[Devel] [PATCH hci-8.1 3/5] Revert "vfio/type1: revert "block on invalid vaddr""

[Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>]

From: Anthony Yznaga <anthony.yznaga@oracle.com>

This reverts commit da4f1c2e1c9cb2832b5a4de3472cd1cad63781b2.

This is needed in order to re-enable support for using VFIO_UPDATE_VADDR
with vfio mediated devices which is needed to fully support Live Update.

Orabug: 35370252
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Reviewed-by: Steve Sistare <steven.sistare@oracle.com>

https://virtuozzo.atlassian.net/browse/VSTOR-150595
(cherry picked from commit b1bfe0e165fd85657e530462da70bccb498256b2)
---
 drivers/vfio/vfio_iommu_type1.c | 94 +++++++++++++++++++++++++++++++--
 1 file changed, 89 insertions(+), 5 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index b2d6c68fa79c..6193ff966667 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -73,6 +73,7 @@ struct vfio_iommu {
 	unsigned int		vaddr_invalid_count;
 	uint64_t		pgsize_bitmap;
 	uint64_t		num_non_pinned_groups;
+	wait_queue_head_t	vaddr_wait;
 	bool			v2;
 	bool			dirty_page_tracking;
 	bool			container_open;
@@ -153,6 +154,8 @@ struct vfio_regions {
 #define DIRTY_BITMAP_PAGES_MAX	 ((u64)INT_MAX)
 #define DIRTY_BITMAP_SIZE_MAX	 DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX)
 
+#define WAITED 1
+
 static int put_pfn(unsigned long pfn, int prot);
 
 static struct vfio_iommu_group*
@@ -669,6 +672,61 @@ static long vpfn_pages(struct vfio_dma *dma,
 	return ret;
 }
 
+static int vfio_wait(struct vfio_iommu *iommu)
+{
+	DEFINE_WAIT(wait);
+
+	prepare_to_wait(&iommu->vaddr_wait, &wait, TASK_KILLABLE);
+	mutex_unlock(&iommu->lock);
+	schedule();
+	mutex_lock(&iommu->lock);
+	finish_wait(&iommu->vaddr_wait, &wait);
+	if (kthread_should_stop() || !iommu->container_open ||
+	    fatal_signal_pending(current)) {
+		return -EFAULT;
+	}
+	return WAITED;
+}
+
+/*
+ * Find dma struct and wait for its vaddr to be valid.  iommu lock is dropped
+ * if the task waits, but is re-locked on return.  Return result in *dma_p.
+ * Return 0 on success with no waiting, WAITED on success if waited, and -errno
+ * on error.
+ */
+static int vfio_find_dma_valid(struct vfio_iommu *iommu, dma_addr_t start,
+			       size_t size, struct vfio_dma **dma_p)
+{
+	int ret = 0;
+
+	do {
+		*dma_p = vfio_find_dma(iommu, start, size);
+		if (!*dma_p)
+			return -EINVAL;
+		else if (!(*dma_p)->vaddr_invalid)
+			return ret;
+		else
+			ret = vfio_wait(iommu);
+	} while (ret == WAITED);
+
+	return ret;
+}
+
+/*
+ * Wait for all vaddr in the dma_list to become valid.  iommu lock is dropped
+ * if the task waits, but is re-locked on return.  Return 0 on success with no
+ * waiting, WAITED on success if waited, and -errno on error.
+ */
+static int vfio_wait_all_valid(struct vfio_iommu *iommu)
+{
+	int ret = 0;
+
+	while (iommu->vaddr_invalid_count && ret >= 0)
+		ret = vfio_wait(iommu);
+
+	return ret;
+}
+
 /*
  * Attempt to pin pages.  We really don't want to track all the pfns and
  * the iommu can only map chunks of consecutive pfns anyway, so get the
@@ -904,6 +962,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 	unsigned long remote_vaddr;
 	struct vfio_dma *dma;
 	bool do_accounting;
+	dma_addr_t iova;
 	dma_addr_t iova_end;
 	size_t iova_size;
 
@@ -926,6 +985,22 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 		goto pin_done;
 	}
 
+	/*
+	 * Wait for all necessary vaddr's to be valid so they can be used in
+	 * the main loop without dropping the lock, to avoid racing vs unmap.
+	 */
+again:
+	if (iommu->vaddr_invalid_count) {
+		for (i = 0; i < npage; i++) {
+			iova = user_iova + PAGE_SIZE * i;
+			ret = vfio_find_dma_valid(iommu, iova, PAGE_SIZE, &dma);
+			if (ret < 0)
+				goto pin_done;
+			if (ret == WAITED)
+				goto again;
+		}
+	}
+
 	/* Fail if no dma_umap notifier is registered */
 	if (list_empty(&iommu->device_list)) {
 		ret = -EINVAL;
@@ -941,7 +1016,6 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 
 	for (i = 0; i < npage; i++) {
 		unsigned long phys_pfn;
-		dma_addr_t iova;
 		struct vfio_pfn *vpfn;
 
 		iova = user_iova + PAGE_SIZE * i;
@@ -1240,8 +1314,10 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
 	put_task_struct(dma->task);
 	mmdrop(dma->mm);
 	vfio_dma_bitmap_free(dma);
-	if (dma->vaddr_invalid)
+	if (dma->vaddr_invalid) {
 		iommu->vaddr_invalid_count--;
+		wake_up_all(&iommu->vaddr_wait);
+	}
 	kfree(dma);
 	iommu->dma_avail++;
 }
@@ -1737,6 +1813,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 			dma->vaddr = vaddr;
 			dma->vaddr_invalid = false;
 			iommu->vaddr_invalid_count--;
+			wake_up_all(&iommu->vaddr_wait);
 		}
 		goto out_unlock;
 	} else if (dma) {
@@ -1811,6 +1888,10 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	int ret;
 
+	ret = vfio_wait_all_valid(iommu);
+	if (ret < 0)
+		return ret;
+
 	/* Arbitrarily pick the first domain in the list for lookups */
 	if (!list_empty(&iommu->domain_list))
 		d = list_first_entry(&iommu->domain_list,
@@ -2650,6 +2731,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 	mutex_init(&iommu->lock);
 	mutex_init(&iommu->device_list_lock);
 	INIT_LIST_HEAD(&iommu->device_list);
+	init_waitqueue_head(&iommu->vaddr_wait);
 	iommu->pgsize_bitmap = PAGE_MASK;
 	INIT_LIST_HEAD(&iommu->emulated_iommu_groups);
 
@@ -3148,12 +3230,13 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
 	struct vfio_dma *dma;
 	bool kthread = current->mm == NULL;
 	size_t offset;
+	int ret;
 
 	*copied = 0;
 
-	dma = vfio_find_dma(iommu, user_iova, 1);
-	if (!dma)
-		return -EINVAL;
+	ret = vfio_find_dma_valid(iommu, user_iova, 1, &dma);
+	if (ret < 0)
+		return ret;
 
 	if ((write && !(dma->prot & IOMMU_WRITE)) ||
 			!(dma->prot & IOMMU_READ))
@@ -3262,6 +3345,7 @@ static void vfio_iommu_type1_notify(void *iommu_data,
 	mutex_lock(&iommu->lock);
 	iommu->container_open = false;
 	mutex_unlock(&iommu->lock);
+	wake_up_all(&iommu->vaddr_wait);
 }
 
 static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
-- 
2.47.1

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel