[PATCH 5/8] iommufd: Use GFP_KERNEL_ACCOUNT for iommu_map()

Jason Gunthorpe jgg at nvidia.com
Fri Jan 6 08:42:45 PST 2023


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.

However, one of the biggest consumers of kernel memory is the IOPTEs
stored under the iommu_domain. Many drivers will allocate these at
iommu_map() time and will trivially do the right thing if we pass in
GFP_KERNEL_ACCOUNT.

Signed-off-by: Jason Gunthorpe <jgg at nvidia.com>
---
 drivers/iommu/iommufd/pages.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c
index 22cc3bb0c6c55a..f8d92c9bb65b60 100644
--- a/drivers/iommu/iommufd/pages.c
+++ b/drivers/iommu/iommufd/pages.c
@@ -457,7 +457,7 @@ static int batch_iommu_map_small(struct iommu_domain *domain,
 
 	while (size) {
 		rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot,
-			       GFP_KERNEL);
+			       GFP_KERNEL_ACCOUNT);
 		if (rc)
 			goto err_unmap;
 		iova += PAGE_SIZE;
@@ -502,7 +502,7 @@ static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain,
 			rc = iommu_map(domain, iova,
 				       PFN_PHYS(batch->pfns[cur]) + page_offset,
 				       next_iova - iova, area->iommu_prot,
-				       GFP_KERNEL);
+				       GFP_KERNEL_ACCOUNT);
 		if (rc)
 			goto err_unmap;
 		iova = next_iova;
-- 
2.39.0




More information about the ath11k mailing list