linux_dsm_epyc7002/drivers/infiniband/hw/cxgb4/ev.c
Linus Torvalds b5ccb078c8 InfiniBand/RDMA changes for 3.20 merge window:
- Re-enable on-demand paging changes with stable ABI
  - Fairly large set of ocrdma HW driver fixes
  - Some qib HW driver fixes
  - Other miscellaneous changes
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABCAAGBQJU52nHAAoJEENa44ZhAt0hkycP/0vwYNl0JJadasSUrLm2AWje
 iAePU+K7uiyxSuIU+eLnyyDV/iQ2sCjXfhQNE6FnFhH3JjwBYbhS2Q8WcjwfRWYX
 iFhORQltb3spSeLdT7N1QfkMF4MtAw3ENPE3QKIgNaIQSso+J256BHrSiqr9Akwe
 hwIVr0TLDO59ggPs3c083uUhC+5AMViMVgRR+N9+/59WHz2vG2WsTunpg1sYOAgC
 KpUhfZW4za5xYJ0c8BOnPiSAfJasD1UdDg3oX0RPD4j/diiWAO6EOR+jkOLtODpd
 8uhD8HM7ZvCKE1io5QnVdjTR/n51NaVGHk+yfWJRSvV1sw1AALtU4NVniI+E5mFs
 Fwe+zUzbQ3j08TtrU0VjaeteBh2oGC0pJlkJS9+HXeDmH30/LQCMCiA5mBSSEPDg
 0cPEAJgGAZqOIyyZe8jSslW/iN0cE6FDDb8+/1AZ80IfbdMxXh9FVwi7cdXn8+OQ
 nXmtnSa7yzKWS9VVXDrvSzI0Y2oDv8DSDpCWGCm7bUcDXd/T5LpPR3RdSorGkYAr
 O2zmuJZlCdkuKgW91O7cztNj2hTlDnJ+e+5P05KwPOb86Muum6tphLJd5b1h970X
 Actx/6EX/ycSQ3ukiKW7Ksn2bYD3RLZvdbPYQM5xUjlGGWPF6nvmbZ8MqnyaLFfE
 WKvx39DMGq3ktofiMkbf
 =JLsF
 -----END PGP SIGNATURE-----

Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull InfiniBand/RDMA updates from Roland Dreier:
 - Re-enable on-demand paging changes with stable ABI
 - Fairly large set of ocrdma HW driver fixes
 - Some qib HW driver fixes
 - Other miscellaneous changes

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (43 commits)
  IB/qib: Add blank line after declaration
  IB/qib: Fix checkpatch warnings
  IB/mlx5: Enable the ODP capability query verb
  IB/core: Add on demand paging caps to ib_uverbs_ex_query_device
  IB/core: Add support for extended query device caps
  RDMA/cxgb4: Don't hang threads forever waiting on WR replies
  RDMA/ocrdma: Fix off by one in ocrdma_query_gid()
  RDMA/ocrdma: Use unsigned for bit index
  RDMA/ocrdma: Help gcc generate better code for ocrdma_srq_toggle_bit
  RDMA/ocrdma: Update the ocrdma module version string
  RDMA/ocrdma: set vlan present bit for user AH
  RDMA/ocrdma: remove reference of ocrdma_dev out of ocrdma_qp structure
  RDMA/ocrdma: Add support for interrupt moderation
  RDMA/ocrdma: Honor return value of ocrdma_resolve_dmac
  RDMA/ocrdma: Allow expansion of the SQ CQEs via buddy CQ expansion of the QP
  RDMA/ocrdma: Discontinue support of RDMA-READ-WITH-INVALIDATE
  RDMA/ocrdma: Host crash on destroying device resources
  RDMA/ocrdma: Report correct state in ibv_query_qp
  RDMA/ocrdma: Debugfs enhancments for ocrdma driver
  RDMA/ocrdma: Report correct count of interrupt vectors while registering ocrdma device
  ...
2015-02-21 12:53:21 -08:00

245 lines
7.1 KiB
C

/*
* 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/slab.h>
#include <linux/mman.h>
#include <net/sock.h>
#include "iw_cxgb4.h"
static void print_tpte(struct c4iw_dev *dev, u32 stag)
{
int ret;
struct fw_ri_tpte tpte;
ret = cxgb4_read_tpte(dev->rdev.lldi.ports[0], stag,
(__be32 *)&tpte);
if (ret) {
dev_err(&dev->rdev.lldi.pdev->dev,
"%s cxgb4_read_tpte err %d\n", __func__, ret);
return;
}
PDBG("stag idx 0x%x valid %d key 0x%x state %d pdid %d "
"perm 0x%x ps %d len 0x%llx va 0x%llx\n",
stag & 0xffffff00,
FW_RI_TPTE_VALID_G(ntohl(tpte.valid_to_pdid)),
FW_RI_TPTE_STAGKEY_G(ntohl(tpte.valid_to_pdid)),
FW_RI_TPTE_STAGSTATE_G(ntohl(tpte.valid_to_pdid)),
FW_RI_TPTE_PDID_G(ntohl(tpte.valid_to_pdid)),
FW_RI_TPTE_PERM_G(ntohl(tpte.locread_to_qpid)),
FW_RI_TPTE_PS_G(ntohl(tpte.locread_to_qpid)),
((u64)ntohl(tpte.len_hi) << 32) | ntohl(tpte.len_lo),
((u64)ntohl(tpte.va_hi) << 32) | ntohl(tpte.va_lo_fbo));
}
static void dump_err_cqe(struct c4iw_dev *dev, struct t4_cqe *err_cqe)
{
__be64 *p = (void *)err_cqe;
dev_err(&dev->rdev.lldi.pdev->dev,
"AE qpid %d opcode %d status 0x%x "
"type %d len 0x%x wrid.hi 0x%x wrid.lo 0x%x\n",
CQE_QPID(err_cqe), CQE_OPCODE(err_cqe),
CQE_STATUS(err_cqe), CQE_TYPE(err_cqe), ntohl(err_cqe->len),
CQE_WRID_HI(err_cqe), CQE_WRID_LOW(err_cqe));
PDBG("%016llx %016llx %016llx %016llx\n",
be64_to_cpu(p[0]), be64_to_cpu(p[1]), be64_to_cpu(p[2]),
be64_to_cpu(p[3]));
/*
* Ingress WRITE and READ_RESP errors provide
* the offending stag, so parse and log it.
*/
if (RQ_TYPE(err_cqe) && (CQE_OPCODE(err_cqe) == FW_RI_RDMA_WRITE ||
CQE_OPCODE(err_cqe) == FW_RI_READ_RESP))
print_tpte(dev, CQE_WRID_STAG(err_cqe));
}
static void post_qp_event(struct c4iw_dev *dev, struct c4iw_cq *chp,
struct c4iw_qp *qhp,
struct t4_cqe *err_cqe,
enum ib_event_type ib_event)
{
struct ib_event event;
struct c4iw_qp_attributes attrs;
unsigned long flag;
dump_err_cqe(dev, err_cqe);
if (qhp->attr.state == C4IW_QP_STATE_RTS) {
attrs.next_state = C4IW_QP_STATE_TERMINATE;
c4iw_modify_qp(qhp->rhp, qhp, C4IW_QP_ATTR_NEXT_STATE,
&attrs, 0);
}
event.event = ib_event;
event.device = chp->ibcq.device;
if (ib_event == IB_EVENT_CQ_ERR)
event.element.cq = &chp->ibcq;
else
event.element.qp = &qhp->ibqp;
if (qhp->ibqp.event_handler)
(*qhp->ibqp.event_handler)(&event, qhp->ibqp.qp_context);
spin_lock_irqsave(&chp->comp_handler_lock, flag);
(*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
spin_unlock_irqrestore(&chp->comp_handler_lock, flag);
}
void c4iw_ev_dispatch(struct c4iw_dev *dev, struct t4_cqe *err_cqe)
{
struct c4iw_cq *chp;
struct c4iw_qp *qhp;
u32 cqid;
spin_lock_irq(&dev->lock);
qhp = get_qhp(dev, CQE_QPID(err_cqe));
if (!qhp) {
printk(KERN_ERR MOD "BAD AE qpid 0x%x opcode %d "
"status 0x%x type %d wrid.hi 0x%x wrid.lo 0x%x\n",
CQE_QPID(err_cqe),
CQE_OPCODE(err_cqe), CQE_STATUS(err_cqe),
CQE_TYPE(err_cqe), CQE_WRID_HI(err_cqe),
CQE_WRID_LOW(err_cqe));
spin_unlock_irq(&dev->lock);
goto out;
}
if (SQ_TYPE(err_cqe))
cqid = qhp->attr.scq;
else
cqid = qhp->attr.rcq;
chp = get_chp(dev, cqid);
if (!chp) {
printk(KERN_ERR MOD "BAD AE cqid 0x%x qpid 0x%x opcode %d "
"status 0x%x type %d wrid.hi 0x%x wrid.lo 0x%x\n",
cqid, CQE_QPID(err_cqe),
CQE_OPCODE(err_cqe), CQE_STATUS(err_cqe),
CQE_TYPE(err_cqe), CQE_WRID_HI(err_cqe),
CQE_WRID_LOW(err_cqe));
spin_unlock_irq(&dev->lock);
goto out;
}
c4iw_qp_add_ref(&qhp->ibqp);
atomic_inc(&chp->refcnt);
spin_unlock_irq(&dev->lock);
/* Bad incoming write */
if (RQ_TYPE(err_cqe) &&
(CQE_OPCODE(err_cqe) == FW_RI_RDMA_WRITE)) {
post_qp_event(dev, chp, qhp, err_cqe, IB_EVENT_QP_REQ_ERR);
goto done;
}
switch (CQE_STATUS(err_cqe)) {
/* Completion Events */
case T4_ERR_SUCCESS:
printk(KERN_ERR MOD "AE with status 0!\n");
break;
case T4_ERR_STAG:
case T4_ERR_PDID:
case T4_ERR_QPID:
case T4_ERR_ACCESS:
case T4_ERR_WRAP:
case T4_ERR_BOUND:
case T4_ERR_INVALIDATE_SHARED_MR:
case T4_ERR_INVALIDATE_MR_WITH_MW_BOUND:
post_qp_event(dev, chp, qhp, err_cqe, IB_EVENT_QP_ACCESS_ERR);
break;
/* Device Fatal Errors */
case T4_ERR_ECC:
case T4_ERR_ECC_PSTAG:
case T4_ERR_INTERNAL_ERR:
post_qp_event(dev, chp, qhp, err_cqe, IB_EVENT_DEVICE_FATAL);
break;
/* QP Fatal Errors */
case T4_ERR_OUT_OF_RQE:
case T4_ERR_PBL_ADDR_BOUND:
case T4_ERR_CRC:
case T4_ERR_MARKER:
case T4_ERR_PDU_LEN_ERR:
case T4_ERR_DDP_VERSION:
case T4_ERR_RDMA_VERSION:
case T4_ERR_OPCODE:
case T4_ERR_DDP_QUEUE_NUM:
case T4_ERR_MSN:
case T4_ERR_TBIT:
case T4_ERR_MO:
case T4_ERR_MSN_GAP:
case T4_ERR_MSN_RANGE:
case T4_ERR_RQE_ADDR_BOUND:
case T4_ERR_IRD_OVERFLOW:
post_qp_event(dev, chp, qhp, err_cqe, IB_EVENT_QP_FATAL);
break;
default:
printk(KERN_ERR MOD "Unknown T4 status 0x%x QPID 0x%x\n",
CQE_STATUS(err_cqe), qhp->wq.sq.qid);
post_qp_event(dev, chp, qhp, err_cqe, IB_EVENT_QP_FATAL);
break;
}
done:
if (atomic_dec_and_test(&chp->refcnt))
wake_up(&chp->wait);
c4iw_qp_rem_ref(&qhp->ibqp);
out:
return;
}
int c4iw_ev_handler(struct c4iw_dev *dev, u32 qid)
{
struct c4iw_cq *chp;
unsigned long flag;
spin_lock_irqsave(&dev->lock, flag);
chp = get_chp(dev, qid);
if (chp) {
atomic_inc(&chp->refcnt);
spin_unlock_irqrestore(&dev->lock, flag);
t4_clear_cq_armed(&chp->cq);
spin_lock_irqsave(&chp->comp_handler_lock, flag);
(*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
spin_unlock_irqrestore(&chp->comp_handler_lock, flag);
if (atomic_dec_and_test(&chp->refcnt))
wake_up(&chp->wait);
} else {
PDBG("%s unknown cqid 0x%x\n", __func__, qid);
spin_unlock_irqrestore(&dev->lock, flag);
}
return 0;
}