[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240205120203.60312-2-jgowans@amazon.com>
Date: Mon, 5 Feb 2024 12:01:46 +0000
From: James Gowans <jgowans@...zon.com>
To: <linux-kernel@...r.kernel.org>
CC: Eric Biederman <ebiederm@...ssion.com>, <kexec@...ts.infradead.org>,
"Joerg Roedel" <joro@...tes.org>, Will Deacon <will@...nel.org>,
<iommu@...ts.linux.dev>, Alexander Viro <viro@...iv.linux.org.uk>, "Christian
Brauner" <brauner@...nel.org>, <linux-fsdevel@...r.kernel.org>, Paolo Bonzini
<pbonzini@...hat.com>, Sean Christopherson <seanjc@...gle.com>,
<kvm@...r.kernel.org>, Andrew Morton <akpm@...ux-foundation.org>,
<linux-mm@...ck.org>, Alexander Graf <graf@...zon.com>, David Woodhouse
<dwmw@...zon.co.uk>, "Jan H . Schoenherr" <jschoenh@...zon.de>, Usama Arif
<usama.arif@...edance.com>, Anthony Yznaga <anthony.yznaga@...cle.com>,
Stanislav Kinsburskii <skinsburskii@...ux.microsoft.com>,
<madvenka@...ux.microsoft.com>, <steven.sistare@...cle.com>,
<yuleixzhang@...cent.com>
Subject: [RFC 01/18] pkernfs: Introduce filesystem skeleton
Add an in-memory filesystem: pkernfs. Memory is donated to pkernfs by
carving it out of the normal System RAM range with the memmap= cmdline
parameter and then giving that same physical range to pkernfs with the
pkernfs= cmdline parameter.
A new filesystem is added; so far it doesn't do much except persist a
super block at the start of the donated memory and allows itself to be
mounted.
---
fs/Kconfig | 1 +
fs/Makefile | 3 ++
fs/pkernfs/Kconfig | 9 ++++
fs/pkernfs/Makefile | 6 +++
fs/pkernfs/pkernfs.c | 99 ++++++++++++++++++++++++++++++++++++++++++++
fs/pkernfs/pkernfs.h | 6 +++
6 files changed, 124 insertions(+)
create mode 100644 fs/pkernfs/Kconfig
create mode 100644 fs/pkernfs/Makefile
create mode 100644 fs/pkernfs/pkernfs.c
create mode 100644 fs/pkernfs/pkernfs.h
diff --git a/fs/Kconfig b/fs/Kconfig
index aa7e03cc1941..33a9770ae657 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -331,6 +331,7 @@ source "fs/sysv/Kconfig"
source "fs/ufs/Kconfig"
source "fs/erofs/Kconfig"
source "fs/vboxsf/Kconfig"
+source "fs/pkernfs/Kconfig"
endif # MISC_FILESYSTEMS
diff --git a/fs/Makefile b/fs/Makefile
index f9541f40be4e..1af35b494b5d 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -19,6 +19,9 @@ obj-y := open.o read_write.o file_table.o super.o \
obj-$(CONFIG_BUFFER_HEAD) += buffer.o mpage.o
obj-$(CONFIG_PROC_FS) += proc_namespace.o
+
+obj-y += pkernfs/
+
obj-$(CONFIG_LEGACY_DIRECT_IO) += direct-io.o
obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
diff --git a/fs/pkernfs/Kconfig b/fs/pkernfs/Kconfig
new file mode 100644
index 000000000000..59621a1d9aef
--- /dev/null
+++ b/fs/pkernfs/Kconfig
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config PKERNFS_FS
+ bool "Persistent Kernel filesystem (pkernfs)"
+ help
+ An in-memory filesystem on top of reserved memory specified via
+ pkernfs= cmdline argument. Used for storing kernel state and
+ userspace memory which is preserved across kexec to support
+ live update.
diff --git a/fs/pkernfs/Makefile b/fs/pkernfs/Makefile
new file mode 100644
index 000000000000..17258cb77f58
--- /dev/null
+++ b/fs/pkernfs/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for persistent kernel filesystem
+#
+
+obj-$(CONFIG_PKERNFS_FS) += pkernfs.o
diff --git a/fs/pkernfs/pkernfs.c b/fs/pkernfs/pkernfs.c
new file mode 100644
index 000000000000..4c476ddc35b6
--- /dev/null
+++ b/fs/pkernfs/pkernfs.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "pkernfs.h"
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/fs_context.h>
+#include <linux/io.h>
+
+static phys_addr_t pkernfs_base, pkernfs_size;
+static void *pkernfs_mem;
+static const struct super_operations pkernfs_super_ops = { };
+
+static int pkernfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+ struct inode *inode;
+ struct dentry *dentry;
+ struct pkernfs_sb *psb;
+
+ pkernfs_mem = memremap(pkernfs_base, pkernfs_size, MEMREMAP_WB);
+ psb = (struct pkernfs_sb *) pkernfs_mem;
+
+ if (psb->magic_number == PKERNFS_MAGIC_NUMBER) {
+ pr_info("pkernfs: Restoring from super block\n");
+ } else {
+ pr_info("pkernfs: Clean super block; initialising\n");
+ psb->magic_number = PKERNFS_MAGIC_NUMBER;
+ }
+
+ sb->s_op = &pkernfs_super_ops;
+
+ inode = new_inode(sb);
+ if (!inode)
+ return -ENOMEM;
+
+ inode->i_ino = 1;
+ inode->i_mode = S_IFDIR;
+ inode->i_op = &simple_dir_inode_operations;
+ inode->i_fop = &simple_dir_operations;
+ inode->i_atime = inode->i_mtime = current_time(inode);
+ inode_set_ctime_current(inode);
+ /* directory inodes start off with i_nlink == 2 (for "." entry) */
+ inc_nlink(inode);
+
+ dentry = d_make_root(inode);
+ if (!dentry)
+ return -ENOMEM;
+ sb->s_root = dentry;
+
+ return 0;
+}
+
+static int pkernfs_get_tree(struct fs_context *fc)
+{
+ return get_tree_nodev(fc, pkernfs_fill_super);
+}
+
+static const struct fs_context_operations pkernfs_context_ops = {
+ .get_tree = pkernfs_get_tree,
+};
+
+static int pkernfs_init_fs_context(struct fs_context *const fc)
+{
+ fc->ops = &pkernfs_context_ops;
+ return 0;
+}
+
+static struct file_system_type pkernfs_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "pkernfs",
+ .init_fs_context = pkernfs_init_fs_context,
+ .kill_sb = kill_litter_super,
+ .fs_flags = FS_USERNS_MOUNT,
+};
+
+static int __init pkernfs_init(void)
+{
+ int ret;
+
+ ret = register_filesystem(&pkernfs_fs_type);
+ return ret;
+}
+
+/**
+ * Format: pkernfs=<size>:<base>
+ * Just like: memmap=nn[KMG]!ss[KMG]
+ */
+static int __init parse_pkernfs_extents(char *p)
+{
+ pkernfs_size = memparse(p, &p);
+ p++; /* Skip over ! char */
+ pkernfs_base = memparse(p, &p);
+ return 0;
+}
+
+early_param("pkernfs", parse_pkernfs_extents);
+
+MODULE_ALIAS_FS("pkernfs");
+module_init(pkernfs_init);
diff --git a/fs/pkernfs/pkernfs.h b/fs/pkernfs/pkernfs.h
new file mode 100644
index 000000000000..bd1e2a6fd336
--- /dev/null
+++ b/fs/pkernfs/pkernfs.h
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#define PKERNFS_MAGIC_NUMBER 0x706b65726e6673
+struct pkernfs_sb {
+ unsigned long magic_number;
+};
--
2.40.1
Powered by blists - more mailing lists