2d381f800f
The old BTL interface provided support for RDMA through the use of the btl_prepare_src and btl_prepare_dst functions. These functions were expected to prepare as much of the user buffer as possible for the RDMA operation and return a descriptor. The descriptor contained segment information on the prepared region. The btl user could then pass the RDMA segment information to a remote peer. Once the peer received that information it then packed it into a similar descriptor on the other side that could then be passed into a single btl_put or btl_get operation. Changes: - Removed the btl_prepare_dst function. This reflects the fact that RDMA operations no longer depend on "prepared" descriptors. - Removed the btl_seg_size member. There is no need to btl's to subclass the mca_btl_base_segment_t class anymore. ... Add more
140 строки
4.8 KiB
C
140 строки
4.8 KiB
C
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
|
|
/*
|
|
* Copyright (c) 2010-2014 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
* Copyright (c) 2014 Research Organization for Information Science
|
|
* and Technology (RIST). All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "opal_config.h"
|
|
|
|
#include "btl_vader.h"
|
|
#include "btl_vader_frag.h"
|
|
#include "btl_vader_endpoint.h"
|
|
#include "btl_vader_xpmem.h"
|
|
|
|
#if OPAL_BTL_VADER_HAVE_CMA
|
|
#include <sys/uio.h>
|
|
|
|
#if OPAL_CMA_NEED_SYSCALL_DEFS
|
|
#include "opal/sys/cma.h"
|
|
#endif /* OPAL_CMA_NEED_SYSCALL_DEFS */
|
|
|
|
#endif
|
|
|
|
/**
|
|
* Initiate an synchronous put.
|
|
*
|
|
* @param btl (IN) BTL module
|
|
* @param endpoint (IN) BTL addressing information
|
|
* @param descriptor (IN) Description of the data to be transferred
|
|
*/
|
|
#if OPAL_BTL_VADER_HAVE_XPMEM
|
|
int mca_btl_vader_put (struct mca_btl_base_module_t *btl, struct mca_btl_base_endpoint_t *endpoint,
|
|
void *local_address, uint64_t remote_address,
|
|
struct mca_btl_base_registration_handle_t *local_handle,
|
|
struct mca_btl_base_registration_handle_t *remote_handle, size_t size, int flags,
|
|
mca_btl_base_rdma_completion_fn_t cbfunc, void *cbcontext, void *cbdata)
|
|
{
|
|
mca_mpool_base_registration_t *reg;
|
|
void *rem_ptr;
|
|
|
|
reg = vader_get_registation (endpoint, (void *)(intptr_t) remote_address, size, 0, &rem_ptr);
|
|
if (OPAL_UNLIKELY(NULL == reg)) {
|
|
return OPAL_ERROR;
|
|
}
|
|
|
|
vader_memmove (rem_ptr, local_address, size);
|
|
|
|
vader_return_registration (reg, endpoint);
|
|
|
|
/* always call the callback function */
|
|
cbfunc (btl, endpoint, local_address, local_handle, cbcontext, cbdata, OPAL_SUCCESS);
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|
|
#endif
|
|
|
|
#if OPAL_BTL_VADER_HAVE_CMA
|
|
int mca_btl_vader_put_cma (struct mca_btl_base_module_t *btl,
|
|
struct mca_btl_base_endpoint_t *endpoint,
|
|
struct mca_btl_base_descriptor_t *des)
|
|
{
|
|
struct iovec src_iov = {.iov_base = local_address, .iov_len = size};
|
|
struct iovec dst_iov = {.iov_base = (void *)(intptr_t) remote_address, .iov_len = size};
|
|
ssize_t ret;
|
|
|
|
ret = process_vm_writev (endpoint->segment_data.other.seg_ds->seg_cpid, &src_iov, 1, &dst_iov, 1, 0);
|
|
if (ret != (ssize_t)size) {
|
|
opal_output(0, "Wrote %ld, expected %lu, errno = %d\n", (long)ret, (unsigned long)size, errno);
|
|
return OPAL_ERROR;
|
|
}
|
|
|
|
/* always call the callback function */
|
|
frag->base.des_flags |= MCA_BTL_DES_SEND_ALWAYS_CALLBACK;
|
|
|
|
frag->endpoint = endpoint;
|
|
mca_btl_vader_frag_complete (frag);
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|
|
#endif
|
|
|
|
#if OPAL_BTL_VADER_HAVE_KNEM
|
|
int mca_btl_vader_put_knem (struct mca_btl_base_module_t *btl,
|
|
struct mca_btl_base_endpoint_t *endpoint,
|
|
struct mca_btl_base_descriptor_t *des)
|
|
{
|
|
mca_btl_vader_frag_t *frag = (mca_btl_vader_frag_t *) des;
|
|
mca_btl_vader_segment_t *src = (mca_btl_vader_segment_t *) des->des_local;
|
|
mca_btl_vader_segment_t *dst = (mca_btl_vader_segment_t *) des->des_remote;
|
|
const size_t size = min(dst->base.seg_len, src->base.seg_len);
|
|
intptr_t offset = dst->base.seg_addr.lval - dst->registered_base;
|
|
struct knem_cmd_param_iovec send_iovec;
|
|
struct knem_cmd_inline_copy icopy;
|
|
|
|
/* Fill in the ioctl data fields. There's no async completion, so
|
|
we don't need to worry about getting a slot, etc. */
|
|
send_iovec.base = (uintptr_t) src->base.seg_addr.lval;
|
|
send_iovec.len = size;
|
|
icopy.local_iovec_array = (uintptr_t) &send_iovec;
|
|
icopy.local_iovec_nr = 1;
|
|
icopy.remote_cookie = dst->cookie;
|
|
icopy.remote_offset = offset;
|
|
icopy.write = 1;
|
|
icopy.flags = 0;
|
|
|
|
/* Use the DMA flag if knem supports it *and* the segment length
|
|
* is greater than the cutoff. Not that if DMA is not supported
|
|
* or the user specified 0 for knem_dma_min the knem_dma_min was
|
|
* set to UINT_MAX in mca_btl_vader_knem_init. */
|
|
if (mca_btl_vader_component.knem_dma_min <= dst->base.seg_len) {
|
|
icopy.flags = KNEM_FLAG_DMA;
|
|
}
|
|
/* synchronous flags only, no need to specify icopy.async_status_index */
|
|
|
|
/* When the ioctl returns, the transfer is done and we can invoke
|
|
the btl callback and return the frag */
|
|
if (OPAL_UNLIKELY(0 != ioctl (mca_btl_vader.knem_fd, KNEM_CMD_INLINE_COPY, &icopy))) {
|
|
return OPAL_ERROR;
|
|
}
|
|
|
|
if (KNEM_STATUS_FAILED == icopy.current_status) {
|
|
return OPAL_ERROR;
|
|
}
|
|
|
|
/* always call the callback function */
|
|
frag->base.des_flags |= MCA_BTL_DES_SEND_ALWAYS_CALLBACK;
|
|
|
|
frag->endpoint = endpoint;
|
|
mca_btl_vader_frag_complete (frag);
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|
|
#endif
|