diff options
Diffstat (limited to 'arch/s390/kvm')
| -rw-r--r-- | arch/s390/kvm/Kconfig | 1 | ||||
| -rw-r--r-- | arch/s390/kvm/Makefile | 2 | ||||
| -rw-r--r-- | arch/s390/kvm/diag.c | 4 | ||||
| -rw-r--r-- | arch/s390/kvm/gaccess.c | 246 | ||||
| -rw-r--r-- | arch/s390/kvm/gaccess.h | 14 | ||||
| -rw-r--r-- | arch/s390/kvm/gmap-vsie.c | 142 | ||||
| -rw-r--r-- | arch/s390/kvm/gmap.c | 121 | ||||
| -rw-r--r-- | arch/s390/kvm/gmap.h | 39 | ||||
| -rw-r--r-- | arch/s390/kvm/intercept.c | 7 | ||||
| -rw-r--r-- | arch/s390/kvm/interrupt.c | 60 | ||||
| -rw-r--r-- | arch/s390/kvm/kvm-s390.c | 463 | ||||
| -rw-r--r-- | arch/s390/kvm/kvm-s390.h | 67 | ||||
| -rw-r--r-- | arch/s390/kvm/pci.c | 7 | ||||
| -rw-r--r-- | arch/s390/kvm/priv.c | 36 | ||||
| -rw-r--r-- | arch/s390/kvm/pv.c | 21 | ||||
| -rw-r--r-- | arch/s390/kvm/sigp.c | 2 | ||||
| -rw-r--r-- | arch/s390/kvm/vsie.c | 164 |
17 files changed, 1003 insertions, 393 deletions
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 72e9b7dcdf7d..cae908d64550 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -19,7 +19,6 @@ if VIRTUALIZATION config KVM def_tristate y prompt "Kernel-based Virtual Machine (KVM) support" - depends on HAVE_KVM select HAVE_KVM_CPU_RELAX_INTERCEPT select HAVE_KVM_VCPU_ASYNC_IOCTL select KVM_ASYNC_PF diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 02217fb4ae10..f0ffe874adc2 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -8,7 +8,7 @@ include $(srctree)/virt/kvm/Makefile.kvm ccflags-y := -Ivirt/kvm -Iarch/s390/kvm kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o +kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap.o gmap-vsie.o kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3c65b8258ae6..74f73141f9b9 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) vcpu->stat.instruction_diagnose_258++; if (vcpu->run->s.regs.gprs[rx] & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); + rc = read_guest_real(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258) @@ -102,7 +102,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - if (kvm_is_error_gpa(vcpu->kvm, parm.token_addr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, parm.token_addr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); vcpu->arch.pfault_token = parm.token_addr; diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 5bfcc50c1a68..f6fded15633a 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -11,169 +11,13 @@ #include <linux/err.h> #include <linux/pgtable.h> #include <linux/bitfield.h> +#include <asm/access-regs.h> #include <asm/fault.h> #include <asm/gmap.h> +#include <asm/dat-bits.h> #include "kvm-s390.h" +#include "gmap.h" #include "gaccess.h" -#include <asm/switch_to.h> - -union asce { - unsigned long val; - struct { - unsigned long origin : 52; /* Region- or Segment-Table Origin */ - unsigned long : 2; - unsigned long g : 1; /* Subspace Group Control */ - unsigned long p : 1; /* Private Space Control */ - unsigned long s : 1; /* Storage-Alteration-Event Control */ - unsigned long x : 1; /* Space-Switch-Event Control */ - unsigned long r : 1; /* Real-Space Control */ - unsigned long : 1; - unsigned long dt : 2; /* Designation-Type Control */ - unsigned long tl : 2; /* Region- or Segment-Table Length */ - }; -}; - -enum { - ASCE_TYPE_SEGMENT = 0, - ASCE_TYPE_REGION3 = 1, - ASCE_TYPE_REGION2 = 2, - ASCE_TYPE_REGION1 = 3 -}; - -union region1_table_entry { - unsigned long val; - struct { - unsigned long rto: 52;/* Region-Table Origin */ - unsigned long : 2; - unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long : 1; - unsigned long tf : 2; /* Region-Second-Table Offset */ - unsigned long i : 1; /* Region-Invalid Bit */ - unsigned long : 1; - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long tl : 2; /* Region-Second-Table Length */ - }; -}; - -union region2_table_entry { - unsigned long val; - struct { - unsigned long rto: 52;/* Region-Table Origin */ - unsigned long : 2; - unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long : 1; - unsigned long tf : 2; /* Region-Third-Table Offset */ - unsigned long i : 1; /* Region-Invalid Bit */ - unsigned long : 1; - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long tl : 2; /* Region-Third-Table Length */ - }; -}; - -struct region3_table_entry_fc0 { - unsigned long sto: 52;/* Segment-Table Origin */ - unsigned long : 1; - unsigned long fc : 1; /* Format-Control */ - unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long : 1; - unsigned long tf : 2; /* Segment-Table Offset */ - unsigned long i : 1; /* Region-Invalid Bit */ - unsigned long cr : 1; /* Common-Region Bit */ - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long tl : 2; /* Segment-Table Length */ -}; - -struct region3_table_entry_fc1 { - unsigned long rfaa : 33; /* Region-Frame Absolute Address */ - unsigned long : 14; - unsigned long av : 1; /* ACCF-Validity Control */ - unsigned long acc: 4; /* Access-Control Bits */ - unsigned long f : 1; /* Fetch-Protection Bit */ - unsigned long fc : 1; /* Format-Control */ - unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long iep: 1; /* Instruction-Execution-Protection */ - unsigned long : 2; - unsigned long i : 1; /* Region-Invalid Bit */ - unsigned long cr : 1; /* Common-Region Bit */ - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long : 2; -}; - -union region3_table_entry { - unsigned long val; - struct region3_table_entry_fc0 fc0; - struct region3_table_entry_fc1 fc1; - struct { - unsigned long : 53; - unsigned long fc : 1; /* Format-Control */ - unsigned long : 4; - unsigned long i : 1; /* Region-Invalid Bit */ - unsigned long cr : 1; /* Common-Region Bit */ - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long : 2; - }; -}; - -struct segment_entry_fc0 { - unsigned long pto: 53;/* Page-Table Origin */ - unsigned long fc : 1; /* Format-Control */ - unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long : 3; - unsigned long i : 1; /* Segment-Invalid Bit */ - unsigned long cs : 1; /* Common-Segment Bit */ - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long : 2; -}; - -struct segment_entry_fc1 { - unsigned long sfaa : 44; /* Segment-Frame Absolute Address */ - unsigned long : 3; - unsigned long av : 1; /* ACCF-Validity Control */ - unsigned long acc: 4; /* Access-Control Bits */ - unsigned long f : 1; /* Fetch-Protection Bit */ - unsigned long fc : 1; /* Format-Control */ - unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long iep: 1; /* Instruction-Execution-Protection */ - unsigned long : 2; - unsigned long i : 1; /* Segment-Invalid Bit */ - unsigned long cs : 1; /* Common-Segment Bit */ - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long : 2; -}; - -union segment_table_entry { - unsigned long val; - struct segment_entry_fc0 fc0; - struct segment_entry_fc1 fc1; - struct { - unsigned long : 53; - unsigned long fc : 1; /* Format-Control */ - unsigned long : 4; - unsigned long i : 1; /* Segment-Invalid Bit */ - unsigned long cs : 1; /* Common-Segment Bit */ - unsigned long tt : 2; /* Table-Type Bits */ - unsigned long : 2; - }; -}; - -enum { - TABLE_TYPE_SEGMENT = 0, - TABLE_TYPE_REGION3 = 1, - TABLE_TYPE_REGION2 = 2, - TABLE_TYPE_REGION1 = 3 -}; - -union page_table_entry { - unsigned long val; - struct { - unsigned long pfra : 52; /* Page-Frame Real Address */ - unsigned long z : 1; /* Zero Bit */ - unsigned long i : 1; /* Page-Invalid Bit */ - unsigned long p : 1; /* DAT-Protection Bit */ - unsigned long iep: 1; /* Instruction-Execution-Protection */ - unsigned long : 8; - }; -}; /* * vaddress union in order to easily decode a virtual address into its @@ -286,8 +130,8 @@ static void ipte_lock_simple(struct kvm *kvm) retry: read_lock(&kvm->arch.sca_lock); ic = kvm_s390_get_ipte_control(kvm); + old = READ_ONCE(*ic); do { - old = READ_ONCE(*ic); if (old.k) { read_unlock(&kvm->arch.sca_lock); cond_resched(); @@ -295,7 +139,7 @@ retry: } new = old; new.k = 1; - } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + } while (!try_cmpxchg(&ic->val, &old.val, new.val)); read_unlock(&kvm->arch.sca_lock); out: mutex_unlock(&kvm->arch.ipte_mutex); @@ -311,11 +155,11 @@ static void ipte_unlock_simple(struct kvm *kvm) goto out; read_lock(&kvm->arch.sca_lock); ic = kvm_s390_get_ipte_control(kvm); + old = READ_ONCE(*ic); do { - old = READ_ONCE(*ic); new = old; new.k = 0; - } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + } while (!try_cmpxchg(&ic->val, &old.val, new.val)); read_unlock(&kvm->arch.sca_lock); wake_up(&kvm->arch.ipte_wq); out: @@ -329,8 +173,8 @@ static void ipte_lock_siif(struct kvm *kvm) retry: read_lock(&kvm->arch.sca_lock); ic = kvm_s390_get_ipte_control(kvm); + old = READ_ONCE(*ic); do { - old = READ_ONCE(*ic); if (old.kg) { read_unlock(&kvm->arch.sca_lock); cond_resched(); @@ -339,7 +183,7 @@ retry: new = old; new.k = 1; new.kh++; - } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + } while (!try_cmpxchg(&ic->val, &old.val, new.val)); read_unlock(&kvm->arch.sca_lock); } @@ -349,13 +193,13 @@ static void ipte_unlock_siif(struct kvm *kvm) read_lock(&kvm->arch.sca_lock); ic = kvm_s390_get_ipte_control(kvm); + old = READ_ONCE(*ic); do { - old = READ_ONCE(*ic); new = old; new.kh--; if (!new.kh) new.k = 0; - } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + } while (!try_cmpxchg(&ic->val, &old.val, new.val)); read_unlock(&kvm->arch.sca_lock); if (!new.kh) wake_up(&kvm->arch.ipte_wq); @@ -391,7 +235,8 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar, if (ar >= NUM_ACRS) return -EINVAL; - save_access_regs(vcpu->run->s.regs.acrs); + if (vcpu->arch.acrs_loaded) + save_access_regs(vcpu->run->s.regs.acrs); alet.val = vcpu->run->s.regs.acrs[ar]; if (ar == 0 || alet.val == 0) { @@ -631,7 +476,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, iep = ctlreg0.iep && test_kvm_facility(vcpu->kvm, 130); if (asce.r) goto real_address; - ptr = asce.origin * PAGE_SIZE; + ptr = asce.rsto * PAGE_SIZE; switch (asce.dt) { case ASCE_TYPE_REGION1: if (vaddr.rfx01 > asce.tl) @@ -664,7 +509,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_REGION1: { union region1_table_entry rfte; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &rfte.val)) return -EFAULT; @@ -682,7 +527,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_REGION2: { union region2_table_entry rste; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &rste.val)) return -EFAULT; @@ -700,7 +545,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_REGION3: { union region3_table_entry rtte; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &rtte.val)) return -EFAULT; @@ -728,7 +573,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &ste.val)) return -EFAULT; @@ -748,7 +593,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, ptr = ste.fc0.pto * (PAGE_SIZE / 2) + vaddr.px * 8; } } - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &pte.val)) return -EFAULT; @@ -770,7 +615,7 @@ absolute_address: *prot = PROT_TYPE_IEP; return PGM_PROTECTION; } - if (kvm_is_error_gpa(vcpu->kvm, raddr.addr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, raddr.addr)) return PGM_ADDRESSING; *gpa = raddr.addr; return 0; @@ -957,7 +802,7 @@ static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, return rc; } else { gpa = kvm_s390_real_to_abs(vcpu, ga); - if (kvm_is_error_gpa(vcpu->kvm, gpa)) { + if (!kvm_is_gpa_in_memslot(vcpu->kvm, gpa)) { rc = PGM_ADDRESSING; prot = PROT_NONE; } @@ -984,6 +829,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, const gfn_t gfn = gpa_to_gfn(gpa); int rc; + if (!gfn_to_memslot(kvm, gfn)) + return PGM_ADDRESSING; if (mode == GACC_STORE) rc = kvm_write_guest_page(kvm, gfn, data, offset, len); else @@ -1141,6 +988,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, gra += fragment_len; data += fragment_len; } + if (rc > 0) + vcpu->arch.pgm.code = rc; return rc; } @@ -1378,7 +1227,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, parent = sg->parent; vaddr.addr = saddr; asce.val = sg->orig_asce; - ptr = asce.origin * PAGE_SIZE; + ptr = asce.rsto * PAGE_SIZE; if (asce.r) { *fake = 1; ptr = 0; @@ -1545,6 +1394,44 @@ shadow_pgt: } /** + * shadow_pgt_lookup() - find a shadow page table + * @sg: pointer to the shadow guest address space structure + * @saddr: the address in the shadow aguest address space + * @pgt: parent gmap address of the page table to get shadowed + * @dat_protection: if the pgtable is marked as protected by dat + * @fake: pgt references contiguous guest memory block, not a pgtable + * + * Returns 0 if the shadow page table was found and -EAGAIN if the page + * table was not found. + * + * Called with sg->mm->mmap_lock in read. + */ +static int shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, unsigned long *pgt, + int *dat_protection, int *fake) +{ + unsigned long pt_index; + unsigned long *table; + struct page *page; + int rc; + + spin_lock(&sg->guest_table_lock); + table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */ + if (table && !(*table & _SEGMENT_ENTRY_INVALID)) { + /* Shadow page tables are full pages (pte+pgste) */ + page = pfn_to_page(*table >> PAGE_SHIFT); + pt_index = gmap_pgste_get_pgt_addr(page_to_virt(page)); + *pgt = pt_index & ~GMAP_SHADOW_FAKE_TABLE; + *dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT); + *fake = !!(pt_index & GMAP_SHADOW_FAKE_TABLE); + rc = 0; + } else { + rc = -EAGAIN; + } + spin_unlock(&sg->guest_table_lock); + return rc; +} + +/** * kvm_s390_shadow_fault - handle fault on a shadow page table * @vcpu: virtual cpu * @sg: pointer to the shadow guest address space structure @@ -1567,6 +1454,9 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, int dat_protection, fake; int rc; + if (KVM_BUG_ON(!gmap_is_shadow(sg), vcpu->kvm)) + return -EFAULT; + mmap_read_lock(sg->mm); /* * We don't want any guest-2 tables to change - so the parent @@ -1575,7 +1465,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, */ ipte_lock(vcpu->kvm); - rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake); + rc = shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake); if (rc) rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection, &fake); diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index b320d12aa049..3fde45a151f2 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -405,11 +405,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, * @len: number of bytes to copy * * Copy @len bytes from @data (kernel space) to @gra (guest real address). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest low address and key protection are not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying from @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to guest memory. */ @@ -428,11 +429,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, * @len: number of bytes to copy * * Copy @len bytes from @gra (guest real address) to @data (kernel space). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest key protection is not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying to @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to kernel space. */ diff --git a/arch/s390/kvm/gmap-vsie.c b/arch/s390/kvm/gmap-vsie.c new file mode 100644 index 000000000000..a6d1dbb04c97 --- /dev/null +++ b/arch/s390/kvm/gmap-vsie.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Guest memory management for KVM/s390 nested VMs. + * + * Copyright IBM Corp. 2008, 2020, 2024 + * + * Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * David Hildenbrand <david@redhat.com> + * Janosch Frank <frankja@linux.vnet.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pgtable.h> +#include <linux/pagemap.h> +#include <linux/mman.h> + +#include <asm/lowcore.h> +#include <asm/gmap.h> +#include <asm/uv.h> + +#include "kvm-s390.h" +#include "gmap.h" + +/** + * gmap_find_shadow - find a specific asce in the list of shadow tables + * @parent: pointer to the parent gmap + * @asce: ASCE for which the shadow table is created + * @edat_level: edat level to be used for the shadow translation + * + * Returns the pointer to a gmap if a shadow table with the given asce is + * already available, ERR_PTR(-EAGAIN) if another one is just being created, + * otherwise NULL + * + * Context: Called with parent->shadow_lock held + */ +static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, int edat_level) +{ + struct gmap *sg; + + lockdep_assert_held(&parent->shadow_lock); + list_for_each_entry(sg, &parent->children, list) { + if (!gmap_shadow_valid(sg, asce, edat_level)) + continue; + if (!sg->initialized) + return ERR_PTR(-EAGAIN); + refcount_inc(&sg->ref_count); + return sg; + } + return NULL; +} + +/** + * gmap_shadow - create/find a shadow guest address space + * @parent: pointer to the parent gmap + * @asce: ASCE for which the shadow table is created + * @edat_level: edat level to be used for the shadow translation + * + * The pages of the top level page table referred by the asce parameter + * will be set to read-only and marked in the PGSTEs of the kvm process. + * The shadow table will be removed automatically on any change to the + * PTE mapping for the source table. + * + * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory, + * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the + * parent gmap table could not be protected. + */ +struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level) +{ + struct gmap *sg, *new; + unsigned long limit; + int rc; + + if (KVM_BUG_ON(parent->mm->context.allow_gmap_hpage_1m, (struct kvm *)parent->private) || + KVM_BUG_ON(gmap_is_shadow(parent), (struct kvm *)parent->private)) + return ERR_PTR(-EFAULT); + spin_lock(&parent->shadow_lock); + sg = gmap_find_shadow(parent, asce, edat_level); + spin_unlock(&parent->shadow_lock); + if (sg) + return sg; + /* Create a new shadow gmap */ + limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11)); + if (asce & _ASCE_REAL_SPACE) + limit = -1UL; + new = gmap_alloc(limit); + if (!new) + return ERR_PTR(-ENOMEM); + new->mm = parent->mm; + new->parent = gmap_get(parent); + new->private = parent->private; + new->orig_asce = asce; + new->edat_level = edat_level; + new->initialized = false; + spin_lock(&parent->shadow_lock); + /* Recheck if another CPU created the same shadow */ + sg = gmap_find_shadow(parent, asce, edat_level); + if (sg) { + spin_unlock(&parent->shadow_lock); + gmap_free(new); + return sg; + } + if (asce & _ASCE_REAL_SPACE) { + /* only allow one real-space gmap shadow */ + list_for_each_entry(sg, &parent->children, list) { + if (sg->orig_asce & _ASCE_REAL_SPACE) { + spin_lock(&sg->guest_table_lock); + gmap_unshadow(sg); + spin_unlock(&sg->guest_table_lock); + list_del(&sg->list); + gmap_put(sg); + break; + } + } + } + refcount_set(&new->ref_count, 2); + list_add(&new->list, &parent->children); + if (asce & _ASCE_REAL_SPACE) { + /* nothing to protect, return right away */ + new->initialized = true; + spin_unlock(&parent->shadow_lock); + return new; + } + spin_unlock(&parent->shadow_lock); + /* protect after insertion, so it will get properly invalidated */ + mmap_read_lock(parent->mm); + rc = __kvm_s390_mprotect_many(parent, asce & _ASCE_ORIGIN, + ((asce & _ASCE_TABLE_LENGTH) + 1), + PROT_READ, GMAP_NOTIFY_SHADOW); + mmap_read_unlock(parent->mm); + spin_lock(&parent->shadow_lock); + new->initialized = true; + if (rc) { + list_del(&new->list); + gmap_free(new); + new = ERR_PTR(rc); + } + spin_unlock(&parent->shadow_lock); + return new; +} diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c new file mode 100644 index 000000000000..6d8944d1b4a0 --- /dev/null +++ b/arch/s390/kvm/gmap.