[PATCH v10 2/6] iommu: Allow .iotlb_sync_map to fail and handle s390's -ENOMEM return

From: Niklas Schnelle
Date: Wed May 24 2023 - 10:56:34 EST


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@xxxxxxxxxxxxxxx>
Reviewed-by: Matthew Rosato <mjrosato@xxxxxxxxxxxxx>
Acked-by: Jernej Skrabec <jernej.skrabec@xxxxxxxxx> # sun50i
Signed-off-by: Niklas Schnelle <schnelle@xxxxxxxxxxxxx>
---
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 | 6 ++++--
drivers/iommu/tegra-gart.c | 5 +++--
include/linux/iommu.h | 4 ++--
11 files changed, 66 insertions(+), 28 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 4a314647d1f7..e5100da23207 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2196,14 +2196,15 @@ 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 8af64b57f048..d061493db634 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 b871a6afd803..84b603543cda 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4704,8 +4704,8 @@ 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);
@@ -4715,6 +4715,7 @@ 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 f1dcfa3f1a1b..51f816367205 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2440,8 +2440,17 @@ 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;
}
@@ -2582,8 +2591,11 @@ 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 79d89bad5132..47926d3290e6 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 aecc7d154f28..843211672cff 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -793,12 +793,13 @@ 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 fbf59a8db29b..6723d77489e8 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -205,6 +205,12 @@ 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);
@@ -212,8 +218,7 @@ 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();
}
@@ -237,20 +242,32 @@ static void s390_iommu_iotlb_sync(struct iommu_domain *domain,
rcu_read_unlock();
}

-static void s390_iommu_iotlb_sync_map(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+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 39e34fdeccda..18d61fe29ca0 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -343,8 +343,8 @@ 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;
@@ -356,6 +356,7 @@ 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 74c5cb93e900..45c90fa27631 100644
--- a/drivers/iommu/sun50i-iommu.c
+++ b/drivers/iommu/sun50i-iommu.c
@@ -402,8 +402,8 @@ 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,
- unsigned long iova, size_t size)
+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);
struct sun50i_iommu *iommu = sun50i_domain->iommu;
@@ -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 e8c9a7da1060..58891eddc2c4 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -333,8 +333,8 @@ 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);


--
2.39.2