Lower OpenPIC INT output cpu %d due to ctpr\n", - __func__, idx); - mpic_irq_lower(opp, dst, ILR_INTTGT_INT); - } else if (dst->raised.priority > dst->servicing.priority) { - pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d\n", - __func__, idx, dst->raised.next); - mpic_irq_raise(opp, dst, ILR_INTTGT_INT); - } - - break; - case 0x90: /* WHOAMI */ - /* Read-only register */ - break; - case 0xA0: /* IACK */ - /* Read-only register */ - break; - case 0xB0: /* EOI */ - pr_debug("EOI\n"); - s_IRQ = IRQ_get_next(opp, &dst->servicing); - - if (s_IRQ < 0) { - pr_debug("%s: EOI with no interrupt in service\n", - __func__); - break; - } - - IRQ_resetbit(&dst->servicing, s_IRQ); - /* Notify listeners that the IRQ is over */ - kvm_notify_acked_irq(opp->kvm, 0, s_IRQ); - /* Set up next servicing IRQ */ - s_IRQ = IRQ_get_next(opp, &dst->servicing); - /* Check queued interrupts. */ - n_IRQ = IRQ_get_next(opp, &dst->raised); - src = &opp->src[n_IRQ]; - if (n_IRQ != -1 && - (s_IRQ == -1 || - IVPR_PRIORITY(src->ivpr) > dst->servicing.priority)) { - pr_debug("Raise OpenPIC INT output cpu %d irq %d\n", - idx, n_IRQ); - mpic_irq_raise(opp, dst, ILR_INTTGT_INT); - } - break; - default: - break; - } - - return 0; -} - -static int openpic_cpu_write(void *opaque, gpa_t addr, u32 val) -{ - struct openpic *opp = opaque; - - return openpic_cpu_write_internal(opp, addr, val, - (addr & 0x1f000) >> 12); -} - -static uint32_t openpic_iack(struct openpic *opp, struct irq_dest *dst, - int cpu) -{ - struct irq_source *src; - int retval, irq; - - pr_debug("Lower OpenPIC INT output\n"); - mpic_irq_lower(opp, dst, ILR_INTTGT_INT); - - irq = IRQ_get_next(opp, &dst->raised); - pr_debug("IACK: irq=%d\n", irq); - - if (irq == -1) - /* No more interrupt pending */ - return opp->spve; - - src = &opp->src[irq]; - if (!(src->ivpr & IVPR_ACTIVITY_MASK) || - !(IVPR_PRIORITY(src->ivpr) > dst->ctpr)) { - pr_err("%s: bad raised IRQ %d ctpr %d ivpr 0x%08x\n", - __func__, irq, dst->ctpr, src->ivpr); - openpic_update_irq(opp, irq); - retval = opp->spve; - } else { - /* IRQ enter servicing state */ - IRQ_setbit(&dst->servicing, irq); - retval = IVPR_VECTOR(opp, src->ivpr); - } - - if (!src->level) { - /* edge-sensitive IRQ */ - src->ivpr &= ~IVPR_ACTIVITY_MASK; - src->pending = 0; - IRQ_resetbit(&dst->raised, irq); - } - - if ((irq >= opp->irq_ipi0) && (irq < (opp->irq_ipi0 + MAX_IPI))) { - src->destmask &= ~(1 << cpu); - if (src->destmask && !src->level) { - /* trigger on CPUs that didn't know about it yet */ - openpic_set_irq(opp, irq, 1); - openpic_set_irq(opp, irq, 0); - /* if all CPUs knew about it, set active bit again */ - src->ivpr |= IVPR_ACTIVITY_MASK; - } - } - - return retval; -} - -void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu) -{ - struct openpic *opp = vcpu->arch.mpic; - int cpu = vcpu->arch.irq_cpu_id; - unsigned long flags; - - spin_lock_irqsave(&opp->lock, flags); - - if ((opp->gcr & opp->mpic_mode_mask) == GCR_MODE_PROXY) - kvmppc_set_epr(vcpu, openpic_iack(opp, &opp->dst[cpu], cpu)); - - spin_unlock_irqrestore(&opp->lock, flags); -} - -static int openpic_cpu_read_internal(void *opaque, gpa_t addr, - u32 *ptr, int idx) -{ - struct openpic *opp = opaque; - struct irq_dest *dst; - uint32_t retval; - - pr_debug("%s: cpu %d addr %#llx\n", __func__, idx, addr); - retval = 0xFFFFFFFF; - - if (idx < 0) - goto out; - - if (addr & 0xF) - goto out; - - dst = &opp->dst[idx]; - addr &= 0xFF0; - switch (addr) { - case 0x80: /* CTPR */ - retval = dst->ctpr; - break; - case 0x90: /* WHOAMI */ - retval = idx; - break; - case 0xA0: /* IACK */ - retval = openpic_iack(opp, dst, idx); - break; - case 0xB0: /* EOI */ - retval = 0; - break; - default: - break; - } - pr_debug("%s: => 0x%08x\n", __func__, retval); - -out: - *ptr = retval; - return 0; -} - -static int openpic_cpu_read(void *opaque, gpa_t addr, u32 *ptr) -{ - struct openpic *opp = opaque; - - return openpic_cpu_read_internal(opp, addr, ptr, - (addr & 0x1f000) >> 12); -} - -struct mem_reg { - struct list_head list; - int (*read)(void *opaque, gpa_t addr, u32 *ptr); - int (*write)(void *opaque, gpa_t addr, u32 val); - gpa_t start_addr; - int size; -}; - -static struct mem_reg openpic_gbl_mmio = { - .write = openpic_gbl_write, - .read = openpic_gbl_read, - .start_addr = OPENPIC_GLB_REG_START, - .size = OPENPIC_GLB_REG_SIZE, -}; - -static struct mem_reg openpic_tmr_mmio = { - .write = openpic_tmr_write, - .read = openpic_tmr_read, - .start_addr = OPENPIC_TMR_REG_START, - .size = OPENPIC_TMR_REG_SIZE, -}; - -static struct mem_reg openpic_cpu_mmio = { - .write = openpic_cpu_write, - .read = openpic_cpu_read, - .start_addr = OPENPIC_CPU_REG_START, - .size = OPENPIC_CPU_REG_SIZE, -}; - -static struct mem_reg openpic_src_mmio = { - .write = openpic_src_write, - .read = openpic_src_read, - .start_addr = OPENPIC_SRC_REG_START, - .size = OPENPIC_SRC_REG_SIZE, -}; - -static struct mem_reg openpic_msi_mmio = { - .read = openpic_msi_read, - .write = openpic_msi_write, - .start_addr = OPENPIC_MSI_REG_START, - .size = OPENPIC_MSI_REG_SIZE, -}; - -static struct mem_reg openpic_summary_mmio = { - .read = openpic_summary_read, - .write = openpic_summary_write, - .start_addr = OPENPIC_SUMMARY_REG_START, - .size = OPENPIC_SUMMARY_REG_SIZE, -}; - -static void fsl_common_init(struct openpic *opp) -{ - int i; - int virq = MAX_SRC; - - list_add(&openpic_msi_mmio.list, &opp->mmio_regions); - list_add(&openpic_summary_mmio.list, &opp->mmio_regions); - - opp->vid = VID_REVISION_1_2; - opp->vir = VIR_GENERIC; - opp->vector_mask = 0xFFFF; - opp->tfrr_reset = 0; - opp->ivpr_reset = IVPR_MASK_MASK; - opp->idr_reset = 1 << 0; - opp->max_irq = MAX_IRQ; - - opp->irq_ipi0 = virq; - virq += MAX_IPI; - opp->irq_tim0 = virq; - virq += MAX_TMR; - - BUG_ON(virq > MAX_IRQ); - - opp->irq_msi = 224; - - for (i = 0; i < opp->fsl->max_ext; i++) - opp->src[i].level = false; - - /* Internal interrupts, including message and MSI */ - for (i = 16; i < MAX_SRC; i++) { - opp->src[i].type = IRQ_TYPE_FSLINT; - opp->src[i].level = true; - } - - /* timers and IPIs */ - for (i = MAX_SRC; i < virq; i++) { - opp->src[i].type = IRQ_TYPE_FSLSPECIAL; - opp->src[i].level = false; - } -} - -static int kvm_mpic_read_internal(struct openpic *opp, gpa_t addr, u32 *ptr) -{ - struct list_head *node; - - list_for_each(node, &opp->mmio_regions) { - struct mem_reg *mr = list_entry(node, struct mem_reg, list); - - if (mr->start_addr > addr || addr >= mr->start_addr + mr->size) - continue; - - return mr->read(opp, addr - mr->start_addr, ptr); - } - - return -ENXIO; -} - -static int kvm_mpic_write_internal(struct openpic *opp, gpa_t addr, u32 val) -{ - struct list_head *node; - - list_for_each(node, &opp->mmio_regions) { - struct mem_reg *mr = list_entry(node, struct mem_reg, list); - - if (mr->start_addr > addr || addr >= mr->start_addr + mr->size) - continue; - - return mr->write(opp, addr - mr->start_addr, val); - } - - return -ENXIO; -} - -static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, - int len, void *ptr) -{ - struct openpic *opp = container_of(this, struct openpic, mmio); - int ret; - union { - u32 val; - u8 bytes[4]; - } u; - - if (addr & (len - 1)) { - pr_debug("%s: bad alignment %llx/%d\n", - __func__, addr, len); - return -EINVAL; - } - - spin_lock_irq(&opp->lock); - ret = kvm_mpic_read_internal(opp, addr - opp->reg_base, &u.val); - spin_unlock_irq(&opp->lock); - - /* - * Technically only 32-bit accesses are allowed, but be nice to - * people dumping registers a byte at a time -- it works in real - * hardware (reads only, not writes). - */ - if (len == 4) { - *(u32 *)ptr = u.val; - pr_debug("%s: addr %llx ret %d len 4 val %x\n", - __func__, addr, ret, u.val); - } else if (len == 1) { - *(u8 *)ptr = u.bytes[addr & 3]; - pr_debug("%s: addr %llx ret %d len 1 val %x\n", - __func__, addr, ret, u.bytes[addr & 3]); - } else { - pr_debug("%s: bad length %d\n", __func__, len); - return -EINVAL; - } - - return ret; -} - -static int kvm_mpic_write(struct kvm_io_device *this, gpa_t addr, - int len, const void *ptr) -{ - struct openpic *opp = container_of(this, struct openpic, mmio); - int ret; - - if (len != 4) { - pr_debug("%s: bad length %d\n", __func__, len); - return -EOPNOTSUPP; - } - if (addr & 3) { - pr_debug("%s: bad alignment %llx/%d\n", __func__, addr, len); - return -EOPNOTSUPP; - } - - spin_lock_irq(&opp->lock); - ret = kvm_mpic_write_internal(opp, addr - opp->reg_base, - *(const u32 *)ptr); - spin_unlock_irq(&opp->lock); - - pr_debug("%s: addr %llx ret %d val %x\n", - __func__, addr, ret, *(const u32 *)ptr); - - return ret; -} - -static void kvm_mpic_dtor(struct kvm_io_device *this) -{ - struct openpic *opp = container_of(this, struct openpic, mmio); - - opp->mmio_mapped = false; -} - -static const struct kvm_io_device_ops mpic_mmio_ops = { - .read = kvm_mpic_read, - .write = kvm_mpic_write, - .destructor = kvm_mpic_dtor, -}; - -static void map_mmio(struct openpic *opp) -{ - BUG_ON(opp->mmio_mapped); - opp->mmio_mapped = true; - - kvm_iodevice_init(&opp->mmio, &mpic_mmio_ops); - - kvm_io_bus_register_dev(opp->kvm, KVM_MMIO_BUS, - opp->reg_base, OPENPIC_REG_SIZE, - &opp->mmio); -} - -static void unmap_mmio(struct openpic *opp) -{ - if (opp->mmio_mapped) { - opp->mmio_mapped = false; - kvm_io_bus_unregister_dev(opp->kvm, KVM_MMIO_BUS, &opp->mmio); - } -} - -static int set_base_addr(struct openpic *opp, struct kvm_device_attr *attr) -{ - u64 base; - - if (copy_from_user(&base, (u64 __user *)(long)attr->addr, sizeof(u64))) - return -EFAULT; - - if (base & 0x3ffff) { - pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx not aligned\n", - __func__, base); - return -EINVAL; - } - - if (base == opp->reg_base) - return 0; - - mutex_lock(&opp->kvm->slots_lock); - - unmap_mmio(opp); - opp->reg_base = base; - - pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx\n", - __func__, base); - - if (base == 0) - goto out; - - map_mmio(opp); - - mutex_unlock(&opp->kvm->slots_lock); -out: - return 0; -} - -#define ATTR_SET 0 -#define ATTR_GET 1 - -static int access_reg(struct openpic *opp, gpa_t addr, u32 *val, int type) -{ - int ret; - - if (addr & 3) - return -ENXIO; - - spin_lock_irq(&opp->lock); - - if (type == ATTR_SET) - ret = kvm_mpic_write_internal(opp, addr, *val); - else - ret = kvm_mpic_read_internal(opp, addr, val); - - spin_unlock_irq(&opp->lock); - - pr_debug("%s: type %d addr %llx val %x\n", __func__, type, addr, *val); - - return ret; -} - -static int mpic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) -{ - struct openpic *opp = dev->private; - u32 attr32; - - switch (attr->group) { - case KVM_DEV_MPIC_GRP_MISC: - switch (attr->attr) { - case KVM_DEV_MPIC_BASE_ADDR: - return set_base_addr(opp, attr); - } - - break; - - case KVM_DEV_MPIC_GRP_REGISTER: - if (get_user(attr32, (u32 __user *)(long)attr->addr)) - return -EFAULT; - - return access_reg(opp, attr->attr, &attr32, ATTR_SET); - - case KVM_DEV_MPIC_GRP_IRQ_ACTIVE: - if (attr->attr > MAX_SRC) - return -EINVAL; - - if (get_user(attr32, (u32 __user *)(long)attr->addr)) - return -EFAULT; - - if (attr32 != 0 && attr32 != 1) - return -EINVAL; - - spin_lock_irq(&opp->lock); - openpic_set_irq(opp, attr->attr, attr32); - spin_unlock_irq(&opp->lock); - return 