Merge branch 'next' into for-linus

Prepare input updates for 5.17 merge window.

1 files changed, 72 insertions, 3 deletions

diff --git a/mm/util.c b/mm/util.c
index a8bf17f18a81..bacabe446906 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -593,6 +593,10 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	if (ret || size <= PAGE_SIZE)
 		return ret;
 
+	/* Don't even allow crazy sizes */
+	if (WARN_ON_ONCE(size > INT_MAX))
+		return NULL;
+
 	return __vmalloc_node(size, 1, flags, node,
 			__builtin_return_address(0));
 }
@@ -635,6 +639,21 @@ void kvfree_sensitive(const void *addr, size_t len)
 }
 EXPORT_SYMBOL(kvfree_sensitive);
 
+void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
+{
+	void *newp;
+
+	if (oldsize >= newsize)
+		return (void *)p;
+	newp = kvmalloc(newsize, flags);
+	if (!newp)
+		return NULL;
+	memcpy(newp, p, oldsize);
+	kvfree(p);
+	return newp;
+}
+EXPORT_SYMBOL(kvrealloc);
+
 static inline void *__page_rmapping(struct page *page)
 {
 	unsigned long mapping;
@@ -731,6 +750,16 @@ int __page_mapcount(struct page *page)
 }
 EXPORT_SYMBOL_GPL(__page_mapcount);
 
+void copy_huge_page(struct page *dst, struct page *src)
+{
+	unsigned i, nr = compound_nr(src);
+
+	for (i = 0; i < nr; i++) {
+		cond_resched();
+		copy_highpage(nth_page(dst, i), nth_page(src, i));
+	}
+}
+
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
 int sysctl_overcommit_ratio __read_mostly = 50;
 unsigned long sysctl_overcommit_kbytes __read_mostly;
@@ -758,7 +787,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
-	int new_policy;
+	int new_policy = -1;
 	int ret;
 
 	/*
@@ -776,7 +805,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
 		t = *table;
 		t.data = &new_policy;
 		ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
-		if (ret)
+		if (ret || new_policy == -1)
 			return ret;
 
 		mm_compute_batch(new_policy);
@@ -983,7 +1012,7 @@ int __weak memcmp_pages(struct page *page1, struct page *page2)
  * depends on the type of object and on how much debugging is enabled.
  * For example, for a slab-cache object, the slab name is printed, and,
  * if available, the return address and stack trace from the allocation
- * of that object.
+ * and last free path of that object.
  */
 void mem_dump_obj(void *object)
 {
@@ -1010,3 +1039,43 @@ void mem_dump_obj(void *object)
 }
 EXPORT_SYMBOL_GPL(mem_dump_obj);
 #endif
+
+/*
+ * A driver might set a page logically offline -- PageOffline() -- and
+ * turn the page inaccessible in the hypervisor; after that, access to page
+ * content can be fatal.
+ *
+ * Some special PFN walkers -- i.e., /proc/kcore -- read content of random
+ * pages after checking PageOffline(); however, these PFN walkers can race
+ * with drivers that set PageOffline().
+ *
+ * page_offline_freeze()/page_offline_thaw() allows for a subsystem to
+ * synchronize with such drivers, achieving that a page cannot be set
+ * PageOffline() while frozen.
+ *
+ * page_offline_begin()/page_offline_end() is used by drivers that care about
+ * such races when setting a page PageOffline().
+ */
+static DECLARE_RWSEM(page_offline_rwsem);
+
+void page_offline_freeze(void)
+{
+	down_read(&page_offline_rwsem);
+}
+
+void page_offline_thaw(void)
+{
+	up_read(&page_offline_rwsem);
+}
+
+void page_offline_begin(void)
+{
+	down_write(&page_offline_rwsem);
+}
+EXPORT_SYMBOL(page_offline_begin);
+
+void page_offline_end(void)
+{
+	up_write(&page_offline_rwsem);
+}
+EXPORT_SYMBOL(page_offline_end);