static u32 ehca_encode_hwpage_size(u32 pgsize)
{
- u32 idx = 0;
- pgsize >>= 12;
- /*
- * map mr page size into hw code:
- * 0, 1, 2, 3 for 4K, 64K, 1M, 64M
- */
- while (!(pgsize & 1)) {
- idx++;
- pgsize >>= 4;
- }
- return idx;
+ int log = ilog2(pgsize);
+ WARN_ON(log < 12 || log > 24 || log & 3);
+ return (log - 12) / 4;
}
static u64 ehca_get_max_hwpage_size(struct ehca_shca *shca)
{
- if (shca->hca_cap_mr_pgsize & HCA_CAP_MR_PGSIZE_16M)
- return EHCA_MR_PGSIZE16M;
- return EHCA_MR_PGSIZE4K;
+ return 1UL << ilog2(shca->hca_cap_mr_pgsize);
}
static struct ehca_mr *ehca_mr_new(void)
pginfo.u.phy.num_phys_buf = num_phys_buf;
pginfo.u.phy.phys_buf_array = phys_buf_array;
pginfo.next_hwpage =
- ((u64)iova_start & ~(hw_pgsize - 1)) / hw_pgsize;
+ ((u64)iova_start & ~PAGE_MASK) / hw_pgsize;
ret = ehca_reg_mr(shca, e_mr, iova_start, size, mr_access_flags,
e_pd, &pginfo, &e_mr->ib.ib_mr.lkey,
container_of(pd->device, struct ehca_shca, ib_device);
struct ehca_pd *e_pd = container_of(pd, struct ehca_pd, ib_pd);
struct ehca_mr_pginfo pginfo;
- int ret;
+ int ret, page_shift;
u32 num_kpages;
u32 num_hwpages;
u64 hwpage_size;
/* determine number of MR pages */
num_kpages = NUM_CHUNKS((virt % PAGE_SIZE) + length, PAGE_SIZE);
/* select proper hw_pgsize */
- if (ehca_mr_largepage &&
- (shca->hca_cap_mr_pgsize & HCA_CAP_MR_PGSIZE_16M)) {
- int page_shift = PAGE_SHIFT;
- if (e_mr->umem->hugetlb) {
- /* determine page_shift, clamp between 4K and 16M */
- page_shift = (fls64(length - 1) + 3) & ~3;
- page_shift = min(max(page_shift, EHCA_MR_PGSHIFT4K),
- EHCA_MR_PGSHIFT16M);
- }
- hwpage_size = 1UL << page_shift;
- } else
- hwpage_size = EHCA_MR_PGSIZE4K; /* ehca1 only supports 4k */
- ehca_dbg(pd->device, "hwpage_size=%lx", hwpage_size);
+ page_shift = PAGE_SHIFT;
+ if (e_mr->umem->hugetlb) {
+ /* determine page_shift, clamp between 4K and 16M */
+ page_shift = (fls64(length - 1) + 3) & ~3;
+ page_shift = min(max(page_shift, EHCA_MR_PGSHIFT4K),
+ EHCA_MR_PGSHIFT16M);
+ }
+ hwpage_size = 1UL << page_shift;
+
+ /* now that we have the desired page size, shift until it's
+ * supported, too. 4K is always supported, so this terminates.
+ */
+ while (!(hwpage_size & shca->hca_cap_mr_pgsize))
+ hwpage_size >>= 4;
reg_user_mr_fallback:
num_hwpages = NUM_CHUNKS((virt % hwpage_size) + length, hwpage_size);
pginfo.u.phy.num_phys_buf = num_phys_buf;
pginfo.u.phy.phys_buf_array = phys_buf_array;
pginfo.next_hwpage =
- ((u64)iova_start & ~(hw_pgsize - 1)) / hw_pgsize;
+ ((u64)iova_start & ~PAGE_MASK) / hw_pgsize;
}
if (mr_rereg_mask & IB_MR_REREG_ACCESS)
new_acl = mr_access_flags;
ib_fmr = ERR_PTR(-EINVAL);
goto alloc_fmr_exit0;
}
- hw_pgsize = ehca_get_max_hwpage_size(shca);
- if ((1 << fmr_attr->page_shift) != hw_pgsize) {
+
+ hw_pgsize = 1 << fmr_attr->page_shift;
+ if (!(hw_pgsize & shca->hca_cap_mr_pgsize)) {
ehca_err(pd->device, "unsupported fmr_attr->page_shift=%x",
fmr_attr->page_shift);
ib_fmr = ERR_PTR(-EINVAL);
/* register MR on HCA */
memset(&pginfo, 0, sizeof(pginfo));
+ pginfo.hwpage_size = hw_pgsize;
/*
* pginfo.num_hwpages==0, ie register_rpages() will not be called
* but deferred to map_phys_fmr()
list_for_each_entry_continue(
chunk, (&(pginfo->u.usr.region->chunk_list)), list) {
for (i = pginfo->u.usr.next_nmap; i < chunk->nmap; ) {
- pgaddr = page_to_pfn(chunk->page_list[i].page)
+ pgaddr = page_to_pfn(sg_page(&chunk->page_list[i]))
<< PAGE_SHIFT ;
*kpage = phys_to_abs(pgaddr +
(pginfo->next_hwpage *
{
int t;
for (t = start_idx; t <= end_idx; t++) {
- u64 pgaddr = page_to_pfn(page_list[t].page) << PAGE_SHIFT;
+ u64 pgaddr = page_to_pfn(sg_page(&page_list[t])) << PAGE_SHIFT;
ehca_gen_dbg("chunk_page=%lx value=%016lx", pgaddr,
*(u64 *)abs_to_virt(phys_to_abs(pgaddr)));
if (pgaddr - PAGE_SIZE != *prev_pgaddr) {
chunk, (&(pginfo->u.usr.region->chunk_list)), list) {
for (i = pginfo->u.usr.next_nmap; i < chunk->nmap; ) {
if (nr_kpages == kpages_per_hwpage) {
- pgaddr = ( page_to_pfn(chunk->page_list[i].page)
+ pgaddr = ( page_to_pfn(sg_page(&chunk->page_list[i]))
<< PAGE_SHIFT );
*kpage = phys_to_abs(pgaddr);
if ( !(*kpage) ) {