*
* Authors: Dietmar Decker <ddecker@de.ibm.com>
* Christoph Raisch <raisch@de.ibm.com>
+ * Hoang-Nam Nguyen <hnguyen@de.ibm.com>
*
* Copyright (c) 2005 IBM Corporation
*
* POSSIBILITY OF SUCH DAMAGE.
*/
-#include <rdma/ib_umem.h>
-
#include <asm/current.h>
+#include <rdma/ib_umem.h>
+
#include "ehca_iverbs.h"
#include "ehca_mrmw.h"
#include "hcp_if.h"
#define NUM_CHUNKS(length, chunk_size) \
(((length) + (chunk_size - 1)) / (chunk_size))
+
/* max number of rpages (per hcall register_rpages) */
#define MAX_RPAGES 512
static struct kmem_cache *mr_cache;
static struct kmem_cache *mw_cache;
+enum ehca_mr_pgsize {
+ EHCA_MR_PGSIZE4K = 0x1000L,
+ EHCA_MR_PGSIZE64K = 0x10000L,
+ EHCA_MR_PGSIZE1M = 0x100000L,
+ EHCA_MR_PGSIZE16M = 0x1000000L
+};
+
+#define EHCA_MR_PGSHIFT4K 12
+#define EHCA_MR_PGSHIFT64K 16
+#define EHCA_MR_PGSHIFT1M 20
+#define EHCA_MR_PGSHIFT16M 24
+
+static u32 ehca_encode_hwpage_size(u32 pgsize)
+{
+ 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)
+{
+ return 1UL << ilog2(shca->hca_cap_mr_pgsize);
+}
+
static struct ehca_mr *ehca_mr_new(void)
{
struct ehca_mr *me;
get_dma_mr_exit0:
if (IS_ERR(ib_mr))
- ehca_err(&shca->ib_device, "rc=%lx pd=%p mr_access_flags=%x ",
+ ehca_err(&shca->ib_device, "h_ret=%li pd=%p mr_access_flags=%x",
PTR_ERR(ib_mr), pd, mr_access_flags);
return ib_mr;
} /* end ehca_get_dma_mr() */
struct ehca_mr_pginfo pginfo;
u32 num_kpages;
u32 num_hwpages;
+ u64 hw_pgsize;
num_kpages = NUM_CHUNKS(((u64)iova_start % PAGE_SIZE) + size,
PAGE_SIZE);
- num_hwpages = NUM_CHUNKS(((u64)iova_start % EHCA_PAGESIZE) +
- size, EHCA_PAGESIZE);
+ /* for kernel space we try most possible pgsize */
+ hw_pgsize = ehca_get_max_hwpage_size(shca);
+ num_hwpages = NUM_CHUNKS(((u64)iova_start % hw_pgsize) + size,
+ hw_pgsize);
memset(&pginfo, 0, sizeof(pginfo));
pginfo.type = EHCA_MR_PGI_PHYS;
pginfo.num_kpages = num_kpages;
+ pginfo.hwpage_size = hw_pgsize;
pginfo.num_hwpages = num_hwpages;
pginfo.u.phy.num_phys_buf = num_phys_buf;
pginfo.u.phy.phys_buf_array = phys_buf_array;
- pginfo.next_hwpage = (((u64)iova_start & ~PAGE_MASK) /
- EHCA_PAGESIZE);
+ pginfo.next_hwpage =
+ ((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,
ehca_mr_delete(e_mr);
reg_phys_mr_exit0:
if (IS_ERR(ib_mr))
- ehca_err(pd->device, "rc=%lx pd=%p phys_buf_array=%p "
+ ehca_err(pd->device, "h_ret=%li pd=%p phys_buf_array=%p "
"num_phys_buf=%x mr_access_flags=%x iova_start=%p",
PTR_ERR(ib_mr), pd, phys_buf_array,
num_phys_buf, mr_access_flags, iova_start);
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;
if (!pd) {
ehca_gen_err("bad pd=%p", pd);
/* determine number of MR pages */
num_kpages = NUM_CHUNKS((virt % PAGE_SIZE) + length, PAGE_SIZE);
- num_hwpages = NUM_CHUNKS((virt % EHCA_PAGESIZE) + length,
- EHCA_PAGESIZE);
-
+ /* select proper hw_pgsize */
+ 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);
/* register MR on HCA */
memset(&pginfo, 0, sizeof(pginfo));
pginfo.type = EHCA_MR_PGI_USER;
+ pginfo.hwpage_size = hwpage_size;
pginfo.num_kpages = num_kpages;
pginfo.num_hwpages = num_hwpages;
pginfo.u.usr.region = e_mr->umem;
- pginfo.next_hwpage = e_mr->umem->offset / EHCA_PAGESIZE;
+ pginfo.next_hwpage = e_mr->umem->offset / hwpage_size;
pginfo.u.usr.next_chunk = list_prepare_entry(pginfo.u.usr.next_chunk,
(&e_mr->umem->chunk_list),
list);
ret = ehca_reg_mr(shca, e_mr, (u64 *)virt, length, mr_access_flags,
e_pd, &pginfo, &e_mr->ib.ib_mr.lkey,
&e_mr->ib.ib_mr.rkey);
+ if (ret == -EINVAL && pginfo.hwpage_size > PAGE_SIZE) {
+ ehca_warn(pd->device, "failed to register mr "
+ "with hwpage_size=%lx", hwpage_size);
+ ehca_info(pd->device, "try to register mr with "
+ "kpage_size=%lx", PAGE_SIZE);
+ /*
+ * this means kpages are not contiguous for a hw page
+ * try kernel page size as fallback solution
