Merge branch 'perf/urgent' into perf/core

Merge reason: queue up dependent patch, update to -rc4

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 282 insertions, 161 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 43ea8c3a2bbf..17b8947aa7da 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -221,6 +221,7 @@ config KSM
 
 config DEFAULT_MMAP_MIN_ADDR
         int "Low address space to protect from user allocation"
+        depends on MMU
         default 4096
         help
           This is the portion of low virtual memory which should be protected
@@ -252,7 +253,7 @@ config MEMORY_FAILURE
 
 config HWPOISON_INJECT
         tristate "HWPoison pages injector"
-        depends on MEMORY_FAILURE && DEBUG_KERNEL
+        depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
         select PROC_PAGE_MONITOR
 
 config NOMMU_INITIAL_TRIM_EXCESS
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 65f38c218207..e91b81b63670 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -402,7 +402,7 @@ static void clear_huge_page(struct page *page,
 {
         int i;
 
-        if (unlikely(sz > MAX_ORDER_NR_PAGES)) {
+        if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) {
                 clear_gigantic_page(page, addr, sz);
                 return;
         }
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 13f33b3081ec..5b069e4f5e48 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -93,6 +93,7 @@
 #include <linux/nodemask.h>
 #include <linux/mm.h>
 #include <linux/workqueue.h>
+#include <linux/crc32.h>
 
 #include <asm/sections.h>
 #include <asm/processor.h>
@@ -108,7 +109,6 @@
 #define MSECS_MIN_AGE           5000    /* minimum object age for reporting */
 #define SECS_FIRST_SCAN         60      /* delay before the first scan */
 #define SECS_SCAN_WAIT          600     /* subsequent auto scanning delay */
-#define GRAY_LIST_PASSES        25      /* maximum number of gray list scans */
 #define MAX_SCAN_SIZE           4096    /* maximum size of a scanned block */
 
 #define BYTES_PER_POINTER       sizeof(void *)
@@ -119,8 +119,8 @@
 /* scanning area inside a memory block */
 struct kmemleak_scan_area {
         struct hlist_node node;
-        unsigned long offset;
-        size_t length;
+        unsigned long start;
+        size_t size;
 };
 
 #define KMEMLEAK_GREY   0
@@ -149,6 +149,8 @@ struct kmemleak_object {
         int min_count;
         /* the total number of pointers found pointing to this object */
         int count;
+        /* checksum for detecting modified objects */
+        u32 checksum;
         /* memory ranges to be scanned inside an object (empty for all) */
         struct hlist_head area_list;
         unsigned long trace[MAX_TRACE];
@@ -164,8 +166,6 @@ struct kmemleak_object {
 #define OBJECT_REPORTED         (1 << 1)
 /* flag set to not scan the object */
 #define OBJECT_NO_SCAN          (1 << 2)
-/* flag set on newly allocated objects */
-#define OBJECT_NEW              (1 << 3)
 
 /* number of bytes to print per line; must be 16 or 32 */
 #define HEX_ROW_SIZE            16
@@ -241,8 +241,6 @@ struct early_log {
         const void *ptr;                /* allocated/freed memory block */
         size_t size;                    /* memory block size */
         int min_count;                  /* minimum reference count */
-        unsigned long offset;           /* scan area offset */
-        size_t length;                  /* scan area length */
         unsigned long trace[MAX_TRACE]; /* stack trace */
         unsigned int trace_len;         /* stack trace length */
 };
@@ -323,11 +321,6 @@ static bool color_gray(const struct kmemleak_object *object)
                 object->count >= object->min_count;
 }
 
-static bool color_black(const struct kmemleak_object *object)
-{
-        return object->min_count == KMEMLEAK_BLACK;
-}
-
 /*
  * Objects are considered unreferenced only if their color is white, they have
  * not be deleted and have a minimum age to avoid false positives caused by
@@ -335,7 +328,7 @@ static bool color_black(const struct kmemleak_object *object)
  */
 static bool unreferenced_object(struct kmemleak_object *object)
 {
-        return (object->flags & OBJECT_ALLOCATED) && color_white(object) &&
+        return (color_white(object) && object->flags & OBJECT_ALLOCATED) &&
                 time_before_eq(object->jiffies + jiffies_min_age,
                                jiffies_last_scan);
 }
@@ -348,11 +341,13 @@ static void print_unreferenced(struct seq_file *seq,
                                struct kmemleak_object *object)
 {
         int i;
+        unsigned int msecs_age = jiffies_to_msecs(jiffies - object->jiffies);
 
         seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n",
                    object->pointer, object->size);
-        seq_printf(seq, "  comm \"%s\", pid %d, jiffies %lu\n",
-                   object->comm, object->pid, object->jiffies);
+        seq_printf(seq, "  comm \"%s\", pid %d, jiffies %lu (age %d.%03ds)\n",
+                   object->comm, object->pid, object->jiffies,
+                   msecs_age / 1000, msecs_age % 1000);
         hex_dump_object(seq, object);
         seq_printf(seq, "  backtrace:\n");
 
@@ -381,6 +376,7 @@ static void dump_object_info(struct kmemleak_object *object)
         pr_notice("  min_count = %d\n", object->min_count);
         pr_notice("  count = %d\n", object->count);
         pr_notice("  flags = 0x%lx\n", object->flags);
+        pr_notice("  checksum = %d\n", object->checksum);
         pr_notice("  backtrace:\n");
         print_stack_trace(&trace, 4);
 }
@@ -522,12 +518,13 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
         INIT_HLIST_HEAD(&object->area_list);
         spin_lock_init(&object->lock);
         atomic_set(&object->use_count, 1);
-        object->flags = OBJECT_ALLOCATED | OBJECT_NEW;
+        object->flags = OBJECT_ALLOCATED;
         object->pointer = ptr;
         object->size = size;
         object->min_count = min_count;
-        object->count = -1;                     /* no color initially */
+        object->count = 0;                      /* white color initially */
         object->jiffies = jiffies;
+        object->checksum = 0;
 
         /* task information */
         if (in_irq()) {
@@ -720,14 +717,13 @@ static void make_black_object(unsigned long ptr)
  * Add a scanning area to the object. If at least one such area is added,
  * kmemleak will only scan these ranges rather than the whole memory block.
  */
-static void add_scan_area(unsigned long ptr, unsigned long offset,
-                          size_t length, gfp_t gfp)
+static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 {
         unsigned long flags;
         struct kmemleak_object *object;
         struct kmemleak_scan_area *area;
 
-        object = find_and_get_object(ptr, 0);
+        object = find_and_get_object(ptr, 1);
         if (!object) {
                 kmemleak_warn("Adding scan area to unknown object at 0x%08lx\n",
                               ptr);
@@ -741,7 +737,7 @@ static void add_scan_area(unsigned long ptr, unsigned long offset,
         }
 
         spin_lock_irqsave(&object->lock, flags);
-        if (offset + length > object->size) {
+        if (ptr + size > object->pointer + object->size) {
                 kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
                 dump_object_info(object);
                 kmem_cache_free(scan_area_cache, area);
@@ -749,8 +745,8 @@ static void add_scan_area(unsigned long ptr, unsigned long offset,
         }
 
         INIT_HLIST_NODE(&area->node);
-        area->offset = offset;
-        area->length = length;
+        area->start = ptr;
+        area->size = size;
 
         hlist_add_head(&area->node, &object->area_list);
 out_unlock:
@@ -786,7 +782,7 @@ static void object_no_scan(unsigned long ptr)
  * processed later once kmemleak is fully initialized.
  */
 static void __init log_early(int op_type, const void *ptr, size_t size,
-                             int min_count, unsigned long offset, size_t length)
+                             int min_count)
 {
         unsigned long flags;
         struct early_log *log;
@@ -808,8 +804,6 @@ static void __init log_early(int op_type, const void *ptr, size_t size,
         log->ptr = ptr;
         log->size = size;
         log->min_count = min_count;
-        log->offset = offset;
-        log->length = length;
         if (op_type == KMEMLEAK_ALLOC)
                 log->trace_len = __save_stack_trace(log->trace);
         crt_early_log++;
@@ -858,7 +852,7 @@ void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count,
         if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
                 create_object((unsigned long)ptr, size, min_count, gfp);
         else if (atomic_read(&kmemleak_early_log))
-                log_early(KMEMLEAK_ALLOC, ptr, size, min_count, 0, 0);
+                log_early(KMEMLEAK_ALLOC, ptr, size, min_count);
 }
 EXPORT_SYMBOL_GPL(kmemleak_alloc);
 
@@ -873,7 +867,7 @@ void __ref kmemleak_free(const void *ptr)
         if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
                 delete_object_full((unsigned long)ptr);
         else if (atomic_read(&kmemleak_early_log))
-                log_early(KMEMLEAK_FREE, ptr, 0, 0, 0, 0);
+                log_early(KMEMLEAK_FREE, ptr, 0, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free);
 
@@ -888,7 +882,7 @@ void __ref kmemleak_free_part(const void *ptr, size_t size)
         if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
                 delete_object_part((unsigned long)ptr, size);
         else if (atomic_read(&kmemleak_early_log))
-                log_early(KMEMLEAK_FREE_PART, ptr, size, 0, 0, 0);
+                log_early(KMEMLEAK_FREE_PART, ptr, size, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_part);
 
@@ -903,7 +897,7 @@ void __ref kmemleak_not_leak(const void *ptr)
         if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
                 make_gray_object((unsigned long)ptr);
         else if (atomic_read(&kmemleak_early_log))
-                log_early(KMEMLEAK_NOT_LEAK, ptr, 0, 0, 0, 0);
+                log_early(KMEMLEAK_NOT_LEAK, ptr, 0, 0);
 }
 EXPORT_SYMBOL(kmemleak_not_leak);
 
@@ -919,22 +913,21 @@ void __ref kmemleak_ignore(const void *ptr)
         if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
                 make_black_object((unsigned long)ptr);
         else if (atomic_read(&kmemleak_early_log))
-                log_early(KMEMLEAK_IGNORE, ptr, 0, 0, 0, 0);
+                log_early(KMEMLEAK_IGNORE, ptr, 0, 0);
 }
 EXPORT_SYMBOL(kmemleak_ignore);
 
 /*
  * Limit the range to be scanned in an allocated memory block.
  */
-void __ref kmemleak_scan_area(const void *ptr, unsigned long offset,
-                              size_t length, gfp_t gfp)
+void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 {
         pr_debug("%s(0x%p)\n", __func__, ptr);
 
         if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
-                add_scan_area((unsigned long)ptr, offset, length, gfp);
+                add_scan_area((unsigned long)ptr, size, gfp);
         else if (atomic_read(&kmemleak_early_log))
-                log_early(KMEMLEAK_SCAN_AREA, ptr, 0, 0, offset, length);
+                log_early(KMEMLEAK_SCAN_AREA, ptr, size, 0);
 }
 EXPORT_SYMBOL(kmemleak_scan_area);
 
@@ -948,11 +941,25 @@ void __ref kmemleak_no_scan(const void *ptr)
         if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
                 object_no_scan((unsigned long)ptr);
         else if (atomic_read(&kmemleak_early_log))
-                log_early(KMEMLEAK_NO_SCAN, ptr, 0, 0, 0, 0);
+                log_early(KMEMLEAK_NO_SCAN, ptr, 0, 0);
 }
 EXPORT_SYMBOL(kmemleak_no_scan);
 
 /*
+ * Update an object's checksum and return true if it was modified.
+ */
+static bool update_checksum(struct kmemleak_object *object)
+{
+        u32 old_csum = object->checksum;
+
+        if (!kmemcheck_is_obj_initialized(object->pointer, object->size))
+                return false;
+
+        object->checksum = crc32(0, (void *)object->pointer, object->size);
+        return object->checksum != old_csum;
+}
+
+/*
  * Memory scanning is a long process and it needs to be interruptable. This
  * function checks whether such interrupt condition occured.
  */
@@ -1031,11 +1038,14 @@ static void scan_block(void *_start, void *_end,
                  * added to the gray_list.
                  */
                 object->count++;
-                if (color_gray(object))
+                if (color_gray(object)) {
                         list_add_tail(&object->gray_list, &gray_list);
-                else
-                        put_object(object);
+                        spin_unlock_irqrestore(&object->lock, flags);
+                        continue;
+                }
+
                 spin_unlock_irqrestore(&object->lock, flags);
+                put_object(object);
         }
 }
 
@@ -1075,14 +1085,47 @@ static void scan_object(struct kmemleak_object *object)
                 }
         } else
                 hlist_for_each_entry(area, elem, &object->area_list, node)
-                        scan_block((void *)(object->pointer + area->offset),
-                                   (void *)(object->pointer + area->offset
-                                            + area->length), object, 0);
+                        scan_block((void *)area->start,
+                                   (void *)(area->start + area->size),
+                                   object, 0);
 out:
         spin_unlock_irqrestore(&object->lock, flags);
 }
 
 /*
+ * Scan the objects already referenced (gray objects). More objects will be
+ * referenced and, if there are no memory leaks, all the objects are scanned.
+ */
+static void scan_gray_list(void)
+{
+        struct kmemleak_object *object, *tmp;
+
+        /*
+         * The list traversal is safe for both tail additions and removals
+         * from inside the loop. The kmemleak objects cannot be freed from
+         * outside the loop because their use_count was incremented.
+         */
+        object = list_entry(gray_list.next, typeof(*object), gray_list);
+        while (&object->gray_list != &gray_list) {
+                cond_resched();
+
+                /* may add new objects to the list */
+                if (!scan_should_stop())
+                        scan_object(object);
+
+                tmp = list_entry(object->gray_list.next, typeof(*object),
+                                 gray_list);
+
+                /* remove the object from the list and release it */
+                list_del(&object->gray_list);
+                put_object(object);
+
+                object = tmp;
+        }
+        WARN_ON(!list_empty(&gray_list));
+}
+
+/*
  * Scan data sections and all the referenced memory blocks allocated via the
  * kernel's standard allocators. This function must be called with the
  * scan_mutex held.
@@ -1090,10 +1133,9 @@ out:
 static void kmemleak_scan(void)
 {
         unsigned long flags;
-        struct kmemleak_object *object, *tmp;
+        struct kmemleak_object *object;
         int i;
         int new_leaks = 0;
-        int gray_list_pass = 0;
 
         jiffies_last_scan = jiffies;
 
@@ -1114,7 +1156,6 @@ static void kmemleak_scan(void)
 #endif
                 /* reset the reference count (whiten the object) */
                 object->count = 0;
-                object->flags &= ~OBJECT_NEW;
                 if (color_gray(object) && get_object(object))
                         list_add_tail(&object->gray_list, &gray_list);
 
@@ -1172,62 +1213,36 @@ static void kmemleak_scan(void)
 
         /*
          * Scan the objects already referenced from the sections scanned
-         * above. More objects will be referenced and, if there are no memory
-         * leaks, all the objects will be scanned. The list traversal is safe
-         * for both tail additions and removals from inside the loop. The
-         * kmemleak objects cannot be freed from outside the loop because their
-         * use_count was increased.
+         * above.
          */
-repeat:
-        object = list_entry(gray_list.next, typeof(*object), gray_list);
-        while (&object->gray_list != &gray_list) {
-                cond_resched();
-
-                /* may add new objects to the list */
-                if (!scan_should_stop())
-                        scan_object(object);
-
-                tmp = list_entry(object->gray_list.next, typeof(*object),
-                                 gray_list);
-
-                /* remove the object from the list and release it */
-                list_del(&object->gray_list);
-                put_object(object);
-
-                object = tmp;
-        }
-
-        if (scan_should_stop() || ++gray_list_pass >= GRAY_LIST_PASSES)
-                goto scan_end;
+        scan_gray_list();
 
         /*
-         * Check for new objects allocated during this scanning and add them
-         * to the gray list.
+         * Check for new or unreferenced objects modified since the previous
+         * scan and color them gray until the next scan.
          */
         rcu_read_lock();
         list_for_each_entry_rcu(object, &object_list, object_list) {
                 spin_lock_irqsave(&object->lock, flags);
-                if ((object->flags & OBJECT_NEW) && !color_black(object) &&
-                    get_object(object)) {
-                        object->flags &= ~OBJECT_NEW;
+                if (color_white(object) && (object->flags & OBJECT_ALLOCATED)
+                    && update_checksum(object) && get_object(object)) {
+                        /* color it gray temporarily */
+                        object->count = object->min_count;
                         list_add_tail(&object->gray_list, &gray_list);
                 }
                 spin_unlock_irqrestore(&object->lock, flags);
         }
         rcu_read_unlock();
 
-        if (!list_empty(&gray_list))
-                goto repeat;
-
-scan_end:
-        WARN_ON(!list_empty(&gray_list));
+        /*
+         * Re-scan the gray list for modified unreferenced objects.
+         */
+        scan_gray_list();
 
         /*
-         * If scanning was stopped or new objects were being allocated at a
-         * higher rate than gray list scanning, do not report any new
-         * unreferenced objects.
+         * If scanning was stopped do not report any new unreferenced objects.
          */
-        if (scan_should_stop() || gray_list_pass >= GRAY_LIST_PASSES)
+        if (scan_should_stop())
                 return;
 
         /*
@@ -1642,8 +1657,7 @@ void __init kmemleak_init(void)
                         kmemleak_ignore(log->ptr);
                         break;
                 case KMEMLEAK_SCAN_AREA:
-                        kmemleak_scan_area(log->ptr, log->offset, log->length,
-                                           GFP_KERNEL);
+                        kmemleak_scan_area(log->ptr, log->size, GFP_KERNEL);
                         break;
                 case KMEMLEAK_NO_SCAN:
                         kmemleak_no_scan(log->ptr);
diff --git a/mm/maccess.c b/mm/maccess.c
index 9073695ff25f..4e348dbaecd7 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -14,7 +14,11 @@
  * Safely read from address @src to the buffer at @dst.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long probe_kernel_read(void *dst, void *src, size_t size)
+
+long __weak probe_kernel_read(void *dst, void *src, size_t size)
+    __attribute__((alias("__probe_kernel_read")));
+
+long __probe_kernel_read(void *dst, void *src, size_t size)
 {
         long ret;
         mm_segment_t old_fs = get_fs();
@@ -39,7 +43,10 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long notrace __weak probe_kernel_write(void *dst, void *src, size_t size)
+long __weak probe_kernel_write(void *dst, void *src, size_t size)
+    __attribute__((alias("__probe_kernel_write")));
+
+long __probe_kernel_write(void *dst, void *src, size_t size)
 {
         long ret;
         mm_segment_t old_fs = get_fs();
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6a0466ed5bfd..17299fd4577c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -52,6 +52,8 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
+#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
+
 u32 hwpoison_filter_enable = 0;
 u32 hwpoison_filter_dev_major = ~0U;
 u32 hwpoison_filter_dev_minor = ~0U;
@@ -164,6 +166,13 @@ int hwpoison_filter(struct page *p)
 
         return 0;
 }
+#else
+int hwpoison_filter(struct page *p)
+{
+        return 0;
+}
+#endif
+
 EXPORT_SYMBOL_GPL(hwpoison_filter);
 
 /*
diff --git a/mm/mmap.c b/mm/mmap.c
index d9c77b2dbe9d..ee2298936fe6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1043,6 +1043,46 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+                unsigned long, prot, unsigned long, flags,
+                unsigned long, fd, unsigned long, pgoff)
+{
+        struct file *file = NULL;
+        unsigned long retval = -EBADF;
+
+        if (!(flags & MAP_ANONYMOUS)) {
+                if (unlikely(flags & MAP_HUGETLB))
+                        return -EINVAL;
+                file = fget(fd);
+                if (!file)
+                        goto out;
+        } else if (flags & MAP_HUGETLB) {
+                struct user_struct *user = NULL;
+                /*
+                 * VM_NORESERVE is used because the reservations will be
+                 * taken when vm_ops->mmap() is called
+                 * A dummy user value is used because we are not locking
+                 * memory so no accounting is necessary
+                 */
+                len = ALIGN(len, huge_page_size(&default_hstate));
+                file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
+                                                &user, HUGETLB_ANONHUGE_INODE);
+                if (IS_ERR(file))
+                        return PTR_ERR(file);
+        }
+
+        flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+        down_write(&current->mm->mmap_sem);
+        retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+        up_write(&current->mm->mmap_sem);
+
+        if (file)
+                fput(file);
+out:
+        return retval;
+}
+
 /*
  * Some shared mappigns will want the pages marked read-only
  * to track write events. If so, we'll downgrade vm_page_prot
diff --git a/mm/nommu.c b/mm/nommu.c
index 8687973462bb..17773862619b 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -432,6 +432,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
         /*
          * Ok, looks good - let it rip.
          */
+        flush_icache_range(mm->brk, brk);
         return mm->brk = brk;
 }
 
@@ -1353,10 +1354,14 @@ unsigned long do_mmap_pgoff(struct file *file,
 share:
         add_vma_to_mm(current->mm, vma);
 
-        up_write(&nommu_region_sem);
+        /* we flush the region from the icache only when the first executable
+         * mapping of it is made  */
+        if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
+                flush_icache_range(region->vm_start, region->vm_end);
+                region->vm_icache_flushed = true;
+        }
 
-        if (prot & PROT_EXEC)
-                flush_icache_range(result, result + len);
+        up_write(&nommu_region_sem);
 
         kleave(" = %lx", result);
         return result;
@@ -1398,6 +1403,31 @@ error_getting_region:
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+                unsigned long, prot, unsigned long, flags,
+                unsigned long, fd, unsigned long, pgoff)
+{
+        struct file *file = NULL;
+        unsigned long retval = -EBADF;
+
+        if (!(flags & MAP_ANONYMOUS)) {
+                file = fget(fd);
+                if (!file)
+                        goto out;
+        }
+
+        flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+        down_write(&current->mm->mmap_sem);
+        retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+        up_write(&current->mm->mmap_sem);
+
+        if (file)
+                fput(file);
+out:
+        return retval;
+}
+
 /*
  * split a vma into two pieces at address 'addr', a new vma is allocated either
  * for the first part or the tail.
@@ -1891,9 +1921,11 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 
                 /* only read or write mappings where it is permitted */
                 if (write && vma->vm_flags & VM_MAYWRITE)
-                        len -= copy_to_user((void *) addr, buf, len);
+                        copy_to_user_page(vma, NULL, addr,
+                                         (void *) addr, buf, len);
                 else if (!write && vma->vm_flags & VM_MAYREAD)
-                        len -= copy_from_user(buf, (void *) addr, len);
+                        copy_from_user_page(vma, NULL, addr,
+                                            buf, (void *) addr, len);
                 else
                         len = 0;
         } else {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 74af449b1f1d..4e9f5cc5fb59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,6 +48,7 @@
 #include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
+#include <linux/memory.h>
 #include <trace/events/kmem.h>
 
 #include <asm/tlbflush.h>
@@ -2401,13 +2402,14 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 {
         char saved_string[NUMA_ZONELIST_ORDER_LEN];
         int ret;
+        static DEFINE_MUTEX(zl_order_mutex);
 
+        mutex_lock(&zl_order_mutex);
         if (write)
-                strncpy(saved_string, (char*)table->data,
-                        NUMA_ZONELIST_ORDER_LEN);
+                strcpy(saved_string, (char*)table->data);
         ret = proc_dostring(table, write, buffer, length, ppos);
         if (ret)
-                return ret;
+                goto out;
         if (write) {
                 int oldval = user_zonelist_order;
                 if (__parse_numa_zonelist_order((char*)table->data)) {
@@ -2420,7 +2422,9 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
                 } else if (oldval != user_zonelist_order)
                         build_all_zonelists();
         }
-        return 0;
+out:
+        mutex_unlock(&zl_order_mutex);
+        return ret;
 }
 
 
@@ -3579,7 +3583,7 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
  * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
  * then all holes in the requested range will be accounted for.
  */
-static unsigned long __meminit __absent_pages_in_range(int nid,
+unsigned long __meminit __absent_pages_in_range(int nid,
                                 unsigned long range_start_pfn,
                                 unsigned long range_end_pfn)
 {
@@ -4108,7 +4112,7 @@ static int __init cmp_node_active_region(const void *a, const void *b)
 }
 
 /* sort the node_map by start_pfn */
-static void __init sort_node_map(void)
+void __init sort_node_map(void)
 {
         sort(early_node_map, (size_t)nr_nodemap_entries,
                         sizeof(struct node_active_region),
@@ -5008,23 +5012,65 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
 int set_migratetype_isolate(struct page *page)
 {
         struct zone *zone;
-        unsigned long flags;
+        struct page *curr_page;
+        unsigned long flags, pfn, iter;
+        unsigned long immobile = 0;
+        struct memory_isolate_notify arg;
+        int notifier_ret;
         int ret = -EBUSY;
         int zone_idx;
 
         zone = page_zone(page);
         zone_idx = zone_idx(zone);
+
         spin_lock_irqsave(&zone->lock, flags);
+        if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE ||
+            zone_idx == ZONE_MOVABLE) {
+                ret = 0;
+                goto out;
+        }
+
+        pfn = page_to_pfn(page);
+        arg.start_pfn = pfn;
+        arg.nr_pages = pageblock_nr_pages;
+        arg.pages_found = 0;
+
         /*
-         * In future, more migrate types will be able to be isolation target.
+         * It may be possible to isolate a pageblock even if the
+         * migratetype is not MIGRATE_MOVABLE. The memory isolation
+         * notifier chain is used by balloon drivers to return the
+         * number of pages in a range that are held by the balloon
+         * driver to shrink memory. If all the pages are accounted for
+         * by balloons, are free, or on the LRU, isolation can continue.
+         * Later, for example, when memory hotplug notifier runs, these
+         * pages reported as "can be isolated" should be isolated(freed)
+         * by the balloon driver through the memory notifier chain.
          */
-        if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE &&
-            zone_idx != ZONE_MOVABLE)
+        notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
+        notifier_ret = notifier_to_errno(notifier_ret);
+        if (notifier_ret || !arg.pages_found)
                 goto out;
-        set_pageblock_migratetype(page, MIGRATE_ISOLATE);
-        move_freepages_block(zone, page, MIGRATE_ISOLATE);
-        ret = 0;
+
+        for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) {
+                if (!pfn_valid_within(pfn))
+                        continue;
+
+                curr_page = pfn_to_page(iter);
+                if (!page_count(curr_page) || PageLRU(curr_page))
+                        continue;
+
+                immobile++;
+        }
+
+        if (arg.pages_found == immobile)
+                ret = 0;
+
 out:
+        if (!ret) {
+                set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+                move_freepages_block(zone, page, MIGRATE_ISOLATE);
+        }
+
         spin_unlock_irqrestore(&zone->lock, flags);
         if (!ret)
                 drain_all_pages();
diff --git a/mm/percpu.c b/mm/percpu.c
index 442010cc91c6..083e7c91e5f6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1271,7 +1271,7 @@ static void pcpu_reclaim(struct work_struct *work)
  */
 void free_percpu(void *ptr)
 {
-        void *addr = __pcpu_ptr_to_addr(ptr);
+        void *addr;
         struct pcpu_chunk *chunk;
         unsigned long flags;
         int off;
@@ -1279,6 +1279,8 @@ void free_percpu(void *ptr)
         if (!ptr)
                 return;
 
+        addr = __pcpu_ptr_to_addr(ptr);
+
         spin_lock_irqsave(&pcpu_lock, flags);
 
         chunk = pcpu_chunk_addr_search(addr);
diff --git a/mm/readahead.c b/mm/readahead.c
index aa1aa2345235..033bc135a41f 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -547,5 +547,17 @@ page_cache_async_readahead(struct address_space *mapping,
 
         /* do read-ahead */
         ondemand_readahead(mapping, ra, filp, true, offset, req_size);
+
+#ifdef CONFIG_BLOCK
+        /*
+         * Normally the current page is !uptodate and lock_page() will be
+         * immediately called to implicitly unplug the device. However this
+         * is not always true for RAID conifgurations, where data arrives
+         * not strictly in their submission order. In this case we need to
+         * explicitly kick off the IO.
+         */
+        if (PageUptodate(page))
+                blk_run_backing_dev(mapping->backing_dev_info, NULL);
+#endif
 }
 EXPORT_SYMBOL_GPL(page_cache_async_readahead);
diff --git a/mm/slab.c b/mm/slab.c
index 3f4822938f46..7451bdacaf18 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -654,7 +654,7 @@ static void init_node_lock_keys(int q)
 
                 l3 = s->cs_cachep->nodelists[q];
                 if (!l3 || OFF_SLAB(s->cs_cachep))
-                        return;
+                        continue;
                 lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
                 alc = l3->alien;
                 /*
@@ -665,7 +665,7 @@ static void init_node_lock_keys(int q)
                  * for alloc_alien_cache,
                  */
                 if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
-                        return;
+                        continue;
                 for_each_node(r) {
                         if (alc[r])
                                 lockdep_set_class(&alc[r]->lock,
@@ -1132,7 +1132,7 @@ static void __cpuinit cpuup_canceled(long cpu)
                 if (nc)
                         free_block(cachep, nc->entry, nc->avail, node);
 
-                if (!cpus_empty(*mask)) {
+                if (!cpumask_empty(mask)) {
                         spin_unlock_irq(&l3->list_lock);
                         goto free_array_cache;
                 }
@@ -2275,9 +2275,11 @@ kmem_cache_create (const char *name, size_t size, size_t align,
         /*
          * Determine if the slab management is 'on' or 'off' slab.
          * (bootstrapping cannot cope with offslab caches so don't do
-         * it too early on.)
+         * it too early on. Always use on-slab management when
+         * SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
          */
-        if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init)
+        if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init &&
+            !(flags & SLAB_NOLEAKTRACE))
                 /*
                  * Size is large, assume best to place the slab management obj
                  * off-slab (should allow better packing of objs).
@@ -2596,8 +2598,8 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
                  * kmemleak does not treat the ->s_mem pointer as a reference
                  * to the object. Otherwise we will not report the leak.
                  */
-                kmemleak_scan_area(slabp, offsetof(struct slab, list),
-                                   sizeof(struct list_head), local_flags);
+                kmemleak_scan_area(&slabp->list, sizeof(struct list_head),
+                                   local_flags);
                 if (!slabp)
                         return NULL;
         } else {
diff --git a/mm/util.c b/mm/util.c
index b377ce430803..7c35ad95f927 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,10 +4,6 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/sched.h>
-#include <linux/hugetlb.h>
-#include <linux/syscalls.h>
-#include <linux/mman.h>
-#include <linux/file.h>
 #include <asm/uaccess.h>
 
 #define CREATE_TRACE_POINTS
@@ -272,46 +268,6 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 }
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
-SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
-                unsigned long, prot, unsigned long, flags,
-                unsigned long, fd, unsigned long, pgoff)
-{
-        struct file * file = NULL;
-        unsigned long retval = -EBADF;
-
-        if (!(flags & MAP_ANONYMOUS)) {
-                if (unlikely(flags & MAP_HUGETLB))
-                        return -EINVAL;
-                file = fget(fd);
-                if (!file)
-                        goto out;
-        } else if (flags & MAP_HUGETLB) {
-                struct user_struct *user = NULL;
-                /*
-                 * VM_NORESERVE is used because the reservations will be
-                 * taken when vm_ops->mmap() is called
-                 * A dummy user value is used because we are not locking
-                 * memory so no accounting is necessary
-                 */
-                len = ALIGN(len, huge_page_size(&default_hstate));
-                file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
-                                                &user, HUGETLB_ANONHUGE_INODE);
-                if (IS_ERR(file))
-                        return PTR_ERR(file);
-        }
-
-        flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
-
-        down_write(&current->mm->mmap_sem);
-        retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
-        up_write(&current->mm->mmap_sem);
-
-        if (file)
-                fput(file);
-out:
-        return retval;
-}
-
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);