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 below components:
- memfile_backing_store: Each supported memory file subsystem can be
implemented as a memory backing store which bookmarks memory and
provides callbacks for other kernel systems (memfile_notifier
consumers) to interact with.
- memfile_notifier: memfile_notifier consumers defines callbacks and
associate them to a file using memfile_register_notifier().
- memfile_node: A memfile_node is associated with the file (inode) from
the backing store and includes feature flags and a list of registered
memfile_notifier for notifying.
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 memory slot to memory backing store via memfile_register_notifier.
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 | 99 ++++++++++++++++++++++
mm/Kconfig | 4 +
mm/Makefile | 1 +
mm/memfile_notifier.c | 137 +++++++++++++++++++++++++++++++
4 files changed, 241 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..dcb3ee6ed626
--- /dev/null
+++ b/include/linux/memfile_notifier.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MEMFILE_NOTIFIER_H
+#define _LINUX_MEMFILE_NOTIFIER_H
+
+#include <linux/pfn_t.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <linux/srcu.h>
+#include <linux/fs.h>
+
+
+#define MEMFILE_F_USER_INACCESSIBLE BIT(0) /* memory allocated in the file is inaccessible from userspace (e.g. read/write/mmap) */
+#define MEMFILE_F_UNMOVABLE BIT(1) /* memory allocated in the file is unmovable (e.g. via pagemigration)*/
+#define MEMFILE_F_UNRECLAIMABLE BIT(2) /* memory allocated in the file is unreclaimable (e.g. via kswapd) */
+
+#define MEMFILE_F_ALLOWED_MASK (MEMFILE_F_USER_INACCESSIBLE | \
+ MEMFILE_F_UNMOVABLE | \
+ MEMFILE_F_UNRECLAIMABLE)
+
+struct memfile_node {
+ struct list_head notifiers; /* registered memfile_notifier list on the file */
+ unsigned long flags; /* MEMFILE_F_* flags */
+};
+
+struct memfile_backing_store {
+ struct list_head list;
+ spinlock_t lock;
+ struct memfile_node* (*lookup_memfile_node)(struct file *file);
+ int (*get_lock_pfn)(struct file *file, pgoff_t offset, pfn_t *pfn,
+ int *order);
+ void (*put_unlock_pfn)(pfn_t pfn);
+};
+
+struct memfile_notifier;
+struct memfile_notifier_ops {
+ void (*populate)(struct memfile_notifier *notifier,
+ pgoff_t start, pgoff_t end);
+ void (*invalidate)(struct memfile_notifier *notifier,
+ pgoff_t start, pgoff_t end);
+};
+
+struct memfile_notifier {
+ struct list_head list;
+ struct memfile_notifier_ops *ops;
+ struct memfile_backing_store *bs;
+};
+
+static inline void memfile_node_init(struct memfile_node *node)
+{
+ INIT_LIST_HEAD(&node->notifiers);
+ node->flags = 0;
+}
+
+#ifdef CONFIG_MEMFILE_NOTIFIER
+/* APIs for backing stores */
+extern void memfile_register_backing_store(struct memfile_backing_store *bs);
+extern int memfile_node_set_flags(struct file *file, unsigned long flags);
+extern void memfile_notifier_populate(struct memfile_node *node,
+ pgoff_t start, pgoff_t end);
+extern void memfile_notifier_invalidate(struct memfile_node *node,
+ pgoff_t start, pgoff_t end);
+/*APIs for notifier consumers */
+extern int memfile_register_notifier(struct file *file, unsigned long flags,
+ struct memfile_notifier *notifier);
+extern void memfile_unregister_notifier(struct memfile_notifier *notifier);
+
+#else /* !CONFIG_MEMFILE_NOTIFIER */
+static void memfile_register_backing_store(struct memfile_backing_store *bs)
+{
+}
+
+static int memfile_node_set_flags(struct file *file, unsigned long flags)
+{
+ return -EOPNOTSUPP;
+}
+
+static void memfile_notifier_populate(struct memfile_node *node,
+ pgoff_t start, pgoff_t end)
+{
+}
+
+static void memfile_notifier_invalidate(struct memfile_node *node,
+ pgoff_t start, pgoff_t end)
+{
+}
+
+static int memfile_register_notifier(struct file *file, flags,
+ struct memfile_notifier *notifier)
+{
+ return -EOPNOTSUPP;
+}
+
+static void memfile_unregister_notifier(struct memfile_notifier *notifier)
+{
+}
+
+#endif /* CONFIG_MEMFILE_NOTIFIER */
+
+#endif /* _LINUX_MEMFILE_NOTIFIER_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index 034d87953600..e551e99cd42a 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -909,6 +909,10 @@ 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 4cc13f3179a5..261a5cb315f9 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -133,3 +133,4 @@ 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..ab9461cb874e
--- /dev/null
+++ b/mm/memfile_notifier.c
@@ -0,0 +1,137 @@
+// 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/pagemap.h>
+#include <linux/srcu.h>
+
+DEFINE_STATIC_SRCU(memfile_srcu);
+static __ro_after_init LIST_HEAD(backing_store_list);
+
+void memfile_notifier_populate(struct memfile_node *node,
+ pgoff_t start, pgoff_t end)
+{
+ struct memfile_notifier *notifier;
+ int id;
+
+ id = srcu_read_lock(&memfile_srcu);
+ list_for_each_entry_srcu(notifier, &node->notifiers, list,
+ srcu_read_lock_held(&memfile_srcu)) {
+ if (notifier->ops->populate)
+ notifier->ops->populate(notifier, start, end);
+ }
+ srcu_read_unlock(&memfile_srcu, id);
+}
+
+void memfile_notifier_invalidate(struct memfile_node *node,
+ pgoff_t start, pgoff_t end)
+{
+ struct memfile_notifier *notifier;
+ int id;
+
+ id = srcu_read_lock(&memfile_srcu);
+ list_for_each_entry_srcu(notifier, &node->notifiers, list,
+ srcu_read_lock_held(&memfile_srcu)) {
+ if (notifier->ops->invalidate)
+ notifier->ops->invalidate(notifier, start, end);
+ }
+ srcu_read_unlock(&memfile_srcu, id);
+}
+
+void __init memfile_register_backing_store(struct memfile_backing_store *bs)
+{
+ spin_lock_init(&bs->lock);
+ list_add_tail(&bs->list, &backing_store_list);
+}
+
+static void memfile_node_update_flags(struct file *file, unsigned long flags)
+{
+ struct address_space *mapping = file_inode(file)->i_mapping;
+ gfp_t gfp;
+
+ gfp = mapping_gfp_mask(mapping);
+ if (flags & MEMFILE_F_UNMOVABLE)
+ gfp &= ~__GFP_MOVABLE;
+ else
+ gfp |= __GFP_MOVABLE;
+ mapping_set_gfp_mask(mapping, gfp);
+
+ if (flags & MEMFILE_F_UNRECLAIMABLE)
+ mapping_set_unevictable(mapping);
+ else
+ mapping_clear_unevictable(mapping);
+}
+
+int memfile_node_set_flags(struct file *file, unsigned long flags)
+{
+ struct memfile_backing_store *bs;
+ struct memfile_node *node;
+
+ if (flags & ~MEMFILE_F_ALLOWED_MASK)
+ return -EINVAL;
+
+ list_for_each_entry(bs, &backing_store_list, list) {
+ node = bs->lookup_memfile_node(file);
+ if (node) {
+ spin_lock(&bs->lock);
+ node->flags = flags;
+ spin_unlock(&bs->lock);
+ memfile_node_update_flags(file, flags);
+ return 0;
+ }
+ }
+
+ return -EOPNOTSUPP;
+}
+
+int memfile_register_notifier(struct file *file, unsigned long flags,
+ struct memfile_notifier *notifier)
+{
+ struct memfile_backing_store *bs;
+ struct memfile_node *node;
+ struct list_head *list;
+
+ if (!file || !notifier || !notifier->ops)
+ return -EINVAL;
+ if (flags & ~MEMFILE_F_ALLOWED_MASK)
+ return -EINVAL;
+
+ list_for_each_entry(bs, &backing_store_list, list) {
+ node = bs->lookup_memfile_node(file);
+ if (node) {
+ list = &node->notifiers;
+ notifier->bs = bs;
+
+ spin_lock(&bs->lock);
+ if (list_empty(list))
+ node->flags = flags;
+ else if (node->flags ^ flags) {
+ spin_unlock(&bs->lock);
+ return -EINVAL;
+ }
+
+ list_add_rcu(¬ifier->list, list);
+ spin_unlock(&bs->lock);
+ memfile_node_update_flags(file, flags);
+ return 0;
+ }
+ }
+
+ return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(memfile_register_notifier);
+
+void memfile_unregister_notifier(struct memfile_notifier *notifier)
+{
+ spin_lock(¬ifier->bs->lock);
+ list_del_rcu(¬ifier->list);
+ spin_unlock(¬ifier->bs->lock);
+
+ synchronize_srcu(&memfile_srcu);
+}
+EXPORT_SYMBOL_GPL(memfile_unregister_notifier);
--
2.25.1
