mm/vmalloc: enable mapping of huge pages at pte level in vmalloc

On some architectures like powerpc, there are huge pages that are mapped
at pte level.

Enable it in vmalloc.

For that, architectures can provide arch_vmap_pte_supported_shift() that
returns the shift for pages to map at pte level.

Link: https://lkml.kernel.org/r/2c717e3b1fba1894d890feb7669f83025bfa314d.1620795204.git.christophe.leroy@csgroup.eu
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Uladzislau Rezki <uladzislau.rezki@sony.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 54ec073..1dabd6f 100644 (file)
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -112,6 +112,13 @@ static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, uns
 }
 #endif
 
+#ifndef arch_vmap_pte_supported_shift
+static inline int arch_vmap_pte_supported_shift(unsigned long size)
+{
+       return PAGE_SHIFT;
+}
+#endif
+
 /*
  *     Highlevel APIs for driver use
  */

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index fe0af8d..71dd29f 100644 (file)
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2927,8 +2927,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
                return NULL;
        }
 
-       if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) &&
-                       arch_vmap_pmd_supported(prot)) {
+       if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) {
                unsigned long size_per_node;
 
                /*
@@ -2941,11 +2940,13 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
                size_per_node = size;
                if (node == NUMA_NO_NODE)
                        size_per_node /= num_online_nodes();
-               if (size_per_node >= PMD_SIZE) {
+               if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE)
                        shift = PMD_SHIFT;
-                       align = max(real_align, 1UL << shift);
-                       size = ALIGN(real_size, 1UL << shift);
-               }
+               else
+                       shift = arch_vmap_pte_supported_shift(size_per_node);
+
+               align = max(real_align, 1UL << shift);
+               size = ALIGN(real_size, 1UL << shift);
        }
 
 again: