linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
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,
	 yu.c.zhang@linux.intel.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,
	tabba@google.com
Subject: [RFC PATCH v1 1/9] KVM: guest_memfd: Allow host to mmap guest_memfd() pages
Date: Wed, 22 Jan 2025 15:27:30 +0000	[thread overview]
Message-ID: <20250122152738.1173160-2-tabba@google.com> (raw)
In-Reply-To: <20250122152738.1173160-1-tabba@google.com>

Add support for mmap() and fault() for guest_memfd 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 architecture has that support, and only allows mmap()
if that's the case.

Additionally, this is gated with a new configuration option,
CONFIG_KVM_GMEM_MAPPABLE.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 arch/x86/include/asm/kvm_host.h |  2 +
 include/linux/kvm_host.h        | 11 +++++
 virt/kvm/Kconfig                |  4 ++
 virt/kvm/guest_memfd.c          | 71 +++++++++++++++++++++++++++++++++
 4 files changed, 88 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e159e44a6a1b..c0e149bc1d79 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2206,6 +2206,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
 #define kvm_arch_has_private_mem(kvm) false
 #endif
 
+#define kvm_arch_private_mem_inplace(kvm) false
+
 #define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state)
 
 static inline u16 kvm_read_ldt(void)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 401439bb21e3..ebca0ab4c5e2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -717,6 +717,17 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
 }
 #endif
 
+/*
+ * Arch code must define kvm_arch_private_mem_inplace if support for private
+ * memory is enabled it supports in-place conversion between shared and private.
+ */
+#if !defined(kvm_arch_private_mem_inplace) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_private_mem_inplace(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/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 54e959e7d68f..59400fd8f539 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -124,3 +124,7 @@ config HAVE_KVM_ARCH_GMEM_PREPARE
 config HAVE_KVM_ARCH_GMEM_INVALIDATE
        bool
        depends on KVM_PRIVATE_MEM
+
+config KVM_GMEM_MAPPABLE
+       select KVM_PRIVATE_MEM
+       bool
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 47a9f68f7b24..9ee162bf6bde 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -307,7 +307,78 @@ 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_MAPPABLE
+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)) {
+		ret = VM_FAULT_SIGBUS;
+		goto out_filemap;
+	}
+
+	if (folio_test_hwpoison(folio)) {
+		ret = VM_FAULT_HWPOISON;
+		goto out_folio;
+	}
+
+	if (!folio_test_uptodate(folio)) {
+		unsigned long nr_pages = folio_nr_pages(folio);
+		unsigned long i;
+
+		for (i = 0; i < nr_pages; i++)
+			clear_highpage(folio_page(folio, i));
+
+		folio_mark_uptodate(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_private_mem_inplace(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_MAPPABLE */
+
 static struct file_operations kvm_gmem_fops = {
+	.mmap		= kvm_gmem_mmap,
 	.open		= generic_file_open,
 	.release	= kvm_gmem_release,
 	.fallocate	= kvm_gmem_fallocate,
-- 
2.48.0.rc2.279.g1de40edade-goog



  reply	other threads:[~2025-01-22 15:27 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-22 15:27 [RFC PATCH v1 0/9] KVM: Mapping of guest_memfd at the host and a software protected VM type Fuad Tabba
2025-01-22 15:27 ` Fuad Tabba [this message]
2025-01-22 22:06   ` [RFC PATCH v1 1/9] KVM: guest_memfd: Allow host to mmap guest_memfd() pages David Hildenbrand
2025-01-23  9:44     ` Fuad Tabba
2025-01-23 10:27       ` David Hildenbrand
2025-01-23 11:02         ` Fuad Tabba
2025-01-22 15:27 ` [RFC PATCH v1 2/9] KVM: guest_memfd: Add guest_memfd support to kvm_(read|/write)_guest_page() Fuad Tabba
2025-01-22 22:10   ` David Hildenbrand
2025-01-23  9:48     ` Fuad Tabba
2025-01-23 11:39       ` David Hildenbrand
2025-01-23 11:57         ` Patrick Roy
2025-01-23 12:28           ` Fuad Tabba
2025-01-23 13:57             ` Patrick Roy
2025-01-23 14:21               ` David Hildenbrand
2025-01-23 14:25                 ` Fuad Tabba
2025-01-23 14:18           ` David Hildenbrand
2025-01-23 15:22             ` Patrick Roy
2025-01-24 14:44               ` David Hildenbrand
2025-01-23 12:16         ` Fuad Tabba
2025-01-23 14:15           ` David Hildenbrand
2025-01-22 15:27 ` [RFC PATCH v1 3/9] KVM: guest_memfd: Add KVM capability to check if guest_memfd is host mappable Fuad Tabba
2025-01-23 11:42   ` David Hildenbrand
2025-01-23 11:46     ` Fuad Tabba
2025-01-22 15:27 ` [RFC PATCH v1 4/9] KVM: arm64: Skip VMA checks for slots without userspace address Fuad Tabba
2025-01-22 15:27 ` [RFC PATCH v1 5/9] KVM: arm64: Refactor user_mem_abort() calculation of force_pte Fuad Tabba
2025-01-22 15:27 ` [RFC PATCH v1 6/9] KVM: arm64: Handle guest_memfd()-backed guest page faults Fuad Tabba
2025-01-22 15:27 ` [RFC PATCH v1 7/9] KVM: arm64: Introduce KVM_VM_TYPE_ARM_SW_PROTECTED machine type Fuad Tabba
2025-01-22 15:27 ` [RFC PATCH v1 8/9] KVM: guest_memfd: selftests: guest_memfd mmap() test when mapping is allowed Fuad Tabba
2025-01-22 15:27 ` [RFC PATCH v1 9/9] KVM: arm64: Enable mapping guest_memfd in arm64 Fuad Tabba
2025-01-22 15:35 ` [RFC PATCH v1 0/9] KVM: Mapping of guest_memfd at the host and a software protected VM type David Hildenbrand
2025-01-22 15:41   ` David Hildenbrand
2025-01-22 17:16     ` Fuad Tabba
2025-01-22 21:42       ` David Hildenbrand
2025-01-23  9:09         ` Fuad Tabba
2025-01-23  9:14           ` David Hildenbrand

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=20250122152738.1173160-2-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=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=yu.c.zhang@linux.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