[S390] add support for physical memory > 4TB

The kernel address space of a 64 bit kernel currently uses a three level
page table and the vmemmap array has a fixed address and a fixed maximum
size. A three level page table is good enough for systems with less than
3.8TB of memory, for bigger systems four page table levels need to be
used. Each page table level costs a bit of performance, use 3 levels for
normal systems and 4 levels only for the really big systems.
To avoid bloating sparse.o too much set MAX_PHYSMEM_BITS to 46 for a
maximum of 64TB of memory.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

2 files changed, 10 insertions, 17 deletions

diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index d4b9fb4d0042..5d633019d8f3 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -93,18 +93,22 @@ static unsigned long setup_zero_pages(void)
 void __init paging_init(void)
 {
         unsigned long max_zone_pfns[MAX_NR_ZONES];
-        unsigned long pgd_type;
+        unsigned long pgd_type, asce_bits;
 
         init_mm.pgd = swapper_pg_dir;
-        S390_lowcore.kernel_asce = __pa(init_mm.pgd) & PAGE_MASK;
 #ifdef CONFIG_64BIT
-        /* A three level page table (4TB) is enough for the kernel space. */
-        S390_lowcore.kernel_asce |= _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
-        pgd_type = _REGION3_ENTRY_EMPTY;
+        if (VMALLOC_END > (1UL << 42)) {
+                asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
+                pgd_type = _REGION2_ENTRY_EMPTY;
+        } else {
+                asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
+                pgd_type = _REGION3_ENTRY_EMPTY;
+        }
 #else
-        S390_lowcore.kernel_asce |= _ASCE_TABLE_LENGTH;
+        asce_bits = _ASCE_TABLE_LENGTH;
         pgd_type = _SEGMENT_ENTRY_EMPTY;
 #endif
+        S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
         clear_table((unsigned long *) init_mm.pgd, pgd_type,
                     sizeof(unsigned long)*2048);
         vmem_map_init();
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index dc2269f1821c..9a4d02f64f16 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -33,17 +33,6 @@
 #define FRAG_MASK       0x03
 #endif
 
-unsigned long VMALLOC_START = VMALLOC_END - VMALLOC_SIZE;
-EXPORT_SYMBOL(VMALLOC_START);
-
-static int __init parse_vmalloc(char *arg)
-{
-        if (!arg)
-                return -EINVAL;
-        VMALLOC_START = (VMALLOC_END - memparse(arg, &arg)) & PAGE_MASK;
-        return 0;
-}
-early_param("vmalloc", parse_vmalloc);
 
 unsigned long *crst_table_alloc(struct mm_struct *mm)
 {