+ */
+ hwpage_size = PAGE_SIZE;
+ goto reg_user_mr_fallback;
+ }
if (ret) {
ib_mr = ERR_PTR(ret);
goto reg_user_mr_exit2;
ehca_mr_delete(e_mr);
reg_user_mr_exit0:
if (IS_ERR(ib_mr))
- ehca_err(pd->device, "rc=%lx pd=%p mr_access_flags=%x"
- " udata=%p",
+ ehca_err(pd->device, "rc=%li pd=%p mr_access_flags=%x udata=%p",
PTR_ERR(ib_mr), pd, mr_access_flags, udata);
return ib_mr;
} /* end ehca_reg_user_mr() */
new_pd = container_of(mr->pd, struct ehca_pd, ib_pd);
if (mr_rereg_mask & IB_MR_REREG_TRANS) {
+ u64 hw_pgsize = ehca_get_max_hwpage_size(shca);
+
new_start = iova_start; /* change address */
/* check physical buffer list and calculate size */
ret = ehca_mr_chk_buf_and_calc_size(phys_buf_array,
}
num_kpages = NUM_CHUNKS(((u64)new_start % PAGE_SIZE) +
new_size, PAGE_SIZE);
- num_hwpages = NUM_CHUNKS(((u64)new_start % EHCA_PAGESIZE) +
- new_size, EHCA_PAGESIZE);
+ num_hwpages = NUM_CHUNKS(((u64)new_start % hw_pgsize) +
+ new_size, hw_pgsize);
memset(&pginfo, 0, sizeof(pginfo));
pginfo.type = EHCA_MR_PGI_PHYS;
pginfo.num_kpages = num_kpages;
+ pginfo.hwpage_size = hw_pgsize;
pginfo.num_hwpages = num_hwpages;
pginfo.u.phy.num_phys_buf = num_phys_buf;
pginfo.u.phy.phys_buf_array = phys_buf_array;
- pginfo.next_hwpage = (((u64)iova_start & ~PAGE_MASK) /
- EHCA_PAGESIZE);
+ pginfo.next_hwpage =
+ ((u64)iova_start & ~PAGE_MASK) / hw_pgsize;
}
if (mr_rereg_mask & IB_MR_REREG_ACCESS)
new_acl = mr_access_flags;
spin_unlock_irqrestore(&e_mr->mrlock, sl_flags);
rereg_phys_mr_exit0:
if (ret)
- ehca_err(mr->device, "ret=%x mr=%p mr_rereg_mask=%x pd=%p "
+ ehca_err(mr->device, "ret=%i mr=%p mr_rereg_mask=%x pd=%p "
"phys_buf_array=%p num_phys_buf=%x mr_access_flags=%x "
"iova_start=%p",
ret, mr, mr_rereg_mask, pd, phys_buf_array,
h_ret = hipz_h_query_mr(shca->ipz_hca_handle, e_mr, &hipzout);
if (h_ret != H_SUCCESS) {
- ehca_err(mr->device, "hipz_mr_query failed, h_ret=%lx mr=%p "
+ ehca_err(mr->device, "hipz_mr_query failed, h_ret=%li mr=%p "
"hca_hndl=%lx mr_hndl=%lx lkey=%x",
h_ret, mr, shca->ipz_hca_handle.handle,
e_mr->ipz_mr_handle.handle, mr->lkey);
spin_unlock_irqrestore(&e_mr->mrlock, sl_flags);
query_mr_exit0:
if (ret)
- ehca_err(mr->device, "ret=%x mr=%p mr_attr=%p",
+ ehca_err(mr->device, "ret=%i mr=%p mr_attr=%p",
ret, mr, mr_attr);
return ret;
} /* end ehca_query_mr() */
/* TODO: BUSY: MR still has bound window(s) */
h_ret = hipz_h_free_resource_mr(shca->ipz_hca_handle, e_mr);
if (h_ret != H_SUCCESS) {
- ehca_err(mr->device, "hipz_free_mr failed, h_ret=%lx shca=%p "
+ ehca_err(mr->device, "hipz_free_mr failed, h_ret=%li shca=%p "
"e_mr=%p hca_hndl=%lx mr_hndl=%lx mr->lkey=%x",
h_ret, shca, e_mr, shca->ipz_hca_handle.handle,
e_mr->ipz_mr_handle.handle, mr->lkey);
dereg_mr_exit0:
if (ret)
- ehca_err(mr->device, "ret=%x mr=%p", ret, mr);
+ ehca_err(mr->device, "ret=%i mr=%p", ret, mr);
return ret;
} /* end ehca_dereg_mr() */
h_ret = hipz_h_alloc_resource_mw(shca->ipz_hca_handle, e_mw,
e_pd->fw_pd, &hipzout);
if (h_ret != H_SUCCESS) {
- ehca_err(pd->device, "hipz_mw_allocate failed, h_ret=%lx "
+ ehca_err(pd->device, "hipz_mw_allocate failed, h_ret=%li "
"shca=%p hca_hndl=%lx mw=%p",
h_ret, shca, shca->ipz_hca_handle.handle, e_mw);
ib_mw = ERR_PTR(ehca2ib_return_code(h_ret));
ehca_mw_delete(e_mw);
alloc_mw_exit0:
if (IS_ERR(ib_mw))
- ehca_err(pd->device, "rc=%lx pd=%p", PTR_ERR(ib_mw), pd);
+ ehca_err(pd->device, "h_ret=%li pd=%p", PTR_ERR(ib_mw), pd);
return ib_mw;
} /* end ehca_alloc_mw() */
h_ret = hipz_h_free_resource_mw(shca->ipz_hca_handle, e_mw);
if (h_ret != H_SUCCESS) {
- ehca_err(mw->device, "hipz_free_mw failed, h_ret=%lx shca=%p "
+ ehca_err(mw->device, "hipz_free_mw failed, h_ret=%li shca=%p "
"mw=%p rkey=%x hca_hndl=%lx mw_hndl=%lx",
h_ret, shca, mw, mw->rkey, shca->ipz_hca_handle.handle,
