提交 11b83888 编写于 作者: J Joerg Roedel

amd-iommu: enlarge the aperture dynamically

By dynamically increasing the aperture the extended allocator is now
ready for use.
Signed-off-by: NJoerg Roedel <joerg.roedel@amd.com>
上级 00cd122a
......@@ -1403,10 +1403,26 @@ static dma_addr_t __map_single(struct device *dev,
if (align)
align_mask = (1UL << get_order(size)) - 1;
retry:
address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask,
dma_mask);
if (unlikely(address == bad_dma_address))
goto out;
if (unlikely(address == bad_dma_address)) {
/*
* setting next_address here will let the address
* allocator only scan the new allocated range in the
* first run. This is a small optimization.
*/
dma_dom->next_address = dma_dom->aperture_size;
if (alloc_new_range(iommu, dma_dom, false, GFP_ATOMIC))
goto out;
/*
* aperture was sucessfully enlarged by 128 MB, try
* allocation again
*/
goto retry;
}
start = address;
for (i = 0; i < pages; ++i) {
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册