From 3e6c556899d02e04d3d65f0e12adfbe05a557832 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Wed, 2 Oct 2019 04:46:58 -0400 Subject: KVM: s390: protvirt: Add UV debug trace Let's have some debug traces which stay around for longer than the guest. Signed-off-by: Janosch Frank Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d7ff30e45589..7e4a982bfea3 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2,7 +2,7 @@ /* * hosting IBM Z kernel virtual machines (s390x) * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte * Christian Borntraeger @@ -220,6 +220,7 @@ 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) @@ -460,7 +461,12 @@ int kvm_arch_init(void *opaque) if (!kvm_s390_dbf) return -ENOMEM; - if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) + kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long)); + if (!kvm_s390_dbf_uv) + goto out; + + if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) || + debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view)) goto out; kvm_s390_cpu_feat_init(); @@ -487,6 +493,7 @@ void kvm_arch_exit(void) { kvm_s390_gib_destroy(); debug_unregister(kvm_s390_dbf); + debug_unregister(kvm_s390_dbf_uv); } /* Section: device related */ -- cgit v1.2.3 From 29b40f105ec8d555984c1f72dc9133b122e51903 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Mon, 30 Sep 2019 04:19:18 -0400 Subject: KVM: s390: protvirt: Add initial vm and cpu lifecycle handling This contains 3 main changes: 1. changes in SIE control block handling for secure guests 2. helper functions for create/destroy/unpack secure guests 3. KVM_S390_PV_COMMAND ioctl to allow userspace dealing with secure machines Signed-off-by: Janosch Frank Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 24 +++- arch/s390/include/asm/uv.h | 69 ++++++++++ arch/s390/kvm/Makefile | 2 +- arch/s390/kvm/kvm-s390.c | 214 ++++++++++++++++++++++++++++++- arch/s390/kvm/kvm-s390.h | 33 +++++ arch/s390/kvm/pv.c | 266 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 31 +++++ 7 files changed, 635 insertions(+), 4 deletions(-) create mode 100644 arch/s390/kvm/pv.c (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index d058289385a5..1aa2382fe363 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -160,7 +160,13 @@ struct kvm_s390_sie_block { __u8 reserved08[4]; /* 0x0008 */ #define PROG_IN_SIE (1<<0) __u32 prog0c; /* 0x000c */ - __u8 reserved10[16]; /* 0x0010 */ + union { + __u8 reserved10[16]; /* 0x0010 */ + struct { + __u64 pv_handle_cpu; + __u64 pv_handle_config; + }; + }; #define PROG_BLOCK_SIE (1<<0) #define PROG_REQUEST (1<<1) atomic_t prog20; /* 0x0020 */ @@ -233,7 +239,7 @@ struct kvm_s390_sie_block { #define ECB3_RI 0x01 __u8 ecb3; /* 0x0063 */ __u32 scaol; /* 0x0064 */ - __u8 reserved68; /* 0x0068 */ + __u8 sdf; /* 0x0068 */ __u8 epdx; /* 0x0069 */ __u8 reserved6a[2]; /* 0x006a */ __u32 todpr; /* 0x006c */ @@ -645,6 +651,11 @@ struct kvm_guestdbg_info_arch { unsigned long last_bp; }; +struct kvm_s390_pv_vcpu { + u64 handle; + unsigned long stor_base; +}; + struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; /* if vsie is active, currently executed shadow sie control block */ @@ -673,6 +684,7 @@ struct kvm_vcpu_arch { __u64 cputm_start; bool gs_enabled; bool skey_enabled; + struct kvm_s390_pv_vcpu pv; }; struct kvm_vm_stat { @@ -843,6 +855,13 @@ struct kvm_s390_gisa_interrupt { DECLARE_BITMAP(kicked_mask, KVM_MAX_VCPUS); }; +struct kvm_s390_pv { + u64 handle; + u64 guest_len; + unsigned long stor_base; + void *stor_var; +}; + struct kvm_arch{ void *sca; int use_esca; @@ -878,6 +897,7 @@ struct kvm_arch{ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS); struct kvm_s390_gisa_interrupt gisa_int; + struct kvm_s390_pv pv; }; #define KVM_HVA_ERR_BAD (-1UL) diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index d7aa91c89f6c..91ef26983bfd 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -23,11 +23,19 @@ #define UVC_RC_INV_STATE 0x0003 #define UVC_RC_INV_LEN 0x0005 #define UVC_RC_NO_RESUME 0x0007 +#define UVC_RC_NEED_DESTROY 0x8000 #define UVC_CMD_QUI 0x0001 #define UVC_CMD_INIT_UV 0x000f +#define UVC_CMD_CREATE_SEC_CONF 0x0100 +#define UVC_CMD_DESTROY_SEC_CONF 0x0101 +#define UVC_CMD_CREATE_SEC_CPU 0x0120 +#define UVC_CMD_DESTROY_SEC_CPU 0x0121 #define UVC_CMD_CONV_TO_SEC_STOR 0x0200 #define UVC_CMD_CONV_FROM_SEC_STOR 0x0201 +#define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300 +#define UVC_CMD_UNPACK_IMG 0x0301 +#define UVC_CMD_VERIFY_IMG 0x0302 #define UVC_CMD_PIN_PAGE_SHARED 0x0341 #define UVC_CMD_UNPIN_PAGE_SHARED 0x0342 #define UVC_CMD_SET_SHARED_ACCESS 0x1000 @@ -37,10 +45,17 @@ enum uv_cmds_inst { BIT_UVC_CMD_QUI = 0, BIT_UVC_CMD_INIT_UV = 1, + BIT_UVC_CMD_CREATE_SEC_CONF = 2, + BIT_UVC_CMD_DESTROY_SEC_CONF = 3, + BIT_UVC_CMD_CREATE_SEC_CPU = 4, + BIT_UVC_CMD_DESTROY_SEC_CPU = 5, BIT_UVC_CMD_CONV_TO_SEC_STOR = 6, BIT_UVC_CMD_CONV_FROM_SEC_STOR = 7, BIT_UVC_CMD_SET_SHARED_ACCESS = 8, BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9, + BIT_UVC_CMD_SET_SEC_PARMS = 11, + BIT_UVC_CMD_UNPACK_IMG = 13, + BIT_UVC_CMD_VERIFY_IMG = 14, BIT_UVC_CMD_PIN_PAGE_SHARED = 21, BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22, }; @@ -52,6 +67,7 @@ struct uv_cb_header { u16 rrc; /* Return Reason Code */ } __packed __aligned(8); +/* Query Ultravisor Information */ struct uv_cb_qui { struct uv_cb_header header; u64 reserved08; @@ -71,6 +87,7 @@ struct uv_cb_qui { u8 reserveda0[200 - 160]; } __packed __aligned(8); +/* Initialize Ultravisor */ struct uv_cb_init { struct uv_cb_header header; u64 reserved08[2]; @@ -79,6 +96,35 @@ struct uv_cb_init { u64 reserved28[4]; } __packed __aligned(8); +/* Create Guest Configuration */ +struct uv_cb_cgc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 conf_base_stor_origin; + u64 conf_virt_stor_origin; + u64 reserved30; + u64 guest_stor_origin; + u64 guest_stor_len; + u64 guest_sca; + u64 guest_asce; + u64 reserved58[5]; +} __packed __aligned(8); + +/* Create Secure CPU */ +struct uv_cb_csc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 cpu_handle; + u64 guest_handle; + u64 stor_origin; + u8 reserved30[6]; + u16 num; + u64 state_origin; + u64 reserved40[4]; +} __packed __aligned(8); + +/* Convert to Secure */ struct uv_cb_cts { struct uv_cb_header header; u64 reserved08[2]; @@ -86,12 +132,34 @@ struct uv_cb_cts { u64 gaddr; } __packed __aligned(8); +/* Convert from Secure / Pin Page Shared */ struct uv_cb_cfs { struct uv_cb_header header; u64 reserved08[2]; u64 paddr; } __packed __aligned(8); +/* Set Secure Config Parameter */ +struct uv_cb_ssc { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 sec_header_origin; + u32 sec_header_len; + u32 reserved2c; + u64 reserved30[4]; +} __packed __aligned(8); + +/* Unpack */ +struct uv_cb_unp { + struct uv_cb_header header; + u64 reserved08[2]; + u64 guest_handle; + u64 gaddr; + u64 tweak[2]; + u64 reserved38[3]; +} __packed __aligned(8); + /* * A common UV call struct for calls that take no payload * Examples: @@ -105,6 +173,7 @@ struct uv_cb_nodata { u64 reserved20[4]; } __packed __aligned(8); +/* Set Shared Access */ struct uv_cb_share { struct uv_cb_header header; u64 reserved08[3]; diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 05ee90a5ea08..12decca22e7c 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -9,6 +9,6 @@ common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqch ccflags-y := -Ivirt/kvm -Iarch/s390/kvm kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-objs += diag.o gaccess.o guestdbg.o vsie.o +kvm-objs += diag.o gaccess.o guestdbg.o vsie.o pv.