#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);
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+int direct_gbpages __meminitdata
+#ifdef CONFIG_DIRECT_GBPAGES
+ = 1
+#endif
+;
+
+static int __init parse_direct_gbpages_off(char *arg)
+{
+ direct_gbpages = 0;
+ return 0;
+}
+early_param("nogbpages", parse_direct_gbpages_off);
+
+static int __init parse_direct_gbpages_on(char *arg)
+{
+ direct_gbpages = 1;
+ return 0;
+}
+early_param("gbpages", parse_direct_gbpages_on);
+
/*
* NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
* physical space so we can cache the place of the first one and move
__flush_tlb_one(vaddr);
}
+/*
+ * 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
+ * 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)
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) {
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));
}
}
* need roughly 0.5KB per GB.
*/
start = 0x8000;
- table_start = find_e820_area(start, end, tables);
+ table_start = find_e820_area(start, end, tables, PAGE_SIZE);
if (table_start == -1UL)
panic("Cannot find space for the kernel page tables");
- /*
- * When you have a lot of RAM like 256GB, early_table will not fit
- * into 0x8000 range, find_e820_area() will find area after kernel
- * bss but the table_start is not page aligned, so need to round it
- * up to avoid overlap with bss:
- */
- table_start = round_up(table_start, PAGE_SIZE);
table_start >>= PAGE_SHIFT;
table_end = table_start;
mmu_cr4_features = read_cr4();
__flush_tlb_all();
- reserve_early(table_start << PAGE_SHIFT, table_end << PAGE_SHIFT, "PGTABLE");
+ if (!after_bootmem)
+ reserve_early(table_start << PAGE_SHIFT,
+ table_end << PAGE_SHIFT, "PGTABLE");
}
#ifndef CONFIG_NUMA
}
#endif
-/*
- * Unmap a kernel mapping if it exists. This is useful to avoid
- * prefetches from the CPU leading to inconsistent cache lines.
- * address and size must be aligned to 2MB boundaries.
- * Does nothing when the mapping doesn't exist.
- */
-void __init clear_kernel_mapping(unsigned long address, unsigned long size)
-{
- unsigned long end = address + size;
-
- BUG_ON(address & ~LARGE_PAGE_MASK);
- BUG_ON(size & ~LARGE_PAGE_MASK);
-
- for (; address < end; address += LARGE_PAGE_SIZE) {
- pgd_t *pgd = pgd_offset_k(address);
- pud_t *pud;
- pmd_t *pmd;
-
- if (pgd_none(*pgd))
- continue;
-
- pud = pud_offset(pgd, address);
- if (pud_none(*pud))
- continue;
-
- pmd = pmd_offset(pud, address);
- if (!pmd || pmd_none(*pmd))
- continue;
-
- if (!(pmd_val(*pmd) & _PAGE_PSE)) {
- /*
- * Could handle this, but it should not happen
- * currently:
- */
- printk(KERN_ERR "clear_kernel_mapping: "
- "mapping has been split. will leak memory\n");
- pmd_ERROR(*pmd);
- }
- set_pmd(pmd, __pmd(0));
- }
- __flush_tlb_all();
-}
-
/*
* Memory hotplug specific functions
*/
/* clear_bss() already clear the empty_zero_page */
- /* temporary debugging - double check it's true: */
- {
- int i;
-
- for (i = 0; i < 1024; i++)
- WARN_ON_ONCE(empty_zero_page[i]);
- }
-
reservedpages = 0;
/* this will put all low memory onto the freelists */
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;
/*
#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)),
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();
/* 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;