In certain configurations without power management support, gcc report
the following warning:
drivers/net/ethernet/sun/cassini.c:5206:12: warning:
'cas_resume' defined but not used [-Wunused-function]
5206 | static int cas_resume(struct device *dev_d)
| ^~~~~~~~~~
Mark cas_resume() as __maybe_unused to make it clear.
Fixes: f193f4ebde ("sun/cassini: use generic power management")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The upgraded .suspend() and .resume() throw
"defined but not used [-Wunused-function]" warning for certain
configurations.
Mark them with "__maybe_unused" attribute.
Compile-tested only.
Fixes: b0db0cc2f6 ("sun/niu: use generic power management")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To ensure that the octeon MDIO driver has been loaded, the Cavium
ethernet drivers reference a dummy symbol in the MDIO driver. This
forces it to be loaded first. And this symbol has not been cleanly
implemented, resulting in warnings when build W=1 C=1.
Since device tree is being used, and a phandle points to the PHY on
the MDIO bus, we can make use of deferred probing. If the PHY fails to
connect, it should be because the MDIO bus driver has not loaded
yet. Return -EPROBE_DEFER so it will be tried again later.
Additionally, add a MODULE_SOFTDEP() to give user space a hint as to
what order it should load the modules.
v2:
s/octoen/octeon/
Add MODULE_SOFTDEP()
Cc: Sunil Goutham <sgoutham@marvell.com>
Cc: Robert Richter <rrichter@marvell.com>
Cc: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
SYSTEMPORT is capable of performing VLAN transmit acceleration, support
that by configuring it appropriately, providing the VLAN ID and PCP/DEI
where necessary.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Flow Dissector's keys are mostly Network / Big Endian. U{16,32}_MAX are
the same in either of byteorders, but let's make sparse happy with
wrapping them into noops.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
One of the function arguments was renamed some time ago, but this
wasn't reflected in its kernel-doc comment.
Also add the description for return values.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Current code assumes that both host and device operates in Little Endian
in lots of places. While this is true for x86 platform, this doesn't mean
we should not care about this.
This commit addresses all parts of the code that were pointed out by sparse
checker. All operations with restricted (__be*/__le*) types are now
protected with explicit from/to CPU conversions, even if they're noops on
common setups.
I'm sure there are more such places, but this implies a deeper code
investigation, and is a subject for future works.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use intermediate pointers instead of multiple dereferencing to
simplify and beautify parts of code that will be addressed in
the next commit.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To not mix functional and stylistic changes, correct indentation
of code that will be modified in the subsequent commits.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Get rid of the kernel-doc warnings when building with W=1+ by
rewriting the problematic doc comments according to the
recommended format and style.
Note that this only fixes problems found in C source files,
headers aren't in scope for now.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change the prototype of qed_hw_err_notify() with the following:
* constify "fmt" argument according to printk() declarations;
* anontate it with __cold attribute to move the function out of
the line;
* annotate it with __printf() attribute;
This eliminates W=1+ warning:
drivers/net/ethernet/qlogic/qed/qed_hw.c: In function
‘qed_hw_err_notify’:
drivers/net/ethernet/qlogic/qed/qed_hw.c:851:3: warning: function
‘qed_hw_err_notify’ might be a candidate for ‘gnu_printf’ format
attribute [-Wsuggest-attribute=format]
len = vsnprintf(buf, QED_HW_ERR_MAX_STR_SIZE, fmt, vl);
^~~
as well as saves some code size:
add/remove: 0/0 grow/shrink: 2/4 up/down: 40/-125 (-85)
Function old new delta
qed_dmae_execute_command 1680 1711 +31
qed_spq_post 1104 1113 +9
qed_int_sp_dpc 3554 3545 -9
qed_mcp_cmd_and_union 1896 1876 -20
qed_hw_err_notify 395 352 -43
qed_mcp_handle_events 2630 2577 -53
Total: Before=368645, After=368560, chg -0.02%
__printf() will also be helpful with catching bad format strings
and arguments.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix several sparse warnings by moving structs declarations into
the corresponding header files:
drivers/net/ethernet/qlogic/qed/qed_dcbx.c:2402:32: warning:
symbol 'qed_dcbnl_ops_pass' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_ll2.c:2754:26: warning: symbol
'qed_ll2_ops_pass' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_ptp.c:449:30: warning: symbol
'qed_ptp_ops_pass' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_sriov.c:5265:29: warning:
symbol 'qed_iov_ops_pass' was not declared. Should it be static?
(some of them were declared twice in different header files)
Also make qed_hw_err_type_descr[] const while at it.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Static variables (and functions, unless they're inline) should not
be declared in header files.
Move the static array iro_arr[] from "qed_hsi.h" to the sole place
where it's used, "qed_init_ops.c". This eliminates lots of warnings
(42 of them actually) against W=1+:
In file included from drivers/net/ethernet/qlogic/qed/qed.h:51:0,
from drivers/net/ethernet/qlogic/qed/qed_ooo.c:40:
drivers/net/ethernet/qlogic/qed/qed_hsi.h:4421:18: warning: 'iro_arr'
defined but not used [-Wunused-const-variable=]
static const u32 iro_arr[] = {
^~~~~~~
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On link down, the draining of the S/G cache should be done on all
_possible_ CPUs not just the ones that are online in that moment.
Fix this by changing the iterator.
Fixes: d70446ee1f ("dpaa2-eth: send a scatter-gather FD instead of realloc-ing")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The variable 'err = -ENODEV;' in au1000_probe() is
duplicate, so remove redundant one. And remove the
extra blank lines in the file au1000_eth.c
Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Signed-off-by: Tang Bin <tangbin@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enable promisc mode of PF, set VF link state to enable, and
run iperf of the VF, then do self test of the PF. The self test
will fail with a low frequency, and may cause a use-after-free
problem.
[ 87.142126] selftest:000004a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
[ 87.159722] ==================================================================
[ 87.174187] BUG: KASAN: use-after-free in hex_dump_to_buffer+0x140/0x608
[ 87.187600] Read of size 1 at addr ffff003b22828000 by task ethtool/1186
[ 87.201012]
[ 87.203978] CPU: 7 PID: 1186 Comm: ethtool Not tainted 5.5.0-rc4-gfd51c473-dirty #4
[ 87.219306] Hardware name: Huawei TaiShan 2280 V2/BC82AMDA, BIOS TA BIOS 2280-A CS V2.B160.01 01/15/2020
[ 87.238292] Call trace:
[ 87.243173] dump_backtrace+0x0/0x280
[ 87.250491] show_stack+0x24/0x30
[ 87.257114] dump_stack+0xe8/0x140
[ 87.263911] print_address_description.isra.8+0x70/0x380
[ 87.274538] __kasan_report+0x12c/0x230
[ 87.282203] kasan_report+0xc/0x18
[ 87.288999] __asan_load1+0x60/0x68
[ 87.295969] hex_dump_to_buffer+0x140/0x608
[ 87.304332] print_hex_dump+0x140/0x1e0
[ 87.312000] hns3_lb_check_skb_data+0x168/0x170
[ 87.321060] hns3_clean_rx_ring+0xa94/0xfe0
[ 87.329422] hns3_self_test+0x708/0x8c0
The length of packet sent by the selftest process is only
128 + 14 bytes, and the min buffer size of a BD is 256 bytes,
and the receive process will make sure the packet sent by
the selftest process is in the linear part, so only check
the linear part in hns3_lb_check_skb_data().
