summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
...
* 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.
* MFC r282120:hselasky2015-05-056-12/+12
| | | | | | | | | | | | The add_bounce_page() function can be called when loading physical pages which pass a NULL virtual address. If the BUS_DMA_KEEP_PG_OFFSET flag is set, use the physical address to compute the page offset instead. The physical address should always be valid when adding bounce pages and should contain the same page offset like the virtual address. Submitted by: Svatopluk Kraus <onwahe@gmail.com> Reviewed by: jhb@
* Update the last svn rev marker.gjb2015-05-051-1/+1
| | | | Sponsored by: The FreeBSD Foundation
* Document r282278, wc(1) race when receiving SIGINFO fixed.gjb2015-05-051-0/+5
| | | | Sponsored by: The FreeBSD Foundation
* Backport some parts of r272200.np2015-05-052-14/+38
| | | | | | | - a lock to protect indirect register access - put code that deals with stats in a separate cxgbe_refresh_stats. This is a direct commit to stable/10.
* MFC r282128:kib2015-05-051-0/+4
| | | | | Do not sleep waiting for the MAP_ENTRY_IN_TRANSITION state ending with the vnode locked.
* MFC r281483:markj2015-05-051-4/+3
| | | | Fix a possible refcount leak in regen_tmpaddr().
* MFC 281701:markj2015-05-051-1/+31
| | | | | | SDT(9): add a section on SDT providers, mentioning the "sdt" provider. Add examples demonstrating how one can list available providers and the DTrace probes provided by a provider.
* MFC r281765:mav2015-05-041-1/+3
| | | | | | | | | | | Activate write-only optimization if bpf device opened with O_WRONLY. dhclient opens bpf as write-only to send packets. It never reads received packets from that descriptor, but processing them in kernel takes time. Especially much time takes packet timestamping on systems with expensive timecounter, such as bhyve guest, where network speed dropped in half. Sponsored by: iXsystems, Inc.
* MFC r282109:kib2015-05-041-36/+45
| | | | Always do token substitution, do not require -z origin to do it.
* MFC r282085:kib2015-05-041-29/+64
| | | | | | | Partially revert r255986: do not call VOP_FSYNC() when helping bufdaemon in getnewbuf(), do use buf_flush(). The difference is that bufdaemon uses TRYLOCK to get buffer locks, which allows calls to getnewbuf() while another buffer is locked.
* MFC r282084:kib2015-05-041-26/+24
| | | | Fix locking for oshmctl() and shmsys().
* MFC r281763:kib2015-05-041-37/+36
| | | | | Remove code to support the top of the stack layout for FreeBSD 1.x/2.x kernel.
* MFC r272183:np2015-05-031-0/+6
| | | | | | Make sure the adapter's management queue and the event queue are available before any uppper layer driver (TOE, iWARP, or iSCSI) registers with the base cxgbe(4) driver.
* MFC r281592, r281918, r282119, r282266:kevlo2015-05-032-19/+44
| | | | | - Fix the length of efuse content - Disable usb aggregation mode by default since it boots performance
* MFC r272051:np2015-05-031-1/+3
| | | | | | | cxgbe(4): Verify that the addresses in if_multiaddrs really are multicast addresses. (The chip doesn't really care, it's just that it needs to be told explicitly if unicast DMACs are checked for "hits" in the hash that is used after the TCAM entries are all used up).
* MFC r281738:mav2015-05-031-4/+7
| | | | | | | | | | | | | | | | | | Change wcommitsize default from one empirical value to another. The new value is more predictable with growing RAM size: hibufspace maxvnodes old new i386: 256MB 32980992 15800 2198732 2097152 2GB 94027776 107677 878764 4194304 amd64: 256MB 32980992 15800 2198732 2097152 1GB 114114560 68062 1678155 4194304 4GB 217055232 111807 1955452 4194304 16GB 1717846016 337308 5097465 16777216 64GB 1734918144 1164427 1490479 16777216 256GB 1734918144 4426453 391983 16777216
* MFC r281026, r281108, r281109:mav2015-05-033-2/+25
| | | | | | | | | | | | | | | | | | | | | | | | Make ZFS ARC track both KVA usage and fragmentation. Even on Illumos, with its much larger KVA, ZFS ARC steps back if KVA usage reaches certain threshold (3/4 on i386 or 16/17 otherwise). FreeBSD has even less KVA, but had no such limit on archs with direct map as amd64. As result, on machines with a lot of RAM, during load with very small user- space memory pressure, such as `zfs send`, it was possible to reach state, when there is enough both physical RAM and KVA (I've seen up to 25-30%), but no continuous KVA range to allocate even single 128KB I/O request. Address this situation from two sides: - restore KVA usage limitations in a way the most close to Illumos; - introduce new requirement for KVA fragmentation, specifying that we should have at least one sequential KVA range of zfs_max_recordsize bytes. Experiments show that first limitation done alone is not sufficient. On machine with 64GB of RAM it is sometimes needed to drop up to half of ARC size to get at leats one 1MB KVA chunk. Statically limiting ARC to half of KVA/RAM is too strict, so second limitation makes it to work in cycles: accumulate trash up to certain critical mass, do massive spring-cleaning, and then start littering again.
* MFC: r281962rmacklem2015-05-021-1/+2
| | | | | | Fix the NFS server's handling of a bogus NFSv2 ROOT RPC. The ROOT RPC is deprecated in the NFSv2 RFC, RFC-1094 and should never be used by a client.
* MFC r281923, r281924: Add link to mvs(4).mav2015-05-011-0/+1
|
* MFC r281782: Don't set bits that should be zero for SATA devices.mav2015-05-011-1/+0
| | | | Old value made Linux think that it is PATA device with SATA bridge.
* MFC r281700:mav2015-05-014-18/+100
| | | | | | | | | Workaround bhyve virtual disks operation on top of GEOM providers. GEOM does not support scatter/gather lists in its I/Os. Such requests are cut in pieces by physio(), that may be problematic, if those pieces are not multiple of provider's sector size. If such case is detected, move the data through temporary sequential buffer.
* MFC r281666: Make virtual AHCI more careful with I/O lengths.mav2015-05-011-92/+84
|
* MFC r282148:gjb2015-05-015-5/+5
| | | | | | | Fix CROCHETBRANCH. PR: 199760 Sponsored by: The FreeBSD Foundation
* MFC r281617:bdrewery2015-04-301-0/+11
| | | | | | wc: Fix SIGINFO race causing final results to be lost to stderr. Relnotes: yes
* MFC r275805:tijl2015-04-3043-95/+95
| | | | | | | | | | | | | Fix incorrect type of "invalids" argument in __iconv() prototype. MFC r281550,281591: Remove the const qualifier from iconv(3) to comply with POSIX: http://pubs.opengroup.org/onlinepubs/9699919799/functions/iconv.html Adjust all code that calls iconv. PR: 199099
* MFC: r281628rmacklem2015-04-304-7/+18
| | | | | | | | | | | mav@ has found that NFS servers exporting ZFS file systems can perform better when using a 128K read/write data size. This patch changes NFS_MAXDATA from 64K to 128K so that clients can use 128K for NFS mounts to allow this. The patch also renames NFS_MAXDATA to NFS_SRVMAXIO so that it is clear that it applies to the NFS server side only. It also avoids a name conflict with the NFS_MAXDATA defined in rpcsvc/nfs_prot.h, that is used for userland RPC.
* MFC: r281562rmacklem2015-04-3010-4/+16
| | | | | | | | | | | File systems that do not use the buffer cache (such as ZFS) must use VOP_FSYNC() to perform the NFS server's Commit operation. This patch adds a mnt_kern_flag called MNTK_USES_BCACHE which is set by file systems that use the buffer cache. If this flag is not set, the NFS server always does a VOP_FSYNC(). This should be ok for old file system modules that do not set MNTK_USES_BCACHE, since calling VOP_FSYNC() is correct, although it might not be optimal for file systems that use the buffer cache.
* MFC r282116:gjb2015-04-301-6/+10
| | | | | | | Add the cw-ec2-portinstall target to always install the net/bsdec2-image-upload port. Sponsored by: The FreeBSD Foundation
OpenPOWER on IntegriCloud