cxl/region: Flag partially torn down regions as unusable

cxl_region_decode_reset() walks all the decoders associated with a given
region and disables them. Due to decoder ordering rules it is possible
that a switch in the topology notices that a given decoder can not be
shutdown before another region with a higher HPA is shutdown first. That
can leave the region in a partially committed state.

Capture that state in a new CXL_REGION_F_NEEDS_RESET flag and require
that a successful cxl_region_decode_reset() attempt must be completed
before cxl_region_probe() accepts the region.

This is a corollary for the bug that Jonathan identified in "CXL/region
:  commit reset of out of order region appears to succeed." [1].

Cc: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Link: http://lore.kernel.org/r/20230316171441.0000205b@Huawei.com
Fixes: 176baefb2eb5 ("cxl/hdm: Commit decoder state to hardware")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/168696507423.3590522.16254212607926684429.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 594ce3c2565df86f36a141d04f5429a2874004ce..fa29bd2ec3227042a0f578e33954ad7a77f0ad89 100644 (file)
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -182,14 +182,19 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count)
                                rc = cxld->reset(cxld);
                        if (rc)
                                return rc;
+                       set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
                }
 
 endpoint_reset:
                rc = cxled->cxld.reset(&cxled->cxld);
                if (rc)
                        return rc;
+               set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
        }
 
+       /* all decoders associated with this region have been torn down */
+       clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
+
        return 0;
 }
 
@@ -2864,6 +2869,13 @@ static int cxl_region_probe(struct device *dev)
                goto out;
        }
 
+       if (test_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags)) {
+               dev_err(&cxlr->dev,
+                       "failed to activate, re-commit region and retry\n");
+               rc = -ENXIO;
+               goto out;
+       }
+
        /*
         * From this point on any path that changes the region's state away from
         * CXL_CONFIG_COMMIT is also responsible for releasing the driver.

diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 21ee135d91b684e7bba535e05ec6049eafd5c339..492673d04da2cd8db8ae5267f3ce1f81b296dccd 100644 (file)
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -469,6 +469,14 @@ struct cxl_region_params {
  */
 #define CXL_REGION_F_AUTO 0
 
+/*
+ * Require that a committed region successfully complete a teardown once
+ * any of its associated decoders have been torn down. This maintains
+ * the commit state for the region since there are committed decoders,
+ * but blocks cxl_region_probe().
+ */
+#define CXL_REGION_F_NEEDS_RESET 1
+
 /**
  * struct cxl_region - CXL region
  * @dev: This region's device