Cc: linuxppc-dev@lists.ozlabs.org, linux-ker...@vger.kernel.org,
Currently both iommu_alloc_coherent() and iommu_free_coherent() align the
desired allocation size to PAGE_SIZE, and gets system pages and IOMMU
mappings (TCEs) for that value.
When IOMMU_PAGE_SIZE < PAGE_SIZE, this behavior may cause unnecessary
TCEs to be created for mapping the whole system page.
Example:
- PAGE_SIZE = 64k, IOMMU_PAGE_SIZE() = 4k
- iommu_alloc_coherent() is called for 128 bytes
- 1 system page (64k) is allocated
- 16 IOMMU pages (16 x 4k) are allocated (16 TCEs used)
It would be enough to use a single TCE for this, so 15 TCEs are
wasted in the process.
Update iommu_*_coherent() to make sure the size alignment happens only
for IOMMU_PAGE_SIZE() before calling iommu_alloc() and iommu_free().
Also, on iommu_range_alloc(), replace ALIGN(n, 1 << tbl->it_page_shift)
with IOMMU_PAGE_ALIGN(n, tbl), which is easier to read and does the
same.
Signed-off-by: Leonardo Bras <leobra...@gmail.com>
---
arch/powerpc/kernel/iommu.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 9704f3f76e63..7961645a6980 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -237,10 +237,9 @@ static unsigned long iommu_range_alloc(struct device *dev,
}
if (dev)
- boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
- 1 << tbl->it_page_shift);
+ boundary_size = IOMMU_PAGE_ALIGN(dma_get_seg_boundary(dev) + 1,
tbl);
else
- boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
+ boundary_size = IOMMU_PAGE_ALIGN(1UL << 32, tbl);
/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
@@ -858,6 +857,7 @@ void *iommu_alloc_coherent(struct device *dev, struct
iommu_table *tbl,
unsigned int order;
unsigned int nio_pages, io_order;
struct page *page;
+ size_t size_io = size;
size = PAGE_ALIGN(size);
order = get_order(size);
@@ -884,8 +884,9 @@ void *iommu_alloc_coherent(struct device *dev, struct
iommu_table *tbl,
memset(ret, 0, size);
/* Set up tces to cover the allocated range */
- nio_pages = size >> tbl->it_page_shift;
- io_order = get_iommu_order(size, tbl);
+ size_io = IOMMU_PAGE_ALIGN(size_io, tbl);
+ nio_pages = size_io >> tbl->it_page_shift;
+ io_order = get_iommu_order(size_io, tbl);
mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
mask >> tbl->it_page_shift, io_order, 0);
if (mapping == DMA_MAPPING_ERROR) {
@@ -900,10 +901,9 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t
size,
void *vaddr, dma_addr_t dma_handle)
{
if (tbl) {
- unsigned int nio_pages;
+ size_t size_io = IOMMU_PAGE_ALIGN(size, tbl);
+ unsigned int nio_pages = size_io >> tbl->it_page_shift;
- size = PAGE_ALIGN(size);
- nio_pages = size >> tbl->it_page_shift;
iommu_free(tbl, dma_handle, nio_pages);
size = PAGE_ALIGN(size);
free_pages((unsigned long)vaddr, get_order(size));
--
2.25.4
