[59/74] [PATCH] Revert "x86: Cleanup highmap after brk is concluded"

[Greg KH <gregkh@suse.de>]

2.6.32-longterm review patch.  If anyone has any objections, please let us know.

------------------

This reverts upstream commit e5f15b45ddf3afa2bbbb10c7ea34fb32b6de0a0e

It caused problems in the stable tree and should not have been there.

Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/head64.c |    3 +++
 arch/x86/kernel/setup.c  |    5 -----
 arch/x86/mm/init.c       |   19 +++++++++++++++++++
 arch/x86/mm/init_64.c    |   11 +++++------
 4 files changed, 27 insertions(+), 11 deletions(-)

--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -76,6 +76,9 @@ void __init x86_64_start_kernel(char * r
 	/* Make NULL pointers segfault */
 	zap_identity_mappings();
 
+	/* Cleanup the over mapped high alias */
+	cleanup_highmap();
+
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
 #ifdef CONFIG_EARLY_PRINTK
 		set_intr_gate(i, &early_idt_handlers[i]);
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -294,9 +294,6 @@ static void __init init_gbpages(void)
 static inline void init_gbpages(void)
 {
 }
-static void __init cleanup_highmap(void)
-{
-}
 #endif
 
 static void __init reserve_brk(void)
@@ -924,8 +921,6 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_brk();
 
-	cleanup_highmap();
-
 	init_gbpages();
 
 	/* max_pfn_mapped is updated here */
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -287,6 +287,25 @@ unsigned long __init_refok init_memory_m
 	load_cr3(swapper_pg_dir);
 #endif
 
+#ifdef CONFIG_X86_64
+	if (!after_bootmem && !start) {
+		pud_t *pud;
+		pmd_t *pmd;
+
+		mmu_cr4_features = read_cr4();
+
+		/*
+		 * _brk_end cannot change anymore, but it and _end may be
+		 * located on different 2M pages. cleanup_highmap(), however,
+		 * can only consider _end when it runs, so destroy any
+		 * mappings beyond _brk_end here.
+		 */
+		pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
+		pmd = pmd_offset(pud, _brk_end - 1);
+		while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
+			pmd_clear(pmd);
+	}
+#endif
 	__flush_tlb_all();
 
 	if (!after_bootmem && e820_table_end > e820_table_start)
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -49,7 +49,6 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 #include <asm/init.h>
-#include <asm/setup.h>
 #include <linux/bootmem.h>
 
 static unsigned long dma_reserve __initdata;
@@ -258,18 +257,18 @@ void __init init_extra_mapping_uc(unsign
  * to the compile time generated pmds. This results in invalid pmds up
  * to the point where we hit the physaddr 0 mapping.
  *
- * We limit the mappings to the region from _text to _brk_end.  _brk_end
- * is rounded up to the 2MB boundary. This catches the invalid pmds as
+ * We limit the mappings to the region from _text to _end.  _end is
+ * rounded up to the 2MB boundary. This catches the invalid pmds as
  * well, as they are located before _text:
  */
 void __init cleanup_highmap(void)
 {
 	unsigned long vaddr = __START_KERNEL_map;
-	unsigned long vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
-	unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
+	unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
 	pmd_t *pmd = level2_kernel_pgt;
+	pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
-	for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
+	for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
 		if (vaddr < (unsigned long) _text || vaddr > end)