From:   Niklas Schnelle <schnelle@linux.ibm.com>
To:     Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
        Robin Murphy <robin.murphy@arm.com>,
        Jason Gunthorpe <jgg@nvidia.com>,
        Wenjia Zhang <wenjia@linux.ibm.com>
Cc:     Matthew Rosato <mjrosato@linux.ibm.com>,
        Gerd Bayer <gbayer@linux.ibm.com>,
        Pierre Morel <pmorel@linux.ibm.com>, iommu@lists.linux.dev,
        linux-s390@vger.kernel.org, borntraeger@linux.ibm.com,
        hca@linux.ibm.com, gor@linux.ibm.com,
        gerald.schaefer@linux.ibm.com, agordeev@linux.ibm.com,
        svens@linux.ibm.com, linux-kernel@vger.kernel.org,
        Julian Ruess <julianr@linux.ibm.com>
Subject: [PATCH v7 2/6] iommu: Allow .iotlb_sync_map to fail and handle s390's -ENOMEM return
Date:   Mon, 20 Feb 2023 16:22:18 +0100
Message-Id: <20230220152222.1818344-3-schnelle@linux.ibm.com>
In-Reply-To: <20230220152222.1818344-1-schnelle@linux.ibm.com>
References: <20230220152222.1818344-1-schnelle@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
---
v3 -> v4:
- Adapted signature of .iommu_tlb_sync mapo for sun50i IOMMU driver added in
  v6.2-rc1 (kernel test robot)

 drivers/iommu/amd/iommu.c    |  5 +++--
 drivers/iommu/apple-dart.c   |  5 +++--
 drivers/iommu/intel/iommu.c  |  5 +++--
 drivers/iommu/iommu.c        | 20 ++++++++++++++++----
 drivers/iommu/msm_iommu.c    |  5 +++--
 drivers/iommu/mtk_iommu.c    |  5 +++--
 drivers/iommu/s390-iommu.c   | 29 ++++++++++++++++++++++++-----
 drivers/iommu/sprd-iommu.c   |  5 +++--
 drivers/iommu/sun50i-iommu.c |  4 +++-
 drivers/iommu/tegra-gart.c   |  5 +++--
 include/linux/iommu.h        |  4 ++--
 11 files changed, 66 insertions(+), 26 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index c20c41dd9c91..d0e378408d79 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2187,14 +2187,15 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 	return ret;
 }
 
-static void amd_iommu_iotlb_sync_map(struct iommu_domain *dom,
-				     unsigned long iova, size_t size)
+static int amd_iommu_iotlb_sync_map(struct iommu_domain *dom,
+				    unsigned long iova, size_t size)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	struct io_pgtable_ops *ops = &domain->iop.iop.ops;
 
 	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,
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index 06169d36eab8..cbed1f87eae9 100644
--- a/drivers/iommu/apple-dart.c
+++ b/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,
-				      unsigned long iova, size_t size)
+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,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 86ee06ac058b..c1a6d64be89a 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4747,8 +4747,8 @@ static bool risky_device(struct pci_dev *pdev)
 	return false;
 }
 
-static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
-				       unsigned long iova, size_t size)
+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);
 	unsigned long pages = aligned_nrpages(iova, size);
@@ -4758,6 +4758,7 @@ 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)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index b3f847b25b4f..a3de8d5928bf 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2386,8 +2386,17 @@ 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;
 }
@@ -2528,8 +2537,11 @@ 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:
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 454f6331c889..2033716eac78 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -486,12 +486,13 @@ 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,
-			       size_t size)
+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,
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index d5a4955910ff..29769fb5c51e 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -750,12 +750,13 @@ 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,
-			       size_t size)
+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,
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 6849644e2892..f79aa527d621 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -207,6 +207,14 @@ 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);
@@ -214,8 +222,7 @@ 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();
 }
@@ -239,20 +246,32 @@ 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,
-				   iova, size);
+		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,
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
index ae94d74b73f4..74bcae69653c 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -315,8 +315,8 @@ 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,
-				unsigned long iova, size_t size)
+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);
 	unsigned int reg;
@@ -328,6 +328,7 @@ 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,
diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c
index 2d993d0cea7d..60a983f4a494 100644
--- a/drivers/iommu/sun50i-iommu.c
+++ b/drivers/iommu/sun50i-iommu.c
@@ -402,7 +402,7 @@ 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);
@@ -412,6 +412,8 @@ 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,
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index a482ff838b53..44966d7b07ba 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -252,10 +252,11 @@ static int gart_iommu_of_xlate(struct device *dev,
 	return 0;
 }
 
-static void gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
-				size_t size)
+static int gart_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+			       size_t size)
 {
 	FLUSH_GART_REGS(gart_handle);
+	return 0;
 }
 
 static void gart_iommu_sync(struct iommu_domain *domain,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3589d1b8f922..1d5f9250d9ea 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -334,8 +334,8 @@ 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,
-			       size_t size);
+	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);
 
-- 
2.37.2