On Mon, 2019-04-29 at 23:08 -0400, David Miller wrote:
> From: Johannes Berg
> Date: Fri, 26 Apr 2019 14:13:46 +0200
>
> > From: Johannes Berg
> >
> > Now that we have nested policies, we can theoretically
> > recurse forever parsing attributes if a (sub-)policy
> > refers back to a higher leve
On Mon, Apr 29, 2019 at 09:16:18AM -0700, David Ahern wrote:
> From: David Ahern
>
> Now that the cached routes are in fib_nh_common, pass it to
> rt_cache_route and simplify its callers. For rt_set_nexthop,
> the tclassid becomes the last user of fib_nh so move the
> container of under the #ifde
On Mon, 2019-04-29 at 22:49 -0400, David Miller wrote:
> From: Johannes Berg
> Date: Fri, 26 Apr 2019 14:13:02 +0200
>
> > * NLA_POLICY_RANGE() macros.
> > + *NLA_U8,
> > + *NLA_U16,
> > + *NLA_U32,
> > + *NLA_U64 If the validation_type field
On Mon, Apr 29, 2019 at 09:16:17AM -0700, David Ahern wrote:
> /* Release a nexthop info record */
> @@ -491,9 +491,15 @@ int fib_nh_common_init(struct fib_nh_common *nhc, struct
> nlattr *encap,
> u16 encap_type, void *cfg, gfp_t gfp_flags,
> struct netl
From: Florian Westphal
These functions are small and we only have versions for tunnel
and transport mode for ipv4 and ipv6 respectively.
Just place the 'transport or tunnel' conditional in the protocol
specific function instead of using an indirection.
Before:
3226 12 0 3238
From: Boris Pismenny
This patch introduces support for gso partial ESP offload.
Signed-off-by: Boris Pismenny
Signed-off-by: Raed Salem
Signed-off-by: Steffen Klassert
---
net/ipv4/esp4_offload.c | 10 +++---
net/xfrm/xfrm_device.c | 3 +++
2 files changed, 10 insertions(+), 3 deletion
1) A lot of work to remove indirections from the xfrm code.
From Florian Westphal.
2) Support ESP offload in combination with gso partial.
From Boris Pismenny.
3) Remove some duplicated code from vti4.
From Jeremy Sowden.
Please note that there is merge conflict
between commit:
8742dc
From: Florian Westphal
Now that we have the family available directly in the
xfrm_mode struct, we can use that and avoid one extra dereference.
Signed-off-by: Florian Westphal
Reviewed-by: Sabrina Dubroca
Signed-off-by: Steffen Klassert
---
net/ipv4/ip_vti.c | 2 +-
net/ipv6/ip6_vti.
From: Florian Westphal
similar to previous patch: no external module dependencies,
so we can avoid the indirection by placing this in the core.
This change removes the last indirection from xfrm_mode and the
xfrm4|6_mode_{beet,tunnel}.c modules contain (almost) no code anymore.
Before:
text
From: Florian Westphal
Same is input indirection. Only exception: we need to export
xfrm_outer_mode_output for pktgen.
Increases size of vmlinux by about 163 byte:
Before:
textdata bss dec filename
15730208 6936948 4046908 26714064 vmlinux
After:
15730311 6937008 404690
From: Florian Westphal
handle this directly, its only used by ipv6.
Signed-off-by: Florian Westphal
Signed-off-by: Steffen Klassert
---
include/net/xfrm.h | 3 ---
net/ipv4/xfrm4_policy.c | 7 ---
net/ipv6/xfrm6_policy.c | 14 --
net/xfrm/xfrm_policy.c | 21 +++
From: Florian Westphal
Only used by ipv4, we can read the fl4 tos value directly instead.
Signed-off-by: Florian Westphal
Signed-off-by: Steffen Klassert
---
include/net/xfrm.h | 1 -
net/ipv4/xfrm4_policy.c | 6 --
net/ipv6/xfrm6_policy.c | 6 --
net/xfrm/xfrm_policy.c | 14
From: Florian Westphal
No external dependencies on any module, place this in the core.
Increase is about 1800 byte for xfrm_input.o.
The beet helpers get added to internal header, as they can be reused
from xfrm_output.c in the next patch (kernel contains several
copies of them in the xfrm{4,6}_
From: Florian Westphal
None of them have any external callers, make them static.
Signed-off-by: Florian Westphal
Signed-off-by: Steffen Klassert
---
include/net/xfrm.h| 2 --
net/ipv4/xfrm4_protocol.c | 3 +--
net/ipv6/xfrm6_protocol.c | 3 +--
net/xfrm/xfrm_state.c | 5 ++---
4 f
From: Florian Westphal
Adds an EXPORT_SYMBOL for afinfo_get_rcu, as it will now be called from
ipv6 in case of CONFIG_IPV6=m.
This change has virtually no effect on vmlinux size, but it reduces
afinfo size and allows followup patch to make xfrm modes const.
v2: mark if (afinfo) tests as likely
From: Florian Westphal
No need for any indirection or abstraction here, both functions
are pretty much the same and quite small, they also have no external
dependencies.
xfrm_prepare_input can then be made static.
With allmodconfig build, size increase of vmlinux is 25 byte:
Before:
text
From: Jeremy Sowden
The ipip tunnel introduced in commit dd9ee3444014 ("vti4: Fix a ipip
packet processing bug in 'IPCOMP' virtual tunnel") largely duplicated
the existing vti_input and vti_recv functions. Refactored to
deduplicate the common code.
Signed-off-by: Jeremy Sowden
Signed-off-by: S
From: Florian Westphal
when CONFIG_INET is not enabled:
net/xfrm/xfrm_output.c: In function ‘xfrm4_tunnel_encap_add’:
net/xfrm/xfrm_output.c:234:2: error: implicit declaration of function
‘ip_select_ident’ [-Werror=implicit-function-declaration]
ip_select_ident(dev_net(dst->dev), skb, NULL);
XF
From: Florian Westphal
No external dependencies, might as well handle this directly.
xfrm_afinfo_policy is now 40 bytes on x86_64.
Signed-off-by: Florian Westphal
Signed-off-by: Steffen Klassert
---
include/net/xfrm.h | 3 -
net/ipv4/xfrm4_policy.c | 114
net/ipv6/
From: Florian Westphal
There are only two versions (tunnel and transport). The ip/ipv6 versions
are only differ in sizeof(iphdr) vs ipv6hdr.
Place this in the core and use x->outer_mode->encap type to call the
correct adjustment helper.
Before:
text databss dec filename
157303
From: Florian Westphal
This will be useful to know if we're supposed to decode ipv4 or ipv6.
While at it, make the unregister function return void, all module_exit
functions did just BUG(); there is never a point in doing error checks
if there is no way to handle such error.
Signed-off-by: Flor
From: Florian Westphal
after previous changes, xfrm_mode contains no function pointers anymore
and all modules defining such struct contain no code except an init/exit
functions to register the xfrm_mode struct with the xfrm core.
Just place the xfrm modes core and remove the modules,
the run-ti
From: Florian Westphal
This structure is now only 4 bytes, so its more efficient
to cache a copy rather than its address.
No significant size difference in allmodconfig vmlinux.
With non-modular kernel that has all XFRM options enabled, this
series reduces vmlinux image size by ~11kb. All xfrm_
On Tue, Apr 23, 2019 at 08:27:36PM -0600, David Ahern wrote:
> 2 more columns fixes the current problem, what assurances are there that
> the occupancy levels and max won't reach 100 million in the next few years?
Yes, I thought about that as well, but while the size of the shared
buffers is getti
From: Su Yanjun
When unloading xfrm6_tunnel module, xfrm6_tunnel_fini directly
frees the xfrm6_tunnel_spi_kmem. Maybe someone has gotten the
xfrm6_tunnel_spi, so need to wait it.
Fixes: 91cc3bb0b04ff("xfrm6_tunnel: RCU conversion")
Signed-off-by: Su Yanjun
Acked-by: Herbert Xu
Signed-off-by: S
From: YueHaibing
UBSAN report this:
UBSAN: Undefined behaviour in net/xfrm/xfrm_policy.c:1289:24
index 6 is out of range for type 'unsigned int [6]'
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.4.162-514.55.6.9.x86_64+ #13
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu
1) Fix an out-of-bound array accesses in __xfrm_policy_unlink.
From YueHaibing.
2) Reset the secpath on failure in the ESP GRO handlers
to avoid dereferencing an invalid pointer on error.
From Myungho Jung.
3) Add and revert a patch that tried to add rcu annotations
to netns_xfrm. Fro
This reverts commit f10e0010fae8174dc20bdc872bcaa85baa925cb7.
This commit was just wrong. It caused a lot of
syzbot warnings, so just revert it.
Signed-off-by: Steffen Klassert
---
include/net/netns/xfrm.h | 2 +-
net/xfrm/xfrm_user.c | 30 +++---
2 files changed, 8
From: Martin Willi
If an xfrmi is associated to a vrf layer 3 master device,
xfrm_policy_check() fails after traffic decapsulation. The input
interface is replaced by the layer 3 master device, and hence
xfrmi_decode_session() can't match the xfrmi anymore to satisfy
policy checking.
Extend ingr
From: Nicolas Dichtel
Those entries are not used anymore.
CC: Florian Westphal
Fixes: 09c7570480f7 ("xfrm: remove flow cache")
Signed-off-by: Nicolas Dichtel
Signed-off-by: Steffen Klassert
---
Documentation/networking/ip-sysctl.txt | 2 ++
1 file changed, 2 insertions(+)
diff --git a/Docum
From: Jeremy Sowden
If tunnel registration failed during module initialization, the module
would fail to deregister the IPPROTO_COMP protocol and would attempt to
deregister the tunnel.
The tunnel was not deregistered during module-exit.
Fixes: dd9ee3444014e ("vti4: Fix a ipip packet processing
From: Cong Wang
In commit 6a53b7593233 ("xfrm: check id proto in validate_tmpl()")
I introduced a check for xfrm protocol, but according to Herbert
IPSEC_PROTO_ANY should only be used as a wildcard for lookup, so
it should be removed from validate_tmpl().
And, IPSEC_PROTO_ANY is expected to only
We currently don't reload pointers pointing into skb header
after doing pskb_may_pull() in _decode_session4(). So in case
pskb_may_pull() changed the pointers, we read from random
memory. Fix this by putting all the needed infos on the
stack, so that we don't need to access the header pointers
afte
From: Sabrina Dubroca
esp_output_udp_encap can produce a length that doesn't fit in the 16
bits of a UDP header's length field. In that case, we'll send a
fragmented packet whose length is larger than IP_MAX_MTU (resulting in
"Oversized IP packet" warnings on receive) and with a bogus UDP
length.
From: Su Yanjun
For rcu protected pointers, we'd better add '__rcu' for them.
Once added '__rcu' tag for rcu protected pointer, the sparse tool reports
warnings.
net/xfrm/xfrm_user.c:1198:39: sparse:expected struct sock *sk
net/xfrm/xfrm_user.c:1198:39: sparse:got struct sock [noderef]
From: Jeremy Sowden
Removed info log-message if ipip tunnel registration fails during
module-initialization: it adds nothing to the error message that is
written on all failures.
Fixes: dd9ee3444014e ("vti4: Fix a ipip packet processing bug in 'IPCOMP'
virtual tunnel")
Signed-off-by: Jeremy Sow
From: Myungho Jung
In esp4_gro_receive() and esp6_gro_receive(), secpath can be allocated
without adding xfrm state to xvec. Then, sp->xvec[sp->len - 1] would
fail and result in dereferencing invalid pointer in esp4_gso_segment()
and esp6_gso_segment(). Reset secpath if xfrm function returns erro
On 29.04.2019 23:52, Andrew Lunn wrote:
>> @@ -2078,6 +2089,11 @@ EXPORT_SYMBOL(phy_set_sym_pause);
>> void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx)
>> {
>> __ETHTOOL_DECLARE_LINK_MODE_MASK(oldadv);
>> +bool asym_pause_supported;
>> +
>> +asym_pause_supported =
From: Stephen Suryaputra
Date: Sat, 27 Apr 2019 09:14:33 -0400
> When there is no route to an IPv6 dest addr, skb_dst(skb) points
> to loopback dev in the case of that the IP6CB(skb)->iif is
> enslaved to a vrf. This causes Ip6InNoRoutes to be incremented on the
> loopback dev. This also causes t
From: Eric Dumazet
Date: Fri, 26 Apr 2019 10:10:05 -0700
> Richard and Bruno both reported that my commit added a bug,
> and Bruno was able to determine the problem came when a segment
> wih a FIN packet was coalesced to a prior one in tcp backlog queue.
>
> It turns out the header prediction in
From: Johannes Berg
Date: Fri, 26 Apr 2019 14:13:46 +0200
> From: Johannes Berg
>
> Now that we have nested policies, we can theoretically
> recurse forever parsing attributes if a (sub-)policy
> refers back to a higher level one. This is a situation
> that has happened in nl80211, and we've av
On Tue, Apr 30, 2019 at 11:17:32AM +1000, Stephen Mallon wrote:
>
> I've found that SOF_TIMESTAMPING_OPT_ID already works with hardware timestamps
> for TCP just not datagram sockets and so I though this was a fix.
Right, so if HW time stamping worked for TCP but not for UDP, then I
would call it
From: Johannes Berg
Date: Fri, 26 Apr 2019 14:13:02 +0200
> * NLA_POLICY_RANGE() macros.
> + *NLA_U8,
> + *NLA_U16,
> + *NLA_U32,
> + *NLA_U64 If the validation_type field instead is set to
> + * NLA_VALIDATE_RANGE_PTR
Fixes: 65b2b4939a64 ("selftests: net: initial fib rule tests")
Signed-off-by: Hangbin Liu
---
tools/testing/selftests/net/fib_rule_tests.sh | 6 ++
1 file changed, 6 insertions(+)
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh
b/tools/testing/selftests/net/fib_rule_tests.sh
inde
On Mon, Apr 29, 2019 at 10:30:09AM -0700, David Ahern wrote:
> From: David Ahern
>
> A recent commit returns an error if icmp is used as the ip-proto for
> IPv6 fib rules. Update fib_rule_tests to send ipv6-icmp instead of icmp.
>
> Fixes: 5e1a99eae8499 ("ipv4: Add ICMPv6 support when parse rout
Fix inconsistent IS_ERR and PTR_ERR in cpsw_probe,
The proper pointer to use is clk instead of mode.
This issue was detected with the help of Coccinelle.
Fixes: 83a8471ba255 ("net: ethernet: ti: cpsw: refactor probe to group common
hw initialization")
Signed-off-by: YueHaibing
Reviewed-by: Andr
On 2019/4/30 0:30, Julia Lawall wrote:
>
>
> On Mon, 29 Apr 2019, YueHaibing wrote:
>
>> Change the call to PTR_ERR to access the value just tested by IS_ERR.
>
> I assume you didn't find the problem just looking through the code by
> hand. If you used a tool, it would be really good to acknow
On Mon, Apr 29, 2019 at 11:32:08AM -0400, Willem de Bruijn wrote:
> On Mon, Apr 29, 2019 at 11:02 AM Richard Cochran
> wrote:
> >
> > On Sun, Apr 28, 2019 at 10:57:57PM -0400, Willem de Bruijn wrote:
> > > It is debatable whether this is a fix or a new feature. It extends
> > > SOF_TIMESTAMPING_OP
On 4/29/19 5:48 PM, Rob Herring wrote:
> On Tue, Apr 16, 2019 at 08:01:56PM -0700, Frank Rowand wrote:
>> Hi Rob,
>>
>> On 4/16/19 5:29 PM, Florian Fainelli wrote:
>>>
>>>
>>> On 16/04/2019 13:05, Petr Štetiar wrote:
From: John Crispin
Many embedded devices have information such as
On Mon, 29 Apr 2019 12:16:28 -0700, Jeff Kirsher wrote:
> From: Alice Michael
>
> This patch introduces "recovery mode" to the i40e driver. It is
> part of a new Any2Any idea of upgrading the firmware. In this
> approach, it is required for the driver to have support for
> "transition firmware",
On Mon, 29 Apr 2019 17:17:39 +0300, Aya Levin wrote:
> In order to offline translate the raw memory into a human readable
> format, the user can use some out-of-kernel scripts which receives as an
> input the following:
> - Object raw memory
> - Driver object compiled with debug info (can be taken/
On Tue, Apr 16, 2019 at 08:01:56PM -0700, Frank Rowand wrote:
> Hi Rob,
>
> On 4/16/19 5:29 PM, Florian Fainelli wrote:
> >
> >
> > On 16/04/2019 13:05, Petr Štetiar wrote:
> >> From: John Crispin
> >>
> >> Many embedded devices have information such as MAC addresses stored
> >> inside MTD devi
Hi,
Jakub Kicinski writes:
> Recent changes to taprio did not use the correct div64 helpers,
> leading to:
>
> net/sched/sch_taprio.o: In function `taprio_dequeue':
> sch_taprio.c:(.text+0x34a): undefined reference to `__divdi3'
> net/sched/sch_taprio.o: In function `advance_sched':
> sch_tapr
Test test_libbpf.sh failed on my development server with failure
-bash-4.4$ sudo ./test_libbpf.sh
[0] libbpf: Error in bpf_object__probe_name():Operation not permitted(1).
Couldn't load basic 'r0 = 0' BPF program.
test_libbpf: failed at file test_l4lb.o
selftests: test_libbpf [FAILED]
On Mon, 2019-04-29 at 18:13 +, Saeed Mahameed wrote:
> Hi,
>
> This series provides misc low level updates to mlx5 core driver, to
> be
> shared between rdma and net-next trees.
>
> 1) From Aya: Enable general events on all physical link types and
> restrict general event handling of subtype
RDS doesn't support RDMA on memory apertures that require On Demand
Paging (ODP), such as FS DAX memory. A sysctl is added to indicate
whether RDMA requiring ODP is supported.
Reviewed-by: Håkon Bugge
Reviewed-tested-by: Zhu Yanjun
Signed-off-by: Hans Westgaard Ry
Signed-off-by: Santosh Shilimk
RDS doesn't support RDMA on memory apertures that require On Demand
Paging (ODP), such as FS DAX memory. User applications can try to use
RDS to perform RDMA over such memories and since it doesn't report any
failure, it can lead to unexpected issues like memory corruption when
a couple of out of s
From: Hans Westgaard Ry
RDS doesn't support RDMA on memory apertures that require On Demand
Paging (ODP), such as FS DAX memory. User applications can try to use
RDS to perform RDMA over such memories and since it doesn't report any
failure, it can lead to unexpected issues like memory corruption
On Mon, Apr 29, 2019 at 2:53 AM Quentin Monnet
wrote:
>
> libbpf has three levels of priority for output: warn, info, debug. By
> default, debug output is not printed to stderr.
>
> Add a new "--log-libbpf LOG_LEVEL" option to bpftool to provide more
> flexibility on the log level for libbpf. LOG_
Validate Destination and Hop-by-Hop options. This uses the information
in the TLV parameters table to validate various aspects of both
individual TLVs as well as a list of TLVs in an extension header.
