1. 24 Jul, 2006 9 commits
  2. 23 Jul, 2006 5 commits
    • Roland Dreier's avatar
      IB/uverbs: Fix lockdep warnings · 43db2bc0
      Roland Dreier authored
      Lockdep warns because uverbs is trying to take uobj->mutex when it
      already holds that lock.  This is because there are really multiple
      types of uobjs even though all of their locks are initialized in
      common code.
      Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      43db2bc0
    • Michael S. Tsirkin's avatar
      IB/uverbs: Fix unlocking in error paths · ec924b47
      Michael S. Tsirkin authored
      ib_uverbs_create_ah() and ib_uverbs_create_srq() did not release the
      PD's read lock in their error paths, which lead to deadlock when
      destroying the PD.
      Signed-off-by: default avatarMichael S. Tsirkin <mst@mellanox.co.il>
      Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      ec924b47
    • Paul Jackson's avatar
      [PATCH] Cpuset: fix ABBA deadlock with cpu hotplug lock · abb5a5cc
      Paul Jackson authored
      Fix ABBA deadlock between lock_cpu_hotplug() and the cpuset
      callback_mutex lock.
      
      It only happens on cpu_exclusive cpusets, due to the dynamic
      sched domain code trying to take the cpu hotplug lock inside
      the cpuset callback_mutex lock.
      
      This bug has apparently been here for several months, but didn't
      get hit until the right customer load on a large system.
      
      This fix appears right from inspection, but it will take a few
      more days running it on that customers workload to be confident
      we nailed it.  We don't have any other reproducible test case.
      
      The cpu_hotplug_lock() tends to cover large runs of code.
      The other places that hold both that lock and the cpuset callback
      mutex lock always nest the cpuset lock inside the hotplug lock.
      This place tries to do the reverse, risking an ABBA deadlock.
      
      This is in the cpuset_rmdir() code, where we:
        * take the callback_mutex lock
        * mark the cpuset CS_REMOVED
        * call update_cpu_domains for cpu_exclusive cpusets
        * in that call, take the cpu_hotplug lock if the
          cpuset is marked for removal.
      
      Thanks to Jack Steiner for identifying this deadlock.
      
      The fix is to tear down the dynamic sched domain before we grab
      the cpuset callback_mutex lock.  This way, the two locks are
      serialized, with the hotplug lock taken and released before
      trying for the cpuset lock.
      
      I suspect that this bug was introduced when I changed the
      cpuset locking from one lock to two.  The dynamic sched domain
      dependency on cpu_exclusive cpusets and its hotplug hooks were
      added to this code earlier, when cpusets had only a single lock.
      It may well have been fine then.
      Signed-off-by: default avatarPaul Jackson <pj@sgi.com>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      abb5a5cc
    • Linus Torvalds's avatar
      cpu hotplug: simplify and hopefully fix locking · aa953877
      Linus Torvalds authored
      The CPU hotplug locking was quite messy, with a recursive lock to
      handle the fact that both the actual up/down sequence wanted to
      protect itself from being re-entered, but the callbacks that it
      called also tended to want to protect themselves from CPU events.
      
      This splits the lock into two (one to serialize the whole hotplug
      sequence, the other to protect against the CPU present bitmaps
      changing). The latter still allows recursive usage because some
      subsystems (ondemand policy for cpufreq at least) had already gotten
      too used to the lax locking, but the locking mistakes are hopefully
      now less fundamental, and we now warn about recursive lock usage
      when we see it, in the hope that it can be fixed.
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      aa953877
    • Linus Torvalds's avatar
      [cpufreq] ondemand: make shutdown sequence more robust · 2cd7cbdf
      Linus Torvalds authored
      Shutting down the ondemand policy was fraught with potential
      problems, causing issues for SMP suspend (which wants to hot-
      unplug) all but the last CPU.
      
      This should fix at least the worst problems (divide-by-zero
      and infinite wait for the workqueue to shut down).
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      2cd7cbdf
  3. 21 Jul, 2006 26 commits