summaryrefslogtreecommitdiffstats
path: root/sys/mips/conf/PB92.hints
diff options
context:
space:
mode:
authoradrian <adrian@FreeBSD.org>2011-05-05 08:11:22 +0000
committeradrian <adrian@FreeBSD.org>2011-05-05 08:11:22 +0000
commit7bb431331ff49407ccd475783ff321aeeda4efd4 (patch)
tree4840ddbc9a033d5dd7a10de0f446cc0320b46bf5 /sys/mips/conf/PB92.hints
parent2e02cf00cc81e5fac2eb1ea356e27b032d6920a1 (diff)
downloadFreeBSD-src-7bb431331ff49407ccd475783ff321aeeda4efd4.zip
FreeBSD-src-7bb431331ff49407ccd475783ff321aeeda4efd4.tar.gz
Don't perform NF calibration for radio chains which aren't in use:
Quoting the ath9k commit message: At present the noise floor calibration is processed in supported control and extension chains rather than required chains. Unnccesarily doing nfcal in all supported chains leads to invalid nf readings on extn chains and these invalid values got updated into history buffer. While loading those values from history buffer is moving the chip to deaf state. This issue was observed in AR9002/AR9003 chips while doing associate/dissociate in HT40 mode and interface up/down in iterative manner. After some iterations, the chip was moved to deaf state. Somehow the pci devices are recovered by poll work after chip reset. Raading the nf values in all supported extension chains when the hw is not yet configured in HT40 mode results invalid values. Reference: https://patchwork.kernel.org/patch/753862/ Obtained from: Linux ath9k
Diffstat (limited to 'sys/mips/conf/PB92.hints')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud