* [PATCH] net: r6040: add in missing white space in error message text
From: Colin King @ 2016-09-12 12:08 UTC (permalink / raw)
To: Florian Fainelli, netdev, linux-kernel
From: Colin Ian King <colin.king@canonical.com>
A couple of dev_err messages span two lines and the literal
string is missing a white space between words. Add the white
space.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
---
drivers/net/ethernet/rdc/r6040.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index cb29ee2..5dc655b 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -1062,13 +1062,13 @@ static int r6040_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
/* this should always be supported */
err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
if (err) {
- dev_err(&pdev->dev, "32-bit PCI DMA addresses"
+ dev_err(&pdev->dev, "32-bit PCI DMA addresses "
"not supported by the card\n");
goto err_out_disable_dev;
}
err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
if (err) {
- dev_err(&pdev->dev, "32-bit PCI DMA addresses"
+ dev_err(&pdev->dev, "32-bit PCI DMA addresses "
"not supported by the card\n");
goto err_out_disable_dev;
}
--
2.9.3
^ permalink raw reply related
* [PATCH] test_bpf: fix the dummy skb after dissector changes
From: Jakub Kicinski @ 2016-09-12 12:04 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann
Cc: netdev, Hadar Hen Zion, Jakub Kicinski
Commit d5709f7ab776 ("flow_dissector: For stripped vlan, get vlan
info from skb->vlan_tci") made flow dissector look at vlan_proto
when vlan is present. Since test_bpf sets skb->vlan_tci to ~0
(including VLAN_TAG_PRESENT) we have to populate skb->vlan_proto.
Fixes false negative on test #24:
test_bpf: #24 LD_PAYLOAD_OFF jited:0 175 ret 0 != 42 FAIL (1 times)
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dinan Gunawardena <dinan.gunawardena@netronome.com>
---
lib/test_bpf.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 93f45011a59d..94346b4d8984 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5485,6 +5485,7 @@ static struct sk_buff *populate_skb(char *buf, int size)
skb->hash = SKB_HASH;
skb->queue_mapping = SKB_QUEUE_MAP;
skb->vlan_tci = SKB_VLAN_TCI;
+ skb->vlan_proto = htons(ETH_P_IP);
skb->dev = &dev;
skb->dev->ifindex = SKB_DEV_IFINDEX;
skb->dev->type = SKB_DEV_TYPE;
--
1.9.1
^ permalink raw reply related
* Re: [PATCH 20/26] stmmac: pci: constify local structures
From: Julia Lawall @ 2016-09-12 12:08 UTC (permalink / raw)
To: Giuseppe Cavallaro
Cc: joe, kernel-janitors, Alexandre Torgue, netdev, linux-kernel
In-Reply-To: <1473599168-30561-21-git-send-email-Julia.Lawall@lip6.fr>
On Sun, 11 Sep 2016, Julia Lawall wrote:
> For structure types defined in the same file or local header files, find
> top-level static structure declarations that have the following
> properties:
> 1. Never reassigned.
> 2. Address never taken
> 3. Not passed to a top-level macro call
> 4. No pointer or array-typed field passed to a function or stored in a
> variable.
> Declare structures having all of these properties as const.
Please ignore this patch. Coccinelle incorrectly interpreted
{PCI_VDEVICE(INTEL, STMMAC_QUARK_ID), (kernel_ulong_t)&quark_pci_info}
as a bit and operation, since it did not recognize kernel_ulong_t as a
type.
julia
> Done using Coccinelle.
> Based on a suggestion by Joe Perches <joe@perches.com>.
>
> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
>
> ---
> The semantic patch seems too long for a commit log, but is in the cover
> letter.
>
> drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
> index 56c8a23..5c612c3 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
> @@ -141,7 +141,7 @@ static struct stmmac_pci_dmi_data quark_pci_dmi_data[] = {
> {}
> };
>
> -static struct stmmac_pci_info quark_pci_info = {
> +static const struct stmmac_pci_info quark_pci_info = {
> .setup = quark_default_data,
> .dmi = quark_pci_dmi_data,
> };
>
> --
> To unsubscribe from this list: send the line "unsubscribe kernel-janitors" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply
* Re: [PATCH] net: dsa: add FIB support
From: kbuild test robot @ 2016-09-12 12:05 UTC (permalink / raw)
To: John Crispin
Cc: kbuild-all, David S. Miller, Andrew Lunn, Florian Fainelli,
netdev, linux-kernel, John Crispin
In-Reply-To: <1473675233-36952-1-git-send-email-john@phrozen.org>
[-- Attachment #1: Type: text/plain, Size: 7351 bytes --]
Hi John,
[auto build test WARNING on net-next/master]
[also build test WARNING on next-20160912]
[cannot apply to v4.8-rc6]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
[Suggest to use git(>=2.9.0) format-patch --base=<commit> (or --base=auto for convenience) to record what (public, well-known) commit your patch series was built on]
[Check https://git-scm.com/docs/git-format-patch for more information]
url: https://github.com/0day-ci/linux/commits/John-Crispin/net-dsa-add-FIB-support/20160912-190416
config: i386-randconfig-x011-09112120 (attached as .config)
compiler: gcc-6 (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
All warnings (new ones prefixed by >>):
In file included from include/uapi/linux/stddef.h:1:0,
from include/linux/stddef.h:4,
from include/uapi/linux/posix_types.h:4,
from include/uapi/linux/types.h:13,
from include/linux/types.h:5,
from include/linux/list.h:4,
from net/dsa/slave.c:11:
net/dsa/slave.c: In function 'dsa_slave_ipv4_fib_add':
net/dsa/slave.c:345:9: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^
include/linux/compiler.h:149:30: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^~~~
>> net/dsa/slave.c:345:2: note: in expansion of macro 'if'
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:345:39: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^
include/linux/compiler.h:149:30: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^~~~
>> net/dsa/slave.c:345:2: note: in expansion of macro 'if'
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:345:9: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^
include/linux/compiler.h:149:42: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^~~~
>> net/dsa/slave.c:345:2: note: in expansion of macro 'if'
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:345:39: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^
include/linux/compiler.h:149:42: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^~~~
>> net/dsa/slave.c:345:2: note: in expansion of macro 'if'
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:345:9: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^
include/linux/compiler.h:160:16: note: in definition of macro '__trace_if'
______r = !!(cond); \
^~~~
>> net/dsa/slave.c:345:2: note: in expansion of macro 'if'
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:345:39: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^
include/linux/compiler.h:160:16: note: in definition of macro '__trace_if'
______r = !!(cond); \
^~~~
>> net/dsa/slave.c:345:2: note: in expansion of macro 'if'
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:349:11: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
ret = ds->drv->ipv4_fib_prepare(ds, p->port, fib4, trans);
^~
net/dsa/slave.c:351:11: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
ret = ds->drv->ipv4_fib_add(ds, p->port, fib4, trans);
^~
In file included from include/uapi/linux/stddef.h:1:0,
from include/linux/stddef.h:4,
from include/uapi/linux/posix_types.h:4,
from include/uapi/linux/types.h:13,
from include/linux/types.h:5,
from include/linux/list.h:4,
from net/dsa/slave.c:11:
net/dsa/slave.c: In function 'dsa_slave_ipv4_fib_del':
net/dsa/slave.c:363:8: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (ds->drv->ipv4_fib_del)
^
include/linux/compiler.h:149:30: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^~~~
net/dsa/slave.c:363:2: note: in expansion of macro 'if'
if (ds->drv->ipv4_fib_del)
^~
net/dsa/slave.c:363:8: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (ds->drv->ipv4_fib_del)
^
include/linux/compiler.h:149:42: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^~~~
net/dsa/slave.c:363:2: note: in expansion of macro 'if'
if (ds->drv->ipv4_fib_del)
^~
net/dsa/slave.c:363:8: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (ds->drv->ipv4_fib_del)
^
include/linux/compiler.h:160:16: note: in definition of macro '__trace_if'
