thompsa [Wed, 9 Dec 2009 22:37:06 +0000 (22:37 +0000)]
MFC r199672
Improve High Speed slot allocation mechanism by moving the computation to the
endpoint rather than per xfer and provide functions around get/free of resources.
thompsa [Wed, 9 Dec 2009 22:32:36 +0000 (22:32 +0000)]
MFC r198776
- Add usb_fill_bulk_urb() and usb_bulk_msg() linux compat functions [1]
- Don't write actual length if the actual length pointer is NULL [2]
- correct Linux Compatibility error codes for short isochronous IN transfers
and make status field signed.
Submitted by: Leunam Elebek [1], Manuel Gebele [2]
thompsa [Wed, 9 Dec 2009 22:10:45 +0000 (22:10 +0000)]
MFC r197761,r198194,r198862
updates device entries supported with the product name not magic numbers
and sorts entries. WUSB54GCV2 is added.
overhauls urtw(4) for supporting RTL8187B devices properly that there
was major changes to initialize RF chipset and set H/W registers and
removed a lot of magic numbers on code.
nwhitehorn [Wed, 9 Dec 2009 21:56:55 +0000 (21:56 +0000)]
MFC r199169:
Reduce probe priority of USB input devices to BUS_PROBE_GENERIC from
BUS_PROBE_SPECIFIC. This allows device-specific drivers like atp to
attach reliably.
thompsa [Wed, 9 Dec 2009 21:34:38 +0000 (21:34 +0000)]
MFC r199575
- fix a transfer cancelling bug/segfault [1]
- correct a return code in the transfer cancel function.
- add new API function, libusb20_tr_bulk_intr_sync().
mav [Wed, 9 Dec 2009 17:20:10 +0000 (17:20 +0000)]
MFC r200121:
Do not ignore device interrupt if bus mastering is still active. It is
normal in case of media read error and some ATAPI cases, when transfer size
is unknown beforehand. PCI ATA BM specification tells that in case of such
underrun driver should just manually stop DMA engine. DMA engine should
same time guarantie that all bus mastering transfers completed at the moment
of driver reads interrupt flag asserted.
This change fixes interrupt storms and command timeouts in many cases.
mav [Wed, 9 Dec 2009 17:11:09 +0000 (17:11 +0000)]
MFC r200117:
On Soft Reset, read device signature from FIS receive area, instead of
PxSIG register. It works better for NVidia chipsets. ahci(4) does the same.
mav [Wed, 9 Dec 2009 13:32:49 +0000 (13:32 +0000)]
MFC r200223:
Explicitly acknowledge MSI completion, as required by SiI3124 datasheet.
It makes MSI working there. Later (and cheaper) PCIe chips (3132/3531)
still randomly crashing system in few seconds of high MSI rates, generating
something inaporopriate, like NMI or "Fatal trap 30".
mav [Wed, 9 Dec 2009 13:27:06 +0000 (13:27 +0000)]
MFC r200196:
Add Asynchronous Notification support for controllers without SNTF
capability by snooping SDB FIS receive area. It should be even faster
then regular way, but less reliable.
mav [Tue, 8 Dec 2009 23:23:45 +0000 (23:23 +0000)]
MFC r200086:
Change 'load' balancing mode algorithm:
- Instead of measuring last request execution time for each drive and
choosing one with smallest time, use averaged number of requests, running
on each drive. This information is more accurate and timely. It allows to
distribute load between drives in more even and predictable way.
- For each drive track offset of the last submitted request. If new request
offset matches previous one or close for some drive, prefer that drive.
It allows to significantly speedup simultaneous sequential reads.
rmacklem [Tue, 8 Dec 2009 22:41:37 +0000 (22:41 +0000)]
MFC: r199715
Modify the experimental nfs server so that it falls back to
using VOP_LOOKUP() when VFS_VGET() returns EOPNOTSUPP in the
ReaddirPlus RPC. This patch is based upon one by pjd@ for the
regular nfs server which has not yet been committed. It is needed
when a ZFS volume is exported and ReaddirPlus (which almost
always happens for NFSv4) is performed by a client. The patch
also simplifies vnode lock handling somewhat.
rmacklem [Tue, 8 Dec 2009 22:28:55 +0000 (22:28 +0000)]
MFC: r199616
Patch the experimental NFS server is a manner analagous to
r197525, so that the creation verifier is handled correctly
in va_atime for 64bit architectures. There were two problems.
One was that the code incorrectly assumed that
sizeof (struct timespec) == 8 and the other was that the tv_sec
field needs to be assigned from a signed 32bit integer, so that
sign extension occurs on 64bit architectures. This is required
for correct operation when exporting ZFS volumes.
Tested by: gerrit at pmp.uni-hannover.de
Reviewed by: pjd
delphij [Tue, 8 Dec 2009 18:23:51 +0000 (18:23 +0000)]
MFC revisions 196550 and 196552:
Add a new rc.d script, static_arp, which enables the administrator to
statically bind IPv4 <-> MAC address at boot time.
In order to use this, the administrator needs to configure the following
rc.conf(5) variable:
- static_arp_pairs: A list of names for static bind pairs, and,
- a series of static_arp_(name): the arguments that is being passed to
``arp -S'' operation.
nwhitehorn [Tue, 8 Dec 2009 05:37:08 +0000 (05:37 +0000)]
MFC r199886:
Add a CPU features framework on PowerPC and simplify CPU setup a little
more. This provides three new sysctls to user space:
hw.cpu_features - A bitmask of available CPU features
hw.floatingpoint - Whether or not there is hardware FP support
hw.altivec - Whether or not Altivec is available
nwhitehorn [Tue, 8 Dec 2009 05:27:06 +0000 (05:27 +0000)]
MFC r198445:
Turn on NAP mode on G5 systems, and refactor the HID0 setup code a little.
This makes my G5 Xserve sound slightly less like it is filled with
howling banshees.
MFC r198968:
Unbreak E500 builds. The inline assembly for the 970 CPUs
is invalid when compiling for BookE.
fabient [Mon, 7 Dec 2009 20:44:43 +0000 (20:44 +0000)]
MFC 198433:
Not all Intel Core (TM) CPUs implement PMC_CLASS_IAF fixed-function
counters. For such CPUs, use an alternate mapping of convenience
names to events supported by PMC_CLASS_IAP programmable counters.
delphij [Mon, 7 Dec 2009 19:59:28 +0000 (19:59 +0000)]
MFC revision 197579 and 199617:
Add two new fcntls to enable/disable read-ahead:
- F_READAHEAD: specify the amount for sequential access. The amount is
specified in bytes and is rounded up to nearest block size.
- F_RDAHEAD: Darwin compatible version that use 128KB as the sequential
access size.
A third argument of zero disables the read-ahead behavior.
Please note that the read-ahead amount is also constrainted by sysctl
variable, vfs.read_max, which may need to be raised in order to better
utilize this feature.
Thanks Igor Sysoev for proposing the feature and submitting the original
version, and kib@ for his valuable comments.
jhb [Mon, 7 Dec 2009 19:07:45 +0000 (19:07 +0000)]
MFC 200061:
The fd_mask type is an unsigned long, not an int, so treat the mask as a
long instead of an int when examining the results of select() to look for
RPC requests. Previously this routine would ignore RPC requests to sockets
whose file descriptor mod 64 was greater than 31 on a 64-bit platform.
jhb [Mon, 7 Dec 2009 17:18:52 +0000 (17:18 +0000)]
MFC 199974:
Remove extra parantheses from usb_ethernet.c and usb_serial.c lines.
config(8) doesn't parse parantheses and instead treated them as being
part of the device driver name (e.g. '(u3g' vs 'u3g'). While here, fix the
style of these long lines to match the wrapping used for other long lines
in this file.
rnoland [Mon, 7 Dec 2009 16:37:02 +0000 (16:37 +0000)]
MFC 199714
Create a seperate ZFS enabled loader.
