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, jun.nakajima@intel.com, dave.hansen@intel.com,
ak@linux.intel.com, david@redhat.com
Subject: [PATCH v4 03/12] mm: Introduce memfile_notifier
Date: Tue, 18 Jan 2022 21:21:12 +0800 [thread overview]
Message-ID: <20220118132121.31388-4-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20220118132121.31388-1-chao.p.peng@linux.intel.com>
This patch introduces memfile_notifier facility so existing memory file
subsystems (e.g. tmpfs/hugetlbfs) can provide memory pages to allow a
third kernel component to make use of memory bookmarked in the memory
file and gets notified when the pages in the memory file become
allocated/invalidated.
It will be used for KVM to use a file descriptor as the guest memory
backing store and KVM will use this memfile_notifier interface to
interact with memory file subsystems. In the future there might be other
consumers (e.g. VFIO with encrypted device memory).
It consists two sets of callbacks:
- memfile_notifier_ops: callbacks for memory backing store to notify
KVM when memory gets allocated/invalidated.
- memfile_pfn_ops: callbacks for KVM to call into memory backing store
to request memory pages for guest private memory.
Userspace is in charge of guest memory lifecycle: it first allocates
pages in memory backing store and then passes the fd to KVM and lets KVM
register each memory slot to memory backing store via
memfile_register_notifier.
The supported memory backing store should maintain a memfile_notifier list
and provide routine for memfile_notifier to get the list head address and
memfile_pfn_ops callbacks for memfile_register_notifier. It also should call
memfile_notifier_fallocate/memfile_notifier_invalidate when the bookmarked
memory gets allocated/invalidated.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
include/linux/memfile_notifier.h | 53 +++++++++++++++++++
mm/Kconfig | 4 ++
mm/Makefile | 1 +
mm/memfile_notifier.c | 89 ++++++++++++++++++++++++++++++++
4 files changed, 147 insertions(+)
create mode 100644 include/linux/memfile_notifier.h
create mode 100644 mm/memfile_notifier.c
diff --git a/include/linux/memfile_notifier.h b/include/linux/memfile_notifier.h
new file mode 100644
index 000000000000..a03bebdd1322
--- /dev/null
+++ b/include/linux/memfile_notifier.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MEMFILE_NOTIFIER_H
+#define _LINUX_MEMFILE_NOTIFIER_H
+
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <linux/srcu.h>
+#include <linux/fs.h>
+
+struct memfile_notifier;
+
+struct memfile_notifier_ops {
+ void (*invalidate)(struct memfile_notifier *notifier,
+ pgoff_t start, pgoff_t end);
+ void (*fallocate)(struct memfile_notifier *notifier,
+ pgoff_t start, pgoff_t end);
+};
+
+struct memfile_pfn_ops {
+ long (*get_lock_pfn)(struct inode *inode, pgoff_t offset, int *order);
+ void (*put_unlock_pfn)(unsigned long pfn);
+};
+
+struct memfile_notifier {
+ struct list_head list;
+ struct memfile_notifier_ops *ops;
+};
+
+struct memfile_notifier_list {
+ struct list_head head;
+ spinlock_t lock;
+};
+
+#ifdef CONFIG_MEMFILE_NOTIFIER
+static inline void memfile_notifier_list_init(struct memfile_notifier_list *list)
+{
+ INIT_LIST_HEAD(&list->head);
+ spin_lock_init(&list->lock);
+}
+
+extern void memfile_notifier_invalidate(struct memfile_notifier_list *list,
+ pgoff_t start, pgoff_t end);
+extern void memfile_notifier_fallocate(struct memfile_notifier_list *list,
+ pgoff_t start, pgoff_t end);
+extern int memfile_register_notifier(struct inode *inode,
+ struct memfile_notifier *notifier,
+ struct memfile_pfn_ops **pfn_ops);
+extern void memfile_unregister_notifier(struct inode *inode,
+ struct memfile_notifier *notifier);
+
+#endif /* CONFIG_MEMFILE_NOTIFIER */
+
+#endif /* _LINUX_MEMFILE_NOTIFIER_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index 28edafc820ad..fa31eda3c895 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -900,6 +900,10 @@ config IO_MAPPING
config SECRETMEM
def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+config MEMFILE_NOTIFIER
+ bool
+ select SRCU
+
source "mm/damon/Kconfig"
endmenu
diff --git a/mm/Makefile b/mm/Makefile
index d6c0042e3aa0..80588f7c3bc2 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -130,3 +130,4 @@ obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
obj-$(CONFIG_IO_MAPPING) += io-mapping.o
obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
+obj-$(CONFIG_MEMFILE_NOTIFIER) += memfile_notifier.o
diff --git a/mm/memfile_notifier.c b/mm/memfile_notifier.c
new file mode 100644
index 000000000000..8171d4601a04
--- /dev/null
+++ b/mm/memfile_notifier.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/mm/memfile_notifier.c
+ *
+ * Copyright (C) 2022 Intel Corporation.
+ * Chao Peng <chao.p.peng@linux.intel.com>
+ */
+
+#include <linux/memfile_notifier.h>
+#include <linux/srcu.h>
+
+DEFINE_STATIC_SRCU(srcu);
+
+void memfile_notifier_invalidate(struct memfile_notifier_list *list,
+ pgoff_t start, pgoff_t end)
+{
+ struct memfile_notifier *notifier;
+ int id;
+
+ id = srcu_read_lock(&srcu);
+ list_for_each_entry_srcu(notifier, &list->head, list,
+ srcu_read_lock_held(&srcu)) {
+ if (notifier->ops && notifier->ops->invalidate)
+ notifier->ops->invalidate(notifier, start, end);
+ }
+ srcu_read_unlock(&srcu, id);
+}
+
+void memfile_notifier_fallocate(struct memfile_notifier_list *list,
+ pgoff_t start, pgoff_t end)
+{
+ struct memfile_notifier *notifier;
+ int id;
+
+ id = srcu_read_lock(&srcu);
+ list_for_each_entry_srcu(notifier, &list->head, list,
+ srcu_read_lock_held(&srcu)) {
+ if (notifier->ops && notifier->ops->fallocate)
+ notifier->ops->fallocate(notifier, start, end);
+ }
+ srcu_read_unlock(&srcu, id);
+}
+
+static int memfile_get_notifier_info(struct inode *inode,
+ struct memfile_notifier_list **list,
+ struct memfile_pfn_ops **ops)
+{
+ return -EOPNOTSUPP;
+}
+
+int memfile_register_notifier(struct inode *inode,
+ struct memfile_notifier *notifier,
+ struct memfile_pfn_ops **pfn_ops)
+{
+ struct memfile_notifier_list *list;
+ int ret;
+
+ if (!inode || !notifier | !pfn_ops)
+ return -EINVAL;
+
+ ret = memfile_get_notifier_info(inode, &list, pfn_ops);
+ if (ret)
+ return ret;
+
+ spin_lock(&list->lock);
+ list_add_rcu(¬ifier->list, &list->head);
+ spin_unlock(&list->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(memfile_register_notifier);
+
+void memfile_unregister_notifier(struct inode *inode,
+ struct memfile_notifier *notifier)
+{
+ struct memfile_notifier_list *list;
+
+ if (!inode || !notifier)
+ return;
+
+ BUG_ON(memfile_get_notifier_info(inode, &list, NULL));
+
+ spin_lock(&list->lock);
+ list_del_rcu(¬ifier->list);
+ spin_unlock(&list->lock);
+
+ synchronize_srcu(&srcu);
+}
+EXPORT_SYMBOL_GPL(memfile_unregister_notifier);
--
2.17.1
next prev parent reply other threads:[~2022-01-18 13:22 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-18 13:21 [PATCH v4 00/12] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 01/12] mm/shmem: Introduce F_SEAL_INACCESSIBLE Chao Peng
2022-02-07 12:24 ` Vlastimil Babka
2022-02-17 12:56 ` Chao Peng
2022-02-11 23:33 ` Andy Lutomirski
2022-02-17 13:06 ` Chao Peng
2022-02-17 19:09 ` Andy Lutomirski
2022-02-23 11:49 ` Chao Peng
2022-02-23 12:05 ` Steven Price
2022-03-04 19:24 ` Andy Lutomirski
2022-03-07 13:26 ` Chao Peng
2022-03-08 12:17 ` Paolo Bonzini
2022-01-18 13:21 ` [PATCH v4 02/12] mm/memfd: Introduce MFD_INACCESSIBLE flag Chao Peng
2022-01-21 15:50 ` Steven Price
2022-01-24 13:29 ` Chao Peng
2022-02-07 18:51 ` Vlastimil Babka
2022-02-08 8:49 ` David Hildenbrand
2022-02-08 18:22 ` Mike Rapoport
2022-01-18 13:21 ` Chao Peng [this message]
2022-03-07 15:42 ` [PATCH v4 03/12] mm: Introduce memfile_notifier Vlastimil Babka
2022-03-08 1:45 ` Chao Peng
2022-01-18 13:21 ` [PATCH v4 04/12] mm/shmem: Support memfile_notifier Chao Peng
2022-02-08 18:29 ` Mike Rapoport
2022-02-17 13:10 ` Chao Peng
2022-02-11 23:40 ` Andy Lutomirski
2022-02-17 13:23 ` Chao Peng
2022-01-18 13:21 ` [PATCH v4 05/12] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 06/12] KVM: Use kvm_userspace_memory_region_ext Chao Peng
2022-01-18 13:21 ` [PATCH v4 07/12] KVM: Add KVM_EXIT_MEMORY_ERROR exit Chao Peng
2022-01-18 13:21 ` [PATCH v4 08/12] KVM: Use memfile_pfn_ops to obtain pfn for private pages Chao Peng
2022-01-18 13:21 ` [PATCH v4 09/12] KVM: Handle page fault for private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 10/12] KVM: Register private memslot to memory backing store Chao Peng
2022-01-18 13:21 ` [PATCH v4 11/12] KVM: Zap existing KVM mappings when pages changed in the private fd Chao Peng
2022-01-18 13:21 ` [PATCH v4 12/12] KVM: Expose KVM_MEM_PRIVATE Chao Peng
2022-01-25 20:20 ` Maciej S. Szmigiero
2022-02-17 13:45 ` Chao Peng
2022-02-22 1:16 ` Maciej S. Szmigiero
2022-02-23 12:00 ` Chao Peng
2022-02-23 18:32 ` Maciej S. Szmigiero
2022-02-24 8:07 ` Chao Peng
2022-01-28 16:47 ` [PATCH v4 00/12] KVM: mm: fd-based approach for supporting KVM guest private memory Steven Price
2022-02-02 2:28 ` Nakajima, Jun
2022-02-02 9:23 ` Steven Price
2022-02-02 20:47 ` Nakajima, Jun
2022-02-08 18:33 ` Mike Rapoport
2022-02-17 13:47 ` Chao Peng
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=20220118132121.31388-4-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=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=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).