diff mbox series

[v2,05/10] iommufd: Use GFP_KERNEL_ACCOUNT for iommu_map()

Message ID 5-v2-ce66f632bd0d+484-iommu_map_gfp_jgg@nvidia.com
State Superseded
Headers show
Series Let iommufd charge IOPTE allocations to the memory cgroup | expand

Commit Message

Jason Gunthorpe Jan. 18, 2023, 6 p.m. UTC
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@nvidia.com>
---
 drivers/iommu/iommufd/pages.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Comments

Tian, Kevin Jan. 19, 2023, 3:48 a.m. UTC | #1
> From: Jason Gunthorpe <jgg@nvidia.com>
> Sent: Thursday, January 19, 2023 2:01 AM
> 
> 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@nvidia.com>

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
diff mbox series

Patch

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;