x86: fix spontaneous reboot with allyesconfig bzImage

recently the 64-bit allyesconfig bzImage kernel started spontaneously
rebooting during early bootup.

after a few fun hours spent with early init debugging, it turns out
that we've got this rather annoying limit on the size of the kernel
image:

      #define KERNEL_TEXT_SIZE  (40*1024*1024)

which limit my vmlinux just happened to pass:

       text           data       bss        dec       hex   filename
   29703744        4222751   8646224   42572719   2899baf   vmlinux

40 MB is 42572719 bytes, so my vmlinux was just 1.5% above this limit :-/

So it happily crashed right in head_64.S, which - as we all know - is
the most debuggable code in the whole architecture ;-)

So increase the limit to allow an up to 128MB kernel image to be mapped.
(should anyone be that crazy or lazy)

We have a full 4K of pagetable (level2_kernel_pgt) allocated for these
mappings already, so there's no RAM overhead and the limit was rather
pointless and arbitrary.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 17 insertions, 10 deletions

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index eb415043a929..b037b15be7f8 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -379,18 +379,24 @@ NEXT_PAGE(level2_ident_pgt)
         /* Since I easily can, map the first 1G.
          * Don't set NX because code runs from these pages.
          */
-        PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD)
+        PMDS(0, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD)
 
 NEXT_PAGE(level2_kernel_pgt)
-        /* 40MB kernel mapping. The kernel code cannot be bigger than that.
-           When you change this change KERNEL_TEXT_SIZE in page.h too. */
-        /* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */
-        PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, KERNEL_TEXT_SIZE/PMD_SIZE)
-        /* Module mapping starts here */
-        .fill   (PTRS_PER_PMD - (KERNEL_TEXT_SIZE/PMD_SIZE)),8,0
+        /*
+         * 128 MB kernel mapping. We spend a full page on this pagetable
+         * anyway.
+         *
+         * The kernel code+data+bss must not be bigger than that.
+         *
+         * (NOTE: at +128MB starts the module area, see MODULES_VADDR.
+         *  If you want to increase this then increase MODULES_VADDR
+         *  too.)
+         */
+        PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL,
+                KERNEL_TEXT_SIZE/PMD_SIZE)
 
 NEXT_PAGE(level2_spare_pgt)
-        .fill   512,8,0
+        .fill   512, 8, 0
 
 #undef PMDS
 #undef NEXT_PAGE
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 6dbb0035c57a..a02a14f0f324 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -172,8 +172,9 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
 }
 
 /*
- * The head.S code sets up the kernel high mapping from:
- * __START_KERNEL_map to __START_KERNEL_map + KERNEL_TEXT_SIZE
+ * The head.S code sets up the kernel high mapping:
+ *
+ *   from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text)
  *
  * phys_addr holds the negative offset to the kernel, which is added
  * to the compile time generated pmds. This results in invalid pmds up