| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20230914015531.1419405-16-seanjc@google.com>
Date: Wed, 13 Sep 2023 18:55:13 -0700
From: Sean Christopherson <seanjc@...gle.com>
To: Paolo Bonzini <pbonzini@...hat.com>, Marc Zyngier <maz@...nel.org>,
Oliver Upton <oliver.upton@...ux.dev>,
Huacai Chen <chenhuacai@...nel.org>,
Michael Ellerman <mpe@...erman.id.au>,
Anup Patel <anup@...infault.org>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
Sean Christopherson <seanjc@...gle.com>,
"Matthew Wilcox (Oracle)" <willy@...radead.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Paul Moore <paul@...l-moore.com>,
James Morris <jmorris@...ei.org>,
"Serge E. Hallyn" <serge@...lyn.com>
Cc: kvm@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
kvmarm@...ts.linux.dev, linux-mips@...r.kernel.org,
linuxppc-dev@...ts.ozlabs.org, kvm-riscv@...ts.infradead.org,
linux-riscv@...ts.infradead.org, linux-fsdevel@...r.kernel.org,
linux-mm@...ck.org, linux-security-module@...r.kernel.org,
linux-kernel@...r.kernel.org,
Chao Peng <chao.p.peng@...ux.intel.com>,
Fuad Tabba <tabba@...gle.com>,
Jarkko Sakkinen <jarkko@...nel.org>,
Anish Moorthy <amoorthy@...gle.com>,
Yu Zhang <yu.c.zhang@...ux.intel.com>,
Isaku Yamahata <isaku.yamahata@...el.com>,
Xu Yilun <yilun.xu@...el.com>,
Vlastimil Babka <vbabka@...e.cz>,
Vishal Annapurve <vannapurve@...gle.com>,
Ackerley Tng <ackerleytng@...gle.com>,
Maciej Szmigiero <mail@...iej.szmigiero.name>,
David Hildenbrand <david@...hat.com>,
Quentin Perret <qperret@...gle.com>,
Michael Roth <michael.roth@....com>,
Wang <wei.w.wang@...el.com>,
Liam Merwick <liam.merwick@...cle.com>,
Isaku Yamahata <isaku.yamahata@...il.com>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [RFC PATCH v12 15/33] KVM: Add transparent hugepage support for
dedicated guest memory
TODO: writeme
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
include/uapi/linux/kvm.h | 2 ++
virt/kvm/guest_mem.c | 54 ++++++++++++++++++++++++++++++++++++----
2 files changed, 51 insertions(+), 5 deletions(-)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index b6f90a273e2e..2df18796fd8e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -2314,6 +2314,8 @@ struct kvm_memory_attributes {
#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd)
+#define KVM_GUEST_MEMFD_ALLOW_HUGEPAGE (1ULL << 0)
+
struct kvm_create_guest_memfd {
__u64 size;
__u64 flags;
diff --git a/virt/kvm/guest_mem.c b/virt/kvm/guest_mem.c
index 0dd3f836cf9c..a819367434e9 100644
--- a/virt/kvm/guest_mem.c
+++ b/virt/kvm/guest_mem.c
@@ -17,15 +17,48 @@ struct kvm_gmem {
struct list_head entry;
};
-static struct folio *kvm_gmem_get_folio(struct file *file, pgoff_t index)
+static struct folio *kvm_gmem_get_huge_folio(struct inode *inode, pgoff_t index)
{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ unsigned long huge_index = round_down(index, HPAGE_PMD_NR);
+ unsigned long flags = (unsigned long)inode->i_private;
+ struct address_space *mapping = inode->i_mapping;
+ gfp_t gfp = mapping_gfp_mask(mapping);
struct folio *folio;
- /* TODO: Support huge pages. */
- folio = filemap_grab_folio(file->f_mapping, index);
- if (IS_ERR_OR_NULL(folio))
+ if (!(flags & KVM_GUEST_MEMFD_ALLOW_HUGEPAGE))
return NULL;
+ if (filemap_range_has_page(mapping, huge_index << PAGE_SHIFT,
+ (huge_index + HPAGE_PMD_NR - 1) << PAGE_SHIFT))
+ return NULL;
+
+ folio = filemap_alloc_folio(gfp, HPAGE_PMD_ORDER);
+ if (!folio)
+ return NULL;
+
+ if (filemap_add_folio(mapping, folio, huge_index, gfp)) {
+ folio_put(folio);
+ return NULL;
+ }
+
+ return folio;
+#else
+ return NULL;
+#endif
+}
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+{
+ struct folio *folio;
+
+ folio = kvm_gmem_get_huge_folio(inode, index);
+ if (!folio) {
+ folio = filemap_grab_folio(inode->i_mapping, index);
+ if (IS_ERR_OR_NULL(folio))
+ return NULL;
+ }
+
/*
* Use the up-to-date flag to track whether or not the memory has been
* zeroed before being handed off to the guest. There is no backing
@@ -323,7 +356,8 @@ static const struct inode_operations kvm_gmem_iops = {
.setattr = kvm_gmem_setattr,
};
-static int __kvm_gmem_create(struct kvm *kvm, loff_t size, struct vfsmount *mnt)
+static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags,
+ struct vfsmount *mnt)
{
const char *anon_name = "[kvm-gmem]";
const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name));
@@ -346,6 +380,7 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, struct vfsmount *mnt)
inode->i_mode |= S_IFREG;
inode->i_size = size;
mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+ mapping_set_large_folios(inode->i_mapping);
mapping_set_unmovable(inode->i_mapping);
/* Unmovable mappings are supposed to be marked unevictable as well. */
WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
@@ -396,6 +431,12 @@ static bool kvm_gmem_is_valid_size(loff_t size, u64 flags)
if (size < 0 || !PAGE_ALIGNED(size))
return false;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if ((flags & KVM_GUEST_MEMFD_ALLOW_HUGEPAGE) &&
+ !IS_ALIGNED(size, HPAGE_PMD_SIZE))
+ return false;
+#endif
+
return true;
}
@@ -405,6 +446,9 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
u64 flags = args->flags;
u64 valid_flags = 0;
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+ valid_flags |= KVM_GUEST_MEMFD_ALLOW_HUGEPAGE;
+
if (flags & ~valid_flags)
return -EINVAL;
--
2.42.0.283.g2d96d420d3-goog
Powered by blists - more mailing lists