iommu: Allow .iotlb_sync_map to fail and handle s390's -ENOMEM return

On s390 when using a paging hypervisor, .iotlb_sync_map is used to sync
mappings by letting the hypervisor inspect the synced IOVA range and
updating a shadow table. This however means that .iotlb_sync_map can
fail as the hypervisor may run out of resources while doing the sync.
This can be due to the hypervisor being unable to pin guest pages, due
to a limit on mapped addresses such as vfio_iommu_type1.dma_entry_limit
or lack of other resources. Either way such a failure to sync a mapping
should result in a DMA_MAPPING_ERROR.

Now especially when running with batched IOTLB flushes for unmap it may
be that some IOVAs have already been invalidated but not yet synced via
.iotlb_sync_map. Thus if the hypervisor indicates running out of
resources, first do a global flush allowing the hypervisor to free
resources associated with these mappings as well a retry creating the
new mappings and only if that also fails report this error to callers.
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com> # sun50i
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Link: https://lore.kernel.org/r/20230928-dma_iommu-v13-1-9e5fc4dacc36@linux.ibm.comSigned-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/amd/iommu.c

@@ -2233,7 +2233,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 	return ret;
 }
 
-static void amd_iommu_iotlb_sync_map(struct iommu_domain *dom,
+static int amd_iommu_iotlb_sync_map(struct iommu_domain *dom,
 				    unsigned long iova, size_t size)
 {
 	struct protection_domain *domain = to_pdomain(dom);
@@ -2241,6 +2241,7 @@ static void amd_iommu_iotlb_sync_map(struct iommu_domain *dom,
 
 	if (ops->map_pages)
 		domain_flush_np_cache(domain, iova, size);
+	return 0;
 }
 
 static int amd_iommu_map_pages(struct iommu_domain *dom, unsigned long iova,

drivers/iommu/apple-dart.c

@@ -506,10 +506,11 @@ static void apple_dart_iotlb_sync(struct iommu_domain *domain,
 	apple_dart_domain_flush_tlb(to_dart_domain(domain));
 }
 
-static void apple_dart_iotlb_sync_map(struct iommu_domain *domain,
+static int apple_dart_iotlb_sync_map(struct iommu_domain *domain,
 				     unsigned long iova, size_t size)
 {
 	apple_dart_domain_flush_tlb(to_dart_domain(domain));
+	return 0;
 }
 
 static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain,

drivers/iommu/intel/iommu.c

@@ -4678,7 +4678,7 @@ static bool risky_device(struct pci_dev *pdev)
 	return false;
 }
 
-static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
+static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				      unsigned long iova, size_t size)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
@@ -4689,6 +4689,7 @@ static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 
 	xa_for_each(&dmar_domain->iommu_array, i, info)
 		__mapping_notify_one(info->iommu, dmar_domain, pfn, pages);
+	return 0;
 }
 
 static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)

drivers/iommu/iommu.c

@@ -2585,8 +2585,17 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		return -EINVAL;
 
 	ret = __iommu_map(domain, iova, paddr, size, prot, gfp);
-	if (ret == 0 && ops->iotlb_sync_map)
-		ops->iotlb_sync_map(domain, iova, size);
+	if (ret == 0 && ops->iotlb_sync_map) {
+		ret = ops->iotlb_sync_map(domain, iova, size);
+		if (ret)
+			goto out_err;
+	}
+
+	return ret;
+
+out_err:
+	/* undo mappings already done */
+	iommu_unmap(domain, iova, size);
 
 	return ret;
 }
@@ -2714,8 +2723,11 @@ ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			sg = sg_next(sg);
 	}
 
-	if (ops->iotlb_sync_map)
-		ops->iotlb_sync_map(domain, iova, mapped);
+	if (ops->iotlb_sync_map) {
+		ret = ops->iotlb_sync_map(domain, iova, mapped);
+		if (ret)
+			goto out_err;
+	}
 	return mapped;
 
 out_err:

drivers/iommu/msm_iommu.c

@@ -498,12 +498,13 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
-static void msm_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+static int msm_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
 			      size_t size)
 {
 	struct msm_priv *priv = to_msm_priv(domain);
 
 	__flush_iotlb_range(iova, size, SZ_4K, false, priv);
+	return 0;
 }
 
 static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,

drivers/iommu/mtk_iommu.c

@@ -837,12 +837,13 @@ static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 	mtk_iommu_tlb_flush_range_sync(gather->start, length, dom->bank);
 }
 
-static void mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+static int mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
 			      size_t size)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 
 	mtk_iommu_tlb_flush_range_sync(iova, size, dom->bank);
+	return 0;
 }
 
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,

drivers/iommu/s390-iommu.c

@@ -219,6 +219,12 @@ static void s390_iommu_release_device(struct device *dev)
 		__s390_iommu_detach_device(zdev);
 }
 
+static int zpci_refresh_all(struct zpci_dev *zdev)
+{
+	return zpci_refresh_trans((u64)zdev->fh << 32, zdev->start_dma,
+				  zdev->end_dma - zdev->start_dma + 1);
+}
+
 static void s390_iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
 	struct s390_domain *s390_domain = to_s390_domain(domain);
@@ -226,8 +232,7 @@ static void s390_iommu_flush_iotlb_all(struct iommu_domain *domain)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(zdev, &s390_domain->devices, iommu_list) {
-		zpci_refresh_trans((u64)zdev->fh << 32, zdev->start_dma,
-				   zdev->end_dma - zdev->start_dma + 1);
+		zpci_refresh_all(zdev);
 	}
 	rcu_read_unlock();
 }
@@ -251,20 +256,32 @@ static void s390_iommu_iotlb_sync(struct iommu_domain *domain,
 	rcu_read_unlock();
 }
 
-static void s390_iommu_iotlb_sync_map(struct iommu_domain *domain,
+static int s390_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				     unsigned long iova, size_t size)
 {
 	struct s390_domain *s390_domain = to_s390_domain(domain);
 	struct zpci_dev *zdev;
+	int ret = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(zdev, &s390_domain->devices, iommu_list) {
 		if (!zdev->tlb_refresh)
 			continue;
-		zpci_refresh_trans((u64)zdev->fh << 32,
+		ret = zpci_refresh_trans((u64)zdev->fh << 32,
 					 iova, size);
+		/*
+		 * let the hypervisor discover invalidated entries
+		 * allowing it to free IOVAs and unpin pages
+		 */
+		if (ret == -ENOMEM) {
+			ret = zpci_refresh_all(zdev);
+			if (ret)
+				break;
+		}
 	}
 	rcu_read_unlock();
+
+	return ret;
 }
 
 static int s390_iommu_validate_trans(struct s390_domain *s390_domain,

drivers/iommu/sprd-iommu.c

@@ -341,7 +341,7 @@ static size_t sprd_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return size;
 }
 
-static void sprd_iommu_sync_map(struct iommu_domain *domain,
+static int sprd_iommu_sync_map(struct iommu_domain *domain,
 			       unsigned long iova, size_t size)
 {
 	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
@@ -354,6 +354,7 @@ static void sprd_iommu_sync_map(struct iommu_domain *domain,
 
 	/* clear IOMMU TLB buffer after page table updated */
 	sprd_iommu_write(dom->sdev, reg, 0xffffffff);
+	return 0;
 }
 
 static void sprd_iommu_sync(struct iommu_domain *domain,

drivers/iommu/sun50i-iommu.c

@@ -401,7 +401,7 @@ static void sun50i_iommu_flush_iotlb_all(struct iommu_domain *domain)
 	spin_unlock_irqrestore(&iommu->iommu_lock, flags);
 }
 
-static void sun50i_iommu_iotlb_sync_map(struct iommu_domain *domain,
+static int sun50i_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				       unsigned long iova, size_t size)
 {
 	struct sun50i_iommu_domain *sun50i_domain = to_sun50i_domain(domain);
@@ -411,6 +411,8 @@ static void sun50i_iommu_iotlb_sync_map(struct iommu_domain *domain,
 	spin_lock_irqsave(&iommu->iommu_lock, flags);
 	sun50i_iommu_zap_range(iommu, iova, size);
 	spin_unlock_irqrestore(&iommu->iommu_lock, flags);
+
+	return 0;
 }
 
 static void sun50i_iommu_iotlb_sync(struct iommu_domain *domain,

include/linux/iommu.h

@@ -350,7 +350,7 @@ struct iommu_domain_ops {
 			      struct iommu_iotlb_gather *iotlb_gather);
 
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
-	void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova,
+	int (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova,
 			      size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);