Merge tag 'kvm-s390-master-7.2-3' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Misc fixes for 7.2

Fix a bunch of small issues that came up during the previous round of
fixes.

They are mostly extremely unlikely races, but they should be fixed
nonetheless.

8 files changed, 176 insertions, 33 deletions

diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
index 420d89ba7f83..4aff0b58fa5d 100644
--- a/drivers/s390/cio/vfio_ccw_async.c
+++ b/drivers/s390/cio/vfio_ccw_async.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/vfio.h>
+#include <linux/nospec.h>
 
 #include "vfio_ccw_private.h"
 
@@ -24,11 +25,20 @@ static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private,
 		return -EINVAL;
 
 	mutex_lock(&private->io_mutex);
+
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 	if (copy_to_user(buf, (void *)region + pos, count))
 		ret = -EFAULT;
 	else
 		ret = count;
+
+out_unlock:
 	mutex_unlock(&private->io_mutex);
 	return ret;
 }
@@ -48,6 +58,12 @@ static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private,
 	if (!mutex_trylock(&private->io_mutex))
 		return -EAGAIN;
 
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 	if (copy_from_user((void *)region + pos, buf, count)) {
 		ret = -EFAULT;
diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index 38c176cf6295..7708eb4d6de0 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/vfio.h>
 #include "vfio_ccw_private.h"
 
@@ -26,6 +27,13 @@ static ssize_t vfio_ccw_schib_region_read(struct vfio_ccw_private *private,
 		return -EINVAL;
 
 	mutex_lock(&private->io_mutex);
+
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 
 	if (cio_update_schib(sch)) {
@@ -85,19 +93,30 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
 	struct ccw_crw_region *region;
 	struct vfio_ccw_crw *crw;
+	unsigned long flags;
 	int ret;
 
 	if (pos + count > sizeof(*region))
 		return -EINVAL;
 
+	mutex_lock(&private->io_mutex);
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
+	region = private->region[i].data;
+
+	spin_lock_irqsave(&private->crw_lock, flags);
 	crw = list_first_entry_or_null(&private->crw,
 				       struct vfio_ccw_crw, next);
 
 	if (crw)
 		list_del(&crw->next);
 
-	mutex_lock(&private->io_mutex);
-	region = private->region[i].data;
+	/* Drop CRW lock while copying to userspace */
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 
 	if (crw)
 		memcpy(&region->crw, &crw->crw, sizeof(region->crw));
@@ -108,14 +127,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 		ret = count;
 
 	region->crw = 0;
-
-	mutex_unlock(&private->io_mutex);
-
 	kfree(crw);
 
 	/* Notify the guest if more CRWs are on our queue */
+	spin_lock_irqsave(&private->crw_lock, flags);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
+
+out:
+	mutex_unlock(&private->io_mutex);
 
 	return ret;
 }
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 7561aa7d3e01..58722c4baa25 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -233,6 +233,7 @@ static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
 }
 
 #define idal_is_2k(_cp) (!(_cp)->orb.cmd.c64 || (_cp)->orb.cmd.i2k)
+#define get_idaw_size(_cp) ((_cp)->orb.cmd.c64 ? sizeof(u64) : sizeof(u32))
 
 /*
  * Helpers to operate ccwchain.
@@ -332,6 +333,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
 		goto out_err;
 
 	list_add_tail(&chain->next, &cp->ccwchain_list);
+	cp->ccwchain_count++;
 
 	return chain;
 
@@ -376,11 +378,9 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx)
 static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 {
 	struct ccw1 *ccw = cp->guest_cp;
-	int cnt = 0;
-
-	do {
-		cnt++;
+	int cnt;
 
+	for (cnt = 1; cnt <= CCWCHAIN_LEN_MAX; cnt++, ccw++) {
 		/*
 		 * We want to keep counting if the current CCW has the
 		 * command-chaining flag enabled, or if it is a TIC CCW
@@ -390,15 +390,10 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 		 * after the TIC, depending on the results of its operation.
 		 */
 		if (!ccw_is_chain(ccw) && !is_tic_within_range(ccw, iova, cnt))
-			break;
-
-		ccw++;
-	} while (cnt < CCWCHAIN_LEN_MAX + 1);
-
-	if (cnt == CCWCHAIN_LEN_MAX + 1)
-		cnt = -EINVAL;
+			return cnt;
+	}
 
-	return cnt;
+	return -EINVAL;
 }
 
 static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)
@@ -441,6 +436,10 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
 	if (len < 0)
 		return len;
 
+	/* Limit number of chains in a single channel program */
+	if (cp->ccwchain_count >= CCWCHAIN_COUNT_MAX)
+		return -EINVAL;
+
 	/* Need alloc a new chain for this one. */
 	chain = ccwchain_alloc(cp, len);
 	if (!chain)
@@ -455,9 +454,6 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
 	/* Loop for tics on this new chain. */
 	ret = ccwchain_loop_tic(chain, cp);
 
-	if (ret)
-		ccwchain_free(chain);
-
 	return ret;
 }
 
@@ -486,6 +482,23 @@ static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
 	return 0;
 }
 
+static int ccwchain_build_ccws(dma32_t cda, struct channel_program *cp)
+{
+	struct ccwchain *chain, *temp;
+	int ret;
+
+	ret = ccwchain_handle_ccw(cda, cp);
+
+	if (ret) {
+		/* Cleanup if an error occurred */
+		list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
+			ccwchain_free(chain);
+		}
+	}
+
+	return ret;
+}
+
 static int ccwchain_fetch_tic(struct ccw1 *ccw,
 			      struct channel_program *cp)
 {
@@ -511,7 +524,8 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
 		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	dma64_t *idaws;
 	dma32_t *idaws_f1;
-	int idal_len = idaw_nr * sizeof(*idaws);
+	u64 first_idaw;
+	int idal_len = idaw_nr * get_idaw_size(cp);
 	int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE;
 	int idaw_mask = ~(idaw_size - 1);
 	int i, ret;
@@ -527,6 +541,18 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
 			kfree(idaws);
 			return ERR_PTR(ret);
 		}
+
+		idaws_f1 = (dma32_t *)idaws;
+		if (cp->orb.cmd.c64)
+			first_idaw = dma64_to_u64(idaws[0]);
+		else
+			first_idaw = dma32_to_u32(idaws_f1[0]);
+
+		/* Unexpected mismatch from earlier read */
+		if (first_idaw != cp->guest_iova) {
+			kfree(idaws);
+			return ERR_PTR(-EINVAL);
+		}
 	} else {
 		/* Fabricate an IDAL based off CCW data address */
 		if (cp->orb.cmd.c64) {
@@ -568,7 +594,7 @@ static int ccw_count_idaws(struct ccw1 *ccw,
 	struct vfio_device *vdev =
 		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	u64 iova;
-	int size = cp->orb.cmd.c64 ? sizeof(u64) : sizeof(u32);
+	int size = get_idaw_size(cp);
 	int ret;
 	int bytes = 1;
 
@@ -592,6 +618,9 @@ static int ccw_count_idaws(struct ccw1 *ccw,
 		iova = dma32_to_u32(ccw->cda);
 	}
 
+	/* Save the read address for later */
+	cp->guest_iova = iova;
+
 	/* Format-1 IDAWs operate on 2K each */
 	if (!cp->orb.cmd.c64)
 		return idal_2k_nr_words((void *)iova, bytes);
@@ -731,11 +760,12 @@ int cp_init(struct channel_program *cp, union orb *orb)
 			vdev->dev,
 			"Prefetching channel program even though prefetch not specified in ORB");
 
+	cp->ccwchain_count = 0;
 	INIT_LIST_HEAD(&cp->ccwchain_list);
 	memcpy(&cp->orb, orb, sizeof(*orb));
 
 	/* Build a ccwchain for the first CCW segment */
-	ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
+	ret = ccwchain_build_ccws(orb->cmd.cpa, cp);
 
 	if (!ret)
 		cp->initialized = true;
@@ -947,17 +977,23 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
  */
 bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length)
 {
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
 	struct ccwchain *chain;
 	int i;
 
 	if (!cp->initialized)
 		return false;
 
+	mutex_lock(&private->io_mutex);
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++)
-			if (page_array_iova_pinned(&chain->ch_pa[i], iova, length))
+			if (page_array_iova_pinned(&chain->ch_pa[i], iova, length)) {
+				mutex_unlock(&private->io_mutex);
 				return true;
+			}
 	}
+	mutex_unlock(&private->io_mutex);
 
 	return false;
 }
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index fc31eb699807..9af98ff12d67 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -23,11 +23,19 @@
  */
 #define CCWCHAIN_LEN_MAX	256
 
+/*
+ * Maximum number of chains
+ */
+#define CCWCHAIN_COUNT_MAX	16
+
 /**
  * struct channel_program - manage information for channel program
  * @ccwchain_list: list head of ccwchains
  * @orb: orb for the currently processed ssch request
  * @initialized: whether this instance is actually initialized
+ * @guest_cp: copy of guest channel program
+ * @ccwchain_count: number of channel program segments (linked by TIC)
+ * @guest_iova: first data address of a guest channel program
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by
@@ -38,6 +46,8 @@ struct channel_program {
 	union orb orb;
 	bool initialized;
 	struct ccw1 *guest_cp;
+	unsigned int ccwchain_count;
+	u64 guest_iova;
 };
 
 int cp_init(struct channel_program *cp, union orb *orb);
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 1a095085bc72..ab6b518cc353 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -91,6 +91,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 
 	is_final = !(scsw_actl(&irb->scsw) &
 		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
+	mutex_lock(&private->io_mutex);
 	if (scsw_is_solicited(&irb->scsw)) {
 		cp_update_scsw(&private->cp, &irb->scsw);
 		if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) {
@@ -98,9 +99,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 			cp_is_finished = true;
 		}
 	}
-	mutex_lock(&private->io_mutex);
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
-	mutex_unlock(&private->io_mutex);
 
 	/*
 	 * Reset to IDLE only if processing of a channel program
@@ -110,6 +109,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 	 */
 	if (cp_is_finished)
 		private->state = VFIO_CCW_STATE_IDLE;
+	mutex_unlock(&private->io_mutex);
 
 	if (private->io_trigger)
 		eventfd_signal(private->io_trigger);
@@ -118,11 +118,25 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 void vfio_ccw_crw_todo(struct work_struct *work)
 {
 	struct vfio_ccw_private *private;
+	unsigned long flags;
 
 	private = container_of(work, struct vfio_ccw_private, crw_work);
 
+	spin_lock_irqsave(&private->crw_lock, flags);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
+}
+
+void vfio_ccw_notoper_todo(struct work_struct *work)
+{
+	struct vfio_ccw_private *private;
+
+	private = container_of(work, struct vfio_ccw_private, notoper_work);
+
+	mutex_lock(&private->io_mutex);
+	cp_free(&private->cp);
+	mutex_unlock(&private->io_mutex);
 }
 
 /*
@@ -275,6 +289,7 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 			       unsigned int rsid)
 {
 	struct vfio_ccw_crw *crw;
+	unsigned long flags;
 
 	/*
 	 * If unable to allocate a CRW, just drop the event and
@@ -292,7 +307,9 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 	crw->crw.erc = erc;
 	crw->crw.rsid = rsid;
 
+	spin_lock_irqsave(&private->crw_lock, flags);
 	list_add_tail(&crw->next, &private->crw);
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 	queue_work(vfio_ccw_work_q, &private->crw_work);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 4d7988ea47ef..5fd94e9d5c61 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -170,8 +170,8 @@ static void fsm_notoper(struct vfio_ccw_private *private,
 	css_sched_sch_todo(sch, SCH_TODO_UNREG);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
 
-	/* This is usually handled during CLOSE event */
-	cp_free(&private->cp);
+	/* This routine could be called from IRQ context, so defer */
+	queue_work(vfio_ccw_work_q, &private->notoper_work);
 }
 
 /*
@@ -410,7 +410,11 @@ static void fsm_close(struct vfio_ccw_private *private,
 
 	private->state = VFIO_CCW_STATE_STANDBY;
 	spin_unlock_irq(&sch->lock);
+
+	mutex_lock(&private->io_mutex);
 	cp_free(&private->cp);
+	mutex_unlock(&private->io_mutex);
+
 	return;
 
 err_unlock:
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 45ec722d25ea..5ce91285c7d5 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -54,6 +54,8 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 	INIT_LIST_HEAD(&private->crw);
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
 	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
+	INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo);
+	spin_lock_init(&private->crw_lock);
 
 	private->cp.guest_cp = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX);
 	if (!private->cp.guest_cp)
@@ -130,11 +132,28 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
 	struct vfio_ccw_crw *crw, *temp;
+	unsigned long flags;
 
+	/*
+	 * Ensure these work items are fully drained, so none can
+	 * fire after being released.
+	 *
+	 * notoper_work should have nothing to do here, because only
+	 * open devices could have channel_program resources in use
+	 * and those would be released during close. Nevertheless,
+	 * call flush here as well to be certain anything that was
+	 * allocated is freed.
+	 */
+	cancel_work_sync(&private->io_work);
+	cancel_work_sync(&private->crw_work);
+	flush_work(&private->notoper_work);
+
+	spin_lock_irqsave(&private->crw_lock, flags);
 	list_for_each_entry_safe(crw, temp, &private->crw, next) {
 		list_del(&crw->next);
 		kfree(crw);
 	}
+	spin_unlock_irqrestore(&private->crw_lock, flags);
 
 	kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
 	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
@@ -202,6 +221,19 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
+
+	/*
+	 * Ensure these work items are drained, in the event the
+	 * device is re-opened instead of released.
+	 *
+	 * notoper_work needs to be given a chance to run if it
+	 * is queued, so any memory associated with the channel
+	 * program can be returned.
+	 */
+	cancel_work_sync(&private->io_work);
+	cancel_work_sync(&private->crw_work);
+	flush_work(&private->notoper_work);
+
 	vfio_ccw_unregister_dev_regions(private);
 }
 
@@ -243,6 +275,7 @@ static ssize_t vfio_ccw_mdev_read(struct vfio_device *vdev,
 		return vfio_ccw_mdev_read_io_region(private, buf, count, ppos);
 	default:
 		index -= VFIO_CCW_NUM_REGIONS;
+		index = array_index_nospec(index, private->num_regions);
 		return private->region[index].ops->read(private, buf, count,
 							ppos);
 	}
@@ -295,6 +328,7 @@ static ssize_t vfio_ccw_mdev_write(struct vfio_device *vdev,
 		return vfio_ccw_mdev_write_io_region(private, buf, count, ppos);
 	default:
 		index -= VFIO_CCW_NUM_REGIONS;
+		index = array_index_nospec(index, private->num_regions);
 		return private->region[index].ops->write(private, buf, count,
 							 ppos);
 	}
@@ -338,11 +372,8 @@ static int vfio_ccw_mdev_ioctl_get_region_info(struct vfio_device *vdev,
 		    VFIO_CCW_NUM_REGIONS + private->num_regions)
 			return -EINVAL;
 
-		info->index = array_index_nospec(info->index,
-						 VFIO_CCW_NUM_REGIONS +
-						 private->num_regions);
-
 		i = info->index - VFIO_CCW_NUM_REGIONS;
+		i = array_index_nospec(i, private->num_regions);
 
 		info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index);
 		info->size = private->region[i].size;
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 0501d4bbcdbd..3bd0171d38d0 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -88,7 +88,8 @@ struct vfio_ccw_parent {
  * @state: internal state of the device
  * @completion: synchronization helper of the I/O completion
  * @io_region: MMIO region to input/output I/O arguments/results
- * @io_mutex: protect against concurrent update of I/O regions
+ * @io_mutex: protect against concurrent update of I/O resources
+ *            and @cp lifecycle
  * @region: additional regions for other subchannel operations
  * @cmd_region: MMIO region for asynchronous I/O commands other than START
  * @schib_region: MMIO region for SCHIB information
@@ -97,11 +98,14 @@ struct vfio_ccw_parent {
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
+ * @crw_lock: serialization of CRW list information
+ * @crw: list of Channel Report Word elements
  * @io_trigger: eventfd ctx for signaling userspace I/O results
  * @crw_trigger: eventfd ctx for signaling userspace CRW information
  * @req_trigger: eventfd ctx for signaling userspace to return device
  * @io_work: work for deferral process of I/O handling
  * @crw_work: work for deferral process of CRW handling
+ * @notoper_work: work for deferred processing in not-operational state
  */
 struct vfio_ccw_private {
 	struct vfio_device vdev;
@@ -118,6 +122,8 @@ struct vfio_ccw_private {
 	struct channel_program	cp;
 	struct irb		irb;
 	union scsw		scsw;
+
+	spinlock_t		crw_lock;
 	struct list_head	crw;
 
 	struct eventfd_ctx	*io_trigger;
@@ -125,11 +131,13 @@ struct vfio_ccw_private {
 	struct eventfd_ctx	*req_trigger;
 	struct work_struct	io_work;
 	struct work_struct	crw_work;
+	struct work_struct	notoper_work;
 } __aligned(8);
 
 int vfio_ccw_sch_quiesce(struct subchannel *sch);
 void vfio_ccw_sch_io_todo(struct work_struct *work);
 void vfio_ccw_crw_todo(struct work_struct *work);
+void vfio_ccw_notoper_todo(struct work_struct *work);
 
 extern struct mdev_driver vfio_ccw_mdev_driver;