* Thanks to Ben LaHaise for precious feedback.
*/
#include <linux/highmem.h>
+#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>
-void clflush_cache_range(void *addr, int size)
-{
- int i;
-
- for (i = 0; i < size; i += boot_cpu_data.x86_clflush_size)
- clflush(addr+i);
-}
-
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
+/*
+ * We must allow the BIOS range to be executable:
+ */
+#define BIOS_BEGIN 0x000a0000
+#define BIOS_END 0x00100000
+
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
+{
+ return addr >= start && addr < end;
+}
+
+/*
+ * Certain areas of memory on x86 require very specific protection flags,
+ * for example the BIOS area or kernel text. Callers don't always get this
+ * right (again, ioremap() on BIOS memory is not uncommon) so this function
+ * checks and fixes these known static required protection bits.
+ */
+static inline pgprot_t static_protections(pgprot_t prot, unsigned long address)
+{
+ pgprot_t forbidden = __pgprot(0);
+
+ /*
+ * The BIOS area between 640k and 1Mb needs to be executable for
+ * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
+ */
+ if (within(__pa(address), BIOS_BEGIN, BIOS_END))
+ pgprot_val(forbidden) |= _PAGE_NX;
+
+ /*
+ * The kernel text needs to be executable for obvious reasons
+ * Does not cover __inittext since that is gone later on
+ */
+ if (within(address, (unsigned long)_text, (unsigned long)_etext))
+ pgprot_val(forbidden) |= _PAGE_NX;
+
+#ifdef CONFIG_DEBUG_RODATA
+ /* The .rodata section needs to be read-only */
+ if (within(address, (unsigned long)__start_rodata,
+ (unsigned long)__end_rodata))
+ pgprot_val(forbidden) |= _PAGE_RW;
+#endif
+
+ prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
+
+ return prot;
+}
+
pte_t *lookup_address(unsigned long address, int *level)
{
pgd_t *pgd = pgd_offset_k(address);
set_pte(&pbase[i], pfn_pte(addr >> PAGE_SHIFT, ref_prot));
/*
- * Install the new, split up pagetable:
+ * Install the new, split up pagetable. Important detail here:
+ *
+ * On Intel the NX bit of all levels must be cleared to make a
+ * page executable. See section 4.13.2 of Intel 64 and IA-32
+ * Architectures Software Developer's Manual).
*/
+ ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte)));
__set_pmd_pte(kpte, address, mk_pte(base, ref_prot));
base = NULL;
}
static int
-__change_page_attr(unsigned long address, struct page *page, pgprot_t prot)
+__change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot)
{
struct page *kpte_page;
int level, err = 0;
pte_t *kpte;
- BUG_ON(PageHighMem(page));
+#ifdef CONFIG_X86_32
+ BUG_ON(pfn > max_low_pfn);
+#endif
repeat:
kpte = lookup_address(address, &level);
BUG_ON(PageLRU(kpte_page));
BUG_ON(PageCompound(kpte_page));
- /*
- * Better fail early if someone sets the kernel text to NX.
- * Does not cover __inittext
- */
- BUG_ON(address >= (unsigned long)&_text &&
- address < (unsigned long)&_etext &&
- (pgprot_val(prot) & _PAGE_NX));
+ prot = static_protections(prot, address);
if (level == PG_LEVEL_4K) {
- set_pte_atomic(kpte, mk_pte(page, canon_pgprot(prot)));
+ set_pte_atomic(kpte, pfn_pte(pfn, canon_pgprot(prot)));
} else {
err = split_large_page(kpte, address);
if (!err)
* mem_map entry (pfn_valid() is false).
*
* See change_page_attr() documentation for more details.
+ *
+ * Modules and drivers should use the set_memory_* APIs instead.