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7e4a982bfea3..87258bebb955 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -44,6 +44,7 @@ #include #include #include +#include #include "kvm-s390.h" #include "gaccess.h" @@ -234,8 +235,10 @@ 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) { @@ -2165,6 +2168,160 @@ out: return r; } +static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) +{ + struct kvm_vcpu *vcpu; + u16 rc, rrc; + int ret = 0; + int i; + + /* + * 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) { + *rcp = rc; + *rrcp = rrc; + ret = -EIO; + } + mutex_unlock(&vcpu->mutex); + } + return ret; +} + +static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + int i, r = 0; + u16 dummy; + + struct kvm_vcpu *vcpu; + + 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; +} + +static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) +{ + int r = 0; + u16 dummy; + void __user *argp = (void __user *)cmd->data; + + 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; + + 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); + 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_vm(kvm, &cmd->rc, &cmd->rrc); + 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)) + 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; + } + default: + r = -ENOTTY; + } + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2262,6 +2419,31 @@ long kvm_arch_vm_ioctl(struct file *filp, mutex_unlock(&kvm->slots_lock); break; } + case KVM_S390_PV_COMMAND: { + struct kvm_pv_cmd args; + + 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; + } + mutex_lock(&kvm->lock); + r = kvm_s390_handle_pv(kvm, &args); + mutex_unlock(&kvm->lock); + if (copy_to_user(argp, &args, sizeof(args))) { + r = -EFAULT; + break; + } + break; + } default: r = -ENOTTY; } @@ -2525,6 +2707,8 @@ 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); @@ -2537,6 +2721,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) 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)); } @@ -2558,10 +2745,20 @@ static void kvm_free_vcpus(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { + u16 rc, rrc; + kvm_free_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. To avoid lockdep_assert_held from + * complaining we do not use kvm_s390_pv_is_protected. + */ + if (kvm_s390_pv_get_handle(kvm)) + kvm_s390_pv_deinit_vm(kvm, &rc, &rrc); + debug_unregister(kvm->arch.dbf); free_page((unsigned long)kvm->arch.sie_page2); if (!kvm_is_ucontrol(kvm)) gmap_remove(kvm->arch.gmap); @@ -2657,6 +2854,9 @@ static int sca_switch_to_extended(struct kvm *kvm) unsigned int vcpu_idx; u32 scaol, scaoh; + if (kvm->arch.use_esca) + return 0; + new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO); if (!new_sca) return -ENOMEM; @@ -2908,6 +3108,7 @@ static void kvm_s390_vcpu_setup_model(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 | @@ -2975,6 +3176,14 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) kvm_s390_vcpu_crypto_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; } @@ -4540,6 +4749,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) return -EINVAL; + /* When we are protected, we should not change the memory slots */ + if (kvm_s390_pv_get_handle(kvm)) + return -EINVAL; return 0; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index be55b4b99bd3..13e6986596ed 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -207,6 +208,38 @@ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) return kvm->arch.user_cpu_state_ctrl != 0; } +/* implemented in pv.c */ +int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); +int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); +int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, + u16 *rrc); +int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, + unsigned long tweak, u16 *rc, u16 *rrc); + +static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm) +{ + return kvm->arch.pv.handle; +} + +static inline u64 kvm_s390_pv_cpu_get_handle(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pv.handle; +} + +static inline bool kvm_s390_pv_is_protected(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->lock); + return !!kvm_s390_pv_get_handle(kvm); +} + +static inline bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu) +{ + lockdep_assert_held(&vcpu->mutex); + return !!kvm_s390_pv_cpu_get_handle(vcpu); +} + /* implemented in interrupt.c */ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c new file mode 100644 index 000000000000..e9e020475f4a --- /dev/null +++ b/arch/s390/kvm/pv.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hosting Protected Virtual Machines + * + * Copyright IBM Corp. 2019, 2020 + * Author(s): Janosch Frank + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "kvm-s390.h" + +int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) +{ + int cc = 0; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) { + cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), + UVC_CMD_DESTROY_SEC_CPU, rc, rrc); + + KVM_UV_EVENT(vcpu->kvm, 3, + "PROTVIRT DESTROY VCPU %d: rc %x rrc %x", + vcpu->vcpu_id, *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", + *rc, *rrc); + } + /* Intended memory leak for something that should never happen. */ + if (!cc) + free_pages(vcpu->arch.pv.stor_base, + get_order(uv_info.guest_cpu_stor_len)); + vcpu->arch.sie_block->pv_handle_cpu = 0; + vcpu->arch.sie_block->pv_handle_config = 0; + memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); + vcpu->arch.sie_block->sdf = 0; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + + return cc ? EIO : 0; +} + +int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) +{ + struct uv_cb_csc uvcb = { + .header.cmd = UVC_CMD_CREATE_SEC_CPU, + .header.len = sizeof(uvcb), + }; + int cc; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) + return -EINVAL; + + vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, + get_order(uv_info.guest_cpu_stor_len)); + if (!vcpu->arch.pv.stor_base) + return -ENOMEM; + + /* Input */ + uvcb.guest_handle = kvm_s390_pv_get_handle(vcpu->kvm); + uvcb.num = vcpu->arch.sie_block->icpua; + uvcb.state_origin = (u64)vcpu->arch.sie_block; + uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base; + + cc = uv_call(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(vcpu->kvm, 3, + "PROTVIRT CREATE VCPU: cpu %d handle %llx rc %x rrc %x", + vcpu->vcpu_id, uvcb.cpu_handle, uvcb.header.rc, + uvcb.header.rrc); + + if (cc) { + u16 dummy; + + kvm_s390_pv_destroy_cpu(vcpu, &dummy, &dummy); + return -EIO; + } + + /* Output */ + vcpu->arch.pv.handle = uvcb.cpu_handle; + vcpu->arch.sie_block->pv_handle_cpu = uvcb.cpu_handle; + vcpu->arch.sie_block->pv_handle_config = kvm_s390_pv_get_handle(vcpu->kvm); + vcpu->arch.sie_block->sdf = 2; + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + return 0; +} + +/* only free resources when the destroy was successful */ +static void kvm_s390_pv_dealloc_vm(struct kvm *kvm) +{ + vfree(kvm->arch.pv.stor_var); + free_pages(kvm->arch.pv.stor_base, + get_order(uv_info.guest_base_stor_len)); + memset(&kvm->arch.pv, 