[lkml]   [2009]   [Apr]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [PATCH 0/2] [GIT PULL] tracing: various bug fixes

    On Thu, 23 Apr 2009, Jeremy Fitzhardinge wrote:

    > Steven Rostedt wrote:
    > > Ah, this is a lockdep thing.
    > >
    > > The raw_local_irq_save/restore in __native_flush_tlb_global does not update
    > > hardirqs_enabled.
    > >
    > > When we call into ftrace, when we cross page bounderies, we disable
    > > interrupts using the normal local_irq_save/restore calls.
    > >
    > > But when we restore, it detects that interrupts are not going to be enabled,
    > > and keeps hardirqs_enabled off.
    > >
    > > The printk solved the issue because it called local_irq_restore, which set
    > > the variable back.
    > >
    > > I guess there's two solutions here. One, we can change the
    > > raw_local_irq_enable/disable variants in __native_flush_tlb_global to the
    > > non-raw type (it should protect against recursion).
    > >
    > > or we can try to make the ring buffer use the raw_local_irq variants too. I
    > > tried this once before, and it did cause issues.
    > >
    > > Note, there's a "check_flags" in lockdep, but it is only called on locking,
    > > it is not called when we only disable/enable interrupts.
    > >
    > OK, the good news is that its not a callee-save calling convention problem,
    > which is what I feared. But it does sound pretty awkward to fix. Does
    > __native_flush_tlb_global() have to use raw_local_irq_save/restore?

    No, I just investigated (and booted) without the raw versions (using the
    normal disable instead). The hooks just update variables in the task
    struct. I see no reason to have use it.

    I use to use it with ftrace, but I found that issues are caused if ftrace
    called something internal that used local_irq_save.

    Perhaps that is the issue. If something uses raw_local_irq_save then calls
    flush_tlb_global you might get a problem with the flags again (like we did
    here). But the only user of raw_* should be lockdep and irqsoff, and they
    should be able to deal with recursion. I don't think there should be any
    other user.

    -- Steve

     \ /
      Last update: 2009-04-23 19:55    [W:0.021 / U:177.036 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site