summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* MFC r318314stevek2017-05-251-0/+10
| | | | | | | | | Add information to open(2) man page about the O_VERIFY flag. PR: 219262 Reviewed by: bjk wblock Approved by: sjg (mentor) Obtained from: Juniper Networks, Inc.
* MFC r318511truckman2017-05-252-42/+76
| | | | | | | | | | | | | | | | The result of right shifting a negative signed value is implementation defined. On machines without arithmetic shift instructions, zero bits may be shifted in from the left, giving a large positive result instead of the desired divide-by power-of-2. Fix this by operating on the absolute value and compensating for the possible negation later. Reverse the order of the underflow/overflow tests and the exponential decay calculation to avoid the possibility of an erroneous overflow detection if p is a sufficiently small non-negative value. Also check for negative values of prob before doing the exponential decay to avoid another instance of of right shifting a negative value. Tested by: Rasool Al-Saadi <ralsaadi@swin.edu.au>
* MFC r318655:dim2017-05-253-0/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull in r302416 from upstream llvm trunk (by Martin Storsjö): [ARM] Clear the constant pool cache on explicit .ltorg directives Multiple ldr pseudoinstructions with the same constant value will reuse the same constant pool entry. However, if the constant pool is explicitly flushed with a .ltorg directive, we should not try to reference constants in the previous pool any longer, since they may be out of range. This fixes assembling hand-written assembler source which repeatedly loads the same constant value, across a binary size larger than the pc-relative fixup range for ldr instructions (4096 bytes). Such assembler source already uses explicit .ltorg instructions to emit constant pools with regular intervals. However if we try to reuse constants emitted in earlier pools, they end up out of range. This makes the output of the testcase match what binutils gas does (prior to this patch, it would fail to assemble). Differential Revision: https://reviews.llvm.org/D32847 This should fix "out of range pc-relative fixup value" errors, when compiling certain ARM inline assembly for www/webkit-gtk[23]. Reported by: mmel
* Further expand the r318785 entry, noting vfs.zfs.debugflags can begjb2017-05-251-1/+4
| | | | | | | set in loader.conf(5), whereas vfs.zfs.debug_flags could not. Submitted by: avg Sponsored by: The FreeBSD Foundation
* Document r312790, EC2 IPv6 by default.gjb2017-05-251-0/+4
| | | | Sponsored by: The FreeBSD Foundation
* Document r318660, Amazon EFS support in the NFS client.gjb2017-05-251-0/+4
| | | | Sponsored by: The FreeBSD Foundation
* Document r318660, various NFS client fixes.gjb2017-05-251-1/+7
| | | | Sponsored by: The FreeBSD Foundation
* Document r318785, vfs.zfs.debug_flags -> vfs.zfs.debugflags rename.gjb2017-05-251-1/+4
| | | | Sponsored by: The FreeBSD Foundation
* MFC r318863:jlh2017-05-251-1/+1
| | | | Replace stale handbook URL with the proper one.
* MFC r318014, r318091, r318125, and r318263.np2017-05-253-9/+50
| | | | | | | | | | | | | | | | | | | | | | | r318014: cxgbe(4): Fixes related to the knob that controls link autonegotiation. - Do not leak the adapter lock in sysctl_autoneg. - Accept only 0 or 1 as valid settings for autonegotiation. - A fixed speed must be requested by the driver when autonegotiation is disabled otherwise the firmware will reject the l1cfg command. Use the top speed supported by the port for now. r318091: cxgbe(4): Do not assume that if_qflush is always followed by inteface-down. r318125: Adjust whitespace and fix a comment. No functional change. r318263: cxgbe(4): netmap-only interrupts for a VI do not have an associated rxq or ofld_rxq and should be ignored by vi_intr_iq. Sponsored by: Chelsio Communications
* MFC r318646:gjb2017-05-252-5/+6
| | | | | | | Allow PORTSDIR to be overridden in the pkg-stage target. PR: 218393 Sponsored by: The FreeBSD Foundation
* MFC r318599, r318643:gjb2017-05-251-18/+16
| | | | | | | | | | | | | r318599 (bjk): Updates for efivar.8 Fix spelling, appease igor and mandoc -Tlint, and adopt the language style to be more consistent with our corpus. r318643: Correct the "first appeared in" version for efivar(8). Sponsored by: The FreeBSD Foundation
* MFC r317702, r317847, r318307np2017-05-259-294/+640
| | | | | | | | | | | | | | | | | | | | | | | r317702: cxgbe(4): Support routines for Tx traffic scheduling. - Create a new file, t4_sched.c, and move all of the code related to traffic management from t4_main.c and t4_sge.c to this file. - Track both Channel Rate Limiter (ch_rl) and Class Rate Limiter (cl_rl) parameters in the PF driver. - Initialize all the cl_rl limiters with somewhat arbitrary default rates and provide routines to update them on the fly. - Provide routines to reserve and release traffic classes. r317847: cxgbe(4): The Tx scheduler initialization either works or doesn't. It doesn't need a refresh in either case. r318307: cxgbe(4): Avoid an out of bounds access when an attempt to unbind a tx queue from a traffic class fails. Sponsored by: Chelsio Communications
* MFC r308737, r308779:gjb2017-05-251-2/+2
| | | | | | | | | | | | r308737: Pass SWAPSIZE in env(1) when invoking mk-vmimage.sh, otherwise mkimg(1) does not create the second partition after r307008. r308779: Pass SWAPSIZE in env(1) when invoking mk-vmimage.sh for the vm-image target, missed in r308737. Sponsored by: The FreeBSD Foundation
* MFC r318479:markj2017-05-251-1/+1
| | | | Don't bother enqueuing a page immediately before freeing it.
* MFC r318476, r318478:markj2017-05-252-3/+3
| | | | Fix up some kern_yield() usages.
* MFC r318124:np2017-05-251-0/+1
| | | | ip6_output runs with the inp lock held, just like ip_output.
* MFC r318191:markj2017-05-251-2/+2
| | | | Let ptracestop() suspend threads sleeping in an SBDRY section.
* MFC r317820 and r317837.np2017-05-253-2/+42
| | | | | | | | | | | | r317820: cxgbe(4): Update the list of PCIe devices claimed by the driver. At this point any board with a T6 should just work. r317837: cxgbe(4): Update the VF device ids too. This should have been part of r317820. Sponsored by: Chelsio Communications
* MFC r317041:np2017-05-252-10/+58
| | | | | | | | cxgbe: Add tunables to control the number of LRO entries and the number of rx mbufs that should be presorted before LRO. There is no change in default behavior. Sponsored by: Chelsio Communications
* MFC r318603: nm: document 'r' symbol typeemaste2017-05-251-1/+3
| | | | | PR: 219245 Sponsored by: The FreeBSD Foundation
* MFC r316971:np2017-05-253-8/+39
| | | | | | | | | | | cxgbe: Add a tunable to configure the SGE time scaler, which is available starting with T6. The values in the timer holdoff registers are multiplied by the scaling factor before use. dev.<nexus>.<n>.holdoff_timers shows the final values of the timers in microseconds. Sponsored by: Chelsio Communications
* MFC r316506:np2017-05-241-9/+12
| | | | cxgbe(4): Program the global RSS key once instead of once per ifnet.
* MFC r316172:np2017-05-241-1/+2
| | | | | | cxgbe: Don't call t4_edc_err_read for errors not related to the EDCs. Sponsored by: Chelsio Communications
* MFC r309725:np2017-05-242-2/+6
| | | | | | | cxgbe(4): netmap does not set IFCAP_NETMAP in an ifnet's if_capabilities any more (since r307394). Do it in the driver instead. Sponsored by: Chelsio Communications
* MFC r317759:asomers2017-05-241-9/+6
| | | | | | | | | | Fix memory leaks in camcontrol Reported by: Coverity CID: 1331674, 1331675 Reviewed by: ken Sponsored by: Spectra Logic Corp Differential Revision: https://reviews.freebsd.org/D10588
* MFC r307380:np2017-05-241-1/+1
| | | | Fix typo in comments.
* MFC r317755, r317758asomers2017-05-245-39/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | r317755: Various Coverity fixes in ifconfig(8) * Exit early if kldload(2) fails (1011259). This is the only change that affects ifconfig's behavior. * Close memory and resource leaks (1305624, 1305205, 1007100) * Mark usage() as _Noreturn (1305806, 1305750) * Fix some dereference after null checks (1011474, 270774) Reported by: Coverity CID: 1305624, 1305205, 1007100, 1305806, 1305750, 1011474, CID: 270774, 1011259 Reviewed by: cem Sponsored by: Spectra Logic Corp Differential Revision: https://reviews.freebsd.org/D10587 r317758: Unbreak ifconfig for mlx4en(4) after r317755 ifconfig doesn't correctly infer mlx interfaces' module names, so it will attempt to load the mlx(4) module even when not necessary. Reported by: rstone X-MFC-With: 317755 Sponsored by: Spectra Logic Corp
* MFC r307008:np2017-05-242-1/+2
| | | | | | | Add the ability to override the size of the swap partition when building VM images. The default continues to be 1G. Sponsored by: Chelsio Communications
* MFC r313318:np2017-05-242-46/+50
| | | | | | | | | | | cxgbe(4): Allow tunables that control the number of queues to be set to '-n' to tell the driver to create _up to_ 'n' queues if enough cores are available. For example, setting hw.cxgbe.nrxq10g="-32" will result in 16 queues if the system has 16 cores, 32 if it has 32. There is no change in the default number of queues of any type. Sponsored by: Chelsio Communications
* MFC r317715:asomers2017-05-241-2/+1
| | | | | | | | ifconfig displays ND6_IFF_NO_DAD as "IGNORELOOP" PR: 218958 Reviewed by: kristof Differential Revision: https://reviews.freebsd.org/D10543
* MFC 318401jpaetzel2017-05-241-1/+1
| | | | | | | | | | Increase the number of LUNs this hardware can support. Experimentally we know this value works, but the hardware may support an even higher value. PR: 213876 Reported by: J.Catrysse@proximedia.be
* MFC r313346:np2017-05-244-6/+9
| | | | | | | | cxgbe/t4_tom: Fix CLIP entry refcounting on the passive side. Every IPv6 connection being handled by the TOE should have a reference on its CLIP entry. Sponsored by: Chelsio Communications
* MFC r314131:np2017-05-241-2/+2
| | | | | | | Avoid NULL dereference in a couple of sysctl handlers in ibcore. iw_cxgbe sets ib_device->dma_device to NULL (since r311880). Sponsored by: Chelsio Communications
* MFC r311880, r314167, r316118, r316571, r316573, r316580, r316936-r316937,np2017-05-248-58/+83
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | r316940, and r317410. r311880: The iw_cxgb and iw_cxgbe drivers should not use a FreeBSD device_t where a linuxkpi style device is expected. If OFED/linuxkpi actually starts using this field then we'll have to figure out whether to create fake devices for these drivers or have linuxkpi deal with NULL device. This mismatch was first reported as part of D6585. r314167: cxgbe/iw_cxgbe: Minor changes for T6. r316118: cxgbe/iw_cxgbe: T6 has no limit on the amount of memory that can be registered in one ib_reg_phys_mr. r316571: cxgbe/iw_cxgbe: Remove bad cast that resulted in incorrect length for memory regions larger than 4GB. r316573: 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. r316580: cxgbe/iw_cxgbe: Remove another bad cast. This should have been included in r316571. r316936: cxgbe/iw_cxgbe: hw supports 64K (not 32K) Protection Domains. r316937: cxgbe/iw_cxgbe: Report accurate page_size_cap in ib_query_device. r316940: cxgbe/iw_cxgbe: Report the actual values of various parameters as configured by the firmware. r317410: cxgbe/iw_cxgbe: Pull in some updates to c4iw_wait_for_reply from the iw_cxgb4 Linux driver. Sponsored by: Chelsio Communications
* MFC r316774:np2017-05-243-0/+19
| | | | | | cxgbe: Query some more RDMA related parameters from the firmware. Sponsored by: Chelsio Communications
* MFC r312346:loos2017-05-241-2/+6
| | | | | | | | Set the the wp_disabled flag when asked to. While here, add the missing new line. Sponsored by: Rubicon Communications, LLC (Netgate)
* Document r318763, EARLY_AP_STARTUP enabled by default.gjb2017-05-241-0/+6
| | | | Sponsored by: The FreeBSD Foundation
* MFC r316854: rename vfs.zfs.debug_flags to vfs.zfs.debugflagsavg2017-05-241-1/+5
| | | | | Since this is a stable branch vfs.zfs.debug_flags sysctl is also kept. The corresponing tunable could never work.
* MFC r316853: dtrace: fix normalization of stddev aggregationavg2017-05-241-0/+2
| | | | Sponsored by: Panzura
* MFC r316643: use msr 0xc001100c to discover multi-node AMD processorsavg2017-05-241-7/+14
|
* MFC r318399:ae2017-05-241-0/+8
| | | | | | | | | | | | | | | | | Set M_BCAST and M_MCAST flags on mbuf sent via divert socket. r290383 has changed how mbufs sent by divert socket are handled. Previously they are always handled by slow path processing in ip_input(). Now ip_tryforward() is invoked from ip_input() before in_broadcast() check. Since diverted packet lost all mbuf flags, it passes the broadcast check in ip_tryforward() due to missing M_BCAST flag. In the result the broadcast packet is forwarded to the wire instead of be consumed by network stack. Add in_broadcast() check to the div_output() function. And restore the M_BCAST flag if destination address is broadcast for the given network interface. PR: 209491
* MFC r318400:ae2017-05-241-10/+6
| | | | | | Allow zero port specification in table entries with type flow. PR: 217620
* MFC r318135:mmel2017-05-241-8/+8
| | | | Fix parsing of 'vmov Q<n>.F32,Q<n>.F32' instruction.
* MFC r311846:np2017-05-241-1/+594
| | | | | cxgbe(4): Refresh t4_msg.h, mainly for definitions related to the crypto engine.
* MFC r317170, r317389, and r317390.np2017-05-241-8/+5
| | | | | | | | | | | | | | | r317170: Remove redundant assignment. r317389: Frames that are not considered for LRO should not be counted in LRO statistics. r317390: Flush the LRO ctrl as soon as lro_mbufs fills up. There is no need to wait for the next enqueue from the driver. Sponsored by: Chelsio Communications
* MFC 315334: Decode arguments to chflagsat().jhb2017-05-241-0/+2
|
* MFC 315310: Spell "const" properly.jhb2017-05-241-1/+1
| | | | PR: 217797
* MFC 315283:jhb2017-05-241-9/+1
| | | | | | Fix sysdecode_cap_rights which currently prints bogus capability rights. PR: 217787
* MFC 310177: Enable EARLY_AP_STARTUP on amd64 and i386 kernels by default.jhb2017-05-243-0/+3
| | | | | | PR: 199321, 203682 Discussed with: re (kib) Relnotes: yes
OpenPOWER on IntegriCloud