Merge branch 'iommu-memory-accounting' into core

Merge patch-set from Jason:

	"Let iommufd charge IOPTE allocations to the memory cgroup"

Description:

IOMMUFD follows the same design as KVM and uses memory cgroups to limit
the amount of kernel memory a iommufd file descriptor can pin down. The
various internal data structures already use GFP_KERNEL_ACCOUNT to charge
its own memory.

However, one of the biggest consumers of kernel memory is the IOPTEs
stored under the iommu_domain and these allocations are not tracked.

This series is the first step in fixing it.

The iommu driver contract already includes a 'gfp' argument to the
map_pages op, allowing iommufd to specify GFP_KERNEL_ACCOUNT and then
having the driver allocate the IOPTE tables with that flag will capture a
significant amount of the allocations.

Update the iommu_map() API to pass in the GFP argument, and fix all call
sites. Replace iommu_map_atomic().

Audit the "enterprise" iommu drivers to make sure they do the right thing.
Intel and S390 ignore the GFP argument and always use GFP_ATOMIC. This is
problematic for iommufd anyhow, so fix it. AMD and ARM SMMUv2/3 are
already correct.

A follow up series will be needed to capture the allocations made when the
iommu_domain itself is allocated, which will complete the job.

Link: https://lore.kernel.org/linux-iommu/0-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com/

1 files changed, 20 insertions, 33 deletions

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 9135540d7d59..42591766266d 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -954,7 +954,7 @@ map_end:
 			if (map_size) {
 				ret = iommu_map(domain, addr - map_size,
 						addr - map_size, map_size,
-						entry->prot);
+						entry->prot, GFP_KERNEL);
 				if (ret)
 					goto out;
 				map_size = 0;
@@ -2354,34 +2354,27 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
-static int _iommu_map(struct iommu_domain *domain, unsigned long iova,
-		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	const struct iommu_domain_ops *ops = domain->ops;
 	int ret;
 
+	might_sleep_if(gfpflags_allow_blocking(gfp));
+
+	/* Discourage passing strange GFP flags */
+	if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
+				__GFP_HIGHMEM)))
+		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);
 
 	return ret;
 }
-
-int iommu_map(struct iommu_domain *domain, unsigned long iova,
-	      phys_addr_t paddr, size_t size, int prot)
-{
-	might_sleep();
-	return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
-}
 EXPORT_SYMBOL_GPL(iommu_map);
 
-int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
-	      phys_addr_t paddr, size_t size, int prot)
-{
-	return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
-}
-EXPORT_SYMBOL_GPL(iommu_map_atomic);
-
 static size_t __iommu_unmap_pages(struct iommu_domain *domain,
 				  unsigned long iova, size_t size,
 				  struct iommu_iotlb_gather *iotlb_gather)
@@ -2471,9 +2464,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 
-static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-		struct scatterlist *sg, unsigned int nents, int prot,
-		gfp_t gfp)
+ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		     struct scatterlist *sg, unsigned int nents, int prot,
+		     gfp_t gfp)
 {
 	const struct iommu_domain_ops *ops = domain->ops;
 	size_t len = 0, mapped = 0;
@@ -2481,6 +2474,13 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 	unsigned int i = 0;
 	int ret;
 
+	might_sleep_if(gfpflags_allow_blocking(gfp));
+
+	/* Discourage passing strange GFP flags */
+	if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
+				__GFP_HIGHMEM)))
+		return -EINVAL;
+
 	while (i <= nents) {
 		phys_addr_t s_phys = sg_phys(sg);
 
@@ -2520,21 +2520,8 @@ out_err:
 
 	return ret;
 }
-
-ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-		     struct scatterlist *sg, unsigned int nents, int prot)
-{
-	might_sleep();
-	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
-}
 EXPORT_SYMBOL_GPL(iommu_map_sg);
 
-ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
-		    struct scatterlist *sg, unsigned int nents, int prot)
-{
-	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
-}
-
 /**
  * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
  * @domain: the iommu domain where the fault has happened