diff options
author | Paolo Bonzini <pbonzini@redhat.com> | 2024-05-07 19:54:03 +0300 |
---|---|---|
committer | Paolo Bonzini <pbonzini@redhat.com> | 2024-05-10 20:11:46 +0300 |
commit | 3bb2531e20bff99f9cd8719ee7aea8bd82687173 (patch) | |
tree | bacc22f7ae3bd52ce1302f61f57219ea43a08380 /virt | |
parent | fa30b0dc91c815b9579d6f758437c35db059f5ae (diff) | |
download | linux-3bb2531e20bff99f9cd8719ee7aea8bd82687173.tar.xz |
KVM: guest_memfd: Add hook for initializing memory
guest_memfd pages are generally expected to be in some arch-defined
initial state prior to using them for guest memory. For SEV-SNP this
initial state is 'private', or 'guest-owned', and requires additional
operations to move these pages into a 'private' state by updating the
corresponding entries the RMP table.
Allow for an arch-defined hook to handle updates of this sort, and go
ahead and implement one for x86 so KVM implementations like AMD SVM can
register a kvm_x86_ops callback to handle these updates for SEV-SNP
guests.
The preparation callback is always called when allocating/grabbing
folios via gmem, and it is up to the architecture to keep track of
whether or not the pages are already in the expected state (e.g. the RMP
table in the case of SEV-SNP).
In some cases, it is necessary to defer the preparation of the pages to
handle things like in-place encryption of initial guest memory payloads
before marking these pages as 'private'/'guest-owned'. Add an argument
(always true for now) to kvm_gmem_get_folio() that allows for the
preparation callback to be bypassed. To detect possible issues in
the way userspace initializes memory, it is only possible to add an
unprepared page if it is not already included in the filemap.
Link: https://lore.kernel.org/lkml/ZLqVdvsF11Ddo7Dq@google.com/
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-Id: <20231230172351.574091-5-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'virt')
-rw-r--r-- | virt/kvm/Kconfig | 4 | ||||
-rw-r--r-- | virt/kvm/guest_memfd.c | 51 |
2 files changed, 52 insertions, 3 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 29b73eedfe74..ca870157b2ed 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -109,3 +109,7 @@ config KVM_GENERIC_PRIVATE_MEM select KVM_GENERIC_MEMORY_ATTRIBUTES select KVM_PRIVATE_MEM bool + +config HAVE_KVM_GMEM_PREPARE + bool + depends on KVM_PRIVATE_MEM diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index fd32288d0fbc..0176089be731 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -13,7 +13,43 @@ struct kvm_gmem { struct list_head entry; }; -static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) +static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct folio *folio) +{ +#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE + struct list_head *gmem_list = &inode->i_mapping->i_private_list; + struct kvm_gmem *gmem; + + list_for_each_entry(gmem, gmem_list, entry) { + struct kvm_memory_slot *slot; + struct kvm *kvm = gmem->kvm; + struct page *page; + kvm_pfn_t pfn; + gfn_t gfn; + int rc; + + if (!kvm_arch_gmem_prepare_needed(kvm)) + continue; + + slot = xa_load(&gmem->bindings, index); + if (!slot) + continue; + + page = folio_file_page(folio, index); + pfn = page_to_pfn(page); + gfn = slot->base_gfn + index - slot->gmem.pgoff; + rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, compound_order(compound_head(page))); + if (rc) { + pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx, error %d.\n", + index, rc); + return rc; + } + } + +#endif + return 0; +} + +static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index, bool prepare) { struct folio *folio; @@ -41,6 +77,15 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) folio_mark_uptodate(folio); } + if (prepare) { + int r = kvm_gmem_prepare_folio(inode, index, folio); + if (r < 0) { + folio_unlock(folio); + folio_put(folio); + return ERR_PTR(r); + } + } + /* * Ignore accessed, referenced, and dirty flags. The memory is * unevictable and there is no storage to write back to. @@ -145,7 +190,7 @@ static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len) break; } - folio = kvm_gmem_get_folio(inode, index); + folio = kvm_gmem_get_folio(inode, index, true); if (IS_ERR(folio)) { r = PTR_ERR(folio); break; @@ -505,7 +550,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, goto out_fput; } - folio = kvm_gmem_get_folio(file_inode(file), index); + folio = kvm_gmem_get_folio(file_inode(file), index, true); if (IS_ERR(folio)) { r = PTR_ERR(folio); goto out_fput; |