From: Fuad Tabba <tabba@google.com>
To: kvm@vger.kernel.org, linux-arm-msm@vger.kernel.org, linux-mm@kvack.org
Cc: pbonzini@redhat.com, chenhuacai@kernel.org, mpe@ellerman.id.au,
anup@brainfault.org, paul.walmsley@sifive.com,
palmer@dabbelt.com, aou@eecs.berkeley.edu, seanjc@google.com,
viro@zeniv.linux.org.uk, brauner@kernel.org,
willy@infradead.org, akpm@linux-foundation.org,
xiaoyao.li@intel.com, yilun.xu@intel.com,
chao.p.peng@linux.intel.com, jarkko@kernel.org,
amoorthy@google.com, dmatlack@google.com,
isaku.yamahata@intel.com, mic@digikod.net, vbabka@suse.cz,
vannapurve@google.com, ackerleytng@google.com,
mail@maciej.szmigiero.name, david@redhat.com,
michael.roth@amd.com, wei.w.wang@intel.com,
liam.merwick@oracle.com, isaku.yamahata@gmail.com,
kirill.shutemov@linux.intel.com, suzuki.poulose@arm.com,
steven.price@arm.com, quic_eberman@quicinc.com,
quic_mnalajal@quicinc.com, quic_tsoni@quicinc.com,
quic_svaddagi@quicinc.com, quic_cvanscha@quicinc.com,
quic_pderrin@quicinc.com, quic_pheragu@quicinc.com,
catalin.marinas@arm.com, james.morse@arm.com,
yuzenghui@huawei.com, oliver.upton@linux.dev, maz@kernel.org,
will@kernel.org, qperret@google.com, keirf@google.com,
roypat@amazon.co.uk, shuah@kernel.org, hch@infradead.org,
jgg@nvidia.com, rientjes@google.com, jhubbard@nvidia.com,
fvdl@google.com, hughd@google.com, jthoughton@google.com,
peterx@redhat.com, tabba@google.com
Subject: [PATCH v5 3/9] KVM: guest_memfd: Allow host to map guest_memfd() pages
Date: Mon, 3 Mar 2025 17:10:07 +0000 [thread overview]
Message-ID: <20250303171013.3548775-4-tabba@google.com> (raw)
In-Reply-To: <20250303171013.3548775-1-tabba@google.com>
Add support for mmap() and fault() for guest_memfd backed memory
in the host for VMs that support in-place conversion between
shared and private. To that end, this patch adds the ability to
check whether the VM type supports in-place conversion, and only
allows mapping its memory if that's the case.
Also add the KVM capability KVM_CAP_GMEM_SHARED_MEM, which
indicates that the VM supports shared memory in guest_memfd, or
that the host can create VMs that support shared memory.
Supporting shared memory implies that memory can be mapped when
shared with the host.
This is controlled by the KVM_GMEM_SHARED_MEM configuration
option.
Signed-off-by: Fuad Tabba <tabba@google.com>
---
include/linux/kvm_host.h | 11 ++++
include/uapi/linux/kvm.h | 1 +
virt/kvm/guest_memfd.c | 105 +++++++++++++++++++++++++++++++++++++++
virt/kvm/kvm_main.c | 4 ++
4 files changed, 121 insertions(+)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7788e3625f6d..2d025b8ee20e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -728,6 +728,17 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
}
#endif
+/*
+ * Arch code must define kvm_arch_gmem_supports_shared_mem if support for
+ * private memory is enabled and it supports in-place shared/private conversion.
