summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Set correct argemdio addr, comment out arge1 as its not physicallysbruno2015-10-042-13/+11
| | | | | connected to anything. Move a couple of devices out of the kernel and into modules.
* When trying to execute from a misaligned address raise a SIGBUS with theandrew2015-10-041-0/+5
| | | | | | | invalid address alignment code. Obtained from: EuroBSDCon Sponsored by: ABT Systems Ltd
* Invoke lle_event for new entry iff it has lladdr set.melifaro2015-10-041-2/+4
|
* Bump the stack protector to level "strong".pfg2015-10-041-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The general stack protector is known to be weak and has pretty small coverage. While setting stack-protector-all would give better protection it would come with a performance cost: for this reason Google's Chrome OS team developed a new stack-protector-strong variant. In addition to the protections offered by -fstack-protector, the new option will guard any function that declares any type or length of local array, even those in structs or unions. It will also protect functions that use a local variable's address in a function argument or on the right-hand side of an assignment. The option was introduced in GCC-4.9, but support for it has been back-ported to our base GCC (r286074) and is also available in clang. The change was tested with dbench and doesn't introduce performance regressions. An exp-run over the ports tree revealed no failures when using the stricter stack-protector-all. Thanks to all testers involved. Reference: https://outflux.net/blog/archives/2014/01/27/fstack-protector-strong/ Tested by: pho, portmgr (antoine) Discussed with: secteam (delphij) Differential Revision: https://reviews.freebsd.org/D3463 PR: 203394 (exp-run) Relnotes: yes MFC: no (not supported in older clang)
* Replace M_NOWAIT with M_WAITOK for consistency with other wireless drivers.kevlo2015-10-041-4/+1
|
* Fix max TX power settings for RT5390/RT5392.kevlo2015-10-042-3/+2
| | | | While here remove wrong definition of RT2860_USB_PHY_MAN_RST.
* When asserting IL bit in exception syndrome register, print the rawkib2015-10-041-1/+1
| | | | | | | register value. Reviewed by: andrew Sponsored by: The FreeBSD Foundation
* Simplify if (lladdr) condition in nd6_cache_lladdr():melifaro2015-10-041-8/+5
| | | | | | | | | | For case (7) (new entry) nothing has to be done except lle_event. Invoke this event directly from "create new lle" code block. For case (4) (existing entry, same mac) useless mac update was performed, along with LLENTRY_RESOLVED lle_event. There was no sense in doing that, since nothing really had changed. Simply avoid this condition instead. Given that, condition was simplified to (3),(5) states which can be merged with previous block.
* Add missing stack unwind information to several assembly functions onrwatson2015-10-043-2/+7
| | | | | | | | | | | | | | ARMv6/7: - Define _SAVE() macro to allow unwind data to be conditionally defined for ARM assembly code in the kernel. - Use _SAVE() to provide unwind information for bcopy_page(), and two (of many) instances of copyin() and copyout(). Reviewed by: andrew, imp MFC after: 3 days Sponsored by: University of Cambridge
* Eliminate nd6_llinfo_settimer(). All consumers were converted tomelifaro2015-10-042-13/+2
| | | | | | use nd6_llinfo_settimer_locked() in r216022. Make nd6_llinfo_settimer_locked() static: last external consumer was converted in r288124.
* Add __noinline attribute to several functions to ease dtrace instrumentationmelifaro2015-10-041-10/+22
|
* Remove per complete the fec aggregation protocol.araujo2015-10-042-11/+0
| | | | | | | | | | | | The remove began with revision r271733. NOTE: This patch must never be merge to 10-Stable Reviewed by: glebius Approved by: bapt (mentor) Relnotes: Yes Sponsored by: EuroBSDCon Sweden. Differential Revision: D3786
* drm2: a few minor fixes after r280183adrian2015-10-048-24/+19
| | | | | | | | | | | | | | * Remove obsolete drm_agp_*_memory() prototypes. * Fix comment in drm_fops.c (outisde -> outside). * Fix some formatting issues in drm_stub.c (spaces -> tabs). * Add missing case statement (gen == 3) in intel_gpu_reset(). * Restore pci_enable_busmaster() call in the init path (fixes gpu hang on i945GM). * Replace M_WAITOK with M_NOWAIT when the return value of malloc is checked (may be incorrect). Submitted by: <s3erios@gmail.com> Reviewed by: dumbbell Approved by: dumbbell Differential Revision: https://reviews.freebsd.org/D3413
* Fix condition for nd6_llinfo_getholdsrc() introduced in r287484.melifaro2015-10-041-2/+3
| | | | | | | | | | Effectively it always returned NULL so SAS was always performed and sometimes the result might have been different. Fix state machine change accidentally introduced in r287985: state (4) inside nd6_cache_lladdr() (existing entry got nd message with the same lladdress) started to cause lle state transition to STALE instead of no-action.
* Fix run(4) mbuf queue flushing / freeing.adrian2015-10-041-1/+20
| | | | | Ensure things are freed during interface stop, or start may end up never being able to transmit a full queue.
* Random zyd(4) fixes to bring TX handling in line with rsu, etcadrian2015-10-041-2/+20
| | | | | | | | | | * don't free buffers in the TX routine, only in transmit/raw_xmit * free nodes + references * .. and free those nodes/references /before/ net80211 detach Tested: * STA mode: zyd0: HMAC ZD1211B, FW 47.25, RF AL2230 S0, PA0 LED 0 BE0 NP1 Gain1 F0
* Fix to make compile on gcc-4.2.1 (eg mips, sparc64.)adrian2015-10-041-20/+20
|
* Fix to compile using gcc-4.2 (eg mips, sparc64.)adrian2015-10-041-22/+22
|
* Initialize fd to -1 so that gcc doesn't emit an unitialized warning.sbruno2015-10-041-1/+2
|
* Add a little, but very useful script for use with programs that work using anpjd2015-10-042-1/+59
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | event loop and should sleep only when waiting for events (eg. via kevent(2)). When a program is going to sleep in the kernel, the script will show its name, PID, kernel stack trace and userland stack trace. Sleeping in kevent(2) is ignored as it is expected to be valid. Sample output: # ./blocking lynxd lynxd(15042) is blocking... kernel`_cv_wait_sig+0x124 kernel`seltdwait+0xae kernel`sys_poll+0x3a3 kernel`amd64_syscall+0x343 kernel`0xffffffff806c79ab lynxd`poll+0xa lynxd`pqSocketCheck+0xa2 lynxd`pqWaitTimed+0x29 lynxd`connectDBComplete+0xd7 lynxd`PQsetdbLogin+0x2ec lynxd`db_connect+0x3c lynxd`main+0x198 lynxd`_start+0x16f 0x2 lynxd(1925) is blocking... kernel`_cv_wait+0x125 zfs.ko`zio_wait+0x5b zfs.ko`dmu_buf_hold_array_by_dnode+0x1dc zfs.ko`dmu_read+0xcb zfs.ko`zfs_freebsd_getpages+0x37b kernel`VOP_GETPAGES_APV+0xa7 kernel`vnode_pager_getpages+0x9a kernel`vm_fault_hold+0x885 kernel`vm_fault+0x77 kernel`trap_pfault+0x211 kernel`trap+0x506 kernel`0xffffffff806c76c2 lynxd`EVP_add_cipher+0x13 lynxd`SSL_library_init+0x11 lynxd`main+0x94 lynxd`_start+0x16f 0x2 lynxd(1925) is blocking... kernel`_cv_wait+0x125 zfs.ko`zio_wait+0x5b zfs.ko`dbuf_read+0x791 zfs.ko`dbuf_findbp+0x12f zfs.ko`dbuf_hold_impl+0xa2 zfs.ko`dbuf_hold+0x1b zfs.ko`dmu_buf_hold_array_by_dnode+0x153 zfs.ko`dmu_read_uio+0x66 zfs.ko`zfs_freebsd_read+0x3a3 kernel`VOP_READ_APV+0xa1 kernel`vn_read+0x13a kernel`vn_io_fault+0x10b kernel`dofileread+0x95 kernel`kern_readv+0x68 kernel`sys_read+0x63 kernel`amd64_syscall+0x343 kernel`0xffffffff806c79ab lynxd`_read+0xa lynxd`__srefill+0x122 lynxd`fgets+0x78 lynxd`file_gets+0x1d lynxd`BIO_gets+0x64 lynxd`PEM_read_bio+0xf5 lynxd`PEM_X509_INFO_read_bio+0x90 lynxd`X509_load_cert_crl_file+0x47 lynxd`by_file_ctrl+0x2e lynxd`X509_STORE_load_locations+0x4a lynxd`sslctx_init+0x255 lynxd`main+0x215 lynxd`_start+0x16f 0x2 Requested by: gnn Obtained from: Wheel Systems http://wheelsystems.com
* net80211: reduce code duplication in the ieee80211_ioctl_setwmeparam() + fix ↵adrian2015-10-031-35/+17
| | | | | | | comments. Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3701
* rum(4): add WME support.adrian2015-10-033-15/+103
| | | | | | | | | | Tested: * WUSB54GC, HOSTAP and STA modes. * Me: rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528 Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3700
* run(4): fix WME support (untested).adrian2015-10-031-21/+22
| | | | | | | | | | | Now run(4) fetches parameters from ic->ic_wme.wme_params array, which is never initialized (and can be safely removed). This patch replaces &ic->ic_wme.wme_params with &ic->ic_wme.wme_chanParams.cap_wmeParams (contains parameters for local station; used by other drivers with WME support). Tested: * me: STA: run0: MAC/BBP RT5390 (rev 0x0502), RF RT5370 (MIMO 1T1R), address 38:83:45:11:78:ae
* Revert r288628 and instead fix a discrepancy between the posix_fadvise(2)markj2015-10-032-7/+10
| | | | | | | man page and POSIX: posix_fadvise(2) returns an error number on failure. Reported by: jilles MFC after: 1 week
* rum(4): fix stats interpretation in rum_ratectl_task()adrian2015-10-031-15/+20
| | | | | | | | | Testing: * WUSB54GC, STA mode Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3690
* rum(4): set short/long retry limitsadrian2015-10-033-1/+25
| | | | | | | | | | | | Now device will use retry limit, which is set via 'ifconfig <interface> maxretry <number>'. Tested: * Tested on WUSB54GC, STA mode. Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3689
* rum(4): fix sequence number generation.adrian2015-10-031-9/+26
| | | | | | | | * drop erroneous RT2573_TX_MORE_FRAG flag; * provide RT2573_TX_HWSEQ where needed. Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3672
* net80211: drop ieee80211_beacon_offsets parameter from ↵adrian2015-10-0312-37/+29
| | | | | | | ieee80211_beacon_alloc() and ieee80211_beacon_update() Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3659
* net80211: drop redundant 3rd parameter from iv_key_set().adrian2015-10-039-29/+28
| | | | | | | | | The MAC can be fetched from the key struct. I added the ndis updates to make it compile. Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3657
* rum(4): drop unused 'node id' parameter.adrian2015-10-032-26/+21
| | | | | Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3655
* rum(4): add support for hardware encryption (WEP, TKIP and CCMP).adrian2015-10-033-29/+451
| | | | | | | | | | | | | | | | | This diff includes: * Transmitter Addresses, Keys and TKIP MIC addition to the Security Key Table. * Proper SEC Control Registers initialization and maintenance. * Additional flags and values in TX descriptor, which are required for encryption support. * Error checking in RX path. Tested: * Tested on WUSB54GC, STA (WEP, TKIP, CCMP), HOSTAP (CCMP) and IBSS (CCMP, WPA-None) modes. * rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode (CCMP+TKIP) Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3640
* rum(4): implement iv_update_beacon call (fixes client power save support).adrian2015-10-031-0/+54
| | | | | Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3632
* rum(4): attach rum_update_slot to ic_updateslot.adrian2015-10-031-3/+13
| | | | | Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3631
* Make GCC happybdrewery2015-10-031-0/+1
|
* Include stddef.h for ptrdiff_tbdrewery2015-10-031-0/+2
|
* The return value of posix_fadvise(2) is just an error status, somarkj2015-10-031-3/+2
| | | | | | | sys_posix_fadvise() should simply return the errno (or 0) to syscallenter() rather than setting a return value. MFC after: 1 week
* Reduce the scope of a variable to the only file where it is used.alc2015-10-033-2/+2
|
* Style fix.bdrewery2015-10-031-0/+1
|
* Add decoding for struct statfs.bdrewery2015-10-032-1/+30
| | | | Reviewed by: jhb (briefly)
* rum(4): split rum_prepare_beacon() into 'alloc' and 'set' stagesadrian2015-10-033-24/+44
| | | | | | | | Note: I manually had to merge this; I merged in the "put beacon_offsets into vap" commit before this. Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3628
* rum(4): add support for AHDEMO mode.adrian2015-10-031-2/+7
| | | | | Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3627
* rum(4): simplify rum_set_bssid(), rum_set_macaddr() and rum_update_promisc()adrian2015-10-032-18/+11
| | | | | | | | | Tested: * rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3626
* Mute this cookie as wellbdrewery2015-10-031-1/+1
|
* rum(4): do not corrupt MAC addressadrian2015-10-032-3/+5
| | | | | | | | Don't override the NIC MAC address with an overridden MAC address for a VAP. Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3625
* rum(4): add error handling for rum_enable_tsf_sync() and rum_prepare_beacon()adrian2015-10-031-22/+42
| | | | | | | | | | | Tested: * rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode Note: haven't tested AP mode yet; will do once the rest of the AP mode / power save commits are in. Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3624
* Perform a single batched update to the object's paging-in-progress countalc2015-10-031-4/+2
| | | | rather than updating it for each page.
* rum(4): move some code from rum_init() into separate function.adrian2015-10-031-13/+24
| | | | | | | | | Tested: * rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3623
* Remove redundant COMPAT_32BIT guard on pkgconfig files. This is already handledbdrewery2015-10-032-4/+2
| | | | | | by the LIBRARIES_ONLY mechanism protecting FILES. Sponsored by: EMC / Isilon Storage Division
* rum(4): add error handling in initialization pathadrian2015-10-031-27/+32
| | | | | | | | | | Tested: * Tested on WUSB54GC, STA mode. * rum0: MAC/BBP RT2573 (rev 0x2573a), RF RT2528, STA mode Submitted by: <s3erios@gmail.com> Differential Revision: https://reviews.freebsd.org/D3622
* Avoid make compatibility mode issues with creating cookies from r287844 and ↵bdrewery2015-10-031-5/+3
| | | | | | | | r287848. Also hide the cookie creation. Suggested by: imp, Daniel O'Connor
OpenPOWER on IntegriCloud