David S. Miller [Fri, 18 Mar 2022 10:30:00 +0000 (10:30 +0000)]
Merge tag 'mlx5-updates-2022-03-17' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2022-03-17
1) From Maxim Mikityanskiy,
Datapath improvements in preparation for XDP multi buffer
This series contains general improvements for the datapath that are
useful for the upcoming XDP multi buffer support:
a. Non-linear legacy RQ: validate MTU for robustness, build the linear
part of SKB over the first hardware fragment (instead of copying the
packet headers), adjust headroom calculations to allow enabling headroom
in the non-linear mode (useful for XDP multi buffer).
b. XDP: do the XDP program test before function call, optimize
parameters of mlx5e_xdp_handle.
2) From Rongwei Liu, DR, reduce steering memory usage
Currently, mlx5 driver uses mlx5_htbl/chunk/ste to organize
steering logic. However there is a little memory waste.
This update targets to reduce steering memory footprint by:
a. Adjust struct member layout.
b. Remove duplicated indicator by using simple functions call.
With 500k TX rules(3 ste) plus 500k RX rules(6 stes), these patches
can save around 17% memory.
3) Three cleanup commits at the end of this series.
===================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Fri, 18 Mar 2022 00:42:50 +0000 (17:42 -0700)]
Merge branch 'mirroring-for-ocelot-switches'
Vladimir Oltean says:
====================
Mirroring for Ocelot switches
This series adds support for tc-matchall (port-based) and tc-flower
(flow-based) offloading of the tc-mirred action. Support has been added
for both the ocelot switchdev driver and felix DSA driver.
====================
Vladimir Oltean [Wed, 16 Mar 2022 20:41:42 +0000 (22:41 +0200)]
net: mscc: ocelot: offload per-flow mirroring using tc-mirred and VCAP IS2
Per-flow mirroring with the VCAP IS2 TCAM (in itself handled as an
offload for tc-flower) is done by setting the MIRROR_ENA bit from the
action vector of the filter. The packet is mirrored to the port mask
configured in the ANA:ANA:MIRRORPORTS register (the same port mask as
the destinations for port-based mirroring).
Functionality was tested with:
tc qdisc add dev swp3 clsact
tc filter add dev swp3 ingress protocol ip \
flower skip_sw ip_proto icmp \
action mirred egress mirror dev swp1
and pinging through swp3, while seeing that the ICMP replies are
mirrored towards swp1.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Wed, 16 Mar 2022 20:41:41 +0000 (22:41 +0200)]
net: mscc: ocelot: establish functions for handling VCAP aux resources
Some VCAP filters utilize resources which are global to the switch, like
for example VCAP IS2 policers take an index into a global policer pool.
In commit c9a7fe1238e5 ("net: mscc: ocelot: add action of police on
vcap_is2"), Xiaoliang expressed this by hooking into the low-level
ocelot_vcap_filter_add_to_block() and ocelot_vcap_block_remove_filter()
functions, and allocating/freeing the policers from there.
Evaluating the code, there probably isn't a better place, but we'll need
to do something similar for the mirror ports, and the code will start to
look even more hacked up than it is right now.
Create two ocelot_vcap_filter_{add,del}_aux_resources() functions to
contain the madness, and pollute less the body of other functions such
as ocelot_vcap_filter_add_to_block().
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Wed, 16 Mar 2022 20:41:40 +0000 (22:41 +0200)]
net: mscc: ocelot: add port mirroring support using tc-matchall
Ocelot switches perform port-based ingress mirroring if
ANA:PORT:PORT_CFG field SRC_MIRROR_ENA is set, and egress mirroring if
the port is in ANA:ANA:EMIRRORPORTS.
Both ingress-mirrored and egress-mirrored frames are copied to the port
mask from ANA:ANA:MIRRORPORTS.
So the choice of limiting to a single mirror port via ocelot_mirror_get()
and ocelot_mirror_put() may seem bizarre, but the hardware model doesn't
map very well to the user space model. If the user wants to mirror the
ingress of swp1 towards swp2 and the ingress of swp3 towards swp4, we'd
have to program ANA:ANA:MIRRORPORTS with BIT(2) | BIT(4), and that would
make swp1 be mirrored towards swp4 too, and swp3 towards swp2. But there
are no tc-matchall rules to describe those actions.
Now, we could offload a matchall rule with multiple mirred actions, one
per desired mirror port, and force the user to stick to the multi-action
rule format for subsequent matchall filters. But both DSA and ocelot
have the flow_offload_has_one_action() check for the matchall offload,
plus the fact that it will get cumbersome to cross-check matchall
mirrors with flower mirrors (which will be added in the next patch).
As a result, we limit the configuration to a single mirror port, with
the possibility of lifting the restriction in the future.
Frames injected from the CPU don't get egress-mirrored, since they are
sent with the BYPASS bit in the injection frame header, and this
bypasses the analyzer module (effectively also the mirroring logic).
I don't know what to do/say about this.
Functionality was tested with:
tc qdisc add dev swp3 clsact
tc filter add dev swp3 ingress \
matchall skip_sw \
action mirred egress mirror dev swp1
and pinging through swp3, while seeing that the ICMP replies are
mirrored towards swp1.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Vladimir Oltean [Wed, 16 Mar 2022 20:41:39 +0000 (22:41 +0200)]
net: mscc: ocelot: refactor policer work out of ocelot_setup_tc_cls_matchall
In preparation for adding port mirroring support to the ocelot driver,
the dispatching function ocelot_setup_tc_cls_matchall() must be free of
action-specific code. Move port policer creation and deletion to
separate functions.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jonathan Lemon [Wed, 16 Mar 2022 16:53:47 +0000 (09:53 -0700)]
ptp: ocp: Make debugfs variables the correct bitwidth
An earlier patch mistakenly changed these variables from u32 to u16,
leading to unintended truncation. Restore the original logic.
Fixes: a509a7c61e3b ("ptp: ocp: Add support for selectable SMA directions.") Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com> Link: https://lore.kernel.org/r/20220316165347.599154-1-jonathan.lemon@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
According to erratum described in DS80000687C[1]: "Module 2: Link drops with
some EEE link partners.", we need to "Disable the EEE next page
exchange in EEE Global Register 2"
- The mapping from VLAN to STP state is fixed as 1:1, i.e. each VLAN
is managed independently. This is awkward from an MSTP (802.1Q-2018,
Clause 13.5) point of view, where the model is that multiple VLANs
are grouped into MST instances.
Because of the way that the standard is written, presumably, this is
also reflected in hardware implementations. It is not uncommon for a
switch to support the full 4k range of VIDs, but that the pool of
MST instances is much smaller. Some examples:
Marvell LinkStreet (mv88e6xxx): 4k VLANs, but only 64 MSTIs
Marvell Prestera: 4k VLANs, but only 128 MSTIs
Microchip SparX-5i: 4k VLANs, but only 128 MSTIs
- By default, the feature is enabled, and there is no way to disable
it. This makes it hard to add offloading in a backwards compatible
way, since any underlying switchdevs have no way to refuse the
function if the hardware does not support it
- The port-global STP state has precedence over per-VLAN states. In
MSTP, as far as I understand it, all VLANs will use the common
spanning tree (CST) by default - through traffic engineering you can
then optimize your network to group subsets of VLANs to use
different trees (MSTI). To my understanding, the way this is
typically managed in silicon is roughly:
What this is trying to show is that the STP state (whether MSTP is
used, or ye olde STP) is always accessed via the VLAN table. If STP
is running, all MSTI pointers in that table will reference the same
index in the STP stable - if MSTP is running, some VLANs may point
to other trees (like in this example).
The fact that in the Linux bridge, the global state (think: index 0
in most hardware implementations) is supposed to override the
per-VLAN state, is very awkward to offload. In effect, this means
that when the global state changes to blocking, drivers will have to
iterate over all MSTIs in use, and alter them all to match. This
also means that you have to cache whether the hardware state is
currently tracking the global state or the per-VLAN state. In the
first case, you also have to cache the per-VLAN state so that you
can restore it if the global state transitions back to forwarding.
This series adds a new mst_enable bridge setting (as suggested by Nik)
that can only be changed when no VLANs are configured on the
bridge. Enabling this mode has the following effect:
- The port-global STP state is used to represent the CST (Common
Spanning Tree) (1/15)
- Ingress STP filtering is deferred until the frame's VLAN has been
resolved (1/15)
- The preexisting per-VLAN states can no longer be controlled directly
(1/15). They are instead placed under the MST module's control,
which is managed using a new netlink interface (described in 3/15)
- VLANs can br mapped to MSTIs in an arbitrary M:N fashion, using a
new global VLAN option (2/15)
Switchdev notifications are added so that a driver can track:
- MST enabled state
- VID to MSTI mappings
- MST port states
An offloading implementation is this provided for mv88e6xxx.
====================
In early LinkStreet silicon (e.g. 6095/6185), the per-VLAN STP states
were kept in the VTU - there was no concept of a SID. Later, the
information was split into two tables, where the VTU only tracked
memberships and deferred the STP state tracking to the STU via a
pointer (SID). This meant that a group of VLANs could share the same
STU entry. Most likely, this was done to align with MSTP (802.1Q-2018,
Clause 13), which is built on this principle.
While the VTU is still 4k lines on most devices, the STU is capped at
64 entries. This means that the current stategy, updating STU info
whenever a VTU entry is updated, can not easily support MSTP because:
- The maximum number of VIDs would also be capped at 64, as we would
have to allocate one SID for every VTU entry - even if many VLANs
would effectively share the same MST.
- MSTP updates would be unnecessarily slow as you would have to
iterate over all VLANs that share the same MST.
In order to support MSTP offloading in the future, manage the STU as a
separate entity from the VTU.
Only add support for newer hardware with separate VTU and
STU. VTU-only devices can also be supported, but essentially this
requires a software implementation of an STU (fanning out state
changed to all VLANs tied to the same MST).
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add the usual trampoline functionality from the generic DSA layer down
to the drivers for MST state changes.
When a state changes to disabled/blocking/listening, make sure to fast
age any dynamic entries in the affected VLANs (those controlled by the
MSTI in question).
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: bridge: mst: Add helper to query a port's MST state
This is useful for switchdev drivers who are offloading MST states
into hardware. As an example, a driver may wish to flush the FDB for a
port when it transitions from forwarding to blocking - which means
that the previous state must be discoverable.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: bridge: mst: Add helper to map an MSTI to a VID set
br_mst_get_info answers the question: "On this bridge, which VIDs are
mapped to the given MSTI?"
This is useful in switchdev drivers, which might have to fan-out
operations, relating to an MSTI, per VLAN.