+ */
+#if !defined(kvm_arch_gmem_supports_shared_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_gmem_supports_shared_mem(struct kvm *kvm)
+{
+ return false;
+}
+#endif
+
#ifndef kvm_arch_has_readonly_mem
static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
{
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 45e6d8fca9b9..117937a895da 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -929,6 +929,7 @@ struct kvm_enable_cap {
#define KVM_CAP_PRE_FAULT_MEMORY 236
#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
#define KVM_CAP_X86_GUEST_MODE 238
+#define KVM_CAP_GMEM_SHARED_MEM 239
struct kvm_irq_routing_irqchip {
__u32 irqchip;
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index b2aa6bf24d3a..4291956b51ae 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -312,7 +312,112 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
return gfn - slot->base_gfn + slot->gmem.pgoff;
}
+#ifdef CONFIG_KVM_GMEM_SHARED_MEM
+static bool kvm_gmem_offset_is_shared(struct file *file, pgoff_t index)
+{
+ struct kvm_gmem *gmem = file->private_data;
+
+ /* For now, VMs that support shared memory share all their memory. */
+ return kvm_arch_gmem_supports_shared_mem(gmem->kvm);
+}
+
+static vm_fault_t kvm_gmem_fault(struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vmf->vma->vm_file);
+ struct folio *folio;
+ vm_fault_t ret = VM_FAULT_LOCKED;
+
+ filemap_invalidate_lock_shared(inode->i_mapping);
+
+ folio = kvm_gmem_get_folio(inode, vmf->pgoff);
+ if (IS_ERR(folio)) {
+ switch (PTR_ERR(folio)) {
+ case -EAGAIN:
+ ret = VM_FAULT_RETRY;
+ break;
+ case -ENOMEM:
+ ret = VM_FAULT_OOM;
+ break;
+ default:
+ ret = VM_FAULT_SIGBUS;
+ break;
+ }
+ goto out_filemap;
+ }
+
+ if (folio_test_hwpoison(folio)) {
+ ret = VM_FAULT_HWPOISON;
+ goto out_folio;
+ }
+
+ /* Must be called with folio lock held, i.e., after kvm_gmem_get_folio() */
+ if (!kvm_gmem_offset_is_shared(vmf->vma->vm_file, vmf->pgoff)) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_folio;
+ }
+
+ /*
+ * Only private folios are marked as "guestmem" so far, and we never
+ * expect private folios at this point.
+ */
+ if (WARN_ON_ONCE(folio_test_guestmem(folio))) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_folio;
+ }
+
+ /* No support for huge pages. */
+ if (WARN_ON_ONCE(folio_test_large(folio))) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_folio;
+ }
+
+ if (!folio_test_uptodate(folio)) {
+ clear_highpage(folio_page(folio, 0));
+ kvm_gmem_mark_prepared(folio);
+ }
+
+ vmf->page = folio_file_page(folio, vmf->pgoff);
+
+out_folio:
+ if (ret != VM_FAULT_LOCKED) {
+ folio_unlock(folio);
+ folio_put(folio);
+ }
+
+out_filemap:
+ filemap_invalidate_unlock_shared(inode->i_mapping);
+
+ return ret;
+}
+
+static const struct vm_operations_struct kvm_gmem_vm_ops = {
+ .fault = kvm_gmem_fault,
+};
+
+static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct kvm_gmem *gmem = file->private_data;
+
+ if (!kvm_arch_gmem_supports_shared_mem(gmem->kvm))
+ return -ENODEV;
+
+ if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
+ (VM_SHARED | VM_MAYSHARE)) {
+ return -EINVAL;
+ }
+
+ file_accessed(file);
+ vm_flags_set(vma, VM_DONTDUMP);
+ vma->vm_ops = &kvm_gmem_vm_ops;
+
+ return 0;
+}
+#else
+#define kvm_gmem_mmap NULL
+#endif /* CONFIG_KVM_GMEM_SHARED_MEM */
+
static struct file_operations kvm_gmem_fops = {
+ .mmap = kvm_gmem_mmap,
.open = generic_file_open,
.release = kvm_gmem_release,
.fallocate = kvm_gmem_fallocate,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ba0327e2d0d3..38f0f402ea46 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4830,6 +4830,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
#ifdef CONFIG_KVM_PRIVATE_MEM
case KVM_CAP_GUEST_MEMFD:
return !kvm || kvm_arch_has_private_mem(kvm);
+#endif
+#ifdef CONFIG_KVM_GMEM_SHARED_MEM
