From: Jason Xing <[email protected]>
I encountered one case where I cannot increase the MTU size with XDP
enabled if the server is equipped with IXGBE card, which happened on
thousands of servers. I noticed it was prohibited from 2017[1] and
added size checks[2] if allowed soon after the previous patch.
Interesting part goes like this:
1) Changing MTU directly from 1500 (default value) to 2000 doesn't
work because the driver finds out that 'new_frame_size >
ixgbe_rx_bufsz(ring)' in ixgbe_change_mtu() function.
2) However, if we change MTU to 1501 then change from 1501 to 2000, it
does work, because the driver sets __IXGBE_RX_3K_BUFFER when MTU size
is converted to 1501, which later size check policy allows.
The default MTU value for most servers is 1500 which cannot be adjusted
directly to the value larger than IXGBE_MAX_2K_FRAME_BUILD_SKB (1534 or
1536) if it loads XDP.
After I do a quick study on the manner of i40E driver allowing two kinds
of buffer size (one is 2048 while another is 3072) to support XDP mode in
i40e_max_xdp_frame_size(), I believe the default MTU size is possibly not
satisfied in XDP mode when IXGBE driver is in use, we sometimes need to
insert a new header, say, vxlan header. So setting the 3K-buffer flag
could solve the issue.
[1] commit 38b7e7f8ae82 ("ixgbe: Do not allow LRO or MTU change with XDP")
[2] commit fabf1bce103a ("ixgbe: Prevent unsupported configurations with
XDP")
Signed-off-by: Jason Xing <[email protected]>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ab8370c413f3..dc016582f91e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4313,6 +4313,9 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
(max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
+
+ if (ixgbe_enabled_xdp_adapter(adapter))
+ set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
#endif
}
}
--
2.37.3
Dear Jason,
Thank you for your patch.
Am 21.01.23 um 09:55 schrieb Jason Xing:
> From: Jason Xing <[email protected]>
There is a small typo in the summary: ena*bl*ed
> I encountered one case where I cannot increase the MTU size with XDP
> enabled if the server is equipped with IXGBE card, which happened on
> thousands of servers. I noticed it was prohibited from 2017[1] and
That’s included since Linux 4.19-rc1.
> added size checks[2] if allowed soon after the previous patch.
>
> Interesting part goes like this:
> 1) Changing MTU directly from 1500 (default value) to 2000 doesn't
> work because the driver finds out that 'new_frame_size >
> ixgbe_rx_bufsz(ring)' in ixgbe_change_mtu() function.
> 2) However, if we change MTU to 1501 then change from 1501 to 2000, it
> does work, because the driver sets __IXGBE_RX_3K_BUFFER when MTU size
> is converted to 1501, which later size check policy allows.
>
> The default MTU value for most servers is 1500 which cannot be adjusted
> directly to the value larger than IXGBE_MAX_2K_FRAME_BUILD_SKB (1534 or
> 1536) if it loads XDP.
>
> After I do a quick study on the manner of i40E driver allowing two kinds
> of buffer size (one is 2048 while another is 3072) to support XDP mode in
> i40e_max_xdp_frame_size(), I believe the default MTU size is possibly not
> satisfied in XDP mode when IXGBE driver is in use, we sometimes need to
> insert a new header, say, vxlan header. So setting the 3K-buffer flag
> could solve the issue.
What card did you test with exactly?
> [1] commit 38b7e7f8ae82 ("ixgbe: Do not allow LRO or MTU change with XDP")
> [2] commit fabf1bce103a ("ixgbe: Prevent unsupported configurations with
> XDP")
I’d say to not break the line in references.
> Signed-off-by: Jason Xing <[email protected]>
> ---
> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> index ab8370c413f3..dc016582f91e 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> @@ -4313,6 +4313,9 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
> if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
> (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
> set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> +
> + if (ixgbe_enabled_xdp_adapter(adapter))
> + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> #endif
> }
> }
Kind regards,
Paul
On Mon, Jan 23, 2023 at 4:21 AM Paul Menzel <[email protected]> wrote:
>
> Dear Jason,
>
>
> Thank you for your patch.
Hello Paul,
Thanks for the review.
>
> Am 21.01.23 um 09:55 schrieb Jason Xing:
> > From: Jason Xing <[email protected]>
>
> There is a small typo in the summary: ena*bl*ed
>
Sure it is. That's my fault.
> > I encountered one case where I cannot increase the MTU size with XDP
> > enabled if the server is equipped with IXGBE card, which happened on
> > thousands of servers. I noticed it was prohibited from 2017[1] and
>
> That’s included since Linux 4.19-rc1.
>
> > added size checks[2] if allowed soon after the previous patch.
> >
> > Interesting part goes like this:
> > 1) Changing MTU directly from 1500 (default value) to 2000 doesn't
> > work because the driver finds out that 'new_frame_size >
> > ixgbe_rx_bufsz(ring)' in ixgbe_change_mtu() function.
> > 2) However, if we change MTU to 1501 then change from 1501 to 2000, it
> > does work, because the driver sets __IXGBE_RX_3K_BUFFER when MTU size
> > is converted to 1501, which later size check policy allows.
> >
> > The default MTU value for most servers is 1500 which cannot be adjusted
> > directly to the value larger than IXGBE_MAX_2K_FRAME_BUILD_SKB (1534 or
> > 1536) if it loads XDP.
> >
> > After I do a quick study on the manner of i40E driver allowing two kinds
> > of buffer size (one is 2048 while another is 3072) to support XDP mode in
> > i40e_max_xdp_frame_size(), I believe the default MTU size is possibly not
> > satisfied in XDP mode when IXGBE driver is in use, we sometimes need to
> > insert a new header, say, vxlan header. So setting the 3K-buffer flag
> > could solve the issue.
>
> What card did you test with exactly?
>
It is the IXGBE driver that has such an issue. The I40E driver I
mentioned here is only for contrast. It's not that proper from my
point of view if the IXGBE driver cannot directly adjust to 2000. Thus
I would like more reviews and suggestions.
Thanks,
Jason
> > [1] commit 38b7e7f8ae82 ("ixgbe: Do not allow LRO or MTU change with XDP")
> > [2] commit fabf1bce103a ("ixgbe: Prevent unsupported configurations with
> > XDP")
>
> I’d say to not break the line in references.
>
> > Signed-off-by: Jason Xing <[email protected]>
> > ---
> > drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
> > 1 file changed, 3 insertions(+)
> >
> > diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> > index ab8370c413f3..dc016582f91e 100644
> > --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> > +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> > @@ -4313,6 +4313,9 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
> > if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
> > (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
> > set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> > +
> > + if (ixgbe_enabled_xdp_adapter(adapter))
> > + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> > #endif
> > }
> > }
>
>
> Kind regards,
>
> Paul
I'm sorry. I just noticed that I sent it to the wrong email address of
john.fastabend previously. So I corrected it here.
Thanks,
Jason
On Sat, Jan 21, 2023 at 4:55 PM Jason Xing <[email protected]> wrote:
>
> From: Jason Xing <[email protected]>
>
> I encountered one case where I cannot increase the MTU size with XDP
> enabled if the server is equipped with IXGBE card, which happened on
> thousands of servers. I noticed it was prohibited from 2017[1] and
> added size checks[2] if allowed soon after the previous patch.
>
> Interesting part goes like this:
> 1) Changing MTU directly from 1500 (default value) to 2000 doesn't
> work because the driver finds out that 'new_frame_size >
> ixgbe_rx_bufsz(ring)' in ixgbe_change_mtu() function.
> 2) However, if we change MTU to 1501 then change from 1501 to 2000, it
> does work, because the driver sets __IXGBE_RX_3K_BUFFER when MTU size
> is converted to 1501, which later size check policy allows.
>
> The default MTU value for most servers is 1500 which cannot be adjusted
> directly to the value larger than IXGBE_MAX_2K_FRAME_BUILD_SKB (1534 or
> 1536) if it loads XDP.
>
> After I do a quick study on the manner of i40E driver allowing two kinds
> of buffer size (one is 2048 while another is 3072) to support XDP mode in
> i40e_max_xdp_frame_size(), I believe the default MTU size is possibly not
> satisfied in XDP mode when IXGBE driver is in use, we sometimes need to
> insert a new header, say, vxlan header. So setting the 3K-buffer flag
> could solve the issue.
>
> [1] commit 38b7e7f8ae82 ("ixgbe: Do not allow LRO or MTU change with XDP")
> [2] commit fabf1bce103a ("ixgbe: Prevent unsupported configurations with
> XDP")
>
> Signed-off-by: Jason Xing <[email protected]>
> ---
> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> index ab8370c413f3..dc016582f91e 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> @@ -4313,6 +4313,9 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
> if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
> (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
> set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> +
> + if (ixgbe_enabled_xdp_adapter(adapter))
> + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> #endif
> }
> }
> --
> 2.37.3
>
On Sat, Jan 21, 2023 at 04:55:21PM +0800, Jason Xing wrote:
> From: Jason Xing <[email protected]>
>
> I encountered one case where I cannot increase the MTU size with XDP
> enabled if the server is equipped with IXGBE card, which happened on
> thousands of servers. I noticed it was prohibited from 2017[1] and
> added size checks[2] if allowed soon after the previous patch.
>
> Interesting part goes like this:
> 1) Changing MTU directly from 1500 (default value) to 2000 doesn't
> work because the driver finds out that 'new_frame_size >
> ixgbe_rx_bufsz(ring)' in ixgbe_change_mtu() function.
> 2) However, if we change MTU to 1501 then change from 1501 to 2000, it
> does work, because the driver sets __IXGBE_RX_3K_BUFFER when MTU size
> is converted to 1501, which later size check policy allows.
>
> The default MTU value for most servers is 1500 which cannot be adjusted
> directly to the value larger than IXGBE_MAX_2K_FRAME_BUILD_SKB (1534 or
> 1536) if it loads XDP.
>
> After I do a quick study on the manner of i40E driver allowing two kinds
> of buffer size (one is 2048 while another is 3072) to support XDP mode in
> i40e_max_xdp_frame_size(), I believe the default MTU size is possibly not
> satisfied in XDP mode when IXGBE driver is in use, we sometimes need to
> insert a new header, say, vxlan header. So setting the 3K-buffer flag
> could solve the issue.
>
> [1] commit 38b7e7f8ae82 ("ixgbe: Do not allow LRO or MTU change with XDP")
> [2] commit fabf1bce103a ("ixgbe: Prevent unsupported configurations with
> XDP")
>
> Signed-off-by: Jason Xing <[email protected]>
> ---
> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> index ab8370c413f3..dc016582f91e 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> @@ -4313,6 +4313,9 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
> if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
> (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
> set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> +
> + if (ixgbe_enabled_xdp_adapter(adapter))
> + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
This will result with unnecessary overhead for 1500 MTU because you will
be working on order-1 pages. Instead I would focus on fixing
ixgbe_change_mtu() and stop relying on ixgbe_rx_bufsz() in there. You can
check what we do on ice/i40e sides.
I'm not looking actively into ixgbe internals but I don't think that there
is anything that stops us from using 3k buffers with XDP.
> #endif
> }
> }
> --
> 2.37.3
>
From: Maciej Fijalkowski <[email protected]>
Date: Thu, 26 Jan 2023 13:17:20 +0100
> On Sat, Jan 21, 2023 at 04:55:21PM +0800, Jason Xing wrote:
>> From: Jason Xing <[email protected]>
>>
>> I encountered one case where I cannot increase the MTU size with XDP
>> enabled if the server is equipped with IXGBE card, which happened on
>> thousands of servers. I noticed it was prohibited from 2017[1] and
>> added size checks[2] if allowed soon after the previous patch.
>>
>> Interesting part goes like this:
>> 1) Changing MTU directly from 1500 (default value) to 2000 doesn't
>> work because the driver finds out that 'new_frame_size >
>> ixgbe_rx_bufsz(ring)' in ixgbe_change_mtu() function.
>> 2) However, if we change MTU to 1501 then change from 1501 to 2000, it
>> does work, because the driver sets __IXGBE_RX_3K_BUFFER when MTU size
>> is converted to 1501, which later size check policy allows.
>>
>> The default MTU value for most servers is 1500 which cannot be adjusted
>> directly to the value larger than IXGBE_MAX_2K_FRAME_BUILD_SKB (1534 or
>> 1536) if it loads XDP.
>>
>> After I do a quick study on the manner of i40E driver allowing two kinds
>> of buffer size (one is 2048 while another is 3072) to support XDP mode in
>> i40e_max_xdp_frame_size(), I believe the default MTU size is possibly not
>> satisfied in XDP mode when IXGBE driver is in use, we sometimes need to
>> insert a new header, say, vxlan header. So setting the 3K-buffer flag
>> could solve the issue.
>>
>> [1] commit 38b7e7f8ae82 ("ixgbe: Do not allow LRO or MTU change with XDP")
>> [2] commit fabf1bce103a ("ixgbe: Prevent unsupported configurations with
>> XDP")
>>
>> Signed-off-by: Jason Xing <[email protected]>
>> ---
>> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
>> 1 file changed, 3 insertions(+)
>>
>> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
>> index ab8370c413f3..dc016582f91e 100644
>> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
>> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
>> @@ -4313,6 +4313,9 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
>> if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
>> (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
>> set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
>> +
>> + if (ixgbe_enabled_xdp_adapter(adapter))
>> + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
>
> This will result with unnecessary overhead for 1500 MTU because you will
> be working on order-1 pages. Instead I would focus on fixing
> ixgbe_change_mtu() and stop relying on ixgbe_rx_bufsz() in there. You can
> check what we do on ice/i40e sides.
>
> I'm not looking actively into ixgbe internals but I don't think that there
> is anything that stops us from using 3k buffers with XDP.
I think it uses the same logics as the rest of drivers: splits a 4k page
into two 2k buffers when MTU is <= 1536, otherwise uses order-1 pages
and uses 3k buffers.
OTOH ixgbe is not fully correct in terms how it calculates Rx headroom,
but the main problem is how it calculates the maximum MTU available when
XDP is on. Our usual MTU supported when XDP is on is 3046 bytes.
For MTU <= 1536, 2k buffers are used even for XDP, so the fix is not
correct. Maciej is right that i40e and ice do that way better and don't
have such issue.
>
>> #endif
>> }
>> }
>> --
>> 2.37.3
>>
Thanks,
Olek
On Thu, Jan 26, 2023 at 11:56 PM Alexander Lobakin
<[email protected]> wrote:
>
> From: Maciej Fijalkowski <[email protected]>
> Date: Thu, 26 Jan 2023 13:17:20 +0100
>
> > On Sat, Jan 21, 2023 at 04:55:21PM +0800, Jason Xing wrote:
> >> From: Jason Xing <[email protected]>
> >>
> >> I encountered one case where I cannot increase the MTU size with XDP
> >> enabled if the server is equipped with IXGBE card, which happened on
> >> thousands of servers. I noticed it was prohibited from 2017[1] and
> >> added size checks[2] if allowed soon after the previous patch.
> >>
> >> Interesting part goes like this:
> >> 1) Changing MTU directly from 1500 (default value) to 2000 doesn't
> >> work because the driver finds out that 'new_frame_size >
> >> ixgbe_rx_bufsz(ring)' in ixgbe_change_mtu() function.
> >> 2) However, if we change MTU to 1501 then change from 1501 to 2000, it
> >> does work, because the driver sets __IXGBE_RX_3K_BUFFER when MTU size
> >> is converted to 1501, which later size check policy allows.
> >>
> >> The default MTU value for most servers is 1500 which cannot be adjusted
> >> directly to the value larger than IXGBE_MAX_2K_FRAME_BUILD_SKB (1534 or
> >> 1536) if it loads XDP.
> >>
> >> After I do a quick study on the manner of i40E driver allowing two kinds
> >> of buffer size (one is 2048 while another is 3072) to support XDP mode in
> >> i40e_max_xdp_frame_size(), I believe the default MTU size is possibly not
> >> satisfied in XDP mode when IXGBE driver is in use, we sometimes need to
> >> insert a new header, say, vxlan header. So setting the 3K-buffer flag
> >> could solve the issue.
> >>
> >> [1] commit 38b7e7f8ae82 ("ixgbe: Do not allow LRO or MTU change with XDP")
> >> [2] commit fabf1bce103a ("ixgbe: Prevent unsupported configurations with
> >> XDP")
> >>
> >> Signed-off-by: Jason Xing <[email protected]>
> >> ---
> >> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
> >> 1 file changed, 3 insertions(+)
> >>
> >> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> >> index ab8370c413f3..dc016582f91e 100644
> >> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> >> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> >> @@ -4313,6 +4313,9 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
> >> if (IXGBE_2K_TOO_SMALL_WITH_PADDING ||
> >> (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
> >> set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> >> +
> >> + if (ixgbe_enabled_xdp_adapter(adapter))
> >> + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
> >
> > This will result with unnecessary overhead for 1500 MTU because you will
> > be working on order-1 pages. Instead I would focus on fixing
> > ixgbe_change_mtu() and stop relying on ixgbe_rx_bufsz() in there. You can
> > check what we do on ice/i40e sides.
Well, now I see the commit 23b44513c3e6f in 2019. Thanks, Maciej.
> >
> > I'm not looking actively into ixgbe internals but I don't think that there
> > is anything that stops us from using 3k buffers with XDP.
>
> I think it uses the same logics as the rest of drivers: splits a 4k page
> into two 2k buffers when MTU is <= 1536, otherwise uses order-1 pages
> and uses 3k buffers.
>
> OTOH ixgbe is not fully correct in terms how it calculates Rx headroom,
> but the main problem is how it calculates the maximum MTU available when
> XDP is on. Our usual MTU supported when XDP is on is 3046 bytes.
> For MTU <= 1536, 2k buffers are used even for XDP, so the fix is not
> correct. Maciej is right that i40e and ice do that way better and don't
> have such issue.
Thank you for the detailed explanation. And yes, I checked this part
in the ice/i40e driver which introduces ice/i40e_max_xdp_frame_size()
to test if we can change MTU size when the driver is loading the XDP
program.
I will rewrite the patch as the i40e/ice does in the next submission.
Thanks,
Jason
>
> >
> >> #endif
> >> }
> >> }
> >> --
> >> 2.37.3
> >>
>
> Thanks,
> Olek