1 files changed, 73 insertions, 56 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index c1f2ea4a0b99..7f855206e7fb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -70,7 +70,7 @@ static void unmap_region(struct mm_struct *mm,
  * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
  *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
  *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
- *		
+ *
  * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
  *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
  *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
@@ -89,6 +89,25 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags)
 }
 EXPORT_SYMBOL(vm_get_page_prot);
 
+static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
+{
+	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
+}
+
+/* Update vma->vm_page_prot to reflect vma->vm_flags. */
+void vma_set_page_prot(struct vm_area_struct *vma)
+{
+	unsigned long vm_flags = vma->vm_flags;
+
+	vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
+	if (vma_wants_writenotify(vma)) {
+		vm_flags &= ~VM_SHARED;
+		vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot,
+						     vm_flags);
+	}
+}
+
+
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio __read_mostly = 50;	/* default is 50% */
 unsigned long sysctl_overcommit_kbytes __read_mostly;
@@ -268,7 +287,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len);
 
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
-	unsigned long rlim, retval;
+	unsigned long retval;
 	unsigned long newbrk, oldbrk;
 	struct mm_struct *mm = current->mm;
 	unsigned long min_brk;
@@ -298,9 +317,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	 * segment grow beyond its set limit the in case where the limit is
 	 * not page aligned -Ram Gupta
 	 */
-	rlim = rlimit(RLIMIT_DATA);
-	if (rlim < RLIM_INFINITY && (brk - mm->start_brk) +
-			(mm->end_data - mm->start_data) > rlim)
+	if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk,
+			      mm->end_data, mm->start_data))
 		goto out;
 
 	newbrk = PAGE_ALIGN(brk);
@@ -369,20 +387,22 @@ static int browse_rb(struct rb_root *root)
 		struct vm_area_struct *vma;
 		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
 		if (vma->vm_start < prev) {
-			pr_info("vm_start %lx prev %lx\n", vma->vm_start, prev);
+			pr_emerg("vm_start %lx < prev %lx\n",
+				  vma->vm_start, prev);
 			bug = 1;
 		}
 		if (vma->vm_start < pend) {
-			pr_info("vm_start %lx pend %lx\n", vma->vm_start, pend);
+			pr_emerg("vm_start %lx < pend %lx\n",
+				  vma->vm_start, pend);
 			bug = 1;
 		}
 		if (vma->vm_start > vma->vm_end) {
-			pr_info("vm_end %lx < vm_start %lx\n",
-				vma->vm_end, vma->vm_start);
+			pr_emerg("vm_start %lx > vm_end %lx\n",
+				  vma->vm_start, vma->vm_end);
 			bug = 1;
 		}
 		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
-			pr_info("free gap %lx, correct %lx\n",
+			pr_emerg("free gap %lx, correct %lx\n",
 			       vma->rb_subtree_gap,
 			       vma_compute_subtree_gap(vma));
 			bug = 1;
@@ -396,7 +416,7 @@ static int browse_rb(struct rb_root *root)
 	for (nd = pn; nd; nd = rb_prev(nd))
 		j++;
 	if (i != j) {
-		pr_info("backwards %d, forwards %d\n", j, i);
+		pr_emerg("backwards %d, forwards %d\n", j, i);
 		bug = 1;
 	}
 	return bug ? -1 : i;
@@ -409,8 +429,9 @@ static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
 	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct vm_area_struct *vma;
 		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
-		BUG_ON(vma != ignore &&
-		       vma->rb_subtree_gap != vma_compute_subtree_gap(vma));
+		VM_BUG_ON_VMA(vma != ignore &&
+			vma->rb_subtree_gap != vma_compute_subtree_gap(vma),
+			vma);
 	}
 }
 
