sfxge: do not use DEBUG_FLAGS to enable extra debug checks
DEBUG_FLAGS are set to DEBUG option value when kernel is built.
For example, it is -g in GENERIC config to have debug symbols.
Also DEBUG_FLAGS are used to determine if ctfconvert should keep
debug symbols.
Since we redefined DEBUG_FLAGS, debug symbols were always missing.
ctfconvert complains about it during kernel build.
It is incorrect to append DEBUG_FLAGS, since if DEBUG has no -g (or
similar), we'll have no debug symbols and ctfconvert will complain.
If it incorrect to always have -g in our DEBUG_FLAGS, since debug
symbols presence should be controllable by kernel config.
So, just add disabled by default addition of -DDEBUG=1 to CFLAGS.
Reviewed by: imp
Sponsored by: Solarflare Communications, Inc.
sfxge: add 7xxx NICs family support
Support 7xxx adapters including firmware-assisted TSO and VLAN tagging:
- Solarflare Flareon Ultra 7000 series 10/40G adapters:
- Solarflare SFN7042Q QSFP+ Server Adapter
- Solarflare SFN7142Q QSFP+ Server Adapter
- Solarflare Flareon Ultra 7000 series 10G adapters:
- Solarflare SFN7022F SFP+ Server Adapter
- Solarflare SFN7122F SFP+ Server Adapter
- Solarflare SFN7322F Precision Time Synchronization Server Adapter
- Solarflare Flareon 7000 series 10G adapters:
- Solarflare SFN7002F SFP+ Server Adapter
Support utilities to configure adapters and update firmware.
The work is done by Solarflare developers
(Andy Moreton, Andrew Lee and many others),
Artem V. Andreev <Artem.Andreev at oktetlabs.ru> and me.
Sponsored by: Solarflare Communications, Inc.
Implement multiqueue (max 2 tx/rx queues) for the 82574L chipset.
Change default tuning parameters to handle this new configuration if
EM_MULTIQUEUE is set in the kernel configuration. Off by default.
See r283959 changelog for the scope of these changes.
Relnotes: Yes
Sponsored by: Limelight Networks
- Add vxlan interface
- Use the size of the Ethernet address, not the entire header, when
copying into forwarding entry.
- Prefix all the vxlan ifconfig commands so they are unique
Add a dtb module for AM335x systems (just Beaglebone right now).
Remove the static DTB config and instead build modules/dtb/am335x.
Also, remove WITHOUT_MODULES="ahc" which was added long ago to work
around build problems that have long since been fixed correctly.
Revert accidentally commited modules/Makefile file from r279824.
Create a module to install the Raspberry Pi dtb files.
Pull in the rpi.dts -> rpi.dtb module (dtb/rpi) and have it install
rpi.dtb in /boot/dtb by default.
Add a module to build the dtb files for all supported imx6 systems.
Remove imx6s-wandboard.dts, there is no such file.
Overhaul if_gre(4).
Split it into two modules: if_gre(4) for GRE encapsulation and
if_me(4) for minimal encapsulation within IP.
gre(4) changes:
* convert to if_transmit;
* rework locking: protect access to softc with rmlock,
protect from concurrent ioctls with sx lock;
* correct interface accounting for outgoing datagramms (count only payload size);
* implement generic support for using IPv6 as delivery header;
* make implementation conform to the RFC 2784 and partially to RFC 2890;
* add support for GRE checksums - calculate for outgoing datagramms and check
for inconming datagramms;
* add support for sending sequence number in GRE header;
* remove support of cached routes. This fixes problem, when gre(4) doesn't
work at system startup. But this also removes support for having tunnels with
the same addresses for inner and outer header.
* deprecate support for various GREXXX ioctls, that doesn't used in FreeBSD.
Use our standard ioctls for tunnels.
me(4):
* implementation conform to RFC 2004;
* use if_transmit;
* use the same locking model as gre(4);
PR: 164475
MFC r274289 (by bz):
gcc requires variables to be initialised in two places. One of them
is correctly used only under the same conditional though.
For module builds properly check if the kernel supports INET or INET6,
as otherwise various mips kernels without IPv6 support would fail to build.
MFC r274964:
Add ip_gre.h to ObsoleteFiles.inc.
r277637, and r283149 (by emaste@).
r276485 is the real change here, the rest deal with the fallout of
mp_ring's reliance on 64b atomics.
Use the incorrectly spelled 'eigth' from struct pkthdr in this branch
instead of MFC'ing r261733, which would have renamed the field of a
public structure in a -STABLE branch.
---
r276480:
Temporarily unplug cxgbe(4) from !amd64 builds.
r276485:
cxgbe(4): major tx rework.
a) Front load as much work as possible in if_transmit, before any driver
lock or software queue has to get involved.
b) Replace buf_ring with a brand new mp_ring (multiproducer ring). This
is specifically for the tx multiqueue model where one of the if_transmit
producer threads becomes the consumer and other producers carry on as
usual. mp_ring is implemented as standalone code and it should be
possible to use it in any driver with tx multiqueue. It also has:
- the ability to enqueue/dequeue multiple items. This might become
significant if packet batching is ever implemented.
- an abdication mechanism to allow a thread to give up writing tx
descriptors and have another if_transmit thread take over. A thread
that's writing tx descriptors can end up doing so for an unbounded
time period if a) there are other if_transmit threads continuously
feeding the sofware queue, and b) the chip keeps up with whatever the
thread is throwing at it.
- accurate statistics about interesting events even when the stats come
at the expense of additional branches/conditional code.
The NIC txq lock is uncontested on the fast path at this point. I've
left it there for synchronization with the control events (interface
up/down, modload/unload).
c) Add support for "type 1" coalescing work request in the normal NIC tx
path. This work request is optimized for frames with a single item in
the DMA gather list. These are very common when forwarding packets.
Note that netmap tx in cxgbe already uses these "type 1" work requests.
d) Do not request automatic cidx updates every 32 descriptors. Instead,
request updates via bits in individual work requests (still every 32
descriptors approximately). Also, request an automatic final update
when the queue idles after activity. This means NIC tx reclaim is still
performed lazily but it will catch up quickly as soon as the queue
idles. This seems to be the best middle ground and I'll probably do
something similar for netmap tx as well.
e) Implement a faster tx path for WRQs (used by TOE tx and control
queues, _not_ by the normal NIC tx). Allow work requests to be written
directly to the hardware descriptor ring if room is available. I will
convert t4_tom and iw_cxgbe modules to this faster style gradually.
r276498:
cxgbe(4): remove buf_ring specific restriction on the txq size.
r277225:
Make cxgbe(4) buildable with the gcc in base.
r277226:
Allow cxgbe(4) to be built on i386. Driver attach will succeed only on
a subset of i386 systems.
r277227:
Plug cxgbe(4) back into !powerpc && !arm builds, instead of building it
on amd64 only.
r277230:
Build cxgbe(4) on powerpc64 too.
r277637:
Make sure the compiler flag to get cxgbe(4) to compile with gcc is used
only when gcc is being used. This is what r277225 should have been.
Rename the kld for oce(4) to if_oce.ko. ifconfig(8) has special knowledge
about kld filenames for network drivers that requires them to follow the
pattern of if_<foo>. This also fixes the existing documentation in the
manpage which says to use if_oce_load=YES in loader.conf.
PR: 199095
- Re-introduce "device ixgbe" option for kernel configs. This allows
users to continue using existing kernel configurations, while still
letting if_ix and if_ixv exist to allow ifconfig magic to work.
Though the amd64 GENERIC config has "device ix" and "device ixv" instead of
"device ixgbe".
This is achieved by making the if_ixgbe module a stub that depends
on if_ix and if_ixv.
- Replace if_baudrate assignment with if_initbaudrate() call.
Thanks to jhb@ for the stub module suggestion and pointing out the if_baudrate
error.
Approved by: jfv (mentor)
This update brings few features:
o Support for the setmaster/dropmaster ioctls. For instance, they
are used to run multiple X servers simultaneously.
o Support for minor devices. The only user-visible change is a new
entry in /dev/dri but it is useless at the moment. This is a
first step to support render nodes [1].
The main benefit is to greatly reduce the diff with Linux (at the
expense of an unreadable commit diff). Hopefully, next upgrades will be
easier.
No updates were made to the drivers, beside adapting them to API
changes.
[1] https://en.wikipedia.org/wiki/Direct_Rendering_Manager#Render_nodes
r280814 is merged at the same time to avoid a short window where RANDR
might be broken:
drm: Import Linux commit 9bc3cd5673d84d29272fa7181a4dfca83cbb48c1
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri May 31 12:17:08 2013 +0000
drm: Sort connector modes based on vrefresh
Keeping the modes sorted by vrefresh before the pixel clock makes the
mode list somehow more pleasing to the eye.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
PR: 198936 (r280814)
Tested by: Many people
MFC of: r280183, r280187 (original commit by glebius), r280814
Relnotes: yes
Drop experimental ext2fs dir_index support.
The htree directory index is a highly desirable feature for research
purposes and was meant to improve performance in our ext2/3 driver.
Unfortunately our implementation has two problems:
- It never really delivered any performance improvement.
- It appears to corrupt the filesystem in undetermined circumstances.
Strictly speaking dir_index is not required for read/write support in
ext2/3 and our limited ext4 support still works fine without it.
Regain stability in the ext2 driver by removing it. We may need it back
(fixed) if we want to support encrypted ext4 support but thanks to the
wonders of version control we can always revert this change and bring it
back.
PR: 191895
PR: 198731
PR: 199309
cxgbe(4): Add a minimal if_cxl module that pulls in the real driver as
a dependency. This ensures "ifconfig cxl<n> ..." does the right thing
even when it's run with no driver loaded.
if_cxl.ko is the tiniest module in /boot/kernel.
sfxge: compile out LRO if kernel is compiled without IPv4 and IPv6
Sponsored by: Solarflare Communications, Inc.
Approved by: gnn (mentor)
MFC: 279411
Unbreak 'make depend' with sfxge by removing debugging code activated in the
INET || INET6 case
X-MFC with: r279398
Pointyhat to: arybchik
sfxge: adding version info to device description
The information is required for NIC update and config tools.
Submitted by: Artem V. Andreev <Artem.Andreev at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Approved by: gnn (mentor)
An update for the i915 GPU driver, which brings the code up to Linux
commit 4d93914ae3db4a897ead4b.
MFC r277959 (by adrian):
Fix backlight for ivybridge based laptops (and whatever else comes through
this codepath.)
MFC r278146:
Do not attach to the unsupported chipsets, unless magic tunable is
frobbed.
MFC r278147, r278148:
Fix sign for the error code returned from the driver-specific code.
MFC r278152:
Do not access gmbus_ports array past its end.
MFC r278159 (by emaste):
Remove duplicate intel_fbc_enabled prototype.
279573: Sync AHCI driver with HEAD.
Due to code reorganization in r271146 and many previous reordered merges it
is problematic to merge those revisions separately.
r277675:
Add MK_ISCSI knob for building the iscsi initiator, iscsi daemon, kernel
modules, etc
Sponsored by: EMC / Isilon Storage Division
r277726:
Build sbin/iscontrol again if MK_ISCSI != no
Pointyhat to: me
r278070:
Remove duplicate MK_ISCSI block and sort the conditional blocks so this error
won't crop up again in the future
Reported by: gjb
Move the ACPI PM timer emulation into vmm.ko.
MFC r273706
Change the type of the first argument to the I/O emulation handlers to
'struct vm *'.
MFC r273710
Add a comment explaining the intent behind the I/O reservation [0x72-0x77].
MFC r273744
Add foo_genassym.c files to DPSRCS so dependencies for them are generated.
This ensures these objects are rebuilt to generate an updated header of
assembly constants if needed.
MFC r274045
If the start bit, PxCMD.ST, is cleared and nothing is in-flight then
PxCI, PxSACT, PxCMD.CCS and PxCMD.CR should be 0.
MFC r274076
Improve the ability to cancel an in-flight request by using an interrupt,
via SIGCONT, to force the read or write system call to return prematurely.
MFC r274330
To allow a request to be submitted from within the callback routine of
a completing one increase the total by 1 but don't advertise it.
MFC r274931
Change the lower bound for guest vmspace allocation to 0 instead of using
the VM_MIN_ADDRESS constant.
MFC r275817
For level triggered interrupts clear the PIC IRR bit when the interrupt pin
is deasserted.
MFC r275850
Fix 8259 IRQ priority resolver.
MFC r275952
Various 8259 device model improvements.
MFC r275965
Emulate writes to the IA32_MISC_ENABLE MSR.
Add support AMD processors with the SVM/AMD-V hardware extensions.
