Wrapping fwip_unicast_input() with NET_EPOCH_{ENTER,EXIT} to avoid a
NET_EPOCH_ASSERT() in netisr_dispatch().
Reviewed by: hselasky
MFC after: 2 weeks
(cherry picked from commit bdf316e892)
Usually on boot the MPS is already configured by BIOS. But we've
found that on hot-plug it is not true at least for our Supermicro
X11 boards. As result, mismatch between root's configuration of
256 bytes and device's default of 128 bytes cause problems for some
devices, while others seem to work fine.
MFC after: 1 month
Sponsored by: iXsystems, Inc.
(cherry picked from commit 5a898b2b78)
The correct name of this register is CTRL_EXT.
Approved by: markj
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D29967
(cherry picked from commit ba7b31b3e9)
Add support for current and future client platform PCI IDs. These are
all I219 variants and have no known driver changes versus previous
generation client platform I219 variants.
Reviewed by: markj
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D29801
(cherry picked from commit 59690eab57)
Restore 525e07418c after the iflib conversion of igb(4). This
reenables random MAC address generation when attaching to a VF with a
zeroed MAC.
PR: 253535
Reported by: Balaev PA <mail@void.so>
Reviewed by: markj
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D29785
(cherry picked from commit 68a46f11ea)
iwnstats was not compiling because of some issues raised by the clang
compiler due to -Werror. As a tool it is not connected to world build.
Add missing field "barker_mrc" initialization in struct
iwn_sensitivity_limits for -Wmissing-field-initializers, remove unused
pointer *is on iwn_stats_*_print functions and unused variables for
-Wunused-parameter and -Wunused-variable.
The value for field "barker_mrc" of struct iwn2030_sensitivity_limits
was obtained from linux 3.2 wireless/iwlwifi driver code (iwl-2000.c:115
.barker_corr_th_min_mrc = 390).
Also set BINDIR in Makefile to make it possible to install under
/usr/local/sbin/iwnstats as it require super user.
Reviewed by: adrian
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D29800
(cherry picked from commit 561d34d705)
A doomed VI does not have a valid ifnet.
Reported by: Jithesh Arakkan @ Chelsio
Sponsored by: Chelsio Communications
(cherry picked from commit 45d5c28439)
iscsid can be sleeping in iscsi_ioctl() causing the destroy_dev() to
sleep forever if iscsi.ko is unloaded while iscsid is running.
Reported by: Jithesh Arakkan @ Chelsio
Sponsored by: Chelsio Communications
(cherry picked from commit 89df484739)
This avoids some atomics by using counter_u64 for TX and relying on
existing single-threading (single ithread per rxq) for RX.
Sponsored by: Chelsio Communications
(cherry picked from commit fe496dc02a)
This type mirrors struct sge_ofld_rxq and holds state for TCP offload
transmit queues. Currently it only holds a work queue but will
include additional state in future changes.
Sponsored by: Chelsio Communications
(cherry picked from commit 077ba6a845)
This avoids mixing the use of two different enums which modern C
compilers warn about.
Sponsored by: Chelsio Communications
(cherry picked from commit 017902fc5f)
Completions for crypto requests on port 1 can sometimes return a stale
cookie value due to a firmware bug. Disable requests on port 1 by
default on affected firmware.
Sponsored by: Chelsio Communications
(cherry picked from commit 5fe0cd6503)
These fixes are only relevant for requests on the second port. In
some cases, the crypto completion data, completion message, and
receive descriptor could be written in the wrong order.
- Add a separate rx_channel_id that is a copy of the port's rx_c_chan
and use it when an RX channel ID is required in crypto requests
instead of using the tx_channel_id.
- Set the correct rx_channel_id in the CPL_RX_PHYS_ADDR used to write
the crypto result.
- Set the FID to the first rx queue ID on the adapter rather than the
queue ID of the first rx queue for the port.
- While here, use tx_chan to set the tx_channel_id though this is
identical to the previous value.
Reported by: Chelsio QA
Sponsored by: Chelsio Communications
(cherry picked from commit 8f885fd1f3)
These errors do not clear so to NULL, so the existing check was
treating these failures as success. The rest of do_pass_establish()
then tried to use the listen socket as if it was a connection socket
newly created by syncache_expand().
In addition, for negative return values, do not send a RST to the
peer.
Reported by: Sony Arpita Das @ Chelsio
Sponsored by: Chelsio Communications
(cherry picked from commit 1deaad9364)
"It looks like it would be less confusing to rename 'count' to
something like 'idx', since that's what it's used for in this
function."
Reviewed by: erj
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D29798
(cherry picked from commit 21afed4b1d)
First, two of those four checks are unreachable.
Second, I don't believe there should be ">=" instead of ">".
Third, bus_dma(9) already returns the same EFBIG if ">".
This fixes false I/O errors in worst S/G cases with maxphys >= 2MB.
MFC after: 1 week
(cherry picked from commit 0f29396e49)
There is a weird limit of AGTIAPI_MAX_DMA_SEGS (128) S/G segments per
I/O since the initial driver import. I don't know why it was added,
can only guess some hardware limitation, but in worst case it means
maximum I/O size of 508KB. Respect it to be safe, rounding to 256KB.
MFC after: 1 week
Sponsored by: iXsystems, Inc.
(cherry picked from commit 3e34783420)
It is a direct request for data corruptions, one report of which we
have received. I am very surprised that only one.
MFC after: 1 week
Sponsored by: iXsystems, Inc.
(cherry picked from commit 8434a65ce4)
Such type cannot be used in code that is in common between
FreeBSD and Linux. Use the FreeBSD type instead.
MFC after: 3 days
Reported by: markj
Differential Revision: https://reviews.freebsd.org/D29677
(cherry picked from commit 70275a6735)
The driver needs to provide a LinuxKPI device structure to register
itself with the IB subsystem. It was erroneously using a copy of its
FreeBSD device structure for this purpose.
Use linux_pci_attach_device() instead, following the example of the
Chelsio iwarp driver. Also ensure that we don't leak the faked device
during detach.
Reviewed by: hselasky
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D29595
(cherry picked from commit 56cbd386fb)
Under geom(4) nvme_ns_bio_process() is on the path where sleep
is prohibited as g_io_shedule_down() calls THREAD_NO_SLEEPNG()
before geom->start().
Reviewed By: imp
Differential Revision: https://reviews.freebsd.org/D29539
(cherry picked from commit a78109d5db)
LLVM12 complains if you change the symbol binding:
error: mfs_root_end changed binding to STB_WEAK [-Werror,-Winline-asm]
error: mfs_root changed binding to STB_WEAK [-Werror,-Winline-asm]
(cherry picked from commit 69e18c9b7b)
We don't need the result before next sleep time, so no reason to
additionally increase interrupt latency.
While there, remove extra PM ticks to microseconds conversion, making
C2/C3 sleep times look 4 times smaller than really. The conversion
is already done by AcpiGetTimerDuration(). Now I see reported sleep
times up to 0.5s, just as expected for planned 2 wakeups per second.
MFC after: 1 month
(cherry picked from commit 2cee045b4d)
When we enter C2+ state via memory read, it may take chipset some
time to stop CPU. Extra register read covers that time. But MWAIT
makes CPU stop immediately, so we don't need to waste time after
wakeup with interrupts still disabled, increasing latency.
On my system it reduces ping localhost latency, waking up all CPUs
once a second, from 277us to 242us.
MFC after: 1 month
(cherry picked from commit 075e4807df)
Even though the information is very limited, it seems the intent of
this flag is to control ACPI_BITREG_BUS_MASTER_STATUS use for C3,
not force ACPI_BITREG_ARB_DISABLE manipulations for C2, where it was
never needed, and which register not really doing anything for years.
It wasted lots of CPU time on congested global ACPI hardware lock
when many CPU cores were trying to enter/exit deep C-states same time.
On idle 80-core system it pushed ping localhost latency up to 20ms,
since badport_bandlim() via counter_ratecheck() wakes up all CPUs
same time once a second just to synchronously reset the counters.
Now enabling C-states increases the latency from 0.1 to just 0.25ms.
Discussed with: kib
MFC after: 1 month
(cherry picked from commit 455219675d)
For guests running under some kind of VMMs, configuration structure is
available in memory space but not I/O space.
Reported by: Yuan Rui <number201724@me.com>
Reviewed by: rpokala, bryanv, jhb
Approved by: philip (mentor)
Differential Revision: https://reviews.freebsd.org/D28818
(cherry picked from commit cf5d111240)
The MSI-X resource shouldn't be assumed to be always on BAR1.
The Virtio v1.1 Spec did not specify that MSI-X table and PBA BAR has to
be BAR1 either.
Reported by: Yuan Rui <number201724@me.com>
Reviewed by: bryanv, jhb
Approved by: philip (mentor)
Differential Revision: https://reviews.freebsd.org/D28817
(cherry picked from commit faf9a4e914)
Set default alternate setting when USB audio devices are not in use,
to activate power save features.
Differential Revision: https://reviews.freebsd.org/D28032
Suggested by: Shichun_Ma@Dell.com
Sponsored by: Mellanox Technologies // NVIDIA Networking
(cherry picked from commit 31070b5bc7)
Use strncmp() instead of bcmp(), so that we don't have to find the
minimum of the string lengths before comparing.
Reviewed by: kib
Reported by: KASAN
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D29463
(cherry picked from commit 3428b6c050)
