In some cases, like with SEV-SNP, guest memory needs to be updated in a
platform-specific manner before it can be safely freed back to the host.
Wire up arch-defined hooks to the .free_folio kvm_gmem_aops callback to
allow for special handling of this sort when freeing memory in response
to FALLOC_FL_PUNCH_HOLE operations and when releasing the inode, and go
ahead and define an arch-specific hook for x86 since it will be needed
for handling memory used for SEV-SNP guests.
Signed-off-by: Michael Roth <michael.roth@xxxxxxx>
---
arch/x86/include/asm/kvm-x86-ops.h | 1 +
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/x86.c | 7 +++++++
include/linux/kvm_host.h | 4 ++++
virt/kvm/Kconfig | 4 ++++
virt/kvm/guest_memfd.c | 14 ++++++++++++++
6 files changed, 31 insertions(+)
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 0c113f42d5c7..f1505a5fa781 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -135,6 +135,7 @@ KVM_X86_OP(complete_emulated_msr)
KVM_X86_OP(vcpu_deliver_sipi_vector)
KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
+KVM_X86_OP_OPTIONAL(gmem_invalidate)
#undef KVM_X86_OP
#undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 66fc89d1858f..dbec74783f48 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1754,6 +1754,7 @@ struct kvm_x86_ops {
unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
+ void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end);
};
struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 33a4cc33d86d..0e95c3a95e59 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13308,6 +13308,13 @@ int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_ord
}
#endif
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
+{
+ static_call_cond(kvm_x86_gmem_invalidate)(start, end);
+}
+#endif
+
int kvm_spec_ctrl_test_value(u64 value)
{
/*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c7f82c2f1bcf..840a5be5962a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2429,4 +2429,8 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
#endif
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
+#endif
+
#endif
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 992cf6ed86ef..7fd1362a7ebe 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -113,3 +113,7 @@ config KVM_GENERIC_PRIVATE_MEM
config HAVE_KVM_GMEM_PREPARE
bool
depends on KVM_PRIVATE_MEM
+
+config HAVE_KVM_GMEM_INVALIDATE
+ bool
+ depends on KVM_PRIVATE_MEM
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 72ff8b7b31d5..b4c4df259fb8 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -369,12 +369,26 @@ static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
return MF_DELAYED;
}
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+static void kvm_gmem_free_folio(struct folio *folio)
+{
+ struct page *page = folio_page(folio, 0);
+ kvm_pfn_t pfn = page_to_pfn(page);
+ int order = folio_order(folio);
+
+ kvm_arch_gmem_invalidate(pfn, pfn + (1ul << order));
+}
+#endif
+
static const struct address_space_operations kvm_gmem_aops = {
.dirty_folio = noop_dirty_folio,
#ifdef CONFIG_MIGRATION
.migrate_folio = kvm_gmem_migrate_folio,
#endif
.error_remove_page = kvm_gmem_error_page,
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+ .free_folio = kvm_gmem_free_folio,
+#endif
};
static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
--
2.25.1