This adds zfsloader which will be called by zfsboot/gptzfsboot code rather
than the tradional loader. This eliminates the need to set the
LOADER_ZFS_SUPPORT variable in order to get a ZFS enabled loader.
Note however, that you must reinstall your bootcode (zfsboot/gptzfsboot)
in order for the boot process to use the new loader.
New installations will no longer be required to build a ZFS enabled
loader for a working ZFS boot system. Installing zfsboot/gptzfsboot is
sufficient for acknowledging the use of CDDL code and therefore the ZFS
enabled loader.
hrs [Mon, 7 Dec 2009 06:25:19 +0000 (06:25 +0000)]
MFC:
r197144:
- Add an extension of set_rcvar(), a new function set_rcvar_obsolete(),
and $desc.
The set_rcvar_obsolete() is to mark a variable as obsolete and define
the new one. More specifically, a warning is displayed when
a variable is removed or changed in the source tree and the user
still defines the old one.
jilles [Sun, 6 Dec 2009 22:14:58 +0000 (22:14 +0000)]
MFC r198406: wordexp(3): fix some bugs with signals and long outputs
* retry various system calls on EINTR
* retry the rest after a short read (common if there is more than about 1K
of output)
* block SIGCHLD like system(3) does (note that this does not and cannot
work fully in threaded programs, they will need to be careful with wait
functions)
Unconditionally call the setsockopt for IPV6_V6ONLY for v6 linux sockets
no matter whether we are compiled as module or if our default of the
net.inet6.ip6.v6only sysctl already matches what we would set.
This avoids unnecessary complications with modules, VIMAGES, INET6 and
the sysctl value, especially considering that most users will use
linux compat as a module.
Make sure that the primary native brandinfo always gets added
first and the native ia32 compat as middle (before other things).
o(ld)brandinfo as well as third party like linux, kfreebsd, etc.
stays on SI_ORDER_ANY coming last.
The reason for this is only to make sure that even in case we would
overflow the MAX_BRANDS sized array, the native FreeBSD brandinfo
would still be there and the system would be operational.
lindev(4) [1] is supposed to be a collection of linux-specific pseudo
devices that we also support, just not by default (thus only LINT or
module builds by default).
While currently there is only "/dev/full" [2], we are planning to see more
in the future. We may decide to change the module/dependency logic in the
future should the list grow too long.
This is not part of linux.ko as also non-linux binaries like kFreeBSD
userland or ports can make use of this as well.
In case the compression result is the same size as the orignal version,
the compression was useless as well. Make sure to not update the data
and return, else we would waste resources when decompressing.
This also avoids the copyback() changing data other consumers like
xform_ipcomp.c would have ignored because of no win and sent out without
noting that compression was used, resulting in invalid packets at the
receiver.
MFC r199899:
Only add the IPcomp header if crypto reported success and we have a lower
payload size. Before we had always added the header, no matter if we
actually send out compressed data or not.
With this, after the opencrypto/deflate changes, IPcomp starts to work
apart from edge cases. Leave it disabled by default until those are
fixed as well.
MFC r199895:
Change memory managment from a fixed size array to a list.
This is needed to avoid running into out of buffer situations
where we cannot alloc a new buffer because we hit the array size
limit (ZBUF).
Use a combined allocation for the struct and the actual data buffer
to not increase the number of malloc calls. [1]
Defer initialization of zbuf until we actually need it.
Make sure the output buffer will be large enough in all cases.
MFC r199887:
Z_PARTIAL_FLUSH is marked deprecated. Z_SYNC_FLUSH is the suggested
replacement but only use it for inflate. For deflate use Z_FINISH
as Z_SYNC_FLUSH adds a trailing marker in some cases that inflate(),
despite the comment in zlib, does npt seem to cope well with, resulting
in errors when uncompressing exactly fills the outbut buffer without
a Z_STREAM_END and a successive call returns an error.
luigi [Sat, 5 Dec 2009 12:51:51 +0000 (12:51 +0000)]
some simple MFC:
r200020:
change the type of the opcode from enum *:8 to u_int8_t
so the size and alignment of the ipfw_insn is not compiler dependent.
No changes in the code generated by gcc.
r200023:
Add new sockopt names for ipfw and dummynet.
This commit is just grabbing entries for the new names
that will be used in the future, so you don't need to
rebuild anything now.
r200034
Dispatch sockopt calls to ipfw and dummynet
using the new option numbers, IP_FW3 and IP_DUMMYNET3.
Right now the modules return an error if called with those arguments
so there is no danger of unwanted behaviour.
r200040
- initialize src_ip in the main loop to prevent a compiler warning
(gcc 4.x under linux, not sure how real is the complaint).
- rename a macro argument to prevent name clashes.
- add the macro name on a couple of #endif
- add a blank line for readability.
yongari [Thu, 3 Dec 2009 18:42:19 +0000 (18:42 +0000)]
MFC r199564:
Minimize interface reinitialization by checking IFF_DRV_RUNNING
flag. This fixes unnecessary interface UP/DOWNs during getting an
IP address via DHCP.
mav [Wed, 2 Dec 2009 10:47:11 +0000 (10:47 +0000)]
MFC r199822:
Drop USB mass storage devices support from ata(4). It is out of the build as
long as I remember, and completely superseded by better maintained umass(4).
It's main idea was to optionally avoid CAM dependency for such devices, but
with move ATA to CAM, it is not actual any more.
mav [Wed, 2 Dec 2009 10:32:34 +0000 (10:32 +0000)]
MFC r199747, r199799, r199821:
- Extend XPT-SIM transfer settings control API. Now it allows to report to
SATA SIM number of tags supported by each device, implement ATA mode and
SATA revision negotiation for both SATA and PATA SIMs.
- Make ahci(4) and siis(4) to use submitted maximum tag number, when
scheduling requests. It allows to support NCQ on devices with lower tags
count then controller supports.
- Make PMP driver to report attached devices connection speeds.
- Implement ATA mode negotiation between user settings, device and
controller capabilities.
- Improve ATA mode/SATA revision control.
mav [Wed, 2 Dec 2009 10:10:37 +0000 (10:10 +0000)]
MFC r199279, r199280, r199281:
- Fix several device freeze counting bugs.
- Remove code that years ago was closing race between request submission
to SIM and device/SIM freeze. That race become impossible after moving from
spl to mutex locking, while this workaround causes some unexpected effects.
wollman [Wed, 2 Dec 2009 02:47:29 +0000 (02:47 +0000)]
MFC revs 199781,199782,199784,199785,199786:
Eliminate dead stores.
In __mbsconv(), if prec was zero, nconv could have been used
uninitialized. Initialize it to a safe value so that there's no
chance of returning an error if stack garbage happens to be equal to
(size_t)-1 or (size_t)-2.
In svc_raw_reply(), don't leave stat uninitialized if the MSG_ACCEPTED
&& SUCCESS case succeeds. The stack garbage might be zero.
In clnt_raw_create(), avoid minor race condition initializing the
file-scope variable clntraw_private.
fabient [Tue, 1 Dec 2009 23:06:17 +0000 (23:06 +0000)]
MFC 199763:
- fix a LOR between process lock and pmc thread mutex
- fix a system deadlock on process exit when the sample buffer
is full (pmclog_loop blocked in fo_write) and pmcstat exit.
yongari [Sun, 29 Nov 2009 20:19:24 +0000 (20:19 +0000)]
MFC r199413:
It seems generation of link state change of e1000phy(4) is not
reliable on some Marvell PHYs. If msk(4) know it still does not
have established link check whether msk(4) missed the link state
change by looking into polled link state.
Reported by: Mel Flynn < mel.flynn+fbsd.current <> mailing.thruhere dot net >,
Gleb Kurtsou <gleb.kurtsou <> gmail dot com >
Tested by: Gleb Kurtsou <gleb.kurtsou <> gmail dot com >
projects / FreeBSD / stable / 8.git / log