0; - } - - return -ENXIO; -} - -static int mpic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) -{ - struct openpic *opp = dev->private; - u64 attr64; - u32 attr32; - int ret; - - switch (attr->group) { - case KVM_DEV_MPIC_GRP_MISC: - switch (attr->attr) { - case KVM_DEV_MPIC_BASE_ADDR: - mutex_lock(&opp->kvm->slots_lock); - attr64 = opp->reg_base; - mutex_unlock(&opp->kvm->slots_lock); - - if (copy_to_user((u64 __user *)(long)attr->addr, - &attr64, sizeof(u64))) - return -EFAULT; - - return 0; - } - - break; - - case KVM_DEV_MPIC_GRP_REGISTER: - ret = access_reg(opp, attr->attr, &attr32, ATTR_GET); - if (ret) - return ret; - - if (put_user(attr32, (u32 __user *)(long)attr->addr)) - return -EFAULT; - - return 0; - - case KVM_DEV_MPIC_GRP_IRQ_ACTIVE: - if (attr->attr > MAX_SRC) - return -EINVAL; - - spin_lock_irq(&opp->lock); - attr32 = opp->src[attr->attr].pending; - spin_unlock_irq(&opp->lock); - - if (put_user(attr32, (u32 __user *)(long)attr->addr)) - return -EFAULT; - - return 0; - } - - return -ENXIO; -} - -static int mpic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) -{ - switch (attr->group) { - case KVM_DEV_MPIC_GRP_MISC: - switch (attr->attr) { - case KVM_DEV_MPIC_BASE_ADDR: - return 0; - } - - break; - - case KVM_DEV_MPIC_GRP_REGISTER: - return 0; - - case KVM_DEV_MPIC_GRP_IRQ_ACTIVE: - if (attr->attr > MAX_SRC) - break; - - return 0; - } - - return -ENXIO; -} - -static void mpic_destroy(struct kvm_device *dev) -{ - struct openpic *opp = dev->private; - - if (opp->mmio_mapped) { - /* - * Normally we get unmapped by kvm_io_bus_destroy(), - * which happens before the VCPUs release their references. - * - * Thus, we should only get here if no VCPUs took a reference - * to us in the first place. - */ - WARN_ON(opp->nb_cpus != 0); - unmap_mmio(opp); - } - - dev->kvm->arch.mpic = NULL; - kfree(opp); -} - -static int mpic_set_default_irq_routing(struct openpic *opp) -{ - int i; - struct kvm_irq_routing_entry *routing; - - /* XXX be more dynamic if we ever want to support multiple MPIC chips */ - routing = kzalloc((sizeof(*routing) * opp->nb_irqs), GFP_KERNEL); - if (!routing) - return -ENOMEM; - - for (i = 0; i < opp->nb_irqs; i++) { - routing[i].gsi = i; - routing[i].type = KVM_IRQ_ROUTING_IRQCHIP; - routing[i].u.irqchip.irqchip = 0; - routing[i].u.irqchip.pin = i; - } - - kvm_set_irq_routing(opp->kvm, routing, opp->nb_irqs, 0); - - kfree(routing); - return 0; -} - -static int mpic_create(struct kvm_device *dev, u32 type) -{ - struct openpic *opp; - int ret; - - /* We only support one MPIC at a time for now */ - if (dev->kvm->arch.mpic) - return -EINVAL; - - opp = kzalloc(sizeof(struct openpic), GFP_KERNEL); - if (!opp) - return -ENOMEM; - - dev->private = opp; - opp->kvm = dev->kvm; - opp->dev = dev; - opp->model = type; - spin_lock_init(&opp->lock); - - INIT_LIST_HEAD(&opp->mmio_regions); - list_add(&openpic_gbl_mmio.list, &opp->mmio_regions); - list_add(&openpic_tmr_mmio.list, &opp->mmio_regions); - list_add(&openpic_src_mmio.list, &opp->mmio_regions); - list_add(&openpic_cpu_mmio.list, &opp->mmio_regions); - - switch (opp->model) { - case KVM_DEV_TYPE_FSL_MPIC_20: - opp->fsl = &fsl_mpic_20; - opp->brr1 = 0x00400200; - opp->flags |= OPENPIC_FLAG_IDR_CRIT; - opp->nb_irqs = 80; - opp->mpic_mode_mask = GCR_MODE_MIXED; - - fsl_common_init(opp); - - break; - - case KVM_DEV_TYPE_FSL_MPIC_42: - opp->fsl = &fsl_mpic_42; - opp->brr1 = 0x00400402; - opp->flags |= OPENPIC_FLAG_ILR; - opp->nb_irqs = 196; - opp->mpic_mode_mask = GCR_MODE_PROXY; - - fsl_common_init(opp); - - break; - - default: - ret = -ENODEV; - goto err; - } - - dev->kvm->arch.mpic = opp; - - ret = mpic_set_default_irq_routing(opp); - if (ret) - goto err; - - openpic_reset(opp); - - return 0; - -err: - dev->kvm->arch.mpic = NULL; - kfree(opp); - return ret; -} - -struct kvm_device_ops kvm_mpic_ops = { - .name = "kvm-mpic", - .create = mpic_create, - .destroy = mpic_destroy, - .set_attr = mpic_set_attr, - .get_attr = mpic_get_attr, - .has_attr = mpic_has_attr, -}; - -int kvmppc_mpic_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, - u32 cpu) -{ - struct openpic *opp = dev->private; - int ret = 0; - - if (dev->ops != &kvm_mpic_ops) - return -EPERM; - if (opp->kvm != vcpu->kvm) - return -EPERM; - if (cpu < 0 || cpu >= MAX_CPU) - return -EPERM; - - spin_lock_irq(&opp->lock); - - if (opp->dst[cpu].vcpu) { - ret = -EEXIST; - goto out; - } - if (vcpu->arch.irq_type) { - ret = -EBUSY; - goto out; - } - - opp->dst[cpu].vcpu = vcpu; - opp->nb_cpus = max(opp->nb_cpus, cpu + 1); - - vcpu->arch.mpic = opp; - vcpu->arch.irq_cpu_id = cpu; - vcpu->arch.irq_type = KVMPPC_IRQ_MPIC; - - /* This might need to be changed if GCR gets extended */ - if (opp->mpic_mode_mask == GCR_MODE_PROXY) - vcpu->arch.epr_flags |= KVMPPC_EPR_KERNEL; - - kvm_device_get(dev); -out: - spin_unlock_irq(&opp->lock); - return ret; -} - -/* - * This should only happen immediately before the mpic is destroyed, - * so we shouldn't need to worry about anything still trying to - * access the vcpu pointer. - */ -void kvmppc_mpic_disconnect_vcpu(struct openpic *opp, struct kvm_vcpu *vcpu) -{ - BUG_ON(!opp->dst[vcpu->arch.irq_cpu_id].vcpu); - - opp->dst[vcpu->arch.irq_cpu_id].vcpu = NULL; - kvm_device_put(opp->dev); -} - -/* - * Return value: - * < 0 Interrupt was ignored (masked or not delivered for other reasons) - * = 0 Interrupt was coalesced (previous irq is still pending) - * > 0 Number of CPUs interrupt was delivered to - */ -static int mpic_set_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level) -{ - u32 irq = e->irqchip.pin; - struct openpic *opp = kvm->arch.mpic; - - spin_lock_irq(&opp->lock); - openpic_set_irq(opp, irq, level); - spin_unlock_irq(&opp->lock); - - /* All code paths we care about don't check for the return value */ - return 0; -} - -int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level) -{ - struct openpic *opp = kvm->arch.mpic; - spin_lock_irq(&opp->lock); - - /* - * XXX We ignore the target address for now, as we only support - * a single MSI bank. - */ - openpic_msi_write(kvm->arch.mpic, MSIIR_OFFSET, e->msi.data); - spin_unlock_irq(&opp->lock); - - /* All code paths we care about don't check for the return value */ - return 0; -} - -int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, - struct kvm_kernel_irq_routing_entry *e, - const struct kvm_irq_routing_entry *ue) -{ - int r = -EINVAL; - - switch (ue->type) { - case KVM_IRQ_ROUTING_IRQCHIP: - e->set = mpic_set_irq; - e->irqchip.irqchip = ue->u.irqchip.irqchip; - e->irqchip.pin = ue->u.irqchip.pin; - if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) - goto out; - rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; - break; - case KVM_IRQ_ROUTING_MSI: - e->set = kvm_set_msi; - e->msi.address_lo = ue->u.msi.address_lo; - e->msi.address_hi = ue->u.msi.address_hi; - e->msi.data = ue->u.msi.data; - break; - default: - goto out; - } - - r = 0; -out: - return r; -} diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 990e24a..4bf74d4 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -25,7 +25,6 @@ #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/slab.h> -#include <linux/file.h> #include <asm/cputable.h> #include <asm/uaccess.h> #include <asm/kvm_ppc.h> @@ -33,7 +32,6 @@ #include <asm/cputhreads.h> #include <asm/irqflags.h> #include "timing.h" -#include "irq.h" #include "../mm/mmu_decl.h" #define CREATE_TRACE_POINTS @@ -319,7 +317,6 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_ONE_REG: case KVM_CAP_IOEVENTFD: - case KVM_CAP_DEVICE_CTRL: r = 1; break; #ifndef CONFIG_KVM_BOOK3S_64_HV @@ -329,9 +326,6 @@ int kvm_dev_ioctl_check_extension(long ext) #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC) case KVM_CAP_SW_TLB: #endif -#ifdef CONFIG_KVM_MPIC - case KVM_CAP_IRQ_MPIC: -#endif r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -466,15 +460,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) tasklet_kill(&vcpu->arch.tasklet); kvmppc_remove_vcpu_debugfs(vcpu); - - switch (vcpu->arch.irq_type) { -#ifdef CONFIG_KVM_MPIC - case KVMPPC_IRQ_MPIC: - kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu); - break; -#endif - } - kvmppc_core_vcpu_free(vcpu); } @@ -778,10 +763,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; case KVM_CAP_PPC_EPR: r = 0; - if (cap->args[0]) - vcpu->arch.epr_flags |= KVMPPC_EPR_USER; - else - vcpu->arch.epr_flags &= ~KVMPPC_EPR_USER; + vcpu->arch.epr_enabled = cap->args[0]; break; #ifdef CONFIG_BOOKE case KVM_CAP_PPC_BOOKE_WATCHDOG: @@ -802,25 +784,6 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; } #endif -#ifdef CONFIG_KVM_MPIC - case KVM_CAP_IRQ_MPIC: { - struct file *filp; - struct kvm_device *dev; - - r = -EBADF; - filp = fget(cap->args[0]); - if (!filp) - break; - - r = -EPERM; - dev = kvm_device_from_filp(filp); - if (dev) - r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]); - - fput(filp); - break; - } -#endif default: r = -EINVAL; break; @@ -943,20 +906,9 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo) return 0; } -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event) -{ - if (!irqchip_in_kernel(kvm)) - return -ENXIO; - - irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event->irq, irq_event->level); - return 0; -} - long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { - struct kvm *kvm __maybe_unused = filp->private_data; void __user *argp = (void __user *)arg; long r; @@ -975,6 +927,7 @@ long kvm_arch_vm_ioctl(struct file *filp, #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CREATE_SPAPR_TCE: { struct kvm_create_spapr_tce create_tce; + struct kvm *kvm = filp->private_data; r = -EFAULT; if (copy_from_user(&create_tce, argp, sizeof(create_tce))) @@ -986,6 +939,7 @@ long kvm_arch_vm_ioctl(struct file *filp, #ifdef CONFIG_KVM_BOOK3S_64_HV case KVM_ALLOCATE_RMA: { + struct kvm *kvm = filp->private_data; struct kvm_allocate_rma rma; r = kvm_vm_ioctl_allocate_rma(kvm, &rma); @@ -995,6 +949,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_PPC_ALLOCATE_HTAB: { + struct kvm *kvm = filp->private_data; u32 htab_order; r = -EFAULT; @@ -1011,6 +966,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_PPC_GET_HTAB_FD: { + struct kvm *kvm = filp->private_data; struct kvm_get_htab_fd ghf; r = -EFAULT; @@ -1023,6 +979,7 @@ long kvm_arch_vm_ioctl(struct file *filp, #ifdef CONFIG_PPC_BOOK3S_64 case KVM_PPC_GET_SMMU_INFO: { + struct kvm *kvm = filp->private_data; struct kvm_ppc_smmu_info info; memset(&info, 0, sizeof(info)); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ff691d6..85039f9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -43,8 +43,6 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 -#define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS - #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 9d50efd..586f000 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -29,7 +29,6 @@ config KVM select MMU_NOTIFIER select ANON_INODES select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE select KVM_ASYNC_PF diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a797b8e..04d3040 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -7,7 +7,7 @@ CFLAGS_vmx.o := -I. kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ coalesced_mmio.o irq_comm.o eventfd.o \ - assigned-dev.o irqchip.o) + assigned-dev.o) kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3dd9625..fb485ba 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2500,6 +2500,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PCI_2_3: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: + case KVM_CAP_IRQFD_RESAMPLE: r = 1; break; case KVM_CAP_COALESCED_MMIO: diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 226d10b..3fd7b15 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -295,10 +295,10 @@ struct kvm_kernel_irq_routing_entry { struct hlist_node link; }; -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef __KVM_HAVE_IOAPIC struct kvm_irq_routing_table { - int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; + int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS]; struct kvm_kernel_irq_routing_entry *rt_entries; u32 nr_rt_entries; /* @@ -419,7 +419,7 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); int __must_check vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef __KVM_HAVE_IOAPIC int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else @@ -690,6 +690,11 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask); +#ifdef __KVM_HAVE_IOAPIC +void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, + union kvm_ioapic_redirect_entry *entry, + unsigned long *deliver_bitmask); +#endif int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, @@ -885,7 +890,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) } #endif -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef KVM_CAP_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES 1024 @@ -894,9 +899,6 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); -int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, - struct kvm_kernel_irq_routing_entry *e, - const struct kvm_irq_routing_entry *ue); void kvm_free_irq_routing(struct kvm *kvm); int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); @@ -995,43 +997,6 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) } } -struct kvm_device_ops; - -struct kvm_device { - struct kvm_device_ops *ops; - struct kvm *kvm; - atomic_t users; - void *private; -}; - -/* create, destroy, and name are mandatory */ -struct kvm_device_ops { - const char *name; - int (*create)(struct kvm_device *dev, u32 type); - - /* - * Destroy is responsible for freeing dev. - * - * Destroy may be called before or after destructors are called - * on emulated I/O regions, depending on whether a reference is - * held by a vcpu or other kvm component that gets destroyed - * after the emulated I/O. - */ - void (*destroy)(struct kvm_device *dev); - - int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); - int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); - int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); - long (*ioctl)(struct kvm_device *dev, unsigned int ioctl, - unsigned long arg); -}; - -void kvm_device_get(struct kvm_device *dev); -void kvm_device_put(struct kvm_device *dev); -struct kvm_device *kvm_device_from_filp(struct file *filp); - -extern struct kvm_device_ops kvm_mpic_ops; - #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 85422a8..7ef9e75 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -37,7 +37,7 @@ TRACE_EVENT(kvm_userspace_exit, __entry->errno < 0 ? -__entry->errno : __entry->reason) ); -#if defined(CONFIG_HAVE_KVM_IRQCHIP) +#if defined(__KVM_HAVE_IRQ_LINE) TRACE_EVENT(kvm_set_irq, TP_PROTO(unsigned int gsi, int level, int irq_source_id), TP_ARGS(gsi, level, irq_source_id), @@ -122,10 +122,6 @@ TRACE_EVENT(kvm_msi_set_irq, {KVM_IRQCHIP_PIC_SLAVE, "PIC slave"}, \ {KVM_IRQCHIP_IOAPIC, "IOAPIC"} -#endif /* defined(__KVM_HAVE_IOAPIC) */ - -#if defined(CONFIG_HAVE_KVM_IRQCHIP) - TRACE_EVENT(kvm_ack_irq, TP_PROTO(unsigned int irqchip, unsigned int pin), TP_ARGS(irqchip, pin), @@ -140,18 +136,14 @@ TRACE_EVENT(kvm_ack_irq, __entry->pin = pin; ), -#ifdef kvm_irqchips TP_printk("irqchip %s pin %u", __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin) -#else - TP_printk("irqchip %d pin %u", __entry->irqchip, __entry->pin) -#endif ); -#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ +#endif /* defined(__KVM_HAVE_IOAPIC) */ #define KVM_TRACE_MMIO_READ_UNSATISFIED 0 #define KVM_TRACE_MMIO_READ 1 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7a7a3c3..710634c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -555,7 +555,9 @@ struct kvm_ppc_smmu_info { #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif +#ifdef __KVM_HAVE_IOAPIC #define KVM_CAP_IRQ_ROUTING 25 +#endif #define KVM_CAP_IRQ_INJECT_STATUS 26 #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT #define KVM_CAP_DEVICE_DEASSIGNMENT 27 @@ -639,8 +641,6 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_PPC_BOOKE_WATCHDOG 83 #define KVM_CAP_PPC_HTAB_FD 84 #define KVM_CAP_PPC_EPR 86 -#define KVM_CAP_DEVICE_CTRL 89 -#define KVM_CAP_IRQ_MPIC 90 #ifdef KVM_CAP_IRQ_ROUTING @@ -870,35 +870,6 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_HTAB_FD _IOW(KVMIO, 0xaa, struct kvm_get_htab_fd) /* - * Device control API, available with KVM_CAP_DEVICE_CTRL - */ -#define KVM_CREATE_DEVICE_TEST 1 - -struct kvm_create_device { - __u32 type; /* in: KVM_DEV_TYPE_xxx */ - __u32 fd; /* out: device handle */ - __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ -}; - -struct kvm_device_attr { - __u32 flags; /* no flags currently defined */ - __u32 group; /* device-defined */ - __u64 attr; /* group-defined */ - __u64 addr; /* userspace address of attr data */ -}; - -#define KVM_DEV_TYPE_FSL_MPIC_20 1 -#define KVM_DEV_TYPE_FSL_MPIC_42 2 - -/* ioctl for vm fd */ -#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) - -/* ioctls for fds returned by KVM_CREATE_DEVICE */ -#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xe1, struct kvm_device_attr) -#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xe2, struct kvm_device_attr) -#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xe3, struct kvm_device_attr) - -/* * ioctls for vcpu fds */ #define KVM_RUN _IO(KVMIO, 0x80) diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 779262f..d01b24b 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -6,9 +6,6 @@ config HAVE_KVM config HAVE_KVM_IRQCHIP bool -config HAVE_KVM_IRQ_ROUTING - bool - config HAVE_KVM_EVENTFD bool select EVENTFD diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index 468c05d..3642239 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -982,6 +982,36 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } +#ifdef KVM_CAP_IRQ_ROUTING + case KVM_SET_GSI_ROUTING: { + struct kvm_irq_routing routing; + struct kvm_irq_routing __user *urouting; + struct kvm_irq_routing_entry *entries; + + r = -EFAULT; + if (copy_from_user(&routing, argp, sizeof(routing))) + goto out; + r = -EINVAL; + if (routing.nr >= KVM_MAX_IRQ_ROUTES) + goto out; + if (routing.flags) + goto out; + r = -ENOMEM; + entries = vmalloc(routing.nr * sizeof(*entries)); + if (!entries) + goto out; + r = -EFAULT; + urouting = argp; + if (copy_from_user(entries, urouting->entries, + routing.nr * sizeof(*entries))) + goto out_free_irq_routing; + r = kvm_set_irq_routing(kvm, entries, routing.nr, + routing.flags); + out_free_irq_routing: + vfree(entries); + break; + } +#endif /* KVM_CAP_IRQ_ROUTING */ #ifdef __KVM_HAVE_MSIX case KVM_ASSIGN_SET_MSIX_NR: { struct kvm_assigned_msix_nr entry_nr; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index c95a075..f0ced1a 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -35,7 +35,7 @@ #include "iodev.h" -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef __KVM_HAVE_IOAPIC /* * -------------------------------------------------------------------- * irqfd: Allows an fd to be used to inject an interrupt to the guest @@ -431,7 +431,7 @@ fail: void kvm_eventfd_init(struct kvm *kvm) { -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef __KVM_HAVE_IOAPIC spin_lock_init(&kvm->irqfds.lock); INIT_LIST_HEAD(&kvm->irqfds.items); INIT_LIST_HEAD(&kvm->irqfds.resampler_list); @@ -440,7 +440,7 @@ kvm_eventfd_init(struct kvm *kvm) INIT_LIST_HEAD(&kvm->ioeventfds); } -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef __KVM_HAVE_IOAPIC /* * shutdown any irqfd's that match fd+gsi */ diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index c62509d..656fa45 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -147,6 +147,58 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, return -EWOULDBLOCK; } +int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) +{ + struct kvm_kernel_irq_routing_entry route; + + if (!irqchip_in_kernel(kvm) || msi->flags != 0) + return -EINVAL; + + route.msi.address_lo = msi->address_lo; + route.msi.address_hi = msi->address_hi; + route.msi.data = msi->data; + + return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1); +} + +/* + * Return value: + * < 0 Interrupt was ignored (masked or not delivered for other reasons) + * = 0 Interrupt was coalesced (previous irq is still pending) + * > 0 Number of CPUs interrupt was delivered to + */ +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) +{ + struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; + int ret = -1, i = 0; + struct kvm_irq_routing_table *irq_rt; + struct hlist_node *n; + + trace_kvm_set_irq(irq, level, irq_source_id); + + /* Not possible to detect if the guest uses the PIC or the + * IOAPIC. So set the bit in both. The guest will ignore + * writes to the unused one. + */ + rcu_read_lock(); + irq_rt = rcu_dereference(kvm->irq_routing); + if (irq < irq_rt->nr_rt_entries) + hlist_for_each_entry(e, n, &irq_rt->map[irq], link) + irq_set[i++] = *e; + rcu_read_unlock(); + + while(i--) { + int r; + r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level); + if (r < 0) + continue; + + ret = r + ((ret < 0) ? 0 : ret); + } + + return ret; +} + /* * Deliver an IRQ in an atomic context if we can, or return a failure, * user can retry in a process context. @@ -185,6 +237,41 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) return ret; } +void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + struct kvm_irq_ack_notifier *kian; + struct hlist_node *n; + int gsi; + + trace_kvm_ack_irq(irqchip, pin); + + rcu_read_lock(); + gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + if (gsi != -1) + hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, + link) + if (kian->gsi == gsi) + kian->irq_acked(kian); + rcu_read_unlock(); +} + +void kvm_register_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian) +{ + mutex_lock(&kvm->irq_lock); + hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); + mutex_unlock(&kvm->irq_lock); +} + +void kvm_unregister_irq_ack_notifier(struct kvm *kvm, + struct kvm_irq_ack_notifier *kian) +{ + mutex_lock(&kvm->irq_lock); + hlist_del_init_rcu(&kian->link); + mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); +} + int kvm_request_irq_source_id(struct kvm *kvm) { unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; @@ -269,14 +356,35 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, rcu_read_unlock(); } -int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, - struct