* Re: [PATCH v4 net-next 15/19] ionic: Add netdev-event handling
From: Saeed Mahameed @ 2019-07-25 23:55 UTC (permalink / raw)
To: snelson@pensando.io, netdev@vger.kernel.org, davem@davemloft.net
In-Reply-To: <20190722214023.9513-16-snelson@pensando.io>
On Mon, 2019-07-22 at 14:40 -0700, Shannon Nelson wrote:
> When the netdev gets a new name from userland, pass that name
> down to the NIC for internal tracking.
>
Just out of curiosity, why your NIC internal device/firmware need to
keep tracking of the netdev name ?
^ permalink raw reply
* Re: [PATCH net 1/1] bnx2x: Disable multi-cos feature.
From: David Miller @ 2019-07-26 0:10 UTC (permalink / raw)
To: skalluru; +Cc: netdev, manishc, mkalderon
In-Reply-To: <20190724023241.24794-1-skalluru@marvell.com>
From: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Date: Tue, 23 Jul 2019 19:32:41 -0700
> Commit 3968d38917eb ("bnx2x: Fix Multi-Cos.") which enabled multi-cos
> feature after prolonged time in driver added some regression causing
> numerous issues (sudden reboots, tx timeout etc.) reported by customers.
> We plan to backout this commit and submit proper fix once we have root
> cause of issues reported with this feature enabled.
>
> Fixes: 3968d38917eb ("bnx2x: Fix Multi-Cos.")
> Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
> Signed-off-by: Manish Chopra <manishc@marvell.com>
Applied and queued up for -stable.
^ permalink raw reply
* Re: [PATCH v4 net-next 18/19] ionic: Add coalesce and other features
From: Saeed Mahameed @ 2019-07-26 0:13 UTC (permalink / raw)
To: snelson@pensando.io, netdev@vger.kernel.org, davem@davemloft.net
In-Reply-To: <20190722214023.9513-19-snelson@pensando.io>
On Mon, 2019-07-22 at 14:40 -0700, Shannon Nelson wrote:
> Interrupt coalescing, tunable copybreak value, and
> tx timeout.
>
> Signed-off-by: Shannon Nelson <snelson@pensando.io>
> ---
> drivers/net/ethernet/pensando/ionic/ionic.h | 2 +-
> .../ethernet/pensando/ionic/ionic_ethtool.c | 105
> ++++++++++++++++++
> .../net/ethernet/pensando/ionic/ionic_lif.c | 13 ++-
> .../net/ethernet/pensando/ionic/ionic_lif.h | 1 +
> 4 files changed, 119 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h
> b/drivers/net/ethernet/pensando/ionic/ionic.h
> index 9b720187b549..cd08166f73a9 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic.h
> +++ b/drivers/net/ethernet/pensando/ionic/ionic.h
> @@ -11,7 +11,7 @@ struct lif;
>
> #define DRV_NAME "ionic"
> #define DRV_DESCRIPTION "Pensando Ethernet NIC Driver"
> -#define DRV_VERSION "0.11.0-k"
> +#define DRV_VERSION "0.11.0-44-k"
>
> #define PCI_VENDOR_ID_PENSANDO 0x1dd8
>
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
> b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
> index 742d7d47f4d8..e6b579a40b70 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
> @@ -377,6 +377,75 @@ static int ionic_get_coalesce(struct net_device
> *netdev,
> return 0;
> }
>
> +static int ionic_set_coalesce(struct net_device *netdev,
> + struct ethtool_coalesce *coalesce)
> +{
> + struct lif *lif = netdev_priv(netdev);
> + struct identity *ident = &lif->ionic->ident;
> + struct ionic_dev *idev = &lif->ionic->idev;
> + u32 tx_coal, rx_coal;
> + struct qcq *qcq;
> + unsigned int i;
> +
> + if (coalesce->rx_max_coalesced_frames ||
> + coalesce->rx_coalesce_usecs_irq ||
> + coalesce->rx_max_coalesced_frames_irq ||
> + coalesce->tx_max_coalesced_frames ||
> + coalesce->tx_coalesce_usecs_irq ||
> + coalesce->tx_max_coalesced_frames_irq ||
> + coalesce->stats_block_coalesce_usecs ||
> + coalesce->use_adaptive_rx_coalesce ||
> + coalesce->use_adaptive_tx_coalesce ||
> + coalesce->pkt_rate_low ||
> + coalesce->rx_coalesce_usecs_low ||
> + coalesce->rx_max_coalesced_frames_low ||
> + coalesce->tx_coalesce_usecs_low ||
> + coalesce->tx_max_coalesced_frames_low ||
> + coalesce->pkt_rate_high ||
> + coalesce->rx_coalesce_usecs_high ||
> + coalesce->rx_max_coalesced_frames_high ||
> + coalesce->tx_coalesce_usecs_high ||
> + coalesce->tx_max_coalesced_frames_high ||
> + coalesce->rate_sample_interval)
> + return -EINVAL;
> +
> + if (ident->dev.intr_coal_div == 0)
> + return -EIO;
> +
> + /* Convert from usecs to device units */
> + tx_coal = coalesce->tx_coalesce_usecs *
> + le32_to_cpu(ident->dev.intr_coal_mult) /
> + le32_to_cpu(ident->dev.intr_coal_div);
> + rx_coal = coalesce->rx_coalesce_usecs *
> + le32_to_cpu(ident->dev.intr_coal_mult) /
> + le32_to_cpu(ident->dev.intr_coal_div);
> +
> + if (tx_coal > INTR_CTRL_COAL_MAX || rx_coal >
> INTR_CTRL_COAL_MAX)
> + return -ERANGE;
> +
> + if (coalesce->tx_coalesce_usecs != lif->tx_coalesce_usecs) {
> + for (i = 0; i < lif->nxqs; i++) {
> + qcq = lif->txqcqs[i].qcq;
> + ionic_intr_coal_init(idev->intr_ctrl,
> + qcq->intr.index,
> + tx_coal);
> + }
> + lif->tx_coalesce_usecs = coalesce->tx_coalesce_usecs;
> + }
> +
> + if (coalesce->rx_coalesce_usecs != lif->rx_coalesce_usecs) {
> + for (i = 0; i < lif->nxqs; i++) {
> + qcq = lif->rxqcqs[i].qcq;
> + ionic_intr_coal_init(idev->intr_ctrl,
> + qcq->intr.index,
> + rx_coal);
> + }
> + lif->rx_coalesce_usecs = coalesce->rx_coalesce_usecs;
> + }
> +
> + return 0;
> +}
> +
> static void ionic_get_ringparam(struct net_device *netdev,
> struct ethtool_ringparam *ring)
> {
> @@ -562,6 +631,39 @@ static int ionic_set_priv_flags(struct
> net_device *netdev, u32 priv_flags)
> return 0;
> }
>
> +static int ionic_set_tunable(struct net_device *dev,
> + const struct ethtool_tunable *tuna,
> + const void *data)
> +{
> + struct lif *lif = netdev_priv(dev);
> +
> + switch (tuna->id) {
> + case ETHTOOL_RX_COPYBREAK:
> + lif->rx_copybreak = *(u32 *)data;
> + break;
> + default:
> + return -EOPNOTSUPP;
> + }
> +
> + return 0;
> +}
> +
> +static int ionic_get_tunable(struct net_device *netdev,
> + const struct ethtool_tunable *tuna, void
