Rick Macklem [Mon, 10 Apr 2017 01:28:01 +0000 (01:28 +0000)]
Avoid starvation of the server crash recovery thread for the NFSv4 client.
This patch gives a requestor of the exclusive lock on the client state
in the NFSv4 client priority over shared lock requestors. This avoids
the server crash recovery thread being starved out by other threads doing
RPCs.
Rick Macklem [Sun, 9 Apr 2017 21:50:21 +0000 (21:50 +0000)]
Fix the NFSv4 client hndling of a stale write verifier in the Commit operation.
When the NFSv4 client Commit operation encountered a stale write verifier,
it erroneously mapped that to EIO. This could have caused recently written
data to be lost when a server crashes/reboots between an UNSTABLE write
and the subsequent commit. This patch fixes this.
The bug was only for the NFSv4 client and did not affect NFSv3.
Rick Macklem [Sun, 9 Apr 2017 21:06:21 +0000 (21:06 +0000)]
Fix the NFSv4.1 client for NFSERR_BADSESSION recovery via ReclaimComplete.
For the ReclaimComplete operation, the RPC layer should not loop on
NFSERR_BADSESSION. If it does, the recovery thread (nfscl) can get stuck
looping and will not do a recovery.
This patch fixes it so it does not loop. This bug only affects NFSv4.1 and
only when a server reboots.
Ian Lepore [Sun, 9 Apr 2017 20:59:12 +0000 (20:59 +0000)]
Add code/constants for detecting imx6ul (ultralite) chips, a species of
imx6 based on a single cortex-a7 core. Other changes to imx6 drivers
and support code are needed to fully support the imx6ul.
Also fix an indentation glitch committed in the prior change.
Ian Lepore [Sun, 9 Apr 2017 20:41:00 +0000 (20:41 +0000)]
Update the code that compensates for the lack of a GPC interrupt controller
driver for imx6. Some newer dts source puts the GIC node at the root
instead of under /soc, so look in both places. Also, sometimes the GIC
node doesn't list itself as its own interrupt-parent, allow that too.
Ian Lepore [Sun, 9 Apr 2017 18:31:33 +0000 (18:31 +0000)]
Remove some old interrupt handling workaround code from the pre-INTRNG days.
At this point, INTRNG is not going away (the option may go away, but the
code is not), so we no longer need code to support workarounds that handled
the lack of INTRNG functionality.
Adding SIOCGIFNAME support in Linuxulator. This should silence the console warning associated
with linux-opera:
linux: pid 23492 (opera): ioctl fd=5, cmd=0x8910 ('\M^I',16) is not implemented
linux: pid 23492 (opera): ioctl fd=28, cmd=0x8910 ('\M^I',16) is not implemented
...
Rick Macklem [Sun, 9 Apr 2017 12:32:22 +0000 (12:32 +0000)]
Fix parsing failure for NFSv4 Setattr operation for failed case.
If an operation that preceeds a Setattr in an NFSv4 compound fails,
there is no bitmap of attributes to parse. Without this patch, the
parsing would fail and return EBADRPC instead of the correct failure
error. This could break recovery from a server crash/reboot.
Toomas Soome [Sun, 9 Apr 2017 11:16:16 +0000 (11:16 +0000)]
loader: r316585 did miss userboot update
The work to implement zfs reader to inspect all pool label copies did
miss the userboot, this update does correct this issue.
Since userboot is already using common/disk.c API (disk_open() etc),
the fix is quite simple - we only need to make sure the userdisk_iocl()
will call disk_ioctl(). In addition, the diskioctl callback does return
int, not pointer.
Note, the review request is actually addressing the sparc and userboot,
but as testing the fix for sparc will take some more time, I am posting the
userboot fix now.
This patch is part of the implementation presented in review:
https://reviews.freebsd.org/D10302
Once we have the sparc part tested, we will have the complete fix
for the issue.
Trying to be more compatible with Linux if.h definitions:
- renaming l_ifreq::ifru_metric to l_ifreq::ifru_ivalue;
- adding a definition for ifr_ifindex which points to l_ifreq::ifru_ivalue.
A quick search indicates that Linux already got the above changes since 2.1.14.
use msr 0xc001100c to discover multi-node AMD processors
This is applicable only to the older processors that do not have the AMD
Topology extension.
