ehea: Detect 16GB hugepages for firmware restriction

All kernel memory which is used for kernel/hardware data transfer must
be registered with firmware using "memory regions". 16GB hugepages
may not be part of a memory region due to firmware restrictions.
This patch modifies the walk_memory_resource callback fn to filter
hugepages and add only standard memory to the busmap which is later
on used for MR registration.

Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>

1 files changed, 52 insertions, 5 deletions

diff --git a/drivers/net/ehea/ehea_qmr.c b/drivers/net/ehea/ehea_qmr.c
index 9b61dc9865d1..9d006878f045 100644
--- a/drivers/net/ehea/ehea_qmr.c
+++ b/drivers/net/ehea/ehea_qmr.c
@@ -632,10 +632,13 @@ static void ehea_rebuild_busmap(void)
         }
 }
 
-static int ehea_update_busmap(unsigned long pfn, unsigned long pgnum, int add)
+static int ehea_update_busmap(unsigned long pfn, unsigned long nr_pages, int add)
 {
         unsigned long i, start_section, end_section;
 
+        if (!nr_pages)
+                return 0;
+
         if (!ehea_bmap) {
                 ehea_bmap = kzalloc(sizeof(struct ehea_bmap), GFP_KERNEL);
                 if (!ehea_bmap)
@@ -643,7 +646,7 @@ static int ehea_update_busmap(unsigned long pfn, unsigned long pgnum, int add)
         }
 
         start_section = (pfn * PAGE_SIZE) / EHEA_SECTSIZE;
-        end_section = start_section + ((pgnum * PAGE_SIZE) / EHEA_SECTSIZE);
+        end_section = start_section + ((nr_pages * PAGE_SIZE) / EHEA_SECTSIZE);
         /* Mark entries as valid or invalid only; address is assigned later */
         for (i = start_section; i < end_section; i++) {
                 u64 flag;
@@ -692,10 +695,54 @@ int ehea_rem_sect_bmap(unsigned long pfn, unsigned long nr_pages)
         return ret;
 }
 
-static int ehea_create_busmap_callback(unsigned long pfn,
-                                       unsigned long nr_pages, void *arg)
+static int ehea_is_hugepage(unsigned long pfn)
+{
+        int page_order;
+
+        if (pfn & EHEA_HUGEPAGE_PFN_MASK)
+                return 0;
+
+        page_order = compound_order(pfn_to_page(pfn));
+        if (page_order + PAGE_SHIFT != EHEA_HUGEPAGESHIFT)
+                return 0;
+
+        return 1;
+}
+
+static int ehea_create_busmap_callback(unsigned long initial_pfn,
+                                       unsigned long total_nr_pages, void *arg)
 {
-        return ehea_update_busmap(pfn, nr_pages, EHEA_BUSMAP_ADD_SECT);
+        int ret;
+        unsigned long pfn, start_pfn, end_pfn, nr_pages;
+
+        if ((total_nr_pages * PAGE_SIZE) < EHEA_HUGEPAGE_SIZE)
+                return ehea_update_busmap(initial_pfn, total_nr_pages,
+                                          EHEA_BUSMAP_ADD_SECT);
+
+        /* Given chunk is >= 16GB -> check for hugepages */
+        start_pfn = initial_pfn;
+        end_pfn = initial_pfn + total_nr_pages;
+        pfn = start_pfn;
+
+        while (pfn < end_pfn) {
+                if (ehea_is_hugepage(pfn)) {
+                        /* Add mem found in front of the hugepage */
+                        nr_pages = pfn - start_pfn;
+                        ret = ehea_update_busmap(start_pfn, nr_pages,
+                                                 EHEA_BUSMAP_ADD_SECT);
+                        if (ret)
+                                return ret;
+
+                        /* Skip the hugepage */
+                        pfn += (EHEA_HUGEPAGE_SIZE / PAGE_SIZE);
+                        start_pfn = pfn;
+                } else
+                        pfn += (EHEA_SECTSIZE / PAGE_SIZE);
+        }
+
+        /* Add mem found behind the hugepage(s)  */
+        nr_pages = pfn - start_pfn;
+        return ehea_update_busmap(start_pfn, nr_pages, EHEA_BUSMAP_ADD_SECT);
 }
 
 int ehea_create_busmap(void)