linux/net/smc/smc_wr.c

744 lines
20 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
* Work Requests exploiting Infiniband API
*
* Work requests (WR) of type ib_post_send or ib_post_recv respectively
* are submitted to either RC SQ or RC RQ respectively
* (reliably connected send/receive queue)
* and become work queue entries (WQEs).
* While an SQ WR/WQE is pending, we track it until transmission completion.
* Through a send or receive completion queue (CQ) respectively,
* we get completion queue entries (CQEs) [aka work completions (WCs)].
* Since the CQ callback is called from IRQ context, we split work by using
* bottom halves implemented by tasklets.
*
* SMC uses this to exchange LLC (link layer control)
* and CDC (connection data control) messages.
*
* Copyright IBM Corp. 2016
*
* Author(s): Steffen Maier <maier@linux.vnet.ibm.com>
*/
#include <linux/atomic.h>
#include <linux/hashtable.h>
#include <linux/wait.h>
#include <rdma/ib_verbs.h>
#include <asm/div64.h>
#include "smc.h"
#include "smc_wr.h"
#define SMC_WR_MAX_POLL_CQE 10 /* max. # of compl. queue elements in 1 poll */
#define SMC_WR_RX_HASH_BITS 4
static DEFINE_HASHTABLE(smc_wr_rx_hash, SMC_WR_RX_HASH_BITS);
static DEFINE_SPINLOCK(smc_wr_rx_hash_lock);
struct smc_wr_tx_pend { /* control data for a pending send request */
u64 wr_id; /* work request id sent */
smc_wr_tx_handler handler;
enum ib_wc_status wc_status; /* CQE status */
struct smc_link *link;
u32 idx;
struct smc_wr_tx_pend_priv priv;
u8 compl_requested;
};
/******************************** send queue *********************************/
/*------------------------------- completion --------------------------------*/
/* returns true if at least one tx work request is pending on the given link */
static inline bool smc_wr_is_tx_pend(struct smc_link *link)
{
if (find_first_bit(link->wr_tx_mask, link->wr_tx_cnt) !=
link->wr_tx_cnt) {
return true;
}
return false;
}
/* wait till all pending tx work requests on the given link are completed */
int smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
{
if (wait_event_timeout(link->wr_tx_wait, !smc_wr_is_tx_pend(link),
SMC_WR_TX_WAIT_PENDING_TIME))
return 0;
else /* timeout */
return -EPIPE;
}
static inline int smc_wr_tx_find_pending_index(struct smc_link *link, u64 wr_id)
{
u32 i;
for (i = 0; i < link->wr_tx_cnt; i++) {
if (link->wr_tx_pends[i].wr_id == wr_id)
return i;
}
return link->wr_tx_cnt;
}
static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
{
struct smc_wr_tx_pend pnd_snd;
struct smc_link *link;
u32 pnd_snd_idx;
int i;
link = wc->qp->qp_context;
if (wc->opcode == IB_WC_REG_MR) {
if (wc->status)
link->wr_reg_state = FAILED;
else
link->wr_reg_state = CONFIRMED;
smc_wr_wakeup_reg_wait(link);
return;
}
pnd_snd_idx = smc_wr_tx_find_pending_index(link, wc->wr_id);
if (pnd_snd_idx == link->wr_tx_cnt)
return;
link->wr_tx_pends[pnd_snd_idx].wc_status = wc->status;
if (link->wr_tx_pends[pnd_snd_idx].compl_requested)
complete(&link->wr_tx_compl[pnd_snd_idx]);
memcpy(&pnd_snd, &link->wr_tx_pends[pnd_snd_idx], sizeof(pnd_snd));
/* clear the full struct smc_wr_tx_pend including .priv */
memset(&link->wr_tx_pends[pnd_snd_idx], 0,
sizeof(link->wr_tx_pends[pnd_snd_idx]));
memset(&link->wr_tx_bufs[pnd_snd_idx], 0,
sizeof(link->wr_tx_bufs[pnd_snd_idx]));
if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask))
return;
if (wc->status) {
for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
/* clear full struct smc_wr_tx_pend including .priv */
memset(&link->wr_tx_pends[i], 0,
sizeof(link->wr_tx_pends[i]));
