• David Mosberger-Tang's avatar
    [IA64] esi-support · 2ab561a1
    David Mosberger-Tang authored
    Add support for making ESI calls [1].  ESI stands for "Extensible SAL
    specification" and is basically a way for invoking firmware
    subroutines which are identified by a GUID.  I don't know whether ESI
    is used by vendors other than HP (if you do, please let me know) but
    as firmware "backdoors" go, this seems one of the cleaner methods, so
    it seems reasonable to support it, even though I'm not aware of any
    publicly documented ESI calls.  I'd have liked to make the ESI module
    completely stand-alone, but unfortunately that is not easily (or not
    at all) possible because in order to make ESI calls in physical mode,
    a small stub similar to the EFI stub is needed in the kernel proper.
    I did try to create a stub that would work in user-level, but it
    quickly got ugly beyond recognition (e.g., the stub had to make
    assumptions about how the module-loader generated call-stubs work) and
    I didn't even get it to work (that's probably fixable, but I didn't
    bother because I concluded it was too ugly anyhow).  While it's not
    terribly elegant to have kernel code which isn't actively used in the
    kernel proper, I think it might be worth making an exception here for
    two reasons: the code is trivially small (all that's really needed is
    esi_stub.S) and by including it in the normal kernel distro, it might
    encourage other OEMs to also use ESI, which I think would be far
    better than each inventing their own firmware "backdoor".
    
    The code was originally written by Alex.  I just massaged and packaged
    it a bit (and perhaps messed up some things along the way...).
    
    Changes since first version of patch that was posted to mailing list:
    * Export ia64_esi_call and ia64_esi_call_phys() as GPL symbols.
    * Disallow building esi.c as a module for now.  Building as a module
      would currently lead to an unresolved reference to "sal_lock" on SMP kernels
      because that symbol doesn't get exported.
    * Export esi_call_phys() only if ESI is enabled.
    * Remove internal stuff from esi.h and add a "proc_type" argument to
      ia64_esi_call() such that serialization-requirements can be expressed (ESI
      follows SAL here, where procedure calls may have to be serialized, are
      MP-safe, or MP-safe andr reentrant).
    
    [1] h21007.www2.hp.com/dspp/tech/tech_TechDocumentDetailPage_IDX/1,1701,919,00.html
    Signed-off-by: default avatarDavid Mosberger <David.Mosberger@acm.org>
    Signed-off-by: default avatarAlex Williamson <alex.williamson@hp.com>
    Signed-off-by: default avatarTony Luck <tony.luck@intel.com>
    2ab561a1
esi.h 881 Bytes