x86: put initial_pg_tables into .bss

Impact: makes vmlinux section information more useful

Don't use ram after _end blindly for pagetables. aka init pages is before _end
put those pg table into .bss

[Adapted to use brk segment - Jeremy]

v2: keep initial page table up to 512M only.
v4: put initial page tables just before _end

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 9e89f2a..c79741c 100644 (file)
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -41,41 +41,28 @@
  * This is how much memory *in addition to the memory covered up to
  * and including _end* we need mapped initially.
  * We need:
- *  - one bit for each possible page, but only in low memory, which means
- *     2^32/4096/8 = 128K worst case (4G/4G split.)
- *  - enough space to map all low memory, which means
- *     (2^32/4096) / 1024 pages (worst case, non PAE)
- *     (2^32/4096) / 512 + 4 pages (worst case for PAE)
- *  - a few pages for allocator use before the kernel pagetable has
- *     been set up
+ *     (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE)
+ *     (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE)
  *
  * Modulo rounding, each megabyte assigned here requires a kilobyte of
  * memory, which is currently unreclaimed.
  *
  * This should be a multiple of a page.
+ *
+ * KERNEL_IMAGE_SIZE should be greater than pa(_end)
+ * and small than max_low_pfn, otherwise will waste some page table entries
  */
 LOW_PAGES = (KERNEL_IMAGE_SIZE + PAGE_SIZE_asm - 1)>>PAGE_SHIFT
 
-/*
- * To preserve the DMA pool in PAGEALLOC kernels, we'll allocate
- * pagetables from above the 16MB DMA limit, so we'll have to set
- * up pagetables 16MB more (worst-case):
- */
-#ifdef CONFIG_DEBUG_PAGEALLOC
-LOW_PAGES = LOW_PAGES + 0x1000000
-#endif
-
 #if PTRS_PER_PMD > 1
 PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PMD) + PTRS_PER_PGD
 #else
 PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PGD)
 #endif
-BOOTBITMAP_SIZE = LOW_PAGES / 8
 ALLOCATOR_SLOP = 4
 
-INIT_MAP_BEYOND_END = BOOTBITMAP_SIZE + (PAGE_TABLE_SIZE + ALLOCATOR_SLOP)*PAGE_SIZE_asm
-
-RESERVE_BRK(pagetables, PAGE_TABLE_SIZE * PAGE_SIZE)
+INIT_MAP_SIZE = (PAGE_TABLE_SIZE + ALLOCATOR_SLOP) * PAGE_SIZE_asm
+RESERVE_BRK(pagetables, INIT_MAP_SIZE)
 
 /*
  * 32-bit kernel entrypoint; only used by the boot CPU.  On entry,
@@ -168,10 +155,10 @@ num_subarch_entries = (. - subarch_entries) / 4
 
 /*
  * Initialize page tables.  This creates a PDE and a set of page
- * tables, which are located immediately beyond _end.  The variable
+ * tables, which are located immediately beyond __brk_base.  The variable
  * _brk_end is set up to point to the first "safe" location.
  * Mappings are created both at virtual address 0 (identity mapping)
- * and PAGE_OFFSET for up to _end+sizeof(page tables)+INIT_MAP_BEYOND_END.
+ * and PAGE_OFFSET for up to _end.
  *
  * Note that the stack is not yet set up!
  */
@@ -210,10 +197,9 @@ default_entry:
        loop 11b
 
        /*
-        * End condition: we must map up to and including INIT_MAP_BEYOND_END
-        * bytes beyond the end of our own page tables.
+        * End condition: we must map up to the end.
         */
-       leal (INIT_MAP_BEYOND_END+PTE_IDENT_ATTR)(%edi),%ebp
+       movl $pa(_end) + PTE_IDENT_ATTR, %ebp
        cmpl %ebp,%eax
        jb 10b
 1:
@@ -243,11 +229,9 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
        addl $0x1000,%eax
        loop 11b
        /*
-        * End condition: we must map up to and including INIT_MAP_BEYOND_END
-        * bytes beyond the end of our own page tables; the +0x007 is
-        * the attribute bits
+        * End condition: we must map up to end
         */
-       leal (INIT_MAP_BEYOND_END+PTE_IDENT_ATTR)(%edi),%ebp
+       movl $pa(_end) + PTE_IDENT_ATTR, %ebp
        cmpl %ebp,%eax
        jb 10b
        addl $__PAGE_OFFSET, %edi
@@ -638,6 +622,7 @@ swapper_pg_fixmap:
        .fill 1024,4,0
 ENTRY(empty_zero_page)
        .fill 4096,1,0
+
 /*
  * This starts the data section.
  */

diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index a1f28b8..98424f3 100644 (file)
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -210,6 +210,12 @@ SECTIONS
   DWARF_DEBUG
 }
 
+/*
+ * Build-time check on the image size:
+ */
+ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+       "kernel image bigger than KERNEL_IMAGE_SIZE")
+
 #ifdef CONFIG_KEXEC
 /* Link time checks */
 #include <asm/kexec.h>