kvm_kernel_irq_routing_entry *e, - const struct kvm_irq_routing_entry *ue) +void kvm_free_irq_routing(struct kvm *kvm) +{ + /* Called only during vm destruction. Nobody can use the pointer + at this stage */ + kfree(kvm->irq_routing); +} + +static int setup_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; int delta; unsigned max_pin; + struct kvm_kernel_irq_routing_entry *ei; + struct hlist_node *n; + /* + * Do not allow GSI to be mapped to the same irqchip more than once. + * Allow only one to one mapping between GSI and MSI. + */ + hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) + if (ei->type == KVM_IRQ_ROUTING_MSI || + ue->type == KVM_IRQ_ROUTING_MSI || + ue->u.irqchip.irqchip == ei->irqchip.irqchip) + return r; + + e->gsi = ue->gsi; + e->type = ue->type; switch (ue->type) { case KVM_IRQ_ROUTING_IRQCHIP: delta = 0; @@ -319,6 +427,63 @@ out: return r; } + +int kvm_set_irq_routing(struct kvm *kvm, + const struct kvm_irq_routing_entry *ue, + unsigned nr, + unsigned flags) +{ + struct kvm_irq_routing_table *new, *old; + u32 i, j, nr_rt_entries = 0; + int r; + + for (i = 0; i < nr; ++i) { + if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) + return -EINVAL; + nr_rt_entries = max(nr_rt_entries, ue[i].gsi); + } + + nr_rt_entries += 1; + + new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) + + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), + GFP_KERNEL); + + if (!new) + return -ENOMEM; + + new->rt_entries = (void *)&new->map[nr_rt_entries]; + + new->nr_rt_entries = nr_rt_entries; + for (i = 0; i < 3; i++) + for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++) + new->chip[i][j] = -1; + + for (i = 0; i < nr; ++i) { + r = -EINVAL; + if (ue->flags) + goto out; + r = setup_routing_entry(new, &new->rt_entries[i], ue); + if (r) + goto out; + ++ue; + } + + mutex_lock(&kvm->irq_lock); + old = kvm->irq_routing; + kvm_irq_routing_update(kvm, new); + mutex_unlock(&kvm->irq_lock); + + synchronize_rcu(); + + new = old; + r = 0; + +out: + kfree(new); + return r; +} + #define IOAPIC_ROUTING_ENTRY(irq) \ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) } diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c deleted file mode 100644 index f1a4add..0000000 --- a/virt/kvm/irqchip.c +++ /dev/null @@ -1,211 +0,0 @@ -/* - * irqchip.c: Common API for in kernel interrupt controllers - * Copyright (c) 2007, Intel Corporation. - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - * Copyright (c) 2013, Alexander Graf <agraf@suse.de> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. - * - * This file is derived from virt/kvm/irq_comm.c. - * - * Authors: - * Yaozu (Eddie) Dong <Eddie.dong@intel.com> - * Alexander Graf <agraf@suse.de> - */ - -#include <linux/kvm_host.h> -#include <linux/slab.h> -#include <linux/export.h> -#include <trace/events/kvm.h> -#include "irq.h" - -void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) -{ - struct kvm_irq_ack_notifier *kian; - struct hlist_node *n; - int gsi; - - trace_kvm_ack_irq(irqchip, pin); - - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - if (gsi != -1) - hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, - link) - if (kian->gsi == gsi) - kian->irq_acked(kian); - rcu_read_unlock(); -} - -void kvm_register_irq_ack_notifier(struct kvm *kvm, - struct kvm_irq_ack_notifier *kian) -{ - mutex_lock(&kvm->irq_lock); - hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); - mutex_unlock(&kvm->irq_lock); -} - -void kvm_unregister_irq_ack_notifier(struct kvm *kvm, - struct kvm_irq_ack_notifier *kian) -{ - mutex_lock(&kvm->irq_lock); - hlist_del_init_rcu(&kian->link); - mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); -} - -int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) -{ - struct kvm_kernel_irq_routing_entry route; - - if (!irqchip_in_kernel(kvm) || msi->flags != 0) - return -EINVAL; - - route.msi.address_lo = msi->address_lo; - route.msi.address_hi = msi->address_hi; - route.msi.data = msi->data; - - return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1); -} - -/* - * Return value: - * < 0 Interrupt was ignored (masked or not delivered for other reasons) - * = 0 Interrupt was coalesced (previous irq is still pending) - * > 0 Number of CPUs interrupt was delivered to - */ -int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) -{ - struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; - int ret = -1, i = 0; - struct kvm_irq_routing_table *irq_rt; - struct hlist_node *n; - - trace_kvm_set_irq(irq, level, irq_source_id); - - /* Not possible to detect if the guest uses the PIC or the - * IOAPIC. So set the bit in both. The guest will ignore - * writes to the unused one. - */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); - if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, n, &irq_rt->map[irq], link) - irq_set[i++] = *e; - rcu_read_unlock(); - - while(i--) { - int r; - r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level); - if (r < 0) - continue; - - ret = r + ((ret < 0) ? 0 : ret); - } - - return ret; -} - -void kvm_free_irq_routing(struct kvm *kvm) -{ - /* Called only during vm destruction. Nobody can use the pointer - at this stage */ - kfree(kvm->irq_routing); -} - -static int setup_routing_entry(struct kvm_irq_routing_table *rt, - struct kvm_kernel_irq_routing_entry *e, - const struct kvm_irq_routing_entry *ue) -{ - int r = -EINVAL; - struct kvm_kernel_irq_routing_entry *ei; - struct hlist_node *n; - - /* - * Do not allow GSI to be mapped to the same irqchip more than once. - * Allow only one to one mapping between GSI and MSI. - */ - hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) - if (ei->type == KVM_IRQ_ROUTING_MSI || - ue->type == KVM_IRQ_ROUTING_MSI || - ue->u.irqchip.irqchip == ei->irqchip.irqchip) - return r; - - e->gsi = ue->gsi; - e->type = ue->type; - r = kvm_set_routing_entry(rt, e, ue); - if (r) - goto out; - - hlist_add_head(&e->link, &rt->map[e->gsi]); - r = 0; -out: - return r; -} - -int kvm_set_irq_routing(struct kvm *kvm, - const struct kvm_irq_routing_entry *ue, - unsigned nr, - unsigned flags) -{ - struct kvm_irq_routing_table *new, *old; - u32 i, j, nr_rt_entries = 0; - int r; - - for (i = 0; i < nr; ++i) { - if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) - return -EINVAL; - nr_rt_entries = max(nr_rt_entries, ue[i].gsi); - } - - nr_rt_entries += 1; - - new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) - + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), - GFP_KERNEL); - - if (!new) - return -ENOMEM; - - new->rt_entries = (void *)&new->map[nr_rt_entries]; - - new->nr_rt_entries = nr_rt_entries; - for (i = 0; i < KVM_NR_IRQCHIPS; i++) - for (j = 0; j < KVM_IRQCHIP_NUM_PINS; j++) - new->chip[i][j] = -1; - - for (i = 0; i < nr; ++i) { - r = -EINVAL; - if (ue->flags) - goto out; - r = setup_routing_entry(new, &new->rt_entries[i], ue); - if (r) - goto out; - ++ue; - } - - mutex_lock(&kvm->irq_lock); - old = kvm->irq_routing; - kvm_irq_routing_update(kvm, new); - mutex_unlock(&kvm->irq_lock); - - synchronize_rcu(); - - new = old; - r = 0; - -out: - kfree(new); - return r; -} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 60ac292..5ff30ca 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2133,123 +2133,6 @@ out: } #endif -static int kvm_device_ioctl_attr(struct kvm_device *dev, - int (*accessor)(struct kvm_device *dev, - struct kvm_device_attr *attr), - unsigned long arg) -{ - struct kvm_device_attr attr; - - if (!accessor) - return -EPERM; - - if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) - return -EFAULT; - - return accessor(dev, &attr); -} - -static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, - unsigned long arg) -{ - struct kvm_device *dev = filp->private_data; - - switch (ioctl) { - case KVM_SET_DEVICE_ATTR: - return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); - case KVM_GET_DEVICE_ATTR: - return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg); - case KVM_HAS_DEVICE_ATTR: - return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg); - default: - if (dev->ops->ioctl) - return dev->ops->ioctl(dev, ioctl, arg); - - return -ENOTTY; - } -} - -void kvm_device_get(struct kvm_device *dev) -{ - atomic_inc(&dev->users); -} - -void kvm_device_put(struct kvm_device *dev) -{ - if (atomic_dec_and_test(&dev->users)) - dev->ops->destroy(dev); -} - -static int kvm_device_release(struct inode *inode, struct file *filp) -{ - struct kvm_device *dev = filp->private_data; - struct kvm *kvm = dev->kvm; - - kvm_device_put(dev); - kvm_put_kvm(kvm); - return 0; -} - -static const struct file_operations kvm_device_fops = { - .unlocked_ioctl = kvm_device_ioctl, - .release = kvm_device_release, -}; - -struct kvm_device *kvm_device_from_filp(struct file *filp) -{ - if (filp->f_op != &kvm_device_fops) - return NULL; - - return filp->private_data; -} - -static int kvm_ioctl_create_device(struct kvm *kvm, - struct kvm_create_device *cd) -{ - struct kvm_device_ops *ops = NULL; - struct kvm_device *dev; - bool test = cd->flags & KVM_CREATE_DEVICE_TEST; - int ret; - - switch (cd->type) { -#ifdef CONFIG_KVM_MPIC - case KVM_DEV_TYPE_FSL_MPIC_20: - case KVM_DEV_TYPE_FSL_MPIC_42: - ops = &kvm_mpic_ops; - break; -#endif - default: - return -ENODEV; - } - - if (test) - return 0; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return -ENOMEM; - - dev->ops = ops; - dev->kvm = kvm; - atomic_set(&dev->users, 1); - - ret = ops->create(dev, cd->type); - if (ret < 0) { - kfree(dev); - return ret; - } - - ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR); - if (ret < 0) { - ops->destroy(dev); - return ret; - } - - kvm_get_kvm(kvm); - cd->fd = ret; - return 0; -} - static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2364,54 +2247,6 @@ static long kvm_vm_ioctl(struct file *filp, break; } #endif -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING - case KVM_SET_GSI_ROUTING: { - struct kvm_irq_routing routing; - struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; - - r = -EFAULT; - if (copy_from_user(&routing, argp, sizeof(routing))) - goto out; - r = -EINVAL; - if (routing.nr >= KVM_MAX_IRQ_ROUTES) - goto out; - if (routing.flags) - goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) - goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; - r = kvm_set_irq_routing(kvm, entries, routing.nr, - routing.flags); - out_free_irq_routing: - vfree(entries); - break; - } -#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ - case KVM_CREATE_DEVICE: { - struct kvm_create_device cd; - - r = -EFAULT; - if (copy_from_user(&cd, argp, sizeof(cd))) - goto out; - - r = kvm_ioctl_create_device(kvm, &cd); - if (r) - goto out; - - r = -EFAULT; - if (copy_to_user(argp, &cd, sizeof(cd))) - goto out; - - r = 0; - break; - } default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); if (r == -ENOTTY) @@ -2541,11 +2376,8 @@ static long kvm_dev_ioctl_check_extension_generic(long arg) #ifdef CONFIG_HAVE_KVM_MSI case KVM_CAP_SIGNAL_MSI: #endif -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING - case KVM_CAP_IRQFD_RESAMPLE: -#endif return 1; -#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING +#ifdef KVM_CAP_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif |