mjg [Wed, 8 May 2019 16:30:38 +0000 (16:30 +0000)]
Reduce umtx-related work on exec and exit
- there is no need to take the process lock to iterate the thread
list after single-threading is enforced
- typically there are no mutexes to clean up (testable without taking
the global umtx lock)
- typically there is no need to adjust the priority (testable without
taking thread lock)
Reviewed by: kib
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D20160
jhibbits [Wed, 8 May 2019 16:15:28 +0000 (16:15 +0000)]
powerpc/booke: Rewrite pmap_sync_icache() a bit
* Make mmu_booke_sync_icache() use the DMAP on 64-bit prcoesses, no need to
map the page into the user's address space. This removes the
pvh_global_lock from the equation on 64-bit.
* Don't map the page with user-readability on 32-bit. I don't know what the
chance of a given user process being able to access the NULL page when
another process's page is added there, but it doesn't seem like a good
idea to map it to NULL with user read permissions.
* Only sync as much as we need to. There are only two significant places
where pmap_sync_icache is used: proc_rwmem(), and the SIGILL second-chance
for powerpc. The SIGILL second chance is likely the most common, and only
syncs 4 bytes, so avoid the other 127 loop iterations (4096 / 32 byte
cacheline) in __syncicache().
jhibbits [Wed, 8 May 2019 16:05:18 +0000 (16:05 +0000)]
powerpc/booke: Do as much work outside of TLB locks as possible
Reduce the surface area of the TLB locks. Unfortunately the same trick for
serializing the tlbie instruction on OEA64 cannot be used here to reduce the
scope of the tlbivax mutex to the tlbsync only, as the mutex also serializes
the TLB miss lock as a side effect, so contention on this lock may not be
reducible any further.
o Implement a bounce buffer based on device reserved memory.
Grab device reserved physical memory regions from FDT using standard
"memory-region" property and use vmem(9) to allocate buffers from it.
The same vmem could be used by DMA engine drivers to allocate memory for
DMA descriptors.
This is required for platforms that provide uncached memory region
reserved exclusively for DMA operations.
o Change sleepable sx(9) lock type to non-sleepable mutex(9) since
network drivers usually hold mutex during DMA operations. So we don't
take sleepable lock after non-sleepable.
Tested on U.S. Government Furnished Equipment (GFE) 64-bit RISC-V cores.
cem [Wed, 8 May 2019 14:54:32 +0000 (14:54 +0000)]
random(4): Don't complain noisily when an entropy source is slow
Mjg@ reports that RDSEED (r347239) causes a lot of logspam from this printf,
and I don't feel that it is especially useful (even ratelimited). There are
many other quality/quantity checks we're not performing on entropy sources;
lack of high frequency availability does not disqualify a good entropy
source.
There is some discussion in the linked Differential about what logging might
be appropriate and/or polling policy for slower TRNG sources. Please feel
free to chime in if you have opinions.
hselasky [Wed, 8 May 2019 11:09:08 +0000 (11:09 +0000)]
Make command workqueue persistant in mlx5core.
There is no reason to re-create the command workqueue during healthcare.
This also fixes an issue where a previous work struct may refer to a
destroyed workqueue.
MFC after: 3 days
Sponsored by: Mellanox Technologies
hselasky [Wed, 8 May 2019 11:08:48 +0000 (11:08 +0000)]
Fix race between driver unload and dumping firmware in mlx5core.
Present code uses lock-less accesses to the dump data to prevent top
level ioctls from blocking bottom-level call to dump. Unfortunately, this
depends on the type stability of the dump data structure, which makes it
non-functional during driver teardown.
Switch to the mutex locking scheme where top levels use the mutex in the
bound regions, while copyouts and drain for completion utilize condvars.
The mutex lifetime is guaranteed to be strictly larger than the time
interval where driver can initiate dump, and most of the control fields
of the old struct mlx5_dump_data are directly embedded into struct
mlx5_core_dev.
hselasky [Wed, 8 May 2019 11:07:20 +0000 (11:07 +0000)]
Flush command workqueue when command completion is triggered in mlx5core.
Avoid race for command completion when triggering a command completions event.
Serialize operation by queueing all commands on the same work queue.
This can happen when healthcare triggers.
MFC after: 3 days
Sponsored by: Mellanox Technologies
hselasky [Wed, 8 May 2019 11:07:00 +0000 (11:07 +0000)]
Make command timeout way shorter in mlx5core.
The command timeout is terribly long, whole two hours. Make it 60s so if
things do go wrong, the user gets feedback in relatively short time, so
they can take corrective actions and/or investigate using tools and such.
hselasky [Wed, 8 May 2019 10:59:16 +0000 (10:59 +0000)]
Extend the counters framework in mlx5en(4).
Allow more macro arguments and split the variable type and name into
separate arguments. This allows simple and powerful copy and extraction
of values from IFC based structures into SYSCTLs with the use of a single
macro.
MFC after: 3 days
Sponsored by: Mellanox Technologies
hselasky [Wed, 8 May 2019 10:58:06 +0000 (10:58 +0000)]
Implement reading PCI power status in mlx5core.
Implement a watchdog as part of the healtcare subsystem which
reads the PCI power status during startup and upon the PCI
power status change event and store it into the core device
structure. This value is then exported to user-space via a
read-only SYSCTL. A dmesg print has been added to inform
the admin about the PCI power status.
MFC after: 3 days
Sponsored by: Mellanox Technologies
hselasky [Wed, 8 May 2019 10:57:16 +0000 (10:57 +0000)]
Always return success for RoCE modify port in mlx5ib.
CM layer calls ib_modify_port() regardless of the link layer.
For the Ethernet ports, qkey violation and Port capabilities
are meaningless. Therefore, always return success for ib_modify_port
calls on the Ethernet ports.
hselasky [Wed, 8 May 2019 10:53:47 +0000 (10:53 +0000)]
Correct check for the calibration generation in mlx5en(4).
If generation is cleared due to hardware clock failure, check for it before
the divisor is used. Actually clear generation when failure occurs.
While there, stop doing the calculations inside the generation loop. Since
all members of mlx5e_clbr_point are used for calculations, get the
local copy of the structure and use it after generation stabilized.
hselasky [Wed, 8 May 2019 10:52:32 +0000 (10:52 +0000)]
Use software counters for rx_packets and rx_bytes in mlx5en(4).
The physical- and virtual- port counters might not reflect the amount
of data received after address filtering. Use the software counters
instead for rx_packets and rx_bytes to know exactly how much data
was received.
MFC after: 3 days
Sponsored by: Mellanox Technologies
hselasky [Wed, 8 May 2019 10:42:33 +0000 (10:42 +0000)]
Fix netstat counters mapping in mlx5en(4).
The current mapping of driver counters to netstat counters is wrong.
For example, a single jabber packet, will cause the Ierrs counter to
count three times.
The work for mapping the hardware and software counters to their right
place in netstat counters were already done in Linux, take that as is
to the FreeBSD driver.
hselasky [Wed, 8 May 2019 10:42:05 +0000 (10:42 +0000)]
Fix endless loop in ipoib_poll().
ib_req_notify_cq may return negative value which will indicate a
failure. In the case of uncorrectable error, we will end up in an
endless loop. Fix that, by going to another loop with poll_more
only if there is anything left to poll.
hselasky [Wed, 8 May 2019 10:39:53 +0000 (10:39 +0000)]
Query and cache PCAM, MCAM registers on initialization in mlx5core.
On load_one, we now cache our capabilities registers internally, similar
to QUERY_HCA_CAP. Capabilities can later be queried using macros
introduced in this patch.
hselasky [Wed, 8 May 2019 10:39:25 +0000 (10:39 +0000)]
Implement PCAM, MCAM access register commands in mlx5core.
Introduced registers will expose capabilities of new registers and
features related to port/management.
Driver will query MCAM and PCAM in order to avoid failing on old
firmwares with lack of support.
PCAM and MCAM registers will provide information regarding firmware
support for different features, in order to avoid cases where new driver
combined with old firmware results in syndromes (for ex. PCIe counters
before this patchset).
hselasky [Wed, 8 May 2019 10:38:06 +0000 (10:38 +0000)]
Add Fast teardown support to mlx5core.
Today mlx5 devices support two teardown modes:
1- Regular teardown
2- Force teardown
This change introduces the enhanced version of the "Force teardown" that
allows SW to perform teardown in a faster way without the need to reclaim
all the pages.
Fast teardown provides the following advantages:
1- Fix a FW race condition that could cause command timeout
2- Avoid moving to polling mode
3- Close the vport to prevent PCI ACK to be sent without been
scattered to memory
hselasky [Wed, 8 May 2019 10:35:55 +0000 (10:35 +0000)]
Configure firmware to use RX hash format in mini CQE in mlx5en(4).
When using CQE zipping, one can choose between RX hash and Checksum.
This will indicate the parameter on which a zipping session should be
stopped.
While porting the Linux code, Checksum was chosen. However, the value
of Checksum is not being used anywhere.
For the FreeBSD driver, we prefer to use the RX hash format which will
guarantee the RX hash value for all the mini CQEs.
While at it, make sure to initialize the Checksum value in the
decompressed CQE.
hselasky [Wed, 8 May 2019 10:35:35 +0000 (10:35 +0000)]
Disable CQE zipping by default in mlx5en(4).
After doing performance measurements, it seems like CQE zipping doesn't
have any significant benefit.
Moreover, we know that this feature is disabled by default on other
operating systems (Linux for example).
hselasky [Wed, 8 May 2019 10:35:14 +0000 (10:35 +0000)]
Split mlx5e_update_stats_work() in mlx5en(4).
Split the function into the mlx5e_update_stats_locked() core and make
mlx5e_update_stats_work() call the _locked helper, similar to many other
places in the kernel. This improves the code structure, making the
locking clean.
hselasky [Wed, 8 May 2019 10:34:42 +0000 (10:34 +0000)]
Implement fast close of RX channel in mlx5en(4).
Instead of waiting for all jobs to be cancelled, simply close the completion
queue to prevent more completion events and let mlx5e_destroy_rq() cleanup
the remaining mbufs.
MFC after: 3 days
Sponsored by: Mellanox Technologies
hselasky [Wed, 8 May 2019 10:32:03 +0000 (10:32 +0000)]
Fix tx_jumbo_packets counter in mlx5en(4).
Instead of reading Ethernet RFC 2819 pXtoYoctets counters from
hardware which counts RX octets, count tx_stat_pXtoYoctets from
Ethernet extended counters which counts TX octets.
TX jumbo counters should be accumulated only after the PPCNT
counters were fetched from hardware with their latest value.
hselasky [Wed, 8 May 2019 10:30:47 +0000 (10:30 +0000)]
Protect from infinite sw-reset loop in mlx5core.
Avoid an infinite software firmware reset loop that may be caused by a
hardware bug by limiting the maximum number of resets.
The counter between resets is reset by request for reset, and not by a
successful reset.
The interval between two resets can be configured via sysctl:
hw.mlx5.sw_reset_timeout
which is global to all mlx5 devices in the system.
hselasky [Wed, 8 May 2019 10:28:18 +0000 (10:28 +0000)]
Add temperature warning event to log in mlx5core.
Temperature warning event is sent by FW to indicate high temperature
as detected by one of the sensors on the board.
Add handling of this event by writing the numbers of the alert sensors
to the kernel log.
hselasky [Wed, 8 May 2019 10:27:29 +0000 (10:27 +0000)]
Correctly define the interface state bits in mlx5en(4).
While at it remove unused interface state bits. This also fixes and issue
during shutdown:
There is an issue where the firmware fails during mlx5_load_one,
the health_care timer detects the issue and schedules a health_care call.
Then the mlx5_load_one detects the issue, cleans up and quits. Then
the health_care starts and calls mlx5_unload_one to clean up the resources
that no longer exist and causes kernel panic.
