From: Ackerley Tng <[email protected]> A refcount on the resource_fd is taken only to keep the reference stable for guest_memfd to figure out the existence of a provider. The provider is responsible for pinning anything required to keep the provider's ops and the actual provided resource alive.
.release() is called when this guest_memfd inode is destroyed to allow the provider to clean up. Signed-off-by: Ackerley Tng <[email protected]> --- Documentation/virt/kvm/api.rst | 28 ++++++++++++++--------- include/linux/kvm_host.h | 2 +- include/uapi/linux/kvm.h | 5 ++++- virt/kvm/guest_memfd.c | 51 ++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 72 insertions(+), 14 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 67f0f290797ab..b48df2827a2c3 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6470,7 +6470,9 @@ and cannot be resized (guest_memfd files do however support PUNCH_HOLE). struct kvm_create_guest_memfd { __u64 size; __u64 flags; - __u64 reserved[6]; + __s32 resource_fd; + __u32 pad; + __u64 reserved[5]; }; Conceptually, the inode backing a guest_memfd file represents physical memory, @@ -6492,15 +6494,21 @@ a single guest_memfd file, but the bound ranges must not overlap). The capability KVM_CAP_GUEST_MEMFD_FLAGS enumerates the `flags` that can be specified via KVM_CREATE_GUEST_MEMFD. Currently defined flags: - ============================ ================================================ - GUEST_MEMFD_FLAG_MMAP Enable using mmap() on the guest_memfd file - descriptor. - GUEST_MEMFD_FLAG_INIT_SHARED Make all memory in the file shared during - KVM_CREATE_GUEST_MEMFD (memory files created - without INIT_SHARED will be marked private). - Shared memory can be faulted into host userspace - page tables. Private memory cannot. - ============================ ================================================ + ============================= ================================================ + GUEST_MEMFD_FLAG_MMAP Enable using mmap() on the guest_memfd file + descriptor. + GUEST_MEMFD_FLAG_INIT_SHARED Make all memory in the file shared during + KVM_CREATE_GUEST_MEMFD (memory files created + without INIT_SHARED will be marked private). + Shared memory can be faulted into host userspace + page tables. Private memory cannot. + GUEST_MEMFD_FLAG_USE_RESOURCE Consume resource_fd as an external memory + provider or resource pool. When not set, + resource_fd must be '0'. When set, the provider + must be a supported resource (e.g. tmpfs mount + root directory). Currently, tmpfs resource pools + require noswap and huge=never mount options. + ============================= ================================================ When the KVM MMU performs a PFN lookup to service a guest fault, the fault will always be consumed from guest_memfd, regardless of whether it is a shared or a diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 485f18454eb45..f4241c05650e9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2588,7 +2588,7 @@ bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm); static inline u64 kvm_gmem_get_supported_flags(struct kvm *kvm) { - u64 flags = GUEST_MEMFD_FLAG_MMAP; + u64 flags = GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_USE_RESOURCE; if (!kvm || kvm_arch_supports_gmem_init_shared(kvm)) flags |= GUEST_MEMFD_FLAG_INIT_SHARED; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8dff2fc1972e9..f4108bf7e3192 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1674,11 +1674,14 @@ struct kvm_memory_attributes2 { #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) #define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) #define GUEST_MEMFD_FLAG_INIT_SHARED (1ULL << 1) +#define GUEST_MEMFD_FLAG_USE_RESOURCE (1ULL << 2) struct kvm_create_guest_memfd { __u64 size; __u64 flags; - __u64 reserved[6]; + __s32 resource_fd; + __u32 pad; + __u64 reserved[5]; }; #define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 00f3bd0cf21e6..0e0d7e93f4148 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -71,6 +71,12 @@ static inline void gmem_provider_invalidate_folio(struct gmem_inode *gi, gi->provider_ops->invalidate_folio(gi->provider, folio); } +static inline void gmem_provider_release(struct gmem_inode *gi) +{ + if (gi->provider_ops && gi->provider_ops->release) + gi->provider_ops->release(gi->provider); +} + #define kvm_gmem_for_each_file(f, inode) \ list_for_each_entry(f, &GMEM_I(inode)->gmem_file_list, entry) @@ -984,7 +990,37 @@ static int kvm_gmem_init_inode(struct inode *inode, loff_t size, u64 flags) return r; } -static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) +static int kvm_gmem_attach_resource(struct inode *inode, int resource_fd) +{ + struct file *resource_file; + struct inode *res_inode; + const struct guest_memfd_provider_operations *ops = NULL; + void *provider; + + resource_file = fget_raw(resource_fd); + if (!resource_file) + return -EBADF; + + res_inode = file_inode(resource_file); + ops = res_inode->i_sb->s_op->gmem_provider_ops; + + if (!ops || !ops->attach || !ops->alloc_folio) { + fput(resource_file); + return -EOPNOTSUPP; + } + + provider = ops->attach(resource_file); + fput(resource_file); + if (IS_ERR(provider)) + return PTR_ERR(provider); + + GMEM_I(inode)->provider = provider; + GMEM_I(inode)->provider_ops = ops; + + return 0; +} + +static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags, int resource_fd) { static const char *name = "[kvm-gmem]"; struct gmem_file *f; @@ -1018,6 +1054,12 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) if (err) goto err_inode; + if (flags & GUEST_MEMFD_FLAG_USE_RESOURCE) { + err = kvm_gmem_attach_resource(inode, resource_fd); + if (err) + goto err_inode; + } + file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR, &kvm_gmem_fops); if (IS_ERR(file)) { err = PTR_ERR(file); @@ -1057,7 +1099,10 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args) if (size <= 0 || !PAGE_ALIGNED(size)) return -EINVAL; - return __kvm_gmem_create(kvm, size, flags); + if (!(flags & GUEST_MEMFD_FLAG_USE_RESOURCE) && args->resource_fd) + return -EINVAL; + + return __kvm_gmem_create(kvm, size, flags, args->resource_fd); } int kvm_gmem_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -1401,6 +1446,8 @@ static void kvm_gmem_destroy_inode(struct inode *inode) { struct gmem_inode *gi = GMEM_I(inode); + gmem_provider_release(gi); + mpol_free_shared_policy(&gi->policy); /* -- 2.56.0.rc1.315.gc6ed9934b7-goog
