diff options
author | Jason Gunthorpe <jgg@nvidia.com> | 2023-01-30 18:53:04 +0100 |
---|---|---|
committer | Jason Gunthorpe <jgg@nvidia.com> | 2023-01-30 18:54:35 +0100 |
commit | fd9f2a912255106d3b53163d816a4bd99ba29664 (patch) | |
tree | 892f38b617b534c93dc5c0b1f1efc3950812e828 /drivers/iommu/s390-iommu.c | |
parent | iommufd: Add three missing structures in ucmd_buffer (diff) | |
parent | iommu/s390: Use GFP_KERNEL in sleepable contexts (diff) | |
download | linux-fd9f2a912255106d3b53163d816a4bd99ba29664.tar.xz linux-fd9f2a912255106d3b53163d816a4bd99ba29664.zip |
Merge branch 'iommu-memory-accounting' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/joro/iommu intoiommufd/for-next
Jason Gunthorpe says:
====================
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.
====================
* 'iommu-memory-accounting' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu/s390: Use GFP_KERNEL in sleepable contexts
iommu/s390: Push the gfp parameter to the kmem_cache_alloc()'s
iommu/intel: Use GFP_KERNEL in sleepable contexts
iommu/intel: Support the gfp argument to the map_pages op
iommu/intel: Add a gfp parameter to alloc_pgtable_page()
iommufd: Use GFP_KERNEL_ACCOUNT for iommu_map()
iommu/dma: Use the gfp parameter in __iommu_dma_alloc_noncontiguous()
iommu: Add a gfp parameter to iommu_map_sg()
iommu: Remove iommu_map_atomic()
iommu: Add a gfp parameter to iommu_map()
Link: https://lore.kernel.org/linux-iommu/0-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'drivers/iommu/s390-iommu.c')
-rw-r--r-- | drivers/iommu/s390-iommu.c | 15 |
1 files changed, 9 insertions, 6 deletions
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index bb00580a30d8..c489714ddc4d 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -50,7 +50,7 @@ static struct iommu_domain *s390_domain_alloc(unsigned domain_type) if (!s390_domain) return NULL; - s390_domain->dma_table = dma_alloc_cpu_table(); + s390_domain->dma_table = dma_alloc_cpu_table(GFP_KERNEL); if (!s390_domain->dma_table) { kfree(s390_domain); return NULL; @@ -258,7 +258,8 @@ static void s390_iommu_iotlb_sync_map(struct iommu_domain *domain, static int s390_iommu_validate_trans(struct s390_domain *s390_domain, phys_addr_t pa, dma_addr_t dma_addr, - unsigned long nr_pages, int flags) + unsigned long nr_pages, int flags, + gfp_t gfp) { phys_addr_t page_addr = pa & PAGE_MASK; unsigned long *entry; @@ -266,7 +267,8 @@ static int s390_iommu_validate_trans(struct s390_domain *s390_domain, int rc; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr, + gfp); if (unlikely(!entry)) { rc = -ENOMEM; goto undo_cpu_trans; @@ -282,7 +284,7 @@ undo_cpu_trans: while (i-- > 0) { dma_addr -= PAGE_SIZE; entry = dma_walk_cpu_trans(s390_domain->dma_table, - dma_addr); + dma_addr, gfp); if (!entry) break; dma_update_cpu_trans(entry, 0, ZPCI_PTE_INVALID); @@ -299,7 +301,8 @@ static int s390_iommu_invalidate_trans(struct s390_domain *s390_domain, int rc = 0; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr, + GFP_ATOMIC); if (unlikely(!entry)) { rc = -EINVAL; break; @@ -337,7 +340,7 @@ static int s390_iommu_map_pages(struct iommu_domain *domain, flags |= ZPCI_TABLE_PROTECTED; rc = s390_iommu_validate_trans(s390_domain, paddr, iova, - pgcount, flags); + pgcount, flags, gfp); if (!rc) *mapped = size; |