From e300614f10bd2f33252c8ba40b34d6c3fbf95d72 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:53 -0400 Subject: KVM: cleanup and add shortcuts to kvm_range_has_memory_attributes() Use a guard to simplify early returns, and add two more easy shortcuts. If the requested attributes are invalid, the attributes xarray will never show them as set. And if testing a single page, kvm_get_memory_attributes() is more efficient. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 42 ++++++++++++++++++++---------------------- 1 file changed, 20 insertions(+), 22 deletions(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d0788d0a72cc..30328ff2d840 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2398,6 +2398,14 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static u64 kvm_supported_mem_attributes(struct kvm *kvm) +{ + if (!kvm || kvm_arch_has_private_mem(kvm)) + return KVM_MEMORY_ATTRIBUTE_PRIVATE; + + return 0; +} + /* * Returns true if _all_ gfns in the range [@start, @end) have attributes * matching @attrs. @@ -2406,40 +2414,30 @@ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); + unsigned long mask = kvm_supported_mem_attributes(kvm); unsigned long index; - bool has_attrs; void *entry; - rcu_read_lock(); + if (attrs & ~mask) + return false; - if (!attrs) { - has_attrs = !xas_find(&xas, end - 1); - goto out; - } + if (end == start + 1) + return kvm_get_memory_attributes(kvm, start) == attrs; + + guard(rcu)(); + if (!attrs) + return !xas_find(&xas, end - 1); - has_attrs = true; for (index = start; index < end; index++) { do { entry = xas_next(&xas); } while (xas_retry(&xas, entry)); - if (xas.xa_index != index || xa_to_value(entry) != attrs) { - has_attrs = false; - break; - } + if (xas.xa_index != index || xa_to_value(entry) != attrs) + return false; } -out: - rcu_read_unlock(); - return has_attrs; -} - -static u64 kvm_supported_mem_attributes(struct kvm *kvm) -{ - if (!kvm || kvm_arch_has_private_mem(kvm)) - return KVM_MEMORY_ATTRIBUTE_PRIVATE; - - return 0; + return true; } static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, -- cgit From 4b5f67120a88c713b82907d55a767693382e9e9d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:54 -0400 Subject: KVM: extend kvm_range_has_memory_attributes() to check subset of attributes While currently there is no other attribute than KVM_MEMORY_ATTRIBUTE_PRIVATE, KVM code such as kvm_mem_is_private() is written to expect their existence. Allow using kvm_range_has_memory_attributes() as a multi-page version of kvm_mem_is_private(), without it breaking later when more attributes are introduced. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 30328ff2d840..92901656a0d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2408,21 +2408,21 @@ static u64 kvm_supported_mem_attributes(struct kvm *kvm) /* * Returns true if _all_ gfns in the range [@start, @end) have attributes - * matching @attrs. + * such that the bits in @mask match @attrs. */ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs) + unsigned long mask, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); - unsigned long mask = kvm_supported_mem_attributes(kvm); unsigned long index; void *entry; + mask &= kvm_supported_mem_attributes(kvm); if (attrs & ~mask) return false; if (end == start + 1) - return kvm_get_memory_attributes(kvm, start) == attrs; + return (kvm_get_memory_attributes(kvm, start) & mask) == attrs; guard(rcu)(); if (!attrs) @@ -2433,7 +2433,8 @@ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, entry = xas_next(&xas); } while (xas_retry(&xas, entry)); - if (xas.xa_index != index || xa_to_value(entry) != attrs) + if (xas.xa_index != index || + (xa_to_value(entry) & mask) != attrs) return false; } @@ -2532,7 +2533,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, mutex_lock(&kvm->slots_lock); /* Nothing to do if the entire range as the desired attributes. */ - if (kvm_range_has_memory_attributes(kvm, start, end, attributes)) + if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) goto out_unlock; /* -- cgit From 66155de93bcf4f2967e602a4b3bf7ebe58f34b11 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 9 Aug 2024 12:02:58 -0700 Subject: KVM: x86: Disallow read-only memslots for SEV-ES and SEV-SNP (and TDX) Disallow read-only memslots for SEV-{ES,SNP} VM types, as KVM can't directly emulate instructions for ES/SNP, and instead the guest must explicitly request emulation. Unless the guest explicitly requests emulation without accessing memory, ES/SNP relies on KVM creating an MMIO SPTE, with the subsequent #NPF being reflected into the guest as a #VC. But for read-only memslots, KVM deliberately doesn't create MMIO SPTEs, because except for ES/SNP, doing so requires setting reserved bits in the SPTE, i.e. the SPTE can't be readable while also generating a #VC on writes. Because KVM never creates MMIO SPTEs and jumps directly to emulation, the guest never gets a #VC. And since KVM simply resumes the guest if ES/SNP guests trigger emulation, KVM effectively puts the vCPU into an infinite #NPF loop if the vCPU attempts to write read-only memory. Disallow read-only memory for all VMs with protected state, i.e. for upcoming TDX VMs as well as ES/SNP VMs. For TDX, it's actually possible to support read-only memory, as TDX uses EPT Violation #VE to reflect the fault into the guest, e.g. KVM could configure read-only SPTEs with RX protections and SUPPRESS_VE=0. But there is no strong use case for supporting read-only memslots on TDX, e.g. the main historical usage is to emulate option ROMs, but TDX disallows executing from shared memory. And if someone comes along with a legitimate, strong use case, the restriction can always be lifted for TDX. Don't bother trying to retroactively apply the restriction to SEV-ES VMs that are created as type KVM_X86_DEFAULT_VM. Read-only memslots can't possibly work for SEV-ES, i.e. disallowing such memslots is really just means reporting an error to userspace instead of silently hanging vCPUs. Trying to deal with the ordering between KVM_SEV_INIT and memslot creation isn't worth the marginal benefit it would provide userspace. Fixes: 26c44aa9e076 ("KVM: SEV: define VM types for SEV and SEV-ES") Fixes: 1dfe571c12cf ("KVM: SEV: Add initial SEV-SNP support") Cc: Peter Gonda Cc: Michael Roth Cc: Vishal Annapurve Cc: Ackerly Tng Signed-off-by: Sean Christopherson Message-ID: <20240809190319.1710470-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'virt/kvm/kvm_main.c') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 92901656a0d4..cb2b78e92910 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1578,15 +1578,14 @@ static int check_memory_region_flags(struct kvm *kvm, if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; -#ifdef CONFIG_HAVE_KVM_READONLY_MEM /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ - if (!(mem->flags & KVM_MEM_GUEST_MEMFD)) + if (kvm_arch_has_readonly_mem(kvm) && + !(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; -#endif if (mem->flags & ~valid_flags) return -EINVAL; -- cgit