From: Ira Weiny <[email protected]>

Add an alignment gate, cxl_validate_group(), that cxl_add_pending() runs
before realizing a tag group: every extent in the group must have its
start_dpa and length aligned to the dax region's mapping granularity.
A misaligned extent makes the resulting dax device unusable, so drop
the whole group rather than accept a partial allocation that would
surface a broken dax_resource.

Based on patches by John Groves.

Signed-off-by: Ira Weiny <[email protected]>
Co-developed-by: John Groves <[email protected]>
Signed-off-by: John Groves <[email protected]>
Co-developed-by: Anisa Su <[email protected]>
Signed-off-by: Anisa Su <[email protected]>
Tested-by: Wonjae Lee <[email protected]>
Tested-by: Junhee Park <[email protected]>
Tested-by: Heesoo Kim <[email protected]>
---
 drivers/cxl/core/mbox.c | 46 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 18044f216de5..a605ffc4c64f 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -7,6 +7,8 @@
 #include <linux/unaligned.h>
 #include <linux/list.h>
 #include <linux/list_sort.h>
+#include <linux/pgtable.h>
+#include <linux/sizes.h>
 #include <cxlpci.h>
 #include <cxlmem.h>
 #include <cxl.h>
@@ -1395,6 +1397,19 @@ static int stage_pending_extent(struct list_head 
*pending,
        return 0;
 }
 
+/*
+ * Extents need to be aligned to dax region's mapping granularity.
+ * Use PMD_SIZE, since cxl_dax_region_probe() calls alloc_dax_region with
+ * PMD_SIZE for the 'align' parameter.
+ */
+static bool cxl_extent_dcd_aligned(const struct cxl_extent *extent)
+{
+       u64 start = le64_to_cpu(extent->start_dpa);
+       u64 len = le64_to_cpu(extent->length);
+
+       return IS_ALIGNED(start, PMD_SIZE) && IS_ALIGNED(len, PMD_SIZE);
+}
+
 /*
  * Compare two extents by shared_extn_seq (ascending).  list_sort is
  * stable, so extents with equal keys keep their arrival order from
@@ -1497,6 +1512,32 @@ static int cxl_realize_group(struct cxl_memdev_state 
*mds, const uuid_t *tag,
        return rc;
 }
 
+/*
+ * Validate a tag @group before realizing it.  Returns 0 if the group may be
+ * added, or a negative errno if it must be dropped.
+ */
+static int cxl_validate_group(struct cxl_memdev_state *mds, const uuid_t *tag,
+                             struct list_head *group)
+{
+       struct device *dev = mds->cxlds.dev;
+       struct cxl_extent_list_node *pos;
+
+       /* Alignment gate — drop the group if any member fails */
+       list_for_each_entry(pos, group, list) {
+               if (!cxl_extent_dcd_aligned(pos->extent)) {
+                       dev_warn_ratelimited(dev,
+                                            "Tag %pUb: dropping group, extent 
DPA:%#llx LEN:%#llx not %#llx-aligned\n",
+                                            tag,
+                                            
le64_to_cpu(pos->extent->start_dpa),
+                                            le64_to_cpu(pos->extent->length),
+                                            (u64)PMD_SIZE);
+                       return -EINVAL;
+               }
+       }
+
+       return 0;
+}
+
 /*
  * Drive the pending Add-Capacity records through cxl_realize_group() one
  * tag group at a time, moving each group that realizes onto the accepted
@@ -1541,6 +1582,11 @@ static int cxl_add_pending(struct cxl_memdev_state *mds,
                 */
                list_sort(NULL, &group, extent_seq_compare);
 
+               if (cxl_validate_group(mds, &tag, &group)) {
+                       drop_extent_group(&group);
+                       continue;
+               }
+
                cnt = cxl_realize_group(mds, &tag, &group);
                if (cnt < 0) {
                        drop_extent_group(&group);
-- 
2.43.0


Reply via email to