| Message ID | 20220310140911.50924-13-chao.p.peng@linux.intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | KVM: mm: fd-based approach for supporting KVM guest private memory | expand |
On Thu, Mar 10, 2022, Chao Peng wrote: > KVM_MEM_PRIVATE is not exposed by default but architecture code can turn > on it by implementing kvm_arch_private_memory_supported(). > > Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com> > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > --- > include/linux/kvm_host.h | 1 + > virt/kvm/kvm_main.c | 24 +++++++++++++++++++----- > 2 files changed, 20 insertions(+), 5 deletions(-) > > diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h > index 186b9b981a65..0150e952a131 100644 > --- a/include/linux/kvm_host.h > +++ b/include/linux/kvm_host.h > @@ -1432,6 +1432,7 @@ bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); > int kvm_arch_post_init_vm(struct kvm *kvm); > void kvm_arch_pre_destroy_vm(struct kvm *kvm); > int kvm_arch_create_vm_debugfs(struct kvm *kvm); > +bool kvm_arch_private_memory_supported(struct kvm *kvm); > > #ifndef __KVM_HAVE_ARCH_VM_ALLOC > /* > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c > index 52319f49d58a..df5311755a40 100644 > --- a/virt/kvm/kvm_main.c > +++ b/virt/kvm/kvm_main.c > @@ -1485,10 +1485,19 @@ static void kvm_replace_memslot(struct kvm *kvm, > } > } > > -static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) > +bool __weak kvm_arch_private_memory_supported(struct kvm *kvm) > +{ > + return false; > +} > + > +static int check_memory_region_flags(struct kvm *kvm, > + const struct kvm_userspace_memory_region *mem) > { > u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; > > + if (kvm_arch_private_memory_supported(kvm)) > + valid_flags |= KVM_MEM_PRIVATE; > + > #ifdef __KVM_HAVE_READONLY_MEM > valid_flags |= KVM_MEM_READONLY; > #endif > @@ -1900,7 +1909,7 @@ int __kvm_set_memory_region(struct kvm *kvm, > int as_id, id; > int r; > > - r = check_memory_region_flags(mem); > + r = check_memory_region_flags(kvm, mem); > if (r) > return r; > > @@ -1913,10 +1922,12 @@ int __kvm_set_memory_region(struct kvm *kvm, > return -EINVAL; > if (mem->guest_phys_addr & (PAGE_SIZE - 1)) > return -EINVAL; > - /* We can read the guest memory with __xxx_user() later on. */ > if ((mem->userspace_addr & (PAGE_SIZE - 1)) || > - (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || > - !access_ok((void __user *)(unsigned long)mem->userspace_addr, > + (mem->userspace_addr != untagged_addr(mem->userspace_addr))) > + return -EINVAL; > + /* We can read the guest memory with __xxx_user() later on. */ > + if (!(mem->flags & KVM_MEM_PRIVATE) && > + !access_ok((void __user *)(unsigned long)mem->userspace_addr, This should sanity check private_offset for private memslots. At a bare minimum, wrapping should be disallowed. > mem->memory_size)) > return -EINVAL; > if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) > @@ -1957,6 +1968,9 @@ int __kvm_set_memory_region(struct kvm *kvm, > if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) > return -EINVAL; > } else { /* Modify an existing slot. */ > + /* Private memslots are immutable, they can only be deleted. */ > + if (mem->flags & KVM_MEM_PRIVATE) > + return -EINVAL; These sanity checks belong in "KVM: Register private memslot to memory backing store", e.g. that patch is "broken" without the immutability restriction. It's somewhat moot because the code is unreachable, but it makes reviewing confusing/difficult. But rather than move the sanity checks back, I think I'd prefer to pull all of patch 10 here. I think it also makes sense to drop "KVM: Use memfile_pfn_ops to obtain pfn for private pages" and add the pointer in "struct kvm_memory_slot" in patch "KVM: Extend the memslot to support fd-based private memory", with the use of the ops folded into "KVM: Handle page fault for private memory". Adding code to KVM and KVM-x86 in a single patch is ok, and overall makes things easier to review because the new helpers have a user right away, especially since there will be #ifdeffery. I.e. end up with something like: mm: Introduce memfile_notifier mm/shmem: Restrict MFD_INACCESSIBLE memory against RLIMIT_MEMLOCK KVM: Extend the memslot to support fd-based private memory KVM: Use kvm_userspace_memory_region_ext KVM: Add KVM_EXIT_MEMORY_ERROR exit KVM: Handle page fault for private memory KVM: Register private memslot to memory backing store KVM: Zap existing KVM mappings when pages changed in the private fd KVM: Enable and expose KVM_MEM_PRIVATE > if ((mem->userspace_addr != old->userspace_addr) || > (npages != old->npages) || > ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) > -- > 2.17.1 >
On Tue, Mar 29, 2022 at 07:13:00PM +0000, Sean Christopherson wrote: > On Thu, Mar 10, 2022, Chao Peng wrote: > > KVM_MEM_PRIVATE is not exposed by default but architecture code can turn > > on it by implementing kvm_arch_private_memory_supported(). > > > > Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com> > > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > > --- > > include/linux/kvm_host.h | 1 + > > virt/kvm/kvm_main.c | 24 +++++++++++++++++++----- > > 2 files changed, 20 insertions(+), 5 deletions(-) > > > > diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h > > index 186b9b981a65..0150e952a131 100644 > > --- a/include/linux/kvm_host.h > > +++ b/include/linux/kvm_host.h > > @@ -1432,6 +1432,7 @@ bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); > > int kvm_arch_post_init_vm(struct kvm *kvm); > > void kvm_arch_pre_destroy_vm(struct kvm *kvm); > > int kvm_arch_create_vm_debugfs(struct kvm *kvm); > > +bool kvm_arch_private_memory_supported(struct kvm *kvm); > > > > #ifndef __KVM_HAVE_ARCH_VM_ALLOC > > /* > > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c > > index 52319f49d58a..df5311755a40 100644 > > --- a/virt/kvm/kvm_main.c > > +++ b/virt/kvm/kvm_main.c > > @@ -1485,10 +1485,19 @@ static void kvm_replace_memslot(struct kvm *kvm, > > } > > } > > > > -static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) > > +bool __weak kvm_arch_private_memory_supported(struct kvm *kvm) > > +{ > > + return false; > > +} > > + > > +static int check_memory_region_flags(struct kvm *kvm, > > + const struct kvm_userspace_memory_region *mem) > > { > > u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; > > > > + if (kvm_arch_private_memory_supported(kvm)) > > + valid_flags |= KVM_MEM_PRIVATE; > > + > > #ifdef __KVM_HAVE_READONLY_MEM > > valid_flags |= KVM_MEM_READONLY; > > #endif > > @@ -1900,7 +1909,7 @@ int __kvm_set_memory_region(struct kvm *kvm, > > int as_id, id; > > int r; > > > > - r = check_memory_region_flags(mem); > > + r = check_memory_region_flags(kvm, mem); > > if (r) > > return r; > > > > @@ -1913,10 +1922,12 @@ int __kvm_set_memory_region(struct kvm *kvm, > > return -EINVAL; > > if (mem->guest_phys_addr & (PAGE_SIZE - 1)) > > return -EINVAL; > > - /* We can read the guest memory with __xxx_user() later on. */ > > if ((mem->userspace_addr & (PAGE_SIZE - 1)) || > > - (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || > > - !access_ok((void __user *)(unsigned long)mem->userspace_addr, > > + (mem->userspace_addr != untagged_addr(mem->userspace_addr))) > > + return -EINVAL; > > + /* We can read the guest memory with __xxx_user() later on. */ > > + if (!