______r = !!(cond); \
^~~~
net/dsa/slave.c:363:2: note: in expansion of macro 'if'
if (ds->drv->ipv4_fib_del)
^~
net/dsa/slave.c:364:11: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
ret = ds->drv->ipv4_fib_del(ds, p->port, fib4);
^~
vim +/if +345 net/dsa/slave.c
329 struct dsa_switch *ds = p->parent;
330
331 if (ds->ops->port_mdb_dump)
332 return ds->ops->port_mdb_dump(ds, p->port, mdb, cb);
333
334 return -EOPNOTSUPP;
335 }
336
337 static int dsa_slave_ipv4_fib_add(struct net_device *dev,
338 const struct switchdev_obj_ipv4_fib *fib4,
339 struct switchdev_trans *trans)
340 {
341 struct dsa_slave_priv *p = netdev_priv(dev);
342 struct dsa_switch *ds = p->parent;
343 int ret;
344
> 345 if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
346 return -EOPNOTSUPP;
347
348 if (switchdev_trans_ph_prepare(trans))
349 ret = ds->drv->ipv4_fib_prepare(ds, p->port, fib4, trans);
350 else
351 ret = ds->drv->ipv4_fib_add(ds, p->port, fib4, trans);
352
353 return ret;
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/octet-stream, Size: 31649 bytes --]
^ permalink raw reply
* [PATCH][V2] atm: iphase: fix newline escape and minor tweak to source formatting Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit
From: Colin King @ 2016-09-12 12:01 UTC (permalink / raw)
To: Chas Williams, linux-atm-general, netdev; +Cc: linux-kernel
From: Colin Ian King <colin.king@canonical.com>
The newline escape is incorrect and needs fixing. Also adjust source
formatting / indentation and add { } to trailing else.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
---
drivers/atm/iphase.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 9d8807e..ddb244e 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -1885,9 +1885,9 @@ static int open_tx(struct atm_vcc *vcc)
if ((ret = ia_cbr_setup (iadev, vcc)) < 0) {
return ret;
}
- }
- else
- printk("iadev: Non UBR, ABR and CBR traffic not supportedn");
+ } else {
+ printk("iadev: Non UBR, ABR and CBR traffic not supported\n");
+ }
iadev->testTable[vcc->vci]->vc_status |= VC_ACTIVE;
IF_EVENT(printk("ia open_tx returning \n");)
--
2.9.3
^ permalink raw reply related
* Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines
From: Jesper Dangaard Brouer @ 2016-09-12 11:56 UTC (permalink / raw)
To: Tom Herbert
Cc: John Fastabend, Brenden Blanco, Alexei Starovoitov, Jeff Kirsher,
David S. Miller, Cong Wang, intel-wired-lan, William Tu,
Linux Kernel Network Developers, brouer
In-Reply-To: <CALx6S36SM-wq6Fj8XK7GfMta1dVGr3RZ5uAgGdnxm7kgpVNFbw@mail.gmail.com>
On Fri, 9 Sep 2016 18:19:56 -0700 Tom Herbert <tom@herbertland.com> wrote:
> On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend <john.fastabend@gmail.com> wrote:
> > On 16-09-09 06:04 PM, Tom Herbert wrote:
> >> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend <john.fastabend@gmail.com> wrote:
> >>> On 16-09-09 04:44 PM, Tom Herbert wrote:
> >>>> On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend <john.fastabend@gmail.com> wrote:
> >>>>> e1000 supports a single TX queue so it is being shared with the stack
> >>>>> when XDP runs XDP_TX action. This requires taking the xmit lock to
> >>>>> ensure we don't corrupt the tx ring. To avoid taking and dropping the
> >>>>> lock per packet this patch adds a bundling implementation to submit
> >>>>> a bundle of packets to the xmit routine.
> >>>>>
> >>>>> I tested this patch running e1000 in a VM using KVM over a tap
> >>>>> device using pktgen to generate traffic along with 'ping -f -l 100'.
> >>>>>
> >>>> Hi John,
> >>>>
> >>>> How does this interact with BQL on e1000?
> >>>>
> >>>> Tom
> >>>>
> >>>
> >>> Let me check if I have the API correct. When we enqueue a packet to
> >>> be sent we must issue a netdev_sent_queue() call and then on actual
> >>> transmission issue a netdev_completed_queue().
> >>>
> >>> The patch attached here missed a few things though.
> >>>
> >>> But it looks like I just need to call netdev_sent_queue() from the
> >>> e1000_xmit_raw_frame() routine and then let the tx completion logic
> >>> kick in which will call netdev_completed_queue() correctly.
> >>>
> >>> I'll need to add a check for the queue state as well. So if I do these
> >>> three things,
> >>>
> >>> check __QUEUE_STATE_XOFF before sending
> >>> netdev_sent_queue() -> on XDP_TX
> >>> netdev_completed_queue()
> >>>
> >>> It should work agree? Now should we do this even when XDP owns the
> >>> queue? Or is this purely an issue with sharing the queue between
> >>> XDP and stack.
> >>>
> >> But what is the action for XDP_TX if the queue is stopped? There is no
> >> qdisc to back pressure in the XDP path. Would we just start dropping
> >> packets then?
> >
> > Yep that is what the patch does if there is any sort of error packets
> > get dropped on the floor. I don't think there is anything else that
> > can be done.
I agree, the only option is the drop the packet. For a DDoS use-case,
this is good, because this "switch" XDP into a more efficient mode
(direct recycling pages).
> >
> That probably means that the stack will always win out under load.
Why would the stack win? Wouldn't XDP_TX win?
> Trying to used the same queue where half of the packets are well
> managed by a qdisc and half aren't is going to leave someone unhappy.
> Maybe in the this case where we have to share the qdisc we can
> allocate the skb on on returning XDP_TX and send through the normal
> qdisc for the device.
Hmmm. I'm not sure I like the approach of allocating an SKB, and
injecting into the qdisc. Most of the performance gain goes out the
window. Unless, we (1) bulk alloc SKBs, and (2) can avoid initializing
the entire SKB, and (3) bulk enqueue into qdisc. It would be an
interesting "tool" for a zoom-in benchmark, what would allow us to
determine the cost/overhead of the network stack between RX to
qdisc-enqueue.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: [PATCH] atm: iphase: fix newline escape and minor tweak to source formatting
From: Sergei Shtylyov @ 2016-09-12 11:55 UTC (permalink / raw)
To: Colin King, Chas Williams, linux-atm-general, netdev; +Cc: linux-kernel
In-Reply-To: <20160912092930.20683-1-colin.king@canonical.com>
Hello.
On 9/12/2016 12:29 PM, Colin King wrote:
> From: Colin Ian King <colin.king@canonical.com>
>
> The newline escape is incorrect and needs fixing. Also adjust source
> formatting / indentation and remove trailing white space.
>
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
> ---
> drivers/atm/iphase.c | 5 ++---
> 1 file changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
> index 9d8807e..256b191 100644
> --- a/drivers/atm/iphase.c
> +++ b/drivers/atm/iphase.c
> @@ -1885,9 +1885,8 @@ static int open_tx(struct atm_vcc *vcc)
> if ((ret = ia_cbr_setup (iadev, vcc)) < 0) {
> return ret;
> }
> - }
> - else
> - printk("iadev: Non UBR, ABR and CBR traffic not supportedn");
> + } else
> + printk("iadev: Non UBR, ABR and CBR traffic not supported\n");
All branches of the *if* statement should have {} if at least one has them
(perhaps a material for a follow-up patch).
[...]
MBR, Sergei
^ permalink raw reply
* Re: [PATCH] atm: iphase: fix newline escape and minor tweak to source formatting
From: Sergei Shtylyov @ 2016-09-12 11:55 UTC (permalink / raw)
To: Colin King, Chas Williams, linux-atm-general, netdev; +Cc: linux-kernel
In-Reply-To: <20160912092930.20683-1-colin.king@canonical.com>
Hello.
On 9/12/2016 12:29 PM, Colin King wrote:
> From: Colin Ian King <colin.king@canonical.com>
>
> The newline escape is incorrect and needs fixing. Also adjust source
> formatting / indentation and remove trailing white space.
>
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
> ---
> drivers/atm/iphase.c | 5 ++---
> 1 file changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
> index 9d8807e..256b191 100644
> --- a/drivers/atm/iphase.c
> +++ b/drivers/atm/iphase.c
> @@ -1885,9 +1885,8 @@ static int open_tx(struct atm_vcc *vcc)
> if ((ret = ia_cbr_setup (iadev, vcc)) < 0) {
> return ret;
> }
> - }
> - else
> - printk("iadev: Non UBR, ABR and CBR traffic not supportedn");
> + } else
> + printk("iadev: Non UBR, ABR and CBR traffic not supported\n");
All branches of the *if* statement should have {} if at least one has
them, perhaps a material for a follow-up patch).
[...]
MBR, Sergei
^ permalink raw reply
* Re: [PATCH 1/3] Documentation: devicetree: add qca8k binding
From: Sergei Shtylyov @ 2016-09-12 11:53 UTC (permalink / raw)
To: John Crispin, David S. Miller, Andrew Lunn, Florian Fainelli
Cc: netdev, linux-kernel, qsdk-review, devicetree
In-Reply-To: <1473669337-21221-2-git-send-email-john@phrozen.org>
On 9/12/2016 11:35 AM, John Crispin wrote:
> Add device-tree binding for ar8xxx switch families.
>
> Cc: devicetree@vger.kernel.org
> Signed-off-by: John Crispin <john@phrozen.org>
> ---
> .../devicetree/bindings/net/dsa/qca8k.txt | 53 ++++++++++++++++++++
> 1 file changed, 53 insertions(+)
> create mode 100644 Documentation/devicetree/bindings/net/dsa/qca8k.txt
>
> diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.txt b/Documentation/devicetree/bindings/net/dsa/qca8k.txt
> new file mode 100644
> index 0000000..2a1ad06
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/net/dsa/qca8k.txt
> @@ -0,0 +1,53 @@
> +* Qualcomm Atheros QCA8xxx switch family
> +
> +Required properties:
> +
> +- compatible: should be "qca,qca8337"
> +- #size-cells: must be 0
> +- #address-cells: must be 1
> +
> +Subnodes:
> +
> +The integrated switch subnode should be specified according to the binding
> +described in dsa/dsa.txt.
> +
> +Example:
> +
> + &mdio0 {
> + switch@0 {
> + compatible = "qca,qca8337";
> +
> + #address-cells = <1>;
> + #size-cells = <0>;
> + reg = <30>;
> +
> + ports {
> + port@0 {
> + reg = <11>;
> + label = "cpu";
> + ethernet = <&gmac1>;
> + phy-mode = "rgmii";
> + };
> +
> + port@1 {
> + reg = <0>;
> + label = "lan1";
> + };
> +
> + port@2 {
> + reg = <1>;
> + label = "lan2";
> + };
> +
> + port@3 {
> + reg = <2>;
> + label = "lan3";
> + };
> +
> + port@4 {
> + reg = <3>;
> + label = "lan4";
> + };
The <unit-address> part of the node name should correspond to the "reg"
prop. I think modern 'dtc' even warns about that...
[...]
MBR, Sergei
^ permalink raw reply
* Re: [PATCH net-next] xen-netfront: avoid packet loss when ethernet header crosses page boundary
From: Vitaly Kuznetsov @ 2016-09-12 11:52 UTC (permalink / raw)
To: David Miller
Cc: netdev, xen-devel, linux-kernel, Boris Ostrovsky, Juergen Gross,
Patrick Talbert, David Vrabel
In-Reply-To: <57D2BC13.8050903@citrix.com>
David Vrabel <david.vrabel@citrix.com> writes:
> On 22/08/16 16:42, Vitaly Kuznetsov wrote:
>> Small packet loss is reported on complex multi host network configurations
>> including tunnels, NAT, ... My investigation led me to the following check
>> in netback which drops packets:
>>
>> if (unlikely(txreq.size < ETH_HLEN)) {
>> netdev_err(queue->vif->dev,
>> "Bad packet size: %d\n", txreq.size);
>> xenvif_tx_err(queue, &txreq, extra_count, idx);
>> break;
>> }
>>
>> But this check itself is legitimate. SKBs consist of a linear part (which
>> has to have the ethernet header) and (optionally) a number of frags.
>> Netfront transmits the head of the linear part up to the page boundary
>> as the first request and all the rest becomes frags so when we're
>> reconstructing the SKB in netback we can't distinguish between original
>> frags and the 'tail' of the linear part. The first SKB needs to be at
>> least ETH_HLEN size. So in case we have an SKB with its linear part
>> starting too close to the page boundary the packet is lost.
>>
>> I see two ways to fix the issue:
>> - Change the 'wire' protocol between netfront and netback to start keeping
>> the original SKB structure. We'll have to add a flag indicating the fact
>> that the particular request is a part of the original linear part and not
>> a frag. We'll need to know the length of the linear part to pre-allocate
>> memory.
>> - Avoid transmitting SKBs with linear parts starting too close to the page
>> boundary. That seems preferable short-term and shouldn't bring
>> significant performance degradation as such packets are rare. That's what
>> this patch is trying to achieve with skb_copy().
>>
>> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
>
> We should probably fix the backend to handle this (by grant copying a
> minimum amount in the linear area, but since netfront needs to work with
> older netback.
>
> Acked-by: David Vrabel <david.vrabel@citrix.com>
David,
could you please pick this up for net-next or are there any concerns
remaining?
Thanks,
--
Vitaly
^ permalink raw reply
* Re: [PATCH] net: dsa: add FIB support
From: kbuild test robot @ 2016-09-12 11:48 UTC (permalink / raw)
To: John Crispin
Cc: kbuild-all, David S. Miller, Andrew Lunn, Florian Fainelli,
netdev, linux-kernel, John Crispin
In-Reply-To: <1473675233-36952-1-git-send-email-john@phrozen.org>
[-- Attachment #1: Type: text/plain, Size: 2496 bytes --]
Hi John,
[auto build test ERROR on net-next/master]
[also build test ERROR on next-20160912]
[cannot apply to v4.8-rc6]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
[Suggest to use git(>=2.9.0) format-patch --base=<commit> (or --base=auto for convenience) to record what (public, well-known) commit your patch series was built on]
[Check https://git-scm.com/docs/git-format-patch for more information]
url: https://github.com/0day-ci/linux/commits/John-Crispin/net-dsa-add-FIB-support/20160912-190416
config: x86_64-randconfig-x006-201637 (attached as .config)
compiler: gcc-6 (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
All errors (new ones prefixed by >>):
net/dsa/slave.c: In function 'dsa_slave_ipv4_fib_add':
>> net/dsa/slave.c:345:9: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:345:39: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
^~
net/dsa/slave.c:349:11: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
ret = ds->drv->ipv4_fib_prepare(ds, p->port, fib4, trans);
^~
net/dsa/slave.c:351:11: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
ret = ds->drv->ipv4_fib_add(ds, p->port, fib4, trans);
^~
net/dsa/slave.c: In function 'dsa_slave_ipv4_fib_del':
net/dsa/slave.c:363:8: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
if (ds->drv->ipv4_fib_del)
^~
net/dsa/slave.c:364:11: error: 'struct dsa_switch' has no member named 'drv'; did you mean 'dev'?
ret = ds->drv->ipv4_fib_del(ds, p->port, fib4);
^~
vim +345 net/dsa/slave.c
339 struct switchdev_trans *trans)
340 {
341 struct dsa_slave_priv *p = netdev_priv(dev);
342 struct dsa_switch *ds = p->parent;
343 int ret;
344
> 345 if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
346 return -EOPNOTSUPP;
347
348 if (switchdev_trans_ph_prepare(trans))
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/octet-stream, Size: 26906 bytes --]
^ permalink raw reply
* Re: README: [PATCH RFC 11/11] net/mlx5e: XDP TX xmit more
From: Jesper Dangaard Brouer via iovisor-dev @ 2016-09-12 11:30 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Tom Herbert, iovisor-dev, Jamal Hadi Salim, Saeed Mahameed,
Eric Dumazet, netdev-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20160909063048.GA67375-+o4/htvd0TDFYCXBM6kdu7fOX0fSgVTm@public.gmane.org>
On Thu, 8 Sep 2016 23:30:50 -0700
Alexei Starovoitov <alexei.starovoitov-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:
> On Fri, Sep 09, 2016 at 07:36:52AM +0200, Jesper Dangaard Brouer wrote:
[...]
> > Imagine you have packets intermixed towards the stack and XDP_TX.
> > Every time you call the stack code, then you flush your icache. When
> > returning to the driver code, you will have to reload all the icache
> > associated with the XDP_TX, this is a costly operation.
