RDMA/hns: Support WQE/CQE/PBL page size configurable feature in hip08
This patch updates to support WQE, CQE and PBL page size configurable
feature, which includes base address page size and buffer page size.
Signed-off-by: Shaobo Xu <xushaobo2@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Lijun Ou <oulijun@huawei.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index 8c9a33f..3e4c525 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -167,12 +167,12 @@ void hns_roce_buf_free(struct hns_roce_dev *hr_dev, u32 size,
if (buf->nbufs == 1) {
dma_free_coherent(dev, size, buf->direct.buf, buf->direct.map);
} else {
- if (bits_per_long == 64)
+ if (bits_per_long == 64 && buf->page_shift == PAGE_SHIFT)
vunmap(buf->direct.buf);
for (i = 0; i < buf->nbufs; ++i)
if (buf->page_list[i].buf)
- dma_free_coherent(dev, PAGE_SIZE,
+ dma_free_coherent(dev, 1 << buf->page_shift,
buf->page_list[i].buf,
buf->page_list[i].map);
kfree(buf->page_list);
@@ -181,20 +181,27 @@ void hns_roce_buf_free(struct hns_roce_dev *hr_dev, u32 size,
EXPORT_SYMBOL_GPL(hns_roce_buf_free);
int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
- struct hns_roce_buf *buf)
+ struct hns_roce_buf *buf, u32 page_shift)
{
int i = 0;
dma_addr_t t;
struct page **pages;
struct device *dev = hr_dev->dev;
u32 bits_per_long = BITS_PER_LONG;
+ u32 page_size = 1 << page_shift;
+ u32 order;
/* SQ/RQ buf lease than one page, SQ + RQ = 8K */
if (size <= max_direct) {
buf->nbufs = 1;
/* Npages calculated by page_size */
- buf->npages = 1 << get_order(size);
- buf->page_shift = PAGE_SHIFT;
+ order = get_order(size);
+ if (order <= page_shift - PAGE_SHIFT)
+ order = 0;
+ else
+ order -= page_shift - PAGE_SHIFT;
+ buf->npages = 1 << order;
+ buf->page_shift = page_shift;
/* MTT PA must be recorded in 4k alignment, t is 4k aligned */
buf->direct.buf = dma_alloc_coherent(dev, size, &t, GFP_KERNEL);
if (!buf->direct.buf)
@@ -209,9 +216,9 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
memset(buf->direct.buf, 0, size);
} else {
- buf->nbufs = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+ buf->nbufs = (size + page_size - 1) / page_size;
buf->npages = buf->nbufs;
- buf->page_shift = PAGE_SHIFT;
+ buf->page_shift = page_shift;
buf->page_list = kcalloc(buf->nbufs, sizeof(*buf->page_list),
GFP_KERNEL);
@@ -220,16 +227,16 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
for (i = 0; i < buf->nbufs; ++i) {
buf->page_list[i].buf = dma_alloc_coherent(dev,
- PAGE_SIZE, &t,
+ page_size, &t,
GFP_KERNEL);
if (!buf->page_list[i].buf)
goto err_free;
buf->page_list[i].map = t;
- memset(buf->page_list[i].buf, 0, PAGE_SIZE);
+ memset(buf->page_list[i].buf, 0, page_size);
}
- if (bits_per_long == 64) {
+ if (bits_per_long == 64 && page_shift == PAGE_SHIFT) {
pages = kmalloc_array(buf->nbufs, sizeof(*pages),
GFP_KERNEL);
if (!pages)
@@ -243,6 +250,8 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
kfree(pages);
if (!buf->direct.buf)
goto err_free;
+ } else {
+ buf->direct.buf = NULL;
}
}