[PATCH v3 2/2] arm64: mm: reserve per-numa CMA to localize coherent dma buffers

Barry Song song.bao.hua at hisilicon.com
Sun Jun 28 07:12:51 EDT 2020

Right now, smmu is using dma_alloc_coherent() to get memory to save queues
and tables. Typically, on ARM64 server, there is a default CMA located at
node0, which could be far away from node2, node3 etc.
with this patch, smmu will get memory from local numa node to save command
queues and page tables. that means dma_unmap latency will be shrunk much.
Meanwhile, when iommu.passthrough is on, device drivers which call dma_
alloc_coherent() will also get local memory and avoid the travel between
numa nodes.

Cc: Christoph Hellwig <hch at lst.de>
Cc: Marek Szyprowski <m.szyprowski at samsung.com>
Cc: Will Deacon <will at kernel.org>
Cc: Robin Murphy <robin.murphy at arm.com>
Cc: Ganapatrao Kulkarni <ganapatrao.kulkarni at cavium.com>
Cc: Catalin Marinas <catalin.marinas at arm.com>
Cc: Nicolas Saenz Julienne <nsaenzjulienne at suse.de>
Cc: Steve Capper <steve.capper at arm.com>
Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: Mike Rapoport <rppt at linux.ibm.com>
Signed-off-by: Barry Song <song.bao.hua at hisilicon.com>
  * move dma_pernuma_cma_reserve() after hugetlb_cma_reserve() to
  reuse the comment before hugetlb_cma_reserve() with respect to
  Robin's comment

 arch/arm64/mm/init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 1e93cfc7c47a..a01eeb829372 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -429,6 +429,8 @@ void __init bootmem_init(void)
 	hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+	dma_pernuma_cma_reserve();
 	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
 	 * done after the fixed reservations.

More information about the linux-arm-kernel mailing list