e_mw->ipz_mw_handle.handle);
int ret;
u32 tmp_lkey, tmp_rkey;
struct ehca_mr_pginfo pginfo;
+ u64 hw_pgsize;
/* check other parameters */
if (((mr_access_flags & IB_ACCESS_REMOTE_WRITE) &&
ib_fmr = ERR_PTR(-EINVAL);
goto alloc_fmr_exit0;
}
- if (((1 << fmr_attr->page_shift) != EHCA_PAGESIZE) &&
- ((1 << fmr_attr->page_shift) != PAGE_SIZE)) {
+
+ 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()
+ */
ret = ehca_reg_mr(shca, e_fmr, NULL,
fmr_attr->max_pages * (1 << fmr_attr->page_shift),
mr_access_flags, e_pd, &pginfo,
}
/* successful */
+ e_fmr->hwpage_size = hw_pgsize;
e_fmr->fmr_page_size = 1 << fmr_attr->page_shift;
e_fmr->fmr_max_pages = fmr_attr->max_pages;
e_fmr->fmr_max_maps = fmr_attr->max_maps;
alloc_fmr_exit1:
ehca_mr_delete(e_fmr);
alloc_fmr_exit0:
- if (IS_ERR(ib_fmr))
- ehca_err(pd->device, "rc=%lx pd=%p mr_access_flags=%x "
- "fmr_attr=%p", PTR_ERR(ib_fmr), pd,
- mr_access_flags, fmr_attr);
return ib_fmr;
} /* end ehca_alloc_fmr() */
memset(&pginfo, 0, sizeof(pginfo));
pginfo.type = EHCA_MR_PGI_FMR;
pginfo.num_kpages = list_len;
- pginfo.num_hwpages = list_len * (e_fmr->fmr_page_size / EHCA_PAGESIZE);
+ pginfo.hwpage_size = e_fmr->hwpage_size;
+ pginfo.num_hwpages =
+ list_len * e_fmr->fmr_page_size / pginfo.hwpage_size;
pginfo.u.fmr.page_list = page_list;
- pginfo.next_hwpage = ((iova & (e_fmr->fmr_page_size-1)) /
- EHCA_PAGESIZE);
+ pginfo.next_hwpage =
+ (iova & (e_fmr->fmr_page_size-1)) / pginfo.hwpage_size;
pginfo.u.fmr.fmr_pgsize = e_fmr->fmr_page_size;
ret = ehca_rereg_mr(shca, e_fmr, (u64 *)iova,
map_phys_fmr_exit0:
if (ret)
- ehca_err(fmr->device, "ret=%x fmr=%p page_list=%p list_len=%x "
+ ehca_err(fmr->device, "ret=%i fmr=%p page_list=%p list_len=%x "
"iova=%lx", ret, fmr, page_list, list_len, iova);
return ret;
} /* end ehca_map_phys_fmr() */
unmap_fmr_exit0:
if (ret)
- ehca_gen_err("ret=%x fmr_list=%p num_fmr=%x unmap_fmr_cnt=%x",
+ ehca_gen_err("ret=%i fmr_list=%p num_fmr=%x unmap_fmr_cnt=%x",
ret, fmr_list, num_fmr, unmap_fmr_cnt);
return ret;
} /* end ehca_unmap_fmr() */
h_ret = hipz_h_free_resource_mr(shca->ipz_hca_handle, e_fmr);
if (h_ret != H_SUCCESS) {
- ehca_err(fmr->device, "hipz_free_mr failed, h_ret=%lx e_fmr=%p "
+ ehca_err(fmr->device, "hipz_free_mr failed, h_ret=%li e_fmr=%p "
"hca_hndl=%lx fmr_hndl=%lx fmr->lkey=%x",
h_ret, e_fmr, shca->ipz_hca_handle.handle,
e_fmr->ipz_mr_handle.handle, fmr->lkey);
free_fmr_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x fmr=%p", ret, fmr);
+ ehca_err(&shca->ib_device, "ret=%i fmr=%p", ret, fmr);
return ret;
} /* end ehca_dealloc_fmr() */
struct ehca_mr_hipzout_parms hipzout;
ehca_mrmw_map_acl(acl, &hipz_acl);
- ehca_mrmw_set_pgsize_hipz_acl(&hipz_acl);
+ ehca_mrmw_set_pgsize_hipz_acl(pginfo->hwpage_size, &hipz_acl);
if (ehca_use_hp_mr == 1)
hipz_acl |= 0x00000001;
(u64)iova_start, size, hipz_acl,
e_pd->fw_pd, &hipzout);
if (h_ret != H_SUCCESS) {
- ehca_err(&shca->ib_device, "hipz_alloc_mr failed, h_ret=%lx "
+ ehca_err(&shca->ib_device, "hipz_alloc_mr failed, h_ret=%li "
"hca_hndl=%lx", h_ret, shca->ipz_hca_handle.handle);
ret = ehca2ib_return_code(h_ret);
goto ehca_reg_mr_exit0;
/* successful registration */
e_mr->num_kpages = pginfo->num_kpages;
e_mr->num_hwpages = pginfo->num_hwpages;
+ e_mr->hwpage_size = pginfo->hwpage_size;
e_mr->start = iova_start;
e_mr->size = size;
e_mr->acl = acl;
ehca_reg_mr_exit1:
h_ret = hipz_h_free_resource_mr(shca->ipz_hca_handle, e_mr);
if (h_ret != H_SUCCESS) {
- ehca_err(&shca->ib_device, "h_ret=%lx shca=%p e_mr=%p "
+ ehca_err(&shca->ib_device, "h_ret=%li shca=%p e_mr=%p "
"iova_start=%p size=%lx acl=%x e_pd=%p lkey=%x "
- "pginfo=%p num_kpages=%lx num_hwpages=%lx ret=%x",
+ "pginfo=%p num_kpages=%lx num_hwpages=%lx ret=%i",
h_ret, shca, e_mr, iova_start, size, acl, e_pd,
hipzout.lkey, pginfo, pginfo->num_kpages,
pginfo->num_hwpages, ret);
}
ehca_reg_mr_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x shca=%p e_mr=%p "
+ ehca_err(&shca->ib_device, "ret=%i shca=%p e_mr=%p "
"iova_start=%p size=%lx acl=%x e_pd=%p pginfo=%p "
"num_kpages=%lx num_hwpages=%lx",
ret, shca, e_mr, iova_start, size, acl, e_pd, pginfo,
u32 i;
u64 *kpage;
+ if (!pginfo->num_hwpages) /* in case of fmr */
+ return 0;
+
kpage = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
if (!kpage) {
ehca_err(&shca->ib_device, "kpage alloc failed");
goto ehca_reg_mr_rpages_exit0;
}
- /* max 512 pages per shot */
+ /* max MAX_RPAGES ehca mr pages per register call */
for (i = 0; i < NUM_CHUNKS(pginfo->num_hwpages, MAX_RPAGES); i++) {
if (i == NUM_CHUNKS(pginfo->num_hwpages, MAX_RPAGES) - 1) {
ret = ehca_set_pagebuf(pginfo, rnum, kpage);
if (ret) {
ehca_err(&shca->ib_device, "ehca_set_pagebuf "
- "bad rc, ret=%x rnum=%x kpage=%p",
- ret, rnum, kpage);
+ "bad rc, ret=%i rnum=%x kpage=%p",
+ ret, rnum, kpage);
goto ehca_reg_mr_rpages_exit1;
}
} else
rpage = *kpage;
- h_ret = hipz_h_register_rpage_mr(shca->ipz_hca_handle, e_mr,
- 0, /* pagesize 4k */
- 0, rpage, rnum);
+ h_ret = hipz_h_register_rpage_mr(
+ shca->ipz_hca_handle, e_mr,
+ ehca_encode_hwpage_size(pginfo->hwpage_size),
+ 0, rpage, rnum);
if (i == NUM_CHUNKS(pginfo->num_hwpages, MAX_RPAGES) - 1) {
/*
*/
if (h_ret != H_SUCCESS) {
ehca_err(&shca->ib_device, "last "
- "hipz_reg_rpage_mr failed, h_ret=%lx "
+ "hipz_reg_rpage_mr failed, h_ret=%li "
"e_mr=%p i=%x hca_hndl=%lx mr_hndl=%lx"
" lkey=%x", h_ret, e_mr, i,
shca->ipz_hca_handle.handle,
ret = 0;
} else if (h_ret != H_PAGE_REGISTERED) {
ehca_err(&shca->ib_device, "hipz_reg_rpage_mr failed, "
- "h_ret=%lx e_mr=%p i=%x lkey=%x hca_hndl=%lx "
+ "h_ret=%li e_mr=%p i=%x lkey=%x hca_hndl=%lx "
"mr_hndl=%lx", h_ret, e_mr, i,
e_mr->ib.ib_mr.lkey,
shca->ipz_hca_handle.handle,
ehca_free_fw_ctrlblock(kpage);
ehca_reg_mr_rpages_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x shca=%p e_mr=%p pginfo=%p "
+ ehca_err(&shca->ib_device, "ret=%i shca=%p e_mr=%p pginfo=%p "
"num_kpages=%lx num_hwpages=%lx", ret, shca, e_mr,
pginfo, pginfo->num_kpages, pginfo->num_hwpages);
return ret;
struct ehca_mr_hipzout_parms hipzout;
ehca_mrmw_map_acl(acl, &hipz_acl);
- ehca_mrmw_set_pgsize_hipz_acl(&hipz_acl);
+ ehca_mrmw_set_pgsize_hipz_acl(pginfo->hwpage_size, &hipz_acl);
kpage = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
if (!kpage) {
* (MW bound or MR is shared)
*/
ehca_warn(&shca->ib_device, "hipz_h_reregister_pmr failed "
- "(Rereg1), h_ret=%lx e_mr=%p", h_ret, e_mr);
+ "(Rereg1), h_ret=%li e_mr=%p", h_ret, e_mr);
*pginfo = pginfo_save;
ret = -EAGAIN;
} else if ((u64 *)hipzout.vaddr != iova_start) {
*/
e_mr->num_kpages = pginfo->num_kpages;
e_mr->num_hwpages = pginfo->num_hwpages;
+ e_mr->hwpage_size = pginfo->hwpage_size;
e_mr->start = iova_start;
e_mr->size = size;
e_mr->acl = acl;
ehca_free_fw_ctrlblock(kpage);
ehca_rereg_mr_rereg1_exit0:
if ( ret && (ret != -EAGAIN) )
- ehca_err(&shca->ib_device, "ret=%x lkey=%x rkey=%x "
+ ehca_err(&shca->ib_device, "ret=%i lkey=%x rkey=%x "
"pginfo=%p num_kpages=%lx num_hwpages=%lx",
ret, *lkey, *rkey, pginfo, pginfo->num_kpages,
pginfo->num_hwpages);
h_ret = hipz_h_free_resource_mr(shca->ipz_hca_handle, e_mr);
if (h_ret != H_SUCCESS) {
ehca_err(&shca->ib_device, "hipz_free_mr failed, "
- "h_ret=%lx e_mr=%p hca_hndl=%lx mr_hndl=%lx "
+ "h_ret=%li e_mr=%p hca_hndl=%lx mr_hndl=%lx "
"mr->lkey=%x",
h_ret, e_mr, shca->ipz_hca_handle.handle,
e_mr->ipz_mr_handle.handle,
/* set some MR values */
e_mr->flags = save_mr.flags;
+ e_mr->hwpage_size = save_mr.hwpage_size;
e_mr->fmr_page_size = save_mr.fmr_page_size;
e_mr->fmr_max_pages = save_mr.fmr_max_pages;
e_mr->fmr_max_maps = save_mr.fmr_max_maps;
e_mr->fmr_map_cnt = save_mr.fmr_map_cnt;
ret = ehca_reg_mr(shca, e_mr, iova_start, size, acl,
- e_pd, pginfo, lkey, rkey);
+ e_pd, pginfo, lkey, rkey);
if (ret) {
u32 offset = (u64)(&e_mr->flags) - (u64)e_mr;
memcpy(&e_mr->flags, &(save_mr.flags),
ehca_rereg_mr_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x shca=%p e_mr=%p "
+ ehca_err(&shca->ib_device, "ret=%i shca=%p e_mr=%p "
"iova_start=%p size=%lx acl=%x e_pd=%p pginfo=%p "
"num_kpages=%lx lkey=%x rkey=%x rereg_1_hcall=%x "
"rereg_3_hcall=%x", ret, shca, e_mr, iova_start, size,
* FMRs are not shared and no MW bound to FMRs
*/
ehca_err(&shca->ib_device, "hipz_reregister_pmr failed "
- "(Rereg1), h_ret=%lx e_fmr=%p hca_hndl=%lx "
+ "(Rereg1), h_ret=%li e_fmr=%p hca_hndl=%lx "
"mr_hndl=%lx lkey=%x lkey_out=%x",
h_ret, e_fmr, shca->ipz_hca_handle.handle,
e_fmr->ipz_mr_handle.handle,
h_ret = hipz_h_free_resource_mr(shca->ipz_hca_handle, e_fmr);
if (h_ret != H_SUCCESS) {
ehca_err(&shca->ib_device, "hipz_free_mr failed, "
- "h_ret=%lx e_fmr=%p hca_hndl=%lx mr_hndl=%lx "
+ "h_ret=%li e_fmr=%p hca_hndl=%lx mr_hndl=%lx "
"lkey=%x",
h_ret, e_fmr, shca->ipz_hca_handle.handle,
e_fmr->ipz_mr_handle.handle,
/* set some MR values */
e_fmr->flags = save_fmr.flags;
+ e_fmr->hwpage_size = save_fmr.hwpage_size;
e_fmr->fmr_page_size = save_fmr.fmr_page_size;
e_fmr->fmr_max_pages = save_fmr.fmr_max_pages;
e_fmr->fmr_max_maps = save_fmr.fmr_max_maps;
memset(&pginfo, 0, sizeof(pginfo));
pginfo.type = EHCA_MR_PGI_FMR;
- pginfo.num_kpages = 0;
- pginfo.num_hwpages = 0;
ret = ehca_reg_mr(shca, e_fmr, NULL,
(e_fmr->fmr_max_pages * e_fmr->fmr_page_size),
e_fmr->acl, e_pd, &pginfo, &tmp_lkey,
u32 offset = (u64)(&e_fmr->flags) - (u64)e_fmr;
memcpy(&e_fmr->flags, &(save_mr.flags),
sizeof(struct ehca_mr) - offset);
- goto ehca_unmap_one_fmr_exit0;
}
ehca_unmap_one_fmr_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x tmp_lkey=%x tmp_rkey=%x "
+ ehca_err(&shca->ib_device, "ret=%i tmp_lkey=%x tmp_rkey=%x "
"fmr_max_pages=%x",
ret, tmp_lkey, tmp_rkey, e_fmr->fmr_max_pages);
return ret;
struct ehca_mr_hipzout_parms hipzout;
ehca_mrmw_map_acl(acl, &hipz_acl);
- ehca_mrmw_set_pgsize_hipz_acl(&hipz_acl);
+ ehca_mrmw_set_pgsize_hipz_acl(e_origmr->hwpage_size, &hipz_acl);
h_ret = hipz_h_register_smr(shca->ipz_hca_handle, e_newmr, e_origmr,
(u64)iova_start, hipz_acl, e_pd->fw_pd,
&hipzout);
if (h_ret != H_SUCCESS) {
- ehca_err(&shca->ib_device, "hipz_reg_smr failed, h_ret=%lx "
+ ehca_err(&shca->ib_device, "hipz_reg_smr failed, h_ret=%li "
"shca=%p e_origmr=%p e_newmr=%p iova_start=%p acl=%x "
"e_pd=%p hca_hndl=%lx mr_hndl=%lx lkey=%x",
h_ret, shca, e_origmr, e_newmr, iova_start, acl, e_pd,
/* successful registration */
e_newmr->num_kpages = e_origmr->num_kpages;
e_newmr->num_hwpages = e_origmr->num_hwpages;
+ e_newmr->hwpage_size = e_origmr->hwpage_size;
e_newmr->start = iova_start;
e_newmr->size = e_origmr->size;
e_newmr->acl = acl;
ehca_reg_smr_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x shca=%p e_origmr=%p "
+ ehca_err(&shca->ib_device, "ret=%i shca=%p e_origmr=%p "
"e_newmr=%p iova_start=%p acl=%x e_pd=%p",
ret, shca, e_origmr, e_newmr, iova_start, acl, e_pd);
return ret;
struct ib_phys_buf ib_pbuf;
u32 num_kpages;
u32 num_hwpages;
+ u64 hw_pgsize;
e_mr = ehca_mr_new();
if (!e_mr) {
ib_pbuf.size = size_maxmr;
num_kpages = NUM_CHUNKS(((u64)iova_start % PAGE_SIZE) + size_maxmr,
PAGE_SIZE);
- num_hwpages = NUM_CHUNKS(((u64)iova_start % EHCA_PAGESIZE) + size_maxmr,
- EHCA_PAGESIZE);
+ hw_pgsize = ehca_get_max_hwpage_size(shca);
+ num_hwpages = NUM_CHUNKS(((u64)iova_start % hw_pgsize) + size_maxmr,
+ hw_pgsize);
memset(&pginfo, 0, sizeof(pginfo));
pginfo.type = EHCA_MR_PGI_PHYS;
pginfo.num_kpages = num_kpages;
pginfo.num_hwpages = num_hwpages;
+ pginfo.hwpage_size = hw_pgsize;
pginfo.u.phy.num_phys_buf = 1;
pginfo.u.phy.phys_buf_array = &ib_pbuf;
ehca_mr_delete(e_mr);
ehca_reg_internal_maxmr_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x shca=%p e_pd=%p e_maxmr=%p",
+ ehca_err(&shca->ib_device, "ret=%i shca=%p e_pd=%p e_maxmr=%p",
ret, shca, e_pd, e_maxmr);
return ret;
} /* end ehca_reg_internal_maxmr() */
struct ehca_mr_hipzout_parms hipzout;
ehca_mrmw_map_acl(acl, &hipz_acl);
- ehca_mrmw_set_pgsize_hipz_acl(&hipz_acl);
+ ehca_mrmw_set_pgsize_hipz_acl(e_origmr->hwpage_size, &hipz_acl);
h_ret = hipz_h_register_smr(shca->ipz_hca_handle, e_newmr, e_origmr,
(u64)iova_start, hipz_acl, e_pd->fw_pd,
&hipzout);
if (h_ret != H_SUCCESS) {
- ehca_err(&shca->ib_device, "hipz_reg_smr failed, h_ret=%lx "
+ ehca_err(&shca->ib_device, "hipz_reg_smr failed, h_ret=%li "
"e_origmr=%p hca_hndl=%lx mr_hndl=%lx lkey=%x",
h_ret, e_origmr, shca->ipz_hca_handle.handle,
e_origmr->ipz_mr_handle.handle,
/* successful registration */
e_newmr->num_kpages = e_origmr->num_kpages;
e_newmr->num_hwpages = e_origmr->num_hwpages;
+ e_newmr->hwpage_size = e_origmr->hwpage_size;
e_newmr->start = iova_start;
e_newmr->size = e_origmr->size;
e_newmr->acl = acl;
ret = ehca_dereg_mr(&e_maxmr->ib.ib_mr);
if (ret) {
ehca_err(&shca->ib_device, "dereg internal max-MR failed, "
- "ret=%x e_maxmr=%p shca=%p lkey=%x",
+ "ret=%i e_maxmr=%p shca=%p lkey=%x",
ret, e_maxmr, shca, e_maxmr->ib.ib_mr.lkey);
shca->maxmr = e_maxmr;
goto ehca_dereg_internal_maxmr_exit0;
ehca_dereg_internal_maxmr_exit0:
if (ret)
- ehca_err(&shca->ib_device, "ret=%x shca=%p shca->maxmr=%p",
+ ehca_err(&shca->ib_device, "ret=%i shca=%p shca->maxmr=%p",
ret, shca, shca->maxmr);
return ret;
} /* end ehca_dereg_internal_maxmr() */
u64 pgaddr;
u32 i = 0;
u32 j = 0;
+ int hwpages_per_kpage = PAGE_SIZE / pginfo->hwpage_size;
/* loop over desired chunk entries */
chunk = pginfo->u.usr.next_chunk;
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 *
- EHCA_PAGESIZE));
+ pginfo->hwpage_size));
if ( !(*kpage) ) {
ehca_gen_err("pgaddr=%lx "
"chunk->page_list[i]=%lx "
(pginfo->hwpage_cnt)++;
(pginfo->next_hwpage)++;
kpage++;
- if (pginfo->next_hwpage %
- (PAGE_SIZE / EHCA_PAGESIZE) == 0) {
+ if (pginfo->next_hwpage % hwpages_per_kpage == 0) {
(pginfo->kpage_cnt)++;
(pginfo->u.usr.next_nmap)++;
pginfo->next_hwpage = 0;
return ret;
}
+/*
+ * check given pages for contiguous layout
+ * last page addr is returned in prev_pgaddr for further check
+ */
+static int ehca_check_kpages_per_ate(struct scatterlist *page_list,
+ int start_idx, int end_idx,
+ u64 *prev_pgaddr)
+{
+ int t;
+ for (t = start_idx; t <= end_idx; t++) {
+ 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) {
+ ehca_gen_err("uncontiguous page found pgaddr=%lx "
+ "prev_pgaddr=%lx page_list_i=%x",
+ pgaddr, *prev_pgaddr, t);
+ return -EINVAL;
+ }
+ *prev_pgaddr = pgaddr;
+ }
+ return 0;
+}
+
+/* PAGE_SIZE < pginfo->hwpage_size */
+static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
+ u32 number,
+ u64 *kpage)
+{
+ int ret = 0;
+ struct ib_umem_chunk *prev_chunk;
+ struct ib_umem_chunk *chunk;
+ u64 pgaddr, prev_pgaddr;
+ u32 i = 0;
+ u32 j = 0;
+ int kpages_per_hwpage = pginfo->hwpage_size / PAGE_SIZE;
+ int nr_kpages = kpages_per_hwpage;
+
+ /* loop over desired chunk entries */
+ chunk = pginfo->u.usr.next_chunk;
+ prev_chunk = pginfo->u.usr.next_chunk;
+ list_for_each_entry_continue(
+ 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(sg_page(&chunk->page_list[i]))
+ << PAGE_SHIFT );
+ *kpage = phys_to_abs(pgaddr);
+ if ( !(*kpage) ) {
+ ehca_gen_err("pgaddr=%lx i=%x",
+ pgaddr, i);
+ ret = -EFAULT;
+ return ret;
+ }
+ /*
+ * The first page in a hwpage must be aligned;
+ * the first MR page is exempt from this rule.
+ */
+ if (pgaddr & (pginfo->hwpage_size - 1)) {
+ if (pginfo->hwpage_cnt) {
+ ehca_gen_err(
+ "invalid alignment "
+ "pgaddr=%lx i=%x "
+ "mr_pgsize=%lx",
+ pgaddr, i,
+ pginfo->hwpage_size);
+ ret = -EFAULT;
+ return ret;
+ }
+ /* first MR page */
+ pginfo->kpage_cnt =
+ (pgaddr &
+ (pginfo->hwpage_size - 1)) >>
+ PAGE_SHIFT;
+ nr_kpages -= pginfo->kpage_cnt;
+ *kpage = phys_to_abs(
+ pgaddr &
+ ~(pginfo->hwpage_size - 1));
+ }
+ ehca_gen_dbg("kpage=%lx chunk_page=%lx "
+ "value=%016lx", *kpage, pgaddr,
+ *(u64 *)abs_to_virt(
+ phys_to_abs(pgaddr)));
+ prev_pgaddr = pgaddr;
+ i++;
+ pginfo->kpage_cnt++;
+ pginfo->u.usr.next_nmap++;
+ nr_kpages--;
+ if (!nr_kpages)
+ goto next_kpage;
+ continue;
+ }
+ if (i + nr_kpages > chunk->nmap) {
+ ret = ehca_check_kpages_per_ate(
+ chunk->page_list, i,
+ chunk->nmap - 1, &prev_pgaddr);
+ if (ret) return ret;
+ pginfo->kpage_cnt += chunk->nmap - i;
+ pginfo->u.usr.next_nmap += chunk->nmap - i;
+ nr_kpages -= chunk->nmap - i;
+ break;
+ }
+
+ ret = ehca_check_kpages_per_ate(chunk->page_list, i,
+ i + nr_kpages - 1,
+ &prev_pgaddr);
+ if (ret) return ret;
+ i += nr_kpages;
+ pginfo->kpage_cnt += nr_kpages;
+ pginfo->u.usr.next_nmap += nr_kpages;
+next_kpage:
+ nr_kpages = kpages_per_hwpage;
+ (pginfo->hwpage_cnt)++;
+ kpage++;
+ j++;
+ if (j >= number) break;
+ }
+ if ((pginfo->u.usr.next_nmap >= chunk->nmap) &&
+ (j >= number)) {
+ pginfo->u.usr.next_nmap = 0;
+ prev_chunk = chunk;
+ break;
+ } else if (pginfo->u.usr.next_nmap >= chunk->nmap) {
+ pginfo->u.usr.next_nmap = 0;
+ prev_chunk = chunk;
+ } else if (j >= number)
+ break;
+ else
+ prev_chunk = chunk;
+ }
+ pginfo->u.usr.next_chunk =
+ list_prepare_entry(prev_chunk,
+ (&(pginfo->u.usr.region->chunk_list)),
+ list);
+ return ret;
+}
+
int ehca_set_pagebuf_phys(struct ehca_mr_pginfo *pginfo,
u32 number,
u64 *kpage)
/* loop over desired phys_buf_array entries */
while (i < number) {
pbuf = pginfo->u.phy.phys_buf_array + pginfo->u.phy.next_buf;
- num_hw = NUM_CHUNKS((pbuf->addr % EHCA_PAGESIZE) +
- pbuf->size, EHCA_PAGESIZE);
- offs_hw = (pbuf->addr & ~PAGE_MASK) / EHCA_PAGESIZE;
+ num_hw = NUM_CHUNKS((pbuf->addr % pginfo->hwpage_size) +
+ pbuf->size, pginfo->hwpage_size);
+ offs_hw = (pbuf->addr & ~(pginfo->hwpage_size - 1)) /
+ pginfo->hwpage_size;
while (pginfo->next_hwpage < offs_hw + num_hw) {
/* sanity check */
if ((pginfo->kpage_cnt >= pginfo->num_kpages) ||
return -EFAULT;
}
*kpage = phys_to_abs(
- (pbuf->addr & EHCA_PAGEMASK)
- + (pginfo->next_hwpage * EHCA_PAGESIZE));
+ (pbuf->addr & ~(pginfo->hwpage_size - 1)) +
+ (pginfo->next_hwpage * pginfo->hwpage_size));
if ( !(*kpage) && pbuf->addr ) {
- ehca_gen_err("pbuf->addr=%lx "
- "pbuf->size=%lx "
+ ehca_gen_err("pbuf->addr=%lx pbuf->size=%lx "
"next_hwpage=%lx", pbuf->addr,
- pbuf->size,
- pginfo->next_hwpage);
+ pbuf->size, pginfo->next_hwpage);
return -EFAULT;
}
(pginfo->hwpage_cnt)++;
(pginfo->next_hwpage)++;
- if (pginfo->next_hwpage %
- (PAGE_SIZE / EHCA_PAGESIZE) == 0)
- (pginfo->kpage_cnt)++;
+ if (PAGE_SIZE >= pginfo->hwpage_size) {
