linux/Documentation/irqflags-tracing.txt
<<
>>
Prefs
   1IRQ-flags state tracing
   2
   3started by Ingo Molnar <mingo@redhat.com>
   4
   5the "irq-flags tracing" feature "traces" hardirq and softirq state, in
   6that it gives interested subsystems an opportunity to be notified of
   7every hardirqs-off/hardirqs-on, softirqs-off/softirqs-on event that
   8happens in the kernel.
   9
  10CONFIG_TRACE_IRQFLAGS_SUPPORT is needed for CONFIG_PROVE_SPIN_LOCKING
  11and CONFIG_PROVE_RW_LOCKING to be offered by the generic lock debugging
  12code. Otherwise only CONFIG_PROVE_MUTEX_LOCKING and
  13CONFIG_PROVE_RWSEM_LOCKING will be offered on an architecture - these
  14are locking APIs that are not used in IRQ context. (the one exception
  15for rwsems is worked around)
  16
  17architecture support for this is certainly not in the "trivial"
  18category, because lots of lowlevel assembly code deal with irq-flags
  19state changes. But an architecture can be irq-flags-tracing enabled in a
  20rather straightforward and risk-free manner.
  21
  22Architectures that want to support this need to do a couple of
  23code-organizational changes first:
  24
  25- move their irq-flags manipulation code from their asm/system.h header
  26  to asm/irqflags.h
  27
  28- rename local_irq_disable()/etc to raw_local_irq_disable()/etc. so that
  29  the linux/irqflags.h code can inject callbacks and can construct the
  30  real local_irq_disable()/etc APIs.
  31
  32- add and enable TRACE_IRQFLAGS_SUPPORT in their arch level Kconfig file
  33
  34and then a couple of functional changes are needed as well to implement
  35irq-flags-tracing support:
  36
  37- in lowlevel entry code add (build-conditional) calls to the
  38  trace_hardirqs_off()/trace_hardirqs_on() functions. The lock validator
  39  closely guards whether the 'real' irq-flags matches the 'virtual'
  40  irq-flags state, and complains loudly (and turns itself off) if the
  41  two do not match. Usually most of the time for arch support for
  42  irq-flags-tracing is spent in this state: look at the lockdep
  43  complaint, try to figure out the assembly code we did not cover yet,
  44  fix and repeat. Once the system has booted up and works without a
  45  lockdep complaint in the irq-flags-tracing functions arch support is
  46  complete.
  47- if the architecture has non-maskable interrupts then those need to be
  48  excluded from the irq-tracing [and lock validation] mechanism via
  49  lockdep_off()/lockdep_on().
  50
  51in general there is no risk from having an incomplete irq-flags-tracing
  52implementation in an architecture: lockdep will detect that and will
  53turn itself off. I.e. the lock validator will still be reliable. There
  54should be no crashes due to irq-tracing bugs. (except if the assembly
  55changes break other code by modifying conditions or registers that
  56shouldnt be)
  57
  58