1 files changed, 109 insertions, 127 deletions

diff --git a/mm/util.c b/mm/util.c
index f7bc2096071c..fec39d4509a9 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1,6 +1,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/err.h>
 #include <linux/sched.h>
@@ -9,14 +10,12 @@
 #include <linux/swapops.h>
 #include <linux/mman.h>
 #include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
 
 #include <asm/uaccess.h>
 
 #include "internal.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/kmem.h>
-
 /**
  * kstrdup - allocate space for and copy an existing string
  * @s: the string to duplicate
@@ -110,97 +109,6 @@ void *memdup_user(const void __user *src, size_t len)
 }
 EXPORT_SYMBOL(memdup_user);
 
-static __always_inline void *__do_krealloc(const void *p, size_t new_size,
-					   gfp_t flags)
-{
-	void *ret;
-	size_t ks = 0;
-
-	if (p)
-		ks = ksize(p);
-
-	if (ks >= new_size)
-		return (void *)p;
-
-	ret = kmalloc_track_caller(new_size, flags);
-	if (ret && p)
-		memcpy(ret, p, ks);
-
-	return ret;
-}
-
-/**
- * __krealloc - like krealloc() but don't free @p.
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * This function is like krealloc() except it never frees the originally
- * allocated buffer. Use this if you don't want to free the buffer immediately
- * like, for example, with RCU.
- */
-void *__krealloc(const void *p, size_t new_size, gfp_t flags)
-{
-	if (unlikely(!new_size))
-		return ZERO_SIZE_PTR;
-
-	return __do_krealloc(p, new_size, flags);
-
-}
-EXPORT_SYMBOL(__krealloc);
-
-/**
- * krealloc - reallocate memory. The contents will remain unchanged.
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * The contents of the object pointed to are preserved up to the
- * lesser of the new and old sizes.  If @p is %NULL, krealloc()
- * behaves exactly like kmalloc().  If @new_size is 0 and @p is not a
- * %NULL pointer, the object pointed to is freed.
- */
-void *krealloc(const void *p, size_t new_size, gfp_t flags)
-{
-	void *ret;
-
-	if (unlikely(!new_size)) {
-		kfree(p);
-		return ZERO_SIZE_PTR;
-	}
-
-	ret = __do_krealloc(p, new_size, flags);
-	if (ret && p != ret)
-		kfree(p);
-
-	return ret;
-}
-EXPORT_SYMBOL(krealloc);
-
-/**
- * kzfree - like kfree but zero memory
- * @p: object to free memory of
- *
- * The memory of the object @p points to is zeroed before freed.
- * If @p is %NULL, kzfree() does nothing.
- *
- * Note: this function zeroes the whole allocated buffer which can be a good
- * deal bigger than the requested buffer size passed to kmalloc(). So be
- * careful when using this function in performance sensitive code.
- */
-void kzfree(const void *p)
-{
-	size_t ks;
-	void *mem = (void *)p;
-
-	if (unlikely(ZERO_OR_NULL_PTR(mem)))
-		return;
-	ks = ksize(mem);
-	memset(mem, 0, ks);
-	kfree(mem);
-}
-EXPORT_SYMBOL(kzfree);
-
 /*
  * strndup_user - duplicate an existing string from user space
  * @s: The string to duplicate
@@ -262,35 +170,25 @@ static int vm_is_stack_for_task(struct task_struct *t,
 /*
  * Check if the vma is being used as a stack.
  * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the pid of the task that
- * the vma is stack for.
+ * just check in the current task. Returns the task_struct of the task
+ * that the vma is stack for. Must be called under rcu_read_lock().
  */
-pid_t vm_is_stack(struct task_struct *task,
-		  struct vm_area_struct *vma, int in_group)
+struct task_struct *task_of_stack(struct task_struct *task,
+				struct vm_area_struct *vma, bool in_group)
 {
-	pid_t ret = 0;
-
 	if (vm_is_stack_for_task(task, vma))
-		return task->pid;
+		return task;
 
 	if (in_group) {
 		struct task_struct *t;
-		rcu_read_lock();
-		if (!pid_alive(task))
-			goto done;
-
-		t = task;
-		do {
-			if (vm_is_stack_for_task(t, vma)) {
-				ret = t->pid;
-				goto done;
-			}
-		} while_each_thread(task, t);
-done:
-		rcu_read_unlock();
+
+		for_each_thread(task, t) {
+			if (vm_is_stack_for_task(t, vma))
+				return t;
+		}
 	}
 
-	return ret;
+	return NULL;
 }
 
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
@@ -307,7 +205,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
  * If the architecture not support this function, simply return with no
  * page pinned
  */
-int __attribute__((weak)) __get_user_pages_fast(unsigned long start,
+int __weak __get_user_pages_fast(unsigned long start,
 				 int nr_pages, int write, struct page **pages)
 {
 	return 0;
@@ -338,7 +236,7 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast);
  * callers need to carefully consider what to use. On many architectures,
  * get_user_pages_fast simply falls back to get_user_pages.
  */
-int __attribute__((weak)) get_user_pages_fast(unsigned long start,
+int __weak get_user_pages_fast(unsigned long start,
 				int nr_pages, int write, struct page **pages)
 {
 	struct mm_struct *mm = current->mm;
@@ -386,11 +284,23 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_mmap);
 
+void kvfree(const void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		vfree(addr);
+	else
+		kfree(addr);
+}
+EXPORT_SYMBOL(kvfree);
+
 struct address_space *page_mapping(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 
-	VM_BUG_ON(PageSlab(page));
+	/* This happens if someone calls flush_dcache_page on slab page */
+	if (unlikely(PageSlab(page)))
+		return NULL;
+
 	if (unlikely(PageSwapCache(page))) {
 		swp_entry_t entry;
 
@@ -401,20 +311,92 @@ struct address_space *page_mapping(struct page *page)
 	return mapping;
 }
 
+int overcommit_ratio_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_kbytes = 0;
+	return ret;
+}
+
+int overcommit_kbytes_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_ratio = 0;
+	return ret;
+}
+
 /*
  * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
  */
 unsigned long vm_commit_limit(void)
 {
-	return ((totalram_pages - hugetlb_total_pages())
-		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+	unsigned long allowed;
+
+	if (sysctl_overcommit_kbytes)
+		allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
+	else
+		allowed = ((totalram_pages - hugetlb_total_pages())
+			   * sysctl_overcommit_ratio / 100);
+	allowed += total_swap_pages;
+
+	return allowed;
 }
 
+/**
+ * get_cmdline() - copy the cmdline value to a buffer.
+ * @task:     the task whose cmdline value to copy.
+ * @buffer:   the buffer to copy to.
+ * @buflen:   the length of the buffer. Larger cmdline values are truncated
+ *            to this length.
+ * Returns the size of the cmdline field copied. Note that the copy does
+ * not guarantee an ending NULL byte.
+ */
+int get_cmdline(struct task_struct *task, char *buffer, int buflen)
+{
+	int res = 0;
+	unsigned int len;
+	struct mm_struct *mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+	if (!mm->arg_end)
+		goto out_mm;	/* Shh! No looking before we're done */
+
+	len = mm->arg_end - mm->arg_start;
+
+	if (len > buflen)
+		len = buflen;
+
+	res = access_process_vm(task, mm->arg_start, buffer, len, 0);
 
-/* Tracepoints definitions. */
-EXPORT_TRACEPOINT_SYMBOL(kmalloc);
-EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
-EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
-EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
-EXPORT_TRACEPOINT_SYMBOL(kfree);
-EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
+	/*
+	 * If the nul at the end of args has been overwritten, then
+	 * assume application is using setproctitle(3).
+	 */
+	if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
+		len = strnlen(buffer, res);
+		if (len < res) {
+			res = len;
+		} else {
+			len = mm->env_end - mm->env_start;
+			if (len > buflen - res)
+				len = buflen - res;
+			res += access_process_vm(task, mm->env_start,
+						 buffer+res, len, 0);
+			res = strnlen(buffer, res);
+		}
+	}
+out_mm:
+	mmput(mm);
+out:
+	return res;
+}