On Sat, 2011-11-19 at 11:20 +0200, Philip Paeps wrote:
> On 18 Nov 2011, at 23:34, Ben Hutchings wrote:
> > sfxge: Remove interrupt self-test code
> >
> > It's not currently used; it didn't build on 32-bit and the previous
> > build fix is incorrect. If we
On Sat, 2011-11-19 at 00:35 +0100, Marius Strobl wrote:
> On Fri, Nov 18, 2011 at 09:34:11PM +0000, Ben Hutchings wrote:
> > sfxge: Remove interrupt self-test code
> >
> > It's not currently used; it didn't build on 32-bit and the previous
> > build fix is in
STING;
+ intr->state = SFXGE_INTR_STARTED;
/* Enable interrupts at the NIC */
efx_intr_enable(sc->enp);
- intr->state = SFXGE_INTR_STARTED;
-
return (0);
fail:
--
Ben Hutchings, Staff Engineer, Solarflare
No
EFX_LINK_DOWN ?
LINK_STATE_UP : LINK_STATE_DOWN);
- sc->ifnet->if_baudrate = sfxge_link_speed_kbit[port->link_mode];
+ sc->ifnet->if_baudrate = sfxge_link_baudrate[port->link_mode];
if_link_state_change(sc->ifnet, link_state);
}
--
Ben Hutchings, Staff Engine
On Fri, 2011-11-18 at 01:38 +, Ben Hutchings wrote:
> On Thu, 2011-11-17 at 14:01 -0800, YongHyeon PYUN wrote:
> > On Thu, Nov 17, 2011 at 01:39:24PM -0800, Juli Mallett wrote:
> > > On Thu, Nov 17, 2011 at 13:12, Maksim Yevmenkin
> > > wrote:
> > > >
this.
> ifp->if_baudrate = IF_Gbps(10UL);
>
> I think the driver should update if_baudrate depending on
> resolved speed(lost link, resolved speed etc).
> And if we really care about overflowing if_baudrate on 32bit
> machines, the IF_Gbps macro could be conditionally defined.
I
On Tue, 2011-10-18 at 00:28 +0100, Ben Hutchings wrote:
> On Mon, 2011-10-17 at 18:09 +0200, Andre Oppermann wrote:
> > On 17.10.2011 17:29, Ben Hutchings wrote:
> > > This is the fix/workaround I used:
> >
> > Thanks for the fix. I'll review it and put it i
On Mon, 2011-10-17 at 23:59 +, Bjoern A. Zeeb wrote:
> On 17. Oct 2011, at 23:28 , Ben Hutchings wrote:
>
> > On Mon, 2011-10-17 at 18:09 +0200, Andre Oppermann wrote:
> >> On 17.10.2011 17:29, Ben Hutchings wrote:
> >>> This is the fix/workaround I used:
>
On Mon, 2011-10-17 at 18:09 +0200, Andre Oppermann wrote:
> On 17.10.2011 17:29, Ben Hutchings wrote:
> > This is the fix/workaround I used:
>
> Thanks for the fix. I'll review it and put it into FreeBSD maybe in
> a slightly different form.
Which one? One is tested b
ries options
+* and thus we normally have somewhat less data in segments.
+ */
+ tp->t_maxopd = mss + ts_len;
}
void
--- END ---
Ben.
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketi
BYTES)
mss &= ~(MCLBYTES-1);
#else
if (mss > MCLBYTES)
mss = mss / MCLBYTES * MCLBYTES;
#endif
tp->t_maxseg = mss;
(All the above code is from 9, but I found the assertion failure on 8.2
which has fairly similar code.)
Ben.
