diff options
Diffstat (limited to 'arch/s390/kvm/kvm-s390.c')
-rw-r--r-- | arch/s390/kvm/kvm-s390.c | 2479 |
1 files changed, 1884 insertions, 595 deletions
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d9e6bf3d54f0..ea63ac769889 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2,11 +2,10 @@ /* * hosting IBM Z kernel virtual machines (s390x) * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * 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> */ @@ -31,11 +30,12 @@ #include <linux/bitmap.h> #include <linux/sched/signal.h> #include <linux/string.h> +#include <linux/pgtable.h> +#include <linux/mmu_notifier.h> #include <asm/asm-offsets.h> #include <asm/lowcore.h> #include <asm/stp.h> -#include <asm/pgtable.h> #include <asm/gmap.h> #include <asm/nmi.h> #include <asm/switch_to.h> @@ -44,8 +44,11 @@ #include <asm/cpacf.h> #include <asm/timex.h> #include <asm/ap.h> +#include <asm/uv.h> +#include <asm/fpu/api.h> #include "kvm-s390.h" #include "gaccess.h" +#include "pci.h" #define CREATE_TRACE_POINTS #include "trace.h" @@ -56,118 +59,137 @@ #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 -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM - -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_io_request", VCPU_STAT(exit_io_request) }, - { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) }, - { "exit_instruction", VCPU_STAT(exit_instruction) }, - { "exit_pei", VCPU_STAT(exit_pei) }, - { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, - { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, - { "exit_operation_exception", VCPU_STAT(exit_operation_exception) }, - { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, - { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, - { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, - { "halt_no_poll_steal", VCPU_STAT(halt_no_poll_steal) }, - { "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_ckc", VCPU_STAT(deliver_ckc) }, - { "deliver_cputm", VCPU_STAT(deliver_cputm) }, - { "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", VCPU_STAT(deliver_virtio) }, - { "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", VCPU_STAT(deliver_program) }, - { "deliver_io", VCPU_STAT(deliver_io) }, - { "deliver_machine_check", VCPU_STAT(deliver_machine_check) }, - { "exit_wait_state", VCPU_STAT(exit_wait_state) }, - { "inject_ckc", VCPU_STAT(inject_ckc) }, - { "inject_cputm", VCPU_STAT(inject_cputm) }, - { "inject_external_call", VCPU_STAT(inject_external_call) }, - { "inject_float_mchk", VM_STAT(inject_float_mchk) }, - { "inject_emergency_signal", VCPU_STAT(inject_emergency_signal) }, - { "inject_io", VM_STAT(inject_io) }, - { "inject_mchk", VCPU_STAT(inject_mchk) }, - { "inject_pfault_done", VM_STAT(inject_pfault_done) }, - { "inject_program", VCPU_STAT(inject_program) }, - { "inject_restart", VCPU_STAT(inject_restart) }, - { "inject_service_signal", VM_STAT(inject_service_signal) }, - { "inject_set_prefix", VCPU_STAT(inject_set_prefix) }, - { "inject_stop_signal", VCPU_STAT(inject_stop_signal) }, - { "inject_pfault_init", VCPU_STAT(inject_pfault_init) }, - { "inject_virtio", VM_STAT(inject_virtio) }, - { "instruction_epsw", VCPU_STAT(instruction_epsw) }, - { "instruction_gs", VCPU_STAT(instruction_gs) }, - { "instruction_io_other", VCPU_STAT(instruction_io_other) }, - { "instruction_lpsw", VCPU_STAT(instruction_lpsw) }, - { "instruction_lpswe", VCPU_STAT(instruction_lpswe) }, - { "instruction_pfmf", VCPU_STAT(instruction_pfmf) }, - { "instruction_ptff", VCPU_STAT(instruction_ptff) }, - { "instruction_stidp", VCPU_STAT(instruction_stidp) }, - { "instruction_sck", VCPU_STAT(instruction_sck) }, - { "instruction_sckpf", VCPU_STAT(instruction_sckpf) }, - { "instruction_spx", VCPU_STAT(instruction_spx) }, - { "instruction_stpx", VCPU_STAT(instruction_stpx) }, - { "instruction_stap", VCPU_STAT(instruction_stap) }, - { "instruction_iske", VCPU_STAT(instruction_iske) }, - { "instruction_ri", VCPU_STAT(instruction_ri) }, - { "instruction_rrbe", VCPU_STAT(instruction_rrbe) }, - { "instruction_sske", VCPU_STAT(instruction_sske) }, - { "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) }, - { "instruction_essa", VCPU_STAT(instruction_essa) }, - { "instruction_stsi", VCPU_STAT(instruction_stsi) }, - { "instruction_stfl", VCPU_STAT(instruction_stfl) }, - { "instruction_tb", VCPU_STAT(instruction_tb) }, - { "instruction_tpi", VCPU_STAT(instruction_tpi) }, - { "instruction_tprot", VCPU_STAT(instruction_tprot) }, - { "instruction_tsch", VCPU_STAT(instruction_tsch) }, - { "instruction_sthyi", VCPU_STAT(instruction_sthyi) }, - { "instruction_sie", VCPU_STAT(instruction_sie) }, - { "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) }, - { "instruction_diag_10", VCPU_STAT(diagnose_10) }, - { "instruction_diag_44", VCPU_STAT(diagnose_44) }, - { "instruction_diag_9c", VCPU_STAT(diagnose_9c) }, - { "diag_9c_ignored", VCPU_STAT(diagnose_9c_ignored) }, - { "instruction_diag_258", VCPU_STAT(diagnose_258) }, - { "instruction_diag_308", VCPU_STAT(diagnose_308) }, - { "instruction_diag_500", VCPU_STAT(diagnose_500) }, - { "instruction_diag_other", VCPU_STAT(diagnose_other) }, - { NULL } +const struct _kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS(), + STATS_DESC_COUNTER(VM, inject_io), + STATS_DESC_COUNTER(VM, inject_float_mchk), + STATS_DESC_COUNTER(VM, inject_pfault_done), + STATS_DESC_COUNTER(VM, inject_service_signal), + STATS_DESC_COUNTER(VM, inject_virtio), + STATS_DESC_COUNTER(VM, aen_forward), + STATS_DESC_COUNTER(VM, gmap_shadow_reuse), + STATS_DESC_COUNTER(VM, gmap_shadow_create), + STATS_DESC_COUNTER(VM, gmap_shadow_r1_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r2_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r3_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_sg_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_pg_entry), }; -struct kvm_s390_tod_clock_ext { - __u8 epoch_idx; - __u64 tod; - __u8 reserved[7]; -} __packed; +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, exit_userspace), + STATS_DESC_COUNTER(VCPU, exit_null), + STATS_DESC_COUNTER(VCPU, exit_external_request), + STATS_DESC_COUNTER(VCPU, exit_io_request), + STATS_DESC_COUNTER(VCPU, exit_external_interrupt), + STATS_DESC_COUNTER(VCPU, exit_stop_request), + STATS_DESC_COUNTER(VCPU, exit_validity), + STATS_DESC_COUNTER(VCPU, exit_instruction), + STATS_DESC_COUNTER(VCPU, exit_pei), + STATS_DESC_COUNTER(VCPU, halt_no_poll_steal), + STATS_DESC_COUNTER(VCPU, instruction_lctl), + STATS_DESC_COUNTER(VCPU, instruction_lctlg), + STATS_DESC_COUNTER(VCPU, instruction_stctl), + STATS_DESC_COUNTER(VCPU, instruction_stctg), + STATS_DESC_COUNTER(VCPU, exit_program_interruption), + STATS_DESC_COUNTER(VCPU, exit_instr_and_program), + STATS_DESC_COUNTER(VCPU, exit_operation_exception), + STATS_DESC_COUNTER(VCPU, deliver_ckc), + STATS_DESC_COUNTER(VCPU, deliver_cputm), + STATS_DESC_COUNTER(VCPU, deliver_external_call), + STATS_DESC_COUNTER(VCPU, deliver_emergency_signal), + STATS_DESC_COUNTER(VCPU, deliver_service_signal), + STATS_DESC_COUNTER(VCPU, deliver_virtio), + STATS_DESC_COUNTER(VCPU, deliver_stop_signal), + STATS_DESC_COUNTER(VCPU, deliver_prefix_signal), + STATS_DESC_COUNTER(VCPU, deliver_restart_signal), + STATS_DESC_COUNTER(VCPU, deliver_program), + STATS_DESC_COUNTER(VCPU, deliver_io), + STATS_DESC_COUNTER(VCPU, deliver_machine_check), + STATS_DESC_COUNTER(VCPU, exit_wait_state), + STATS_DESC_COUNTER(VCPU, inject_ckc), + STATS_DESC_COUNTER(VCPU, inject_cputm), + STATS_DESC_COUNTER(VCPU, inject_external_call), + STATS_DESC_COUNTER(VCPU, inject_emergency_signal), + STATS_DESC_COUNTER(VCPU, inject_mchk), + STATS_DESC_COUNTER(VCPU, inject_pfault_init), + STATS_DESC_COUNTER(VCPU, inject_program), + STATS_DESC_COUNTER(VCPU, inject_restart), + STATS_DESC_COUNTER(VCPU, inject_set_prefix), + STATS_DESC_COUNTER(VCPU, inject_stop_signal), + STATS_DESC_COUNTER(VCPU, instruction_epsw), + STATS_DESC_COUNTER(VCPU, instruction_gs), + STATS_DESC_COUNTER(VCPU, instruction_io_other), + STATS_DESC_COUNTER(VCPU, instruction_lpsw), + STATS_DESC_COUNTER(VCPU, instruction_lpswe), + STATS_DESC_COUNTER(VCPU, instruction_pfmf), + STATS_DESC_COUNTER(VCPU, instruction_ptff), + STATS_DESC_COUNTER(VCPU, instruction_sck), + STATS_DESC_COUNTER(VCPU, instruction_sckpf), + STATS_DESC_COUNTER(VCPU, instruction_stidp), + STATS_DESC_COUNTER(VCPU, instruction_spx), + STATS_DESC_COUNTER(VCPU, instruction_stpx), + STATS_DESC_COUNTER(VCPU, instruction_stap), + STATS_DESC_COUNTER(VCPU, instruction_iske), + STATS_DESC_COUNTER(VCPU, instruction_ri), + STATS_DESC_COUNTER(VCPU, instruction_rrbe), + STATS_DESC_COUNTER(VCPU, instruction_sske), + STATS_DESC_COUNTER(VCPU, instruction_ipte_interlock), + STATS_DESC_COUNTER(VCPU, instruction_stsi), + STATS_DESC_COUNTER(VCPU, instruction_stfl), + STATS_DESC_COUNTER(VCPU, instruction_tb), + STATS_DESC_COUNTER(VCPU, instruction_tpi), + STATS_DESC_COUNTER(VCPU, instruction_tprot), + STATS_DESC_COUNTER(VCPU, instruction_tsch), + STATS_DESC_COUNTER(VCPU, instruction_sie), + STATS_DESC_COUNTER(VCPU, instruction_essa), + STATS_DESC_COUNTER(VCPU, instruction_sthyi), + STATS_DESC_COUNTER(VCPU, instruction_sigp_sense), + STATS_DESC_COUNTER(VCPU, instruction_sigp_sense_running), + STATS_DESC_COUNTER(VCPU, instruction_sigp_external_call), + STATS_DESC_COUNTER(VCPU, instruction_sigp_emergency), + STATS_DESC_COUNTER(VCPU, instruction_sigp_cond_emergency), + STATS_DESC_COUNTER(VCPU, instruction_sigp_start), + STATS_DESC_COUNTER(VCPU, instruction_sigp_stop), + STATS_DESC_COUNTER(VCPU, instruction_sigp_stop_store_status), + STATS_DESC_COUNTER(VCPU, instruction_sigp_store_status), + STATS_DESC_COUNTER(VCPU, instruction_sigp_store_adtl_status), + STATS_DESC_COUNTER(VCPU, instruction_sigp_arch), + STATS_DESC_COUNTER(VCPU, instruction_sigp_prefix), + STATS_DESC_COUNTER(VCPU, instruction_sigp_restart), + STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset), + STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset), + STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_10), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_44), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_9c), + STATS_DESC_COUNTER(VCPU, diag_9c_ignored), + STATS_DESC_COUNTER(VCPU, diag_9c_forward), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_258), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_308), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_500), + STATS_DESC_COUNTER(VCPU, instruction_diagnose_other), + STATS_DESC_COUNTER(VCPU, pfault_sync) +}; + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), +}; /* allow nested virtualization in KVM (if enabled by user space) */ static int nested; @@ -184,6 +206,24 @@ static u8 halt_poll_max_steal = 10; module_param(halt_poll_max_steal, byte, 0644); MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling"); +/* if set to true, the GISA will be initialized and used if available */ +static bool use_gisa = true; +module_param(use_gisa, bool, 0644); +MODULE_PARM_DESC(use_gisa, "Use the GISA if the host supports it."); + +/* maximum diag9c forwarding per second */ +unsigned int diag9c_forwarding_hz; +module_param(diag9c_forwarding_hz, uint, 0644); +MODULE_PARM_DESC(diag9c_forwarding_hz, "Maximum diag9c forwarding per second, 0 to turn off"); + +/* + * allow asynchronous deinit for protected guests; enable by default since + * the feature is opt-in anyway + */ +static int async_destroy = 1; +module_param(async_destroy, int, 0444); +MODULE_PARM_DESC(async_destroy, "Asynchronous destroy for protected guests"); + /* * For now we handle at most 16 double words as this is what the s390 base * kernel handles and stores in the prefix page. If we ever need to go beyond @@ -207,7 +247,7 @@ static unsigned long kvm_s390_fac_size(void) BUILD_BUG_ON(SIZE_INTERNAL > S390_ARCH_FAC_MASK_SIZE_U64); BUILD_BUG_ON(SIZE_INTERNAL > S390_ARCH_FAC_LIST_SIZE_U64); BUILD_BUG_ON(SIZE_INTERNAL * sizeof(unsigned long) > - sizeof(S390_lowcore.stfle_fac_list)); + sizeof(stfle_fac_list)); return SIZE_INTERNAL; } @@ -220,21 +260,13 @@ static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc; static struct gmap_notifier gmap_notifier; static struct gmap_notifier vsie_gmap_notifier; debug_info_t *kvm_s390_dbf; +debug_info_t *kvm_s390_dbf_uv; /* Section: not file related */ -int kvm_arch_hardware_enable(void) -{ - /* every s390 is virtualization enabled ;-) */ - return 0; -} - -int kvm_arch_check_processor_compat(void) -{ - return 0; -} - +/* forward