*
* 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
* (Gerhard.Wichert@pdb.siemens.de)
+ *
+ * Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
*/
#include <linux/kernel_stat.h>
* and ZONE_HIGHMEM.
*/
void * high_memory;
-struct page *highmem_start_page;
unsigned long vmalloc_earlyreserve;
EXPORT_SYMBOL(num_physpages);
-EXPORT_SYMBOL(highmem_start_page);
EXPORT_SYMBOL(high_memory);
EXPORT_SYMBOL(vmalloc_earlyreserve);
/*
- * We special-case the C-O-W ZERO_PAGE, because it's such
- * a common occurrence (no need to read the page to know
- * that it's zero - better for the cache and memory subsystem).
+ * If a p?d_bad entry is found while walking page tables, report
+ * the error, before resetting entry to p?d_none. Usually (but
+ * very seldom) called out from the p?d_none_or_clear_bad macros.
*/
-static inline void copy_cow_page(struct page * from, struct page * to, unsigned long address)
+
+void pgd_clear_bad(pgd_t *pgd)
{
- if (from == ZERO_PAGE(address)) {
- clear_user_highpage(to, address);
- return;
- }
- copy_user_highpage(to, from, address);
+ pgd_ERROR(*pgd);
+ pgd_clear(pgd);
+}
+
+void pud_clear_bad(pud_t *pud)
+{
+ pud_ERROR(*pud);
+ pud_clear(pud);
+}
+
+void pmd_clear_bad(pmd_t *pmd)
+{
+ pmd_ERROR(*pmd);
+ pmd_clear(pmd);
}
/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
-static inline void free_one_pmd(struct mmu_gather *tlb, pmd_t * dir)
+static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
{
- struct page *page;
-
- if (pmd_none(*dir))
- return;
- if (unlikely(pmd_bad(*dir))) {
- pmd_ERROR(*dir);
- pmd_clear(dir);
- return;
- }
- page = pmd_page(*dir);
- pmd_clear(dir);
+ struct page *page = pmd_page(*pmd);
+ pmd_clear(pmd);
+ pte_free_tlb(tlb, page);
dec_page_state(nr_page_table_pages);
tlb->mm->nr_ptes--;
- pte_free_tlb(tlb, page);
}
-static inline void free_one_pgd(struct mmu_gather *tlb, pgd_t * dir)
+static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
{
- int j;
- pmd_t * pmd;
+ pmd_t *pmd;
+ unsigned long next;
+ unsigned long start;
- if (pgd_none(*dir))
- return;
- if (unlikely(pgd_bad(*dir))) {
- pgd_ERROR(*dir);
- pgd_clear(dir);
+ start = addr;
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (pmd_none_or_clear_bad(pmd))
+ continue;
+ free_pte_range(tlb, pmd);
+ } while (pmd++, addr = next, addr != end);
+
+ start &= PUD_MASK;
+ if (start < floor)
return;
+ if (ceiling) {
+ ceiling &= PUD_MASK;
+ if (!ceiling)
+ return;
}
- pmd = pmd_offset(dir, 0);
- pgd_clear(dir);
- for (j = 0; j < PTRS_PER_PMD ; j++)
- free_one_pmd(tlb, pmd+j);
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pmd = pmd_offset(pud, start);
+ pud_clear(pud);
pmd_free_tlb(tlb, pmd);
}
+static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ pud_t *pud;
+ unsigned long next;
+ unsigned long start;
+
+ start = addr;
+ pud = pud_offset(pgd, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (pud_none_or_clear_bad(pud))
+ continue;
+ free_pmd_range(tlb, pud, addr, next, floor, ceiling);
+ } while (pud++, addr = next, addr != end);
+
+ start &= PGDIR_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= PGDIR_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pud = pud_offset(pgd, start);
+ pgd_clear(pgd);
+ pud_free_tlb(tlb, pud);
+}
+
/*
- * This function clears all user-level page tables of a process - this
- * is needed by execve(), so that old pages aren't in the way.
+ * This function frees user-level page tables of a process.
*
* Must be called with pagetable lock held.
*/
-void clear_page_tables(struct mmu_gather *tlb, unsigned long first, int nr)
+void free_pgd_range(struct mmu_gather **tlb,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
{
- pgd_t * page_dir = tlb->mm->pgd;
+ pgd_t *pgd;
+ unsigned long next;
+ unsigned long start;
+
+ /*
+ * The next few lines have given us lots of grief...
+ *
+ * Why are we testing PMD* at this top level? Because often
+ * there will be no work to do at all, and we'd prefer not to
+ * go all the way down to the bottom just to discover that.
+ *
+ * Why all these "- 1"s? Because 0 represents both the bottom
+ * of the address space and the top of it (using -1 for the
+ * top wouldn't help much: the masks would do the wrong thing).
+ * The rule is that addr 0 and floor 0 refer to the bottom of
+ * the address space, but end 0 and ceiling 0 refer to the top
+ * Comparisons need to use "end - 1" and "ceiling - 1" (though
+ * that end 0 case should be mythical).
+ *
+ * Wherever addr is brought up or ceiling brought down, we must
+ * be careful to reject "the opposite 0" before it confuses the
+ * subsequent tests. But what about where end is brought down
+ * by PMD_SIZE below? no, end can't go down to 0 there.
+ *
+ * Whereas we round start (addr) and ceiling down, by different
+ * masks at different levels, in order to test whether a table
+ * now has no other vmas using it, so can be freed, we don't
+ * bother to round floor or end up - the tests don't need that.
+ */
- page_dir += first;
+ addr &= PMD_MASK;
+ if (addr < floor) {
+ addr += PMD_SIZE;
+ if (!addr)
+ return;
+ }
+ if (ceiling) {
+ ceiling &= PMD_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ end -= PMD_SIZE;
+ if (addr > end - 1)
+ return;
+
+ start = addr;
+ pgd = pgd_offset((*tlb)->mm, addr);
do {
- free_one_pgd(tlb, page_dir);
- page_dir++;
- } while (--nr);
+ next = pgd_addr_end(addr, end);
+ if (pgd_none_or_clear_bad(pgd))
+ continue;
+ 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);
+}
+
+void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
+ unsigned long floor, unsigned long ceiling)
+{
+ while (vma) {
+ struct vm_area_struct *next = vma->vm_next;
+ unsigned long addr = vma->vm_start;
+
+ 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;
out:
return pte_offset_kernel(pmd, address);
}
-#define PTE_TABLE_MASK ((PTRS_PER_PTE-1) * sizeof(pte_t))
-#define PMD_TABLE_MASK ((PTRS_PER_PMD-1) * sizeof(pmd_t))
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
* covered by this vma.
*
- * 08Jan98 Merged into one routine from several inline routines to reduce
- * variable count and make things faster. -jj
- *
* dst->page_table_lock is held on entry and exit,
- * but may be dropped within pmd_alloc() and pte_alloc_map().
+ * but may be dropped within p[mg]d_alloc() and pte_alloc_map().
*/
-int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
- struct vm_area_struct *vma)
+
+static inline void
+copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags,
+ unsigned long addr)
{
- pgd_t * src_pgd, * dst_pgd;
- unsigned long address = vma->vm_start;
- unsigned long end = vma->vm_end;
- unsigned long cow;
+ pte_t pte = *src_pte;
+ struct page *page;
+ unsigned long pfn;
- if (is_vm_hugetlb_page(vma))
- return copy_hugetlb_page_range(dst, src, vma);
+ /* pte contains position in swap or file, so copy. */
+ if (unlikely(!pte_present(pte))) {
+ if (!pte_file(pte)) {
+ swap_duplicate(pte_to_swp_entry(pte));
+ /* make sure dst_mm is on swapoff's mmlist. */
+ if (unlikely(list_empty(&dst_mm->mmlist))) {
+ spin_lock(&mmlist_lock);
+ list_add(&dst_mm->mmlist, &src_mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ }
+ set_pte_at(dst_mm, addr, dst_pte, pte);
+ return;
+ }
- cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
- src_pgd = pgd_offset(src, address)-1;
- dst_pgd = pgd_offset(dst, address)-1;
+ pfn = pte_pfn(pte);
+ /* the pte points outside of valid memory, the
+ * mapping is assumed to be good, meaningful
+ * and not mapped via rmap - duplicate the
+ * mapping as is.
+ */
+ page = NULL;
+ if (pfn_valid(pfn))
+ page = pfn_to_page(pfn);
- for (;;) {
- pmd_t * src_pmd, * dst_pmd;
+ if (!page || PageReserved(page)) {
+ set_pte_at(dst_mm, addr, dst_pte, pte);
+ return;
+ }
- src_pgd++; dst_pgd++;
-
- /* copy_pmd_range */
-
- if (pgd_none(*src_pgd))
- goto skip_copy_pmd_range;
- if (unlikely(pgd_bad(*src_pgd))) {
- pgd_ERROR(*src_pgd);
- pgd_clear(src_pgd);
-skip_copy_pmd_range: address = (address + PGDIR_SIZE) & PGDIR_MASK;
- if (!address || (address >= end))
- goto out;
+ /*
+ * If it's a COW mapping, write protect it both
+ * in the parent and the child
+ */
+ if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) {
+ ptep_set_wrprotect(src_mm, addr, src_pte);
+ pte = *src_pte;
+ }
+
+ /*
+ * If it's a shared mapping, mark it clean in
+ * the child
+ */
+ if (vm_flags & VM_SHARED)
+ pte = pte_mkclean(pte);
+ pte = pte_mkold(pte);
+ get_page(page);
+ inc_mm_counter(dst_mm, rss);
+ if (PageAnon(page))
+ inc_mm_counter(dst_mm, anon_rss);
+ set_pte_at(dst_mm, addr, dst_pte, pte);
+ page_dup_rmap(page);
+}
+
+static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ pte_t *src_pte, *dst_pte;
+ unsigned long vm_flags = vma->vm_flags;
+ int progress;
+
+again:
+ dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr);
+ if (!dst_pte)
+ return -ENOMEM;
+ src_pte = pte_offset_map_nested(src_pmd, addr);
+
+ progress = 0;
+ spin_lock(&src_mm->page_table_lock);
+ do {
+ /*
+ * We are holding two locks at this point - either of them
+ * could generate latencies in another task on another CPU.
+ */
+ if (progress >= 32 && (need_resched() ||
+ need_lockbreak(&src_mm->page_table_lock) ||
+ need_lockbreak(&dst_mm->page_table_lock)))
+ break;
+ if (pte_none(*src_pte)) {
+ progress++;
continue;
}
+ copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vm_flags, addr);
+ progress += 8;
+ } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
+ spin_unlock(&src_mm->page_table_lock);
+
+ pte_unmap_nested(src_pte - 1);
+ pte_unmap(dst_pte - 1);
+ cond_resched_lock(&dst_mm->page_table_lock);
+ if (addr != end)
+ goto again;
+ return 0;
+}
- src_pmd = pmd_offset(src_pgd, address);
- dst_pmd = pmd_alloc(dst, dst_pgd, address);
- if (!dst_pmd)
- goto nomem;
+static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ pmd_t *src_pmd, *dst_pmd;
+ unsigned long next;
- do {
- pte_t * src_pte, * dst_pte;
-
- /* copy_pte_range */
-
- if (pmd_none(*src_pmd))
- goto skip_copy_pte_range;
- if (unlikely(pmd_bad(*src_pmd))) {
- pmd_ERROR(*src_pmd);
- pmd_clear(src_pmd);
-skip_copy_pte_range:
- address = (address + PMD_SIZE) & PMD_MASK;
- if (address >= end)
- goto out;
- goto cont_copy_pmd_range;
- }
+ dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
+ if (!dst_pmd)
+ return -ENOMEM;
+ src_pmd = pmd_offset(src_pud, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (pmd_none_or_clear_bad(src_pmd))
+ continue;
+ if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
+ vma, addr, next))
+ return -ENOMEM;
+ } while (dst_pmd++, src_pmd++, addr = next, addr != end);
+ return 0;
+}
- dst_pte = pte_alloc_map(dst, dst_pmd, address);
- if (!dst_pte)
- goto nomem;
- spin_lock(&src->page_table_lock);
- src_pte = pte_offset_map_nested(src_pmd, address);
- do {
- pte_t pte = *src_pte;
- struct page *page;
- unsigned long pfn;
-
- if (!vx_rsspages_avail(dst, 1)) {
- spin_unlock(&src->page_table_lock);
- goto nomem;
- }
- /* copy_one_pte */
-
- if (pte_none(pte))
- goto cont_copy_pte_range_noset;
- /* pte contains position in swap, so copy. */
- if (!pte_present(pte)) {
- if (!pte_file(pte)) {
- swap_duplicate(pte_to_swp_entry(pte));
- if (list_empty(&dst->mmlist)) {
- spin_lock(&mmlist_lock);
- list_add(&dst->mmlist,
- &src->mmlist);
- spin_unlock(&mmlist_lock);
- }
- }
- set_pte(dst_pte, pte);
- goto cont_copy_pte_range_noset;
- }
- pfn = pte_pfn(pte);
- /* the pte points outside of valid memory, the
- * mapping is assumed to be good, meaningful
- * and not mapped via rmap - duplicate the
- * mapping as is.
- */
- page = NULL;
- if (pfn_valid(pfn))
- page = pfn_to_page(pfn);
+static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ pud_t *src_pud, *dst_pud;
+ unsigned long next;
- if (!page || PageReserved(page)) {
- set_pte(dst_pte, pte);
- goto cont_copy_pte_range_noset;
- }
+ dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+ if (!dst_pud)
+ return -ENOMEM;
+ src_pud = pud_offset(src_pgd, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (pud_none_or_clear_bad(src_pud))
+ continue;
+ if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
+ vma, addr, next))
+ return -ENOMEM;
+ } while (dst_pud++, src_pud++, addr = next, addr != end);
+ return 0;
+}
- /*
- * If it's a COW mapping, write protect it both
- * in the parent and the child
- */
- if (cow) {
- ptep_set_wrprotect(src_pte);
- pte = *src_pte;
- }
+int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ struct vm_area_struct *vma)
+{
+ pgd_t *src_pgd, *dst_pgd;
+ unsigned long next;
+ unsigned long addr = vma->vm_start;
+ unsigned long end = vma->vm_end;
- /*
- * If it's a shared mapping, mark it clean in
- * the child
- */
- if (vma->vm_flags & VM_SHARED)
- pte = pte_mkclean(pte);
- pte = pte_mkold(pte);
- get_page(page);
- // dst->rss++;
- vx_rsspages_inc(dst);
- if (PageAnon(page))
- dst->anon_rss++;
- set_pte(dst_pte, pte);
- page_dup_rmap(page);
-cont_copy_pte_range_noset:
- address += PAGE_SIZE;
- if (address >= end) {
- pte_unmap_nested(src_pte);
- pte_unmap(dst_pte);
- goto out_unlock;
- }
- src_pte++;
- dst_pte++;
- } while ((unsigned long)src_pte & PTE_TABLE_MASK);
- pte_unmap_nested(src_pte-1);
- pte_unmap(dst_pte-1);
- spin_unlock(&src->page_table_lock);
- cond_resched_lock(&dst->page_table_lock);
-cont_copy_pmd_range:
- src_pmd++;
- dst_pmd++;
- } while ((unsigned long)src_pmd & PMD_TABLE_MASK);
- }
-out_unlock:
- spin_unlock(&src->page_table_lock);
-out:
+ if (is_vm_hugetlb_page(vma))
+ return copy_hugetlb_page_range(dst_mm, src_mm, vma);
+
+ dst_pgd = pgd_offset(dst_mm, addr);
+ src_pgd = pgd_offset(src_mm, addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ if (pgd_none_or_clear_bad(src_pgd))
+ continue;
+ if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+ vma, addr, next))
+ return -ENOMEM;
+ } while (dst_pgd++, src_pgd++, addr = next, addr != end);
return 0;
-nomem:
- return -ENOMEM;
}
-static void zap_pte_range(struct mmu_gather *tlb,
- pmd_t *pmd, unsigned long address,
- unsigned long size, struct zap_details *details)
+static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ struct zap_details *details)
{
- unsigned long offset;
- pte_t *ptep;
+ pte_t *pte;
- if (pmd_none(*pmd))
- return;
- if (unlikely(pmd_bad(*pmd))) {
- pmd_ERROR(*pmd);
- pmd_clear(pmd);
- return;
- }
- ptep = pte_offset_map(pmd, address);
- offset = address & ~PMD_MASK;
- if (offset + size > PMD_SIZE)
- size = PMD_SIZE - offset;
- size &= PAGE_MASK;
- if (details && !details->check_mapping && !details->nonlinear_vma)
- details = NULL;
- for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
- pte_t pte = *ptep;
- if (pte_none(pte))
+ pte = pte_offset_map(pmd, addr);
+ do {
+ pte_t ptent = *pte;
+ if (pte_none(ptent))
continue;
- if (pte_present(pte)) {
+ if (pte_present(ptent)) {
struct page *page = NULL;
- unsigned long pfn = pte_pfn(pte);
+ unsigned long pfn = pte_pfn(ptent);
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
if (PageReserved(page))
page->index > details->last_index))
continue;
}
- pte = ptep_get_and_clear(ptep);
- tlb_remove_tlb_entry(tlb, ptep, address+offset);
+ ptent = ptep_get_and_clear(tlb->mm, addr, pte);
+ tlb_remove_tlb_entry(tlb, pte, addr);
if (unlikely(!page))
continue;
if (unlikely(details) && details->nonlinear_vma
&& linear_page_index(details->nonlinear_vma,
- address+offset) != page->index)
- set_pte(ptep, pgoff_to_pte(page->index));
- if (pte_dirty(pte))
+ addr) != page->index)
+ set_pte_at(tlb->mm, addr, pte,
+ pgoff_to_pte(page->index));
+ if (pte_dirty(ptent))
set_page_dirty(page);
if (PageAnon(page))
- tlb->mm->anon_rss--;
- else if (pte_young(pte))
+ dec_mm_counter(tlb->mm, anon_rss);
+ else if (pte_young(ptent))
mark_page_accessed(page);
tlb->freed++;
page_remove_rmap(page);
*/
if (unlikely(details))
continue;
- if (!pte_file(pte))
- free_swap_and_cache(pte_to_swp_entry(pte));
- pte_clear(ptep);
- }
- pte_unmap(ptep-1);
+ if (!pte_file(ptent))
+ free_swap_and_cache(pte_to_swp_entry(ptent));
+ pte_clear(tlb->mm, addr, pte);
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+ pte_unmap(pte - 1);
}
-static void zap_pmd_range(struct mmu_gather *tlb,
- pgd_t * dir, unsigned long address,
- unsigned long size, struct zap_details *details)
+static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ struct zap_details *details)
{
- pmd_t * pmd;
- unsigned long end;
+ pmd_t *pmd;
+ unsigned long next;
- if (pgd_none(*dir))
- return;
- if (unlikely(pgd_bad(*dir))) {
- pgd_ERROR(*dir);
- pgd_clear(dir);
- return;
- }
- pmd = pmd_offset(dir, address);
- end = address + size;
- if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
- end = ((address + PGDIR_SIZE) & PGDIR_MASK);
+ pmd = pmd_offset(pud, addr);
do {
- zap_pte_range(tlb, pmd, address, end - address, details);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
+ next = pmd_addr_end(addr, end);
+ if (pmd_none_or_clear_bad(pmd))
+ continue;
+ zap_pte_range(tlb, pmd, addr, next, details);
+ } while (pmd++, addr = next, addr != end);
}
-static void unmap_page_range(struct mmu_gather *tlb,
- struct vm_area_struct *vma, unsigned long address,
- unsigned long end, struct zap_details *details)
+static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ struct zap_details *details)
{
- pgd_t * dir;
+ pud_t *pud;
+ unsigned long next;
- BUG_ON(address >= end);
- dir = pgd_offset(vma->vm_mm, address);
- tlb_start_vma(tlb, vma);
+ pud = pud_offset(pgd, addr);
do {
- zap_pmd_range(tlb, dir, address, end - address, details);
- address = (address + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (address && (address < end));
- tlb_end_vma(tlb, vma);
+ next = pud_addr_end(addr, end);
+ if (pud_none_or_clear_bad(pud))
+ continue;
+ zap_pmd_range(tlb, pud, addr, next, details);
+ } while (pud++, addr = next, addr != end);
}
-/* Dispose of an entire struct mmu_gather per rescheduling point */
-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT)
-#define ZAP_BLOCK_SIZE (FREE_PTE_NR * PAGE_SIZE)
-#endif
+static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end,
+ struct zap_details *details)
+{
+ pgd_t *pgd;
+ unsigned long next;
-/* For UP, 256 pages at a time gives nice low latency */
-#if !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT)
-#define ZAP_BLOCK_SIZE (256 * PAGE_SIZE)
-#endif
+ if (details && !details->check_mapping && !details->nonlinear_vma)
+ details = NULL;
+ BUG_ON(addr >= end);
+ tlb_start_vma(tlb, vma);
+ pgd = pgd_offset(vma->vm_mm, addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ if (pgd_none_or_clear_bad(pgd))
+ continue;
+ zap_pud_range(tlb, pgd, addr, next, details);
+ } while (pgd++, addr = next, addr != end);
+ tlb_end_vma(tlb, vma);
+}
+
+#ifdef CONFIG_PREEMPT
+# define ZAP_BLOCK_SIZE (8 * PAGE_SIZE)
+#else
/* No preempt: go for improved straight-line efficiency */
-#if !defined(CONFIG_PREEMPT)
-#define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE)
+# define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE)
#endif
/**
* @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;
- int atomic = details && details->atomic;
+ 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;
zap_bytes -= block;
if ((long)zap_bytes > 0)
continue;
- if (!atomic && need_resched()) {
- int fullmm = tlb_is_full_mm(*tlbp);
- tlb_finish_mmu(*tlbp, tlb_start, start);
- cond_resched_lock(&mm->page_table_lock);
- *tlbp = tlb_gather_mmu(mm, fullmm);
- tlb_start_valid = 0;
+
+ tlb_finish_mmu(*tlbp, tlb_start, start);
+
+ if (need_resched() ||
+ need_lockbreak(&mm->page_table_lock) ||
+ (i_mmap_lock && need_lockbreak(i_mmap_lock))) {
+ if (i_mmap_lock) {
+ /* must reset count of rss freed */
+ *tlbp = tlb_gather_mmu(mm, fullmm);
+ goto out;
+ }
+ spin_unlock(&mm->page_table_lock);
+ cond_resched();
+ spin_lock(&mm->page_table_lock);
}
+
+ *tlbp = tlb_gather_mmu(mm, fullmm);
+ tlb_start_valid = 0;
zap_bytes = ZAP_BLOCK_SIZE;
}
}
- return ret;
+out:
+ 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;
}
/*
* Do a quick page-table lookup for a single page.
* mm->page_table_lock must be held.
*/
-struct page *
-follow_page(struct mm_struct *mm, unsigned long address, int write)
+static struct page *
+__follow_page(struct mm_struct *mm, unsigned long address, int read, int write)
{
pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
unsigned long pfn;
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
goto out;
- pmd = pmd_offset(pgd, address);
- if (pmd_none(*pmd))
+ pud = pud_offset(pgd, address);
+ if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+ goto out;
+
+ pmd = pmd_offset(pud, address);
+ if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
goto out;
if (pmd_huge(*pmd))
return follow_huge_pmd(mm, address, pmd, write);
- if (unlikely(pmd_bad(*pmd)))
- goto out;
ptep = pte_offset_map(pmd, address);
if (!ptep)
if (pte_present(pte)) {
if (write && !pte_write(pte))
goto out;
+ if (read && !pte_read(pte))
+ goto out;
pfn = pte_pfn(pte);
if (pfn_valid(pfn)) {
page = pfn_to_page(pfn);
return NULL;
}
+struct page *
+follow_page(struct mm_struct *mm, unsigned long address, int write)
+{
+ return __follow_page(mm, address, /*read*/0, write);
+}
+
+int
+check_user_page_readable(struct mm_struct *mm, unsigned long address)
+{
+ 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
unsigned long address)
{
pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
/* Check if the vma is for an anonymous mapping. */
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return 1;
+ pud = pud_offset(pgd, address);
+ if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+ return 1;
+
/* Check if page middle directory entry exists. */
- pmd = pmd_offset(pgd, address);
+ pmd = pmd_offset(pud, address);
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
return 1;
unsigned long pg = start & PAGE_MASK;
struct vm_area_struct *gate_vma = get_gate_vma(tsk);
pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
pte_t *pte;
if (write) /* user gate pages are read-only */
else
pgd = pgd_offset_gate(mm, pg);
BUG_ON(pgd_none(*pgd));
- pmd = pmd_offset(pgd, pg);
+ pud = pud_offset(pgd, pg);
+ BUG_ON(pud_none(*pud));
+ pmd = pmd_offset(pud, pg);
BUG_ON(pmd_none(*pmd));
pte = pte_offset_map(pmd, pg);
BUG_ON(pte_none(*pte));
do {
struct page *map;
int lookup_write = write;
+
+ cond_resched_lock(&mm->page_table_lock);
while (!(map = follow_page(mm, start, lookup_write))) {
/*
* Shortcut for anonymous pages. We don't want
EXPORT_SYMBOL(get_user_pages);
-static void zeromap_pte_range(pte_t * pte, unsigned long address,
- unsigned long size, pgprot_t prot)
+static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
+ unsigned long addr, unsigned long end, pgprot_t prot)
{
- unsigned long end;
+ pte_t *pte;
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
+ pte = pte_alloc_map(mm, pmd, addr);
+ if (!pte)
+ return -ENOMEM;
do {
- pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address), prot));
+ pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(addr), prot));
BUG_ON(!pte_none(*pte));
- set_pte(pte, zero_pte);
- address += PAGE_SIZE;
- pte++;
- } while (address && (address < end));
+ set_pte_at(mm, addr, pte, zero_pte);
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+ pte_unmap(pte - 1);
+ return 0;
}
-static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address,
- unsigned long size, pgprot_t prot)
+static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud,
+ unsigned long addr, unsigned long end, pgprot_t prot)
{
- unsigned long base, end;
+ pmd_t *pmd;
+ unsigned long next;
- base = address & PGDIR_MASK;
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return -ENOMEM;
do {
- pte_t * pte = pte_alloc_map(mm, pmd, base + address);
- if (!pte)
+ next = pmd_addr_end(addr, end);
+ if (zeromap_pte_range(mm, pmd, addr, next, prot))
return -ENOMEM;
- zeromap_pte_range(pte, base + address, end - address, prot);
- pte_unmap(pte);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
+ } while (pmd++, addr = next, addr != end);
return 0;
}
-int zeromap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, pgprot_t prot)
+static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long addr, unsigned long end, pgprot_t prot)
{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = address;
- unsigned long end = address + size;
- struct mm_struct *mm = vma->vm_mm;
+ pud_t *pud;
+ unsigned long next;
- dir = pgd_offset(mm, address);
- flush_cache_range(vma, beg, end);
- if (address >= end)
- BUG();
+ pud = pud_alloc(mm, pgd, addr);
+ if (!pud)
+ return -ENOMEM;
+ do {
+ next = pud_addr_end(addr, end);
+ if (zeromap_pmd_range(mm, pud, addr, next, prot))
+ return -ENOMEM;
+ } while (pud++, addr = next, addr != end);
+ return 0;
+}
+int zeromap_page_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long size, pgprot_t prot)
+{
+ pgd_t *pgd;
+ unsigned long next;
+ unsigned long end = addr + size;
+ struct mm_struct *mm = vma->vm_mm;
+ int err;
+
+ BUG_ON(addr >= end);
+ pgd = pgd_offset(mm, addr);
+ flush_cache_range(vma, addr, end);
spin_lock(&mm->page_table_lock);
do {
- pmd_t *pmd = pmd_alloc(mm, dir, address);
- error = -ENOMEM;
- if (!pmd)
- break;
- error = zeromap_pmd_range(mm, pmd, address, end - address, prot);
- if (error)
+ next = pgd_addr_end(addr, end);
+ err = zeromap_pud_range(mm, pgd, addr, next, prot);
+ if (err)
break;
- address = (address + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (address && (address < end));
- /*
- * Why flush? zeromap_pte_range has a BUG_ON for !pte_none()
- */
- flush_tlb_range(vma, beg, end);
+ } while (pgd++, addr = next, addr != end);
spin_unlock(&mm->page_table_lock);
- return error;
+ return err;
}
/*
* mappings are removed. any references to nonexistent pages results
* in null mappings (currently treated as "copy-on-access")
*/
-static inline void remap_pte_range(pte_t * pte, unsigned long address, unsigned long size,
- unsigned long pfn, pgprot_t prot)
+static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ unsigned long pfn, pgprot_t prot)
{
- unsigned long end;
+ pte_t *pte;
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
+ pte = pte_alloc_map(mm, pmd, addr);
+ if (!pte)
+ return -ENOMEM;
do {
BUG_ON(!pte_none(*pte));
if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
- set_pte(pte, pfn_pte(pfn, prot));
- address += PAGE_SIZE;
+ set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
pfn++;
- pte++;
- } while (address && (address < end));
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+ pte_unmap(pte - 1);
+ return 0;
}
-static inline int remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
- unsigned long pfn, pgprot_t prot)
+static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ unsigned long pfn, pgprot_t prot)
{
- unsigned long base, end;
-
- base = address & PGDIR_MASK;
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- pfn -= address >> PAGE_SHIFT;
+ pmd_t *pmd;
+ unsigned long next;
+
+ pfn -= addr >> PAGE_SHIFT;
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return -ENOMEM;
do {
- pte_t * pte = pte_alloc_map(mm, pmd, base + address);
- if (!pte)
+ next = pmd_addr_end(addr, end);
+ if (remap_pte_range(mm, pmd, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot))
return -ENOMEM;
- remap_pte_range(pte, base + address, end - address, pfn + (address >> PAGE_SHIFT), prot);
- pte_unmap(pte);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
+ } while (pmd++, addr = next, addr != end);
+ return 0;
+}
+
+static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long pfn, pgprot_t prot)
+{
+ pud_t *pud;
+ unsigned long next;
+
+ pfn -= addr >> PAGE_SHIFT;
+ pud = pud_alloc(mm, pgd, addr);
+ if (!pud)
+ return -ENOMEM;
+ do {
+ next = pud_addr_end(addr, end);
+ if (remap_pmd_range(mm, pud, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot))
+ return -ENOMEM;
+ } while (pud++, addr = next, addr != end);
return 0;
}
/* Note: this is only safe if the mm semaphore is held when called. */
-int remap_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot)
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = from;
- unsigned long end = from + size;
+ pgd_t *pgd;
+ unsigned long next;
+ unsigned long end = addr + PAGE_ALIGN(size);
struct mm_struct *mm = vma->vm_mm;
-
- pfn -= from >> PAGE_SHIFT;
- dir = pgd_offset(mm, from);
- flush_cache_range(vma, beg, end);
- if (from >= end)
- BUG();
+ int err;
/*
* Physically remapped pages are special. Tell the
* this region.
*/
vma->vm_flags |= VM_IO | VM_RESERVED;
+
+ BUG_ON(addr >= end);
+ pfn -= addr >> PAGE_SHIFT;
+ pgd = pgd_offset(mm, addr);
+ flush_cache_range(vma, addr, end);
spin_lock(&mm->page_table_lock);
do {
- pmd_t *pmd = pmd_alloc(mm, dir, from);
- error = -ENOMEM;
- if (!pmd)
- break;
- error = remap_pmd_range(mm, pmd, from, end - from, pfn + (from >> PAGE_SHIFT), prot);
- if (error)
+ next = pgd_addr_end(addr, end);
+ err = remap_pud_range(mm, pgd, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot);
+ if (err)
break;
- from = (from + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (from && (from < end));
- /*
- * Why flush? remap_pte_range has a BUG_ON for !pte_none()
- */
- flush_tlb_range(vma, beg, end);
+ } while (pgd++, addr = next, addr != end);
spin_unlock(&mm->page_table_lock);
- return error;
+ return err;
}
EXPORT_SYMBOL(remap_pfn_range);
{
pte_t entry;
- flush_cache_page(vma, address);
entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)),
vma);
ptep_establish(vma, address, page_table, entry);
update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
}
/*
int reuse = can_share_swap_page(old_page);
unlock_page(old_page);
if (reuse) {
- flush_cache_page(vma, address);
+ flush_cache_page(vma, address, pfn);
entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)),
vma);
ptep_set_access_flags(vma, address, page_table, entry, 1);
update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
return VM_FAULT_MINOR;
if (unlikely(anon_vma_prepare(vma)))
goto no_new_page;
- new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
- if (!new_page)
- goto no_new_page;
- copy_cow_page(old_page,new_page,address);
-
+ if (old_page == ZERO_PAGE(address)) {
+ new_page = alloc_zeroed_user_highpage(vma, address);
+ if (!new_page)
+ goto no_new_page;
+ } else {
+ new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
+ if (!new_page)
+ goto no_new_page;
+ copy_user_highpage(new_page, old_page, address);
+ }
/*
* Re-check the pte - we dropped the lock
*/
page_table = pte_offset_map(pmd, address);
if (likely(pte_same(*page_table, pte))) {
if (PageAnon(old_page))
- mm->anon_rss--;
+ dec_mm_counter(mm, anon_rss);
if (PageReserved(old_page))
- // ++mm->rss;
- vx_rsspages_inc(mm);
+ inc_mm_counter(mm, rss);
else
page_remove_rmap(old_page);
+ flush_cache_page(vma, address, pfn);
break_cow(vma, new_page, address, page_table);
lru_cache_add_active(new_page);
page_add_anon_rmap(new_page, vma, address);
}
/*
- * Helper function for unmap_mapping_range().
+ * Helper functions for unmap_mapping_range().
+ *
+ * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
+ *
+ * We have to restart searching the prio_tree whenever we drop the lock,
+ * since the iterator is only valid while the lock is held, and anyway
+ * a later vma might be split and reinserted earlier while lock dropped.
+ *
+ * The list of nonlinear vmas could be handled more efficiently, using
+ * a placeholder, but handle it in the same way until a need is shown.
+ * It is important to search the prio_tree before nonlinear list: a vma
+ * may become nonlinear and be shifted from prio_tree to nonlinear list
+ * while the lock is dropped; but never shifted from list to prio_tree.
+ *
+ * In order to make forward progress despite restarting the search,
+ * vm_truncate_count is used to mark a vma as now dealt with, so we can
+ * quickly skip it next time around. Since the prio_tree search only
+ * shows us those vmas affected by unmapping the range in question, we
+ * can't efficiently keep all vmas in step with mapping->truncate_count:
+ * so instead reset them all whenever it wraps back to 0 (then go to 1).
+ * mapping->truncate_count and vma->vm_truncate_count are protected by
+ * i_mmap_lock.
+ *
+ * In order to make forward progress despite repeatedly restarting some
+ * 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.
+ * unmap_mapping_range forces truncate_count to leap over page-aligned
+ * values so we can save vma's restart_addr in its truncate_count field.
*/
-static inline void unmap_mapping_range_list(struct prio_tree_root *root,
+#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
+
+static void reset_vma_truncate_counts(struct address_space *mapping)
+{
+ struct vm_area_struct *vma;
+ struct prio_tree_iter iter;
+
+ vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
+ vma->vm_truncate_count = 0;
+ list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
+ vma->vm_truncate_count = 0;
+}
+
+static int unmap_mapping_range_vma(struct vm_area_struct *vma,
+ unsigned long start_addr, unsigned long end_addr,
+ struct zap_details *details)
+{
+ unsigned long restart_addr;
+ int need_break;
+
+again:
+ restart_addr = vma->vm_truncate_count;
+ if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
+ start_addr = restart_addr;
+ if (start_addr >= end_addr) {
+ /* Top of vma has been split off since last time */
+ vma->vm_truncate_count = details->truncate_count;
+ return 0;
+ }
+ }
+
+ restart_addr = zap_page_range(vma, start_addr,
+ end_addr - start_addr, details);
+
+ /*
+ * We cannot rely on the break test in unmap_vmas:
+ * on the one hand, we don't want to restart our loop
+ * just because that broke out for the page_table_lock;
+ * on the other hand, it does no test when vma is small.
+ */
+ need_break = need_resched() ||
+ need_lockbreak(details->i_mmap_lock);
+
+ 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 = restart_addr;
+ if (!need_break)
+ goto again;
+ }
+
+ spin_unlock(details->i_mmap_lock);
+ cond_resched();
+ spin_lock(details->i_mmap_lock);
+ return -EINTR;
+}
+
+static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
struct zap_details *details)
{
struct vm_area_struct *vma;
struct prio_tree_iter iter;
pgoff_t vba, vea, zba, zea;
+restart:
vma_prio_tree_foreach(vma, &iter, root,
details->first_index, details->last_index) {
+ /* Skip quickly over those we have already dealt with */
+ if (vma->vm_truncate_count == details->truncate_count)
+ continue;
+
vba = vma->vm_pgoff;
vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
zea = details->last_index;
if (zea > vea)
zea = vea;
- zap_page_range(vma,
+
+ if (unmap_mapping_range_vma(vma,
((zba - vba) << PAGE_SHIFT) + vma->vm_start,
- (zea - zba + 1) << PAGE_SHIFT, details);
+ ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
+ details) < 0)
+ goto restart;
+ }
+}
+
+static inline void unmap_mapping_range_list(struct list_head *head,
+ struct zap_details *details)
+{
+ struct vm_area_struct *vma;
+
+ /*
+ * In nonlinear VMAs there is no correspondence between virtual address
+ * offset and file offset. So we must perform an exhaustive search
+ * across *all* the pages in each nonlinear VMA, not just the pages
+ * whose virtual address lies outside the file truncation point.
+ */
+restart:
+ list_for_each_entry(vma, head, shared.vm_set.list) {
+ /* Skip quickly over those we have already dealt with */
+ if (vma->vm_truncate_count == details->truncate_count)
+ continue;
+ details->nonlinear_vma = vma;
+ if (unmap_mapping_range_vma(vma, vma->vm_start,
+ vma->vm_end, details) < 0)
+ goto restart;
}
}
details.nonlinear_vma = NULL;
details.first_index = hba;
details.last_index = hba + hlen - 1;
- details.atomic = 1; /* A spinlock is held */
if (details.last_index < details.first_index)
details.last_index = ULONG_MAX;
+ details.i_mmap_lock = &mapping->i_mmap_lock;
spin_lock(&mapping->i_mmap_lock);
- /* Protect against page fault */
- atomic_inc(&mapping->truncate_count);
-
- if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
- unmap_mapping_range_list(&mapping->i_mmap, &details);
+ /* serialize i_size write against truncate_count write */
+ smp_wmb();
+ /* Protect against page faults, and endless unmapping loops */
+ mapping->truncate_count++;
/*
- * In nonlinear VMAs there is no correspondence between virtual address
- * offset and file offset. So we must perform an exhaustive search
- * across *all* the pages in each nonlinear VMA, not just the pages
- * whose virtual address lies outside the file truncation point.
+ * For archs where spin_lock has inclusive semantics like ia64
+ * this smp_mb() will prevent to read pagetable contents
+ * before the truncate_count increment is visible to
+ * other cpus.
*/
- if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) {
- struct vm_area_struct *vma;
- list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
- shared.vm_set.list) {
- details.nonlinear_vma = vma;
- zap_page_range(vma, vma->vm_start,
- vma->vm_end - vma->vm_start, &details);
- }
+ smp_mb();
+ if (unlikely(is_restart_addr(mapping->truncate_count))) {
+ if (mapping->truncate_count == 0)
+ reset_vma_truncate_counts(mapping);
+ mapping->truncate_count++;
}
+ details.truncate_count = mapping->truncate_count;
+
+ if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
+ unmap_mapping_range_tree(&mapping->i_mmap, &details);
+ if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
+ unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
spin_unlock(&mapping->i_mmap_lock);
}
EXPORT_SYMBOL(unmap_mapping_range);
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. */
if (vm_swap_full())
remove_exclusive_swap_page(page);
- // mm->rss++;
- vx_rsspages_inc(mm);
+ inc_mm_counter(mm, rss);
pte = mk_pte(page, vma->vm_page_prot);
if (write_access && can_share_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
unlock_page(page);
flush_icache_page(vma, page);
- set_pte(page_table, pte);
+ set_pte_at(mm, address, page_table, pte);
page_add_anon_rmap(page, vma, address);
if (write_access) {
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
+ lazy_mmu_prot_update(pte);
pte_unmap(page_table);
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;
}
/*
pte_unmap(page_table);
spin_unlock(&mm->page_table_lock);
- if (unlikely(anon_vma_prepare(vma)))
- goto no_mem;
if (!vx_rsspages_avail(mm, 1))
goto no_mem;
-
- page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
+ if (unlikely(anon_vma_prepare(vma)))
+ goto no_mem;
+ page = alloc_zeroed_user_highpage(vma, addr);
if (!page)
goto no_mem;
- clear_user_highpage(page, addr);
spin_lock(&mm->page_table_lock);
page_table = pte_offset_map(pmd, addr);
spin_unlock(&mm->page_table_lock);
goto out;
}
- // mm->rss++;
- vx_rsspages_inc(mm);
+ inc_mm_counter(mm, rss);
entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
vma->vm_page_prot)),
vma);
lru_cache_add_active(page);
- mark_page_accessed(page);
+ SetPageReferenced(page);
page_add_anon_rmap(page, vma, addr);
}
- set_pte(page_table, entry);
+ set_pte_at_new(mm, addr, page_table, entry);
pte_unmap(page_table);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, addr, entry);
+ lazy_mmu_prot_update(entry);
spin_unlock(&mm->page_table_lock);
out:
return VM_FAULT_MINOR;
struct page * new_page;
struct address_space *mapping = NULL;
pte_t entry;
- int sequence = 0;
+ unsigned int sequence = 0;
int ret = VM_FAULT_MINOR;
int anon = 0;
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
- sequence = atomic_read(&mapping->truncate_count);
+ sequence = mapping->truncate_count;
+ smp_rmb(); /* serializes i_size against truncate_count */
}
- smp_rmb(); /* Prevent CPU from reordering lock-free ->nopage() */
retry:
+ cond_resched();
+ /* FIXME: is that check useful here? */
+ if (!vx_rsspages_avail(mm, 1))
+ return VM_FAULT_OOM;
new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
+ /*
+ * No smp_rmb is needed here as long as there's a full
+ * spin_lock/unlock sequence inside the ->nopage callback
+ * (for the pagecache lookup) that acts as an implicit
+ * smp_mb() and prevents the i_size read to happen
+ * after the next truncate_count read.
+ */
/* no page was available -- either SIGBUS or OOM */
if (new_page == NOPAGE_SIGBUS)
* invalidated this page. If unmap_mapping_range got called,
* retry getting the page.
*/
- if (mapping &&
- (unlikely(sequence != atomic_read(&mapping->truncate_count)))) {
- sequence = atomic_read(&mapping->truncate_count);
+ if (mapping && unlikely(sequence != mapping->truncate_count)) {
+ sequence = mapping->truncate_count;
spin_unlock(&mm->page_table_lock);
page_cache_release(new_page);
goto retry;
/* Only go through if we didn't race with anybody else... */
if (pte_none(*page_table)) {
if (!PageReserved(new_page))
- // ++mm->rss;
- vx_rsspages_inc(mm);
+ inc_mm_counter(mm, rss);
+
flush_icache_page(vma, new_page);
entry = mk_pte(new_page, vma->vm_page_prot);
if (write_access)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- set_pte(page_table, entry);
+ set_pte_at_new(mm, address, page_table, entry);
if (anon) {
lru_cache_add_active(new_page);
page_add_anon_rmap(new_page, vma, address);
/* no need to invalidate: a not-present page shouldn't be cached */
update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
spin_unlock(&mm->page_table_lock);
out:
return ret;
*/
if (!vma->vm_ops || !vma->vm_ops->populate ||
(write_access && !(vma->vm_flags & VM_SHARED))) {
- pte_clear(pte);
+ pte_clear(mm, address, pte);
return do_no_page(mm, vma, address, write_access, pte, pmd);
}
entry = pte_mkyoung(entry);
ptep_set_access_flags(vma, address, pte, entry, write_access);
update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
pte_unmap(pte);
spin_unlock(&mm->page_table_lock);
return VM_FAULT_MINOR;
* By the time we get here, we already hold the mm semaphore
*/
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
- unsigned long address, int write_access)
+ unsigned long address, int write_access)
{
pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
+ pte_t *pte;
__set_current_state(TASK_RUNNING);
- pgd = pgd_offset(mm, address);
inc_page_state(pgfault);
* We need the page table lock to synchronize with kswapd
* and the SMP-safe atomic PTE updates.
*/
+ pgd = pgd_offset(mm, address);
spin_lock(&mm->page_table_lock);
- pmd = pmd_alloc(mm, pgd, address);
- if (pmd) {
- pte_t * pte = pte_alloc_map(mm, pmd, address);
- if (pte)
- return handle_pte_fault(mm, vma, address, write_access, pte, pmd);
- }
+ pud = pud_alloc(mm, pgd, address);
+ if (!pud)
+ goto oom;
+
+ pmd = pmd_alloc(mm, pud, address);
+ if (!pmd)
+ goto oom;
+
+ pte = pte_alloc_map(mm, pmd, address);
+ if (!pte)
+ goto oom;
+
+ return handle_pte_fault(mm, vma, address, write_access, pte, pmd);
+
+ oom:
spin_unlock(&mm->page_table_lock);
return VM_FAULT_OOM;
}
+#ifndef __PAGETABLE_PUD_FOLDED
/*
- * Allocate page middle directory.
+ * Allocate page upper directory.
*
* We've already handled the fast-path in-line, and we own the
* page table lock.
+ */
+pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+ pud_t *new;
+
+ spin_unlock(&mm->page_table_lock);
+ new = pud_alloc_one(mm, address);
+ spin_lock(&mm->page_table_lock);
+ if (!new)
+ return NULL;
+
+ /*
+ * Because we dropped the lock, we should re-check the
+ * entry, as somebody else could have populated it..
+ */
+ if (pgd_present(*pgd)) {
+ pud_free(new);
+ goto out;
+ }
+ pgd_populate(mm, pgd, new);
+ out:
+ return pud_offset(pgd, address);
+}
+#endif /* __PAGETABLE_PUD_FOLDED */
+
+#ifndef __PAGETABLE_PMD_FOLDED
+/*
+ * Allocate page middle directory.
*
- * On a two-level page table, this ends up actually being entirely
- * optimized away.
+ * We've already handled the fast-path in-line, and we own the
+ * page table lock.
*/
-pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
pmd_t *new;
* Because we dropped the lock, we should re-check the
* entry, as somebody else could have populated it..
*/
- if (pgd_present(*pgd)) {
+#ifndef __ARCH_HAS_4LEVEL_HACK
+ if (pud_present(*pud)) {
pmd_free(new);
goto out;
}
- pgd_populate(mm, pgd, new);
-out:
- return pmd_offset(pgd, address);
+ pud_populate(mm, pud, new);
+#else
+ if (pgd_present(*pud)) {
+ pmd_free(new);
+ goto out;
+ }
+ pgd_populate(mm, pud, new);
+#endif /* __ARCH_HAS_4LEVEL_HACK */
+
+ out:
+ return pmd_offset(pud, address);
}
+#endif /* __PAGETABLE_PMD_FOLDED */
int make_pages_present(unsigned long addr, unsigned long end)
{
unsigned long addr = (unsigned long) vmalloc_addr;
struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
+ pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
if (!pgd_none(*pgd)) {
- pmd = pmd_offset(pgd, addr);
- if (!pmd_none(*pmd)) {
- ptep = pte_offset_map(pmd, addr);
- pte = *ptep;
- if (pte_present(pte))
- page = pte_page(pte);
- pte_unmap(ptep);
+ pud = pud_offset(pgd, addr);
+ if (!pud_none(*pud)) {
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_none(*pmd)) {
+ ptep = pte_offset_map(pmd, addr);
+ pte = *ptep;
+ if (pte_present(pte))
+ page = pte_page(pte);
+ pte_unmap(ptep);
+ }
}
}
return page;
EXPORT_SYMBOL(vmalloc_to_pfn);
-#if !defined(CONFIG_ARCH_GATE_AREA)
+/*
+ * update_mem_hiwater
+ * - update per process rss and vm high water data
+ */
+void update_mem_hiwater(struct task_struct *tsk)
+{
+ if (tsk->mm) {
+ unsigned long rss = get_mm_counter(tsk->mm, rss);
+
+ if (tsk->mm->hiwater_rss < rss)
+ tsk->mm->hiwater_rss = rss;
+ if (tsk->mm->hiwater_vm < tsk->mm->total_vm)
+ tsk->mm->hiwater_vm = tsk->mm->total_vm;
+ }
+}
+
+#if !defined(__HAVE_ARCH_GATE_AREA)
#if defined(AT_SYSINFO_EHDR)
struct vm_area_struct gate_vma;
#endif
}
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area_no_task(unsigned long addr)
{
#ifdef AT_SYSINFO_EHDR
if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
return 0;
}
-#endif
+#endif /* __HAVE_ARCH_GATE_AREA */
git://git.onelab.eu / linux-2.6.git / blobdiff