--
Ben Hut
On Sun, 2011-09-25 at 21:31 -0400, Arnaud Lacombe wrote:
> Hi,
>
> On Sun, Sep 25, 2011 at 8:03 PM, Ben Hutchings
> wrote:
> > On Sat, 2011-09-24 at 13:56 -0700, Juli Mallett wrote:
> >> On Sat, Sep 24, 2011 at 13:52, Luigi Rizzo wrote:
> >> > apart fr
o improving throughput. (The latency should
be pretty good if you turn off interrupt moderation, though.) And
really I think Onload is more useful than netmap, since it's compatible
with existing source and binaries.
Ben.
--
Ben Hutchings, Staff Engi
On Fri, 2011-09-09 at 13:18 +0900, Takuya ASADA wrote:
> On Sep 9, 2011, at 9:44 AM, Ben Hutchings wrote:
>
> > But it would be a lot nicer if this could be done automatically. Which
> > I believe it can - see the RFS and XPS features in Linux.
>
> Does it coopera
On Thu, 2011-09-08 at 20:13 -0400, George Neville-Neil wrote:
> On Sep 8, 2011, at 14:49 , Navdeep Parhar wrote:
>
> > On Thu, Sep 08, 2011 at 08:34:11AM -0400, John Baldwin wrote:
> >> On Monday, September 05, 2011 7:21:12 am Ben Hutchings wrote:
> >>> On Mon,
"right" one?
RX NFC is the right one. The other one (RX n-tuple) will be removed
once I've converted the sfc driver to use RX NFC.
It isn't flexible enough to cover the full matching capabilities and it
doesn't allow for requesting steering + hashing, although I'm hop
On Thu, 2011-09-08 at 11:06 -0400, John Baldwin wrote:
> On Thursday, September 08, 2011 10:48:25 am K. Macy wrote:
> > On Thu, Sep 8, 2011 at 2:34 PM, John Baldwin wrote:
> > > On Monday, September 05, 2011 7:21:12 am Ben Hutchings wrote:
> > >> On Mon, 2011-09-0
On Thu, 2011-09-08 at 10:55 +0200, Vlad Galu wrote:
> On Sep 8, 2011, at 10:11 AM, Takuya ASADA wrote:
> > Hi,
> >
> > 2011/9/5 Ben Hutchings :
> >> On Mon, 2011-09-05 at 15:51 +0900, Takuya ASADA wrote:
> >>> Hi,
> >>>
> >>>
On Thu, 2011-09-08 at 08:34 -0400, John Baldwin wrote:
> On Monday, September 05, 2011 7:21:12 am Ben Hutchings wrote:
> > On Mon, 2011-09-05 at 15:51 +0900, Takuya ASADA wrote:
> > > Hi,
> > >
> > > I implemented Ethernet Flow Director sysctls to ixgbe(4), he
tter for FreeBSD
to support something like that?
Ben.
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
__
> incorrect csums but the kernel covers up for it.
[...]
That's right. Linux doesn't entirely trust hardware checksum
validation, so drivers can't report that the checksum was definitely
bad. You should be able to get this behaviour on FreeBSD by not setting
any checksum flag
ocally assigned). I don't know
whether FreeBSD has a function for this, but Linux has one which just
gets 6 random bytes and then changes the first byte to conform to this.
There are a small number of old OUIs which should be avoided; see
<http://thread.gmane.org/gmane.linux.network/195545&g
"up" driver works as expected.
It's common behaviour that the physical link status is not (easily)
available while the interface is down. In Linux we resolved that when
an interface is down its link state is always reported as down (where we
have to give a boolean answer).
Ben.
e RAM, a DMA write of 64 bytes with 8-byte alignment
covers exactly 8 memory words. However a DMA write of 63 bytes with
8-byte alignment at the start covers 7 full and one partial memory word.
So a read-modify-write operation is required for the last word.
Ben.
--
Ben Hutchings, Senior Soft
d some other PHYs), the phy_id for
SIOC{G,S}MIIREG (but not SIOCGMIIPHY) provides both PRT and DEV
addresses, as specified in .
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing departmen
25 matches
Mail list logo