An example: When a port's MST state changes from forwarding to
blocking, a driver may choose to flush the dynamic FDB entries on that
port to get faster reconvergence of the network, but this should only
be done in the VLANs that are managed by the MSTI in question.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: bridge: mst: Notify switchdev drivers of MST state changes
Generate a switchdev notification whenever an MST state changes. This
notification is keyed by the VLANs MSTI rather than the VID, since
multiple VLANs may share the same MST instance.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: bridge: mst: Notify switchdev drivers of MST mode changes
Trigger a switchdev event whenever the bridge's MST mode is
enabled/disabled. This allows constituent ports to either perform any
required hardware config, or refuse the change if it not supported.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: bridge: mst: Support setting and reporting MST port states
Make it possible to change the port state in a given MSTI by extending
the bridge port netlink interface (RTM_SETLINK on PF_BRIDGE).The
proposed iproute2 interface would be:
bridge mst set dev <PORT> msti <MSTI> state <STATE>
Current states in all applicable MSTIs can also be dumped via a
corresponding RTM_GETLINK. The proposed iproute interface looks like
this:
$ bridge mst
port msti
vb1 0
state forwarding
100
state disabled
vb2 0
state forwarding
100
state forwarding
The preexisting per-VLAN states are still valid in the MST
mode (although they are read-only), and can be queried as usual if one
is interested in knowing a particular VLAN's state without having to
care about the VID to MSTI mapping (in this example VLAN 20 and 30 are
bound to MSTI 100):
$ bridge -d vlan
port vlan-id
vb1 10
state forwarding mcast_router 1
20
state disabled mcast_router 1
30
state disabled mcast_router 1
40
state forwarding mcast_router 1
vb2 10
state forwarding mcast_router 1
20
state forwarding mcast_router 1
30
state forwarding mcast_router 1
40
state forwarding mcast_router 1
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: bridge: mst: Multiple Spanning Tree (MST) mode
Allow the user to switch from the current per-VLAN STP mode to an MST
mode.
Up to this point, per-VLAN STP states where always isolated from each
other. This is in contrast to the MSTP standard (802.1Q-2018, Clause
13.5), where VLANs are grouped into MST instances (MSTIs), and the
state is managed on a per-MSTI level, rather that at the per-VLAN
level.
Perhaps due to the prevalence of the standard, many switching ASICs
are built after the same model. Therefore, add a corresponding MST
mode to the bridge, which we can later add offloading support for in a
straight-forward way.
For now, all VLANs are fixed to MSTI 0, also called the Common
Spanning Tree (CST). That is, all VLANs will follow the port-global
state.
Upcoming changes will make this actually useful by allowing VLANs to
be mapped to arbitrary MSTIs and allow individual MSTI states to be
changed.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Heiner Kallweit [Wed, 16 Mar 2022 21:31:00 +0000 (22:31 +0100)]
r8169: improve driver unload and system shutdown behavior on DASH-enabled systems
There's a number of systems supporting DASH remote management.
Driver unload and system shutdown can result in the PHY suspending,
thus making DASH unusable. Improve this by handling DASH being enabled
very similar to WoL being enabled.
Bill Wendling [Wed, 16 Mar 2022 21:31:25 +0000 (14:31 -0700)]
vlan: use correct format characters
When compiling with -Wformat, clang emits the following warning:
net/8021q/vlanproc.c:284:22: warning: format specifies type 'unsigned
short' but the argument has type 'int' [-Wformat]
mp->priority, ((mp->vlan_qos >> 13) & 0x7));
^~~~~~~~~~~~~~~~~~~~~~~~~~~~
The types of these arguments are unconditionally defined, so this patch
updates the format character to the correct ones for ints and unsigned
ints.
Bill Wendling [Wed, 16 Mar 2022 21:31:14 +0000 (14:31 -0700)]
net/fsl: xgmac_mdio: use correct format characters
When compiling with -Wformat, clang emits the following warning:
drivers/net/ethernet/freescale/xgmac_mdio.c:243:22: warning: format
specifies type 'unsigned char' but the argument has type 'int'
[-Wformat]
phy_id, dev_addr, regnum);
^~~~~~
./include/linux/dev_printk.h:163:47: note: expanded from macro 'dev_dbg'
dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \
~~~ ^~~~~~~~~~~
./include/linux/dev_printk.h:129:34: note: expanded from macro 'dev_printk'
_dev_printk(level, dev, fmt, ##__VA_ARGS__); \
~~~ ^~~~~~~~~~~
The types of these arguments are unconditionally defined, so this patch
updates the format character to the correct ones for ints and unsigned
ints.
Bill Wendling [Wed, 16 Mar 2022 21:31:04 +0000 (14:31 -0700)]
bnx2x: use correct format characters
When compiling with -Wformat, clang emits the following warnings:
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c:6181:40: warning: format
specifies type 'unsigned short' but the argument has type 'u32'
(aka 'unsigned int') [-Wformat]
ret = scnprintf(str, *len, "%hx.%hx", num >> 16, num);
~~~ ^~~~~~~~~
%x
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c:6181:51: warning: format
specifies type 'unsigned short' but the argument has type 'u32'
(aka 'unsigned int') [-Wformat]
ret = scnprintf(str, *len, "%hx.%hx", num >> 16, num);
~~~ ^~~
%x
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c:6196:47: warning: format
specifies type 'unsigned char' but the argument has type 'u32'
(aka 'unsigned int') [-Wformat]
ret = scnprintf(str, *len, "%hhx.%hhx.%hhx", num >> 16, num >> 8, num);
~~~~ ^~~~~~~~~
%x
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c:6196:58: warning: format
specifies type 'unsigned char' but the argument has type 'u32'
(aka 'unsigned int') [-Wformat]
ret = scnprintf(str, *len, "%hhx.%hhx.%hhx", num >> 16, num >> 8, num);
~~~~ ^~~~~~~~
%x
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c:6196:68: warning: format
specifies type 'unsigned char' but the argument has type 'u32'
(aka 'unsigned int') [-Wformat]
ret = scnprintf(str, *len, "%hhx.%hhx.%hhx", num >> 16, num >> 8, num);
~~~~ ^~~
%x
The types of these arguments are unconditionally defined, so this patch
updates the format character to the correct ones for ints and unsigned
ints.