>
[...]
> To make further progress in this discussion can we talk about
> the use case you have in mind instead? Then solution will
> be much clear, I hope.
The DDoS use-case _is_ affected by this "hidden" bulking design.
Lets say, I want to implement a DDoS facility. Instead of just
dropping the malicious packets, I want to see the bad packets. I
implement this by rewriting the destination-MAC to be my monitor
machine and then XDP_TX the packet.
In the DDoS use-case, you have loaded your XDP/eBPF program, and 100%
of the traffic is delivered to the stack. (See note 1)
Once the DDoS attack starts, then the traffic pattern changes, and XDP
should (hopefully only) catch the malicious traffic (monitor machine can
help diagnose false positive). Now, due to interleaving the DDoS
traffic with the clean traffic, then efficiency of XDP_TX is reduced due to
more icache misses...
Note(1): Notice I have already demonstrated that loading a XDP/eBPF
program with 100% delivery to the stack, actually slows down the
normal stack. This is due to hitting a bottleneck in the page
allocator. I'm working removing that bottleneck with page_pool, and
that solution is orthogonal to this problem.
It is actually an excellent argument, for why you would want to run a
DDoS XDP filter only on a restricted number of RX queues.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* [patch net-next 5/5] mlxsw: spectrum: Add support for new ethtool API
From: Jiri Pirko @ 2016-09-12 11:26 UTC (permalink / raw)
To: netdev; +Cc: davem, idosch, eladr, yotamg, nogahf, ogerlitz
In-Reply-To: <1473679587-9112-1-git-send-email-jiri@resnulli.us>
From: Ido Schimmel <idosch@mellanox.com>
Remove the deprecated {get,set}_settings callbacks and instead add
{get,set}_link_ksettings along with support for newly available speeds.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 1 +
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 344 +++++++++++++------------
2 files changed, 185 insertions(+), 160 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 43ce27f..4e2354c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2164,6 +2164,7 @@ MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4);
#define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_ER_LR BIT(14)
#define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 BIT(15)
#define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_LR4_ER4 BIT(16)
+#define MLXSW_REG_PTYS_ETH_SPEED_50GBASE_SR2 BIT(18)
#define MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR4 BIT(19)
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 BIT(20)
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 BIT(21)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f7db669..47f2a41 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1598,158 +1598,179 @@ static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset)
}
struct mlxsw_sp_port_link_mode {
+ enum ethtool_link_mode_bit_indices mask_ethtool;
u32 mask;
- u32 supported;
- u32 advertised;
u32 speed;
};
static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T,
- .supported = SUPPORTED_100baseT_Full,
- .advertised = ADVERTISED_100baseT_Full,
- .speed = 100,
- },
- {
- .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_TX,
- .speed = 100,
+ .mask_ethtool = ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+ .speed = SPEED_100,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII |
MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX,
- .supported = SUPPORTED_1000baseKX_Full,
- .advertised = ADVERTISED_1000baseKX_Full,
- .speed = 1000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+ .speed = SPEED_1000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T,
- .supported = SUPPORTED_10000baseT_Full,
- .advertised = ADVERTISED_10000baseT_Full,
- .speed = 10000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+ .speed = SPEED_10000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4,
- .supported = SUPPORTED_10000baseKX4_Full,
- .advertised = ADVERTISED_10000baseKX4_Full,
- .speed = 10000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+ .speed = SPEED_10000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_ER_LR,
- .supported = SUPPORTED_10000baseKR_Full,
- .advertised = ADVERTISED_10000baseKR_Full,
- .speed = 10000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+ .speed = SPEED_10000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2,
- .supported = SUPPORTED_20000baseKR2_Full,
- .advertised = ADVERTISED_20000baseKR2_Full,
- .speed = 20000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT,
+ .speed = SPEED_20000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4,
- .supported = SUPPORTED_40000baseCR4_Full,
- .advertised = ADVERTISED_40000baseCR4_Full,
- .speed = 40000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+ .speed = SPEED_40000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4,
- .supported = SUPPORTED_40000baseKR4_Full,
- .advertised = ADVERTISED_40000baseKR4_Full,
- .speed = 40000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+ .speed = SPEED_40000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4,
- .supported = SUPPORTED_40000baseSR4_Full,
- .advertised = ADVERTISED_40000baseSR4_Full,
- .speed = 40000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+ .speed = SPEED_40000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_LR4_ER4,
- .supported = SUPPORTED_40000baseLR4_Full,
- .advertised = ADVERTISED_40000baseLR4_Full,
- .speed = 40000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+ .speed = SPEED_40000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR,
+ .mask_ethtool = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+ .speed = SPEED_25000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR,
+ .mask_ethtool = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+ .speed = SPEED_25000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR,
+ .mask_ethtool = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+ .speed = SPEED_25000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR,
+ .mask_ethtool = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+ .speed = SPEED_25000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_50GBASE_CR2,
+ .mask_ethtool = ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+ .speed = SPEED_50000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR2,
+ .mask_ethtool = ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+ .speed = SPEED_50000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_50GBASE_SR2,
+ .mask_ethtool = ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+ .speed = SPEED_50000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT,
+ .speed = SPEED_56000,
},
{
- .mask = MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR |
- MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR |
- MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR,
- .speed = 25000,
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT,
+ .speed = SPEED_56000,
},
{
- .mask = MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR4 |
- MLXSW_REG_PTYS_ETH_SPEED_50GBASE_CR2 |
- MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR2,
- .speed = 50000,
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT,
+ .speed = SPEED_56000,
},
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4,
- .supported = SUPPORTED_56000baseKR4_Full,
- .advertised = ADVERTISED_56000baseKR4_Full,
- .speed = 56000,
+ .mask_ethtool = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT,
+ .speed = SPEED_56000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+ .speed = SPEED_100000,
},
{
- .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 |
- MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
- MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 |
- MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4,
- .speed = 100000,
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+ .speed = SPEED_100000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+ .speed = SPEED_100000,
+ },
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+ .speed = SPEED_100000,
},
};
#define MLXSW_SP_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp_port_link_mode)
-static u32 mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto)
+static void
+mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto,
+ struct ethtool_link_ksettings *cmd)
{
- u32 modes = 0;
-
if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 |
MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 |
MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
MLXSW_REG_PTYS_ETH_SPEED_SGMII))
- modes |= SUPPORTED_FIBRE;
+ ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 |
MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 |
MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 |
MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX))
- modes |= SUPPORTED_Backplane;
- return modes;
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
}
-static u32 mlxsw_sp_from_ptys_supported_link(u32 ptys_eth_proto)
+static void mlxsw_sp_from_ptys_link(u32 ptys_eth_proto, unsigned long *mode)
{
- u32 modes = 0;
int i;
for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask)
- modes |= mlxsw_sp_port_link_mode[i].supported;
+ __set_bit(mlxsw_sp_port_link_mode[i].mask_ethtool,
+ mode);
}
- return modes;
-}
-
-static u32 mlxsw_sp_from_ptys_advert_link(u32 ptys_eth_proto)
-{
- u32 modes = 0;
- int i;
-
- for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
- if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask)
- modes |= mlxsw_sp_port_link_mode[i].advertised;
- }
- return modes;
}
static void mlxsw_sp_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto,
- struct ethtool_cmd *cmd)
+ struct ethtool_link_ksettings *cmd)
{
u32 speed = SPEED_UNKNOWN;
u8 duplex = DUPLEX_UNKNOWN;
@@ -1766,8 +1787,8 @@ static void mlxsw_sp_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto,
}
}
out:
- ethtool_cmd_speed_set(cmd, speed);
- cmd->duplex = duplex;
+ cmd->base.speed = speed;
+ cmd->base.duplex = duplex;
}
static u8 mlxsw_sp_port_connector_port(u32 ptys_eth_proto)
@@ -1792,60 +1813,15 @@ static u8 mlxsw_sp_port_connector_port(u32 ptys_eth_proto)
return PORT_OTHER;
}
-static int mlxsw_sp_port_get_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
-{
- struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
- char ptys_pl[MLXSW_REG_PTYS_LEN];
- u32 eth_proto_cap;
- u32 eth_proto_admin;
- u32 eth_proto_oper;
- u8 autoneg_status;
- u32 eth_proto_lp;
- int err;
-
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
- err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
- if (err) {
- netdev_err(dev, "Failed to get proto");
- return err;
- }
- mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap,
- ð_proto_admin, ð_proto_oper);
- eth_proto_lp = mlxsw_reg_ptys_eth_proto_lp_advertise_get(ptys_pl);
- autoneg_status = mlxsw_reg_ptys_an_status_get(ptys_pl);
-
- cmd->supported = mlxsw_sp_from_ptys_supported_port(eth_proto_cap) |
- mlxsw_sp_from_ptys_supported_link(eth_proto_cap) |
- SUPPORTED_Pause | SUPPORTED_Asym_Pause |
- SUPPORTED_Autoneg;
- if (mlxsw_sp_port->link.autoneg) {
- cmd->advertising =
- mlxsw_sp_from_ptys_advert_link(eth_proto_admin);
- cmd->advertising |= ADVERTISED_Autoneg;
- cmd->autoneg = AUTONEG_ENABLE;
- }
- mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev),
- eth_proto_oper, cmd);
-
- cmd->port = mlxsw_sp_port_connector_port(eth_proto_oper);
-
- if (autoneg_status == MLXSW_REG_PTYS_AN_STATUS_OK && eth_proto_lp)
- cmd->lp_advertising =
- mlxsw_sp_from_ptys_advert_link(eth_proto_lp);
-
- cmd->transceiver = XCVR_INTERNAL;
- return 0;
-}
-
-static u32 mlxsw_sp_to_ptys_advert_link(u32 advertising)
+static u32
+mlxsw_sp_to_ptys_advert_link(const struct ethtool_link_ksettings *cmd)
{
u32 ptys_proto = 0;
int i;
for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
- if (advertising & mlxsw_sp_port_link_mode[i].advertised)
+ if (test_bit(mlxsw_sp_port_link_mode[i].mask_ethtool,
+ cmd->link_modes.advertising))
ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
}
return ptys_proto;
@@ -1875,65 +1851,113 @@ static u32 mlxsw_sp_to_ptys_upper_speed(u32 upper_speed)
return ptys_proto;
}
-static int mlxsw_sp_port_set_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
+static void mlxsw_sp_port_get_link_supported(u32 eth_proto_cap,
+ struct ethtool_link_ksettings *cmd)
+{
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Asym_Pause);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
+
+ mlxsw_sp_from_ptys_supported_port(eth_proto_cap, cmd);
+ mlxsw_sp_from_ptys_link(eth_proto_cap, cmd->link_modes.supported);
+}
+
+static void mlxsw_sp_port_get_link_advertise(u32 eth_proto_admin, bool autoneg,
+ struct ethtool_link_ksettings *cmd)
{
+ if (!autoneg)
+ return;
+
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
+ mlxsw_sp_from_ptys_link(eth_proto_admin, cmd->link_modes.advertising);
+}
+
+static void
+mlxsw_sp_port_get_link_lp_advertise(u32 eth_proto_lp, u8 autoneg_status,
+ struct ethtool_link_ksettings *cmd)
+{
+ if (autoneg_status != MLXSW_REG_PTYS_AN_STATUS_OK || !eth_proto_lp)
+ return;
+
+ ethtool_link_ksettings_add_link_mode(cmd, lp_advertising, Autoneg);
+ mlxsw_sp_from_ptys_link(eth_proto_lp, cmd->link_modes.lp_advertising);
+}
+
+static int mlxsw_sp_port_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
+{
+ u32 eth_proto_cap, eth_proto_admin, eth_proto_oper, eth_proto_lp;
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char ptys_pl[MLXSW_REG_PTYS_LEN];
- u32 speed;
- u32 eth_proto_new;
- u32 eth_proto_cap;
- u32 eth_proto_admin;
+ u8 autoneg_status;
bool autoneg;
int err;
- autoneg = cmd->autoneg == AUTONEG_ENABLE;
- speed = ethtool_cmd_speed(cmd);
+ autoneg = mlxsw_sp_port->link.autoneg;
+ mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
+ if (err)
+ return err;
+ mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, ð_proto_admin,
+ ð_proto_oper);
+
+ mlxsw_sp_port_get_link_supported(eth_proto_cap, cmd);
- eth_proto_new = autoneg ?
- mlxsw_sp_to_ptys_advert_link(cmd->advertising) :
- mlxsw_sp_to_ptys_speed(speed);
+ mlxsw_sp_port_get_link_advertise(eth_proto_admin, autoneg, cmd);
+
+ eth_proto_lp = mlxsw_reg_ptys_eth_proto_lp_advertise_get(ptys_pl);
+ autoneg_status = mlxsw_reg_ptys_an_status_get(ptys_pl);
+ mlxsw_sp_port_get_link_lp_advertise(eth_proto_lp, autoneg_status, cmd);
+
+ cmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+ cmd->base.port = mlxsw_sp_port_connector_port(eth_proto_oper);
+ mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev), eth_proto_oper,
+ cmd);
+
+ return 0;
+}
+
+static int
+mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char ptys_pl[MLXSW_REG_PTYS_LEN];
+ u32 eth_proto_cap, eth_proto_new;
+ bool autoneg;
+ int err;
mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
- if (err) {
- netdev_err(dev, "Failed to get proto");
+ if (err)
return err;
- }
- mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, ð_proto_admin, NULL);
+ mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, NULL, NULL);
+
+ autoneg = cmd->base.autoneg == AUTONEG_ENABLE;
+ eth_proto_new = autoneg ?
+ mlxsw_sp_to_ptys_advert_link(cmd) :
+ mlxsw_sp_to_ptys_speed(cmd->base.speed);
eth_proto_new = eth_proto_new & eth_proto_cap;
if (!eth_proto_new) {
- netdev_err(dev, "Not supported proto admin requested");
+ netdev_err(dev, "No supported speed requested\n");
return -EINVAL;
}
- if (eth_proto_new == eth_proto_admin)
- return 0;
mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, eth_proto_new);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
- if (err) {
- netdev_err(dev, "Failed to set proto admin");
+ if (err)
return err;
- }
if (!netif_running(dev))
return 0;
mlxsw_sp_port->link.autoneg = autoneg;
- err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
- if (err) {
- netdev_err(dev, "Failed to set admin status");
- return err;
- }
-
- err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
- if (err) {
- netdev_err(dev, "Failed to set admin status");
- return err;
- }
+ mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
+ mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
return 0;
}
@@ -1947,8 +1971,8 @@ static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
.set_phys_id = mlxsw_sp_port_set_phys_id,
.get_ethtool_stats = mlxsw_sp_port_get_stats,
.get_sset_count = mlxsw_sp_port_get_sset_count,
- .get_settings = mlxsw_sp_port_get_settings,
- .set_settings = mlxsw_sp_port_set_settings,
+ .get_link_ksettings = mlxsw_sp_port_get_link_ksettings,
+ .set_link_ksettings = mlxsw_sp_port_set_link_ksettings,
};
static int
--
2.5.5
^ permalink raw reply related
* [patch net-next 4/5] mlxsw: spectrum: Indicate support of multiple port types
From: Jiri Pirko @ 2016-09-12 11:26 UTC (permalink / raw)
To: netdev; +Cc: davem, idosch, eladr, yotamg, nogahf, ogerlitz
In-Reply-To: <1473679587-9112-1-git-send-email-jiri@resnulli.us>
From: Ido Schimmel <idosch@mellanox.com>
The device can support multiple port types, so don't return on first
match.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 49b8d69..f7db669 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1705,21 +1705,23 @@ static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
static u32 mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto)
{
+ u32 modes = 0;
+
if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 |
MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 |
MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
MLXSW_REG_PTYS_ETH_SPEED_SGMII))
- return SUPPORTED_FIBRE;
+ modes |= SUPPORTED_FIBRE;
if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 |
MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 |
MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 |
MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX))
- return SUPPORTED_Backplane;
- return 0;
+ modes |= SUPPORTED_Backplane;
+ return modes;
}
static u32 mlxsw_sp_from_ptys_supported_link(u32 ptys_eth_proto)
--
2.5.5
^ permalink raw reply related
* [patch net-next 3/5] mlxsw: spectrum: Report port type according to operational speed
From: Jiri Pirko @ 2016-09-12 11:26 UTC (permalink / raw)
To: netdev; +Cc: davem, idosch, eladr, yotamg, nogahf, ogerlitz
In-Reply-To: <1473679587-9112-1-git-send-email-jiri@resnulli.us>
From: Ido Schimmel <idosch@mellanox.com>
In case port isn't operational we shouldn't report the port type, but
instead return PORT_OTHER. This is consistent with most other drivers
that return PORT_OTHER when media type can't be determined.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index e035a9d..49b8d69 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1827,7 +1827,6 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev,
mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev),
eth_proto_oper, cmd);
- eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
cmd->port = mlxsw_sp_port_connector_port(eth_proto_oper);
if (autoneg_status == MLXSW_REG_PTYS_AN_STATUS_OK && eth_proto_lp)
--
2.5.5
^ permalink raw reply related
* [patch net-next 2/5] mlxsw: spectrum: Report link partner's advertised speeds
From: Jiri Pirko @ 2016-09-12 11:26 UTC (permalink / raw)
To: netdev; +Cc: davem, idosch, eladr, yotamg, nogahf, ogerlitz
In-Reply-To: <1473679587-9112-1-git-send-email-jiri@resnulli.us>
From: Ido Schimmel <idosch@mellanox.com>
If autonegotiation was performed successfully, then we should report the
link partner's advertised speeds instead of the operational speed of the
port.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 19 +++++++++++++++++++
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 9 ++++++++-
2 files changed, 27 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index b83d0a7..43ce27f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2138,6 +2138,18 @@ MLXSW_ITEM32(reg, ptys, local_port, 0x00, 16, 8);
*/
MLXSW_ITEM32(reg, ptys, proto_mask, 0x00, 0, 3);
+enum {
+ MLXSW_REG_PTYS_AN_STATUS_NA,
+ MLXSW_REG_PTYS_AN_STATUS_OK,
+ MLXSW_REG_PTYS_AN_STATUS_FAIL,
+};
+
+/* reg_ptys_an_status
+ * Autonegotiation status.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4);
+
#define MLXSW_REG_PTYS_ETH_SPEED_SGMII BIT(0)
#define MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX BIT(1)
#define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 BIT(2)
@@ -2184,6 +2196,13 @@ MLXSW_ITEM32(reg, ptys, eth_proto_admin, 0x18, 0, 32);
*/
MLXSW_ITEM32(reg, ptys, eth_proto_oper, 0x24, 0, 32);
+/* reg_ptys_eth_proto_lp_advertise
+ * The protocols that were advertised by the link partner during
+ * autonegotiation.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, eth_proto_lp_advertise, 0x30, 0, 32);
+
static inline void mlxsw_reg_ptys_pack(char *payload, u8 local_port,
u32 proto_admin)
{
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9de2383..e035a9d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1799,6 +1799,8 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev,
u32 eth_proto_cap;
u32 eth_proto_admin;
u32 eth_proto_oper;
+ u8 autoneg_status;
+ u32 eth_proto_lp;
int err;
mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
@@ -1809,6 +1811,8 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev,
}
mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap,
ð_proto_admin, ð_proto_oper);
+ eth_proto_lp = mlxsw_reg_ptys_eth_proto_lp_advertise_get(ptys_pl);
+ autoneg_status = mlxsw_reg_ptys_an_status_get(ptys_pl);
cmd->supported = mlxsw_sp_from_ptys_supported_port(eth_proto_cap) |
mlxsw_sp_from_ptys_supported_link(eth_proto_cap) |
@@ -1825,7 +1829,10 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev,
eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
cmd->port = mlxsw_sp_port_connector_port(eth_proto_oper);
- cmd->lp_advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_oper);
+
+ if (autoneg_status == MLXSW_REG_PTYS_AN_STATUS_OK && eth_proto_lp)
+ cmd->lp_advertising =
+ mlxsw_sp_from_ptys_advert_link(eth_proto_lp);
cmd->transceiver = XCVR_INTERNAL;
return 0;
--
2.5.5
^ permalink raw reply related
* [patch net-next 1/5] mlxsw: spectrum: Correctly report autonegotiation
From: Jiri Pirko @ 2016-09-12 11:26 UTC (permalink / raw)
To: netdev; +Cc: davem, idosch, eladr, yotamg, nogahf, ogerlitz
In-Reply-To: <1473679587-9112-1-git-send-email-jiri@resnulli.us>
From: Ido Schimmel <idosch@mellanox.com>
Up until now the device always reported autonegotiation to be off
although it was on by default.
Allow the user to disable / enable autonegotiation and report its status
correctly.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 14 ++++++++++++--
drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 3 ++-
2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 6c6b726..9de2383 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1814,7 +1814,12 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev,
mlxsw_sp_from_ptys_supported_link(eth_proto_cap) |
SUPPORTED_Pause | SUPPORTED_Asym_Pause |
SUPPORTED_Autoneg;
- cmd->advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_admin);
+ if (mlxsw_sp_port->link.autoneg) {
+ cmd->advertising =
+ mlxsw_sp_from_ptys_advert_link(eth_proto_admin);
+ cmd->advertising |= ADVERTISED_Autoneg;
+ cmd->autoneg = AUTONEG_ENABLE;
+ }
mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev),
eth_proto_oper, cmd);
@@ -1872,11 +1877,13 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev,
u32 eth_proto_new;
u32 eth_proto_cap;
u32 eth_proto_admin;
+ bool autoneg;
int err;
+ autoneg = cmd->autoneg == AUTONEG_ENABLE;
speed = ethtool_cmd_speed(cmd);
- eth_proto_new = cmd->autoneg == AUTONEG_ENABLE ?
+ eth_proto_new = autoneg ?
mlxsw_sp_to_ptys_advert_link(cmd->advertising) :
mlxsw_sp_to_ptys_speed(speed);
@@ -1906,6 +1913,8 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev,
if (!netif_running(dev))
return 0;
+ mlxsw_sp_port->link.autoneg = autoneg;
+
err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
if (err) {
netdev_err(dev, "Failed to set admin status");
@@ -2081,6 +2090,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
mlxsw_sp_port->mapping.module = module;
mlxsw_sp_port->mapping.width = width;
mlxsw_sp_port->mapping.lane = lane;
+ mlxsw_sp_port->link.autoneg = 1;
bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE);
mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL);
if (!mlxsw_sp_port->active_vlans) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 01537d3..ae04613 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -341,7 +341,8 @@ struct mlxsw_sp_port {
} vport;
struct {
u8 tx_pause:1,
- rx_pause:1;
+ rx_pause:1,
+ autoneg:1;
} link;
struct {
struct ieee_ets *ets;
--
2.5.5
^ permalink raw reply related
* [patch net-next 0/5] mlxsw: ethtool enhancements
From: Jiri Pirko @ 2016-09-12 11:26 UTC (permalink / raw)
To: netdev; +Cc: davem, idosch, eladr, yotamg, nogahf, ogerlitz
From: Jiri Pirko <jiri@mellanox.com>
Ido says:
Patches 1-4 do some minor cleanup in current ethtool ops. Patch 5
replace legacy {get,set}_settings callbacks with
{get,set}_link_ksettings.
Ido Schimmel (5):
mlxsw: spectrum: Correctly report autonegotiation
mlxsw: spectrum: Report link partner's advertised speeds
mlxsw: spectrum: Report port type according to operational speed
mlxsw: spectrum: Indicate support of multiple port types
mlxsw: spectrum: Add support for new ethtool API
drivers/net/ethernet/mellanox/mlxsw/reg.h | 20 ++
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 332 ++++++++++++++-----------
drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 3 +-
3 files changed, 209 insertions(+), 146 deletions(-)
--
2.5.5
^ permalink raw reply
* Re: [PATCH 08/26] iwlegacy: constify local structures
From: Stanislaw Gruszka @ 2016-09-12 11:24 UTC (permalink / raw)
To: Julia Lawall
Cc: joe, kernel-janitors, Kalle Valo, linux-wireless, netdev,
linux-kernel
In-Reply-To: <1473599168-30561-9-git-send-email-Julia.Lawall@lip6.fr>
On Sun, Sep 11, 2016 at 03:05:50PM +0200, Julia Lawall wrote:
> For structure types defined in the same file or local header files, find
> top-level static structure declarations that have the following
> properties:
> 1. Never reassigned.