(mem->flags & KVM_MEM_PRIVATE) && > > + !access_ok((void __user *)(unsigned long)mem->userspace_addr, > > This should sanity check private_offset for private memslots. At a bare minimum, > wrapping should be disallowed. Will add this. > > > mem->memory_size)) > > return -EINVAL; > > if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) > > @@ -1957,6 +1968,9 @@ int __kvm_set_memory_region(struct kvm *kvm, > > if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) > > return -EINVAL; > > } else { /* Modify an existing slot. */ > > + /* Private memslots are immutable, they can only be deleted. */ > > + if (mem->flags & KVM_MEM_PRIVATE) > > + return -EINVAL; > > These sanity checks belong in "KVM: Register private memslot to memory backing store", > e.g. that patch is "broken" without the immutability restriction. It's somewhat moot > because the code is unreachable, but it makes reviewing confusing/difficult. > > But rather than move the sanity checks back, I think I'd prefer to pull all of patch 10 > here. I think it also makes sense to drop "KVM: Use memfile_pfn_ops to obtain pfn for > private pages" and add the pointer in "struct kvm_memory_slot" in patch "KVM: Extend the > memslot to support fd-based private memory", with the use of the ops folded into > "KVM: Handle page fault for private memory". Adding code to KVM and KVM-x86 in a single > patch is ok, and overall makes things easier to review because the new helpers have a > user right away, especially since there will be #ifdeffery. > > I.e. end up with something like: > > mm: Introduce memfile_notifier > mm/shmem: Restrict MFD_INACCESSIBLE memory against RLIMIT_MEMLOCK > KVM: Extend the memslot to support fd-based private memory > KVM: Use kvm_userspace_memory_region_ext > KVM: Add KVM_EXIT_MEMORY_ERROR exit > KVM: Handle page fault for private memory > KVM: Register private memslot to memory backing store > KVM: Zap existing KVM mappings when pages changed in the private fd > KVM: Enable and expose KVM_MEM_PRIVATE Thanks for the suggestion. That makes sense. Chao > > > if ((mem->userspace_addr != old->userspace_addr) || > > (npages != old->npages) || > > ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) > > -- > > 2.17.1 > >
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 186b9b981a65..0150e952a131 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1432,6 +1432,7 @@ bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); int kvm_arch_create_vm_debugfs(struct kvm *kvm); +bool kvm_arch_private_memory_supported(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 52319f49d58a..df5311755a40 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1485,10 +1485,19 @@ static void kvm_replace_memslot(struct kvm *kvm, } } -static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) +bool __weak kvm_arch_private_memory_supported(struct kvm *kvm) +{ + return false; +} + +static int check_memory_region_flags(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; + if (kvm_arch_private_memory_supported(kvm)) + valid_flags |= KVM_MEM_PRIVATE; + #ifdef __KVM_HAVE_READONLY_MEM valid_flags |= KVM_MEM_READONLY; #endif @@ -1900,7 +1909,7 @@ int __kvm_set_memory_region(struct kvm *kvm, int as_id, id; int r; - r = check_memory_region_flags(mem); + r = check_memory_region_flags(kvm, mem); if (r) return r; @@ -1913,10 +1922,12 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) return -EINVAL; - /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || - (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || - !access_ok((void __user *)(unsigned long)mem->userspace_addr, + (mem->userspace_addr != untagged_addr(mem->userspace_addr))) + return -EINVAL; + /* We can read the guest memory with __xxx_user() later on. */ + if (!(mem->flags & KVM_MEM_PRIVATE) && + !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL; if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) @@ -1957,6 +1968,9 @@ int __kvm_set_memory_region(struct kvm *kvm, if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) return -EINVAL; } else { /* Modify an existing slot. */ + /* Private memslots are immutable, they can only be deleted. */ + if (mem->flags & KVM_MEM_PRIVATE) + return -EINVAL; if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) || ((mem->flags ^ old->flags) & KVM_MEM_READONLY))