summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* MFC r282344: Handle ATA_SEND_FPDMA_QUEUED as NCQ in ahci_port_stop().mav2015-05-131-1/+2
|
* MFC r282073:ngie2015-05-132-57/+57
| | | | | | | | | | - Fix style(9) a bit -- Fix whitespace -- Use err/errx -- Remove superfluous braces - Be a bit more defensive with input from the end-user - Don't throw a floating point exception by dividing by 0 when processing a zero-byte file
* MFC r282067:ngie2015-05-1326-148/+424
| | | | | Integrate tools/regression/fifo into the FreeBSD test suite as tests/sys/fifo and tools/regression/file into the FreeBSD test suite as tests/sys/file
* MFC r282063:ngie2015-05-1313-4/+29
| | | | | Integrate tools/regression/kqueue into the FreeBSD test suite as tests/sys/kqueue
* MFC r281766, r281767:mav2015-05-131-2/+2
| | | | | | Report link as up only if we managed to open tap device. It would be cool to report tap device status, but it has no such API.
* MFC r281764, r282563: Disable RX/TX queues notifications when not needed.mav2015-05-131-14/+15
| | | | | | This reduces CPU load and doubles iperf throughput, reaching 2-3Gbit/s. Sponsored by: iXsystems, Inc.
* MFC r282062:ngie2015-05-131-5/+5
| | | | | Fix -Wformat warnings by using proper format string qualifiers for long and unsigned[ long] types
* MFC r282056:ngie2015-05-131-0/+6
| | | | | | | | The fmodl compat shims on arm/mips/powerpc aren't complete Disable the test code for now on those architectures PR: 199422
* MFC r282054:ngie2015-05-131-4/+9
| | | | | ath3kfw, bcmfw, bthidcontrol, bthidd all require usb(4); build them conditionally if MK_USB != no
* MFC r281967:ngie2015-05-131-0/+1
| | | | | Assuming a system has /bin/csh on it is a bad idea (especially it being optional on FreeBSD). Look for /bin/cat instead
* Convert space to tabs in the bits that I changed in my last commit.araujo2015-05-131-23/+23
| | | | | | No functional change. Reported by: jmallet@
* MFC r281984:hiren2015-05-131-5/+10
| | | | | | | | | | Currently there is no easy way to specify net.isr.maxthreads = all cpus. We need to specify exact number of cpus in loader.conf which get annoying when you have mix of machines which don't have equal number of total cpus. I propose "-1" as that value. When loader.conf has net.isr.maxthreads = -1, netisr will use all available cpus. Sponsored by: Limelight Networks
* Partial MFC r281838:hiren2015-05-131-2/+19
| | | | | | | | | For igb(4), when we are doing multiqueue, we are all setup to have full 32bit RSS hash from the card. Expose that so others like lagg(4) can use that and avoid hashing the traffic by themselves. Setting hashtype as OPAQUE because FreeBSD 10 doesn't have RSS support. Sponsored by: Limelight Networks
* MFC: 282215gnn2015-05-133-0/+9
| | | | | | | | Make it possible to statically link SIFTR into the kernel as a new option. Reviewed by: bz Discussed with: lstewart
* MFC r281944: vt(4): Simplify mouse area detectionemaste2015-05-121-13/+7
| | | | | | | | vt_is_cursor_in_area needs to return true if any part of the mouse cursor is visible in the rectangle area. Replace the existing test with a simpler version of a test for overlapping rectangles. Sponsored by: The FreeBSD Foundation
* MFC r282247: vt: fix vt_fb_bitblt_bitmap mask corruptionemaste2015-05-121-31/+23
| | | | | | | | | Previously the mask wrapped when one or more of the mask bytes extended past the right edge of the window. Simplify the logic and use the same byte offset and bit in both the pattern and mask. PR: 199648 Sponsored by: The FreeBSD Foundation
* Fix the media detected for copper cables NIC based on chipsest X540T.araujo2015-05-121-11/+23
| | | | | Requested by: hiren@ MFH: 279803
* MFC r282469:garga2015-05-122-0/+2
| | | | | | | | | Add support for Sierra MC7354 card Author: Jeremy Porter <jporter@netgate.com> Differential Revision: https://reviews.freebsd.org/D2444 Reviewed by: gnn, hselasky Sponsored by: Netgate
* followup to r282748: sys/modules/cyclic was not removed by svn mergeavg2015-05-121-19/+0
| | | | | | | This directory and its content were removed by the original commit but somehow the merge did not remove the directory. Spotted by: smh
* followup to r282748: remove another instance of cyclic in sys/modules/Makefileavg2015-05-121-3/+0
| | | | | Those lines were not present in head and thus were not removed by the original commit and its merge.
* MFC r282205:smh2015-05-121-15/+17
| | | | | | | Fix misuse of input argument in traverse_visitbp Obtained from: zfsonlinux (a585f2f844ed3d4270221fed88f5e494eb55d932 Sponsored by: Multiplay
* MFC r282680:kib2015-05-121-2/+0
| | | | Remove unused define.
* MFC r274223 (by glebius):hrs2015-05-121-4/+0
| | | | | | | Remove VNET_SYSCTL_ARG(). The generic sysctl(9) code handles that. A panic could occur by "sysctl -a" when using VIMAGE-enabled stable/10 kernel after r262734 because of this missing MFC.
* Fix r282781:hiren2015-05-121-2/+3
| | | | | | | We should return OPAQUE from M_HASHTYPE_GET() if M_FLOWID is there and rsstype is not set. Submitted by: hans
* r281955 removed M_FLOWID which could cause problems for old drivers still usinghiren2015-05-113-12/+20
| | | | | | | | | | | | | | | | | the field. It cannot be removed from stable/10 so restore it. Change M_HASHTYPE_GET() and M_HASHTYPE_SET() to do the right thing when M_FLOWID exists. Also bumping the FreeBSD version to note the fact that M_FLOWID is brought back in stable/10. (Just a note that M_FLOWID has been removed from -head.) Spotted by: np Suggested by: hans Reviewed by: hans, tuexen (earlier version) Helped by: jhb, delphij, gjb Sponsored by: Limelight Networks
* MFC r282131: replace a comment about zfs recv -F corner case with a longer oneavg2015-05-111-7/+17
|
* MFC r282130: zfs_onexit_fd_hold: return EBADF even if devfs_get_cdevpriv ↵avg2015-05-111-1/+1
| | | | gave ENOENT
* MFC r282127: dsl_dir_rename_check: return EXDEV on cross-pool rename attemptavg2015-05-111-1/+1
|
* MFC r282126: FV r282123: 5610 zfs clone from different source and target poolsavg2015-05-112-12/+4
|
* MFC r282125: MFV r282124: 5393 spurious failures from dsl_dataset_hold_obj()avg2015-05-111-1/+2
|
* MFC r282122: nvpair_type_is_array: DATA_TYPE_INT8_ARRAY was not recognizedavg2015-05-111-0/+1
|
* MFC r282121: dump_nvlist: handle DATA_TYPE_BOOLEAN_ARRAYavg2015-05-111-0/+11
|
* MFC r277796: hook userland threads suspend + resume into acpi suspend codeavg2015-05-114-3/+8
|
* MFC r277795,278849: vt(4): Use power_{suspend,resume} event handlersavg2015-05-115-33/+65
|
* MFC r275576: remove opensolaris cyclic code, replace with high-precision ↵avg2015-05-1115-2336/+171
| | | | callouts
* MFC r282434:gjb2015-05-1114-269/+1131
| | | | | | | | | | | | | | MFV r225523, r282431: r225523 (hrs): Import openresolv-3.4.4. r282431: Import openresolv-3.7.0. PR: 199854 Submitted by: yuri@rawbw.com Relnotes: yes Sponsored by: The FreeBSD Foundation
* MFC r282041: hexdump: Don't use uninitialized struct stat.jilles2015-05-101-1/+1
| | | | PR: 196194
* MFC: 273293gnn2015-05-091-0/+2
| | | | | | | Update the TCP structure used by DTrace to show the smoothed RTT. This will allow similar functionality to SIFTR to be built with DTrace. Submitted by: Grenville Armitage
* MFC: 281558gnn2015-05-091-6/+5
| | | | Minor change to the macros to make sure that if an AF is passed that is neither AF_INET6 nor AF_INET that we don't touch random bits of memory.
* MFC: 281529gnn2015-05-091-1/+1
| | | | | | | | | | I can find no reason to allow packets with both SYN and FIN bits set past this point in the code. The packet should be dropped and not massaged as it is here. Differential Revision: https://reviews.freebsd.org/D2266 Submitted by: eri Sponsored by: Rubicon Communications (Netgate)
* MFC r281840:delphij2015-05-081-1/+1
| | | | | | Extend DA_Q_NO_RC16 to MXUB3* devices. PR: kern/198647
* MFC r261708, r261847, r268525, r274316, r274347, r275593,hiren2015-05-088-418/+481
| | | | | | | | | | | | | | | r276844, r276847, r279531, r279559, r279564, r279676 A bunch of IPv6 fixes by melifaro, hrs and ae Major changes: Simplify nd6_output_lle() Add refcounting to DAD and fix races and other errors Implement Enhanced DAD algorithm for IPv6 Suggested by: ae Tested by: Jason Wolfe <j at nitrology.com> Sponsored by: Limelight Networks
* MFC r282419, r282435:gjb2015-05-081-1/+12
| | | | | | | | | | | | | | | | r282419: Add logic to detect if the net/bsdec2-image-upload port needs to be installed. [1] For the cw-ec2-portinstall and ec2ami targets, touch the .TARGET file after completion to prevent duplicate invocations. Add cw-ec2-portinstall and ec2ami to CLEANFILES. r282435: Remove a debugging line that snuck in with the previous commit. Sponsored by: The FreeBSD Foundation
* MFC r281860: Make AIO to not allocate pbufs for unmapped I/O like r281825.mav2015-05-061-101/+105
| | | | | | | | | While there, make few more performance optimizations. On 40-core system doing many 512-byte AIO reads from array of raw SSDs this change removes lock congestions inside pbuf allocator and devfs, and bottleneck on single AIO completion taskqueue thread. It improves peak AIO performance from ~600K to ~1.3M IOPS.
* MFC r281825: Rewrite physio() to not allocate pbufs for unmapped I/O.mav2015-05-061-61/+93
| | | | | | | | | | | | | pbufs is a limited resource, and their allocator is not SMP-scalable. So instead of always allocating pbuf to immediately convert it to bio, allocate bio just here. If buffer needs kernel mapping, then pbuf is still allocated, but used only as a source of KVA and storage for a list of held pages. On 40-core system doing many 512-byte reads from user level to array of raw SSDs this change removes huge lock congestion inside pbuf allocator. It improves peak performance from ~300K to ~1.2M IOPS. On my previous 24-core system this problem also existed, but was less serious.
* MFC r282245:kib2015-05-061-14/+0
| | | | | | | Remove the #ifdef DEBUG code, which is not compilable on 64bit architectures. PR: 199767
* MFC r277396, r278681, r278865, r278924, r279205, r280208,hselasky2015-05-0520-178/+349
| | | | | | | | | | | | | | | | | | | | | r280210, r280764 and r280768: Update the Linux compatibility layer: - Add more functions. - Add some missing includes which are needed when the header files are not included in a particular order. - The kasprintf() function cannot be inlined due to using a variable number of arguments. Move it to a C-file. - Fix problems about 32-bit ticks wraparound and unsigned long conversion. Jiffies or ticks in FreeBSD have integer type and are not long. - Add missing "order_base_2()" macro. - Fix BUILD_BUG_ON() macro. - Declare a missing symbol which is needed when compiling without -O2 - Clean up header file inclusions in the linux/completion.h, linux/in.h and linux/fs.h header files. Sponsored by: Mellanox Technologies
* MFC r280597:hselasky2015-05-051-0/+7
| | | | | | Add DA_Q_NO_RC16 quirk for USB mass storage device. PR: 198647
* MFC r280598:hselasky2015-05-051-0/+5
| | | | | Add definition of the ISOCHRONOUS endpoint usage bits. Refer to the USB v2.0 specification for more information.
* MFC r281881:hselasky2015-05-051-9/+7
| | | | | | Disable multi process interrupts, because the current code doesn't use them. Else we can end up in an infinite interrupt loop in USB device mode.
OpenPOWER on IntegriCloud