diff options
Diffstat (limited to 'arch/s390/kvm')
| -rw-r--r-- | arch/s390/kvm/Makefile | 2 | ||||
| -rw-r--r-- | arch/s390/kvm/gaccess.c | 44 | ||||
| -rw-r--r-- | arch/s390/kvm/gmap-vsie.c | 142 | ||||
| -rw-r--r-- | arch/s390/kvm/gmap.c | 212 | ||||
| -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 | 19 | ||||
| -rw-r--r-- | arch/s390/kvm/kvm-s390.c | 237 | ||||
| -rw-r--r-- | arch/s390/kvm/kvm-s390.h | 19 | ||||
| -rw-r--r-- | arch/s390/kvm/pv.c | 21 | ||||
| -rw-r--r-- | arch/s390/kvm/vsie.c | 106 |
11 files changed, 757 insertions, 91 deletions
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/gaccess.c b/arch/s390/kvm/gaccess.c index 9816b0060fbe..f6fded15633a 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -16,6 +16,7 @@ #include <asm/gmap.h> #include <asm/dat-bits.h> #include "kvm-s390.h" +#include "gmap.h" #include "gaccess.h" /* @@ -1393,6 +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 @@ -1415,6 +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 @@ -1423,7 +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/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..02adf151d4de --- /dev/null +++ b/arch/s390/kvm/gmap.c @@ -0,0 +1,212 @@ +// 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" + +/** + * should_export_before_import - Determine whether an export is needed + * before an import-like operation + * @uvcb: the Ultravisor control block of the UVC to be performed + * @mm: the mm of the process + * + * Returns whether an export is needed before every import-like operation. + * This is needed for shared pages, which don't trigger a secure storage + * exception when accessed from a different guest. + * + * Although considered as one, the Unpin Page UVC is not an actual import, + * so it is not affected. + * + * No export is needed also when there is only one protected VM, because the + * page cannot belong to the wrong VM in that case (there is no "other VM" + * it can belong to). + * + * Return: true if an export is needed before every import, otherwise false. + */ +static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm) +{ + /* + * The misc feature indicates, among other things, that importing a + * shared page from a different protected VM will automatically also + * transfer its ownership. + */ + if (uv_has_feature(BIT_UV_FEAT_MISC)) + return false; + if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED) + return false; + return atomic_read(&mm->context.protected_count) > 1; +} + +static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb) +{ + struct folio *folio = page_folio(page); + int rc; + + /* + * Secure pages cannot be huge and userspace should not combine both. + * In case userspace does it anyway this will result in an -EFAULT for + * the unpack. The guest is thus never reaching secure mode. + * If userspace plays dirty tricks and decides to map huge pages at a + * later point in time, it will receive a segmentation fault or + * KVM_RUN will return -EFAULT. + */ + if (folio_test_hugetlb(folio)) + return -EFAULT; + if (folio_test_large(folio)) { + mmap_read_unlock(gmap->mm); + rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true); + mmap_read_lock(gmap->mm); + if (rc) + return rc; + folio = page_folio(page); + } + + if (!folio_trylock(folio)) + return -EAGAIN; + if (should_export_before_import(uvcb, gmap->mm)) + uv_convert_from_secure(folio_to_phys(folio)); + rc = make_folio_secure(folio, uvcb); + folio_unlock(folio); + + /* + * In theory a race is possible and the folio might have become + * large again before the folio_trylock() above. In that case, no + * action is performed and -EAGAIN is returned; the callers will + * have to try again later. + * In most cases this implies running the VM again, getting the same + * exception again, and make another attempt in this function. + * This is expected to happen extremely rarely. + */ + if (rc == -E2BIG) + return -EAGAIN; + /* The folio has too many references, try to shake some off */ + if (rc == -EBUSY) { + mmap_read_unlock(gmap->mm); + kvm_s390_wiggle_split_folio(gmap->mm, folio, false); + mmap_read_lock(gmap->mm); + return -EAGAIN; + } + + return rc; +} + +/** + * 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 (see __gmap_make_secure()). + */ +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) +{ + struct kvm *kvm = gmap->private; + struct page *page; + int rc = 0; + + lockdep_assert_held(&kvm->srcu); + + page = gfn_to_page(kvm, gpa_to_gfn(gaddr)); + mmap_read_lock(gmap->mm); + if (page) + rc = __gmap_make_secure(gmap, page, uvcb); + kvm_release_page_clean(page); + mmap_read_unlock(gmap->mm); + + return rc; +} + +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 5bbaadf75dc6..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 = gmap_fault(vcpu->arch.gmap, 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 = gmap_fault(vcpu->arch.gmap, dstaddr, FAULT_FLAG_WRITE); + 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 d4f031e086fc..07ff0e10cb7f 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2893,7 +2893,8 @@ 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 */ @@ -2901,14 +2902,16 @@ int kvm_set_routing_entry(struct kvm *kvm, 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 d8080c27d45b..ebecb96bacce 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -50,6 +50,7 @@ #include "kvm-s390.h" #include "gaccess.h" #include "pci.h" +#include "gmap.h" #define CREATE_TRACE_POINTS #include "trace.h" @@ -3428,8 +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; @@ -4498,6 +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: @@ -4513,9 +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; @@ -4766,11 +4847,111 @@ static int vcpu_post_run_addressing_exception(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 = 0; gaddr = current->thread.gmap_teid.addr * PAGE_SIZE; if (kvm_s390_cur_gmap_fault_is_write()) @@ -4781,9 +4962,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) vcpu->stat.exit_null++; break; case PGM_NON_SECURE_STORAGE_ACCESS: - 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_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 @@ -4794,9 +4973,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) break; case PGM_SECURE_STORAGE_ACCESS: case PGM_SECURE_STORAGE_VIOLATION: - 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_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 @@ -4825,40 +5002,15 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) case PGM_REGION_FIRST_TRANS: case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: - 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); - if (vcpu->arch.gmap->pfault_enabled) { - rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT); - if (rc == -EFAULT) - return vcpu_post_run_addressing_exception(vcpu); - if (rc == -EAGAIN) { - trace_kvm_s390_major_guest_pfault(vcpu); - if (kvm_arch_setup_async_pf(vcpu)) - return 0; - vcpu->stat.pfault_sync++; - } else { - return rc; - } - } - rc = gmap_fault(vcpu->arch.gmap, gaddr, flags); - if (rc == -EFAULT) { - if (kvm_is_ucontrol(vcpu->kvm)) { - vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; - vcpu->run->s390_ucontrol.trans_exc_code = gaddr; - vcpu->run->s390_ucontrol.pgm_code = 0x10; - return -EREMOTE; - } - return vcpu_post_run_addressing_exception(vcpu); - } - break; + 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 rc; + return 0; } static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) @@ -5737,7 +5889,9 @@ 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: @@ -5853,7 +6007,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, { gpa_t size; - if (kvm_is_ucontrol(kvm)) + if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS) return -EINVAL; /* When we are protected, we should not change the memory slots */ @@ -5905,6 +6059,9 @@ 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 597d7a71deeb..8d3bbb2dd8d2 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -20,6 +20,8 @@ #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); @@ -279,6 +281,15 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) 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); @@ -408,6 +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); 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/vsie.c b/arch/s390/kvm/vsie.c index a687695d8f68..a78df3a4f353 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -13,6 +13,7 @@ #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> @@ -22,6 +23,11 @@ #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 */ }; @@ -584,7 +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)) @@ -594,10 +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; @@ -1345,6 +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. * @@ -1355,16 +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); + } } /* @@ -1375,36 +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; @@ -1412,14 +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; @@ -1470,7 +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; } @@ -1486,18 +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); |