MFC r273749
Remove bhyve SVM feature printf's now that they are available in the general
CPU feature detection code.
MFC r273766
Add missing 'break' pointed out by Coverity CID 1249760.
MFC r276098
Allow ktr(4) tracing of all guest exceptions via the tunable "hw.vmm.trace_guest_exceptions"
MFC r276392
Inject #UD into the guest when it executes either 'MONITOR' or 'MWAIT' on an
AMD/SVM host.
MFC r276402
Remove "svn:mergeinfo" property that was dragged along when these files were
svn copied in r273375.
Rename the AMD MSR_PERFCTR[0-3] so the Pentium Pro MSR_PERFCTR[0-1] aren't
redefined.
MFC r273214
Fix build to not bogusly always rebuild vmm.ko.
MFC r273338
Add support for AMD's nested page tables in pmap.c:
- Provide the correct bit mask for various bit fields in a PTE (e.g. valid bit)
for a pmap of type PT_RVI.
- Add a function 'pmap_type_guest(pmap)' that returns TRUE if the pmap is of
type PT_EPT or PT_RVI.
Add CPU_SET_ATOMIC_ACQ(num, cpuset):
This is used when activating a vcpu in the nested pmap. Using the 'acquire'
variant guarantees that the load of the 'pm_eptgen' will happen only after
the vcpu is activated in 'pm_active'.
Add defines for various AMD-specific MSRs.
Discussed with: kib (r261321)
Fix a recursive lock acquisition in vi_reset_dev().
MFC r270434
Return the spurious interrupt vector (IRQ7 or IRQ15) if the atpic cannot find
any unmasked pin with an interrupt asserted.
MFC r270436
Fix a bug in the emulation of CPUID leaf 0x4.
MFC r270437
Add "hw.vmm.topology.threads_per_core" and "hw.vmm.topology.cores_per_package"
tunables to modify the default cpu topology advertised by bhyve.
MFC r270855
Set the 'inst_length' to '0' early on before any error conditions are detected
in the emulation of the task switch. If any exceptions are triggered then the
guest %rip should point to instruction that caused the task switch as opposed
to the one after it.
MFC r270857
The "SUB" instruction used in getcc() actually does 'x -= y' so use the
proper constraint for 'x'. The "+r" constraint indicates that 'x' is an
input and output register operand.
While here generate code for different variants of getcc() using a macro
GETCC(sz) where 'sz' indicates the operand size.
Update the status bits in %rflags when emulating AND and OR opcodes.
MFC r271439
Initialize 'bc_rdonly' to the right value.
MFC r271451
Optimize the common case of injecting an interrupt into a vcpu after a HLT
by explicitly moving it out of the interrupt shadow.
MFC r271888
Restructure the MSR handling so it is entirely handled by processor-specific
code.
MFC r271890
MSR_KGSBASE is no longer saved and restored from the guest MSR save area. This
behavior was changed in r271888 so update the comment block to reflect this.
MFC r271891
Add some more KTR events to help debugging.
MFC r272197
mmap(2) requires either MAP_PRIVATE or MAP_SHARED for non-anonymous mappings.
MFC r272395
Get rid of code that dealt with the hardware not being able to save/restore
the PAT MSR on guest exit/entry. This workaround was done for a beta release
of VMware Fusion 5 but is no longer needed in later versions.
All Intel CPUs since Nehalem have supported saving and restoring MSR_PAT
in the VM exit and entry controls.
MFC r272670
Inject #UD into the guest when it executes either 'MONITOR' or 'MWAIT'.
MFC r272710
Implement the FLUSH operation in the virtio-block emulation.
MFC r272838
iasl(8) expects integer fields in data tables to be specified as hexadecimal
values. Therefore the bit width of the "PM Timer Block" was actually being
interpreted as 50-bits instead of the expected 32-bit.
This eliminates an error message emitted by a Linux 3.17 guest during boot:
"Invalid length for FADT/PmTimerBlock: 50, using default 32"
MFC r272839
Support Intel-specific MSRs that are accessed when booting up a linux in bhyve:
- MSR_PLATFORM_INFO
- MSR_TURBO_RATIO_LIMITx
- MSR_RAPL_POWER_UNIT
MFC r273108
Emulate "POP r/m". This is needed to boot OpenBSD/i386 MP kernel in bhyve.
MFC r273212
Support stopping and restarting the AHCI command list via toggling PxCMD.ST
from '1' to '0' and back. This allows the driver a chance to recover if
for instance a timeout occurred due to activity on the host.
Support upto 256VD.
MFC r272737:
Support 32-bit linux binaries on FreeBSD 64bit.
MFC r272738:
Fix the minor svn add issue.
MFC r272739:
Extended MSI-x vectors support for Invader and Fury(12Gb/s HBA).
MFC r272740:
Add d_poll support.
MFC r272741:
Fix leak of mfi cmd in the passthru and correctly limit oustanding.
MFC r272742:
Import vendor Phase 6.5 driver
MFC r272744:
Style (9) fixes.
MFC r273040:
Fix for build issue on i386.xen and amd64.xen.
Sponsored by: Multiplay
Port the TTM AGP backend to the FreeBSD agp driver and enable AGP support
in the radeonkms driver.
Note: In PCI mode virtual addresses on the graphics card that map to system
RAM are translated to physical addresses by the graphics card itself. In
AGP mode address translation is done by the AGP chipset so fictitious
addresses appear on the system bus. For the CPU cache management to work
correctly when the CPU accesses this memory it needs to use the same
fictitious addresses (and let the chipset translate them) instead of using
the physical addresses directly.
Reviewed by: kib
and verified.
The flowdirector feature shares on-chip memory with other things
such as the RX buffers. In theory it should be configured in a way
that doesn't interfere with the rest of operation. In practice,
the RX buffer calculation didn't take the flow-director allocation
into account and there'd be overlap. This lead to various garbage
frames being received containing what looks like internal NIC state.
What _I_ saw was traffic ending up in the wrong RX queues.
If I was doing a UDP traffic test with only one NIC ring receiving
traffic, everything is fine. If I fired up a second UDP stream
which came in on another ring, there'd be a few percent of traffic
from both rings ending up in the wrong ring. Ie, the RSS hash would
indicate it was supposed to come in ring X, but it'd come in ring Y.
However, when the allocation was fixed up, the developers at Verisign
still saw traffic stalls.
The flowdirector feature ends up fiddling with the NIC to do various
attempts at load balancing connections by populating flow table rules
based on sampled traffic. It's likely that all of that has to be
carefully reviewed and made less "magic".
So for now the flow director feature is disabled (which fixes both
what I was seeing and what they were seeing) until it's all much
more debugged and verified.
Tested:
* (me) 82599EB 2x10G NIC, RSS UDP testing.
* (verisign) not sure on the NIC (but likely 82599), 100k-200k/sec TCP
transaction tests.
Submitted by: Marc De La Gueronniere <mdelagueronniere@verisign.com>
Sponsored by: Verisign, Inc.
Add dtrace probe support for zfs SET_ERROR(..)
MFC r271873:
Fix static kernel build with options ZFS
MFC r271819:
Remove sys/types.h include as per style (9)
Sponsored by: Multiplay
Import HyperV Key-Value Pair (KVP) driver and daemon code by Microsoft,
many thanks for their continued support of FreeBSD.
While I'm there, also implement a new build knob, WITHOUT_HYPERV to
disable building and installing of the HyperV utilities when necessary.
The HyperV utilities are only built for i386 and amd64 targets.
Approved by: re (gjb)
Though this passes the buildworld test, this fails during
installworld with:
make[3]: "/releng/scripts-release/chroots/10/i386/release/etc/devd/Makefile"
line 13: Malformed conditional (${MK_HYPERV} != "no")
Approved by: re (implicit)
Sponsored by: The FreeBSD Foundation
Import HyperV Key-Value Pair (KVP) driver and daemon code by Microsoft,
many thanks for their continued support of FreeBSD.
While I'm there, also implement a new build knob, WITHOUT_HYPERV to
disable building and installing of the HyperV utilities when necessary.
The HyperV utilities are only built for i386 and amd64 targets.
Approved by: re (gjb)
Implement most of timer_{create,settime,gettime,getoverrun,delete}
for amd64/linux32. Fix the entirely bogus (untested) version from
r161310 for i386/linux using the same shared code in compat/linux.
It is unclear to me if we could support more clock mappings but
the current set allows me to successfully run commercial
32bit linux software under linuxolator on amd64.
Reviewed by: jhb
Differential Revision: D784
Sponsored by: DARPA, AFRL
Approved by: re (gjb)
