Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 5 May 2011 08:11:22 +0000 (UTC)
From:      Adrian Chadd <adrian@FreeBSD.org>
To:        cvs-src-old@freebsd.org
Subject:   cvs commit: src/sys/dev/ath/ath_hal/ar5416 ar5416_cal.c
Message-ID:  <201105050811.p458BVZl033366@repoman.freebsd.org>

next in thread | raw e-mail | index | archive | help
adrian      2011-05-05 08:11:22 UTC

  FreeBSD src repository

  Modified files:
    sys/dev/ath/ath_hal/ar5416 ar5416_cal.c 
  Log:
  SVN rev 221488 on 2011-05-05 08:11:22Z by adrian
  
  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
  
  Revision  Changes    Path
  1.24      +12 -4     src/sys/dev/ath/ath_hal/ar5416/ar5416_cal.c



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201105050811.p458BVZl033366>