2 files changed, 208 insertions, 121 deletions

diff --git a/drivers/char/random.c b/drivers/char/random.c
index e027e7fa1472..cd888d4ee605 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -261,6 +261,7 @@
 #include <linux/ptrace.h>
 #include <linux/workqueue.h>
 #include <linux/irq.h>
+#include <linux/ratelimit.h>
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
@@ -427,8 +428,9 @@ struct crng_state primary_crng = {
  * its value (from 0->1->2).
  */
 static int crng_init = 0;
-#define crng_ready() (likely(crng_init > 0))
+#define crng_ready() (likely(crng_init > 1))
 static int crng_init_cnt = 0;
+static unsigned long crng_global_init_time = 0;
 #define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
 static void _extract_crng(struct crng_state *crng,
 			  __u32 out[CHACHA20_BLOCK_WORDS]);
@@ -437,6 +439,16 @@ static void _crng_backtrack_protect(struct crng_state *crng,
 static void process_random_ready_list(void);
 static void _get_random_bytes(void *buf, int nbytes);
 
+static struct ratelimit_state unseeded_warning =
+	RATELIMIT_STATE_INIT("warn_unseeded_randomness", HZ, 3);
+static struct ratelimit_state urandom_warning =
+	RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3);
+
+static int ratelimit_disable __read_mostly;
+
+module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
+MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
+
 /**********************************************************************
  *
  * OS independent entropy store.   Here are the functions which handle
@@ -787,6 +799,43 @@ static void crng_initialize(struct crng_state *crng)
 	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
 }
 
+#ifdef CONFIG_NUMA
+static void do_numa_crng_init(struct work_struct *work)
+{
+	int i;
+	struct crng_state *crng;
+	struct crng_state **pool;
+
+	pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
+	for_each_online_node(i) {
+		crng = kmalloc_node(sizeof(struct crng_state),
+				    GFP_KERNEL | __GFP_NOFAIL, i);
+		spin_lock_init(&crng->lock);
+		crng_initialize(crng);
+		pool[i] = crng;
+	}
+	mb();
+	if (cmpxchg(&crng_node_pool, NULL, pool)) {
+		for_each_node(i)
+			kfree(pool[i]);
+		kfree(pool);
+	}
+}
+
+static DECLARE_WORK(numa_crng_init_work, do_numa_crng_init);
+
+static void numa_crng_init(void)
+{
+	schedule_work(&numa_crng_init_work);
+}
+#else
+static void numa_crng_init(void) {}
+#endif
+
+/*
+ * crng_fast_load() can be called by code in the interrupt service
+ * path.  So we can't afford to dilly-dally.
+ */
 static int crng_fast_load(const char *cp, size_t len)
 {
 	unsigned long flags;
@@ -794,7 +843,7 @@ static int crng_fast_load(const char *cp, size_t len)
 
 	if (!spin_trylock_irqsave(&primary_crng.lock, flags))
 		return 0;
-	if (crng_ready()) {
+	if (crng_init != 0) {
 		spin_unlock_irqrestore(&primary_crng.lock, flags);
 		return 0;
 	}
@@ -813,6 +862,51 @@ static int crng_fast_load(const char *cp, size_t len)
 	return 1;
 }
 
+/*
+ * crng_slow_load() is called by add_device_randomness, which has two
+ * attributes.  (1) We can't trust the buffer passed to it is
+ * guaranteed to be unpredictable (so it might not have any entropy at
+ * all), and (2) it doesn't have the performance constraints of
+ * crng_fast_load().
+ *
+ * So we do something more comprehensive which is guaranteed to touch
+ * all of the primary_crng's state, and which uses a LFSR with a
+ * period of 255 as part of the mixing algorithm.  Finally, we do
+ * *not* advance crng_init_cnt since buffer we may get may be something
+ * like a fixed DMI table (for example), which might very well be
+ * unique to the machine, but is otherwise unvarying.
+ */
+static int crng_slow_load(const char *cp, size_t len)
+{
+	unsigned long		flags;
+	static unsigned char	lfsr = 1;
+	unsigned char		tmp;
+	unsigned		i, max = CHACHA20_KEY_SIZE;
+	const char *		src_buf = cp;
+	char *			dest_buf = (char *) &primary_crng.state[4];
+
+	if (!spin_trylock_irqsave(&primary_crng.lock, flags))
+		return 0;
+	if (crng_init != 0) {
+		spin_unlock_irqrestore(&primary_crng.lock, flags);
+		return 0;
+	}
+	if (len > max)
+		max = len;
+
+	for (i = 0; i < max ; i++) {
+		tmp = lfsr;
+		lfsr >>= 1;
+		if (tmp & 1)
+			lfsr ^= 0xE1;
+		tmp = dest_buf[i % CHACHA20_KEY_SIZE];
+		dest_buf[i % CHACHA20_KEY_SIZE] ^= src_buf[i % len] ^ lfsr;
+		lfsr += (tmp << 3) | (tmp >> 5);
+	}
+	spin_unlock_irqrestore(&primary_crng.lock, flags);
+	return 1;
+}
+
 static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 {
 	unsigned long	flags;
@@ -831,7 +925,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 		_crng_backtrack_protect(&primary_crng, buf.block,
 					CHACHA20_KEY_SIZE);
 	}
-	spin_lock_irqsave(&primary_crng.lock, flags);
+	spin_lock_irqsave(&crng->lock, flags);
 	for (i = 0; i < 8; i++) {
 		unsigned long	rv;
 		if (!arch_get_random_seed_long(&rv) &&
@@ -841,13 +935,26 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 	}
 	memzero_explicit(&buf, sizeof(buf));
 	crng->init_time = jiffies;
-	spin_unlock_irqrestore(&primary_crng.lock, flags);
+	spin_unlock_irqrestore(&crng->lock, flags);
 	if (crng == &primary_crng && crng_init < 2) {
 		invalidate_batched_entropy();
+		numa_crng_init();
 		crng_init = 2;
 		process_random_ready_list();
 		wake_up_interruptible(&crng_init_wait);
 		pr_notice("random: crng init done\n");
+		if (unseeded_warning.missed) {
+			pr_notice("random: %d get_random_xx warning(s) missed "
+				  "due to ratelimiting\n",
+				  unseeded_warning.missed);
+			unseeded_warning.missed = 0;
+		}
+		if (urandom_warning.missed) {
+			pr_notice("random: %d urandom warning(s) missed "
+				  "due to ratelimiting\n",
+				  urandom_warning.missed);
+			urandom_warning.missed = 0;
+		}
 	}
 }
 
@@ -856,8 +963,9 @@ static void _extract_crng(struct crng_state *crng,
 {
 	unsigned long v, flags;
 
-	if (crng_init > 1 &&
-	    time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL))
+	if (crng_ready() &&
+	    (time_after(crng_global_init_time, crng->init_time) ||
+	     time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL)))
 		crng_reseed(crng, crng == &primary_crng ? &input_pool : NULL);
 	spin_lock_irqsave(&crng->lock, flags);
 	if (arch_get_random_long(&v))
@@ -981,10 +1089,8 @@ void add_device_randomness(const void *buf, unsigned int size)
 	unsigned long time = random_get_entropy() ^ jiffies;
 	unsigned long flags;
 
-	if (!crng_ready()) {
-		crng_fast_load(buf, size);
-		return;
-	}
+	if (!crng_ready() && size)
+		crng_slow_load(buf, size);
 
 	trace_add_device_randomness(size, _RET_IP_);
 	spin_lock_irqsave(&input_pool.lock, flags);
@@ -1139,7 +1245,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
 
-	if (!crng_ready()) {
+	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
 		    crng_fast_load((char *) fast_pool->pool,
 				   sizeof(fast_pool->pool))) {
@@ -1489,8 +1595,9 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
 #ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM
 	print_once = true;
 #endif
-	pr_notice("random: %s called from %pS with crng_init=%d\n",
-		  func_name, caller, crng_init);
+	if (__ratelimit(&unseeded_warning))
+		pr_notice("random: %s called from %pS with crng_init=%d\n",
+			  func_name, caller, crng_init);
 }
 
 /*
@@ -1680,28 +1787,14 @@ static void init_std_data(struct entropy_store *r)
  */
 static int rand_initialize(void)
 {
-#ifdef CONFIG_NUMA
-	int i;
-	struct crng_state *crng;
-	struct crng_state **pool;
-#endif
-
 	init_std_data(&input_pool);
 	init_std_data(&blocking_pool);
 	crng_initialize(&primary_crng);
-
-#ifdef CONFIG_NUMA
-	pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
-	for_each_online_node(i) {
-		crng = kmalloc_node(sizeof(struct crng_state),
-				    GFP_KERNEL | __GFP_NOFAIL, i);
-		spin_lock_init(&crng->lock);
-		crng_initialize(crng);
-		pool[i] = crng;
+	crng_global_init_time = jiffies;
+	if (ratelimit_disable) {
+		urandom_warning.interval = 0;
+		unseeded_warning.interval = 0;
 	}
-	mb();
-	crng_node_pool = pool;
-#endif
 	return 0;
 }
 early_initcall(rand_initialize);
@@ -1769,9 +1862,10 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 
 	if (!crng_ready() && maxwarn > 0) {
 		maxwarn--;
-		printk(KERN_NOTICE "random: %s: uninitialized urandom read "
-		       "(%zd bytes read)\n",
-		       current->comm, nbytes);
+		if (__ratelimit(&urandom_warning))
+			printk(KERN_NOTICE "random: %s: uninitialized "
+			       "urandom read (%zd bytes read)\n",
+			       current->comm, nbytes);
 		spin_lock_irqsave(&primary_crng.lock, flags);
 		crng_init_cnt = 0;
 		spin_unlock_irqrestore(&primary_crng.lock, flags);
@@ -1875,6 +1969,14 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 		input_pool.entropy_count = 0;
 		blocking_pool.entropy_count = 0;
 		return 0;
+	case RNDRESEEDCRNG:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (crng_init < 2)
+			return -ENODATA;
+		crng_reseed(&primary_crng, NULL);
+		crng_global_init_time = jiffies - 1;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -2212,7 +2314,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 {
 	struct entropy_store *poolp = &input_pool;
 
-	if (!crng_ready()) {
+	if (unlikely(crng_init == 0)) {
 		crng_fast_load(buffer, count);
 		return;
 	}
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 468f06134012..21085515814f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -422,7 +422,7 @@ static void reclaim_dma_bufs(void)
 	}
 }
 
-static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
+static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size,
 				     int pages)
 {
 	struct port_buffer *buf;
@@ -445,16 +445,16 @@ static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
 		return buf;
 	}
 
-	if (is_rproc_serial(vq->vdev)) {
+	if (is_rproc_serial(vdev)) {
 		/*
 		 * Allocate DMA memory from ancestor. When a virtio
 		 * device is created by remoteproc, the DMA memory is
 		 * associated with the grandparent device:
 		 * vdev => rproc => platform-dev.
 		 */
-		if (!vq->vdev->dev.parent || !vq->vdev->dev.parent->parent)
+		if (!vdev->dev.parent || !vdev->dev.parent->parent)
 			goto free_buf;
-		buf->dev = vq->vdev->dev.parent->parent;
+		buf->dev = vdev->dev.parent->parent;
 
 		/* Increase device refcnt to avoid freeing it */
 		get_device(buf->dev);
@@ -838,7 +838,7 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
 
 	count = min((size_t)(32 * 1024), count);
 
-	buf = alloc_buf(port->out_vq, count, 0);
+	buf = alloc_buf(port->portdev->vdev, count, 0);
 	if (!buf)
 		return -ENOMEM;
 
@@ -957,7 +957,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 	if (ret < 0)
 		goto error_out;
 
-	buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
+	buf = alloc_buf(port->portdev->vdev, 0, pipe->nrbufs);
 	if (!buf) {
 		ret = -ENOMEM;
 		goto error_out;
@@ -1374,7 +1374,7 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
 
 	nr_added_bufs = 0;
 	do {
-		buf = alloc_buf(vq, PAGE_SIZE, 0);
+		buf = alloc_buf(vq->vdev, PAGE_SIZE, 0);
 		if (!buf)
 			break;
 
@@ -1402,7 +1402,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 {
 	char debugfs_name[16];
 	struct port *port;
-	struct port_buffer *buf;
 	dev_t devt;
 	unsigned int nr_added_bufs;
 	int err;
@@ -1513,8 +1512,6 @@ static int add_port(struct ports_device *portdev, u32 id)
 	return 0;
 
 free_inbufs:
-	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf, true);
 free_device:
 	device_destroy(pdrvdata.class, port->dev->devt);
 free_cdev:
@@ -1539,34 +1536,14 @@ static void remove_port(struct kref *kref)
 
 static void remove_port_data(struct port *port)
 {
-	struct port_buffer *buf;
-
 	spin_lock_irq(&port->inbuf_lock);
 	/* Remove unused data this port might have received. */
 	discard_port_data(port);
 	spin_unlock_irq(&port->inbuf_lock);
 
-	/* Remove buffers we queued up for the Host to send us data in. */
-	do {
-		spin_lock_irq(&port->inbuf_lock);
-		buf = virtqueue_detach_unused_buf(port->in_vq);
-		spin_unlock_irq(&port->inbuf_lock);
-		if (buf)
-			free_buf(buf, true);
-	} while (buf);
-
 	spin_lock_irq(&port->outvq_lock);
 	reclaim_consumed_buffers(port);
 	spin_unlock_irq(&port->outvq_lock);
-
-	/* Free pending buffers from the out-queue. */
-	do {
-		spin_lock_irq(&port->outvq_lock);
-		buf = virtqueue_detach_unused_buf(port->out_vq);
-		spin_unlock_irq(&port->outvq_lock);
-		if (buf)
-			free_buf(buf, true);
-	} while (buf);
 }
 
 /*
@@ -1791,13 +1768,24 @@ static void control_work_handler(struct work_struct *work)
 	spin_unlock(&portdev->c_ivq_lock);
 }
 
+static void flush_bufs(struct virtqueue *vq, bool can_sleep)
+{
+	struct port_buffer *buf;
+	unsigned int len;
+
+	while ((buf = virtqueue_get_buf(vq, &len)))
+		free_buf(buf, can_sleep);
+}
+
 static void out_intr(struct virtqueue *vq)
 {
 	struct port *port;
 
 	port = find_port_by_vq(vq->vdev->priv, vq);
-	if (!port)
+	if (!port) {
+		flush_bufs(vq, false);
 		return;
+	}
 
 	wake_up_interruptible(&port->waitqueue);
 }
@@ -1808,8 +1796,10 @@ static void in_intr(struct virtqueue *vq)
 	unsigned long flags;
 
 	port = find_port_by_vq(vq->vdev->priv, vq);
-	if (!port)
+	if (!port) {
+		flush_bufs(vq, false);
 		return;
+	}
 
 	spin_lock_irqsave(&port->inbuf_lock, flags);
 	port->inbuf = get_inbuf(port);
@@ -1984,24 +1974,54 @@ static const struct file_operations portdev_fops = {
 
 static void remove_vqs(struct ports_device *portdev)
 {
+	struct virtqueue *vq;
+
+	virtio_device_for_each_vq(portdev->vdev, vq) {
+		struct port_buffer *buf;
+
+		flush_bufs(vq, true);
+		while ((buf = virtqueue_detach_unused_buf(vq)))
+			free_buf(buf, true);
+	}
 	portdev->vdev->config->del_vqs(portdev->vdev);
 	kfree(portdev->in_vqs);
 	kfree(portdev->out_vqs);
 }
 
-static void remove_controlq_data(struct ports_device *portdev)
+static void virtcons_remove(struct virtio_device *vdev)
 {
-	struct port_buffer *buf;
-	unsigned int len;
+	struct ports_device *portdev;
+	struct port *port, *port2;
 
-	if (!use_multiport(portdev))
-		return;
+	portdev = vdev->priv;
 
-	while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-		free_buf(buf, true);
+	spin_lock_irq(&pdrvdata_lock);
+	list_del(&portdev->list);
+	spin_unlock_irq(&pdrvdata_lock);
 
-	while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-		free_buf(buf, true);
+	/* Disable interrupts for vqs */
+	vdev->config->reset(vdev);
+	/* Finish up work that's lined up */
+	if (use_multiport(portdev))
+		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
+
+	list_for_each_entry_safe(port, port2, &portdev->ports, list)
+		unplug_port(port);
+
+	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
+
+	/*
+	 * When yanking out a device, we immediately lose the
+	 * (device-side) queues.  So there's no point in keeping the
+	 * guest side around till we drop our final reference.  This
+	 * also means that any ports which are in an open state will
+	 * have to just stop using the port, as the vqs are going
+	 * away.
+	 */
+	remove_vqs(portdev);
+	kfree(portdev);
 }
 
 /*
@@ -2070,6 +2090,7 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	spin_lock_init(&portdev->ports_lock);
 	INIT_LIST_HEAD(&portdev->ports);
+	INIT_LIST_HEAD(&portdev->list);
 
 	virtio_device_ready(portdev->vdev);
 
@@ -2087,8 +2108,15 @@ static int virtcons_probe(struct virtio_device *vdev)
 		if (!nr_added_bufs) {
 			dev_err(&vdev->dev,
 				"Error allocating buffers for control queue\n");
-			err = -ENOMEM;
-			goto free_vqs;
+			/*
+			 * The host might want to notify mgmt sw about device
+			 * add failure.
+			 */
+			__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
+					   VIRTIO_CONSOLE_DEVICE_READY, 0);
+			/* Device was functional: we need full cleanup. */
+			virtcons_remove(vdev);
+			return -ENOMEM;
 		}
 	} else {
 		/*
@@ -2119,11 +2147,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 
 	return 0;
 
-free_vqs:
-	/* The host might want to notify mgmt sw about device add failure */
-	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
-			   VIRTIO_CONSOLE_DEVICE_READY, 0);
-	remove_vqs(portdev);
 free_chrdev:
 	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
 free:
@@ -2132,43 +2155,6 @@ fail:
 	return err;
 }
 
-static void virtcons_remove(struct virtio_device *vdev)
-{
-	struct ports_device *portdev;
-	struct port *port, *port2;
-
-	portdev = vdev->priv;
-
-	spin_lock_irq(&pdrvdata_lock);
-	list_del(&portdev->list);
-	spin_unlock_irq(&pdrvdata_lock);
-
-	/* Disable interrupts for vqs */
-	vdev->config->reset(vdev);
-	/* Finish up work that's lined up */
-	if (use_multiport(portdev))
-		cancel_work_sync(&portdev->control_work);
-	else
-		cancel_work_sync(&portdev->config_work);
-
-	list_for_each_entry_safe(port, port2, &portdev->ports, list)
-		unplug_port(port);
-
-	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
-
-	/*
-	 * When yanking out a device, we immediately lose the
-	 * (device-side) queues.  So there's no point in keeping the
-	 * guest side around till we drop our final reference.  This
-	 * also means that any ports which are in an open state will
-	 * have to just stop using the port, as the vqs are going
-	 * away.
-	 */
-	remove_controlq_data(portdev);
-	remove_vqs(portdev);
-	kfree(portdev);
-}
-
 static struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -2209,7 +2195,6 @@ static int virtcons_freeze(struct virtio_device *vdev)
 	 */
 	if (use_multiport(portdev))
 		virtqueue_disable_cb(portdev->c_ivq);
-	remove_controlq_data(portdev);
 
 	list_for_each_entry(port, &portdev->ports, list) {
 		virtqueue_disable_cb(port->in_vq);