+ if (pginfo->next_hwpage %
+ (PAGE_SIZE / pginfo->hwpage_size) == 0)
+ (pginfo->kpage_cnt)++;
+ } else
+ pginfo->kpage_cnt += pginfo->hwpage_size /
+ PAGE_SIZE;
kpage++;
i++;
if (i >= number) break;
/* loop over desired page_list entries */
fmrlist = pginfo->u.fmr.page_list + pginfo->u.fmr.next_listelem;
for (i = 0; i < number; i++) {
- *kpage = phys_to_abs((*fmrlist & EHCA_PAGEMASK) +
- pginfo->next_hwpage * EHCA_PAGESIZE);
+ *kpage = phys_to_abs((*fmrlist & ~(pginfo->hwpage_size - 1)) +
+ pginfo->next_hwpage * pginfo->hwpage_size);
if ( !(*kpage) ) {
ehca_gen_err("*fmrlist=%lx fmrlist=%p "
"next_listelem=%lx next_hwpage=%lx",
return -EFAULT;
}
(pginfo->hwpage_cnt)++;
- (pginfo->next_hwpage)++;
- kpage++;
- if (pginfo->next_hwpage %
- (pginfo->u.fmr.fmr_pgsize / EHCA_PAGESIZE) == 0) {
- (pginfo->kpage_cnt)++;
- (pginfo->u.fmr.next_listelem)++;
- fmrlist++;
- pginfo->next_hwpage = 0;
+ if (pginfo->u.fmr.fmr_pgsize >= pginfo->hwpage_size) {
+ if (pginfo->next_hwpage %
+ (pginfo->u.fmr.fmr_pgsize /
+ pginfo->hwpage_size) == 0) {
+ (pginfo->kpage_cnt)++;
+ (pginfo->u.fmr.next_listelem)++;
+ fmrlist++;
+ pginfo->next_hwpage = 0;
+ } else
+ (pginfo->next_hwpage)++;
+ } else {
+ unsigned int cnt_per_hwpage = pginfo->hwpage_size /
+ pginfo->u.fmr.fmr_pgsize;
+ unsigned int j;
+ u64 prev = *kpage;
+ /* check if adrs are contiguous */
+ for (j = 1; j < cnt_per_hwpage; j++) {
+ u64 p = phys_to_abs(fmrlist[j] &
+ ~(pginfo->hwpage_size - 1));
+ if (prev + pginfo->u.fmr.fmr_pgsize != p) {
+ ehca_gen_err("uncontiguous fmr pages "
+ "found prev=%lx p=%lx "
+ "idx=%x", prev, p, i + j);
+ return -EINVAL;
+ }
+ prev = p;
+ }
+ pginfo->kpage_cnt += cnt_per_hwpage;
+ pginfo->u.fmr.next_listelem += cnt_per_hwpage;
+ fmrlist += cnt_per_hwpage;
}
+ kpage++;
}
return ret;
}
ret = ehca_set_pagebuf_phys(pginfo, number, kpage);
break;
case EHCA_MR_PGI_USER:
- ret = ehca_set_pagebuf_user1(pginfo, number, kpage);
+ ret = PAGE_SIZE >= pginfo->hwpage_size ?
+ ehca_set_pagebuf_user1(pginfo, number, kpage) :
+ ehca_set_pagebuf_user2(pginfo, number, kpage);
break;
case EHCA_MR_PGI_FMR:
ret = ehca_set_pagebuf_fmr(pginfo, number, kpage);
/*----------------------------------------------------------------------*/
/* sets page size in hipz access control for MR/MW. */
-void ehca_mrmw_set_pgsize_hipz_acl(u32 *hipz_acl) /*INOUT*/
+void ehca_mrmw_set_pgsize_hipz_acl(u32 pgsize, u32 *hipz_acl) /*INOUT*/
{
- return; /* HCA supports only 4k */
+ *hipz_acl |= (ehca_encode_hwpage_size(pgsize) << 24);
} /* end ehca_mrmw_set_pgsize_hipz_acl() */
/*----------------------------------------------------------------------*/
mr_cache = kmem_cache_create("ehca_cache_mr",
sizeof(struct ehca_mr), 0,
SLAB_HWCACHE_ALIGN,
- NULL, NULL);
+ NULL);
if (!mr_cache)
return -ENOMEM;
mw_cache = kmem_cache_create("ehca_cache_mw",
sizeof(struct ehca_mw), 0,
SLAB_HWCACHE_ALIGN,
- NULL, NULL);
+ NULL);
if (!mw_cache) {
kmem_cache_destroy(mr_cache);
mr_cache = NULL;
projects / GitHub / mt8127 / android_kernel_alcatel_ttab.git / blobdiff