memset(&link->wr_tx_bufs[i], 0,
sizeof(link->wr_tx_bufs[i]));
clear_bit(i, link->wr_tx_mask);
}
/* terminate link */
smcr_link_down_cond_sched(link);
}
if (pnd_snd.handler)
pnd_snd.handler(&pnd_snd.priv, link, wc->status);
wake_up(&link->wr_tx_wait);
}
static void smc_wr_tx_tasklet_fn(unsigned long data)
{
struct smc_ib_device *dev = (struct smc_ib_device *)data;
struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
int i = 0, rc;
int polled = 0;
again:
polled++;
do {
memset(&wc, 0, sizeof(wc));
rc = ib_poll_cq(dev->roce_cq_send, SMC_WR_MAX_POLL_CQE, wc);
if (polled == 1) {
ib_req_notify_cq(dev->roce_cq_send,
IB_CQ_NEXT_COMP |
IB_CQ_REPORT_MISSED_EVENTS);
}
if (!rc)
break;
for (i = 0; i < rc; i++)
smc_wr_tx_process_cqe(&wc[i]);
} while (rc > 0);
if (polled == 1)
goto again;
}
void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context)
{
struct smc_ib_device *dev = (struct smc_ib_device *)cq_context;
tasklet_schedule(&dev->send_tasklet);
}
/*---------------------------- request submission ---------------------------*/
static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
{
*idx = link->wr_tx_cnt;
if (!smc_link_usable(link))
return -ENOLINK;
for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) {
if (!test_and_set_bit(*idx, link->wr_tx_mask))
return 0;
}
*idx = link->wr_tx_cnt;
return -EBUSY;
}
/**
* smc_wr_tx_get_free_slot() - returns buffer for message assembly,
* and sets info for pending transmit tracking
* @link: Pointer to smc_link used to later send the message.
* @handler: Send completion handler function pointer.
* @wr_buf: Out value returns pointer to message buffer.
* @wr_rdma_buf: Out value returns pointer to rdma work request.
* @wr_pend_priv: Out value returns pointer serving as handler context.
*
* Return: 0 on success, or -errno on error.
*/
int smc_wr_tx_get_free_slot(struct smc_link *link,
smc_wr_tx_handler handler,
struct smc_wr_buf **wr_buf,
struct smc_rdma_wr **wr_rdma_buf,
struct smc_wr_tx_pend_priv **wr_pend_priv)
{
struct smc_link_group *lgr = smc_get_lgr(link);
struct smc_wr_tx_pend *wr_pend;
u32 idx = link->wr_tx_cnt;
struct ib_send_wr *wr_ib;
u64 wr_id;
int rc;
*wr_buf = NULL;
*wr_pend_priv = NULL;
if (in_softirq() || lgr->terminating) {
rc = smc_wr_tx_get_free_slot_index(link, &idx);
if (rc)
return rc;
} else {
rc = wait_event_interruptible_timeout(
link->wr_tx_wait,
!smc_link_usable(link) ||
lgr->terminating ||
(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
SMC_WR_TX_WAIT_FREE_SLOT_TIME);
if (!rc) {
/* timeout - terminate link */
smcr_link_down_cond_sched(link);
return -EPIPE;
}
if (idx == link->wr_tx_cnt)
return -EPIPE;
}
wr_id = smc_wr_tx_get_next_wr_id(link);
wr_pend = &link->wr_tx_pends[idx];
wr_pend->wr_id = wr_id;
wr_pend->handler = handler;
wr_pend->link = link;
wr_pend->idx = idx;
wr_ib = &link->wr_tx_ibs[idx];
wr_ib->wr_id = wr_id;
*wr_buf = &link->wr_tx_bufs[idx];
if (wr_rdma_buf)
*wr_rdma_buf = &link->wr_tx_rdmas[idx];
*wr_pend_priv = &wr_pend->priv;
return 0;
}
int smc_wr_tx_put_slot(struct smc_link *link,
struct smc_wr_tx_pend_priv *wr_pend_priv)
{
struct smc_wr_tx_pend *pend;
pend = container_of(wr_pend_priv, struct smc_wr_tx_pend, priv);
if (pend->idx < link->wr_tx_cnt) {
u32 idx = pend->idx;
/* clear the full struct smc_wr_tx_pend including .priv */
memset(&link->wr_tx_pends[idx], 0,
sizeof(link->wr_tx_pends[idx]));
memset(&link->wr_tx_bufs[idx], 0,
sizeof(link->wr_tx_bufs[idx]));
test_and_clear_bit(idx, link->wr_tx_mask);
wake_up(&link->wr_tx_wait);
return 1;
}
return 0;
}
/* Send prepared WR slot via ib_post_send.
* @priv: pointer to smc_wr_tx_pend_priv identifying prepared message buffer
*/
int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
{
struct smc_wr_tx_pend *pend;
int rc;
ib_req_notify_cq(link->smcibdev->roce_cq_send,
IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
pend = container_of(priv, struct smc_wr_tx_pend, priv);
rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx], NULL);
if (rc) {
smc_wr_tx_put_slot(link, priv);
smcr_link_down_cond_sched(link);
}
return rc;
}
/* Send prepared WR slot via ib_post_send and wait for send completion
* notification.
* @priv: pointer to smc_wr_tx_pend_priv identifying prepared message buffer
*/
int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv,
unsigned long timeout)
{
struct smc_wr_tx_pend *pend;
int rc;
pend = container_of(priv, struct smc_wr_tx_pend, priv);
pend->compl_requested = 1;
init_completion(&link->wr_tx_compl[pend->idx]);
rc = smc_wr_tx_send(link, priv);
if (rc)
return rc;
/* wait for completion by smc_wr_tx_process_cqe() */
rc = wait_for_completion_interruptible_timeout(
&link->wr_tx_compl[pend->idx], timeout);
if (rc <= 0)
rc = -ENODATA;
if (rc > 0)
rc = 0;
return rc;
}
/* Register a memory region and wait for result. */
int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
{
int rc;
ib_req_notify_cq(link->smcibdev->roce_cq_send,
IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
link->wr_reg_state = POSTED;
link->wr_reg.wr.wr_id = (u64)(uintptr_t)mr;
link->wr_reg.mr = mr;
link->wr_reg.key = mr->rkey;
rc = ib_post_send(link->roce_qp, &link->wr_reg.wr, NULL);
if (rc)
return rc;
rc = wait_event_interruptible_timeout(link->wr_reg_wait,
(link->wr_reg_state != POSTED),
SMC_WR_REG_MR_WAIT_TIME);
if (!rc) {
/* timeout - terminate link */
smcr_link_down_cond_sched(link);
return -EPIPE;
}
if (rc == -ERESTARTSYS)
return -EINTR;
switch (link->wr_reg_state) {
case CONFIRMED:
rc = 0;
break;
case FAILED:
rc = -EIO;
break;
case POSTED:
rc = -EPIPE;
break;
}
return rc;
}
void smc_wr_tx_dismiss_slots(struct smc_link *link, u8 wr_tx_hdr_type,
smc_wr_tx_filter filter,
smc_wr_tx_dismisser dismisser,
unsigned long data)
{
struct smc_wr_tx_pend_priv *tx_pend;
struct smc_wr_rx_hdr *wr_tx;
int i;
for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
wr_tx = (struct smc_wr_rx_hdr *)&link->wr_tx_bufs[i];
if (wr_tx->type != wr_tx_hdr_type)
continue;
tx_pend = &link->wr_tx_pends[i].priv;
if (filter(tx_pend, data))
dismisser(tx_pend);
}
}
/****************************** receive queue ********************************/
int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler)
{
struct smc_wr_rx_handler *h_iter;
int rc = 0;
spin_lock(&smc_wr_rx_hash_lock);
hash_for_each_possible(smc_wr_rx_hash, h_iter, list, handler->type) {
if (h_iter->type == handler->type) {
rc = -EEXIST;
goto out_unlock;
}
}
hash_add(smc_wr_rx_hash, &handler->list, handler->type);
out_unlock:
spin_unlock(&smc_wr_rx_hash_lock);
return rc;
}
/* Demultiplex a received work request based on the message type to its handler.
* Relies on smc_wr_rx_hash having been completely filled before any IB WRs,
* and not being modified any more afterwards so we don't need to lock it.
*/
static inline void smc_wr_rx_demultiplex(struct ib_wc *wc)
{
struct smc_link *link = (struct smc_link *)wc->qp->qp_context;
struct smc_wr_rx_handler *handler;
struct smc_wr_rx_hdr *wr_rx;
u64 temp_wr_id;
u32 index;
if (wc->byte_len < sizeof(*wr_rx))
return; /* short message */
temp_wr_id = wc->wr_id;
index = do_div(temp_wr_id, link->wr_rx_cnt);
wr_rx = (struct smc_wr_rx_hdr *)&link->wr_rx_bufs[index];
hash_for_each_possible(smc_wr_rx_hash, handler, list, wr_rx->type) {
if (handler->type == wr_rx->type)
handler->handler(wc, wr_rx);
}
}
static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
{
struct smc_link *link;
int i;
for (i = 0; i < num; i++) {
link = wc[i].qp->qp_context;
if (wc[i].status == IB_WC_SUCCESS) {
link->wr_rx_tstamp = jiffies;
smc_wr_rx_demultiplex(&wc[i]);
smc_wr_rx_post(link); /* refill WR RX */
} else {
/* handle status errors */
switch (wc[i].status) {
case IB_WC_RETRY_EXC_ERR:
case IB_WC_RNR_RETRY_EXC_ERR:
case IB_WC_WR_FLUSH_ERR:
smcr_link_down_cond_sched(link);
break;
default:
smc_wr_rx_post(link); /* refill WR RX */
break;
}
}
}
}
static void smc_wr_rx_tasklet_fn(unsigned long data)
{
struct smc_ib_device *dev = (struct smc_ib_device *)data;
struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
int polled = 0;
int rc;
again:
polled++;
do {
memset(&wc, 0, sizeof(wc));
rc = ib_poll_cq(dev->roce_cq_recv, SMC_WR_MAX_POLL_CQE, wc);
if (polled == 1) {
ib_req_notify_cq(dev->roce_cq_recv,
IB_CQ_SOLICITED_MASK
| IB_CQ_REPORT_MISSED_EVENTS);
}
if (!rc)
break;
smc_wr_rx_process_cqes(&wc[0], rc);
} while (rc > 0);
if (polled == 1)
goto again;
}
void smc_wr_rx_cq_handler(struct ib_cq *ib_cq, void *cq_context)
{
struct smc_ib_device *dev = (struct smc_ib_device *)cq_context;
tasklet_schedule(&dev->recv_tasklet);
}
int smc_wr_rx_post_init(struct smc_link *link)
{
u32 i;
int rc = 0;
for (i = 0; i < link->wr_rx_cnt; i++)
rc = smc_wr_rx_post(link);
return rc;
}
/***************************** init, exit, misc ******************************/
void smc_wr_remember_qp_attr(struct smc_link *lnk)
{
struct ib_qp_attr *attr = &lnk->qp_attr;
struct ib_qp_init_attr init_attr;
memset(attr, 0, sizeof(*attr));
memset(&init_attr, 0, sizeof(init_attr));
ib_query_qp(lnk->roce_qp, attr,
IB_QP_STATE |
IB_QP_CUR_STATE |
IB_QP_PKEY_INDEX |
IB_QP_PORT |
IB_QP_QKEY |
IB_QP_AV |
IB_QP_PATH_MTU |
IB_QP_TIMEOUT |
IB_QP_RETRY_CNT |
IB_QP_RNR_RETRY |
IB_QP_RQ_PSN |
IB_QP_ALT_PATH |
IB_QP_MIN_RNR_TIMER |
IB_QP_SQ_PSN |
IB_QP_PATH_MIG_STATE |
IB_QP_CAP |
IB_QP_DEST_QPN,
&init_attr);
lnk->wr_tx_cnt = min_t(size_t, SMC_WR_BUF_CNT,
lnk->qp_attr.cap.max_send_wr);
lnk->wr_rx_cnt = min_t(size_t, SMC_WR_BUF_CNT * 3,
lnk->qp_attr.cap.max_recv_wr);
}
static void smc_wr_init_sge(struct smc_link *lnk)
{
u32 i;
for (i = 0; i < lnk->wr_tx_cnt; i++) {
lnk->wr_tx_sges[i].addr =
lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE;
lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE;
lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey =
lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey =
lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey =
lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey =
lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_ibs[i].next = NULL;
lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i];
lnk->wr_tx_ibs[i].num_sge = 1;
lnk->wr_tx_ibs[i].opcode = IB_WR_SEND;
lnk->wr_tx_ibs[i].send_flags =
IB_SEND_SIGNALED | IB_SEND_SOLICITED;
lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE;
lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE;
lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list =
lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge;
lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list =
lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge;
}
for (i = 0; i < lnk->wr_rx_cnt; i++) {
lnk->wr_rx_sges[i].addr =
lnk->wr_rx_dma_addr + i * SMC_WR_BUF_SIZE;
lnk->wr_rx_sges[i].length = SMC_WR_BUF_SIZE;
lnk->wr_rx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
lnk->wr_rx_ibs[i].next = NULL;
lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[i];
lnk->wr_rx_ibs[i].num_sge = 1;
}
lnk->wr_reg.wr.next = NULL;
lnk->wr_reg.wr.num_sge = 0;
lnk->wr_reg.wr.send_flags = IB_SEND_SIGNALED;
lnk->wr_reg.wr.opcode = IB_WR_REG_MR;
lnk->wr_reg.access = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE;
}
void smc_wr_free_link(struct smc_link *lnk)
{
struct ib_device *ibdev;
if (!lnk->smcibdev)
return;
ibdev = lnk->smcibdev->ibdev;
if (smc_wr_tx_wait_no_pending_sends(lnk))
memset(lnk->wr_tx_mask, 0,
BITS_TO_LONGS(SMC_WR_BUF_CNT) *
sizeof(*lnk->wr_tx_mask));
if (lnk->wr_rx_dma_addr) {
ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
DMA_FROM_DEVICE);
lnk->wr_rx_dma_addr = 0;
}
if (lnk->wr_tx_dma_addr) {
ib_dma_unmap_single(ibdev, lnk->wr_tx_dma_addr,
SMC_WR_BUF_SIZE * lnk->wr_tx_cnt,
DMA_TO_DEVICE);
lnk->wr_tx_dma_addr = 0;
}
}
void smc_wr_free_link_mem(struct smc_link *lnk)
{
kfree(lnk->wr_tx_compl);
lnk->wr_tx_compl = NULL;
kfree(lnk->wr_tx_pends);
lnk->wr_tx_pends = NULL;
kfree(lnk->wr_tx_mask);
lnk->wr_tx_mask = NULL;
kfree(lnk->wr_tx_sges);
lnk->wr_tx_sges = NULL;
kfree(lnk->wr_tx_rdma_sges);
lnk->wr_tx_rdma_sges = NULL;
kfree(lnk->wr_rx_sges);
lnk->wr_rx_sges = NULL;
kfree(lnk->wr_tx_rdmas);
lnk->wr_tx_rdmas = NULL;
kfree(lnk->wr_rx_ibs);
lnk->wr_rx_ibs = NULL;
kfree(lnk->wr_tx_ibs);
lnk->wr_tx_ibs = NULL;
kfree(lnk->wr_tx_bufs);
lnk->wr_tx_bufs = NULL;
kfree(lnk->wr_rx_bufs);
lnk->wr_rx_bufs = NULL;
}
int smc_wr_alloc_link_mem(struct smc_link *link)
{
/* allocate link related memory */
link->wr_tx_bufs = kcalloc(SMC_WR_BUF_CNT, SMC_WR_BUF_SIZE, GFP_KERNEL);
if (!link->wr_tx_bufs)
goto no_mem;
link->wr_rx_bufs = kcalloc(SMC_WR_BUF_CNT * 3, SMC_WR_BUF_SIZE,
GFP_KERNEL);
if (!link->wr_rx_bufs)
goto no_mem_wr_tx_bufs;
link->wr_tx_ibs = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_ibs[0]),
GFP_KERNEL);
if (!link->wr_tx_ibs)
goto no_mem_wr_rx_bufs;
link->wr_rx_ibs = kcalloc(SMC_WR_BUF_CNT * 3,
sizeof(link->wr_rx_ibs[0]),
GFP_KERNEL);
if (!link->wr_rx_ibs)
goto no_mem_wr_tx_ibs;
link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT,
sizeof(link->wr_tx_rdmas[0]),
GFP_KERNEL);
if (!link->wr_tx_rdmas)
goto no_mem_wr_rx_ibs;
link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT,
sizeof(link->wr_tx_rdma_sges[0]),
GFP_KERNEL);
if (!link->wr_tx_rdma_sges)
goto no_mem_wr_tx_rdmas;
link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]),
GFP_KERNEL);
if (!link->wr_tx_sges)
goto no_mem_wr_tx_rdma_sges;
link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3,
sizeof(link->wr_rx_sges[0]),
GFP_KERNEL);
if (!link->wr_rx_sges)
goto no_mem_wr_tx_sges;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
link->wr_tx_mask = kcalloc(BITS_TO_LONGS(SMC_WR_BUF_CNT),
sizeof(*link->wr_tx_mask),
GFP_KERNEL);
if (!link->wr_tx_mask)
goto no_mem_wr_rx_sges;
link->wr_tx_pends = kcalloc(SMC_WR_BUF_CNT,
sizeof(link->wr_tx_pends[0]),
GFP_KERNEL);
if (!link->wr_tx_pends)
goto no_mem_wr_tx_mask;
link->wr_tx_compl = kcalloc(SMC_WR_BUF_CNT,
sizeof(link->wr_tx_compl[0]),
GFP_KERNEL);
if (!link->wr_tx_compl)
goto no_mem_wr_tx_pends;
return 0;
no_mem_wr_tx_pends:
kfree(link->wr_tx_pends);
no_mem_wr_tx_mask:
kfree(link->wr_tx_mask);
no_mem_wr_rx_sges:
kfree(link->wr_rx_sges);
no_mem_wr_tx_sges:
kfree(link->wr_tx_sges);
no_mem_wr_tx_rdma_sges:
kfree(link->wr_tx_rdma_sges);
no_mem_wr_tx_rdmas:
kfree(link->wr_tx_rdmas);
no_mem_wr_rx_ibs:
kfree(link->wr_rx_ibs);
no_mem_wr_tx_ibs:
kfree(link->wr_tx_ibs);
no_mem_wr_rx_bufs:
kfree(link->wr_rx_bufs);
no_mem_wr_tx_bufs:
kfree(link->wr_tx_bufs);
no_mem:
return -ENOMEM;
}
void smc_wr_remove_dev(struct smc_ib_device *smcibdev)
{
tasklet_kill(&smcibdev->recv_tasklet);
tasklet_kill(&smcibdev->send_tasklet);
}
void smc_wr_add_dev(struct smc_ib_device *smcibdev)
{
tasklet_init(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn,
(unsigned long)smcibdev);
tasklet_init(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn,
(unsigned long)smcibdev);
}
int smc_wr_create_link(struct smc_link *lnk)
{
struct ib_device *ibdev = lnk->smcibdev->ibdev;
int rc = 0;
smc_wr_tx_set_wr_id(&lnk->wr_tx_id, 0);
lnk->wr_rx_id = 0;
lnk->wr_rx_dma_addr = ib_dma_map_single(
ibdev, lnk->wr_rx_bufs, SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
DMA_FROM_DEVICE);
if (ib_dma_mapping_error(ibdev, lnk->wr_rx_dma_addr)) {
lnk->wr_rx_dma_addr = 0;
rc = -EIO;
goto out;
}
lnk->wr_tx_dma_addr = ib_dma_map_single(
ibdev, lnk->wr_tx_bufs, SMC_WR_BUF_SIZE * lnk->wr_tx_cnt,
DMA_TO_DEVICE);
if (ib_dma_mapping_error(ibdev, lnk->wr_tx_dma_addr)) {
rc = -EIO;
goto dma_unmap;
}
smc_wr_init_sge(lnk);
memset(lnk->wr_tx_mask, 0,
BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask));
init_waitqueue_head(&lnk->wr_tx_wait);
init_waitqueue_head(&lnk->wr_reg_wait);
return rc;
dma_unmap:
ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
SMC_WR_BUF_SIZE * lnk->wr_rx_cnt,
DMA_FROM_DEVICE);
lnk->wr_rx_dma_addr = 0;
out:
return rc;
}