diff options
Diffstat (limited to 'arch/s390/kvm')
| -rw-r--r-- | arch/s390/kvm/Kconfig | 58 | ||||
| -rw-r--r-- | arch/s390/kvm/Makefile | 17 | ||||
| -rw-r--r-- | arch/s390/kvm/diag.c | 255 | ||||
| -rw-r--r-- | arch/s390/kvm/gaccess.c | 915 | ||||
| -rw-r--r-- | arch/s390/kvm/gaccess.h | 338 | ||||
| -rw-r--r-- | arch/s390/kvm/guestdbg.c | 482 | ||||
| -rw-r--r-- | arch/s390/kvm/intercept.c | 379 | ||||
| -rw-r--r-- | arch/s390/kvm/interrupt.c | 2268 | ||||
| -rw-r--r-- | arch/s390/kvm/irq.h | 22 | ||||
| -rw-r--r-- | arch/s390/kvm/kvm-s390.c | 2628 | ||||
| -rw-r--r-- | arch/s390/kvm/kvm-s390.h | 290 | ||||
| -rw-r--r-- | arch/s390/kvm/priv.c | 1060 | ||||
| -rw-r--r-- | arch/s390/kvm/sigp.c | 493 | ||||
| -rw-r--r-- | arch/s390/kvm/trace-s390.h | 282 | ||||
| -rw-r--r-- | arch/s390/kvm/trace.h | 418 |
15 files changed, 9905 insertions, 0 deletions
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig new file mode 100644 index 000000000..5fce52cf0 --- /dev/null +++ b/arch/s390/kvm/Kconfig @@ -0,0 +1,58 @@ +# +# KVM configuration +# +source "virt/kvm/Kconfig" + +menuconfig VIRTUALIZATION + def_bool y + prompt "KVM" + ---help--- + Say Y here to get to see options for using your Linux host to run other + operating systems inside virtual machines (guests). + This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped and disabled. + +if VIRTUALIZATION + +config KVM + def_tristate y + prompt "Kernel-based Virtual Machine (KVM) support" + depends on HAVE_KVM + select PREEMPT_NOTIFIERS + select ANON_INODES + select HAVE_KVM_CPU_RELAX_INTERCEPT + select HAVE_KVM_EVENTFD + select KVM_ASYNC_PF + select KVM_ASYNC_PF_SYNC + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD + select HAVE_KVM_IRQ_ROUTING + select SRCU + ---help--- + Support hosting paravirtualized guest machines using the SIE + virtualization capability on the mainframe. This should work + on any 64bit machine. + + This module provides access to the hardware capabilities through + a character device node named /dev/kvm. + + To compile this as a module, choose M here: the module + will be called kvm. + + If unsure, say N. + +config KVM_S390_UCONTROL + bool "Userspace controlled virtual machines" + depends on KVM + ---help--- + Allow CAP_SYS_ADMIN users to create KVM virtual machines that are + controlled by userspace. + + If unsure, say N. + +# OK, it's a little counter-intuitive to do this, but it puts it neatly under +# the virtualization menu. +source drivers/vhost/Kconfig + +endif # VIRTUALIZATION diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile new file mode 100644 index 000000000..b3b553469 --- /dev/null +++ b/arch/s390/kvm/Makefile @@ -0,0 +1,17 @@ +# Makefile for kernel virtual machines on s390 +# +# Copyright IBM Corp. 2008 +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License (version 2 only) +# as published by the Free Software Foundation. + +KVM := ../../../virt/kvm +common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o + +ccflags-y := -Ivirt/kvm -Iarch/s390/kvm + +kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o +kvm-objs += diag.o gaccess.o guestdbg.o + +obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c new file mode 100644 index 000000000..fc7ec9584 --- /dev/null +++ b/arch/s390/kvm/diag.c @@ -0,0 +1,255 @@ +/* + * handling diagnose instructions + * + * Copyright IBM Corp. 2008, 2011 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <asm/pgalloc.h> +#include <asm/virtio-ccw.h> +#include "kvm-s390.h" +#include "trace.h" +#include "trace-s390.h" +#include "gaccess.h" + +static int diag_release_pages(struct kvm_vcpu *vcpu) +{ + unsigned long start, end; + unsigned long prefix = kvm_s390_get_prefix(vcpu); + + start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; + end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096; + + if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end + || start < 2 * PAGE_SIZE) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end); + vcpu->stat.diagnose_10++; + + /* + * We checked for start >= end above, so lets check for the + * fast path (no prefix swap page involved) + */ + if (end <= prefix || start >= prefix + 2 * PAGE_SIZE) { + gmap_discard(vcpu->arch.gmap, start, end); + } else { + /* + * This is slow path. gmap_discard will check for start + * so lets split this into before prefix, prefix, after + * prefix and let gmap_discard make some of these calls + * NOPs. + */ + gmap_discard(vcpu->arch.gmap, start, prefix); + if (start <= prefix) + gmap_discard(vcpu->arch.gmap, 0, 4096); + if (end > prefix + 4096) + gmap_discard(vcpu->arch.gmap, 4096, 8192); + gmap_discard(vcpu->arch.gmap, prefix + 2 * PAGE_SIZE, end); + } + return 0; +} + +static int __diag_page_ref_service(struct kvm_vcpu *vcpu) +{ + struct prs_parm { + u16 code; + u16 subcode; + u16 parm_len; + u16 parm_version; + u64 token_addr; + u64 select_mask; + u64 compare_mask; + u64 zarch; + }; + struct prs_parm parm; + int rc; + u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4; + u16 ry = (vcpu->arch.sie_block->ipa & 0x0f); + + if (vcpu->run->s.regs.gprs[rx] & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + switch (parm.subcode) { + case 0: /* TOKEN */ + if (vcpu->arch.pfault_token != KVM_S390_PFAULT_TOKEN_INVALID) { + /* + * If the pagefault handshake is already activated, + * the token must not be changed. We have to return + * decimal 8 instead, as mandated in SC24-6084. + */ + vcpu->run->s.regs.gprs[ry] = 8; + return 0; + } + + if ((parm.compare_mask & parm.select_mask) != parm.compare_mask || + parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + if (kvm_is_error_gpa(vcpu->kvm, parm.token_addr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + vcpu->arch.pfault_token = parm.token_addr; + vcpu->arch.pfault_select = parm.select_mask; + vcpu->arch.pfault_compare = parm.compare_mask; + vcpu->run->s.regs.gprs[ry] = 0; + rc = 0; + break; + case 1: /* + * CANCEL + * Specification allows to let already pending tokens survive + * the cancel, therefore to reduce code complexity, we assume + * all outstanding tokens are already pending. + */ + if (parm.token_addr || parm.select_mask || + parm.compare_mask || parm.zarch) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + vcpu->run->s.regs.gprs[ry] = 0; + /* + * If the pfault handling was not established or is already + * canceled SC24-6084 requests to return decimal 4. + */ + if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) + vcpu->run->s.regs.gprs[ry] = 4; + else + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + + rc = 0; + break; + default: + rc = -EOPNOTSUPP; + break; + } + + return rc; +} + +static int __diag_time_slice_end(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 5, "%s", "diag time slice end"); + vcpu->stat.diagnose_44++; + kvm_vcpu_on_spin(vcpu); + return 0; +} + +static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *tcpu; + int tid; + int i; + + tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; + vcpu->stat.diagnose_9c++; + VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid); + + if (tid == vcpu->vcpu_id) + return 0; + + kvm_for_each_vcpu(i, tcpu, kvm) + if (tcpu->vcpu_id == tid) { + kvm_vcpu_yield_to(tcpu); + break; + } + + return 0; +} + +static int __diag_ipl_functions(struct kvm_vcpu *vcpu) +{ + unsigned int reg = vcpu->arch.sie_block->ipa & 0xf; + unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff; + + VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode); + switch (subcode) { + case 3: + vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR; + break; + case 4: + vcpu->run->s390_reset_flags = 0; + break; + default: + return -EOPNOTSUPP; + } + + if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) + kvm_s390_vcpu_stop(vcpu); + vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM; + vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL; + vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT; + vcpu->run->exit_reason = KVM_EXIT_S390_RESET; + VCPU_EVENT(vcpu, 3, "requesting userspace resets %llx", + vcpu->run->s390_reset_flags); + trace_kvm_s390_request_resets(vcpu->run->s390_reset_flags); + return -EREMOTE; +} + +static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) +{ + int ret; + + /* No virtio-ccw notification? Get out quickly. */ + if (!vcpu->kvm->arch.css_support || + (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY)) + return -EOPNOTSUPP; + + /* + * The layout is as follows: + * - gpr 2 contains the subchannel id (passed as addr) + * - gpr 3 contains the virtqueue index (passed as datamatch) + * - gpr 4 contains the index on the bus (optionally) + */ + ret = kvm_io_bus_write_cookie(vcpu, KVM_VIRTIO_CCW_NOTIFY_BUS, + vcpu->run->s.regs.gprs[2] & 0xffffffff, + 8, &vcpu->run->s.regs.gprs[3], + vcpu->run->s.regs.gprs[4]); + + /* + * Return cookie in gpr 2, but don't overwrite the register if the + * diagnose will be handled by userspace. + */ + if (ret != -EOPNOTSUPP) + vcpu->run->s.regs.gprs[2] = ret; + /* kvm_io_bus_write_cookie returns -EOPNOTSUPP if it found no match. */ + return ret < 0 ? ret : 0; +} + +int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) +{ + int code = kvm_s390_get_base_disp_rs(vcpu, NULL) & 0xffff; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + trace_kvm_s390_handle_diag(vcpu, code); + switch (code) { + case 0x10: + return diag_release_pages(vcpu); + case 0x44: + return __diag_time_slice_end(vcpu); + case 0x9c: + return __diag_time_slice_end_directed(vcpu); + case 0x258: + return __diag_page_ref_service(vcpu); + case 0x308: + return __diag_ipl_functions(vcpu); + case 0x500: + return __diag_virtio_hypercall(vcpu); + default: + return -EOPNOTSUPP; + } +} diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c new file mode 100644 index 000000000..a7559f720 --- /dev/null +++ b/arch/s390/kvm/gaccess.c @@ -0,0 +1,915 @@ +/* + * guest access functions + * + * Copyright IBM Corp. 2014 + * + */ + +#include <linux/vmalloc.h> +#include <linux/err.h> +#include <asm/pgtable.h> +#include "kvm-s390.h" +#include "gaccess.h" +#include <asm/switch_to.h> + +union asce { + unsigned long val; + struct { + unsigned long origin : 52; /* Region- or Segment-Table Origin */ + unsigned long : 2; + unsigned long g : 1; /* Subspace Group Control */ + unsigned long p : 1; /* Private Space Control */ + unsigned long s : 1; /* Storage-Alteration-Event Control */ + unsigned long x : 1; /* Space-Switch-Event Control */ + unsigned long r : 1; /* Real-Space Control */ + unsigned long : 1; + unsigned long dt : 2; /* Designation-Type Control */ + unsigned long tl : 2; /* Region- or Segment-Table Length */ + }; +}; + +enum { + ASCE_TYPE_SEGMENT = 0, + ASCE_TYPE_REGION3 = 1, + ASCE_TYPE_REGION2 = 2, + ASCE_TYPE_REGION1 = 3 +}; + +union region1_table_entry { + unsigned long val; + struct { + unsigned long rto: 52;/* Region-Table Origin */ + unsigned long : 2; + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 1; + unsigned long tf : 2; /* Region-Second-Table Offset */ + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long : 1; + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long tl : 2; /* Region-Second-Table Length */ + }; +}; + +union region2_table_entry { + unsigned long val; + struct { + unsigned long rto: 52;/* Region-Table Origin */ + unsigned long : 2; + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 1; + unsigned long tf : 2; /* Region-Third-Table Offset */ + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long : 1; + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long tl : 2; /* Region-Third-Table Length */ + }; +}; + +struct region3_table_entry_fc0 { + unsigned long sto: 52;/* Segment-Table Origin */ + unsigned long : 1; + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 1; + unsigned long tf : 2; /* Segment-Table Offset */ + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long cr : 1; /* Common-Region Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long tl : 2; /* Segment-Table Length */ +}; + +struct region3_table_entry_fc1 { + unsigned long rfaa : 33; /* Region-Frame Absolute Address */ + unsigned long : 14; + unsigned long av : 1; /* ACCF-Validity Control */ + unsigned long acc: 4; /* Access-Control Bits */ + unsigned long f : 1; /* Fetch-Protection Bit */ + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long co : 1; /* Change-Recording Override */ + unsigned long : 2; + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long cr : 1; /* Common-Region Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; +}; + +union region3_table_entry { + unsigned long val; + struct region3_table_entry_fc0 fc0; + struct region3_table_entry_fc1 fc1; + struct { + unsigned long : 53; + unsigned long fc : 1; /* Format-Control */ + unsigned long : 4; + unsigned long i : 1; /* Region-Invalid Bit */ + unsigned long cr : 1; /* Common-Region Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; + }; +}; + +struct segment_entry_fc0 { + unsigned long pto: 53;/* Page-Table Origin */ + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long : 3; + unsigned long i : 1; /* Segment-Invalid Bit */ + unsigned long cs : 1; /* Common-Segment Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; +}; + +struct segment_entry_fc1 { + unsigned long sfaa : 44; /* Segment-Frame Absolute Address */ + unsigned long : 3; + unsigned long av : 1; /* ACCF-Validity Control */ + unsigned long acc: 4; /* Access-Control Bits */ + unsigned long f : 1; /* Fetch-Protection Bit */ + unsigned long fc : 1; /* Format-Control */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long co : 1; /* Change-Recording Override */ + unsigned long : 2; + unsigned long i : 1; /* Segment-Invalid Bit */ + unsigned long cs : 1; /* Common-Segment Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; +}; + +union segment_table_entry { + unsigned long val; + struct segment_entry_fc0 fc0; + struct segment_entry_fc1 fc1; + struct { + unsigned long : 53; + unsigned long fc : 1; /* Format-Control */ + unsigned long : 4; + unsigned long i : 1; /* Segment-Invalid Bit */ + unsigned long cs : 1; /* Common-Segment Bit */ + unsigned long tt : 2; /* Table-Type Bits */ + unsigned long : 2; + }; +}; + +enum { + TABLE_TYPE_SEGMENT = 0, + TABLE_TYPE_REGION3 = 1, + TABLE_TYPE_REGION2 = 2, + TABLE_TYPE_REGION1 = 3 +}; + +union page_table_entry { + unsigned long val; + struct { + unsigned long pfra : 52; /* Page-Frame Real Address */ + unsigned long z : 1; /* Zero Bit */ + unsigned long i : 1; /* Page-Invalid Bit */ + unsigned long p : 1; /* DAT-Protection Bit */ + unsigned long co : 1; /* Change-Recording Override */ + unsigned long : 8; + }; +}; + +/* + * vaddress union in order to easily decode a virtual address into its + * region first index, region second index etc. parts. + */ +union vaddress { + unsigned long addr; + struct { + unsigned long rfx : 11; + unsigned long rsx : 11; + unsigned long rtx : 11; + unsigned long sx : 11; + unsigned long px : 8; + unsigned long bx : 12; + }; + struct { + unsigned long rfx01 : 2; + unsigned long : 9; + unsigned long rsx01 : 2; + unsigned long : 9; + unsigned long rtx01 : 2; + unsigned long : 9; + unsigned long sx01 : 2; + unsigned long : 29; + }; +}; + +/* + * raddress union which will contain the result (real or absolute address) + * after a page table walk. The rfaa, sfaa and pfra members are used to + * simply assign them the value of a region, segment or page table entry. + */ +union raddress { + unsigned long addr; + unsigned long rfaa : 33; /* Region-Frame Absolute Address */ + unsigned long sfaa : 44; /* Segment-Frame Absolute Address */ + unsigned long pfra : 52; /* Page-Frame Real Address */ +}; + +union alet { + u32 val; + struct { + u32 reserved : 7; + u32 p : 1; + u32 alesn : 8; + u32 alen : 16; + }; +}; + +union ald { + u32 val; + struct { + u32 : 1; + u32 alo : 24; + u32 all : 7; + }; +}; + +struct ale { + unsigned long i : 1; /* ALEN-Invalid Bit */ + unsigned long : 5; + unsigned long fo : 1; /* Fetch-Only Bit */ + unsigned long p : 1; /* Private Bit */ + unsigned long alesn : 8; /* Access-List-Entry Sequence Number */ + unsigned long aleax : 16; /* Access-List-Entry Authorization Index */ + unsigned long : 32; + unsigned long : 1; + unsigned long asteo : 25; /* ASN-Second-Table-Entry Origin */ + unsigned long : 6; + unsigned long astesn : 32; /* ASTE Sequence Number */ +} __packed; + +struct aste { + unsigned long i : 1; /* ASX-Invalid Bit */ + unsigned long ato : 29; /* Authority-Table Origin */ + unsigned long : 1; + unsigned long b : 1; /* Base-Space Bit */ + unsigned long ax : 16; /* Authorization Index */ + unsigned long atl : 12; /* Authority-Table Length */ + unsigned long : 2; + unsigned long ca : 1; /* Controlled-ASN Bit */ + unsigned long ra : 1; /* Reusable-ASN Bit */ + unsigned long asce : 64; /* Address-Space-Control Element */ + unsigned long ald : 32; + unsigned long astesn : 32; + /* .. more fields there */ +} __packed; + +int ipte_lock_held(struct kvm_vcpu *vcpu) +{ + union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control; + + if (vcpu->arch.sie_block->eca & 1) + return ic->kh != 0; + return vcpu->kvm->arch.ipte_lock_count != 0; +} + +static void ipte_lock_simple(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + mutex_lock(&vcpu->kvm->arch.ipte_mutex); + vcpu->kvm->arch.ipte_lock_count++; + if (vcpu->kvm->arch.ipte_lock_count > 1) + goto out; + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + old = READ_ONCE(*ic); + while (old.k) { + cond_resched(); + old = READ_ONCE(*ic); + } + new = old; + new.k = 1; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); +out: + mutex_unlock(&vcpu->kvm->arch.ipte_mutex); +} + +static void ipte_unlock_simple(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + mutex_lock(&vcpu->kvm->arch.ipte_mutex); + vcpu->kvm->arch.ipte_lock_count--; + if (vcpu->kvm->arch.ipte_lock_count) + goto out; + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + old = READ_ONCE(*ic); + new = old; + new.k = 0; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + wake_up(&vcpu->kvm->arch.ipte_wq); +out: + mutex_unlock(&vcpu->kvm->arch.ipte_mutex); +} + +static void ipte_lock_siif(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + old = READ_ONCE(*ic); + while (old.kg) { + cond_resched(); + old = READ_ONCE(*ic); + } + new = old; + new.k = 1; + new.kh++; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); +} + +static void ipte_unlock_siif(struct kvm_vcpu *vcpu) +{ + union ipte_control old, new, *ic; + + ic = &vcpu->kvm->arch.sca->ipte_control; + do { + old = READ_ONCE(*ic); + new = old; + new.kh--; + if (!new.kh) + new.k = 0; + } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + if (!new.kh) + wake_up(&vcpu->kvm->arch.ipte_wq); +} + +void ipte_lock(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->eca & 1) + ipte_lock_siif(vcpu); + else + ipte_lock_simple(vcpu); +} + +void ipte_unlock(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->eca & 1) + ipte_unlock_siif(vcpu); + else + ipte_unlock_simple(vcpu); +} + +static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, + int write) +{ + union alet alet; + struct ale ale; + struct aste aste; + unsigned long ald_addr, authority_table_addr; + union ald ald; + int eax, rc; + u8 authority_table; + + if (ar >= NUM_ACRS) + return -EINVAL; + + save_access_regs(vcpu->run->s.regs.acrs); + alet.val = vcpu->run->s.regs.acrs[ar]; + + if (ar == 0 || alet.val == 0) { + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; + } else if (alet.val == 1) { + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; + } + + if (alet.reserved) + return PGM_ALET_SPECIFICATION; + + if (alet.p) + ald_addr = vcpu->arch.sie_block->gcr[5]; + else + ald_addr = vcpu->arch.sie_block->gcr[2]; + ald_addr &= 0x7fffffc0; + + rc = read_guest_real(vcpu, ald_addr + 16, &ald.val, sizeof(union ald)); + if (rc) + return rc; + + if (alet.alen / 8 > ald.all) + return PGM_ALEN_TRANSLATION; + + if (0x7fffffff - ald.alo * 128 < alet.alen * 16) + return PGM_ADDRESSING; + + rc = read_guest_real(vcpu, ald.alo * 128 + alet.alen * 16, &ale, + sizeof(struct ale)); + if (rc) + return rc; + + if (ale.i == 1) + return PGM_ALEN_TRANSLATION; + if (ale.alesn != alet.alesn) + return PGM_ALE_SEQUENCE; + + rc = read_guest_real(vcpu, ale.asteo * 64, &aste, sizeof(struct aste)); + if (rc) + return rc; + + if (aste.i) + return PGM_ASTE_VALIDITY; + if (aste.astesn != ale.astesn) + return PGM_ASTE_SEQUENCE; + + if (ale.p == 1) { + eax = (vcpu->arch.sie_block->gcr[8] >> 16) & 0xffff; + if (ale.aleax != eax) { + if (eax / 16 > aste.atl) + return PGM_EXTENDED_AUTHORITY; + + authority_table_addr = aste.ato * 4 + eax / 4; + + rc = read_guest_real(vcpu, authority_table_addr, + &authority_table, + sizeof(u8)); + if (rc) + return rc; + + if ((authority_table & (0x40 >> ((eax & 3) * 2))) == 0) + return PGM_EXTENDED_AUTHORITY; + } + } + + if (ale.fo == 1 && write) + return PGM_PROTECTION; + + asce->val = aste.asce; + return 0; +} + +struct trans_exc_code_bits { + unsigned long addr : 52; /* Translation-exception Address */ + unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ + unsigned long : 6; + unsigned long b60 : 1; + unsigned long b61 : 1; + unsigned long as : 2; /* ASCE Identifier */ +}; + +enum { + FSI_UNKNOWN = 0, /* Unknown wether fetch or store */ + FSI_STORE = 1, /* Exception was due to store operation */ + FSI_FETCH = 2 /* Exception was due to fetch operation */ +}; + +static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, + ar_t ar, int write) +{ + int rc; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + struct trans_exc_code_bits *tec_bits; + + memset(pgm, 0, sizeof(*pgm)); + tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + tec_bits->fsi = write ? FSI_STORE : FSI_FETCH; + tec_bits->as = psw_bits(*psw).as; + + if (!psw_bits(*psw).t) { + asce->val = 0; + asce->r = 1; + return 0; + } + + switch (psw_bits(vcpu->arch.sie_block->gpsw).as) { + case PSW_AS_PRIMARY: + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; + case PSW_AS_SECONDARY: + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; + case PSW_AS_HOME: + asce->val = vcpu->arch.sie_block->gcr[13]; + return 0; + case PSW_AS_ACCREG: + rc = ar_translation(vcpu, asce, ar, write); + switch (rc) { + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_ASTE_SEQUENCE: + case PGM_EXTENDED_AUTHORITY: + vcpu->arch.pgm.exc_access_id = ar; + break; + case PGM_PROTECTION: + tec_bits->b60 = 1; + tec_bits->b61 = 1; + break; + } + if (rc > 0) + pgm->code = rc; + return rc; + } + return 0; +} + +static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) +{ + return kvm_read_guest(kvm, gpa, val, sizeof(*val)); +} + +/** + * guest_translate - translate a guest virtual into a guest absolute address + * @vcpu: virtual cpu + * @gva: guest virtual address + * @gpa: points to where guest physical (absolute) address should be stored + * @asce: effective asce + * @write: indicates if access is a write access + * + * Translate a guest virtual address into a guest absolute address by means + * of dynamic address translation as specified by the architecture. + * If the resulting absolute address is not available in the configuration + * an addressing exception is indicated and @gpa will not be changed. + * + * Returns: - zero on success; @gpa contains the resulting absolute address + * - a negative value if guest access failed due to e.g. broken + * guest mapping + * - a positve value if an access exception happened. In this case + * the returned value is the program interruption code as defined + * by the architecture + */ +static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, + unsigned long *gpa, const union asce asce, + int write) +{ + union vaddress vaddr = {.addr = gva}; + union raddress raddr = {.addr = gva}; + union page_table_entry pte; + int dat_protection = 0; + union ctlreg0 ctlreg0; + unsigned long ptr; + int edat1, edat2; + + ctlreg0.val = vcpu->arch.sie_block->gcr[0]; + edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8); + edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78); + if (asce.r) + goto real_address; + ptr = asce.origin * 4096; + switch (asce.dt) { + case ASCE_TYPE_REGION1: + if (vaddr.rfx01 > asce.tl) + return PGM_REGION_FIRST_TRANS; + ptr += vaddr.rfx * 8; + break; + case ASCE_TYPE_REGION2: + if (vaddr.rfx) + return PGM_ASCE_TYPE; + if (vaddr.rsx01 > asce.tl) + return PGM_REGION_SECOND_TRANS; + ptr += vaddr.rsx * 8; + break; + case ASCE_TYPE_REGION3: + if (vaddr.rfx || vaddr.rsx) + return PGM_ASCE_TYPE; + if (vaddr.rtx01 > asce.tl) + return PGM_REGION_THIRD_TRANS; + ptr += vaddr.rtx * 8; + break; + case ASCE_TYPE_SEGMENT: + if (vaddr.rfx || vaddr.rsx || vaddr.rtx) + return PGM_ASCE_TYPE; + if (vaddr.sx01 > asce.tl) + return PGM_SEGMENT_TRANSLATION; + ptr += vaddr.sx * 8; + break; + } + switch (asce.dt) { + case ASCE_TYPE_REGION1: { + union region1_table_entry rfte; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &rfte.val)) + return -EFAULT; + if (rfte.i) + return PGM_REGION_FIRST_TRANS; + if (rfte.tt != TABLE_TYPE_REGION1) + return PGM_TRANSLATION_SPEC; + if (vaddr.rsx01 < rfte.tf || vaddr.rsx01 > rfte.tl) + return PGM_REGION_SECOND_TRANS; + if (edat1) + dat_protection |= rfte.p; + ptr = rfte.rto * 4096 + vaddr.rsx * 8; + } + /* fallthrough */ + case ASCE_TYPE_REGION2: { + union region2_table_entry rste; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &rste.val)) + return -EFAULT; + if (rste.i) + return PGM_REGION_SECOND_TRANS; + if (rste.tt != TABLE_TYPE_REGION2) + return PGM_TRANSLATION_SPEC; + if (vaddr.rtx01 < rste.tf || vaddr.rtx01 > rste.tl) + return PGM_REGION_THIRD_TRANS; + if (edat1) + dat_protection |= rste.p; + ptr = rste.rto * 4096 + vaddr.rtx * 8; + } + /* fallthrough */ + case ASCE_TYPE_REGION3: { + union region3_table_entry rtte; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &rtte.val)) + return -EFAULT; + if (rtte.i) + return PGM_REGION_THIRD_TRANS; + if (rtte.tt != TABLE_TYPE_REGION3) + return PGM_TRANSLATION_SPEC; + if (rtte.cr && asce.p && edat2) + return PGM_TRANSLATION_SPEC; + if (rtte.fc && edat2) { + dat_protection |= rtte.fc1.p; + raddr.rfaa = rtte.fc1.rfaa; + goto absolute_address; + } + if (vaddr.sx01 < rtte.fc0.tf) + return PGM_SEGMENT_TRANSLATION; + if (vaddr.sx01 > rtte.fc0.tl) + return PGM_SEGMENT_TRANSLATION; + if (edat1) + dat_protection |= rtte.fc0.p; + ptr = rtte.fc0.sto * 4096 + vaddr.sx * 8; + } + /* fallthrough */ + case ASCE_TYPE_SEGMENT: { + union segment_table_entry ste; + + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &ste.val)) + return -EFAULT; + if (ste.i) + return PGM_SEGMENT_TRANSLATION; + if (ste.tt != TABLE_TYPE_SEGMENT) + return PGM_TRANSLATION_SPEC; + if (ste.cs && asce.p) + return PGM_TRANSLATION_SPEC; + if (ste.fc && edat1) { + dat_protection |= ste.fc1.p; + raddr.sfaa = ste.fc1.sfaa; + goto absolute_address; + } + dat_protection |= ste.fc0.p; + ptr = ste.fc0.pto * 2048 + vaddr.px * 8; + } + } + if (kvm_is_error_gpa(vcpu->kvm, ptr)) + return PGM_ADDRESSING; + if (deref_table(vcpu->kvm, ptr, &pte.val)) + return -EFAULT; + if (pte.i) + return PGM_PAGE_TRANSLATION; + if (pte.z) + return PGM_TRANSLATION_SPEC; + if (pte.co && !edat1) + return PGM_TRANSLATION_SPEC; + dat_protection |= pte.p; + raddr.pfra = pte.pfra; +real_address: + raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr); +absolute_address: + if (write && dat_protection) + return PGM_PROTECTION; + if (kvm_is_error_gpa(vcpu->kvm, raddr.addr)) + return PGM_ADDRESSING; + *gpa = raddr.addr; + return 0; +} + +static inline int is_low_address(unsigned long ga) +{ + /* Check for address ranges 0..511 and 4096..4607 */ + return (ga & ~0x11fful) == 0; +} + +static int low_address_protection_enabled(struct kvm_vcpu *vcpu, + const union asce asce) +{ + union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + + if (!ctlreg0.lap) + return 0; + if (psw_bits(*psw).t && asce.p) + return 0; + return 1; +} + +static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, + unsigned long *pages, unsigned long nr_pages, + const union asce asce, int write) +{ + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct trans_exc_code_bits *tec_bits; + int lap_enabled, rc; + + tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + lap_enabled = low_address_protection_enabled(vcpu, asce); + while (nr_pages) { + ga = kvm_s390_logical_to_effective(vcpu, ga); + tec_bits->addr = ga >> PAGE_SHIFT; + if (write && lap_enabled && is_low_address(ga)) { + pgm->code = PGM_PROTECTION; + return pgm->code; + } + ga &= PAGE_MASK; + if (psw_bits(*psw).t) { + rc = guest_translate(vcpu, ga, pages, asce, write); + if (rc < 0) + return rc; + if (rc == PGM_PROTECTION) + tec_bits->b61 = 1; + if (rc) + pgm->code = rc; + } else { + *pages = kvm_s390_real_to_abs(vcpu, ga); + if (kvm_is_error_gpa(vcpu->kvm, *pages)) + pgm->code = PGM_ADDRESSING; + } + if (pgm->code) + return pgm->code; + ga += PAGE_SIZE; + pages++; + nr_pages--; + } + return 0; +} + +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, + unsigned long len, int write) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + unsigned long _len, nr_pages, gpa, idx; + unsigned long pages_array[2]; + unsigned long *pages; + int need_ipte_lock; + union asce asce; + int rc; + + if (!len) + return 0; + rc = get_vcpu_asce(vcpu, &asce, ar, write); + if (rc) + return rc; + nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1; + pages = pages_array; + if (nr_pages > ARRAY_SIZE(pages_array)) + pages = vmalloc(nr_pages * sizeof(unsigned long)); + if (!pages) + return -ENOMEM; + need_ipte_lock = psw_bits(*psw).t && !asce.r; + if (need_ipte_lock) + ipte_lock(vcpu); + rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write); + for (idx = 0; idx < nr_pages && !rc; idx++) { + gpa = *(pages + idx) + (ga & ~PAGE_MASK); + _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); + if (write) + rc = kvm_write_guest(vcpu->kvm, gpa, data, _len); + else + rc = kvm_read_guest(vcpu->kvm, gpa, data, _len); + len -= _len; + ga += _len; + data += _len; + } + if (need_ipte_lock) + ipte_unlock(vcpu); + if (nr_pages > ARRAY_SIZE(pages_array)) + vfree(pages); + return rc; +} + +int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, + void *data, unsigned long len, int write) +{ + unsigned long _len, gpa; + int rc = 0; + + while (len && !rc) { + gpa = kvm_s390_real_to_abs(vcpu, gra); + _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); + if (write) + rc = write_guest_abs(vcpu, gpa, data, _len); + else + rc = read_guest_abs(vcpu, gpa, data, _len); + len -= _len; + gra += _len; + data += _len; + } + return rc; +} + +/** + * guest_translate_address - translate guest logical into guest absolute address + * + * Parameter semantics are the same as the ones from guest_translate. + * The memory contents at the guest address are not changed. + * + * Note: The IPTE lock is not taken during this function, so the caller + * has to take care of this. + */ +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long *gpa, int write) +{ + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct trans_exc_code_bits *tec; + union asce asce; + int rc; + + gva = kvm_s390_logical_to_effective(vcpu, gva); + tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + rc = get_vcpu_asce(vcpu, &asce, ar, write); + tec->addr = gva >> PAGE_SHIFT; + if (rc) + return rc; + if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) { + if (write) { + rc = pgm->code = PGM_PROTECTION; + return rc; + } + } + + if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */ + rc = guest_translate(vcpu, gva, gpa, asce, write); + if (rc > 0) { + if (rc == PGM_PROTECTION) + tec->b61 = 1; + pgm->code = rc; + } + } else { + rc = 0; + *gpa = kvm_s390_real_to_abs(vcpu, gva); + if (kvm_is_error_gpa(vcpu->kvm, *gpa)) + rc = pgm->code = PGM_ADDRESSING; + } + + return rc; +} + +/** + * check_gva_range - test a range of guest virtual addresses for accessibility + */ +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write) +{ + unsigned long gpa; + unsigned long currlen; + int rc = 0; + + ipte_lock(vcpu); + while (length > 0 && !rc) { + currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE)); + rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write); + gva += currlen; + length -= currlen; + } + ipte_unlock(vcpu); + + return rc; +} + +/** + * kvm_s390_check_low_addr_prot_real - check for low-address protection + * @gra: Guest real address + * + * Checks whether an address is subject to low-address protection and set + * up vcpu->arch.pgm accordingly if necessary. + * + * Return: 0 if no protection exception, or PGM_PROTECTION if protected. + */ +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra) +{ + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct trans_exc_code_bits *tec_bits; + union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; + + if (!ctlreg0.lap || !is_low_address(gra)) + return 0; + + memset(pgm, 0, sizeof(*pgm)); + tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + tec_bits->fsi = FSI_STORE; + tec_bits->as = psw_bits(*psw).as; + tec_bits->addr = gra >> PAGE_SHIFT; + pgm->code = PGM_PROTECTION; + + return pgm->code; +} diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h new file mode 100644 index 000000000..ef03726cc --- /dev/null +++ b/arch/s390/kvm/gaccess.h @@ -0,0 +1,338 @@ +/* + * access guest memory + * + * Copyright IBM Corp. 2008, 2014 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + */ + +#ifndef __KVM_S390_GACCESS_H +#define __KVM_S390_GACCESS_H + +#include <linux/compiler.h> +#include <linux/kvm_host.h> +#include <linux/uaccess.h> +#include <linux/ptrace.h> +#include "kvm-s390.h" + +/** + * kvm_s390_real_to_abs - convert guest real address to guest absolute address + * @vcpu - guest virtual cpu + * @gra - guest real address + * + * Returns the guest absolute address that corresponds to the passed guest real + * address @gra of a virtual guest cpu by applying its prefix. + */ +static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu, + unsigned long gra) +{ + unsigned long prefix = kvm_s390_get_prefix(vcpu); + + if (gra < 2 * PAGE_SIZE) + gra += prefix; + else if (gra >= prefix && gra < prefix + 2 * PAGE_SIZE) + gra -= prefix; + return gra; +} + +/** + * kvm_s390_logical_to_effective - convert guest logical to effective address + * @vcpu: guest virtual cpu + * @ga: guest logical address + * + * Convert a guest vcpu logical address to a guest vcpu effective address by + * applying the rules of the vcpu's addressing mode defined by PSW bits 31 + * and 32 (extendended/basic addressing mode). + * + * Depending on the vcpu's addressing mode the upper 40 bits (24 bit addressing + * mode), 33 bits (31 bit addressing mode) or no bits (64 bit addressing mode) + * of @ga will be zeroed and the remaining bits will be returned. + */ +static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu, + unsigned long ga) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + + if (psw_bits(*psw).eaba == PSW_AMODE_64BIT) + return ga; + if (psw_bits(*psw).eaba == PSW_AMODE_31BIT) + return ga & ((1UL << 31) - 1); + return ga & ((1UL << 24) - 1); +} + +/* + * put_guest_lc, read_guest_lc and write_guest_lc are guest access functions + * which shall only be used to access the lowcore of a vcpu. + * These functions should be used for e.g. interrupt handlers where no + * guest memory access protection facilities, like key or low address + * protection, are applicable. + * At a later point guest vcpu lowcore access should happen via pinned + * prefix pages, so that these pages can be accessed directly via the + * kernel mapping. All of these *_lc functions can be removed then. + */ + +/** + * put_guest_lc - write a simple variable to a guest vcpu's lowcore + * @vcpu: virtual cpu + * @x: value to copy to guest + * @gra: vcpu's destination guest real address + * + * Copies a simple value from kernel space to a guest vcpu's lowcore. + * The size of the variable may be 1, 2, 4 or 8 bytes. The destination + * must be located in the vcpu's lowcore. Otherwise the result is undefined. + * + * Returns zero on success or -EFAULT on error. + * + * Note: an error indicates that either the kernel is out of memory or + * the guest memory mapping is broken. In any case the best solution + * would be to terminate the guest. + * It is wrong to inject a guest exception. + */ +#define put_guest_lc(vcpu, x, gra) \ +({ \ + struct kvm_vcpu *__vcpu = (vcpu); \ + __typeof__(*(gra)) __x = (x); \ + unsigned long __gpa; \ + \ + __gpa = (unsigned long)(gra); \ + __gpa += kvm_s390_get_prefix(__vcpu); \ + kvm_write_guest(__vcpu->kvm, __gpa, &__x, sizeof(__x)); \ +}) + +/** + * write_guest_lc - copy data from kernel space to guest vcpu's lowcore + * @vcpu: virtual cpu + * @gra: vcpu's source guest real address + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy data from kernel space to guest vcpu's lowcore. The entire range must + * be located within the vcpu's lowcore, otherwise the result is undefined. + * + * Returns zero on success or -EFAULT on error. + * + * Note: an error indicates that either the kernel is out of memory or + * the guest memory mapping is broken. In any case the best solution + * would be to terminate the guest. + * It is wrong to inject a guest exception. + */ +static inline __must_check +int write_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) +{ + unsigned long gpa = gra + kvm_s390_get_prefix(vcpu); + + return kvm_write_guest(vcpu->kvm, gpa, data, len); +} + +/** + * read_guest_lc - copy data from guest vcpu's lowcore to kernel space + * @vcpu: virtual cpu + * @gra: vcpu's source guest real address + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy data from guest vcpu's lowcore to kernel space. The entire range must + * be located within the vcpu's lowcore, otherwise the result is undefined. + * + * Returns zero on success or -EFAULT on error. + * + * Note: an error indicates that either the kernel is out of memory or + * the guest memory mapping is broken. In any case the best solution + * would be to terminate the guest. + * It is wrong to inject a guest exception. + */ +static inline __must_check +int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) +{ + unsigned long gpa = gra + kvm_s390_get_prefix(vcpu); + + return kvm_read_guest(vcpu->kvm, gpa, data, len); +} + +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, + ar_t ar, unsigned long *gpa, int write); +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write); + +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, + unsigned long len, int write); + +int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, + void *data, unsigned long len, int write); + +/** + * write_guest - copy data from kernel space to guest space + * @vcpu: virtual cpu + * @ga: guest address + * @ar: access register + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @data (kernel space) to @ga (guest address). + * In order to copy data to guest space the PSW of the vcpu is inspected: + * If DAT is off data will be copied to guest real or absolute memory. + * If DAT is on data will be copied to the address space as specified by + * the address space bits of the PSW: + * Primary, secondary, home space or access register mode. + * The addressing mode of the PSW is also inspected, so that address wrap + * around is taken into account for 24-, 31- and 64-bit addressing mode, + * if the to be copied data crosses page boundaries in guest address space. + * In addition also low address and DAT protection are inspected before + * copying any data (key protection is currently not implemented). + * + * This function modifies the 'struct kvm_s390_pgm_info pgm' member of @vcpu. + * In case of an access exception (e.g. protection exception) pgm will contain + * all data necessary so that a subsequent call to 'kvm_s390_inject_prog_vcpu()' + * will inject a correct exception into the guest. + * If no access exception happened, the contents of pgm are undefined when + * this function returns. + * + * Returns: - zero on success + * - a negative value if e.g. the guest mapping is broken or in + * case of out-of-memory. In this case the contents of pgm are + * undefined. Also parts of @data may have been copied to guest + * space. + * - a positive value if an access exception happened. In this case + * the returned value is the program interruption code and the + * contents of pgm may be used to inject an exception into the + * guest. No data has been copied to guest space. + * + * Note: in case an access exception is recognized no data has been copied to + * guest space (this is also true, if the to be copied data would cross + * one or more page boundaries in guest space). + * Therefore this function may be used for nullifying and suppressing + * instruction emulation. + * It may also be used for terminating instructions, if it is undefined + * if data has been changed in guest space in case of an exception. + */ +static inline __must_check +int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, + unsigned long len) +{ + return access_guest(vcpu, ga, ar, data, len, 1); +} + +/** + * read_guest - copy data from guest space to kernel space + * @vcpu: virtual cpu + * @ga: guest address + * @ar: access register + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @ga (guest address) to @data (kernel space). + * + * The behaviour of read_guest is identical to write_guest, except that + * data will be copied from guest space to kernel space. + */ +static inline __must_check +int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, + unsigned long len) +{ + return access_guest(vcpu, ga, ar, data, len, 0); +} + +/** + * write_guest_abs - copy data from kernel space to guest space absolute + * @vcpu: virtual cpu + * @gpa: guest physical (absolute) address + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @data (kernel space) to @gpa (guest absolute address). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest low address and key protection are not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to guest memory. + */ +static inline __must_check +int write_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, + unsigned long len) +{ + return kvm_write_guest(vcpu->kvm, gpa, data, len); +} + +/** + * read_guest_abs - copy data from guest space absolute to kernel space + * @vcpu: virtual cpu + * @gpa: guest physical (absolute) address + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @gpa (guest absolute address) to @data (kernel space). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest key protection is not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to kernel space. + */ +static inline __must_check +int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, + unsigned long len) +{ + return kvm_read_guest(vcpu->kvm, gpa, data, len); +} + +/** + * write_guest_real - copy data from kernel space to guest space real + * @vcpu: virtual cpu + * @gra: guest real address + * @data: source address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @data (kernel space) to @gra (guest real address). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest low address and key protection are not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to guest memory. + */ +static inline __must_check +int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) +{ + return access_guest_real(vcpu, gra, data, len, 1); +} + +/** + * read_guest_real - copy data from guest space real to kernel space + * @vcpu: virtual cpu + * @gra: guest real address + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from @gra (guest real address) to @data (kernel space). + * It is up to the caller to ensure that the entire guest memory range is + * valid memory before calling this function. + * Guest key protection is not checked. + * + * Returns zero on success or -EFAULT on error. + * + * If an error occurs data may have been copied partially to kernel space. + */ +static inline __must_check +int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, + unsigned long len) +{ + return access_guest_real(vcpu, gra, data, len, 0); +} + +void ipte_lock(struct kvm_vcpu *vcpu); +void ipte_unlock(struct kvm_vcpu *vcpu); +int ipte_lock_held(struct kvm_vcpu *vcpu); +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra); + +#endif /* __KVM_S390_GACCESS_H */ diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c new file mode 100644 index 000000000..e97b3455d --- /dev/null +++ b/arch/s390/kvm/guestdbg.c @@ -0,0 +1,482 @@ +/* + * kvm guest debug support + * + * Copyright IBM Corp. 2014 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com> + */ +#include <linux/kvm_host.h> +#include <linux/errno.h> +#include "kvm-s390.h" +#include "gaccess.h" + +/* + * Extends the address range given by *start and *stop to include the address + * range starting with estart and the length len. Takes care of overflowing + * intervals and tries to minimize the overall intervall size. + */ +static void extend_address_range(u64 *start, u64 *stop, u64 estart, int len) +{ + u64 estop; + + if (len > 0) + len--; + else + len = 0; + + estop = estart + len; + + /* 0-0 range represents "not set" */ + if ((*start == 0) && (*stop == 0)) { + *start = estart; + *stop = estop; + } else if (*start <= *stop) { + /* increase the existing range */ + if (estart < *start) + *start = estart; + if (estop > *stop) + *stop = estop; + } else { + /* "overflowing" interval, whereby *stop > *start */ + if (estart <= *stop) { + if (estop > *stop) + *stop = estop; + } else if (estop > *start) { + if (estart < *start) + *start = estart; + } + /* minimize the range */ + else if ((estop - *stop) < (*start - estart)) + *stop = estop; + else + *start = estart; + } +} + +#define MAX_INST_SIZE 6 + +static void enable_all_hw_bp(struct kvm_vcpu *vcpu) +{ + unsigned long start, len; + u64 *cr9 = &vcpu->arch.sie_block->gcr[9]; + u64 *cr10 = &vcpu->arch.sie_block->gcr[10]; + u64 *cr11 = &vcpu->arch.sie_block->gcr[11]; + int i; + + if (vcpu->arch.guestdbg.nr_hw_bp <= 0 || + vcpu->arch.guestdbg.hw_bp_info == NULL) + return; + + /* + * If the guest is not interrested in branching events, we can savely + * limit them to the PER address range. + */ + if (!(*cr9 & PER_EVENT_BRANCH)) + *cr9 |= PER_CONTROL_BRANCH_ADDRESS; + *cr9 |= PER_EVENT_IFETCH | PER_EVENT_BRANCH; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_bp; i++) { + start = vcpu->arch.guestdbg.hw_bp_info[i].addr; + len = vcpu->arch.guestdbg.hw_bp_info[i].len; + + /* + * The instruction in front of the desired bp has to + * report instruction-fetching events + */ + if (start < MAX_INST_SIZE) { + len += start; + start = 0; + } else { + start -= MAX_INST_SIZE; + len += MAX_INST_SIZE; + } + + extend_address_range(cr10, cr11, start, len); + } +} + +static void enable_all_hw_wp(struct kvm_vcpu *vcpu) +{ + unsigned long start, len; + u64 *cr9 = &vcpu->arch.sie_block->gcr[9]; + u64 *cr10 = &vcpu->arch.sie_block->gcr[10]; + u64 *cr11 = &vcpu->arch.sie_block->gcr[11]; + int i; + + if (vcpu->arch.guestdbg.nr_hw_wp <= 0 || + vcpu->arch.guestdbg.hw_wp_info == NULL) + return; + + /* if host uses storage alternation for special address + * spaces, enable all events and give all to the guest */ + if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) { + *cr9 &= ~PER_CONTROL_ALTERATION; + *cr10 = 0; + *cr11 = PSW_ADDR_INSN; + } else { + *cr9 &= ~PER_CONTROL_ALTERATION; + *cr9 |= PER_EVENT_STORE; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) { + start = vcpu->arch.guestdbg.hw_wp_info[i].addr; + len = vcpu->arch.guestdbg.hw_wp_info[i].len; + + extend_address_range(cr10, cr11, start, len); + } + } +} + +void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu) +{ + vcpu->arch.guestdbg.cr0 = vcpu->arch.sie_block->gcr[0]; + vcpu->arch.guestdbg.cr9 = vcpu->arch.sie_block->gcr[9]; + vcpu->arch.guestdbg.cr10 = vcpu->arch.sie_block->gcr[10]; + vcpu->arch.guestdbg.cr11 = vcpu->arch.sie_block->gcr[11]; +} + +void kvm_s390_restore_guest_per_regs(struct kvm_vcpu *vcpu) +{ + vcpu->arch.sie_block->gcr[0] = vcpu->arch.guestdbg.cr0; + vcpu->arch.sie_block->gcr[9] = vcpu->arch.guestdbg.cr9; + vcpu->arch.sie_block->gcr[10] = vcpu->arch.guestdbg.cr10; + vcpu->arch.sie_block->gcr[11] = vcpu->arch.guestdbg.cr11; +} + +void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu) +{ + /* + * TODO: if guest psw has per enabled, otherwise 0s! + * This reduces the amount of reported events. + * Need to intercept all psw changes! + */ + + if (guestdbg_sstep_enabled(vcpu)) { + /* disable timer (clock-comparator) interrupts */ + vcpu->arch.sie_block->gcr[0] &= ~0x800ul; + vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH; + vcpu->arch.sie_block->gcr[10] = 0; + vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN; + } + + if (guestdbg_hw_bp_enabled(vcpu)) { + enable_all_hw_bp(vcpu); + enable_all_hw_wp(vcpu); + } + + /* TODO: Instruction-fetching-nullification not allowed for now */ + if (vcpu->arch.sie_block->gcr[9] & PER_EVENT_NULLIFICATION) + vcpu->arch.sie_block->gcr[9] &= ~PER_EVENT_NULLIFICATION; +} + +#define MAX_WP_SIZE 100 + +static int __import_wp_info(struct kvm_vcpu *vcpu, + struct kvm_hw_breakpoint *bp_data, + struct kvm_hw_wp_info_arch *wp_info) +{ + int ret = 0; + wp_info->len = bp_data->len; + wp_info->addr = bp_data->addr; + wp_info->phys_addr = bp_data->phys_addr; + wp_info->old_data = NULL; + + if (wp_info->len < 0 || wp_info->len > MAX_WP_SIZE) + return -EINVAL; + + wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL); + if (!wp_info->old_data) + return -ENOMEM; + /* try to backup the original value */ + ret = read_guest_abs(vcpu, wp_info->phys_addr, wp_info->old_data, + wp_info->len); + if (ret) { + kfree(wp_info->old_data); + wp_info->old_data = NULL; + } + + return ret; +} + +#define MAX_BP_COUNT 50 + +int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + int ret = 0, nr_wp = 0, nr_bp = 0, i, size; + struct kvm_hw_breakpoint *bp_data = NULL; + struct kvm_hw_wp_info_arch *wp_info = NULL; + struct kvm_hw_bp_info_arch *bp_info = NULL; + + if (dbg->arch.nr_hw_bp <= 0 || !dbg->arch.hw_bp) + return 0; + else if (dbg->arch.nr_hw_bp > MAX_BP_COUNT) + return -EINVAL; + + size = dbg->arch.nr_hw_bp * sizeof(struct kvm_hw_breakpoint); + bp_data = kmalloc(size, GFP_KERNEL); + if (!bp_data) { + ret = -ENOMEM; + goto error; + } + + if (copy_from_user(bp_data, dbg->arch.hw_bp, size)) { + ret = -EFAULT; + goto error; + } + + for (i = 0; i < dbg->arch.nr_hw_bp; i++) { + switch (bp_data[i].type) { + case KVM_HW_WP_WRITE: + nr_wp++; + break; + case KVM_HW_BP: + nr_bp++; + break; + default: + break; + } + } + + size = nr_wp * sizeof(struct kvm_hw_wp_info_arch); + if (size > 0) { + wp_info = kmalloc(size, GFP_KERNEL); + if (!wp_info) { + ret = -ENOMEM; + goto error; + } + } + size = nr_bp * sizeof(struct kvm_hw_bp_info_arch); + if (size > 0) { + bp_info = kmalloc(size, GFP_KERNEL); + if (!bp_info) { + ret = -ENOMEM; + goto error; + } + } + + for (nr_wp = 0, nr_bp = 0, i = 0; i < dbg->arch.nr_hw_bp; i++) { + switch (bp_data[i].type) { + case KVM_HW_WP_WRITE: + ret = __import_wp_info(vcpu, &bp_data[i], + &wp_info[nr_wp]); + if (ret) + goto error; + nr_wp++; + break; + case KVM_HW_BP: + bp_info[nr_bp].len = bp_data[i].len; + bp_info[nr_bp].addr = bp_data[i].addr; + nr_bp++; + break; + } + } + + vcpu->arch.guestdbg.nr_hw_bp = nr_bp; + vcpu->arch.guestdbg.hw_bp_info = bp_info; + vcpu->arch.guestdbg.nr_hw_wp = nr_wp; + vcpu->arch.guestdbg.hw_wp_info = wp_info; + return 0; +error: + kfree(bp_data); + kfree(wp_info); + kfree(bp_info); + return ret; +} + +void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_hw_wp_info_arch *hw_wp_info = NULL; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) { + hw_wp_info = &vcpu->arch.guestdbg.hw_wp_info[i]; + kfree(hw_wp_info->old_data); + hw_wp_info->old_data = NULL; + } + kfree(vcpu->arch.guestdbg.hw_wp_info); + vcpu->arch.guestdbg.hw_wp_info = NULL; + + kfree(vcpu->arch.guestdbg.hw_bp_info); + vcpu->arch.guestdbg.hw_bp_info = NULL; + + vcpu->arch.guestdbg.nr_hw_wp = 0; + vcpu->arch.guestdbg.nr_hw_bp = 0; +} + +static inline int in_addr_range(u64 addr, u64 a, u64 b) +{ + if (a <= b) + return (addr >= a) && (addr <= b); + else + /* "overflowing" interval */ + return (addr <= a) && (addr >= b); +} + +#define end_of_range(bp_info) (bp_info->addr + bp_info->len - 1) + +static struct kvm_hw_bp_info_arch *find_hw_bp(struct kvm_vcpu *vcpu, + unsigned long addr) +{ + struct kvm_hw_bp_info_arch *bp_info = vcpu->arch.guestdbg.hw_bp_info; + int i; + + if (vcpu->arch.guestdbg.nr_hw_bp == 0) + return NULL; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_bp; i++) { + /* addr is directly the start or in the range of a bp */ + if (addr == bp_info->addr) + goto found; + if (bp_info->len > 0 && + in_addr_range(addr, bp_info->addr, end_of_range(bp_info))) + goto found; + + bp_info++; + } + + return NULL; +found: + return bp_info; +} + +static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_hw_wp_info_arch *wp_info = NULL; + void *temp = NULL; + + if (vcpu->arch.guestdbg.nr_hw_wp == 0) + return NULL; + + for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) { + wp_info = &vcpu->arch.guestdbg.hw_wp_info[i]; + if (!wp_info || !wp_info->old_data || wp_info->len <= 0) + continue; + + temp = kmalloc(wp_info->len, GFP_KERNEL); + if (!temp) + continue; + + /* refetch the wp data and compare it to the old value */ + if (!read_guest_abs(vcpu, wp_info->phys_addr, temp, + wp_info->len)) { + if (memcmp(temp, wp_info->old_data, wp_info->len)) { + kfree(temp); + return wp_info; + } + } + kfree(temp); + temp = NULL; + } + + return NULL; +} + +void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu) +{ + vcpu->run->exit_reason = KVM_EXIT_DEBUG; + vcpu->guest_debug &= ~KVM_GUESTDBG_EXIT_PENDING; +} + +#define per_bp_event(code) \ + (code & (PER_EVENT_IFETCH | PER_EVENT_BRANCH)) +#define per_write_wp_event(code) \ + (code & (PER_EVENT_STORE | PER_EVENT_STORE_REAL)) + +static int debug_exit_required(struct kvm_vcpu *vcpu) +{ + u32 perc = (vcpu->arch.sie_block->perc << 24); + struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch; + struct kvm_hw_wp_info_arch *wp_info = NULL; + struct kvm_hw_bp_info_arch *bp_info = NULL; + unsigned long addr = vcpu->arch.sie_block->gpsw.addr; + unsigned long peraddr = vcpu->arch.sie_block->peraddr; + + if (guestdbg_hw_bp_enabled(vcpu)) { + if (per_write_wp_event(perc) && + vcpu->arch.guestdbg.nr_hw_wp > 0) { + wp_info = any_wp_changed(vcpu); + if (wp_info) { + debug_exit->addr = wp_info->addr; + debug_exit->type = KVM_HW_WP_WRITE; + goto exit_required; + } + } + if (per_bp_event(perc) && + vcpu->arch.guestdbg.nr_hw_bp > 0) { + bp_info = find_hw_bp(vcpu, addr); + /* remove duplicate events if PC==PER address */ + if (bp_info && (addr != peraddr)) { + debug_exit->addr = addr; + debug_exit->type = KVM_HW_BP; + vcpu->arch.guestdbg.last_bp = addr; + goto exit_required; + } + /* breakpoint missed */ + bp_info = find_hw_bp(vcpu, peraddr); + if (bp_info && vcpu->arch.guestdbg.last_bp != peraddr) { + debug_exit->addr = peraddr; + debug_exit->type = KVM_HW_BP; + goto exit_required; + } + } + } + if (guestdbg_sstep_enabled(vcpu) && per_bp_event(perc)) { + debug_exit->addr = addr; + debug_exit->type = KVM_SINGLESTEP; + goto exit_required; + } + + return 0; +exit_required: + return 1; +} + +#define guest_per_enabled(vcpu) \ + (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) + +static void filter_guest_per_event(struct kvm_vcpu *vcpu) +{ + u32 perc = vcpu->arch.sie_block->perc << 24; + u64 peraddr = vcpu->arch.sie_block->peraddr; + u64 addr = vcpu->arch.sie_block->gpsw.addr; + u64 cr9 = vcpu->arch.sie_block->gcr[9]; + u64 cr10 = vcpu->arch.sie_block->gcr[10]; + u64 cr11 = vcpu->arch.sie_block->gcr[11]; + /* filter all events, demanded by the guest */ + u32 guest_perc = perc & cr9 & PER_EVENT_MASK; + + if (!guest_per_enabled(vcpu)) + guest_perc = 0; + + /* filter "successful-branching" events */ + if (guest_perc & PER_EVENT_BRANCH && + cr9 & PER_CONTROL_BRANCH_ADDRESS && + !in_addr_range(addr, cr10, cr11)) + guest_perc &= ~PER_EVENT_BRANCH; + + /* filter "instruction-fetching" events */ + if (guest_perc & PER_EVENT_IFETCH && + !in_addr_range(peraddr, cr10, cr11)) + guest_perc &= ~PER_EVENT_IFETCH; + + /* All other PER events will be given to the guest */ + /* TODO: Check alterated address/address space */ + + vcpu->arch.sie_block->perc = guest_perc >> 24; + + if (!guest_perc) + vcpu->arch.sie_block->iprcc &= ~PGM_PER; +} + +void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu) +{ + if (debug_exit_required(vcpu)) + vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING; + + filter_guest_per_event(vcpu); +} diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c new file mode 100644 index 000000000..9e3779e3e --- /dev/null +++ b/arch/s390/kvm/intercept.c @@ -0,0 +1,379 @@ +/* + * in-kernel handling for sie intercepts + * + * Copyright IBM Corp. 2008, 2014 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#include <linux/kvm_host.h> +#include <linux/errno.h> +#include <linux/pagemap.h> + +#include <asm/kvm_host.h> +#include <asm/asm-offsets.h> +#include <asm/irq.h> + +#include "kvm-s390.h" +#include "gaccess.h" +#include "trace.h" +#include "trace-s390.h" + + +static const intercept_handler_t instruction_handlers[256] = { + [0x01] = kvm_s390_handle_01, + [0x82] = kvm_s390_handle_lpsw, + [0x83] = kvm_s390_handle_diag, + [0xae] = kvm_s390_handle_sigp, + [0xb2] = kvm_s390_handle_b2, + [0xb6] = kvm_s390_handle_stctl, + [0xb7] = kvm_s390_handle_lctl, + [0xb9] = kvm_s390_handle_b9, + [0xe5] = kvm_s390_handle_e5, + [0xeb] = kvm_s390_handle_eb, +}; + +void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc) +{ + struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; + + /* Use the length of the EXECUTE instruction if necessary */ + if (sie_block->icptstatus & 1) { + ilc = (sie_block->icptstatus >> 4) & 0x6; + if (!ilc) + ilc = 4; + } + sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc); +} + +static int handle_noop(struct kvm_vcpu *vcpu) +{ + switch (vcpu->arch.sie_block->icptcode) { + case 0x0: + vcpu->stat.exit_null++; + break; + case 0x10: + vcpu->stat.exit_external_request++; + break; + default: + break; /* nothing */ + } + return 0; +} + +static int handle_stop(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc = 0; + uint8_t flags, stop_pending; + + vcpu->stat.exit_stop_request++; + + /* delay the stop if any non-stop irq is pending */ + if (kvm_s390_vcpu_has_irq(vcpu, 1)) + return 0; + + /* avoid races with the injection/SIGP STOP code */ + spin_lock(&li->lock); + flags = li->irq.stop.flags; + stop_pending = kvm_s390_is_stop_irq_pending(vcpu); + spin_unlock(&li->lock); + + trace_kvm_s390_stop_request(stop_pending, flags); + if (!stop_pending) + return 0; + + if (flags & KVM_S390_STOP_FLAG_STORE_STATUS) { + rc = kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_NOADDR); + if (rc) + return rc; + } + + if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) + kvm_s390_vcpu_stop(vcpu); + return -EOPNOTSUPP; +} + +static int handle_validity(struct kvm_vcpu *vcpu) +{ + int viwhy = vcpu->arch.sie_block->ipb >> 16; + + vcpu->stat.exit_validity++; + trace_kvm_s390_intercept_validity(vcpu, viwhy); + WARN_ONCE(true, "kvm: unhandled validity intercept 0x%x\n", viwhy); + return -EOPNOTSUPP; +} + +static int handle_instruction(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + vcpu->stat.exit_instruction++; + trace_kvm_s390_intercept_instruction(vcpu, + vcpu->arch.sie_block->ipa, + vcpu->arch.sie_block->ipb); + handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8]; + if (handler) + return handler(vcpu); + return -EOPNOTSUPP; +} + +static void __extract_prog_irq(struct kvm_vcpu *vcpu, + struct kvm_s390_pgm_info *pgm_info) +{ + memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info)); + pgm_info->code = vcpu->arch.sie_block->iprcc; + + switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) { + case PGM_AFX_TRANSLATION: + case PGM_ASX_TRANSLATION: + case PGM_EX_TRANSLATION: + case PGM_LFX_TRANSLATION: + case PGM_LSTE_SEQUENCE: + case PGM_LSX_TRANSLATION: + case PGM_LX_TRANSLATION: + case PGM_PRIMARY_AUTHORITY: + case PGM_SECONDARY_AUTHORITY: + case PGM_SPACE_SWITCH: + pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; + break; + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_INSTANCE: + case PGM_ASTE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_EXTENDED_AUTHORITY: + pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + break; + case PGM_ASCE_TYPE: + case PGM_PAGE_TRANSLATION: + case PGM_REGION_FIRST_TRANS: + case PGM_REGION_SECOND_TRANS: + case PGM_REGION_THIRD_TRANS: + case PGM_SEGMENT_TRANSLATION: + pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; + pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + pgm_info->op_access_id = vcpu->arch.sie_block->oai; + break; + case PGM_MONITOR: + pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn; + pgm_info->mon_code = vcpu->arch.sie_block->tecmc; + break; + case PGM_VECTOR_PROCESSING: + case PGM_DATA: + pgm_info->data_exc_code = vcpu->arch.sie_block->dxc; + break; + case PGM_PROTECTION: + pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; + pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + break; + default: + break; + } + + if (vcpu->arch.sie_block->iprcc & PGM_PER) { + pgm_info->per_code = vcpu->arch.sie_block->perc; + pgm_info->per_atmid = vcpu->arch.sie_block->peratmid; + pgm_info->per_address = vcpu->arch.sie_block->peraddr; + pgm_info->per_access_id = vcpu->arch.sie_block->peraid; + } +} + +/* + * restore ITDB to program-interruption TDB in guest lowcore + * and set TX abort indication if required +*/ +static int handle_itdb(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_itdb *itdb; + int rc; + + if (!IS_TE_ENABLED(vcpu) || !IS_ITDB_VALID(vcpu)) + return 0; + if (current->thread.per_flags & PER_FLAG_NO_TE) + return 0; + itdb = (struct kvm_s390_itdb *)vcpu->arch.sie_block->itdba; + rc = write_guest_lc(vcpu, __LC_PGM_TDB, itdb, sizeof(*itdb)); + if (rc) + return rc; + memset(itdb, 0, sizeof(*itdb)); + + return 0; +} + +#define per_event(vcpu) (vcpu->arch.sie_block->iprcc & PGM_PER) + +static int handle_prog(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_pgm_info pgm_info; + psw_t psw; + int rc; + + vcpu->stat.exit_program_interruption++; + + if (guestdbg_enabled(vcpu) && per_event(vcpu)) { + kvm_s390_handle_per_event(vcpu); + /* the interrupt might have been filtered out completely */ + if (vcpu->arch.sie_block->iprcc == 0) + return 0; + } + + trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc); + if (vcpu->arch.sie_block->iprcc == PGM_SPECIFICATION) { + rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &psw, sizeof(psw_t)); + if (rc) + return rc; + /* Avoid endless loops of specification exceptions */ + if (!is_valid_psw(&psw)) + return -EOPNOTSUPP; + } + rc = handle_itdb(vcpu); + if (rc) + return rc; + + __extract_prog_irq(vcpu, &pgm_info); + return kvm_s390_inject_prog_irq(vcpu, &pgm_info); +} + +static int handle_instruction_and_prog(struct kvm_vcpu *vcpu) +{ + int rc, rc2; + + vcpu->stat.exit_instr_and_program++; + rc = handle_instruction(vcpu); + rc2 = handle_prog(vcpu); + + if (rc == -EOPNOTSUPP) + vcpu->arch.sie_block->icptcode = 0x04; + if (rc) + return rc; + return rc2; +} + +/** + * handle_external_interrupt - used for external interruption interceptions + * + * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if + * the new PSW does not have external interrupts disabled. In the first case, + * we've got to deliver the interrupt manually, and in the second case, we + * drop to userspace to handle the situation there. + */ +static int handle_external_interrupt(struct kvm_vcpu *vcpu) +{ + u16 eic = vcpu->arch.sie_block->eic; + struct kvm_s390_irq irq; + psw_t newpsw; + int rc; + + vcpu->stat.exit_external_interrupt++; + + rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t)); + if (rc) + return rc; + /* We can not handle clock comparator or timer interrupt with bad PSW */ + if ((eic == EXT_IRQ_CLK_COMP || eic == EXT_IRQ_CPU_TIMER) && + (newpsw.mask & PSW_MASK_EXT)) + return -EOPNOTSUPP; + + switch (eic) { + case EXT_IRQ_CLK_COMP: + irq.type = KVM_S390_INT_CLOCK_COMP; + break; + case EXT_IRQ_CPU_TIMER: + irq.type = KVM_S390_INT_CPU_TIMER; + break; + case EXT_IRQ_EXTERNAL_CALL: + irq.type = KVM_S390_INT_EXTERNAL_CALL; + irq.u.extcall.code = vcpu->arch.sie_block->extcpuaddr; + rc = kvm_s390_inject_vcpu(vcpu, &irq); + /* ignore if another external call is already pending */ + if (rc == -EBUSY) + return 0; + return rc; + default: + return -EOPNOTSUPP; + } + + return kvm_s390_inject_vcpu(vcpu, &irq); +} + +/** + * Handle MOVE PAGE partial execution interception. + * + * This interception can only happen for guests with DAT disabled and + * addresses that are currently not mapped in the host. Thus we try to + * set up the mappings for the corresponding user pages here (or throw + * addressing exceptions in case of illegal guest addresses). + */ +static int handle_mvpg_pei(struct kvm_vcpu *vcpu) +{ + unsigned long srcaddr, dstaddr; + int reg1, reg2, rc; + + kvm_s390_get_regs_rre(vcpu, ®1, ®2); + + /* Make sure that the source is paged-in */ + rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2], + reg2, &srcaddr, 0); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0); + if (rc != 0) + return rc; + + /* Make sure that the destination is paged-in */ + rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1], + reg1, &dstaddr, 1); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1); + if (rc != 0) + return rc; + + kvm_s390_rewind_psw(vcpu, 4); + + return 0; +} + +static int handle_partial_execution(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->ipa == 0xb254) /* MVPG */ + return handle_mvpg_pei(vcpu); + if (vcpu->arch.sie_block->ipa >> 8 == 0xae) /* SIGP */ + return kvm_s390_handle_sigp_pei(vcpu); + + return -EOPNOTSUPP; +} + +static const intercept_handler_t intercept_funcs[] = { + [0x00 >> 2] = handle_noop, + [0x04 >> 2] = handle_instruction, + [0x08 >> 2] = handle_prog, + [0x0C >> 2] = handle_instruction_and_prog, + [0x10 >> 2] = handle_noop, + [0x14 >> 2] = handle_external_interrupt, + [0x18 >> 2] = handle_noop, + [0x1C >> 2] = kvm_s390_handle_wait, + [0x20 >> 2] = handle_validity, + [0x28 >> 2] = handle_stop, + [0x38 >> 2] = handle_partial_execution, +}; + +int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) +{ + intercept_handler_t func; + u8 code = vcpu->arch.sie_block->icptcode; + + if (code & 3 || (code >> 2) >= ARRAY_SIZE(intercept_funcs)) + return -EOPNOTSUPP; + func = intercept_funcs[code >> 2]; + if (func) + return func(vcpu); + return -EOPNOTSUPP; +} diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c new file mode 100644 index 000000000..b745a109b --- /dev/null +++ b/arch/s390/kvm/interrupt.c @@ -0,0 +1,2268 @@ +/* + * handling kvm guest interrupts + * + * Copyright IBM Corp. 2008, 2015 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + */ + +#include <linux/interrupt.h> +#include <linux/kvm_host.h> +#include <linux/hrtimer.h> +#include <linux/mmu_context.h> +#include <linux/signal.h> +#include <linux/slab.h> +#include <linux/bitmap.h> +#include <linux/vmalloc.h> +#include <asm/asm-offsets.h> +#include <asm/dis.h> +#include <asm/uaccess.h> +#include <asm/sclp.h> +#include <asm/isc.h> +#include "kvm-s390.h" +#include "gaccess.h" +#include "trace-s390.h" + +#define IOINT_SCHID_MASK 0x0000ffff +#define IOINT_SSID_MASK 0x00030000 +#define IOINT_CSSID_MASK 0x03fc0000 +#define IOINT_AI_MASK 0x04000000 +#define PFAULT_INIT 0x0600 +#define PFAULT_DONE 0x0680 +#define VIRTIO_PARAM 0x0d00 + +int psw_extint_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT); +} + +static int psw_ioint_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO); +} + +static int psw_mchk_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK); +} + +static int psw_interrupts_disabled(struct kvm_vcpu *vcpu) +{ + if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) || + (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO) || + (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT)) + return 0; + return 1; +} + +static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) +{ + if (psw_extint_disabled(vcpu) || + !(vcpu->arch.sie_block->gcr[0] & 0x800ul)) + return 0; + if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu)) + /* No timer interrupts when single stepping */ + return 0; + return 1; +} + +static int ckc_irq_pending(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.sie_block->ckc < + get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) + return 0; + return ckc_interrupts_enabled(vcpu); +} + +static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu) +{ + return !psw_extint_disabled(vcpu) && + (vcpu->arch.sie_block->gcr[0] & 0x400ul); +} + +static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.sie_block->cputm >> 63) && + cpu_timer_interrupts_enabled(vcpu); +} + +static inline int is_ioirq(unsigned long irq_type) +{ + return ((irq_type >= IRQ_PEND_IO_ISC_0) && + (irq_type <= IRQ_PEND_IO_ISC_7)); +} + +static uint64_t isc_to_isc_bits(int isc) +{ + return (0x80 >> isc) << 24; +} + +static inline u8 int_word_to_isc(u32 int_word) +{ + return (int_word & 0x38000000) >> 27; +} + +static inline unsigned long pending_floating_irqs(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.float_int.pending_irqs; +} + +static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.local_int.pending_irqs; +} + +static unsigned long disable_iscs(struct kvm_vcpu *vcpu, + unsigned long active_mask) +{ + int i; + + for (i = 0; i <= MAX_ISC; i++) + if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i))) + active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i)); + + return active_mask; +} + +static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) +{ + unsigned long active_mask; + + active_mask = pending_local_irqs(vcpu); + active_mask |= pending_floating_irqs(vcpu); + + if (psw_extint_disabled(vcpu)) + active_mask &= ~IRQ_PEND_EXT_MASK; + if (psw_ioint_disabled(vcpu)) + active_mask &= ~IRQ_PEND_IO_MASK; + else + active_mask = disable_iscs(vcpu, active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul)) + __clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul)) + __clear_bit(IRQ_PEND_EXT_EMERGENCY, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul)) + __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul)) + __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul)) + __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); + if (psw_mchk_disabled(vcpu)) + active_mask &= ~IRQ_PEND_MCHK_MASK; + if (!(vcpu->arch.sie_block->gcr[14] & + vcpu->kvm->arch.float_int.mchk.cr14)) + __clear_bit(IRQ_PEND_MCHK_REP, &active_mask); + + /* + * STOP irqs will never be actively delivered. They are triggered via + * intercept requests and cleared when the stop intercept is performed. + */ + __clear_bit(IRQ_PEND_SIGP_STOP, &active_mask); + + return active_mask; +} + +static void __set_cpu_idle(struct kvm_vcpu *vcpu) +{ + atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); + set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask); +} + +static void __unset_cpu_idle(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); + clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask); +} + +static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT, + &vcpu->arch.sie_block->cpuflags); + vcpu->arch.sie_block->lctl = 0x0000; + vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT); + + if (guestdbg_enabled(vcpu)) { + vcpu->arch.sie_block->lctl |= (LCTL_CR0 | LCTL_CR9 | + LCTL_CR10 | LCTL_CR11); + vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT); + } +} + +static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) +{ + atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags); +} + +static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) +{ + if (!(pending_floating_irqs(vcpu) & IRQ_PEND_IO_MASK)) + return; + else if (psw_ioint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_IO_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR6; +} + +static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) +{ + if (!(pending_local_irqs(vcpu) & IRQ_PEND_EXT_MASK)) + return; + if (psw_extint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_EXT_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR0; +} + +static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu) +{ + if (!(pending_local_irqs(vcpu) & IRQ_PEND_MCHK_MASK)) + return; + if (psw_mchk_disabled(vcpu)) + vcpu->arch.sie_block->ictl |= ICTL_LPSW; + else + vcpu->arch.sie_block->lctl |= LCTL_CR14; +} + +static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu) +{ + if (kvm_s390_is_stop_irq_pending(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_STOP_INT); +} + +/* Set interception request for non-deliverable interrupts */ +static void set_intercept_indicators(struct kvm_vcpu *vcpu) +{ + set_intercept_indicators_io(vcpu); + set_intercept_indicators_ext(vcpu); + set_intercept_indicators_mchk(vcpu); + set_intercept_indicators_stop(vcpu); +} + +static u16 get_ilc(struct kvm_vcpu *vcpu) +{ + switch (vcpu->arch.sie_block->icptcode) { + case ICPT_INST: + case ICPT_INSTPROGI: + case ICPT_OPEREXC: + case ICPT_PARTEXEC: + case ICPT_IOINST: + /* last instruction only stored for these icptcodes */ + return insn_length(vcpu->arch.sie_block->ipa >> 8); + case ICPT_PROGI: + return vcpu->arch.sie_block->pgmilc; + default: + return 0; + } +} + +static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER, + 0, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP, + 0, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, + (u16 __user *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_ext_info ext; + int rc; + + spin_lock(&li->lock); + ext = li->irq.ext; + clear_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs); + li->irq.ext.ext_params2 = 0; + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx", + 0, ext.ext_params2); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_PFAULT_INIT, + 0, ext.ext_params2); + + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *) __LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, PFAULT_INIT, (u16 *) __LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_mchk_info mchk = {}; + unsigned long adtl_status_addr; + int deliver = 0; + int rc = 0; + + spin_lock(&fi->lock); + spin_lock(&li->lock); + if (test_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs) || + test_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs)) { + /* + * If there was an exigent machine check pending, then any + * repressible machine checks that might have been pending + * are indicated along with it, so always clear bits for + * repressible and exigent interrupts + */ + mchk = li->irq.mchk; + clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); + clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); + memset(&li->irq.mchk, 0, sizeof(mchk)); + deliver = 1; + } + /* + * We indicate floating repressible conditions along with + * other pending conditions. Channel Report Pending and Channel + * Subsystem damage are the only two and and are indicated by + * bits in mcic and masked in cr14. + */ + if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + mchk.mcic |= fi->mchk.mcic; + mchk.cr14 |= fi->mchk.cr14; + memset(&fi->mchk, 0, sizeof(mchk)); + deliver = 1; + } + spin_unlock(&li->lock); + spin_unlock(&fi->lock); + + if (deliver) { + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + mchk.mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_MCHK, + mchk.cr14, mchk.mcic); + + rc = kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_PREFIXED); + rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, + &adtl_status_addr, + sizeof(unsigned long)); + rc |= kvm_s390_vcpu_store_adtl_status(vcpu, + adtl_status_addr); + rc |= put_guest_lc(vcpu, mchk.mcic, + (u64 __user *) __LC_MCCK_CODE); + rc |= put_guest_lc(vcpu, mchk.failing_storage_address, + (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); + rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, + &mchk.fixed_logout, + sizeof(mchk.fixed_logout)); + rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + } + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart"); + vcpu->stat.deliver_restart_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0); + + rc = write_guest_lc(vcpu, + offsetof(struct _lowcore, restart_old_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + clear_bit(IRQ_PEND_RESTART, &li->pending_irqs); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_prefix_info prefix; + + spin_lock(&li->lock); + prefix = li->irq.prefix; + li->irq.prefix.address = 0; + clear_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address); + vcpu->stat.deliver_prefix_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_SIGP_SET_PREFIX, + prefix.address, 0); + + kvm_s390_set_prefix(vcpu, prefix.address); + return 0; +} + +static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + int cpu_addr; + + spin_lock(&li->lock); + cpu_addr = find_first_bit(li->sigp_emerg_pending, KVM_MAX_VCPUS); + clear_bit(cpu_addr, li->sigp_emerg_pending); + if (bitmap_empty(li->sigp_emerg_pending, KVM_MAX_VCPUS)) + clear_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg"); + vcpu->stat.deliver_emergency_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, + cpu_addr, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_extcall_info extcall; + int rc; + + spin_lock(&li->lock); + extcall = li->irq.extcall; + li->irq.extcall.code = 0; + clear_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call"); + vcpu->stat.deliver_external_call++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_EXTERNAL_CALL, + extcall.code, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_pgm_info pgm_info; + int rc = 0, nullifying = false; + u16 ilc = get_ilc(vcpu); + + spin_lock(&li->lock); + pgm_info = li->irq.pgm; + clear_bit(IRQ_PEND_PROG, &li->pending_irqs); + memset(&li->irq.pgm, 0, sizeof(pgm_info)); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x", + pgm_info.code, ilc); + vcpu->stat.deliver_program_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, + pgm_info.code, 0); + + switch (pgm_info.code & ~PGM_PER) { + case PGM_AFX_TRANSLATION: + case PGM_ASX_TRANSLATION: + case PGM_EX_TRANSLATION: + case PGM_LFX_TRANSLATION: + case PGM_LSTE_SEQUENCE: + case PGM_LSX_TRANSLATION: + case PGM_LX_TRANSLATION: + case PGM_PRIMARY_AUTHORITY: + case PGM_SECONDARY_AUTHORITY: + nullifying = true; + /* fall through */ + case PGM_SPACE_SWITCH: + rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, + (u64 *)__LC_TRANS_EXC_CODE); + break; + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_INSTANCE: + case PGM_ASTE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_EXTENDED_AUTHORITY: + rc = put_guest_lc(vcpu, pgm_info.exc_access_id, + (u8 *)__LC_EXC_ACCESS_ID); + nullifying = true; + break; + case PGM_ASCE_TYPE: + case PGM_PAGE_TRANSLATION: + case PGM_REGION_FIRST_TRANS: + case PGM_REGION_SECOND_TRANS: + case PGM_REGION_THIRD_TRANS: + case PGM_SEGMENT_TRANSLATION: + rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, + (u64 *)__LC_TRANS_EXC_CODE); + rc |= put_guest_lc(vcpu, pgm_info.exc_access_id, + (u8 *)__LC_EXC_ACCESS_ID); + rc |= put_guest_lc(vcpu, pgm_info.op_access_id, + (u8 *)__LC_OP_ACCESS_ID); + nullifying = true; + break; + case PGM_MONITOR: + rc = put_guest_lc(vcpu, pgm_info.mon_class_nr, + (u16 *)__LC_MON_CLASS_NR); + rc |= put_guest_lc(vcpu, pgm_info.mon_code, + (u64 *)__LC_MON_CODE); + break; + case PGM_VECTOR_PROCESSING: + case PGM_DATA: + rc = put_guest_lc(vcpu, pgm_info.data_exc_code, + (u32 *)__LC_DATA_EXC_CODE); + break; + case PGM_PROTECTION: + rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, + (u64 *)__LC_TRANS_EXC_CODE); + rc |= put_guest_lc(vcpu, pgm_info.exc_access_id, + (u8 *)__LC_EXC_ACCESS_ID); + break; + case PGM_STACK_FULL: + case PGM_STACK_EMPTY: + case PGM_STACK_SPECIFICATION: + case PGM_STACK_TYPE: + case PGM_STACK_OPERATION: + case PGM_TRACE_TABEL: + case PGM_CRYPTO_OPERATION: + nullifying = true; + break; + } + + if (pgm_info.code & PGM_PER) { + rc |= put_guest_lc(vcpu, pgm_info.per_code, + (u8 *) __LC_PER_CODE); + rc |= put_guest_lc(vcpu, pgm_info.per_atmid, + (u8 *)__LC_PER_ATMID); + rc |= put_guest_lc(vcpu, pgm_info.per_address, + (u64 *) __LC_PER_ADDRESS); + rc |= put_guest_lc(vcpu, pgm_info.per_access_id, + (u8 *) __LC_PER_ACCESS_ID); + } + + if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST) + kvm_s390_rewind_psw(vcpu, ilc); + + rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC); + rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea, + (u64 *) __LC_LAST_BREAK); + rc |= put_guest_lc(vcpu, pgm_info.code, + (u16 *)__LC_PGM_INT_CODE); + rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_service(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_ext_info ext; + int rc = 0; + + spin_lock(&fi->lock); + if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { + spin_unlock(&fi->lock); + return 0; + } + ext = fi->srv_signal; + memset(&fi->srv_signal, 0, sizeof(ext)); + clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + spin_unlock(&fi->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", + ext.ext_params); + vcpu->stat.deliver_service_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, + ext.ext_params, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, ext.ext_params, + (u32 *)__LC_EXT_PARAMS); + + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; + + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_PFAULT], + struct kvm_s390_interrupt_info, + list); + if (inti) { + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_PFAULT_DONE, 0, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_PFAULT] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_PFAULT])) + clear_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); + + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, PFAULT_DONE, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + kfree(inti); + } + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; + + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_VIRTIO], + struct kvm_s390_interrupt_info, + list); + if (inti) { + VCPU_EVENT(vcpu, 4, + "interrupt: virtio parm:%x,parm64:%llx", + inti->ext.ext_params, inti->ext.ext_params2); + vcpu->stat.deliver_virtio_interrupt++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + inti->type, + inti->ext.ext_params, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_VIRTIO] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_VIRTIO])) + clear_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); + + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, VIRTIO_PARAM, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__LC_EXT_PARAMS); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + kfree(inti); + } + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_io(struct kvm_vcpu *vcpu, + unsigned long irq_type) +{ + struct list_head *isc_list; + struct kvm_s390_float_interrupt *fi; + struct kvm_s390_interrupt_info *inti = NULL; + int rc = 0; + + fi = &vcpu->kvm->arch.float_int; + + spin_lock(&fi->lock); + isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0]; + inti = list_first_entry_or_null(isc_list, + struct kvm_s390_interrupt_info, + list); + if (inti) { + VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); + vcpu->stat.deliver_io_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + inti->type, + ((__u32)inti->io.subchannel_id << 16) | + inti->io.subchannel_nr, + ((__u64)inti->io.io_int_parm << 32) | + inti->io.io_int_word); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + } + if (list_empty(isc_list)) + clear_bit(irq_type, &fi->pending_irqs); + spin_unlock(&fi->lock); + + if (inti) { + rc = put_guest_lc(vcpu, inti->io.subchannel_id, + (u16 *)__LC_SUBCHANNEL_ID); + rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, + (u16 *)__LC_SUBCHANNEL_NR); + rc |= put_guest_lc(vcpu, inti->io.io_int_parm, + (u32 *)__LC_IO_INT_PARM); + rc |= put_guest_lc(vcpu, inti->io.io_int_word, + (u32 *)__LC_IO_INT_WORD); + rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + kfree(inti); + } + + return rc ? -EFAULT : 0; +} + +typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); + +static const deliver_irq_t deliver_irq_funcs[] = { + [IRQ_PEND_MCHK_EX] = __deliver_machine_check, + [IRQ_PEND_MCHK_REP] = __deliver_machine_check, + [IRQ_PEND_PROG] = __deliver_prog, + [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, + [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, + [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc, + [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer, + [IRQ_PEND_RESTART] = __deliver_restart, + [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, + [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, + [IRQ_PEND_EXT_SERVICE] = __deliver_service, + [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done, + [IRQ_PEND_VIRTIO] = __deliver_virtio, +}; + +/* Check whether an external call is pending (deliverable or not) */ +int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + + if (!sclp_has_sigpif()) + return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs); + + return (sigp_ctrl & SIGP_CTRL_C) && + (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND); +} + +int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop) +{ + int rc; + + rc = !!deliverable_irqs(vcpu); + + if (!rc && kvm_cpu_has_pending_timer(vcpu)) + rc = 1; + + /* external call pending and deliverable */ + if (!rc && kvm_s390_ext_call_pending(vcpu) && + !psw_extint_disabled(vcpu) && + (vcpu->arch.sie_block->gcr[0] & 0x2000ul)) + rc = 1; + + if (!rc && !exclude_stop && kvm_s390_is_stop_irq_pending(vcpu)) + rc = 1; + + return rc; +} + +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) +{ + return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu); +} + +int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) +{ + u64 now, sltime; + + vcpu->stat.exit_wait_state++; + + /* fast path */ + if (kvm_cpu_has_pending_timer(vcpu) || kvm_arch_vcpu_runnable(vcpu)) + return 0; + + if (psw_interrupts_disabled(vcpu)) { + VCPU_EVENT(vcpu, 3, "%s", "disabled wait"); + return -EOPNOTSUPP; /* disabled wait */ + } + + if (!ckc_interrupts_enabled(vcpu)) { + VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer"); + __set_cpu_idle(vcpu); + goto no_timer; + } + + now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch; + sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); + + /* underflow */ + if (vcpu->arch.sie_block->ckc < now) + return 0; + + __set_cpu_idle(vcpu); + hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL); + VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime); +no_timer: + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_block(vcpu); + __unset_cpu_idle(vcpu); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + hrtimer_cancel(&vcpu->arch.ckc_timer); + return 0; +} + +void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) +{ + if (waitqueue_active(&vcpu->wq)) { + /* + * The vcpu gave up the cpu voluntarily, mark it as a good + * yield-candidate. + */ + vcpu->preempted = true; + wake_up_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } +} + +enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer) +{ + struct kvm_vcpu *vcpu; + u64 now, sltime; + + vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer); + now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch; + sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); + + /* + * If the monotonic clock runs faster than the tod clock we might be + * woken up too early and have to go back to sleep to avoid deadlocks. + */ + if (vcpu->arch.sie_block->ckc > now && + hrtimer_forward_now(timer, ns_to_ktime(sltime))) + return HRTIMER_RESTART; + kvm_s390_vcpu_wakeup(vcpu); + return HRTIMER_NORESTART; +} + +void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + spin_lock(&li->lock); + li->pending_irqs = 0; + bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS); + memset(&li->irq, 0, sizeof(li->irq)); + spin_unlock(&li->lock); + + /* clear pending external calls set by sigp interpretation facility */ + atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags); + vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0; +} + +int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + deliver_irq_t func; + int rc = 0; + unsigned long irq_type; + unsigned long irqs; + + __reset_intercept_indicators(vcpu); + + /* pending ckc conditions might have been invalidated */ + clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + if (ckc_irq_pending(vcpu)) + set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + + /* pending cpu timer conditions might have been invalidated */ + clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + if (cpu_timer_irq_pending(vcpu)) + set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + + do { + irqs = deliverable_irqs(vcpu); + /* bits are in the order of interrupt priority */ + irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT); + if (irq_type == IRQ_PEND_COUNT) + break; + if (is_ioirq(irq_type)) { + rc = __deliver_io(vcpu, irq_type); + } else { + func = deliver_irq_funcs[irq_type]; + if (!func) { + WARN_ON_ONCE(func == NULL); + clear_bit(irq_type, &li->pending_irqs); + continue; + } + rc = func(vcpu); + } + if (rc) + break; + } while (!rc); + + set_intercept_indicators(vcpu); + + return rc; +} + +static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + li->irq.pgm = irq->u.pgm; + set_bit(IRQ_PEND_PROG, &li->pending_irqs); + return 0; +} + +int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_irq irq; + + VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code, + 0, 1); + spin_lock(&li->lock); + irq.u.pgm.code = code; + __inject_prog(vcpu, &irq); + BUG_ON(waitqueue_active(li->wq)); + spin_unlock(&li->lock); + return 0; +} + +int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu, + struct kvm_s390_pgm_info *pgm_info) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_irq irq; + int rc; + + VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)", + pgm_info->code); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, + pgm_info->code, 0, 1); + spin_lock(&li->lock); + irq.u.pgm = *pgm_info; + rc = __inject_prog(vcpu, &irq); + BUG_ON(waitqueue_active(li->wq)); + spin_unlock(&li->lock); + return rc; +} + +static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: external irq params:%x, params2:%llx", + irq->u.ext.ext_params, irq->u.ext.ext_params2); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT, + irq->u.ext.ext_params, + irq->u.ext.ext_params2, 2); + + li->irq.ext = irq->u.ext; + set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id) +{ + unsigned char new_val, old_val; + uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + + new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK); + old_val = *sigp_ctrl & ~SIGP_CTRL_C; + if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) { + /* another external call is pending */ + return -EBUSY; + } + atomic_set_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags); + return 0; +} + +static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_extcall_info *extcall = &li->irq.extcall; + uint16_t src_id = irq->u.extcall.code; + + VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u", + src_id); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL, + src_id, 0, 2); + + /* sending vcpu invalid */ + if (src_id >= KVM_MAX_VCPUS || + kvm_get_vcpu(vcpu->kvm, src_id) == NULL) + return -EINVAL; + + if (sclp_has_sigpif()) + return __inject_extcall_sigpif(vcpu, src_id); + + if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) + return -EBUSY; + *extcall = irq->u.extcall; + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_prefix_info *prefix = &li->irq.prefix; + + VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)", + irq->u.prefix.address); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX, + irq->u.prefix.address, 0, 2); + + if (!is_vcpu_stopped(vcpu)) + return -EBUSY; + + *prefix = irq->u.prefix; + set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs); + return 0; +} + +#define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS) +static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_stop_info *stop = &li->irq.stop; + int rc = 0; + + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2); + + if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS) + return -EINVAL; + + if (is_vcpu_stopped(vcpu)) { + if (irq->u.stop.flags & KVM_S390_STOP_FLAG_STORE_STATUS) + rc = kvm_s390_store_status_unloaded(vcpu, + KVM_S390_STORE_STATUS_NOADDR); + return rc; + } + + if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs)) + return -EBUSY; + stop->flags = irq->u.stop.flags; + __set_cpuflag(vcpu, CPUSTAT_STOP_INT); + return 0; +} + +static int __inject_sigp_restart(struct kvm_vcpu *vcpu, + struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: restart type %llx", irq->type); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0, 2); + + set_bit(IRQ_PEND_RESTART, &li->pending_irqs); + return 0; +} + +static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, + struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", + irq->u.emerg.code); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, + irq->u.emerg.code, 0, 2); + + set_bit(irq->u.emerg.code, li->sigp_emerg_pending); + set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_mchk_info *mchk = &li->irq.mchk; + + VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx", + irq->u.mchk.mcic); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0, + irq->u.mchk.mcic, 2); + + /* + * Because repressible machine checks can be indicated along with + * exigent machine checks (PoP, Chapter 11, Interruption action) + * we need to combine cr14, mcic and external damage code. + * Failing storage address and the logout area should not be or'ed + * together, we just indicate the last occurrence of the corresponding + * machine check + */ + mchk->cr14 |= irq->u.mchk.cr14; + mchk->mcic |= irq->u.mchk.mcic; + mchk->ext_damage_code |= irq->u.mchk.ext_damage_code; + mchk->failing_storage_address = irq->u.mchk.failing_storage_address; + memcpy(&mchk->fixed_logout, &irq->u.mchk.fixed_logout, + sizeof(mchk->fixed_logout)); + if (mchk->mcic & MCHK_EX_MASK) + set_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); + else if (mchk->mcic & MCHK_REP_MASK) + set_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); + return 0; +} + +static int __inject_ckc(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CLOCK_COMP); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP, + 0, 0, 2); + + set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static int __inject_cpu_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CPU_TIMER); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER, + 0, 0, 2); + + set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm, + int isc, u32 schid) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + struct list_head *isc_list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + struct kvm_s390_interrupt_info *iter; + u16 id = (schid & 0xffff0000U) >> 16; + u16 nr = schid & 0x0000ffffU; + + spin_lock(&fi->lock); + list_for_each_entry(iter, isc_list, list) { + if (schid && (id != iter->io.subchannel_id || + nr != iter->io.subchannel_nr)) + continue; + /* found an appropriate entry */ + list_del_init(&iter->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + if (list_empty(isc_list)) + clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); + spin_unlock(&fi->lock); + return iter; + } + spin_unlock(&fi->lock); + return NULL; +} + +/* + * Dequeue and return an I/O interrupt matching any of the interruption + * subclasses as designated by the isc mask in cr6 and the schid (if != 0). + */ +struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, + u64 isc_mask, u32 schid) +{ + struct kvm_s390_interrupt_info *inti = NULL; + int isc; + + for (isc = 0; isc <= MAX_ISC && !inti; isc++) { + if (isc_mask & isc_to_isc_bits(isc)) + inti = get_io_int(kvm, isc, schid); + } + return inti; +} + +#define SCCB_MASK 0xFFFFFFF8 +#define SCCB_EVENT_PENDING 0x3 + +static int __inject_service(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING; + /* + * Early versions of the QEMU s390 bios will inject several + * service interrupts after another without handling a + * condition code indicating busy. + * We will silently ignore those superfluous sccb values. + * A future version of QEMU will take care of serialization + * of servc requests + */ + if (fi->srv_signal.ext_params & SCCB_MASK) + goto out; + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_MASK; + set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); +out: + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_virtio(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_VIRTIO] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_VIRTIO]); + set_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +static int __inject_pfault_done(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_PFAULT] >= + (ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_PFAULT] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_PFAULT]); + set_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +#define CR_PENDING_SUBCLASS 28 +static int __inject_float_mchk(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS); + fi->mchk.mcic |= inti->mchk.mcic; + set_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs); + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi; + struct list_head *list; + int isc; + + fi = &kvm->arch.float_int; + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_IO] += 1; + + isc = int_word_to_isc(inti->io.io_int_word); + list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + list_add_tail(&inti->list, list); + set_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_local_interrupt *li; + struct kvm_s390_float_interrupt *fi; + struct kvm_vcpu *dst_vcpu = NULL; + int sigcpu; + u64 type = READ_ONCE(inti->type); + int rc; + + fi = &kvm->arch.float_int; + + switch (type) { + case KVM_S390_MCHK: + rc = __inject_float_mchk(kvm, inti); + break; + case KVM_S390_INT_VIRTIO: + rc = __inject_virtio(kvm, inti); + break; + case KVM_S390_INT_SERVICE: + rc = __inject_service(kvm, inti); + break; + case KVM_S390_INT_PFAULT_DONE: + rc = __inject_pfault_done(kvm, inti); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + rc = __inject_io(kvm, inti); + break; + default: + rc = -EINVAL; + } + if (rc) + return rc; + + sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); + if (sigcpu == KVM_MAX_VCPUS) { + do { + sigcpu = fi->next_rr_cpu++; + if (sigcpu == KVM_MAX_VCPUS) + sigcpu = fi->next_rr_cpu = 0; + } while (kvm_get_vcpu(kvm, sigcpu) == NULL); + } + dst_vcpu = kvm_get_vcpu(kvm, sigcpu); + li = &dst_vcpu->arch.local_int; + spin_lock(&li->lock); + switch (type) { + case KVM_S390_MCHK: + atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags); + break; + default: + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + break; + } + spin_unlock(&li->lock); + kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu)); + return 0; + +} + +int kvm_s390_inject_vm(struct kvm *kvm, + struct kvm_s390_interrupt *s390int) +{ + struct kvm_s390_interrupt_info *inti; + int rc; + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + inti->type = s390int->type; + switch (inti->type) { + case KVM_S390_INT_VIRTIO: + VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx", + s390int->parm, s390int->parm64); + inti->ext.ext_params = s390int->parm; + inti->ext.ext_params2 = s390int->parm64; + break; + case KVM_S390_INT_SERVICE: + VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm); + inti->ext.ext_params = s390int->parm; + break; + case KVM_S390_INT_PFAULT_DONE: + inti->ext.ext_params2 = s390int->parm64; + break; + case KVM_S390_MCHK: + VM_EVENT(kvm, 5, "inject: machine check parm64:%llx", + s390int->parm64); + inti->mchk.cr14 = s390int->parm; /* upper bits are not used */ + inti->mchk.mcic = s390int->parm64; + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + if (inti->type & IOINT_AI_MASK) + VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)"); + else + VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x", + s390int->type & IOINT_CSSID_MASK, + s390int->type & IOINT_SSID_MASK, + s390int->type & IOINT_SCHID_MASK); + inti->io.subchannel_id = s390int->parm >> 16; + inti->io.subchannel_nr = s390int->parm & 0x0000ffffu; + inti->io.io_int_parm = s390int->parm64 >> 32; + inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull; + break; + default: + kfree(inti); + return -EINVAL; + } + trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64, + 2); + + rc = __inject_vm(kvm, inti); + if (rc) + kfree(inti); + return rc; +} + +int kvm_s390_reinject_io_int(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + return __inject_vm(kvm, inti); +} + +int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, + struct kvm_s390_irq *irq) +{ + irq->type = s390int->type; + switch (irq->type) { + case KVM_S390_PROGRAM_INT: + if (s390int->parm & 0xffff0000) + return -EINVAL; + irq->u.pgm.code = s390int->parm; + break; + case KVM_S390_SIGP_SET_PREFIX: + irq->u.prefix.address = s390int->parm; + break; + case KVM_S390_SIGP_STOP: + irq->u.stop.flags = s390int->parm; + break; + case KVM_S390_INT_EXTERNAL_CALL: + if (s390int->parm & 0xffff0000) + return -EINVAL; + irq->u.extcall.code = s390int->parm; + break; + case KVM_S390_INT_EMERGENCY: + if (s390int->parm & 0xffff0000) + return -EINVAL; + irq->u.emerg.code = s390int->parm; + break; + case KVM_S390_MCHK: + irq->u.mchk.mcic = s390int->parm64; + break; + } + return 0; +} + +int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); +} + +void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + spin_lock(&li->lock); + li->irq.stop.flags = 0; + clear_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); + spin_unlock(&li->lock); +} + +static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + int rc; + + switch (irq->type) { + case KVM_S390_PROGRAM_INT: + VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)", + irq->u.pgm.code); + rc = __inject_prog(vcpu, irq); + break; + case KVM_S390_SIGP_SET_PREFIX: + rc = __inject_set_prefix(vcpu, irq); + break; + case KVM_S390_SIGP_STOP: + rc = __inject_sigp_stop(vcpu, irq); + break; + case KVM_S390_RESTART: + rc = __inject_sigp_restart(vcpu, irq); + break; + case KVM_S390_INT_CLOCK_COMP: + rc = __inject_ckc(vcpu); + break; + case KVM_S390_INT_CPU_TIMER: + rc = __inject_cpu_timer(vcpu); + break; + case KVM_S390_INT_EXTERNAL_CALL: + rc = __inject_extcall(vcpu, irq); + break; + case KVM_S390_INT_EMERGENCY: + rc = __inject_sigp_emergency(vcpu, irq); + break; + case KVM_S390_MCHK: + rc = __inject_mchk(vcpu, irq); + break; + case KVM_S390_INT_PFAULT_INIT: + rc = __inject_pfault_init(vcpu, irq); + break; + case KVM_S390_INT_VIRTIO: + case KVM_S390_INT_SERVICE: + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + default: + rc = -EINVAL; + } + + return rc; +} + +int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + spin_lock(&li->lock); + rc = do_inject_vcpu(vcpu, irq); + spin_unlock(&li->lock); + if (!rc) + kvm_s390_vcpu_wakeup(vcpu); + return rc; +} + +static inline void clear_irq_list(struct list_head *_list) +{ + struct kvm_s390_interrupt_info *inti, *n; + + list_for_each_entry_safe(inti, n, _list, list) { + list_del(&inti->list); + kfree(inti); + } +} + +static void inti_to_irq(struct kvm_s390_interrupt_info *inti, + struct kvm_s390_irq *irq) +{ + irq->type = inti->type; + switch (inti->type) { + case KVM_S390_INT_PFAULT_INIT: + case KVM_S390_INT_PFAULT_DONE: + case KVM_S390_INT_VIRTIO: + irq->u.ext = inti->ext; + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + irq->u.io = inti->io; + break; + } +} + +void kvm_s390_clear_float_irqs(struct kvm *kvm) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + int i; + + spin_lock(&fi->lock); + fi->pending_irqs = 0; + memset(&fi->srv_signal, 0, sizeof(fi->srv_signal)); + memset(&fi->mchk, 0, sizeof(fi->mchk)); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + clear_irq_list(&fi->lists[i]); + for (i = 0; i < FIRQ_MAX_COUNT; i++) + fi->counters[i] = 0; + spin_unlock(&fi->lock); +}; + +static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) +{ + struct kvm_s390_interrupt_info *inti; + struct kvm_s390_float_interrupt *fi; + struct kvm_s390_irq *buf; + struct kvm_s390_irq *irq; + int max_irqs; + int ret = 0; + int n = 0; + int i; + + if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0) + return -EINVAL; + + /* + * We are already using -ENOMEM to signal + * userspace it may retry with a bigger buffer, + * so we need to use something else for this case + */ + buf = vzalloc(len); + if (!buf) + return -ENOBUFS; + + max_irqs = len / sizeof(struct kvm_s390_irq); + + fi = &kvm->arch.float_int; + spin_lock(&fi->lock); + for (i = 0; i < FIRQ_LIST_COUNT; i++) { + list_for_each_entry(inti, &fi->lists[i], list) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + inti_to_irq(inti, &buf[n]); + n++; + } + } + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_INT_SERVICE; + irq->u.ext = fi->srv_signal; + n++; + } + if (test_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_MCHK; + irq->u.mchk = fi->mchk; + n++; +} + +out: + spin_unlock(&fi->lock); + if (!ret && n > 0) { + if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n)) + ret = -EFAULT; + } + vfree(buf); + + return ret < 0 ? ret : n; +} + +static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + int r; + + switch (attr->group) { + case KVM_DEV_FLIC_GET_ALL_IRQS: + r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr, + attr->attr); + break; + default: + r = -EINVAL; + } + + return r; +} + +static inline int copy_irq_from_user(struct kvm_s390_interrupt_info *inti, + u64 addr) +{ + struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr; + void *target = NULL; + void __user *source; + u64 size; + + if (get_user(inti->type, (u64 __user *)addr)) + return -EFAULT; + + switch (inti->type) { + case KVM_S390_INT_PFAULT_INIT: + case KVM_S390_INT_PFAULT_DONE: + case KVM_S390_INT_VIRTIO: + case KVM_S390_INT_SERVICE: + target = (void *) &inti->ext; + source = &uptr->u.ext; + size = sizeof(inti->ext); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + target = (void *) &inti->io; + source = &uptr->u.io; + size = sizeof(inti->io); + break; + case KVM_S390_MCHK: + target = (void *) &inti->mchk; + source = &uptr->u.mchk; + size = sizeof(inti->mchk); + break; + default: + return -EINVAL; + } + + if (copy_from_user(target, source, size)) + return -EFAULT; + + return 0; +} + +static int enqueue_floating_irq(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + struct kvm_s390_interrupt_info *inti = NULL; + int r = 0; + int len = attr->attr; + + if (len % sizeof(struct kvm_s390_irq) != 0) + return -EINVAL; + else if (len > KVM_S390_FLIC_MAX_BUFFER) + return -EINVAL; + + while (len >= sizeof(struct kvm_s390_irq)) { + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + r = copy_irq_from_user(inti, attr->addr); + if (r) { + kfree(inti); + return r; + } + r = __inject_vm(dev->kvm, inti); + if (r) { + kfree(inti); + return r; + } + len -= sizeof(struct kvm_s390_irq); + attr->addr += sizeof(struct kvm_s390_irq); + } + + return r; +} + +static struct s390_io_adapter *get_io_adapter(struct kvm *kvm, unsigned int id) +{ + if (id >= MAX_S390_IO_ADAPTERS) + return NULL; + return kvm->arch.adapters[id]; +} + +static int register_io_adapter(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + struct s390_io_adapter *adapter; + struct kvm_s390_io_adapter adapter_info; + + if (copy_from_user(&adapter_info, + (void __user *)attr->addr, sizeof(adapter_info))) + return -EFAULT; + + if ((adapter_info.id >= MAX_S390_IO_ADAPTERS) || + (dev->kvm->arch.adapters[adapter_info.id] != NULL)) + return -EINVAL; + + adapter = kzalloc(sizeof(*adapter), GFP_KERNEL); + if (!adapter) + return -ENOMEM; + + INIT_LIST_HEAD(&adapter->maps); + init_rwsem(&adapter->maps_lock); + atomic_set(&adapter->nr_maps, 0); + adapter->id = adapter_info.id; + adapter->isc = adapter_info.isc; + adapter->maskable = adapter_info.maskable; + adapter->masked = false; + adapter->swap = adapter_info.swap; + dev->kvm->arch.adapters[adapter->id] = adapter; + + return 0; +} + +int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked) +{ + int ret; + struct s390_io_adapter *adapter = get_io_adapter(kvm, id); + + if (!adapter || !adapter->maskable) + return -EINVAL; + ret = adapter->masked; + adapter->masked = masked; + return ret; +} + +static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr) +{ + struct s390_io_adapter *adapter = get_io_adapter(kvm, id); + struct s390_map_info *map; + int ret; + + if (!adapter || !addr) + return -EINVAL; + + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) { + ret = -ENOMEM; + goto out; + } + INIT_LIST_HEAD(&map->list); + map->guest_addr = addr; + map->addr = gmap_translate(kvm->arch.gmap, addr); + if (map->addr == -EFAULT) { + ret = -EFAULT; + goto out; + } + ret = get_user_pages_fast(map->addr, 1, 1, &map->page); + if (ret < 0) + goto out; + BUG_ON(ret != 1); + down_write(&adapter->maps_lock); + if (atomic_inc_return(&adapter->nr_maps) < MAX_S390_ADAPTER_MAPS) { + list_add_tail(&map->list, &adapter->maps); + ret = 0; + } else { + put_page(map->page); + ret = -EINVAL; + } + up_write(&adapter->maps_lock); +out: + if (ret) + kfree(map); + return ret; +} + +static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr) +{ + struct s390_io_adapter *adapter = get_io_adapter(kvm, id); + struct s390_map_info *map, *tmp; + int found = 0; + + if (!adapter || !addr) + return -EINVAL; + + down_write(&adapter->maps_lock); + list_for_each_entry_safe(map, tmp, &adapter->maps, list) { + if (map->guest_addr == addr) { + found = 1; + atomic_dec(&adapter->nr_maps); + list_del(&map->list); + put_page(map->page); + kfree(map); + break; + } + } + up_write(&adapter->maps_lock); + + return found ? 0 : -EINVAL; +} + +void kvm_s390_destroy_adapters(struct kvm *kvm) +{ + int i; + struct s390_map_info *map, *tmp; + + for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) { + if (!kvm->arch.adapters[i]) + continue; + list_for_each_entry_safe(map, tmp, + &kvm->arch.adapters[i]->maps, list) { + list_del(&map->list); + put_page(map->page); + kfree(map); + } + kfree(kvm->arch.adapters[i]); + } +} + +static int modify_io_adapter(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + struct kvm_s390_io_adapter_req req; + struct s390_io_adapter *adapter; + int ret; + + if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req))) + return -EFAULT; + + adapter = get_io_adapter(dev->kvm, req.id); + if (!adapter) + return -EINVAL; + switch (req.type) { + case KVM_S390_IO_ADAPTER_MASK: + ret = kvm_s390_mask_adapter(dev->kvm, req.id, req.mask); + if (ret > 0) + ret = 0; + break; + case KVM_S390_IO_ADAPTER_MAP: + ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr); + break; + case KVM_S390_IO_ADAPTER_UNMAP: + ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr); + break; + default: + ret = -EINVAL; + } + + return ret; +} + +static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + int r = 0; + unsigned int i; + struct kvm_vcpu *vcpu; + + switch (attr->group) { + case KVM_DEV_FLIC_ENQUEUE: + r = enqueue_floating_irq(dev, attr); + break; + case KVM_DEV_FLIC_CLEAR_IRQS: + kvm_s390_clear_float_irqs(dev->kvm); + break; + case KVM_DEV_FLIC_APF_ENABLE: + dev->kvm->arch.gmap->pfault_enabled = 1; + break; + case KVM_DEV_FLIC_APF_DISABLE_WAIT: + dev->kvm->arch.gmap->pfault_enabled = 0; + /* + * Make sure no async faults are in transition when + * clearing the queues. So we don't need to worry + * about late coming workers. + */ + synchronize_srcu(&dev->kvm->srcu); + kvm_for_each_vcpu(i, vcpu, dev->kvm) + kvm_clear_async_pf_completion_queue(vcpu); + break; + case KVM_DEV_FLIC_ADAPTER_REGISTER: + r = register_io_adapter(dev, attr); + break; + case KVM_DEV_FLIC_ADAPTER_MODIFY: + r = modify_io_adapter(dev, attr); + break; + default: + r = -EINVAL; + } + + return r; +} + +static int flic_create(struct kvm_device *dev, u32 type) +{ + if (!dev) + return -EINVAL; + if (dev->kvm->arch.flic) + return -EINVAL; + dev->kvm->arch.flic = dev; + return 0; +} + +static void flic_destroy(struct kvm_device *dev) +{ + dev->kvm->arch.flic = NULL; + kfree(dev); +} + +/* s390 floating irq controller (flic) */ +struct kvm_device_ops kvm_flic_ops = { + .name = "kvm-flic", + .get_attr = flic_get_attr, + .set_attr = flic_set_attr, + .create = flic_create, + .destroy = flic_destroy, +}; + +static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) +{ + unsigned long bit; + + bit = bit_nr + (addr % PAGE_SIZE) * 8; + + return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit; +} + +static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter, + u64 addr) +{ + struct s390_map_info *map; + + if (!adapter) + return NULL; + + list_for_each_entry(map, &adapter->maps, list) { + if (map->guest_addr == addr) + return map; + } + return NULL; +} + +static int adapter_indicators_set(struct kvm *kvm, + struct s390_io_adapter *adapter, + struct kvm_s390_adapter_int *adapter_int) +{ + unsigned long bit; + int summary_set, idx; + struct s390_map_info *info; + void *map; + + info = get_map_info(adapter, adapter_int->ind_addr); + if (!info) + return -1; + map = page_address(info->page); + bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap); + set_bit(bit, map); + idx = srcu_read_lock(&kvm->srcu); + mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); + set_page_dirty_lock(info->page); + info = get_map_info(adapter, adapter_int->summary_addr); + if (!info) { + srcu_read_unlock(&kvm->srcu, idx); + return -1; + } + map = page_address(info->page); + bit = get_ind_bit(info->addr, adapter_int->summary_offset, + adapter->swap); + summary_set = test_and_set_bit(bit, map); + mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); + set_page_dirty_lock(info->page); + srcu_read_unlock(&kvm->srcu, idx); + return summary_set ? 0 : 1; +} + +/* + * < 0 - not injected due to error + * = 0 - coalesced, summary indicator already active + * > 0 - injected interrupt + */ +static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + int ret; + struct s390_io_adapter *adapter; + + /* We're only interested in the 0->1 transition. */ + if (!level) + return 0; + adapter = get_io_adapter(kvm, e->adapter.adapter_id); + if (!adapter) + return -1; + down_read(&adapter->maps_lock); + ret = adapter_indicators_set(kvm, adapter, &e->adapter); + up_read(&adapter->maps_lock); + if ((ret > 0) && !adapter->masked) { + struct kvm_s390_interrupt s390int = { + .type = KVM_S390_INT_IO(1, 0, 0, 0), + .parm = 0, + .parm64 = (adapter->isc << 27) | 0x80000000, + }; + ret = kvm_s390_inject_vm(kvm, &s390int); + if (ret == 0) + ret = 1; + } + return ret; +} + +int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) +{ + int ret; + + switch (ue->type) { + case KVM_IRQ_ROUTING_S390_ADAPTER: + e->set = set_adapter_int; + e->adapter.summary_addr = ue->u.adapter.summary_addr; + e->adapter.ind_addr = ue->u.adapter.ind_addr; + e->adapter.summary_offset = ue->u.adapter.summary_offset; + e->adapter.ind_offset = ue->u.adapter.ind_offset; + e->adapter.adapter_id = ue->u.adapter.adapter_id; + ret = 0; + break; + default: + ret = -EINVAL; + } + + return ret; +} + +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status) +{ + return -EINVAL; +} + +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_irq *buf; + int r = 0; + int n; + + buf = vmalloc(len); + if (!buf) + return -ENOMEM; + + if (copy_from_user((void *) buf, irqstate, len)) { + r = -EFAULT; + goto out_free; + } + + /* + * Don't allow setting the interrupt state + * when there are already interrupts pending + */ + spin_lock(&li->lock); + if (li->pending_irqs) { + r = -EBUSY; + goto out_unlock; + } + + for (n = 0; n < len / sizeof(*buf); n++) { + r = do_inject_vcpu(vcpu, &buf[n]); + if (r) + break; + } + +out_unlock: + spin_unlock(&li->lock); +out_free: + vfree(buf); + + return r; +} + +static void store_local_irq(struct kvm_s390_local_interrupt *li, + struct kvm_s390_irq *irq, + unsigned long irq_type) +{ + switch (irq_type) { + case IRQ_PEND_MCHK_EX: + case IRQ_PEND_MCHK_REP: + irq->type = KVM_S390_MCHK; + irq->u.mchk = li->irq.mchk; + break; + case IRQ_PEND_PROG: + irq->type = KVM_S390_PROGRAM_INT; + irq->u.pgm = li->irq.pgm; + break; + case IRQ_PEND_PFAULT_INIT: + irq->type = KVM_S390_INT_PFAULT_INIT; + irq->u.ext = li->irq.ext; + break; + case IRQ_PEND_EXT_EXTERNAL: + irq->type = KVM_S390_INT_EXTERNAL_CALL; + irq->u.extcall = li->irq.extcall; + break; + case IRQ_PEND_EXT_CLOCK_COMP: + irq->type = KVM_S390_INT_CLOCK_COMP; + break; + case IRQ_PEND_EXT_CPU_TIMER: + irq->type = KVM_S390_INT_CPU_TIMER; + break; + case IRQ_PEND_SIGP_STOP: + irq->type = KVM_S390_SIGP_STOP; + irq->u.stop = li->irq.stop; + break; + case IRQ_PEND_RESTART: + irq->type = KVM_S390_RESTART; + break; + case IRQ_PEND_SET_PREFIX: + irq->type = KVM_S390_SIGP_SET_PREFIX; + irq->u.prefix = li->irq.prefix; + break; + } +} + +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) +{ + uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + unsigned long pending_irqs; + struct kvm_s390_irq irq; + unsigned long irq_type; + int cpuaddr; + int n = 0; + + spin_lock(&li->lock); + pending_irqs = li->pending_irqs; + memcpy(&sigp_emerg_pending, &li->sigp_emerg_pending, + sizeof(sigp_emerg_pending)); + spin_unlock(&li->lock); + + for_each_set_bit(irq_type, &pending_irqs, IRQ_PEND_COUNT) { + memset(&irq, 0, sizeof(irq)); + if (irq_type == IRQ_PEND_EXT_EMERGENCY) + continue; + if (n + sizeof(irq) > len) + return -ENOBUFS; + store_local_irq(&vcpu->arch.local_int, &irq, irq_type); + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + if (test_bit(IRQ_PEND_EXT_EMERGENCY, &pending_irqs)) { + for_each_set_bit(cpuaddr, sigp_emerg_pending, KVM_MAX_VCPUS) { + memset(&irq, 0, sizeof(irq)); + if (n + sizeof(irq) > len) + return -ENOBUFS; + irq.type = KVM_S390_INT_EMERGENCY; + irq.u.emerg.code = cpuaddr; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + } + + if ((sigp_ctrl & SIGP_CTRL_C) && + (atomic_read(&vcpu->arch.sie_block->cpuflags) & + CPUSTAT_ECALL_PEND)) { + if (n + sizeof(irq) > len) + return -ENOBUFS; + memset(&irq, 0, sizeof(irq)); + irq.type = KVM_S390_INT_EXTERNAL_CALL; + irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + return n; +} diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h new file mode 100644 index 000000000..d98e41596 --- /dev/null +++ b/arch/s390/kvm/irq.h @@ -0,0 +1,22 @@ +/* + * s390 irqchip routines + * + * Copyright IBM Corp. 2014 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> + */ +#ifndef __KVM_IRQ_H +#define __KVM_IRQ_H + +#include <linux/kvm_host.h> + +static inline int irqchip_in_kernel(struct kvm *kvm) +{ + return 1; +} + +#endif diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c new file mode 100644 index 000000000..8cd8e7b28 --- /dev/null +++ b/arch/s390/kvm/kvm-s390.c @@ -0,0 +1,2628 @@ +/* + * hosting zSeries kernel virtual machines + * + * Copyright IBM Corp. 2008, 2009 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + * Heiko Carstens <heiko.carstens@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> + * Jason J. Herne <jjherne@us.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/hrtimer.h> +#include <linux/init.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <linux/vmalloc.h> +#include <asm/asm-offsets.h> +#include <asm/lowcore.h> +#include <asm/pgtable.h> +#include <asm/nmi.h> +#include <asm/switch_to.h> +#include <asm/isc.h> +#include <asm/sclp.h> +#include "kvm-s390.h" +#include "gaccess.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" +#include "trace-s390.h" + +#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */ +#define LOCAL_IRQS 32 +#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ + (KVM_MAX_VCPUS + LOCAL_IRQS)) + +#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU + +struct kvm_stats_debugfs_item debugfs_entries[] = { + { "userspace_handled", VCPU_STAT(exit_userspace) }, + { "exit_null", VCPU_STAT(exit_null) }, + { "exit_validity", VCPU_STAT(exit_validity) }, + { "exit_stop_request", VCPU_STAT(exit_stop_request) }, + { "exit_external_request", VCPU_STAT(exit_external_request) }, + { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) }, + { "exit_instruction", VCPU_STAT(exit_instruction) }, + { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, + { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, + { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, + { "halt_wakeup", VCPU_STAT(halt_wakeup) }, + { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, + { "instruction_lctl", VCPU_STAT(instruction_lctl) }, + { "instruction_stctl", VCPU_STAT(instruction_stctl) }, + { "instruction_stctg", VCPU_STAT(instruction_stctg) }, + { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) }, + { "deliver_external_call", VCPU_STAT(deliver_external_call) }, + { "deliver_service_signal", VCPU_STAT(deliver_service_signal) }, + { "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) }, + { "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) }, + { "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) }, + { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, + { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, + { "exit_wait_state", VCPU_STAT(exit_wait_state) }, + { "instruction_pfmf", VCPU_STAT(instruction_pfmf) }, + { "instruction_stidp", VCPU_STAT(instruction_stidp) }, + { "instruction_spx", VCPU_STAT(instruction_spx) }, + { "instruction_stpx", VCPU_STAT(instruction_stpx) }, + { "instruction_stap", VCPU_STAT(instruction_stap) }, + { "instruction_storage_key", VCPU_STAT(instruction_storage_key) }, + { "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) }, + { "instruction_stsch", VCPU_STAT(instruction_stsch) }, + { "instruction_chsc", VCPU_STAT(instruction_chsc) }, + { "instruction_essa", VCPU_STAT(instruction_essa) }, + { "instruction_stsi", VCPU_STAT(instruction_stsi) }, + { "instruction_stfl", VCPU_STAT(instruction_stfl) }, + { "instruction_tprot", VCPU_STAT(instruction_tprot) }, + { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) }, + { "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) }, + { "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) }, + { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) }, + { "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) }, + { "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) }, + { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, + { "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) }, + { "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) }, + { "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) }, + { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, + { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, + { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, + { "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) }, + { "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) }, + { "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) }, + { "diagnose_10", VCPU_STAT(diagnose_10) }, + { "diagnose_44", VCPU_STAT(diagnose_44) }, + { "diagnose_9c", VCPU_STAT(diagnose_9c) }, + { NULL } +}; + +/* upper facilities limit for kvm */ +unsigned long kvm_s390_fac_list_mask[] = { + 0xffe6fffbfcfdfc40UL, + 0x005c800000000000UL, +}; + +unsigned long kvm_s390_fac_list_mask_size(void) +{ + BUILD_BUG_ON(ARRAY_SIZE(kvm_s390_fac_list_mask) > S390_ARCH_FAC_MASK_SIZE_U64); + return ARRAY_SIZE(kvm_s390_fac_list_mask); +} + +static struct gmap_notifier gmap_notifier; + +/* Section: not file related */ +int kvm_arch_hardware_enable(void) +{ + /* every s390 is virtualization enabled ;-) */ + return 0; +} + +static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address); + +int kvm_arch_hardware_setup(void) +{ + gmap_notifier.notifier_call = kvm_gmap_notifier; + gmap_register_ipte_notifier(&gmap_notifier); + return 0; +} + +void kvm_arch_hardware_unsetup(void) +{ + gmap_unregister_ipte_notifier(&gmap_notifier); +} + +int kvm_arch_init(void *opaque) +{ + /* Register floating interrupt controller interface. */ + return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); +} + +/* Section: device related */ +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + if (ioctl == KVM_S390_ENABLE_SIE) + return s390_enable_sie(); + return -EINVAL; +} + +int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) +{ + int r; + + switch (ext) { + case KVM_CAP_S390_PSW: + case KVM_CAP_S390_GMAP: + case KVM_CAP_SYNC_MMU: +#ifdef CONFIG_KVM_S390_UCONTROL + case KVM_CAP_S390_UCONTROL: +#endif + case KVM_CAP_ASYNC_PF: + case KVM_CAP_SYNC_REGS: + case KVM_CAP_ONE_REG: + case KVM_CAP_ENABLE_CAP: + case KVM_CAP_S390_CSS_SUPPORT: + case KVM_CAP_IOEVENTFD: + case KVM_CAP_DEVICE_CTRL: + case KVM_CAP_ENABLE_CAP_VM: + case KVM_CAP_S390_IRQCHIP: + case KVM_CAP_VM_ATTRIBUTES: + case KVM_CAP_MP_STATE: + case KVM_CAP_S390_INJECT_IRQ: + case KVM_CAP_S390_USER_SIGP: + case KVM_CAP_S390_USER_STSI: + case KVM_CAP_S390_SKEYS: + case KVM_CAP_S390_IRQ_STATE: + r = 1; + break; + case KVM_CAP_S390_MEM_OP: + r = MEM_OP_MAX_SIZE; + break; + case KVM_CAP_NR_VCPUS: + case KVM_CAP_MAX_VCPUS: + r = KVM_MAX_VCPUS; + break; + case KVM_CAP_NR_MEMSLOTS: + r = KVM_USER_MEM_SLOTS; + break; + case KVM_CAP_S390_COW: + r = MACHINE_HAS_ESOP; + break; + case KVM_CAP_S390_VECTOR_REGISTERS: + r = MACHINE_HAS_VX; + break; + default: + r = 0; + } + return r; +} + +static void kvm_s390_sync_dirty_log(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + gfn_t cur_gfn, last_gfn; + unsigned long address; + struct gmap *gmap = kvm->arch.gmap; + + down_read(&gmap->mm->mmap_sem); + /* Loop over all guest pages */ + last_gfn = memslot->base_gfn + memslot->npages; + for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) { + address = gfn_to_hva_memslot(memslot, cur_gfn); + + if (gmap_test_and_clear_dirty(address, gmap)) + mark_page_dirty(kvm, cur_gfn); + } + up_read(&gmap->mm->mmap_sem); +} + +/* Section: vm related */ +/* + * Get (and clear) the dirty memory log for a memory slot. + */ +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log) +{ + int r; + unsigned long n; + struct kvm_memory_slot *memslot; + int is_dirty = 0; + + mutex_lock(&kvm->slots_lock); + + r = -EINVAL; + if (log->slot >= KVM_USER_MEM_SLOTS) + goto out; + + memslot = id_to_memslot(kvm->memslots, log->slot); + r = -ENOENT; + if (!memslot->dirty_bitmap) + goto out; + + kvm_s390_sync_dirty_log(kvm, memslot); + r = kvm_get_dirty_log(kvm, log, &is_dirty); + if (r) + goto out; + + /* Clear the dirty log */ + if (is_dirty) { + n = kvm_dirty_bitmap_bytes(memslot); + memset(memslot->dirty_bitmap, 0, n); + } + r = 0; +out: + mutex_unlock(&kvm->slots_lock); + return r; +} + +static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_S390_IRQCHIP: + kvm->arch.use_irqchip = 1; + r = 0; + break; + case KVM_CAP_S390_USER_SIGP: + kvm->arch.user_sigp = 1; + r = 0; + break; + case KVM_CAP_S390_VECTOR_REGISTERS: + if (MACHINE_HAS_VX) { + set_kvm_facility(kvm->arch.model.fac->mask, 129); + set_kvm_facility(kvm->arch.model.fac->list, 129); + r = 0; + } else + r = -EINVAL; + break; + case KVM_CAP_S390_USER_STSI: + kvm->arch.user_stsi = 1; + r = 0; + break; + default: + r = -EINVAL; + break; + } + return r; +} + +static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + switch (attr->attr) { + case KVM_S390_VM_MEM_LIMIT_SIZE: + ret = 0; + if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr)) + ret = -EFAULT; + break; + default: + ret = -ENXIO; + break; + } + return ret; +} + +static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + unsigned int idx; + switch (attr->attr) { + case KVM_S390_VM_MEM_ENABLE_CMMA: + ret = -EBUSY; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus) == 0) { + kvm->arch.use_cmma = 1; + ret = 0; + } + mutex_unlock(&kvm->lock); + break; + case KVM_S390_VM_MEM_CLR_CMMA: + mutex_lock(&kvm->lock); + idx = srcu_read_lock(&kvm->srcu); + s390_reset_cmma(kvm->arch.gmap->mm); + srcu_read_unlock(&kvm->srcu, idx); + mutex_unlock(&kvm->lock); + ret = 0; + break; + case KVM_S390_VM_MEM_LIMIT_SIZE: { + unsigned long new_limit; + + if (kvm_is_ucontrol(kvm)) + return -EINVAL; + + if (get_user(new_limit, (u64 __user *)attr->addr)) + return -EFAULT; + + if (new_limit > kvm->arch.gmap->asce_end) + return -E2BIG; + + ret = -EBUSY; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus) == 0) { + /* gmap_alloc will round the limit up */ + struct gmap *new = gmap_alloc(current->mm, new_limit); + + if (!new) { + ret = -ENOMEM; + } else { + gmap_free(kvm->arch.gmap); + new->private = kvm; + kvm->arch.gmap = new; + ret = 0; + } + } + mutex_unlock(&kvm->lock); + break; + } + default: + ret = -ENXIO; + break; + } + return ret; +} + +static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu); + +static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_vcpu *vcpu; + int i; + + if (!test_kvm_facility(kvm, 76)) + return -EINVAL; + + mutex_lock(&kvm->lock); + switch (attr->attr) { + case KVM_S390_VM_CRYPTO_ENABLE_AES_KW: + get_random_bytes( + kvm->arch.crypto.crycb->aes_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask)); + kvm->arch.crypto.aes_kw = 1; + break; + case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW: + get_random_bytes( + kvm->arch.crypto.crycb->dea_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask)); + kvm->arch.crypto.dea_kw = 1; + break; + case KVM_S390_VM_CRYPTO_DISABLE_AES_KW: + kvm->arch.crypto.aes_kw = 0; + memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0, + sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask)); + break; + case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW: + kvm->arch.crypto.dea_kw = 0; + memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0, + sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask)); + break; + default: + mutex_unlock(&kvm->lock); + return -ENXIO; + } + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_s390_vcpu_crypto_setup(vcpu); + exit_sie(vcpu); + } + mutex_unlock(&kvm->lock); + return 0; +} + +static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) +{ + u8 gtod_high; + + if (copy_from_user(>od_high, (void __user *)attr->addr, + sizeof(gtod_high))) + return -EFAULT; + + if (gtod_high != 0) + return -EINVAL; + + return 0; +} + +static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_vcpu *cur_vcpu; + unsigned int vcpu_idx; + u64 host_tod, gtod; + int r; + + if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) + return -EFAULT; + + r = store_tod_clock(&host_tod); + if (r) + return r; + + mutex_lock(&kvm->lock); + kvm->arch.epoch = gtod - host_tod; + kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) { + cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch; + exit_sie(cur_vcpu); + } + mutex_unlock(&kvm->lock); + return 0; +} + +static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + if (attr->flags) + return -EINVAL; + + switch (attr->attr) { + case KVM_S390_VM_TOD_HIGH: + ret = kvm_s390_set_tod_high(kvm, attr); + break; + case KVM_S390_VM_TOD_LOW: + ret = kvm_s390_set_tod_low(kvm, attr); + break; + default: + ret = -ENXIO; + break; + } + return ret; +} + +static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) +{ + u8 gtod_high = 0; + + if (copy_to_user((void __user *)attr->addr, >od_high, + sizeof(gtod_high))) + return -EFAULT; + + return 0; +} + +static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) +{ + u64 host_tod, gtod; + int r; + + r = store_tod_clock(&host_tod); + if (r) + return r; + + gtod = host_tod + kvm->arch.epoch; + if (copy_to_user((void __user *)attr->addr, >od, sizeof(gtod))) + return -EFAULT; + + return 0; +} + +static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + if (attr->flags) + return -EINVAL; + + switch (attr->attr) { + case KVM_S390_VM_TOD_HIGH: + ret = kvm_s390_get_tod_high(kvm, attr); + break; + case KVM_S390_VM_TOD_LOW: + ret = kvm_s390_get_tod_low(kvm, attr); + break; + default: + ret = -ENXIO; + break; + } + return ret; +} + +static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_processor *proc; + int ret = 0; + + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus)) { + ret = -EBUSY; + goto out; + } + proc = kzalloc(sizeof(*proc), GFP_KERNEL); + if (!proc) { + ret = -ENOMEM; + goto out; + } + if (!copy_from_user(proc, (void __user *)attr->addr, + sizeof(*proc))) { + memcpy(&kvm->arch.model.cpu_id, &proc->cpuid, + sizeof(struct cpuid)); + kvm->arch.model.ibc = proc->ibc; + memcpy(kvm->arch.model.fac->list, proc->fac_list, + S390_ARCH_FAC_LIST_SIZE_BYTE); + } else + ret = -EFAULT; + kfree(proc); +out: + mutex_unlock(&kvm->lock); + return ret; +} + +static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret = -ENXIO; + + switch (attr->attr) { + case KVM_S390_VM_CPU_PROCESSOR: + ret = kvm_s390_set_processor(kvm, attr); + break; + } + return ret; +} + +static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_processor *proc; + int ret = 0; + + proc = kzalloc(sizeof(*proc), GFP_KERNEL); + if (!proc) { + ret = -ENOMEM; + goto out; + } + memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid)); + proc->ibc = kvm->arch.model.ibc; + memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE); + if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc))) + ret = -EFAULT; + kfree(proc); +out: + return ret; +} + +static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_machine *mach; + int ret = 0; + + mach = kzalloc(sizeof(*mach), GFP_KERNEL); + if (!mach) { + ret = -ENOMEM; + goto out; + } + get_cpu_id((struct cpuid *) &mach->cpuid); + mach->ibc = sclp_get_ibc(); + memcpy(&mach->fac_mask, kvm->arch.model.fac->mask, + S390_ARCH_FAC_LIST_SIZE_BYTE); + memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list, + S390_ARCH_FAC_LIST_SIZE_BYTE); + if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach))) + ret = -EFAULT; + kfree(mach); +out: + return ret; +} + +static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret = -ENXIO; + + switch (attr->attr) { + case KVM_S390_VM_CPU_PROCESSOR: + ret = kvm_s390_get_processor(kvm, attr); + break; + case KVM_S390_VM_CPU_MACHINE: + ret = kvm_s390_get_machine(kvm, attr); + break; + } + return ret; +} + +static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + switch (attr->group) { + case KVM_S390_VM_MEM_CTRL: + ret = kvm_s390_set_mem_control(kvm, attr); + break; + case KVM_S390_VM_TOD: + ret = kvm_s390_set_tod(kvm, attr); + break; + case KVM_S390_VM_CPU_MODEL: + ret = kvm_s390_set_cpu_model(kvm, attr); + break; + case KVM_S390_VM_CRYPTO: + ret = kvm_s390_vm_set_crypto(kvm, attr); + break; + default: + ret = -ENXIO; + break; + } + + return ret; +} + +static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + switch (attr->group) { + case KVM_S390_VM_MEM_CTRL: + ret = kvm_s390_get_mem_control(kvm, attr); + break; + case KVM_S390_VM_TOD: + ret = kvm_s390_get_tod(kvm, attr); + break; + case KVM_S390_VM_CPU_MODEL: + ret = kvm_s390_get_cpu_model(kvm, attr); + break; + default: + ret = -ENXIO; + break; + } + + return ret; +} + +static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + int ret; + + switch (attr->group) { + case KVM_S390_VM_MEM_CTRL: + switch (attr->attr) { + case KVM_S390_VM_MEM_ENABLE_CMMA: + case KVM_S390_VM_MEM_CLR_CMMA: + case KVM_S390_VM_MEM_LIMIT_SIZE: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + case KVM_S390_VM_TOD: + switch (attr->attr) { + case KVM_S390_VM_TOD_LOW: + case KVM_S390_VM_TOD_HIGH: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + case KVM_S390_VM_CPU_MODEL: + switch (attr->attr) { + case KVM_S390_VM_CPU_PROCESSOR: + case KVM_S390_VM_CPU_MACHINE: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + case KVM_S390_VM_CRYPTO: + switch (attr->attr) { + case KVM_S390_VM_CRYPTO_ENABLE_AES_KW: + case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW: + case KVM_S390_VM_CRYPTO_DISABLE_AES_KW: + case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW: + ret = 0; + break; + default: + ret = -ENXIO; + break; + } + break; + default: + ret = -ENXIO; + break; + } + + return ret; +} + +static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + unsigned long curkey; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Is this guest using storage keys? */ + if (!mm_use_skey(current->mm)) + return KVM_S390_GET_SKEYS_NONE; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + curkey = get_guest_storage_key(current->mm, hva); + if (IS_ERR_VALUE(curkey)) { + r = curkey; + goto out; + } + keys[i] = curkey; + } + + r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys, + sizeof(uint8_t) * args->count); + if (r) + r = -EFAULT; +out: + kvfree(keys); + return r; +} + +static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr, + sizeof(uint8_t) * args->count); + if (r) { + r = -EFAULT; + goto out; + } + + /* Enable storage key handling for the guest */ + s390_enable_skey(); + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + /* Lowest order bit is reserved */ + if (keys[i] & 0x01) { + r = -EINVAL; + goto out; + } + + r = set_guest_storage_key(current->mm, hva, + (unsigned long)keys[i], 0); + if (r) + goto out; + } +out: + kvfree(keys); + return r; +} + +long kvm_arch_vm_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + void __user *argp = (void __user *)arg; + struct kvm_device_attr attr; + int r; + + switch (ioctl) { + case KVM_S390_INTERRUPT: { + struct kvm_s390_interrupt s390int; + + r = -EFAULT; + if (copy_from_user(&s390int, argp, sizeof(s390int))) + break; + r = kvm_s390_inject_vm(kvm, &s390int); + break; + } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + break; + r = kvm_vm_ioctl_enable_cap(kvm, &cap); + break; + } + case KVM_CREATE_IRQCHIP: { + struct kvm_irq_routing_entry routing; + + r = -EINVAL; + if (kvm->arch.use_irqchip) { + /* Set up dummy routing. */ + memset(&routing, 0, sizeof(routing)); + kvm_set_irq_routing(kvm, &routing, 0, 0); + r = 0; + } + break; + } + case KVM_SET_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_s390_vm_set_attr(kvm, &attr); + break; + } + case KVM_GET_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_s390_vm_get_attr(kvm, &attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_s390_vm_has_attr(kvm, &attr); + break; + } + case KVM_S390_GET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_get_skeys(kvm, &args); + break; + } + case KVM_S390_SET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_set_skeys(kvm, &args); + break; + } + default: + r = -ENOTTY; + } + + return r; +} + +static int kvm_s390_query_ap_config(u8 *config) +{ + u32 fcn_code = 0x04000000UL; + u32 cc = 0; + + memset(config, 0, 128); + asm volatile( + "lgr 0,%1\n" + "lgr 2,%2\n" + ".long 0xb2af0000\n" /* PQAP(QCI) */ + "0: ipm %0\n" + "srl %0,28\n" + "1:\n" + EX_TABLE(0b, 1b) + : "+r" (cc) + : "r" (fcn_code), "r" (config) + : "cc", "0", "2", "memory" + ); + + return cc; +} + +static int kvm_s390_apxa_installed(void) +{ + u8 config[128]; + int cc; + + if (test_facility(2) && test_facility(12)) { + cc = kvm_s390_query_ap_config(config); + + if (cc) + pr_err("PQAP(QCI) failed with cc=%d", cc); + else + return config[0] & 0x40; + } + + return 0; +} + +static void kvm_s390_set_crycb_format(struct kvm *kvm) +{ + kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb; + + if (kvm_s390_apxa_installed()) + kvm->arch.crypto.crycbd |= CRYCB_FORMAT2; + else + kvm->arch.crypto.crycbd |= CRYCB_FORMAT1; +} + +static void kvm_s390_get_cpu_id(struct cpuid *cpu_id) +{ + get_cpu_id(cpu_id); + cpu_id->version = 0xff; +} + +static int kvm_s390_crypto_init(struct kvm *kvm) +{ + if (!test_kvm_facility(kvm, 76)) + return 0; + + kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb), + GFP_KERNEL | GFP_DMA); + if (!kvm->arch.crypto.crycb) + return -ENOMEM; + + kvm_s390_set_crycb_format(kvm); + + /* Enable AES/DEA protected key functions by default */ + kvm->arch.crypto.aes_kw = 1; + kvm->arch.crypto.dea_kw = 1; + get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask)); + get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask, + sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask)); + + return 0; +} + +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) +{ + int i, rc; + char debug_name[16]; + static unsigned long sca_offset; + + rc = -EINVAL; +#ifdef CONFIG_KVM_S390_UCONTROL + if (type & ~KVM_VM_S390_UCONTROL) + goto out_err; + if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN))) + goto out_err; +#else + if (type) + goto out_err; +#endif + + rc = s390_enable_sie(); + if (rc) + goto out_err; + + rc = -ENOMEM; + + kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL); + if (!kvm->arch.sca) + goto out_err; + spin_lock(&kvm_lock); + sca_offset = (sca_offset + 16) & 0x7f0; + kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset); + spin_unlock(&kvm_lock); + + sprintf(debug_name, "kvm-%u", current->pid); + + kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long)); + if (!kvm->arch.dbf) + goto out_err; + + /* + * The architectural maximum amount of facilities is 16 kbit. To store + * this amount, 2 kbyte of memory is required. Thus we need a full + * page to hold the guest facility list (arch.model.fac->list) and the + * facility mask (arch.model.fac->mask). Its address size has to be + * 31 bits and word aligned. + */ + kvm->arch.model.fac = + (struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!kvm->arch.model.fac) + goto out_err; + + /* Populate the facility mask initially. */ + memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list, + S390_ARCH_FAC_LIST_SIZE_BYTE); + for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) { + if (i < kvm_s390_fac_list_mask_size()) + kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i]; + else + kvm->arch.model.fac->mask[i] = 0UL; + } + + /* Populate the facility list initially. */ + memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask, + S390_ARCH_FAC_LIST_SIZE_BYTE); + + kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id); + kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff; + + if (kvm_s390_crypto_init(kvm) < 0) + goto out_err; + + spin_lock_init(&kvm->arch.float_int.lock); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]); + init_waitqueue_head(&kvm->arch.ipte_wq); + mutex_init(&kvm->arch.ipte_mutex); + + debug_register_view(kvm->arch.dbf, &debug_sprintf_view); + VM_EVENT(kvm, 3, "%s", "vm created"); + + if (type & KVM_VM_S390_UCONTROL) { + kvm->arch.gmap = NULL; + } else { + kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1); + if (!kvm->arch.gmap) + goto out_err; + kvm->arch.gmap->private = kvm; + kvm->arch.gmap->pfault_enabled = 0; + } + + kvm->arch.css_support = 0; + kvm->arch.use_irqchip = 0; + kvm->arch.epoch = 0; + + spin_lock_init(&kvm->arch.start_stop_lock); + + return 0; +out_err: + kfree(kvm->arch.crypto.crycb); + free_page((unsigned long)kvm->arch.model.fac); + debug_unregister(kvm->arch.dbf); + free_page((unsigned long)(kvm->arch.sca)); + return rc; +} + +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 3, "%s", "free cpu"); + trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id); + kvm_s390_clear_local_irqs(vcpu); + kvm_clear_async_pf_completion_queue(vcpu); + if (!kvm_is_ucontrol(vcpu->kvm)) { + clear_bit(63 - vcpu->vcpu_id, + (unsigned long *) &vcpu->kvm->arch.sca->mcn); + if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda == + (__u64) vcpu->arch.sie_block) + vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0; + } + smp_mb(); + + if (kvm_is_ucontrol(vcpu->kvm)) + gmap_free(vcpu->arch.gmap); + + if (kvm_s390_cmma_enabled(vcpu->kvm)) + kvm_s390_vcpu_unsetup_cmma(vcpu); + free_page((unsigned long)(vcpu->arch.sie_block)); + + kvm_vcpu_uninit(vcpu); + kmem_cache_free(kvm_vcpu_cache, vcpu); +} + +static void kvm_free_vcpus(struct kvm *kvm) +{ + unsigned int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_arch_vcpu_destroy(vcpu); + + mutex_lock(&kvm->lock); + for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) + kvm->vcpus[i] = NULL; + + atomic_set(&kvm->online_vcpus, 0); + mutex_unlock(&kvm->lock); +} + +void kvm_arch_destroy_vm(struct kvm *kvm) +{ + kvm_free_vcpus(kvm); + free_page((unsigned long)kvm->arch.model.fac); + free_page((unsigned long)(kvm->arch.sca)); + debug_unregister(kvm->arch.dbf); + kfree(kvm->arch.crypto.crycb); + if (!kvm_is_ucontrol(kvm)) + gmap_free(kvm->arch.gmap); + kvm_s390_destroy_adapters(kvm); + kvm_s390_clear_float_irqs(kvm); +} + +/* Section: vcpu related */ +static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu) +{ + vcpu->arch.gmap = gmap_alloc(current->mm, -1UL); + if (!vcpu->arch.gmap) + return -ENOMEM; + vcpu->arch.gmap->private = vcpu->kvm; + + return 0; +} + +int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + kvm_clear_async_pf_completion_queue(vcpu); + vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | + KVM_SYNC_GPRS | + KVM_SYNC_ACRS | + KVM_SYNC_CRS | + KVM_SYNC_ARCH0 | + KVM_SYNC_PFAULT; + if (test_kvm_facility(vcpu->kvm, 129)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; + + if (kvm_is_ucontrol(vcpu->kvm)) + return __kvm_ucontrol_vcpu_init(vcpu); + + return 0; +} + +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + save_fp_ctl(&vcpu->arch.host_fpregs.fpc); + if (test_kvm_facility(vcpu->kvm, 129)) + save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + save_fp_regs(vcpu->arch.host_fpregs.fprs); + save_access_regs(vcpu->arch.host_acrs); + if (test_kvm_facility(vcpu->kvm, 129)) { + restore_fp_ctl(&vcpu->run->s.regs.fpc); + restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + restore_fp_regs(vcpu->arch.guest_fpregs.fprs); + } + restore_access_regs(vcpu->run->s.regs.acrs); + gmap_enable(vcpu->arch.gmap); + atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); +} + +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + gmap_disable(vcpu->arch.gmap); + if (test_kvm_facility(vcpu->kvm, 129)) { + save_fp_ctl(&vcpu->run->s.regs.fpc); + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + save_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + save_fp_regs(vcpu->arch.guest_fpregs.fprs); + } + save_access_regs(vcpu->run->s.regs.acrs); + restore_fp_ctl(&vcpu->arch.host_fpregs.fpc); + if (test_kvm_facility(vcpu->kvm, 129)) + restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + restore_fp_regs(vcpu->arch.host_fpregs.fprs); + restore_access_regs(vcpu->arch.host_acrs); +} + +static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) +{ + /* this equals initial cpu reset in pop, but we don't switch to ESA */ + vcpu->arch.sie_block->gpsw.mask = 0UL; + vcpu->arch.sie_block->gpsw.addr = 0UL; + kvm_s390_set_prefix(vcpu, 0); + vcpu->arch.sie_block->cputm = 0UL; + vcpu->arch.sie_block->ckc = 0UL; + vcpu->arch.sie_block->todpr = 0; + memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); + vcpu->arch.sie_block->gcr[0] = 0xE0UL; + vcpu->arch.sie_block->gcr[14] = 0xC2000000UL; + vcpu->arch.guest_fpregs.fpc = 0; + asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); + vcpu->arch.sie_block->gbea = 1; + vcpu->arch.sie_block->pp = 0; + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + kvm_clear_async_pf_completion_queue(vcpu); + if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) + kvm_s390_vcpu_stop(vcpu); + kvm_s390_clear_local_irqs(vcpu); +} + +void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + mutex_lock(&vcpu->kvm->lock); + vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch; + mutex_unlock(&vcpu->kvm->lock); + if (!kvm_is_ucontrol(vcpu->kvm)) + vcpu->arch.gmap = vcpu->kvm->arch.gmap; +} + +static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) +{ + if (!test_kvm_facility(vcpu->kvm, 76)) + return; + + vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA); + + if (vcpu->kvm->arch.crypto.aes_kw) + vcpu->arch.sie_block->ecb3 |= ECB3_AES; + if (vcpu->kvm->arch.crypto.dea_kw) + vcpu->arch.sie_block->ecb3 |= ECB3_DEA; + + vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd; +} + +void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu) +{ + free_page(vcpu->arch.sie_block->cbrlo); + vcpu->arch.sie_block->cbrlo = 0; +} + +int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) +{ + vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL); + if (!vcpu->arch.sie_block->cbrlo) + return -ENOMEM; + + vcpu->arch.sie_block->ecb2 |= 0x80; + vcpu->arch.sie_block->ecb2 &= ~0x08; + return 0; +} + +static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model; + + vcpu->arch.cpu_id = model->cpu_id; + vcpu->arch.sie_block->ibc = model->ibc; + vcpu->arch.sie_block->fac = (int) (long) model->fac->list; +} + +int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +{ + int rc = 0; + + atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | + CPUSTAT_SM | + CPUSTAT_STOPPED | + CPUSTAT_GED); + kvm_s390_vcpu_setup_model(vcpu); + + vcpu->arch.sie_block->ecb = 6; + if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73)) + vcpu->arch.sie_block->ecb |= 0x10; + + vcpu->arch.sie_block->ecb2 = 8; + vcpu->arch.sie_block->eca = 0xC1002000U; + if (sclp_has_siif()) + vcpu->arch.sie_block->eca |= 1; + if (sclp_has_sigpif()) + vcpu->arch.sie_block->eca |= 0x10000000U; + if (test_kvm_facility(vcpu->kvm, 129)) { + vcpu->arch.sie_block->eca |= 0x00020000; + vcpu->arch.sie_block->ecd |= 0x20000000; + } + vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; + + if (kvm_s390_cmma_enabled(vcpu->kvm)) { + rc = kvm_s390_vcpu_setup_cmma(vcpu); + if (rc) + return rc; + } + hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup; + + kvm_s390_vcpu_crypto_setup(vcpu); + + return rc; +} + +struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, + unsigned int id) +{ + struct kvm_vcpu *vcpu; + struct sie_page *sie_page; + int rc = -EINVAL; + + if (id >= KVM_MAX_VCPUS) + goto out; + + rc = -ENOMEM; + + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + if (!vcpu) + goto out; + + sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL); + if (!sie_page) + goto out_free_cpu; + + vcpu->arch.sie_block = &sie_page->sie_block; + vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; + vcpu->arch.host_vregs = &sie_page->vregs; + + vcpu->arch.sie_block->icpua = id; + if (!kvm_is_ucontrol(kvm)) { + if (!kvm->arch.sca) { + WARN_ON_ONCE(1); + goto out_free_cpu; + } + if (!kvm->arch.sca->cpu[id].sda) + kvm->arch.sca->cpu[id].sda = + (__u64) vcpu->arch.sie_block; + vcpu->arch.sie_block->scaoh = + (__u32)(((__u64)kvm->arch.sca) >> 32); + vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; + set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn); + } + + spin_lock_init(&vcpu->arch.local_int.lock); + vcpu->arch.local_int.float_int = &kvm->arch.float_int; + vcpu->arch.local_int.wq = &vcpu->wq; + vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; + + rc = kvm_vcpu_init(vcpu, kvm, id); + if (rc) + goto out_free_sie_block; + VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu, + vcpu->arch.sie_block); + trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block); + + return vcpu; +out_free_sie_block: + free_page((unsigned long)(vcpu->arch.sie_block)); +out_free_cpu: + kmem_cache_free(kvm_vcpu_cache, vcpu); +out: + return ERR_PTR(rc); +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_s390_vcpu_has_irq(vcpu, 0); +} + +void s390_vcpu_block(struct kvm_vcpu *vcpu) +{ + atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); +} + +void s390_vcpu_unblock(struct kvm_vcpu *vcpu) +{ + atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20); +} + +/* + * Kick a guest cpu out of SIE and wait until SIE is not running. + * If the CPU is not running (e.g. waiting as idle) the function will + * return immediately. */ +void exit_sie(struct kvm_vcpu *vcpu) +{ + atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags); + while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE) + cpu_relax(); +} + +/* Kick a guest cpu out of SIE and prevent SIE-reentry */ +void exit_sie_sync(struct kvm_vcpu *vcpu) +{ + s390_vcpu_block(vcpu); + exit_sie(vcpu); +} + +static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address) +{ + int i; + struct kvm *kvm = gmap->private; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + /* match against both prefix pages */ + if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) { + VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address); + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + exit_sie_sync(vcpu); + } + } +} + +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + /* kvm common code refers to this, but never calls it */ + BUG(); + return 0; +} + +static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, + struct kvm_one_reg *reg) +{ + int r = -EINVAL; + + switch (reg->id) { + case KVM_REG_S390_TODPR: + r = put_user(vcpu->arch.sie_block->todpr, + (u32 __user *)reg->addr); + break; + case KVM_REG_S390_EPOCHDIFF: + r = put_user(vcpu->arch.sie_block->epoch, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_CPU_TIMER: + r = put_user(vcpu->arch.sie_block->cputm, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_CLOCK_COMP: + r = put_user(vcpu->arch.sie_block->ckc, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_PFTOKEN: + r = put_user(vcpu->arch.pfault_token, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_PFCOMPARE: + r = put_user(vcpu->arch.pfault_compare, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_PFSELECT: + r = put_user(vcpu->arch.pfault_select, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_PP: + r = put_user(vcpu->arch.sie_block->pp, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_GBEA: + r = put_user(vcpu->arch.sie_block->gbea, + (u64 __user *)reg->addr); + break; + default: + break; + } + + return r; +} + +static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, + struct kvm_one_reg *reg) +{ + int r = -EINVAL; + + switch (reg->id) { + case KVM_REG_S390_TODPR: + r = get_user(vcpu->arch.sie_block->todpr, + (u32 __user *)reg->addr); + break; + case KVM_REG_S390_EPOCHDIFF: + r = get_user(vcpu->arch.sie_block->epoch, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_CPU_TIMER: + r = get_user(vcpu->arch.sie_block->cputm, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_CLOCK_COMP: + r = get_user(vcpu->arch.sie_block->ckc, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_PFTOKEN: + r = get_user(vcpu->arch.pfault_token, + (u64 __user *)reg->addr); + if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) + kvm_clear_async_pf_completion_queue(vcpu); + break; + case KVM_REG_S390_PFCOMPARE: + r = get_user(vcpu->arch.pfault_compare, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_PFSELECT: + r = get_user(vcpu->arch.pfault_select, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_PP: + r = get_user(vcpu->arch.sie_block->pp, + (u64 __user *)reg->addr); + break; + case KVM_REG_S390_GBEA: + r = get_user(vcpu->arch.sie_block->gbea, + (u64 __user *)reg->addr); + break; + default: + break; + } + + return r; +} + +static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) +{ + kvm_s390_vcpu_initial_reset(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + memcpy(&vcpu->run->s.regs.gprs, ®s->gprs, sizeof(regs->gprs)); + return 0; +} + +int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + memcpy(®s->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs)); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs)); + memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs)); + restore_access_regs(vcpu->run->s.regs.acrs); + return 0; +} + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs)); + memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs)); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + if (test_fp_ctl(fpu->fpc)) + return -EINVAL; + memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); + vcpu->arch.guest_fpregs.fpc = fpu->fpc; + restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + restore_fp_regs(vcpu->arch.guest_fpregs.fprs); + return 0; +} + +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs)); + fpu->fpc = vcpu->arch.guest_fpregs.fpc; + return 0; +} + +static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw) +{ + int rc = 0; + + if (!is_vcpu_stopped(vcpu)) + rc = -EBUSY; + else { + vcpu->run->psw_mask = psw.mask; + vcpu->run->psw_addr = psw.addr; + } + return rc; +} + +int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, + struct kvm_translation *tr) +{ + return -EINVAL; /* not implemented yet */ +} + +#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \ + KVM_GUESTDBG_USE_HW_BP | \ + KVM_GUESTDBG_ENABLE) + +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + int rc = 0; + + vcpu->guest_debug = 0; + kvm_s390_clear_bp_data(vcpu); + + if (dbg->control & ~VALID_GUESTDBG_FLAGS) + return -EINVAL; + + if (dbg->control & KVM_GUESTDBG_ENABLE) { + vcpu->guest_debug = dbg->control; + /* enforce guest PER */ + atomic_set_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + + if (dbg->control & KVM_GUESTDBG_USE_HW_BP) + rc = kvm_s390_import_bp_data(vcpu, dbg); + } else { + atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + vcpu->arch.guestdbg.last_bp = 0; + } + + if (rc) { + vcpu->guest_debug = 0; + kvm_s390_clear_bp_data(vcpu); + atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + } + + return rc; +} + +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + /* CHECK_STOP and LOAD are not supported yet */ + return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED : + KVM_MP_STATE_OPERATING; +} + +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + int rc = 0; + + /* user space knows about this interface - let it control the state */ + vcpu->kvm->arch.user_cpu_state_ctrl = 1; + + switch (mp_state->mp_state) { + case KVM_MP_STATE_STOPPED: + kvm_s390_vcpu_stop(vcpu); + break; + case KVM_MP_STATE_OPERATING: + kvm_s390_vcpu_start(vcpu); + break; + case KVM_MP_STATE_LOAD: + case KVM_MP_STATE_CHECK_STOP: + /* fall through - CHECK_STOP and LOAD are not supported yet */ + default: + rc = -ENXIO; + } + + return rc; +} + +bool kvm_s390_cmma_enabled(struct kvm *kvm) +{ + if (!MACHINE_IS_LPAR) + return false; + /* only enable for z10 and later */ + if (!MACHINE_HAS_EDAT1) + return false; + if (!kvm->arch.use_cmma) + return false; + return true; +} + +static bool ibs_enabled(struct kvm_vcpu *vcpu) +{ + return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS; +} + +static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) +{ +retry: + s390_vcpu_unblock(vcpu); + /* + * We use MMU_RELOAD just to re-arm the ipte notifier for the + * guest prefix page. gmap_ipte_notify will wait on the ptl lock. + * This ensures that the ipte instruction for this request has + * already finished. We might race against a second unmapper that + * wants to set the blocking bit. Lets just retry the request loop. + */ + if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) { + int rc; + rc = gmap_ipte_notify(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu), + PAGE_SIZE * 2); + if (rc) + return rc; + goto retry; + } + + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) { + vcpu->arch.sie_block->ihcpu = 0xffff; + goto retry; + } + + if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) { + if (!ibs_enabled(vcpu)) { + trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1); + atomic_set_mask(CPUSTAT_IBS, + &vcpu->arch.sie_block->cpuflags); + } + goto retry; + } + + if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) { + if (ibs_enabled(vcpu)) { + trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0); + atomic_clear_mask(CPUSTAT_IBS, + &vcpu->arch.sie_block->cpuflags); + } + goto retry; + } + + /* nothing to do, just clear the request */ + clear_bit(KVM_REQ_UNHALT, &vcpu->requests); + + return 0; +} + +/** + * kvm_arch_fault_in_page - fault-in guest page if necessary + * @vcpu: The corresponding virtual cpu + * @gpa: Guest physical address + * @writable: Whether the page should be writable or not + * + * Make sure that a guest page has been faulted-in on the host. + * + * Return: Zero on success, negative error code otherwise. + */ +long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable) +{ + return gmap_fault(vcpu->arch.gmap, gpa, + writable ? FAULT_FLAG_WRITE : 0); +} + +static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token, + unsigned long token) +{ + struct kvm_s390_interrupt inti; + struct kvm_s390_irq irq; + + if (start_token) { + irq.u.ext.ext_params2 = token; + irq.type = KVM_S390_INT_PFAULT_INIT; + WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq)); + } else { + inti.type = KVM_S390_INT_PFAULT_DONE; + inti.parm64 = token; + WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti)); + } +} + +void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ + trace_kvm_s390_pfault_init(vcpu, work->arch.pfault_token); + __kvm_inject_pfault_token(vcpu, true, work->arch.pfault_token); +} + +void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ + trace_kvm_s390_pfault_done(vcpu, work->arch.pfault_token); + __kvm_inject_pfault_token(vcpu, false, work->arch.pfault_token); +} + +void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ + /* s390 will always inject the page directly */ +} + +bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +{ + /* + * s390 will always inject the page directly, + * but we still want check_async_completion to cleanup + */ + return true; +} + +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu) +{ + hva_t hva; + struct kvm_arch_async_pf arch; + int rc; + + if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) + return 0; + if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) != + vcpu->arch.pfault_compare) + return 0; + if (psw_extint_disabled(vcpu)) + return 0; + if (kvm_s390_vcpu_has_irq(vcpu, 0)) + return 0; + if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul)) + return 0; + if (!vcpu->arch.gmap->pfault_enabled) + return 0; + + hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr)); + hva += current->thread.gmap_addr & ~PAGE_MASK; + if (read_guest_real(vcpu, vcpu->arch.pfault_token, &arch.pfault_token, 8)) + return 0; + + rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch); + return rc; +} + +static int vcpu_pre_run(struct kvm_vcpu *vcpu) +{ + int rc, cpuflags; + + /* + * On s390 notifications for arriving pages will be delivered directly + * to the guest but the house keeping for completed pfaults is + * handled outside the worker. + */ + kvm_check_async_pf_completion(vcpu); + + memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16); + + if (need_resched()) + schedule(); + + if (test_cpu_flag(CIF_MCCK_PENDING)) + s390_handle_mcck(); + + if (!kvm_is_ucontrol(vcpu->kvm)) { + rc = kvm_s390_deliver_pending_interrupts(vcpu); + if (rc) + return rc; + } + + rc = kvm_s390_handle_requests(vcpu); + if (rc) + return rc; + + if (guestdbg_enabled(vcpu)) { + kvm_s390_backup_guest_per_regs(vcpu); + kvm_s390_patch_guest_per_regs(vcpu); + } + + vcpu->arch.sie_block->icptcode = 0; + cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); + VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags); + trace_kvm_s390_sie_enter(vcpu, cpuflags); + + return 0; +} + +static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + u8 opcode; + int rc; + + VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); + trace_kvm_s390_sie_fault(vcpu); + + /* + * We want to inject an addressing exception, which is defined as a + * suppressing or terminating exception. However, since we came here + * by a DAT access exception, the PSW still points to the faulting + * instruction since DAT exceptions are nullifying. So we've got + * to look up the current opcode to get the length of the instruction + * to be able to forward the PSW. + */ + rc = read_guest(vcpu, psw->addr, 0, &opcode, 1); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + psw->addr = __rewind_psw(*psw, -insn_length(opcode)); + + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); +} + +static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) +{ + int rc = -1; + + VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", + vcpu->arch.sie_block->icptcode); + trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode); + + if (guestdbg_enabled(vcpu)) + kvm_s390_restore_guest_per_regs(vcpu); + + if (exit_reason >= 0) { + rc = 0; + } else if (kvm_is_ucontrol(vcpu->kvm)) { + vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; + vcpu->run->s390_ucontrol.trans_exc_code = + current->thread.gmap_addr; + vcpu->run->s390_ucontrol.pgm_code = 0x10; + rc = -EREMOTE; + + } else if (current->thread.gmap_pfault) { + trace_kvm_s390_major_guest_pfault(vcpu); + current->thread.gmap_pfault = 0; + if (kvm_arch_setup_async_pf(vcpu)) { + rc = 0; + } else { + gpa_t gpa = current->thread.gmap_addr; + rc = kvm_arch_fault_in_page(vcpu, gpa, 1); + } + } + + if (rc == -1) + rc = vcpu_post_run_fault_in_sie(vcpu); + + memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16); + + if (rc == 0) { + if (kvm_is_ucontrol(vcpu->kvm)) + /* Don't exit for host interrupts. */ + rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0; + else + rc = kvm_handle_sie_intercept(vcpu); + } + + return rc; +} + +static int __vcpu_run(struct kvm_vcpu *vcpu) +{ + int rc, exit_reason; + + /* + * We try to hold kvm->srcu during most of vcpu_run (except when run- + * ning the guest), so that memslots (and other stuff) are protected + */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + do { + rc = vcpu_pre_run(vcpu); + if (rc) + break; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + /* + * As PF_VCPU will be used in fault handler, between + * guest_enter and guest_exit should be no uaccess. + */ + preempt_disable(); + kvm_guest_enter(); + preempt_enable(); + exit_reason = sie64a(vcpu->arch.sie_block, + vcpu->run->s.regs.gprs); + kvm_guest_exit(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + rc = vcpu_post_run(vcpu, exit_reason); + } while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc); + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + return rc; +} + +static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask; + vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr; + if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) + kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix); + if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) { + memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128); + /* some control register changes require a tlb flush */ + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + } + if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) { + vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm; + vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc; + vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr; + vcpu->arch.sie_block->pp = kvm_run->s.regs.pp; + vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea; + } + if (kvm_run->kvm_dirty_regs & KVM_SYNC_PFAULT) { + vcpu->arch.pfault_token = kvm_run->s.regs.pft; + vcpu->arch.pfault_select = kvm_run->s.regs.pfs; + vcpu->arch.pfault_compare = kvm_run->s.regs.pfc; + if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) + kvm_clear_async_pf_completion_queue(vcpu); + } + kvm_run->kvm_dirty_regs = 0; +} + +static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask; + kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr; + kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu); + memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128); + kvm_run->s.regs.cputm = vcpu->arch.sie_block->cputm; + kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc; + kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr; + kvm_run->s.regs.pp = vcpu->arch.sie_block->pp; + kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea; + kvm_run->s.regs.pft = vcpu->arch.pfault_token; + kvm_run->s.regs.pfs = vcpu->arch.pfault_select; + kvm_run->s.regs.pfc = vcpu->arch.pfault_compare; +} + +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + int rc; + sigset_t sigsaved; + + if (guestdbg_exit_pending(vcpu)) { + kvm_s390_prepare_debug_exit(vcpu); + return 0; + } + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); + + if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) { + kvm_s390_vcpu_start(vcpu); + } else if (is_vcpu_stopped(vcpu)) { + pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n", + vcpu->vcpu_id); + return -EINVAL; + } + + sync_regs(vcpu, kvm_run); + + might_fault(); + rc = __vcpu_run(vcpu); + + if (signal_pending(current) && !rc) { + kvm_run->exit_reason = KVM_EXIT_INTR; + rc = -EINTR; + } + + if (guestdbg_exit_pending(vcpu) && !rc) { + kvm_s390_prepare_debug_exit(vcpu); + rc = 0; + } + + if (rc == -EOPNOTSUPP) { + /* intercept cannot be handled in-kernel, prepare kvm-run */ + kvm_run->exit_reason = KVM_EXIT_S390_SIEIC; + kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode; + kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; + kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; + rc = 0; + } + + if (rc == -EREMOTE) { + /* intercept was handled, but userspace support is needed + * kvm_run has been prepared by the handler */ + rc = 0; + } + + store_regs(vcpu, kvm_run); + + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + vcpu->stat.exit_userspace++; + return rc; +} + +/* + * store status at address + * we use have two special cases: + * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit + * KVM_S390_STORE_STATUS_PREFIXED: -> prefix + */ +int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) +{ + unsigned char archmode = 1; + unsigned int px; + u64 clkcomp; + int rc; + + if (gpa == KVM_S390_STORE_STATUS_NOADDR) { + if (write_guest_abs(vcpu, 163, &archmode, 1)) + return -EFAULT; + gpa = SAVE_AREA_BASE; + } else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) { + if (write_guest_real(vcpu, 163, &archmode, 1)) + return -EFAULT; + gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE); + } + rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs), + vcpu->arch.guest_fpregs.fprs, 128); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs), + vcpu->run->s.regs.gprs, 128); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw), + &vcpu->arch.sie_block->gpsw, 16); + px = kvm_s390_get_prefix(vcpu); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg), + &px, 4); + rc |= write_guest_abs(vcpu, + gpa + offsetof(struct save_area, fp_ctrl_reg), + &vcpu->arch.guest_fpregs.fpc, 4); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg), + &vcpu->arch.sie_block->todpr, 4); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer), + &vcpu->arch.sie_block->cputm, 8); + clkcomp = vcpu->arch.sie_block->ckc >> 8; + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp), + &clkcomp, 8); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs), + &vcpu->run->s.regs.acrs, 64); + rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs), + &vcpu->arch.sie_block->gcr, 128); + return rc ? -EFAULT : 0; +} + +int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) +{ + /* + * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy + * copying in vcpu load/put. Lets update our copies before we save + * it into the save area + */ + save_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + save_fp_regs(vcpu->arch.guest_fpregs.fprs); + save_access_regs(vcpu->run->s.regs.acrs); + + return kvm_s390_store_status_unloaded(vcpu, addr); +} + +/* + * store additional status at address + */ +int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long gpa) +{ + /* Only bits 0-53 are used for address formation */ + if (!(gpa & ~0x3ff)) + return 0; + + return write_guest_abs(vcpu, gpa & ~0x3ff, + (void *)&vcpu->run->s.regs.vrs, 512); +} + +int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr) +{ + if (!test_kvm_facility(vcpu->kvm, 129)) + return 0; + + /* + * The guest VXRS are in the host VXRs due to the lazy + * copying in vcpu load/put. Let's update our copies before we save + * it into the save area. + */ + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + + return kvm_s390_store_adtl_status_unloaded(vcpu, addr); +} + +static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) +{ + kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu); + kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu); + exit_sie_sync(vcpu); +} + +static void __disable_ibs_on_all_vcpus(struct kvm *kvm) +{ + unsigned int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + __disable_ibs_on_vcpu(vcpu); + } +} + +static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu) +{ + kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu); + kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu); + exit_sie_sync(vcpu); +} + +void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) +{ + int i, online_vcpus, started_vcpus = 0; + + if (!is_vcpu_stopped(vcpu)) + return; + + trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1); + /* Only one cpu at a time may enter/leave the STOPPED state. */ + spin_lock(&vcpu->kvm->arch.start_stop_lock); + online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + + for (i = 0; i < online_vcpus; i++) { + if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) + started_vcpus++; + } + + if (started_vcpus == 0) { + /* we're the only active VCPU -> speed it up */ + __enable_ibs_on_vcpu(vcpu); + } else if (started_vcpus == 1) { + /* + * As we are starting a second VCPU, we have to disable + * the IBS facility on all VCPUs to remove potentially + * oustanding ENABLE requests. + */ + __disable_ibs_on_all_vcpus(vcpu->kvm); + } + + atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + /* + * Another VCPU might have used IBS while we were offline. + * Let's play safe and flush the VCPU at startup. + */ + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return; +} + +void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) +{ + int i, online_vcpus, started_vcpus = 0; + struct kvm_vcpu *started_vcpu = NULL; + + if (is_vcpu_stopped(vcpu)) + return; + + trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0); + /* Only one cpu at a time may enter/leave the STOPPED state. */ + spin_lock(&vcpu->kvm->arch.start_stop_lock); + online_vcpus = atomic_read(&vcpu->kvm->online_vcpus); + + /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */ + kvm_s390_clear_stop_irq(vcpu); + + atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + __disable_ibs_on_vcpu(vcpu); + + for (i = 0; i < online_vcpus; i++) { + if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) { + started_vcpus++; + started_vcpu = vcpu->kvm->vcpus[i]; + } + } + + if (started_vcpus == 1) { + /* + * As we only have one VCPU left, we want to enable the + * IBS facility for that VCPU to speed it up. + */ + __enable_ibs_on_vcpu(started_vcpu); + } + + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return; +} + +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_S390_CSS_SUPPORT: + if (!vcpu->kvm->arch.css_support) { + vcpu->kvm->arch.css_support = 1; + trace_kvm_s390_enable_css(vcpu->kvm); + } + r = 0; + break; + default: + r = -EINVAL; + break; + } + return r; +} + +static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + void *tmpbuf = NULL; + int r, srcu_idx; + const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION + | KVM_S390_MEMOP_F_CHECK_ONLY; + + if (mop->flags & ~supported_flags) + return -EINVAL; + + if (mop->size > MEM_OP_MAX_SIZE) + return -E2BIG; + + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { + tmpbuf = vmalloc(mop->size); + if (!tmpbuf) + return -ENOMEM; + } + + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + switch (mop->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false); + break; + } + r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + if (r == 0) { + if (copy_to_user(uaddr, tmpbuf, mop->size)) + r = -EFAULT; + } + break; + case KVM_S390_MEMOP_LOGICAL_WRITE: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true); + break; + } + if (copy_from_user(tmpbuf, uaddr, mop->size)) { + r = -EFAULT; + break; + } + r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + break; + default: + r = -EINVAL; + } + + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + + if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) + kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + + vfree(tmpbuf); + return r; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + int idx; + long r; + + switch (ioctl) { + case KVM_S390_IRQ: { + struct kvm_s390_irq s390irq; + + r = -EFAULT; + if (copy_from_user(&s390irq, argp, sizeof(s390irq))) + break; + r = kvm_s390_inject_vcpu(vcpu, &s390irq); + break; + } + case KVM_S390_INTERRUPT: { + struct kvm_s390_interrupt s390int; + struct kvm_s390_irq s390irq; + + r = -EFAULT; + if (copy_from_user(&s390int, argp, sizeof(s390int))) + break; + if (s390int_to_s390irq(&s390int, &s390irq)) + return -EINVAL; + r = kvm_s390_inject_vcpu(vcpu, &s390irq); + break; + } + case KVM_S390_STORE_STATUS: + idx = srcu_read_lock(&vcpu->kvm->srcu); + r = kvm_s390_vcpu_store_status(vcpu, arg); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + break; + case KVM_S390_SET_INITIAL_PSW: { + psw_t psw; + + r = -EFAULT; + if (copy_from_user(&psw, argp, sizeof(psw))) + break; + r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw); + break; + } + case KVM_S390_INITIAL_RESET: + r = kvm_arch_vcpu_ioctl_initial_reset(vcpu); + break; + case KVM_SET_ONE_REG: + case KVM_GET_ONE_REG: { + struct kvm_one_reg reg; + r = -EFAULT; + if (copy_from_user(®, argp, sizeof(reg))) + break; + if (ioctl == KVM_SET_ONE_REG) + r = kvm_arch_vcpu_ioctl_set_one_reg(vcpu, ®); + else + r = kvm_arch_vcpu_ioctl_get_one_reg(vcpu, ®); + break; + } +#ifdef CONFIG_KVM_S390_UCONTROL + case KVM_S390_UCAS_MAP: { + struct kvm_s390_ucas_mapping ucasmap; + + if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) { + r = -EFAULT; + break; + } + + if (!kvm_is_ucontrol(vcpu->kvm)) { + r = -EINVAL; + break; + } + + r = gmap_map_segment(vcpu->arch.gmap, ucasmap.user_addr, + ucasmap.vcpu_addr, ucasmap.length); + break; + } + case KVM_S390_UCAS_UNMAP: { + struct kvm_s390_ucas_mapping ucasmap; + + if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) { + r = -EFAULT; + break; + } + + if (!kvm_is_ucontrol(vcpu->kvm)) { + r = -EINVAL; + break; + } + + r = gmap_unmap_segment(vcpu->arch.gmap, ucasmap.vcpu_addr, + ucasmap.length); + break; + } +#endif + case KVM_S390_VCPU_FAULT: { + r = gmap_fault(vcpu->arch.gmap, arg, 0); + break; + } + case KVM_ENABLE_CAP: + { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + break; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } + case KVM_S390_MEM_OP: { + struct kvm_s390_mem_op mem_op; + + if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0) + r = kvm_s390_guest_mem_op(vcpu, &mem_op); + else + r = -EFAULT; + break; + } + case KVM_S390_SET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len > VCPU_IRQS_MAX_BUF || + irq_state.len == 0 || + irq_state.len % sizeof(struct kvm_s390_irq) > 0) { + r = -EINVAL; + break; + } + r = kvm_s390_set_irq_state(vcpu, + (void __user *) irq_state.buf, + irq_state.len); + break; + } + case KVM_S390_GET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len == 0) { + r = -EINVAL; + break; + } + r = kvm_s390_get_irq_state(vcpu, + (__u8 __user *) irq_state.buf, + irq_state.len); + break; + } + default: + r = -ENOTTY; + } + return r; +} + +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ +#ifdef CONFIG_KVM_S390_UCONTROL + if ((vmf->pgoff == KVM_S390_SIE_PAGE_OFFSET) + && (kvm_is_ucontrol(vcpu->kvm))) { + vmf->page = virt_to_page(vcpu->arch.sie_block); + get_page(vmf->page); + return 0; + } +#endif + return VM_FAULT_SIGBUS; +} + +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) +{ + return 0; +} + +/* Section: memory related */ +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) +{ + /* A few sanity checks. We can have memory slots which have to be + located/ended at a segment boundary (1MB). The memory in userland is + ok to be fragmented into various different vmas. It is okay to mmap() + and munmap() stuff in this slot after doing this call at any time */ + + if (mem->userspace_addr & 0xffffful) + return -EINVAL; + + if (mem->memory_size & 0xffffful) + return -EINVAL; + + return 0; +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + enum kvm_mr_change change) +{ + int rc; + + /* If the basics of the memslot do not change, we do not want + * to update the gmap. Every update causes several unnecessary + * segment translation exceptions. This is usually handled just + * fine by the normal fault handler + gmap, but it will also + * cause faults on the prefix page of running guest CPUs. + */ + if (old->userspace_addr == mem->userspace_addr && + old->base_gfn * PAGE_SIZE == mem->guest_phys_addr && + old->npages * PAGE_SIZE == mem->memory_size) + return; + + rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, + mem->guest_phys_addr, mem->memory_size); + if (rc) + printk(KERN_WARNING "kvm-s390: failed to commit memory region\n"); + return; +} + +static int __init kvm_s390_init(void) +{ + return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); +} + +static void __exit kvm_s390_exit(void) +{ + kvm_exit(); +} + +module_init(kvm_s390_init); +module_exit(kvm_s390_exit); + +/* + * Enable autoloading of the kvm module. + * Note that we add the module alias here instead of virt/kvm/kvm_main.c + * since x86 takes a different approach. + */ +#include <linux/miscdevice.h> +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h new file mode 100644 index 000000000..ca108b90a --- /dev/null +++ b/arch/s390/kvm/kvm-s390.h @@ -0,0 +1,290 @@ +/* + * definition for kvm on s390 + * + * Copyright IBM Corp. 2008, 2009 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> + */ + +#ifndef ARCH_S390_KVM_S390_H +#define ARCH_S390_KVM_S390_H + +#include <linux/hrtimer.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <asm/facility.h> + +typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); + +/* Transactional Memory Execution related macros */ +#define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & 0x10)) +#define TDB_FORMAT1 1 +#define IS_ITDB_VALID(vcpu) ((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1)) + +#define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ +do { \ + debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \ + d_args); \ +} while (0) + +#define VCPU_EVENT(d_vcpu, d_loglevel, d_string, d_args...)