0, sizeof(kvm->arch.pv)); +} + +static int kvm_s390_pv_alloc_vm(struct kvm *kvm) +{ + unsigned long base = uv_info.guest_base_stor_len; + unsigned long virt = uv_info.guest_virt_var_stor_len; + unsigned long npages = 0, vlen = 0; + struct kvm_memory_slot *memslot; + + kvm->arch.pv.stor_var = NULL; + kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, get_order(base)); + if (!kvm->arch.pv.stor_base) + return -ENOMEM; + + /* + * Calculate current guest storage for allocation of the + * variable storage, which is based on the length in MB. + * + * Slots are sorted by GFN + */ + mutex_lock(&kvm->slots_lock); + memslot = kvm_memslots(kvm)->memslots; + npages = memslot->base_gfn + memslot->npages; + mutex_unlock(&kvm->slots_lock); + + kvm->arch.pv.guest_len = npages * PAGE_SIZE; + + /* Allocate variable storage */ + vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); + vlen += uv_info.guest_virt_base_stor_len; + kvm->arch.pv.stor_var = vzalloc(vlen); + if (!kvm->arch.pv.stor_var) + goto out_err; + return 0; + +out_err: + kvm_s390_pv_dealloc_vm(kvm); + return -ENOMEM; +} + +/* this should not fail, but if it does, we must not free the donated memory */ +int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + int cc; + + cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_DESTROY_SEC_CONF, rc, rrc); + WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); + atomic_set(&kvm->mm->context.is_protected, 0); + KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); + /* Inteded memory leak on "impossible" error */ + if (!cc) + kvm_s390_pv_dealloc_vm(kvm); + return cc ? -EIO : 0; +} + +int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + struct uv_cb_cgc uvcb = { + .header.cmd = UVC_CMD_CREATE_SEC_CONF, + .header.len = sizeof(uvcb) + }; + int cc, ret; + u16 dummy; + + ret = kvm_s390_pv_alloc_vm(kvm); + if (ret) + return ret; + + /* Inputs */ + uvcb.guest_stor_origin = 0; /* MSO is 0 for KVM */ + uvcb.guest_stor_len = kvm->arch.pv.guest_len; + uvcb.guest_asce = kvm->arch.gmap->asce; + uvcb.guest_sca = (unsigned long)kvm->arch.sca; + uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base; + uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var; + + cc = uv_call(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x", + uvcb.guest_handle, uvcb.guest_stor_len, *rc, *rrc); + + /* Outputs */ + kvm->arch.pv.handle = uvcb.guest_handle; + + if (cc) { + if (uvcb.header.rc & UVC_RC_NEED_DESTROY) + kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); + else + kvm_s390_pv_dealloc_vm(kvm); + return -EIO; + } + kvm->arch.gmap->guest_handle = uvcb.guest_handle; + atomic_set(&kvm->mm->context.is_protected, 1); + return 0; +} + +int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, + u16 *rrc) +{ + struct uv_cb_ssc uvcb = { + .header.cmd = UVC_CMD_SET_SEC_CONF_PARAMS, + .header.len = sizeof(uvcb), + .sec_header_origin = (u64)hdr, + .sec_header_len = length, + .guest_handle = kvm_s390_pv_get_handle(kvm), + }; + int cc = uv_call(0, (u64)&uvcb); + + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", + *rc, *rrc); + return cc ? -EINVAL : 0; +} + +static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, + u64 offset, u16 *rc, u16 *rrc) +{ + struct uv_cb_unp uvcb = { + .header.cmd = UVC_CMD_UNPACK_IMG, + .header.len = sizeof(uvcb), + .guest_handle = kvm_s390_pv_get_handle(kvm), + .gaddr = addr, + .tweak[0] = tweak, + .tweak[1] = offset, + }; + int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb); + + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + + if (ret && ret != -EAGAIN) + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", + uvcb.gaddr, *rc, *rrc); + return ret; +} + +int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, + unsigned long tweak, u16 *rc, u16 *rrc) +{ + u64 offset = 0; + int ret = 0; + + if (addr & ~PAGE_MASK || !size || size & ~PAGE_MASK) + return -EINVAL; + + KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx", + addr, size); + + while (offset < size) { + ret = unpack_one(kvm, addr, tweak, offset, rc, rrc); + if (ret == -EAGAIN) { + cond_resched(); + if (fatal_signal_pending(current)) + break; + continue; + } + if (ret) + break; + addr += PAGE_SIZE; + offset += PAGE_SIZE; + } + if (!ret) + KVM_UV_EVENT(kvm, 3, "%s", "PROTVIRT VM UNPACK: successful"); + return ret; +} diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4b95f9a31a2f..ad69817f7792 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1478,6 +1478,37 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +/* Available with KVM_CAP_S390_PROTECTED */ +#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From fa0c5eabbdd33012b369cf75d6a39389cc9ae707 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 16 Jul 2019 13:08:37 +0200 Subject: KVM: s390: protvirt: Secure memory is not mergeable KSM will not work on secure pages, because when the kernel reads a secure page, it will be encrypted and hence no two pages will look the same. Let's mark the guest pages as unmergeable when we transition to secure mode. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/gmap.h | 1 + arch/s390/kvm/kvm-s390.c | 6 ++++++ arch/s390/mm/gmap.c | 30 ++++++++++++++++++++---------- 3 files changed, 27 insertions(+), 10 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index 3c4926aa78f4..6f9ff7a69fa2 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -148,4 +148,5 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start, void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); +int gmap_mark_unmergeable(void); #endif /* _ASM_S390_GMAP_H */ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 87258bebb955..bf61f48e9a3d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2234,6 +2234,12 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) if (r) break; + down_write(¤t->mm->mmap_sem); + r = gmap_mark_unmergeable(); + up_write(¤t->mm->mmap_sem); + if (r) + break; + r = kvm_s390_pv_init_vm(kvm, &cmd->rc, &cmd->rrc); if (r) break; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index edcdca97e85e..7291452fe5f0 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2548,6 +2548,22 @@ int s390_enable_sie(void) } EXPORT_SYMBOL_GPL(s390_enable_sie); +int gmap_mark_unmergeable(void) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (ksm_madvise(vma, vma->vm_start, vma->vm_end, + MADV_UNMERGEABLE, &vma->vm_flags)) { + return -ENOMEM; + } + } + mm->def_flags &= ~VM_MERGEABLE; + return 0; +} +EXPORT_SYMBOL_GPL(gmap_mark_unmergeable); + /* * Enable storage key handling from now on and initialize the storage * keys with the default key. @@ -2593,7 +2609,6 @@ static const struct mm_walk_ops enable_skey_walk_ops = { int s390_enable_skey(void) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; int rc = 0; down_write(&mm->mmap_sem); @@ -2601,16 +2616,11 @@ int s390_enable_skey(void) goto out_up; mm->context.uses_skeys = 1; - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (ksm_madvise(vma, vma->vm_start, vma->vm_end, - MADV_UNMERGEABLE, &vma->vm_flags)) { - mm->context.uses_skeys = 0; - rc = -ENOMEM; - goto out_up; - } + rc = gmap_mark_unmergeable(); + if (rc) { + mm->context.uses_skeys = 0; + goto out_up; } - mm->def_flags &= ~VM_MERGEABLE; - walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL); out_up: -- cgit v1.2.3 From 0890ddea1a90e57114b5704cd560192c743f3d2e Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 3 Feb 2020 09:13:37 +0100 Subject: KVM: s390: protvirt: Add SCLP interrupt handling The sclp interrupt is kind of special. The ultravisor polices that we do not inject an sclp interrupt with payload if no sccb is outstanding. On the other hand we have "asynchronous" event interrupts, e.g. for console input. We separate both variants into sclp interrupt and sclp event interrupt. The sclp interrupt is masked until a previous servc instruction has finished (sie exit 108). [frankja@linux.ibm.com: factoring out write_sclp] Signed-off-by: Janosch Frank Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 6 ++- arch/s390/kvm/intercept.c | 27 ++++++++++++ arch/s390/kvm/interrupt.c | 95 ++++++++++++++++++++++++++++++++-------- arch/s390/kvm/kvm-s390.c | 6 +++ 4 files changed, 115 insertions(+), 19 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index a13dc77f8b07..ba3364b37159 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -518,6 +518,7 @@ enum irq_types { IRQ_PEND_PFAULT_INIT, IRQ_PEND_EXT_HOST, IRQ_PEND_EXT_SERVICE, + IRQ_PEND_EXT_SERVICE_EV, IRQ_PEND_EXT_TIMING, IRQ_PEND_EXT_CPU_TIMER, IRQ_PEND_EXT_CLOCK_COMP, @@ -562,6 +563,7 @@ enum irq_types { (1UL << IRQ_PEND_EXT_TIMING) | \ (1UL << IRQ_PEND_EXT_HOST) | \ (1UL << IRQ_PEND_EXT_SERVICE) | \ + (1UL << IRQ_PEND_EXT_SERVICE_EV) | \ (1UL << IRQ_PEND_VIRTIO) | \ (1UL << IRQ_PEND_PFAULT_INIT) | \ (1UL << IRQ_PEND_PFAULT_DONE)) @@ -582,7 +584,8 @@ enum irq_types { (1UL << IRQ_PEND_EXT_CLOCK_COMP) | \ (1UL << IRQ_PEND_EXT_EMERGENCY) | \ (1UL << IRQ_PEND_EXT_EXTERNAL) | \ - (1UL << IRQ_PEND_EXT_SERVICE)) + (1UL << IRQ_PEND_EXT_SERVICE) | \ + (1UL << IRQ_PEND_EXT_SERVICE_EV)) struct kvm_s390_interrupt_info { struct list_head list; @@ -642,6 +645,7 @@ struct kvm_s390_local_interrupt { struct kvm_s390_float_interrupt { unsigned long pending_irqs; + unsigned long masked_irqs; spinlock_t lock; struct list_head lists[FIRQ_LIST_COUNT]; int counters[FIRQ_MAX_COUNT]; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 9966c43c6035..00a79442a428 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -444,8 +444,35 @@ static int handle_operexc(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); } +static int handle_pv_sclp(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + + spin_lock(&fi->lock); + /* + * 2 cases: + * a: an sccb answering interrupt was already pending or in flight. + * As the sccb value is not known we can simply set some value to + * trigger delivery of a saved SCCB. UV will then use its saved + * copy of the SCCB value. + * b: an error SCCB interrupt needs to be injected so we also inject + * a fake SCCB address. Firmware will use the proper one. + * This makes sure, that both errors and real sccb returns will only + * be delivered after a notification intercept (instruction has + * finished) but not after others. + */ + fi->srv_signal.ext_params |= 0x43000; + set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + clear_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs); + spin_unlock(&fi->lock); + return 0; +} + static int handle_pv_notification(struct kvm_vcpu *vcpu) { + if (vcpu->arch.sie_block->ipa == 0xb220) + return handle_pv_sclp(vcpu); + return handle_instruction(vcpu); } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index fc55f09938eb..145cccd498d7 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -324,8 +324,11 @@ static inline int gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) { - return vcpu->kvm->arch.float_int.pending_irqs | - vcpu->arch.local_int.pending_irqs; + unsigned long pending = vcpu->kvm->arch.float_int.pending_irqs | + vcpu->arch.local_int.pending_irqs; + + pending &= ~vcpu->kvm->arch.float_int.masked_irqs; + return pending; } static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) @@ -383,8 +386,10 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & CR0_CPU_TIMER_SUBMASK)) __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); - if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) + if (!(vcpu->arch.sie_block->gcr[0] & CR0_SERVICE_SIGNAL_SUBMASK)) { __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); + __clear_bit(IRQ_PEND_EXT_SERVICE_EV, &active_mask); + } if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; /* PV guest cpus can have a single interruption injected at a time. */ @@ -946,20 +951,49 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +#define SCCB_MASK 0xFFFFFFF8 +#define SCCB_EVENT_PENDING 0x3 + +static int write_sclp(struct kvm_vcpu *vcpu, u32 parm) +{ + int rc; + + if (kvm_s390_pv_cpu_get_handle(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_SERVICE_SIG; + vcpu->arch.sie_block->eiparams = parm; + return 0; + } + + rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, parm, + (u32 *)__LC_EXT_PARAMS); + + return rc ? -EFAULT : 0; +} + static int __must_check __deliver_service(struct kvm_vcpu *vcpu) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_ext_info ext; - int rc = 0; spin_lock(&fi->lock); - if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs) || + !(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { spin_unlock(&fi->lock); return 0; } ext = fi->srv_signal; memset(&fi->srv_signal, 0, sizeof(ext)); clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + if (kvm_s390_pv_cpu_is_protected(vcpu)) + set_bit(IRQ_PEND_EXT_SERVICE, &fi->masked_irqs); spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x", @@ -968,16 +1002,31 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, ext.ext_params, 0); - rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, ext.ext_params, - (u32 *)__LC_EXT_PARAMS); + return write_sclp(vcpu, ext.ext_params); +} - return rc ? -EFAULT : 0; +static int __must_check __deliver_service_ev(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_ext_info ext; + + spin_lock(&fi->lock); + if (!(test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs))) { + spin_unlock(&fi->lock); + return 0; + } + ext = fi->srv_signal; + /* only clear the event bit */ + fi->srv_signal.ext_params &= ~SCCB_EVENT_PENDING; + clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + spin_unlock(&fi->lock); + + VCPU_EVENT(vcpu, 4, "%s", "deliver: sclp parameter event"); + vcpu->stat.deliver_service_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, + ext.ext_params, 0); + + return write_sclp(vcpu, SCCB_EVENT_PENDING); } static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) @@ -1382,6 +1431,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) case IRQ_PEND_EXT_SERVICE: rc = __deliver_service(vcpu); break; + case IRQ_PEND_EXT_SERVICE_EV: + rc = __deliver_service_ev(vcpu); + break; case IRQ_PEND_PFAULT_DONE: rc = __deliver_pfault_done(vcpu); break; @@ -1734,9 +1786,6 @@ out: return inti; } -#define SCCB_MASK 0xFFFFFFF8 -#define SCCB_EVENT_PENDING 0x3 - static int __inject_service(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { @@ -1745,6 +1794,11 @@ static int __inject_service(struct kvm *kvm, kvm->stat.inject_service_signal++; spin_lock(&fi->lock); fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING; + + /* We always allow events, track them separately from the sccb ints */ + if (fi->srv_signal.ext_params & SCCB_EVENT_PENDING) + set_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); + /* * Early versions of the QEMU s390 bios will inject several * service interrupts after another without handling a @@ -2141,6 +2195,10 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; int i; + mutex_lock(&kvm->lock); + if (!kvm_s390_pv_is_protected(kvm)) + fi->masked_irqs = 0; + mutex_unlock(&kvm->lock); spin_lock(&fi->lock); fi->pending_irqs = 0; memset(&fi->srv_signal, 0, sizeof(fi->srv_signal)); @@ -2207,7 +2265,8 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) n++; } } - if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) { + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs) || + test_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs)) { if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bf61f48e9a3d..2881151fd773 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2247,6 +2247,9 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) 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_DISABLE: { @@ -2263,6 +2266,9 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) if (r) break; r = kvm_s390_pv_deinit_vm(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: { -- cgit v1.2.3 From c8aac2344d663ec9c635ccec368341602f255f4c Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Wed, 8 May 2019 15:52:00 +0200 Subject: KVM: s390: protvirt: Add new gprs location handling Guest registers for protected guests are stored at offset 0x380. We will copy those to the usual places. Long term we could refactor this or use register access functions. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 4 +++- arch/s390/kvm/kvm-s390.c | 11 +++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index ba3364b37159..4fcbb055a565 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -343,7 +343,9 @@ struct kvm_s390_itdb { struct sie_page { struct kvm_s390_sie_block sie_block; struct mcck_volatile_info mcck_info; /* 0x0200 */ - __u8 reserved218[1000]; /* 0x0218 */ + __u8 reserved218[360]; /* 0x0218 */ + __u64 pv_grregs[16]; /* 0x0380 */ + __u8 reserved400[512]; /* 0x0400 */ struct kvm_s390_itdb itdb; /* 0x0600 */ __u8 reserved700[2304]; /* 0x0700 */ }; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 2881151fd773..bd62312fdc0e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4059,6 +4059,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) 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- @@ -4080,8 +4081,18 @@ 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)); + } 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)); + } local_irq_disable(); __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); -- cgit v1.2.3 From 19e1227768863a1469797c13ef8fea1af7beac2c Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 2 Apr 2019 09:21:06 +0200 Subject: KVM: S390: protvirt: Introduce instruction data area bounce buffer Now that we can't access guest memory anymore, we have a dedicated satellite block that's a bounce buffer for instruction data. We re-use the memop interface to copy the instruction data to / from userspace. This lets us re-use a lot of QEMU code which used that interface to make logical guest memory accesses which are not possible anymore in protected mode anyway. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Reviewed-by: David Hildenbrand [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/kvm_host.h | 11 ++++++- arch/s390/kvm/kvm-s390.c | 66 +++++++++++++++++++++++++++++++++++----- arch/s390/kvm/pv.c | 16 ++++++++++ include/uapi/linux/kvm.h | 9 ++++-- 4 files changed, 91 insertions(+), 11 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 4fcbb055a565..aa945b101fff 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -127,6 +127,12 @@ struct mcck_volatile_info { #define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \ CR14_EXTERNAL_DAMAGE_SUBMASK) +#define SIDAD_SIZE_MASK 0xff +#define sida_origin(sie_block) \ + ((sie_block)->sidad & PAGE_MASK) +#define sida_size(sie_block) \ + ((((sie_block)->sidad & SIDAD_SIZE_MASK) + 1) * PAGE_SIZE) + #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -315,7 +321,10 @@ struct kvm_s390_sie_block { #define CRYCB_FORMAT2 0x00000003 __u32 crycbd; /* 0x00fc */ __u64 gcr[16]; /* 0x0100 */ - __u64 gbea; /* 0x0180 */ + union { + __u64 gbea; /* 0x0180 */ + __u64 sidad; + }; __u8 reserved188[8]; /* 0x0188 */ __u64 sdnxo; /* 0x0190 */ __u8 reserved198[8]; /* 0x0198 */ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bd62312fdc0e..efbbcd2948a3 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4495,12 +4495,40 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + int r = 0; + + if (mop->flags || !mop->size) + return -EINVAL; + if (mop->size + mop->sida_offset < mop->size) + return -EINVAL; + if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block)) + return -E2BIG; + + switch (mop->op) { + case KVM_S390_MEMOP_SIDA_READ: + if (copy_to_user(uaddr, (void *)(sida_origin(vcpu->arch.sie_block) + + mop->sida_offset), mop->size)) + r = -EFAULT; + + break; + case KVM_S390_MEMOP_SIDA_WRITE: + if (copy_from_user((void *)(sida_origin(vcpu->arch.sie_block) + + mop->sida_offset), uaddr, mop->size)) + r = -EFAULT; + break; + } + return r; +} static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, struct kvm_s390_mem_op *mop) { void __user *uaddr = (void __user *)mop->buf; void *tmpbuf = NULL; - int r, srcu_idx; + int r = 0; const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION | KVM_S390_MEMOP_F_CHECK_ONLY; @@ -4510,14 +4538,15 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; + 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; } - 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) { @@ -4543,12 +4572,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, } r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); break; - default: - r = -EINVAL; } - srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); - if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); @@ -4556,6 +4581,31 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_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: + case KVM_S390_MEMOP_LOGICAL_WRITE: + r = kvm_s390_guest_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_guest_sida_op(vcpu, mop); + break; + default: + r = -EINVAL; + } + + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + return r; +} + long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4686,7 +4736,7 @@ 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_guest_memsida_op(vcpu, &mem_op); else r = -EFAULT; break; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 9840ee49e572..13a41533eacf 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -33,10 +33,18 @@ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) if (!cc) free_pages(vcpu->arch.pv.stor_base, get_order(uv_info.guest_cpu_stor_len)); + + free_page(sida_origin(vcpu->arch.sie_block)); vcpu->arch.sie_block->pv_handle_cpu = 0; vcpu->arch.sie_block->pv_handle_config = 0; memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv)); vcpu->arch.sie_block->sdf = 0; + /* + * The sidad field (for sdf == 2) is now the gbea field (for sdf == 0). + * Use the reset value of gbea to avoid leaking the kernel pointer of + * the just freed sida. + */ + vcpu->arch.sie_block->gbea = 1; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); return cc ? EIO : 0; @@ -64,6 +72,14 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) uvcb.state_origin = (u64)vcpu->arch.sie_block; uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base; + /* Alloc Secure Instruction Data Area Designation */ + vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!vcpu->arch.sie_block->sidad) { + free_pages(vcpu->arch.pv.stor_base, + get_order(uv_info.guest_cpu_stor_len)); + return -ENOMEM; + } + cc = uv_call(0, (u64)&uvcb); *rc = uvcb.header.rc; *rrc = uvcb.header.rrc; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ad69817f7792..f4cac1c09e97 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -474,12 +474,17 @@ struct kvm_s390_mem_op { __u32 size; /* amount of bytes */ __u32 op; /* type of operation */ __u64 buf; /* buffer in userspace */ - __u8 ar; /* the access register number */ - __u8 reserved[31]; /* should be set to 0 */ + union { + __u8 ar; /* the access register number */ + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* should be set to 0 */ + }; }; /* types for kvm_s390_mem_op->op */ #define KVM_S390_MEMOP_LOGICAL_READ 0 #define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) -- cgit v1.2.3 From 68cf7b1f137e61cea71925e48bc0c6d7bcfc637c Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Fri, 14 Jun 2019 13:11:21 +0200 Subject: KVM: s390: protvirt: disallow one_reg A lot of the registers are controlled by the Ultravisor and never visible to KVM. Some fields in the sie control block are overlayed, like gbea. As no known userspace uses the ONE_REG interface on s390 if sync regs are available, no functionality is lost if it is disabled for protected guests. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- Documentation/virt/kvm/api.rst | 6 ++++-- arch/s390/kvm/kvm-s390.c | 3 +++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 97a72a53fa4b..7505d7a6c0d8 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -2117,7 +2117,8 @@ Errors: ====== ============================================================  ENOENT   no such register -  EINVAL   invalid register ID, or no such register +  EINVAL   invalid register ID, or no such register or used with VMs in + protected virtualization mode on s390  EPERM    (arm64) register access not allowed before vcpu finalization ====== ============================================================ @@ -2552,7 +2553,8 @@ Errors include: ======== ============================================================  ENOENT   no such register -  EINVAL   invalid register ID, or no such register +  EINVAL   invalid register ID, or no such register or used with VMs in + protected virtualization mode on s390  EPERM    (arm64) register access not allowed before vcpu finalization ======== ============================================================ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index efbbcd2948a3..797b4031ed4d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4674,6 +4674,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, 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; -- cgit v1.2.3 From 0f3035047140b3dc18fc5a028ed5f273f24b5539 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Mon, 10 Feb 2020 04:27:47 -0500 Subject: KVM: s390: protvirt: Do only reset registers that are accessible For protected VMs the hypervisor can not access guest breaking event address, program parameter, bpbc and todpr. Do not reset those fields as the control block does not provide access to these fields. Signed-off-by: Janosch Frank Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 797b4031ed4d..1c7bbc2497a2 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3502,14 +3502,21 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) kvm_s390_set_prefix(vcpu, 0); kvm_s390_set_cpu_timer(vcpu, 0); vcpu->arch.sie_block->ckc = 0; - vcpu->arch.sie_block->todpr = 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; vcpu->run->s.regs.fpc = 0; - vcpu->arch.sie_block->gbea = 1; - vcpu->arch.sie_block->pp = 0; - vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + /* + * Do not reset these registers in the protected case, as some of + * them are overlayed 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) -- cgit v1.2.3 From 811ea797118a8caf54b54fc5c30e0b6c90c8abf3 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Fri, 14 Jun 2019 13:11:21 +0200 Subject: KVM: s390: protvirt: Only sync fmt4 registers A lot of the registers are controlled by the Ultravisor and never visible to KVM. Also some registers are overlayed, like gbea is with sidad, which might leak data to userspace. Hence we sync a minimal set of registers for both SIE formats and then check and sync format 2 registers if necessary. Signed-off-by: Janosch Frank Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 110 ++++++++++++++++++++++++++++++----------------- 1 file changed, 70 insertions(+), 40 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 1c7bbc2497a2..abe295077d00 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4113,7 +4113,7 @@ static int __vcpu_run(struct kvm_vcpu *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) { struct runtime_instr_cb *riccb; struct gs_cb *gscb; @@ -4122,16 +4122,7 @@ 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; @@ -4172,6 +4163,36 @@ 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; } + if (MACHINE_HAS_GS) { + preempt_disable(); + __ctl_set_bit(2, 4); + if (current->thread.gs_cb) { + vcpu->arch.host_gscb = current->thread.gs_cb; + save_gs_cb(vcpu->arch.host_gscb); + } + if (vcpu->arch.gs_enabled) { + current->thread.gs_cb = (struct gs_cb *) + &vcpu->run->s.regs.gscb; + restore_gs_cb(current->thread.gs_cb); + } + 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) +{ + 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 */ @@ -4186,23 +4207,47 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; + + /* Sync fmt2 only data */ + if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) { + sync_regs_fmt2(vcpu, kvm_run); + } 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_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_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; if (MACHINE_HAS_GS) { - preempt_disable(); __ctl_set_bit(2, 4); - if (current->thread.gs_cb) { - vcpu->arch.host_gscb = current->thread.gs_cb; - save_gs_cb(vcpu->arch.host_gscb); - } - if (vcpu->arch.gs_enabled) { - current->thread.gs_cb = (struct gs_cb *) - &vcpu->run->s.regs.gscb; - restore_gs_cb(current->thread.gs_cb); - } + 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 load etoken directly from SDNX and therefore kvm_run */ - - kvm_run->kvm_dirty_regs = 0; + /* SIE will save etoken directly into SDNX and therefore kvm_run */ } static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -4213,13 +4258,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) 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 */ @@ -4228,19 +4269,8 @@ 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, kvm_run); } int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -- cgit v1.2.3 From e0d2773d487c2a41c99d9e256d51cc0a859aa9ab Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Thu, 9 May 2019 13:07:21 +0200 Subject: KVM: s390: protvirt: UV calls in support of diag308 0, 1 diag 308 subcode 0 and 1 require several KVM and Ultravisor interactions. Specific to these "soft" reboots are * The "unshare all" UVC * The "prepare for reset" UVC Signed-off-by: Janosch Frank Acked-by: David Hildenbrand Reviewed-by: Cornelia Huck [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/uv.h | 4 ++++ arch/s390/kvm/kvm-s390.c | 22 ++++++++++++++++++++++ include/uapi/linux/kvm.h | 2 ++ 3 files changed, 28 insertions(+) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 91ef26983bfd..f149c29ddb84 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -36,6 +36,8 @@ #define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300 #define UVC_CMD_UNPACK_IMG 0x0301 #define UVC_CMD_VERIFY_IMG 0x0302 +#define UVC_CMD_PREPARE_RESET 0x0320 +#define UVC_CMD_SET_UNSHARE_ALL 0x0340 #define UVC_CMD_PIN_PAGE_SHARED 0x0341 #define UVC_CMD_UNPIN_PAGE_SHARED 0x0342 #define UVC_CMD_SET_SHARED_ACCESS 0x1000 @@ -56,6 +58,8 @@ enum uv_cmds_inst { BIT_UVC_CMD_SET_SEC_PARMS = 11, BIT_UVC_CMD_UNPACK_IMG = 13, BIT_UVC_CMD_VERIFY_IMG = 14, + BIT_UVC_CMD_PREPARE_RESET = 18, + BIT_UVC_CMD_UNSHARE_ALL = 20, BIT_UVC_CMD_PIN_PAGE_SHARED = 21, BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22, }; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index abe295077d00..16531b251eab 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2328,6 +2328,28 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) 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; + } default: r = -ENOTTY; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f4cac1c09e97..2c354ba3a610 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1500,6 +1500,8 @@ enum pv_cmd_id { KVM_PV_SET_SEC_PARMS, KVM_PV_UNPACK, KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, }; struct kvm_pv_cmd { -- cgit v1.2.3 From fe28c7868f68b82e4517efb1dc3c22e2297df340 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Wed, 15 May 2019 13:24:30 +0200 Subject: KVM: s390: protvirt: Report CPU state to Ultravisor VCPU states have to be reported to the ultravisor for SIGP interpretation, kdump, kexec and reboot. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/uv.h | 15 +++++++++++++++ arch/s390/kvm/diag.c | 6 +++++- arch/s390/kvm/intercept.c | 4 ++++ arch/s390/kvm/kvm-s390.c | 44 ++++++++++++++++++++++++++++++++++---------- arch/s390/kvm/kvm-s390.h | 5 +++-- arch/s390/kvm/pv.c | 18 ++++++++++++++++++ 6 files changed, 79 insertions(+), 13 deletions(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index f149c29ddb84..fc221d91a965 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -37,6 +37,7 @@ #define UVC_CMD_UNPACK_IMG 0x0301 #define UVC_CMD_VERIFY_IMG 0x0302 #define UVC_CMD_PREPARE_RESET 0x0320 +#define UVC_CMD_CPU_SET_STATE 0x0330 #define UVC_CMD_SET_UNSHARE_ALL 0x0340 #define UVC_CMD_PIN_PAGE_SHARED 0x0341 #define UVC_CMD_UNPIN_PAGE_SHARED 0x0342 @@ -58,6 +59,7 @@ enum uv_cmds_inst { BIT_UVC_CMD_SET_SEC_PARMS = 11, BIT_UVC_CMD_UNPACK_IMG = 13, BIT_UVC_CMD_VERIFY_IMG = 14, + BIT_UVC_CMD_CPU_SET_STATE = 17, BIT_UVC_CMD_PREPARE_RESET = 18, BIT_UVC_CMD_UNSHARE_ALL = 20, BIT_UVC_CMD_PIN_PAGE_SHARED = 21, @@ -164,6 +166,19 @@ struct uv_cb_unp { u64 reserved38[3]; } __packed __aligned(8); +#define PV_CPU_STATE_OPR 1 +#define PV_CPU_STATE_STP 2 +#define PV_CPU_STATE_CHKSTP 3 + +struct uv_cb_cpu_set_state { + struct uv_cb_header header; + u64 reserved08[2]; + u64 cpu_handle; + u8 reserved20[7]; + u8 state; + u64 reserved28[5]; +}; + /* * A common UV call struct for calls that take no payload * Examples: diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3fb54ec2cf3e..563429dece03 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -2,7 +2,7 @@ /* * handling diagnose instructions * - * Copyright IBM Corp. 2008, 2011 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte * Christian Borntraeger @@ -201,6 +201,10 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } + /* + * no need to check the return value of vcpu_stop 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_stop(vcpu); vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 6d5e486c82d5..49b4fcf8ba67 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -80,6 +80,10 @@ static int handle_stop(struct kvm_vcpu *vcpu) return rc; } + /* + * no need to check the return value of vcpu_stop 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_stop(vcpu); return -EOPNOTSUPP; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 16531b251eab..80e16bd72d48 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2456,6 +2456,8 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_S390_PV_COMMAND: { struct kvm_pv_cmd args; + /* protvirt means user sigp */ + kvm->arch.user_cpu_state_ctrl = 1; r = 0; if (!is_prot_virt_host()) { r = -EINVAL; @@ -3728,10 +3730,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, 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: case KVM_MP_STATE_CHECK_STOP: @@ -4316,6 +4318,10 @@ 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)) { @@ -4453,18 +4459,27 @@ 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])) started_vcpus++; @@ -4489,22 +4504,31 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) */ 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); + /* 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; + } + } + /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */ kvm_s390_clear_stop_irq(vcpu); @@ -4527,7 +4551,7 @@ 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, diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 13e6986596ed..79dcd647b378 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -217,6 +217,7 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, u16 *rrc); int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, unsigned long tweak, u16 *rc, u16 *rrc); +int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state); static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm) { @@ -330,8 +331,8 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); -void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); -void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); +int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu); bool kvm_s390_vcpu_sie_inhibited(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 13a41533eacf..63e330109b63 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -283,3 +283,21 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, KVM_UV_EVENT(kvm, 3, "%s", "PROTVIRT VM UNPACK: successful"); return ret; } + +int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state) +{ + struct uv_cb_cpu_set_state uvcb = { + .header.cmd = UVC_CMD_CPU_SET_STATE, + .header.len = sizeof(uvcb), + .cpu_handle = kvm_s390_pv_cpu_get_handle(vcpu), + .state = state, + }; + int cc; + + cc = uv_call(0, (u64)&uvcb); + KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT SET CPU %d STATE %d rc %x rrc %x", + vcpu->vcpu_id, state, uvcb.header.rc, uvcb.header.rrc); + if (cc) + return -EINVAL; + return 0; +} -- cgit v1.2.3 From 7c36a3fcf444ced8efc3da106cc7215227d60fde Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Mon, 2 Sep 2019 08:34:44 +0200 Subject: KVM: s390: protvirt: Support cmd 5 operation state Code 5 for the set cpu state UV call tells the UV to load a PSW from the SE header (first IPL) or from guest location 0x0 (diag 308 subcode 0/1). Also it sets the cpu into operating state afterwards, so we can start it. Signed-off-by: Janosch Frank Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/uv.h | 1 + arch/s390/kvm/kvm-s390.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index fc221d91a965..e55727b63a68 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -169,6 +169,7 @@ struct uv_cb_unp { #define PV_CPU_STATE_OPR 1 #define PV_CPU_STATE_STP 2 #define PV_CPU_STATE_CHKSTP 3 +#define PV_CPU_STATE_OPR_LOAD 5 struct uv_cb_cpu_set_state { struct uv_cb_header header; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 80e16bd72d48..028ce4e74393 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3736,6 +3736,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *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 */ default: -- cgit v1.2.3 From 3adae0b4ca64c08a6c05a54be0becf9d127d39dc Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Fri, 13 Dec 2019 08:26:06 -0500 Subject: KVM: s390: protvirt: Mask PSW interrupt bits for interception 104 and 112 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, namely secure instruction interception (104) and secure prefix interception (112). As our PSW is just a copy of the real one that will be replaced on the next exit, we can mask out the interrupt bits in the PSW to make sure that we do not inject anything. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 028ce4e74393..66ba6ca714fb 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4093,6 +4093,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) 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; @@ -4129,6 +4130,16 @@ static int __vcpu_run(struct kvm_vcpu *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); -- cgit v1.2.3 From 72f218208fa63806ebcfca7e793b095d346ee0a4 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 30 Jan 2020 11:18:28 -0500 Subject: KVM: s390: protvirt: do not inject interrupts after start As PSW restart is handled by the ultravisor (and we only get a start notification) we must re-check the PSW after a start before injecting interrupts. Signed-off-by: Christian Borntraeger Reviewed-by: Cornelia Huck Reviewed-by: Thomas Huth Reviewed-by: David Hildenbrand --- arch/s390/kvm/kvm-s390.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 66ba6ca714fb..fed025ea6f62 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4515,6 +4515,13 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) } 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. -- cgit v1.2.3 From 8a8378fa61571eb308428780dee063c4580edb2a Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Thu, 9 Jan 2020 04:37:50 -0500 Subject: KVM: s390: protvirt: Add UV cpu reset calls For protected VMs, the VCPU resets are done by the Ultravisor, as KVM has no access to the VCPU registers. Note that the ultravisor will only accept a call for the exact reset that has been requested. Signed-off-by: Janosch Frank Reviewed-by: Thomas Huth Reviewed-by: David Hildenbrand Reviewed-by: Cornelia Huck [borntraeger@de.ibm.com: patch merging, splitting, fixing] Signed-off-by: Christian Borntraeger --- arch/s390/include/asm/uv.h | 6 ++++++ arch/s390/kvm/kvm-s390.c | 20 ++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index e55727b63a68..cff4b4c99b75 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -36,7 +36,10 @@ #define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300 #define UVC_CMD_UNPACK_IMG 0x0301 #define UVC_CMD_VERIFY_IMG 0x0302 +#define UVC_CMD_CPU_RESET 0x0310 +#define UVC_CMD_CPU_RESET_INITIAL 0x0311 #define UVC_CMD_PREPARE_RESET 0x0320 +#define UVC_CMD_CPU_RESET_CLEAR 0x0321 #define UVC_CMD_CPU_SET_STATE 0x0330 #define UVC_CMD_SET_UNSHARE_ALL 0x0340 #define UVC_CMD_PIN_PAGE_SHARED 0x0341 @@ -59,8 +62,11 @@ enum uv_cmds_inst { BIT_UVC_CMD_SET_SEC_PARMS = 11, BIT_UVC_CMD_UNPACK_IMG = 13, BIT_UVC_CMD_VERIFY_IMG = 14, + BIT_UVC_CMD_CPU_RESET = 15, + BIT_UVC_CMD_CPU_RESET_INITIAL = 16, BIT_UVC_CMD_CPU_SET_STATE = 17, BIT_UVC_CMD_PREPARE_RESET = 18, + BIT_UVC_CMD_CPU_PERFORM_CLEAR_RESET = 19, BIT_UVC_CMD_UNSHARE_ALL = 20, BIT_UVC_CMD_PIN_PAGE_SHARED = 21, BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index fed025ea6f62..bb060064cce0 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4748,6 +4748,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int idx; long r; + u16 rc, rrc; vcpu_load(vcpu); @@ -4769,14 +4770,33 @@ long kvm_arch_vcpu_ioctl(struct file *filp, 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 = 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: { -- cgit v1.2.3 From 13da9ae1cdbf1ec4ea36b7612e606681c27cca13 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 18 Feb 2020 15:08:07 -0500 Subject: KVM: s390: protvirt: introduce and enable KVM_CAP_S390_PROTECTED Now that everything is in place, we can announce the feature. Signed-off-by: Christian Borntraeger Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand --- arch/s390/kvm/kvm-s390.c | 3 +++ include/uapi/linux/kvm.h | 1 + 2 files changed, 4 insertions(+) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bb060064cce0..f4cd436ba979 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -574,6 +574,9 @@ 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: + r = is_prot_virt_host(); + break; default: r = 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2c354ba3a610..2ab168d6d2a8 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1015,6 +1015,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_NISV_TO_USER 177 #define KVM_CAP_ARM_INJECT_EXT_DABT 178 #define KVM_CAP_S390_VCPU_RESETS 179 +#define KVM_CAP_S390_PROTECTED 180 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From cc674ef252f4750bdcea1560ff491081bb960954 Mon Sep 17 00:00:00 2001 From: Michael Mueller Date: Thu, 27 Feb 2020 10:10:31 +0100 Subject: KVM: s390: introduce module parameter kvm.use_gisa The boolean module parameter "kvm.use_gisa" controls if newly created guests will use the GISA facility if provided by the host system. The default is yes. # cat /sys/module/kvm/parameters/use_gisa Y The parameter can be changed on the fly. # echo N > /sys/module/kvm/parameters/use_gisa Already running guests are not affected by this change. The kvm s390 debug feature shows if a guest is running with GISA. # grep gisa /sys/kernel/debug/s390dbf/kvm-$pid/sprintf 00 01582725059:843303 3 - 08 00000000e119bc01 gisa 0x00000000c9ac2642 initialized 00 01582725059:903840 3 - 11 000000004391ee22 00[0000000000000000-0000000000000000]: AIV gisa format-1 enabled for cpu 000 ... 00 01582725059:916847 3 - 08 0000000094fff572 gisa 0x00000000c9ac2642 cleared In general, that value should not be changed as the GISA facility enhances interruption delivery performance. A reason to switch the GISA facility off might be a performance comparison run or debugging. Signed-off-by: Michael Mueller Link: https://lore.kernel.org/r/20200227091031.102993-1-mimu@linux.ibm.com Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/s390/kvm/kvm-s390.c') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f4cd436ba979..6b1842a9feed 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -185,6 +185,11 @@ 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."); + /* * 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 @@ -2732,7 +2737,8 @@ 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); KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); return 0; -- cgit v1.2.3