declarations */ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); +static int sca_switch_to_extended(struct kvm *kvm); static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta) { @@ -269,7 +301,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { @@ -293,25 +325,6 @@ static struct notifier_block kvm_clock_notifier = { .notifier_call = kvm_clock_sync, }; -int kvm_arch_hardware_setup(void) -{ - gmap_notifier.notifier_call = kvm_gmap_notifier; - gmap_register_pte_notifier(&gmap_notifier); - vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier; - gmap_register_pte_notifier(&vsie_gmap_notifier); - atomic_notifier_chain_register(&s390_epoch_delta_notifier, - &kvm_clock_notifier); - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - gmap_unregister_pte_notifier(&gmap_notifier); - gmap_unregister_pte_notifier(&vsie_gmap_notifier); - atomic_notifier_chain_unregister(&s390_epoch_delta_notifier, - &kvm_clock_notifier); -} - static void allow_cpu_feat(unsigned long nr) { set_bit_inv(nr, kvm_s390_available_cpu_feat); @@ -319,37 +332,37 @@ static void allow_cpu_feat(unsigned long nr) static inline int plo_test_bit(unsigned char nr) { - register unsigned long r0 asm("0") = (unsigned long) nr | 0x100; + unsigned long function = (unsigned long)nr | 0x100; int cc; asm volatile( + " lgr 0,%[function]\n" /* Parameter registers are ignored for "test bit" */ " plo 0,0,0,0(0)\n" " ipm %0\n" " srl %0,28\n" : "=d" (cc) - : "d" (r0) - : "cc"); + : [function] "d" (function) + : "cc", "0"); return cc == 0; } static __always_inline void __insn32_query(unsigned int opcode, u8 *query) { - register unsigned long r0 asm("0") = 0; /* query function */ - register unsigned long r1 asm("1") = (unsigned long) query; - asm volatile( - /* Parameter regs are ignored */ + " lghi 0,0\n" + " lgr 1,%[query]\n" + /* Parameter registers are ignored */ " .insn rrf,%[opc] << 16,2,4,6,0\n" : - : "d" (r0), "a" (r1), [opc] "i" (opcode) - : "cc", "memory"); + : [query] "d" ((unsigned long)query), [opc] "i" (opcode) + : "cc", "memory", "0", "1"); } #define INSN_SORTL 0xb938 #define INSN_DFLTCC 0xb939 -static void kvm_s390_cpu_feat_init(void) +static void __init kvm_s390_cpu_feat_init(void) { int i; @@ -452,7 +465,7 @@ static void kvm_s390_cpu_feat_init(void) */ } -int kvm_arch_init(void *opaque) +static int __init __kvm_s390_init(void) { int rc = -ENOMEM; @@ -460,8 +473,13 @@ int kvm_arch_init(void *opaque) if (!kvm_s390_dbf) return -ENOMEM; - if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) - goto out; + kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long)); + if (!kvm_s390_dbf_uv) + goto err_kvm_uv; + + if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) || + debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view)) + goto err_debug_view; kvm_s390_cpu_feat_init(); @@ -469,24 +487,54 @@ int kvm_arch_init(void *opaque) rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); if (rc) { pr_err("A FLIC registration call failed with rc=%d\n", rc); - goto out; + goto err_flic; + } + + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { + rc = kvm_s390_pci_init(); + if (rc) { + pr_err("Unable to allocate AIFT for PCI\n"); + goto err_pci; + } } rc = kvm_s390_gib_init(GAL_ISC); if (rc) - goto out; + goto err_gib; + + gmap_notifier.notifier_call = kvm_gmap_notifier; + gmap_register_pte_notifier(&gmap_notifier); + vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier; + gmap_register_pte_notifier(&vsie_gmap_notifier); + atomic_notifier_chain_register(&s390_epoch_delta_notifier, + &kvm_clock_notifier); return 0; -out: - kvm_arch_exit(); +err_gib: + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + kvm_s390_pci_exit(); +err_pci: +err_flic: +err_debug_view: + debug_unregister(kvm_s390_dbf_uv); +err_kvm_uv: + debug_unregister(kvm_s390_dbf); return rc; } -void kvm_arch_exit(void) +static void __kvm_s390_exit(void) { + gmap_unregister_pte_notifier(&gmap_notifier); + gmap_unregister_pte_notifier(&vsie_gmap_notifier); + atomic_notifier_chain_unregister(&s390_epoch_delta_notifier, + &kvm_clock_notifier); + kvm_s390_gib_destroy(); + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + kvm_s390_pci_exit(); debug_unregister(kvm_s390_dbf); + debug_unregister(kvm_s390_dbf_uv); } /* Section: device related */ @@ -515,7 +563,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_S390_CSS_SUPPORT: case KVM_CAP_IOEVENTFD: - case KVM_CAP_DEVICE_CTRL: case KVM_CAP_S390_IRQCHIP: case KVM_CAP_VM_ATTRIBUTES: case KVM_CAP_MP_STATE: @@ -529,8 +576,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_CMMA_MIGRATION: case KVM_CAP_S390_AIS: case KVM_CAP_S390_AIS_MIGRATION: + case KVM_CAP_S390_VCPU_RESETS: + case KVM_CAP_SET_GUEST_DEBUG: + case KVM_CAP_S390_DIAG318: + case KVM_CAP_IRQFD_RESAMPLE: r = 1; break; + case KVM_CAP_SET_GUEST_DEBUG2: + r = KVM_GUESTDBG_VALID_MASK; + break; case KVM_CAP_S390_HPAGE_1M: r = 0; if (hpage && !kvm_is_ucontrol(kvm)) @@ -539,6 +593,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_MEM_OP: r = MEM_OP_MAX_SIZE; break; + case KVM_CAP_S390_MEM_OP_EXTENSION: + /* + * Flag bits indicating which extensions are supported. + * If r > 0, the base extension must also be supported/indicated, + * in order to maintain backwards compatibility. + */ + r = KVM_S390_MEMOP_EXTENSION_CAP_BASE | + KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG; + break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: @@ -547,12 +610,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; else if (sclp.has_esca && sclp.has_64bscao) r = KVM_S390_ESCA_CPU_SLOTS; + if (ext == KVM_CAP_NR_VCPUS) + r = min_t(unsigned int, num_online_cpus(), r); break; case KVM_CAP_S390_COW: r = MACHINE_HAS_ESOP; break; case KVM_CAP_S390_VECTOR_REGISTERS: - r = MACHINE_HAS_VX; + r = test_facility(129); break; case KVM_CAP_S390_RI: r = test_facility(64); @@ -563,14 +628,45 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_BPB: r = test_facility(82); break; + case KVM_CAP_S390_PROTECTED_ASYNC_DISABLE: + r = async_destroy && is_prot_virt_host(); + break; + case KVM_CAP_S390_PROTECTED: + r = is_prot_virt_host(); + break; + case KVM_CAP_S390_PROTECTED_DUMP: { + u64 pv_cmds_dump[] = { + BIT_UVC_CMD_DUMP_INIT, + BIT_UVC_CMD_DUMP_CONFIG_STOR_STATE, + BIT_UVC_CMD_DUMP_CPU, + BIT_UVC_CMD_DUMP_COMPLETE, + }; + int i; + + r = is_prot_virt_host(); + + for (i = 0; i < ARRAY_SIZE(pv_cmds_dump); i++) { + if (!test_bit_inv(pv_cmds_dump[i], + (unsigned long *)&uv_info.inst_calls_list)) { + r = 0; + break; + } + } + break; + } + case KVM_CAP_S390_ZPCI_OP: + r = kvm_s390_pci_interp_allowed(); + break; + case KVM_CAP_S390_CPU_TOPOLOGY: + r = test_facility(11); + break; default: r = 0; } return r; } -static void kvm_s390_sync_dirty_log(struct kvm *kvm, - struct kvm_memory_slot *memslot) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { int i; gfn_t cur_gfn, last_gfn; @@ -611,9 +707,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, { int r; unsigned long n; - struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int is_dirty = 0; + int is_dirty; if (kvm_is_ucontrol(kvm)) return -EINVAL; @@ -624,14 +719,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - slots = kvm_memslots(kvm); - memslot = id_to_memslot(slots, 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); + r = kvm_get_dirty_log(kvm, log, &is_dirty, &memslot); if (r) goto out; @@ -648,7 +736,7 @@ out: static void icpt_operexc_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -678,7 +766,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) mutex_lock(&kvm->lock); if (kvm->created_vcpus) { r = -EBUSY; - } else if (MACHINE_HAS_VX) { + } else if (cpu_has_vx()) { set_kvm_facility(kvm->arch.model.fac_mask, 129); set_kvm_facility(kvm->arch.model.fac_list, 129); if (test_facility(134)) { @@ -697,6 +785,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) set_kvm_facility(kvm->arch.model.fac_mask, 152); set_kvm_facility(kvm->arch.model.fac_list, 152); } + if (test_facility(192)) { + set_kvm_facility(kvm->arch.model.fac_mask, 192); + set_kvm_facility(kvm->arch.model.fac_list, 192); + } r = 0; } else r = -EINVAL; @@ -753,9 +845,9 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) r = -EINVAL; else { r = 0; - down_write(&kvm->mm->mmap_sem); + mmap_write_lock(kvm->mm); kvm->mm->context.allow_gmap_hpage_1m = 1; - up_write(&kvm->mm->mmap_sem); + mmap_write_unlock(kvm->mm); /* * We might have to create fake 4k page * tables. To avoid that the hardware works on @@ -779,6 +871,20 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) icpt_operexc_on_all_vcpus(kvm); r = 0; break; + case KVM_CAP_S390_CPU_TOPOLOGY: + r = -EINVAL; + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) { + r = -EBUSY; + } else if (test_facility(11)) { + set_kvm_facility(kvm->arch.model.fac_mask, 11); + set_kvm_facility(kvm->arch.model.fac_list, 11); + r = 0; + } + mutex_unlock(&kvm->lock); + VM_EVENT(kvm, 3, "ENABLE: CAP_S390_CPU_TOPOLOGY %s", + r ? "(not available)" : "(success)"); + break; default: r = -EINVAL; break; @@ -898,7 +1004,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_s390_vcpu_block_all(kvm); @@ -981,9 +1087,45 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) return 0; } +static void kvm_s390_vcpu_pci_setup(struct kvm_vcpu *vcpu) +{ + /* Only set the ECB bits after guest requests zPCI interpretation */ + if (!vcpu->kvm->arch.use_zpci_interp) + return; + + vcpu->arch.sie_block->ecb2 |= ECB2_ZPCI_LSI; + vcpu->arch.sie_block->ecb3 |= ECB3_AISII + ECB3_AISI; +} + +void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + + lockdep_assert_held(&kvm->lock); + + if (!kvm_s390_pci_interp_allowed()) + return; + + /* + * If host is configured for PCI and the necessary facilities are + * available, turn on interpretation for the life of this guest + */ + kvm->arch.use_zpci_interp = 1; + + kvm_s390_vcpu_block_all(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_s390_vcpu_pci_setup(vcpu); + kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu); + } + + kvm_s390_vcpu_unblock_all(kvm); +} + static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) { - int cx; + unsigned long cx; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(cx, vcpu, kvm) @@ -999,13 +1141,13 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) struct kvm_memory_slot *ms; struct kvm_memslots *slots; unsigned long ram_pages = 0; - int slotnr; + int bkt; /* migration mode already enabled */ if (kvm->arch.migration_mode) return 0; slots = kvm_memslots(kvm); - if (!slots || !slots->used_slots) + if (!slots || kvm_memslots_empty(slots)) return -EINVAL; if (!kvm->arch.use_cmma) { @@ -1013,8 +1155,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) return 0; } /* mark all the pages in active slots as dirty */ - for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { - ms = slots->memslots + slotnr; + kvm_for_each_memslot(ms, bkt, slots) { if (!ms->dirty_bitmap) return -EINVAL; /* @@ -1081,6 +1222,8 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm, return 0; } +static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod); + static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) { struct kvm_s390_vm_tod_clock gtod; @@ -1090,7 +1233,7 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx) return -EINVAL; - kvm_s390_set_tod_clock(kvm, >od); + __kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx", gtod.epoch_idx, gtod.tod); @@ -1121,7 +1264,7 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) sizeof(gtod.tod))) return -EFAULT; - kvm_s390_set_tod_clock(kvm, >od); + __kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod); return 0; } @@ -1133,6 +1276,16 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) if (attr->flags) return -EINVAL; + mutex_lock(&kvm->lock); + /* + * For protected guests, the TOD is managed by the ultravisor, so trying + * to change it will never bring the expected results. + */ + if (kvm_s390_pv_is_protected(kvm)) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + switch (attr->attr) { case KVM_S390_VM_TOD_EXT: ret = kvm_s390_set_tod_ext(kvm, attr); @@ -1147,23 +1300,26 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) ret = -ENXIO; break; } + +out_unlock: + mutex_unlock(&kvm->lock); return ret; } static void kvm_s390_get_tod_clock(struct kvm *kvm, struct kvm_s390_vm_tod_clock *gtod) { - struct kvm_s390_tod_clock_ext htod; + union tod_clock clk; preempt_disable(); - get_tod_clock_ext((char *)&htod); + store_tod_clock_ext(&clk); - gtod->tod = htod.tod + kvm->arch.epoch; + gtod->tod = clk.tod + kvm->arch.epoch; gtod->epoch_idx = 0; if (test_kvm_facility(kvm, 139)) { - gtod->epoch_idx = htod.epoch_idx + kvm->arch.epdx; - if (gtod->tod < htod.tod) + gtod->epoch_idx = clk.ei + kvm->arch.epdx; + if (gtod->tod < clk.tod) gtod->epoch_idx += 1; } @@ -1243,7 +1399,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr) ret = -EBUSY; goto out; } - proc = kzalloc(sizeof(*proc), GFP_KERNEL); + proc = kzalloc(sizeof(*proc), GFP_KERNEL_ACCOUNT); if (!proc) { ret = -ENOMEM; goto out; @@ -1295,8 +1451,7 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm, mutex_unlock(&kvm->lock); return -EBUSY; } - bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat, - KVM_S390_VM_CPU_FEAT_NR_BITS); + bitmap_from_arr64(kvm->arch.cpu_feat, data.feat, KVM_S390_VM_CPU_FEAT_NR_BITS); mutex_unlock(&kvm->lock); VM_EVENT(kvm, 3, "SET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx", data.feat[0], @@ -1382,6 +1537,39 @@ static int kvm_s390_set_processor_subfunc(struct kvm *kvm, return 0; } +#define KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK \ +( \ + ((struct kvm_s390_vm_cpu_uv_feat){ \ + .ap = 1, \ + .ap_intr = 1, \ + }) \ + .feat \ +) + +static int kvm_s390_set_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_uv_feat __user *ptr = (void __user *)attr->addr; + unsigned long data, filter; + + filter = uv_info.uv_feature_indications & KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK; + if (get_user(data, &ptr->feat)) + return -EFAULT; + if (!bitmap_subset(&data, &filter, KVM_S390_VM_CPU_UV_FEAT_NR_BITS)) + return -EINVAL; + + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) { + mutex_unlock(&kvm->lock); + return -EBUSY; + } + kvm->arch.model.uv_feat_guest.feat = data; + mutex_unlock(&kvm->lock); + + VM_EVENT(kvm, 3, "SET: guest UV-feat: 0x%16.16lx", data); + + return 0; +} + static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) { int ret = -ENXIO; @@ -1396,6 +1584,9 @@ static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC: ret = kvm_s390_set_processor_subfunc(kvm, attr); break; + case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST: + ret = kvm_s390_set_uv_feat(kvm, attr); + break; } return ret; } @@ -1405,7 +1596,7 @@ 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); + proc = kzalloc(sizeof(*proc), GFP_KERNEL_ACCOUNT); if (!proc) { ret = -ENOMEM; goto out; @@ -1433,7 +1624,7 @@ 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); + mach = kzalloc(sizeof(*mach), GFP_KERNEL_ACCOUNT); if (!mach) { ret = -ENOMEM; goto out; @@ -1442,8 +1633,8 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr) mach->ibc = sclp.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, - sizeof(S390_lowcore.stfle_fac_list)); + memcpy((unsigned long *)&mach->fac_list, stfle_fac_list, + sizeof(stfle_fac_list)); VM_EVENT(kvm, 3, "GET: host ibc: 0x%4.4x, host cpuid: 0x%16.16llx", kvm->arch.model.ibc, kvm->arch.model.cpuid); @@ -1467,8 +1658,7 @@ static int kvm_s390_get_processor_feat(struct kvm *kvm, { struct kvm_s390_vm_cpu_feat data; - bitmap_copy((unsigned long *) data.feat, kvm->arch.cpu_feat, - KVM_S390_VM_CPU_FEAT_NR_BITS); + bitmap_to_arr64(data.feat, kvm->arch.cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); if (copy_to_user((void __user *)attr->addr, &data, sizeof(data))) return -EFAULT; VM_EVENT(kvm, 3, "GET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx", @@ -1483,9 +1673,7 @@ static int kvm_s390_get_machine_feat(struct kvm *kvm, { struct kvm_s390_vm_cpu_feat data; - bitmap_copy((unsigned long *) data.feat, - kvm_s390_available_cpu_feat, - KVM_S390_VM_CPU_FEAT_NR_BITS); + bitmap_to_arr64(data.feat, kvm_s390_available_cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); if (copy_to_user((void __user *)attr->addr, &data, sizeof(data))) return -EFAULT; VM_EVENT(kvm, 3, "GET: host feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx", @@ -1631,6 +1819,33 @@ static int kvm_s390_get_machine_subfunc(struct kvm *kvm, return 0; } +static int kvm_s390_get_processor_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_uv_feat __user *dst = (void __user *)attr->addr; + unsigned long feat = kvm->arch.model.uv_feat_guest.feat; + + if (put_user(feat, &dst->feat)) + return -EFAULT; + VM_EVENT(kvm, 3, "GET: guest UV-feat: 0x%16.16lx", feat); + + return 0; +} + +static int kvm_s390_get_machine_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr) +{ + struct kvm_s390_vm_cpu_uv_feat __user *dst = (void __user *)attr->addr; + unsigned long feat; + + BUILD_BUG_ON(sizeof(*dst) != sizeof(uv_info.uv_feature_indications)); + + feat = uv_info.uv_feature_indications & KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK; + if (put_user(feat, &dst->feat)) + return -EFAULT; + VM_EVENT(kvm, 3, "GET: guest UV-feat: 0x%16.16lx", feat); + + return 0; +} + static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) { int ret = -ENXIO; @@ -1654,10 +1869,67 @@ static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CPU_MACHINE_SUBFUNC: ret = kvm_s390_get_machine_subfunc(kvm, attr); break; + case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST: + ret = kvm_s390_get_processor_uv_feat(kvm, attr); + break; + case KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST: + ret = kvm_s390_get_machine_uv_feat(kvm, attr); + break; } return ret; } +/** + * kvm_s390_update_topology_change_report - update CPU topology change report + * @kvm: guest KVM description + * @val: set or clear the MTCR bit + * + * Updates the Multiprocessor Topology-Change-Report bit to signal + * the guest with a topology change. + * This is only relevant if the topology facility is present. + * + * The SCA version, bsca or esca, doesn't matter as offset is the same. + */ +static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val) +{ + union sca_utility new, old; + struct bsca_block *sca; + + read_lock(&kvm->arch.sca_lock); + sca = kvm->arch.sca; + do { + old = READ_ONCE(sca->utility); + new = old; + new.mtcr = val; + } while (cmpxchg(&sca->utility.val, old.val, new.val) != old.val); + read_unlock(&kvm->arch.sca_lock); +} + +static int kvm_s390_set_topo_change_indication(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + if (!test_kvm_facility(kvm, 11)) + return -ENXIO; + + kvm_s390_update_topology_change_report(kvm, !!attr->attr); + return 0; +} + +static int kvm_s390_get_topo_change_indication(struct kvm *kvm, + struct kvm_device_attr *attr) +{ + u8 topo; + + if (!test_kvm_facility(kvm, 11)) + return -ENXIO; + + read_lock(&kvm->arch.sca_lock); + topo = ((struct bsca_block *)kvm->arch.sca)->utility.mtcr; + read_unlock(&kvm->arch.sca_lock); + + return put_user(topo, (u8 __user *)attr->addr); +} + static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { int ret; @@ -1678,6 +1950,9 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = kvm_s390_vm_set_migration(kvm, attr); break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = kvm_s390_set_topo_change_indication(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1703,6 +1978,9 @@ static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = kvm_s390_vm_get_migration(kvm, attr); break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = kvm_s390_get_topo_change_indication(kvm, attr); + break; default: ret = -ENXIO; break; @@ -1749,6 +2027,8 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CPU_MACHINE_FEAT: case KVM_S390_VM_CPU_MACHINE_SUBFUNC: case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC: + case KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST: + case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST: ret = 0; break; default: @@ -1776,6 +2056,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MIGRATION: ret = 0; break; + case KVM_S390_VM_CPU_TOPOLOGY: + ret = test_kvm_facility(kvm, 11) ? 0 : -ENXIO; + break; default: ret = -ENXIO; break; @@ -1784,7 +2067,7 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) return ret; } -static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) { uint8_t *keys; uint64_t hva; @@ -1801,11 +2084,11 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) return -EINVAL; - keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL); + keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL_ACCOUNT); if (!keys) return -ENOMEM; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); srcu_idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < args->count; i++) { hva = gfn_to_hva(kvm, args->start_gfn + i); @@ -1819,7 +2102,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) break; } srcu_read_unlock(&kvm->srcu, srcu_idx); - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (!r) { r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys, @@ -1832,7 +2115,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) return r; } -static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) { uint8_t *keys; uint64_t hva; @@ -1846,7 +2129,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) return -EINVAL; - keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL); + keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL_ACCOUNT); if (!keys) return -ENOMEM; @@ -1863,7 +2146,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) goto out; i = 0; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); srcu_idx = srcu_read_lock(&kvm->srcu); while (i < args->count) { unlocked = false; @@ -1881,7 +2164,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) r = set_guest_storage_key(current->mm, hva, keys[i], 0); if (r) { - r = fixup_user_fault(current, current->mm, hva, + r = fixup_user_fault(current->mm, hva, FAULT_FLAG_WRITE, &unlocked); if (r) break; @@ -1890,7 +2173,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) i++; } srcu_read_unlock(&kvm->srcu, srcu_idx); - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); out: kvfree(keys); return r; @@ -1905,38 +2188,6 @@ out: /* for consistency */ #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) -/* - * Similar to gfn_to_memslot, but returns the index of a memslot also when the - * address falls in a hole. In that case the index of one of the memslots - * bordering the hole is returned. - */ -static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) -{ - int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->lru_slot); - struct kvm_memory_slot *memslots = slots->memslots; - - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return slot; - - while (start < end) { - slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - if (gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->lru_slot, start); - } - - return start; -} - static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, u8 *res, unsigned long bufsize) { @@ -1960,27 +2211,36 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, return 0; } +static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots, + gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, true); +} + static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, unsigned long cur_gfn) { - int slotidx = gfn_to_memslot_approx(slots, cur_gfn); - struct kvm_memory_slot *ms = slots->memslots + slotidx; + struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn); unsigned long ofs = cur_gfn - ms->base_gfn; + struct rb_node *mnode = &ms->gfn_node[slots->node_idx]; if (ms->base_gfn + ms->npages <= cur_gfn) { - slotidx--; + mnode = rb_next(mnode); /* If we are above the highest slot, wrap around */ - if (slotidx < 0) - slotidx = slots->used_slots - 1; + if (!mnode) + mnode = rb_first(&slots->gfn_tree); - ms = slots->memslots + slotidx; + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = 0; } + + if (cur_gfn < ms->base_gfn) + ofs = 0; + ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs); - while ((slotidx > 0) && (ofs >= ms->npages)) { - slotidx--; - ms = slots->memslots + slotidx; - ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0); + while (ofs >= ms->npages && (mnode = rb_next(mnode))) { + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); + ofs = find_first_bit(kvm_second_dirty_bitmap(ms), ms->npages); } return ms->base_gfn + ofs; } @@ -1992,6 +2252,9 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *ms; + if (unlikely(kvm_memslots_empty(slots))) + return 0; + cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); ms = gfn_to_memslot(kvm, cur_gfn); args->count = 0; @@ -1999,7 +2262,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, if (!ms) return 0; next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1); - mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages; + mem_end = kvm_s390_get_gfn_end(slots); while (args->count < bufsize) { hva = gfn_to_hva(kvm, cur_gfn); @@ -2073,14 +2336,14 @@ static int kvm_s390_get_cmma_bits(struct kvm *kvm, if (!values) return -ENOMEM; - down_read(&kvm->mm->mmap_sem); + mmap_read_lock(kvm->mm); srcu_idx = srcu_read_lock(&kvm->srcu); if (peek) ret = kvm_s390_peek_cmma(kvm, args, values, bufsize); else ret = kvm_s390_get_cmma(kvm, args, values, bufsize); srcu_read_unlock(&kvm->srcu, srcu_idx); - up_read(&kvm->mm->mmap_sem); + mmap_read_unlock(kvm->mm); if (kvm->arch.migration_mode) args->remaining = atomic64_read(&kvm->arch.cmma_dirty_pages); @@ -2130,7 +2393,7 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm, goto out; } - down_read(&kvm->mm->mmap_sem); + mmap_read_lock(kvm->mm); srcu_idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < args->count; i++) { hva = gfn_to_hva(kvm, args->start_gfn + i); @@ -2145,20 +2408,579 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm, set_pgste_bits(kvm->mm, hva, mask, pgstev); } srcu_read_unlock(&kvm->srcu, srcu_idx); - up_read(&kvm->mm->mmap_sem); + mmap_read_unlock(kvm->mm); if (!kvm->mm->context.uses_cmm) { - down_write(&kvm->mm->mmap_sem); + mmap_write_lock(kvm->mm); kvm->mm->context.uses_cmm = 1; - up_write(&kvm->mm->mmap_sem); + mmap_write_unlock(kvm->mm); } out: vfree(bits); return r; } -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +/** + * kvm_s390_cpus_from_pv - Convert all protected vCPUs in a protected VM to + * non protected. + * @kvm: the VM whose protected vCPUs are to be converted + * @rc: return value for the RC field of the UVC (in case of error) + * @rrc: return value for the RRC field of the UVC (in case of error) + * + * Does not stop in case of error, tries to convert as many + * CPUs as possible. In case of error, the RC and RRC of the last error are + * returned. + * + * Return: 0 in case of success, otherwise -EIO + */ +int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + u16 _rc, _rrc; + int ret = 0; + + /* + * We ignore failures and try to destroy as many CPUs as possible. + * At the same time we must not free the assigned resources when + * this fails, as the ultravisor has still access to that memory. + * So kvm_s390_pv_destroy_cpu can leave a "wanted" memory leak + * behind. + * We want to return the first failure rc and rrc, though. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_lock(&vcpu->mutex); + if (kvm_s390_pv_destroy_cpu(vcpu, &_rc, &_rrc) && !ret) { + *rc = _rc; + *rrc = _rrc; + ret = -EIO; + } + mutex_unlock(&vcpu->mutex); + } + /* Ensure that we re-enable gisa if the non-PV guest used it but the PV guest did not. */ + if (use_gisa) + kvm_s390_gisa_enable(kvm); + return ret; +} + +/** + * kvm_s390_cpus_to_pv - Convert all non-protected vCPUs in a protected VM + * to protected. + * @kvm: the VM whose protected vCPUs are to be converted + * @rc: return value for the RC field of the UVC (in case of error) + * @rrc: return value for the RRC field of the UVC (in case of error) + * + * Tries to undo the conversion in case of error. + * + * Return: 0 in case of success, otherwise -EIO + */ +static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + unsigned long i; + int r = 0; + u16 dummy; + + struct kvm_vcpu *vcpu; + + /* Disable the GISA if the ultravisor does not support AIV. */ + if (!uv_has_feature(BIT_UV_FEAT_AIV)) + kvm_s390_gisa_disable(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_lock(&vcpu->mutex); + r = kvm_s390_pv_create_cpu(vcpu, rc, rrc); + mutex_unlock(&vcpu->mutex); + if (r) + break; + } + if (r) + kvm_s390_cpus_from_pv(kvm, &dummy, &dummy); + return r; +} + +/* + * Here we provide user space with a direct interface to query UV + * related data like UV maxima and available features as well as + * feature specific data. + * + * To facilitate future extension of the data structures we'll try to + * write data up to the maximum requested length. + */ +static ssize_t kvm_s390_handle_pv_info(struct kvm_s390_pv_info *info) +{ + ssize_t len_min; + + switch (info->header.id) { + case KVM_PV_INFO_VM: { + len_min = sizeof(info->header) + sizeof(info->vm); + + if (info->header.len_max < len_min) + return -EINVAL; + + memcpy(info->vm.inst_calls_list, + uv_info.inst_calls_list, + sizeof(uv_info.inst_calls_list)); + + /* It's max cpuid not max cpus, so it's off by one */ + info->vm.max_cpus = uv_info.max_guest_cpu_id + 1; + info->vm.max_guests = uv_info.max_num_sec_conf; + info->vm.max_guest_addr = uv_info.max_sec_stor_addr; + info->vm.feature_indication = uv_info.uv_feature_indications; + + return len_min; + } + case KVM_PV_INFO_DUMP: { + len_min = sizeof(info->header) + sizeof(info->dump); + + if (info->header.len_max < len_min) + return -EINVAL; + + info->dump.dump_cpu_buffer_len = uv_info.guest_cpu_stor_len; + info->dump.dump_config_mem_buffer_per_1m = uv_info.conf_dump_storage_state_len; + info->dump.dump_config_finalize_len = uv_info.conf_dump_finalize_len; + return len_min; + } + default: + return -EINVAL; + } +} + +static int kvm_s390_pv_dmp(struct kvm *kvm, struct kvm_pv_cmd *cmd, + struct kvm_s390_pv_dmp dmp) +{ + int r = -EINVAL; + void __user *result_buff = (void __user *)dmp.buff_addr; + + switch (dmp.subcmd) { + case KVM_PV_DUMP_INIT: { + if (kvm->arch.pv.dumping) + break; + + /* + * Block SIE entry as concurrent dump UVCs could lead + * to validities. + */ + kvm_s390_vcpu_block_all(kvm); + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_DUMP_INIT, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT DUMP INIT: rc %x rrc %x", + cmd->rc, cmd->rrc); + if (!r) { + kvm->arch.pv.dumping = true; + } else { + kvm_s390_vcpu_unblock_all(kvm); + r = -EINVAL; + } + break; + } + case KVM_PV_DUMP_CONFIG_STOR_STATE: { + if (!kvm->arch.pv.dumping) + break; + + /* + * gaddr is an output parameter since we might stop + * early. As dmp will be copied back in our caller, we + * don't need to do it ourselves. + */ + r = kvm_s390_pv_dump_stor_state(kvm, result_buff, &dmp.gaddr, dmp.buff_len, + &cmd->rc, &cmd->rrc); + break; + } + case KVM_PV_DUMP_COMPLETE: { + if (!kvm->arch.pv.dumping) + break; + + r = -EINVAL; + if (dmp.buff_len < uv_info.conf_dump_finalize_len) + break; + + r = kvm_s390_pv_dump_complete(kvm, result_buff, + &cmd->rc, &cmd->rrc); + break; + } + default: + r = -ENOTTY; + break; + } + + return r; +} + +static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) +{ + const bool need_lock = (cmd->cmd != KVM_PV_ASYNC_CLEANUP_PERFORM); + void __user *argp = (void __user *)cmd->data; + int r = 0; + u16 dummy; + + if (need_lock) + mutex_lock(&kvm->lock); + + switch (cmd->cmd) { + case KVM_PV_ENABLE: { + r = -EINVAL; + if (kvm_s390_pv_is_protected(kvm)) + break; + + /* + * FMT 4 SIE needs esca. As we never switch back to bsca from + * esca, we need no cleanup in the error cases below + */ + r = sca_switch_to_extended(kvm); + if (r) + break; + + mmap_write_lock(current->mm); + r = gmap_mark_unmergeable(); + mmap_write_unlock(current->mm); + if (r) + break; + + r = kvm_s390_pv_init_vm(kvm, &cmd->rc, &cmd->rrc); + if (r) + break; + + r = kvm_s390_cpus_to_pv(kvm, &cmd->rc, &cmd->rrc); + if (r) + kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); + + /* we need to block service interrupts from now on */ + set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + } + case KVM_PV_ASYNC_CLEANUP_PREPARE: + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm) || !async_destroy) + break; + + r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc); + /* + * If a CPU could not be destroyed, destroy VM will also fail. + * There is no point in trying to destroy it. Instead return + * the rc and rrc from the first CPU that failed destroying. + */ + if (r) + break; + r = kvm_s390_pv_set_aside(kvm, &cmd->rc, &cmd->rrc); + + /* no need to block service interrupts any more */ + clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + case KVM_PV_ASYNC_CLEANUP_PERFORM: + r = -EINVAL; + if (!async_destroy) + break; + /* kvm->lock must not be held; this is asserted inside the function. */ + r = kvm_s390_pv_deinit_aside_vm(kvm, &cmd->rc, &cmd->rrc); + break; + case KVM_PV_DISABLE: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc); + /* + * If a CPU could not be destroyed, destroy VM will also fail. + * There is no point in trying to destroy it. Instead return + * the rc and rrc from the first CPU that failed destroying. + */ + if (r) + break; + r = kvm_s390_pv_deinit_cleanup_all(kvm, &cmd->rc, &cmd->rrc); + + /* no need to block service interrupts any more */ + clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + } + case KVM_PV_SET_SEC_PARMS: { + struct kvm_s390_pv_sec_parm parms = {}; + void *hdr; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = -EFAULT; + if (copy_from_user(&parms, argp, sizeof(parms))) + break; + + /* Currently restricted to 8KB */ + r = -EINVAL; + if (parms.length > PAGE_SIZE * 2) + break; + + r = -ENOMEM; + hdr = vmalloc(parms.length); + if (!hdr) + break; + + r = -EFAULT; + if (!copy_from_user(hdr, (void __user *)parms.origin, + parms.length)) + r = kvm_s390_pv_set_sec_parms(kvm, hdr, parms.length, + &cmd->rc, &cmd->rrc); + + vfree(hdr); + break; + } + case KVM_PV_UNPACK: { + struct kvm_s390_pv_unp unp = {}; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm) || !mm_is_protected(kvm->mm)) + break; + + r = -EFAULT; + if (copy_from_user(&unp, argp, sizeof(unp))) + break; + + r = kvm_s390_pv_unpack(kvm, unp.addr, unp.size, unp.tweak, + &cmd->rc, &cmd->rrc); + break; + } + case KVM_PV_VERIFY: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_VERIFY_IMG, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT VERIFY: rc %x rrc %x", cmd->rc, + cmd->rrc); + break; + } + case KVM_PV_PREP_RESET: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_PREPARE_RESET, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT PREP RESET: rc %x rrc %x", + cmd->rc, cmd->rrc); + break; + } + case KVM_PV_UNSHARE_ALL: { + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_SET_UNSHARE_ALL, &cmd->rc, &cmd->rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT UNSHARE: rc %x rrc %x", + cmd->rc, cmd->rrc); + break; + } + case KVM_PV_INFO: { + struct kvm_s390_pv_info info = {}; + ssize_t data_len; + + /* + * No need to check the VM protection here. + * + * Maybe user space wants to query some of the data + * when the VM is still unprotected. If we see the + * need to fence a new data command we can still + * return an error in the info handler. + */ + + r = -EFAULT; + if (copy_from_user(&info, argp, sizeof(info.header))) + break; + + r = -EINVAL; + if (info.header.len_max < sizeof(info.header)) + break; + + data_len = kvm_s390_handle_pv_info(&info); + if (data_len < 0) { + r = data_len; + break; + } + /* + * If a data command struct is extended (multiple + * times) this can be used to determine how much of it + * is valid. + */ + info.header.len_written = data_len; + + r = -EFAULT; + if (copy_to_user(argp, &info, data_len)) + break; + + r = 0; + break; + } + case KVM_PV_DUMP: { + struct kvm_s390_pv_dmp dmp; + + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm)) + break; + + r = -EFAULT; + if (copy_from_user(&dmp, argp, sizeof(dmp))) + break; + + r = kvm_s390_pv_dmp(kvm, cmd, dmp); + if (r) + break; + + if (copy_to_user(argp, &dmp, sizeof(dmp))) { + r = -EFAULT; + break; + } + + break; + } + default: + r = -ENOTTY; + } + if (need_lock) + mutex_unlock(&kvm->lock); + + return r; +} + +static int mem_op_validate_common(struct kvm_s390_mem_op *mop, u64 supported_flags) +{ + if (mop->flags & ~supported_flags || !mop->size) + return -EINVAL; + if (mop->size > MEM_OP_MAX_SIZE) + return -E2BIG; + if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) { + if (mop->key > 0xf) + return -EINVAL; + } else { + mop->key = 0; + } + return 0; +} + +static int kvm_s390_vm_mem_op_abs(struct kvm *kvm, struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + enum gacc_mode acc_mode; + void *tmpbuf = NULL; + int r, srcu_idx; + + r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION | + KVM_S390_MEMOP_F_CHECK_ONLY); + if (r) + return r; + + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { + tmpbuf = vmalloc(mop->size); + if (!tmpbuf) + return -ENOMEM; + } + + srcu_idx = srcu_read_lock(&kvm->srcu); + + if (kvm_is_error_gpa(kvm, mop->gaddr)) { + r = PGM_ADDRESSING; + goto out_unlock; + } + + acc_mode = mop->op == KVM_S390_MEMOP_ABSOLUTE_READ ? GACC_FETCH : GACC_STORE; + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gpa_range(kvm, mop->gaddr, mop->size, acc_mode, mop->key); + goto out_unlock; + } + if (acc_mode == GACC_FETCH) { + r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf, + mop->size, GACC_FETCH, mop->key); + if (r) + goto out_unlock; + if (copy_to_user(uaddr, tmpbuf, mop->size)) + r = -EFAULT; + } else { + if (copy_from_user(tmpbuf, uaddr, mop->size)) { + r = -EFAULT; + goto out_unlock; + } + r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf, + mop->size, GACC_STORE, mop->key); + } + +out_unlock: + srcu_read_unlock(&kvm->srcu, srcu_idx); + + vfree(tmpbuf); + return r; +} + +static int kvm_s390_vm_mem_op_cmpxchg(struct kvm *kvm, struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + void __user *old_addr = (void __user *)mop->old_addr; + union { + __uint128_t quad; + char raw[sizeof(__uint128_t)]; + } old = { .quad = 0}, new = { .quad = 0 }; + unsigned int off_in_quad = sizeof(new) - mop->size; + int r, srcu_idx; + bool success; + + r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION); + if (r) + return r; + /* + * This validates off_in_quad. Checking that size is a power + * of two is not necessary, as cmpxchg_guest_abs_with_key + * takes care of that + */ + if (mop->size > sizeof(new)) + return -EINVAL; + if (copy_from_user(&new.raw[off_in_quad], uaddr, mop->size)) + return -EFAULT; + if (copy_from_user(&old.raw[off_in_quad], old_addr, mop->size)) + return -EFAULT; + + srcu_idx = srcu_read_lock(&kvm->srcu); + + if (kvm_is_error_gpa(kvm, mop->gaddr)) { + r = PGM_ADDRESSING; + goto out_unlock; + } + + r = cmpxchg_guest_abs_with_key(kvm, mop->gaddr, mop->size, &old.quad, + new.quad, mop->key, &success); + if (!success && copy_to_user(old_addr, &old.raw[off_in_quad], mop->size)) + r = -EFAULT; + +out_unlock: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return r; +} + +static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) +{ + /* + * This is technically a heuristic only, if the kvm->lock is not + * taken, it is not guaranteed that the vm is/remains non-protected. + * This is ok from a kernel perspective, wrongdoing is detected + * on the access, -EFAULT is returned and the vm may crash the + * next time it accesses the memory in question. + * There is no sane usecase to do switching and a memop on two + * different CPUs at the same time. + */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; + + switch (mop->op) { + case KVM_S390_MEMOP_ABSOLUTE_READ: + case KVM_S390_MEMOP_ABSOLUTE_WRITE: + return kvm_s390_vm_mem_op_abs(kvm, mop); + case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG: + return kvm_s390_vm_mem_op_cmpxchg(kvm, mop); + default: + return -EINVAL; + } +} + +int 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; @@ -2254,6 +3076,54 @@ long kvm_arch_vm_ioctl(struct file *filp, mutex_unlock(&kvm->slots_lock); break; } + case KVM_S390_PV_COMMAND: { + struct kvm_pv_cmd args; + + /* protvirt means user cpu state */ + kvm_s390_set_user_cpu_state_ctrl(kvm); + r = 0; + if (!is_prot_virt_host()) { + r = -EINVAL; + break; + } + if (copy_from_user(&args, argp, sizeof(args))) { + r = -EFAULT; + break; + } + if (args.flags) { + r = -EINVAL; + break; + } + /* must be called without kvm->lock */ + r = kvm_s390_handle_pv(kvm, &args); + if (copy_to_user(argp, &args, sizeof(args))) { + r = -EFAULT; + break; + } + 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_vm_mem_op(kvm, &mem_op); + else + r = -EFAULT; + break; + } + case KVM_S390_ZPCI_OP: { + struct kvm_s390_zpci_op args; + + r = -EINVAL; + if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + break; + if (copy_from_user(&args, argp, sizeof(args))) { + r = -EFAULT; + break; + } + r = kvm_s390_pci_zpci_op(kvm, &args); + break; + } default: r = -ENOTTY; } @@ -2298,12 +3168,26 @@ static void kvm_s390_set_crycb_format(struct kvm *kvm) kvm->arch.crypto.crycbd |= CRYCB_FORMAT1; } +/* + * kvm_arch_crypto_set_masks + * + * @kvm: pointer to the target guest's KVM struct containing the crypto masks + * to be set. + * @apm: the mask identifying the accessible AP adapters + * @aqm: the mask identifying the accessible AP domains + * @adm: the mask identifying the accessible AP control domains + * + * Set the masks that identify the adapters, domains and control domains to + * which the KVM guest is granted access. + * + * Note: The kvm->lock mutex must be locked by the caller before invoking this + * function. + */ void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm, unsigned long *aqm, unsigned long *adm) { struct kvm_s390_crypto_cb *crycb = kvm->arch.crypto.crycb; - mutex_lock(&kvm->lock); kvm_s390_vcpu_block_all(kvm); switch (kvm->arch.crypto.crycbd & CRYCB_FORMAT_MASK) { @@ -2334,13 +3218,23 @@ void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm, /* recreate the shadow crycb for each vcpu */ kvm_s390_sync_request_broadcast(kvm, KVM_REQ_VSIE_RESTART); kvm_s390_vcpu_unblock_all(kvm); - mutex_unlock(&kvm->lock); } EXPORT_SYMBOL_GPL(kvm_arch_crypto_set_masks); +/* + * kvm_arch_crypto_clear_masks + * + * @kvm: pointer to the target guest's KVM struct containing the crypto masks + * to be cleared. + * + * Clear the masks that identify the adapters, domains and control domains to + * which the KVM guest is granted access. + * + * Note: The kvm->lock mutex must be locked by the caller before invoking this + * function. + */ void kvm_arch_crypto_clear_masks(struct kvm *kvm) { - mutex_lock(&kvm->lock); kvm_s390_vcpu_block_all(kvm); memset(&kvm->arch.crypto.crycb->apcb0, 0, @@ -2352,7 +3246,6 @@ void kvm_arch_crypto_clear_masks(struct kvm *kvm) /* recreate the shadow crycb for each vcpu */ kvm_s390_sync_request_broadcast(kvm, KVM_REQ_VSIE_RESTART); kvm_s390_vcpu_unblock_all(kvm); - mutex_unlock(&kvm->lock); } EXPORT_SYMBOL_GPL(kvm_arch_crypto_clear_masks); @@ -2369,6 +3262,7 @@ static void kvm_s390_crypto_init(struct kvm *kvm) { kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb; kvm_s390_set_crycb_format(kvm); + init_rwsem(&kvm->arch.crypto.pqap_hook_rwsem); if (!test_kvm_facility(kvm, 76)) return; @@ -2391,9 +3285,17 @@ static void sca_dispose(struct kvm *kvm) kvm->arch.sca = NULL; } +void kvm_arch_free_vm(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + kvm_s390_pci_clear_list(kvm); + + __kvm_arch_free_vm(kvm); +} + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - gfp_t alloc_flags = GFP_KERNEL; + gfp_t alloc_flags = GFP_KERNEL_ACCOUNT; int i, rc; char debug_name[16]; static unsigned long sca_offset; @@ -2438,7 +3340,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) BUILD_BUG_ON(sizeof(struct sie_page2) != 4096); kvm->arch.sie_page2 = - (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA); + (struct sie_page2 *) get_zeroed_page(GFP_KERNEL_ACCOUNT | GFP_DMA); if (!kvm->arch.sie_page2) goto out_err; @@ -2446,10 +3348,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list; for (i = 0; i < kvm_s390_fac_size(); i++) { - kvm->arch.model.fac_mask[i] = S390_lowcore.stfle_fac_list[i] & + kvm->arch.model.fac_mask[i] = stfle_fac_list[i] & (kvm_s390_fac_base[i] | kvm_s390_fac_ext[i]); - kvm->arch.model.fac_list[i] = S390_lowcore.stfle_fac_list[i] & + kvm->arch.model.fac_list[i] = stfle_fac_list[i] & kvm_s390_fac_base[i]; } kvm->arch.model.subfuncs = kvm_s390_available_subfunc; @@ -2471,8 +3373,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid(); kvm->arch.model.ibc = sclp.ibc & 0x0fff; + kvm->arch.model.uv_feat_guest.feat = 0; + kvm_s390_crypto_init(kvm); + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { + mutex_lock(&kvm->lock); + kvm_s390_pci_init_list(kvm); + kvm_s390_vcpu_pci_enable_interp(kvm); + mutex_unlock(&kvm->lock); + } + mutex_init(&kvm->arch.float_int.ais_lock); spin_lock_init(&kvm->arch.float_int.lock); for (i = 0; i < FIRQ_LIST_COUNT; i++) @@ -2503,7 +3414,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.use_skf = sclp.has_skey; spin_lock_init(&kvm->arch.start_stop_lock); kvm_s390_vsie_init(kvm); - kvm_s390_gisa_init(kvm); + if (use_gisa) + kvm_s390_gisa_init(kvm); + INIT_LIST_HEAD(&kvm->arch.pv.need_cleanup); + kvm->arch.pv.set_aside = NULL; KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); return 0; @@ -2517,46 +3431,50 @@ out_err: void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { + u16 rc, rrc; + 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)) sca_del_vcpu(vcpu); + kvm_s390_update_topology_change_report(vcpu->kvm, 1); if (kvm_is_ucontrol(vcpu->kvm)) gmap_remove(vcpu->arch.gmap); if (vcpu->kvm->arch.use_cmma) kvm_s390_vcpu_unsetup_cmma(vcpu); + /* We can not hold the vcpu mutex here, we are already dying */ + if (kvm_s390_pv_cpu_get_handle(vcpu)) + kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc); 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); + u16 rc, rrc; + + kvm_destroy_vcpus(kvm); sca_dispose(kvm); - debug_unregister(kvm->arch.dbf); kvm_s390_gisa_destroy(kvm); + /* + * We are already at the end of life and kvm->lock is not taken. + * This is ok as the file descriptor is closed by now and nobody + * can mess with the pv state. + */ + kvm_s390_pv_deinit_cleanup_all(kvm, &rc, &rrc); + /* + * Remove the mmu notifier only when the whole KVM VM is torn down, + * and only if one was registered to begin with. If the VM is + * currently not protected, but has been previously been protected, + * then it's possible that the notifier is still registered. + */ + if (kvm->arch.pv.mmu_notifier.ops) + mmu_notifier_unregister(&kvm->arch.pv.mmu_notifier, kvm->mm); + + debug_unregister(kvm->arch.dbf); free_page((unsigned long)kvm->arch.sie_page2); if (!kvm_is_ucontrol(kvm)) gmap_remove(kvm->arch.gmap); @@ -2599,28 +3517,30 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu) static void sca_add_vcpu(struct kvm_vcpu *vcpu) { if (!kvm_s390_use_sca_entries()) { - struct bsca_block *sca = vcpu->kvm->arch.sca; + phys_addr_t sca_phys = virt_to_phys(vcpu->kvm->arch.sca); /* we still need the basic sca for the ipte control */ - vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); - vcpu->arch.sie_block->scaol = (__u32)(__u64)sca; + vcpu->arch.sie_block->scaoh = sca_phys >> 32; + vcpu->arch.sie_block->scaol = sca_phys; return; } read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { struct esca_block *sca = vcpu->kvm->arch.sca; + phys_addr_t sca_phys = virt_to_phys(sca); - sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block; - vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); - vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU; + sca->cpu[vcpu->vcpu_id].sda = virt_to_phys(vcpu->arch.sie_block); + vcpu->arch.sie_block->scaoh = sca_phys >> 32; + vcpu->arch.sie_block->scaol = sca_phys & ESCA_SCAOL_MASK; vcpu->arch.sie_block->ecb2 |= ECB2_ESCA; set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; + phys_addr_t sca_phys = virt_to_phys(sca); - sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block; - vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); - vcpu->arch.sie_block->scaol = (__u32)(__u64)sca; + sca->cpu[vcpu->vcpu_id].sda = virt_to_phys(vcpu->arch.sie_block); + vcpu->arch.sie_block->scaoh = sca_phys >> 32; + vcpu->arch.sie_block->scaol = sca_phys; set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn); } read_unlock(&vcpu->kvm->arch.sca_lock); @@ -2649,15 +3569,20 @@ static int sca_switch_to_extended(struct kvm *kvm) struct bsca_block *old_sca = kvm->arch.sca; struct esca_block *new_sca; struct kvm_vcpu *vcpu; - unsigned int vcpu_idx; + unsigned long vcpu_idx; u32 scaol, scaoh; + phys_addr_t new_sca_phys; - new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO); + if (kvm->arch.use_esca) + return 0; + + new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!new_sca) return -ENOMEM; - scaoh = (u32)((u64)(new_sca) >> 32); - scaol = (u32)(u64)(new_sca) & ~0x3fU; + new_sca_phys = virt_to_phys(new_sca); + scaoh = new_sca_phys >> 32; + scaol = new_sca_phys & ESCA_SCAOL_MASK; kvm_s390_vcpu_block_all(kvm); write_lock(&kvm->arch.sca_lock); @@ -2696,46 +3621,11 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id) if (!sclp.has_esca || !sclp.has_64bscao) return false; - mutex_lock(&kvm->lock); rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm); - mutex_unlock(&kvm->lock); return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS; } -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; - kvm_s390_set_prefix(vcpu, 0); - if (test_kvm_facility(vcpu->kvm, 64)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; - if (test_kvm_facility(vcpu->kvm, 82)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; - if (test_kvm_facility(vcpu->kvm, 133)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; - if (test_kvm_facility(vcpu->kvm, 156)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; - /* fprs can be synchronized via vrs, even if the guest has no vx. With - * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. - */ - if (MACHINE_HAS_VX) - vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; - else - vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; - - if (kvm_is_ucontrol(vcpu->kvm)) - return __kvm_ucontrol_vcpu_init(vcpu); - - return 0; -} - /* needs disabled preemption to protect from TOD sync and vcpu_load/put */ static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu) { @@ -2844,35 +3734,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) } -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); - kvm_s390_set_cpu_timer(vcpu, 0); - 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] = CR0_UNUSED_56 | - CR0_INTERRUPT_KEY_SUBMASK | - CR0_MEASUREMENT_ALERT_SUBMASK; - vcpu->arch.sie_block->gcr[14] = CR14_UNUSED_32 | - CR14_UNUSED_33 | - CR14_EXTERNAL_DAMAGE_SUBMASK; - /* make sure the new fpc will be lazily loaded */ - save_fpu_regs(); - current->thread.fpu.fpc = 0; - vcpu->arch.sie_block->gbea = 1; - vcpu->arch.sie_block->pp = 0; - vcpu->arch.sie_block->fpf &= ~FPF_BPBC; - 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); @@ -2941,15 +3802,18 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu) { - free_page(vcpu->arch.sie_block->cbrlo); + free_page((unsigned long)phys_to_virt(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) + void *cbrlo_page = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + + if (!cbrlo_page) return -ENOMEM; + + vcpu->arch.sie_block->cbrlo = virt_to_phys(cbrlo_page); return 0; } @@ -2959,12 +3823,13 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->ibc = model->ibc; if (test_kvm_facility(vcpu->kvm, 7)) - vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list; + vcpu->arch.sie_block->fac = virt_to_phys(model->fac_list); } -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; + u16 uvrc, uvrrc; atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM | @@ -2982,8 +3847,12 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->ecb |= ECB_HOSTPROTINT; if (test_kvm_facility(vcpu->kvm, 9)) vcpu->arch.sie_block->ecb |= ECB_SRSI; + if (test_kvm_facility(vcpu->kvm, 11)) + vcpu->arch.sie_block->ecb |= ECB_PTF; if (test_kvm_facility(vcpu->kvm, 73)) vcpu->arch.sie_block->ecb |= ECB_TE; + if (!kvm_is_ucontrol(vcpu->kvm)) + vcpu->arch.sie_block->ecb |= ECB_SPECI; if (test_kvm_facility(vcpu->kvm, 8) && vcpu->kvm->arch.use_pfmfi) vcpu->arch.sie_block->ecb2 |= ECB2_PFMFI; @@ -3011,9 +3880,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 3, "AIV gisa format-%u enabled for cpu %03u", vcpu->arch.sie_block->gd & 0x3, vcpu->vcpu_id); } - vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx) - | SDNXC; - vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb; + vcpu->arch.sie_block->sdnxo = virt_to_phys(&vcpu->run->s.regs.sdnx) | SDNXC; + vcpu->arch.sie_block->riccbd = virt_to_phys(&vcpu->run->s.regs.riccb); if (sclp.has_kss) kvm_s390_set_cpuflags(vcpu, CPUSTAT_KSS); @@ -3032,62 +3900,102 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvm_s390_vcpu_crypto_setup(vcpu); + kvm_s390_vcpu_pci_setup(vcpu); + + mutex_lock(&vcpu->kvm->lock); + if (kvm_s390_pv_is_protected(vcpu->kvm)) { + rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc); + if (rc) + kvm_s390_vcpu_unsetup_cmma(vcpu); + } + mutex_unlock(&vcpu->kvm->lock); + return rc; } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - struct kvm_vcpu *vcpu; - struct sie_page *sie_page; - int rc = -EINVAL; - if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id)) - goto out; - - rc = -ENOMEM; + return -EINVAL; + return 0; +} - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu) - goto out; +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) +{ + struct sie_page *sie_page; + int rc; BUILD_BUG_ON(sizeof(struct sie_page) != 4096); - sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL); + sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!sie_page) - goto out_free_cpu; + return -ENOMEM; vcpu->arch.sie_block = &sie_page->sie_block; - vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; + vcpu->arch.sie_block->itdba = virt_to_phys(&sie_page->itdb); /* the real guest size will always be smaller than msl */ vcpu->arch.sie_block->mso = 0; vcpu->arch.sie_block->msl = sclp.hamax; - vcpu->arch.sie_block->icpua = id; + vcpu->arch.sie_block->icpua = vcpu->vcpu_id; spin_lock_init(&vcpu->arch.local_int.lock); - vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa_int.origin; - if (vcpu->arch.sie_block->gd && sclp.has_gisaf) - vcpu->arch.sie_block->gd |= GISA_FORMAT1; + vcpu->arch.sie_block->gd = kvm_s390_get_gisa_desc(vcpu->kvm); seqcount_init(&vcpu->arch.cputm_seqcount); - rc = kvm_vcpu_init(vcpu, kvm, id); + 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 | + KVM_SYNC_DIAG318; + kvm_s390_set_prefix(vcpu, 0); + if (test_kvm_facility(vcpu->kvm, 64)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; + if (test_kvm_facility(vcpu->kvm, 82)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; + if (test_kvm_facility(vcpu->kvm, 133)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; + if (test_kvm_facility(vcpu->kvm, 156)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; + /* fprs can be synchronized via vrs, even if the guest has no vx. With + * cpu_has_vx(), (load|store)_fpu_regs() will work with vrs format. + */ + if (cpu_has_vx()) + vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; + else + vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; + + if (kvm_is_ucontrol(vcpu->kvm)) { + rc = __kvm_ucontrol_vcpu_init(vcpu); + if (rc) + goto out_free_sie_block; + } + + VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", + vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); + trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); + + rc = kvm_s390_vcpu_setup(vcpu); if (rc) - goto out_free_sie_block; - VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu, - vcpu->arch.sie_block); - trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block); + goto out_ucontrol_uninit; - return vcpu; + kvm_s390_update_topology_change_report(vcpu->kvm, 1); + return 0; + +out_ucontrol_uninit: + if (kvm_is_ucontrol(vcpu->kvm)) + gmap_remove(vcpu->arch.gmap); 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); + return rc; } int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); return kvm_s390_vcpu_has_irq(vcpu, 0); } @@ -3139,7 +4047,7 @@ void exit_sie(struct kvm_vcpu *vcpu) /* Kick a guest cpu out of SIE to process a request synchronously */ void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu) { - kvm_make_request(req, vcpu); + __kvm_make_request(req, vcpu); kvm_s390_vcpu_request(vcpu); } @@ -3149,7 +4057,9 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct kvm_vcpu *vcpu; unsigned long prefix; - int i; + unsigned long i; + + trace_kvm_s390_gmap_notifier(start, end, gmap_is_shadow(gmap)); if (gmap_is_shadow(gmap)) return; @@ -3162,7 +4072,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, if (prefix <= end && start <= prefix + 2*PAGE_SIZE - 1) { VCPU_EVENT(vcpu, 2, "gmap notifier for %lx-%lx", start, end); - kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu); + kvm_s390_sync_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu); } } } @@ -3171,7 +4081,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { /* do not poll with more than halt_poll_max_steal percent of steal time */ if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >= - halt_poll_max_steal) { + READ_ONCE(halt_poll_max_steal)) { vcpu->stat.halt_no_poll_steal++; return true; } @@ -3287,10 +4197,76 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, return r; } -static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) +static void kvm_arch_vcpu_ioctl_normal_reset(struct kvm_vcpu *vcpu) { - kvm_s390_vcpu_initial_reset(vcpu); - return 0; + vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_RI; + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + memset(vcpu->run->s.regs.riccb, 0, sizeof(vcpu->run->s.regs.riccb)); + + 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); +} + +static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) +{ + /* Initial reset is a superset of the normal reset */ + kvm_arch_vcpu_ioctl_normal_reset(vcpu); + + /* + * This equals initial cpu reset in pop, but we don't switch to ESA. + * We do not only reset the internal data, but also ... + */ + vcpu->arch.sie_block->gpsw.mask = 0; + vcpu->arch.sie_block->gpsw.addr = 0; + kvm_s390_set_prefix(vcpu, 0); + kvm_s390_set_cpu_timer(vcpu, 0); + vcpu->arch.sie_block->ckc = 0; + memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr)); + vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK; + vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK; + + /* ... the data in sync regs */ + memset(vcpu->run->s.regs.crs, 0, sizeof(vcpu->run->s.regs.crs)); + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.crs[0] = CR0_INITIAL_MASK; + vcpu->run->s.regs.crs[14] = CR14_INITIAL_MASK; + vcpu->run->psw_addr = 0; + vcpu->run->psw_mask = 0; + vcpu->run->s.regs.todpr = 0; + vcpu->run->s.regs.cputm = 0; + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.pp = 0; + vcpu->run->s.regs.gbea = 1; + vcpu->run->s.regs.fpc = 0; + /* + * Do not reset these registers in the protected case, as some of + * them are overlaid and they are not accessible in this case + * anyway. + */ + if (!kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->gbea = 1; + vcpu->arch.sie_block->pp = 0; + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + vcpu->arch.sie_block->todpr = 0; + } +} + +static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_sync_regs *regs = &vcpu->run->s.regs; + + /* Clear reset is a superset of the initial reset */ + kvm_arch_vcpu_ioctl_initial_reset(vcpu); + + memset(®s->gprs, 0, sizeof(regs->gprs)); + memset(®s->vrs, 0, sizeof(regs->vrs)); + memset(®s->acrs, 0, sizeof(regs->acrs)); + memset(®s->gscb, 0, sizeof(regs->gscb)); + + regs->etoken = 0; + regs->etoken_extension = 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) @@ -3339,18 +4315,13 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_load(vcpu); - if (test_fp_ctl(fpu->fpc)) { - ret = -EINVAL; - goto out; - } vcpu->run->s.regs.fpc = fpu->fpc; - if (MACHINE_HAS_VX) + if (cpu_has_vx()) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, (freg_t *) fpu->fprs); else memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs)); -out: vcpu_put(vcpu); return ret; } @@ -3359,9 +4330,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { vcpu_load(vcpu); - /* make sure we have the latest values */ - save_fpu_regs(); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) convert_vx_to_fp((freg_t *) fpu->fprs, (__vector128 *) vcpu->run->s.regs.vrs); else @@ -3460,18 +4429,24 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, vcpu_load(vcpu); /* user space knows about this interface - let it control the state */ - vcpu->kvm->arch.user_cpu_state_ctrl = 1; + kvm_s390_set_user_cpu_state_ctrl(vcpu->kvm); switch (mp_state->mp_state) { case KVM_MP_STATE_STOPPED: - kvm_s390_vcpu_stop(vcpu); + rc = kvm_s390_vcpu_stop(vcpu); break; case KVM_MP_STATE_OPERATING: - kvm_s390_vcpu_start(vcpu); + rc = kvm_s390_vcpu_start(vcpu); break; case KVM_MP_STATE_LOAD: + if (!kvm_s390_pv_cpu_is_protected(vcpu)) { + rc = -ENXIO; + break; + } + rc = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR_LOAD); + break; case KVM_MP_STATE_CHECK_STOP: - /* fall through - CHECK_STOP and LOAD are not supported yet */ + fallthrough; /* CHECK_STOP and LOAD are not supported yet */ default: rc = -ENXIO; } @@ -3492,19 +4467,19 @@ retry: if (!kvm_request_pending(vcpu)) return 0; /* - * We use MMU_RELOAD just to re-arm the ipte notifier for the + * If the guest prefix changed, re-arm the ipte notifier for the * guest prefix page. gmap_mprotect_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)) { + if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) { int rc; rc = gmap_mprotect_notify(vcpu->arch.gmap, kvm_s390_get_prefix(vcpu), PAGE_SIZE * 2, PROT_WRITE); if (rc) { - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu); return rc; } goto retry; @@ -3557,30 +4532,26 @@ retry: goto retry; } - /* nothing to do, just clear the request */ - kvm_clear_request(KVM_REQ_UNHALT, vcpu); /* we left the vsie handler, nothing to do, just clear the request */ kvm_clear_request(KVM_REQ_VSIE_RESTART, vcpu); return 0; } -void kvm_s390_set_tod_clock(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod) +static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod) { struct kvm_vcpu *vcpu; - struct kvm_s390_tod_clock_ext htod; - int i; + union tod_clock clk; + unsigned long i; - mutex_lock(&kvm->lock); preempt_disable(); - get_tod_clock_ext((char *)&htod); + store_tod_clock_ext(&clk); - kvm->arch.epoch = gtod->tod - htod.tod; + kvm->arch.epoch = gtod->tod - clk.tod; kvm->arch.epdx = 0; if (test_kvm_facility(kvm, 139)) { - kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; + kvm->arch.epdx = gtod->epoch_idx - clk.ei; if (kvm->arch.epoch > gtod->tod) kvm->arch.epdx -= 1; } @@ -3593,7 +4564,15 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, kvm_s390_vcpu_unblock_all(kvm); preempt_enable(); +} + +int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod) +{ + if (!mutex_trylock(&kvm->lock)) + return 0; + __kvm_s390_set_tod_clock(kvm, gtod); mutex_unlock(&kvm->lock); + return 1; } /** @@ -3629,11 +4608,13 @@ static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token, } } -void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, +bool 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); + + return true; } void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, @@ -3649,7 +4630,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, /* s390 will always inject the page directly */ } -bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) { /* * s390 will always inject the page directly, @@ -3658,33 +4639,31 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) return true; } -static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu) +static bool 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; + return false; if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) != vcpu->arch.pfault_compare) - return 0; + return false; if (psw_extint_disabled(vcpu)) - return 0; + return false; if (kvm_s390_vcpu_has_irq(vcpu, 0)) - return 0; + return false; if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) - return 0; + return false; if (!vcpu->arch.gmap->pfault_enabled) - return 0; + return false; 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; + return false; - rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch); - return rc; + return kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch); } static int vcpu_pre_run(struct kvm_vcpu *vcpu) @@ -3704,12 +4683,9 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) 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) + if (rc || guestdbg_exit_pending(vcpu)) return rc; } @@ -3722,7 +4698,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) kvm_s390_patch_guest_per_regs(vcpu); } - clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.gisa_int.kicked_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); vcpu->arch.sie_block->icptcode = 0; cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); @@ -3816,27 +4792,30 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) current->thread.gmap_pfault = 0; if (kvm_arch_setup_async_pf(vcpu)) return 0; + vcpu->stat.pfault_sync++; return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1); } return vcpu_post_run_fault_in_sie(vcpu); } +#define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK) static int __vcpu_run(struct kvm_vcpu *vcpu) { int rc, exit_reason; + struct sie_page *sie_page = (struct sie_page *)vcpu->arch.sie_block; /* * 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); + kvm_vcpu_srcu_read_lock(vcpu); do { rc = vcpu_pre_run(vcpu); - if (rc) + if (rc || guestdbg_exit_pending(vcpu)) break; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * As PF_VCPU will be used in fault handler, between * guest_enter and guest_exit should be no uaccess. @@ -3845,23 +4824,46 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) guest_enter_irqoff(); __disable_cpu_timer_accounting(vcpu); local_irq_enable(); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy(sie_page->pv_grregs, + vcpu->run->s.regs.gprs, + sizeof(sie_page->pv_grregs)); + } + if (test_cpu_flag(CIF_FPU)) + load_fpu_regs(); exit_reason = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy(vcpu->run->s.regs.gprs, + sie_page->pv_grregs, + sizeof(sie_page->pv_grregs)); + /* + * We're not allowed to inject interrupts on intercepts + * that leave the guest state in an "in-between" state + * where the next SIE entry will do a continuation. + * Fence interrupts in our "internal" PSW. + */ + if (vcpu->arch.sie_block->icptcode == ICPT_PV_INSTR || + vcpu->arch.sie_block->icptcode == ICPT_PV_PREF) { + vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK; + } + } local_irq_disable(); __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); local_irq_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); 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); + kvm_vcpu_srcu_read_unlock(vcpu); return rc; } -static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void sync_regs_fmt2(struct kvm_vcpu *vcpu) { + struct kvm_run *kvm_run = vcpu->run; struct runtime_instr_cb *riccb; struct gs_cb *gscb; @@ -3869,16 +4871,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) gscb = (struct gs_cb *) &kvm_run->s.regs.gscb; 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) { - kvm_s390_set_cpu_timer(vcpu, 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; @@ -3890,6 +4883,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) kvm_clear_async_pf_completion_queue(vcpu); } + if (kvm_run->kvm_dirty_regs & KVM_SYNC_DIAG318) { + vcpu->arch.diag318_info.val = kvm_run->s.regs.diag318; + vcpu->arch.sie_block->cpnc = vcpu->arch.diag318_info.cpnc; + VCPU_EVENT(vcpu, 3, "setting cpnc to %d", vcpu->arch.diag318_info.cpnc); + } /* * If userspace sets the riccb (e.g. after migration) to a valid state, * we should enable RI here instead of doing the lazy enablement. @@ -3919,23 +4917,9 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0; } - save_access_regs(vcpu->arch.host_acrs); - restore_access_regs(vcpu->run->s.regs.acrs); - /* save host (userspace) fprs/vrs */ - save_fpu_regs(); - vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; - vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; - if (MACHINE_HAS_VX) - current->thread.fpu.regs = vcpu->run->s.regs.vrs; - else - current->thread.fpu.regs = vcpu->run->s.regs.fprs; - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - if (test_fp_ctl(current->thread.fpu.fpc)) - /* User space provided an invalid FPC, let's clear it */ - current->thread.fpu.fpc = 0; if (MACHINE_HAS_GS) { preempt_disable(); - __ctl_set_bit(2, 4); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); if (current->thread.gs_cb) { vcpu->arch.host_gscb = current->thread.gs_cb; save_gs_cb(vcpu->arch.host_gscb); @@ -3948,25 +4932,93 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) preempt_enable(); } /* SIE will load etoken directly from SDNX and therefore kvm_run */ +} + +static void sync_regs(struct kvm_vcpu *vcpu) +{ + struct kvm_run *kvm_run = vcpu->run; + + 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) { + kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm); + vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc; + } + save_access_regs(vcpu->arch.host_acrs); + restore_access_regs(vcpu->run->s.regs.acrs); + /* save host (userspace) fprs/vrs */ + save_fpu_regs(); + vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; + vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; + if (cpu_has_vx()) + current->thread.fpu.regs = vcpu->run->s.regs.vrs; + else + current->thread.fpu.regs = vcpu->run->s.regs.fprs; + current->thread.fpu.fpc = vcpu->run->s.regs.fpc; + + /* Sync fmt2 only data */ + if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) { + sync_regs_fmt2(vcpu); + } else { + /* + * In several places we have to modify our internal view to + * not do things that are disallowed by the ultravisor. For + * example we must not inject interrupts after specific exits + * (e.g. 112 prefix page not secure). We do this by turning + * off the machine check, external and I/O interrupt bits + * of our PSW copy. To avoid getting validity intercepts, we + * do only accept the condition code from userspace. + */ + vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_CC; + vcpu->arch.sie_block->gpsw.mask |= kvm_run->psw_mask & + PSW_MASK_CC; + } kvm_run->kvm_dirty_regs = 0; } -static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void store_regs_fmt2(struct kvm_vcpu *vcpu) { + struct kvm_run *kvm_run = vcpu->run; + + 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.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; + kvm_run->s.regs.diag318 = vcpu->arch.diag318_info.val; + if (MACHINE_HAS_GS) { + preempt_disable(); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); + if (vcpu->arch.gs_enabled) + save_gs_cb(current->thread.gs_cb); + current->thread.gs_cb = vcpu->arch.host_gscb; + restore_gs_cb(vcpu->arch.host_gscb); + if (!vcpu->arch.host_gscb) + local_ctl_clear_bit(2, CR2_GUARDED_STORAGE_BIT); + vcpu->arch.host_gscb = NULL; + preempt_enable(); + } + /* SIE will save etoken directly into SDNX and therefore kvm_run */ +} + +static void store_regs(struct kvm_vcpu *vcpu) +{ + struct kvm_run *kvm_run = vcpu->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 = kvm_s390_get_cpu_timer(vcpu); 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; - kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); /* Save guest register state */ @@ -3975,25 +5027,24 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) /* Restore will be done lazily at return */ current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; - if (MACHINE_HAS_GS) { - __ctl_set_bit(2, 4); - if (vcpu->arch.gs_enabled) - save_gs_cb(current->thread.gs_cb); - preempt_disable(); - current->thread.gs_cb = vcpu->arch.host_gscb; - restore_gs_cb(vcpu->arch.host_gscb); - preempt_enable(); - if (!vcpu->arch.host_gscb) - __ctl_clear_bit(2, 4); - vcpu->arch.host_gscb = NULL; - } - /* SIE will save etoken directly into SDNX and therefore kvm_run */ + if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) + store_regs_fmt2(vcpu); } -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { + struct kvm_run *kvm_run = vcpu->run; int rc; + /* + * Running a VM while dumping always has the potential to + * produce inconsistent dump data. But for PV vcpus a SIE + * entry while dumping could also lead to a fatal validity + * intercept which we absolutely want to avoid. + */ + if (vcpu->kvm->arch.pv.dumping) + return -EINVAL; + if (kvm_run->immediate_exit) return -EINTR; @@ -4011,6 +5062,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_sigset_activate(vcpu); + /* + * no need to check the return value of vcpu_start as it can only have + * an error for protvirt, but protvirt means user cpu state + */ if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) { kvm_s390_vcpu_start(vcpu); } else if (is_vcpu_stopped(vcpu)) { @@ -4020,7 +5075,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - sync_regs(vcpu, kvm_run); + sync_regs(vcpu); enable_cpu_timer_accounting(vcpu); might_fault(); @@ -4042,7 +5097,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } disable_cpu_timer_accounting(vcpu); - store_regs(vcpu, kvm_run); + store_regs(vcpu); kvm_sigset_deactivate(vcpu); @@ -4079,7 +5134,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) gpa -= __LC_FPREGS_SAVE_AREA; /* manually convert vector registers if necessary */ - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, fprs, 128); @@ -4132,7 +5187,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) static void __disable_ibs_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -4148,20 +5203,29 @@ static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu) kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu); } -void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) +int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) { - int i, online_vcpus, started_vcpus = 0; + int i, online_vcpus, r = 0, started_vcpus = 0; if (!is_vcpu_stopped(vcpu)) - return; + return 0; 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); + /* Let's tell the UV that we want to change into the operating state */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR); + if (r) { + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return r; + } + } + for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) + if (!is_vcpu_stopped(kvm_get_vcpu(vcpu->kvm, i))) started_vcpus++; } @@ -4172,44 +5236,67 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) /* * As we are starting a second VCPU, we have to disable * the IBS facility on all VCPUs to remove potentially - * oustanding ENABLE requests. + * outstanding ENABLE requests. */ __disable_ibs_on_all_vcpus(vcpu->kvm); } kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED); /* + * The real PSW might have changed due to a RESTART interpreted by the + * ultravisor. We block all interrupts and let the next sie exit + * refresh our view. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK; + /* * 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; + return 0; } -void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) +int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) { - int i, online_vcpus, started_vcpus = 0; + int i, online_vcpus, r = 0, started_vcpus = 0; struct kvm_vcpu *started_vcpu = NULL; if (is_vcpu_stopped(vcpu)) - return; + return 0; 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); + /* Let's tell the UV that we want to change into the stopped state */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_STP); + if (r) { + spin_unlock(&vcpu->kvm->arch.start_stop_lock); + return r; + } + } + /* + * Set the VCPU to STOPPED and THEN clear the interrupt flag, + * now that the SIGP STOP and SIGP STOP AND STORE STATUS orders + * have been fully processed. This will ensure that the VCPU + * is kept BUSY if another VCPU is inquiring with SIGP SENSE. + */ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED); + kvm_s390_clear_stop_irq(vcpu); + __disable_ibs_on_vcpu(vcpu); for (i = 0; i < online_vcpus; i++) { - if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) { + struct kvm_vcpu *tmp = kvm_get_vcpu(vcpu->kvm, i); + + if (!is_vcpu_stopped(tmp)) { started_vcpus++; - started_vcpu = vcpu->kvm->vcpus[i]; + started_vcpu = tmp; } } @@ -4222,7 +5309,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) } spin_unlock(&vcpu->kvm->arch.start_stop_lock); - return; + return 0; } static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, @@ -4249,64 +5336,116 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } -static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, +static long kvm_s390_vcpu_sida_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; + void *sida_addr; + int r = 0; - if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size) + if (mop->flags || !mop->size) return -EINVAL; - - if (mop->size > MEM_OP_MAX_SIZE) + if (mop->size + mop->sida_offset < mop->size) + return -EINVAL; + if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block)) return -E2BIG; + if (!kvm_s390_pv_cpu_is_protected(vcpu)) + return -EINVAL; + + sida_addr = (char *)sida_addr(vcpu->arch.sie_block) + mop->sida_offset; + switch (mop->op) { + case KVM_S390_MEMOP_SIDA_READ: + if (copy_to_user(uaddr, sida_addr, mop->size)) + r = -EFAULT; + + break; + case KVM_S390_MEMOP_SIDA_WRITE: + if (copy_from_user(sida_addr, uaddr, mop->size)) + r = -EFAULT; + break; + } + return r; +} + +static long kvm_s390_vcpu_mem_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + enum gacc_mode acc_mode; + void *tmpbuf = NULL; + int r; + + r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_INJECT_EXCEPTION | + KVM_S390_MEMOP_F_CHECK_ONLY | + KVM_S390_MEMOP_F_SKEY_PROTECTION); + if (r) + return r; + if (mop->ar >= NUM_ACRS) + return -EINVAL; + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return -EINVAL; if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { tmpbuf = vmalloc(mop->size); if (!tmpbuf) return -ENOMEM; } + acc_mode = mop->op == KVM_S390_MEMOP_LOGICAL_READ ? GACC_FETCH : GACC_STORE; + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, + acc_mode, mop->key); + goto out_inject; + } + if (acc_mode == GACC_FETCH) { + r = read_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf, + mop->size, mop->key); + if (r) + goto out_inject; + if (copy_to_user(uaddr, tmpbuf, mop->size)) { + r = -EFAULT; + goto out_free; + } + } else { + if (copy_from_user(tmpbuf, uaddr, mop->size)) { + r = -EFAULT; + goto out_free; + } + r = write_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf, + mop->size, mop->key); + } + +out_inject: + if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) + kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + +out_free: + vfree(tmpbuf); + return r; +} + +static long kvm_s390_vcpu_memsida_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + int r, srcu_idx; + 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, GACC_FETCH); - 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, GACC_STORE); - break; - } - if (copy_from_user(tmpbuf, uaddr, mop->size)) { - r = -EFAULT; - break; - } - r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + r = kvm_s390_vcpu_mem_op(vcpu, mop); + break; + case KVM_S390_MEMOP_SIDA_READ: + case KVM_S390_MEMOP_SIDA_WRITE: + /* we are locked against sida going away by the vcpu->mutex */ + r = kvm_s390_vcpu_sida_op(vcpu, mop); 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; } @@ -4315,6 +5454,7 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp, { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; + int rc; switch (ioctl) { case KVM_S390_IRQ: { @@ -4322,7 +5462,8 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp, if (copy_from_user(&s390irq, argp, sizeof(s390irq))) return -EFAULT; - return kvm_s390_inject_vcpu(vcpu, &s390irq); + rc = kvm_s390_inject_vcpu(vcpu, &s390irq); + break; } case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; @@ -4332,10 +5473,67 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp, return -EFAULT; if (s390int_to_s390irq(&s390int, &s390irq)) return -EINVAL; - return kvm_s390_inject_vcpu(vcpu, &s390irq); + rc = kvm_s390_inject_vcpu(vcpu, &s390irq); + break; } + default: + rc = -ENOIOCTLCMD; + break; } - return -ENOIOCTLCMD; + + /* + * To simplify single stepping of userspace-emulated instructions, + * KVM_EXIT_S390_SIEIC exit sets KVM_GUESTDBG_EXIT_PENDING (see + * should_handle_per_ifetch()). However, if userspace emulation injects + * an interrupt, it needs to be cleared, so that KVM_EXIT_DEBUG happens + * after (and not before) the interrupt delivery. + */ + if (!rc) + vcpu->guest_debug &= ~KVM_GUESTDBG_EXIT_PENDING; + + return rc; +} + +static int kvm_s390_handle_pv_vcpu_dump(struct kvm_vcpu *vcpu, + struct kvm_pv_cmd *cmd) +{ + struct kvm_s390_pv_dmp dmp; + void *data; + int ret; + + /* Dump initialization is a prerequisite */ + if (!vcpu->kvm->arch.pv.dumping) + return -EINVAL; + + if (copy_from_user(&dmp, (__u8 __user *)cmd->data, sizeof(dmp))) + return -EFAULT; + + /* We only handle this subcmd right now */ + if (dmp.subcmd != KVM_PV_DUMP_CPU) + return -EINVAL; + + /* CPU dump length is the same as create cpu storage donation. */ + if (dmp.buff_len != uv_info.guest_cpu_stor_len) + return -EINVAL; + + data = kvzalloc(uv_info.guest_cpu_stor_len, GFP_KERNEL); + if (!data) + return -ENOMEM; + + ret = kvm_s390_pv_dump_cpu(vcpu, data, &cmd->rc, &cmd->rrc); + + VCPU_EVENT(vcpu, 3, "PROTVIRT DUMP CPU %d rc %x rrc %x", + vcpu->vcpu_id, cmd->rc, cmd->rrc); + + if (ret) + ret = -EINVAL; + + /* On success copy over the dump data */ + if (!ret && copy_to_user((__u8 __user *)dmp.buff_addr, data, uv_info.guest_cpu_stor_len)) + ret = -EFAULT; + + kvfree(data); + return ret; } long kvm_arch_vcpu_ioctl(struct file *filp, @@ -4345,13 +5543,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int idx; long r; + u16 rc, rrc; vcpu_load(vcpu); switch (ioctl) { case KVM_S390_STORE_STATUS: idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_s390_vcpu_store_status(vcpu, arg); + r = kvm_s390_store_status_unloaded(vcpu, arg); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; case KVM_S390_SET_INITIAL_PSW: { @@ -4363,12 +5562,43 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw); break; } + case KVM_S390_CLEAR_RESET: + r = 0; + kvm_arch_vcpu_ioctl_clear_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET_CLEAR, &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET CLEAR VCPU: rc %x rrc %x", + rc, rrc); + } + break; case KVM_S390_INITIAL_RESET: - r = kvm_arch_vcpu_ioctl_initial_reset(vcpu); + r = 0; + kvm_arch_vcpu_ioctl_initial_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET_INITIAL, + &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET INITIAL VCPU: rc %x rrc %x", + rc, rrc); + } + break; + case KVM_S390_NORMAL_RESET: + r = 0; + kvm_arch_vcpu_ioctl_normal_reset(vcpu); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_CPU_RESET, &rc, &rrc); + VCPU_EVENT(vcpu, 3, "PROTVIRT RESET NORMAL VCPU: rc %x rrc %x", + rc, rrc); + } break; case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; + r = -EINVAL; + if (kvm_s390_pv_cpu_is_protected(vcpu)) + break; r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) break; @@ -4431,7 +5661,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, 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); + r = kvm_s390_vcpu_memsida_op(vcpu, &mem_op); else r = -EFAULT; break; @@ -4470,6 +5700,33 @@ long kvm_arch_vcpu_ioctl(struct file *filp, irq_state.len); break; } + case KVM_S390_PV_CPU_COMMAND: { + struct kvm_pv_cmd cmd; + + r = -EINVAL; + if (!is_prot_virt_host()) + break; + + r = -EFAULT; + if (copy_from_user(&cmd, argp, sizeof(cmd))) + break; + + r = -EINVAL; + if (cmd.flags) + break; + + /* We only handle this cmd right now */ + if (cmd.cmd != KVM_PV_DUMP) + break; + + r = kvm_s390_handle_pv_vcpu_dump(vcpu, &cmd); + + /* Always copy over UV rc / rrc data */ + if (copy_to_user((__u8 __user *)argp, &cmd.rc, + sizeof(cmd.rc) + sizeof(cmd.rrc))) + r = -EFAULT; + break; + } default: r = -ENOTTY; } @@ -4491,38 +5748,63 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) { - return 0; + return true; } /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, 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 */ + gpa_t size; - if (mem->userspace_addr & 0xffffful) + /* When we are protected, we should not change the memory slots */ + if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; - if (mem->memory_size & 0xffffful) - return -EINVAL; + if (change != KVM_MR_DELETE && change != KVM_MR_FLAGS_ONLY) { + /* + * 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->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) - return -EINVAL; + if (new->userspace_addr & 0xffffful) + return -EINVAL; + + size = new->npages * PAGE_SIZE; + if (size & 0xffffful) + return -EINVAL; + + if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit) + return -EINVAL; + } + + if (!kvm->arch.migration_mode) + return 0; + + /* + * Turn off migration mode when: + * - userspace creates a new memslot with dirty logging off, + * - userspace modifies an existing memslot (MOVE or FLAGS_ONLY) and + * dirty logging is turned off. + * Migration mode expects dirty page logging being enabled to store + * its dirty bitmap. + */ + if (change != KVM_MR_DELETE && + !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + WARN(kvm_s390_vm_stop_migration(kvm), + "Failed to stop migration mode"); return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -4538,10 +5820,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, old->npages * PAGE_SIZE); if (rc) break; - /* FALLTHROUGH */ + fallthrough; case KVM_MR_CREATE: - rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, - mem->guest_phys_addr, mem->memory_size); + rc = gmap_map_segment(kvm->arch.gmap, new->userspace_addr, + new->base_gfn * PAGE_SIZE, + new->npages * PAGE_SIZE); break; case KVM_MR_FLAGS_ONLY: break; @@ -4560,14 +5843,9 @@ static inline unsigned long nonhyp_mask(int i) return 0x0000ffffffffffffUL >> (nonhyp_fai << 4); } -void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) -{ - vcpu->valid_wakeup = false; -} - static int __init kvm_s390_init(void) { - int i; + int i, r; if (!sclp.has_sief2) { pr_info("SIE is not available\n"); @@ -4581,14 +5859,25 @@ static int __init kvm_s390_init(void) for (i = 0; i < 16; i++) kvm_s390_fac_base[i] |= - S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i); + stfle_fac_list[i] & nonhyp_mask(i); + + r = __kvm_s390_init(); + if (r) + return r; - return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (r) { + __kvm_s390_exit(); + return r; + } + return 0; } static void __exit kvm_s390_exit(void) { kvm_exit(); + + __kvm_s390_exit(); } module_init(kvm_s390_init); |