*/
int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
unsigned long pfn = __pa(address) >> PAGE_SHIFT;
if (!kernel_map || pte_present(pfn_pte(0, prot))) {
- err = __change_page_attr(address, pfn_to_page(pfn), prot);
+ err = __change_page_attr(address, pfn, prot);
if (err)
break;
}
addr2 = __START_KERNEL_map + __pa(address);
/* Make sure the kernel mappings stay executable */
prot2 = pte_pgprot(pte_mkexec(pfn_pte(0, prot)));
- err = __change_page_attr(addr2, pfn_to_page(pfn), prot2);
+ err = __change_page_attr(addr2, pfn, prot2);
}
#endif
}
* (e.g. in user space) * This function only deals with the kernel linear map.
*
* For MMIO areas without mem_map use change_page_attr_addr() instead.
+ *
+ * Modules and drivers should use the set_pages_* APIs instead.
*/
int change_page_attr(struct page *page, int numpages, pgprot_t prot)
{
return change_page_attr_addr(addr, numpages, prot);
}
-EXPORT_SYMBOL(change_page_attr);
+EXPORT_UNUSED_SYMBOL(change_page_attr); /* to be removed in 2.6.27 */
+
+/**
+ * change_page_attr_set - Change page table attributes in the linear mapping.
+ * @addr: Virtual address in linear mapping.
+ * @numpages: Number of pages to change
+ * @prot: Protection/caching type bits to set (PAGE_*)
+ *
+ * Returns 0 on success, otherwise a negated errno.
+ *
+ * This should be used when a page is mapped with a different caching policy
+ * than write-back somewhere - some CPUs do not like it when mappings with
+ * different caching policies exist. This changes the page attributes of the
+ * in kernel linear mapping too.
+ *
+ * Caller must call global_flush_tlb() later to make the changes active.
+ *
+ * The caller needs to ensure that there are no conflicting mappings elsewhere
+ * (e.g. in user space) * This function only deals with the kernel linear map.
+ *
+ * This function is different from change_page_attr() in that only selected bits
+ * are impacted, all other bits remain as is.
+ */
+int change_page_attr_set(unsigned long addr, int numpages, pgprot_t prot)
+{
+ pgprot_t current_prot;
+ int level;
+ pte_t *pte;
+
+ pte = lookup_address(addr, &level);
+ if (pte)
+ current_prot = pte_pgprot(*pte);
+ else
+ pgprot_val(current_prot) = 0;
+
+ pgprot_val(prot) = pgprot_val(current_prot) | pgprot_val(prot);
+
+ return change_page_attr_addr(addr, numpages, prot);
+}
+
+/**
+ * change_page_attr_clear - Change page table attributes in the linear mapping.
+ * @addr: Virtual address in linear mapping.
+ * @numpages: Number of pages to change
+ * @prot: Protection/caching type bits to clear (PAGE_*)
+ *
+ * Returns 0 on success, otherwise a negated errno.
+ *
+ * This should be used when a page is mapped with a different caching policy
+ * than write-back somewhere - some CPUs do not like it when mappings with
+ * different caching policies exist. This changes the page attributes of the
+ * in kernel linear mapping too.
+ *
+ * Caller must call global_flush_tlb() later to make the changes active.
+ *
+ * The caller needs to ensure that there are no conflicting mappings elsewhere
+ * (e.g. in user space) * This function only deals with the kernel linear map.
+ *
+ * This function is different from change_page_attr() in that only selected bits
+ * are impacted, all other bits remain as is.
