blob: 761d3ce6a63a0a2cc31e8ed5787dc35c13881d58 [file] [log] [blame]
/*
* Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/slab.h>
#include <rdma/ib_user_verbs.h>
#include "mlx4_ib.h"
static u32 convert_access(int acc)
{
return (acc & IB_ACCESS_REMOTE_ATOMIC ? MLX4_PERM_ATOMIC : 0) |
(acc & IB_ACCESS_REMOTE_WRITE ? MLX4_PERM_REMOTE_WRITE : 0) |
(acc & IB_ACCESS_REMOTE_READ ? MLX4_PERM_REMOTE_READ : 0) |
(acc & IB_ACCESS_LOCAL_WRITE ? MLX4_PERM_LOCAL_WRITE : 0) |
(acc & IB_ACCESS_MW_BIND ? MLX4_PERM_BIND_MW : 0) |
MLX4_PERM_LOCAL_READ;
}
static enum mlx4_mw_type to_mlx4_type(enum ib_mw_type type)
{
switch (type) {
case IB_MW_TYPE_1: return MLX4_MW_TYPE_1;
case IB_MW_TYPE_2: return MLX4_MW_TYPE_2;
default: return -1;
}
}
struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
{
struct mlx4_ib_mr *mr;
int err;
mr = kzalloc(sizeof(*mr), GFP_KERNEL);
if (!mr)
return ERR_PTR(-ENOMEM);
err = mlx4_mr_alloc(to_mdev(pd->device)->dev, to_mpd(pd)->pdn, 0,
~0ull, convert_access(acc), 0, 0, &mr->mmr);
if (err)
goto err_free;
err = mlx4_mr_enable(to_mdev(pd->device)->dev, &mr->mmr);
if (err)
goto err_mr;
mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
mr->umem = NULL;
return &mr->ibmr;
err_mr:
(void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
err_free:
kfree(mr);
return ERR_PTR(err);
}
int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
struct ib_umem *umem)
{
u64 *pages;
int i, k, entry;
int n;
int len;
int err = 0;
struct scatterlist *sg;
pages = (u64 *) __get_free_page(GFP_KERNEL);
if (!pages)
return -ENOMEM;
i = n = 0;
for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
len = sg_dma_len(sg) >> mtt->page_shift;
for (k = 0; k < len; ++k) {
pages[i++] = sg_dma_address(sg) +
(k << umem->page_shift);
/*
* Be friendly to mlx4_write_mtt() and
* pass it chunks of appropriate size.
*/
if (i == PAGE_SIZE / sizeof (u64)) {
err = mlx4_write_mtt(dev->dev, mtt, n,
i, pages);
if (err)
goto out;
n += i;
i = 0;
}
}
}
if (i)
err = mlx4_write_mtt(dev->dev, mtt, n, i, pages);
out:
free_page((unsigned long) pages);
return err;
}
static struct ib_umem *mlx4_get_umem_mr(struct ib_ucontext *context, u64 start,
u64 length, u64 virt_addr,
int access_flags)
{
/*
* Force registering the memory as writable if the underlying pages
* are writable. This is so rereg can change the access permissions
* from readable to writable without having to run through ib_umem_get
* again
*/
if (!ib_access_writable(access_flags)) {
struct vm_area_struct *vma;
down_read(&current->mm->mmap_sem);
/*
* FIXME: Ideally this would iterate over all the vmas that
* cover the memory, but for now it requires a single vma to
* entirely cover the MR to support RO mappings.
*/
vma = find_vma(current->mm, start);
if (vma && vma->vm_end >= start + length &&
vma->vm_start <= start) {
if (vma->vm_flags & VM_WRITE)
access_flags |= IB_ACCESS_LOCAL_WRITE;
} else {
access_flags |= IB_ACCESS_LOCAL_WRITE;
}
up_read(&current->mm->mmap_sem);
}
return ib_umem_get(context, start, length, access_flags, 0);
}
struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int access_flags,
struct ib_udata *udata)
{
struct mlx4_ib_dev *dev = to_mdev(pd->device);
struct mlx4_ib_mr *mr;
int shift;
int err;
int n;
mr = kzalloc(sizeof(*mr), GFP_KERNEL);
if (!mr)
return ERR_PTR(-ENOMEM);
mr->umem = mlx4_get_umem_mr(pd->uobject->context, start, length,
virt_addr, access_flags);
if (IS_ERR(mr->umem)) {
err = PTR_ERR(mr->umem);
goto err_free;
}
n = ib_umem_page_count(mr->umem);
shift = mr->umem->page_shift;
err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, virt_addr, length,
convert_access(access_flags), n, shift, &mr->mmr);
if (err)
goto err_umem;
err = mlx4_ib_umem_write_mtt(dev, &mr->mmr.mtt, mr->umem);
if (err)
goto err_mr;
err = mlx4_mr_enable(dev->dev, &mr->mmr);
if (err)
goto err_mr;
mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
return &mr->ibmr;
err_mr:
(void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
err_umem:
ib_umem_release(mr->umem);
err_free:
kfree(mr);
return ERR_PTR(err);
}
int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
u64 start, u64 length, u64 virt_addr,
int mr_access_flags, struct ib_pd *pd,
struct ib_udata *udata)
{
struct mlx4_ib_dev *dev = to_mdev(mr->device);
struct mlx4_ib_mr *mmr = to_mmr(mr);
struct mlx4_mpt_entry *mpt_entry;
struct mlx4_mpt_entry **pmpt_entry = &mpt_entry;
int err;
/* Since we synchronize this call and mlx4_ib_dereg_mr via uverbs,
* we assume that the calls can't run concurrently. Otherwise, a
* race exists.
*/
err = mlx4_mr_hw_get_mpt(dev->dev, &mmr->mmr, &pmpt_entry);
if (err)
return err;
if (flags & IB_MR_REREG_PD) {
err = mlx4_mr_hw_change_pd(dev->dev, *pmpt_entry,
to_mpd(pd)->pdn);
if (err)
goto release_mpt_entry;
}
if (flags & IB_MR_REREG_ACCESS) {
if (ib_access_writable(mr_access_flags) &&
!mmr->umem->writable) {
err = -EPERM;
goto release_mpt_entry;
}
err = mlx4_mr_hw_change_access(dev->dev, *pmpt_entry,
convert_access(mr_access_flags));
if (err)
goto release_mpt_entry;
}
if (flags & IB_MR_REREG_TRANS) {
int shift;
int n;
mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);
ib_umem_release(mmr->umem);
mmr->umem =
mlx4_get_umem_mr(mr->uobject->context, start, length,
virt_addr, mr_access_flags);
if (IS_ERR(mmr->umem)) {
err = PTR_ERR(mmr->umem);
/* Prevent mlx4_ib_dereg_mr from free'ing invalid pointer */
mmr->umem = NULL;
goto release_mpt_entry;
}
n = ib_umem_page_count(mmr->umem);
shift = mmr->umem->page_shift;
err = mlx4_mr_rereg_mem_write(dev->dev, &mmr->mmr,
virt_addr, length, n, shift,
*pmpt_entry);
if (err) {
ib_umem_release(mmr->umem);
goto release_mpt_entry;
}
mmr->mmr.iova = virt_addr;
mmr->mmr.size = length;
err = mlx4_ib_umem_write_mtt(dev, &mmr->mmr.mtt, mmr->umem);
if (err) {
mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);
ib_umem_release(mmr->umem);
goto release_mpt_entry;
}
}
/* If we couldn't transfer the MR to the HCA, just remember to
* return a failure. But dereg_mr will free the resources.
*/
err = mlx4_mr_hw_write_mpt(dev->dev, &mmr->mmr, pmpt_entry);
if (!err && flags & IB_MR_REREG_ACCESS)
mmr->mmr.access = mr_access_flags;
release_mpt_entry:
mlx4_mr_hw_put_mpt(dev->dev, pmpt_entry);
return err;
}
static int
mlx4_alloc_priv_pages(struct ib_device *device,
struct mlx4_ib_mr *mr,
int max_pages)
{
int ret;
/* Ensure that size is aligned to DMA cacheline
* requirements.
* max_pages is limited to MLX4_MAX_FAST_REG_PAGES
* so page_map_size will never cross PAGE_SIZE.
*/
mr->page_map_size = roundup(max_pages * sizeof(u64),
MLX4_MR_PAGES_ALIGN);
/* Prevent cross page boundary allocation. */
mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL);
if (!mr->pages)
return -ENOMEM;
mr->page_map = dma_map_single(device->dev.parent, mr->pages,
mr->page_map_size, DMA_TO_DEVICE);
if (dma_mapping_error(device->dev.parent, mr->page_map)) {
ret = -ENOMEM;
goto err;
}
return 0;
err:
free_page((unsigned long)mr->pages);
return ret;
}
static void
mlx4_free_priv_pages(struct mlx4_ib_mr *mr)
{
if (mr->pages) {
struct ib_device *device = mr->ibmr.device;
dma_unmap_single(device->dev.parent, mr->page_map,
mr->page_map_size, DMA_TO_DEVICE);
free_page((unsigned long)mr->pages);
mr->pages = NULL;
}
}
int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
{
struct mlx4_ib_mr *mr = to_mmr(ibmr);
int ret;
mlx4_free_priv_pages(mr);
ret = mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
if (ret)
return ret;
if (mr->umem)
ib_umem_release(mr->umem);
kfree(mr);
return 0;
}
struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
struct ib_udata *udata)
{
struct mlx4_ib_dev *dev = to_mdev(pd->device);
struct mlx4_ib_mw *mw;
int err;
mw = kmalloc(sizeof(*mw), GFP_KERNEL);
if (!mw)
return ERR_PTR(-ENOMEM);
err = mlx4_mw_alloc(dev->dev, to_mpd(pd)->pdn,
to_mlx4_type(type), &mw->mmw);
if (err)
goto err_free;
err = mlx4_mw_enable(dev->dev, &mw->mmw);
if (err)
goto err_mw;
mw->ibmw.rkey = mw->mmw.key;
return &mw->ibmw;
err_mw:
mlx4_mw_free(dev->dev, &mw->mmw);
err_free:
kfree(mw);
return ERR_PTR(err);
}
int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
{
struct mlx4_ib_mw *mw = to_mmw(ibmw);
mlx4_mw_free(to_mdev(ibmw->device)->dev, &mw->mmw);
kfree(mw);
return 0;
}
struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
enum ib_mr_type mr_type,
u32 max_num_sg)
{
struct mlx4_ib_dev *dev = to_mdev(pd->device);
struct mlx4_ib_mr *mr;
int err;
if (mr_type != IB_MR_TYPE_MEM_REG ||
max_num_sg > MLX4_MAX_FAST_REG_PAGES)
return ERR_PTR(-EINVAL);
mr = kzalloc(sizeof(*mr), GFP_KERNEL);
if (!mr)
return ERR_PTR(-ENOMEM);
err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, 0, 0, 0,
max_num_sg, 0, &mr->mmr);
if (err)
goto err_free;
err = mlx4_alloc_priv_pages(pd->device, mr, max_num_sg);
if (err)
goto err_free_mr;
mr->max_pages = max_num_sg;
err = mlx4_mr_enable(dev->dev, &mr->mmr);
if (err)
goto err_free_pl;
mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
mr->umem = NULL;
return &mr->ibmr;
err_free_pl:
mr->ibmr.device = pd->device;
mlx4_free_priv_pages(mr);
err_free_mr:
(void) mlx4_mr_free(dev->dev, &mr->mmr);
err_free:
kfree(mr);
return ERR_PTR(err);
}
struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc,
struct ib_fmr_attr *fmr_attr)
{
struct mlx4_ib_dev *dev = to_mdev(pd->device);
struct mlx4_ib_fmr *fmr;
int err = -ENOMEM;
fmr = kmalloc(sizeof *fmr, GFP_KERNEL);
if (!fmr)
return ERR_PTR(-ENOMEM);
err = mlx4_fmr_alloc(dev->dev, to_mpd(pd)->pdn, convert_access(acc),
fmr_attr->max_pages, fmr_attr->max_maps,
fmr_attr->page_shift, &fmr->mfmr);
if (err)
goto err_free;
err = mlx4_fmr_enable(to_mdev(pd->device)->dev, &fmr->mfmr);
if (err)
goto err_mr;
fmr->ibfmr.rkey = fmr->ibfmr.lkey = fmr->mfmr.mr.key;
return &fmr->ibfmr;
err_mr:
(void) mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);
err_free:
kfree(fmr);
return ERR_PTR(err);
}
int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
int npages, u64 iova)
{
struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
struct mlx4_ib_dev *dev = to_mdev(ifmr->ibfmr.device);
return mlx4_map_phys_fmr(dev->dev, &ifmr->mfmr, page_list, npages, iova,
&ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
}
int mlx4_ib_unmap_fmr(struct list_head *fmr_list)
{
struct ib_fmr *ibfmr;
int err;
struct mlx4_dev *mdev = NULL;
list_for_each_entry(ibfmr, fmr_list, list) {
if (mdev && to_mdev(ibfmr->device)->dev != mdev)
return -EINVAL;
mdev = to_mdev(ibfmr->device)->dev;
}
if (!mdev)
return 0;
list_for_each_entry(ibfmr, fmr_list, list) {
struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
mlx4_fmr_unmap(mdev, &ifmr->mfmr, &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
}
/*
* Make sure all MPT status updates are visible before issuing
* SYNC_TPT firmware command.
*/
wmb();
err = mlx4_SYNC_TPT(mdev);
if (err)
pr_warn("SYNC_TPT error %d when "
"unmapping FMRs\n", err);
return 0;
}
int mlx4_ib_fmr_dealloc(struct ib_fmr *ibfmr)
{
struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
struct mlx4_ib_dev *dev = to_mdev(ibfmr->device);
int err;
err = mlx4_fmr_free(dev->dev, &ifmr->mfmr);
if (!err)
kfree(ifmr);
return err;
}
static int mlx4_set_page(struct ib_mr *ibmr, u64 addr)
{
struct mlx4_ib_mr *mr = to_mmr(ibmr);
if (unlikely(mr->npages == mr->max_pages))
return -ENOMEM;
mr->pages[mr->npages++] = cpu_to_be64(addr | MLX4_MTT_FLAG_PRESENT);
return 0;
}
int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
unsigned int *sg_offset)
{
struct mlx4_ib_mr *mr = to_mmr(ibmr);
int rc;
mr->npages = 0;
ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
mr->page_map_size, DMA_TO_DEVICE);
rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page);
ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
mr->page_map_size, DMA_TO_DEVICE);
return rc;
}