#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
#include <asm/e820.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
+#include <asm/setup.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
+#include <asm/proto.h>
+#include <asm/pat.h>
+/*
+ * The current flushing context - we pass it instead of 5 arguments:
+ */
struct cpa_data {
- unsigned long vaddr;
+ unsigned long *vaddr;
pgprot_t mask_set;
pgprot_t mask_clr;
int numpages;
- int flushtlb;
+ int flags;
+ unsigned long pfn;
+ unsigned force_split : 1;
+ int curpage;
+ struct page **pages;
};
-enum {
- CPA_NO_SPLIT = 0,
- CPA_SPLIT,
-};
+/*
+ * Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings)
+ * using cpa_lock. So that we don't allow any other cpu, with stale large tlb
+ * entries change the page attribute in parallel to some other cpu
+ * splitting a large page entry along with changing the attribute.
+ */
+static DEFINE_SPINLOCK(cpa_lock);
+
+#define CPA_FLUSHTLB 1
+#define CPA_ARRAY 2
+#define CPA_PAGES_ARRAY 4
+
+#ifdef CONFIG_PROC_FS
+static unsigned long direct_pages_count[PG_LEVEL_NUM];
+
+void update_page_count(int level, unsigned long pages)
+{
+ unsigned long flags;
+
+ /* Protect against CPA */
+ spin_lock_irqsave(&pgd_lock, flags);
+ direct_pages_count[level] += pages;
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+static void split_page_count(int level)
+{
+ direct_pages_count[level]--;
+ direct_pages_count[level - 1] += PTRS_PER_PTE;
+}
+
+void arch_report_meminfo(struct seq_file *m)
+{
+ seq_printf(m, "DirectMap4k: %8lu kB\n",
+ direct_pages_count[PG_LEVEL_4K] << 2);
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+ seq_printf(m, "DirectMap2M: %8lu kB\n",
+ direct_pages_count[PG_LEVEL_2M] << 11);
+#else
+ seq_printf(m, "DirectMap4M: %8lu kB\n",
+ direct_pages_count[PG_LEVEL_2M] << 12);
+#endif
+#ifdef CONFIG_X86_64
+ if (direct_gbpages)
+ seq_printf(m, "DirectMap1G: %8lu kB\n",
+ direct_pages_count[PG_LEVEL_1G] << 20);
+#endif
+}
+#else
+static inline void split_page_count(int level) { }
+#endif
+
+#ifdef CONFIG_X86_64
+
+static inline unsigned long highmap_start_pfn(void)
+{
+ return __pa(_text) >> PAGE_SHIFT;
+}
+
+static inline unsigned long highmap_end_pfn(void)
+{
+ return __pa(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
+}
+
+#endif
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+# define debug_pagealloc 1
+#else
+# define debug_pagealloc 0
+#endif
static inline int
within(unsigned long addr, unsigned long start, unsigned long end)
{
BUG_ON(irqs_disabled());
- on_each_cpu(__cpa_flush_all, (void *) cache, 1, 1);
+ on_each_cpu(__cpa_flush_all, (void *) cache, 1);
}
static void __cpa_flush_range(void *arg)
BUG_ON(irqs_disabled());
WARN_ON(PAGE_ALIGN(start) != start);
- on_each_cpu(__cpa_flush_range, NULL, 1, 1);
+ on_each_cpu(__cpa_flush_range, NULL, 1);
if (!cache)
return;
}
}
-#define HIGH_MAP_START __START_KERNEL_map
-#define HIGH_MAP_END (__START_KERNEL_map + KERNEL_TEXT_SIZE)
+static void cpa_flush_array(unsigned long *start, int numpages, int cache,
+ int in_flags, struct page **pages)
+{
+ unsigned int i, level;
+ BUG_ON(irqs_disabled());
-/*
- * Converts a virtual address to a X86-64 highmap address
- */
-static unsigned long virt_to_highmap(void *address)
-{
-#ifdef CONFIG_X86_64
- return __pa((unsigned long)address) + HIGH_MAP_START - phys_base;
-#else
- return (unsigned long)address;
-#endif
+ on_each_cpu(__cpa_flush_range, NULL, 1);
+
+ if (!cache)
+ return;
+
+ /* 4M threshold */
+ if (numpages >= 1024) {
+ if (boot_cpu_data.x86_model >= 4)
+ wbinvd();
+ return;
+ }
+ /*
+ * We only need to flush on one CPU,
+ * clflush is a MESI-coherent instruction that
+ * will cause all other CPUs to flush the same
+ * cachelines:
+ */
+ for (i = 0; i < numpages; i++) {
+ unsigned long addr;
+ pte_t *pte;
+
+ if (in_flags & CPA_PAGES_ARRAY)
+ addr = (unsigned long)page_address(pages[i]);
+ else
+ addr = start[i];
+
+ pte = lookup_address(addr, &level);
+
+ /*
+ * Only flush present addresses:
+ */
+ if (pte && (pte_val(*pte) & _PAGE_PRESENT))
+ clflush_cache_range((void *)addr, PAGE_SIZE);
+ }
}
/*
* 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)
+static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
+ unsigned long pfn)
{
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))
+ if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
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
+ * Does not cover __inittext since that is gone later on. On
+ * 64bit we do not enforce !NX on the low mapping
*/
if (within(address, (unsigned long)_text, (unsigned long)_etext))
pgprot_val(forbidden) |= _PAGE_NX;
- /*
- * Do the same for the x86-64 high kernel mapping
- */
- if (within(address, virt_to_highmap(_text), virt_to_highmap(_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;
/*
- * Do the same for the x86-64 high kernel mapping
+ * The .rodata section needs to be read-only. Using the pfn
+ * catches all aliases.
*/
- if (within(address, virt_to_highmap(__start_rodata),
- virt_to_highmap(__end_rodata)))
+ if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
+ __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
pgprot_val(forbidden) |= _PAGE_RW;
-#endif
prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
* or when the present bit is not set. Otherwise we would return a
* pointer to a nonexisting mapping.
*/
-pte_t *lookup_address(unsigned long address, int *level)
+pte_t *lookup_address(unsigned long address, unsigned int *level)
{
pgd_t *pgd = pgd_offset_k(address);
pud_t *pud;
if (pgd_none(*pgd))
return NULL;
+
pud = pud_offset(pgd, address);
if (pud_none(*pud))
return NULL;
return (pte_t *)pmd;
*level = PG_LEVEL_4K;
+
return pte_offset_kernel(pmd, address);
}
+EXPORT_SYMBOL_GPL(lookup_address);
+/*
+ * Set the new pmd in all the pgds we know about:
+ */
static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
{
/* change init_mm */
#endif
}
-static int try_preserve_large_page(pte_t *kpte, unsigned long address,
- struct cpa_data *cpa)
+static int
+try_preserve_large_page(pte_t *kpte, unsigned long address,
+ struct cpa_data *cpa)
{
- unsigned long nextpage_addr, numpages, pmask, psize, flags;
+ unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
pte_t new_pte, old_pte, *tmp;
pgprot_t old_prot, new_prot;
- int level, res = CPA_SPLIT;
+ int i, do_split = 1;
+ unsigned int level;
- /*
- * An Athlon 64 X2 showed hard hangs if we tried to preserve
- * largepages and changed the PSE entry from RW to RO.
- *
- * As AMD CPUs have a long series of erratas in this area,
- * (and none of the known ones seem to explain this hang),
- * disable this code until the hang can be debugged:
- */
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
- return res;
+ if (cpa->force_split)
+ return 1;
spin_lock_irqsave(&pgd_lock, flags);
/*
psize = PMD_PAGE_SIZE;
pmask = PMD_PAGE_MASK;
break;
+#ifdef CONFIG_X86_64
case PG_LEVEL_1G:
+ psize = PUD_PAGE_SIZE;
+ pmask = PUD_PAGE_MASK;
+ break;
+#endif
default:
- res = -EINVAL;
+ do_split = -EINVAL;
goto out_unlock;
}
pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
- new_prot = static_protections(new_prot, address);
+
+ /*
+ * old_pte points to the large page base address. So we need
+ * to add the offset of the virtual address:
+ */
+ pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT);
+ cpa->pfn = pfn;
+
+ new_prot = static_protections(new_prot, address, pfn);
+
+ /*
+ * We need to check the full range, whether
+ * static_protection() requires a different pgprot for one of
+ * the pages in the range we try to preserve:
+ */
+ addr = address + PAGE_SIZE;
+ pfn++;
+ for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) {
+ pgprot_t chk_prot = static_protections(new_prot, addr, pfn);
+
+ if (pgprot_val(chk_prot) != pgprot_val(new_prot))
+ goto out_unlock;
+ }
/*
* If there are no changes, return. maxpages has been updated
* above:
*/
if (pgprot_val(new_prot) == pgprot_val(old_prot)) {
- res = CPA_NO_SPLIT;
+ do_split = 0;
goto out_unlock;
}
*/
new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot));
__set_pmd_pte(kpte, address, new_pte);
- cpa->flushtlb = 1;
- res = CPA_NO_SPLIT;
+ cpa->flags |= CPA_FLUSHTLB;
+ do_split = 0;
}
out_unlock:
spin_unlock_irqrestore(&pgd_lock, flags);
- return res;
+
+ return do_split;
}
static int split_large_page(pte_t *kpte, unsigned long address)
{
- pgprot_t ref_prot;
- gfp_t gfp_flags = GFP_KERNEL;
- unsigned long flags, addr, pfn;
+ unsigned long flags, pfn, pfninc = 1;
+ unsigned int i, level;
pte_t *pbase, *tmp;
+ pgprot_t ref_prot;
struct page *base;
- unsigned int i, level;
-#ifdef CONFIG_DEBUG_PAGEALLOC
- gfp_flags = GFP_ATOMIC | __GFP_NOWARN;
-#endif
- base = alloc_pages(gfp_flags, 0);
+ if (!debug_pagealloc)
+ spin_unlock(&cpa_lock);
+ base = alloc_pages(GFP_KERNEL, 0);
+ if (!debug_pagealloc)
+ spin_lock(&cpa_lock);
if (!base)
return -ENOMEM;
if (tmp != kpte)
goto out_unlock;
- address = __pa(address);
- addr = address & PMD_PAGE_MASK;
pbase = (pte_t *)page_address(base);
-#ifdef CONFIG_X86_32
- paravirt_alloc_pt(&init_mm, page_to_pfn(base));
-#endif
+ paravirt_alloc_pte(&init_mm, page_to_pfn(base));
ref_prot = pte_pgprot(pte_clrhuge(*kpte));
+ /*
+ * If we ever want to utilize the PAT bit, we need to
+ * update this function to make sure it's converted from
+ * bit 12 to bit 7 when we cross from the 2MB level to
+ * the 4K level:
+ */
+ WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE);
+
+#ifdef CONFIG_X86_64
+ if (level == PG_LEVEL_1G) {
+ pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
+ pgprot_val(ref_prot) |= _PAGE_PSE;
+ }
+#endif
/*
* Get the target pfn from the original entry:
*/
pfn = pte_pfn(*kpte);
- for (i = 0; i < PTRS_PER_PTE; i++, pfn++)
+ for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
+ if (address >= (unsigned long)__va(0) &&
+ address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT))
+ split_page_count(level);
+
+#ifdef CONFIG_X86_64
+ if (address >= (unsigned long)__va(1UL<<32) &&
+ address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT))
+ split_page_count(level);
+#endif
+
/*
- * Install the new, split up pagetable. Important details here:
+ * Install the new, split up pagetable.
*
- * 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).
+ * We use the standard kernel pagetable protections for the new
+ * pagetable protections, the actual ptes set above control the
+ * primary protection behavior:
+ */
+ __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
+
+ /*
+ * Intel Atom errata AAH41 workaround.
*
- * Mark the entry present. The current mapping might be
- * set to not present, which we preserved above.
+ * The real fix should be in hw or in a microcode update, but
+ * we also probabilistically try to reduce the window of having
+ * a large TLB mixed with 4K TLBs while instruction fetches are
+ * going on.
*/
- ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte)));
- pgprot_val(ref_prot) |= _PAGE_PRESENT;
- __set_pmd_pte(kpte, address, mk_pte(base, ref_prot));
+ __flush_tlb_all();
+
base = NULL;
out_unlock:
- spin_unlock_irqrestore(&pgd_lock, flags);
-
+ /*
+ * If we dropped out via the lookup_address check under
+ * pgd_lock then stick the page back into the pool:
+ */
if (base)
- __free_pages(base, 0);
+ __free_page(base);
+ spin_unlock_irqrestore(&pgd_lock, flags);
return 0;
}
-static int __change_page_attr(unsigned long address, struct cpa_data *cpa)
+static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
+ int primary)
{
- struct page *kpte_page;
- int level, res;
- pte_t *kpte;
+ /*
+ * Ignore all non primary paths.
+ */
+ if (!primary)
+ return 0;
+
+ /*
+ * Ignore the NULL PTE for kernel identity mapping, as it is expected
+ * to have holes.
+ * Also set numpages to '1' indicating that we processed cpa req for
+ * one virtual address page and its pfn. TBD: numpages can be set based
+ * on the initial value and the level returned by lookup_address().
+ */
+ if (within(vaddr, PAGE_OFFSET,
+ PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
+ cpa->numpages = 1;
+ cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
+ return 0;
+ } else {
+ WARN(1, KERN_WARNING "CPA: called for zero pte. "
+ "vaddr = %lx cpa->vaddr = %lx\n", vaddr,
+ *cpa->vaddr);
+ return -EFAULT;
+ }
+}
+
+static int __change_page_attr(struct cpa_data *cpa, int primary)
+{
+ unsigned long address;
+ int do_split, err;
+ unsigned int level;
+ pte_t *kpte, old_pte;
+
+ if (cpa->flags & CPA_PAGES_ARRAY)
+ address = (unsigned long)page_address(cpa->pages[cpa->curpage]);
+ else if (cpa->flags & CPA_ARRAY)
+ address = cpa->vaddr[cpa->curpage];
+ else
+ address = *cpa->vaddr;
repeat:
kpte = lookup_address(address, &level);
if (!kpte)
- return -EINVAL;
+ return __cpa_process_fault(cpa, address, primary);
- kpte_page = virt_to_page(kpte);
- BUG_ON(PageLRU(kpte_page));
- BUG_ON(PageCompound(kpte_page));
+ old_pte = *kpte;
+ if (!pte_val(old_pte))
+ return __cpa_process_fault(cpa, address, primary);
if (level == PG_LEVEL_4K) {
- pte_t new_pte, old_pte = *kpte;
+ pte_t new_pte;
pgprot_t new_prot = pte_pgprot(old_pte);
-
- if(!pte_val(old_pte)) {
- printk(KERN_WARNING "CPA: called for zero pte. "
- "vaddr = %lx cpa->vaddr = %lx\n", address,
- cpa->vaddr);
- WARN_ON(1);
- return -EINVAL;
- }
+ unsigned long pfn = pte_pfn(old_pte);
pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
- new_prot = static_protections(new_prot, address);
+ new_prot = static_protections(new_prot, address, pfn);
/*
* We need to keep the pfn from the existing PTE,
* after all we're only going to change it's attributes
* not the memory it points to
*/
- new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot));
-
+ new_pte = pfn_pte(pfn, canon_pgprot(new_prot));
+ cpa->pfn = pfn;
/*
* Do we really change anything ?
*/
if (pte_val(old_pte) != pte_val(new_pte)) {
set_pte_atomic(kpte, new_pte);
- cpa->flushtlb = 1;
+ cpa->flags |= CPA_FLUSHTLB;
}
cpa->numpages = 1;
return 0;
* Check, whether we can keep the large page intact
* and just change the pte:
*/
- res = try_preserve_large_page(kpte, address, cpa);
- if (res < 0)
- return res;
-
+ do_split = try_preserve_large_page(kpte, address, cpa);
/*
* When the range fits into the existing large page,
* return. cp->numpages and cpa->tlbflush have been updated in
* try_large_page:
*/
- if (res == CPA_NO_SPLIT)
- return 0;
+ if (do_split <= 0)
+ return do_split;
/*
* We have to split the large page:
*/
- res = split_large_page(kpte, address);
- if (res)
- return res;
- cpa->flushtlb = 1;
- goto repeat;
+ err = split_large_page(kpte, address);
+ if (!err) {
+ /*
+ * Do a global flush tlb after splitting the large page
+ * and before we do the actual change page attribute in the PTE.
+ *
+ * With out this, we violate the TLB application note, that says
+ * "The TLBs may contain both ordinary and large-page
+ * translations for a 4-KByte range of linear addresses. This
+ * may occur if software modifies the paging structures so that
+ * the page size used for the address range changes. If the two
+ * translations differ with respect to page frame or attributes
+ * (e.g., permissions), processor behavior is undefined and may
+ * be implementation-specific."
+ *
+ * We do this global tlb flush inside the cpa_lock, so that we
+ * don't allow any other cpu, with stale tlb entries change the
+ * page attribute in parallel, that also falls into the
+ * just split large page entry.
+ */
+ flush_tlb_all();
+ goto repeat;
+ }
+
+ return err;
}
-/**
- * change_page_attr_addr - Change page table attributes in linear mapping
- * @address: Virtual address in linear mapping.
- * @prot: New page table attribute (PAGE_*)
- *
- * Change page attributes of a page in the direct mapping. This is a variant
- * of change_page_attr() that also works on memory holes that do not have
- * 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.
- */
+static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias);
-static int change_page_attr_addr(struct cpa_data *cpa)
+static int cpa_process_alias(struct cpa_data *cpa)
{
- int err;
- unsigned long address = cpa->vaddr;
+ struct cpa_data alias_cpa;
+ int ret = 0;
+ unsigned long temp_cpa_vaddr, vaddr;
-#ifdef CONFIG_X86_64
- unsigned long phys_addr = __pa(address);
+ if (cpa->pfn >= max_pfn_mapped)
+ return 0;
+#ifdef CONFIG_X86_64
+ if (cpa->pfn >= max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT)))
+ return 0;
+#endif
/*
- * If we are inside the high mapped kernel range, then we
- * fixup the low mapping first. __va() returns the virtual
- * address in the linear mapping:
+ * No need to redo, when the primary call touched the direct
+ * mapping already:
*/
- if (within(address, HIGH_MAP_START, HIGH_MAP_END))
- address = (unsigned long) __va(phys_addr);
-#endif
+ if (cpa->flags & CPA_PAGES_ARRAY)
+ vaddr = (unsigned long)page_address(cpa->pages[cpa->curpage]);
+ else if (cpa->flags & CPA_ARRAY)
+ vaddr = cpa->vaddr[cpa->curpage];
+ else
+ vaddr = *cpa->vaddr;
- err = __change_page_attr(address, cpa);
- if (err)
- return err;
+ if (!(within(vaddr, PAGE_OFFSET,
+ PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {
+
+ alias_cpa = *cpa;
+ temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
+ alias_cpa.vaddr = &temp_cpa_vaddr;
+ alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+
+
+ ret = __change_page_attr_set_clr(&alias_cpa, 0);
+ }
#ifdef CONFIG_X86_64
+ if (ret)
+ return ret;
+ /*
+ * No need to redo, when the primary call touched the high
+ * mapping already:
+ */
+ if (within(vaddr, (unsigned long) _text, _brk_end))
+ return 0;
+
/*
* If the physical address is inside the kernel map, we need
* to touch the high mapped kernel as well:
*/
- if (within(phys_addr, 0, KERNEL_TEXT_SIZE)) {
- /*
- * Calc the high mapping address. See __phys_addr()
- * for the non obvious details.
- *
- * Note that NX and other required permissions are
- * checked in static_protections().
- */
- address = phys_addr + HIGH_MAP_START - phys_base;
+ if (!within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn()))
+ return 0;
- /*
- * Our high aliases are imprecise, because we check
- * everything between 0 and KERNEL_TEXT_SIZE, so do
- * not propagate lookup failures back to users:
- */
- __change_page_attr(address, cpa);
- }
+ alias_cpa = *cpa;
+ temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base;
+ alias_cpa.vaddr = &temp_cpa_vaddr;
+ alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+
+ /*
+ * The high mapping range is imprecise, so ignore the return value.
+ */
+ __change_page_attr_set_clr(&alias_cpa, 0);
#endif
- return err;
+ return ret;
}
-static int __change_page_attr_set_clr(struct cpa_data *cpa)
+static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
{
int ret, numpages = cpa->numpages;
* preservation check.
*/
cpa->numpages = numpages;
- ret = change_page_attr_addr(cpa);
+ /* for array changes, we can't use large page */
+ if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY))
+ cpa->numpages = 1;
+
+ if (!debug_pagealloc)
+ spin_lock(&cpa_lock);
+ ret = __change_page_attr(cpa, checkalias);
+ if (!debug_pagealloc)
+ spin_unlock(&cpa_lock);
if (ret)
return ret;
+ if (checkalias) {
+ ret = cpa_process_alias(cpa);
+ if (ret)
+ return ret;
+ }
+
/*
* Adjust the number of pages with the result of the
* CPA operation. Either a large page has been
*/
BUG_ON(cpa->numpages > numpages);
numpages -= cpa->numpages;
- cpa->vaddr += cpa->numpages * PAGE_SIZE;
+ if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
+ cpa->curpage++;
+ else
+ *cpa->vaddr += cpa->numpages * PAGE_SIZE;
+
}
return 0;
}
(_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD);
}
-static int change_page_attr_set_clr(unsigned long addr, int numpages,
- pgprot_t mask_set, pgprot_t mask_clr)
+static int change_page_attr_set_clr(unsigned long *addr, int numpages,
+ pgprot_t mask_set, pgprot_t mask_clr,
+ int force_split, int in_flag,
+ struct page **pages)
{
struct cpa_data cpa;
- int ret, cache;
+ int ret, cache, checkalias;
/*
* Check, if we are requested to change a not supported
*/
mask_set = canon_pgprot(mask_set);
mask_clr = canon_pgprot(mask_clr);
- if (!pgprot_val(mask_set) && !pgprot_val(mask_clr))
+ if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split)
return 0;
+ /* Ensure we are PAGE_SIZE aligned */
+ if (in_flag & CPA_ARRAY) {
+ int i;
+ for (i = 0; i < numpages; i++) {
+ if (addr[i] & ~PAGE_MASK) {
+ addr[i] &= PAGE_MASK;
+ WARN_ON_ONCE(1);
+ }
+ }
+ } else if (!(in_flag & CPA_PAGES_ARRAY)) {
+ /*
+ * in_flag of CPA_PAGES_ARRAY implies it is aligned.
+ * No need to cehck in that case
+ */
+ if (*addr & ~PAGE_MASK) {
+ *addr &= PAGE_MASK;
+ /*
+ * People should not be passing in unaligned addresses:
+ */
+ WARN_ON_ONCE(1);
+ }
+ }
+
+ /* Must avoid aliasing mappings in the highmem code */
+ kmap_flush_unused();
+
+ vm_unmap_aliases();
+
cpa.vaddr = addr;
+ cpa.pages = pages;
cpa.numpages = numpages;
cpa.mask_set = mask_set;
cpa.mask_clr = mask_clr;
- cpa.flushtlb = 0;
+ cpa.flags = 0;
+ cpa.curpage = 0;
+ cpa.force_split = force_split;
- ret = __change_page_attr_set_clr(&cpa);
+ if (in_flag & (CPA_ARRAY | CPA_PAGES_ARRAY))
+ cpa.flags |= in_flag;
+
+ /* No alias checking for _NX bit modifications */
+ checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
+
+ ret = __change_page_attr_set_clr(&cpa, checkalias);
/*
* Check whether we really changed something:
*/
- if (!cpa.flushtlb)
- return ret;
+ if (!(cpa.flags & CPA_FLUSHTLB))
+ goto out;
/*
* No need to flush, when we did not set any of the caching
* error case we fall back to cpa_flush_all (which uses
* wbindv):
*/
- if (!ret && cpu_has_clflush)
- cpa_flush_range(addr, numpages, cache);
- else
+ if (!ret && cpu_has_clflush) {
+ if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+ cpa_flush_array(addr, numpages, cache,
+ cpa.flags, pages);
+ } else
+ cpa_flush_range(*addr, numpages, cache);
+ } else
cpa_flush_all(cache);
+out:
return ret;
}
-static inline int change_page_attr_set(unsigned long addr, int numpages,
+static inline int change_page_attr_set(unsigned long *addr, int numpages,
+ pgprot_t mask, int array)
+{
+ return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0,
+ (array ? CPA_ARRAY : 0), NULL);
+}
+
+static inline int change_page_attr_clear(unsigned long *addr, int numpages,
+ pgprot_t mask, int array)
+{
+ return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0,
+ (array ? CPA_ARRAY : 0), NULL);
+}
+
+static inline int cpa_set_pages_array(struct page **pages, int numpages,
pgprot_t mask)
{
- return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0));
+ return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0,
+ CPA_PAGES_ARRAY, pages);
}
-static inline int change_page_attr_clear(unsigned long addr, int numpages,
+static inline int cpa_clear_pages_array(struct page **pages, int numpages,
pgprot_t mask)
{
- return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask);
+ return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0,
+ CPA_PAGES_ARRAY, pages);
+}
+
+int _set_memory_uc(unsigned long addr, int numpages)
+{
+ /*
+ * for now UC MINUS. see comments in ioremap_nocache()
+ */
+ return change_page_attr_set(&addr, numpages,
+ __pgprot(_PAGE_CACHE_UC_MINUS), 0);
}
int set_memory_uc(unsigned long addr, int numpages)
{
- return change_page_attr_set(addr, numpages,
- __pgprot(_PAGE_PCD | _PAGE_PWT));
+ int ret;
+
+ /*
+ * for now UC MINUS. see comments in ioremap_nocache()
+ */
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_UC_MINUS, NULL);
+ if (ret)
+ goto out_err;
+
+ ret = _set_memory_uc(addr, numpages);
+ if (ret)
+ goto out_free;
+
+ return 0;
+
+out_free:
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+ return ret;
}
EXPORT_SYMBOL(set_memory_uc);
+int set_memory_array_uc(unsigned long *addr, int addrinarray)
+{
+ int i, j;
+ int ret;
+
+ /*
+ * for now UC MINUS. see comments in ioremap_nocache()
+ */
+ for (i = 0; i < addrinarray; i++) {
+ ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
+ _PAGE_CACHE_UC_MINUS, NULL);
+ if (ret)
+ goto out_free;
+ }
+
+ ret = change_page_attr_set(addr, addrinarray,
+ __pgprot(_PAGE_CACHE_UC_MINUS), 1);
+ if (ret)
+ goto out_free;
+
+ return 0;
+
+out_free:
+ for (j = 0; j < i; j++)
+ free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE);
+
+ return ret;
+}
+EXPORT_SYMBOL(set_memory_array_uc);
+
+int _set_memory_wc(unsigned long addr, int numpages)
+{
+ int ret;
+ ret = change_page_attr_set(&addr, numpages,
+ __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+
+ if (!ret) {
+ ret = change_page_attr_set(&addr, numpages,
+ __pgprot(_PAGE_CACHE_WC), 0);
+ }
+ return ret;
+}
+
+int set_memory_wc(unsigned long addr, int numpages)
+{
+ int ret;
+
+ if (!pat_enabled)
+ return set_memory_uc(addr, numpages);
+
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_WC, NULL);
+ if (ret)
+ goto out_err;
+
+ ret = _set_memory_wc(addr, numpages);
+ if (ret)
+ goto out_free;
+
+ return 0;
+
+out_free:
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+ return ret;
+}
+EXPORT_SYMBOL(set_memory_wc);
+
+int _set_memory_wb(unsigned long addr, int numpages)
+{
+ return change_page_attr_clear(&addr, numpages,
+ __pgprot(_PAGE_CACHE_MASK), 0);
+}
+
int set_memory_wb(unsigned long addr, int numpages)
{
- return change_page_attr_clear(addr, numpages,
- __pgprot(_PAGE_PCD | _PAGE_PWT));
+ int ret;
+
+ ret = _set_memory_wb(addr, numpages);
+ if (ret)
+ return ret;
+
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+ return 0;
}
EXPORT_SYMBOL(set_memory_wb);
+int set_memory_array_wb(unsigned long *addr, int addrinarray)
+{
+ int i;
+ int ret;
+
+ ret = change_page_attr_clear(addr, addrinarray,
+ __pgprot(_PAGE_CACHE_MASK), 1);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < addrinarray; i++)
+ free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE);
+
+ return 0;
+}
+EXPORT_SYMBOL(set_memory_array_wb);
+
int set_memory_x(unsigned long addr, int numpages)
{
- return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_NX));
+ return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0);
}
EXPORT_SYMBOL(set_memory_x);
int set_memory_nx(unsigned long addr, int numpages)
{
- return change_page_attr_set(addr, numpages, __pgprot(_PAGE_NX));
+ return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0);
}
EXPORT_SYMBOL(set_memory_nx);
int set_memory_ro(unsigned long addr, int numpages)
{
- return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_RW));
+ return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0);
}
+EXPORT_SYMBOL_GPL(set_memory_ro);
int set_memory_rw(unsigned long addr, int numpages)
{
- return change_page_attr_set(addr, numpages, __pgprot(_PAGE_RW));
+ return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0);
}
+EXPORT_SYMBOL_GPL(set_memory_rw);
int set_memory_np(unsigned long addr, int numpages)
{
- return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_PRESENT));
+ return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
+int set_memory_4k(unsigned long addr, int numpages)
+{
+ return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+ __pgprot(0), 1, 0, NULL);
}
int set_pages_uc(struct page *page, int numpages)
}
EXPORT_SYMBOL(set_pages_uc);
+int set_pages_array_uc(struct page **pages, int addrinarray)
+{
+ unsigned long start;
+ unsigned long end;
+ int i;
+ int free_idx;
+
+ for (i = 0; i < addrinarray; i++) {
+ start = (unsigned long)page_address(pages[i]);
+ end = start + PAGE_SIZE;
+ if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
+ goto err_out;
+ }
+
+ if (cpa_set_pages_array(pages, addrinarray,
+ __pgprot(_PAGE_CACHE_UC_MINUS)) == 0) {
+ return 0; /* Success */
+ }
+err_out:
+ free_idx = i;
+ for (i = 0; i < free_idx; i++) {
+ start = (unsigned long)page_address(pages[i]);
+ end = start + PAGE_SIZE;
+ free_memtype(start, end);
+ }
+ return -EINVAL;
+}
+EXPORT_SYMBOL(set_pages_array_uc);
+
int set_pages_wb(struct page *page, int numpages)
{
unsigned long addr = (unsigned long)page_address(page);
}
EXPORT_SYMBOL(set_pages_wb);
+int set_pages_array_wb(struct page **pages, int addrinarray)
+{
+ int retval;
+ unsigned long start;
+ unsigned long end;
+ int i;
+
+ retval = cpa_clear_pages_array(pages, addrinarray,
+ __pgprot(_PAGE_CACHE_MASK));
+ if (retval)
+ return retval;
+
+ for (i = 0; i < addrinarray; i++) {
+ start = (unsigned long)page_address(pages[i]);
+ end = start + PAGE_SIZE;
+ free_memtype(start, end);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(set_pages_array_wb);
+
int set_pages_x(struct page *page, int numpages)
{
unsigned long addr = (unsigned long)page_address(page);
static int __set_pages_p(struct page *page, int numpages)
{
- struct cpa_data cpa = { .vaddr = (unsigned long) page_address(page),
+ unsigned long tempaddr = (unsigned long) page_address(page);
+ struct cpa_data cpa = { .vaddr = &tempaddr,
.numpages = numpages,
.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
- .mask_clr = __pgprot(0)};
+ .mask_clr = __pgprot(0),
+ .flags = 0};
- return __change_page_attr_set_clr(&cpa);
+ /*
+ * No alias checking needed for setting present flag. otherwise,
+ * we may need to break large pages for 64-bit kernel text
+ * mappings (this adds to complexity if we want to do this from
+ * atomic context especially). Let's keep it simple!
+ */
+ return __change_page_attr_set_clr(&cpa, 0);
}
static int __set_pages_np(struct page *page, int numpages)
{
- struct cpa_data cpa = { .vaddr = (unsigned long) page_address(page),
+ unsigned long tempaddr = (unsigned long) page_address(page);
+ struct cpa_data cpa = { .vaddr = &tempaddr,
.numpages = numpages,
.mask_set = __pgprot(0),
- .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW)};
+ .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
+ .flags = 0};
- return __change_page_attr_set_clr(&cpa);
+ /*
+ * No alias checking needed for setting not present flag. otherwise,
+ * we may need to break large pages for 64-bit kernel text
+ * mappings (this adds to complexity if we want to do this from
+ * atomic context especially). Let's keep it simple!
+ */
+ return __change_page_attr_set_clr(&cpa, 0);
}
void kernel_map_pages(struct page *page, int numpages, int enable)
return;
/*
- * The return value is ignored - the calls cannot fail,
- * large pages are disabled at boot time:
+ * The return value is ignored as the calls cannot fail.
+ * Large pages for identity mappings are not used at boot time
+ * and hence no memory allocations during large page split.
*/
if (enable)
__set_pages_p(page, numpages);
*/
__flush_tlb_all();
}
-#endif
+
+#ifdef CONFIG_HIBERNATION
+
+bool kernel_page_present(struct page *page)
+{
+ unsigned int level;
+ pte_t *pte;
+
+ if (PageHighMem(page))
+ return false;
+
+ pte = lookup_address((unsigned long)page_address(page), &level);
+ return (pte_val(*pte) & _PAGE_PRESENT);
+}
+
+#endif /* CONFIG_HIBERNATION */
+
+#endif /* CONFIG_DEBUG_PAGEALLOC */
/*
* The testcases use internal knowledge of the implementation that shouldn't
Code Review / linux-2.6.git / blobdiff