+ */
+int change_page_attr_clear(unsigned long addr, int numpages, pgprot_t prot)
+{
+ pgprot_t current_prot;
+ int level;
+ pte_t *pte;
+
+ pte = lookup_address(addr, &level);
+ if (pte)
+ current_prot = pte_pgprot(*pte);
+ else
+ pgprot_val(current_prot) = 0;
+
+ pgprot_val(prot) = pgprot_val(current_prot) & ~pgprot_val(prot);
+
+ return change_page_attr_addr(addr, numpages, prot);
+}
+
+
+
+int set_memory_uc(unsigned long addr, int numpages)
+{
+ pgprot_t uncached;
+
+ pgprot_val(uncached) = _PAGE_PCD | _PAGE_PWT;
+ return change_page_attr_set(addr, numpages, uncached);
+}
+EXPORT_SYMBOL(set_memory_uc);
+
+int set_memory_wb(unsigned long addr, int numpages)
+{
+ pgprot_t uncached;
+
+ pgprot_val(uncached) = _PAGE_PCD | _PAGE_PWT;
+ return change_page_attr_clear(addr, numpages, uncached);
+}
+EXPORT_SYMBOL(set_memory_wb);
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+ pgprot_t nx;
+
+ pgprot_val(nx) = _PAGE_NX;
+ return change_page_attr_clear(addr, numpages, nx);
+}
+EXPORT_SYMBOL(set_memory_x);
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+ pgprot_t nx;
+
+ pgprot_val(nx) = _PAGE_NX;
+ return change_page_attr_set(addr, numpages, nx);
+}
+EXPORT_SYMBOL(set_memory_nx);
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+ pgprot_t rw;
+
+ pgprot_val(rw) = _PAGE_RW;
+ return change_page_attr_clear(addr, numpages, rw);
+}
+EXPORT_SYMBOL(set_memory_ro);
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+ pgprot_t rw;
+
+ pgprot_val(rw) = _PAGE_RW;
+ return change_page_attr_set(addr, numpages, rw);
+}
+EXPORT_SYMBOL(set_memory_rw);
+
+int set_pages_uc(struct page *page, int numpages)
+{
+ unsigned long addr = (unsigned long)page_address(page);
+ pgprot_t uncached;
+
+ pgprot_val(uncached) = _PAGE_PCD | _PAGE_PWT;
+ return change_page_attr_set(addr, numpages, uncached);
+}
+EXPORT_SYMBOL(set_pages_uc);
+
+int set_pages_wb(struct page *page, int numpages)
+{
+ unsigned long addr = (unsigned long)page_address(page);
+ pgprot_t uncached;
+
+ pgprot_val(uncached) = _PAGE_PCD | _PAGE_PWT;
+ return change_page_attr_clear(addr, numpages, uncached);
+}
+EXPORT_SYMBOL(set_pages_wb);
+
+int set_pages_x(struct page *page, int numpages)
+{
+ unsigned long addr = (unsigned long)page_address(page);
+ pgprot_t nx;
+
+ pgprot_val(nx) = _PAGE_NX;
+ return change_page_attr_clear(addr, numpages, nx);
+}
+EXPORT_SYMBOL(set_pages_x);
+
+int set_pages_nx(struct page *page, int numpages)
+{
+ unsigned long addr = (unsigned long)page_address(page);
+ pgprot_t nx;
+
+ pgprot_val(nx) = _PAGE_NX;
+ return change_page_attr_set(addr, numpages, nx);
+}
+EXPORT_SYMBOL(set_pages_nx);
+
+int set_pages_ro(struct page *page, int numpages)
+{
+ unsigned long addr = (unsigned long)page_address(page);
+ pgprot_t rw;
+
+ pgprot_val(rw) = _PAGE_RW;
+ return change_page_attr_clear(addr, numpages, rw);
+}
+EXPORT_SYMBOL(set_pages_ro);
+
+int set_pages_rw(struct page *page, int numpages)
+{
+ unsigned long addr = (unsigned long)page_address(page);
+ pgprot_t rw;
+
+ pgprot_val(rw) = _PAGE_RW;
+ return change_page_attr_set(addr, numpages, rw);
+}
+EXPORT_SYMBOL(set_pages_rw);
+
+
+void clflush_cache_range(void *addr, int size)
+{
+ int i;
+
+ for (i = 0; i < size; i += boot_cpu_data.x86_clflush_size)
+ clflush(addr+i);
+}
static void flush_kernel_map(void *arg)
{