So fix this use-after-free by using skb_headlen() to dump
skb->data instead of skb->len.
Fixes: c39c4d98dc ("net: hns3: Add mac loopback selftest support in hns3 driver")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When unloading driver, if flag HNS3_NIC_STATE_INITED has been
already cleared, the debugfs will not be uninitialized, so fix it.
Fixes: b2292360bb ("net: hns3: Add debugfs framework registration")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When asserts VF reset fail, flag HCLGEVF_STATE_CMD_DISABLE
and handshake status should not set, otherwise the retry will
fail. So adds a check for asserting VF reset and returns
directly when fails.
Fixes: ef5f8e507e ("net: hns3: stop handling command queue while resetting VF")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If there is a PF reset pending before FLR prepare, FLR's
preparatory work will not fail, but the FLR rebuild procedure
will fail for this pending. So this PF reset pending should
be handled in the FLR preparatory.
Fixes: 8627bdedc4 ("net: hns3: refactor the precedure of PF FLR")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
The driver was calling pci_save/restore_state() which is no more needed.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states. And they use PCI
helper functions to do it.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
In this driver:
gem_suspend() calls gem_do_stop() which in turn invokes
pci_disable_device(). As the PCI helper function is not called at the
end/start of the function body, breaking the function in two parts
may change its behavior.
The only other function invoking gem_do_stop() is gem_close(). Hence,
gem_close() and gem_suspend() can do the required end steps on their own.
The same case is with gem_resume(). Both gem_resume() and gem_open()
invoke gem_do_start(). Again, make the caller functions do the required
steps on their own.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
rmnet can have only two bridge interface.
One of them is a link interface and another one is added by
the master operation.
rmnet interface shouldn't allow adding additional
bridge interfaces by mater operation.
But, there is no code to deny additional interfaces.
So, interface leak occurs.
Test commands:
ip link add dummy0 type dummy
ip link add dummy1 type dummy
ip link add dummy2 type dummy
ip link add rmnet0 link dummy0 type rmnet mux_id 1
ip link set dummy1 master rmnet0
ip link set dummy2 master rmnet0
ip link del rmnet0
In the above test command, the dummy0 was attached to rmnet as VND mode.
Then, dummy1 was attached to rmnet0 as BRIDGE mode.
At this point, dummy0 mode is switched from VND to BRIDGE automatically.
Then, dummy2 is attached to rmnet as BRIDGE mode.
At this point, rmnet0 should deny this operation.
But, rmnet0 doesn't deny this.
So that below splat occurs when the rmnet0 interface is deleted.
Splat looks like:
[ 186.684787][ C2] WARNING: CPU: 2 PID: 1009 at net/core/dev.c:8992 rollback_registered_many+0x986/0xcf0
[ 186.684788][ C2] Modules linked in: rmnet dummy openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_x
[ 186.684805][ C2] CPU: 2 PID: 1009 Comm: ip Not tainted 5.8.0-rc1+ #621
[ 186.684807][ C2] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 186.684808][ C2] RIP: 0010:rollback_registered_many+0x986/0xcf0
[ 186.684811][ C2] Code: 41 8b 4e cc 45 31 c0 31 d2 4c 89 ee 48 89 df e8 e0 47 ff ff 85 c0 0f 84 cd fc ff ff 5
[ 186.684812][ C2] RSP: 0018:ffff8880cd9472e0 EFLAGS: 00010287
[ 186.684815][ C2] RAX: ffff8880cc56da58 RBX: ffff8880ab21c000 RCX: ffffffff9329d323
[ 186.684816][ C2] RDX: 1ffffffff2be6410 RSI: 0000000000000008 RDI: ffffffff95f32080
[ 186.684818][ C2] RBP: dffffc0000000000 R08: fffffbfff2be6411 R09: fffffbfff2be6411
[ 186.684819][ C2] R10: ffffffff95f32087 R11: 0000000000000001 R12: ffff8880cd947480
[ 186.684820][ C2] R13: ffff8880ab21c0b8 R14: ffff8880cd947400 R15: ffff8880cdf10640
[ 186.684822][ C2] FS: 00007f00843890c0(0000) GS:ffff8880d4e00000(0000) knlGS:0000000000000000
[ 186.684823][ C2] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 186.684825][ C2] CR2: 000055b8ab1077b8 CR3: 00000000ab612006 CR4: 00000000000606e0
[ 186.684826][ C2] Call Trace:
[ 186.684827][ C2] ? lockdep_hardirqs_on_prepare+0x379/0x540
[ 186.684829][ C2] ? netif_set_real_num_tx_queues+0x780/0x780
[ 186.684830][ C2] ? rmnet_unregister_real_device+0x56/0x90 [rmnet]
[ 186.684831][ C2] ? __kasan_slab_free+0x126/0x150
[ 186.684832][ C2] ? kfree+0xdc/0x320
[ 186.684834][ C2] ? rmnet_unregister_real_device+0x56/0x90 [rmnet]
[ 186.684835][ C2] unregister_netdevice_many.part.135+0x13/0x1b0
[ 186.684836][ C2] rtnl_delete_link+0xbc/0x100
[ ... ]
[ 238.440071][ T1009] unregister_netdevice: waiting for rmnet0 to become free. Usage count = 1
Fixes: 037f9cdf72 ("net: rmnet: use upper/lower device infrastructure")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and taking care of register states. And they use PCI
helper functions to do it.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
.suspend() calls __qlcnic_shutdown, which then calls qlcnic_82xx_shutdown;
.resume() calls __qlcnic_resume, which then calls qlcnic_82xx_resume;
Both ...82xx..() are define in
drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c and are used only in
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c.
Hence upgrade them and remove PCI function calls, like pci_save_state() and
pci_enable_wake(), inside them
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states. And they use PCI
helper functions to do it.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
In this driver:
netxen_nic_resume() calls netxen_nic_attach_func() which then invokes PCI
helper functions like pci_enable_device(), pci_set_power_state() and
pci_restore_state(). Other function:
- netxen_io_slot_reset()
also calls netxen_nic_attach_func().
Also, netxen_io_slot_reset() returns specific value based on the return value
of netxen_nic_attach_func() as whole. Thus, cannot simply move some piece of
code from netxen_nic_attach_func() to it.
Hence, define a new function netxen_nic_attach_late_func() to do the tasks
which has to be done after PCI helper functions have done their job.
Now, netxen_nic_attach_func() invokes netxen_nic_attach_late_func(), thus
netxen_io_slot_reset() behaves normally.
And, netxen_nic_resume() calls netxen_nic_attach_late_func() to avoid PCI
helper functions calls.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When sending mailbox in the work of aeq event, another aeq event
will be triggered. because the last aeq work is not exited and only
one work can be excuted simultaneously in the same workqueue, mailbox
sending function will return failure of timeout. We create and use
another workqueue to fix this.
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The patch adds driver changes to perform Idlechk dump during the debug
data collection.
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch populates a database of idlechk tests (registers and
predicates) and performs the idlechk using this data.
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The patch adds register definitions required for Idlechk implementation.
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the transmit part of XDP support, which includes:
- support for XDP_TX in mvpp2_xdp()
- .ndo_xdp_xmit hook for AF_XDP and XDP_REDIRECT with mvpp2 as destination
mvpp2_xdp_submit_frame() is a generic function which is called by
mvpp2_xdp_xmit_back() when doing XDP_TX, and by mvpp2_xdp_xmit when
doing AF_XDP or XDP_REDIRECT target.
The buffer allocation has been reworked to be able to map the buffers
as DMA_FROM_DEVICE or DMA_BIDIRECTIONAL depending if native XDP is
in use or not.
Co-developed-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add XDP native support.
By now only XDP_DROP, XDP_PASS and XDP_REDIRECT
verdicts are supported.
Co-developed-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the page_pool API for memory management.
This is a prerequisite for native XDP support.
Tested-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In mvpp2_swf_bm_pool_init_percpu(), a reference to a struct
mvpp2_bm_pool is obtained traversing multiple structs, when a
local variable already points to the same object.
Fix it and, while at it, give the variable a meaningful name.
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The GENET driver interfaces with internal MoCA interface as well as
external MoCA chips like the BCM6802/6803 through a fixed link
interface. It is desirable for the mocad user-space daemon to be able to
control the carrier state based upon out of band messages that it
receives from the MoCA chip.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Upon a TX timeout handle, if the TX reporter was not able to recover
from the error, reopen the channels. If tried to reopen channels, do not
loop over TX queues for timeout.
With that, the reporters state and separation will better
expose the driver's state.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add helper which retrieves the RQ WQE's head. Use this helper in RX
reporter diagnose callback.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Use txrx.h to contain helper function regarding TX/RX. In the coming
patches, I will add more RQ helpers.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Change the hierarchy of the RX reporter 'Common config' in the diagnose
output to match the 'Common config' of the TX reporter which reflects
that CQ is a helper to the traffic queues.
Before:
$ devlink health diagnose pci/0000:00:0b.0 reporter rx
Common config:
RQ:
type: 2 stride size: 2048 size: 8
CQ:
stride size: 64 size: 1024
RQs:
...
After:
$ devlink health diagnose pci/0000:00:0b.0 reporter rx
Common config:
RQ:
type: 2 stride size: 2048 size: 8
CQ:
stride size: 64 size: 1024
RQs:
...
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When received a CQE error, the driver inspect the syndrome given by the
firmware. RQ recovery is initiated only as a result of a fatal syndrome;
syndrome which set the RQ into an error state. Hence no need to query
the RQ state at the beginning of the recovery process. Add additional
debug prints before recovering.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
During queue's recovery, driver waits for flush. The flush timeout is
set to 2 seconds. Add a define for this value for the benefit of RX and
TX reporters.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Creation of devlink health reporters is not fatal for mlx5e instance load.
In case of error in reporter's creation, the return value is ignored.
Change all reporters creation functions to return void.
In addition, with this change, a failure in creating a reporter, will not
prevent the driver from trying to create the next reporter in the list.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
We have yet another new scheme for NVRAM, and a corresponding new MCDI.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The QDMA subsystem on EF100 needs this information.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since ethtool_common.o will be built into both sfc and sfc_ef100 drivers,
it can't use KBUILD_MODNAME directly. Instead, make it reference a
string provided by the individual driver code.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously this was only happening in ef10-specific code.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
_down() merely removes all our filters and VLANs, it doesn't free
efx->filter_state itself.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since we only allocate VIs for the number of TXQs we actually need, we
cannot naively use "channel * TXQ_TYPES + txq" for the TXQ number, as
this has gaps (when efx->tx_queues_per_channel < EFX_TXQ_TYPES) and
thus overruns the driver's VI allocations, causing the firmware to
reject the MC_CMD_INIT_TXQ based on INSTANCE.
Thus, we distinguish INSTANCE (stored in tx_queue->queue) from LABEL
(tx_queue->label); the former is allocated starting from 0 in
efx_set_channels(), while the latter is simply the txq type (index in
channel->tx_queue array).
To simplify things, rather than changing tx_queues_per_channel after
setting up TXQs, make Siena always probe its HIGHPRI queues at start
of day, rather than deferring it until tc mqprio enables them.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Siena needs four TX queues (csum * highpri), EF10 needs two (csum),
and EF100 only needs one (as checksumming is controlled entirely by
the transmit descriptor). Rather than having various bits of ad-hoc
code to decide which queues to set up etc., put the knowledge of how
many TXQs a channel has in one place.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of exposing this old module parameter on the new driver (thus
having to keep it forever after for compatibility), let's confine it
to the old one; if we find later that we need the feature, we ought
to support it properly, with ethtool set-channels.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
EF100 only supports MSI-X, so there's no need for the new driver to
expose this old module parameter.
Since it's now visible to the linker, we have to rename it internally
to efx_interrupt_mode to avoid symbol collisions in non-modular
builds.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All NICs supported by this driver are capable of MSI-X interrupts (only
Falcon A1 wasn't, and that's now hived off into its own driver), so no
need for a nic-type parameter. Besides, the code that checked it was
buggy anyway (the following assignment that checked min_interrupt_mode
overrode it).
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Unprivileged functions (such as VFs) may set their MTU by use of the
'control' field of MC_CMD_SET_MAC_EXT, as used in efx_mcdi_set_mtu().
If calling efx_ef10_mac_reconfigure() from efx_change_mtu(), and the
NIC supports the above (SET_MAC_ENHANCED capability), use it rather
than efx_mcdi_set_mac().
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In certain configurations without power management support, the
following warnings happen:
drivers/net/ethernet/mellanox/mlx4/main.c:4388:12:
warning: 'mlx4_resume' defined but not used [-Wunused-function]
4388 | static int mlx4_resume(struct device *dev_d)
| ^~~~~~~~~~~
drivers/net/ethernet/mellanox/mlx4/main.c:4373:12: warning:
'mlx4_suspend' defined but not used [-Wunused-function]
4373 | static int mlx4_suspend(struct device *dev_d)
| ^~~~~~~~~~~~
Mark these functions as __maybe_unused to make it clear to the
compiler that this is going to happen based on the configuration,
which is the standard for these types of functions.
Fixes: 0e3e206a3e ("mlx4: use generic power management")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In certain configurations without power management support, gcc report
the following warning:
drivers/net/ethernet/micrel/ksz884x.c:7182:12: warning:
'pcidev_suspend' defined but not used [-Wunused-function]
7182 | static int pcidev_suspend(struct device *dev_d)
| ^~~~~~~~~~~~~~
Mark pcidev_suspend() as __maybe_unused to make it clear.
Fixes: 64120615d1 ("ksz884x: use generic power management")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove is_udp variable that is used in only one place and use
ip_hdr(skb)->protocol == IPPROTO_UDP check instead.
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Do not initialize queue variable. It is already initialized in for loops.
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use hweight32() to count set bits in queue_mask.
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bit 0 of queue_mask is set at the beginning of
macb_probe_queues() function. Do not set it again after reading
DGFG6 but instead use "|=" operator.
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2020-07-01
This series contains updates to all Intel drivers, but a majority of the
changes are to the i40e driver.
Jeff converts 'fall through' comments to the 'fallthrough;' keyword for
all Intel drivers. Removed unnecessary delay in the ixgbe ethtool
diagnostics test.
Arkadiusz implements Total Port Shutdown for i40e. This is the revised
patch based on Jakub's feedback from an earlier submission of this
patch, where additional code comments and description was needed to
describe the functionality.
Wei Yongjun fixes return error code for iavf_init_get_resources().
Magnus optimizes XDP code in i40e; starting with AF_XDP zero-copy
transmit completion path. Then by only executing a division when
necessary in the napi_poll data path. Move the check for transmit ring
full outside the send loop to increase performance.
Ciara add XDP ring statistics to i40e and the ability to dump these
statistics and descriptors.
Tony fixes reporting iavf statistics.
Radoslaw adds support for 2.5 and 5 Gbps by implementing the newer ethtool
ksettings API in ixgbe.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Tony Nguyen says:
====================
100GbE Intel Wired LAN Driver Updates 2020-07-01
This series contains updates to the ice driver only.
Jacob implements a devlink region for device capabilities.
Bruce removes structs containing only one-element arrays that are either
unused or only used for indexing. Instead, use pointer arithmetic or
other indexing to access the elements. Converts "C struct hack"
variable-length types to the preferred C99 flexible array member.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert the pre-C90-extension "C struct hack" method (using a single-
element array at the end of a structure for implementing variable-length
types) to the preferred use of C99 flexible array member.
Additional code cleanups were done near areas affected by this change.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
There are a number of structures that consist of a one-element array as the
only struct member. Some of those are unused so remove them. Others are
used to index into a buffer/array consisting of a variable number of a
different data or structure type. Those are unnecessary since we can use
simple pointer arithmetic or index directly into the buffer to access
individual elements of the buffer/array.
Additional code cleanups were done near areas affected by this change.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Add a new devlink region used for capturing a snapshot of the device
capabilities buffer which is reported by the firmware over the AdminQ.
This information can useful in debugging driver and firmware
interactions.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Added full support for new version Ethtool API. New API allow use
2500Gbase-T and 5000base-T supported and advertised link speed modes.
Signed-off-by: Radoslaw Tyl <radoslawx.tyl@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
There is a 4 seconds delay in ixgbe_diag_test() that is holding up other
ioctls such as SIOCGIFCONF that Oracle database applications use.
One of Oracle's product runs "ethtool -t ethX online" periodically for
system monitoring and that is impacting database applications that use
SIOCGIFCONF at that same time.
This 4 second delay was needed in out early 1GbE parts to give the PHY
time to recover from a reset. This code was carried forward to the 10 GbE
driver even it was not needed for the supported PHYs in the ixgbe driver.
CC: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
CC: Jack Vogel <jack.vogel@oracle.com>
Reported-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Commit bac8486116 ("iavf: Refactor the watchdog state machine") inverted
the logic for when to update statistics. Statistics should be updated when
no other commands are pending, instead they were only requested when a
command was processed. iavf_request_stats() would see a pending request
and not request statistics to be updated. This caused statistics to never
be updated; fix the logic.
Fixes: bac8486116 ("iavf: Refactor the watchdog state machine")
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Interfaces already exist for dumping Rx and Tx descriptor information.
Introduce another for doing the same for XDP descriptors.
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Prior to this, only the Rx and Tx ring statistics were dumped. The XDP
ring statistics are now dumped as well.
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Prior to this, only Rx and Tx ring statistics were accounted for.
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Move the check if the HW Tx ring is full to outside the send
loop. Currently it is checked for every single descriptor that we
send. Instead, tell the send loop to only process a maximum number of
packets equal to the number of available slots in the Tx ring. This
way, we can remove the check inside the send loop to and gain some
performance.
Suggested-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Eliminate a division in the napi_poll data path. This division is
executed even though it is only needed in the rare case when there are
not enough interrupt lines so they have to be shared between queue
pairs. Instead, just test for this case and only execute the division
if needed. The code has been lifted from the ice driver.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Improve the performance of the AF_XDP zero-copy Tx completion
path. When there are no XDP buffers being sent using XDP_TX or
XDP_REDIRECT, we do not have go through the SW ring to clean up any
entries since the AF_XDP path does not use these. In these cases, just
fast forward the next-to-use counter and skip going through the SW
ring. The limit on the maximum number of entries to complete is also
removed since the algorithm is now O(1). To simplify the code path, the
maximum number of entries to complete for the XDP path is therefore
also increased from 256 to 512 (the default number of Tx HW
descriptors). This should be fine since the completion in the XDP path
is faster than in the SKB path that has 256 as the maximum number.
This patch provides around 4% throughput improvement for the l2fwd
application in xdpsock on my machine.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Fix to return negative error code -ENOMEM from the error handling
case instead of 0, as done elsewhere in this function.
Fixes: b66c7bc1cd ("iavf: Refactor init state machine")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
After OS requests to down a link on a physical network port, the
traffic is no longer being processed but the physical link with
a link partner is still established.
Currently there is a feature (Link down on close) which allows
to physically bring the link down (after OS request).
With this patch new feature with similar capability is introduced:
TOTAL_PORT_SHUTDOWN
Allows to physically disable the link on the NIC's port.
If enabled, (after link down request from the OS)
no link, traffic or led activity is possible on that port.
If I40E_FLAG_TOTAL_PORT_SHUTDOWN is enabled, the
I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED must be explicitly forced to
true and cannot be disabled at that time.
The functionalities are exclusive in terms of configuration, but
they also have similar behavior (allowing to disable physical link
of the port), with following differences:
- LINK_DOWN_ON_CLOSE_ENABLED is configurable at host OS run-time
and is supported by whole family of 7xx Intel Ethernet Controllers
- TOTAL_PORT_SHUTDOWN may be enabled only before OS loads (in BIOS)
only if motherboard's BIOS and NIC's FW has support of it
- when LINK_DOWN_ON_CLOSE_ENABLED is used, the link is being brought
down by sending phy_type=0 to NIC's FW
- when TOTAL_PORT_SHUTDOWN is used, phy_type is not altered, instead
the link is being brought down by clearing bit
(I40E_AQ_PHY_ENABLE_LINK) in abilities field of
i40e_aq_set_phy_config structure
Introduced changes:
- new private flag I40E_FLAG_TOTAL_PORT_SHUTDOWN for handling the
feature
- probe of NVM if the feature was enabled at driver's port
initialization
- special handling on link-down procedure to let FW physically
shutdown the port if the feature was enabled
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Convert all the remaining 'fall through" code comments to the newer
'fallthrough;' keyword.
Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Thus, there is no need to call the PCI helper functions like
pci_enable_device, which is not recommended. Hence, removed.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Use "struct dev_pm_ops" variable to bind the callbacks.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Thus, there is no need to call the PCI helper functions like
pci_enable_wake(), pci_save/restore_sate() and
pci_set_power_state().
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Use "struct dev_pm_ops" variable to bind the callbacks.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Thus, there is no need to call the PCI helper functions like
pci_enable/disable_device(), pci_save/restore_sate() and
pci_set_power_state().
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Thus, there is no need to call the PCI helper functions like
pci_enable/disable_device(), pci_save/restore_sate() and
pci_set_power_state().
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Drivers should not use legacy power management as they have to manage power
states and related operations, for the device, themselves. This driver was
handling them with the help of PCI helper functions.
With generic PM, all essentials will be handled by the PCI core. Driver
needs to do only device-specific operations.
The driver defined empty-body .suspend() and .resume() callbacks earlier.
They can now be define NULL and bind with "struct dev_pm_ops" variable.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Thus, there is no need to call the PCI helper functions like
pci_save/restore_sate() and pci_set_power_state().
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
Thus, there is no need to call the PCI helper functions like
pci_enable/disable_device(), pci_save/restore_sate() and
pci_set_power_state().
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With legacy PM, drivers themselves were responsible for managing the
device's power states and takes care of register states. And they use PCI
helper functions to do it.
After upgrading to the generic structure, PCI core will take care of
required tasks and drivers should do only device-specific operations.
In this driver:
typhoon_resume() calls typhoon_wakeup() which then calls PCI helper
functions pci_set_power_state() and pci_restore_state(). The only other
function, using typhoon_wakeup() is typhoon_open().
Thus remove the pci_*() calls from tyhpoon_wakeup() and place them in
typhoon_open(), maintaining the order, to retain the normal behavior of
the function
Now, typhoon_suspend() calls typhoon_sleep() which then calls PCI helper
functions pci_enable_wake(), pci_disable_device() and
pci_set_power_state(). Other functions:
- typhoon_open()
- typhoon_close()
- typhoon_init_one()
are also invoking typhoon_sleep(). Thus, in this case, cannot simply
move PCI helper functions call.
Hence, define a new function typhoon_sleep_early() which will do all the
operations, which typhoon_sleep() was doing before calling PCI helper
functions. Now typhoon_sleep() will call typhoon_sleep_early() to do
those tasks, hence, the behavior for _open(), _close and _init_one() remain
unchanged. And typhon_suspend() only requires typhoon_sleep_early().
Compile-tested only.
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix sparse build warning:
drivers/net/ethernet/qlogic/qed/qed_main.c:2480:6: warning:
symbol 'qed_hw_err_type_descr' was not declared. Should it be static?
Signed-off-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
get_dev_cap and set_resources_state functions may return a positive
value because of hardware failure, and the positive return value
can not be passed to ERR_PTR directly.
Fixes: 7dd29ee128 ("hinic: add sriov feature support")
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When mirror VI is enabled, replicate various VI config params
enabled on main VI to mirror VI. These include replicating MTU,
promiscuous mode, all-multicast mode, and enabled netdev Rx
feature offloads.
v3:
- Replace mirror VI refcount_t with normal u32 variable.
- Add back calling cxgb4_port_mirror_start() in cxgb_open(), which
was there in v1, but got missed in v2 during refactoring.
v2:
- Simplify the replication code by refactoring t4_set_rxmode()
to handle mirror VI, instead of duplicating the t4_set_rxmode()
calls in multiple places.
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When mirror VI is enabled, allocate the mirror Rxqs and setup the
mirror VI RSS table. The mirror Rxqs are allocated/freed when
the mirror VI is created/destroyed or when underlying port is
brought up/down, respectively.
v3:
- Replace mirror VI refcount_t with normal u32 variable.
v2:
- Use mutex to protect all mirror VI data, instead of just
mirror Rxqs.
- Remove the un-needed mirror Rxq mutex.
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add mirror Virtual Interface (VI) support to receive all ingress
mirror traffic from the underlying device. The mirror VI is
created dynamically, if the TC-MATCHALL rule has a corresponding
mirror action. Also request MSI-X vectors needed for the mirror VI
Rxqs. If no vectors are available, then disable mirror VI support.
v3:
- Replace mirror VI refcount_t with normal u32 variable.
v2:
- Add mutex to protect all mirror VI data, instead of just
mirror Rxqs.
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In certain configurations without power management support, the
following warnings happen:
../drivers/net/ethernet/amd/pcnet32.c:2928:12: warning:
'pcnet32_pm_resume' defined but not used [-Wunused-function]
2928 | static int pcnet32_pm_resume(struct device *device_d)
| ^~~~~~~~~~~~~~~~~
../drivers/net/ethernet/amd/pcnet32.c:2916:12: warning:
'pcnet32_pm_suspend' defined but not used [-Wunused-function]
2916 | static int pcnet32_pm_suspend(struct device *device_d)
| ^~~~~~~~~~~~~~~~~~
Mark these functions as __maybe_unused to make it clear to the compiler
that this is going to happen based on the configuration, which is the
standard for these types of functions.
Fixes: a86688fbef ("pcnet32: Convert to generic power management")
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In certain configurations without power management support, the
following warnings happen:
../drivers/net/ethernet/amd/amd8111e.c:1623:12: warning:
'amd8111e_resume' defined but not used [-Wunused-function]
1623 | static int amd8111e_resume(struct device *dev_d)
| ^~~~~~~~~~~~~~~
../drivers/net/ethernet/amd/amd8111e.c:1584:12: warning:
'amd8111e_suspend' defined but not used [-Wunused-function]
1584 | static int amd8111e_suspend(struct device *dev_d)
| ^~~~~~~~~~~~~~~~
Mark these functions as __maybe_unused to make it clear to the compiler
that this is going to happen based on the configuration, which is the
standard for these types of functions.
Fixes: 2caf751fe0 ("amd8111e: Convert to generic power management")
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shrink the code by using the managed variant of of_mdiobus_register().
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We currently have two managed helpers for mdiobus - devm_mdiobus_alloc()
and devm_mdiobus_register(). The idea behind devres is that the release
callback releases whatever resource the devm function allocates. In the
mdiobus case however there's no devres associated with the device by
devm_mdiobus_register(). Instead the release callback for
devm_mdiobus_alloc(): _devm_mdiobus_free() unregisters the device if
it is marked as managed.
This all seems wrong. The managed structure shouldn't need to know or
care about whether it's managed or not - and this is the case now for
struct mii_bus. The devres wrapper should be opaque to the managed
resource.
This changeset makes devm_mdiobus_alloc() and devm_mdiobus_register()
conform to common devres standards: devm_mdiobus_alloc() allocates a
devres structure and registers a callback that will call mdiobus_free().
__devm_mdiobus_register() allocated another devres and registers a
callback that will unregister the bus.
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The idea behind devres is that the release callbacks are called if
probe fails. As we now check the return value of ixgbe_mii_bus_init(),
we can drop the call devm_mdiobus_free() in error path as the release
callback will be called automatically.
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This function may fail. Check its return value and propagate the error
code.
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Find ports accessible by the VF, based on the index of the
mac address stored for the VF in the adapter. If no mac address
is stored for the VF, use the port mask provided by firmware.
Signed-off-by: Nirranjan Kirubaharan <nirranjan@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
t4_prep_fw goto bye tag with positive return value when something
bad happened and which can not free resource in adap_init0.
so fix it to return negative value.
Fixes: 16e47624e7 ("cxgb4: Add new scheme to update T4/T5 firmware")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Li Heng <liheng40@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Set the actual copyright holder and years in all qede source files.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
QLogic QED drivers source code is dual licensed under
GPL-2.0/BSD-3-Clause.
Remove all the boilerplates in the existing code and replace it with the
correct SPDX tag.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
QLogic QED drivers source code is dual licensed under
GPL-2.0/BSD-3-Clause.