\ +do { \ + debug_sprintf_event(d_vcpu->kvm->arch.dbf, d_loglevel, \ + "%02d[%016lx-%016lx]: " d_string "\n", d_vcpu->vcpu_id, \ + d_vcpu->arch.sie_block->gpsw.mask, d_vcpu->arch.sie_block->gpsw.addr,\ + d_args); \ +} while (0) + +static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) +{ + return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED; +} + +static inline int kvm_is_ucontrol(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_S390_UCONTROL + if (kvm->arch.gmap) + return 0; + return 1; +#else + return 0; +#endif +} + +#define GUEST_PREFIX_SHIFT 13 +static inline u32 kvm_s390_get_prefix(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.sie_block->prefix << GUEST_PREFIX_SHIFT; +} + +static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix) +{ + vcpu->arch.sie_block->prefix = prefix >> GUEST_PREFIX_SHIFT; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); +} + +typedef u8 __bitwise ar_t; + +static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar) +{ + u32 base2 = vcpu->arch.sie_block->ipb >> 28; + u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + + if (ar) + *ar = base2; + + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; +} + +static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, + u64 *address1, u64 *address2, + ar_t *ar_b1, ar_t *ar_b2) +{ + u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; + u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; + u32 base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12; + u32 disp2 = vcpu->arch.sie_block->ipb & 0x0fff; + + *address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; + *address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; + + if (ar_b1) + *ar_b1 = base1; + if (ar_b2) + *ar_b2 = base2; +} + +static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2) +{ + if (r1) + *r1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 20; + if (r2) + *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; +} + +static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar) +{ + u32 base2 = vcpu->arch.sie_block->ipb >> 28; + u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + + ((vcpu->arch.sie_block->ipb & 0xff00) << 4); + /* The displacement is a 20bit _SIGNED_ value */ + if (disp2 & 0x80000) + disp2+=0xfff00000; + + if (ar) + *ar = base2; + + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2; +} + +static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar) +{ + u32 base2 = vcpu->arch.sie_block->ipb >> 28; + u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + + if (ar) + *ar = base2; + + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; +} + +/* Set the condition code in the guest program status word */ +static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) +{ + vcpu->arch.sie_block->gpsw.mask &= ~(3UL << 44); + vcpu->arch.sie_block->gpsw.mask |= cc << 44; +} + +/* test availability of facility in a kvm instance */ +static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr) +{ + return __test_facility(nr, kvm->arch.model.fac->mask) && + __test_facility(nr, kvm->arch.model.fac->list); +} + +static inline int set_kvm_facility(u64 *fac_list, unsigned long nr) +{ + unsigned char *ptr; + + if (nr >= MAX_FACILITY_BIT) + return -EINVAL; + ptr = (unsigned char *) fac_list + (nr >> 3); + *ptr |= (0x80UL >> (nr & 7)); + return 0; +} + +/* are cpu states controlled by user space */ +static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) +{ + return kvm->arch.user_cpu_state_ctrl != 0; +} + +int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); +void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu); +enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); +int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu); +void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu); +void kvm_s390_clear_float_irqs(struct kvm *kvm); +int __must_check kvm_s390_inject_vm(struct kvm *kvm, + struct kvm_s390_interrupt *s390int); +int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, + struct kvm_s390_irq *irq); +int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); +struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, + u64 isc_mask, u32 schid); +int kvm_s390_reinject_io_int(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti); +int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); + +/* implemented in intercept.c */ +void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc); +int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); + +/* implemented in priv.c */ +int is_valid_psw(psw_t *psw); +int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); +int kvm_s390_handle_e5(struct kvm_vcpu *vcpu); +int kvm_s390_handle_01(struct kvm_vcpu *vcpu); +int kvm_s390_handle_b9(struct kvm_vcpu *vcpu); +int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu); +int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu); +int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu); +int kvm_s390_handle_eb(struct kvm_vcpu *vcpu); + +/* implemented in sigp.c */ +int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); +int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); + +/* implemented in kvm-s390.c */ +long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); +int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); +int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long addr); +int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); +int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); +void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); +void s390_vcpu_block(struct kvm_vcpu *vcpu); +void s390_vcpu_unblock(struct kvm_vcpu *vcpu); +void exit_sie(struct kvm_vcpu *vcpu); +void exit_sie_sync(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu); +void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu); +/* is cmma enabled */ +bool kvm_s390_cmma_enabled(struct kvm *kvm); +unsigned long kvm_s390_fac_list_mask_size(void); +extern unsigned long kvm_s390_fac_list_mask[]; + +/* implemented in diag.c */ +int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); +/* implemented in interrupt.c */ +int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu, + struct kvm_s390_pgm_info *pgm_info); + +/** + * kvm_s390_inject_prog_cond - conditionally inject a program check + * @vcpu: virtual cpu + * @rc: original return/error code + * + * This function is supposed to be used after regular guest access functions + * failed, to conditionally inject a program check to a vcpu. The typical + * pattern would look like + * + * rc = write_guest(vcpu, addr, data, len); + * if (rc) + * return kvm_s390_inject_prog_cond(vcpu, rc); + * + * A negative return code from guest access functions implies an internal error + * like e.g. out of memory. In these cases no program check should be injected + * to the guest. + * A positive value implies that an exception happened while accessing a guest's + * memory. In this case all data belonging to the corresponding program check + * has been stored in vcpu->arch.pgm and can be injected with + * kvm_s390_inject_prog_irq(). + * + * Returns: - the original @rc value if @rc was negative (internal error) + * - zero if @rc was already zero + * - zero or error code from injecting if @rc was positive + * (program check injected to @vcpu) + */ +static inline int kvm_s390_inject_prog_cond(struct kvm_vcpu *vcpu, int rc) +{ + if (rc <= 0) + return rc; + return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); +} + +int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, + struct kvm_s390_irq *s390irq); + +/* implemented in interrupt.c */ +int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop); +int psw_extint_disabled(struct kvm_vcpu *vcpu); +void kvm_s390_destroy_adapters(struct kvm *kvm); +int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu); +extern struct kvm_device_ops kvm_flic_ops; +int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu); +void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu); +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, + void __user *buf, int len); +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, + __u8 __user *buf, int len); + +/* implemented in guestdbg.c */ +void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu); +void kvm_s390_restore_guest_per_regs(struct kvm_vcpu *vcpu); +void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu); +int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg); +void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu); +void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu); +void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c new file mode 100644 index 000000000..d22d8ee1f --- /dev/null +++ b/arch/s390/kvm/priv.c @@ -0,0 +1,1060 @@ +/* + * handling privileged instructions + * + * Copyright IBM Corp. 2008, 2013 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + */ + +#include <linux/kvm.h> +#include <linux/gfp.h> +#include <linux/errno.h> +#include <linux/compat.h> +#include <asm/asm-offsets.h> +#include <asm/facility.h> +#include <asm/current.h> +#include <asm/debug.h> +#include <asm/ebcdic.h> +#include <asm/sysinfo.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/io.h> +#include <asm/ptrace.h> +#include <asm/compat.h> +#include "gaccess.h" +#include "kvm-s390.h" +#include "trace.h" + +/* Handle SCK (SET CLOCK) interception */ +static int handle_set_clock(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *cpup; + s64 hostclk, val; + int i, rc; + ar_t ar; + u64 op2; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + op2 = kvm_s390_get_base_disp_s(vcpu, &ar); + if (op2 & 7) /* Operand must be on a doubleword boundary */ + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + if (store_tod_clock(&hostclk)) { + kvm_s390_set_psw_cc(vcpu, 3); + return 0; + } + val = (val - hostclk) & ~0x3fUL; + + mutex_lock(&vcpu->kvm->lock); + kvm_for_each_vcpu(i, cpup, vcpu->kvm) + cpup->arch.sie_block->epoch = val; + mutex_unlock(&vcpu->kvm->lock); + + kvm_s390_set_psw_cc(vcpu, 0); + return 0; +} + +static int handle_set_prefix(struct kvm_vcpu *vcpu) +{ + u64 operand2; + u32 address; + int rc; + ar_t ar; + + vcpu->stat.instruction_spx++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); + + /* must be word boundary */ + if (operand2 & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* get the value */ + rc = read_guest(vcpu, operand2, ar, &address, sizeof(address)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + address &= 0x7fffe000u; + + /* + * Make sure the new value is valid memory. We only need to check the + * first page, since address is 8k aligned and memory pieces are always + * at least 1MB aligned and have at least a size of 1MB. + */ + if (kvm_is_error_gpa(vcpu->kvm, address)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + kvm_s390_set_prefix(vcpu, address); + + VCPU_EVENT(vcpu, 5, "setting prefix to %x", address); + trace_kvm_s390_handle_prefix(vcpu, 1, address); + return 0; +} + +static int handle_store_prefix(struct kvm_vcpu *vcpu) +{ + u64 operand2; + u32 address; + int rc; + ar_t ar; + + vcpu->stat.instruction_stpx++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); + + /* must be word boundary */ + if (operand2 & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + address = kvm_s390_get_prefix(vcpu); + + /* get the value */ + rc = write_guest(vcpu, operand2, ar, &address, sizeof(address)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + VCPU_EVENT(vcpu, 5, "storing prefix to %x", address); + trace_kvm_s390_handle_prefix(vcpu, 0, address); + return 0; +} + +static int handle_store_cpu_address(struct kvm_vcpu *vcpu) +{ + u16 vcpu_id = vcpu->vcpu_id; + u64 ga; + int rc; + ar_t ar; + + vcpu->stat.instruction_stap++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_s(vcpu, &ar); + + if (ga & 1) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = write_guest(vcpu, ga, ar, &vcpu_id, sizeof(vcpu_id)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", ga); + trace_kvm_s390_handle_stap(vcpu, ga); + return 0; +} + +static int __skey_check_enable(struct kvm_vcpu *vcpu) +{ + int rc = 0; + if (!(vcpu->arch.sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE))) + return rc; + + rc = s390_enable_skey(); + trace_kvm_s390_skey_related_inst(vcpu); + vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE); + return rc; +} + + +static int handle_skey(struct kvm_vcpu *vcpu) +{ + int rc = __skey_check_enable(vcpu); + + if (rc) + return rc; + vcpu->stat.instruction_storage_key++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + kvm_s390_rewind_psw(vcpu, 4); + VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); + return 0; +} + +static int handle_ipte_interlock(struct kvm_vcpu *vcpu) +{ + vcpu->stat.instruction_ipte_interlock++; + if (psw_bits(vcpu->arch.sie_block->gpsw).p) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu)); + kvm_s390_rewind_psw(vcpu, 4); + VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation"); + return 0; +} + +static int handle_test_block(struct kvm_vcpu *vcpu) +{ + gpa_t addr; + int reg2; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + kvm_s390_get_regs_rre(vcpu, NULL, ®2); + addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + addr = kvm_s390_logical_to_effective(vcpu, addr); + if (kvm_s390_check_low_addr_prot_real(vcpu, addr)) + return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + addr = kvm_s390_real_to_abs(vcpu, addr); + + if (kvm_is_error_gpa(vcpu->kvm, addr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + /* + * We don't expect errors on modern systems, and do not care + * about storage keys (yet), so let's just clear the page. + */ + if (kvm_clear_guest(vcpu->kvm, addr, PAGE_SIZE)) + return -EFAULT; + kvm_s390_set_psw_cc(vcpu, 0); + vcpu->run->s.regs.gprs[0] = 0; + return 0; +} + +static int handle_tpi(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_interrupt_info *inti; + unsigned long len; + u32 tpi_data[3]; + int rc; + u64 addr; + ar_t ar; + + addr = kvm_s390_get_base_disp_s(vcpu, &ar); + if (addr & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0); + if (!inti) { + kvm_s390_set_psw_cc(vcpu, 0); + return 0; + } + + tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr; + tpi_data[1] = inti->io.io_int_parm; + tpi_data[2] = inti->io.io_int_word; + if (addr) { + /* + * Store the two-word I/O interruption code into the + * provided area. + */ + len = sizeof(tpi_data) - 4; + rc = write_guest(vcpu, addr, ar, &tpi_data, len); + if (rc) { + rc = kvm_s390_inject_prog_cond(vcpu, rc); + goto reinject_interrupt; + } + } else { + /* + * Store the three-word I/O interruption code into + * the appropriate lowcore area. + */ + len = sizeof(tpi_data); + if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) { + /* failed writes to the low core are not recoverable */ + rc = -EFAULT; + goto reinject_interrupt; + } + } + + /* irq was successfully handed to the guest */ + kfree(inti); + kvm_s390_set_psw_cc(vcpu, 1); + return 0; +reinject_interrupt: + /* + * If we encounter a problem storing the interruption code, the + * instruction is suppressed from the guest's view: reinject the + * interrupt. + */ + if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) { + kfree(inti); + rc = -EFAULT; + } + /* don't set the cc, a pgm irq was injected or we drop to user space */ + return rc ? -EFAULT : 0; +} + +static int handle_tsch(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_interrupt_info *inti = NULL; + const u64 isc_mask = 0xffUL << 24; /* all iscs set */ + + /* a valid schid has at least one bit set */ + if (vcpu->run->s.regs.gprs[1]) + inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask, + vcpu->run->s.regs.gprs[1]); + + /* + * Prepare exit to userspace. + * We indicate whether we dequeued a pending I/O interrupt + * so that userspace can re-inject it if the instruction gets + * a program check. While this may re-order the pending I/O + * interrupts, this is no problem since the priority is kept + * intact. + */ + vcpu->run->exit_reason = KVM_EXIT_S390_TSCH; + vcpu->run->s390_tsch.dequeued = !!inti; + if (inti) { + vcpu->run->s390_tsch.subchannel_id = inti->io.subchannel_id; + vcpu->run->s390_tsch.subchannel_nr = inti->io.subchannel_nr; + vcpu->run->s390_tsch.io_int_parm = inti->io.io_int_parm; + vcpu->run->s390_tsch.io_int_word = inti->io.io_int_word; + } + vcpu->run->s390_tsch.ipb = vcpu->arch.sie_block->ipb; + kfree(inti); + return -EREMOTE; +} + +static int handle_io_inst(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 4, "%s", "I/O instruction"); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (vcpu->kvm->arch.css_support) { + /* + * Most I/O instructions will be handled by userspace. + * Exceptions are tpi and the interrupt portion of tsch. + */ + if (vcpu->arch.sie_block->ipa == 0xb236) + return handle_tpi(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb235) + return handle_tsch(vcpu); + /* Handle in userspace. */ + return -EOPNOTSUPP; + } else { + /* + * Set condition code 3 to stop the guest from issuing channel + * I/O instructions. + */ + kvm_s390_set_psw_cc(vcpu, 3); + return 0; + } +} + +static int handle_stfl(struct kvm_vcpu *vcpu) +{ + int rc; + unsigned int fac; + + vcpu->stat.instruction_stfl++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + /* + * We need to shift the lower 32 facility bits (bit 0-31) from a u64 + * into a u32 memory representation. They will remain bits 0-31. + */ + fac = *vcpu->kvm->arch.model.fac->list >> 32; + rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list), + &fac, sizeof(fac)); + if (rc) + return rc; + VCPU_EVENT(vcpu, 5, "store facility list value %x", fac); + trace_kvm_s390_handle_stfl(vcpu, fac); + return 0; +} + +#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA) +#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL +#define PSW_ADDR_24 0x0000000000ffffffUL +#define PSW_ADDR_31 0x000000007fffffffUL + +int is_valid_psw(psw_t *psw) +{ + if (psw->mask & PSW_MASK_UNASSIGNED) + return 0; + if ((psw->mask & PSW_MASK_ADDR_MODE) == PSW_MASK_BA) { + if (psw->addr & ~PSW_ADDR_31) + return 0; + } + if (!(psw->mask & PSW_MASK_ADDR_MODE) && (psw->addr & ~PSW_ADDR_24)) + return 0; + if ((psw->mask & PSW_MASK_ADDR_MODE) == PSW_MASK_EA) + return 0; + if (psw->addr & 1) + return 0; + return 1; +} + +int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) +{ + psw_t *gpsw = &vcpu->arch.sie_block->gpsw; + psw_compat_t new_psw; + u64 addr; + int rc; + ar_t ar; + + if (gpsw->mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + addr = kvm_s390_get_base_disp_s(vcpu, &ar); + if (addr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + if (!(new_psw.mask & PSW32_MASK_BASE)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + gpsw->mask = (new_psw.mask & ~PSW32_MASK_BASE) << 32; + gpsw->mask |= new_psw.addr & PSW32_ADDR_AMODE; + gpsw->addr = new_psw.addr & ~PSW32_ADDR_AMODE; + if (!is_valid_psw(gpsw)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + return 0; +} + +static int handle_lpswe(struct kvm_vcpu *vcpu) +{ + psw_t new_psw; + u64 addr; + int rc; + ar_t ar; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + addr = kvm_s390_get_base_disp_s(vcpu, &ar); + if (addr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + vcpu->arch.sie_block->gpsw = new_psw; + if (!is_valid_psw(&vcpu->arch.sie_block->gpsw)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + return 0; +} + +static int handle_stidp(struct kvm_vcpu *vcpu) +{ + u64 stidp_data = vcpu->arch.stidp_data; + u64 operand2; + int rc; + ar_t ar; + + vcpu->stat.instruction_stidp++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); + + if (operand2 & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = write_guest(vcpu, operand2, ar, &stidp_data, sizeof(stidp_data)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + VCPU_EVENT(vcpu, 5, "%s", "store cpu id"); + return 0; +} + +static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) +{ + int cpus = 0; + int n; + + cpus = atomic_read(&vcpu->kvm->online_vcpus); + + /* deal with other level 3 hypervisors */ + if (stsi(mem, 3, 2, 2)) + mem->count = 0; + if (mem->count < 8) + mem->count++; + for (n = mem->count - 1; n > 0 ; n--) + memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); + + memset(&mem->vm[0], 0, sizeof(mem->vm[0])); + mem->vm[0].cpus_total = cpus; + mem->vm[0].cpus_configured = cpus; + mem->vm[0].cpus_standby = 0; + mem->vm[0].cpus_reserved = 0; + mem->vm[0].caf = 1000; + memcpy(mem->vm[0].name, "KVMguest", 8); + ASCEBC(mem->vm[0].name, 8); + memcpy(mem->vm[0].cpi, "KVM/Linux ", 16); + ASCEBC(mem->vm[0].cpi, 16); +} + +static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar, + u8 fc, u8 sel1, u16 sel2) +{ + vcpu->run->exit_reason = KVM_EXIT_S390_STSI; + vcpu->run->s390_stsi.addr = addr; + vcpu->run->s390_stsi.ar = ar; + vcpu->run->s390_stsi.fc = fc; + vcpu->run->s390_stsi.sel1 = sel1; + vcpu->run->s390_stsi.sel2 = sel2; +} + +static int handle_stsi(struct kvm_vcpu *vcpu) +{ + int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28; + int sel1 = vcpu->run->s.regs.gprs[0] & 0xff; + int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff; + unsigned long mem = 0; + u64 operand2; + int rc = 0; + ar_t ar; + + vcpu->stat.instruction_stsi++; + VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (fc > 3) { + kvm_s390_set_psw_cc(vcpu, 3); + return 0; + } + + if (vcpu->run->s.regs.gprs[0] & 0x0fffff00 + || vcpu->run->s.regs.gprs[1] & 0xffff0000) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + if (fc == 0) { + vcpu->run->s.regs.gprs[0] = 3 << 28; + kvm_s390_set_psw_cc(vcpu, 0); + return 0; + } + + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); + + if (operand2 & 0xfff) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + switch (fc) { + case 1: /* same handling for 1 and 2 */ + case 2: + mem = get_zeroed_page(GFP_KERNEL); + if (!mem) + goto out_no_data; + if (stsi((void *) mem, fc, sel1, sel2)) + goto out_no_data; + break; + case 3: + if (sel1 != 2 || sel2 != 2) + goto out_no_data; + mem = get_zeroed_page(GFP_KERNEL); + if (!mem) + goto out_no_data; + handle_stsi_3_2_2(vcpu, (void *) mem); + break; + } + + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); + if (rc) { + rc = kvm_s390_inject_prog_cond(vcpu, rc); + goto out; + } + if (vcpu->kvm->arch.user_stsi) { + insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2); + rc = -EREMOTE; + } + trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); + free_page(mem); + kvm_s390_set_psw_cc(vcpu, 0); + vcpu->run->s.regs.gprs[0] = 0; + return rc; +out_no_data: + kvm_s390_set_psw_cc(vcpu, 3); +out: + free_page(mem); + return rc; +} + +static const intercept_handler_t b2_handlers[256] = { + [0x02] = handle_stidp, + [0x04] = handle_set_clock, + [0x10] = handle_set_prefix, + [0x11] = handle_store_prefix, + [0x12] = handle_store_cpu_address, + [0x21] = handle_ipte_interlock, + [0x29] = handle_skey, + [0x2a] = handle_skey, + [0x2b] = handle_skey, + [0x2c] = handle_test_block, + [0x30] = handle_io_inst, + [0x31] = handle_io_inst, + [0x32] = handle_io_inst, + [0x33] = handle_io_inst, + [0x34] = handle_io_inst, + [0x35] = handle_io_inst, + [0x36] = handle_io_inst, + [0x37] = handle_io_inst, + [0x38] = handle_io_inst, + [0x39] = handle_io_inst, + [0x3a] = handle_io_inst, + [0x3b] = handle_io_inst, + [0x3c] = handle_io_inst, + [0x50] = handle_ipte_interlock, + [0x5f] = handle_io_inst, + [0x74] = handle_io_inst, + [0x76] = handle_io_inst, + [0x7d] = handle_stsi, + [0xb1] = handle_stfl, + [0xb2] = handle_lpswe, +}; + +int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + /* + * A lot of B2 instructions are priviledged. Here we check for + * the privileged ones, that we can handle in the kernel. + * Anything else goes to userspace. + */ + handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; + if (handler) + return handler(vcpu); + + return -EOPNOTSUPP; +} + +static int handle_epsw(struct kvm_vcpu *vcpu) +{ + int reg1, reg2; + + kvm_s390_get_regs_rre(vcpu, ®1, ®2); + + /* This basically extracts the mask half of the psw. */ + vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000UL; + vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32; + if (reg2) { + vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000UL; + vcpu->run->s.regs.gprs[reg2] |= + vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffffUL; + } + return 0; +} + +#define PFMF_RESERVED 0xfffc0101UL +#define PFMF_SK 0x00020000UL +#define PFMF_CF 0x00010000UL +#define PFMF_UI 0x00008000UL +#define PFMF_FSC 0x00007000UL +#define PFMF_NQ 0x00000800UL +#define PFMF_MR 0x00000400UL +#define PFMF_MC 0x00000200UL +#define PFMF_KEY 0x000000feUL + +static int handle_pfmf(struct kvm_vcpu *vcpu) +{ + int reg1, reg2; + unsigned long start, end; + + vcpu->stat.instruction_pfmf++; + + kvm_s390_get_regs_rre(vcpu, ®1, ®2); + + if (!MACHINE_HAS_PFMF) + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_RESERVED) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* Only provide non-quiescing support if the host supports it */ + if (vcpu->run->s.regs.gprs[reg1] & PFMF_NQ && !test_facility(14)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* No support for conditional-SSKE */ + if (vcpu->run->s.regs.gprs[reg1] & (PFMF_MR | PFMF_MC)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + start = kvm_s390_logical_to_effective(vcpu, start); + + switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { + case 0x00000000: + end = (start + (1UL << 12)) & ~((1UL << 12) - 1); + break; + case 0x00001000: + end = (start + (1UL << 20)) & ~((1UL << 20) - 1); + break; + /* We dont support EDAT2 + case 0x00002000: + end = (start + (1UL << 31)) & ~((1UL << 31) - 1); + break;*/ + default: + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + } + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { + if (kvm_s390_check_low_addr_prot_real(vcpu, start)) + return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + } + + while (start < end) { + unsigned long useraddr, abs_addr; + + /* Translate guest address to host address */ + if ((vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) == 0) + abs_addr = kvm_s390_real_to_abs(vcpu, start); + else + abs_addr = start; + useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(abs_addr)); + if (kvm_is_error_hva(useraddr)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { + if (clear_user((void __user *)useraddr, PAGE_SIZE)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK) { + int rc = __skey_check_enable(vcpu); + + if (rc) + return rc; + if (set_guest_storage_key(current->mm, useraddr, + vcpu->run->s.regs.gprs[reg1] & PFMF_KEY, + vcpu->run->s.regs.gprs[reg1] & PFMF_NQ)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } + + start += PAGE_SIZE; + } + if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) + vcpu->run->s.regs.gprs[reg2] = end; + return 0; +} + +static int handle_essa(struct kvm_vcpu *vcpu) +{ + /* entries expected to be 1FF */ + int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3; + unsigned long *cbrlo, cbrle; + struct gmap *gmap; + int i; + + VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries); + gmap = vcpu->arch.gmap; + vcpu->stat.instruction_essa++; + if (!kvm_s390_cmma_enabled(vcpu->kvm)) + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + /* Rewind PSW to repeat the ESSA instruction */ + kvm_s390_rewind_psw(vcpu, 4); + vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ + cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo); + down_read(&gmap->mm->mmap_sem); + for (i = 0; i < entries; ++i) { + cbrle = cbrlo[i]; + if (unlikely(cbrle & ~PAGE_MASK || cbrle < 2 * PAGE_SIZE)) + /* invalid entry */ + break; + /* try to free backing */ + __gmap_zap(gmap, cbrle); + } + up_read(&gmap->mm->mmap_sem); + if (i < entries) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + return 0; +} + +static const intercept_handler_t b9_handlers[256] = { + [0x8a] = handle_ipte_interlock, + [0x8d] = handle_epsw, + [0x8e] = handle_ipte_interlock, + [0x8f] = handle_ipte_interlock, + [0xab] = handle_essa, + [0xaf] = handle_pfmf, +}; + +int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + /* This is handled just as for the B2 instructions. */ + handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; + if (handler) + return handler(vcpu); + + return -EOPNOTSUPP; +} + +int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + int reg, rc, nr_regs; + u32 ctl_array[16]; + u64 ga; + ar_t ar; + + vcpu->stat.instruction_lctl++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); + + if (ga & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga); + + nr_regs = ((reg3 - reg1) & 0xf) + 1; + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + reg = reg1; + nr_regs = 0; + do { + vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul; + vcpu->arch.sie_block->gcr[reg] |= ctl_array[nr_regs++]; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + return 0; +} + +int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + int reg, rc, nr_regs; + u32 ctl_array[16]; + u64 ga; + ar_t ar; + + vcpu->stat.instruction_stctl++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); + + if (ga & 3) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "stctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga); + + reg = reg1; + nr_regs = 0; + do { + ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg]; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); + return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; +} + +static int handle_lctlg(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + int reg, rc, nr_regs; + u64 ctl_array[16]; + u64 ga; + ar_t ar; + + vcpu->stat.instruction_lctlg++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); + + if (ga & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga); + + nr_regs = ((reg3 - reg1) & 0xf) + 1; + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + reg = reg1; + nr_regs = 0; + do { + vcpu->arch.sie_block->gcr[reg] = ctl_array[nr_regs++]; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + return 0; +} + +static int handle_stctg(struct kvm_vcpu *vcpu) +{ + int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + int reg, rc, nr_regs; + u64 ctl_array[16]; + u64 ga; + ar_t ar; + + vcpu->stat.instruction_stctg++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); + + if (ga & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); + trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga); + + reg = reg1; + nr_regs = 0; + do { + ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg]; + if (reg == reg3) + break; + reg = (reg + 1) % 16; + } while (1); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); + return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; +} + +static const intercept_handler_t eb_handlers[256] = { + [0x2f] = handle_lctlg, + [0x25] = handle_stctg, +}; + +int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff]; + if (handler) + return handler(vcpu); + return -EOPNOTSUPP; +} + +static int handle_tprot(struct kvm_vcpu *vcpu) +{ + u64 address1, address2; + unsigned long hva, gpa; + int ret = 0, cc = 0; + bool writable; + ar_t ar; + + vcpu->stat.instruction_tprot++; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + kvm_s390_get_base_disp_sse(vcpu, &address1, &address2, &ar, NULL); + + /* we only handle the Linux memory detection case: + * access key == 0 + * everything else goes to userspace. */ + if (address2 & 0xf0) + return -EOPNOTSUPP; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) + ipte_lock(vcpu); + ret = guest_translate_address(vcpu, address1, ar, &gpa, 1); + if (ret == PGM_PROTECTION) { + /* Write protected? Try again with read-only... */ + cc = 1; + ret = guest_translate_address(vcpu, address1, ar, &gpa, 0); + } + if (ret) { + if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) { + ret = kvm_s390_inject_program_int(vcpu, ret); + } else if (ret > 0) { + /* Translation not available */ + kvm_s390_set_psw_cc(vcpu, 3); + ret = 0; + } + goto out_unlock; + } + + hva = gfn_to_hva_prot(vcpu->kvm, gpa_to_gfn(gpa), &writable); + if (kvm_is_error_hva(hva)) { + ret = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + } else { + if (!writable) + cc = 1; /* Write not permitted ==> read-only */ + kvm_s390_set_psw_cc(vcpu, cc); + /* Note: CC2 only occurs for storage keys (not supported yet) */ + } +out_unlock: + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) + ipte_unlock(vcpu); + return ret; +} + +int kvm_s390_handle_e5(struct kvm_vcpu *vcpu) +{ + /* For e5xx... instructions we only handle TPROT */ + if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01) + return handle_tprot(vcpu); + return -EOPNOTSUPP; +} + +static int handle_sckpf(struct kvm_vcpu *vcpu) +{ + u32 value; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + if (vcpu->run->s.regs.gprs[0] & 0x00000000ffff0000) + return kvm_s390_inject_program_int(vcpu, + PGM_SPECIFICATION); + + value = vcpu->run->s.regs.gprs[0] & 0x000000000000ffff; + vcpu->arch.sie_block->todpr = value; + + return 0; +} + +static const intercept_handler_t x01_handlers[256] = { + [0x07] = handle_sckpf, +}; + +int kvm_s390_handle_01(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; + if (handler) + return handler(vcpu); + return -EOPNOTSUPP; +} diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c new file mode 100644 index 000000000..72e58bd2b --- /dev/null +++ b/arch/s390/kvm/sigp.c @@ -0,0 +1,493 @@ +/* + * handling interprocessor communication + * + * Copyright IBM Corp. 2008, 2013 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Carsten Otte <cotte@de.ibm.com> + * Christian Borntraeger <borntraeger@de.ibm.com> + * Christian Ehrhardt <ehrhardt@de.ibm.com> + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/slab.h> +#include <asm/sigp.h> +#include "gaccess.h" +#include "kvm-s390.h" +#include "trace.h" + +static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, + u64 *reg) +{ + struct kvm_s390_local_interrupt *li; + int cpuflags; + int rc; + int ext_call_pending; + + li = &dst_vcpu->arch.local_int; + + cpuflags = atomic_read(li->cpuflags); + ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu); + if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending) + rc = SIGP_CC_ORDER_CODE_ACCEPTED; + else { + *reg &= 0xffffffff00000000UL; + if (ext_call_pending) + *reg |= SIGP_STATUS_EXT_CALL_PENDING; + if (cpuflags & CPUSTAT_STOPPED) + *reg |= SIGP_STATUS_STOPPED; + rc = SIGP_CC_STATUS_STORED; + } + + VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", dst_vcpu->vcpu_id, + rc); + return rc; +} + +static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu) +{ + struct kvm_s390_irq irq = { + .type = KVM_S390_INT_EMERGENCY, + .u.emerg.code = vcpu->vcpu_id, + }; + int rc = 0; + + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (!rc) + VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", + dst_vcpu->vcpu_id); + + return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED; +} + +static int __sigp_emergency(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu) +{ + return __inject_sigp_emergency(vcpu, dst_vcpu); +} + +static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, + u16 asn, u64 *reg) +{ + const u64 psw_int_mask = PSW_MASK_IO | PSW_MASK_EXT; + u16 p_asn, s_asn; + psw_t *psw; + u32 flags; + + flags = atomic_read(&dst_vcpu->arch.sie_block->cpuflags); + psw = &dst_vcpu->arch.sie_block->gpsw; + p_asn = dst_vcpu->arch.sie_block->gcr[4] & 0xffff; /* Primary ASN */ + s_asn = dst_vcpu->arch.sie_block->gcr[3] & 0xffff; /* Secondary ASN */ + + /* Inject the emergency signal? */ + if (!