#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
+#include <linux/kallsyms.h>
+#include <linux/swapops.h>
+#include <linux/elf.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
-#include <linux/swapops.h>
-#include <linux/elf.h>
-
#include "internal.h"
#ifndef CONFIG_NEED_MULTIPLE_NODES
2;
#endif
-#ifndef track_pfn_vma_new
-/*
- * Interface that can be used by architecture code to keep track of
- * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
- *
- * track_pfn_vma_new is called when a _new_ pfn mapping is being established
- * for physical range indicated by pfn and size.
- */
-int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
- unsigned long pfn, unsigned long size)
-{
- return 0;
-}
-#endif
-
-#ifndef track_pfn_vma_copy
-/*
- * Interface that can be used by architecture code to keep track of
- * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
- *
- * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
- * copied through copy_page_range().
- */
-int track_pfn_vma_copy(struct vm_area_struct *vma)
-{
- return 0;
-}
-#endif
-
-#ifndef untrack_pfn_vma
-/*
- * Interface that can be used by architecture code to keep track of
- * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
- *
- * untrack_pfn_vma is called while unmapping a pfnmap for a region.
- * untrack can be called for a specific region indicated by pfn and size or
- * can be for the entire vma (in which case size can be zero).
- */
-void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
- unsigned long size)
-{
-}
-#endif
-
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
*
* The calling function must still handle the error.
*/
-static void print_bad_pte(struct vm_area_struct *vma, pte_t pte,
- unsigned long vaddr)
-{
- printk(KERN_ERR "Bad pte = %08llx, process = %s, "
- "vm_flags = %lx, vaddr = %lx\n",
- (long long)pte_val(pte),
- (vma->vm_mm == current->mm ? current->comm : "???"),
- vma->vm_flags, vaddr);
+static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
+ pte_t pte, struct page *page)
+{
+ pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
+ pud_t *pud = pud_offset(pgd, addr);
+ pmd_t *pmd = pmd_offset(pud, addr);
+ struct address_space *mapping;
+ pgoff_t index;
+ static unsigned long resume;
+ static unsigned long nr_shown;
+ static unsigned long nr_unshown;
+
+ /*
+ * Allow a burst of 60 reports, then keep quiet for that minute;
+ * or allow a steady drip of one report per second.
+ */
+ if (nr_shown == 60) {
+ if (time_before(jiffies, resume)) {
+ nr_unshown++;
+ return;
+ }
+ if (nr_unshown) {
+ printk(KERN_ALERT
+ "BUG: Bad page map: %lu messages suppressed\n",
+ nr_unshown);
+ nr_unshown = 0;
+ }
+ nr_shown = 0;
+ }
+ if (nr_shown++ == 0)
+ resume = jiffies + 60 * HZ;
+
+ mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
+ index = linear_page_index(vma, addr);
+
+ printk(KERN_ALERT
+ "BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n",
+ current->comm,
+ (long long)pte_val(pte), (long long)pmd_val(*pmd));
+ if (page) {
+ printk(KERN_ALERT
+ "page:%p flags:%p count:%d mapcount:%d mapping:%p index:%lx\n",
+ page, (void *)page->flags, page_count(page),
+ page_mapcount(page), page->mapping, page->index);
+ }
+ printk(KERN_ALERT
+ "addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n",
+ (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
+ /*
+ * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y
+ */
+ if (vma->vm_ops)
+ print_symbol(KERN_ALERT "vma->vm_ops->fault: %s\n",
+ (unsigned long)vma->vm_ops->fault);
+ if (vma->vm_file && vma->vm_file->f_op)
+ print_symbol(KERN_ALERT "vma->vm_file->f_op->mmap: %s\n",
+ (unsigned long)vma->vm_file->f_op->mmap);
dump_stack();
+ add_taint(TAINT_BAD_PAGE);
}
static inline int is_cow_mapping(unsigned int flags)
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte)
{
- unsigned long pfn;
+ unsigned long pfn = pte_pfn(pte);
if (HAVE_PTE_SPECIAL) {
- if (likely(!pte_special(pte))) {
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
- return pte_page(pte);
- }
- VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
+ if (likely(!pte_special(pte)))
+ goto check_pfn;
+ if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)))
+ print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/* !HAVE_PTE_SPECIAL case follows: */
- pfn = pte_pfn(pte);
-
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
if (!pfn_valid(pfn))
}
}
- VM_BUG_ON(!pfn_valid(pfn));
+check_pfn:
+ if (unlikely(pfn > highest_memmap_pfn)) {
+ print_bad_pte(vma, addr, pte, NULL);
+ return NULL;
+ }
/*
* NOTE! We still have PageReserved() pages in the page tables.
- *
* eg. VDSO mappings can cause them to exist.
*/
out:
if (is_vm_hugetlb_page(vma))
return copy_hugetlb_page_range(dst_mm, src_mm, vma);
- if (is_pfn_mapping(vma)) {
+ if (unlikely(is_pfn_mapping(vma))) {
/*
* We do not free on error cases below as remove_vma
* gets called on error from higher level routine
else {
if (pte_dirty(ptent))
set_page_dirty(page);
- if (pte_young(ptent))
- SetPageReferenced(page);
+ if (pte_young(ptent) &&
+ likely(!VM_SequentialReadHint(vma)))
+ mark_page_accessed(page);
file_rss--;
}
- page_remove_rmap(page, vma);
+ page_remove_rmap(page);
+ if (unlikely(page_mapcount(page) < 0))
+ print_bad_pte(vma, addr, ptent, page);
tlb_remove_page(tlb, page);
continue;
}
*/
if (unlikely(details))
continue;
- if (!pte_file(ptent))
- free_swap_and_cache(pte_to_swp_entry(ptent));
+ if (pte_file(ptent)) {
+ if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
+ print_bad_pte(vma, addr, ptent, NULL);
+ } else if
+ (unlikely(!free_swap_and_cache(pte_to_swp_entry(ptent))))
+ print_bad_pte(vma, addr, ptent, NULL);
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
if (vma->vm_flags & VM_ACCOUNT)
*nr_accounted += (end - start) >> PAGE_SHIFT;
- if (is_pfn_mapping(vma))
+ if (unlikely(is_pfn_mapping(vma)))
untrack_pfn_vma(vma, 0, 0);
while (start != end) {
return page;
}
-int follow_pfnmap_pte(struct vm_area_struct *vma, unsigned long address,
- pte_t *ret_ptep)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *ptep, pte;
- spinlock_t *ptl;
- struct page *page;
- struct mm_struct *mm = vma->vm_mm;
-
- if (!is_pfn_mapping(vma))
- goto err;
-
- page = NULL;
- pgd = pgd_offset(mm, address);
- if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
- goto err;
-
- pud = pud_offset(pgd, address);
- if (pud_none(*pud) || unlikely(pud_bad(*pud)))
- goto err;
-
- pmd = pmd_offset(pud, address);
- if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
- goto err;
-
- ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
-
- pte = *ptep;
- if (!pte_present(pte))
- goto err_unlock;
-
- *ret_ptep = pte;
- pte_unmap_unlock(ptep, ptl);
- return 0;
-
-err_unlock:
- pte_unmap_unlock(ptep, ptl);
-err:
- return -EINVAL;
-}
-
/* Can we do the FOLL_ANON optimization? */
static inline int use_zero_page(struct vm_area_struct *vma)
{
int write = !!(flags & GUP_FLAGS_WRITE);
int force = !!(flags & GUP_FLAGS_FORCE);
int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
+ int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);
if (len <= 0)
return 0;
struct page *page;
/*
- * If tsk is ooming, cut off its access to large memory
- * allocations. It has a pending SIGKILL, but it can't
- * be processed until returning to user space.
+ * If we have a pending SIGKILL, don't keep faulting
+ * pages and potentially allocating memory, unless
+ * current is handling munlock--e.g., on exit. In
+ * that case, we are not allocating memory. Rather,
+ * we're only unlocking already resident/mapped pages.
*/
- if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE)))
- return i ? i : -ENOMEM;
+ if (unlikely(!ignore_sigkill &&
+ fatal_signal_pending(current)))
+ return i ? i : -ERESTARTSYS;
if (write)
foll_flags |= FOLL_WRITE;
* do_wp_page has broken COW when necessary,
* even if maybe_mkwrite decided not to set
* pte_write. We can thus safely do subsequent
- * page lookups as if they were reads.
+ * page lookups as if they were reads. But only
+ * do so when looping for pte_write is futile:
+ * in some cases userspace may also be wanting
+ * to write to the gotten user page, which a
+ * read fault here might prevent (a readonly
+ * page might get reCOWed by userspace write).
*/
- if (ret & VM_FAULT_WRITE)
+ if ((ret & VM_FAULT_WRITE) &&
+ !(vma->vm_flags & VM_WRITE))
foll_flags &= ~FOLL_WRITE;
cond_resched();
unsigned long pfn)
{
int ret;
+ pgprot_t pgprot = vma->vm_page_prot;
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
- if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+ if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
return -EINVAL;
- ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+ ret = insert_pfn(vma, addr, pfn, pgprot);
if (ret)
untrack_pfn_vma(vma, pfn, PAGE_SIZE);
* behaviour that some programs depend on. We mark the "original"
* un-COW'ed pages by matching them up with "vma->vm_pgoff".
*/
- if (addr == vma->vm_start && end == vma->vm_end)
+ if (addr == vma->vm_start && end == vma->vm_end) {
vma->vm_pgoff = pfn;
- else if (is_cow_mapping(vma->vm_flags))
+ vma->vm_flags |= VM_PFN_AT_MMAP;
+ } else if (is_cow_mapping(vma->vm_flags))
return -EINVAL;
vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
- err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
- if (err)
+ err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size));
+ if (err) {
+ /*
+ * To indicate that track_pfn related cleanup is not
+ * needed from higher level routine calling unmap_vmas
+ */
+ vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
+ vma->vm_flags &= ~VM_PFN_AT_MMAP;
return -EINVAL;
+ }
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
BUG_ON(pmd_huge(*pmd));
+ arch_enter_lazy_mmu_mode();
+
token = pmd_pgtable(*pmd);
do {
break;
} while (pte++, addr += PAGE_SIZE, addr != end);
+ arch_leave_lazy_mmu_mode();
+
if (mm != &init_mm)
pte_unmap_unlock(pte-1, ptl);
return err;
* not dirty accountable.
*/
if (PageAnon(old_page)) {
- if (trylock_page(old_page)) {
- reuse = can_share_swap_page(old_page);
- unlock_page(old_page);
+ if (!trylock_page(old_page)) {
+ page_cache_get(old_page);
+ pte_unmap_unlock(page_table, ptl);
+ lock_page(old_page);
+ page_table = pte_offset_map_lock(mm, pmd, address,
+ &ptl);
+ if (!pte_same(*page_table, orig_pte)) {
+ unlock_page(old_page);
+ page_cache_release(old_page);
+ goto unlock;
+ }
+ page_cache_release(old_page);
}
+ reuse = reuse_swap_page(old_page);
+ unlock_page(old_page);
} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))) {
/*
* Don't let another task, with possibly unlocked vma,
* keep the mlocked page.
*/
- if (vma->vm_flags & VM_LOCKED) {
+ if ((vma->vm_flags & VM_LOCKED) && old_page) {
lock_page(old_page); /* for LRU manipulation */
clear_page_mlock(old_page);
unlock_page(old_page);
cow_user_page(new_page, old_page, address, vma);
__SetPageUptodate(new_page);
- if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
+ if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
goto oom_free_new;
/*
* thread doing COW.
*/
ptep_clear_flush_notify(vma, address, page_table);
- SetPageSwapBacked(new_page);
- lru_cache_add_active_or_unevictable(new_page, vma);
page_add_new_anon_rmap(new_page, vma, address);
-
-//TODO: is this safe? do_anonymous_page() does it this way.
set_pte_at(mm, address, page_table, entry);
update_mmu_cache(vma, address, entry);
if (old_page) {
* mapcount is visible. So transitively, TLBs to
* old page will be flushed before it can be reused.
*/
- page_remove_rmap(old_page, vma);
+ page_remove_rmap(old_page);
}
/* Free the old page.. */
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
}
- if (inode->i_op && inode->i_op->truncate)
+ if (inode->i_op->truncate)
inode->i_op->truncate(inode);
return 0;
* a way to truncate a range of blocks (punch a hole) -
* we should return failure right now.
*/
- if (!inode->i_op || !inode->i_op->truncate_range)
+ if (!inode->i_op->truncate_range)
return -ENOSYS;
mutex_lock(&inode->i_mutex);
struct page *page;
swp_entry_t entry;
pte_t pte;
+ struct mem_cgroup *ptr = NULL;
int ret = 0;
if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
lock_page(page);
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
- if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
+ if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
ret = VM_FAULT_OOM;
unlock_page(page);
goto out;
goto out_nomap;
}
- /* The page isn't present yet, go ahead with the fault. */
+ /*
+ * The page isn't present yet, go ahead with the fault.
+ *
+ * Be careful about the sequence of operations here.
+ * To get its accounting right, reuse_swap_page() must be called
+ * while the page is counted on swap but not yet in mapcount i.e.
+ * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
+ * must be called after the swap_free(), or it will never succeed.
+ * Because delete_from_swap_page() may be called by reuse_swap_page(),
+ * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
+ * in page->private. In this case, a record in swap_cgroup is silently
+ * discarded at swap_free().
+ */
inc_mm_counter(mm, anon_rss);
pte = mk_pte(page, vma->vm_page_prot);
- if (write_access && can_share_swap_page(page)) {
+ if (write_access && reuse_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
write_access = 0;
}
-
flush_icache_page(vma, page);
set_pte_at(mm, address, page_table, pte);
page_add_anon_rmap(page, vma, address);
+ /* It's better to call commit-charge after rmap is established */
+ mem_cgroup_commit_charge_swapin(page, ptr);
swap_free(entry);
if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
- remove_exclusive_swap_page(page);
+ try_to_free_swap(page);
unlock_page(page);
if (write_access) {
out:
return ret;
out_nomap:
- mem_cgroup_uncharge_page(page);
+ mem_cgroup_cancel_charge_swapin(ptr);
pte_unmap_unlock(page_table, ptl);
unlock_page(page);
page_cache_release(page);
goto oom;
__SetPageUptodate(page);
- if (mem_cgroup_charge(page, mm, GFP_KERNEL))
+ if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
goto oom_free_page;
entry = mk_pte(page, vma->vm_page_prot);
if (!pte_none(*page_table))
goto release;
inc_mm_counter(mm, anon_rss);
- SetPageSwapBacked(page);
- lru_cache_add_active_or_unevictable(page, vma);
page_add_new_anon_rmap(page, vma, address);
set_pte_at(mm, address, page_table, entry);
ret = VM_FAULT_OOM;
goto out;
}
- if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
+ if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
ret = VM_FAULT_OOM;
page_cache_release(page);
goto out;
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (anon) {
inc_mm_counter(mm, anon_rss);
- SetPageSwapBacked(page);
- lru_cache_add_active_or_unevictable(page, vma);
page_add_new_anon_rmap(page, vma, address);
} else {
inc_mm_counter(mm, file_rss);
get_page(dirty_page);
}
}
-//TODO: is this safe? do_anonymous_page() does it this way.
set_pte_at(mm, address, page_table, entry);
/* no need to invalidate: a not-present page won't be cached */
if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
return 0;
- if (unlikely(!(vma->vm_flags & VM_NONLINEAR) ||
- !(vma->vm_flags & VM_CAN_NONLINEAR))) {
+ if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
/*
* Page table corrupted: show pte and kill process.
*/
- print_bad_pte(vma, orig_pte, address);
+ print_bad_pte(vma, address, orig_pte, NULL);
return VM_FAULT_OOM;
}
{
resource_size_t phys_addr;
unsigned long prot = 0;
- void *maddr;
+ void __iomem *maddr;
int offset = addr & (PAGE_SIZE-1);
if (follow_phys(vma, addr, write, &prot, &phys_addr))
}
up_read(¤t->mm->mmap_sem);
}
+
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void)
+{
+ /*
+ * Some code (nfs/sunrpc) uses socket ops on kernel memory while
+ * holding the mmap_sem, this is safe because kernel memory doesn't
+ * get paged out, therefore we'll never actually fault, and the
+ * below annotations will generate false positives.
+ */
+ if (segment_eq(get_fs(), KERNEL_DS))
+ return;
+
+ might_sleep();
+ /*
+ * it would be nicer only to annotate paths which are not under
+ * pagefault_disable, however that requires a larger audit and
+ * providing helpers like get_user_atomic.
+ */
+ if (!in_atomic() && current->mm)
+ might_lock_read(¤t->mm->mmap_sem);
+}
+EXPORT_SYMBOL(might_fault);
+#endif