The root cause is that the bit MLX5_INTERFACE_STATE_DOWN is not set
after mlx5_load_one fails. The solution is removing the bit
MLX5_INTERFACE_STATE_DOWN and quit mlx5_unload_one if the
bit MLX5_INTERFACE_STATE_UP is not set. The bit MLX5_INTERFACE_STATE_DOWN
is redundant and we can use MLX5_INTERFACE_STATE_UP instead.
dim [Wed, 8 May 2019 05:45:00 +0000 (05:45 +0000)]
Pull in r360099 from upstream llvm trunk (by Eli Friedman):
[ARM] Glue register copies to tail calls.
This generally follows what other targets do. I don't completely
understand why the special case for tail calls existed in the first
place; even when the code was committed in r105413, call lowering
didn't work in the way described in the comments.
Stack protector lowering breaks if the register copies are not glued
to a tail call: we have to insert the stack protector check before
the tail call, and we choose the location based on the assumption
that all physical register dependencies of a tail call are adjacent
to the tail call. (See FindSplitPointForStackProtector.) This is sort
of fragile, but I don't see any reason to break that assumption.
I'm guessing nobody has seen this before just because it's hard to
convince the scheduler to actually schedule the code in a way that
breaks; even without the glue, the only computation that could
actually be scheduled after the register copies is the computation of
the call address, and the scheduler usually prefers to schedule that
before the copies anyway.
This should fix several instances of "Bad machine code: Using an
undefined physical register", when compiling ports such as
multimedia/vlc, audio/alsa-lib and devel/avro-c for armv6, with
-fstack-protector-strong.
kevans [Wed, 8 May 2019 02:32:11 +0000 (02:32 +0000)]
tun/tap: merge and rename to `tuntap`
tun(4) and tap(4) share the same general management interface and have a lot
in common. Bugs exist in tap(4) that have been fixed in tun(4), and
vice-versa. Let's reduce the maintenance requirements by merging them
together and using flags to differentiate between the three interface types
(tun, tap, vmnet).
This fixes a couple of tap(4)/vmnet(4) issues right out of the gate:
- tap devices may no longer be destroyed while they're open [0]
- VIMAGE issues already addressed in tun by kp
[0] emaste had removed an easy-panic-button in r240938 due to devdrn
blocking. A naive glance over this leads me to believe that this isn't quite
complete -- destroy_devl will only block while executing d_* functions, but
doesn't block the device from being destroyed while a process has it open.
The latter is the intent of the condvar in tun, so this is "fixed" (for
certain definitions of the word -- it wasn't really broken in tap, it just
wasn't quite ideal).
ifconfig(8) also grew the ability to map an interface name to a kld, so
that `ifconfig {tun,tap}0` can continue to autoload the correct module, and
`ifconfig vmnet0 create` will now autoload the correct module. This is a
low overhead addition.
(MFC commentary)
This may get MFC'd if many bugs in tun(4)/tap(4) are discovered after this,
and how critical they are. Changes after this are likely easily MFC'd
without taking this merge, but the merge will be easier.
mav [Wed, 8 May 2019 01:35:43 +0000 (01:35 +0000)]
Fix dataset name comparison in zfs_compare().
The code never returned match comparing two datasets (not snapshots).
As result, uu_avl_find(), called from zfs_callback(), never succeeded,
allowing to add same dataset into the list multiple times, for example:
# zfs get name pers pers pers@z pers@z
NAME PROPERTY VALUE SOURCE
pers name pers -
pers name pers -
pers@z name pers@z -
With the patch:
# zfs get name pers pers pers@z pers@z
NAME PROPERTY VALUE SOURCE
pers name pers -
pers@z name pers@z -
cem [Wed, 8 May 2019 00:45:16 +0000 (00:45 +0000)]
random: x86 driver: Prefer RDSEED over RDRAND when available
Per
https://software.intel.com/en-us/blogs/2012/11/17/the-difference-between-rdrand-and-rdseed
, RDRAND is a PRNG seeded from the same source as RDSEED. The source is
more suitable as PRNG seed material, so prefer it when the RDSEED intrinsic
is available (indicated in CPU feature bits).