> *data)
> +{
> + struct lif *lif = netdev_priv(netdev);
> +
> + switch (tuna->id) {
> + case ETHTOOL_RX_COPYBREAK:
> + *(u32 *)data = lif->rx_copybreak;
> + break;
> + default:
> + return -EOPNOTSUPP;
> + }
> +
> + return 0;
> +}
> +
> static int ionic_get_module_info(struct net_device *netdev,
> struct ethtool_modinfo *modinfo)
>
> @@ -641,6 +743,7 @@ static const struct ethtool_ops ionic_ethtool_ops
> = {
> .get_link = ethtool_op_get_link,
> .get_link_ksettings = ionic_get_link_ksettings,
> .get_coalesce = ionic_get_coalesce,
> + .set_coalesce = ionic_set_coalesce,
> .get_ringparam = ionic_get_ringparam,
> .set_ringparam = ionic_set_ringparam,
> .get_channels = ionic_get_channels,
> @@ -655,6 +758,8 @@ static const struct ethtool_ops ionic_ethtool_ops
> = {
> .set_rxfh = ionic_set_rxfh,
> .get_priv_flags = ionic_get_priv_flags,
> .set_priv_flags = ionic_set_priv_flags,
> + .get_tunable = ionic_get_tunable,
> + .set_tunable = ionic_set_tunable,
> .get_module_info = ionic_get_module_info,
> .get_module_eeprom = ionic_get_module_eeprom,
> .get_pauseparam = ionic_get_pauseparam,
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
> b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
> index 68a9975e34c6..8473b065763b 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
> @@ -744,9 +744,19 @@ static int ionic_change_mtu(struct net_device
> *netdev, int new_mtu)
> return err;
> }
>
> +static void ionic_tx_timeout_work(struct work_struct *ws)
> +{
> + struct lif *lif = container_of(ws, struct lif,
> tx_timeout_work);
> +
> + netdev_info(lif->netdev, "Tx Timeout recovery\n");
> + ionic_reset_queues(lif);
missing rtnl_lock ?
> +}
> +
> static void ionic_tx_timeout(struct net_device *netdev)
> {
> - netdev_info(netdev, "%s: stubbed\n", __func__);
> + struct lif *lif = netdev_priv(netdev);
> +
> + schedule_work(&lif->tx_timeout_work);
> }
missing cancel work ? be careful when combined with the rtnl_lockthough ..
>
> static int ionic_vlan_rx_add_vid(struct net_device *netdev, __be16
> proto,
> @@ -2009,6 +2019,7 @@ static int ionic_lif_init(struct lif *lif)
>
> ionic_link_status_check(lif);
>
> + INIT_WORK(&lif->tx_timeout_work, ionic_tx_timeout_work);
> return 0;
>
> err_out_notifyq_deinit:
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
> b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
> index 0e6908f959f2..76cc519acd5a 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
> @@ -180,6 +180,7 @@ struct lif {
> unsigned int dbid_count;
> struct dentry *dentry;
> u32 flags;
> + struct work_struct tx_timeout_work;
> };
>
> #define lif_to_txqcq(lif, i) ((lif)->txqcqs[i].qcq)
^ permalink raw reply
* Re: [PATCH] net: mscc: ocelot: null check devm_kcalloc
From: David Miller @ 2019-07-26 0:20 UTC (permalink / raw)
To: navid.emamdoost
Cc: emamd001, kjlu, smccaman, secalert, alexandre.belloni,
UNGLinuxDriver, netdev, linux-kernel
In-Reply-To: <20190725015609.24389-1-navid.emamdoost@gmail.com>
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 24 Jul 2019 20:56:09 -0500
> devm_kcalloc may fail and return NULL. Added the null check.
>
> Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
> ---
> drivers/net/ethernet/mscc/ocelot_board.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
> index 58bde1a9eacb..52377cfdc31a 100644
> --- a/drivers/net/ethernet/mscc/ocelot_board.c
> +++ b/drivers/net/ethernet/mscc/ocelot_board.c
> @@ -257,6 +257,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
>
> ocelot->ports = devm_kcalloc(&pdev->dev, ocelot->num_phys_ports,
> sizeof(struct ocelot_port *), GFP_KERNEL);
> + if (!ocelot->ports)
> + return -ENOMEM;
>
At the very least this leaks a reference to 'ports'. I didn't check what other
resources obtained by this function are leaked as well by this change, please
audit before resubmitting.
^ permalink raw reply
* Re: [PATCH] ipip: validate header length in ipip_tunnel_xmit
From: David Miller @ 2019-07-26 0:26 UTC (permalink / raw)
To: yanhaishuang; +Cc: kuznet, netdev, linux-kernel
In-Reply-To: <1564024076-13764-1-git-send-email-yanhaishuang@cmss.chinamobile.com>
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Thu, 25 Jul 2019 11:07:55 +0800
> We need the same checks introduced by commit cb9f1b783850
> ("ip: validate header length on virtual device xmit") for
> ipip tunnel.
>
> Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Applied and queued up for -stable.
^ permalink raw reply
* Re: [PATCH net] selftests/net: add missing gitignores (ipv6_flowlabel)
From: David Miller @ 2019-07-26 0:26 UTC (permalink / raw)
To: jakub.kicinski; +Cc: netdev, oss-drivers, willemb, quentin.monnet
In-Reply-To: <20190725000714.10200-1-jakub.kicinski@netronome.com>
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 24 Jul 2019 17:07:14 -0700
> ipv6_flowlabel and ipv6_flowlabel_mgr are missing from
> gitignore. Quentin points out that the original
> commit 3fb321fde22d ("selftests/net: ipv6 flowlabel")
> did add ignore entries, they are just missing the "ipv6_"
> prefix.
>
> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Applied.
^ permalink raw reply
* Re: [PATCH] hv_sock: use HV_HYP_PAGE_SIZE instead of PAGE_SIZE_4K
From: David Miller @ 2019-07-26 0:26 UTC (permalink / raw)
To: himadrispandya
Cc: mikelley, kys, haiyangz, sthemmin, sashal, linux-hyperv, netdev,
linux-kernel, himadri18.07
In-Reply-To: <20190725051125.10605-1-himadri18.07@gmail.com>
From: Himadri Pandya <himadrispandya@gmail.com>
Date: Thu, 25 Jul 2019 05:11:25 +0000
> Older windows hosts require the hv_sock ring buffer to be defined
> using 4K pages. This was achieved by using the symbol PAGE_SIZE_4K
> defined specifically for this purpose. But now we have a new symbol
> HV_HYP_PAGE_SIZE defined in hyperv-tlfs which can be used for this.
>
> This patch removes the definition of symbol PAGE_SIZE_4K and replaces
> its usage with the symbol HV_HYP_PAGE_SIZE. This patch also aligns
> sndbuf and rcvbuf to hyper-v specific page size using HV_HYP_PAGE_SIZE
> instead of the guest page size(PAGE_SIZE) as hyper-v expects the page
> size to be 4K and it might not be the case on ARM64 architecture.
>
> Signed-off-by: Himadri Pandya <himadri18.07@gmail.com>
This doesn't compile:
CC [M] net/vmw_vsock/hyperv_transport.o
net/vmw_vsock/hyperv_transport.c:58:28: error: ‘HV_HYP_PAGE_SIZE’ undeclared here (not in a function); did you mean ‘HV_MESSAGE_SIZE’?
#define HVS_SEND_BUF_SIZE (HV_HYP_PAGE_SIZE - sizeof(struct vmpipe_proto_header))
^~~~~~~~~~~~~~~~
^ permalink raw reply
* Re: [PATCH net-next] net: mvneta: use devm_platform_ioremap_resource() to simplify code
From: David Miller @ 2019-07-26 0:28 UTC (permalink / raw)
To: Jisheng.Zhang; +Cc: thomas.petazzoni, netdev, linux-kernel
In-Reply-To: <20190725153741.095dca99@xhacker.debian>
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Thu, 25 Jul 2019 07:48:04 +0000
> devm_platform_ioremap_resource() wraps platform_get_resource() and
> devm_ioremap_resource() in a single helper, let's use that helper to
> simplify the code.
>
> Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Applied.
^ permalink raw reply
* Re: pull-request: bpf 2019-07-25
From: David Miller @ 2019-07-26 0:35 UTC (permalink / raw)
To: ast; +Cc: daniel, netdev, bpf, kernel-team
In-Reply-To: <20190725173541.2413580-1-ast@kernel.org>
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 25 Jul 2019 10:35:41 -0700
> The following pull-request contains BPF updates for your *net* tree.
>
> The main changes are:
>
> 1) fix segfault in libbpf, from Andrii.
>
> 2) fix gso_segs access, from Eric.
>
> 3) tls/sockmap fixes, from Jakub and John.
>
> Please consider pulling these changes from:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
Pulled, thanks Alexei.
I will push back out after build testing.
^ permalink raw reply
* Re: [PATCH bpf-next v10 0/2] bpf: Allow bpf_skb_event_output for more prog types
From: Alexei Starovoitov @ 2019-07-26 0:59 UTC (permalink / raw)
To: Allan Zhang
Cc: Network Development, bpf, Song Liu, Daniel Borkmann,
Andrii Nakryiko, Alexei Starovoitov
In-Reply-To: <20190724000725.15634-1-allanzhang@google.com>
On Tue, Jul 23, 2019 at 5:07 PM Allan Zhang <allanzhang@google.com> wrote:
>
> Software event output is only enabled by a few prog types right now (TC,
> LWT out, XDP, sockops). Many other skb based prog types need
> bpf_skb_event_output to produce software event.
>
> More prog types are enabled to access bpf_skb_event_output in this
> patch.
Applied. Thanks
^ permalink raw reply
* Re: [PATCH bpf-next 2/6] bpf: add BPF_MAP_DUMP command to dump more than one entry per call
From: Willem de Bruijn @ 2019-07-26 1:02 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Brian Vazquez, Song Liu, Brian Vazquez, Alexei Starovoitov,
Daniel Borkmann, David S . Miller, Stanislav Fomichev,
Petar Penkov, open list, Networking, bpf
In-Reply-To: <20190725235432.lkptx3fafegnm2et@ast-mbp>
On Thu, Jul 25, 2019 at 7:54 PM Alexei Starovoitov
<alexei.starovoitov@gmail.com> wrote:
>
> On Thu, Jul 25, 2019 at 04:25:53PM -0700, Brian Vazquez wrote:
> > > > > If prev_key is deleted before map_get_next_key(), we get the first key
> > > > > again. This is pretty weird.
> > > >
> > > > Yes, I know. But note that the current scenario happens even for the
> > > > old interface (imagine you are walking a map from userspace and you
> > > > tried get_next_key the prev_key was removed, you will start again from
> > > > the beginning without noticing it).
> > > > I tried to sent a patch in the past but I was missing some context:
> > > > before NULL was used to get the very first_key the interface relied in
> > > > a random (non existent) key to retrieve the first_key in the map, and
> > > > I was told what we still have to support that scenario.
> > >
> > > BPF_MAP_DUMP is slightly different, as you may return the first key
> > > multiple times in the same call. Also, BPF_MAP_DUMP is new, so we
> > > don't have to support legacy scenarios.
> > >
> > > Since BPF_MAP_DUMP keeps a list of elements. It is possible to try
> > > to look up previous keys. Would something down this direction work?
> >
> > I've been thinking about it and I think first we need a way to detect
> > that since key was not present we got the first_key instead:
> >
> > - One solution I had in mind was to explicitly asked for the first key
> > with map_get_next_key(map, NULL, first_key) and while walking the map
> > check that map_get_next_key(map, prev_key, key) doesn't return the
> > same key. This could be done using memcmp.
> > - Discussing with Stan, he mentioned that another option is to support
> > a flag in map_get_next_key to let it know that we want an error
> > instead of the first_key.
> >
> > After detecting the problem we also need to define what we want to do,
> > here some options:
> >
> > a) Return the error to the caller
> > b) Try with previous keys if any (which be limited to the keys that we
> > have traversed so far in this dump call)
> > c) continue with next entries in the map. array is easy just get the
> > next valid key (starting on i+1), but hmap might be difficult since
> > starting on the next bucket could potentially skip some keys that were
> > concurrently added to the same bucket where key used to be, and
> > starting on the same bucket could lead us to return repeated elements.
> >
> > Or maybe we could support those 3 cases via flags and let the caller
> > decide which one to use?
>
> this type of indecision is the reason why I wasn't excited about
> batch dumping in the first place and gave 'soft yes' when Stan
> mentioned it during lsf/mm/bpf uconf.
> We probably shouldn't do it.
> It feels this map_dump makes api more complex and doesn't really
> give much benefit to the user other than large map dump becomes faster.
> I think we gotta solve this problem differently.
Multiple variants with flags indeed makes the API complex. I think the
kernel should expose only the simplest, most obvious behavior that
allows the application to recover. In this case, that sounds like
option (a) and restart.
In practice, the common use case is to allocate enough user memory to
read an entire table in one go, in which case the entire issue is
moot.
The cycle savings of dump are significant for large tables. I'm not
sure how we achieve that differently and even simpler? We originally
looked at shared memory, but that is obviously much more complex.
^ permalink raw reply
* Re: [PATCH bpf-next v3 0/7] bpf/flow_dissector: support input flags
From: Alexei Starovoitov @ 2019-07-26 1:06 UTC (permalink / raw)
To: Stanislav Fomichev
Cc: Network Development, bpf, David S. Miller, Alexei Starovoitov,
Daniel Borkmann, Song Liu, Willem de Bruijn, Petar Penkov
In-Reply-To: <20190725225231.195090-1-sdf@google.com>
On Thu, Jul 25, 2019 at 3:52 PM Stanislav Fomichev <sdf@google.com> wrote:
>
> C flow dissector supports input flags that tell it to customize parsing
> by either stopping early or trying to parse as deep as possible.