Correct already existing but wrong SPDX tags to match the actual
license.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Set the actual copyright holder and years in all qed source files.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
QLogic QED drivers source code is dual licensed under
GPL-2.0/BSD-3-Clause.
Remove all the boilerplates in the existing code and replace it with the
correct SPDX tag.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
QLogic QED drivers source code is dual licensed under
GPL-2.0/BSD-3-Clause.
Correct already existing but wrong SPDX tags to match the actual
license.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The error return path when create_singlethread_workqueue fails currently
does not kfree tls and leads to a memory leak. Fix this by kfree'ing
tls before returning -ENOMEM.
Addresses-Coverity: ("Resource leak")
Fixes: 1182f36593 ("net/mlx5e: kTLS, Add kTLS RX HW offload support")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
EF100 won't have an efx->type->tx_remove method, because there's
nothing for it to do. So make the call conditional.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ef100 will need to check this against NIC limits.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Define it in nic_common.h, even though the ef100 driver will have a
different implementation backing it (actually a WARN_ON_ONCE as it
should never get called by ef100. But it needs to still exist because
common TX path code references it).
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ef100 will need this if it gets GSO skbs it can't handle (e.g. too long
header length).
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ef100 RX path will also need to DMA-sync RX buffers.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Refactor it a little as we go, and introduce efx_mcdi_set_mtu() which we
will later use for ef100 to change MTU without touching other MAC settings.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Various left-over bits and pieces from efx.c that are needed by ef100.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Both the licence notice and the SPDX tag were missing from this file.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most of it was already declared in mcdi_port_common.h, so just move the
implementations to mcdi_port_common.c.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These functions are implemented in mcdi_port.c, which will not be linked
into the EF100 driver; thus their prototypes should not be visible in
common header files.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When support for short preambles was added, it incorrectly keyed its
decision off state->speed instead of state->interface. state->speed
is not guaranteed to be correct for in-band modes, which can lead to
short preambles being unexpectedly disabled.
Fix this by keying off the interface mode, which is the only way that
mvneta can operate at 2.5Gbps.
Fixes: da58a931f2 ("net: mvneta: Add support for 2500Mbps SGMII")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
remove unused but set variable to avoid auto build test WARNING
Signed-off-by: Luo bin <luobin9@huawei.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher says:
====================
1GbE Intel Wired LAN Driver Updates 2020-06-29
This series contains updates to only the igc driver.
Sasha added Energy Efficient Ethernet (EEE) support and Latency Tolerance
Reporting (LTR) support for the igc driver. Added Low Power Idle (LPI)
counters and cleaned up unused TCP segmentation counters. Removed
igc_power_down_link() and call igc_power_down_phy_copper_base()
directly. Removed unneeded copper media check.
Andre cleaned up timestamping by removing un-supported features and
duplicate code for i225. Fixed the timestamp check on the proper flag
instead of the skb for pending transmit timestamps. Refactored
igc_ptp_set_timestamp_mode() to simply the flow.
v2: Removed the log message in patch 1 as suggested by David Miller.
Note: The locking issue Jakub Kicinski saw in patch 5, currently
exists in the current net-next tree, so Andre will resolve the
locking issue in a follow-on patch.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
i225 device support only copper mode.
There is no point to check media type in the
igc_config_fc_after_link_up() method.
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
PHY of the i225 device support only copper mode.
There is no point to check media type in the
igc_power_up_link() method.
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Currently the implementation of igc_power_down_link()
method was just calling igc_power_down_phy_copper_base()
method.
We can just call igc_power_down_phy_copper_base()
method directly.
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
TCP segmentation TX context fail counter is not
applicable for i225 devices.
This patch comes to clean up this counter.
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown<aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Add EEE TX LPI and EEE RX LPI counters. A EEE TX LPI event
occurs when the transmitter enters EEE (IEEE 802.3az) LPI
state. A EEE RX LPI event occurs when the receiver detect
link partner entry into EEE(IEEE 802.3az) LPI state.
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
When Rx timestamping is enabled, we set the timestamp bit in SRRCTL
register for each queue, but we don't clear it when disabling. This
patch fixes igc_ptp_disable_rx_timestamp() accordingly.
Also, this patch gets rid of igc_ptp_enable_tstamp_rxqueue() and
igc_ptp_enable_tstamp_all_rxqueues() and move their logic into
igc_ptp_enable_rx_timestamp() to keep the enable and disable
helpers symmetric.
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Current igc_ptp_set_timestamp_mode() logic is a bit tangled since it
handles many different hardware configurations in one single place,
making it harder to follow. This patch untangles that code by breaking
it into helper functions.
Quick note about the hw->mac.type check which was removed in this
refactoring: this check it not really needed since igc_i225 is the only
type supported by the IGC driver.
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
As implemented in igc_ethtool_get_ts_info(), igc only supports HWTSTAMP_
FILTER_ALL so any HWTSTAMP_FILTER_* option the user may set falls back to
HWTSTAMP_FILTER_ALL.
HWTSTAMP_FILTER_ALL is implemented via Rx Time Sync Control (TSYNCRXCTL)
configuration which timestamps all incoming packets. Configuring a
UDP filter, in addition to TSYNCRXCTL, doesn't add much so this patch
removes that code. It also takes this opportunity to remove some
non-applicable comments.
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The __IGC_PTP_TX_IN_PROGRESS flag indicates we have a pending Tx
timestamp. In some places, instead of checking that flag, we check
adapter->ptp_tx_skb. This patch fixes those places to use the flag.
Quick note about igc_ptp_tx_hwtstamp() change: when that function is
called, adapter->ptp_tx_skb is expected to be valid always so we
WARN_ON_ONCE() in case it is not.
Quick note about igc_ptp_suspend() change: when suspending, we don't
really need to check if there is a pending timestamp. We can simply
clear it unconditionally.
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The functions igc_ptp_tx_hang() and igc_ptp_tx_work() have duplicate
code which handles Tx timestamp timeouts. This patch does a trivial
refactoring by moving that code to its own function and reusing it.
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Differently from I210, I225 doesn't report Rx timestamps via the TS bit
Rx descriptor + RXSTMPL/RXSTMPH registers mechanism. Rx timestamps are
reported in the packet buffer only, which is implemented by igc_ptp_rx_
pktstamp(). So this patch removes igc_ptp_rx_rgtstamp() and all code
related to it, copied from igb driver.
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The LTR message on the PCIe inform the requested latency
on which the PCIe must become active to the downstream
PCIe port of the system.
This patch provide recommended LTR parameters by i225
specification.
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Implement .get_down_ext_state() as part of ethtool_ops.
Query link down reason from PDDR register and convert it to ethtool
link_ext_state.
In case that more information than common link_ext_state is provided,
fill link_ext_substate also with the appropriate value.
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The PDDR register enables to read the Phy debug database.
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move mlxsw_sp1_port_type_speed_ops and mlxsw_sp2_port_type_speed_ops
with the relevant code from spectrum.c to spectrum_ethtool.c.
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add spectrum_ethtool.c file for ethtool code.
Move ethtool_ops and the relevant code from spectrum.c to
spectrum_ethtool.c.
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
mlxsw_sp_port_headroom_set() is defined twice - in spectrum.c and in
spectrum_dcb.c, with different arguments and different implementation
but the name is same.
Rename mlxsw_sp_port_headroom_set() to mlxsw_sp_port_headroom_ets_set()
in order to allow using the second function in several files, and not
only as static function in spectrum.c.
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IEEE802.3az-2010 Energy Efficient Ethernet has been
approved as standard (September 2010) and the driver
can enable and disable it via ethtool.
Disable the feature by default on parts which support it.
Add enable/disable eee options.
tx-lpi, tx-timer and advertise not supported yet.
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Reviewed-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
With the previous commit, in case of insufficient SKB headroom on the Tx
path instead of reallocing the SKB we now send a S/G frame descriptor.
Export the number of occurences of this case as a per CPU counter (in
debugfs) and a total number in the ethtool statistics - "tx converted sg
frames'.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of realloc-ing the skb on the Tx path when the provided headroom
is smaller than the HW requirements, create a Scatter/Gather frame
descriptor with only one entry.
Remove the '[drv] tx realloc frames' counter exposed previously through
ethtool since it is no longer used.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
EF100 will use CHECKSUM_COMPLETE, but will also make use of
efx_rx_packet_gro(), thus needs to be able to pass the checksum value
into that function.
Drivers for older NICs pass in a csum of 0 to get the old semantics (use
the RX flags for CHECKSUM_UNNECESSARY marking).
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
EF100 will use the same approach to ARFS as EF10.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Avoids a call from generic MCDI code into ef10.c.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
EF100 will use the same mechanisms for PCI error recovery.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
EF100 needs to map multiple BARs (sequentially, not concurrently) in
order to read the Function Control Window during probe.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A few more ethtool handlers which EF100 will share.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
EF100 will share EF10's model of filtering, hashing and spreading.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Link speeds, FEC, and autonegotiation are all things EF100 will share.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The new nic_common.h contains the inlines for NIC-type function dispatch,
declarations for NIC-generic functions in nic.c, and other similar NIC-
generic functionality. Retained in nic.h are NIC-specific declarations
such as the siena and ef10 nic_data structs and various farch functions.
The EF100 driver will thus include nic_common.h but not nic.h.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Separate the generation-count handling from the format conversion, to
make it easier to re-use both for EF100.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Calculate efx->max_vis at probe time, and check against it in
efx_allocate_msix_channels() when considering whether to create XDP TX
channels.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that we have an _OFST definition for each individual flag bit,
callers of efx_has_cap() don't need to specify which flag word it's
in; we can just use the flag name directly in MCDI_CAPABILITY_OFST.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The script used to generate these now includes _OFST definitions for
flags, to identify the containing flag word.
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since 'tcfp_burst' with TICK factor, driver side always need to recover
it to the original value, this patch moves the generic calculation and
recover to the 'burst' original value before offloading to device driver.
Signed-off-by: Po Liu <po.liu@nxp.com>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1) Improve hardware layouts and structure for kTLS support
2) Generalize ICOSQ (Internal Channel Operations Send Queue)
Due to the asynchronous nature of adding new kTLS flows and handling
HW asynchronous kTLS resync requests, the XSK ICOSQ was extended to
support generic async operations, such as kTLS add flow and resync, in
addition to the existing XSK usages.
3) kTLS hardware flow steering and classification:
The driver already has the means to classify TCP ipv4/6 flows to send them
to the corresponding RSS HW engine, as reflected in patches 3 through 5,
the series will add a steering layer that will hook to the driver's TCP
classifiers and will match on well known kTLS connection, in case of a
match traffic will be redirected to the kTLS decryption engine, otherwise
traffic will continue flowing normally to the TCP RSS engine.
3) kTLS add flow RX HW offload support
New offload contexts post their static/progress params WQEs
(Work Queue Element) to communicate the newly added kTLS contexts
over the per-channel async ICOSQ.
The Channel/RQ is selected according to the socket's rxq index.
A new TLS-RX workqueue is used to allow asynchronous addition of
steering rules, out of the NAPI context.
It will be also used in a downstream patch in the resync procedure.
Feature is OFF by default. Can be turned on by:
$ ethtool -K <if> tls-hw-rx-offload on
4) Added mlx5 kTLS sw stats and new counters are documented in
Documentation/networking/tls-offload.rst
rx_tls_ctx - number of TLS RX HW offload contexts added to device for
decryption.
rx_tls_ooo - number of RX packets which were part of a TLS stream
but did not arrive in the expected order and triggered the resync
procedure.
rx_tls_del - number of TLS RX HW offload contexts deleted from device
(connection has finished).
rx_tls_err - number of RX packets which were part of a TLS stream
but were not decrypted due to unexpected error in the state machine.
5) Asynchronous RX resync
a. The NIC driver indicates that it would like to resync on some TLS
record within the received packet (P), but the driver does not
know (yet) which of the TLS records within the packet.
At this stage, the NIC driver will query the device to find the exact
TCP sequence for resync (tcpsn), however, the driver does not wait
for the device to provide the response.
b. Eventually, the device responds, and the driver provides the tcpsn
within the resync packet to KTLS. Now, KTLS can check the tcpsn against
any processed TLS records within packet P, and also against any record
that is processed in the future within packet P.
The asynchronous resync path simplifies the device driver, as it can
save bits on the packet completion (32-bit TCP sequence), and pass this
information on an asynchronous command instead.
Performance:
CPU: Intel(R) Xeon(R) CPU E5-2687W v4 @ 3.00GHz, 24 cores, HT off
NIC: ConnectX-6 Dx 100GbE dual port
Goodput (app-layer throughput) comparison:
+---------------+-------+-------+---------+
| # connections | 1 | 4 | 8 |
+---------------+-------+-------+---------+
| SW (Gbps) | 7.26 | 24.70 | 50.30 |
+---------------+-------+-------+---------+
| HW (Gbps) | 18.50 | 64.30 | 92.90 |
+---------------+-------+-------+---------+
| Speedup | 2.55x | 2.56x | 1.85x * |
+---------------+-------+-------+---------+
* After linerate is reached, diff is observed in CPU util
-----BEGIN PGP SIGNATURE-----
iQEzBAABCAAdFiEEGhZs6bAKwk/OTgTpSD+KveBX+j4FAl73s2kACgkQSD+KveBX
+j4wqAf/ZhcEn7i4N2F9wMMIL6wd4DgwKWWhbGpiREIxDwcRbqH7PGom8nBZMNd9
+3g3zfURvByWehLtYcjmMgR4B7+xDgEs0dSx6pQM9764HqLDV2jW8ENr9Vr/u8s1
hJ/eV8uzIfvx27MzbENZi0oJTw7N9nCgdcv1OyZkIba+Iado9pOeakPgBmTbINgo
46LJI9nIEROE15gfjyxrVeYAs3Nxt+bogQCWYfMqUfRmKcMJ0d4oTHaUdtmm+xQB
jC685/e4gE7jRgZ3qH/xvCZYp7+TVKaXsB0EtaJdPFEkvvvQpgPTfquIQ+6l7vvE
Yf1YUhnDOoxGUQy1CdSZ2reNxLIm8A==
=7+rG
-----END PGP SIGNATURE-----
Merge tag 'mlx5-tls-2020-06-26' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-tls-2020-06-26
1) Improve hardware layouts and structure for kTLS support
2) Generalize ICOSQ (Internal Channel Operations Send Queue)
Due to the asynchronous nature of adding new kTLS flows and handling
HW asynchronous kTLS resync requests, the XSK ICOSQ was extended to
support generic async operations, such as kTLS add flow and resync, in
addition to the existing XSK usages.
3) kTLS hardware flow steering and classification:
The driver already has the means to classify TCP ipv4/6 flows to send them
to the corresponding RSS HW engine, as reflected in patches 3 through 5,
the series will add a steering layer that will hook to the driver's TCP
classifiers and will match on well known kTLS connection, in case of a
match traffic will be redirected to the kTLS decryption engine, otherwise
traffic will continue flowing normally to the TCP RSS engine.
3) kTLS add flow RX HW offload support
New offload contexts post their static/progress params WQEs
(Work Queue Element) to communicate the newly added kTLS contexts
over the per-channel async ICOSQ.
The Channel/RQ is selected according to the socket's rxq index.
A new TLS-RX workqueue is used to allow asynchronous addition of
steering rules, out of the NAPI context.
It will be also used in a downstream patch in the resync procedure.
Feature is OFF by default. Can be turned on by:
$ ethtool -K <if> tls-hw-rx-offload on
4) Added mlx5 kTLS sw stats and new counters are documented in
Documentation/networking/tls-offload.rst
rx_tls_ctx - number of TLS RX HW offload contexts added to device for
decryption.
rx_tls_ooo - number of RX packets which were part of a TLS stream
but did not arrive in the expected order and triggered the resync
procedure.
rx_tls_del - number of TLS RX HW offload contexts deleted from device
(connection has finished).
rx_tls_err - number of RX packets which were part of a TLS stream
but were not decrypted due to unexpected error in the state machine.
5) Asynchronous RX resync
a. The NIC driver indicates that it would like to resync on some TLS
record within the received packet (P), but the driver does not
know (yet) which of the TLS records within the packet.
At this stage, the NIC driver will query the device to find the exact
TCP sequence for resync (tcpsn), however, the driver does not wait
for the device to provide the response.
b. Eventually, the device responds, and the driver provides the tcpsn
within the resync packet to KTLS. Now, KTLS can check the tcpsn against
any processed TLS records within packet P, and also against any record
that is processed in the future within packet P.
The asynchronous resync path simplifies the device driver, as it can
save bits on the packet completion (32-bit TCP sequence), and pass this
information on an asynchronous command instead.
Performance:
CPU: Intel(R) Xeon(R) CPU E5-2687W v4 @ 3.00GHz, 24 cores, HT off
NIC: ConnectX-6 Dx 100GbE dual port
Goodput (app-layer throughput) comparison:
+---------------+-------+-------+---------+
| # connections | 1 | 4 | 8 |
+---------------+-------+-------+---------+
| SW (Gbps) | 7.26 | 24.70 | 50.30 |
+---------------+-------+-------+---------+
| HW (Gbps) | 18.50 | 64.30 | 92.90 |
+---------------+-------+-------+---------+
| Speedup | 2.55x | 2.56x | 1.85x * |
+---------------+-------+-------+---------+
* After linerate is reached, diff is observed in CPU util
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The AM65x SR2.0 MCU CPSW has fixed errata i2027 "CPSW: CPSW Does Not
Support CPPI Receive Checksum (Host to Ethernet) Offload Feature". This
errata also fixed for J271E SoC.
Use SOC bus data for K3 SoC identification and apply i2027 errata w/a only
for the AM65x SR1.0 SoC.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ensure that critical setting can only be configured when there are no
running netdevs - all ports are down.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Skip HW configuration when p0-rx-ptype-rrobin is changed as it will be done
by .ndev_open(),
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The MAC SL has to be initialized for each port otherwise
am65_cpsw_nuss_slave_disable_unused() will crash for disabled ports.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The pf_p0_rx_ptype_rrobin is global parameter so move its initialization in
probe.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The vlan configuration is not restored after interface down/up sequence.
Steps to check:
# ip link add link eth0 name eth0.100 type vlan id 100
# ifconfig eth0 down
# ifconfig eth0 up
This patch fixes it, restoring vlan ALE entries on .ndo_open().
Fixes: 93a7653031 ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use list_empty_careful() instead of open-coding.
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix some coding-style issues, including one which
made the function pointers in the struct ei_device
hard to understand.
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that all net_device operations are bundled together inside
mscc_ocelot.ko and no longer part of the common library, there's no
reason to export these symbols.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
So far RTL8401 was treated like a RTL8101e, means we relied on the BIOS
to configure MAC and PHY properly. Make RTL8401 a separate chip version
and copy MAC / PHY config from r8101 vendor driver.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Chip versions 13, 14, 15 are treated the same by the driver, therefore
let's merge them.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.
Fix this by returning 'netdev_tx_t' in this driver too.
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.
Fix this by returning 'netdev_tx_t' in this driver too.
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.
Fix this by returning 'netdev_tx_t' in this driver too.
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.
Fix this by returning 'netdev_tx_t' in this driver too.
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.
Fix this by returning 'netdev_tx_t' in this driver too.
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.
Fix this by returning 'netdev_tx_t' in this driver too.
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.
Fix this by returning 'netdev_tx_t' in this driver too.
Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
add support to get eeprom information from the plug-in module
with ethtool -m cmd.
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
add support to identify physical device by flashing an LED
attached to it with ethtool -p cmd.
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
add support to excute internal and external loopback test with
ethtool -t cmd.
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
add support to set TX/RX irq coalesce params with ethtool -C and
get these params with ethtool -c.
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
add support to set pause params with ethtool -A and get pause
params with ethtool -a. Also remove set_link_ksettings ops for VF
and enable pause by default.
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prior to this patch mlx5e tls rx handler was called unconditionally on
all rx frames and the decision whether a frame is a valid tls record
is done inside that function. A function call can be expensive especially
for regular rx packet rate. To avoid this, check the tls validity before
jumping into the tls rx handler.
While at it, split between kTLS device offload rx handler and FPGA tls rx
handler using a similar method.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
All callers of mlx5e_ktls_build_netdev() check capability
before the call.
Remove the repeated check in the function.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Resync communication with HW for kTLS RX is done via the
async ICOSQs.
kTLS RX resync requests might come in bursts. To improve the
success chances for such bursts, use a larger ICOSQ.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add global and per-channel ethtool SW stats for the device
offload.
Document the new counters in tls-offload.rst.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Implement the RX resync procedure, using the TLS async resync API.
The HW offload of TLS decryption in RX side might get out-of-sync
due to out-of-order reception of packets.
This requires SW intervention to update the HW context and get it
back in-sync.
Performance:
CPU: Intel(R) Xeon(R) CPU E5-2687W v4 @ 3.00GHz, 24 cores, HT off
NIC: ConnectX-6 Dx 100GbE dual port
Goodput (app-layer throughput) comparison:
+---------------+-------+-------+---------+
| # connections | 1 | 4 | 8 |
+---------------+-------+-------+---------+
| SW (Gbps) | 7.26 | 24.70 | 50.30 |
+---------------+-------+-------+---------+
| HW (Gbps) | 18.50 | 64.30 | 92.90 |
+---------------+-------+-------+---------+
| Speedup | 2.55x | 2.56x | 1.85x * |
+---------------+-------+-------+---------+
* After linerate is reached, diff is observed in CPU util.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
