+#include <linux/gfp.h>
+#include <linux/initrd.h>
#include <linux/ioport.h>
#include <linux/swap.h>
+#include <linux/memblock.h>
#include <asm/cacheflush.h>
#include <asm/e820.h>
#include <asm/page.h>
#include <asm/page_types.h>
#include <asm/sections.h>
+#include <asm/setup.h>
#include <asm/system.h>
#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+#include <asm/proto.h>
-unsigned long __initdata e820_table_start;
-unsigned long __meminitdata e820_table_end;
-unsigned long __meminitdata e820_table_top;
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+
+unsigned long __initdata pgt_buf_start;
+unsigned long __meminitdata pgt_buf_end;
+unsigned long __meminitdata pgt_buf_top;
int after_bootmem;
static void __init find_early_table_space(unsigned long end, int use_pse,
int use_gbpages)
{
- unsigned long puds, pmds, ptes, tables, start;
+ unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
+ phys_addr_t base;
puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
#ifdef CONFIG_X86_32
/* for fixmap */
tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-#endif
- /*
- * RED-PEN putting page tables only on node 0 could
- * cause a hotspot and fill up ZONE_DMA. The page tables
- * need roughly 0.5KB per GB.
- */
-#ifdef CONFIG_X86_32
- start = 0x7000;
- e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
- tables, PAGE_SIZE);
-#else /* CONFIG_X86_64 */
- start = 0x8000;
- e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE);
+ good_end = max_pfn_mapped << PAGE_SHIFT;
#endif
- if (e820_table_start == -1UL)
+
+ base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
+ if (base == MEMBLOCK_ERROR)
panic("Cannot find space for the kernel page tables");
- e820_table_start >>= PAGE_SHIFT;
- e820_table_end = e820_table_start;
- e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
+ pgt_buf_start = base >> PAGE_SHIFT;
+ pgt_buf_end = pgt_buf_start;
+ pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
- end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT);
+ end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
+}
+
+void native_pagetable_reserve(u64 start, u64 end)
+{
+ memblock_x86_reserve_range(start, end, "PGTABLE");
}
struct map_range {
return nr_range;
}
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
- if (direct_gbpages && cpu_has_gbpages)
- printk(KERN_INFO "Using GB pages for direct mapping\n");
- else
- direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
-#endif
-
/*
* Setup the direct mapping of the physical memory at PAGE_OFFSET.
* This runs before bootmem is initialized and gets pages directly from
printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
- if (!after_bootmem)
- init_gbpages();
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
/*
* For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
* This will simplify cpa(), which otherwise needs to support splitting
use_gbpages = direct_gbpages;
#endif
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_PAE
- set_nx();
- if (nx_enabled)
- printk(KERN_INFO "NX (Execute Disable) protection: active\n");
-#endif
-
/* Enable PSE if available */
if (cpu_has_pse)
set_in_cr4(X86_CR4_PSE);
set_in_cr4(X86_CR4_PGE);
__supported_pte_mask |= _PAGE_GLOBAL;
}
-#endif
if (use_gbpages)
page_size_mask |= 1 << PG_LEVEL_1G;
if (!after_bootmem)
find_early_table_space(end, use_pse, use_gbpages);
-#ifdef CONFIG_X86_32
- for (i = 0; i < nr_range; i++)
- kernel_physical_mapping_init(mr[i].start, mr[i].end,
- mr[i].page_size_mask);
- ret = end;
-#else /* CONFIG_X86_64 */
for (i = 0; i < nr_range; i++)
ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
mr[i].page_size_mask);
-#endif
#ifdef CONFIG_X86_32
early_ioremap_page_table_range_init();
load_cr3(swapper_pg_dir);
#endif
-#ifdef CONFIG_X86_64
- if (!after_bootmem)
- mmu_cr4_features = read_cr4();
-#endif
__flush_tlb_all();
- if (!after_bootmem && e820_table_end > e820_table_start)
- reserve_early(e820_table_start << PAGE_SHIFT,
- e820_table_end << PAGE_SHIFT, "PGTABLE");
+ /*
+ * Reserve the kernel pagetable pages we used (pgt_buf_start -
+ * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
+ * so that they can be reused for other purposes.
+ *
+ * On native it just means calling memblock_x86_reserve_range, on Xen it
+ * also means marking RW the pagetable pages that we allocated before
+ * but that haven't been used.
+ *
+ * In fact on xen we mark RO the whole range pgt_buf_start -
+ * pgt_buf_top, because we have to make sure that when
+ * init_memory_mapping reaches the pagetable pages area, it maps
+ * RO all the pagetable pages, including the ones that are beyond
+ * pgt_buf_end at that time.
+ */
+ if (!after_bootmem && pgt_buf_end > pgt_buf_start)
+ x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
+ PFN_PHYS(pgt_buf_end));
if (!after_bootmem)
early_memtest(start, end);
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
- unsigned long addr = begin;
+ unsigned long addr;
+ unsigned long begin_aligned, end_aligned;
+
+ /* Make sure boundaries are page aligned */
+ begin_aligned = PAGE_ALIGN(begin);
+ end_aligned = end & PAGE_MASK;
- if (addr >= end)
+ if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+ begin = begin_aligned;
+ end = end_aligned;
+ }
+
+ if (begin >= end)
return;
+ addr = begin;
+
/*
* If debugging page accesses then do not free this memory but
* mark them not present - any buggy init-section access will
*/
#ifdef CONFIG_DEBUG_PAGEALLOC
printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
- begin, PAGE_ALIGN(end));
+ begin, end);
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
/*
* We just marked the kernel text read only above, now that
* we are going to free part of that, we need to make that
- * writeable first.
+ * writeable and non-executable first.
*/
+ set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
for (; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
- memset((void *)(addr & ~(PAGE_SIZE-1)),
- POISON_FREE_INITMEM, PAGE_SIZE);
+ memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
free_page(addr);
totalram_pages++;
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
- free_init_pages("initrd memory", start, end);
+ /*
+ * end could be not aligned, and We can not align that,
+ * decompresser could be confused by aligned initrd_end
+ * We already reserve the end partial page before in
+ * - i386_start_kernel()
+ * - x86_64_start_kernel()
+ * - relocate_initrd()
+ * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+ */
+ free_init_pages("initrd memory", start, PAGE_ALIGN(end));
}
#endif