x86, mm: probe memory block size for generic x86 64bit

On system with 2TiB ram, current x86_64 have 128M as section size, and
one memory_block only include one section.  So will have 16400 entries
under /sys/devices/system/memory/.

Current code try to use block id to find block pointer in /sys for any
section, and reuse that block pointer.  that finding will take some time
even after commit 7c243c7168dc ("mm: speedup in __early_pfn_to_nid")
that will skip the search in that case during booting up.

So solution could be increase block size just like SGI UV system did.
(harded code to 2g).

This patch is trying to probe the block size to make it match mmio remap
size.  for example, Intel Nehalem later system will have memory range [0,
TOML), [4g, TOMH].  If the memory hole is 2g and total is 128g, TOM will
be 2g, and TOM2 will be 130g.

We could use 2g as block size instead of default 128M.  That will reduce
number of entries in /sys/devices/system/memory/

On system 6TiB system will reduce boot time by 35 seconds.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index f35c66c..b92591f 100644 (file)
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1230,17 +1230,43 @@ const char *arch_vma_name(struct vm_area_struct *vma)
        return NULL;
 }
 
-#ifdef CONFIG_X86_UV
-unsigned long memory_block_size_bytes(void)
+static unsigned long probe_memory_block_size(void)
 {
+       /* start from 2g */
+       unsigned long bz = 1UL<<31;
+
+#ifdef CONFIG_X86_UV
        if (is_uv_system()) {
                printk(KERN_INFO "UV: memory block size 2GB\n");
                return 2UL * 1024 * 1024 * 1024;
        }
-       return MIN_MEMORY_BLOCK_SIZE;
-}
 #endif
 
+       /* less than 64g installed */
+       if ((max_pfn << PAGE_SHIFT) < (16UL << 32))
+               return MIN_MEMORY_BLOCK_SIZE;
+
+       /* get the tail size */
+       while (bz > MIN_MEMORY_BLOCK_SIZE) {
+               if (!((max_pfn << PAGE_SHIFT) & (bz - 1)))
+                       break;
+               bz >>= 1;
+       }
+
+       printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20);
+
+       return bz;
+}
+
+static unsigned long memory_block_size_probed;
+unsigned long memory_block_size_bytes(void)
+{
+       if (!memory_block_size_probed)
+               memory_block_size_probed = probe_memory_block_size();
+
+       return memory_block_size_probed;
+}
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.