From: Chao Peng <chao.p.peng@linux.intel.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
qemu-devel@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
Jonathan Corbet <corbet@lwn.net>,
Sean Christopherson <seanjc@google.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
"J . Bruce Fields" <bfields@fieldses.org>,
Andrew Morton <akpm@linux-foundation.org>,
Yu Zhang <yu.c.zhang@linux.intel.com>,
Chao Peng <chao.p.peng@linux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
luto@kernel.org, john.ji@intel.com, susie.li@intel.com,
jun.nakajima@intel.com, dave.hansen@intel.com,
ak@linux.intel.com, david@redhat.com
Subject: [RFC v2 PATCH 05/13] KVM: Implement fd-based memory using new memfd interfaces
Date: Fri, 19 Nov 2021 21:47:31 +0800 [thread overview]
Message-ID: <20211119134739.20218-6-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20211119134739.20218-1-chao.p.peng@linux.intel.com>
This patch pairs a fd-based memslot to a memory backing store. Two sides
handshake to exchange callbacks that will be called later.
KVM->memfd:
- get_pfn: get or allocate(when alloc is true) page at specified
offset in the fd, the page will be locked
- put_pfn: put and unlock the pfn
memfd->KVM:
- invalidate_page_range: called when userspace punch hole on the fd,
KVM should unmap related pages in the second MMU
- fallocate: called when userspace fallocate space on the fd, KVM
can map related pages in the second MMU
Currently tmpfs behind memfd interface is supported.
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
arch/x86/kvm/Makefile | 3 +-
include/linux/kvm_host.h | 6 +++
virt/kvm/memfd.c | 101 +++++++++++++++++++++++++++++++++++++++
3 files changed, 109 insertions(+), 1 deletion(-)
create mode 100644 virt/kvm/memfd.c
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index f919df73e5e3..5d7f289b1ca0 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -11,7 +11,8 @@ KVM := ../../../virt/kvm
kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \
- $(KVM)/dirty_ring.o $(KVM)/binary_stats.o
+ $(KVM)/dirty_ring.o $(KVM)/binary_stats.o \
+ $(KVM)/memfd.o
kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1d4ac0c9b63b..e8646103356b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -769,6 +769,12 @@ static inline void kvm_irqfd_exit(void)
{
}
#endif
+
+int kvm_memfd_register(struct kvm *kvm,
+ const struct kvm_userspace_memory_region_ext *mem,
+ struct kvm_memory_slot *slot);
+void kvm_memfd_unregister(struct kvm *kvm, struct kvm_memory_slot *slot);
+
int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
struct module *module);
void kvm_exit(void);
diff --git a/virt/kvm/memfd.c b/virt/kvm/memfd.c
new file mode 100644
index 000000000000..bd930dcb455f
--- /dev/null
+++ b/virt/kvm/memfd.c
@@ -0,0 +1,101 @@
+
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * memfd.c: routines for fd based guest memory backing store
+ * Copyright (c) 2021, Intel Corporation.
+ *
+ * Author:
+ * Chao Peng <chao.p.peng@linux.intel.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/memfd.h>
+const static struct guest_mem_ops *memfd_ops;
+
+static void memfd_invalidate_page_range(struct inode *inode, void *owner,
+ pgoff_t start, pgoff_t end)
+{
+ //!!!We can get here after the owner no longer exists
+}
+
+static void memfd_fallocate(struct inode *inode, void *owner,
+ pgoff_t start, pgoff_t end)
+{
+ //!!!We can get here after the owner no longer exists
+}
+
+static const struct guest_ops memfd_notifier = {
+ .invalidate_page_range = memfd_invalidate_page_range,
+ .fallocate = memfd_fallocate,
+};
+
+static kvm_pfn_t kvm_memfd_get_pfn(struct kvm_memory_slot *slot,
+ struct file *file, gfn_t gfn,
+ bool alloc, int *order)
+{
+ pgoff_t index = gfn - slot->base_gfn +
+ (slot->userspace_addr >> PAGE_SHIFT);
+
+ return memfd_ops->get_lock_pfn(file->f_inode, index, alloc, order);
+}
+
+static void kvm_memfd_put_pfn(kvm_pfn_t pfn)
+{
+ memfd_ops->put_unlock_pfn(pfn);
+}
+
+static struct kvm_memfd_ops kvm_memfd_ops = {
+ .get_pfn = kvm_memfd_get_pfn,
+ .put_pfn = kvm_memfd_put_pfn,
+};
+
+int kvm_memfd_register(struct kvm *kvm,
+ const struct kvm_userspace_memory_region_ext *mem,
+ struct kvm_memory_slot *slot)
+{
+ int ret;
+ struct fd fd = fdget(mem->fd);
+
+ if (!fd.file)
+ return -EINVAL;
+
+ ret = memfd_register_guest(fd.file->f_inode, kvm,
+ &memfd_notifier, &memfd_ops);
+ if (ret)
+ return ret;
+ slot->file = fd.file;
+
+ if (mem->private_fd >= 0) {
+ fd = fdget(mem->private_fd);
+ if (!fd.file) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ ret = memfd_register_guest(fd.file->f_inode, kvm,
+ &memfd_notifier, &memfd_ops);
+ if (ret)
+ goto err;
+ slot->priv_file = fd.file;
+ }
+
+ slot->memfd_ops = &kvm_memfd_ops;
+ return 0;
+err:
+ kvm_memfd_unregister(kvm, slot);
+ return ret;
+}
+
+void kvm_memfd_unregister(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+ if (slot->file) {
+ fput(slot->file);
+ slot->file = NULL;
+ }
+
+ if (slot->priv_file) {
+ fput(slot->priv_file);
+ slot->priv_file = NULL;
+ }
+ slot->memfd_ops = NULL;
+}
--
2.17.1
next prev parent reply other threads:[~2021-11-19 13:49 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-19 13:47 [RFC v2 PATCH 00/13] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 01/13] mm/shmem: Introduce F_SEAL_GUEST Chao Peng
2021-11-19 13:51 ` David Hildenbrand
2021-11-22 13:59 ` Kirill A. Shutemov
2021-11-19 15:19 ` Jason Gunthorpe
2021-11-19 15:39 ` David Hildenbrand
2021-11-19 16:00 ` Jason Gunthorpe
2021-11-22 9:26 ` David Hildenbrand
2021-11-22 13:31 ` Jason Gunthorpe
2021-11-22 13:35 ` David Hildenbrand
2021-11-22 14:01 ` Jason Gunthorpe
2021-11-22 14:57 ` David Hildenbrand
2021-11-22 15:09 ` Jason Gunthorpe
2021-11-22 15:15 ` David Hildenbrand
2021-11-19 19:18 ` Sean Christopherson
2021-11-19 19:47 ` Jason Gunthorpe
2021-11-19 22:21 ` Sean Christopherson
2021-11-19 23:33 ` Jason Gunthorpe
2021-11-20 1:23 ` Sean Christopherson
2021-11-21 0:05 ` Jason Gunthorpe
2021-11-23 9:06 ` Paolo Bonzini
2021-11-23 14:33 ` Chao Peng
2021-11-23 15:20 ` David Hildenbrand
2021-11-23 17:17 ` Jason Gunthorpe
2021-11-23 8:54 ` Paolo Bonzini
2021-12-03 1:11 ` Andy Lutomirski
2021-11-19 13:47 ` [RFC v2 PATCH 02/13] KVM: Add KVM_EXIT_MEMORY_ERROR exit Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 03/13] KVM: Extend kvm_userspace_memory_region to support fd based memslot Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 04/13] KVM: Add fd-based memslot data structure and utils Chao Peng
2021-11-23 8:41 ` Paolo Bonzini
2021-11-23 14:30 ` Chao Peng
2021-11-19 13:47 ` Chao Peng [this message]
2021-11-19 13:47 ` [RFC v2 PATCH 06/13] KVM: Register/unregister memfd backed memslot Chao Peng
2021-11-25 16:55 ` Steven Price
2021-11-19 13:47 ` [RFC v2 PATCH 07/13] KVM: Handle page fault for fd based memslot Chao Peng
2021-11-20 1:55 ` Yao Yuan
2021-11-22 9:18 ` Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 08/13] KVM: Rename hva memory invalidation code to cover fd-based offset Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 09/13] KVM: Introduce kvm_memfd_invalidate_range Chao Peng
2021-11-23 8:46 ` Paolo Bonzini
2021-11-23 14:24 ` Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 10/13] KVM: Match inode for invalidation of fd-based slot Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 11/13] KVM: Add kvm_map_gfn_range Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 12/13] KVM: Introduce kvm_memfd_fallocate_range Chao Peng
2021-11-19 13:47 ` [RFC v2 PATCH 13/13] KVM: Enable memfd based page invalidation/fallocate Chao Peng
2021-11-22 14:16 ` Kirill A. Shutemov
2021-11-23 1:06 ` Chao Peng
2021-11-23 9:09 ` Paolo Bonzini
2021-11-23 15:00 ` Chao Peng
2021-11-23 8:51 ` Paolo Bonzini
2021-12-03 1:08 ` [RFC v2 PATCH 00/13] KVM: mm: fd-based approach for supporting KVM guest private memory Andy Lutomirski
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=20211119134739.20218-6-chao.p.peng@linux.intel.com \
--to=chao.p.peng@linux.intel.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=bfields@fieldses.org \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jlayton@kernel.org \
--cc=jmattson@google.com \
--cc=john.ji@intel.com \
--cc=joro@8bytes.org \
--cc=jun.nakajima@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=seanjc@google.com \
--cc=susie.li@intel.com \
--cc=tglx@linutronix.de \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=x86@kernel.org \
--cc=yu.c.zhang@linux.intel.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;
as well as URLs for NNTP newsgroup(s).