Bill Wendling [Wed, 16 Mar 2022 21:31:09 +0000 (14:31 -0700)]
enetc: use correct format characters
When compiling with -Wformat, clang emits the following warning:
drivers/net/ethernet/freescale/enetc/enetc_mdio.c:151:22: warning:
format specifies type 'unsigned char' but the argument has type 'int'
[-Wformat]
phy_id, dev_addr, regnum);
^~~~~~
./include/linux/dev_printk.h:163:47: note: expanded from macro 'dev_dbg'
dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \
~~~ ^~~~~~~~~~~
./include/linux/dev_printk.h:129:34: note: expanded from macro 'dev_printk'
_dev_printk(level, dev, fmt, ##__VA_ARGS__); \
~~~ ^~~~~~~~~~~
The types of these arguments are unconditionally defined, so this patch
updates the format character to the correct ones for ints and unsigned
ints.
Linus Torvalds [Thu, 17 Mar 2022 19:40:59 +0000 (12:40 -0700)]
Merge tag 'acpi-5.17-rc9' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull ACPI fix from Rafael Wysocki:
"Revert recent commit that caused multiple systems to misbehave due to
firmware issues"
* tag 'acpi-5.17-rc9' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
Revert "ACPI: scan: Do not add device IDs from _CID if _HID is not valid"
net/mlx5: Remove unused exported contiguous coherent buffer allocation API
All WQ types moved to using the fragmented allocation API
for coherent memory. Contiguous API is not used anymore.
Remove it, reduce the number of exported functions.
Paul Blakey [Wed, 23 Feb 2022 13:37:50 +0000 (15:37 +0200)]
net/mlx5: CT: Remove extra rhashtable remove on tuple entries
On tuple offload del command, tuples are tried to be removed twice
from the hashtable, once directly via mlx5_tc_ct_entry_remove_from_tuples()
and a second time in the following mlx5_tc_ct_entry_put()->
mlx5_tc_ct_entry_del()->mlx5_tc_ct_entry_remove_from_tuples() call.
This doesn't cause any issue since rhashtable first checks if the
removed object exists in the hashtable.
Remove the extra mlx5_tc_ct_entry_remove_from_tuples().
Rongwei Liu [Fri, 28 Jan 2022 04:13:07 +0000 (06:13 +0200)]
net/mlx5: DR, Remove num_of_entries byte_size from struct mlx5_dr_icm_chunk
Target to reduce the memory consumption in large scale of flow rules.
They can be calculated quickly from buddy memory pool.
1. num_of_entries calls dr_icm_pool_get_chunk_num_of_entries().
2. byte_size calls dr_icm_pool_get_chunk_byte_size().
Use chunk size in dr_icm_chunk to speed up and the one in dr_ste_htbl
will be removed in the upcoming commit.
This commit reduce 8 bytes from struct mlx5_dr_icm_chunk and its
current size is 56 bytes.
Rongwei Liu [Fri, 28 Jan 2022 04:12:09 +0000 (06:12 +0200)]
net/mlx5: DR, Remove icm_addr from mlx5dr_icm_chunk to reduce memory
It can be calculated quickly from buddy memory pool by
function mlx5dr_icm_pool_get_chunk_icm_addr().
This function is very lightweight and straightforward.
Reduce 8 bytes and current size of struct mlx5_dr_icm_chunk
is 64 bytes.
Rongwei Liu [Fri, 28 Jan 2022 04:10:54 +0000 (06:10 +0200)]
net/mlx5: DR, Remove mr_addr rkey from struct mlx5dr_icm_chunk
Reduce memory footprint by removing mr_addr and rkey from
mlx5_dr_icm_chunk.
1. mr_addr is calculated by mlx5dr_icm_pool_get_chunk_mr_addr()
2. rkey is calculated by mlx5dr_icm_pool_get_chunk_rkey()
The two new functions are very lightweight and straightforward.
Reduce 8 bytes from struct mlx5_dr_icm_chunk, its current size is
72 bytes.
net/mlx5e: Drop cqe_bcnt32 from mlx5e_skb_from_cqe_mpwrq_linear
The packet size in mlx5e_skb_from_cqe_mpwrq_linear can't overflow u16,
since the maximum packet size in linear striding RQ is 2^13 bytes. Drop
the unneeded u32 variable.
net/mlx5e: Drop the len output parameter from mlx5e_xdp_handle
The len parameter of mlx5e_xdp_handle is used to output the new packet
length after XDP has processed the packet and returned XDP_PASS.
However, this value can be calculated on the caller site, as the caller
knows if it was an XDP_PASS.
This commit drops the len parameter and moves the calculation to the
caller, reducing the number of parameters passed to the function and
preparing for XDP support in non-linear legacy RQ.
Tariq Toukan [Wed, 19 Jan 2022 19:28:36 +0000 (21:28 +0200)]
net/mlx5e: RX, Test the XDP program existence out of the handler
Instead of early return inside mlx5e_xdp_handle(), let the caller check
if an XDP program is loaded. This allows saving a few unnecessary
function calls and calculations in case !prog.
Performance test: single core, drop packets in iptables
Before: 3,872,504 pps
After: 3,975,628 pps (+2.66%)
net/mlx5e: Build SKB in place over the first fragment in non-linear legacy RQ
As a performance optimization and preparation to enabling XDP multi
buffer on non-linear legacy RQ, build the linear part of the SKB over
the first fragment, instead of allocating a new buffer and copying the
first 256 bytes there.
To achieve this, add headroom and tailroom to the first fragment.
net/mlx5e: Add headroom only to the first fragment in legacy RQ
Currently, rq->buff.headroom is applied to all fragments in legacy RQ.
In the linear mode, there is a non-zero headroom, but there is only one
fragment per packet. In the non-linear mode, the headroom is zero.
This commit changes the logic to apply the headroom only to the first
fragment. The current behavior remains the same for both linear and
non-linear modes. However, it allows the next commit to enable headroom
for the non-linear mode, which will be applied only to the first
fragment.
net/mlx5e: Validate MTU when building non-linear legacy RQ fragments info
mlx5e_build_rq_frags_info() assumes that MTU is not bigger than
PAGE_SIZE * MLX5E_MAX_RX_FRAGS, which is 16K for 4K pages. Currently,
the firmware limits MTU to 10K, so the assumption doesn't lead to a bug.
This commits adds an additional driver check for reliability, since the
firmware boundary might be changed.
The calculation is taken to a separate function with a comment
explaining it. It's a preparation for the following patches that
introcuce XDP multi buffer support.
Rework to add the header files to LOCAL_HDRS before including ../lib.mk,
since the dependency is evaluated in '$(OUTPUT)/%:%.c $(LOCAL_HDRS)' in
file lib.mk.
Link: https://lkml.kernel.org/r/20220304000645.1888133-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joseph Qi [Wed, 16 Mar 2022 23:15:09 +0000 (16:15 -0700)]
ocfs2: fix crash when initialize filecheck kobj fails
Once s_root is set, genric_shutdown_super() will be called if
fill_super() fails. That means, we will call ocfs2_dismount_volume()
twice in such case, which can lead to kernel crash.
Fix this issue by initializing filecheck kobj before setting s_root.
Link: https://lkml.kernel.org/r/20220310081930.86305-1-joseph.qi@linux.alibaba.com Fixes: 5f483c4abb50 ("ocfs2: add kobject for online file check") Signed-off-by: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Mark Fasheh <mark@fasheh.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Junxiao Bi <junxiao.bi@oracle.com> Cc: Changwei Ge <gechangwei@live.cn> Cc: Gang He <ghe@suse.com> Cc: Jun Piao <piaojun@huawei.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Qian Cai [Wed, 16 Mar 2022 23:15:06 +0000 (16:15 -0700)]
configs/debug: restore DEBUG_INFO=y for overriding
Previously, I failed to realize that Kees' patch [1] has not been merged
into the mainline yet, and dropped DEBUG_INFO=y too eagerly from the
mainline. As the results, "make debug.config" won't be able to flip
DEBUG_INFO=n from the existing .config. This should close the gaps of a
few weeks before Kees' patch is there, and work regardless of their
merging status anyway.
The reason for the livelock is that swapcache_prepare() always returns
EEXIST, indicating that SWAP_HAS_CACHE has not been cleared, so that it
cannot jump out of the loop. We suspect that the task that clears the
SWAP_HAS_CACHE flag never gets a chance to run. We try to lower the
priority of the task stuck in a livelock so that the task that clears
the SWAP_HAS_CACHE flag will run. The results show that the system
returns to normal after the priority is lowered.
In our testing, multiple real-time tasks are bound to the same core, and
the task in the livelock is the highest priority task of the core, so
the livelocked task cannot be preempted.
Although cond_resched() is used by __read_swap_cache_async, it is an
empty function in the preemptive system and cannot achieve the purpose
of releasing the CPU. A high-priority task cannot release the CPU
unless preempted by a higher-priority task. But when this task is
already the highest priority task on this core, other tasks will not be
able to be scheduled. So we think we should replace cond_resched() with
schedule_timeout_uninterruptible(1), schedule_timeout_interruptible will
call set_current_state first to set the task state, so the task will be
removed from the running queue, so as to achieve the purpose of giving
up the CPU and prevent it from running in kernel mode for too long.
