All of lore.kernel.org
 help / color / mirror / Atom feed
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,

  parent reply	other threads:[~2018-05-08  8:10 UTC|newest]

Thread overview: 61+ 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 14/52] swiotlb: fix inversed DMA_ATTR_NO_WARN test 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 23/52] NET: usb: qmi_wwan: add support for ublox R410M PID 0x90b2 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 40/52] USB: serial: option: adding support for ublox R410M 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 43/52] platform/x86: asus-wireless: Fix NULL pointer dereference 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 45/52] KVM: x86: remove APIC Timer periodic/oneshot spikes 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   ` 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 15:45 ` [PATCH 4.16 00/52] 4.16.8-stable review kernelci.org bot
2018-05-08 16:22 ` 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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.