> 2. Address never taken
> 3. Not passed to a top-level macro call
> 4. No pointer or array-typed field passed to a function or stored in a
> variable.
> Declare structures having all of these properties as const.
>
> Done using Coccinelle.
> Based on a suggestion by Joe Perches <joe@perches.com>.
>
> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Acked-by: Stanislaw Gruszka <sgruszka@redhat.com>
^ permalink raw reply
* Re: [PATCH net 0/2] ip: fix creation flags reported in RTM_NEWROUTE events
From: Guillaume Nault @ 2016-09-12 10:29 UTC (permalink / raw)
To: David Miller; +Cc: netdev, roopa, milon, mkubecek, nicolas.dichtel
In-Reply-To: <20160909.165126.2106988715172525727.davem@davemloft.net>
On Fri, Sep 09, 2016 at 04:51:26PM -0700, David Miller wrote:
> From: Guillaume Nault <g.nault@alphalink.fr>
> Date: Wed, 7 Sep 2016 17:18:50 +0200
>
> > Netlink messages sent to user-space upon RTM_NEWROUTE events have their
> > nlmsg_flags field inconsistently set. While the NLM_F_REPLACE and
> > NLM_F_APPEND bits are correctly handled, NLM_F_CREATE and NLM_F_EXCL
> > are always 0.
> >
> > This series sets the NLM_F_CREATE and NLM_F_EXCL bits when applicable,
> > for IPv4 and IPv6.
> >
> > Since IPv6 ignores the NLM_F_APPEND flags in requests, this flag isn't
> > reported in RTM_NEWROUTE IPv6 events. This keeps IPv6 internal
> > consistency (same flag semantic for user requests and kernel events) at
> > the cost of bringing different flag interpretation for IPv4 and IPv6.
>
> I'm applying this series to net-next so that it has time to cook and
> expose anything in userland that might break due to these changes.
>
> I briefly considered applying this to net but I think that is
> premature at least for the time being.
>
Makes sense, and this could be considered a feature enhancement after
all.
Thanks David.
^ permalink raw reply
* [PATCH v2 net 1/1] net sched actions: fix GETing actions
From: Jamal Hadi Salim @ 2016-09-12 10:21 UTC (permalink / raw)
To: davem; +Cc: xiyou.wangcong, netdev, Jamal Hadi Salim
From: Jamal Hadi Salim <jhs@mojatatu.com>
With the batch changes that translated transient actions into
a temporary list we lost in the translation the fact that
tcf_action_destroy() will eventually delete the action from
the permanent location if the refcount is zero.
Example of what broke:
...add a gact action to drop
sudo $TC actions add action drop index 10
...now retrieve it, looks good
sudo $TC actions get action gact index 10
...retrieve it again and find it is gone!
sudo $TC actions get action gact index 10
Fixes:
22dc13c837c3 ("net_sched: convert tcf_exts from list to pointer array"),
824a7e8863b3 ("net_sched: remove an unnecessary list_del()")
f07fed82ad79 ("net_sched: remove the leftover cleanup_a()")
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
net/sched/act_api.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index d09d068..63b8167 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -592,6 +592,16 @@ err_out:
return ERR_PTR(err);
}
+static void cleanup_a(struct list_head *actions, int ovr)
+{
+ struct tc_action *a, *tmp;
+
+ list_for_each_entry_safe(a, tmp, actions, list) {
+ if (ovr)
+ a->tcfa_refcnt-=1;
+ }
+}
+
int tcf_action_init(struct net *net, struct nlattr *nla,
struct nlattr *est, char *name, int ovr,
int bind, struct list_head *actions)
@@ -612,8 +622,15 @@ int tcf_action_init(struct net *net, struct nlattr *nla,
goto err;
}
act->order = i;
+ if (ovr)
+ act->tcfa_refcnt+=1;
list_add_tail(&act->list, actions);
}
+
+ /* Remove the temp refcnt which was necessary to protect against
+ * destroying an existing action which was being replaced
+ */
+ cleanup_a(actions, ovr);
return 0;
err:
@@ -883,6 +900,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
goto err;
}
act->order = i;
+ if (event == RTM_GETACTION)
+ act->tcfa_refcnt+=1;
list_add_tail(&act->list, &actions);
}
--
1.9.1
^ permalink raw reply related
* Re: README: [PATCH RFC 11/11] net/mlx5e: XDP TX xmit more
From: Jesper Dangaard Brouer via iovisor-dev @ 2016-09-12 10:15 UTC (permalink / raw)
To: Saeed Mahameed
Cc: Tom Herbert, iovisor-dev, Jamal Hadi Salim, Saeed Mahameed,
Eric Dumazet, Linux Netdev List
In-Reply-To: <CALzJLG_r0pDJgxqqak5=NatT8tF7UP2NkGS1wjeWcS5C=Zvv2A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Fri, 9 Sep 2016 18:03:09 +0300
Saeed Mahameed <saeedm-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org> wrote:
> On Fri, Sep 9, 2016 at 6:22 AM, Alexei Starovoitov via iovisor-dev
> <iovisor-dev-9jONkmmOlFHEE9lA1F8Ukti2O/JbrIOy@public.gmane.org> wrote:
> > On Thu, Sep 08, 2016 at 10:11:47AM +0200, Jesper Dangaard Brouer wrote:
> >>
> >> I'm sorry but I have a problem with this patch!
> >> Looking at this patch, I want to bring up a fundamental architectural
> >> concern with the development direction of XDP transmit.
> >>
> >>
> >> What you are trying to implement, with delaying the doorbell, is
> >> basically TX bulking for TX_XDP.
> >>
> >> Why not implement a TX bulking interface directly instead?!?
> >>
> >> Yes, the tailptr/doorbell is the most costly operation, but why not
> >> also take advantage of the benefits of bulking for other parts of the
> >> code? (benefit is smaller, by every cycles counts in this area)
> >>
> >> This hole XDP exercise is about avoiding having a transaction cost per
> >> packet, that reads "bulking" or "bundling" of packets, where possible.
> >>
> >> Lets do bundling/bulking from the start!
>
> Jesper, what we did here is also bulking, instead of bulking in a
> temporary list in the driver we list the packets in the HW and once
> done we transmit all at once via the xdp_doorbell indication.
>
> I agree with you that we can take advantage and improve the icache by
> bulking first in software and then queue all at once in the hw then
> ring one doorbell.
>
> but I also agree with Alexei that this will introduce an extra
> pointer/list handling in the driver and we need to do the comparison
> between both approaches before we decide which is better.
I welcome implementing both approaches and benchmarking them against
each-other, I'll gladly dedicate time for this!
I'm reacting so loudly, because this is a mental model switch, that
need to be applied to the full drivers RX path. Also for normal stack
delivery of SKBs. As both Edward Cree[1] and I[2] have demonstrated,
there is between 10%-25% perf gain here.
The key point is stop seeing the lowest driver RX as something that
works on a per packet basis. It might be easier to view this as a kind
of vector processing. This is about having a vector of packets, where
we apply some action/operation.
This is about using the CPU more efficiently, getting it to do more
instructions per cycle. The next level of optimization (for >= Sandy
Bridge CPUs) is to make these vector processing stages small enough to fit
into the CPUs decoded-I-cache section.
It might also be important to mention, that for netstack delivery, I
don't imagine bulking 64 packets. Instead, I imagine doing 8-16
packets. Why, because the NIC-HW runs independently and have the
opportunity to deliver more frames in the RX ring queue, while the
stack "slow" processed packets. You can view this as "bulking" from
the RX ring queue, with a "look-back" before exiting the NAPI poll loop.
> this must be marked as future work and not have this from the start.
We both know that statement is BS, and the other approach will never be
implemented once this patch is accepted upstream.
> > mlx4 already does bulking and this proposed mlx5 set of patches
> > does bulking as well.
I'm reacting exactly because mlx4 is also doing "bulking" in the wrong
way IMHO. And now mlx5 is building on the same principle. That is why
I'm yelling STOP.
> >> The reason behind the xmit_more API is that we could not change the
> >> API of all the drivers. And we found that calling an explicit NDO
> >> flush came at a cost (only approx 7 ns IIRC), but it still a cost that
> >> would hit the common single packet use-case.
> >>
> >> It should be really easy to build a bundle of packets that need XDP_TX
> >> action, especially given you only have a single destination "port".
> >> And then you XDP_TX send this bundle before mlx5_cqwq_update_db_record.
[1] http://lists.openwall.net/netdev/2016/04/19/89
[2] http://lists.openwall.net/netdev/2016/01/15/51
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* [PATCH] net: dsa: add FIB support
From: John Crispin @ 2016-09-12 10:13 UTC (permalink / raw)
To: David S. Miller, Andrew Lunn, Florian Fainelli
Cc: netdev, linux-kernel, John Crispin
Add SWITCHDEV_OBJ_ID_IPV4_FIB support to the DSA layer.
Signed-off-by: John Crispin <john@phrozen.org>
---
Documentation/networking/dsa/dsa.txt | 18 +++++++++++++++
include/net/dsa.h | 13 +++++++++++
net/dsa/slave.c | 41 ++++++++++++++++++++++++++++++++++
3 files changed, 72 insertions(+)
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt
index 6d6c07c..6cd5831 100644
--- a/Documentation/networking/dsa/dsa.txt
+++ b/Documentation/networking/dsa/dsa.txt
@@ -607,6 +607,24 @@ of DSA, would be the its port-based VLAN, used by the associated bridge device.
function that the driver has to call for each MAC address known to be behind
the given port. A switchdev object is used to carry the VID and MDB info.
+Route offloading
+----------------
+
+- ipv4_fib_prepare: routing layer function invoked to prepare the installation
+ of an ipv4 route into the switches routing database. If the operation is not
+ supported this function should return -EOPNOTSUPP. No hardware setup must be
+ done in this function. See ipv4_fib_add for this and details.
+
+- ipv4_fib_add: routing layer function invoked when a new ipv4 route should be
+ installed into the routing database of the switch, it should be programmed
+ with the route for the specified VLAN ID of the device that the route applies
+ to.
+
+- ipv4_fib_del: routing layer function invoked when an ipv4 route should be
+ removed from the routing database, the switch hardware should be programmed
+ to delete the specified MAC address of the nexthop from the specified VLAN ID
+ if it was mapped into the forwarding database.
+
TODO
====
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 7556646..7fdd63e 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -237,6 +237,7 @@ struct switchdev_obj;
struct switchdev_obj_port_fdb;
struct switchdev_obj_port_mdb;
struct switchdev_obj_port_vlan;
+struct switchdev_obj_ipv4_fib;
struct dsa_switch_ops {
struct list_head list;
@@ -386,6 +387,18 @@ struct dsa_switch_ops {
int (*port_mdb_dump)(struct dsa_switch *ds, int port,
struct switchdev_obj_port_mdb *mdb,
int (*cb)(struct switchdev_obj *obj));
+
+ /*
+ * IPV4 routing
+ */
+ int (*ipv4_fib_prepare)(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_ipv4_fib *fib4,
+ struct switchdev_trans *trans);
+ int (*ipv4_fib_add)(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_ipv4_fib *fib4,
+ struct switchdev_trans *trans);
+ int (*ipv4_fib_del)(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_ipv4_fib *fib4);
};
void register_switch_driver(struct dsa_switch_ops *type);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 9ecbe78..9e6ceb2 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -334,6 +334,38 @@ static int dsa_slave_port_mdb_dump(struct net_device *dev,
return -EOPNOTSUPP;
}
+static int dsa_slave_ipv4_fib_add(struct net_device *dev,
+ const struct switchdev_obj_ipv4_fib *fib4,
+ struct switchdev_trans *trans)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_switch *ds = p->parent;
+ int ret;
+
+ if (!ds->drv->ipv4_fib_prepare || !ds->drv->ipv4_fib_add)
+ return -EOPNOTSUPP;
+
+ if (switchdev_trans_ph_prepare(trans))
+ ret = ds->drv->ipv4_fib_prepare(ds, p->port, fib4, trans);
+ else
+ ret = ds->drv->ipv4_fib_add(ds, p->port, fib4, trans);
+
+ return ret;
+}
+
+static int dsa_slave_ipv4_fib_del(struct net_device *dev,
+ const struct switchdev_obj_ipv4_fib *fib4)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_switch *ds = p->parent;
+ int ret = -EOPNOTSUPP;
+
+ if (ds->drv->ipv4_fib_del)
+ ret = ds->drv->ipv4_fib_del(ds, p->port, fib4);
+
+ return ret;
+}
+
static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
struct dsa_slave_priv *p = netdev_priv(dev);
@@ -465,6 +497,11 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
SWITCHDEV_OBJ_PORT_VLAN(obj),
trans);
break;
+ case SWITCHDEV_OBJ_ID_IPV4_FIB:
+ err = dsa_slave_ipv4_fib_add(dev,
+ SWITCHDEV_OBJ_IPV4_FIB(obj),
+ trans);
+ break;
default:
err = -EOPNOTSUPP;
break;
@@ -490,6 +527,10 @@ static int dsa_slave_port_obj_del(struct net_device *dev,
err = dsa_slave_port_vlan_del(dev,
SWITCHDEV_OBJ_PORT_VLAN(obj));
break;
+ case SWITCHDEV_OBJ_ID_IPV4_FIB:
+ err = dsa_slave_ipv4_fib_del(dev,
+ SWITCHDEV_OBJ_IPV4_FIB(obj));
+ break;
default:
err = -EOPNOTSUPP;
break;
--
1.7.10.4
^ permalink raw reply related
* Re: [PATCH 23/26] sh_eth: constify local structures
From: Julia Lawall @ 2016-09-12 9:43 UTC (permalink / raw)
To: Sergei Shtylyov
Cc: joe, kernel-janitors, netdev, linux-renesas-soc, linux-kernel
In-Reply-To: <cb443416-4fb9-5593-2529-66211299c9a8@cogentembedded.com>
On Sun, 11 Sep 2016, Sergei Shtylyov wrote:
> On 09/11/2016 04:06 PM, Julia Lawall wrote:
> > For structure types defined in the same file or local header files, find
> > top-level static structure declarations that have the following
> > properties:
> > 1. Never reassigned.
>
> Really?
>
> > 2. Address never taken
>
> Really?
OK, I see the problem. The code has, eg:
{ "sh7724-ether", (kernel_ulong_t)&sh7724_data }
Coccinelle doesn't know anything about kernel_ulong_t, so it assumes that
it is an identifier, and that the whole expression is a bit and, rather
than an address computation. And at the same time, the cast causes the
compiler to discard the const annotation, so it doesn't complain either.
I can update the rule to avoid this case, since taking a bit and on the
address of a top-level structure is not likely to be useful, and I will
check whether any of the other patches are affected by this issue.
Thanks for the report.
julia
>
> > 3. Not passed to a top-level macro call
> > 4. No pointer or array-typed field passed to a function or stored in a
> > variable.
> > Declare structures having all of these properties as const.
> >
> > Done using Coccinelle.
> > Based on a suggestion by Joe Perches <joe@perches.com>.
> >
> > Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
>
> NAK, see sh_eth_set_default_cpu_data().
>
> MBR, Sergei
>
> --
> To unsubscribe from this list: send the line "unsubscribe kernel-janitors" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply
* [PATCH] atm: iphase: fix newline escape and minor tweak to source formatting
From: Colin King @ 2016-09-12 9:29 UTC (permalink / raw)
To: Chas Williams, linux-atm-general, netdev; +Cc: linux-kernel
From: Colin Ian King <colin.king@canonical.com>
The newline escape is incorrect and needs fixing. Also adjust source
formatting / indentation and remove trailing white space.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
---
drivers/atm/iphase.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 9d8807e..256b191 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -1885,9 +1885,8 @@ static int open_tx(struct atm_vcc *vcc)
if ((ret = ia_cbr_setup (iadev, vcc)) < 0) {
return ret;
}
- }
- else
- printk("iadev: Non UBR, ABR and CBR traffic not supportedn");
+ } else
+ printk("iadev: Non UBR, ABR and CBR traffic not supported\n");
iadev->testTable[vcc->vci]->vc_status |= VC_ACTIVE;
IF_EVENT(printk("ia open_tx returning \n");)
--
2.9.3
^ 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