(akpm: ugly hack becomes uglier. But it fixes the issue in a
backportable-to-stable fashion while we hopefully work on something
better)
Link: https://lkml.kernel.org/r/20220221111749.1928222-1-cgel.zte@gmail.com Signed-off-by: Guo Ziliang <guo.ziliang@zte.com.cn> Reported-by: Zeal Robot <zealci@zte.com.cn> Reviewed-by: Ran Xiaokai <ran.xiaokai@zte.com.cn> Reviewed-by: Jiang Xuexin <jiang.xuexin@zte.com.cn> Reviewed-by: Yang Yang <yang.yang29@zte.com.cn> Acked-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Roger Quadros <rogerq@kernel.org> Cc: Ziliang Guo <guo.ziliang@zte.com.cn> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ivan Vecera [Thu, 17 Mar 2022 10:45:24 +0000 (11:45 +0100)]
iavf: Fix hang during reboot/shutdown
Recent commit 974578017fc1 ("iavf: Add waiting so the port is
initialized in remove") adds a wait-loop at the beginning of
iavf_remove() to ensure that port initialization is finished
prior unregistering net device. This causes a regression
in reboot/shutdown scenario because in this case callback
iavf_shutdown() is called and this callback detaches the device,
makes it down if it is running and sets its state to __IAVF_REMOVE.
Later shutdown callback of associated PF driver (e.g. ice_shutdown)
is called. That callback calls among other things sriov_disable()
that calls indirectly iavf_remove() (see stack trace below).
As the adapter state is already __IAVF_REMOVE then the mentioned
loop is end-less and shutdown process hangs.
The patch fixes this by checking adapter's state at the beginning
of iavf_remove() and skips the rest of the function if the adapter
is already in remove state (shutdown is in progress).
Reproducer:
1. Create VF on PF driven by ice or i40e driver
2. Ensure that the VF is bound to iavf driver
3. Reboot
Vladimir Oltean [Wed, 16 Mar 2022 19:21:17 +0000 (21:21 +0200)]
net: mscc: ocelot: fix backwards compatibility with single-chain tc-flower offload
ACL rules can be offloaded to VCAP IS2 either through chain 0, or, since
the blamed commit, through a chain index whose number encodes a specific
PAG (Policy Action Group) and lookup number.
The chain number is translated through ocelot_chain_to_pag() into a PAG,
and through ocelot_chain_to_lookup() into a lookup number.
The problem with the blamed commit is that the above 2 functions don't
have special treatment for chain 0. So ocelot_chain_to_pag(0) returns
filter->pag = 224, which is in fact -32, but the "pag" field is an u8.
So we end up programming the hardware with VCAP IS2 entries having a PAG
of 224. But the way in which the PAG works is that it defines a subset
of VCAP IS2 filters which should match on a packet. The default PAG is
0, and previous VCAP IS1 rules (which we offload using 'goto') can
modify it. So basically, we are installing filters with a PAG on which
no packet will ever match. This is the hardware equivalent of adding
filters to a chain which has no 'goto' to it.
Restore the previous functionality by making ACL filters offloaded to
chain 0 go to PAG 0 and lookup number 0. The choice of PAG is clearly
correct, but the choice of lookup number isn't "as before" (which was to
leave the lookup a "don't care"). However, lookup 0 should be fine,
since even though there are ACL actions (policers) which have a
requirement to be used in a specific lookup, that lookup is 0.
Doug Berger [Thu, 17 Mar 2022 01:28:12 +0000 (18:28 -0700)]
net: bcmgenet: skip invalid partial checksums
The RXCHK block will return a partial checksum of 0 if it encounters
a problem while receiving a packet. Since a 1's complement sum can
only produce this result if no bits are set in the received data
stream it is fair to treat it as an invalid partial checksum and
not pass it up the stack.
Fixes: 810155397890 ("net: bcmgenet: use CHECKSUM_COMPLETE for NETIF_F_RXCSUM") Signed-off-by: Doug Berger <opendmb@gmail.com> Acked-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20220317012812.1313196-1-opendmb@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Manish Chopra [Wed, 16 Mar 2022 21:46:13 +0000 (14:46 -0700)]
bnx2x: fix built-in kernel driver load failure
Commit b7a49f73059f ("bnx2x: Utilize firmware 7.13.21.0")
added request_firmware() logic in probe() which caused
load failure when firmware file is not present in initrd (below),
as access to firmware file is not feasible during probe.
Direct firmware load for bnx2x/bnx2x-e2-7.13.15.0.fw failed with error -2
Direct firmware load for bnx2x/bnx2x-e2-7.13.21.0.fw failed with error -2
This patch fixes this issue by -
1. Removing request_firmware() logic from the probe()
such that .ndo_open() handle it as it used to handle
it earlier
2. Given request_firmware() is removed from probe(), so
driver has to relax FW version comparisons a bit against
the already loaded FW version (by some other PFs of same
adapter) to allow different compatible/close enough FWs with which
multiple PFs may run with (in different environments), as the
given PF who is in probe flow has no idea now with which firmware
file version it is going to initialize the device in ndo_open()
Obviously, it makes no sense to check if an unsigned int is >= 0. What
prevents this code from being a forever loop is that later there is a
separate check for if (queue == 0).
The "queue" variable is less than MTL_MAX_RX_QUEUES (8) so it can easily
fit in an int type. Any larger value for "queue" would lead to an array
overflow when we assign "rx_q = &priv->rx_queue[queue]".
Fixes: de0b90e52a11 ("net: stmmac: rearrange RX and TX desc init into per-queue basis") Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Link: https://lore.kernel.org/r/20220316083744.GB30941@kili Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Eyal Birger [Wed, 16 Mar 2022 06:15:57 +0000 (08:15 +0200)]
net: geneve: support IPv4/IPv6 as inner protocol
This patch adds support for encapsulating IPv4/IPv6 within GENEVE.
In order to use this, a new IFLA_GENEVE_INNER_PROTO_INHERIT flag needs
to be provided at device creation. This property cannot be changed for
the time being.
In case IP traffic is received on a non-tun device the drop count is
increased.
Chris Packham [Tue, 15 Mar 2022 21:52:07 +0000 (10:52 +1300)]
net: mvneta: Add support for 98DX2530 Ethernet port
The 98DX2530 SoC is similar to the Armada 3700 except it needs a
different MBUS window configuration. Add a new compatible string to
identify this device and the required MBUS window configuration.
Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The out of band port on the 98DX2530 SoC is similar to the armada-3700
except it requires a slightly different MBUS window configuration. Add a
new compatible string so this difference can be accounted for.
Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Jonathan Lemon [Tue, 15 Mar 2022 19:46:26 +0000 (12:46 -0700)]
ptp: ocp: Fix PTP_PF_* verification requests
Update and check functionality for pin configuration requests:
PTP_PF_NONE: requests "IN: None", disabling the pin.
# testptp -d /dev/ptp3 -L3,0 -i1
set pin function okay
# cat sma4
IN: None
PTP_PF_EXTTS: should configure external timestamps, but since the
timecard can steer inputs to multiple inputs as well as timestamps,
allow the request, but don't change configurations.
# testptp -d /dev/ptp3 -L3,1 -i1
set pin function okay
(no functional or configuration change here yet)
PTP_PF_PEROUT: Channel 0 is the PHC, at 1PPS. Channels 1-4 are
the programmable frequency generators.
# fails because period is not 1PPS.
# testptp -d /dev/ptp3 -L3,2 -i0 -p 500000000
PTP_PEROUT_REQUEST: Invalid argument
====================
flow_offload: add tc vlan push_eth and pop_eth actions
Offloading vlan push_eth and pop_eth actions is needed in order to
correctly offload MPLSoUDP encap and decap flows, this series extends
the flow offload API to support these actions and updates mlx5 to
parse them.
====================
Maor Dickman [Tue, 15 Mar 2022 11:02:11 +0000 (13:02 +0200)]
net/mlx5e: MPLSoUDP encap, support action vlan pop_eth explicitly
Currently the MPLSoUDP encap offload does the L2 pop implicitly
while adding such action explicitly (vlan eth_push) will cause
the rule to not be offloaded.
Solve it by adding offload support for vlan eth_push in case of
MPLSoUDP decap case.
Maor Dickman [Tue, 15 Mar 2022 11:02:10 +0000 (13:02 +0200)]
net/mlx5e: MPLSoUDP decap, use vlan push_eth instead of pedit
Currently action pedit of source and destination MACs is used
to fill the MACs in L2 push step in MPLSoUDP decap offload,
this isn't aligned to tc SW which use vlan eth_push action
to do this.
To fix that, offload support for vlan veth_push action is
added together with mpls pop action, and deprecate the use
of pedit of MACs.
Maor Dickman [Tue, 15 Mar 2022 11:02:09 +0000 (13:02 +0200)]
net/sched: add vlan push_eth and pop_eth action to the hardware IR
Add vlan push_eth and pop_eth action to the hardware intermediate
representation model which would subsequently allow it to be used
by drivers for offload.
Signed-off-by: Maor Dickman <maord@nvidia.com> Reviewed-by: Roi Dayan <roid@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: dsa: Never offload FDB entries on standalone ports
If a port joins a bridge that it can't offload, it will fallback to
standalone mode and software bridging. In this case, we never want to
offload any FDB entries to hardware either.
Previously, for host addresses, we would eventually end up in
dsa_port_bridge_host_fdb_add, which would unconditionally dereference
dp->bridge and cause a segfault.
Fixes: c26933639b54 ("net: dsa: request drivers to perform FDB isolation") Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20220315233033.1468071-1-tobias@waldekranz.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Minghao Chi [Wed, 16 Mar 2022 01:24:44 +0000 (01:24 +0000)]
net: mv643xx_eth: undo some opreations in mv643xx_eth_probe
Cannot directly return platform_get_irq return irq, there
are operations that need to be undone.
Fixes: bf2b83425b59 ("net: mv643xx_eth: use platform_get_irq() instead of platform_get_resource()") Signed-off-by: Minghao Chi <chi.minghao@zte.com.cn> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Link: https://lore.kernel.org/r/20220316012444.2126070-1-chi.minghao@zte.com.cn Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Meng Tang [Tue, 15 Mar 2022 07:48:51 +0000 (15:48 +0800)]
hamradio: Fix wrong assignment of 'bbc->cfg.loopback'
In file hamradio/baycom_epp.c, the baycom_setmode interface, there
is a problem with improper use of strstr.
Suppose that when modestr="noloopback", both conditions which are
'strstr(modestr,"noloopback")' and 'strstr(modestr,"loopback")'
will be true(not NULL), this lead the bc->cfg.loopback variable
will be first assigned to 0, and then reassigned to 1.
This will cause 'bc->cfg.loopback = 0' will never take effect. That
obviously violates the logic of the code, so adjust the order of
their execution to solve the problem.
Hangbin Liu [Tue, 15 Mar 2022 06:26:18 +0000 (14:26 +0800)]
bareudp: use ipv6_mod_enabled to check if IPv6 enabled
bareudp_create_sock() use AF_INET6 by default if IPv6 CONFIG enabled.
But if user start kernel with ipv6.disable=1, the bareudp sock will
created failed, which cause the interface open failed even with ethertype
ip. e.g.
# ip link add bareudp1 type bareudp dstport 2 ethertype ip
# ip link set bareudp1 up
RTNETLINK answers: Address family not supported by protocol
Fix it by using ipv6_mod_enabled() to check if IPv6 enabled. There is
no need to check IS_ENABLED(CONFIG_IPV6) as ipv6_mod_enabled() will
return false when CONFIG_IPV6 no enabled in include/linux/ipv6.h.
Reported-by: Jianlin Shi <jishi@redhat.com> Fixes: 571912c69f0e ("net: UDP tunnel encapsulation module for tunnelling different protocols like MPLS, IP, NSH etc.") Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Link: https://lore.kernel.org/r/20220315062618.156230-1-liuhangbin@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
the first 3 patches are by Oliver Hartkopp target the CAN ISOTP
protocol and fix a problem found by syzbot in isotp_bind(), return
-EADDRNOTAVAIL in unbound sockets in isotp_recvmsg() and add support
for MSG_TRUNC to isotp_recvmsg().
Amit Kumar Mahapatra converts the xilinx,can device tree bindings to
yaml.
The last patch is by Julia Lawall and fixes typos in the ucan driver.
* tag 'linux-can-next-for-5.18-20220316' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next:
can: ucan: fix typos in comments
dt-bindings: can: xilinx_can: Convert Xilinx CAN binding to YAML
can: isotp: support MSG_TRUNC flag when reading from socket
can: isotp: return -EADDRNOTAVAIL when reading from unbound socket
can: isotp: sanitize CAN ID checks in isotp_bind()
====================
Oliver Hartkopp [Wed, 16 Mar 2022 16:42:58 +0000 (17:42 +0100)]
can: isotp: support MSG_TRUNC flag when reading from socket
When providing the MSG_TRUNC flag via recvmsg() syscall the return value
provides the real length of the packet or datagram, even when it was longer
than the passed buffer.
Oliver Hartkopp [Wed, 16 Mar 2022 16:42:57 +0000 (17:42 +0100)]
can: isotp: return -EADDRNOTAVAIL when reading from unbound socket
When reading from an unbound can-isotp socket the syscall blocked
indefinitely. As unbound sockets (without given CAN address information)
do not make sense anyway we directly return -EADDRNOTAVAIL on read()
analogue to the known behavior from sendmsg().
Oliver Hartkopp [Wed, 16 Mar 2022 16:42:56 +0000 (17:42 +0100)]
can: isotp: sanitize CAN ID checks in isotp_bind()
Syzbot created an environment that lead to a state machine status that
can not be reached with a compliant CAN ID address configuration.
The provided address information consisted of CAN ID 0x6000001 and 0xC28001
which both boil down to 11 bit CAN IDs 0x001 in sending and receiving.
Sanitize the SFF/EFF CAN ID values before performing the address checks.
Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol") Link: https://lore.kernel.org/all/20220316164258.54155-1-socketcan@hartkopp.net Reported-by: syzbot+2339c27f5c66c652843e@syzkaller.appspotmail.com Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
====================
devlink: expose instance locking and simplify port splitting
This series puts the devlink ports fully under the devlink instance
lock's protection. As discussed in the past it implements my preferred
solution of exposing the instance lock to the drivers. This way drivers
which want to support port splitting can lock the devlink instance
themselves on the probe path, and we can take that lock in the core
on the split/unsplit paths.
nfp and mlxsw are converted, with slightly deeper changes done in
nfp since I'm more familiar with that driver.
Now that the devlink port is protected we can pass a pointer to
the drivers, instead of passing a port index and forcing the drivers
to do their own lookups. Both nfp and mlxsw can container_of() to
their own structures.
====================
Jakub Kicinski [Tue, 15 Mar 2022 06:00:09 +0000 (23:00 -0700)]
devlink: pass devlink_port to port_split / port_unsplit callbacks
Now that devlink ports are protected by the instance lock
it seems natural to pass devlink_port as an argument to
the port_split / port_unsplit callbacks.
This should save the drivers from doing a lookup.
In theory drivers may have supported unsplitting ports
which were not registered prior to this change.
Jakub Kicinski [Tue, 15 Mar 2022 06:00:06 +0000 (23:00 -0700)]
eth: nfp: replace driver's "pf" lock with devlink instance lock
The whole reason for existence of the pf mutex is that we could
not lock the devlink instance around port splitting. There are
more types of reconfig which can make ports appear or disappear.
Now that the devlink instance lock is exposed to drivers and
"locked" helpers exist we can switch to using the devlink lock
directly.
Next patches will move the locking inside .port_(un)split to
the core.
Jakub Kicinski [Tue, 15 Mar 2022 06:00:05 +0000 (23:00 -0700)]
eth: nfp: wrap locking assertions in helpers
We can replace the PF lock with devlink instance lock in subsequent
changes. To make the patches easier to comprehend and limit line
lengths - factor out the existing locking assertions.
Jakub Kicinski [Tue, 15 Mar 2022 06:00:04 +0000 (23:00 -0700)]
devlink: expose instance locking and add locked port registering
It should be familiar and beneficial to expose devlink instance
lock to the drivers. This way drivers can block devlink from
calling them during critical sections without breakneck locking.
Add port helpers, port splitting callbacks will be the first
target.
Use 'devl_' prefix for "explicitly locked" API. Initial RFC used
'__devlink' but that's too much typing.
devl_lock_is_held() is not defined without lockdep, which is
the same behavior as lockdep_is_held() itself.
Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>