+ case KVM_CAP_GMEM_SHARED_MEM:
+ return !kvm || kvm_arch_gmem_supports_shared_mem(kvm);
#endif
default:
break;
--
2.48.1.711.g2feabab25a-goog
next prev parent reply other threads:[~2025-03-03 17:10 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-03 17:10 [PATCH v5 0/9] KVM: Mapping guest_memfd backed memory at the host for software protected VMs Fuad Tabba
2025-03-03 17:10 ` [PATCH v5 1/9] mm: Consolidate freeing of typed folios on final folio_put() Fuad Tabba
2025-03-04 8:45 ` Kirill A. Shutemov
2025-03-04 9:43 ` David Hildenbrand
2025-03-03 17:10 ` [PATCH v5 2/9] KVM: guest_memfd: Handle final folio_put() of guest_memfd pages Fuad Tabba
2025-03-07 17:04 ` Ackerley Tng
2025-03-10 10:50 ` Fuad Tabba
2025-03-10 14:23 ` Ackerley Tng
2025-03-10 14:35 ` Fuad Tabba
2025-03-03 17:10 ` Fuad Tabba [this message]
2025-03-04 8:58 ` [PATCH v5 3/9] KVM: guest_memfd: Allow host to map guest_memfd() pages Kirill A. Shutemov
2025-03-04 9:27 ` Fuad Tabba
2025-03-04 9:45 ` Kirill A. Shutemov
2025-03-04 9:52 ` Fuad Tabba
2025-03-06 0:01 ` Ackerley Tng
2025-03-06 8:48 ` Fuad Tabba
2025-03-06 17:05 ` Ackerley Tng
2025-03-06 22:46 ` Ackerley Tng
2025-03-07 8:57 ` Fuad Tabba
2025-03-07 1:53 ` James Houghton
2025-03-07 8:55 ` Fuad Tabba
2025-03-03 17:10 ` [PATCH v5 4/9] KVM: guest_memfd: Handle in-place shared memory as guest_memfd backed memory Fuad Tabba
2025-03-06 16:09 ` Ackerley Tng
2025-03-06 17:02 ` Fuad Tabba
2025-03-03 17:10 ` [PATCH v5 5/9] KVM: x86: Mark KVM_X86_SW_PROTECTED_VM as supporting guest_memfd shared memory Fuad Tabba
2025-03-03 17:10 ` [PATCH v5 6/9] KVM: arm64: Refactor user_mem_abort() calculation of force_pte Fuad Tabba
2025-03-06 10:46 ` Quentin Perret
2025-03-06 10:54 ` Fuad Tabba
2025-03-03 17:10 ` [PATCH v5 7/9] KVM: arm64: Handle guest_memfd()-backed guest page faults Fuad Tabba
2025-03-03 17:10 ` [PATCH v5 8/9] KVM: arm64: Enable mapping guest_memfd in arm64 Fuad Tabba
2025-03-03 17:10 ` [PATCH v5 9/9] KVM: guest_memfd: selftests: guest_memfd mmap() test when mapping is allowed Fuad Tabba
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250303171013.3548775-4-tabba@google.com \
--to=tabba@google.com \
--cc=ackerleytng@google.com \
--cc=akpm@linux-foundation.org \
--cc=amoorthy@google.com \
--cc=anup@brainfault.org \
--cc=aou@eecs.berkeley.edu \
--cc=brauner@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=chao.p.peng@linux.intel.com \
--cc=chenhuacai@kernel.org \
--cc=david@redhat.com \
--cc=dmatlack@google.com \
--cc=fvdl@google.com \
--cc=hch@infradead.org \
--cc=hughd@google.com \
--cc=isaku.yamahata@gmail.com \
--cc=isaku.yamahata@intel.com \
--cc=james.morse@arm.com \
--cc=jarkko@kernel.org \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=jthoughton@google.com \
--cc=keirf@google.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=liam.merwick@oracle.com \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mail@maciej.szmigiero.name \
--cc=maz@kernel.org \
--cc=mic@digikod.net \
--cc=michael.roth@amd.com \
--cc=mpe@ellerman.id.au \
--cc=oliver.upton@linux.dev \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qperret@google.com \
--cc=quic_cvanscha@quicinc.com \
--cc=quic_eberman@quicinc.com \
--cc=quic_mnalajal@quicinc.com \
--cc=quic_pderrin@quicinc.com \
--cc=quic_pheragu@quicinc.com \
--cc=quic_svaddagi@quicinc.com \
--cc=quic_tsoni@quicinc.com \
--cc=rientjes@google.com \
--cc=roypat@amazon.co.uk \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=steven.price@arm.com \
--cc=suzuki.poulose@arm.com \
--cc=vannapurve@google.com \
--cc=vbabka@suse.cz \
--cc=viro@zeniv.linux.org.uk \
--cc=wei.w.wang@intel.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=xiaoyao.li@intel.com \
--cc=yilun.xu@intel.com \
--cc=yuzenghui@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox