block,lsm: add LSM blob and new LSM hooks for block devices

This patch introduces a new LSM blob to the block_device structure,
enabling the security subsystem to store security-sensitive data related
to block devices. Currently, for a device mapper's mapped device containing
a dm-verity target, critical security information such as the roothash and
its signing state are not readily accessible. Specifically, while the
dm-verity volume creation process passes the dm-verity roothash and its
signature from userspace to the kernel, the roothash is stored privately
within the dm-verity target, and its signature is discarded
post-verification. This makes it extremely hard for the security subsystem
to utilize these data.

With the addition of the LSM blob to the block_device structure, the
security subsystem can now retain and manage important security metadata
such as the roothash and the signing state of a dm-verity by storing them
inside the blob. Access decisions can then be based on these stored data.

The implementation follows the same approach used for security blobs in
other structures like struct file, struct inode, and struct superblock.
The initialization of the security blob occurs after the creation of the
struct block_device, performed by the security subsystem. Similarly, the
security blob is freed by the security subsystem before the struct
block_device is deallocated or freed.

This patch also introduces a new hook security_bdev_setintegrity() to save
block device's integrity data to the new LSM blob. For example, for
dm-verity, it can use this hook to expose its roothash and signing state
to LSMs, then LSMs can save these data into the LSM blob.

Please note that the new hook should be invoked every time the security
information is updated to keep these data current. For example, in
dm-verity, if the mapping table is reloaded and configured to use a
different dm-verity target with a new roothash and signing information,
the previously stored data in the LSM blob will become obsolete. It is
crucial to re-invoke the hook to refresh these data and ensure they are up
to date. This necessity arises from the design of device-mapper, where a
device-mapper device is first created, and then targets are subsequently
loaded into it. These targets can be modified multiple times during the
device's lifetime. Therefore, while the LSM blob is allocated during the
creation of the block device, its actual contents are not initialized at
this stage and can change substantially over time. This includes
alterations from data that the LSM 'trusts' to those it does not, making
it essential to handle these changes correctly. Failure to address this
dynamic aspect could potentially allow for bypassing LSM checks.
Signed-off-by: Deven Bowers <deven.desai@linux.microsoft.com>
Signed-off-by: Fan Wu <wufan@linux.microsoft.com>
[PM: merge fuzz, subject line tweaks]
Signed-off-by: Paul Moore <paul@paul-moore.com>

block/bdev.c

@@ -24,6 +24,7 @@
 #include <linux/pseudo_fs.h>
 #include <linux/uio.h>
 #include <linux/namei.h>
+#include <linux/security.h>
 #include <linux/part_stat.h>
 #include <linux/uaccess.h>
 #include <linux/stat.h>
@@ -324,6 +325,11 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
 	if (!ei)
 		return NULL;
 	memset(&ei->bdev, 0, sizeof(ei->bdev));
+
+	if (security_bdev_alloc(&ei->bdev)) {
+		kmem_cache_free(bdev_cachep, ei);
+		return NULL;
+	}
 	return &ei->vfs_inode;
 }
 
@@ -333,6 +339,7 @@ static void bdev_free_inode(struct inode *inode)
 
 	free_percpu(bdev->bd_stats);
 	kfree(bdev->bd_meta_info);
+	security_bdev_free(bdev);
 
 	if (!bdev_is_partition(bdev)) {
 		if (bdev->bd_disk && bdev->bd_disk->bdi)

include/linux/blk_types.h

@@ -71,6 +71,9 @@ struct block_device {
 
 	struct partition_meta_info *bd_meta_info;
 	int			bd_writers;
+#ifdef CONFIG_SECURITY
+	void			*bd_security;
+#endif
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
 	 * path

include/linux/lsm_hook_defs.h

@@ -451,3 +451,8 @@ LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd)
 #endif /* CONFIG_IO_URING */
 
 LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void)
+
+LSM_HOOK(int, 0, bdev_alloc_security, struct block_device *bdev)
+LSM_HOOK(void, LSM_RET_VOID, bdev_free_security, struct block_device *bdev)
+LSM_HOOK(int, 0, bdev_setintegrity, struct block_device *bdev,
+	 enum lsm_integrity_type type, const void *value, size_t size)

include/linux/lsm_hooks.h

@@ -83,6 +83,7 @@ struct lsm_blob_sizes {
 	int lbs_task;
 	int lbs_xattr_count; /* number of xattr slots in new_xattrs array */
 	int lbs_tun_dev;
+	int lbs_bdev;
 };
 
 /*

include/linux/security.h

@@ -83,6 +83,10 @@ enum lsm_event {
 	LSM_POLICY_CHANGE,
 };
 
+enum lsm_integrity_type {
+	__LSM_INT_MAX
+};
+
 /*
  * These are reasons that can be passed to the security_locked_down()
  * LSM hook. Lockdown reasons that protect kernel integrity (ie, the
@@ -509,6 +513,11 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen);
 int security_locked_down(enum lockdown_reason what);
 int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len,
 		      void *val, size_t val_len, u64 id, u64 flags);
+int security_bdev_alloc(struct block_device *bdev);
+void security_bdev_free(struct block_device *bdev);
+int security_bdev_setintegrity(struct block_device *bdev,
+			       enum lsm_integrity_type type, const void *value,
+			       size_t size);
 #else /* CONFIG_SECURITY */
 
 static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data)
@@ -1483,6 +1492,23 @@ static inline int lsm_fill_user_ctx(struct lsm_ctx __user *uctx,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int security_bdev_alloc(struct block_device *bdev)
+{
+	return 0;
+}
+
+static inline void security_bdev_free(struct block_device *bdev)
+{
+}
+
+static inline int security_bdev_setintegrity(struct block_device *bdev,
+					     enum lsm_integrity_type type,
+					     const void *value, size_t size)
+{
+	return 0;
+}
+
 #endif	/* CONFIG_SECURITY */
 
 #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)

security/security.c

@@ -29,6 +29,7 @@
 #include <linux/msg.h>
 #include <linux/overflow.h>
 #include <linux/perf_event.h>
+#include <linux/fs.h>
 #include <net/flow.h>
 #include <net/sock.h>
 
@@ -239,6 +240,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed)
 	lsm_set_blob_size(&needed->lbs_tun_dev, &blob_sizes.lbs_tun_dev);
 	lsm_set_blob_size(&needed->lbs_xattr_count,
 			  &blob_sizes.lbs_xattr_count);
+	lsm_set_blob_size(&needed->lbs_bdev, &blob_sizes.lbs_bdev);
 }
 
 /* Prepare LSM for initialization. */
@@ -419,6 +421,7 @@ static void __init ordered_lsm_init(void)
 	init_debug("task blob size       = %d\n", blob_sizes.lbs_task);
 	init_debug("tun device blob size = %d\n", blob_sizes.lbs_tun_dev);
 	init_debug("xattr slots          = %d\n", blob_sizes.lbs_xattr_count);
+	init_debug("bdev blob size       = %d\n", blob_sizes.lbs_bdev);
 
 	/*
 	 * Create any kmem_caches needed for blobs
@@ -758,6 +761,28 @@ static int lsm_msg_msg_alloc(struct msg_msg *mp)
 			      GFP_KERNEL);
 }
 
+/**
+ * lsm_bdev_alloc - allocate a composite block_device blob
+ * @bdev: the block_device that needs a blob
+ *
+ * Allocate the block_device blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_bdev_alloc(struct block_device *bdev)
+{
+	if (blob_sizes.lbs_bdev == 0) {
+		bdev->bd_security = NULL;
+		return 0;
+	}
+
+	bdev->bd_security = kzalloc(blob_sizes.lbs_bdev, GFP_KERNEL);
+	if (!bdev->bd_security)
+		return -ENOMEM;
+
+	return 0;
+}
+
 /**
  * lsm_early_task - during initialization allocate a composite task blob
  * @task: the task that needs a blob
@@ -5658,6 +5683,84 @@ int security_locked_down(enum lockdown_reason what)
 }
 EXPORT_SYMBOL(security_locked_down);
 
+/**
+ * security_bdev_alloc() - Allocate a block device LSM blob
+ * @bdev: block device
+ *
+ * Allocate and attach a security structure to @bdev->bd_security.  The
+ * security field is initialized to NULL when the bdev structure is
+ * allocated.
+ *
+ * Return: Return 0 if operation was successful.
+ */
+int security_bdev_alloc(struct block_device *bdev)
+{
+	int rc = 0;
+
+	rc = lsm_bdev_alloc(bdev);
+	if (unlikely(rc))
+		return rc;
+
+	rc = call_int_hook(bdev_alloc_security, bdev);
+	if (unlikely(rc))
+		security_bdev_free(bdev);
+
+	return rc;
+}
+EXPORT_SYMBOL(security_bdev_alloc);
+
+/**
+ * security_bdev_free() - Free a block device's LSM blob
+ * @bdev: block device
+ *
+ * Deallocate the bdev security structure and set @bdev->bd_security to NULL.
+ */
+void security_bdev_free(struct block_device *bdev)
+{
+	if (!bdev->bd_security)
+		return;
+
+	call_void_hook(bdev_free_security, bdev);
+
+	kfree(bdev->bd_security);
+	bdev->bd_security = NULL;
+}
+EXPORT_SYMBOL(security_bdev_free);
+
+/**
+ * security_bdev_setintegrity() - Set the device's integrity data
+ * @bdev: block device
+ * @type: type of integrity, e.g. hash digest, signature, etc
+ * @value: the integrity value
+ * @size: size of the integrity value
+ *
+ * Register a verified integrity measurement of a bdev with LSMs.
+ * LSMs should free the previously saved data if @value is NULL.
+ * Please note that the new hook should be invoked every time the security
+ * information is updated to keep these data current. For example, in dm-verity,
+ * if the mapping table is reloaded and configured to use a different dm-verity
+ * target with a new roothash and signing information, the previously stored data
+ * in the LSM blob will become obsolete. It is crucial to re-invoke the hook to
+ * refresh these data and ensure they are up to date. This necessity arises from
+ * the design of device-mapper, where a device-mapper device is first created, and
+ * then targets are subsequently loaded into it. These targets can be modified
+ * multiple times during the device's lifetime. Therefore, while the LSM blob is
+ * allocated during the creation of the block device, its actual contents are
+ * not initialized at this stage and can change substantially over time. This
+ * includes alterations from data that the LSMs 'trusts' to those they do not,
+ * making it essential to handle these changes correctly. Failure to address
+ * this dynamic aspect could potentially allow for bypassing LSM checks.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_bdev_setintegrity(struct block_device *bdev,
+			       enum lsm_integrity_type type, const void *value,
+			       size_t size)
+{
+	return call_int_hook(bdev_setintegrity, bdev, type, value, size);
+}
+EXPORT_SYMBOL(security_bdev_setintegrity);
+
 #ifdef CONFIG_PERF_EVENTS
 /**
  * security_perf_event_open() - Check if a perf event open is allowed