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Guest memory management for KVM/s390 + * + * Copyright IBM Corp. 2008, 2020, 2024 + * + * Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * David Hildenbrand <david@redhat.com> + * Janosch Frank <frankja@linux.vnet.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pgtable.h> +#include <linux/pagemap.h> + +#include <asm/lowcore.h> +#include <asm/gmap.h> +#include <asm/uv.h> + +#include "gmap.h" + +/** + * gmap_make_secure() - make one guest page secure + * @gmap: the guest gmap + * @gaddr: the guest address that needs to be made secure + * @uvcb: the UVCB specifying which operation needs to be performed + * + * Context: needs to be called with kvm->srcu held. + * Return: 0 on success, < 0 in case of error. + */ +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) +{ + struct kvm *kvm = gmap->private; + unsigned long vmaddr; + + lockdep_assert_held(&kvm->srcu); + + vmaddr = gfn_to_hva(kvm, gpa_to_gfn(gaddr)); + if (kvm_is_error_hva(vmaddr)) + return -EFAULT; + return make_hva_secure(gmap->mm, vmaddr, uvcb); +} + +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) +{ + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_CONV_TO_SEC_STOR, + .header.len = sizeof(uvcb), + .guest_handle = gmap->guest_handle, + .gaddr = gaddr, + }; + + return gmap_make_secure(gmap, gaddr, &uvcb); +} + +/** + * __gmap_destroy_page() - Destroy a guest page. + * @gmap: the gmap of the guest + * @page: the page to destroy + * + * An attempt will be made to destroy the given guest page. If the attempt + * fails, an attempt is made to export the page. If both attempts fail, an + * appropriate error is returned. + * + * Context: must be called holding the mm lock for gmap->mm + */ +static int __gmap_destroy_page(struct gmap *gmap, struct page *page) +{ + struct folio *folio = page_folio(page); + int rc; + + /* + * See gmap_make_secure(): large folios cannot be secure. Small + * folio implies FW_LEVEL_PTE. + */ + if (folio_test_large(folio)) + return -EFAULT; + + rc = uv_destroy_folio(folio); + /* + * Fault handlers can race; it is possible that two CPUs will fault + * on the same secure page. One CPU can destroy the page, reboot, + * re-enter secure mode and import it, while the second CPU was + * stuck at the beginning of the handler. At some point the second + * CPU will be able to progress, and it will not be able to destroy + * the page. In that case we do not want to terminate the process, + * we instead try to export the page. + */ + if (rc) + rc = uv_convert_from_secure_folio(folio); + + return rc; +} + +/** + * gmap_destroy_page() - Destroy a guest page. + * @gmap: the gmap of the guest + * @gaddr: the guest address to destroy + * + * An attempt will be made to destroy the given guest page. If the attempt + * fails, an attempt is made to export the page. If both attempts fail, an + * appropriate error is returned. + * + * Context: may sleep. + */ +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr) +{ + struct page *page; + int rc = 0; + + mmap_read_lock(gmap->mm); + page = gfn_to_page(gmap->private, gpa_to_gfn(gaddr)); + if (page) + rc = __gmap_destroy_page(gmap, page); + kvm_release_page_clean(page); + mmap_read_unlock(gmap->mm); + return rc; +} diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h new file mode 100644 index 000000000000..c8f031c9ea5f --- /dev/null +++ b/arch/s390/kvm/gmap.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KVM guest address space mapping code + * + * Copyright IBM Corp. 2007, 2016, 2025 + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * Claudio Imbrenda <imbrenda@linux.ibm.com> + */ + +#ifndef ARCH_KVM_S390_GMAP_H +#define ARCH_KVM_S390_GMAP_H + +#define GMAP_SHADOW_FAKE_TABLE 1ULL + +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr); +struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level); + +/** + * gmap_shadow_valid - check if a shadow guest address space matches the + * given properties and is still valid + * @sg: pointer to the shadow guest address space structure + * @asce: ASCE for which the shadow table is requested + * @edat_level: edat level to be used for the shadow translation + * + * Returns 1 if the gmap shadow is still valid and matches the given + * properties, the caller can continue using it. Returns 0 otherwise, the + * caller has to request a new shadow gmap in this case. + * + */ +static inline int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level) +{ + if (sg->removed) + return 0; + return sg->orig_asce == asce && sg->edat_level == edat_level; +} + +#endif diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index b16352083ff9..610dd44a948b 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -21,6 +21,7 @@ #include "gaccess.h" #include "trace.h" #include "trace-s390.h" +#include "gmap.h" u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu) { @@ -367,7 +368,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) reg2, &srcaddr, GACC_FETCH, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0); + rc = kvm_s390_handle_dat_fault(vcpu, srcaddr, 0); if (rc != 0) return rc; @@ -376,7 +377,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) reg1, &dstaddr, GACC_STORE, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1); + rc = kvm_s390_handle_dat_fault(vcpu, dstaddr, FOLL_WRITE); if (rc != 0) return rc; @@ -549,7 +550,7 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu) * If the unpin did not succeed, the guest will exit again for the UVC * and we will retry the unpin. */ - if (rc == -EINVAL) + if (rc == -EINVAL || rc == -ENXIO) return 0; /* * If we got -EAGAIN here, we simply return it. It will eventually diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index fc4007cc067a..07ff0e10cb7f 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -19,13 +19,13 @@ #include <linux/slab.h> #include <linux/bitmap.h> #include <linux/vmalloc.h> +#include <asm/access-regs.h> #include <asm/asm-offsets.h> #include <asm/dis.h> #include <linux/uaccess.h> #include <asm/sclp.h> #include <asm/isc.h> #include <asm/gmap.h> -#include <asm/switch_to.h> #include <asm/nmi.h> #include <asm/airq.h> #include <asm/tpi.h> @@ -118,8 +118,6 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) static void sca_clear_ext_call(struct kvm_vcpu *vcpu) { - int rc, expect; - if (!kvm_s390_use_sca_entries()) return; kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND); @@ -128,23 +126,16 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl old; - old = READ_ONCE(*sigp_ctrl); - expect = old.value; - rc = cmpxchg(&sigp_ctrl->value, old.value, 0); + WRITE_ONCE(sigp_ctrl->value, 0); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl old; - old = READ_ONCE(*sigp_ctrl); - expect = old.value; - rc = cmpxchg(&sigp_ctrl->value, old.value, 0); + WRITE_ONCE(sigp_ctrl->value, 0); } read_unlock(&vcpu->kvm->arch.sca_lock); - WARN_ON(rc != expect); /* cannot clear? */ } int psw_extint_disabled(struct kvm_vcpu *vcpu) @@ -247,12 +238,12 @@ static inline int gisa_set_iam(struct kvm_s390_gisa *gisa, u8 iam) { u64 word, _word; + word = READ_ONCE(gisa->u64.word[0]); do { - word = READ_ONCE(gisa->u64.word[0]); if ((u64)gisa != word >> 32) return -EBUSY; _word = (word & ~0xffUL) | iam; - } while (cmpxchg(&gisa->u64.word[0], word, _word) != word); + } while (!try_cmpxchg(&gisa->u64.word[0], &word, _word)); return 0; } @@ -270,10 +261,10 @@ static inline void gisa_clear_ipm(struct kvm_s390_gisa *gisa) { u64 word, _word; + word = READ_ONCE(gisa->u64.word[0]); do { - word = READ_ONCE(gisa->u64.word[0]); _word = word & ~(0xffUL << 24); - } while (cmpxchg(&gisa->u64.word[0], word, _word) != word); + } while (!try_cmpxchg(&gisa->u64.word[0], &word, _word)); } /** @@ -291,14 +282,14 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi) u8 pending_mask, alert_mask; u64 word, _word; + word = READ_ONCE(gi->origin->u64.word[0]); do { - word = READ_ONCE(gi->origin->u64.word[0]); alert_mask = READ_ONCE(gi->alert.mask); pending_mask = (u8)(word >> 24) & alert_mask; if (pending_mask) return pending_mask; _word = (word & ~0xffUL) | alert_mask; - } while (cmpxchg(&gi->origin->u64.word[0], word, _word) != word); + } while (!try_cmpxchg(&gi->origin->u64.word[0], &word, _word)); return 0; } @@ -584,7 +575,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, mci.val = mchk->mcic; /* take care of lazy register loading */ - save_fpu_regs(); + kvm_s390_fpu_store(vcpu->run); save_access_regs(vcpu->run->s.regs.acrs); if (MACHINE_HAS_GS && vcpu->arch.gs_enabled) save_gs_cb(current->thread.gs_cb); @@ -648,7 +639,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, } rc |= write_guest_lc(vcpu, __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); - rc |= put_guest_lc(vcpu, current->thread.fpu.fpc, + rc |= put_guest_lc(vcpu, vcpu->run->s.regs.fpc, (u32 __user *) __LC_FP_CREG_SAVE_AREA); rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->todpr, (u32 __user *) __LC_TOD_PROGREG_SAVE_AREA); @@ -1031,7 +1022,7 @@ static int __must_check __deliver_service_ev(struct kvm_vcpu *vcpu) return 0; } ext = fi->srv_signal; - /* only clear the event bit */ + /* only clear the event bits */ fi->srv_signal.ext_params &= ~SCCB_EVENT_PENDING; clear_bit(IRQ_PEND_EXT_SERVICE_EV, &fi->pending_irqs); spin_unlock(&fi->lock); @@ -1041,7 +1032,7 @@ static int __must_check __deliver_service_ev(struct kvm_vcpu *vcpu) trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, ext.ext_params, 0); - return write_sclp(vcpu, SCCB_EVENT_PENDING); + return write_sclp(vcpu, ext.ext_params & SCCB_EVENT_PENDING); } static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) @@ -2687,9 +2678,13 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) kvm_s390_clear_float_irqs(dev->kvm); break; case KVM_DEV_FLIC_APF_ENABLE: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 1; break; case KVM_DEV_FLIC_APF_DISABLE_WAIT: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 0; /* * Make sure no async faults are in transition when @@ -2898,20 +2893,25 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { - u64 uaddr; + u64 uaddr_s, uaddr_i; + int idx; switch (ue->type) { /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: + if (kvm_is_ucontrol(kvm)) + return -EINVAL; e->set = set_adapter_int; - 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) + + idx = srcu_read_lock(&kvm->srcu); + uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr); + uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr); + srcu_read_unlock(&kvm->srcu, idx); + + if (kvm_is_error_hva(uaddr_s) || kvm_is_error_hva(uaddr_i)) return -EFAULT; - e->adapter.ind_addr = uaddr; + e->adapter.summary_addr = uaddr_s; + e->adapter.ind_addr = uaddr_i; 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; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ea63ac769889..020502af7dc9 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -33,22 +33,24 @@ #include <linux/pgtable.h> #include <linux/mmu_notifier.h> +#include <asm/access-regs.h> #include <asm/asm-offsets.h> #include <asm/lowcore.h> #include <asm/stp.h> #include <asm/gmap.h> #include <asm/nmi.h> -#include <asm/switch_to.h> #include <asm/isc.h> #include <asm/sclp.h> #include <asm/cpacf.h> #include <asm/timex.h> +#include <asm/asm.h> +#include <asm/fpu.h> #include <asm/ap.h> #include <asm/uv.h> -#include <asm/fpu/api.h> #include "kvm-s390.h" #include "gaccess.h" #include "pci.h" +#include "gmap.h" #define CREATE_TRACE_POINTS #include "trace.h" @@ -132,6 +134,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, instruction_io_other), STATS_DESC_COUNTER(VCPU, instruction_lpsw), STATS_DESC_COUNTER(VCPU, instruction_lpswe), + STATS_DESC_COUNTER(VCPU, instruction_lpswey), STATS_DESC_COUNTER(VCPU, instruction_pfmf), STATS_DESC_COUNTER(VCPU, instruction_ptff), STATS_DESC_COUNTER(VCPU, instruction_sck), @@ -339,28 +342,46 @@ static inline int plo_test_bit(unsigned char nr) " lgr 0,%[function]\n" /* Parameter registers are ignored for "test bit" */ " plo 0,0,0,0(0)\n" - " ipm %0\n" - " srl %0,28\n" - : "=d" (cc) + CC_IPM(cc) + : CC_OUT(cc, cc) : [function] "d" (function) + : CC_CLOBBER_LIST("0")); + return CC_TRANSFORM(cc) == 0; +} + +static __always_inline void pfcr_query(u8 (*query)[16]) +{ + asm volatile( + " lghi 0,0\n" + " .insn rsy,0xeb0000000016,0,0,%[query]\n" + : [query] "=QS" (*query) + : : "cc", "0"); - return cc == 0; } -static __always_inline void __insn32_query(unsigned int opcode, u8 *query) +static __always_inline void __sortl_query(u8 (*query)[32]) { asm volatile( " lghi 0,0\n" - " lgr 1,%[query]\n" + " la 1,%[query]\n" /* Parameter registers are ignored */ - " .insn rrf,%[opc] << 16,2,4,6,0\n" + " .insn rre,0xb9380000,2,4\n" + : [query] "=R" (*query) : - : [query] "d" ((unsigned long)query), [opc] "i" (opcode) - : "cc", "memory", "0", "1"); + : "cc", "0", "1"); } -#define INSN_SORTL 0xb938 -#define INSN_DFLTCC 0xb939 +static __always_inline void __dfltcc_query(u8 (*query)[32]) +{ + asm volatile( + " lghi 0,0\n" + " la 1,%[query]\n" + /* Parameter registers are ignored */ + " .insn rrf,0xb9390000,2,4,6,0\n" + : [query] "=R" (*query) + : + : "cc", "0", "1"); +} static void __init kvm_s390_cpu_feat_init(void) { @@ -414,10 +435,13 @@ static void __init kvm_s390_cpu_feat_init(void) kvm_s390_available_subfunc.kdsa); if (test_facility(150)) /* SORTL */ - __insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl); + __sortl_query(&kvm_s390_available_subfunc.sortl); if (test_facility(151)) /* DFLTCC */ - __insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc); + __dfltcc_query(&kvm_s390_available_subfunc.dfltcc); + + if (test_facility(201)) /* PFCR */ + pfcr_query(&kvm_s390_available_subfunc.pfcr); if (MACHINE_HAS_ESOP) allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP); @@ -587,7 +611,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_S390_HPAGE_1M: r = 0; - if (hpage && !kvm_is_ucontrol(kvm)) + if (hpage && !(kvm && kvm_is_ucontrol(kvm))) r = 1; break; case KVM_CAP_S390_MEM_OP: @@ -789,6 +813,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) set_kvm_facility(kvm->arch.model.fac_mask, 192); set_kvm_facility(kvm->arch.model.fac_list, 192); } + if (test_facility(198)) { + set_kvm_facility(kvm->arch.model.fac_mask, 198); + set_kvm_facility(kvm->arch.model.fac_list, 198); + } + if (test_facility(199)) { + set_kvm_facility(kvm->arch.model.fac_mask, 199); + set_kvm_facility(kvm->arch.model.fac_list, 199); + } r = 0; } else r = -EINVAL; @@ -1533,6 +1565,9 @@ static int kvm_s390_set_processor_subfunc(struct kvm *kvm, ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1], ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2], ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]); + VM_EVENT(kvm, 3, "GET: guest PFCR subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[0], + ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[1]); return 0; } @@ -1747,6 +1782,9 @@ static int kvm_s390_get_processor_subfunc(struct kvm *kvm, ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1], ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2], ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]); + VM_EVENT(kvm, 3, "GET: guest PFCR subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[0], + ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[1]); return 0; } @@ -1815,6 +1853,9 @@ static int kvm_s390_get_machine_subfunc(struct kvm *kvm, ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[1], ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[2], ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[3]); + VM_EVENT(kvm, 3, "GET: host PFCR subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[0], + ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[1]); return 0; } @@ -1897,11 +1938,11 @@ static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val) read_lock(&kvm->arch.sca_lock); sca = kvm->arch.sca; + old = READ_ONCE(sca->utility); do { - old = READ_ONCE(sca->utility); new = old; new.mtcr = val; - } while (cmpxchg(&sca->utility.val, old.val, new.val) != old.val); + } while (!try_cmpxchg(&sca->utility.val, &old.val, new.val)); read_unlock(&kvm->arch.sca_lock); } @@ -2631,9 +2672,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) if (r) break; - mmap_write_lock(current->mm); - r = gmap_mark_unmergeable(); - mmap_write_unlock(current->mm); + r = s390_disable_cow_sharing(); if (r) break; @@ -2878,7 +2917,7 @@ static int kvm_s390_vm_mem_op_abs(struct kvm *kvm, struct kvm_s390_mem_op *mop) srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_is_error_gpa(kvm, mop->gaddr)) { + if (!kvm_is_gpa_in_memslot(kvm, mop->gaddr)) { r = PGM_ADDRESSING; goto out_unlock; } @@ -2940,7 +2979,7 @@ static int kvm_s390_vm_mem_op_cmpxchg(struct kvm *kvm, struct kvm_s390_mem_op *m srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_is_error_gpa(kvm, mop->gaddr)) { + if (!kvm_is_gpa_in_memslot(kvm, mop->gaddr)) { r = PGM_ADDRESSING; goto out_unlock; } @@ -2998,14 +3037,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) break; } case KVM_CREATE_IRQCHIP: { - struct kvm_irq_routing_entry routing; - r = -EINVAL; - if (kvm->arch.use_irqchip) { - /* Set up dummy routing. */ - memset(&routing, 0, sizeof(routing)); - r = kvm_set_irq_routing(kvm, &routing, 0, 0); - } + if (kvm->arch.use_irqchip) + r = 0; break; } case KVM_SET_DEVICE_ATTR: { @@ -3153,7 +3187,7 @@ static int kvm_s390_apxa_installed(void) */ static void kvm_s390_set_crycb_format(struct kvm *kvm) { - kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb; + kvm->arch.crypto.crycbd = virt_to_phys(kvm->arch.crypto.crycb); /* Clear the CRYCB format bits - i.e., set format 0 by default */ kvm->arch.crypto.crycbd &= ~(CRYCB_FORMAT_MASK); @@ -3395,8 +3429,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) VM_EVENT(kvm, 3, "vm created with type %lu", type); if (type & KVM_VM_S390_UCONTROL) { + struct kvm_userspace_memory_region2 fake_memslot = { + .slot = KVM_S390_UCONTROL_MEMSLOT, + .guest_phys_addr = 0, + .userspace_addr = 0, + .memory_size = ALIGN_DOWN(TASK_SIZE, _SEGMENT_SIZE), + .flags = 0, + }; + kvm->arch.gmap = NULL; kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT; + /* one flat fake memslot covering the whole address-space */ + mutex_lock(&kvm->slots_lock); + KVM_BUG_ON(kvm_set_internal_memslot(kvm, &fake_memslot), kvm); + mutex_unlock(&kvm->slots_lock); } else { if (sclp.hamax == U64_MAX) kvm->arch.mem_limit = TASK_SIZE_MAX; @@ -3716,7 +3762,6 @@ __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - gmap_enable(vcpu->arch.enabled_gmap); kvm_s390_set_cpuflags(vcpu, CPUSTAT_RUNNING); if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu)) __start_cpu_timer_accounting(vcpu); @@ -3729,8 +3774,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu)) __stop_cpu_timer_accounting(vcpu); kvm_s390_clear_cpuflags(vcpu, CPUSTAT_RUNNING); - vcpu->arch.enabled_gmap = gmap_get_enabled(); - gmap_disable(vcpu->arch.enabled_gmap); } @@ -3748,8 +3791,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) } if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0) vcpu->arch.sie_block->ictl |= ICTL_OPEREXC; - /* make vcpu_load load the right gmap on the first trigger */ - vcpu->arch.enabled_gmap = vcpu->arch.gmap; } static bool kvm_has_pckmo_subfunc(struct kvm *kvm, unsigned long nr) @@ -3771,6 +3812,13 @@ static bool kvm_has_pckmo_ecc(struct kvm *kvm) } +static bool kvm_has_pckmo_hmac(struct kvm *kvm) +{ + /* At least one HMAC subfunction must be present */ + return kvm_has_pckmo_subfunc(kvm, 118) || + kvm_has_pckmo_subfunc(kvm, 122); +} + static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) { /* @@ -3783,7 +3831,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd; vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA); vcpu->arch.sie_block->eca &= ~ECA_APIE; - vcpu->arch.sie_block->ecd &= ~ECD_ECC; + vcpu->arch.sie_block->ecd &= ~(ECD_ECC | ECD_HMAC); if (vcpu->kvm->arch.crypto.apie) vcpu->arch.sie_block->eca |= ECA_APIE; @@ -3791,9 +3839,11 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) /* Set up protected key support */ if (vcpu->kvm->arch.crypto.aes_kw) { vcpu->arch.sie_block->ecb3 |= ECB3_AES; - /* ecc is also wrapped with AES key */ + /* ecc/hmac is also wrapped with AES key */ if (kvm_has_pckmo_ecc(vcpu->kvm)) vcpu->arch.sie_block->ecd |= ECD_ECC; + if (kvm_has_pckmo_hmac(vcpu->kvm)) + vcpu->arch.sie_block->ecd |= ECD_HMAC; } if (vcpu->kvm->arch.crypto.dea_kw) @@ -3951,6 +4001,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_DIAG318; + vcpu->arch.acrs_loaded = false; kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; @@ -4080,7 +4131,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { /* do not poll with more than halt_poll_max_steal percent of steal time */ - if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >= + if (get_lowcore()->avg_steal_timer * 100 / (TICK_USEC << 12) >= READ_ONCE(halt_poll_max_steal)) { vcpu->stat.halt_no_poll_steal++; return true; @@ -4460,6 +4511,75 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu) return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS); } +static int __kvm_s390_fixup_fault_sync(struct gmap *gmap, gpa_t gaddr, unsigned int flags) +{ + struct kvm *kvm = gmap->private; + gfn_t gfn = gpa_to_gfn(gaddr); + bool unlocked; + hva_t vmaddr; + gpa_t tmp; + int rc; + + if (kvm_is_ucontrol(kvm)) { + tmp = __gmap_translate(gmap, gaddr); + gfn = gpa_to_gfn(tmp); + } + + vmaddr = gfn_to_hva(kvm, gfn); + rc = fixup_user_fault(gmap->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); + if (!rc) + rc = __gmap_link(gmap, gaddr, vmaddr); + return rc; +} + +/** + * __kvm_s390_mprotect_many() - Apply specified protection to guest pages + * @gmap: the gmap of the guest + * @gpa: the starting guest address + * @npages: how many pages to protect + * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE + * @bits: pgste notification bits to set + * + * Returns: 0 in case of success, < 0 in case of error - see gmap_protect_one() + * + * Context: kvm->srcu and gmap->mm need to be held in read mode + */ +int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot, + unsigned long bits) +{ + unsigned int fault_flag = (prot & PROT_WRITE) ? FAULT_FLAG_WRITE : 0; + gpa_t end = gpa + npages * PAGE_SIZE; + int rc; + + for (; gpa < end; gpa = ALIGN(gpa + 1, rc)) { + rc = gmap_protect_one(gmap, gpa, prot, bits); + if (rc == -EAGAIN) { + __kvm_s390_fixup_fault_sync(gmap, gpa, fault_flag); + rc = gmap_protect_one(gmap, gpa, prot, bits); + } + if (rc < 0) + return rc; + } + + return 0; +} + +static int kvm_s390_mprotect_notify_prefix(struct kvm_vcpu *vcpu) +{ + gpa_t gaddr = kvm_s390_get_prefix(vcpu); + int idx, rc; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + mmap_read_lock(vcpu->arch.gmap->mm); + + rc = __kvm_s390_mprotect_many(vcpu->arch.gmap, gaddr, 2, PROT_WRITE, GMAP_NOTIFY_MPROT); + + mmap_read_unlock(vcpu->arch.gmap->mm); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return rc; +} + static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) { retry: @@ -4475,9 +4595,8 @@ retry: */ if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) { int rc; - rc = gmap_mprotect_notify(vcpu->arch.gmap, - kvm_s390_get_prefix(vcpu), - PAGE_SIZE * 2, PROT_WRITE); + + rc = kvm_s390_mprotect_notify_prefix(vcpu); if (rc) { kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu); return rc; @@ -4575,22 +4694,6 @@ int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clo return 1; } -/** - * kvm_arch_fault_in_page - fault-in guest page if necessary - * @vcpu: The corresponding virtual cpu - * @gpa: Guest physical address - * @writable: Whether the page should be writable or not - * - * Make sure that a guest page has been faulted-in on the host. - * - * Return: Zero on success, negative error code otherwise. - */ -long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable) -{ - return gmap_fault(vcpu->arch.gmap, gpa, - writable ? FAULT_FLAG_WRITE : 0); -} - static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token, unsigned long token) { @@ -4658,12 +4761,11 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu) if (!vcpu->arch.gmap->pfault_enabled) return false; - hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr)); - hva += current->thread.gmap_addr & ~PAGE_MASK; + hva = gfn_to_hva(vcpu->kvm, current->thread.gmap_teid.addr); if (read_guest_real(vcpu, vcpu->arch.pfault_token, &arch.pfault_token, 8)) return false; - return kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch); + return kvm_setup_async_pf(vcpu, current->thread.gmap_teid.addr * PAGE_SIZE, hva, &arch); } static int vcpu_pre_run(struct kvm_vcpu *vcpu) @@ -4701,6 +4803,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); vcpu->arch.sie_block->icptcode = 0; + current->thread.gmap_int_code = 0; cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags); trace_kvm_s390_sie_enter(vcpu, cpuflags); @@ -4708,7 +4811,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) return 0; } -static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) +static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu) { struct kvm_s390_pgm_info pgm_info = { .code = PGM_ADDRESSING, @@ -4744,10 +4847,182 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_irq(vcpu, &pgm_info); } +static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu) +{ + KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, + "Unexpected program interrupt 0x%x, TEID 0x%016lx", + current->thread.gmap_int_code, current->thread.gmap_teid.val); +} + +/* + * __kvm_s390_handle_dat_fault() - handle a dat fault for the gmap of a vcpu + * @vcpu: the vCPU whose gmap is to be fixed up + * @gfn: the guest frame number used for memslots (including fake memslots) + * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps + * @flags: FOLL_* flags + * + * Return: 0 on success, < 0 in case of error. + * Context: The mm lock must not be held before calling. May sleep. + */ +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags) +{ + struct kvm_memory_slot *slot; + unsigned int fault_flags; + bool writable, unlocked; + unsigned long vmaddr; + struct page *page; + kvm_pfn_t pfn; + int rc; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return vcpu_post_run_addressing_exception(vcpu); + + fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; + if (vcpu->arch.gmap->pfault_enabled) + flags |= FOLL_NOWAIT; + vmaddr = __gfn_to_hva_memslot(slot, gfn); + +try_again: + pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page); + + /* Access outside memory, inject addressing exception */ + if (is_noslot_pfn(pfn)) + return vcpu_post_run_addressing_exception(vcpu); + /* Signal pending: try again */ + if (pfn == KVM_PFN_ERR_SIGPENDING) + return -EAGAIN; + + /* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */ + if (pfn == KVM_PFN_ERR_NEEDS_IO) { + trace_kvm_s390_major_guest_pfault(vcpu); + if (kvm_arch_setup_async_pf(vcpu)) + return 0; + vcpu->stat.pfault_sync++; + /* Could not setup async pfault, try again synchronously */ + flags &= ~FOLL_NOWAIT; + goto try_again; + } + /* Any other error */ + if (is_error_pfn(pfn)) + return -EFAULT; + + /* Success */ + mmap_read_lock(vcpu->arch.gmap->mm); + /* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */ + rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked); + if (!rc) + rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr); + scoped_guard(spinlock, &vcpu->kvm->mmu_lock) { + kvm_release_faultin_page(vcpu->kvm, page, false, writable); + } + mmap_read_unlock(vcpu->arch.gmap->mm); + return rc; +} + +static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags) +{ + unsigned long gaddr_tmp; + gfn_t gfn; + + gfn = gpa_to_gfn(gaddr); + if (kvm_is_ucontrol(vcpu->kvm)) { + /* + * This translates the per-vCPU guest address into a + * fake guest address, which can then be used with the + * fake memslots that are identity mapping userspace. + * This allows ucontrol VMs to use the normal fault + * resolution path, like normal VMs. + */ + mmap_read_lock(vcpu->arch.gmap->mm); + gaddr_tmp = __gmap_translate(vcpu->arch.gmap, gaddr); + mmap_read_unlock(vcpu->arch.gmap->mm); + if (gaddr_tmp == -EFAULT) { + vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; + vcpu->run->s390_ucontrol.trans_exc_code = gaddr; + vcpu->run->s390_ucontrol.pgm_code = PGM_SEGMENT_TRANSLATION; + return -EREMOTE; + } + gfn = gpa_to_gfn(gaddr_tmp); + } + return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags); +} + +static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) +{ + unsigned int flags = 0; + unsigned long gaddr; + int rc; + + gaddr = current->thread.gmap_teid.addr * PAGE_SIZE; + if (kvm_s390_cur_gmap_fault_is_write()) + flags = FAULT_FLAG_WRITE; + + switch (current->thread.gmap_int_code & PGM_INT_CODE_MASK) { + case 0: + vcpu->stat.exit_null++; + break; + case PGM_SECURE_STORAGE_ACCESS: + case PGM_SECURE_STORAGE_VIOLATION: + kvm_s390_assert_primary_as(vcpu); + /* + * This can happen after a reboot with asynchronous teardown; + * the new guest (normal or protected) will run on top of the + * previous protected guest. The old pages need to be destroyed + * so the new guest can use them. + */ + if (gmap_destroy_page(vcpu->arch.gmap, gaddr)) { + /* + * Either KVM messed up the secure guest mapping or the + * same page is mapped into multiple secure guests. + * + * This exception is only triggered when a guest 2 is + * running and can therefore never occur in kernel + * context. + */ + pr_warn_ratelimited("Secure storage violation (%x) in task: %s, pid %d\n", + current->thread.gmap_int_code, current->comm, + current->pid); + send_sig(SIGSEGV, current, 0); + } + break; + case PGM_NON_SECURE_STORAGE_ACCESS: + kvm_s390_assert_primary_as(vcpu); + /* + * This is normal operation; a page belonging to a protected + * guest has not been imported yet. Try to import the page into + * the protected guest. + */ + rc = gmap_convert_to_secure(vcpu->arch.gmap, gaddr); + if (rc == -EINVAL) + send_sig(SIGSEGV, current, 0); + if (rc != -ENXIO) + break; + flags = FAULT_FLAG_WRITE; + fallthrough; + case PGM_PROTECTION: + case PGM_SEGMENT_TRANSLATION: + case PGM_PAGE_TRANSLATION: + case PGM_ASCE_TYPE: + case PGM_REGION_FIRST_TRANS: + case PGM_REGION_SECOND_TRANS: + case PGM_REGION_THIRD_TRANS: + kvm_s390_assert_primary_as(vcpu); + return vcpu_dat_fault_handler(vcpu, gaddr, flags); + default: + KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx", + current->thread.gmap_int_code, current->thread.gmap_teid.val); + send_sig(SIGSEGV, current, 0); + break; + } + return 0; +} + static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) { struct mcck_volatile_info *mcck_info; struct sie_page *sie_page; + int rc; VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); @@ -4769,7 +5044,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) } if (vcpu->arch.sie_block->icptcode > 0) { - int rc = kvm_handle_sie_intercept(vcpu); + rc = kvm_handle_sie_intercept(vcpu); if (rc != -EOPNOTSUPP) return rc; @@ -4778,24 +5053,9 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; return -EREMOTE; - } else if (exit_reason != -EFAULT) { - vcpu->stat.exit_null++; - return 0; - } else if (kvm_is_ucontrol(vcpu->kvm)) { - vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; - vcpu->run->s390_ucontrol.trans_exc_code = - current->thread.gmap_addr; - vcpu->run->s390_ucontrol.pgm_code = 0x10; - return -EREMOTE; - } else if (current->thread.gmap_pfault) { - trace_kvm_s390_major_guest_pfault(vcpu); - current->thread.gmap_pfault = 0; - if (kvm_arch_setup_async_pf(vcpu)) - return 0; - vcpu->stat.pfault_sync++; - return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1); } - return vcpu_post_run_fault_in_sie(vcpu); + + return vcpu_post_run_handle_fault(vcpu); } #define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK) @@ -4829,10 +5089,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) vcpu->run->s.regs.gprs, sizeof(sie_page->pv_grregs)); } - if (test_cpu_flag(CIF_FPU)) - load_fpu_regs(); exit_reason = sie64a(vcpu->arch.sie_block, - vcpu->run->s.regs.gprs); + vcpu->run->s.regs.gprs, + vcpu->arch.gmap->asce); if (kvm_s390_pv_cpu_is_protected(vcpu)) { memcpy(vcpu->run->s.regs.gprs, sie_page->pv_grregs, @@ -4951,16 +5210,8 @@ static void sync_regs(struct kvm_vcpu *vcpu) } save_access_regs(vcpu->arch.host_acrs); restore_access_regs(vcpu->run->s.regs.acrs); - /* save host (userspace) fprs/vrs */ - save_fpu_regs(); - vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; - vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; - if (cpu_has_vx()) - current->thread.fpu.regs = vcpu->run->s.regs.vrs; - else - current->thread.fpu.regs = vcpu->run->s.regs.fprs; - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - + vcpu->arch.acrs_loaded = true; + kvm_s390_fpu_load(vcpu->run); /* Sync fmt2 only data */ if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) { sync_regs_fmt2(vcpu); @@ -5021,12 +5272,8 @@ static void store_regs(struct kvm_vcpu *vcpu) kvm_run->s.regs.pfc = vcpu->arch.pfault_compare; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); - /* Save guest register state */ - save_fpu_regs(); - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - /* 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; + vcpu->arch.acrs_loaded = false; + kvm_s390_fpu_store(vcpu->run); if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) store_regs_fmt2(vcpu); } @@ -5034,6 +5281,7 @@ static void store_regs(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; + DECLARE_KERNEL_FPU_ONSTACK32(fpu); int rc; /* @@ -5045,7 +5293,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.pv.dumping) return -EINVAL; - if (kvm_run->immediate_exit) + if (!vcpu->wants_to_run) return -EINTR; if (kvm_run->kvm_valid_regs & ~KVM_SYNC_S390_VALID_FIELDS || @@ -5075,6 +5323,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } + kernel_fpu_begin(&fpu, KERNEL_FPC | KERNEL_VXR); sync_regs(vcpu); enable_cpu_timer_accounting(vcpu); @@ -5098,6 +5347,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) disable_cpu_timer_accounting(vcpu); store_regs(vcpu); + kernel_fpu_end(&fpu, KERNEL_FPC | KERNEL_VXR); kvm_sigset_deactivate(vcpu); @@ -5172,8 +5422,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) * switch in the run ioctl. Let's update our copies before we save * it into the save area */ - save_fpu_regs(); - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; + kvm_s390_fpu_store(vcpu->run); save_access_regs(vcpu->run->s.regs.acrs); return kvm_s390_store_status_unloaded(vcpu, addr); @@ -5645,7 +5894,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } #endif case KVM_S390_VCPU_FAULT: { - r = gmap_fault(vcpu->arch.gmap, arg, 0); + idx = srcu_read_lock(&vcpu->kvm->srcu); + r = vcpu_dat_fault_handler(vcpu, arg, 0); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_ENABLE_CAP: @@ -5761,6 +6012,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, { gpa_t size; + if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS) + return -EINVAL; + /* When we are protected, we should not change the memory slots */ if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; @@ -5810,6 +6064,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, { int rc = 0; + if (kvm_is_ucontrol(kvm)) + return; + switch (change) { case KVM_MR_DELETE: rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index a7ea80cfa445..8d3bbb2dd8d2 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -20,6 +20,26 @@ #include <asm/processor.h> #include <asm/sclp.h> +#define KVM_S390_UCONTROL_MEMSLOT (KVM_USER_MEM_SLOTS + 0) + +static inline void kvm_s390_fpu_store(struct kvm_run *run) +{ + fpu_stfpc(&run->s.regs.fpc); + if (cpu_has_vx()) + save_vx_regs((__vector128 *)&run->s.regs.vrs); + else + save_fp_regs((freg_t *)&run->s.regs.fprs); +} + +static inline void kvm_s390_fpu_load(struct kvm_run *run) +{ + fpu_lfpc_safe(&run->s.regs.fpc); + if (cpu_has_vx()) + load_vx_regs((__vector128 *)&run->s.regs.vrs); + else + load_fp_regs((freg_t *)&run->s.regs.fprs); +} + /* Transactional Memory Execution related macros */ #define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & ECB_TE)) #define TDB_FORMAT1 1 @@ -120,6 +140,21 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar) return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } +static inline u64 kvm_s390_get_base_disp_siy(struct kvm_vcpu *vcpu, u8 *ar) +{ + u32 base1 = vcpu->arch.sie_block->ipb >> 28; + s64 disp1; + + /* The displacement is a 20bit _SIGNED_ value */ + disp1 = sign_extend64(((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + + ((vcpu->arch.sie_block->ipb & 0xff00) << 4), 19); + + if (ar) + *ar = base1; + + return (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; +} + static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, u64 *address1, u64 *address2, u8 *ar_b1, u8 *ar_b2) @@ -234,13 +269,27 @@ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) { - u32 gd = virt_to_phys(kvm->arch.gisa_int.origin); + u32 gd; + + if (!kvm->arch.gisa_int.origin) + return 0; + + gd = virt_to_phys(kvm->arch.gisa_int.origin); if (gd && sclp.has_gisaf) gd |= GISA_FORMAT1; return gd; } +static inline hva_t gpa_to_hva(struct kvm *kvm, gpa_t gpa) +{ + hva_t hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); + + if (!kvm_is_error_hva(hva)) + hva |= offset_in_page(gpa); + return hva; +} + /* 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); @@ -356,7 +405,6 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod); -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); int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); @@ -371,6 +419,14 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu); void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm); __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu); int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc); +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags); +int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot, + unsigned long bits); + +static inline int kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gpa_t gaddr, unsigned int flags) +{ + return __kvm_s390_handle_dat_fault(vcpu, gpa_to_gfn(gaddr), gaddr, flags); +} /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); @@ -491,6 +547,13 @@ static inline int kvm_s390_use_sca_entries(void) void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu, struct mcck_volatile_info *mcck_info); +static inline bool kvm_s390_cur_gmap_fault_is_write(void) +{ + if (current->thread.gmap_int_code == PGM_PROTECTION) + return true; + return test_facility(75) && (current->thread.gmap_teid.fsi == TEID_FSI_STORE); +} + /** * kvm_s390_vcpu_crypto_reset_all * diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index ffa7739c7a28..9b9e7fdd5380 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -103,7 +103,7 @@ static int zpci_reset_aipb(u8 nisc) /* * AEN registration can only happen once per system boot. If * an aipb already exists then AEN was already registered and - * we can re-use the aipb contents. This can only happen if + * we can reuse the aipb contents. This can only happen if * the KVM module was removed and re-inserted. However, we must * ensure that the same forwarding ISC is used as this is assigned * during KVM module load. @@ -208,13 +208,12 @@ static inline int account_mem(unsigned long nr_pages) page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + cur_pages = atomic_long_read(&user->locked_vm); do { - cur_pages = atomic_long_read(&user->locked_vm); new_pages = cur_pages + nr_pages; if (new_pages > page_limit) return -ENOMEM; - } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages, - new_pages) != cur_pages); + } while (!atomic_long_try_cmpxchg(&user->locked_vm, &cur_pages, new_pages)); atomic64_add(nr_pages, ¤t->mm->pinned_vm); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index f875a404a0a0..1a49b89706f8 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -149,7 +149,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu) * first page, since address is 8k aligned and memory pieces are always * at least 1MB aligned and have at least a size of 1MB. */ - if (kvm_is_error_gpa(vcpu->kvm, address)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, address)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); kvm_s390_set_prefix(vcpu, address); @@ -464,7 +464,7 @@ static int handle_test_block(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); addr = kvm_s390_real_to_abs(vcpu, addr); - if (kvm_is_error_gpa(vcpu->kvm, addr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, addr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); /* * We don't expect errors on modern systems, and do not care @@ -797,6 +797,36 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) return 0; } +static int handle_lpswey(struct kvm_vcpu *vcpu) +{ + psw_t new_psw; + u64 addr; + int rc; + u8 ar; + + vcpu->stat.instruction_lpswey++; + + if (!test_kvm_facility(vcpu->kvm, 193)) + return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + addr = kvm_s390_get_base_disp_siy(vcpu, &ar); + if (addr & 7) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + + vcpu->arch.sie_block->gpsw = new_psw; + if (!is_valid_psw(&vcpu->arch.sie_block->gpsw)) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + return 0; +} + static int handle_stidp(struct kvm_vcpu *vcpu) { u64 stidp_data = vcpu->kvm->arch.model.cpuid; @@ -1462,6 +1492,8 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) case 0x61: case 0x62: return handle_ri(vcpu); + case 0x71: + return handle_lpswey(vcpu); default: return -EOPNOTSUPP; } diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 75e81ba26d04..22c012aa5206 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -17,6 +17,7 @@ #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> #include "kvm-s390.h" +#include "gmap.h" bool kvm_s390_pv_is_protected(struct kvm *kvm) { @@ -638,10 +639,28 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, .tweak[1] = offset, }; int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb); + unsigned long vmaddr; + bool unlocked; *rc = uvcb.header.rc; *rrc = uvcb.header.rrc; + if (ret == -ENXIO) { + mmap_read_lock(kvm->mm); + vmaddr = gfn_to_hva(kvm, gpa_to_gfn(addr)); + if (kvm_is_error_hva(vmaddr)) { + ret = -EFAULT; + } else { + ret = fixup_user_fault(kvm->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); + if (!ret) + ret = __gmap_link(kvm->arch.gmap, addr, vmaddr); + } + mmap_read_unlock(kvm->mm); + if (!ret) + return -EAGAIN; + return ret; + } + if (ret && ret != -EAGAIN) KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", uvcb.gaddr, *rc, *rrc); @@ -660,6 +679,8 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx", addr, size); + guard(srcu)(&kvm->srcu); + while (offset < size) { ret = unpack_one(kvm, addr, tweak, offset, rc, rrc); if (ret == -EAGAIN) { diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index d9696b530064..55c34cb35428 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -172,7 +172,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, * first page, since address is 8k aligned and memory pieces are always * at least 1MB aligned and have at least a size of 1MB. */ - if (kvm_is_error_gpa(vcpu->kvm, irq.u.prefix.address)) { + if (!kvm_is_gpa_in_memslot(vcpu->kvm, irq.u.prefix.address)) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INVALID_PARAMETER; return SIGP_CC_STATUS_STORED; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 3af3bd20ac7b..a78df3a4f353 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -12,16 +12,22 @@ #include <linux/list.h> #include <linux/bitmap.h> #include <linux/sched/signal.h> +#include <linux/io.h> +#include <linux/mman.h> #include <asm/gmap.h> #include <asm/mmu_context.h> #include <asm/sclp.h> #include <asm/nmi.h> #include <asm/dis.h> -#include <asm/fpu/api.h> #include <asm/facility.h> #include "kvm-s390.h" #include "gaccess.h" +#include "gmap.h" + +enum vsie_page_flags { + VSIE_PAGE_IN_USE = 0, +}; struct vsie_page { struct kvm_s390_sie_block scb_s; /* 0x0000 */ @@ -46,7 +52,18 @@ struct vsie_page { gpa_t gvrd_gpa; /* 0x0240 */ gpa_t riccbd_gpa; /* 0x0248 */ gpa_t sdnx_gpa; /* 0x0250 */ - __u8 reserved[0x0700 - 0x0258]; /* 0x0258 */ + /* + * guest address of the original SCB. Remains set for free vsie + * pages, so we can properly look them up in our addr_to_page + * radix tree. + */ + gpa_t scb_gpa; /* 0x0258 */ + /* + * Flags: must be set/cleared atomically after the vsie page can be + * looked up by other CPUs. + */ + unsigned long flags; /* 0x0260 */ + __u8 reserved[0x0700 - 0x0268]; /* 0x0268 */ struct kvm_s390_crypto_cb crycb; /* 0x0700 */ __u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */ }; @@ -335,7 +352,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) /* we may only allow it if enabled for guest 2 */ ecb3_flags = scb_o->ecb3 & vcpu->arch.sie_block->ecb3 & (ECB3_AES | ECB3_DEA); - ecd_flags = scb_o->ecd & vcpu->arch.sie_block->ecd & ECD_ECC; + ecd_flags = scb_o->ecd & vcpu->arch.sie_block->ecd & + (ECD_ECC | ECD_HMAC); if (!ecb3_flags && !ecd_flags) goto end; @@ -362,7 +380,7 @@ end: case -EACCES: return set_validity_icpt(scb_s, 0x003CU); } - scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT2; + scb_s->crycbd = (u32)virt_to_phys(&vsie_page->crycb) | CRYCB_FORMAT2; return 0; } @@ -583,7 +601,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct vsie_page *cur; unsigned long prefix; - struct page *page; int i; if (!gmap_is_shadow(gmap)) @@ -593,10 +610,9 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start, * therefore we can safely reference them all the time. */ for (i = 0; i < kvm->arch.vsie.page_count; i++) { - page = READ_ONCE(kvm->arch.vsie.pages[i]); - if (!page) + cur = READ_ONCE(kvm->arch.vsie.pages[i]); + if (!cur) continue; - cur = page_to_virt(page); if (READ_ONCE(cur->gmap) != gmap) continue; prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT; @@ -661,7 +677,7 @@ static int pin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t *hpa) struct page *page; page = gfn_to_page(kvm, gpa_to_gfn(gpa)); - if (is_error_page(page)) + if (!page) return -EINVAL; *hpa = (hpa_t)page_to_phys(page) + (gpa & ~PAGE_MASK); return 0; @@ -670,7 +686,7 @@ static int pin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t *hpa) /* Unpins a page previously pinned via pin_guest_page, marking it as dirty. */ static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa) { - kvm_release_pfn_dirty(hpa >> PAGE_SHIFT); + kvm_release_page_dirty(pfn_to_page(hpa >> PAGE_SHIFT)); /* mark the page always as dirty for migration */ mark_page_dirty(kvm, gpa_to_gfn(gpa)); } @@ -853,7 +869,7 @@ unpin: static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, gpa_t gpa) { - hpa_t hpa = (hpa_t) vsie_page->scb_o; + hpa_t hpa = virt_to_phys(vsie_page->scb_o); if (hpa) unpin_guest_page(vcpu->kvm, gpa, hpa); @@ -922,19 +938,19 @@ static int handle_fault(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { int rc; - if (current->thread.gmap_int_code == PGM_PROTECTION) + if ((current->thread.gmap_int_code & PGM_INT_CODE_MASK) == PGM_PROTECTION) /* we can directly forward all protection exceptions */ return inject_fault(vcpu, PGM_PROTECTION, - current->thread.gmap_addr, 1); + current->thread.gmap_teid.addr * PAGE_SIZE, 1); rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, - current->thread.gmap_addr, NULL); + current->thread.gmap_teid.addr * PAGE_SIZE, NULL); if (rc > 0) { rc = inject_fault(vcpu, rc, - current->thread.gmap_addr, - current->thread.gmap_write_flag); + current->thread.gmap_teid.addr * PAGE_SIZE, + kvm_s390_cur_gmap_fault_is_write()); if (rc >= 0) - vsie_page->fault_addr = current->thread.gmap_addr; + vsie_page->fault_addr = current->thread.gmap_teid.addr * PAGE_SIZE; } return rc; } @@ -1006,7 +1022,7 @@ static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (read_guest_real(vcpu, fac, &vsie_page->fac, stfle_size() * sizeof(u64))) return set_validity_icpt(scb_s, 0x1090U); - scb_s->fac = (__u32)(__u64) &vsie_page->fac; + scb_s->fac = (u32)virt_to_phys(&vsie_page->fac); } return 0; } @@ -1148,11 +1164,10 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) * also kick the vSIE. */ vcpu->arch.sie_block->prog0c |= PROG_IN_SIE; + current->thread.gmap_int_code = 0; barrier(); - if (test_cpu_flag(CIF_FPU)) - load_fpu_regs(); if (!kvm_s390_vcpu_sie_inhibited(vcpu)) - rc = sie64a(scb_s, vcpu->run->s.regs.gprs); + rc = sie64a(scb_s, vcpu->run->s.regs.gprs, vsie_page->gmap->asce); barrier(); vcpu->arch.sie_block->prog0c &= ~PROG_IN_SIE; @@ -1174,7 +1189,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (rc > 0) rc = 0; /* we could still have an icpt */ - else if (rc == -EFAULT) + else if (current->thread.gmap_int_code) return handle_fault(vcpu, vsie_page); switch (scb_s->icptcode) { @@ -1297,19 +1312,31 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (!rc) rc = map_prefix(vcpu, vsie_page); if (!rc) { - gmap_enable(vsie_page->gmap); update_intervention_requests(vsie_page); rc = do_vsie_run(vcpu, vsie_page); - gmap_enable(vcpu->arch.gmap); } atomic_andnot(PROG_BLOCK_SIE, &scb_s->prog20); if (rc == -EAGAIN) rc = 0; - if (rc || scb_s->icptcode || signal_pending(current) || + + /* + * Exit the loop if the guest needs to process the intercept + */ + if (rc || scb_s->icptcode) + break; + + /* + * Exit the loop if the host needs to process an intercept, + * but rewind the PSW to re-enter SIE once that's completed + * instead of passing a "no action" intercept to the guest. + */ + if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0) || - kvm_s390_vcpu_sie_inhibited(vcpu)) + kvm_s390_vcpu_sie_inhibited(vcpu)) { + kvm_s390_rewind_psw(vcpu, 4); break; + } cond_resched(); } @@ -1333,6 +1360,20 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return rc; } +/* Try getting a given vsie page, returning "true" on success. */ +static inline bool try_get_vsie_page(struct vsie_page *vsie_page) +{ + if (test_bit(VSIE_PAGE_IN_USE, &vsie_page->flags)) + return false; + return !test_and_set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); +} + +/* Put a vsie page acquired through get_vsie_page / try_get_vsie_page. */ +static void put_vsie_page(struct vsie_page *vsie_page) +{ + clear_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); +} + /* * Get or create a vsie page for a scb address. * @@ -1343,16 +1384,21 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) { struct vsie_page *vsie_page; - struct page *page; int nr_vcpus; rcu_read_lock(); - page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9); + vsie_page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9); rcu_read_unlock(); - if (page) { - if (page_ref_inc_return(page) == 2) - return page_to_virt(page); - page_ref_dec(page); + if (vsie_page) { + if (try_get_vsie_page(vsie_page)) { + if (vsie_page->scb_gpa == addr) + return vsie_page; + /* + * We raced with someone reusing + putting this vsie + * page before we grabbed it. + */ + put_vsie_page(vsie_page); + } } /* @@ -1363,36 +1409,40 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) mutex_lock(&kvm->arch.vsie.mutex); if (kvm->arch.vsie.page_count < nr_vcpus) { - page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA); - if (!page) { + vsie_page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA); + if (!vsie_page) { mutex_unlock(&kvm->arch.vsie.mutex); return ERR_PTR(-ENOMEM); } - page_ref_inc(page); - kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page; + __set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); + kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = vsie_page; kvm->arch.vsie.page_count++; } else { /* reuse an existing entry that belongs to nobody */ while (true) { - page = kvm->arch.vsie.pages[kvm->arch.vsie.next]; - if (page_ref_inc_return(page) == 2) + vsie_page = kvm->arch.vsie.pages[kvm->arch.vsie.next]; + if (try_get_vsie_page(vsie_page)) break; - page_ref_dec(page); kvm->arch.vsie.next++; kvm->arch.vsie.next %= nr_vcpus; } - radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9); + if (vsie_page->scb_gpa != ULONG_MAX) + radix_tree_delete(&kvm->arch.vsie.addr_to_page, + vsie_page->scb_gpa >> 9); } - page->index = addr; - /* double use of the same address */ - if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) { - page_ref_dec(page); + /* Mark it as invalid until it resides in the tree. */ + vsie_page->scb_gpa = ULONG_MAX; + + /* Double use of the same address or allocation failure. */ + if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, + vsie_page)) { + put_vsie_page(vsie_page); mutex_unlock(&kvm->arch.vsie.mutex); return NULL; } + vsie_page->scb_gpa = addr; mutex_unlock(&kvm->arch.vsie.mutex); - vsie_page = page_to_virt(page); memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block)); release_gmap_shadow(vsie_page); vsie_page->fault_addr = 0; @@ -1400,14 +1450,6 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) return vsie_page; } -/* put a vsie page acquired via get_vsie_page */ -static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page) -{ - struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT); - - page_ref_dec(page); -} - int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu) { struct vsie_page *vsie_page; @@ -1428,8 +1470,10 @@ int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0) || - kvm_s390_vcpu_sie_inhibited(vcpu)) + kvm_s390_vcpu_sie_inhibited(vcpu)) { + kvm_s390_rewind_psw(vcpu, 4); return 0; + } vsie_page = get_vsie_page(vcpu->kvm, scb_addr); if (IS_ERR(vsie_page)) @@ -1456,7 +1500,7 @@ out_unshadow: out_unpin_scb: unpin_scb(vcpu, vsie_page, scb_addr); out_put: - put_vsie_page(vcpu->kvm, vsie_page); + put_vsie_page(vsie_page); return rc < 0 ? rc : 0; } @@ -1472,18 +1516,18 @@ void kvm_s390_vsie_init(struct kvm *kvm) void kvm_s390_vsie_destroy(struct kvm *kvm) { struct vsie_page *vsie_page; - struct page *page; int i; mutex_lock(&kvm->arch.vsie.mutex); for (i = 0; i < kvm->arch.vsie.page_count; i++) { - page = kvm->arch.vsie.pages[i]; + vsie_page = kvm->arch.vsie.pages[i]; kvm->arch.vsie.pages[i] = NULL; - vsie_page = page_to_virt(page); release_gmap_shadow(vsie_page); /* free the radix tree entry */ - radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9); - __free_page(page); + if (vsie_page->scb_gpa != ULONG_MAX) + radix_tree_delete(&kvm->arch.vsie.addr_to_page, + vsie_page->scb_gpa >> 9); + free_page((unsigned long)vsie_page); } kvm->arch.vsie.page_count = 0; mutex_unlock(&kvm->arch.vsie.mutex); |