/*
* Copyright (c) 2009-2010 Chelsio, Inc. 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/module.h>
#include <linux/moduleparam.h>
#include <rdma/ib_umem.h>
#include <linux/atomic.h>
#include "iw_cxgb4.h"
int use_dsgl = 0;
module_param(use_dsgl, int, 0644);
MODULE_PARM_DESC(use_dsgl, "Use DSGL for PBL/FastReg (default=0)");
#define T4_ULPTX_MIN_IO 32
#define C4IW_MAX_INLINE_SIZE 96
#define T4_ULPTX_MAX_DMA 1024
#define C4IW_INLINE_THRESHOLD 128
static int inline_threshold = C4IW_INLINE_THRESHOLD;
module_param(inline_threshold, int, 0644);
MODULE_PARM_DESC(inline_threshold, "inline vs dsgl threshold (default=128)");
static int mr_exceeds_hw_limits(struct c4iw_dev *dev, u64 length)
{
return (is_t4(dev->rdev.lldi.adapter_type) ||
is_t5(dev->rdev.lldi.adapter_type)) &&
length >= 8*1024*1024*1024ULL;
}
static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr,
u32 len, dma_addr_t data, int wait)
{
struct sk_buff *skb;
struct ulp_mem_io *req;
struct ulptx_sgl *sgl;
u8 wr_len;
int ret = 0;
struct c4iw_wr_wait wr_wait;
addr &= 0x7FFFFFF;
if (wait)
c4iw_init_wr_wait(&wr_wait);
wr_len = roundup(sizeof(*req) + sizeof(*sgl), 16);
skb = alloc_skb(wr_len, GFP_KERNEL | __GFP_NOFAIL);
if (!skb)
return -ENOMEM;
set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);
req = (struct ulp_mem_io *)__skb_put(skb, wr_len);
memset(req, 0, wr_len);
INIT_ULPTX_WR(req, wr_len, 0, 0);
req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) |
(wait ? FW_WR_COMPL_F : 0));
req->wr.wr_lo = wait ? (__force __be64)(unsigned long) &wr_wait : 0L;
req->wr.wr_mid = cpu_to_be32(FW_WR_LEN16_V(DIV_ROUND_UP(wr_len, 16)));
req->cmd = cpu_to_be32(ULPTX_CMD_V(ULP_TX_MEM_WRITE));
req->cmd |= cpu_to_be32(T5_ULP_MEMIO_ORDER_V(1));
req->dlen = cpu_to_be32(ULP_MEMIO_DATA_LEN_V(len>>5));
req->len16 = cpu_to_be32(DIV_ROUND_UP(wr_len-sizeof(req->wr), 16));
req->lock_addr = cpu_to_be32(ULP_MEMIO_ADDR_V(addr));
sgl = (struct ulptx_sgl *)(req + 1);
sgl->cmd_nsge = cpu_to_be32(ULPTX_CMD_V(ULP_TX_SC_DSGL) |
ULPTX_NSGE_V(1));
sgl->len0 = cpu_to_be32(len);
sgl->addr0 = cpu_to_be64(data);
ret = c4iw_ofld_send(rdev, skb);
if (ret)
return ret;
if (wait)
ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
return ret;
}
static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len,
void *data)
{
struct sk_buff *skb;
struct ulp_mem_io *req;
struct ulptx_idata *sc;
u8 wr_len, *to_dp, *from_dp;
int copy_len, num_wqe, i, ret = 0;
struct c4iw_wr_wait wr_wait;
__be32 cmd = cpu_to_be32(ULPTX_CMD_V(ULP_TX_MEM_WRITE));
if (is_t4(rdev->lldi.adapter_type))
cmd |= cpu_to_be32(ULP_MEMIO_ORDER_F);
else
cmd |= cpu_to_be32(T5_ULP_MEMIO_IMM_F);
addr &= 0x7FFFFFF;
PDBG("%s addr 0x%x len %u\n", __func__, addr, len);
num_wqe = DIV_ROUND_UP(len, C4IW_MAX_INLINE_SIZE);
c4iw_init_wr_wait(&wr_wait);
for (i