Opteron 6100-series "Magny-Cours" processors had multiple nodes within a
package and didn't have the Topology extension. Without this change
FreeBSD would assume that those processors have a single L3 cache shared
by all cores while, in fact, each node has its own L3 cache.
Many thanks to Freddie Cash <fjwcash@gmail.com> for providing valuable
hardware information.
Bruce Evans [Sat, 8 Apr 2017 10:00:39 +0000 (10:00 +0000)]
Quick fix for removal of the mouse cursor in vga direct graphics modes
(that is, in all supported 8, 15, 16 and 24-color modes). Moving the
mouse cursor while holding down a button (giving cut marking) left a
trail of garbage from misremoved mouse cursors (usually colored
rectangles and not cursor shapes). Cases with a button not held down
worked better and may even have worked.
No renderer support for removing (software) mouse cursors is needed
(and many renderers don't have any), since sc_remove_mouse_image()
marks for update the region containing the image and usually much
more. The mouse cursor can be (partially) over as many as 4 character
cells, and removing it in only the 1-4 cells occupied by it would be
best for efficiency and for avoiding flicker. However,
sc_remove_mouse_image() can only mark a single linear region and
usually marks a full row of cells and 1 more to be sure to cover the
4 cells. It always does this, so using the special rendering method
just wastes even more time and gives even more flicker. The special
methods will be removed soon.
The general method always works. vga_pxlmouse_direct() appeared to
defer to it by returning immediately if !on. However,
vga_pxlmouse_direct() actually did foot-shooting using a disguised
saveunder method. Normal order near a mouse move is:
(1) remove the mouse cursor in the renderer (optional)
(2) remove the mouse cursor again and refresh the screen over the
mouse cursor and much more from the vtb. When the mouse has
actually moved and a button is down, many attributes in this
region are changed to be up to date with the new cut marking
(3) draw the keyboard cursor again if it was clobbered by the update
(4) draw the mouse cursor image in its new position.
The bug was to remove the mouse cursor again in step (4), before the
drawing it again in (4), using a saveunder that was valid in step (1)
at best. The quick fix is to use the saveunder in step (1) and not
in step (4). Using it in step (4) also used it before it was
initialized, initially and after mode and screen switches.
When passingthrough from sdiff to diff the -H/--speed-large-files
options rename it to the long version as GNU diff only support the long
version of the option not the short version
Bruce Evans [Sat, 8 Apr 2017 08:24:25 +0000 (08:24 +0000)]
Fix removal of the keyboard cursor image in text mode, especially
in the vga renderer. Removal used stale attributes and didn't try to
merge with the current attribute for cut marking, so special rendering
of cut marking was lost in many cases. The gfb renderer is too broken
to support special rendering of cut marking at all, so this change is
supposed to be just a style fix for it. Remove all traces of the
saveunder method which was used to implement this bug.
Fix drawing of the cursor image in text mode, only in the vga
renderer. This used a stale attribute from the frame buffer instead
of from the saveunder, but did merge with the current attribute for
cut marking so it caused less obvious bugs (subtle misrendering for
the character under the cursor).
The saveunder method may be good in simpler drivers, but in syscons
the 'under' is already saved in a better way in the vtb. Just redraw
it from there, with visible complications for cut marking and
invisible complications for mouse cursors. Almost all drawing
requests are passed a flag 'flip' which currently means to flip to
reverse video for characters in the cut marking region, but should
mean that the the characters are in the cut marking regions so should
be rendered specially, preferably using something better than reverse
video. The gfb renderer always ignores this flag. The vga renderer
ignored it for removal of the text cursor -- the saveunder gave the
stale rendering at the time the cursor was drawn. Mouse cursors need
even more complicated methods. They are handled by drawing them last
and removing them first. Removing them usually redraws many other
characters with the correct cut marking (but transiently loses the
keyboard cursor, which is redrawn soon). This tended to hide the
saveunder bug for forward motions of the keyboard cursor. But slow
backward motions of the keyboard cursor always lost the cut marking,
and fast backwards motions lost in for about 4 in every 5 characters,
depending on races with the scrn_update() timeout handler. This is
because the forward motions are usually into the region redrawn for
the mouse cursor, while backwards motions rarely are.
Text cursor drawing in the vga renderer used also used a
possibly-stale copy of the character and its attribute. The vga
render has the "optimization" of sometimes reading characters from the
screen instead of from the vtb (this was not so good even in 1990 when
main memory was only a few times faster than video RAM). Due to care
in update orders, the character is never stale, but its attribute
might be (just the cut marking part, again due to care in order).
gfb doesn't have the scp->scr pointer used for the "optimization", and
vga only uses this pointer for text mode. So most cases have to
refresh from the vtb, and we can be sure that the ordering of vtb
updates and drawing is as required for this to work.
Ed Maste [Fri, 7 Apr 2017 23:37:22 +0000 (23:37 +0000)]
do not require binutils port when using lld as ld
r279908 added logic to Makefile.inc1 to automatically set
CROSS_BINUTILS_PREFIX for architectures not supported by the in-tree
binutils: arm64 when first introduced, and later riscv64 as well.
LLVM's LLD linker is now included in the base system, and is enabled by
default for arm64 and capable of linking world and kernel. Thus, avoid
automatically setting CROSS_BINUTILS_PREFIX and requiring the binutils
port if WITH_LLD_IS_LD is true.
Reviewed by: kan
Relnotes: Yes
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D10310
GNU toolchain does not recognize LR as standard register alias,
but clang does. Use of #define will work on both. Place the
definition into central machine/asm.h instead of patching every
affected file, as requested by plaftorm maintainers.
The conditional jump can only be performed to targets up to 1MB in
either direction and does not work too well when linker places cerror
further that that from the caller. In that case linker will complain
about relocation overflows.
Reviewed by: emaste, andrew
Differential Revision: https://reviews.freebsd.org/D10305
John Baldwin [Fri, 7 Apr 2017 20:02:01 +0000 (20:02 +0000)]
Explicitly set the desired MIPS ABI in toolchain flags.
Specifically, set '-mabi=XX' in AFLAGS, CFLAGS, and LDFLAGS. This permits
building MIPS worlds and binaries with a toolchain whose default output
does not match the desired TARGET_ARCH.
_LDFLAGS (which is used with LD instead of with CC) required an update as
LD does not accept the -mabi flags (so they must be stripped from LDFLAGS
when generating _LDFLAGS). For bare uses of LD (rather than linking via
CC), the desired ABI must be set by setting an explicit linker emulation
as done in r316514 for kernels and kernel modules.
John Baldwin [Fri, 7 Apr 2017 19:53:14 +0000 (19:53 +0000)]
Rework r234502 to include a modified CFLAGS along with ACFLAGS.
On most architectures crt objects are compiled in a multiple-step process
so that sed can be run on the generated assembly. As the final step,
the C compiler generates an object file from the modified assembly output.
Currently this last step uses $CC with only $ACFLAGS. However, for other
uses in the tree, $ACFLAGS is meant to include assembly-specific compiler
flags that are in addition to $CFLAGS (see default .S.o rules
bsd.suffixes.mk). In particular, external toolchains may require
additional flags to select a non-default target which will be present
in CFLAGS but not ACFLAGS. To support this while still mitigating the
issue with CFLAGS described in r234502, include a modified CFLAGS that
excludes "-g" when assembling the modified assembly files.
Note that normally an assembler ($AS) is used to assemble .s flags to
object files (see bsd.suffixes.mk). However, llvm-based toolchains do
not currently have a stand-alone assembler.
Brooks Davis [Fri, 7 Apr 2017 18:31:31 +0000 (18:31 +0000)]
Remove support for long gone oldnfs.
The code was calling nmount with an fstype of everything in the program
name after the last '_'. This was there to support mount_nfs being
linked to mount_oldnfs. Support for the link was removed in 2015 with
r281691.
- Increase the image size for RPI2 and IMX6-based boards from 1G
to 1.5G.
- Use the 'conv=sync' dd(1) option to fix writing the u-boot.imx
file to the md(4) device for IMX6-based boards.
MFC after: 3 days
Sponsored by: The FreeBSD Foundation
Andrew Turner [Fri, 7 Apr 2017 14:30:51 +0000 (14:30 +0000)]
Add -fPIC to the standalone build flags on arm64. This is needed as
loader.efi is position independend, however we were not building it as
such causing a build failure when building with lld.