> BPF flow dissector always parses as deep as possible which is sub-optimal.
> Pass input flags to the BPF flow dissector as well so it can make the same
> decisions.
>
> Series outline:
> * remove unused FLOW_DISSECTOR_F_STOP_AT_L3 flag
> * export FLOW_DISSECTOR_F_XXX flags as uapi and pass them to BPF
> flow dissector
> * add documentation for the export flags
> * support input flags in BPF_PROG_TEST_RUN via ctx_{in,out}
> * sync uapi to tools
> * support FLOW_DISSECTOR_F_PARSE_1ST_FRAG in selftest
> * support FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL in kernel and selftest
> * support FLOW_DISSECTOR_F_STOP_AT_ENCAP in selftest
>
> Pros:
> * makes BPF flow dissector faster by avoiding burning extra cycles
> * existing BPF progs continue to work by ignoring the flags and always
> parsing as deep as possible
>
> Cons:
> * new UAPI which we need to support (OTOH, if we need to deprecate some
> flags, we can just stop setting them upon calling BPF programs)
>
> Some numbers (with .repeat = 4000000 in test_flow_dissector):
> test_flow_dissector:PASS:ipv4-frag 35 nsec
> test_flow_dissector:PASS:ipv4-frag 35 nsec
> test_flow_dissector:PASS:ipv4-no-frag 32 nsec
> test_flow_dissector:PASS:ipv4-no-frag 32 nsec
>
> test_flow_dissector:PASS:ipv6-frag 39 nsec
> test_flow_dissector:PASS:ipv6-frag 39 nsec
> test_flow_dissector:PASS:ipv6-no-frag 36 nsec
> test_flow_dissector:PASS:ipv6-no-frag 36 nsec
>
> test_flow_dissector:PASS:ipv6-flow-label 36 nsec
> test_flow_dissector:PASS:ipv6-flow-label 36 nsec
> test_flow_dissector:PASS:ipv6-no-flow-label 33 nsec
> test_flow_dissector:PASS:ipv6-no-flow-label 33 nsec
>
> test_flow_dissector:PASS:ipip-encap 38 nsec
> test_flow_dissector:PASS:ipip-encap 38 nsec
> test_flow_dissector:PASS:ipip-no-encap 32 nsec
> test_flow_dissector:PASS:ipip-no-encap 32 nsec
>
> The improvement is around 10%, but it's in a tight cache-hot
> BPF_PROG_TEST_RUN loop.
Applied. Thanks
^ permalink raw reply
* Re: [PATCH 00/12] block/bio, fs: convert put_page() to put_user_page*()
From: John Hubbard @ 2019-07-26 1:24 UTC (permalink / raw)
To: Bob Liu, Andrew Morton
Cc: Alexander Viro, Anna Schumaker, David S . Miller,
Dominique Martinet, Eric Van Hensbergen, Jason Gunthorpe,
Jason Wang, Jens Axboe, Latchesar Ionkov, Michael S . Tsirkin,
Miklos Szeredi, Trond Myklebust, Christoph Hellwig,
Matthew Wilcox, linux-mm, LKML, ceph-devel, kvm, linux-block,
linux-cifs, linux-fsdevel, linux-nfs, linux-rdma, netdev,
samba-technical, v9fs-developer, virtualization
In-Reply-To: <8621066c-e242-c449-eb04-4f2ce6867140@oracle.com>
On 7/24/19 5:41 PM, Bob Liu wrote:
> On 7/24/19 12:25 PM, john.hubbard@gmail.com wrote:
>> From: John Hubbard <jhubbard@nvidia.com>
>>
>> Hi,
>>
>> This is mostly Jerome's work, converting the block/bio and related areas
>> to call put_user_page*() instead of put_page(). Because I've changed
>> Jerome's patches, in some cases significantly, I'd like to get his
>> feedback before we actually leave him listed as the author (he might
>> want to disown some or all of these).
>>
>
> Could you add some background to the commit log for people don't have the context..
> Why this converting? What's the main differences?
>
Hi Bob,
1. Many of the patches have a blurb like this:
For pages that were retained via get_user_pages*(), release those pages
via the new put_user_page*() routines, instead of via put_page().
This is part a tree-wide conversion, as described in commit fc1d8e7cca2d
("mm: introduce put_user_page*(), placeholder versions").
...and if you look at that commit, you'll find several pages of
information in its commit description, which should address your point.
2. This whole series has to be re-worked, as per the other feedback thread.
So I'll keep your comment in mind when I post a new series.
thanks,
--
John Hubbard
NVIDIA
^ permalink raw reply
* Re: [PATCH bpf-next 2/6] bpf: add BPF_MAP_DUMP command to dump more than one entry per call
From: Brian Vazquez @ 2019-07-26 1:24 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Song Liu, Brian Vazquez, Alexei Starovoitov, Daniel Borkmann,
David S . Miller, Stanislav Fomichev, Willem de Bruijn,
Petar Penkov, open list, Networking, bpf
In-Reply-To: <20190725235432.lkptx3fafegnm2et@ast-mbp>
On Thu, Jul 25, 2019 at 4:54 PM Alexei Starovoitov
<alexei.starovoitov@gmail.com> wrote:
>
> On Thu, Jul 25, 2019 at 04:25:53PM -0700, Brian Vazquez wrote:
> > > > > If prev_key is deleted before map_get_next_key(), we get the first key
> > > > > again. This is pretty weird.
> > > >
> > > > Yes, I know. But note that the current scenario happens even for the
> > > > old interface (imagine you are walking a map from userspace and you
> > > > tried get_next_key the prev_key was removed, you will start again from
> > > > the beginning without noticing it).
> > > > I tried to sent a patch in the past but I was missing some context:
> > > > before NULL was used to get the very first_key the interface relied in
> > > > a random (non existent) key to retrieve the first_key in the map, and
> > > > I was told what we still have to support that scenario.
> > >
> > > BPF_MAP_DUMP is slightly different, as you may return the first key
> > > multiple times in the same call. Also, BPF_MAP_DUMP is new, so we
> > > don't have to support legacy scenarios.
> > >
> > > Since BPF_MAP_DUMP keeps a list of elements. It is possible to try
> > > to look up previous keys. Would something down this direction work?
> >
> > I've been thinking about it and I think first we need a way to detect
> > that since key was not present we got the first_key instead:
> >
> > - One solution I had in mind was to explicitly asked for the first key
> > with map_get_next_key(map, NULL, first_key) and while walking the map
> > check that map_get_next_key(map, prev_key, key) doesn't return the
> > same key. This could be done using memcmp.
> > - Discussing with Stan, he mentioned that another option is to support
> > a flag in map_get_next_key to let it know that we want an error
> > instead of the first_key.
