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.
Co-developed-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
---
include/linux/memfile_notifier.h | 64 +++++++++++++++++
mm/Kconfig | 4 ++
mm/Makefile | 1 +
mm/memfile_notifier.c | 114 +++++++++++++++++++++++++++++++
4 files changed, 183 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..e8d400558adb
--- /dev/null
+++ b/include/linux/memfile_notifier.h
@@ -0,0 +1,64 @@
+/* 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;
+};
+
+struct memfile_backing_store {
+ struct list_head list;
+ struct memfile_pfn_ops pfn_ops;
+ struct memfile_notifier_list* (*get_notifier_list)(struct inode *inode);
+};
+
+#ifdef CONFIG_MEMFILE_NOTIFIER
+/* APIs for backing stores */
+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 void memfile_register_backing_store(struct memfile_backing_store *bs);
+extern void memfile_unregister_backing_store(struct memfile_backing_store *bs);
+
+/*APIs for notifier consumers */
+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 3326ee3903f3..7c6b1ad3dade 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -892,6 +892,10 @@ config ANON_VMA_NAME
area from being merged with adjacent virtual memory areas due to the
difference in their name.
+config MEMFILE_NOTIFIER
+ bool
+ select SRCU
+
source "mm/damon/Kconfig"
endmenu
diff --git a/mm/Makefile b/mm/Makefile
index 70d4309c9ce3..f628256dce0d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -132,3 +132,4 @@ 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..a405db56fde2
--- /dev/null
+++ b/mm/memfile_notifier.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/mm/memfile_notifier.c
+ *
+ * Copyright (C) 2022 Intel Corporation.
+ * Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
+ */
+
+#include <linux/memfile_notifier.h>
+#include <linux/srcu.h>
+
+DEFINE_STATIC_SRCU(srcu);
+static LIST_HEAD(backing_store_list);
+
+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);
+}
+
+void memfile_register_backing_store(struct memfile_backing_store *bs)
+{
+ BUG_ON(!bs || !bs->get_notifier_list);
+
+ list_add_tail(&bs->list, &backing_store_list);
+}
+
+void memfile_unregister_backing_store(struct memfile_backing_store *bs)
+{
+ list_del(&bs->list);
+}
+
+static int memfile_get_notifier_info(struct inode *inode,
+ struct memfile_notifier_list **list,
+ struct memfile_pfn_ops **ops)
+{
+ struct memfile_backing_store *bs, *iter;
+ struct memfile_notifier_list *tmp;
+
+ list_for_each_entry_safe(bs, iter, &backing_store_list, list) {
+ tmp = bs->get_notifier_list(inode);
+ if (tmp) {
+ *list = tmp;
+ if (ops)
+ *ops = &bs->pfn_ops;
+ return 0;
+ }
+ }
+ 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
