diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-04-02 15:13:15 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-04-02 15:13:15 -0700 |
commit | 8c1b724ddb218f221612d4c649bc9c7819d8d7a6 (patch) | |
tree | 0e226f4156b554eec2690adb8f30ba54b15b68cc /arch/s390/kvm | |
parent | f14a9532ee30c68a56ff502c382860f674cc180c (diff) | |
parent | 514ccc194971d0649e4e7ec8a9b3a6e33561d7bf (diff) | |
download | linux-stable-8c1b724ddb218f221612d4c649bc9c7819d8d7a6.tar.gz linux-stable-8c1b724ddb218f221612d4c649bc9c7819d8d7a6.tar.bz2 linux-stable-8c1b724ddb218f221612d4c649bc9c7819d8d7a6.zip |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"ARM:
- GICv4.1 support
- 32bit host removal
PPC:
- secure (encrypted) using under the Protected Execution Framework
ultravisor
s390:
- allow disabling GISA (hardware interrupt injection) and protected
VMs/ultravisor support.
x86:
- New dirty bitmap flag that sets all bits in the bitmap when dirty
page logging is enabled; this is faster because it doesn't require
bulk modification of the page tables.
- Initial work on making nested SVM event injection more similar to
VMX, and less buggy.
- Various cleanups to MMU code (though the big ones and related
optimizations were delayed to 5.8). Instead of using cr3 in
function names which occasionally means eptp, KVM too has
standardized on "pgd".
- A large refactoring of CPUID features, which now use an array that
parallels the core x86_features.
- Some removal of pointer chasing from kvm_x86_ops, which will also
be switched to static calls as soon as they are available.
- New Tigerlake CPUID features.
- More bugfixes, optimizations and cleanups.
Generic:
- selftests: cleanups, new MMU notifier stress test, steal-time test
- CSV output for kvm_stat"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (277 commits)
x86/kvm: fix a missing-prototypes "vmread_error"
KVM: x86: Fix BUILD_BUG() in __cpuid_entry_get_reg() w/ CONFIG_UBSAN=y
KVM: VMX: Add a trampoline to fix VMREAD error handling
KVM: SVM: Annotate svm_x86_ops as __initdata
KVM: VMX: Annotate vmx_x86_ops as __initdata
KVM: x86: Drop __exit from kvm_x86_ops' hardware_unsetup()
KVM: x86: Copy kvm_x86_ops by value to eliminate layer of indirection
KVM: x86: Set kvm_x86_ops only after ->hardware_setup() completes
KVM: VMX: Configure runtime hooks using vmx_x86_ops
KVM: VMX: Move hardware_setup() definition below vmx_x86_ops
KVM: x86: Move init-only kvm_x86_ops to separate struct
KVM: Pass kvm_init()'s opaque param to additional arch funcs
s390/gmap: return proper error code on ksm unsharing
KVM: selftests: Fix cosmetic copy-paste error in vm_mem_region_move()
KVM: Fix out of range accesses to memslots
KVM: X86: Micro-optimize IPI fastpath delay
KVM: X86: Delay read msr data iff writes ICR MSR
KVM: PPC: Book3S HV: Add a capability for enabling secure guests
KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs
KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs
...
Diffstat (limited to 'arch/s390/kvm')
-rw-r--r-- | arch/s390/kvm/Makefile | 2 | ||||
-rw-r--r-- | arch/s390/kvm/diag.c | 6 | ||||
-rw-r--r-- | arch/s390/kvm/gaccess.c | 23 | ||||
-rw-r--r-- | arch/s390/kvm/intercept.c | 123 | ||||
-rw-r--r-- | arch/s390/kvm/interrupt.c | 401 | ||||
-rw-r--r-- | arch/s390/kvm/kvm-s390.c | 597 | ||||
-rw-r--r-- | arch/s390/kvm/kvm-s390.h | 51 | ||||
-rw-r--r-- | arch/s390/kvm/priv.c | 13 | ||||
-rw-r--r-- | arch/s390/kvm/pv.c | 303 |
9 files changed, 1237 insertions, 282 deletions
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/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 <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -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/gaccess.c b/arch/s390/kvm/gaccess.c index 07d30ffcfa41..47a67a958107 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -505,7 +505,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, switch (prot) { case PROT_TYPE_IEP: tec->b61 = 1; - /* FALL THROUGH */ + fallthrough; case PROT_TYPE_LA: tec->b56 = 1; break; @@ -514,12 +514,12 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, break; case PROT_TYPE_ALC: tec->b60 = 1; - /* FALL THROUGH */ + fallthrough; case PROT_TYPE_DAT: tec->b61 = 1; break; } - /* FALL THROUGH */ + fallthrough; case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: case PGM_REGION_FIRST_TRANS: @@ -534,7 +534,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, tec->addr = gva >> PAGE_SHIFT; tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH; tec->as = psw_bits(vcpu->arch.sie_block->gpsw).as; - /* FALL THROUGH */ + fallthrough; case PGM_ALEN_TRANSLATION: case PGM_ALE_SEQUENCE: case PGM_ASTE_VALIDITY: @@ -677,7 +677,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rfte.p; ptr = rfte.rto * PAGE_SIZE + vaddr.rsx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_REGION2: { union region2_table_entry rste; @@ -695,7 +695,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rste.p; ptr = rste.rto * PAGE_SIZE + vaddr.rtx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_REGION3: { union region3_table_entry rtte; @@ -723,7 +723,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, dat_protection |= rtte.fc0.p; ptr = rtte.fc0.sto * PAGE_SIZE + vaddr.sx * 8; } - /* fallthrough */ + fallthrough; case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; @@ -1050,7 +1050,8 @@ shadow_r2t: rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_REGION2: { union region2_table_entry rste; @@ -1076,7 +1077,8 @@ shadow_r3t: rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_REGION3: { union region3_table_entry rtte; @@ -1111,7 +1113,8 @@ shadow_sgt: rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake); if (rc) return rc; - } /* fallthrough */ + } + fallthrough; case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index a389fa85cca2..e7a7c499a73f 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -2,7 +2,7 @@ /* * in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008, 2014 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -12,10 +12,10 @@ #include <linux/errno.h> #include <linux/pagemap.h> -#include <asm/kvm_host.h> #include <asm/asm-offsets.h> #include <asm/irq.h> #include <asm/sysinfo.h> +#include <asm/uv.h> #include "kvm-s390.h" #include "gaccess.h" @@ -79,6 +79,10 @@ 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; @@ -231,6 +235,13 @@ static int handle_prog(struct kvm_vcpu *vcpu) vcpu->stat.exit_program_interruption++; + /* + * Intercept 8 indicates a loop of specification exceptions + * for protected guests. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return -EOPNOTSUPP; + if (guestdbg_enabled(vcpu) && per_event(vcpu)) { rc = kvm_s390_handle_per_event(vcpu); if (rc) @@ -384,7 +395,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu) goto out; } - if (addr & ~PAGE_MASK) + if (!kvm_s390_pv_cpu_is_protected(vcpu) && (addr & ~PAGE_MASK)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); sctns = (void *)get_zeroed_page(GFP_KERNEL); @@ -395,10 +406,15 @@ int handle_sthyi(struct kvm_vcpu *vcpu) out: if (!cc) { - r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE); - if (r) { - free_page((unsigned long)sctns); - return kvm_s390_inject_prog_cond(vcpu, r); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy((void *)(sida_origin(vcpu->arch.sie_block)), + sctns, PAGE_SIZE); + } else { + r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE); + if (r) { + free_page((unsigned long)sctns); + return kvm_s390_inject_prog_cond(vcpu, r); + } } } @@ -444,6 +460,77 @@ static int handle_operexc(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); } +static int handle_pv_spx(struct kvm_vcpu *vcpu) +{ + u32 pref = *(u32 *)vcpu->arch.sie_block->sidad; + + kvm_s390_set_prefix(vcpu, pref); + trace_kvm_s390_handle_prefix(vcpu, 1, pref); + return 0; +} + +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_uvc(struct kvm_vcpu *vcpu) +{ + struct uv_cb_share *guest_uvcb = (void *)vcpu->arch.sie_block->sidad; + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_UNPIN_PAGE_SHARED, + .header.len = sizeof(uvcb), + .guest_handle = kvm_s390_pv_get_handle(vcpu->kvm), + .gaddr = guest_uvcb->paddr, + }; + int rc; + + if (guest_uvcb->header.cmd != UVC_CMD_REMOVE_SHARED_ACCESS) { + WARN_ONCE(1, "Unexpected notification intercept for UVC 0x%x\n", + guest_uvcb->header.cmd); + return 0; + } + rc = gmap_make_secure(vcpu->arch.gmap, uvcb.gaddr, &uvcb); + /* + * If the unpin did not succeed, the guest will exit again for the UVC + * and we will retry the unpin. + */ + if (rc == -EINVAL) + return 0; + return rc; +} + +static int handle_pv_notification(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sie_block->ipa == 0xb210) + return handle_pv_spx(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb220) + return handle_pv_sclp(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb9a4) + return handle_pv_uvc(vcpu); + + return handle_instruction(vcpu); +} + int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) { int rc, per_rc = 0; @@ -480,6 +567,28 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) case ICPT_KSS: rc = kvm_s390_skey_check_enable(vcpu); break; + case ICPT_MCHKREQ: + case ICPT_INT_ENABLE: + /* + * PSW bit 13 or a CR (0, 6, 14) changed and we might + * now be able to deliver interrupts. The pre-run code + * will take care of this. + */ + rc = 0; + break; + case ICPT_PV_INSTR: + rc = handle_instruction(vcpu); + break; + case ICPT_PV_NOTIFY: + rc = handle_pv_notification(vcpu); + break; + case ICPT_PV_PREF: + rc = 0; + gmap_convert_to_secure(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu)); + gmap_convert_to_secure(vcpu->arch.gmap, + kvm_s390_get_prefix(vcpu) + PAGE_SIZE); + break; default: return -EOPNOTSUPP; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c06c89d370a7..8191106bf7b9 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2,7 +2,7 @@ /* * handling kvm guest interrupts * - * Copyright IBM Corp. 2008, 2015 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> */ @@ -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) @@ -383,10 +386,18 @@ 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. */ + if (kvm_s390_pv_cpu_is_protected(vcpu) && + vcpu->arch.sie_block->iictl != IICTL_CODE_NONE) + active_mask &= ~(IRQ_PEND_EXT_II_MASK | + IRQ_PEND_IO_MASK | + IRQ_PEND_MCHK_MASK); /* * Check both floating and local interrupt's cr14 because * bit IRQ_PEND_MCHK_REP could be set in both cases. @@ -479,19 +490,23 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu) static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; vcpu->stat.deliver_cputm++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER, 0, 0); - - rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, - (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_CPU_TIMER; + } else { + rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -499,19 +514,23 @@ static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; vcpu->stat.deliver_ckc++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP, 0, 0); - - rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, - (u16 __user *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_CLK_COMP; + } else { + rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, + (u16 __user *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -553,6 +572,20 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, union mci mci; int rc; + /* + * All other possible payload for a machine check (e.g. the register + * contents in the save area) will be handled by the ultravisor, as + * the hypervisor does not not have the needed information for + * protected guests. + */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_MCHK; + vcpu->arch.sie_block->mcic = mchk->mcic; + vcpu->arch.sie_block->faddr = mchk->failing_storage_address; + vcpu->arch.sie_block->edc = mchk->ext_damage_code; + return 0; + } + mci.val = mchk->mcic; /* take care of lazy register loading */ save_fpu_regs(); @@ -696,17 +729,21 @@ static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - int rc; + int rc = 0; VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart"); vcpu->stat.deliver_restart_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0); - rc = write_guest_lc(vcpu, - offsetof(struct lowcore, restart_old_psw), - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw), - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_RESTART; + } else { + rc = write_guest_lc(vcpu, + offsetof(struct lowcore, restart_old_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + } clear_bit(IRQ_PEND_RESTART, &li->pending_irqs); return rc ? -EFAULT : 0; } @@ -748,6 +785,12 @@ static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu) vcpu->stat.deliver_emergency_signal++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, cpu_addr, 0); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_EMERGENCY_SIG; + vcpu->arch.sie_block->extcpuaddr = cpu_addr; + return 0; + } rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG, (u16 *)__LC_EXT_INT_CODE); @@ -776,6 +819,12 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL, extcall.code, 0); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_EXT; + vcpu->arch.sie_block->eic = EXT_IRQ_EXTERNAL_CALL; + vcpu->arch.sie_block->extcpuaddr = extcall.code; + return 0; + } rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL, (u16 *)__LC_EXT_INT_CODE); @@ -787,6 +836,21 @@ static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +static int __deliver_prog_pv(struct kvm_vcpu *vcpu, u16 code) +{ + switch (code) { + case PGM_SPECIFICATION: + vcpu->arch.sie_block->iictl = IICTL_CODE_SPECIFICATION; + break; + case PGM_OPERAND: + vcpu->arch.sie_block->iictl = IICTL_CODE_OPERAND; + break; + default: + return -EINVAL; + } + return 0; +} + static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -807,6 +871,10 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, pgm_info.code, 0); + /* PER is handled by the ultravisor */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) + return __deliver_prog_pv(vcpu, pgm_info.code & ~PGM_PER); + switch (pgm_info.code & ~PGM_PER) { case PGM_AFX_TRANSLATION: case PGM_ASX_TRANSLATION: @@ -818,7 +886,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: nullifying = true; - /* fall through */ + fallthrough; case PGM_SPACE_SWITCH: rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); @@ -902,20 +970,49 @@ 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", @@ -924,16 +1021,31 @@ 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) @@ -1028,6 +1140,15 @@ static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io) { int rc; + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + vcpu->arch.sie_block->iictl = IICTL_CODE_IO; + vcpu->arch.sie_block->subchannel_id = io->subchannel_id; + vcpu->arch.sie_block->subchannel_nr = io->subchannel_nr; + vcpu->arch.sie_block->io_int_parm = io->io_int_parm; + vcpu->arch.sie_block->io_int_word = io->io_int_word; + return 0; + } + rc = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID); rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR); rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM); @@ -1329,6 +1450,9 @@ 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; @@ -1421,7 +1545,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL) return -EINVAL; - if (sclp.has_sigpif) + if (sclp.has_sigpif && !kvm_s390_pv_cpu_get_handle(vcpu)) return sca_inject_ext_call(vcpu, src_id); if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) @@ -1681,9 +1805,6 @@ 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) { @@ -1692,6 +1813,11 @@ 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 @@ -1773,7 +1899,14 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) kvm->stat.inject_io++; isc = int_word_to_isc(inti->io.io_int_word); - if (gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) { + /* + * Do not make use of gisa in protected mode. We do not use the lock + * checking variant as this is just a performance optimization and we + * do not hold the lock here. This is ok as the code will pick + * interrupts from both "lists" for delivery. + */ + if (!kvm_s390_pv_get_handle(kvm) && + gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) { VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc); gisa_set_ipm_gisc(gi->origin, isc); kfree(inti); @@ -1834,7 +1967,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: if (!(type & KVM_S390_INT_IO_AI_MASK && - kvm->arch.gisa_int.origin)) + kvm->arch.gisa_int.origin) || + kvm_s390_pv_cpu_get_handle(dst_vcpu)) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: @@ -2080,6 +2214,10 @@ 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)); @@ -2146,7 +2284,8 @@ 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; @@ -2327,9 +2466,6 @@ static int register_io_adapter(struct kvm_device *dev, if (!adapter) return -ENOMEM; - INIT_LIST_HEAD(&adapter->maps); - init_rwsem(&adapter->maps_lock); - atomic_set(&adapter->nr_maps, 0); adapter->id = adapter_info.id; adapter->isc = adapter_info.isc; adapter->maskable = adapter_info.maskable; @@ -2354,87 +2490,12 @@ int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked) return ret; } -static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr) -{ - struct s390_io_adapter *adapter = get_io_adapter(kvm, id); - struct s390_map_info *map; - int ret; - - if (!adapter || !addr) - return -EINVAL; - - map = kzalloc(sizeof(*map), GFP_KERNEL); - if (!map) { - ret = -ENOMEM; - goto out; - } - INIT_LIST_HEAD(&map->list); - map->guest_addr = addr; - map->addr = gmap_translate(kvm->arch.gmap, addr); - if (map->addr == -EFAULT) { - ret = -EFAULT; - goto out; - } - ret = get_user_pages_fast(map->addr, 1, FOLL_WRITE, &map->page); - if (ret < 0) - goto out; - BUG_ON(ret != 1); - down_write(&adapter->maps_lock); - if (atomic_inc_return(&adapter->nr_maps) < MAX_S390_ADAPTER_MAPS) { - list_add_tail(&map->list, &adapter->maps); - ret = 0; - } else { - put_page(map->page); - ret = -EINVAL; - } - up_write(&adapter->maps_lock); -out: - if (ret) - kfree(map); - return ret; -} - -static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr) -{ - struct s390_io_adapter *adapter = get_io_adapter(kvm, id); - struct s390_map_info *map, *tmp; - int found = 0; - - if (!adapter || !addr) - return -EINVAL; - - down_write(&adapter->maps_lock); - list_for_each_entry_safe(map, tmp, &adapter->maps, list) { - if (map->guest_addr == addr) { - found = 1; - atomic_dec(&adapter->nr_maps); - list_del(&map->list); - put_page(map->page); - kfree(map); - break; - } - } - up_write(&adapter->maps_lock); - - return found ? 0 : -EINVAL; -} - void kvm_s390_destroy_adapters(struct kvm *kvm) { int i; - struct s390_map_info *map, *tmp; - for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) { - if (!kvm->arch.adapters[i]) - continue; - list_for_each_entry_safe(map, tmp, - &kvm->arch.adapters[i]->maps, list) { - list_del(&map->list); - put_page(map->page); - kfree(map); - } + for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) kfree(kvm->arch.adapters[i]); - } } static int modify_io_adapter(struct kvm_device *dev, @@ -2456,11 +2517,14 @@ static int modify_io_adapter(struct kvm_device *dev, if (ret > 0) ret = 0; break; + /* + * The following operations are no longer needed and therefore no-ops. + * The gpa to hva translation is done when an IRQ route is set up. The + * set_irq code uses get_user_pages_remote() to do the actual write. + */ case KVM_S390_IO_ADAPTER_MAP: - ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr); - break; case KVM_S390_IO_ADAPTER_UNMAP: - ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr); + ret = 0; break; default: ret = -EINVAL; @@ -2699,19 +2763,15 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit; } -static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter, - u64 addr) +static struct page *get_map_page(struct kvm *kvm, u64 uaddr) { - struct s390_map_info *map; + struct page *page = NULL; - if (!adapter) - return NULL; - - list_for_each_entry(map, &adapter->maps, list) { - if (map->guest_addr == addr) - return map; - } - return NULL; + down_read(&kvm->mm->mmap_sem); + get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE, + &page, NULL, NULL); + up_read(&kvm->mm->mmap_sem); + return page; } static int adapter_indicators_set(struct kvm *kvm, @@ -2720,30 +2780,35 @@ static int adapter_indicators_set(struct kvm *kvm, { unsigned long bit; int summary_set, idx; - struct s390_map_info *info; + struct page *ind_page, *summary_page; void *map; - info = get_map_info(adapter, adapter_int->ind_addr); - if (!info) + ind_page = get_map_page(kvm, adapter_int->ind_addr); + if (!ind_page) return -1; - map = page_address(info->page); - bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap); - set_bit(bit, map); - idx = srcu_read_lock(&kvm->srcu); - mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); - set_page_dirty_lock(info->page); - info = get_map_info(adapter, adapter_int->summary_addr); - if (!info) { - srcu_read_unlock(&kvm->srcu, idx); + summary_page = get_map_page(kvm, adapter_int->summary_addr); + if (!summary_page) { + put_page(ind_page); return -1; } - map = page_address(info->page); - bit = get_ind_bit(info->addr, adapter_int->summary_offset, - adapter->swap); + + idx = srcu_read_lock(&kvm->srcu); + map = page_address(ind_page); + bit = get_ind_bit(adapter_int->ind_addr, + adapter_int->ind_offset, adapter->swap); + set_bit(bit, map); + mark_page_dirty(kvm, adapter_int->ind_addr >> PAGE_SHIFT); + set_page_dirty_lock(ind_page); + map = page_address(summary_page); + bit = get_ind_bit(adapter_int->summary_addr, + adapter_int->summary_offset, adapter->swap); summary_set = test_and_set_bit(bit, map); - mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT); - set_page_dirty_lock(info->page); + mark_page_dirty(kvm, adapter_int->summary_addr >> PAGE_SHIFT); + set_page_dirty_lock(summary_page); srcu_read_unlock(&kvm->srcu, idx); + + put_page(ind_page); + put_page(summary_page); return summary_set ? 0 : 1; } @@ -2765,9 +2830,7 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e, adapter = get_io_adapter(kvm, e->adapter.adapter_id); if (!adapter) return -1; - down_read(&adapter->maps_lock); ret = adapter_indicators_set(kvm, adapter, &e->adapter); - up_read(&adapter->maps_lock); if ((ret > 0) && !adapter->masked) { ret = kvm_s390_inject_airq(kvm, adapter); if (ret == 0) @@ -2818,23 +2881,27 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { - int ret; + u64 uaddr; switch (ue->type) { + /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: e->set = set_adapter_int; - e->adapter.summary_addr = ue->u.adapter.summary_addr; - e->adapter.ind_addr = ue->u.adapter.ind_addr; + uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); + if (uaddr == -EFAULT) + return -EFAULT; + e->adapter.summary_addr = uaddr; + uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr); + if (uaddr == -EFAULT) + return -EFAULT; + e->adapter.ind_addr = uaddr; e->adapter.summary_offset = ue->u.adapter.summary_offset; e->adapter.ind_offset = ue->u.adapter.ind_offset; e->adapter.adapter_id = ue->u.adapter.adapter_id; - ret = 0; - break; + return 0; default: - ret = -EINVAL; + return -EINVAL; } - - return ret; } int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c2e6d4ba4e23..19a81024fe16 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 <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -44,6 +44,7 @@ #include <asm/cpacf.h> #include <asm/timex.h> #include <asm/ap.h> +#include <asm/uv.h> #include "kvm-s390.h" #include "gaccess.h" @@ -184,6 +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 @@ -220,6 +226,7 @@ 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) @@ -228,13 +235,15 @@ int kvm_arch_hardware_enable(void) return 0; } -int kvm_arch_check_processor_compat(void) +int kvm_arch_check_processor_compat(void *opaque) { 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) { @@ -293,7 +302,7 @@ static struct notifier_block kvm_clock_notifier = { .notifier_call = kvm_clock_sync, }; -int kvm_arch_hardware_setup(void) +int kvm_arch_hardware_setup(void *opaque) { gmap_notifier.notifier_call = kvm_gmap_notifier; gmap_register_pte_notifier(&gmap_notifier); @@ -460,7 +469,12 @@ 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 +501,7 @@ void kvm_arch_exit(void) { kvm_s390_gib_destroy(); debug_unregister(kvm_s390_dbf); + debug_unregister(kvm_s390_dbf_uv); } /* Section: device related */ @@ -564,14 +579,16 @@ 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; } 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; @@ -612,9 +629,8 @@ 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; @@ -625,14 +641,7 @@ 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; @@ -1993,6 +2002,9 @@ 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(!slots->used_slots)) + return 0; + cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); ms = gfn_to_memslot(kvm, cur_gfn); args->count = 0; @@ -2158,6 +2170,194 @@ 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; + + 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; + + 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: { + 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); + + /* 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)) + 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; + } + default: + r = -ENOTTY; + } + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2255,6 +2455,33 @@ 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 sigp */ + kvm->arch.user_cpu_state_ctrl = 1; + 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; } @@ -2504,7 +2731,8 @@ 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; @@ -2518,6 +2746,8 @@ 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); @@ -2530,6 +2760,9 @@ 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)); } @@ -2551,10 +2784,20 @@ 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); @@ -2650,6 +2893,9 @@ 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; @@ -2901,6 +3147,7 @@ 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 | @@ -2968,6 +3215,14 @@ 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; } @@ -3277,7 +3532,6 @@ 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; @@ -3295,9 +3549,17 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) vcpu->run->s.regs.pp = 0; vcpu->run->s.regs.gbea = 1; 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) @@ -3487,14 +3749,20 @@ 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: + 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; } @@ -3844,9 +4112,11 @@ 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; + 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- @@ -3868,8 +4138,28 @@ 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)); + /* + * 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(); @@ -3883,7 +4173,7 @@ 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; @@ -3892,16 +4182,7 @@ 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; @@ -3942,6 +4223,36 @@ 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 */ @@ -3956,23 +4267,47 @@ 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) @@ -3983,13 +4318,9 @@ 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 */ @@ -3998,19 +4329,8 @@ 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) @@ -4034,6 +4354,10 @@ 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)) { @@ -4171,18 +4495,27 @@ 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++; @@ -4202,27 +4535,43 @@ void 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. */ 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); @@ -4245,7 +4594,7 @@ 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, @@ -4272,12 +4621,40 @@ 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; @@ -4287,14 +4664,15 @@ 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) { @@ -4320,12 +4698,8 @@ 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); @@ -4333,6 +4707,31 @@ 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) { @@ -4368,6 +4767,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int idx; long r; + u16 rc, rrc; vcpu_load(vcpu); @@ -4389,18 +4789,40 @@ 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: { 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; @@ -4463,7 +4885,7 @@ 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; @@ -4523,12 +4945,6 @@ 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) -{ - return 0; -} - /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -4549,12 +4965,15 @@ 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; } 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) { @@ -4570,7 +4989,7 @@ 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); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 6d9448dbd052..79dcd647b378 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -2,7 +2,7 @@ /* * definition for kvm on s390 * - * Copyright IBM Corp. 2008, 2009 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -15,6 +15,7 @@ #include <linux/hrtimer.h> #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <linux/lockdep.h> #include <asm/facility.h> #include <asm/processor.h> #include <asm/sclp.h> @@ -25,6 +26,17 @@ #define IS_ITDB_VALID(vcpu) ((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1)) extern debug_info_t *kvm_s390_dbf; +extern debug_info_t *kvm_s390_dbf_uv; + +#define KVM_UV_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ +do { \ + debug_sprintf_event((d_kvm)->arch.dbf, d_loglevel, d_string "\n", \ + d_args); \ + debug_sprintf_event(kvm_s390_dbf_uv, d_loglevel, \ + "%d: " d_string "\n", (d_kvm)->userspace_pid, \ + d_args); \ +} while (0) + #define KVM_EVENT(d_loglevel, d_string, d_args...)\ do { \ debug_sprintf_event(kvm_s390_dbf, d_loglevel, d_string "\n", \ @@ -196,6 +208,39 @@ 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); +int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state); + +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); @@ -286,8 +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/priv.c b/arch/s390/kvm/priv.c index ed52ffa8d5d4..69a824f9ef0b 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -2,7 +2,7 @@ /* * handling privileged instructions * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -872,7 +872,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); - if (operand2 & 0xfff) + if (!kvm_s390_pv_cpu_is_protected(vcpu) && (operand2 & 0xfff)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); switch (fc) { @@ -893,8 +893,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu) handle_stsi_3_2_2(vcpu, (void *) mem); break; } - - rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy((void *)sida_origin(vcpu->arch.sie_block), (void *)mem, + PAGE_SIZE); + rc = 0; + } else { + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); + } if (rc) { rc = kvm_s390_inject_prog_cond(vcpu, rc); goto out; diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c new file mode 100644 index 000000000000..63e330109b63 --- /dev/null +++ b/arch/s390/kvm/pv.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hosting Protected Virtual Machines + * + * Copyright IBM Corp. 2019, 2020 + * Author(s): Janosch Frank <frankja@linux.ibm.com> + */ +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pagemap.h> +#include <linux/sched/signal.h> +#include <asm/pgalloc.h> +#include <asm/gmap.h> +#include <asm/uv.h> +#include <asm/mman.h> +#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)); + + 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; +} + +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; + + /* 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; + 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; + + /* make all pages accessible before destroying the guest */ + s390_reset_acc(kvm->mm); + + 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; +} + +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; +} |