From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org,
"Michael J. Ruhl" <michael.j.ruhl@intel.com>,
Mike Marciniszyn <mike.marciniszyn@intel.com>,
Dennis Dalessandro <dennis.dalessandro@intel.com>,
Doug Ledford <dledford@redhat.com>
Subject: [PATCH 4.16 27/52] IB/hfi1: Fix loss of BECN with AHG
Date: Tue, 8 May 2018 10:10:25 +0200 [thread overview]
Message-ID: <20180508073931.780135827@linuxfoundation.org> (raw)
In-Reply-To: <20180508073928.058320984@linuxfoundation.org>
4.16-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mike Marciniszyn <mike.marciniszyn@intel.com>
commit 0a0bcb046b2f0c15b89f8c1b08ad3de601a83c66 upstream.
AHG may be armed to use the stored header, which by design is limited
to edits in the PSN/A 32 bit word (bth2).
When the code is trying to send a BECN, the use of the stored header
will lose the BECN bit.
Fix by avoiding AHG when getting ready to send a BECN. This is
accomplished by always claiming the packet is not a middle packet which
is an AHG precursor. BECNs are not a normal case and this should not
hurt AHG optimizations.
Cc: <stable@vger.kernel.org> # 4.14.x
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/infiniband/hw/hfi1/ruc.c | 50 +++++++++++++++++++++++++++++++--------
1 file changed, 40 insertions(+), 10 deletions(-)
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -733,6 +733,20 @@ static inline void hfi1_make_ruc_bth(str
ohdr->bth[2] = cpu_to_be32(bth2);
}
+/**
+ * hfi1_make_ruc_header_16B - build a 16B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
struct ib_other_headers *ohdr,
u32 bth0, u32 bth2, int middle,
@@ -777,6 +791,12 @@ static inline void hfi1_make_ruc_header_
else
middle = 0;
+ if (qp->s_flags & RVT_S_ECN) {
+ qp->s_flags &= ~RVT_S_ECN;
+ /* we recently received a FECN, so return a BECN */
+ becn = true;
+ middle = 0;
+ }
if (middle)
build_ahg(qp, bth2);
else
@@ -784,11 +804,6 @@ static inline void hfi1_make_ruc_header_
bth0 |= pkey;
bth0 |= extra_bytes << 20;
- if (qp->s_flags & RVT_S_ECN) {
- qp->s_flags &= ~RVT_S_ECN;
- /* we recently received a FECN, so return a BECN */
- becn = true;
- }
hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
if (!ppd->lid)
@@ -806,6 +821,20 @@ static inline void hfi1_make_ruc_header_
pkey, becn, 0, l4, priv->s_sc);
}
+/**
+ * hfi1_make_ruc_header_9B - build a 9B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
struct ib_other_headers *ohdr,
u32 bth0, u32 bth2, int middle,
@@ -839,6 +868,12 @@ static inline void hfi1_make_ruc_header_
else
middle = 0;
+ if (qp->s_flags & RVT_S_ECN) {
+ qp->s_flags &= ~RVT_S_ECN;
+ /* we recently received a FECN, so return a BECN */
+ bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
+ middle = 0;
+ }
if (middle)
build_ahg(qp, bth2);
else
@@ -846,11 +881,6 @@ static inline void hfi1_make_ruc_header_
bth0 |= pkey;
bth0 |= extra_bytes << 20;
- if (qp->s_flags & RVT_S_ECN) {
- qp->s_flags &= ~RVT_S_ECN;
- /* we recently received a FECN, so return a BECN */
- bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
- }
hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
lrh0,
next prev parent reply other threads:[~2018-05-08 8:12 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-08 8:09 [PATCH 4.16 00/52] 4.16.8-stable review Greg Kroah-Hartman
2018-05-08 8:09 ` [PATCH 4.16 01/52] ACPI / button: make module loadable when booted in non-ACPI mode Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 02/52] arm64: Add work around for Arm Cortex-A55 Erratum 1024718 Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 03/52] ALSA: hda - Fix incorrect usage of IS_REACHABLE() Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 04/52] ALSA: pcm: Check PCM state at xfern compat ioctl Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 05/52] ALSA: seq: Fix races at MIDI encoding in snd_virmidi_output_trigger() Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 06/52] ALSA: dice: fix kernel NULL pointer dereference due to invalid calculation for array index Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 07/52] ALSA: aloop: Mark paused device as inactive Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 08/52] ALSA: aloop: Add missing cable lock to ctl API callbacks Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 09/52] errseq: Always report a writeback error once Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 10/52] tracepoint: Do not warn on ENOMEM Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 11/52] scsi: target: Fix fortify_panic kernel exception Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 12/52] Input: leds - fix out of bound access Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 13/52] Input: atmel_mxt_ts - add touchpad button mapping for Samsung Chromebook Pro Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 15/52] rtlwifi: cleanup 8723be ant_sel definition Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 16/52] xfs: prevent creating negative-sized file via INSERT_RANGE Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 17/52] tools: power/acpi, revert to LD = gcc Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 18/52] RDMA/cxgb4: release hw resources on device removal Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 19/52] RDMA/ucma: Allow resolving address w/o specifying source address Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 20/52] RDMA/mlx5: Fix multiple NULL-ptr deref errors in rereg_mr flow Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 21/52] RDMA/mlx4: Add missed RSS hash inner header flag Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 22/52] RDMA/mlx5: Protect from shift operand overflow Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 24/52] IB/mlx5: Use unlimited rate when static rate is not supported Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 25/52] infiniband: mlx5: fix build errors when INFINIBAND_USER_ACCESS=m Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 26/52] IB/hfi1: Fix handling of FECN marked multicast packet Greg Kroah-Hartman
2018-05-08 8:10 ` Greg Kroah-Hartman [this message]
2018-05-08 8:10 ` [PATCH 4.16 28/52] IB/hfi1: Fix NULL pointer dereference when invalid num_vls is used Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 29/52] iw_cxgb4: Atomically flush per QP HW CQEs Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 30/52] btrfs: Take trans lock before access running trans in check_delayed_ref Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 31/52] drm/vc4: Make sure vc4_bo_{inc,dec}_usecnt() calls are balanced Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 32/52] drm/vmwgfx: Fix a buffer object leak Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 33/52] drm/bridge: vga-dac: Fix edid memory leak Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 34/52] test_firmware: fix setting old custom fw path back on exit, second try Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 35/52] xhci: Fix use-after-free in xhci_free_virt_device Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 36/52] USB: serial: visor: handle potential invalid device configuration Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 37/52] usb: dwc3: gadget: Fix list_del corruption in dwc3_ep_dequeue Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 38/52] USB: Accept bulk endpoints with 1024-byte maxpacket Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 39/52] USB: serial: option: reimplement interface masking Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 41/52] usb: musb: host: fix potential NULL pointer dereference Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 42/52] usb: musb: trace: fix NULL pointer dereference in musb_g_tx() Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 44/52] platform/x86: Kconfig: Fix dell-laptop dependency chain Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 46/52] x86/tsc: Always unregister clocksource_tsc_early Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 47/52] x86/tsc: Fix mark_tsc_unstable() Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 48/52] irqchip/qcom: Fix check for spurious interrupts Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 49/52] clocksource: Allow clocksource_mark_unstable() on unregistered clocksources Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 50/52] clocksource: Initialize cs->wd_list Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 51/52] clocksource: Consistent de-rate when marking unstable Greg Kroah-Hartman
2018-05-08 8:10 ` [PATCH 4.16 52/52] tracing: Fix bad use of igrab in trace_uprobe.c Greg Kroah-Hartman
2018-05-08 16:22 ` [PATCH 4.16 00/52] 4.16.8-stable review Guenter Roeck
2018-05-08 17:52 ` Greg Kroah-Hartman
2018-05-08 17:56 ` Naresh Kamboju
2018-05-08 18:48 ` Greg Kroah-Hartman
2018-05-08 23:53 ` Shuah Khan
2018-05-09 7:32 ` Greg Kroah-Hartman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180508073931.780135827@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=dennis.dalessandro@intel.com \
--cc=dledford@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=michael.j.ruhl@intel.com \
--cc=mike.marciniszyn@intel.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).