powerpc: scan device tree for gigantic pages

The 16G huge pages have to be reserved in the HMC prior to boot.  The
location of the pages are placed in the device tree.  This patch adds code
to scan the device tree during very early boot and save these page
locations until hugetlbfs is ready for them.

Acked-by: Adam Litke <[email protected]>
Signed-off-by: Jon Tollefson <[email protected]>
Signed-off-by: Nick Piggin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 8d3b58ebd38e62d737f2f10aa773406d7c0c6473..ae4c717243a548573c111565947f93d517120c13 100644 (file)
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -68,6 +68,7 @@
 
 #define KB (1024)
 #define MB (1024*KB)
 
 #define KB (1024)
 #define MB (1024*KB)

+#define GB (1024L*MB)

 
 /*
  * Note:  pte   --> Linux PTE
 
 /*
  * Note:  pte   --> Linux PTE


@@ -329,6 +330,44 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
        return 0;
 }
 
        return 0;
 }
 

+/* Scan for 16G memory blocks that have been set aside for huge pages
+ * and reserve those blocks for 16G huge pages.
+ */
+static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
+                                       const char *uname, int depth,
+                                       void *data) {
+       char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+       unsigned long *addr_prop;
+       u32 *page_count_prop;
+       unsigned int expected_pages;
+       long unsigned int phys_addr;
+       long unsigned int block_size;
+
+       /* We are scanning "memory" nodes only */
+       if (type == NULL || strcmp(type, "memory") != 0)
+               return 0;
+
+       /* This property is the log base 2 of the number of virtual pages that
+        * will represent this memory block. */
+       page_count_prop = of_get_flat_dt_prop(node, "ibm,expected#pages", NULL);
+       if (page_count_prop == NULL)
+               return 0;
+       expected_pages = (1 << page_count_prop[0]);
+       addr_prop = of_get_flat_dt_prop(node, "reg", NULL);
+       if (addr_prop == NULL)
+               return 0;
+       phys_addr = addr_prop[0];
+       block_size = addr_prop[1];
+       if (block_size != (16 * GB))
+               return 0;
+       printk(KERN_INFO "Huge page(16GB) memory: "
+                       "addr = 0x%lX size = 0x%lX pages = %d\n",
+                       phys_addr, block_size, expected_pages);
+       lmb_reserve(phys_addr, block_size * expected_pages);
+       add_gpage(phys_addr, block_size, expected_pages);
+       return 0;
+}
+

 static void __init htab_init_page_sizes(void)
 {
        int rc;
 static void __init htab_init_page_sizes(void)
 {
        int rc;


@@ -418,7 +457,10 @@ static void __init htab_init_page_sizes(void)
               );
 
 #ifdef CONFIG_HUGETLB_PAGE
               );
 
 #ifdef CONFIG_HUGETLB_PAGE

-       /* Init large page size. Currently, we pick 16M or 1M depending
+       /* Reserve 16G huge page memory sections for huge pages */
+       of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL);
+
+/* Init large page size. Currently, we pick 16M or 1M depending

         * on what is available
         */
        if (mmu_psize_defs[MMU_PAGE_16M].shift)
         * on what is available
         */
        if (mmu_psize_defs[MMU_PAGE_16M].shift)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5df82186fc93ea12ab9f33c85e4665e5a4022b8e..e2a650a9e533494b9686372baa21f82bfc0e297a 100644 (file)
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -110,6 +110,22 @@ pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr)
 }
 #endif
 
 }
 #endif
 

+/* Build list of addresses of gigantic pages.  This function is used in early
+ * boot before the buddy or bootmem allocator is setup.
+ */
+void add_gpage(unsigned long addr, unsigned long page_size,
+       unsigned long number_of_pages)
+{
+       if (!addr)
+               return;
+       while (number_of_pages > 0) {
+               gpage_freearray[nr_gpages] = addr;
+               nr_gpages++;
+               number_of_pages--;
+               addr += page_size;
+       }
+}
+

 /* Moves the gigantic page addresses from the temporary list to the
  * huge_boot_pages list.  */
 int alloc_bootmem_huge_page(struct hstate *h)
 /* Moves the gigantic page addresses from the temporary list to the
  * huge_boot_pages list.  */
 int alloc_bootmem_huge_page(struct hstate *h)

diff --git a/include/asm-powerpc/mmu-hash64.h b/include/asm-powerpc/mmu-hash64.h
index d1dc16afb1186c4a40f374a0e2f5ba3d89ffff2f..b61181aa77461c6e3bc069d2d65be532884a1478 100644 (file)
--- a/include/asm-powerpc/mmu-hash64.h
+++ b/include/asm-powerpc/mmu-hash64.h
@@ -281,6 +281,8 @@ extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
                             unsigned long pstart, unsigned long mode,
                             int psize, int ssize);
 extern void set_huge_psize(int psize);
                             unsigned long pstart, unsigned long mode,
                             int psize, int ssize);
 extern void set_huge_psize(int psize);

+extern void add_gpage(unsigned long addr, unsigned long page_size,
+                         unsigned long number_of_pages);

 extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
 extern void htab_initialize(void);
 extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
 extern void htab_initialize(void);