| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 21 Jun 2023 18:27:11 +0000
From: Haiyang Zhang <haiyangz@...rosoft.com>
To: souradeep chakrabarti <schakrabarti@...ux.microsoft.com>,
KY Srinivasan <kys@...rosoft.com>,
"wei.liu@...nel.org" <wei.liu@...nel.org>,
Dexuan Cui <decui@...rosoft.com>,
"davem@...emloft.net" <davem@...emloft.net>,
"edumazet@...gle.com" <edumazet@...gle.com>,
"kuba@...nel.org" <kuba@...nel.org>,
"pabeni@...hat.com" <pabeni@...hat.com>,
Long Li <longli@...rosoft.com>,
Ajay Sharma <sharmaajay@...rosoft.com>,
"leon@...nel.org" <leon@...nel.org>,
"cai.huoqing@...ux.dev" <cai.huoqing@...ux.dev>,
"ssengar@...ux.microsoft.com" <ssengar@...ux.microsoft.com>,
"vkuznets@...hat.com" <vkuznets@...hat.com>,
"tglx@...utronix.de" <tglx@...utronix.de>,
"linux-hyperv@...r.kernel.org" <linux-hyperv@...r.kernel.org>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-rdma@...r.kernel.org" <linux-rdma@...r.kernel.org>
Subject: RE: [PATCH] net: mana: Fix MANA VF unload when host is unresponsive
> -----Original Message-----
> From: souradeep chakrabarti <schakrabarti@...ux.microsoft.com>
> Sent: Wednesday, June 21, 2023 6:29 AM
> To: KY Srinivasan <kys@...rosoft.com>; Haiyang Zhang
> <haiyangz@...rosoft.com>; wei.liu@...nel.org; Dexuan Cui
> <decui@...rosoft.com>; davem@...emloft.net; edumazet@...gle.com;
> kuba@...nel.org; pabeni@...hat.com; Long Li <longli@...rosoft.com>; Ajay
> Sharma <sharmaajay@...rosoft.com>; leon@...nel.org;
> cai.huoqing@...ux.dev; ssengar@...ux.microsoft.com; vkuznets@...hat.com;
> tglx@...utronix.de; linux-hyperv@...r.kernel.org; netdev@...r.kernel.org;
> linux-kernel@...r.kernel.org; linux-rdma@...r.kernel.org
> Cc: Souradeep Chakrabarti <schakrabarti@...ux.microsoft.com>
> Subject: [PATCH] net: mana: Fix MANA VF unload when host is unresponsive
>
> From: Souradeep Chakrabarti <schakrabarti@...ux.microsoft.com>
>
> This patch addresses the VF unload issue, where mana_dealloc_queues()
> gets stuck in infinite while loop, because of host unresponsiveness.
> It adds a timeout in the while loop, to fix it.
>
> Also this patch adds a new attribute in mana_context, which gets set when
> mana_hwc_send_request() hits a timeout because of host unresponsiveness.
> This flag then helps to avoid the timeouts in successive calls.
>
> Signed-off-by: Souradeep Chakrabarti <schakrabarti@...ux.microsoft.com>
> ---
> .../net/ethernet/microsoft/mana/gdma_main.c | 4 +++-
> .../net/ethernet/microsoft/mana/hw_channel.c | 12 ++++++++++-
> drivers/net/ethernet/microsoft/mana/mana_en.c | 21 +++++++++++++++++--
> include/net/mana/mana.h | 2 ++
> 4 files changed, 35 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> index 8f3f78b68592..5cc43ae78334 100644
> --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> @@ -946,10 +946,12 @@ int mana_gd_deregister_device(struct gdma_dev
> *gd)
> struct gdma_context *gc = gd->gdma_context;
> struct gdma_general_resp resp = {};
> struct gdma_general_req req = {};
> + struct mana_context *ac;
> int err;
>
> if (gd->pdid == INVALID_PDID)
> return -EINVAL;
> + ac = (struct mana_context *)gd->driver_data;
>
> mana_gd_init_req_hdr(&req.hdr, GDMA_DEREGISTER_DEVICE,
> sizeof(req),
> sizeof(resp));
> @@ -957,7 +959,7 @@ int mana_gd_deregister_device(struct gdma_dev *gd)
> req.hdr.dev_id = gd->dev_id;
>
> err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
> - if (err || resp.hdr.status) {
> + if ((err || resp.hdr.status) && !ac->vf_unload_timeout) {
> dev_err(gc->dev, "Failed to deregister device: %d, 0x%x\n",
> err, resp.hdr.status);
> if (!err)
> diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c
> b/drivers/net/ethernet/microsoft/mana/hw_channel.c
> index 9d1507eba5b9..557b890ad0ae 100644
> --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
> +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
> @@ -1,8 +1,10 @@
> // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
> /* Copyright (c) 2021, Microsoft Corporation. */
>
> +#include "asm-generic/errno.h"
> #include <net/mana/gdma.h>
> #include <net/mana/hw_channel.h>
> +#include <net/mana/mana.h>
>
> static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16
> *msg_id)
> {
> @@ -786,12 +788,19 @@ int mana_hwc_send_request(struct
> hw_channel_context *hwc, u32 req_len,
> struct hwc_wq *txq = hwc->txq;
> struct gdma_req_hdr *req_msg;
> struct hwc_caller_ctx *ctx;
> + struct mana_context *ac;
> u32 dest_vrcq = 0;
> u32 dest_vrq = 0;
> u16 msg_id;
> int err;
>
> mana_hwc_get_msg_index(hwc, &msg_id);
> + ac = (struct mana_context *)hwc->gdma_dev->driver_data;
> + if (ac->vf_unload_timeout) {
> + dev_err(hwc->dev, "HWC: vport is already unloaded.\n");
> + err = -ETIMEDOUT;
> + goto out;
> + }
>
> tx_wr = &txq->msg_buf->reqs[msg_id];
>
> @@ -825,9 +834,10 @@ int mana_hwc_send_request(struct
> hw_channel_context *hwc, u32 req_len,
> goto out;
> }
>
> - if (!wait_for_completion_timeout(&ctx->comp_event, 30 * HZ)) {
> + if (!wait_for_completion_timeout(&ctx->comp_event, 5 * HZ)) {
> dev_err(hwc->dev, "HWC: Request timed out!\n");
> err = -ETIMEDOUT;
> + ac->vf_unload_timeout = true;
> goto out;
> }
>
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c
> b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index d907727c7b7a..24f5508d2979 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -2330,7 +2330,10 @@ static int mana_dealloc_queues(struct net_device
> *ndev)
> struct mana_port_context *apc = netdev_priv(ndev);
> struct gdma_dev *gd = apc->ac->gdma_dev;
> struct mana_txq *txq;
> + struct sk_buff *skb;
> + struct mana_cq *cq;
> int i, err;
> + unsigned long timeout;
>
> if (apc->port_is_up)
> return -EINVAL;
> @@ -2348,13 +2351,26 @@ static int mana_dealloc_queues(struct net_device
> *ndev)
> *
> * Drain all the in-flight TX packets
> */
> +
> + timeout = jiffies + 120 * HZ;
> for (i = 0; i < apc->num_queues; i++) {
> txq = &apc->tx_qp[i].txq;
> -
> - while (atomic_read(&txq->pending_sends) > 0)
> + while (atomic_read(&txq->pending_sends) > 0 &&
> + time_before(jiffies, timeout)) {
> usleep_range(1000, 2000);
> + }
> }
>
> + for (i = 0; i < apc->num_queues; i++) {
> + txq = &apc->tx_qp[i].txq;
> + cq = &apc->tx_qp[i].tx_cq;
> + while (atomic_read(&txq->pending_sends)) {
> + skb = skb_dequeue(&txq->pending_skbs);
> + mana_unmap_skb(skb, apc);
> + napi_consume_skb(skb, cq->budget);
> + atomic_sub(1, &txq->pending_sends);
> + }
> + }
> /* We're 100% sure the queues can no longer be woken up, because
> * we're sure now mana_poll_tx_cq() can't be running.
> */
> @@ -2605,6 +2621,7 @@ int mana_probe(struct gdma_dev *gd, bool
> resuming)
> }
> }
>
> + ac->vf_unload_timeout = false;
> err = add_adev(gd);
> out:
> if (err)
> diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
> index 9eef19972845..34f5d8e06ede 100644
> --- a/include/net/mana/mana.h
> +++ b/include/net/mana/mana.h
> @@ -361,6 +361,8 @@ struct mana_context {
> struct mana_eq *eqs;
>
> struct net_device *ports[MAX_PORTS_IN_MANA_DEV];
> +
> + bool vf_unload_timeout;
> };
>
> struct mana_port_context {
> --
Please specify "net" branch for fixes.
Also Cc: stable@...r.kernel.org So it will be ported to stable trees.
Thanks,
- Haiyang
Powered by blists - more mailing lists