1 files changed, 307 insertions, 20 deletions

diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c
index 319522450854..f89f0ca3d4ed 100644
--- a/security/integrity/ima/ima_queue.c
+++ b/security/integrity/ima/ima_queue.c
@@ -22,24 +22,42 @@
 
 #define AUDIT_CAUSE_LEN_MAX 32
 
+bool ima_flush_htable;
+
+static int __init ima_flush_htable_setup(char *str)
+{
+	if (IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE)) {
+		pr_warn("Hash table not enabled, ignoring request to flush\n");
+		return 1;
+	}
+
+	ima_flush_htable = true;
+	return 1;
+}
+__setup("ima_flush_htable", ima_flush_htable_setup);
+
 /* pre-allocated array of tpm_digest structures to extend a PCR */
 static struct tpm_digest *digests;
 
 LIST_HEAD(ima_measurements);	/* list of all measurements */
+LIST_HEAD(ima_measurements_staged); /* list of staged measurements */
 #ifdef CONFIG_IMA_KEXEC
-static unsigned long binary_runtime_size;
+static unsigned long binary_runtime_size[BINARY__LAST];
 #else
-static unsigned long binary_runtime_size = ULONG_MAX;
+static unsigned long binary_runtime_size[BINARY__LAST] = {
+	[0 ... BINARY__LAST - 1] = ULONG_MAX
+};
 #endif
 
-/* key: inode (before secure-hashing a file) */
-struct ima_h_table ima_htable = {
-	.len = ATOMIC_LONG_INIT(0),
-	.violations = ATOMIC_LONG_INIT(0),
-	.queue[0 ... IMA_MEASURE_HTABLE_SIZE - 1] = HLIST_HEAD_INIT
+atomic_long_t ima_num_records[BINARY__LAST] = {
+	[0 ... BINARY__LAST - 1] = ATOMIC_LONG_INIT(0)
 };
+atomic_long_t ima_num_violations = ATOMIC_LONG_INIT(0);
 
-/* mutex protects atomicity of extending measurement list
+/* key: inode (before secure-hashing a file) */
+struct hlist_head __rcu *ima_htable;
+
+/* mutex protects atomicity of extending and staging measurement list
  * and extending the TPM PCR aggregate. Since tpm_extend can take
  * long (and the tpm driver uses a mutex), we can't use the spinlock.
  */
@@ -51,17 +69,53 @@ static DEFINE_MUTEX(ima_extend_list_mutex);
  */
 static bool ima_measurements_suspended;
 
+/* Callers must call synchronize_rcu() and free the hash table. */
+static struct hlist_head *ima_alloc_replace_htable(void)
+{
+	struct hlist_head *old_htable, *new_htable;
+
+	/* Initializing to zeros is equivalent to call HLIST_HEAD_INIT. */
+	new_htable = kcalloc(IMA_MEASURE_HTABLE_SIZE, sizeof(struct hlist_head),
+			     GFP_KERNEL);
+	if (!new_htable)
+		return ERR_PTR(-ENOMEM);
+
+	old_htable = rcu_replace_pointer(ima_htable, new_htable,
+				lockdep_is_held(&ima_extend_list_mutex));
+
+	return old_htable;
+}
+
+int __init ima_init_htable(void)
+{
+	struct hlist_head *old_htable;
+
+	mutex_lock(&ima_extend_list_mutex);
+	old_htable = ima_alloc_replace_htable();
+	mutex_unlock(&ima_extend_list_mutex);
+
+	if (IS_ERR(old_htable))
+		return PTR_ERR(old_htable);
+
+	/* Synchronize_rcu() and kfree() not necessary, only for robustness. */
+	synchronize_rcu();
+	kfree(old_htable);
+	return 0;
+}
+
 /* lookup up the digest value in the hash table, and return the entry */
 static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value,
 						       int pcr)
 {
 	struct ima_queue_entry *qe, *ret = NULL;
+	struct hlist_head *htable;
 	unsigned int key;
 	int rc;
 
 	key = ima_hash_key(digest_value);
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(qe, &ima_htable.queue[key], hnext) {
+	htable = rcu_dereference(ima_htable);
+	hlist_for_each_entry_rcu(qe, &htable[key], hnext) {
 		rc = memcmp(qe->entry->digests[ima_hash_algo_idx].digest,
 			    digest_value, hash_digest_size[ima_hash_algo]);
 		if ((rc == 0) && (qe->entry->pcr == pcr)) {
@@ -91,6 +145,20 @@ static int get_binary_runtime_size(struct ima_template_entry *entry)
 	return size;
 }
 
+static void ima_update_binary_runtime_size(struct ima_template_entry *entry,
+					   enum binary_lists binary_list)
+{
+	int size;
+
+	if (binary_runtime_size[binary_list] == ULONG_MAX)
+		return;
+
+	size = get_binary_runtime_size(entry);
+	binary_runtime_size[binary_list] =
+		(binary_runtime_size[binary_list] < ULONG_MAX - size) ?
+		binary_runtime_size[binary_list] + size : ULONG_MAX;
+}
+
 /* ima_add_template_entry helper function:
  * - Add template entry to the measurement list and hash table, for
  *   all entries except those carried across kexec.
@@ -101,6 +169,7 @@ static int ima_add_digest_entry(struct ima_template_entry *entry,
 				bool update_htable)
 {
 	struct ima_queue_entry *qe;
+	struct hlist_head *htable;
 	unsigned int key;
 
 	qe = kmalloc_obj(*qe);
@@ -113,19 +182,20 @@ static int ima_add_digest_entry(struct ima_template_entry *entry,
 	INIT_LIST_HEAD(&qe->later);
 	list_add_tail_rcu(&qe->later, &ima_measurements);
 
-	atomic_long_inc(&ima_htable.len);
+	htable = rcu_dereference_protected(ima_htable,
+				lockdep_is_held(&ima_extend_list_mutex));
+
+	atomic_long_inc(&ima_num_records[BINARY]);
+	atomic_long_inc(&ima_num_records[BINARY_FULL]);
+
 	if (update_htable) {
 		key = ima_hash_key(entry->digests[ima_hash_algo_idx].digest);
-		hlist_add_head_rcu(&qe->hnext, &ima_htable.queue[key]);
+		hlist_add_head_rcu(&qe->hnext, &htable[key]);
 	}
 
-	if (binary_runtime_size != ULONG_MAX) {
-		int size;
+	ima_update_binary_runtime_size(entry, BINARY);
+	ima_update_binary_runtime_size(entry, BINARY_FULL);
 
-		size = get_binary_runtime_size(entry);
-		binary_runtime_size = (binary_runtime_size < ULONG_MAX - size) ?
-		     binary_runtime_size + size : ULONG_MAX;
-	}
 	return 0;
 }
 
@@ -134,12 +204,18 @@ static int ima_add_digest_entry(struct ima_template_entry *entry,
  * entire binary_runtime_measurement list, including the ima_kexec_hdr
  * structure.
  */
-unsigned long ima_get_binary_runtime_size(void)
+unsigned long ima_get_binary_runtime_size(enum binary_lists binary_list)
 {
-	if (binary_runtime_size >= (ULONG_MAX - sizeof(struct ima_kexec_hdr)))
+	unsigned long val;
+
+	mutex_lock(&ima_extend_list_mutex);
+	val = binary_runtime_size[binary_list];
+	mutex_unlock(&ima_extend_list_mutex);
+
+	if (val >= (ULONG_MAX - sizeof(struct ima_kexec_hdr)))
 		return ULONG_MAX;
 	else
-		return binary_runtime_size + sizeof(struct ima_kexec_hdr);
+		return val + sizeof(struct ima_kexec_hdr);
 }
 
 static int ima_pcr_extend(struct tpm_digest *digests_arg, int pcr)
@@ -220,6 +296,217 @@ out:
 	return result;
 }
 
+/**
+ * ima_queue_stage - Stage all measurements
+ *
+ * If the staged measurements list is empty, the current measurements list is
+ * not empty, and measurement is not suspended, move the measurements from the
+ * current list to the staged one, and update the number of records and binary
+ * run-time size accordingly.
+ *
+ * Do not allow staging after measurement is suspended, so that dumping
+ * measurements can be done in a lockless way.
+ *
+ * Return: Zero on success, a negative value otherwise.
+ */
+int ima_queue_stage(void)
+{
+	int ret = 0;
+
+	mutex_lock(&ima_extend_list_mutex);
+	if (!list_empty(&ima_measurements_staged)) {
+		ret = -EEXIST;
+		goto out_unlock;
+	}
+
+	if (list_empty(&ima_measurements)) {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
+
+	if (ima_measurements_suspended) {
+		ret = -EACCES;
+		goto out_unlock;
+	}
+
+	list_replace(&ima_measurements, &ima_measurements_staged);
+	INIT_LIST_HEAD(&ima_measurements);
+
+	atomic_long_set(&ima_num_records[BINARY_STAGED],
+			atomic_long_read(&ima_num_records[BINARY]));
+	atomic_long_set(&ima_num_records[BINARY], 0);
+
+	if (IS_ENABLED(CONFIG_IMA_KEXEC)) {
+		binary_runtime_size[BINARY_STAGED] =
+					binary_runtime_size[BINARY];
+		binary_runtime_size[BINARY] = 0;
+	}
+out_unlock:
+	mutex_unlock(&ima_extend_list_mutex);
+	return ret;
+}
+
+static void ima_queue_delete(struct list_head *head, bool flush_htable);
+
+/**
+ * ima_queue_staged_delete_all - Delete staged measurements
+ *
+ * Move staged measurements to a temporary list, ima_measurements_trim, update
+ * the number of records and the binary run-time size accordingly. Finally,
+ * delete measurements in the temporary list.
+ *
+ * Refuse to delete staged measurements if measurement is suspended, so that
+ * dump can be done in a lockless way and user space is notified about staged
+ * measurements being carried over to the secondary kernel, so that it does not
+ * save them twice.
+ *
+ * Return: Zero on success, a negative value otherwise.
+ */
+int ima_queue_staged_delete_all(void)
+{
+	struct hlist_head *old_queue = NULL;
+	LIST_HEAD(ima_measurements_trim);
+
+	mutex_lock(&ima_extend_list_mutex);
+	if (list_empty(&ima_measurements_staged)) {
+		mutex_unlock(&ima_extend_list_mutex);
+		return -ENOENT;
+	}
+
+	if (ima_measurements_suspended) {
+		mutex_unlock(&ima_extend_list_mutex);
+		return -ESTALE;
+	}
+
+	list_replace(&ima_measurements_staged, &ima_measurements_trim);
+	INIT_LIST_HEAD(&ima_measurements_staged);
+
+	atomic_long_set(&ima_num_records[BINARY_STAGED], 0);
+
+	if (IS_ENABLED(CONFIG_IMA_KEXEC))
+		binary_runtime_size[BINARY_STAGED] = 0;
+
+	if (ima_flush_htable) {
+		old_queue = ima_alloc_replace_htable();
+		if (IS_ERR(old_queue)) {
+			mutex_unlock(&ima_extend_list_mutex);
+			return PTR_ERR(old_queue);
+		}
+	}
+
+	mutex_unlock(&ima_extend_list_mutex);
+
+	if (ima_flush_htable) {
+		synchronize_rcu();
+		kfree(old_queue);
+	}
+
+	ima_queue_delete(&ima_measurements_trim, ima_flush_htable);
+	return 0;
+}
+
+/**
+ * ima_queue_delete_partial - Delete current measurements
+ * @req_value: Number of measurements to delete
+ *
+ * Delete the requested number of measurements from the current measurements
+ * list, and update the number of records and the binary run-time size
+ * accordingly.
+ *
+ * Refuse to delete current measurements if measurement is suspended, so that
+ * dump can be done in a lockless way and user space is notified about current
+ * measurements being carried over to the secondary kernel, so that it does not
+ * save them twice.
+ *
+ * Return: Zero on success, a negative value otherwise.
+ */
+int ima_queue_delete_partial(unsigned long req_value)
+{
+	unsigned long req_value_copy = req_value;
+	unsigned long size_to_remove = 0, num_to_remove = 0;
+	LIST_HEAD(ima_measurements_trim);
+	struct ima_queue_entry *qe;
+	int ret = 0;
+
+	/*
+	 * list_for_each_entry_rcu() without rcu_read_lock() is fine because
+	 * only list append can happen concurrently. No list replace due to the
+	 * staging/delete writers mutual exclusion.
+	 */
+	list_for_each_entry_rcu(qe, &ima_measurements, later, true) {
+		size_to_remove += get_binary_runtime_size(qe->entry);
+		num_to_remove++;
+
+		if (--req_value_copy == 0)
+			break;
+	}
+
+	/* Not enough records to delete. */
+	if (req_value_copy > 0)
+		return -ENOENT;
+
+	mutex_lock(&ima_extend_list_mutex);
+	if (ima_measurements_suspended) {
+		mutex_unlock(&ima_extend_list_mutex);
+		return -ESTALE;
+	}
+
+	/*
+	 * qe remains valid because ima_fs.c enforces single-writer exclusion.
+	 */
+	__list_cut_position(&ima_measurements_trim, &ima_measurements,
+			    &qe->later);
+
+	atomic_long_sub(num_to_remove, &ima_num_records[BINARY]);
+
+	if (IS_ENABLED(CONFIG_IMA_KEXEC))
+		binary_runtime_size[BINARY] -= size_to_remove;
+
+	mutex_unlock(&ima_extend_list_mutex);
+
+	ima_queue_delete(&ima_measurements_trim, false);
+	return ret;
+}
+
+/**
+ * ima_queue_delete - Delete measurements
+ * @head: List head measurements are deleted from
+ * @flush_htable: Whether or not the hash table is being flushed
+ *
+ * Delete the measurements from the passed list head completely if the
+ * hash table is not enabled or is being flushed, or partially (only the
+ * template data), if the hash table is used.
+ */
+static void ima_queue_delete(struct list_head *head, bool flush_htable)
+{
+	struct ima_queue_entry *qe, *qe_tmp;
+	unsigned int i;
+
+	list_for_each_entry_safe(qe, qe_tmp, head, later) {
+		/*
+		 * Safe to free template_data here without synchronize_rcu()
+		 * because the only htable reader, ima_lookup_digest_entry(),
+		 * accesses only entry->digests, not template_data. If new
+		 * htable readers are added that access template_data, a
+		 * synchronize_rcu() is required here.
+		 */
+		for (i = 0; i < qe->entry->template_desc->num_fields; i++) {
+			kfree(qe->entry->template_data[i].data);
+			qe->entry->template_data[i].data = NULL;
+			qe->entry->template_data[i].len = 0;
+		}
+
+		list_del(&qe->later);
+
+		/* No leak if condition is false, referenced by ima_htable. */
+		if (IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE) || flush_htable) {
+			kfree(qe->entry->digests);
+			kfree(qe->entry);
+			kfree(qe);
+		}
+	}
+}
+
 int ima_restore_measurement_entry(struct ima_template_entry *entry)
 {
 	int result = 0;