#include <linux/swapops.h>
#include <linux/elf.h>
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_NEED_MULTIPLE_NODES
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;
*
* Must be called with pagetable lock held.
*/
-static inline void free_pgd_range(struct mmu_gather *tlb,
+void free_pgd_range(struct mmu_gather **tlb,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
return;
start = addr;
- pgd = pgd_offset(tlb->mm, addr);
+ pgd = pgd_offset((*tlb)->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+ free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
- if (!tlb_is_full_mm(tlb))
- flush_tlb_pgtables(tlb->mm, start, end);
+ if (!tlb_is_full_mm(*tlb))
+ flush_tlb_pgtables((*tlb)->mm, start, end);
}
void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
- unsigned long floor, unsigned long ceiling)
+ unsigned long floor, unsigned long ceiling)
{
while (vma) {
struct vm_area_struct *next = vma->vm_next;
unsigned long addr = vma->vm_start;
- /* Optimization: gather nearby vmas into a single call down */
- while (next && next->vm_start <= vma->vm_end + PMD_SIZE) {
- vma = next;
- next = vma->vm_next;
- }
- free_pgd_range(*tlb, addr, vma->vm_end,
+ if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
+ hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
floor, next? next->vm_start: ceiling);
+ } else {
+ /*
+ * Optimization: gather nearby vmas into one call down
+ */
+ while (next && next->vm_start <= vma->vm_end + PMD_SIZE
+ && !is_hugepage_only_range(vma->vm_mm, next->vm_start,
+ HPAGE_SIZE)) {
+ vma = next;
+ next = vma->vm_next;
+ }
+ free_pgd_range(tlb, addr, vma->vm_end,
+ floor, next? next->vm_start: ceiling);
+ }
vma = next;
}
}
-pte_t fastcall * pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+pte_t fastcall *pte_alloc_map(struct mm_struct *mm, pmd_t *pmd,
+ unsigned long address)
{
if (!pmd_present(*pmd)) {
struct page *new;
* @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
* @details: details of nonlinear truncation or shared cache invalidation
*
- * Returns the number of vma's which were covered by the unmapping.
+ * Returns the end address of the unmapping (restart addr if interrupted).
*
* Unmap all pages in the vma list. Called under page_table_lock.
*
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
-int unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
+unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr, unsigned long *nr_accounted,
struct zap_details *details)
unsigned long zap_bytes = ZAP_BLOCK_SIZE;
unsigned long tlb_start = 0; /* For tlb_finish_mmu */
int tlb_start_valid = 0;
- int ret = 0;
+ unsigned long start = start_addr;
spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
int fullmm = tlb_is_full_mm(*tlbp);
for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
- unsigned long start;
unsigned long end;
start = max(vma->vm_start, start_addr);
if (vma->vm_flags & VM_ACCOUNT)
*nr_accounted += (end - start) >> PAGE_SHIFT;
- ret++;
while (start != end) {
unsigned long block;
if (i_mmap_lock) {
/* must reset count of rss freed */
*tlbp = tlb_gather_mmu(mm, fullmm);
- details->break_addr = start;
goto out;
}
spin_unlock(&mm->page_table_lock);
}
}
out:
- return ret;
+ return start; /* which is now the end (or restart) address */
}
/**
* @size: number of bytes to zap
* @details: details of nonlinear truncation or shared cache invalidation
*/
-void zap_page_range(struct vm_area_struct *vma, unsigned long address,
+unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *details)
{
struct mm_struct *mm = vma->vm_mm;
if (is_vm_hugetlb_page(vma)) {
zap_hugepage_range(vma, address, size);
- return;
+ return end;
}
lru_add_drain();
spin_lock(&mm->page_table_lock);
tlb = tlb_gather_mmu(mm, 0);
- unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
+ end = unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
tlb_finish_mmu(tlb, address, end);
spin_unlock(&mm->page_table_lock);
+ return end;
}
/*
{
return __follow_page(mm, address, /*read*/1, /*write*/0) != NULL;
}
-
EXPORT_SYMBOL(check_user_page_readable);
-/*
- * Given a physical address, is there a useful struct page pointing to
- * it? This may become more complex in the future if we start dealing
- * with IO-aperture pages for direct-IO.
- */
-
-static inline struct page *get_page_map(struct page *page)
-{
- if (!pfn_valid(page_to_pfn(page)))
- return NULL;
- return page;
-}
-
-
static inline int
untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma,
unsigned long address)
return 0;
}
-
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int len, int write, int force,
struct page **pages, struct vm_area_struct **vmas)
}
spin_lock(&mm->page_table_lock);
do {
- struct page *map;
+ struct page *page;
int lookup_write = write;
cond_resched_lock(&mm->page_table_lock);
- while (!(map = follow_page(mm, start, lookup_write))) {
+ while (!(page = follow_page(mm, start, lookup_write))) {
/*
* Shortcut for anonymous pages. We don't want
* to force the creation of pages tables for
- * insanly big anonymously mapped areas that
+ * insanely big anonymously mapped areas that
* nobody touched so far. This is important
* for doing a core dump for these mappings.
*/
if (!lookup_write &&
untouched_anonymous_page(mm,vma,start)) {
- map = ZERO_PAGE(start);
+ page = ZERO_PAGE(start);
break;
}
spin_unlock(&mm->page_table_lock);
spin_lock(&mm->page_table_lock);
}
if (pages) {
- pages[i] = get_page_map(map);
- if (!pages[i]) {
- spin_unlock(&mm->page_table_lock);
- while (i--)
- page_cache_release(pages[i]);
- i = -EFAULT;
- goto out;
- }
- flush_dcache_page(pages[i]);
- if (!PageReserved(pages[i]))
- page_cache_get(pages[i]);
+ pages[i] = page;
+ flush_dcache_page(page);
+ if (!PageReserved(page))
+ page_cache_get(page);
}
if (vmas)
vmas[i] = vma;
i++;
start += PAGE_SIZE;
len--;
- } while(len && start < vma->vm_end);
+ } while (len && start < vma->vm_end);
spin_unlock(&mm->page_table_lock);
- } while(len);
-out:
+ } while (len);
return i;
}
-
EXPORT_SYMBOL(get_user_pages);
static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
}
old_page = pfn_to_page(pfn);
- if (!TestSetPageLocked(old_page)) {
+ if (PageAnon(old_page) && !TestSetPageLocked(old_page)) {
int reuse = can_share_swap_page(old_page);
unlock_page(old_page);
if (reuse) {
* i_mmap_lock.
*
* In order to make forward progress despite repeatedly restarting some
- * large vma, note the break_addr set by unmap_vmas when it breaks out:
+ * large vma, note the restart_addr from unmap_vmas when it breaks out:
* and restart from that address when we reach that vma again. It might
* have been split or merged, shrunk or extended, but never shifted: so
* restart_addr remains valid so long as it remains in the vma's range.
}
}
- details->break_addr = end_addr;
- zap_page_range(vma, start_addr, end_addr - start_addr, details);
+ restart_addr = zap_page_range(vma, start_addr,
+ end_addr - start_addr, details);
/*
* We cannot rely on the break test in unmap_vmas:
need_break = need_resched() ||
need_lockbreak(details->i_mmap_lock);
- if (details->break_addr >= end_addr) {
+ if (restart_addr >= end_addr) {
/* We have now completed this vma: mark it so */
vma->vm_truncate_count = details->truncate_count;
if (!need_break)
return 0;
} else {
/* Note restart_addr in vma's truncate_count field */
- vma->vm_truncate_count = details->break_addr;
+ vma->vm_truncate_count = restart_addr;
if (!need_break)
goto again;
}
spin_lock(&mm->page_table_lock);
page_table = pte_offset_map(pmd, address);
if (unlikely(!pte_same(*page_table, orig_pte))) {
- pte_unmap(page_table);
- spin_unlock(&mm->page_table_lock);
- unlock_page(page);
- page_cache_release(page);
ret = VM_FAULT_MINOR;
- goto out;
+ goto out_nomap;
+ }
+
+ if (unlikely(!PageUptodate(page))) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_nomap;
}
/* The page isn't present yet, go ahead with the fault. */
-
- swap_free(entry);
- if (vm_swap_full())
- remove_exclusive_swap_page(page);
inc_mm_counter(mm, rss);
pte = mk_pte(page, vma->vm_page_prot);
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
write_access = 0;
}
- unlock_page(page);
flush_icache_page(vma, page);
set_pte_at(mm, address, page_table, pte);
page_add_anon_rmap(page, vma, address);
+ swap_free(entry);
+ if (vm_swap_full())
+ remove_exclusive_swap_page(page);
+ unlock_page(page);
+
if (write_access) {
if (do_wp_page(mm, vma, address,
page_table, pmd, pte) == VM_FAULT_OOM)
spin_unlock(&mm->page_table_lock);
out:
return ret;
+out_nomap:
+ pte_unmap(page_table);
+ spin_unlock(&mm->page_table_lock);
+ unlock_page(page);
+ page_cache_release(page);
+ goto out;
}
/*