Merge branch 'next-lockdown' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security

Pull kernel lockdown mode from James Morris:
 "This is the latest iteration of the kernel lockdown patchset, from
  Matthew Garrett, David Howells and others.

  From the original description:

    This patchset introduces an optional kernel lockdown feature,
    intended to strengthen the boundary between UID 0 and the kernel.
    When enabled, various pieces of kernel functionality are restricted.
    Applications that rely on low-level access to either hardware or the
    kernel may cease working as a result - therefore this should not be
    enabled without appropriate evaluation beforehand.

    The majority of mainstream distributions have been carrying variants
    of this patchset for many years now, so there's value in providing a
    doesn't meet every distribution requirement, but gets us much closer
    to not requiring external patches.

  There are two major changes since this was last proposed for mainline:

   - Separating lockdown from EFI secure boot. Background discussion is
     covered here: https://lwn.net/Articles/751061/

   -  Implementation as an LSM, with a default stackable lockdown LSM
      module. This allows the lockdown feature to be policy-driven,
      rather than encoding an implicit policy within the mechanism.

  The new locked_down LSM hook is provided to allow LSMs to make a
  policy decision around whether kernel functionality that would allow
  tampering with or examining the runtime state of the kernel should be
  permitted.

  The included lockdown LSM provides an implementation with a simple
  policy intended for general purpose use. This policy provides a coarse
  level of granularity, controllable via the kernel command line:

    lockdown={integrity|confidentiality}

  Enable the kernel lockdown feature. If set to integrity, kernel features
  that allow userland to modify the running kernel are disabled. If set to
  confidentiality, kernel features that allow userland to extract
  confidential information from the kernel are also disabled.

  This may also be controlled via /sys/kernel/security/lockdown and
  overriden by kernel configuration.

  New or existing LSMs may implement finer-grained controls of the
  lockdown features. Refer to the lockdown_reason documentation in
  include/linux/security.h for details.

  The lockdown feature has had signficant design feedback and review
  across many subsystems. This code has been in linux-next for some
  weeks, with a few fixes applied along the way.

  Stephen Rothwell noted that commit 9d1f8be5cf42 ("bpf: Restrict bpf
  when kernel lockdown is in confidentiality mode") is missing a
  Signed-off-by from its author. Matthew responded that he is providing
  this under category (c) of the DCO"

* 'next-lockdown' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security: (31 commits)
  kexec: Fix file verification on S390
  security: constify some arrays in lockdown LSM
  lockdown: Print current->comm in restriction messages
  efi: Restrict efivar_ssdt_load when the kernel is locked down
  tracefs: Restrict tracefs when the kernel is locked down
  debugfs: Restrict debugfs when the kernel is locked down
  kexec: Allow kexec_file() with appropriate IMA policy when locked down
  lockdown: Lock down perf when in confidentiality mode
  bpf: Restrict bpf when kernel lockdown is in confidentiality mode
  lockdown: Lock down tracing and perf kprobes when in confidentiality mode
  lockdown: Lock down /proc/kcore
  x86/mmiotrace: Lock down the testmmiotrace module
  lockdown: Lock down module params that specify hardware parameters (eg. ioport)
  lockdown: Lock down TIOCSSERIAL
  lockdown: Prohibit PCMCIA CIS storage when the kernel is locked down
  acpi: Disable ACPI table override if the kernel is locked down
  acpi: Ignore acpi_rsdp kernel param when the kernel has been locked down
  ACPI: Limit access to custom_method when the kernel is locked down
  x86/msr: Restrict MSR access when the kernel is locked down
  x86: Lock down IO port access when the kernel is locked down
  ...

4 files changed, 107 insertions, 3 deletions

diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 93e4ca6b2ad7..87846aad594b 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -19,6 +19,7 @@
 #include <linux/atomic.h>
 #include <linux/device.h>
 #include <linux/poll.h>
+#include <linux/security.h>
 
 #include "internal.h"
 
@@ -136,6 +137,25 @@ void debugfs_file_put(struct dentry *dentry)
 }
 EXPORT_SYMBOL_GPL(debugfs_file_put);
 
+/*
+ * Only permit access to world-readable files when the kernel is locked down.
+ * We also need to exclude any file that has ways to write or alter it as root
+ * can bypass the permissions check.
+ */
+static bool debugfs_is_locked_down(struct inode *inode,
+				   struct file *filp,
+				   const struct file_operations *real_fops)
+{
+	if ((inode->i_mode & 07777) == 0444 &&
+	    !(filp->f_mode & FMODE_WRITE) &&
+	    !real_fops->unlocked_ioctl &&
+	    !real_fops->compat_ioctl &&
+	    !real_fops->mmap)
+		return false;
+
+	return security_locked_down(LOCKDOWN_DEBUGFS);
+}
+
 static int open_proxy_open(struct inode *inode, struct file *filp)
 {
 	struct dentry *dentry = F_DENTRY(filp);
@@ -147,6 +167,11 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
 		return r == -EIO ? -ENOENT : r;
 
 	real_fops = debugfs_real_fops(filp);
+
+	r = debugfs_is_locked_down(inode, filp, real_fops);
+	if (r)
+		goto out;
+
 	real_fops = fops_get(real_fops);
 	if (!real_fops) {
 		/* Huh? Module did not clean up after itself at exit? */
@@ -272,6 +297,11 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
 		return r == -EIO ? -ENOENT : r;
 
 	real_fops = debugfs_real_fops(filp);
+
+	r = debugfs_is_locked_down(inode, filp, real_fops);
+	if (r)
+		goto out;
+
 	real_fops = fops_get(real_fops);
 	if (!real_fops) {
 		/* Huh? Module did not cleanup after itself at exit? */
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 042b688ed124..7b975dbb2bb4 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -26,6 +26,7 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/security.h>
 
 #include "internal.h"
 
@@ -35,6 +36,32 @@ static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
 static bool debugfs_registered;
 
+/*
+ * Don't allow access attributes to be changed whilst the kernel is locked down
+ * so that we can use the file mode as part of a heuristic to determine whether
+ * to lock down individual files.
+ */
+static int debugfs_setattr(struct dentry *dentry, struct iattr *ia)
+{
+	int ret = security_locked_down(LOCKDOWN_DEBUGFS);
+
+	if (ret && (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)))
+		return ret;
+	return simple_setattr(dentry, ia);
+}
+
+static const struct inode_operations debugfs_file_inode_operations = {
+	.setattr	= debugfs_setattr,
+};
+static const struct inode_operations debugfs_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.setattr	= debugfs_setattr,
+};
+static const struct inode_operations debugfs_symlink_inode_operations = {
+	.get_link	= simple_get_link,
+	.setattr	= debugfs_setattr,
+};
+
 static struct inode *debugfs_get_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -369,6 +396,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 	inode->i_mode = mode;
 	inode->i_private = data;
 
+	inode->i_op = &debugfs_file_inode_operations;
 	inode->i_fop = proxy_fops;
 	dentry->d_fsdata = (void *)((unsigned long)real_fops |
 				DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
@@ -532,7 +560,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 	}
 
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
-	inode->i_op = &simple_dir_inode_operations;
+	inode->i_op = &debugfs_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -632,7 +660,7 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 		return failed_creating(dentry);
 	}
 	inode->i_mode = S_IFLNK | S_IRWXUGO;
-	inode->i_op = &simple_symlink_inode_operations;
+	inode->i_op = &debugfs_symlink_inode_operations;
 	inode->i_link = link;
 	d_instantiate(dentry, inode);
 	return end_creating(dentry);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index f5834488b67d..e2ed8e08cc7a 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -31,6 +31,7 @@
 #include <linux/ioport.h>
 #include <linux/memory.h>
 #include <linux/sched/task.h>
+#include <linux/security.h>
 #include <asm/sections.h>
 #include "internal.h"
 
@@ -545,9 +546,14 @@ out:
 
 static int open_kcore(struct inode *inode, struct file *filp)
 {
+	int ret = security_locked_down(LOCKDOWN_KCORE);
+
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
 
+	if (ret)
+		return ret;
+
 	filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!filp->private_data)
 		return -ENOMEM;
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index eeeae0475da9..9fc14e38927f 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -20,6 +20,7 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/security.h>
 
 #define TRACEFS_DEFAULT_MODE	0700
 
@@ -27,6 +28,25 @@ static struct vfsmount *tracefs_mount;
 static int tracefs_mount_count;
 static bool tracefs_registered;
 
+static int default_open_file(struct inode *inode, struct file *filp)
+{
+	struct dentry *dentry = filp->f_path.dentry;
+	struct file_operations *real_fops;
+	int ret;
+
+	if (!dentry)
+		return -EINVAL;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
+	real_fops = dentry->d_fsdata;
+	if (!real_fops->open)
+		return 0;
+	return real_fops->open(inode, filp);
+}
+
 static ssize_t default_read_file(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)
 {
@@ -221,6 +241,12 @@ static int tracefs_apply_options(struct super_block *sb)
 	return 0;
 }
 
+static void tracefs_destroy_inode(struct inode *inode)
+{
+	if (S_ISREG(inode->i_mode))
+		kfree(inode->i_fop);
+}
+
 static int tracefs_remount(struct super_block *sb, int *flags, char *data)
 {
 	int err;
@@ -257,6 +283,7 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root)
 static const struct super_operations tracefs_super_operations = {
 	.statfs		= simple_statfs,
 	.remount_fs	= tracefs_remount,
+	.destroy_inode  = tracefs_destroy_inode,
 	.show_options	= tracefs_show_options,
 };
 
@@ -387,6 +414,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
+	struct file_operations *proxy_fops;
 	struct dentry *dentry;
 	struct inode *inode;
 
@@ -402,8 +430,20 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
+	proxy_fops = kzalloc(sizeof(struct file_operations), GFP_KERNEL);
+	if (unlikely(!proxy_fops)) {
+		iput(inode);
+		return failed_creating(dentry);
+	}
+
+	if (!fops)
+		fops = &tracefs_file_operations;
+
+	dentry->d_fsdata = (void *)fops;
+	memcpy(proxy_fops, fops, sizeof(*proxy_fops));
+	proxy_fops->open = default_open_file;
 	inode->i_mode = mode;
-	inode->i_fop = fops ? fops : &tracefs_file_operations;
+	inode->i_fop = proxy_fops;
 	inode->i_private = data;
 	d_instantiate(dentry, inode);
 	fsnotify_create(dentry->d_parent->d_inode, dentry);