[PATCH RFC v2 0/1] cxl/pci: Support Global Persistent Flush (GPF)

[Davidlohr Bueso <dave@stgolabs.net>]

Hello,

Changes from previous RFC:
 - Added dirty shutdown support such that users can tell via Health
   if there was any data integrity issues. This patch is still marked
   RFC because while in fail (GPF) scenarios that successfully flush the
   data the dirty state is cleared, there is no mention of the regular
   reboot and shutdown scenarios:
   
      o Is the spec relying on the driver to do so? (currently we can
        only reach hot-unplug for this). Regardless, this could use some
	clarification in the spec.
	
      o The spec only mentions reboot/shutdown in that it sets the dirty
        state upon data integrity issues.
   
 - Limited max T1 timeout to 20 seconds (lockup detector default)

For testing, there are patches out for qemu (dirty shutdown):

    https://lore.kernel.org/linux-cxl/20241220160026.204055-3-dave@stgolabs.net/
    
... as well as those shown in the previous RFC:

   https://lore.kernel.org/linux-cxl/20241205082101.1193038-1-dave@stgolabs.net/

Thanks!

Davidlohr Bueso (1):
  cxl/pci: Support Global Persistent Flush (GPF)

 Documentation/driver-api/cxl/maturity-map.rst |   2 +-
 drivers/cxl/core/mbox.c                       |  17 +++
 drivers/cxl/core/pci.c                        | 104 ++++++++++++++++++
 drivers/cxl/core/port.c                       |  68 ++++++++++++
 drivers/cxl/cxl.h                             |   3 +
 drivers/cxl/cxlmem.h                          |  24 ++++
 drivers/cxl/cxlpci.h                          |  64 +++++++++++
 drivers/cxl/pci.c                             |  97 ++++++++++++++++
 8 files changed, 378 insertions(+), 1 deletion(-)

--
2.39.5