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

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

Enable it in vmap.

For that, architectures can provide arch_vmap_pte_range_map_size() that
returns the size of pages to map at pte level.

Link: https://lkml.kernel.org/r/fb3ccc73377832ac6708181ec419128a2f98ce36.1620795204.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 bfaaf0b..54ec073 100644 (file)
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -104,6 +104,14 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot)
 }
 #endif
 
+#ifndef arch_vmap_pte_range_map_size
+static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end,
+                                                        u64 pfn, unsigned int max_page_shift)
+{
+       return PAGE_SIZE;
+}
+#endif
+
 /*
  *     Highlevel APIs for driver use
  */

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b2ec7f7..fe0af8d 100644 (file)
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -36,6 +36,7 @@
 #include <linux/overflow.h>
 #include <linux/pgtable.h>
 #include <linux/uaccess.h>
+#include <linux/hugetlb.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
@@ -83,10 +84,11 @@ static void free_work(struct work_struct *w)
 /*** Page table manipulation functions ***/
 static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
                        phys_addr_t phys_addr, pgprot_t prot,
-                       pgtbl_mod_mask *mask)
+                       unsigned int max_page_shift, pgtbl_mod_mask *mask)
 {
        pte_t *pte;
        u64 pfn;
+       unsigned long size = PAGE_SIZE;
 
        pfn = phys_addr >> PAGE_SHIFT;
        pte = pte_alloc_kernel_track(pmd, addr, mask);
@@ -94,9 +96,22 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
                return -ENOMEM;
        do {
                BUG_ON(!pte_none(*pte));
+
+#ifdef CONFIG_HUGETLB_PAGE
+               size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift);
+               if (size != PAGE_SIZE) {
+                       pte_t entry = pfn_pte(pfn, prot);
+
+                       entry = pte_mkhuge(entry);
+                       entry = arch_make_huge_pte(entry, ilog2(size), 0);
+                       set_huge_pte_at(&init_mm, addr, pte, entry);
+                       pfn += PFN_DOWN(size);
+                       continue;
+               }
+#endif
                set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
                pfn++;
-       } while (pte++, addr += PAGE_SIZE, addr != end);
+       } while (pte += PFN_DOWN(size), addr += size, addr != end);
        *mask |= PGTBL_PTE_MODIFIED;
        return 0;
 }
@@ -145,7 +160,7 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
                        continue;
                }
 
-               if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
+               if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask))
                        return -ENOMEM;
        } while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
        return 0;