[Devel,RHEL7,COMMIT] ms/mm: drop support of non-linear mapping from fault codepath

Submitted by Kirill Tkhai on Oct. 3, 2016, 2:32 p.m.

Details

Message ID 201610031432.u93EWwEX008939@pro
State New
Series "replace remap_file_pages() syscall with emulation"
Headers show

Commit Message

Kirill Tkhai Oct. 3, 2016, 2:32 p.m.
The commit is pushed to "branch-rh7-3.10.0-327.36.1.vz7.18.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.36.1.vz7.18.3
------>
commit 79aedb341a6dde7836c90503ccf86e074bd3a173
Author: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Date:   Mon Oct 3 14:31:58 2016 +0000

    ms/mm: drop support of non-linear mapping from fault codepath
    
    We don't create non-linear mappings anymore.  Let's drop code which
    handles them on page fault.
    
    Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
    
    https://jira.sw.ru/browse/PSBM-52992
    
    (cherry picked from commit 9b4bdd2ffab9557ac43af7dff02e7dab1c8c58bd)
    Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
    Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
---
 include/linux/mm.h | 16 +++++++---------
 mm/memory.c        | 52 +++++++---------------------------------------------
 2 files changed, 14 insertions(+), 54 deletions(-)

Patch hide | download patch | download mbox

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2acaa83..6d49c59 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -194,21 +194,19 @@  extern unsigned int kobjsize(const void *objp);
 extern pgprot_t protection_map[16];
 
 #define FAULT_FLAG_WRITE	0x01	/* Fault was a write access */
-#define FAULT_FLAG_NONLINEAR	0x02	/* Fault was via a nonlinear mapping */
-#define FAULT_FLAG_MKWRITE	0x04	/* Fault was mkwrite of existing pte */
-#define FAULT_FLAG_ALLOW_RETRY	0x08	/* Retry fault if blocking */
-#define FAULT_FLAG_RETRY_NOWAIT	0x10	/* Don't drop mmap_sem and wait when retrying */
-#define FAULT_FLAG_KILLABLE	0x20	/* The fault task is in SIGKILL killable region */
-#define FAULT_FLAG_TRIED	0x40	/* second try */
-#define FAULT_FLAG_USER		0x80	/* The fault originated in userspace */
+#define FAULT_FLAG_MKWRITE	0x02	/* Fault was mkwrite of existing pte */
+#define FAULT_FLAG_ALLOW_RETRY	0x04	/* Retry fault if blocking */
+#define FAULT_FLAG_RETRY_NOWAIT	0x08	/* Don't drop mmap_sem and wait when retrying */
+#define FAULT_FLAG_KILLABLE	0x10	/* The fault task is in SIGKILL killable region */
+#define FAULT_FLAG_TRIED	0x20	/* Second try */
+#define FAULT_FLAG_USER		0x40	/* The fault originated in userspace */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
- * pgoff should be used in favour of virtual_address, if possible. If pgoff
- * is used, one may implement ->remap_pages to get nonlinear mapping support.
+ * pgoff should be used in favour of virtual_address, if possible.
  */
 struct vm_fault {
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
diff --git a/mm/memory.c b/mm/memory.c
index 59c8701..e93aa91 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2729,12 +2729,11 @@  int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 EXPORT_SYMBOL_GPL(apply_to_page_range);
 
 /*
- * handle_pte_fault chooses page fault handler according to an entry
- * which was read non-atomically.  Before making any commitment, on
- * those architectures or configurations (e.g. i386 with PAE) which
- * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault
- * must check under lock before unmapping the pte and proceeding
- * (but do_wp_page is only called after already making such a check;
+ * handle_pte_fault chooses page fault handler according to an entry which was
+ * read non-atomically.  Before making any commitment, on those architectures
+ * or configurations (e.g. i386 with PAE) which might give a mix of unmatched
+ * parts, do_swap_page must check under lock before unmapping the pte and
+ * proceeding (but do_wp_page is only called after already making such a check;
  * and do_anonymous_page can safely check later on).
  */
 static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
@@ -3627,8 +3626,6 @@  static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		entry = mk_pte(page, vma->vm_page_prot);
 		if (flags & FAULT_FLAG_WRITE)
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-		else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
-			entry = pte_mksoft_dirty(entry);
 		if (anon) {
 			inc_mm_counter_fast(mm, MM_ANONPAGES);
 			page_add_new_anon_rmap(page, vma, address);
@@ -3694,7 +3691,7 @@  uncharge_out:
 	return ret;
 }
 
-static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
 		unsigned int flags, pte_t orig_pte)
 {
@@ -3708,38 +3705,6 @@  static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
-/*
- * Fault of a previously existing named mapping. Repopulate the pte
- * from the encoded file_pte if possible. This enables swappable
- * nonlinear vmas.
- *
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
- */
-static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		unsigned int flags, pte_t orig_pte)
-{
-	pgoff_t pgoff;
-
-	flags |= FAULT_FLAG_NONLINEAR;
-
-	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
-		return 0;
-
-	if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
-		/*
-		 * Page table corrupted: show pte and kill process.
-		 */
-		print_bad_pte(vma, address, orig_pte, NULL);
-		return VM_FAULT_SIGBUS;
-	}
-
-	pgoff = pte_to_pgoff(orig_pte);
-	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
-}
-
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
 				unsigned long addr, int page_nid,
 				int *flags)
@@ -3854,14 +3819,11 @@  static int handle_pte_fault(struct mm_struct *mm,
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
 			if (vma->vm_ops)
-				return do_linear_fault(mm, vma, address,
+				return do_fault(mm, vma, address,
 						pte, pmd, flags, entry);
 			return do_anonymous_page(mm, vma, address,
 						 pte, pmd, flags);
 		}
-		if (pte_file(entry))
-			return do_nonlinear_fault(mm, vma, address,
-					pte, pmd, flags, entry);
 		return do_swap_page(mm, vma, address,
 					pte, pmd, flags, entry);
 	}