Andrew Turner [Fri, 7 Apr 2017 12:41:57 +0000 (12:41 +0000)]
Fix linking with lld by marking OPENSSL_armcap_P as hidden.
Linking with lld fails as it contains a relative address, however the data
this address is for may be relocated from the shared object to the main
executable.
Fix this by adding the hidden attribute. This stops moving this value to
the main executable. It seems this is implicit upstream as it uses a
version script.
Brooks Davis [Thu, 6 Apr 2017 23:35:10 +0000 (23:35 +0000)]
Point out that -F probably does not do what the user expects.
Users attempting to create images from mtree METALOG files created by
installworld often use -F when they should be passing the METALOG file
in place of a directory. This is often produces difficult to debug
error reports.
Toomas Soome [Thu, 6 Apr 2017 20:12:39 +0000 (20:12 +0000)]
libstand/dosfs: cache FAT32 in 128 Kb blocks to save loader memory
Current implementation of dosfs in libstand reads full File Allocation Table to
the RAM in the initialization code. In the extreme case of FAT32 filesystem,
this structure will take up to 256-1024 Mb of loader memory, depending on the
cluster size.
Proposed patch reduces libstands/dosfs memory requirements to 128 Kb for all
variants of dosfs filesystem. For FAT12 and FAT16 filesystems, File Allocation
Table is cached in full, as before. For FAT32, File Allocation Table is broken
into the equal blocks of 128 Kilobytes (32768 entries), and only current block
is cached.
Because per-filesystem context is now small, global FAT cache (for all
instances of dosfs filesystem) is replaced by local per-instance cache.
META_MODE: Fix build-tools still sometimes rebuilding during target build.
In a cross-build, the build-tools are native host binaries. We do not
want to rebuild them when building for the target. Bmake previously
did not support checking .NOMETA on an existing target, so .NOMETA_CMP
was used here. However, .NOMETA_CMP still triggers meta mode conditions
if the number of commands or the command changes. In r312467 the paths
to build ncurses files were modified and thus triggered meta mode to
rebuild the build tools (make_keys, make_hash) in ncurses during the
target build. Bmake 20160604 committed in r301462 changed .NOMETA to
also skip meta mode logic for an existing .meta file as well, thus it
is now the proper fix here.
I explored moving the build-tools output to WORLDTMP/tools with
relatively good success, but have concerns that doing so would be
problematic for downstream vendors who use LOCAL_TOOL_DIRS and
expect the tools to be in current OBJDIR for the target. It also
adds more complexity into finding the tools during target build
and handling of where they are for rescue/rescue and
mkcsmapper_static/mkesdb_static which should really not be connected in
build-tools anyway.
Toomas Soome [Thu, 6 Apr 2017 18:17:29 +0000 (18:17 +0000)]
loader: zfs reader should check all labels
The current zfs reader is only checking first label from each device, however,
we do have 4 labels on device and we should check all 4 to be protected
against disk failures and incomplete label updates.
The difficulty is about the fact that 2 label copies are in front of the
pool data, and 2 are at the end, which means, we have to know the size of
the pool data area.
Since we have now the mechanism from common/disk.c to use the partition
information, it does help us in this task; however, there are still some
corner cases.
Namely, if the pool is created without partition, directly on the disk,
and firmware will give us the wrong size for the disk, we only can check
the first two label copies.
Toomas Soome [Thu, 6 Apr 2017 15:57:53 +0000 (15:57 +0000)]
loader: want mechanism to avoid RA with bcache
While we have mechanisms in place to protect ourselves against the read
behind the disk end, there is still one corner case. As the GPT
partition table has backup table at the end of the disk, and we yet
do not know the size of the disk (if the wrong size is provided by the
firmware/bios), we need to limit the reads to avoid read ahead in such case.
Note: this update does add constant into stand.h, so the incremental build
will need to get local stand.h updated first.
Toomas Soome [Thu, 6 Apr 2017 15:42:12 +0000 (15:42 +0000)]
loader: part.c cstyle cleanup
The description tells it all, as an side note, I am using uint8_t instead of
u_char as the partition table data really is handled as byte stream, not
char array.
cxgbe/iw_cxgbe: Replace a magic constant with something more readable
(and accurate).
T4 and later have an extra bit for page shift so the maximum page size
is 8TB (shift of 12 + 31) instead of 128MB (12 + 15). This saves space
in the chip's PBL (physical buffer list) when registering very large
memory regions.
MFC after: 3 days
Sponsored by: Chelsio Communications
Cleanup the bitmap_xxx() functions in the LinuxKPI:
- Move all bitmap related functions from bitops.h to bitmap.h, similar
to what Linux does.
- Apply some minor code cleanup and simplifications to optimize the
generated code when using static inline functions.
- Implement the following list of bitmap functions which are needed by
drm-next and ibcore:
- bitmap_find_next_zero_area_off()
- bitmap_find_next_zero_area()
- bitmap_or()
- bitmap_and()
- bitmap_xor()
- Add missing include directives to the qlnxe driver
(davidcs@ has been notified)
Revert r316487. It is broken, causing boot to fail due to line 25 in
etc/rc.d/dhclient unconditionally testing true when called by a devd
rule during boot, ignoring statically assigned IP addresses in rc.conf.
Fix implementation of task_pid_group_leader() in the LinuxKPI.
In FreeBSD thread IDs and procedure IDs have distinct number
spaces. When asking for the group leader task ID in the LinuxKPI,
return the procedure ID and let this resolve to the first task in the
procedure having a valid LinuxKPI task structure pointer.
Implement proper support for memory map operations in the LinuxKPI,
like open, close and fault using the character device pager.
Some notes about the implementation:
1) Linux drivers set the vm_ops and vm_private_data fields during a
mmap() call to indicate that the driver wants to use the LinuxKPI VM
operations. Else these operations are not used.
2) The vm_private_data pointer is associated with a VM area structure
and inserted into an internal LinuxKPI list. If the vm_private_data
pointer already exists, the existing VM area structure is used instead
of the allocated one which gets freed.
3) The LinuxKPI's vm_private_data pointer is used as the callback
handle for the FreeBSD VM object. The VM subsystem in FreeBSD has a
similar list to identify equal handles and will only call the
character device pager's close function once.
4) All LinuxKPI VM operations are serialized through the mmap_sem
sempaphore, which is per procedure, which prevents simultaneous access
to the shared VM area structure when receiving page faults.
Before registering a new mm_struct in the LinuxKPI check if other
tasks in the belonging procedure already have a valid mm_struct and
reference that instead.
The mm_struct in the LinuxKPI should be shared among all tasks
belonging to the same procedure. This has to do with with the mmap_sem
semaphore which should serialize all VM operations inside a given
procedure. Linux based drivers depend on this behaviour.
Enji Cooper [Thu, 6 Apr 2017 02:46:09 +0000 (02:46 +0000)]
sbuf(9): clarify kernel-only APIs
- move sbuf_bcopyin(9) and sbuf_copyin(9) near sbuf_new_for_sysctl(9), as
all three functions are kernel-only APIs.
- add #ifdef _KERNEL around sbuf_*copyin and sbuf_new_for_sysctl(9) to
make it visually clear that they are kernel-only APIs.
Alan Somers [Thu, 6 Apr 2017 01:37:03 +0000 (01:37 +0000)]
Quiet 450.status-security when *_inline="YES"
Previously, 450.status-security would always set rc=3 in inline mode,
because it doesn't know whether "periodic security" is going to find
anything interesting. But this annoyingly results in daily reports that
simply say "Security check: \n\n-- End of daily output --".
This change fixes that by testing whether "periodic security" printed
anything, and setting 450.status-security's exit status to 3 if it did. An
alternative would be to change the exit status of periodic(8) to be the
worst of its scripts' exit statuses, but that would be a more intrusive
change.
Reviewed by: brian
MFC after: 3 weeks
Differential Revision: https://reviews.freebsd.org/D10267
Adrian Chadd [Thu, 6 Apr 2017 01:35:42 +0000 (01:35 +0000)]
[net80211] refactor out the A-MPDU dispatch routine.
The "dispatch a frame from the A-MPDU reorder buffer" code is essentially
duplicated in a couple of places. This refactors it out into a single
place in preparation for A-MSDU in A-MPDU offload support, where multiple
A-MSDUs are decap'ed in hardware to 802.3/802.11 frames, but with the
same sequence number.