x86: zap invalid and unused pmds in early boot

[safe/jmp/linux-2.6] / arch / x86 / mm / init_64.c

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5855449..bb652f5 100644 (file)
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -45,6 +45,7 @@
 #include <asm/sections.h>
 #include <asm/kdebug.h>
 #include <asm/numa.h>
+#include <asm/cacheflush.h>
 
 const struct dma_mapping_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
@@ -170,6 +171,33 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
        __flush_tlb_one(vaddr);
 }
 
+/*
+ * The head.S code sets up the kernel high mapping from:
+ * __START_KERNEL_map to __START_KERNEL_map + KERNEL_TEXT_SIZE
+ *
+ * phys_addr holds the negative offset to the kernel, which is added
+ * 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 _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 end = round_up((unsigned long)_end, PMD_SIZE) - 1;
+       pmd_t *pmd = level2_kernel_pgt;
+       pmd_t *last_pmd = pmd + PTRS_PER_PMD;
+
+       for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
+               if (!pmd_present(*pmd))
+                       continue;
+               if (vaddr < (unsigned long) _text || vaddr > end)
+                       set_pmd(pmd, __pmd(0));
+       }
+}
+
 /* NOTE: this is meant to be run only at boot */
 void __init
 __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
@@ -273,7 +301,6 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
        int i = pmd_index(address);
 
        for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
-               unsigned long entry;
                pmd_t *pmd = pmd_page + pmd_index(address);
 
                if (address >= end) {
@@ -287,9 +314,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
                if (pmd_val(*pmd))
                        continue;
 
-               entry = __PAGE_KERNEL_LARGE|_PAGE_GLOBAL|address;
-               entry &= __supported_pte_mask;
-               set_pmd(pmd, __pmd(entry));
+               set_pte((pte_t *)pmd,
+                       pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
        }
 }
 
@@ -530,13 +556,15 @@ void __init mem_init(void)
                reservedpages << (PAGE_SHIFT-10),
                datasize >> 10,
                initsize >> 10);
+
+       cpa_init();
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-       unsigned long addr;
+       unsigned long addr = begin;
 
-       if (begin >= end)
+       if (addr >= end)
                return;
 
        /*
@@ -551,7 +579,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 #else
        printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 
-       for (addr = begin; addr < end; addr += PAGE_SIZE) {
+       for (; addr < end; addr += PAGE_SIZE) {
                ClearPageReserved(virt_to_page(addr));
                init_page_count(virt_to_page(addr));
                memset((void *)(addr & ~(PAGE_SIZE-1)),
@@ -593,10 +621,17 @@ void mark_rodata_ro(void)
        if (end <= start)
                return;
 
-       set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
        printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
               (end - start) >> 10);
+       set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+
+       /*
+        * The rodata section (but not the kernel text!) should also be
+        * not-executable.
+        */
+       start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
+       set_memory_nx(start, (end - start) >> PAGE_SHIFT);
 
        rodata_test();
 
@@ -639,9 +674,9 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 
        /* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
-       reserve_bootmem_node(NODE_DATA(nid), phys, len);
+       reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
 #else
-       reserve_bootmem(phys, len);
+       reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #endif
        if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
                dma_reserve += len / PAGE_SIZE;