(flags & CPUSTAT_STOPPED) + || (psw->mask & psw_int_mask) != psw_int_mask + || ((flags & CPUSTAT_WAIT) && psw->addr != 0) + || (!(flags & CPUSTAT_WAIT) && (asn == p_asn || asn == s_asn))) { + return __inject_sigp_emergency(vcpu, dst_vcpu); + } else { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INCORRECT_STATE; + return SIGP_CC_STATUS_STORED; + } +} + +static int __sigp_external_call(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u64 *reg) +{ + struct kvm_s390_irq irq = { + .type = KVM_S390_INT_EXTERNAL_CALL, + .u.extcall.code = vcpu->vcpu_id, + }; + int rc; + + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (rc == -EBUSY) { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_EXT_CALL_PENDING; + return SIGP_CC_STATUS_STORED; + } else if (rc == 0) { + VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", + dst_vcpu->vcpu_id); + } + + return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED; +} + +static int __sigp_stop(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu) +{ + struct kvm_s390_irq irq = { + .type = KVM_S390_SIGP_STOP, + }; + int rc; + + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (rc == -EBUSY) + rc = SIGP_CC_BUSY; + else if (rc == 0) + VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", + dst_vcpu->vcpu_id); + + return rc; +} + +static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u64 *reg) +{ + struct kvm_s390_irq irq = { + .type = KVM_S390_SIGP_STOP, + .u.stop.flags = KVM_S390_STOP_FLAG_STORE_STATUS, + }; + int rc; + + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (rc == -EBUSY) + rc = SIGP_CC_BUSY; + else if (rc == 0) + VCPU_EVENT(vcpu, 4, "sent sigp stop and store status to cpu %x", + dst_vcpu->vcpu_id); + + return rc; +} + +static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) +{ + int rc; + unsigned int i; + struct kvm_vcpu *v; + + switch (parameter & 0xff) { + case 0: + rc = SIGP_CC_NOT_OPERATIONAL; + break; + case 1: + case 2: + kvm_for_each_vcpu(i, v, vcpu->kvm) { + v->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + kvm_clear_async_pf_completion_queue(v); + } + + rc = SIGP_CC_ORDER_CODE_ACCEPTED; + break; + default: + rc = -EOPNOTSUPP; + } + return rc; +} + +static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, + u32 address, u64 *reg) +{ + struct kvm_s390_irq irq = { + .type = KVM_S390_SIGP_SET_PREFIX, + .u.prefix.address = address & 0x7fffe000u, + }; + int rc; + + /* + * Make sure the new value is valid memory. We only need to check the + * first page, since address is 8k aligned and memory pieces are always + * at least 1MB aligned and have at least a size of 1MB. + */ + if (kvm_is_error_gpa(vcpu->kvm, irq.u.prefix.address)) { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INVALID_PARAMETER; + return SIGP_CC_STATUS_STORED; + } + + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); + if (rc == -EBUSY) { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INCORRECT_STATE; + return SIGP_CC_STATUS_STORED; + } else if (rc == 0) { + VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", + dst_vcpu->vcpu_id, irq.u.prefix.address); + } + + return rc; +} + +static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, + u32 addr, u64 *reg) +{ + int flags; + int rc; + + flags = atomic_read(dst_vcpu->arch.local_int.cpuflags); + if (!(flags & CPUSTAT_STOPPED)) { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INCORRECT_STATE; + return SIGP_CC_STATUS_STORED; + } + + addr &= 0x7ffffe00; + rc = kvm_s390_store_status_unloaded(dst_vcpu, addr); + if (rc == -EFAULT) { + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INVALID_PARAMETER; + rc = SIGP_CC_STATUS_STORED; + } + return rc; +} + +static int __sigp_sense_running(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u64 *reg) +{ + struct kvm_s390_local_interrupt *li; + int rc; + + li = &dst_vcpu->arch.local_int; + if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) { + /* running */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; + } else { + /* not running */ + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_NOT_RUNNING; + rc = SIGP_CC_STATUS_STORED; + } + + VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", + dst_vcpu->vcpu_id, rc); + + return rc; +} + +static int __prepare_sigp_re_start(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u8 order_code) +{ + struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int; + /* handle (RE)START in user space */ + int rc = -EOPNOTSUPP; + + /* make sure we don't race with STOP irq injection */ + spin_lock(&li->lock); + if (kvm_s390_is_stop_irq_pending(dst_vcpu)) + rc = SIGP_CC_BUSY; + spin_unlock(&li->lock); + + return rc; +} + +static int __prepare_sigp_cpu_reset(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u8 order_code) +{ + /* handle (INITIAL) CPU RESET in user space */ + return -EOPNOTSUPP; +} + +static int __prepare_sigp_unknown(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu) +{ + /* handle unknown orders in user space */ + return -EOPNOTSUPP; +} + +static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, + u16 cpu_addr, u32 parameter, u64 *status_reg) +{ + int rc; + struct kvm_vcpu *dst_vcpu; + + if (cpu_addr >= KVM_MAX_VCPUS) + return SIGP_CC_NOT_OPERATIONAL; + + dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); + if (!dst_vcpu) + return SIGP_CC_NOT_OPERATIONAL; + + switch (order_code) { + case SIGP_SENSE: + vcpu->stat.instruction_sigp_sense++; + rc = __sigp_sense(vcpu, dst_vcpu, status_reg); + break; + case SIGP_EXTERNAL_CALL: + vcpu->stat.instruction_sigp_external_call++; + rc = __sigp_external_call(vcpu, dst_vcpu, status_reg); + break; + case SIGP_EMERGENCY_SIGNAL: + vcpu->stat.instruction_sigp_emergency++; + rc = __sigp_emergency(vcpu, dst_vcpu); + break; + case SIGP_STOP: + vcpu->stat.instruction_sigp_stop++; + rc = __sigp_stop(vcpu, dst_vcpu); + break; + case SIGP_STOP_AND_STORE_STATUS: + vcpu->stat.instruction_sigp_stop_store_status++; + rc = __sigp_stop_and_store_status(vcpu, dst_vcpu, status_reg); + break; + case SIGP_STORE_STATUS_AT_ADDRESS: + vcpu->stat.instruction_sigp_store_status++; + rc = __sigp_store_status_at_addr(vcpu, dst_vcpu, parameter, + status_reg); + break; + case SIGP_SET_PREFIX: + vcpu->stat.instruction_sigp_prefix++; + rc = __sigp_set_prefix(vcpu, dst_vcpu, parameter, status_reg); + break; + case SIGP_COND_EMERGENCY_SIGNAL: + vcpu->stat.instruction_sigp_cond_emergency++; + rc = __sigp_conditional_emergency(vcpu, dst_vcpu, parameter, + status_reg); + break; + case SIGP_SENSE_RUNNING: + vcpu->stat.instruction_sigp_sense_running++; + rc = __sigp_sense_running(vcpu, dst_vcpu, status_reg); + break; + case SIGP_START: + vcpu->stat.instruction_sigp_start++; + rc = __prepare_sigp_re_start(vcpu, dst_vcpu, order_code); + break; + case SIGP_RESTART: + vcpu->stat.instruction_sigp_restart++; + rc = __prepare_sigp_re_start(vcpu, dst_vcpu, order_code); + break; + case SIGP_INITIAL_CPU_RESET: + vcpu->stat.instruction_sigp_init_cpu_reset++; + rc = __prepare_sigp_cpu_reset(vcpu, dst_vcpu, order_code); + break; + case SIGP_CPU_RESET: + vcpu->stat.instruction_sigp_cpu_reset++; + rc = __prepare_sigp_cpu_reset(vcpu, dst_vcpu, order_code); + break; + default: + vcpu->stat.instruction_sigp_unknown++; + rc = __prepare_sigp_unknown(vcpu, dst_vcpu); + } + + if (rc == -EOPNOTSUPP) + VCPU_EVENT(vcpu, 4, + "sigp order %u -> cpu %x: handled in user space", + order_code, dst_vcpu->vcpu_id); + + return rc; +} + +static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code) +{ + if (!vcpu->kvm->arch.user_sigp) + return 0; + + switch (order_code) { + case SIGP_SENSE: + case SIGP_EXTERNAL_CALL: + case SIGP_EMERGENCY_SIGNAL: + case SIGP_COND_EMERGENCY_SIGNAL: + case SIGP_SENSE_RUNNING: + return 0; + /* update counters as we're directly dropping to user space */ + case SIGP_STOP: + vcpu->stat.instruction_sigp_stop++; + break; + case SIGP_STOP_AND_STORE_STATUS: + vcpu->stat.instruction_sigp_stop_store_status++; + break; + case SIGP_STORE_STATUS_AT_ADDRESS: + vcpu->stat.instruction_sigp_store_status++; + break; + case SIGP_STORE_ADDITIONAL_STATUS: + vcpu->stat.instruction_sigp_store_adtl_status++; + break; + case SIGP_SET_PREFIX: + vcpu->stat.instruction_sigp_prefix++; + break; + case SIGP_START: + vcpu->stat.instruction_sigp_start++; + break; + case SIGP_RESTART: + vcpu->stat.instruction_sigp_restart++; + break; + case SIGP_INITIAL_CPU_RESET: + vcpu->stat.instruction_sigp_init_cpu_reset++; + break; + case SIGP_CPU_RESET: + vcpu->stat.instruction_sigp_cpu_reset++; + break; + default: + vcpu->stat.instruction_sigp_unknown++; + } + + VCPU_EVENT(vcpu, 4, "sigp order %u: completely handled in user space", + order_code); + + return 1; +} + +int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) +{ + int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int r3 = vcpu->arch.sie_block->ipa & 0x000f; + u32 parameter; + u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; + u8 order_code; + int rc; + + /* sigp in userspace can exit */ + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); + if (handle_sigp_order_in_user_space(vcpu, order_code)) + return -EOPNOTSUPP; + + if (r1 % 2) + parameter = vcpu->run->s.regs.gprs[r1]; + else + parameter = vcpu->run->s.regs.gprs[r1 + 1]; + + trace_kvm_s390_handle_sigp(vcpu, order_code, cpu_addr, parameter); + switch (order_code) { + case SIGP_SET_ARCHITECTURE: + vcpu->stat.instruction_sigp_arch++; + rc = __sigp_set_arch(vcpu, parameter); + break; + default: + rc = handle_sigp_dst(vcpu, order_code, cpu_addr, + parameter, + &vcpu->run->s.regs.gprs[r1]); + } + + if (rc < 0) + return rc; + + kvm_s390_set_psw_cc(vcpu, rc); + return 0; +} + +/* + * Handle SIGP partial execution interception. + * + * This interception will occur at the source cpu when a source cpu sends an + * external call to a target cpu and the target cpu has the WAIT bit set in + * its cpuflags. Interception will occurr after the interrupt indicator bits at + * the target cpu have been set. All error cases will lead to instruction + * interception, therefore nothing is to be checked or prepared. + */ +int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) +{ + int r3 = vcpu->arch.sie_block->ipa & 0x000f; + u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; + struct kvm_vcpu *dest_vcpu; + u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); + + trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); + + if (order_code == SIGP_EXTERNAL_CALL) { + dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); + BUG_ON(dest_vcpu == NULL); + + kvm_s390_vcpu_wakeup(dest_vcpu); + kvm_s390_set_psw_cc(vcpu, SIGP_CC_ORDER_CODE_ACCEPTED); + return 0; + } + + return -EOPNOTSUPP; +} diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h new file mode 100644 index 000000000..3208d33a4 --- /dev/null +++ b/arch/s390/kvm/trace-s390.h @@ -0,0 +1,282 @@ +#if !defined(_TRACE_KVMS390_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVMS390_H + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm-s390 +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace-s390 + +/* + * The TRACE_SYSTEM_VAR defaults to TRACE_SYSTEM, but must be a + * legitimate C variable. It is not exported to user space. + */ +#undef TRACE_SYSTEM_VAR +#define TRACE_SYSTEM_VAR kvm_s390 + +/* + * Trace point for the creation of the kvm instance. + */ +TRACE_EVENT(kvm_s390_create_vm, + TP_PROTO(unsigned long type), + TP_ARGS(type), + + TP_STRUCT__entry( + __field(unsigned long, type) + ), + + TP_fast_assign( + __entry->type = type; + ), + + TP_printk("create vm%s", + __entry->type & KVM_VM_S390_UCONTROL ? " (UCONTROL)" : "") + ); + +/* + * Trace points for creation and destruction of vpcus. + */ +TRACE_EVENT(kvm_s390_create_vcpu, + TP_PROTO(unsigned int id, struct kvm_vcpu *vcpu, + struct kvm_s390_sie_block *sie_block), + TP_ARGS(id, vcpu, sie_block), + + TP_STRUCT__entry( + __field(unsigned int, id) + __field(struct kvm_vcpu *, vcpu) + __field(struct kvm_s390_sie_block *, sie_block) + ), + + TP_fast_assign( + __entry->id = id; + __entry->vcpu = vcpu; + __entry->sie_block = sie_block; + ), + + TP_printk("create cpu %d at %p, sie block at %p", __entry->id, + __entry->vcpu, __entry->sie_block) + ); + +TRACE_EVENT(kvm_s390_destroy_vcpu, + TP_PROTO(unsigned int id), + TP_ARGS(id), + + TP_STRUCT__entry( + __field(unsigned int, id) + ), + + TP_fast_assign( + __entry->id = id; + ), + + TP_printk("destroy cpu %d", __entry->id) + ); + +/* + * Trace point for start and stop of vpcus. + */ +TRACE_EVENT(kvm_s390_vcpu_start_stop, + TP_PROTO(unsigned int id, int state), + TP_ARGS(id, state), + + TP_STRUCT__entry( + __field(unsigned int, id) + __field(int, state) + ), + + TP_fast_assign( + __entry->id = id; + __entry->state = state; + ), + + TP_printk("%s cpu %d", __entry->state ? "starting" : "stopping", + __entry->id) + ); + +/* + * Trace points for injection of interrupts, either per machine or + * per vcpu. + */ + +#define kvm_s390_int_type \ + {KVM_S390_SIGP_STOP, "sigp stop"}, \ + {KVM_S390_PROGRAM_INT, "program interrupt"}, \ + {KVM_S390_SIGP_SET_PREFIX, "sigp set prefix"}, \ + {KVM_S390_RESTART, "sigp restart"}, \ + {KVM_S390_INT_VIRTIO, "virtio interrupt"}, \ + {KVM_S390_INT_SERVICE, "sclp interrupt"}, \ + {KVM_S390_INT_EMERGENCY, "sigp emergency"}, \ + {KVM_S390_INT_EXTERNAL_CALL, "sigp ext call"} + +TRACE_EVENT(kvm_s390_inject_vm, + TP_PROTO(__u64 type, __u32 parm, __u64 parm64, int who), + TP_ARGS(type, parm, parm64, who), + + TP_STRUCT__entry( + __field(__u32, inttype) + __field(__u32, parm) + __field(__u64, parm64) + __field(int, who) + ), + + TP_fast_assign( + __entry->inttype = type & 0x00000000ffffffff; + __entry->parm = parm; + __entry->parm64 = parm64; + __entry->who = who; + ), + + TP_printk("inject%s: type:%x (%s) parm:%x parm64:%llx", + (__entry->who == 1) ? " (from kernel)" : + (__entry->who == 2) ? " (from user)" : "", + __entry->inttype, + __print_symbolic(__entry->inttype, kvm_s390_int_type), + __entry->parm, __entry->parm64) + ); + +TRACE_EVENT(kvm_s390_inject_vcpu, + TP_PROTO(unsigned int id, __u64 type, __u32 parm, __u64 parm64, \ + int who), + TP_ARGS(id, type, parm, parm64, who), + + TP_STRUCT__entry( + __field(int, id) + __field(__u32, inttype) + __field(__u32, parm) + __field(__u64, parm64) + __field(int, who) + ), + + TP_fast_assign( + __entry->id = id; + __entry->inttype = type & 0x00000000ffffffff; + __entry->parm = parm; + __entry->parm64 = parm64; + __entry->who = who; + ), + + TP_printk("inject%s (vcpu %d): type:%x (%s) parm:%x parm64:%llx", + (__entry->who == 1) ? " (from kernel)" : + (__entry->who == 2) ? " (from user)" : "", + __entry->id, __entry->inttype, + __print_symbolic(__entry->inttype, kvm_s390_int_type), + __entry->parm, __entry->parm64) + ); + +/* + * Trace point for the actual delivery of interrupts. + */ +TRACE_EVENT(kvm_s390_deliver_interrupt, + TP_PROTO(unsigned int id, __u64 type, __u64 data0, __u64 data1), + TP_ARGS(id, type, data0, data1), + + TP_STRUCT__entry( + __field(int, id) + __field(__u32, inttype) + __field(__u64, data0) + __field(__u64, data1) + ), + + TP_fast_assign( + __entry->id = id; + __entry->inttype = type & 0x00000000ffffffff; + __entry->data0 = data0; + __entry->data1 = data1; + ), + + TP_printk("deliver interrupt (vcpu %d): type:%x (%s) " \ + "data:%08llx %016llx", + __entry->id, __entry->inttype, + __print_symbolic(__entry->inttype, kvm_s390_int_type), + __entry->data0, __entry->data1) + ); + +/* + * Trace point for resets that may be requested from userspace. + */ +TRACE_EVENT(kvm_s390_request_resets, + TP_PROTO(__u64 resets), + TP_ARGS(resets), + + TP_STRUCT__entry( + __field(__u64, resets) + ), + + TP_fast_assign( + __entry->resets = resets; + ), + + TP_printk("requesting userspace resets %llx", + __entry->resets) + ); + +/* + * Trace point for a vcpu's stop requests. + */ +TRACE_EVENT(kvm_s390_stop_request, + TP_PROTO(unsigned char stop_irq, unsigned char flags), + TP_ARGS(stop_irq, flags), + + TP_STRUCT__entry( + __field(unsigned char, stop_irq) + __field(unsigned char, flags) + ), + + TP_fast_assign( + __entry->stop_irq = stop_irq; + __entry->flags = flags; + ), + + TP_printk("stop request, stop irq = %u, flags = %08x", + __entry->stop_irq, __entry->flags) + ); + + +/* + * Trace point for enabling channel I/O instruction support. + */ +TRACE_EVENT(kvm_s390_enable_css, + TP_PROTO(void *kvm), + TP_ARGS(kvm), + + TP_STRUCT__entry( + __field(void *, kvm) + ), + + TP_fast_assign( + __entry->kvm = kvm; + ), + + TP_printk("enabling channel I/O support (kvm @ %p)\n", + __entry->kvm) + ); + +/* + * Trace point for enabling and disabling interlocking-and-broadcasting + * suppression. + */ +TRACE_EVENT(kvm_s390_enable_disable_ibs, + TP_PROTO(unsigned int id, int state), + TP_ARGS(id, state), + + TP_STRUCT__entry( + __field(unsigned int, id) + __field(int, state) + ), + + TP_fast_assign( + __entry->id = id; + __entry->state = state; + ), + + TP_printk("%s ibs on cpu %d", + __entry->state ? "enabling" : "disabling", __entry->id) + ); + + +#endif /* _TRACE_KVMS390_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h new file mode 100644 index 000000000..916834d7a --- /dev/null +++ b/arch/s390/kvm/trace.h @@ -0,0 +1,418 @@ +#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_H + +#include <linux/tracepoint.h> +#include <asm/sie.h> +#include <asm/debug.h> +#include <asm/dis.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* + * Helpers for vcpu-specific tracepoints containing the same information + * as s390dbf VCPU_EVENTs. + */ +#define VCPU_PROTO_COMMON struct kvm_vcpu *vcpu +#define VCPU_ARGS_COMMON vcpu +#define VCPU_FIELD_COMMON __field(int, id) \ + __field(unsigned long, pswmask) \ + __field(unsigned long, pswaddr) +#define VCPU_ASSIGN_COMMON do { \ + __entry->id = vcpu->vcpu_id; \ + __entry->pswmask = vcpu->arch.sie_block->gpsw.mask; \ + __entry->pswaddr = vcpu->arch.sie_block->gpsw.addr; \ + } while (0); +#define VCPU_TP_PRINTK(p_str, p_args...) \ + TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id, \ + __entry->pswmask, __entry->pswaddr, p_args) + +TRACE_EVENT(kvm_s390_skey_related_inst, + TP_PROTO(VCPU_PROTO_COMMON), + TP_ARGS(VCPU_ARGS_COMMON), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + ), + VCPU_TP_PRINTK("%s", "first instruction related to skeys on vcpu") + ); + +TRACE_EVENT(kvm_s390_major_guest_pfault, + TP_PROTO(VCPU_PROTO_COMMON), + TP_ARGS(VCPU_ARGS_COMMON), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + ), + VCPU_TP_PRINTK("%s", "major fault, maybe applicable for pfault") + ); + +TRACE_EVENT(kvm_s390_pfault_init, + TP_PROTO(VCPU_PROTO_COMMON, long pfault_token), + TP_ARGS(VCPU_ARGS_COMMON, pfault_token), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(long, pfault_token) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->pfault_token = pfault_token; + ), + VCPU_TP_PRINTK("init pfault token %ld", __entry->pfault_token) + ); + +TRACE_EVENT(kvm_s390_pfault_done, + TP_PROTO(VCPU_PROTO_COMMON, long pfault_token), + TP_ARGS(VCPU_ARGS_COMMON, pfault_token), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(long, pfault_token) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->pfault_token = pfault_token; + ), + VCPU_TP_PRINTK("done pfault token %ld", __entry->pfault_token) + ); + +/* + * Tracepoints for SIE entry and exit. + */ +TRACE_EVENT(kvm_s390_sie_enter, + TP_PROTO(VCPU_PROTO_COMMON, int cpuflags), + TP_ARGS(VCPU_ARGS_COMMON, cpuflags), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(int, cpuflags) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->cpuflags = cpuflags; + ), + + VCPU_TP_PRINTK("entering sie flags %x", __entry->cpuflags) + ); + +TRACE_EVENT(kvm_s390_sie_fault, + TP_PROTO(VCPU_PROTO_COMMON), + TP_ARGS(VCPU_ARGS_COMMON), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + ), + + VCPU_TP_PRINTK("%s", "fault in sie instruction") + ); + +TRACE_EVENT(kvm_s390_sie_exit, + TP_PROTO(VCPU_PROTO_COMMON, u8 icptcode), + TP_ARGS(VCPU_ARGS_COMMON, icptcode), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(u8, icptcode) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->icptcode = icptcode; + ), + + VCPU_TP_PRINTK("exit sie icptcode %d (%s)", __entry->icptcode, + __print_symbolic(__entry->icptcode, + sie_intercept_code)) + ); + +/* + * Trace point for intercepted instructions. + */ +TRACE_EVENT(kvm_s390_intercept_instruction, + TP_PROTO(VCPU_PROTO_COMMON, __u16 ipa, __u32 ipb), + TP_ARGS(VCPU_ARGS_COMMON, ipa, ipb), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(__u64, instruction) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->instruction = ((__u64)ipa << 48) | + ((__u64)ipb << 16); + ), + + VCPU_TP_PRINTK("intercepted instruction %016llx (%s)", + __entry->instruction, + __print_symbolic(icpt_insn_decoder(__entry->instruction), + icpt_insn_codes)) + ); + +/* + * Trace point for intercepted program interruptions. + */ +TRACE_EVENT(kvm_s390_intercept_prog, + TP_PROTO(VCPU_PROTO_COMMON, __u16 code), + TP_ARGS(VCPU_ARGS_COMMON, code), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(__u16, code) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->code = code; + ), + + VCPU_TP_PRINTK("intercepted program interruption %04x", + __entry->code) + ); + +/* + * Trace point for validity intercepts. + */ +TRACE_EVENT(kvm_s390_intercept_validity, + TP_PROTO(VCPU_PROTO_COMMON, __u16 viwhy), + TP_ARGS(VCPU_ARGS_COMMON, viwhy), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(__u16, viwhy) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->viwhy = viwhy; + ), + + VCPU_TP_PRINTK("got validity intercept %04x", __entry->viwhy) + ); + +/* + * Trace points for instructions that are of special interest. + */ + +TRACE_EVENT(kvm_s390_handle_sigp, + TP_PROTO(VCPU_PROTO_COMMON, __u8 order_code, __u16 cpu_addr, \ + __u32 parameter), + TP_ARGS(VCPU_ARGS_COMMON, order_code, cpu_addr, parameter), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(__u8, order_code) + __field(__u16, cpu_addr) + __field(__u32, parameter) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->order_code = order_code; + __entry->cpu_addr = cpu_addr; + __entry->parameter = parameter; + ), + + VCPU_TP_PRINTK("handle sigp order %02x (%s), cpu address %04x, " \ + "parameter %08x", __entry->order_code, + __print_symbolic(__entry->order_code, + sigp_order_codes), + __entry->cpu_addr, __entry->parameter) + ); + +TRACE_EVENT(kvm_s390_handle_sigp_pei, + TP_PROTO(VCPU_PROTO_COMMON, __u8 order_code, __u16 cpu_addr), + TP_ARGS(VCPU_ARGS_COMMON, order_code, cpu_addr), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(__u8, order_code) + __field(__u16, cpu_addr) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->order_code = order_code; + __entry->cpu_addr = cpu_addr; + ), + + VCPU_TP_PRINTK("handle sigp pei order %02x (%s), cpu address %04x", + __entry->order_code, + __print_symbolic(__entry->order_code, + sigp_order_codes), + __entry->cpu_addr) + ); + +TRACE_EVENT(kvm_s390_handle_diag, + TP_PROTO(VCPU_PROTO_COMMON, __u16 code), + TP_ARGS(VCPU_ARGS_COMMON, code), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(__u16, code) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->code = code; + ), + + VCPU_TP_PRINTK("handle diagnose call %04x (%s)", __entry->code, + __print_symbolic(__entry->code, diagnose_codes)) + ); + +TRACE_EVENT(kvm_s390_handle_lctl, + TP_PROTO(VCPU_PROTO_COMMON, int g, int reg1, int reg3, u64 addr), + TP_ARGS(VCPU_ARGS_COMMON, g, reg1, reg3, addr), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(int, g) + __field(int, reg1) + __field(int, reg3) + __field(u64, addr) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->g = g; + __entry->reg1 = reg1; + __entry->reg3 = reg3; + __entry->addr = addr; + ), + + VCPU_TP_PRINTK("%s: loading cr %x-%x from %016llx", + __entry->g ? "lctlg" : "lctl", + __entry->reg1, __entry->reg3, __entry->addr) + ); + +TRACE_EVENT(kvm_s390_handle_stctl, + TP_PROTO(VCPU_PROTO_COMMON, int g, int reg1, int reg3, u64 addr), + TP_ARGS(VCPU_ARGS_COMMON, g, reg1, reg3, addr), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(int, g) + __field(int, reg1) + __field(int, reg3) + __field(u64, addr) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->g = g; + __entry->reg1 = reg1; + __entry->reg3 = reg3; + __entry->addr = addr; + ), + + VCPU_TP_PRINTK("%s: storing cr %x-%x to %016llx", + __entry->g ? "stctg" : "stctl", + __entry->reg1, __entry->reg3, __entry->addr) + ); + +TRACE_EVENT(kvm_s390_handle_prefix, + TP_PROTO(VCPU_PROTO_COMMON, int set, u32 address), + TP_ARGS(VCPU_ARGS_COMMON, set, address), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(int, set) + __field(u32, address) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->set = set; + __entry->address = address; + ), + + VCPU_TP_PRINTK("%s prefix to %08x", + __entry->set ? "setting" : "storing", + __entry->address) + ); + +TRACE_EVENT(kvm_s390_handle_stap, + TP_PROTO(VCPU_PROTO_COMMON, u64 address), + TP_ARGS(VCPU_ARGS_COMMON, address), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(u64, address) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->address = address; + ), + + VCPU_TP_PRINTK("storing cpu address to %016llx", + __entry->address) + ); + +TRACE_EVENT(kvm_s390_handle_stfl, + TP_PROTO(VCPU_PROTO_COMMON, unsigned int facility_list), + TP_ARGS(VCPU_ARGS_COMMON, facility_list), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(unsigned int, facility_list) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->facility_list = facility_list; + ), + + VCPU_TP_PRINTK("store facility list value %08x", + __entry->facility_list) + ); + +TRACE_EVENT(kvm_s390_handle_stsi, + TP_PROTO(VCPU_PROTO_COMMON, int fc, int sel1, int sel2, u64 addr), + TP_ARGS(VCPU_ARGS_COMMON, fc, sel1, sel2, addr), + + TP_STRUCT__entry( + VCPU_FIELD_COMMON + __field(int, fc) + __field(int, sel1) + __field(int, sel2) + __field(u64, addr) + ), + + TP_fast_assign( + VCPU_ASSIGN_COMMON + __entry->fc = fc; + __entry->sel1 = sel1; + __entry->sel2 = sel2; + __entry->addr = addr; + ), + + VCPU_TP_PRINTK("STSI %d.%d.%d information stored to %016llx", + __entry->fc, __entry->sel1, __entry->sel2, + __entry->addr) + ); + +#endif /* _TRACE_KVM_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> |