TCP ZC Rx requires data to be placed neatly into pages, separate
from the networking headers. This is not supported by most devices
so to make deployment easy this set adds a way for the driver to
report support for this feature thru ethtool.
The larger scope of configuring splitting headers and data, or DMA
scatter seems dauntingly broad, so this set focuses specifically
on the question "is this device usable with TCP ZC Rx?".
The aim is to avoid a litany of conditions on HW platforms, features,
and firmware versions in orchestration systems when the drivers can
easily tell their SG config.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Thu, 27 Jan 2022 18:42:59 +0000 (10:42 -0800)]
ethtool: add header/data split indication
For applications running on a mix of platforms it's useful
to have a clear indication whether host's NIC supports the
geometry requirements of TCP zero-copy. TCP zero-copy Rx
requires data to be neatly placed into memory pages.
Most NICs can't do that.
This patch is adding GET support only, since the NICs
I work with either always have the feature enabled or
enable it whenever MTU is set to jumbo. In other words
I don't need SET. But adding set should be trivial.
(The only note on SET is that we will likely want
the setting to be "sticky" and use 0 / `unknown`
to reset it back to driver default.)
Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
The reference clock output from the KSZ9477 and related Microchip
switch devices is not required on all board designs. Add a device
tree property to disable it for power and EMI reasons.
Changes since v3:
-rework some code for simplicity
Changes since v2:
-check for conflicting options in DT, added note in bindings doc
Changes since v1:
-added Acked-by on patch 1, rebase to net-next
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Robert Hancock [Thu, 27 Jan 2022 16:41:56 +0000 (10:41 -0600)]
net: dsa: microchip: Add property to disable reference clock
Add a new microchip,synclko-disable property which can be specified
to disable the reference clock output from the device if not required
by the board design.
Signed-off-by: Robert Hancock <robert.hancock@calian.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Robert Hancock [Thu, 27 Jan 2022 16:41:55 +0000 (10:41 -0600)]
net: dsa: microchip: Document property to disable reference clock
Document the new microchip,synclko-disable property which can be
specified to disable the reference clock output from the device if not
required by the board design.
Signed-off-by: Robert Hancock <robert.hancock@calian.com> Acked-by: Rob Herring <robh@kernel.org> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Lorenzo Bianconi [Thu, 27 Jan 2022 14:47:49 +0000 (15:47 +0100)]
net: mvneta: remove unnecessary if condition in mvneta_xdp_submit_frame
Get rid of unnecessary if check on tx_desc pointer in
mvneta_xdp_submit_frame routine since num_frames is always greater than
0 and tx_desc pointer is always initialized.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Convert sparx5 to use the mac_select_interface rather than using
phylink_set_pcs(). The intention here is to unify the approach for
PCS and eventually remove phylink_set_pcs().
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Fri, 28 Jan 2022 03:46:13 +0000 (19:46 -0800)]
Merge branch 'udp-ipv6-optimisations'
Pavel Begunkov says:
====================
udp/ipv6 optimisations
Shed some weight from udp/ipv6. Zerocopy benchmarks over dummy showed
~5% tx/s improvement, should be similar for small payload non-zc
cases.
The performance comes from killing 4 atomics and a couple of big struct
memcpy/memset. 1/10 removes a pair of atomics on dst refcounting for
cork->skb setup, 9/10 saves another pair on cork init. 5/10 and 8/10
kill extra 88B memset and memcpy respectively.
====================
Pavel Begunkov [Thu, 27 Jan 2022 00:36:31 +0000 (00:36 +0000)]
ipv6: partially inline ipv6_fixup_options
Inline a part of ipv6_fixup_options() to avoid extra overhead on
function call if opt is NULL.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:30 +0000 (00:36 +0000)]
ipv6: optimise dst refcounting on cork init
udpv6_sendmsg() doesn't need dst after calling ip6_make_skb(), so
instead of taking an additional reference inside ip6_setup_cork()
and releasing the initial one afterwards, we can hand over a reference
into ip6_make_skb() saving two atomics. The only other user of
ip6_setup_cork() is ip6_append_data() and it requires an extra
dst_hold().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:29 +0000 (00:36 +0000)]
udp6: don't make extra copies of iflow
udpv6_sendmsg() first initialises an on-stack 88B struct flowi6 and then
copies it into cork, which is expensive. Avoid the copy in corkless case
by initialising on-stack cork->fl directly.
The main part is a couple of lines under !corkreq check. The rest
converts fl6 variable to be a pointer.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:28 +0000 (00:36 +0000)]
udp6: pass flow in ip6_make_skb together with cork
Another preparation patch. inet_cork_full already contains a field for
iflow, so we can avoid passing a separate struct iflow6 into
__ip6_append_data() and ip6_make_skb(), and use the flow stored in
inet_cork_full. Make sure callers set cork->fl, i.e. we init it in
ip6_append_data() and before calling ip6_make_skb().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:27 +0000 (00:36 +0000)]
ipv6: pass full cork into __ip6_append_data()
Convert a struct inet_cork argument in __ip6_append_data() to struct
inet_cork_full. As one struct contains another inet_cork is still can
be accessed via ->base field. It's a preparation patch making further
changes a bit cleaner.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:26 +0000 (00:36 +0000)]
ipv6: don't zero inet_cork_full::fl after use
It doesn't appear there is any reason for ip6_cork_release() to zero
cork->fl, it'll be fully filled on next initialisation. This 88 bytes
memset accounts to 0.3-0.5% of total CPU cycles.
It's also needed in following patches and allows to remove an extar flow
copy in udp_v6_push_pending_frames().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:25 +0000 (00:36 +0000)]
ipv6: clean up cork setup/release
Clean up ip6_setup_cork() and ip6_cork_release() adding a local variable
for v6_cork->opt. It's a preparation patch for further changes.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:24 +0000 (00:36 +0000)]
ipv6: remove daddr temp buffer in __ip6_make_skb
ipv6_push_nfrag_opts() doesn't change passed daddr, and so
__ip6_make_skb() doesn't actually need to keep an on-stack copy of
fl6->daddr. Set initially final_dst to fl6->daddr,
ipv6_push_nfrag_opts() will override it if needed, and get rid of extra
copies.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:23 +0000 (00:36 +0000)]
udp6: shuffle up->pending AF_INET bits
Corked AF_INET for ipv6 socket doesn't appear to be the hottest case,
so move it out of the common path under up->pending check to remove
overhead.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pavel Begunkov [Thu, 27 Jan 2022 00:36:22 +0000 (00:36 +0000)]
ipv6: optimise dst refcounting on skb init
__ip6_make_skb() gets a cork->dst ref, hands it over to skb and shortly
after puts cork->dst. Save two atomics by stealing it without extra
referencing, ip6_cork_release() handles NULL cork->dst.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Ido Schimmel [Thu, 27 Jan 2022 09:02:26 +0000 (11:02 +0200)]
mlxsw: spectrum_acl: Allocate default actions for internal TCAM regions
In Spectrum-2 and later ASICs, each TCAM region has a default action
that is executed in case a packet did not match any rule in the region.
The location of the action in the database (KVDL) is computed by adding
the region's index to a base value.
Some TCAM regions are not exposed to the host and used internally by the
device. Allocate KVDL entries for the default actions of these regions
to avoid the host from overwriting them.
With mlxsw, lookups in the internal regions are not currently performed,
but it is a good practice not to overwrite their default actions.
Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Amit Cohen [Thu, 27 Jan 2022 09:02:25 +0000 (11:02 +0200)]
mlxsw: spectrum: Guard against invalid local ports
When processing events generated by the device's firmware, the driver
protects itself from events reported for non-existent local ports, but
not for the CPU port (local port 0), which exists, but does not have all
the fields as any local port.
This can result in a NULL pointer dereference when trying access
'struct mlxsw_sp_port' fields which are not initialized for CPU port.
Commit 63b08b1f6834 ("mlxsw: spectrum: Protect driver from buggy firmware")
already handled such issue by bailing early when processing a PUDE event
reported for the CPU port.
Generalize the approach by moving the check to a common function and
making use of it in all relevant places.
Signed-off-by: Amit Cohen <amcohen@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jiri Pirko [Thu, 27 Jan 2022 09:02:24 +0000 (11:02 +0200)]
mlxsw: core: Consolidate trap groups to a single event group
For event traps which are used in core, avoid having a separate trap
group for each event. Instead of that introduce a single core event trap
group and use it for all event traps.
Jiri Pirko [Thu, 27 Jan 2022 09:02:23 +0000 (11:02 +0200)]
mlxsw: core: Move functions to register/unregister array of traps to core.c
These functions belong to core.c alongside the functions that
register/unregister a single trap. Move it there. Make the functions
possibly usable by other parts of mlxsw code.
Signed-off-by: Jiri Pirko <jiri@nvidia.com> Reviewed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jakub Kicinski [Fri, 28 Jan 2022 03:10:25 +0000 (19:10 -0800)]
Merge tag 'mlx5-updates-2022-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2022-01-27
1) Dima, adds an internal mlx5 steering callback per steering provider
(FW vs SW steering), to advertise steering capabilities implemented by
each module, this helps upper modules in mlx5 to know what is
supported and what's not without the need to tell what is the underlying
steering mode.
2nd patch is the usecase where this interface is used to implement
Vlan Push/pop for uplink with SW steering, where in FW mode it's not
supported yet.
2) Roi Dayan improves code readability and maintainability
as preparation step for multi attribute instance per flow
in mlx5 TC module
Currently the mlx5_flow object contains a single mlx5_attr instance.
However, multi table actions (e.g. CT) instantiate multiple attr instances.
This is a refactoring series in a preparation to support multiple
attribute instances per flow.
The commits prepare functions to get attr instance instead of using
flow->attr and also using attr->flags if the flag is more relevant
to be attr flag and not a flow flag considering there will be multiple
attr instances. i.e. CT and SAMPLE flags.
* tag 'mlx5-updates-2022-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
net/mlx5: VLAN push on RX, pop on TX
net/mlx5: Introduce software defined steering capabilities
net/mlx5: Remove unused TIR modify bitmask enums
net/mlx5e: CT, Remove redundant flow args from tc ct calls
net/mlx5e: TC, Store mapped tunnel id on flow attr
net/mlx5e: Test CT and SAMPLE on flow attr
net/mlx5e: Refactor eswitch attr flags to just attr flags
net/mlx5e: CT, Don't set flow flag CT for ct clear flow
net/mlx5e: TC, Hold sample_attr on stack instead of pointer
net/mlx5e: TC, Reject rules with multiple CT actions
net/mlx5e: TC, Refactor mlx5e_tc_add_flow_mod_hdr() to get flow attr
net/mlx5e: TC, Pass attr to tc_act can_offload()
net/mlx5e: TC, Split pedit offloads verify from alloc_tc_pedit_action()
net/mlx5e: TC, Move pedit_headers_action to parse_attr
net/mlx5e: Move counter creation call to alloc_flow_attr_counter()
net/mlx5e: Pass attr arg for attaching/detaching encaps
net/mlx5e: Move code chunk setting encap dests into its own function
====================
Dima Chumak [Mon, 13 Dec 2021 11:21:46 +0000 (13:21 +0200)]
net/mlx5: VLAN push on RX, pop on TX
Some older NIC hardware isn't capable of doing VLAN push on RX and pop
on TX.
A workaround has been added in software to support it, but it has a
performance penalty since it requires a hairpin + loopback.
There's no such limitation with the newer NICs, so no need to pay the
price of the w/a. With this change the software w/a is disabled for
certain HW versions and steering modes that support it.
Dima Chumak [Sun, 21 Nov 2021 21:45:12 +0000 (23:45 +0200)]
net/mlx5: Introduce software defined steering capabilities
There are two different internal steering modes, abstracted from the
rest of the driver. In order to keep upper layer of the driver agnostic
to the differences in capabilities of the steering modes, this patch
introduces mlx5_fs_get_capabilities() API to check if a certain software
defined capability is supported. It differs from the capabilities
exposed by the hardware, as it takes into account the flow steering mode
(SMFS/DMFS) currently enabled.
This implementation supports only two capability flags:
They map to DR_ACTION_STATE_PUSH_VLAN and DR_ACTION_STATE_POP_VLAN
actions, implemented in SW steering earlier in commit f5e22be534e0
("net/mlx5: DR, Split modify VLAN state to separate pop/push states").
Which enables using of pop/push vlan without restrictions, e.g. doing
vlan pop on TX and RX, compared to FW steering that supports only vlan
pop on RX and push on TX.
Roi Dayan [Wed, 15 Dec 2021 13:37:27 +0000 (15:37 +0200)]
net/mlx5e: Test CT and SAMPLE on flow attr
Currently the mlx5_flow object contains a single mlx5_attr instance.
However, multi table actions (e.g. CT) instantiate multiple attr instances.
Prepare for multiple attr instances by testing for CT or SAMPLE flag on attr
flags instead of flow flag.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Reviewed-by: Chris Mi <cmi@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Sun, 19 Dec 2021 09:31:01 +0000 (11:31 +0200)]
net/mlx5e: Refactor eswitch attr flags to just attr flags
The flags are flow attrs and not esw specific attr flags.
Refactor to remove the esw prefix and move from eswitch.h
to en_tc.h where struct mlx5_flow_attr exists.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Reviewed-by: Vlad Buslov <vladbu@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Wed, 15 Dec 2021 08:48:36 +0000 (10:48 +0200)]
net/mlx5e: CT, Don't set flow flag CT for ct clear flow
ct clear action is a normal flow with a modify header for registers to
0. there is no need for any special handling in tc_ct.c.
Parsing of ct clear action still allocates mod acts to set 0 on the
registers and the driver continue to add a normal rule with modify hdr
context.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Sun, 5 Dec 2021 13:10:35 +0000 (15:10 +0200)]
net/mlx5e: TC, Hold sample_attr on stack instead of pointer
In later commit we are going to instantiate multiple attr instances
for flow instead of single attr.
Parsing TC sample allocates a new memory but there is no symmetric
cleanup in the infrastructure.
To avoid asymmetric alloc/free use sample_attr as part of the flow attr
and not allocated and held as a pointer.
This will avoid a cleanup leak when sample action is not on the first
attr.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Thu, 25 Nov 2021 12:32:58 +0000 (14:32 +0200)]
net/mlx5e: TC, Refactor mlx5e_tc_add_flow_mod_hdr() to get flow attr
In later commit we are going to instantiate multiple attr instances
for flow instead of single attr.
Make sure mlx5e_tc_add_flow_mod_hdr() use the correct attr and not flow->attr.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Wed, 24 Nov 2021 12:31:46 +0000 (14:31 +0200)]
net/mlx5e: TC, Pass attr to tc_act can_offload()
In later commit we are going to instantiate multiple attr instances
for flow instead of single attr.
Make sure the parsing using correct attr and not flow->attr.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Wed, 10 Nov 2021 13:14:45 +0000 (15:14 +0200)]
net/mlx5e: TC, Move pedit_headers_action to parse_attr
Move pedit_headers_action from flow parse_state to flow parse_attr.
In a follow up commit we are going to have multiple attr per flow
and pedit_headers_action are unique per attr.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Reviewed-by: Maor Dickman <maord@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Sun, 10 Oct 2021 11:03:12 +0000 (14:03 +0300)]
net/mlx5e: Pass attr arg for attaching/detaching encaps
In later commit that we will have multiple attr instances per flow
we would like to pass a specific attr instance to set encaps.
Currently the mlx5_flow object contains a single mlx5_attr instance.
However, multi table actions (e.g. CT) instantiate multiple attr instances.
Currently mlx5e_attach/detach_encap() reads the first attr instance
from the flow instance. Modify the functions to receive the attr
instance as a parameter which is set by the calling function.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Thu, 23 Sep 2021 06:43:06 +0000 (09:43 +0300)]
net/mlx5e: Move code chunk setting encap dests into its own function
Split setting encap dests code chunk out of mlx5e_tc_add_fdb_flow()
to make the function smaller for maintainability and reuse.
For symmetry do the same for mlx5e_tc_del_fdb_flow().
While at it refactor cleanup to first check for encap flag like
done when setting encap dests.
Signed-off-by: Roi Dayan <roid@nvidia.com> Reviewed-by: Oz Shlomo <ozsh@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Linus Torvalds [Thu, 27 Jan 2022 18:58:39 +0000 (20:58 +0200)]
Merge tag 'net-5.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter and can.
Current release - new code bugs:
- tcp: add a missing sk_defer_free_flush() in tcp_splice_read()
- tcp: add a stub for sk_defer_free_flush(), fix CONFIG_INET=n
- nf_tables: set last expression in register tracking area
- nft_connlimit: fix memleak if nf_ct_netns_get() fails
- mptcp: fix removing ids bitmap setting
- bonding: use rcu_dereference_rtnl when getting active slave
- fix three cases of sleep in atomic context in drivers: lan966x, gve
- handful of build fixes for esoteric drivers after netdev->dev_addr
was made const
Previous releases - regressions:
- revert "ipv6: Honor all IPv6 PIO Valid Lifetime values", it broke
Linux compatibility with USGv6 tests
- procfs: show net device bound packet types
- ipv4: fix ip option filtering for locally generated fragments
- phy: broadcom: hook up soft_reset for BCM54616S
Previous releases - always broken:
- ipv4: raw: lock the socket in raw_bind()
- ipv4: decrease the use of shared IPID generator to decrease the
chance of attackers guessing the values
- procfs: fix cross-netns information leakage in /proc/net/ptype
- ethtool: fix link extended state for big endian
- bridge: vlan: fix single net device option dumping
- ping: fix the sk_bound_dev_if match in ping_lookup"
* tag 'net-5.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (86 commits)
net: bridge: vlan: fix memory leak in __allowed_ingress
net: socket: rename SKB_DROP_REASON_SOCKET_FILTER
ipv4: remove sparse error in ip_neigh_gw4()
ipv4: avoid using shared IP generator for connected sockets
ipv4: tcp: send zero IPID in SYNACK messages
ipv4: raw: lock the socket in raw_bind()
MAINTAINERS: add missing IPv4/IPv6 header paths
MAINTAINERS: add more files to eth PHY
net: stmmac: dwmac-sun8i: use return val of readl_poll_timeout()
net: bridge: vlan: fix single net device option dumping
net: stmmac: skip only stmmac_ptp_register when resume from suspend
net: stmmac: configure PTP clock source prior to PTP initialization
Revert "ipv6: Honor all IPv6 PIO Valid Lifetime values"
connector/cn_proc: Use task_is_in_init_pid_ns()
pid: Introduce helper task_is_in_init_pid_ns()
gve: Fix GFP flags when allocing pages
net: lan966x: Fix sleep in atomic context when updating MAC table
net: lan966x: Fix sleep in atomic context when injecting frames
ethernet: seeq/ether3: don't write directly to netdev->dev_addr
ethernet: 8390/etherh: don't write directly to netdev->dev_addr
...
Tim Yi [Thu, 27 Jan 2022 07:49:53 +0000 (15:49 +0800)]
net: bridge: vlan: fix memory leak in __allowed_ingress
When using per-vlan state, if vlan snooping and stats are disabled,
untagged or priority-tagged ingress frame will go to check pvid state.
If the port state is forwarding and the pvid state is not
learning/forwarding, untagged or priority-tagged frame will be dropped
but skb memory is not freed.
Should free skb when __allowed_ingress returns false.
Fixes: a580c76d534c ("net: bridge: vlan: add per-vlan state") Signed-off-by: Tim Yi <tim.yi@pica8.com> Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com> Link: https://lore.kernel.org/r/20220127074953.12632-1-tim.yi@pica8.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
So, if dma_set_mask_and_coherent() succeeds, 'pci_using_dac' is known to be
1.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
So, if dma_set_mask_and_coherent() succeeds, 'pci_using_dac' is known to be
1.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Tested-by: Gurucharan G <gurucharanx.g@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
So, if dma_set_mask_and_coherent() succeeds, 'pci_using_dac' is known to be
1.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
So, if dma_set_mask_and_coherent() succeeds, 'pci_using_dac' is known to be
1.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
So, if dma_set_mask_and_coherent() succeeds, 'pci_using_dac' is known to be
1.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
So, if dma_set_mask_and_coherent() succeeds, 'pci_using_dac' is known to be
1.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
As stated in [1], dma_set_mask() with a 64-bit mask never fails if
dev->dma_mask is non-NULL.
So, if it fails, the 32 bits case will also fail for the same reason.
So, if dma_set_mask_and_coherent() succeeds, 'pci_using_dac' is known to be
1.
Simplify code and remove some dead code accordingly.
[1]: https://lkml.org/lkml/2021/6/7/398
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Menglong Dong [Thu, 27 Jan 2022 09:13:01 +0000 (17:13 +0800)]
net: socket: rename SKB_DROP_REASON_SOCKET_FILTER
Rename SKB_DROP_REASON_SOCKET_FILTER, which is used
as the reason of skb drop out of socket filter before
it's part of a released kernel. It will be used for
more protocols than just TCP in future series.
Eric Dumazet [Thu, 27 Jan 2022 01:34:04 +0000 (17:34 -0800)]
ipv4: remove sparse error in ip_neigh_gw4()
./include/net/route.h:373:48: warning: incorrect type in argument 2 (different base types)
./include/net/route.h:373:48: expected unsigned int [usertype] key
./include/net/route.h:373:48: got restricted __be32 [usertype] daddr
Fixes: 5c9f7c1dfc2e ("ipv4: Add helpers for neigh lookup for nexthop") Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://lore.kernel.org/r/20220127013404.1279313-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
====================
ipv4: less uses of shared IP generator
From: Eric Dumazet <edumazet@google.com>
We keep receiving research reports based on linux IPID generation.
Before breaking part of the Internet by switching to pure
random generator, this series reduces the need for the
shared IP generator for TCP sockets.
====================
Eric Dumazet [Thu, 27 Jan 2022 01:10:22 +0000 (17:10 -0800)]
ipv4: avoid using shared IP generator for connected sockets
ip_select_ident_segs() has been very conservative about using
the connected socket private generator only for packets with IP_DF
set, claiming it was needed for some VJ compression implementations.
As mentioned in this referenced document, this can be abused.
(Ref: Off-Path TCP Exploits of the Mixed IPID Assignment)
Before switching to pure random IPID generation and possibly hurt
some workloads, lets use the private inet socket generator.
Not only this will remove one vulnerability, this will also
improve performance of TCP flows using pmtudisc==IP_PMTUDISC_DONT
Fixes: 73f156a6e8c1 ("inetpeer: get rid of ip_id_count") Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@kernel.org> Reported-by: Ray Che <xijiache@gmail.com> Cc: Willy Tarreau <w@1wt.eu> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Eric Dumazet [Thu, 27 Jan 2022 01:10:21 +0000 (17:10 -0800)]
ipv4: tcp: send zero IPID in SYNACK messages
In commit 431280eebed9 ("ipv4: tcp: send zero IPID for RST and
ACK sent in SYN-RECV and TIME-WAIT state") we took care of some
ctl packets sent by TCP.
It turns out we need to use a similar strategy for SYNACK packets.
By default, they carry IP_DF and IPID==0, but there are ways
to ask them to use the hashed IP ident generator and thus
be used to build off-path attacks.
(Ref: Off-Path TCP Exploits of the Mixed IPID Assignment)
One of this way is to force (before listener is started)
echo 1 >/proc/sys/net/ipv4/ip_no_pmtu_disc
Another way is using forged ICMP ICMP_FRAG_NEEDED
with a very small MTU (like 68) to force a false return from
ip_dont_fragment()
In this patch, ip_build_and_send_pkt() uses the following
heuristics.
1) Most SYNACK packets are smaller than IPV4_MIN_MTU and therefore
can use IP_DF regardless of the listener or route pmtu setting.
2) In case the SYNACK packet is bigger than IPV4_MIN_MTU,
we use prandom_u32() generator instead of the IPv4 hashed ident one.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Ray Che <xijiache@gmail.com> Reviewed-by: David Ahern <dsahern@kernel.org> Cc: Geoff Alexander <alexandg@cs.unm.edu> Cc: Willy Tarreau <w@1wt.eu> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Mathias Krause [Thu, 27 Jan 2022 08:34:19 +0000 (18:34 +1000)]
drm/vmwgfx: Fix stale file descriptors on failed usercopy
A failing usercopy of the fence_rep object will lead to a stale entry in
the file descriptor table as put_unused_fd() won't release it. This
enables userland to refer to a dangling 'file' object through that still
valid file descriptor, leading to all kinds of use-after-free
exploitation scenarios.
Fix this by deferring the call to fd_install() until after the usercopy
has succeeded.
Eric Dumazet [Thu, 27 Jan 2022 00:51:16 +0000 (16:51 -0800)]
ipv4: raw: lock the socket in raw_bind()
For some reason, raw_bind() forgot to lock the socket.
BUG: KCSAN: data-race in __ip4_datagram_connect / raw_bind
write to 0xffff8881170d4308 of 4 bytes by task 5466 on cpu 0:
raw_bind+0x1b0/0x250 net/ipv4/raw.c:739
inet_bind+0x56/0xa0 net/ipv4/af_inet.c:443
__sys_bind+0x14b/0x1b0 net/socket.c:1697
__do_sys_bind net/socket.c:1708 [inline]
__se_sys_bind net/socket.c:1706 [inline]
__x64_sys_bind+0x3d/0x50 net/socket.c:1706
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff8881170d4308 of 4 bytes by task 5468 on cpu 1:
__ip4_datagram_connect+0xb7/0x7b0 net/ipv4/datagram.c:39
ip4_datagram_connect+0x2a/0x40 net/ipv4/datagram.c:89
inet_dgram_connect+0x107/0x190 net/ipv4/af_inet.c:576
__sys_connect_file net/socket.c:1900 [inline]
__sys_connect+0x197/0x1b0 net/socket.c:1917
__do_sys_connect net/socket.c:1927 [inline]
__se_sys_connect net/socket.c:1924 [inline]
__x64_sys_connect+0x3d/0x50 net/socket.c:1924
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x00000000 -> 0x0003007f
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 5468 Comm: syz-executor.5 Not tainted 5.17.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Yang Guang [Thu, 27 Jan 2022 00:02:36 +0000 (08:02 +0800)]
ptp: replace snprintf with sysfs_emit
coccinelle report:
./drivers/ptp/ptp_sysfs.c:17:8-16:
WARNING: use scnprintf or sprintf
./drivers/ptp/ptp_sysfs.c:390:8-16:
WARNING: use scnprintf or sprintf
Use sysfs_emit instead of scnprintf or sprintf makes more sense.
Reported-by: Zeal Robot <zealci@zte.com.cn> Signed-off-by: Yang Guang <yang.guang5@zte.com.cn> Signed-off-by: David Yang <davidcomponentone@gmail.com> Acked-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Wed, 26 Jan 2022 19:49:59 +0000 (20:49 +0100)]
r8169: enable ASPM L1.2 if system vendor flags it as safe
On some systems there are compatibility issues with ASPM L1.2 and
RTL8125, therefore this state is disabled per default. To allow for
the L1.2 power saving on not affected systems, Realtek provides
vendors that successfully tested ASPM L1.2 the option to flag this
state as safe. According to Realtek this flag will be set first on
certain Chromebox devices.
Suggested-by: Chun-Hao Lin <hau@realtek.com> Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 27 Jan 2022 13:53:27 +0000 (13:53 +0000)]
Merge branch 'static-inlines'
Jakub Kicinski says:
====================
net: get rid of unused static inlines
I noticed a couple of unused static inline functions reviewing
net/sched patches so I run a grep thru all of include/ and net/
to catch other cases. This set removes the cases which look like
obvious dead code.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Wed, 26 Jan 2022 19:10:56 +0000 (11:10 -0800)]
nfc: use *_set_vendor_cmds() helpers
NCI and HCI wrappers for nfc_set_vendor_cmds() exist,
use them. We could also remove the helpers.
It's a coin toss.
Signed-off-by: Jakub Kicinski <kuba@kernel.org> Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jisheng Zhang [Wed, 26 Jan 2022 16:52:15 +0000 (00:52 +0800)]
net: stmmac: dwmac-sun8i: use return val of readl_poll_timeout()
When readl_poll_timeout() timeout, we'd better directly use its return
value.
Before this patch:
[ 2.145528] dwmac-sun8i: probe of 4500000.ethernet failed with error -14
After this patch:
[ 2.138520] dwmac-sun8i: probe of 4500000.ethernet failed with error -110
Signed-off-by: Jisheng Zhang <jszhang@kernel.org> Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Robin Murphy [Wed, 26 Jan 2022 16:30:33 +0000 (16:30 +0000)]
nfp: Simplify array allocation
Prefer kcalloc() to kzalloc(array_size()) for allocating an array.
Signed-off-by: Robin Murphy <robin.murphy@arm.com> Acked-by: Simon Horman <simon.horman@corigine.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: bridge: vlan: fix single net device option dumping
When dumping vlan options for a single net device we send the same
entries infinitely because user-space expects a 0 return at the end but
we keep returning skb->len and restarting the dump on retry. Fix it by
returning the value from br_vlan_dump_dev() if it completed or there was
an error. The only case that must return skb->len is when the dump was
incomplete and needs to continue (-EMSGSIZE).
Reported-by: Benjamin Poirier <bpoirier@nvidia.com> Fixes: 8dcea187088b ("net: bridge: vlan: add rtm definitions and dump support") Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 27 Jan 2022 13:46:18 +0000 (13:46 +0000)]
Merge branch 'stmmac-ptp-fix'
Mohammad Athari Bin Ismail says:
====================
Fix PTP issue in stmmac
This patch series to fix PTP issue in stmmac related to:
1/ PTP clock source configuration during initialization.
2/ PTP initialization during resume from suspend.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
net: stmmac: skip only stmmac_ptp_register when resume from suspend
When resume from suspend, besides skipping PTP registration, it also
skipping PTP HW initialization. This could cause PTP clock not able to
operate properly when resume from suspend.
To fix this, only stmmac_ptp_register() is skipped when resume from
suspend.
Fixes: fe1319291150 ("stmmac: Don't init ptp again when resume from suspend/hibernation") Cc: <stable@vger.kernel.org> # 5.15.x Signed-off-by: Mohammad Athari Bin Ismail <mohammad.athari.ismail@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: stmmac: configure PTP clock source prior to PTP initialization
For Intel platform, it is required to configure PTP clock source prior PTP
initialization in MAC. So, need to move ptp_clk_freq_config execution from
stmmac_ptp_register() to stmmac_init_ptp().
Fixes: 76da35dc99af ("stmmac: intel: Add PSE and PCH PTP clock source selection") Cc: <stable@vger.kernel.org> # 5.15.x Signed-off-by: Mohammad Athari Bin Ismail <mohammad.athari.ismail@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
net/fsl: xgmac_mdio: Preamble suppression and custom MDC frequencies
The first patch removes the docs for a binding that has never been
supported by the driver as far as I can see. This is a bit of a
mystery to me, maybe Freescale/NXP had/has support for it in an
internal version?
We then start working on the xgmac_mdio driver, converting the driver
to exclusively use managed resources, thereby simplifying the error
paths. Suggested by Andrew.
Preamble suppression is then added, followed by MDC frequency
customization. Neither code will change any bits if the corresponding
dt properties are not specified, so as to not trample on any setup
done by the bootloader, which boards might have relied on up to now.
Finally, we document the new bindings.
Tested on a T1023 based board.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
dt-bindings: net: xgmac_mdio: Add "clock-frequency" and "suppress-preamble"
The driver now supports the standard "clock-frequency" and
"suppress-preamble" properties, do document them in the binding
description.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / kernel.git / log