@@ -420,8 +441,10 @@ static void validate_mm(struct mm_struct *mm)
 	int i = 0;
 	unsigned long highest_address = 0;
 	struct vm_area_struct *vma = mm->mmap;
+
 	while (vma) {
 		struct anon_vma_chain *avc;
+
 		vma_lock_anon_vma(vma);
 		list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
 			anon_vma_interval_tree_verify(avc);
@@ -431,20 +454,21 @@ static void validate_mm(struct mm_struct *mm)
 		i++;
 	}
 	if (i != mm->map_count) {
-		pr_info("map_count %d vm_next %d\n", mm->map_count, i);
+		pr_emerg("map_count %d vm_next %d\n", mm->map_count, i);
 		bug = 1;
 	}
 	if (highest_address != mm->highest_vm_end) {
-		pr_info("mm->highest_vm_end %lx, found %lx\n",
-		       mm->highest_vm_end, highest_address);
+		pr_emerg("mm->highest_vm_end %lx, found %lx\n",
+			  mm->highest_vm_end, highest_address);
 		bug = 1;
 	}
 	i = browse_rb(&mm->mm_rb);
 	if (i != mm->map_count) {
-		pr_info("map_count %d rb %d\n", mm->map_count, i);
+		if (i != -1)
+			pr_emerg("map_count %d rb %d\n", mm->map_count, i);
 		bug = 1;
 	}
-	BUG_ON(bug);
+	VM_BUG_ON_MM(bug, mm);
 }
 #else
 #define validate_mm_rb(root, ignore) do { } while (0)
@@ -741,7 +765,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 			 * split_vma inserting another: so it must be
 			 * mprotect case 4 shifting the boundary down.
 			 */
-			adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
+			adjust_next = -((vma->vm_end - end) >> PAGE_SHIFT);
 			exporter = vma;
 			importer = next;
 		}
@@ -787,8 +811,8 @@ again:			remove_next = 1 + (end > next->vm_end);
 	if (!anon_vma && adjust_next)
 		anon_vma = next->anon_vma;
 	if (anon_vma) {
-		VM_BUG_ON(adjust_next && next->anon_vma &&
-			  anon_vma != next->anon_vma);
+		VM_BUG_ON_VMA(adjust_next && next->anon_vma &&
+			  anon_vma != next->anon_vma, next);
 		anon_vma_lock_write(anon_vma);
 		anon_vma_interval_tree_pre_update_vma(vma);
 		if (adjust_next)
@@ -1010,7 +1034,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
 struct vm_area_struct *vma_merge(struct mm_struct *mm,
 			struct vm_area_struct *prev, unsigned long addr,
 			unsigned long end, unsigned long vm_flags,
-		     	struct anon_vma *anon_vma, struct file *file,
+			struct anon_vma *anon_vma, struct file *file,
 			pgoff_t pgoff, struct mempolicy *policy)
 {
 	pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
@@ -1036,7 +1060,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	 * Can it merge with the predecessor?
 	 */
 	if (prev && prev->vm_end == addr &&
-  			mpol_equal(vma_policy(prev), policy) &&
+			mpol_equal(vma_policy(prev), policy) &&
 			can_vma_merge_after(prev, vm_flags,
 						anon_vma, file, pgoff)) {
 		/*
@@ -1064,7 +1088,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	 * Can this new request be merged in front of next?
 	 */
 	if (next && end == next->vm_start &&
- 			mpol_equal(policy, vma_policy(next)) &&
+			mpol_equal(policy, vma_policy(next)) &&
 			can_vma_merge_before(next, vm_flags,
 					anon_vma, file, pgoff+pglen)) {
 		if (prev && addr < prev->vm_end)	/* case 4 */
@@ -1235,7 +1259,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long flags, unsigned long pgoff,
 			unsigned long *populate)
 {
-	struct mm_struct * mm = current->mm;
+	struct mm_struct *mm = current->mm;
 	vm_flags_t vm_flags;
 
 	*populate = 0;
@@ -1263,7 +1287,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 
 	/* offset overflow? */
 	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
-               return -EOVERFLOW;
+		return -EOVERFLOW;
 
 	/* Too many mappings? */
 	if (mm->map_count > sysctl_max_map_count)
@@ -1470,11 +1494,16 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
 		return 1;
 
-	/* The open routine did something to the protections already? */
+	/* The open routine did something to the protections that pgprot_modify
+	 * won't preserve? */
 	if (pgprot_val(vma->vm_page_prot) !=
-	    pgprot_val(vm_get_page_prot(vm_flags)))
+	    pgprot_val(vm_pgprot_modify(vma->vm_page_prot, vm_flags)))
 		return 0;
 
+	/* Do we need to track softdirty? */
+	if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY))
+		return 1;
+
 	/* Specialty mapping? */
 	if (vm_flags & VM_PFNMAP)
 		return 0;
@@ -1610,21 +1639,6 @@ munmap_back:
 			goto free_vma;
 	}
 
-	if (vma_wants_writenotify(vma)) {
-		pgprot_t pprot = vma->vm_page_prot;
-
-		/* Can vma->vm_page_prot have changed??
-		 *
-		 * Answer: Yes, drivers may have changed it in their
-		 *         f_op->mmap method.
-		 *
-		 * Ensures that vmas marked as uncached stay that way.
-		 */
-		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
-		if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
-			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	}
-
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	/* Once vma denies write, undo our temporary denial count */
 	if (file) {
@@ -1658,6 +1672,8 @@ out:
 	 */
 	vma->vm_flags |= VM_SOFTDIRTY;
 
+	vma_set_page_prot(vma);
+
 	return addr;
 
 unmap_and_free_vma:
@@ -1921,7 +1937,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.align_mask = 0;
 	return vm_unmapped_area(&info);
 }
-#endif	
+#endif
 
 /*
  * This mmap-allocator allocates new areas top-down from below the
@@ -2321,13 +2337,13 @@ int expand_stack(struct vm_area_struct *vma, unsigned long address)
 }
 
 struct vm_area_struct *
-find_extend_vma(struct mm_struct * mm, unsigned long addr)
+find_extend_vma(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct * vma;
+	struct vm_area_struct *vma;
 	unsigned long start;
 
 	addr &= PAGE_MASK;
-	vma = find_vma(mm,addr);
+	vma = find_vma(mm, addr);
 	if (!vma)
 		return NULL;
 	if (vma->vm_start <= addr)
@@ -2376,7 +2392,7 @@ static void unmap_region(struct mm_struct *mm,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
 		unsigned long start, unsigned long end)
 {
-	struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
+	struct vm_area_struct *next = prev ? prev->vm_next : mm->mmap;
 	struct mmu_gather tlb;
 
 	lru_add_drain();
@@ -2423,7 +2439,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
  * __split_vma() bypasses sysctl_max_map_count checking.  We use this on the
  * munmap path where it doesn't make sense to fail.
  */
-static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	      unsigned long addr, int new_below)
 {
 	struct vm_area_struct *new;
@@ -2512,7 +2528,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
 		return -EINVAL;
 
-	if ((len = PAGE_ALIGN(len)) == 0)
+	len = PAGE_ALIGN(len);
+	if (len == 0)
 		return -EINVAL;
 
 	/* Find the first overlapping VMA */
@@ -2558,7 +2575,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 		if (error)
 			return error;
 	}
-	vma = prev? prev->vm_next: mm->mmap;
+	vma = prev ? prev->vm_next : mm->mmap;
 
 	/*
 	 * unlock any mlock()ed ranges before detaching vmas
@@ -2621,10 +2638,10 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  */
 static unsigned long do_brk(unsigned long addr, unsigned long len)
 {
-	struct mm_struct * mm = current->mm;
-	struct vm_area_struct * vma, * prev;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma, *prev;
 	unsigned long flags;
-	struct rb_node ** rb_link, * rb_parent;
+	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
@@ -2848,7 +2865,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			 * safe. It is only safe to keep the vm_pgoff
 			 * linear if there are no pages mapped yet.
 			 */
-			VM_BUG_ON(faulted_in_anon_vma);
+			VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma);
 			*vmap = vma = new_vma;
 		}
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
@@ -3196,7 +3213,7 @@ void __init mmap_init(void)
 {
 	int ret;
 
-	ret = percpu_counter_init(&vm_committed_as, 0);
+	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
 	VM_BUG_ON(ret);
 }