There are two levels of validation that can be performed: simple checks
and deep checks. Simple c
Create a single TLV parameter table that holds meta information for IPv6
Hop-by-Hop and Destination TLVs. The data structure is composed of a 256
element array of u8's (one entry for each TLV type to allow O(1)
lookup). Each entry provides an offset into an array of TLV proc data
structures which f
Move generic functions in exthdrs.c to new exthdrs_common.c so that
exthdrs.c only contains functions that are specific to IPv6 processing,
and exthdrs_common.c contains functions that are generic. These
functions include those that will be used with IPv4 extension headers.
Signed-off-by: Tom Herb
Add a netlink interface to manage the TX TLV parameters. Managed
parameters include those for validating and sending TLVs being sent
such as alignment, TLV ordering, length limits, etc.
Signed-off-by: Tom Herbert
---
include/net/ipv6.h | 18 +++
include/uapi/linux/in6.h | 31 +
n
Define a number of transmit parameters for TLV Parameter table
definitions. These will be used for validating TLVs that are set
on a socket.
Signed-off-by: Tom Herbert
---
include/net/ipv6.h | 26 -
include/uapi/linux/in6.h | 8 +++
net/ipv6/exthdrs.c |
Create exthdrs_options.c to hold code related to specific Hop-by-Hop
and Destination extension header options. Move related functions in
exthdrs.c to the new file.
Signed-off-by: Tom Herbert
---
include/net/ipv6.h | 15
net/ipv6/Makefile | 2 +-
net/ipv6/exthdrs.c
Extension headers are the mechanism of extensibility for the IPv6
protocol, however to date they have only seen limited deployment.
The reasons for that are because intermediate devices don't handle
them well, and there haven't really be any useful extension headers
defined. In particular, Destinat
Extension headers are the mechanism of extensibility for the IPv6
protocol, however to date they have only seen limited deployment.
The reasons for that are because intermediate devices don't handle
them well, and there haven't really be any useful extension headers
defined. In particular, Destinat
Add a utility function to replace socket's options with a new set.
Signed-off-by: Tom Herbert
---
include/net/ipv6.h | 2 ++
net/ipv6/ipv6_sockglue.c | 16
2 files changed, 18 insertions(+)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8c19c6f..a8c1e6c 10064
Validate Destination and Hop-by-Hop options. This uses the information
in the TLV parameters table to validate various aspects of both
individual TLVs as well as a list of TLVs in an extension header.
There are two levels of validation that can be performed: simple checks
and deep checks. Simple c
Move generic functions in exthdrs.c to new exthdrs_common.c so that
exthdrs.c only contains functions that are specific to IPv6 processing,
and exthdrs_common.c contains functions that are generic. These
functions include those that will be used with IPv4 extension headers.
Signed-off-by: Tom Herb
Add utility functions in exthdrs_common.c to manipulate individual
TVLs in Hop-by-Hop or Destination Options. This includes functions
to find, insert, and delete in singleton TLV from on IPv6 options
header.
This code is based in part on the TLV option handling in calipso.c.
Signed-off-by: Tom He
This patch provides an interface for adding a deleting
individual Hop-by-Hop or Destination Options on a socket.
The following IPv6 socket options are created:
IPV6_HOPOPTS_TLV
IPV6_RTHDRDSTOPTS_TLV
IPV6_DSTOPTS_TLV
IPV6_HOPOPTS_DEL_TLV
IPV6_RTHDRDSTOPTS_DEL
Extension headers are the mechanism of extensibility for the IPv6
protocol, however to date they have only seen limited deployment.
The reasons for that are because intermediate devices don't handle
them well, and there haven't really be any useful extension headers
defined. In particular, Destinat
Define a number of transmit parameters for TLV Parameter table
definitions. These will be used for validating TLVs that are set
on a socket.
Signed-off-by: Tom Herbert
---
include/net/ipv6.h | 26 -
include/uapi/linux/in6.h | 8 +++
net/ipv6/exthdrs.c |
Create a single TLV parameter table that holds meta information for IPv6
Hop-by-Hop and Destination TLVs. The data structure is composed of a 256
element array of u8's (one entry for each TLV type to allow O(1)
lookup). Each entry provides an offset into an array of TLV proc data
structures which f
Add a netlink interface to manage the TX TLV parameters. Managed
parameters include those for validating and sending TLVs being sent
such as alignment, TLV ordering, length limits, etc.
Signed-off-by: Tom Herbert
---
include/net/ipv6.h | 18 +++
include/uapi/linux/in6.h | 31 +
n
This will be updated when the kernel headers are updated.
Signed-off-by: Vinicius Costa Gomes
---
include/uapi/linux/pkt_sched.h | 18 ++
1 file changed, 18 insertions(+)
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 7ee74c34..ac9f7eab 100644
This allows for a new schedule to be specified during runtime, without
removing the current one.
For that, the semantics of the 'tc qdisc change' operation in the
context of taprio is that if "change" is called and there is a running
schedule, a new schedule is created and the base-time (let's cal
This allows a cycle-time and a cycle-time-extension to be specified.
Specifying a cycle-time will truncate that cycle, so when that instant
is reached, the cycle will start from its beginning.
A cycle-time-extension may cause the last entry of a cycle, just
before the start of a new schedule (the
Hi,
Changes from RFC:
- Removed the patches for taprio offloading, because of the lack of
in-tree users;
- Updated the links to point to the PATCH version of this series;
Original cover letter:
Overview
This RFC has two objectives, it adds support for changing the running
schedu
The IEEE 802.1Q-2018 defines two "types" of schedules, the "Oper" (from
operational?) and "Admin" ones. Up until now, 'taprio' only had
support for the "Oper" one, added when the qdisc is created. This adds
support for the "Admin" one, which allows the .change() operation to
be supported.
Just for
IEEE 802.1Q-2018 defines the concept of a cycle-time-extension, so the
last entry of a schedule before the start of a new schedule can be
extended, so "too-short" entries can be avoided.
Signed-off-by: Vinicius Costa Gomes
---
include/uapi/linux/pkt_sched.h | 1 +
net/sched/sch_taprio.c
IEEE 802.1Q-2018 defines that a the cycle-time of a schedule may be
overridden, so the schedule is truncated to a determined "width".
Signed-off-by: Vinicius Costa Gomes
---
include/uapi/linux/pkt_sched.h | 1 +
net/sched/sch_taprio.c | 59 +-
2 files cha
Right now, this isn't a problem, but the next commit allows schedules
to be added during runtime. When a new schedule transitions from the
inactive to the active state ("admin" -> "oper") the previous one can
be freed, if it's freed just after the RCU read lock is released, we
may access an invalid
Linux implements RFC6298 and use an initial congestion window
of 1 upon establishing the connection if the SYNACK packet is
retransmitted 2 or more times. In cellular networks SYNACK timeouts
are often spurious if the wireless radio was dormant or idle. Also
some network path is longer than the def
This patch makes passive Fast Open reverts the cwnd to default
initial cwnd (10 packets) if the SYNACK timeout is spurious.
Passive Fast Open uses a full socket during handshake so it can
use the existing undo logic to detect spurious retransmission
by recording the first SYNACK timeout in key sta
Use a helper to consolidate two identical code block for passive TFO.
Signed-off-by: Yuchung Cheng
Signed-off-by: Neal Cardwell
Signed-off-by: Soheil Hassas Yeganeh
Signed-off-by: Eric Dumazet
---
net/ipv4/tcp_input.c | 52 +---
1 file changed, 25 inser
Linux implements RFC6298 and use an initial congestion window of 1
upon establishing the connection if the SYN packet is retransmitted 2
or more times. In cellular networks SYN timeouts are often spurious
if the wireless radio was dormant or idle. Also some network path
is longer than the default S
TCP sender would use congestion window of 1 packet on the second SYN
and SYNACK timeout except passive TCP Fast Open. This makes passive
TFO too aggressive and unfair during congestion at handshake. This
patch fixes this issue so TCP (fast open or not, passive or active)
always conforms to the RFC6
Relocate the congestion window initialization from tcp_init_metrics()
to tcp_init_transfer() to improve code readability.
Signed-off-by: Yuchung Cheng
Signed-off-by: Neal Cardwell
Signed-off-by: Soheil Hassas Yeganeh
Signed-off-by: Eric Dumazet
---
net/ipv4/tcp.c | 12
ne
Linux TCP currently uses the initial congestion window of 1 packet
if multiple SYN or SYNACK timeouts per RFC6298. However such
timeouts are often spurious on wireless or cellular networks that
experience high delay variances (e.g. ramping up dormant radios or
local link retransmission). Another ca
Previously if an active TCP open has SYN timeout, it always undo the
cwnd upon receiving the SYNACK. This is because tcp_clean_rtx_queue
would reset tp->retrans_stamp when SYN is acked, which fools then
tcp_try_undo_loss and tcp_packet_delayed. Addressing this issue is
required to properly support
Detecting spurious SYNACK timeout using timestamp option requires
recording the exact SYNACK skb timestamp. Previously the SYNACK
sent timestamp was stamped slightly earlier before the skb
was transmitted. This patch uses the SYNACK skb transmission
timestamp directly.
Signed-off-by: Yuchung Cheng
Hi Mark,
> -Original Message-
> From: Mark Bloch
> Sent: Monday, April 29, 2019 5:31 PM
> To: Parav Pandit ; Leon Romanovsky
> ; Saeed Mahameed
> Cc: Jason Gunthorpe ; netdev@vger.kernel.org; linux-
> r...@vger.kernel.org; Maor Gottlieb
> Subject: Re: [PATCH V2 mlx5-next 09/11] net/mlx5:
On 4/29/19 11:45 AM, Parav Pandit wrote:
>
>
>> -Original Message-
>> From: netdev-ow...@vger.kernel.org On
>> Behalf Of Leon Romanovsky
>> Sent: Monday, April 29, 2019 1:41 PM
>> To: Saeed Mahameed
>> Cc: Jason Gunthorpe ; netdev@vger.kernel.org; linux-
>> r...@vger.kernel.org; Maor
On 4/29/19 3:25 PM, David Miller wrote:
From: Santosh Shilimkar
Date: Thu, 25 Apr 2019 17:44:29 -0700
@@ -158,8 +158,9 @@ static int rds_pin_pages(unsigned long user_addr, unsigned
int nr_pages,
{
int ret;
- ret = get_user_pages_fast(user_addr, nr_pages, write, pages);
-
+
From: Santosh Shilimkar
Date: Thu, 25 Apr 2019 17:44:29 -0700
> @@ -158,8 +158,9 @@ static int rds_pin_pages(unsigned long user_addr,
> unsigned int nr_pages,
> {
> int ret;
>
> - ret = get_user_pages_fast(user_addr, nr_pages, write, pages);
> -
> + /* get_user_pages return -EO
From: Willem de Bruijn
Date: Thu, 25 Apr 2019 12:06:54 -0400
> From: Willem de Bruijn
>
> A request for a flowlabel fails in process or user exclusive mode must
> fail if the caller pid or uid does not match. Invert the test.
>
> Previously, the test was unsafe wrt PID recycling, but indeed te
From: Stefan Schmidt
Date: Thu, 25 Apr 2019 18:03:11 +0200
> An update from ieee802154 for your *net* tree.
>
> Another fix from Kangjie Lu to ensure better checking regmap updates in the
> mcr20a driver. Nothing else I have pending for the final release.
>
> If there are any problems let me kn
On Mon, Apr 29, 2019 at 10:04:52AM +, Igor Russkikh wrote:
> Improve for better readability
>
> Signed-off-by: Nikita Danilov
> Signed-off-by: Igor Russkikh
Hi Igor
https://www.spinics.net/lists/netdev/msg567238.html
Please remember to add any reviewed-by you get.
Andrew
1 - 100 of 253 matches
Mail list logo