> >
> > After detecting the problem we also need to define what we want to do,
> > here some options:
> >
> > a) Return the error to the caller
> > b) Try with previous keys if any (which be limited to the keys that we
> > have traversed so far in this dump call)
> > c) continue with next entries in the map. array is easy just get the
> > next valid key (starting on i+1), but hmap might be difficult since
> > starting on the next bucket could potentially skip some keys that were
> > concurrently added to the same bucket where key used to be, and
> > starting on the same bucket could lead us to return repeated elements.
> >
> > Or maybe we could support those 3 cases via flags and let the caller
> > decide which one to use?
>
> this type of indecision is the reason why I wasn't excited about
> batch dumping in the first place and gave 'soft yes' when Stan
> mentioned it during lsf/mm/bpf uconf.
> We probably shouldn't do it.
> It feels this map_dump makes api more complex and doesn't really
> give much benefit to the user other than large map dump becomes faster.
> I think we gotta solve this problem differently.
Some users are working around the dumping problems with the existing
api by creating a bpf_map_get_next_key_and_delete userspace function
(see https://www.bouncybouncy.net/blog/bpf_map_get_next_key-pitfalls/)
which in my opinion is actually a good idea. The only problem with
that is that calling bpf_map_get_next_key(fd, key, next_key) and then
bpf_map_delete_elem(fd, key) from userspace is racing with kernel code
and it might lose some information when deleting.
We could then do map_dump_and_delete using that idea but in the kernel
where we could better handle the racing condition. In that scenario
even if we retrieve the same key it will contain different info ( the
delta between old and new value). Would that work?
^ permalink raw reply
* RE: [PATCH 0/8] can: flexcan: add CAN FD support for NXP Flexcan
From: Joakim Zhang @ 2019-07-26 1:25 UTC (permalink / raw)
To: Marc Kleine-Budde, linux-can@vger.kernel.org
Cc: wg@grandegger.com, dl-linux-imx, netdev@vger.kernel.org
In-Reply-To: <24eb5c67-4692-1002-2468-4ae2e1a6b68b@pengutronix.de>
> -----Original Message-----
> From: Marc Kleine-Budde <mkl@pengutronix.de>
> Sent: 2019年7月25日 18:37
> To: Joakim Zhang <qiangqing.zhang@nxp.com>; linux-can@vger.kernel.org
> Cc: wg@grandegger.com; dl-linux-imx <linux-imx@nxp.com>;
> netdev@vger.kernel.org
> Subject: Re: [PATCH 0/8] can: flexcan: add CAN FD support for NXP Flexcan
>
> On 7/25/19 9:53 AM, Marc Kleine-Budde wrote:
> > On 7/25/19 9:38 AM, Joakim Zhang wrote:
> >> Kindly pinging...
> >>
> >> After you git pull request for linux-can-next-for-5.4-20190724, some patches
> are missing from linux-can-next/testing.
> >> can: flexcan: flexcan_mailbox_read() make use of flexcan_write64() to
> >> mark the mailbox as read
> >> can: flexcan: flexcan_irq(): add support for TX mailbox in iflag1
> >> can: flexcan: flexcan_read_reg_iflag_rx(): optimize reading
> >> can: flexcan: introduce struct flexcan_priv::tx_mask and make use of
> >> it
> >> can: flexcan: convert struct flexcan_priv::rx_mask{1,2} to rx_mask
> >> can: flexcan: remove TX mailbox bit from struct
> >> flexcan_priv::rx_mask{1,2}
> >> can: flexcan: rename struct flexcan_priv::reg_imask{1,2}_default to
> >> rx_mask{1,2}
> >> can: flexcan: flexcan_irq(): rename variable reg_iflag ->
> >> reg_iflag_rx
> >> can: flexcan: rename macro FLEXCAN_IFLAG_MB() ->
> FLEXCAN_IFLAG2_MB()
> >>
> >> You can refer to below link for the reason of adding above patches:
> >> https://www.spinics.net/lists/linux-can/msg00777.html
> >> https://www.spinics.net/lists/linux-can/msg01150.html
> >>
> >> Are you prepared to add back these patches as they are necessary for
> >> Flexcan CAN FD? And this Flexcan CAN FD patch set is based on these
> >> patches.
> >
> > Yes, these patches will be added back.
>
> I've cleaned up the first patch a bit, and pushed everything to the testing
> branch. Can you give it a test.
Hi Marc,
Both Classic CAN and CAN FD can work fine on my side test, thank you for your kindly review.
Best Regards,
Joakim Zhang
> regards,
> Marc
>
> --
> Pengutronix e.K. | Marc Kleine-Budde |
> Industrial Linux Solutions | Phone: +49-231-2826-924 |
> Vertretung West/Dortmund | Fax: +49-5121-206917-5555 |
> Amtsgericht Hildesheim, HRA 2686 | http://www.pengutronix.de |
^ permalink raw reply
* Re: [PATCH net-next 07/11] net: hns3: adds debug messages to identify eth down cause
From: Jakub Kicinski @ 2019-07-26 1:28 UTC (permalink / raw)
To: Saeed Mahameed
Cc: tanhuazhong@huawei.com, davem@davemloft.net,
liuyonglong@huawei.com, lipeng321@huawei.com,
yisen.zhuang@huawei.com, salil.mehta@huawei.com,
linuxarm@huawei.com, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <75a02bbe5b3b0f2755cd901a8830d4a3026f9383.camel@mellanox.com>
On Thu, 25 Jul 2019 21:59:08 +0000, Saeed Mahameed wrote:
> I couldn't find any rules regarding what to put in kernel log, Maybe
> someone can share ?. but i vaguely remember that the recommendation
> for device drivers is to put nothing, only error/warning messages.
FWIW my understanding is also that only error/warning messages should
be printed. IOW things which should "never happen".
There are some historical exceptions. Probe logs for instance may be
useful, because its not trivial to get to the device if probe fails.
Another one is ethtool flashing, if it takes time we used to print into
logs some message like "please wait patiently". But since Jiri added
the progress messages in devlink that's no longer necessary.
For the messages which are basically printing the name of the function
or name of the function and their args - we have ftrace.
That's my $0.02 :)
^ permalink raw reply
* Re: [PATCH bpf-next 2/6] bpf: add BPF_MAP_DUMP command to dump more than one entry per call
From: Alexei Starovoitov @ 2019-07-26 1:47 UTC (permalink / raw)
To: Brian Vazquez
Cc: Song Liu, Brian Vazquez, Daniel Borkmann, David S . Miller,
Stanislav Fomichev, Willem de Bruijn, Petar Penkov, Networking,
bpf, Yonghong Song
In-Reply-To: <CABCgpaXE=dkBcJVqs95NZQTFuznA-q64kYPEcbvmYvAJ4wSp1A@mail.gmail.com>
On Thu, Jul 25, 2019 at 6:24 PM Brian Vazquez <brianvv.kernel@gmail.com> wrote:
>
> On Thu, Jul 25, 2019 at 4:54 PM Alexei Starovoitov
> <alexei.starovoitov@gmail.com> wrote:
> >
> > On Thu, Jul 25, 2019 at 04:25:53PM -0700, Brian Vazquez wrote:
> > > > > > If prev_key is deleted before map_get_next_key(), we get the first key
> > > > > > again. This is pretty weird.
> > > > >
> > > > > Yes, I know. But note that the current scenario happens even for the
> > > > > old interface (imagine you are walking a map from userspace and you
> > > > > tried get_next_key the prev_key was removed, you will start again from
> > > > > the beginning without noticing it).
> > > > > I tried to sent a patch in the past but I was missing some context:
> > > > > before NULL was used to get the very first_key the interface relied in
> > > > > a random (non existent) key to retrieve the first_key in the map, and
> > > > > I was told what we still have to support that scenario.
> > > >
> > > > BPF_MAP_DUMP is slightly different, as you may return the first key
> > > > multiple times in the same call. Also, BPF_MAP_DUMP is new, so we
> > > > don't have to support legacy scenarios.
> > > >
> > > > Since BPF_MAP_DUMP keeps a list of elements. It is possible to try
> > > > to look up previous keys. Would something down this direction work?
> > >
> > > I've been thinking about it and I think first we need a way to detect
> > > that since key was not present we got the first_key instead:
> > >
> > > - One solution I had in mind was to explicitly asked for the first key
> > > with map_get_next_key(map, NULL, first_key) and while walking the map
> > > check that map_get_next_key(map, prev_key, key) doesn't return the
> > > same key. This could be done using memcmp.
> > > - Discussing with Stan, he mentioned that another option is to support
> > > a flag in map_get_next_key to let it know that we want an error
> > > instead of the first_key.
> > >
> > > After detecting the problem we also need to define what we want to do,
> > > here some options:
> > >
> > > a) Return the error to the caller
> > > b) Try with previous keys if any (which be limited to the keys that we
> > > have traversed so far in this dump call)
> > > c) continue with next entries in the map. array is easy just get the
> > > next valid key (starting on i+1), but hmap might be difficult since
> > > starting on the next bucket could potentially skip some keys that were
> > > concurrently added to the same bucket where key used to be, and
> > > starting on the same bucket could lead us to return repeated elements.
> > >
> > > Or maybe we could support those 3 cases via flags and let the caller
> > > decide which one to use?
> >
> > this type of indecision is the reason why I wasn't excited about
> > batch dumping in the first place and gave 'soft yes' when Stan
> > mentioned it during lsf/mm/bpf uconf.
> > We probably shouldn't do it.
> > It feels this map_dump makes api more complex and doesn't really
> > give much benefit to the user other than large map dump becomes faster.
> > I think we gotta solve this problem differently.
>
> Some users are working around the dumping problems with the existing
> api by creating a bpf_map_get_next_key_and_delete userspace function
> (see https://www.bouncybouncy.net/blog/bpf_map_get_next_key-pitfalls/)
> which in my opinion is actually a good idea. The only problem with
> that is that calling bpf_map_get_next_key(fd, key, next_key) and then
> bpf_map_delete_elem(fd, key) from userspace is racing with kernel code
> and it might lose some information when deleting.
> We could then do map_dump_and_delete using that idea but in the kernel
> where we could better handle the racing condition. In that scenario
> even if we retrieve the same key it will contain different info ( the
> delta between old and new value). Would that work?
you mean get_next+lookup+delete at once?
Sounds useful.
Yonghong has been thinking about batching api as well.
I think if we cannot figure out how to make a batch of two commands
get_next + lookup to work correctly then we need to identify/invent one
command and make batching more generic.
Like make one jumbo/compound/atomic command to be get_next+lookup+delete.
Define the semantics of this single compound command.
And then let batching to be a multiplier of such command.
In a sense that multiplier 1 or N should be have the same way.
No extra flags to alter the batching.
The high level description of the batch would be:
pls execute get_next,lookup,delete and repeat it N times.
or
pls execute get_next,lookup and repeat N times.
where each command action is defined to be composable.
Just a rough idea.
^ permalink raw reply
* Re: [PATCH net-next 06/11] net: hns3: modify firmware version display format
From: tanhuazhong @ 2019-07-26 1:50 UTC (permalink / raw)
To: Saeed Mahameed, davem@davemloft.net
Cc: lipeng321@huawei.com, yisen.zhuang@huawei.com,
salil.mehta@huawei.com, linuxarm@huawei.com,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
moyufeng@huawei.com
In-Reply-To: <d6a32434af7e9c883f104ae66e62b7b376abb39c.camel@mellanox.com>
On 2019/7/26 5:32, Saeed Mahameed wrote:
> On Thu, 2019-07-25 at 10:34 +0800, tanhuazhong wrote:
>>
>> On 2019/7/25 2:34, Saeed Mahameed wrote:
>>> On Wed, 2019-07-24 at 11:18 +0800, Huazhong Tan wrote:
>>>> From: Yufeng Mo <moyufeng@huawei.com>
>>>>
>>>> This patch modifies firmware version display format in
>>>> hclge(vf)_cmd_init() and hns3_get_drvinfo(). Also, adds
>>>> some optimizations for firmware version display format.
>>>>
>>>> Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
>>>> Signed-off-by: Peng Li <lipeng321@huawei.com>
>>>> Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
>>>> ---
>>>> drivers/net/ethernet/hisilicon/hns3/hnae3.h | 9
>>>> +++++++++
>>>> drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 15
>>>> +++++++++++++--
>>>> drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 10
>>>> +++++++++-
>>>> drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 11
>>>> +++++++++--
>>>> 4 files changed, 40 insertions(+), 5 deletions(-)
>>>>
>>>>
>
> [...]
>
>>>> --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
>>>> +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
>>>> @@ -419,7 +419,15 @@ int hclge_cmd_init(struct hclge_dev *hdev)
>>>> }
>>>> hdev->fw_version = version;
>>>>
>>>> - dev_info(&hdev->pdev->dev, "The firmware version is %08x\n",
>>>> version);
>>>> + pr_info_once("The firmware version is %lu.%lu.%lu.%lu\n",
>>>> + hnae3_get_field(version,
>>>> HNAE3_FW_VERSION_BYTE3_MASK,
>>>> + HNAE3_FW_VERSION_BYTE3_SHIFT),
>>>> + hnae3_get_field(version,
>>>> HNAE3_FW_VERSION_BYTE2_MASK,
>>>> + HNAE3_FW_VERSION_BYTE2_SHIFT),
>>>> + hnae3_get_field(version,
>>>> HNAE3_FW_VERSION_BYTE1_MASK,
>>>> + HNAE3_FW_VERSION_BYTE1_SHIFT),
>>>> + hnae3_get_field(version,
>>>> HNAE3_FW_VERSION_BYTE0_MASK,
>>>> + HNAE3_FW_VERSION_BYTE0_SHIFT));
>>>>
>>>
>>> Device name/string will not be printed now, what happens if i have
>>> multiple devices ? at least print the device name as it was before
>>>
>> Since on each board we only have one firmware, the firmware
>> version is same per device, and will not change when running.
>> So pr_info_once() looks good for this case.
>>
>
> boards change too often to have such static assumption.
Ok, I will use dev_info instead of pr_info here.
>
>> BTW, maybe we should change below print in the end of
>> hclge_init_ae_dev(), use dev_info() instead of pr_info(),
>> then we can know that which device has already initialized.
>> I will send other patch to do that, is it acceptable for you?
>>
>> "pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);"
>>
>
> I would avoid using pr_info when i can ! if you have the option to
> print with dev information as it was before that is preferable.
>
> Thanks,
> Saeed.
>
Thanks,
Huazhong.
^ permalink raw reply
* Re: [PATCH net-next 07/11] net: hns3: adds debug messages to identify eth down cause
From: liuyonglong @ 2019-07-26 2:21 UTC (permalink / raw)
To: Saeed Mahameed, tanhuazhong@huawei.com, davem@davemloft.net
Cc: lipeng321@huawei.com, yisen.zhuang@huawei.com,
salil.mehta@huawei.com, linuxarm@huawei.com,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <75a02bbe5b3b0f2755cd901a8830d4a3026f9383.camel@mellanox.com>
We will change all of them to netif_msg_drv() which is default off
Thanks for your reply!
On 2019/7/26 5:59, Saeed Mahameed wrote:
> On Thu, 2019-07-25 at 20:28 +0800, liuyonglong wrote:
>>
>> On 2019/7/25 3:12, Saeed Mahameed wrote:
>>> On Wed, 2019-07-24 at 11:18 +0800, Huazhong Tan wrote:
>>>> From: Yonglong Liu <liuyonglong@huawei.com>
>>>>
>>>> Some times just see the eth interface have been down/up via
>>>> dmesg, but can not know why the eth down. So adds some debug
>>>> messages to identify the cause for this.
>>>>
>>>
>>> I really don't like this. your default msg lvl has NETIF_MSG_IFDOWN
>>> turned on .. dumping every single operation that happens on your
>>> device
>>> by default to kernel log is too much !
>>>
>>> We should really consider using trace buffers with well defined
>>> structures for vendor specific events. so we can use bpf filters
>>> and
>>> state of the art tools for netdev debugging.
>>>
>>
>> We do this because we can just see a link down message in dmesg, and
>> had
>> take a long time to found the cause of link down, just because
>> another
>> user changed the settings.
>>
>> We can change the net_open/net_stop/dcbnl_ops to msg_drv (not default
>> turned on), and want to keep the others default print to kernel log,
>> is it acceptable?
>>
>
> acceptable as long as debug information are kept off by default and
> your driver doens't spam the kernel log.
>
> you should use dynamic debug [1] and/or "off by default" msg lvls for
> debugging information..
>
> I couldn't find any rules regarding what to put in kernel log, Maybe
> someone can share ?. but i vaguely remember that the recommendation
> for device drivers is to put nothing, only error/warning messages.
>
> [1]
> https://www.kernel.org/doc/html/v4.15/admin-guide/dynamic-debug-howto.html
>
>>>> @@ -1593,6 +1603,11 @@ static int hns3_ndo_set_vf_vlan(struct
>>>> net_device *netdev, int vf, u16 vlan,
>>>> struct hnae3_handle *h = hns3_get_handle(netdev);
>>>> int ret = -EIO;
>>>>
>>>> + if (netif_msg_ifdown(h))
>>>
>>> why msg_ifdown ? looks like netif_msg_drv is more appropriate, for
>>> many
>>> of the cases in this patch.
>>>
>>
>> This operation may cause link down, so we use msg_ifdown.
>>
>
> ifdown isn't link down..
>
> to be honest, I couldn't find any documentation explaining how/when to
> use msg lvls, (i didn't look too deep though), by looking at other
> drivers, my interpretations is:
>
> ifdup (open/boot up flow)
> ifdwon (close/teardown flow)
> drv (driver based or dynamic flows)
> etc ..
>
> -Saeed.
>
^ permalink raw reply
* [PATCH 2/2] net: ipv4: Fix a possible null-pointer dereference in fib4_rule_suppress()
From: Jia-Ju Bai @ 2019-07-26 2:25 UTC (permalink / raw)
To: davem, kuznet, yoshfuji; +Cc: netdev, linux-kernel, Jia-Ju Bai
In fib4_rule_suppress(), there is an if statement on line 145 to check
whether result->fi is NULL:
if (result->fi)
When result->fi is NULL, it is used on line 167:
fib_info_put(result->fi);
In fib_info_put(), the argument fi is used:
if (refcount_dec_and_test(&fi->fib_clntref))
Thus, a possible null-pointer dereference may occur.
To fix this bug, result->fi is checked before calling fib_info_put().
This bug is found by a static analysis tool STCheck written by us.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
---
net/ipv4/fib_rules.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index b43a7ba5c6a4..daedce293aab 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -163,7 +163,7 @@ static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg
return false;
suppress_route:
- if (!(arg->flags & FIB_LOOKUP_NOREF))
+ if (!(arg->flags & FIB_LOOKUP_NOREF) && result->fi)
fib_info_put(result->fi);
return true;
}
--
2.17.0
^ permalink raw reply related
* [PATCH 1/2] net: ipv4: Fix a possible null-pointer dereference in inet_csk_rebuild_route()
From: Jia-Ju Bai @ 2019-07-26 2:25 UTC (permalink / raw)
To: davem, kuznet, yoshfuji; +Cc: netdev, linux-kernel, Jia-Ju Bai
In inet_csk_rebuild_route(), rt is assigned to NULL on line 1071.
On line 1076, rt is used:
return &rt->dst;
Thus, a possible null-pointer dereference may occur.
To fix this bug, rt is checked before being used.
This bug is found by a static analysis tool STCheck written by us.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
---
net/ipv4/inet_connection_sock.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f5c163d4771b..27d9d80f3401 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1073,7 +1073,10 @@ static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *f
sk_setup_caps(sk, &rt->dst);
rcu_read_unlock();
- return &rt->dst;
+ if (rt)
+ return &rt->dst;
+ else
+ return NULL;
}
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
--
2.17.0
^ permalink raw reply related
* Re: [PATCH net-next 07/11] net: hns3: adds debug messages to identify eth down cause
From: liuyonglong @ 2019-07-26 2:33 UTC (permalink / raw)
To: Jakub Kicinski, Saeed Mahameed
Cc: tanhuazhong@huawei.com, davem@davemloft.net, lipeng321@huawei.com,
yisen.zhuang@huawei.com, salil.mehta@huawei.com,
linuxarm@huawei.com, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <20190725182846.253ae93f@cakuba.netronome.com>
As Saeed said, we will use netif_msg_drv() which is default off, this
can be easily open with ethtool.
Thanks for your reply!
On 2019/7/26 9:28, Jakub Kicinski wrote:
> On Thu, 25 Jul 2019 21:59:08 +0000, Saeed Mahameed wrote:
>> I couldn't find any rules regarding what to put in kernel log, Maybe
>> someone can share ?. but i vaguely remember that the recommendation
>> for device drivers is to put nothing, only error/warning messages.
>
> FWIW my understanding is also that only error/warning messages should
> be printed. IOW things which should "never happen".
>
> There are some historical exceptions. Probe logs for instance may be
> useful, because its not trivial to get to the device if probe fails.
>
> Another one is ethtool flashing, if it takes time we used to print into
> logs some message like "please wait patiently". But since Jiri added
> the progress messages in devlink that's no longer necessary.
>
> For the messages which are basically printing the name of the function
> or name of the function and their args - we have ftrace.
>
> That's my $0.02 :)
>
> .
>
^ permalink raw reply
* Re: memory leak in dma_buf_ioctl
From: syzbot @ 2019-07-26 2:34 UTC (permalink / raw)
To: bsingharora, coreteam, davem, dri-devel, duwe, dvyukov, kaber,
kadlec, linaro-mm-sig, linux-kernel, linux-media, mingo, mpe,
netdev, netfilter-devel, pablo, rostedt, sumit.semwal,
syzkaller-bugs
In-Reply-To: <000000000000b68e04058e6a3421@google.com>
syzbot has bisected this bug to:
commit 04cf31a759ef575f750a63777cee95500e410994
Author: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu Mar 24 11:04:01 2016 +0000
ftrace: Make ftrace_location_range() global
bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=154293f4600000
start commit: abdfd52a Merge tag 'armsoc-defconfig' of git://git.kernel...
git tree: upstream
final crash: https://syzkaller.appspot.com/x/report.txt?x=174293f4600000
console output: https://syzkaller.appspot.com/x/log.txt?x=134293f4600000
kernel config: https://syzkaller.appspot.com/x/.config?x=d31de3d88059b7fa
dashboard link: https://syzkaller.appspot.com/bug?extid=b2098bc44728a4efb3e9
syz repro: https://syzkaller.appspot.com/x/repro.syz?x=12526e58600000
C reproducer: https://syzkaller.appspot.com/x/repro.c?x=161784f0600000
Reported-by: syzbot+b2098bc44728a4efb3e9@syzkaller.appspotmail.com
Fixes: 04cf31a759ef ("ftrace: Make ftrace_location_range() global")
For information about bisection process see: https://goo.gl/tpsmEJ#bisection
^ permalink raw reply
* Re: memory leak in dma_buf_ioctl
From: Steven Rostedt @ 2019-07-26 2:46 UTC (permalink / raw)
To: syzbot
Cc: bsingharora, coreteam, davem, dri-devel, duwe, dvyukov, kaber,
kadlec, linaro-mm-sig, linux-kernel, linux-media, mingo, mpe,
netdev, netfilter-devel, pablo, sumit.semwal, syzkaller-bugs
In-Reply-To: <00000000000005dbbc058e8c608d@google.com>
On Thu, 25 Jul 2019 19:34:01 -0700
syzbot <syzbot+b2098bc44728a4efb3e9@syzkaller.appspotmail.com> wrote:
> syzbot has bisected this bug to:
>
> commit 04cf31a759ef575f750a63777cee95500e410994
> Author: Michael Ellerman <mpe@ellerman.id.au>
> Date: Thu Mar 24 11:04:01 2016 +0000
>
> ftrace: Make ftrace_location_range() global
It's sad that I have yet to find a single syzbot bisect useful. Really?
setting a function from static to global will cause a memory leak in a
completely unrelated area of the kernel?
I'm about to set these to my /dev/null folder.
-- Steve
>
> bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=154293f4600000
> start commit: abdfd52a Merge tag 'armsoc-defconfig' of git://git.kernel...
> git tree: upstream
> final crash: https://syzkaller.appspot.com/x/report.txt?x=174293f4600000
> console output: https://syzkaller.appspot.com/x/log.txt?x=134293f4600000
> kernel config: https://syzkaller.appspot.com/x/.config?x=d31de3d88059b7fa
> dashboard link: https://syzkaller.appspot.com/bug?extid=b2098bc44728a4efb3e9
> syz repro: https://syzkaller.appspot.com/x/repro.syz?x=12526e58600000
> C reproducer: https://syzkaller.appspot.com/x/repro.c?x=161784f0600000
>
> Reported-by: syzbot+b2098bc44728a4efb3e9@syzkaller.appspotmail.com
> Fixes: 04cf31a759ef ("ftrace: Make ftrace_location_range() global")
>
> For information about bisection process see: https://goo.gl/tpsmEJ#bisection
^ permalink raw reply
* [PATCH V2 net-next 04/11] net: hns3: fix mis-counting IRQ vector numbers issue
From: Huazhong Tan @ 2019-07-26 3:24 UTC (permalink / raw)
To: davem
Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm,
Yonglong Liu, Peng Li, Huazhong Tan
In-Reply-To: <1564111502-15504-1-git-send-email-tanhuazhong@huawei.com>
From: Yonglong Liu <liuyonglong@huawei.com>
The num_msi_left means the vector numbers of NIC, but if the
PF supported RoCE, it contains the vector numbers of NIC and
RoCE(Not expected).
This may cause interrupts lost in some case, because of the
NIC module used the vector resources which belongs to RoCE.
This patch corrects the value of num_msi_left to be equals to
the vector numbers of NIC, and adjust the default tqp numbers
according to the value of num_msi_left. Also, adds a little
cleanup about checking whether the device is supporting RoCE
before allocating IRQ vector.
Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 ++
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 12 ++++++++++--
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3c64d70..9329aab 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1476,6 +1476,8 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
nic->ae_algo = &ae_algo;
nic->numa_node_mask = hdev->numa_node_mask;
+ num_tqps = min_t(u16, hdev->roce_base_msix_offset - 1, num_tqps);
+
ret = hclge_knic_setup(vport, num_tqps,
hdev->num_tx_desc, hdev->num_rx_desc);
if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index a13a0e1..db84782 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -287,6 +287,14 @@ static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
memcpy(&hdev->rss_size_max, &resp_msg[2], sizeof(u16));
memcpy(&hdev->rx_buf_len, &resp_msg[4], sizeof(u16));
+ /* if irq is not enough, let tqps have the same value of irqs,
+ * to make sure one irq just bind to one tqp, this can improve
+ * the performance
+ */
+ hdev->num_tqps = min_t(u16, hdev->roce_base_msix_offset - 1,
+ hdev->num_tqps);
+ hdev->rss_size_max = min_t(u16, hdev->rss_size_max, hdev->num_tqps);
+
return 0;
}
@@ -2208,7 +2216,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
int vectors;
int i;
- if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B))
+ if (hnae3_dev_roce_supported(hdev))
vectors = pci_alloc_irq_vectors(pdev,
hdev->roce_base_msix_offset + 1,
hdev->num_msi,
@@ -2495,7 +2503,7 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
req = (struct hclgevf_query_res_cmd *)desc.data;
- if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) {
+ if (hnae3_dev_roce_supported(hdev)) {
hdev->roce_base_msix_offset =
hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
HCLGEVF_MSIX_OFT_ROCEE_M,
--
2.7.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox