From 9ed5bd7d22241ad232fd3a5be404e83eb6cadc04 Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan@intel.com>
Date: Fri, 4 Oct 2019 16:40:35 -0400
Subject: IB/hfi1: Avoid excessive retry for TID RDMA READ request

A TID RDMA READ request could be retried under one of the following
conditions:
- The RC retry timer expires;
- A later TID RDMA READ RESP packet is received before the next
  expected one.
For the latter, under normal conditions, the PSN in IB space is used
for comparison. More specifically, the IB PSN in the incoming TID RDMA
READ RESP packet is compared with the last IB PSN of a given TID RDMA
READ request to determine if the request should be retried. This is
similar to the retry logic for noraml RDMA READ request.

However, if a TID RDMA READ RESP packet is lost due to congestion,
header suppresion will be disabled and each incoming packet will raise
an interrupt until the hardware flow is reloaded. Under this condition,
each packet KDETH PSN will be checked by software against r_next_psn
and a retry will be requested if the packet KDETH PSN is later than
r_next_psn. Since each TID RDMA READ segment could have up to 64
packets and each TID RDMA READ request could have many segments, we
could make far more retries under such conditions, and thus leading to
RETRY_EXC_ERR status.

This patch fixes the issue by removing the retry when the incoming
packet KDETH PSN is later than r_next_psn. Instead, it resorts to
RC timer and normal IB PSN comparison for any request retry.

Fixes: 9905bf06e890 ("IB/hfi1: Add functions to receive TID RDMA READ response")
Cc: <stable@vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Link: https://lore.kernel.org/r/20191004204035.26542.41684.stgit@awfm-01.aw.intel.com
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/hfi1/tid_rdma.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index b4dcc4d29f84..f21fca3617d5 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -2736,11 +2736,6 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd,
 				diff = cmp_psn(psn,
 					       flow->flow_state.r_next_psn);
 				if (diff > 0) {
-					if (!(qp->r_flags & RVT_R_RDMAR_SEQ))
-						restart_tid_rdma_read_req(rcd,
-									  qp,
-									  wqe);
-
 					/* Drop the packet.*/
 					goto s_unlock;
 				} else if (diff < 0) {
-- 
cgit v1.2.3-59-g8ed1b


From 22bb13653410424d9fce8d447506a41f8292f22f Mon Sep 17 00:00:00 2001
From: Mike Marciniszyn <mike.marciniszyn@intel.com>
Date: Fri, 4 Oct 2019 16:49:34 -0400
Subject: IB/hfi1: Use a common pad buffer for 9B and 16B packets

There is no reason for a different pad buffer for the two
packet types.

Expand the current buffer allocation to allow for both
packet types.

Fixes: f8195f3b14a0 ("IB/hfi1: Eliminate allocation while atomic")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Link: https://lore.kernel.org/r/20191004204934.26838.13099.stgit@awfm-01.aw.intel.com
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/hfi1/sdma.c  |  5 +++--
 drivers/infiniband/hw/hfi1/verbs.c | 10 ++++------
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 2ed7bfd5feea..c61b6022575e 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -65,6 +65,7 @@
 #define SDMA_DESCQ_CNT 2048
 #define SDMA_DESC_INTR 64
 #define INVALID_TAIL 0xffff
+#define SDMA_PAD max_t(size_t, MAX_16B_PADDING, sizeof(u32))
 
 static uint sdma_descq_cnt = SDMA_DESCQ_CNT;
 module_param(sdma_descq_cnt, uint, S_IRUGO);
@@ -1296,7 +1297,7 @@ void sdma_clean(struct hfi1_devdata *dd, size_t num_engines)
 	struct sdma_engine *sde;
 
 	if (dd->sdma_pad_dma) {
-		dma_free_coherent(&dd->pcidev->dev, 4,
+		dma_free_coherent(&dd->pcidev->dev, SDMA_PAD,
 				  (void *)dd->sdma_pad_dma,
 				  dd->sdma_pad_phys);
 		dd->sdma_pad_dma = NULL;
@@ -1491,7 +1492,7 @@ int sdma_init(struct hfi1_devdata *dd, u8 port)
 	}
 
 	/* Allocate memory for pad */
-	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, sizeof(u32),
+	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, SDMA_PAD,
 					      &dd->sdma_pad_phys, GFP_KERNEL);
 	if (!dd->sdma_pad_dma) {
 		dd_dev_err(dd, "failed to allocate SendDMA pad memory\n");
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 7bff0a1e713d..089e201d7550 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -147,9 +147,6 @@ static int pio_wait(struct rvt_qp *qp,
 /* Length of buffer to create verbs txreq cache name */
 #define TXREQ_NAME_LEN 24
 
-/* 16B trailing buffer */
-static const u8 trail_buf[MAX_16B_PADDING];
-
 static uint wss_threshold = 80;
 module_param(wss_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy");
@@ -820,8 +817,8 @@ static int build_verbs_tx_desc(
 
 	/* add icrc, lt byte, and padding to flit */
 	if (extra_bytes)
-		ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq,
-					(void *)trail_buf, extra_bytes);
+		ret = sdma_txadd_daddr(sde->dd, &tx->txreq,
+				       sde->dd->sdma_pad_phys, extra_bytes);
 
 bail_txadd:
 	return ret;
@@ -1089,7 +1086,8 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		}
 		/* add icrc, lt byte, and padding to flit */
 		if (extra_bytes)
-			seg_pio_copy_mid(pbuf, trail_buf, extra_bytes);
+			seg_pio_copy_mid(pbuf, ppd->dd->sdma_pad_dma,
+					 extra_bytes);
 
 		seg_pio_copy_end(pbuf);
 	}
-- 
cgit v1.2.3-59-g8ed1b


From a9c3c4c597704b3a1a2b9bef990e7d8a881f6533 Mon Sep 17 00:00:00 2001
From: James Erwin <james.erwin@intel.com>
Date: Fri, 1 Nov 2019 15:20:59 -0400
Subject: IB/hfi1: Ensure full Gen3 speed in a Gen4 system

If an hfi1 card is inserted in a Gen4 systems, the driver will avoid the
gen3 speed bump and the card will operate at half speed.

This is because the driver avoids the gen3 speed bump when the parent bus
speed isn't identical to gen3, 8.0GT/s.  This is not compatible with gen4
and newer speeds.

Fix by relaxing the test to explicitly look for the lower capability
speeds which inherently allows for gen4 and all future speeds.

Fixes: 7724105686e7 ("IB/hfi1: add driver files")
Link: https://lore.kernel.org/r/20191101192059.106248.1699.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: James Erwin <james.erwin@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/pcie.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 61aa5504d7c3..61362bd6d3ce 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -319,7 +319,9 @@ int pcie_speeds(struct hfi1_devdata *dd)
 	/*
 	 * bus->max_bus_speed is set from the bridge's linkcap Max Link Speed
 	 */
-	if (parent && dd->pcidev->bus->max_bus_speed != PCIE_SPEED_8_0GT) {
+	if (parent &&
+	    (dd->pcidev->bus->max_bus_speed == PCIE_SPEED_2_5GT ||
+	     dd->pcidev->bus->max_bus_speed == PCIE_SPEED_5_0GT)) {
 		dd_dev_info(dd, "Parent PCIe bridge does not support Gen3\n");
 		dd->link_gen3_capable = 0;
 	}
-- 
cgit v1.2.3-59-g8ed1b


From c1abd865bd125015783286b353abb8da51644f59 Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan@intel.com>
Date: Fri, 25 Oct 2019 15:58:30 -0400
Subject: IB/hfi1: Ensure r_tid_ack is valid before building TID RDMA ACK
 packet

The index r_tid_ack is used to indicate the next TID RDMA WRITE request to
acknowledge in the ring s_ack_queue[] on the responder side and should be
set to a valid index other than its initial value before r_tid_tail is
advanced to the next TID RDMA WRITE request and particularly before a TID
RDMA ACK is built. Otherwise, a NULL pointer dereference may result:

  BUG: unable to handle kernel paging request at ffff9a32d27abff8
  IP: [<ffffffffc0d87ea6>] hfi1_make_tid_rdma_pkt+0x476/0xcb0 [hfi1]
  PGD 2749032067 PUD 0
  Oops: 0000 1 SMP
  Modules linked in: osp(OE) ofd(OE) lfsck(OE) ost(OE) mgc(OE) osd_zfs(OE) lquota(OE) lustre(OE) lmv(OE) mdc(OE) lov(OE) fid(OE) fld(OE) ko2iblnd(OE) ptlrpc(OE) obdclass(OE) lnet(OE) libcfs(OE) ib_ipoib(OE) hfi1(OE) rdmavt(OE) nfsv3 nfs_acl rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache ib_isert iscsi_target_mod target_core_mod ib_ucm dm_mirror dm_region_hash dm_log mlx5_ib dm_mod zfs(POE) rpcrdma sunrpc rdma_ucm ib_uverbs opa_vnic ib_iser zunicode(POE) ib_umad zavl(POE) icp(POE) sb_edac intel_powerclamp coretemp rdma_cm intel_rapl iosf_mbi iw_cm libiscsi scsi_transport_iscsi kvm ib_cm iTCO_wdt mxm_wmi iTCO_vendor_support irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd zcommon(POE) znvpair(POE) pcspkr spl(OE) mei_me
  sg mei ioatdma lpc_ich joydev i2c_i801 shpchp ipmi_si ipmi_devintf ipmi_msghandler wmi acpi_power_meter ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic mgag200 mlx5_core drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ixgbe ahci ttm mlxfw ib_core libahci devlink mdio crct10dif_pclmul crct10dif_common drm ptp libata megaraid_sas crc32c_intel i2c_algo_bit pps_core i2c_core dca [last unloaded: rdmavt]
  CPU: 15 PID: 68691 Comm: kworker/15:2H Kdump: loaded Tainted: P W OE ------------ 3.10.0-862.2.3.el7_lustre.x86_64 #1
  Hardware name: Intel Corporation S2600WTT/S2600WTT, BIOS SE5C610.86B.01.01.0016.033120161139 03/31/2016
  Workqueue: hfi0_0 _hfi1_do_tid_send [hfi1]
  task: ffff9a01f47faf70 ti: ffff9a11776a8000 task.ti: ffff9a11776a8000
  RIP: 0010:[<ffffffffc0d87ea6>] [<ffffffffc0d87ea6>] hfi1_make_tid_rdma_pkt+0x476/0xcb0 [hfi1]
  RSP: 0018:ffff9a11776abd08 EFLAGS: 00010002
  RAX: ffff9a32d27abfc0 RBX: ffff99f2d27aa000 RCX: 00000000ffffffff
  RDX: 0000000000000000 RSI: 0000000000000220 RDI: ffff99f2ffc05300
  RBP: ffff9a11776abd88 R08: 000000000001c310 R09: ffffffffc0d87ad4
  R10: 0000000000000000 R11: 0000000000000000 R12: ffff9a117a423c00
  R13: ffff9a117a423c00 R14: ffff9a03500c0000 R15: ffff9a117a423cb8
  FS: 0000000000000000(0000) GS:ffff9a117e9c0000(0000) knlGS:0000000000000000
  CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: ffff9a32d27abff8 CR3: 0000002748a0e000 CR4: 00000000001607e0
  Call Trace:
  [<ffffffffc0d88874>] _hfi1_do_tid_send+0x194/0x320 [hfi1]
  [<ffffffffaf0b2dff>] process_one_work+0x17f/0x440
  [<ffffffffaf0b3ac6>] worker_thread+0x126/0x3c0
  [<ffffffffaf0b39a0>] ? manage_workers.isra.24+0x2a0/0x2a0
  [<ffffffffaf0bae31>] kthread+0xd1/0xe0
  [<ffffffffaf0bad60>] ? insert_kthread_work+0x40/0x40
  [<ffffffffaf71f5f7>] ret_from_fork_nospec_begin+0x21/0x21
  [<ffffffffaf0bad60>] ? insert_kthread_work+0x40/0x40
  hfi1 0000:05:00.0: hfi1_0: reserved_op: opcode 0xf2, slot 2, rsv_used 1, rsv_ops 1
  Code: 00 00 41 8b 8d d8 02 00 00 89 c8 48 89 45 b0 48 c1 65 b0 06 48 8b 83 a0 01 00 00 48 01 45 b0 48 8b 45 b0 41 80 bd 10 03 00 00 00 <48> 8b 50 38 4c 8d 7a 50 74 45 8b b2 d0 00 00 00 85 f6 0f 85 72
  RIP [<ffffffffc0d87ea6>] hfi1_make_tid_rdma_pkt+0x476/0xcb0 [hfi1]
  RSP <ffff9a11776abd08>
  CR2: ffff9a32d27abff8

This problem can happen if a RESYNC request is received before r_tid_ack
is modified.

This patch fixes the issue by making sure that r_tid_ack is set to a valid
value before a TID RDMA ACK is built. Functions are defined to simplify
the code.

Fixes: 07b923701e38 ("IB/hfi1: Add functions to receive TID RDMA WRITE request")
Fixes: 7cf0ad679de4 ("IB/hfi1: Add a function to receive TID RDMA RESYNC packet")
Link: https://lore.kernel.org/r/20191025195830.106825.44022.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/tid_rdma.c | 44 +++++++++++++++++++++--------------
 1 file changed, 27 insertions(+), 17 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index f21fca3617d5..73bc78ba288e 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -136,6 +136,26 @@ static void update_r_next_psn_fecn(struct hfi1_packet *packet,
 				   struct tid_rdma_flow *flow,
 				   bool fecn);
 
+static void validate_r_tid_ack(struct hfi1_qp_priv *priv)
+{
+	if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
+		priv->r_tid_ack = priv->r_tid_tail;
+}
+
+static void tid_rdma_schedule_ack(struct rvt_qp *qp)
+{
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	priv->s_flags |= RVT_S_ACK_PENDING;
+	hfi1_schedule_tid_send(qp);
+}
+
+static void tid_rdma_trigger_ack(struct rvt_qp *qp)
+{
+	validate_r_tid_ack(qp->priv);
+	tid_rdma_schedule_ack(qp);
+}
+
 static u64 tid_rdma_opfn_encode(struct tid_rdma_params *p)
 {
 	return
@@ -3005,10 +3025,7 @@ nak_psn:
 		qpriv->s_nak_state = IB_NAK_PSN_ERROR;
 		/* We are NAK'ing the next expected PSN */
 		qpriv->s_nak_psn = mask_psn(flow->flow_state.r_next_psn);
-		qpriv->s_flags |= RVT_S_ACK_PENDING;
-		if (qpriv->r_tid_ack == HFI1_QP_WQE_INVALID)
-			qpriv->r_tid_ack = qpriv->r_tid_tail;
-		hfi1_schedule_tid_send(qp);
+		tid_rdma_trigger_ack(qp);
 	}
 	goto unlock;
 }
@@ -3526,7 +3543,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 		/*
 		 * If overtaking req->acked_tail, send an RNR NAK. Because the
 		 * QP is not queued in this case, and the issue can only be
-		 * caused due a delay in scheduling the second leg which we
+		 * caused by a delay in scheduling the second leg which we
 		 * cannot estimate, we use a rather arbitrary RNR timeout of
 		 * (MAX_FLOWS / 2) segments
 		 */
@@ -3534,8 +3551,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 				MAX_FLOWS)) {
 			ret = -EAGAIN;
 			to_seg = MAX_FLOWS >> 1;
-			qpriv->s_flags |= RVT_S_ACK_PENDING;
-			hfi1_schedule_tid_send(qp);
+			tid_rdma_trigger_ack(qp);
 			break;
 		}
 
@@ -4335,8 +4351,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet)
 	trace_hfi1_tid_req_rcv_write_data(qp, 0, e->opcode, e->psn, e->lpsn,
 					  req);
 	trace_hfi1_tid_write_rsp_rcv_data(qp);
-	if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
-		priv->r_tid_ack = priv->r_tid_tail;
+	validate_r_tid_ack(priv);
 
 	if (opcode == TID_OP(WRITE_DATA_LAST)) {
 		release_rdma_sge_mr(e);
@@ -4375,8 +4390,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet)
 	}
 
 done:
-	priv->s_flags |= RVT_S_ACK_PENDING;
-	hfi1_schedule_tid_send(qp);
+	tid_rdma_schedule_ack(qp);
 exit:
 	priv->r_next_psn_kdeth = flow->flow_state.r_next_psn;
 	if (fecn)
@@ -4388,10 +4402,7 @@ send_nak:
 	if (!priv->s_nak_state) {
 		priv->s_nak_state = IB_NAK_PSN_ERROR;
 		priv->s_nak_psn = flow->flow_state.r_next_psn;
-		priv->s_flags |= RVT_S_ACK_PENDING;
-		if (priv->r_tid_ack == HFI1_QP_WQE_INVALID)
-			priv->r_tid_ack = priv->r_tid_tail;
-		hfi1_schedule_tid_send(qp);
+		tid_rdma_trigger_ack(qp);
 	}
 	goto done;
 }
@@ -4939,8 +4950,7 @@ void hfi1_rc_rcv_tid_rdma_resync(struct hfi1_packet *packet)
 	qpriv->resync = true;
 	/* RESYNC request always gets a TID RDMA ACK. */
 	qpriv->s_nak_state = 0;
-	qpriv->s_flags |= RVT_S_ACK_PENDING;
-	hfi1_schedule_tid_send(qp);
+	tid_rdma_trigger_ack(qp);
 bail:
 	if (fecn)
 		qp->s_flags |= RVT_S_ECN;
-- 
cgit v1.2.3-59-g8ed1b


From c2be3865a1763c4be39574937e1aae27e917af4d Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan@intel.com>
Date: Fri, 25 Oct 2019 15:58:36 -0400
Subject: IB/hfi1: Calculate flow weight based on QP MTU for TID RDMA

For a TID RDMA WRITE request, a QP on the responder side could be put into
a queue when a hardware flow is not available. A RNR NAK will be returned
to the requester with a RNR timeout value based on the position of the QP
in the queue. The tid_rdma_flow_wt variable is used to calculate the
timeout value and is determined by using a MTU of 4096 at the module
loading time. This could reduce the timeout value by half from the desired
value, leading to excessive RNR retries.

This patch fixes the issue by calculating the flow weight with the real
MTU assigned to the QP.

Fixes: 07b923701e38 ("IB/hfi1: Add functions to receive TID RDMA WRITE request")
Link: https://lore.kernel.org/r/20191025195836.106825.77769.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/init.c     |  1 -
 drivers/infiniband/hw/hfi1/tid_rdma.c | 13 +++++--------
 drivers/infiniband/hw/hfi1/tid_rdma.h |  3 +--
 3 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 71cb9525c074..26b792bb1027 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1489,7 +1489,6 @@ static int __init hfi1_mod_init(void)
 		goto bail_dev;
 	}
 
-	hfi1_compute_tid_rdma_flow_wt();
 	/*
 	 * These must be called before the driver is registered with
 	 * the PCI subsystem.
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index 73bc78ba288e..e53f542b60af 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -107,8 +107,6 @@ static u32 mask_generation(u32 a)
  * C - Capcode
  */
 
-static u32 tid_rdma_flow_wt;
-
 static void tid_rdma_trigger_resume(struct work_struct *work);
 static void hfi1_kern_exp_rcv_free_flows(struct tid_rdma_request *req);
 static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req,
@@ -3388,18 +3386,17 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 	return sizeof(ohdr->u.tid_rdma.w_req) / sizeof(u32);
 }
 
-void hfi1_compute_tid_rdma_flow_wt(void)
+static u32 hfi1_compute_tid_rdma_flow_wt(struct rvt_qp *qp)
 {
 	/*
 	 * Heuristic for computing the RNR timeout when waiting on the flow
 	 * queue. Rather than a computationaly expensive exact estimate of when
 	 * a flow will be available, we assume that if a QP is at position N in
 	 * the flow queue it has to wait approximately (N + 1) * (number of
-	 * segments between two sync points), assuming PMTU of 4K. The rationale
-	 * for this is that flows are released and recycled at each sync point.
+	 * segments between two sync points). The rationale for this is that
+	 * flows are released and recycled at each sync point.
 	 */
-	tid_rdma_flow_wt = MAX_TID_FLOW_PSN * enum_to_mtu(OPA_MTU_4096) /
-		TID_RDMA_MAX_SEGMENT_SIZE;
+	return (MAX_TID_FLOW_PSN * qp->pmtu) >> TID_RDMA_SEGMENT_SHIFT;
 }
 
 static u32 position_in_queue(struct hfi1_qp_priv *qpriv,
@@ -3522,7 +3519,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx)
 		if (qpriv->flow_state.index >= RXE_NUM_TID_FLOWS) {
 			ret = hfi1_kern_setup_hw_flow(qpriv->rcd, qp);
 			if (ret) {
-				to_seg = tid_rdma_flow_wt *
+				to_seg = hfi1_compute_tid_rdma_flow_wt(qp) *
 					position_in_queue(qpriv,
 							  &rcd->flow_queue);
 				break;
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.h b/drivers/infiniband/hw/hfi1/tid_rdma.h
index 1c536185261e..6e82df2190b7 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.h
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.h
@@ -17,6 +17,7 @@
 #define TID_RDMA_MIN_SEGMENT_SIZE       BIT(18)   /* 256 KiB (for now) */
 #define TID_RDMA_MAX_SEGMENT_SIZE       BIT(18)   /* 256 KiB (for now) */
 #define TID_RDMA_MAX_PAGES              (BIT(18) >> PAGE_SHIFT)
+#define TID_RDMA_SEGMENT_SHIFT		18
 
 /*
  * Bit definitions for priv->s_flags.
@@ -274,8 +275,6 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 				  struct ib_other_headers *ohdr,
 				  u32 *bth1, u32 *bth2, u32 *len);
 
-void hfi1_compute_tid_rdma_flow_wt(void);
-
 void hfi1_rc_rcv_tid_rdma_write_req(struct hfi1_packet *packet);
 
 u32 hfi1_build_tid_rdma_write_resp(struct rvt_qp *qp, struct rvt_ack_entry *e,
-- 
cgit v1.2.3-59-g8ed1b


From ce8e8087cf3b5b4f19d29248bfc7deef95525490 Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan@intel.com>
Date: Fri, 25 Oct 2019 15:58:42 -0400
Subject: IB/hfi1: TID RDMA WRITE should not return IB_WC_RNR_RETRY_EXC_ERR

Normal RDMA WRITE request never returns IB_WC_RNR_RETRY_EXC_ERR to ULPs
because it does not need post receive buffer on the responder side.
Consequently, as an enhancement to normal RDMA WRITE request inside the
hfi1 driver, TID RDMA WRITE request should not return such an error status
to ULPs, although it does receive RNR NAKs from the responder when TID
resources are not available. This behavior is violated when
qp->s_rnr_retry_cnt is set in current hfi1 implementation.

This patch enforces these semantics by avoiding any reaction to the updates
of the RNR QP attributes.

Fixes: 3c6cb20a0d17 ("IB/hfi1: Add TID RDMA WRITE functionality into RDMA verbs")
Link: https://lore.kernel.org/r/20191025195842.106825.71532.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/rc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 513a8aac9ccd..1a3c647675a7 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -2209,15 +2209,15 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode,
 		if (qp->s_flags & RVT_S_WAIT_RNR)
 			goto bail_stop;
 		rdi = ib_to_rvt(qp->ibqp.device);
-		if (qp->s_rnr_retry == 0 &&
-		    !((rdi->post_parms[wqe->wr.opcode].flags &
-		      RVT_OPERATION_IGN_RNR_CNT) &&
-		      qp->s_rnr_retry_cnt == 0)) {
-			status = IB_WC_RNR_RETRY_EXC_ERR;
-			goto class_b;
+		if (!(rdi->post_parms[wqe->wr.opcode].flags &
+		       RVT_OPERATION_IGN_RNR_CNT)) {
+			if (qp->s_rnr_retry == 0) {
+				status = IB_WC_RNR_RETRY_EXC_ERR;
+				goto class_b;
+			}
+			if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0)
+				qp->s_rnr_retry--;
 		}
-		if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0)
-			qp->s_rnr_retry--;
 
 		/*
 		 * The last valid PSN is the previous PSN. For TID RDMA WRITE
-- 
cgit v1.2.3-59-g8ed1b


From 333ee7e2d0b6590cde2bea3e17f30262e0dc0706 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 29 Oct 2019 08:27:36 +0200
Subject: RDMA/hfi1: Delete unreachable code

All callers allocate MAD structures with proper sizes, there is no need to
recheck it.

Link: https://lore.kernel.org/r/20191029062745.7932-8-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/mad.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index d8ff063a5419..a54746f4a0ae 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -4921,10 +4921,6 @@ int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 {
 	switch (in_mad->base_version) {
 	case OPA_MGMT_BASE_VERSION:
-		if (unlikely(in_mad_size != sizeof(struct opa_mad))) {
-			dev_err(ibdev->dev.parent, "invalid in_mad_size\n");
-			return IB_MAD_RESULT_FAILURE;
-		}
 		return hfi1_process_opa_mad(ibdev, mad_flags, port,
 					    in_wc, in_grh,
 					    (struct opa_mad *)in_mad,
-- 
cgit v1.2.3-59-g8ed1b


From e26e7b88f6b7482cbff633c6fc9eaee3ecbd41b1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 29 Oct 2019 08:27:45 +0200
Subject: RDMA: Change MAD processing function to remove extra casting and
 parameter

All users of process_mad() converts input pointers from ib_mad_hdr to be
ib_mad, update the function declaration to use ib_mad directly.

Also remove not used input MAD size parameter.

Link: https://lore.kernel.org/r/20191029062745.7932-17-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Tested-By: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/mad.c            | 12 +++---
 drivers/infiniband/core/sysfs.c          |  6 +--
 drivers/infiniband/hw/hfi1/mad.c         | 13 +++---
 drivers/infiniband/hw/hfi1/verbs.h       |  5 +--
 drivers/infiniband/hw/mlx4/mad.c         | 25 +++++-------
 drivers/infiniband/hw/mlx4/mlx4_ib.h     |  7 ++--
 drivers/infiniband/hw/mlx5/mad.c         | 24 +++++------
 drivers/infiniband/hw/mlx5/mlx5_ib.h     |  5 +--
 drivers/infiniband/hw/mthca/mthca_dev.h  | 12 ++----
 drivers/infiniband/hw/mthca/mthca_mad.c  | 70 ++++++++++++++------------------
 drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 17 +++-----
 drivers/infiniband/hw/ocrdma/ocrdma_ah.h | 11 ++---
 drivers/infiniband/hw/qedr/verbs.c       | 17 ++------
 drivers/infiniband/hw/qedr/verbs.h       |  7 ++--
 drivers/infiniband/hw/qib/qib_mad.c      | 15 +++----
 drivers/infiniband/hw/qib/qib_verbs.h    |  5 +--
 include/rdma/ib_verbs.h                  |  7 ++--
 17 files changed, 104 insertions(+), 154 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 8adb487eb314..c54db13fa9b0 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -913,9 +913,9 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 
 	/* No GRH for DR SMP */
 	ret = device->ops.process_mad(device, 0, port_num, &mad_wc, NULL,
-				      (const struct ib_mad_hdr *)smp, mad_size,
-				      (struct ib_mad_hdr *)mad_priv->mad,
-				      &mad_size, &out_mad_pkey_index);
+				      (const struct ib_mad *)smp,
+				      (struct ib_mad *)mad_priv->mad, &mad_size,
+				      &out_mad_pkey_index);
 	switch (ret)
 	{
 	case IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY:
@@ -2321,9 +2321,9 @@ static void ib_mad_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	if (port_priv->device->ops.process_mad) {
 		ret = port_priv->device->ops.process_mad(
 			port_priv->device, 0, port_priv->port_num, wc,
-			&recv->grh, (const struct ib_mad_hdr *)recv->mad,
-			recv->mad_size, (struct ib_mad_hdr *)response->mad,
-			&mad_size, &resp_mad_pkey_index);
+			&recv->grh, (const struct ib_mad *)recv->mad,
+			(struct ib_mad *)response->mad, &mad_size,
+			&resp_mad_pkey_index);
 
 		if (opa)
 			wc->pkey_index = resp_mad_pkey_index;
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 62c756ea5668..087682e6969e 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -497,10 +497,8 @@ static int get_perf_mad(struct ib_device *dev, int port_num, __be16 attr,
 	if (attr != IB_PMA_CLASS_PORT_INFO)
 		in_mad->data[41] = port_num;	/* PortSelect field */
 
-	if ((dev->ops.process_mad(dev, IB_MAD_IGNORE_MKEY,
-				  port_num, NULL, NULL,
-				  (const struct ib_mad_hdr *)in_mad, mad_size,
-				  (struct ib_mad_hdr *)out_mad, &mad_size,
+	if ((dev->ops.process_mad(dev, IB_MAD_IGNORE_MKEY, port_num, NULL, NULL,
+				  in_mad, out_mad, &mad_size,
 				  &out_mad_pkey_index) &
 	     (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) !=
 	    (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) {
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index a54746f4a0ae..a51bcd2b4391 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -4915,11 +4915,10 @@ static int hfi1_process_ib_mad(struct ib_device *ibdev, int mad_flags, u8 port,
  */
 int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		     const struct ib_mad_hdr *in_mad, size_t in_mad_size,
-		     struct ib_mad_hdr *out_mad, size_t *out_mad_size,
-		     u16 *out_mad_pkey_index)
+		     const struct ib_mad *in_mad, struct ib_mad *out_mad,
+		     size_t *out_mad_size, u16 *out_mad_pkey_index)
 {
-	switch (in_mad->base_version) {
+	switch (in_mad->mad_hdr.base_version) {
 	case OPA_MGMT_BASE_VERSION:
 		return hfi1_process_opa_mad(ibdev, mad_flags, port,
 					    in_wc, in_grh,
@@ -4928,10 +4927,8 @@ int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 					    out_mad_size,
 					    out_mad_pkey_index);
 	case IB_MGMT_BASE_VERSION:
-		return hfi1_process_ib_mad(ibdev, mad_flags, port,
-					  in_wc, in_grh,
-					  (const struct ib_mad *)in_mad,
-					  (struct ib_mad *)out_mad);
+		return hfi1_process_ib_mad(ibdev, mad_flags, port, in_wc,
+					   in_grh, in_mad, out_mad);
 	default:
 		break;
 	}
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index ae9582ddbc8f..b0e9bf7cd150 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -330,9 +330,8 @@ void hfi1_sys_guid_chg(struct hfi1_ibport *ibp);
 void hfi1_node_desc_chg(struct hfi1_ibport *ibp);
 int hfi1_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		     const struct ib_mad_hdr *in_mad, size_t in_mad_size,
-		     struct ib_mad_hdr *out_mad, size_t *out_mad_size,
-		     u16 *out_mad_pkey_index);
+		     const struct ib_mad *in_mad, struct ib_mad *out_mad,
+		     size_t *out_mad_size, u16 *out_mad_pkey_index);
 
 /*
  * The PSN_MASK and PSN_SHIFT allow for
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index c6ea4c50da1e..abe68708d6d6 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -983,13 +983,10 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 
 int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad_hdr *in, size_t in_mad_size,
-			struct ib_mad_hdr *out, size_t *out_mad_size,
-			u16 *out_mad_pkey_index)
+			const struct ib_mad *in, struct ib_mad *out,
+			size_t *out_mad_size, u16 *out_mad_pkey_index)
 {
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
-	const struct ib_mad *in_mad = (const struct ib_mad *)in;
-	struct ib_mad *out_mad = (struct ib_mad *)out;
 	enum rdma_link_layer link = rdma_port_get_link_layer(ibdev, port_num);
 
 	/* iboe_process_mad() which uses the HCA flow-counters to implement IB PMA
@@ -997,20 +994,20 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	 */
 	if (link == IB_LINK_LAYER_INFINIBAND) {
 		if (mlx4_is_slave(dev->dev) &&
-		    (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
-		     (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS ||
-		      in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT ||
-		      in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)))
-			return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
-						in_grh, in_mad, out_mad);
+		    (in->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
+		     (in->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS ||
+		      in->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT ||
+		      in->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)))
+			return iboe_process_mad(ibdev, mad_flags, port_num,
+						in_wc, in_grh, in, out);
 
-		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
-				      in_grh, in_mad, out_mad);
+		return ib_process_mad(ibdev, mad_flags, port_num, in_wc, in_grh,
+				      in, out);
 	}
 
 	if (link == IB_LINK_LAYER_ETHERNET)
 		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
-					in_grh, in_mad, out_mad);
+					in_grh, in, out);
 
 	return -EINVAL;
 }
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index eb53bb4c0c91..0d846fea8fdc 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -786,11 +786,10 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
 		 int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
 		 const void *in_mad, void *response_mad);
-int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags,	u8 port_num,
+int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad_hdr *in, size_t in_mad_size,
-			struct ib_mad_hdr *out, size_t *out_mad_size,
-			u16 *out_mad_pkey_index);
+			const struct ib_mad *in, struct ib_mad *out,
+			size_t *out_mad_size, u16 *out_mad_pkey_index);
 int mlx4_ib_mad_init(struct mlx4_ib_dev *dev);
 void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev);
 
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 1c87412a162f..14e0c17de6a9 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -219,15 +219,12 @@ done:
 
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad_hdr *in, size_t in_mad_size,
-			struct ib_mad_hdr *out, size_t *out_mad_size,
-			u16 *out_mad_pkey_index)
+			const struct ib_mad *in, struct ib_mad *out,
+			size_t *out_mad_size, u16 *out_mad_pkey_index)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	const struct ib_mad *in_mad = (const struct ib_mad *)in;
-	struct ib_mad *out_mad = (struct ib_mad *)out;
-	u8 mgmt_class = in_mad->mad_hdr.mgmt_class;
-	u8 method = in_mad->mad_hdr.method;
+	u8 mgmt_class = in->mad_hdr.mgmt_class;
+	u8 method = in->mad_hdr.method;
 	u16 slid;
 	int err;
 
@@ -247,13 +244,13 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 
 		/* Don't process SMInfo queries -- the SMA can't handle them.
 		 */
-		if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO)
+		if (in->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO)
 			return IB_MAD_RESULT_SUCCESS;
 	} break;
 	case IB_MGMT_CLASS_PERF_MGMT:
 		if (MLX5_CAP_GEN(dev->mdev, vport_counters) &&
 		    method == IB_MGMT_METHOD_GET)
-			return process_pma_cmd(dev, port_num, in_mad, out_mad);
+			return process_pma_cmd(dev, port_num, in, out);
 		/* fallthrough */
 	case MLX5_IB_VENDOR_CLASS1:
 		/* fallthrough */
@@ -267,16 +264,15 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		return IB_MAD_RESULT_SUCCESS;
 	}
 
-	err = mlx5_MAD_IFC(to_mdev(ibdev),
-			   mad_flags & IB_MAD_IGNORE_MKEY,
-			   mad_flags & IB_MAD_IGNORE_BKEY,
-			   port_num, in_wc, in_grh, in_mad, out_mad);
+	err = mlx5_MAD_IFC(to_mdev(ibdev), mad_flags & IB_MAD_IGNORE_MKEY,
+			   mad_flags & IB_MAD_IGNORE_BKEY, port_num, in_wc,
+			   in_grh, in, out);
 	if (err)
 		return IB_MAD_RESULT_FAILURE;
 
 	/* set return bit in status of directed route responses */
 	if (mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
-		out_mad->mad_hdr.status |= cpu_to_be16(1 << 15);
+		out->mad_hdr.status |= cpu_to_be16(1 << 15);
 
 	if (method == IB_MGMT_METHOD_TRAP_REPRESS)
 		/* no response for trap repress */
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 0bdb8b45ea15..933a2059886b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1192,9 +1192,8 @@ int mlx5_ib_map_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg,
 			 unsigned int *meta_sg_offset);
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-			const struct ib_mad_hdr *in, size_t in_mad_size,
-			struct ib_mad_hdr *out, size_t *out_mad_size,
-			u16 *out_mad_pkey_index);
+			const struct ib_mad *in, struct ib_mad *out,
+			size_t *out_mad_size, u16 *out_mad_pkey_index);
 struct ib_xrcd *mlx5_ib_alloc_xrcd(struct ib_device *ibdev,
 				   struct ib_udata *udata);
 int mlx5_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h
index bfd4eebc1182..599794c5a78f 100644
--- a/drivers/infiniband/hw/mthca/mthca_dev.h
+++ b/drivers/infiniband/hw/mthca/mthca_dev.h
@@ -576,14 +576,10 @@ enum ib_rate mthca_rate_to_ib(struct mthca_dev *dev, u8 mthca_rate, u8 port);
 int mthca_multicast_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);
 int mthca_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);
 
-int mthca_process_mad(struct ib_device *ibdev,
-		      int mad_flags,
-		      u8 port_num,
-		      const struct ib_wc *in_wc,
-		      const struct ib_grh *in_grh,
-		      const struct ib_mad_hdr *in, size_t in_mad_size,
-		      struct ib_mad_hdr *out, size_t *out_mad_size,
-		      u16 *out_mad_pkey_index);
+int mthca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
+		      const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		      const struct ib_mad *in, struct ib_mad *out,
+		      size_t *out_mad_size, u16 *out_mad_pkey_index);
 int mthca_create_agents(struct mthca_dev *dev);
 void mthca_free_agents(struct mthca_dev *dev);
 
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index 0893604d2a62..99aa8183a7f2 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -196,26 +196,19 @@ static void forward_trap(struct mthca_dev *dev,
 	}
 }
 
-int mthca_process_mad(struct ib_device *ibdev,
-		      int mad_flags,
-		      u8 port_num,
-		      const struct ib_wc *in_wc,
-		      const struct ib_grh *in_grh,
-		      const struct ib_mad_hdr *in, size_t in_mad_size,
-		      struct ib_mad_hdr *out, size_t *out_mad_size,
-		      u16 *out_mad_pkey_index)
+int mthca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
+		      const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		      const struct ib_mad *in, struct ib_mad *out,
+		      size_t *out_mad_size, u16 *out_mad_pkey_index)
 {
 	int err;
 	u16 slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
-	const struct ib_mad *in_mad = (const struct ib_mad *)in;
-	struct ib_mad *out_mad = (struct ib_mad *)out;
 
 	/* Forward locally generated traps to the SM */
-	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&
-	    slid == 0) {
-		forward_trap(to_mdev(ibdev), port_num, in_mad);
+	if (in->mad_hdr.method == IB_MGMT_METHOD_TRAP && !slid) {
+		forward_trap(to_mdev(ibdev), port_num, in);
 		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
 	}
 
@@ -225,40 +218,39 @@ int mthca_process_mad(struct ib_device *ibdev,
 	 * Only handle PMA and Mellanox vendor-specific class gets and
 	 * sets for other classes.
 	 */
-	if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
-	    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
-		if (in_mad->mad_hdr.method   != IB_MGMT_METHOD_GET &&
-		    in_mad->mad_hdr.method   != IB_MGMT_METHOD_SET &&
-		    in_mad->mad_hdr.method   != IB_MGMT_METHOD_TRAP_REPRESS)
+	if (in->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
+	    in->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
+		if (in->mad_hdr.method != IB_MGMT_METHOD_GET &&
+		    in->mad_hdr.method != IB_MGMT_METHOD_SET &&
+		    in->mad_hdr.method != IB_MGMT_METHOD_TRAP_REPRESS)
 			return IB_MAD_RESULT_SUCCESS;
 
 		/*
 		 * Don't process SMInfo queries or vendor-specific
 		 * MADs -- the SMA can't handle them.
 		 */
-		if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO ||
-		    ((in_mad->mad_hdr.attr_id & IB_SMP_ATTR_VENDOR_MASK) ==
+		if (in->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO ||
+		    ((in->mad_hdr.attr_id & IB_SMP_ATTR_VENDOR_MASK) ==
 		     IB_SMP_ATTR_VENDOR_MASK))
 			return IB_MAD_RESULT_SUCCESS;
-	} else if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT ||
-		   in_mad->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS1     ||
-		   in_mad->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS2) {
-		if (in_mad->mad_hdr.method  != IB_MGMT_METHOD_GET &&
-		    in_mad->mad_hdr.method  != IB_MGMT_METHOD_SET)
+	} else if (in->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT ||
+		   in->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS1     ||
+		   in->mad_hdr.mgmt_class == MTHCA_VENDOR_CLASS2) {
+		if (in->mad_hdr.method != IB_MGMT_METHOD_GET &&
+		    in->mad_hdr.method != IB_MGMT_METHOD_SET)
 			return IB_MAD_RESULT_SUCCESS;
 	} else
 		return IB_MAD_RESULT_SUCCESS;
-	if ((in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
-	     in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
-	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
-	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
+	if ((in->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
+	     in->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
+	    in->mad_hdr.method == IB_MGMT_METHOD_SET &&
+	    in->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
 		prev_lid = ib_lid_cpu16(pattr.lid);
 
-	err = mthca_MAD_IFC(to_mdev(ibdev),
-			    mad_flags & IB_MAD_IGNORE_MKEY,
-			    mad_flags & IB_MAD_IGNORE_BKEY,
-			    port_num, in_wc, in_grh, in_mad, out_mad);
+	err = mthca_MAD_IFC(to_mdev(ibdev), mad_flags & IB_MAD_IGNORE_MKEY,
+			    mad_flags & IB_MAD_IGNORE_BKEY, port_num, in_wc,
+			    in_grh, in, out);
 	if (err == -EBADMSG)
 		return IB_MAD_RESULT_SUCCESS;
 	else if (err) {
@@ -266,16 +258,16 @@ int mthca_process_mad(struct ib_device *ibdev,
 		return IB_MAD_RESULT_FAILURE;
 	}
 
-	if (!out_mad->mad_hdr.status) {
-		smp_snoop(ibdev, port_num, in_mad, prev_lid);
-		node_desc_override(ibdev, out_mad);
+	if (!out->mad_hdr.status) {
+		smp_snoop(ibdev, port_num, in, prev_lid);
+		node_desc_override(ibdev, out);
 	}
 
 	/* set return bit in status of directed route responses */
-	if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
-		out_mad->mad_hdr.status |= cpu_to_be16(1 << 15);
+	if (in->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+		out->mad_hdr.status |= cpu_to_be16(1 << 15);
 
-	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS)
+	if (in->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS)
 		/* no response for trap repress */
 		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
 
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 4098508b9240..2b7f00ac41b0 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -247,23 +247,18 @@ int ocrdma_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr)
 	return 0;
 }
 
-int ocrdma_process_mad(struct ib_device *ibdev,
-		       int process_mad_flags,
-		       u8 port_num,
-		       const struct ib_wc *in_wc,
-		       const struct ib_grh *in_grh,
-		       const struct ib_mad_hdr *in, size_t in_mad_size,
-		       struct ib_mad_hdr *out, size_t *out_mad_size,
+int ocrdma_process_mad(struct ib_device *ibdev, int process_mad_flags,
+		       u8 port_num, const struct ib_wc *in_wc,
+		       const struct ib_grh *in_grh, const struct ib_mad *in,
+		       struct ib_mad *out, size_t *out_mad_size,
 		       u16 *out_mad_pkey_index)
 {
 	int status = IB_MAD_RESULT_SUCCESS;
 	struct ocrdma_dev *dev;
-	const struct ib_mad *in_mad = (const struct ib_mad *)in;
-	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT) {
+	if (in->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT) {
 		dev = get_ocrdma_dev(ibdev);
-		ocrdma_pma_counters(dev, out_mad);
+		ocrdma_pma_counters(dev, out);
 		status |= IB_MAD_RESULT_REPLY;
 	}
 
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
index 64cb82c08664..9780afcde780 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
@@ -56,12 +56,9 @@ int ocrdma_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, u32 flags,
 void ocrdma_destroy_ah(struct ib_ah *ah, u32 flags);
 int ocrdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
 
-int ocrdma_process_mad(struct ib_device *,
-		       int process_mad_flags,
-		       u8 port_num,
-		       const struct ib_wc *in_wc,
-		       const struct ib_grh *in_grh,
-		       const struct ib_mad_hdr *in, size_t in_mad_size,
-		       struct ib_mad_hdr *out, size_t *out_mad_size,
+int ocrdma_process_mad(struct ib_device *dev, int process_mad_flags,
+		       u8 port_num, const struct ib_wc *in_wc,
+		       const struct ib_grh *in_grh, const struct ib_mad *in,
+		       struct ib_mad *out, size_t *out_mad_size,
 		       u16 *out_mad_pkey_index);
 #endif				/* __OCRDMA_AH_H__ */
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 8096b8fcab4e..fea95faa3b21 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -4346,19 +4346,10 @@ int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 }
 
 int qedr_process_mad(struct ib_device *ibdev, int process_mad_flags,
-		     u8 port_num,
-		     const struct ib_wc *in_wc,
-		     const struct ib_grh *in_grh,
-		     const struct ib_mad_hdr *mad_hdr,
-		     size_t in_mad_size, struct ib_mad_hdr *out_mad,
-		     size_t *out_mad_size, u16 *out_mad_pkey_index)
+		     u8 port_num, const struct ib_wc *in_wc,
+		     const struct ib_grh *in_grh, const struct ib_mad *in,
+		     struct ib_mad *out_mad, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index)
 {
-	struct qedr_dev *dev = get_qedr_dev(ibdev);
-
-	DP_DEBUG(dev, QEDR_MSG_GSI,
-		 "QEDR_PROCESS_MAD in_mad %x %x %x %x %x %x %x %x\n",
-		 mad_hdr->attr_id, mad_hdr->base_version, mad_hdr->attr_mod,
-		 mad_hdr->class_specific, mad_hdr->class_version,
-		 mad_hdr->method, mad_hdr->mgmt_class, mad_hdr->status);
 	return IB_MAD_RESULT_SUCCESS;
 }
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
index 620472116c6d..18027844eb87 100644
--- a/drivers/infiniband/hw/qedr/verbs.h
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -92,10 +92,9 @@ int qedr_post_recv(struct ib_qp *, const struct ib_recv_wr *,
 		   const struct ib_recv_wr **bad_wr);
 int qedr_process_mad(struct ib_device *ibdev, int process_mad_flags,
 		     u8 port_num, const struct ib_wc *in_wc,
-		     const struct ib_grh *in_grh,
-		     const struct ib_mad_hdr *in_mad,
-		     size_t in_mad_size, struct ib_mad_hdr *out_mad,
-		     size_t *out_mad_size, u16 *out_mad_pkey_index);
+		     const struct ib_grh *in_grh, const struct ib_mad *in_mad,
+		     struct ib_mad *out_mad, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index);
 
 int qedr_port_immutable(struct ib_device *ibdev, u8 port_num,
 			struct ib_port_immutable *immutable);
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index b259aaf85d4a..79bb83222e8d 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -2386,24 +2386,21 @@ bail:
  */
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		    const struct ib_mad_hdr *in, size_t in_mad_size,
-		    struct ib_mad_hdr *out, size_t *out_mad_size,
-		    u16 *out_mad_pkey_index)
+		    const struct ib_mad *in, struct ib_mad *out,
+		    size_t *out_mad_size, u16 *out_mad_pkey_index)
 {
 	int ret;
 	struct qib_ibport *ibp = to_iport(ibdev, port);
 	struct qib_pportdata *ppd = ppd_from_ibp(ibp);
-	const struct ib_mad *in_mad = (const struct ib_mad *)in;
-	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	switch (in_mad->mad_hdr.mgmt_class) {
+	switch (in->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
 	case IB_MGMT_CLASS_SUBN_LID_ROUTED:
-		ret = process_subn(ibdev, mad_flags, port, in_mad, out_mad);
+		ret = process_subn(ibdev, mad_flags, port, in, out);
 		goto bail;
 
 	case IB_MGMT_CLASS_PERF_MGMT:
-		ret = process_perf(ibdev, port, in_mad, out_mad);
+		ret = process_perf(ibdev, port, in, out);
 		goto bail;
 
 	case IB_MGMT_CLASS_CONG_MGMT:
@@ -2412,7 +2409,7 @@ int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 			ret = IB_MAD_RESULT_SUCCESS;
 			goto bail;
 		}
-		ret = process_cc(ibdev, mad_flags, port, in_mad, out_mad);
+		ret = process_cc(ibdev, mad_flags, port, in, out);
 		goto bail;
 
 	default:
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index 17bdf8acee2f..8bf414b47b96 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -245,9 +245,8 @@ void qib_sys_guid_chg(struct qib_ibport *ibp);
 void qib_node_desc_chg(struct qib_ibport *ibp);
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		    const struct ib_mad_hdr *in, size_t in_mad_size,
-		    struct ib_mad_hdr *out, size_t *out_mad_size,
-		    u16 *out_mad_pkey_index);
+		    const struct ib_mad *in, struct ib_mad *out,
+		    size_t *out_mad_size, u16 *out_mad_pkey_index);
 void qib_notify_create_mad_agent(struct rvt_dev_info *rdi, int port_idx);
 void qib_notify_free_mad_agent(struct rvt_dev_info *rdi, int port_idx);
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 416e72ea80d9..663fa16caa76 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2123,7 +2123,7 @@ struct ib_flow_action {
 	atomic_t			usecnt;
 };
 
-struct ib_mad_hdr;
+struct ib_mad;
 struct ib_grh;
 
 enum ib_process_mad_flags {
@@ -2301,9 +2301,8 @@ struct ib_device_ops {
 	int (*process_mad)(struct ib_device *device, int process_mad_flags,
 			   u8 port_num, const struct ib_wc *in_wc,
 			   const struct ib_grh *in_grh,
-			   const struct ib_mad_hdr *in_mad, size_t in_mad_size,
-			   struct ib_mad_hdr *out_mad, size_t *out_mad_size,
-			   u16 *out_mad_pkey_index);
+			   const struct ib_mad *in_mad, struct ib_mad *out_mad,
+			   size_t *out_mad_size, u16 *out_mad_pkey_index);
 	int (*query_device)(struct ib_device *device,
 			    struct ib_device_attr *device_attr,
 			    struct ib_udata *udata);
-- 
cgit v1.2.3-59-g8ed1b


From ab818362c9054beb950b97a09ce7b0d56f5a32a1 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 22 Nov 2019 08:15:19 +0000
Subject: net: use rhashtable_lookup() instead of rhashtable_lookup_fast()

rhashtable_lookup_fast() internally calls rcu_read_lock() then,
calls rhashtable_lookup(). So if rcu_read_lock() is already held,
rhashtable_lookup() is enough.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/infiniband/hw/hfi1/sdma.c                | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  | 2 +-
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 4 ++--
 net/tipc/socket.c                                | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index c61b6022575e..5774dfc22e18 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -881,8 +881,8 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd,
 
 	cpu_id = smp_processor_id();
 	rcu_read_lock();
-	rht_node = rhashtable_lookup_fast(dd->sdma_rht, &cpu_id,
-					  sdma_rht_params);
+	rht_node = rhashtable_lookup(dd->sdma_rht, &cpu_id,
+				     sdma_rht_params);
 
 	if (rht_node && rht_node->map[vl]) {
 		struct sdma_rht_map_elem *map = rht_node->map[vl];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 761fc35c4aab..0d5d84b5fa23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3876,7 +3876,7 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	int err;
 
 	rcu_read_lock();
-	flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
+	flow = rhashtable_lookup(tc_ht, &f->cookie, tc_ht_params);
 	if (!flow || !same_flow_direction(flow, flags)) {
 		err = -EINVAL;
 		goto errout;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 06927ba5a3ae..95a0d3910e31 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -458,8 +458,8 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
 		return -EINVAL;
 
 	rcu_read_lock();
-	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map_id,
-					nfp_bpf_maps_neutral_params);
+	record = rhashtable_lookup(&bpf->maps_neutral, &map_id,
+				   nfp_bpf_maps_neutral_params);
 	if (!record || map_id_full > U32_MAX) {
 		rcu_read_unlock();
 		cmsg_warn(bpf, "perf event: map id %lld (0x%llx) not recognized, dropping event\n",
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 5d7859aac78e..a1c8d722ca20 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2880,7 +2880,7 @@ static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)
 	struct tipc_sock *tsk;
 
 	rcu_read_lock();
-	tsk = rhashtable_lookup_fast(&tn->sk_rht, &portid, tsk_rht_params);
+	tsk = rhashtable_lookup(&tn->sk_rht, &portid, tsk_rht_params);
 	if (tsk)
 		sock_hold(&tsk->sk);
 	rcu_read_unlock();
-- 
cgit v1.2.3-59-g8ed1b


From 3889551db21257919e0ef3449dfcc23450f9a5bd Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 12 Nov 2019 16:22:23 -0400
Subject: RDMA/hfi1: Use mmu_interval_notifier_insert for user_exp_rcv

This converts one of the two users of mmu_notifiers to use the new API.
The conversion is fairly straightforward, however the existing use of
notifiers here seems to be racey.

Link: https://lore.kernel.org/r/20191112202231.3856-7-jgg@ziepe.ca
Tested-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/file_ops.c     |   2 +-
 drivers/infiniband/hw/hfi1/hfi.h          |   2 +-
 drivers/infiniband/hw/hfi1/user_exp_rcv.c | 146 ++++++++++++------------------
 drivers/infiniband/hw/hfi1/user_exp_rcv.h |   3 +-
 4 files changed, 60 insertions(+), 93 deletions(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index f9a7e9d29c8b..7c5e3fb22413 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -1138,7 +1138,7 @@ static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len)
 			HFI1_CAP_UGET_MASK(uctxt->flags, MASK) |
 			HFI1_CAP_KGET_MASK(uctxt->flags, K2U);
 	/* adjust flag if this fd is not able to cache */
-	if (!fd->handler)
+	if (!fd->use_mn)
 		cinfo.runtime_flags |= HFI1_CAP_TID_UNMAP; /* no caching */
 
 	cinfo.num_active = hfi1_count_active_units();
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index fa45350a9a1d..fc10d65fc3e1 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1444,7 +1444,7 @@ struct hfi1_filedata {
 	/* for cpu affinity; -1 if none */
 	int rec_cpu_num;
 	u32 tid_n_pinned;
-	struct mmu_rb_handler *handler;
+	bool use_mn;
 	struct tid_rb_node **entry_to_rb;
 	spinlock_t tid_lock; /* protect tid_[limit,used] counters */
 	u32 tid_limit;
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 3592a9ec155e..f05742ac0949 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -59,11 +59,11 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 			      struct tid_user_buf *tbuf,
 			      u32 rcventry, struct tid_group *grp,
 			      u16 pageidx, unsigned int npages);
-static int tid_rb_insert(void *arg, struct mmu_rb_node *node);
 static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
 				    struct tid_rb_node *tnode);
-static void tid_rb_remove(void *arg, struct mmu_rb_node *node);
-static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode);
+static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
+			      const struct mmu_notifier_range *range,
+			      unsigned long cur_seq);
 static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *,
 			    struct tid_group *grp,
 			    unsigned int start, u16 count,
@@ -73,10 +73,8 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
 			      struct tid_group **grp);
 static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node);
 
-static struct mmu_rb_ops tid_rb_ops = {
-	.insert = tid_rb_insert,
-	.remove = tid_rb_remove,
-	.invalidate = tid_rb_invalidate
+static const struct mmu_interval_notifier_ops tid_mn_ops = {
+	.invalidate = tid_rb_invalidate,
 };
 
 /*
@@ -87,7 +85,6 @@ static struct mmu_rb_ops tid_rb_ops = {
 int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
 			   struct hfi1_ctxtdata *uctxt)
 {
-	struct hfi1_devdata *dd = uctxt->dd;
 	int ret = 0;
 
 	spin_lock_init(&fd->tid_lock);
@@ -109,20 +106,7 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
 			fd->entry_to_rb = NULL;
 			return -ENOMEM;
 		}
-
-		/*
-		 * Register MMU notifier callbacks. If the registration
-		 * fails, continue without TID caching for this context.
-		 */
-		ret = hfi1_mmu_rb_register(fd, fd->mm, &tid_rb_ops,
-					   dd->pport->hfi1_wq,
-					   &fd->handler);
-		if (ret) {
-			dd_dev_info(dd,
-				    "Failed MMU notifier registration %d\n",
-				    ret);
-			ret = 0;
-		}
+		fd->use_mn = true;
 	}
 
 	/*
@@ -139,7 +123,7 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
 	 * init.
 	 */
 	spin_lock(&fd->tid_lock);
-	if (uctxt->subctxt_cnt && fd->handler) {
+	if (uctxt->subctxt_cnt && fd->use_mn) {
 		u16 remainder;
 
 		fd->tid_limit = uctxt->expected_count / uctxt->subctxt_cnt;
@@ -158,18 +142,10 @@ void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd)
 {
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
 
-	/*
-	 * The notifier would have been removed when the process'es mm
-	 * was freed.
-	 */
-	if (fd->handler) {
-		hfi1_mmu_rb_unregister(fd->handler);
-	} else {
-		if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list))
-			unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd);
-		if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list))
-			unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd);
-	}
+	if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list))
+		unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd);
+	if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list))
+		unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd);
 
 	kfree(fd->invalid_tids);
 	fd->invalid_tids = NULL;
@@ -201,7 +177,7 @@ static void unpin_rcv_pages(struct hfi1_filedata *fd,
 
 	if (mapped) {
 		pci_unmap_single(dd->pcidev, node->dma_addr,
-				 node->mmu.len, PCI_DMA_FROMDEVICE);
+				 node->npages * PAGE_SIZE, PCI_DMA_FROMDEVICE);
 		pages = &node->pages[idx];
 	} else {
 		pages = &tidbuf->pages[idx];
@@ -777,8 +753,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 		return -EFAULT;
 	}
 
-	node->mmu.addr = tbuf->vaddr + (pageidx * PAGE_SIZE);
-	node->mmu.len = npages * PAGE_SIZE;
+	node->fdata = fd;
 	node->phys = page_to_phys(pages[0]);
 	node->npages = npages;
 	node->rcventry = rcventry;
@@ -787,23 +762,35 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
 	node->freed = false;
 	memcpy(node->pages, pages, sizeof(struct page *) * npages);
 
-	if (!fd->handler)
-		ret = tid_rb_insert(fd, &node->mmu);
-	else
-		ret = hfi1_mmu_rb_insert(fd->handler, &node->mmu);
-
-	if (ret) {
-		hfi1_cdbg(TID, "Failed to insert RB node %u 0x%lx, 0x%lx %d",
-			  node->rcventry, node->mmu.addr, node->phys, ret);
-		pci_unmap_single(dd->pcidev, phys, npages * PAGE_SIZE,
-				 PCI_DMA_FROMDEVICE);
-		kfree(node);
-		return -EFAULT;
+	if (fd->use_mn) {
+		ret = mmu_interval_notifier_insert(
+			&node->notifier, fd->mm,
+			tbuf->vaddr + (pageidx * PAGE_SIZE), npages * PAGE_SIZE,
+			&tid_mn_ops);
+		if (ret)
+			goto out_unmap;
+		/*
+		 * FIXME: This is in the wrong order, the notifier should be
+		 * established before the pages are pinned by pin_rcv_pages.
+		 */
+		mmu_interval_read_begin(&node->notifier);
 	}
+	fd->entry_to_rb[node->rcventry - uctxt->expected_base] = node;
+
 	hfi1_put_tid(dd, rcventry, PT_EXPECTED, phys, ilog2(npages) + 1);
 	trace_hfi1_exp_tid_reg(uctxt->ctxt, fd->subctxt, rcventry, npages,
-			       node->mmu.addr, node->phys, phys);
+			       node->notifier.interval_tree.start, node->phys,
+			       phys);
 	return 0;
+
+out_unmap:
+	hfi1_cdbg(TID, "Failed to insert RB node %u 0x%lx, 0x%lx %d",
+		  node->rcventry, node->notifier.interval_tree.start,
+		  node->phys, ret);
+	pci_unmap_single(dd->pcidev, phys, npages * PAGE_SIZE,
+			 PCI_DMA_FROMDEVICE);
+	kfree(node);
+	return -EFAULT;
 }
 
 static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
@@ -833,10 +820,9 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
 	if (grp)
 		*grp = node->grp;
 
-	if (!fd->handler)
-		cacheless_tid_rb_remove(fd, node);
-	else
-		hfi1_mmu_rb_remove(fd->handler, &node->mmu);
+	if (fd->use_mn)
+		mmu_interval_notifier_remove(&node->notifier);
+	cacheless_tid_rb_remove(fd, node);
 
 	return 0;
 }
@@ -847,7 +833,8 @@ static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
 	struct hfi1_devdata *dd = uctxt->dd;
 
 	trace_hfi1_exp_tid_unreg(uctxt->ctxt, fd->subctxt, node->rcventry,
-				 node->npages, node->mmu.addr, node->phys,
+				 node->npages,
+				 node->notifier.interval_tree.start, node->phys,
 				 node->dma_addr);
 
 	/*
@@ -894,30 +881,29 @@ static void unlock_exp_tids(struct hfi1_ctxtdata *uctxt,
 				if (!node || node->rcventry != rcventry)
 					continue;
 
+				if (fd->use_mn)
+					mmu_interval_notifier_remove(
+						&node->notifier);
 				cacheless_tid_rb_remove(fd, node);
 			}
 		}
 	}
 }
 
-/*
- * Always return 0 from this function.  A non-zero return indicates that the
- * remove operation will be called and that memory should be unpinned.
- * However, the driver cannot unpin out from under PSM.  Instead, retain the
- * memory (by returning 0) and inform PSM that the memory is going away.  PSM
- * will call back later when it has removed the memory from its list.
- */
-static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode)
+static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
+			      const struct mmu_notifier_range *range,
+			      unsigned long cur_seq)
 {
-	struct hfi1_filedata *fdata = arg;
-	struct hfi1_ctxtdata *uctxt = fdata->uctxt;
 	struct tid_rb_node *node =
-		container_of(mnode, struct tid_rb_node, mmu);
+		container_of(mni, struct tid_rb_node, notifier);
+	struct hfi1_filedata *fdata = node->fdata;
+	struct hfi1_ctxtdata *uctxt = fdata->uctxt;
 
 	if (node->freed)
-		return 0;
+		return true;
 
-	trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt, node->mmu.addr,
+	trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt,
+				 node->notifier.interval_tree.start,
 				 node->rcventry, node->npages, node->dma_addr);
 	node->freed = true;
 
@@ -946,18 +932,7 @@ static int tid_rb_invalidate(void *arg, struct mmu_rb_node *mnode)
 		fdata->invalid_tid_idx++;
 	}
 	spin_unlock(&fdata->invalid_lock);
-	return 0;
-}
-
-static int tid_rb_insert(void *arg, struct mmu_rb_node *node)
-{
-	struct hfi1_filedata *fdata = arg;
-	struct tid_rb_node *tnode =
-		container_of(node, struct tid_rb_node, mmu);
-	u32 base = fdata->uctxt->expected_base;
-
-	fdata->entry_to_rb[tnode->rcventry - base] = tnode;
-	return 0;
+	return true;
 }
 
 static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
@@ -968,12 +943,3 @@ static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
 	fdata->entry_to_rb[tnode->rcventry - base] = NULL;
 	clear_tid_node(fdata, tnode);
 }
-
-static void tid_rb_remove(void *arg, struct mmu_rb_node *node)
-{
-	struct hfi1_filedata *fdata = arg;
-	struct tid_rb_node *tnode =
-		container_of(node, struct tid_rb_node, mmu);
-
-	cacheless_tid_rb_remove(fdata, tnode);
-}
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
index 43b105de1d54..6257eee083a1 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
@@ -65,7 +65,8 @@ struct tid_user_buf {
 };
 
 struct tid_rb_node {
-	struct mmu_rb_node mmu;
+	struct mmu_interval_notifier notifier;
+	struct hfi1_filedata *fdata;
 	unsigned long phys;
 	struct tid_group *grp;
 	u32 rcventry;
-- 
cgit v1.2.3-59-g8ed1b


From 25d24f4241f7bccdc1978daa026d8847e04a73a6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 22 Nov 2019 15:48:14 +0000
Subject: IB/hfi1: remove redundant assignment to variable ret

The variable ret is being initialized with a value that is never
read and it is being updated later with a new value. The
initialization is redundant and can be removed.

Link: https://lore.kernel.org/r/20191122154814.87257-1-colin.king@canonical.com
Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/hw/hfi1')

diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index cbf7faa5038c..36593f2efe26 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -634,7 +634,7 @@ static void apply_tx_lanes(struct hfi1_pportdata *ppd, u8 field_id,
 			   u32 config_data, const char *message)
 {
 	u8 i;
-	int ret = HCMD_SUCCESS;
+	int ret;
 
 	for (i = 0; i < 4; i++) {
 		ret = load_8051_config(ppd->dd, field_id, i, config_data);
-- 
cgit v1.2.3-59-g8ed1b