Merge tag 'v3.4.7' into v3.4-rt

This is the 3.4.7 stable release

Conflicts:
	kernel/hrtimer.c
	kernel/time/timekeeping.c

Required fixup:

diff --cc kernel/hrtimer.c
index a080e62,6db7a5e..0000000
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@@ -1597,17 -1407,24 +1611,23 @@@ void hrtimer_peek_ahead_timers(void
  	local_irq_restore(flags);
  }

 +#else /* CONFIG_HIGH_RES_TIMERS */
 +
 +static inline void __hrtimer_peek_ahead_timers(void) { }
 +
 +#endif	/* !CONFIG_HIGH_RES_TIMERS */
 +
  static void run_hrtimer_softirq(struct softirq_action *h)
  {
+ 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+ 	if (cpu_base->clock_was_set) {
+ 		cpu_base->clock_was_set = 0;
+ 		clock_was_set();
+ 	}
 -
 -	hrtimer_peek_ahead_timers();
 +	hrtimer_rt_run_pending();
  }

 -#else /* CONFIG_HIGH_RES_TIMERS */
 -
 -static inline void __hrtimer_peek_ahead_timers(void) { }
 -
 -#endif	/* !CONFIG_HIGH_RES_TIMERS */
 -
  /*
   * Called from timer softirq every jiffy, expire hrtimers:
   *
diff --cc kernel/time/timekeeping.c
index e8e95ee,7c50de8..0000000
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@@ -70,9 -70,14 +70,15 @@@ struct timekeeper
  	/* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
  	struct timespec raw_time;

+ 	/* Offset clock monotonic -> clock realtime */
+ 	ktime_t offs_real;
+
+ 	/* Offset clock monotonic -> clock boottime */
+ 	ktime_t offs_boot;
+
 -	/* Seqlock for all timekeeper values */
 -	seqlock_t lock;
 +	/* Open coded seqlock for all timekeeper values */
 +	seqcount_t seq;
 +	raw_spinlock_t lock;
  };

  static struct timekeeper timekeeper;
@@@ -616,10 -621,10 +631,11 @@@ void __init timekeeping_init(void
  	}
  	set_normalized_timespec(&timekeeper.wall_to_monotonic,
  				-boot.tv_sec, -boot.tv_nsec);
+ 	update_rt_offset();
  	timekeeper.total_sleep_time.tv_sec = 0;
  	timekeeper.total_sleep_time.tv_nsec = 0;
 -	write_sequnlock_irqrestore(&timekeeper.lock, flags);
 +	write_seqcount_end(&timekeeper.seq);
 +	raw_spin_unlock_irqrestore(&timekeeper.lock, flags);
  }

  /* time in seconds when suspend began */
@@@ -712,8 -719,8 +733,9 @@@ static void timekeeping_resume(void
  	timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
  	timekeeper.ntp_error = 0;
  	timekeeping_suspended = 0;
+ 	timekeeping_update(false);
 -	write_sequnlock_irqrestore(&timekeeper.lock, flags);
 +	write_seqcount_end(&timekeeper.seq);
 +	raw_spin_unlock_irqrestore(&timekeeper.lock, flags);

  	touch_softlockup_watchdog();

@@@ -1263,9 -1271,43 +1289,43 @@@ void get_xtime_and_monotonic_and_sleep_
  		*xtim = timekeeper.xtime;
  		*wtom = timekeeper.wall_to_monotonic;
  		*sleep = timekeeper.total_sleep_time;
 -	} while (read_seqretry(&timekeeper.lock, seq));
 +	} while (read_seqcount_retry(&timekeeper.seq, seq));
  }

+ #ifdef CONFIG_HIGH_RES_TIMERS
+ /**
+  * ktime_get_update_offsets - hrtimer helper
+  * @offs_real:	pointer to storage for monotonic -> realtime offset
+  * @offs_boot:	pointer to storage for monotonic -> boottime offset
+  *
+  * Returns current monotonic time and updates the offsets
+  * Called from hrtimer_interupt() or retrigger_next_event()
+  */
+ ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
+ {
+ 	ktime_t now;
+ 	unsigned int seq;
+ 	u64 secs, nsecs;
+
+ 	do {
 -		seq = read_seqbegin(&timekeeper.lock);
++		seq = read_seqcount_begin(&timekeeper.seq);
+
+ 		secs = timekeeper.xtime.tv_sec;
+ 		nsecs = timekeeper.xtime.tv_nsec;
+ 		nsecs += timekeeping_get_ns();
+ 		/* If arch requires, add in gettimeoffset() */
+ 		nsecs += arch_gettimeoffset();
+
+ 		*offs_real = timekeeper.offs_real;
+ 		*offs_boot = timekeeper.offs_boot;
 -	} while (read_seqretry(&timekeeper.lock, seq));
++	} while (read_seqcount_retry(&timekeeper.seq, seq));
+
+ 	now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+ 	now = ktime_sub(now, *offs_real);
+ 	return now;
+ }
+ #endif
+
  /**
   * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
   */

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

6 files changed, 130 insertions, 67 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 74a8c825ff28..459b0ab60524 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -594,8 +594,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		if (err) {
 			putback_lru_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
+			if (err == -ENOMEM) {
+				ret = COMPACT_PARTIAL;
+				goto out;
+			}
 		}
-
 	}
 
 out:
diff --git a/mm/madvise.c b/mm/madvise.c
index 1ccbba5b6674..55f645c85a35 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>
 #include <linux/sched.h>
 #include <linux/ksm.h>
+#include <linux/file.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -203,14 +204,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 	struct address_space *mapping;
 	loff_t offset, endoff;
 	int error;
+	struct file *f;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
 	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
 		return -EINVAL;
 
-	if (!vma->vm_file || !vma->vm_file->f_mapping
-		|| !vma->vm_file->f_mapping->host) {
+	f = vma->vm_file;
+
+	if (!f || !f->f_mapping || !f->f_mapping->host) {
 			return -EINVAL;
 	}
 
@@ -224,9 +227,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 	endoff = (loff_t)(end - vma->vm_start - 1)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* vmtruncate_range needs to take i_mutex */
+	/*
+	 * vmtruncate_range may need to take i_mutex.  We need to
+	 * explicitly grab a reference because the vma (and hence the
+	 * vma's reference to the file) can go away as soon as we drop
+	 * mmap_sem.
+	 */
+	get_file(f);
 	up_read(&current->mm->mmap_sem);
 	error = vmtruncate_range(mapping->host, offset, endoff);
+	fput(f);
 	down_read(&current->mm->mmap_sem);
 	return error;
 }
diff --git a/mm/memblock.c b/mm/memblock.c
index a44eab3157f8..280d3d7835d6 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -37,6 +37,8 @@ struct memblock memblock __initdata_memblock = {
 
 int memblock_debug __initdata_memblock;
 static int memblock_can_resize __initdata_memblock;
+static int memblock_memory_in_slab __initdata_memblock = 0;
+static int memblock_reserved_in_slab __initdata_memblock = 0;
 
 /* inline so we don't get a warning when pr_debug is compiled out */
 static inline const char *memblock_type_name(struct memblock_type *type)
@@ -141,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					   MAX_NUMNODES);
 }
 
-/*
- * Free memblock.reserved.regions
- */
-int __init_memblock memblock_free_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_free(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
-/*
- * Reserve memblock.reserved.regions
- */
-int __init_memblock memblock_reserve_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_reserve(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
 static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	type->total_size -= type->regions[r].size;
@@ -182,11 +160,42 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 	}
 }
 
-static int __init_memblock memblock_double_array(struct memblock_type *type)
+phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
+					phys_addr_t *addr)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	*addr = __pa(memblock.reserved.regions);
+
+	return PAGE_ALIGN(sizeof(struct memblock_region) *
+			  memblock.reserved.max);
+}
+
+/**
+ * memblock_double_array - double the size of the memblock regions array
+ * @type: memblock type of the regions array being doubled
+ * @new_area_start: starting address of memory range to avoid overlap with
+ * @new_area_size: size of memory range to avoid overlap with
+ *
+ * Double the size of the @type regions array. If memblock is being used to
+ * allocate memory for a new reserved regions array and there is a previously
+ * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
+ * waiting to be reserved, ensure the memory used by the new array does
+ * not overlap.
+ *
+ * RETURNS:
+ * 0 on success, -1 on failure.
+ */
+static int __init_memblock memblock_double_array(struct memblock_type *type,
+						phys_addr_t new_area_start,
+						phys_addr_t new_area_size)
 {
 	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_alloc_size, new_alloc_size;
 	phys_addr_t old_size, new_size, addr;
 	int use_slab = slab_is_available();
+	int *in_slab;
 
 	/* We don't allow resizing until we know about the reserved regions
 	 * of memory that aren't suitable for allocation
@@ -197,6 +206,18 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	/* Calculate new doubled size */
 	old_size = type->max * sizeof(struct memblock_region);
 	new_size = old_size << 1;
+	/*
+	 * We need to allocated new one align to PAGE_SIZE,
+	 *   so we can free them completely later.
+	 */
+	old_alloc_size = PAGE_ALIGN(old_size);
+	new_alloc_size = PAGE_ALIGN(new_size);
+
+	/* Retrieve the slab flag */
+	if (type == &memblock.memory)
+		in_slab = &memblock_memory_in_slab;
+	else
+		in_slab = &memblock_reserved_in_slab;
 
 	/* Try to find some space for it.
 	 *
@@ -212,14 +233,26 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	if (use_slab) {
 		new_array = kmalloc(new_size, GFP_KERNEL);
 		addr = new_array ? __pa(new_array) : 0;
-	} else
-		addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
+	} else {
+		/* only exclude range when trying to double reserved.regions */
+		if (type != &memblock.reserved)
+			new_area_start = new_area_size = 0;
+
+		addr = memblock_find_in_range(new_area_start + new_area_size,
+						memblock.current_limit,
+						new_alloc_size, PAGE_SIZE);
+		if (!addr && new_area_size)
+			addr = memblock_find_in_range(0,
+					min(new_area_start, memblock.current_limit),
+					new_alloc_size, PAGE_SIZE);
+
+		new_array = addr ? __va(addr) : 0;
+	}
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
 		       memblock_type_name(type), type->max, type->max * 2);
 		return -1;
 	}
-	new_array = __va(addr);
 
 	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
 		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
@@ -234,21 +267,23 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	type->regions = new_array;
 	type->max <<= 1;
 
-	/* If we use SLAB that's it, we are done */
-	if (use_slab)
-		return 0;
-
-	/* Add the new reserved region now. Should not fail ! */
-	BUG_ON(memblock_reserve(addr, new_size));
-
-	/* If the array wasn't our static init one, then free it. We only do
-	 * that before SLAB is available as later on, we don't know whether
-	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
-	 * anyways
+	/* Free old array. We needn't free it if the array is the
+	 * static one
 	 */
-	if (old_array != memblock_memory_init_regions &&
-	    old_array != memblock_reserved_init_regions)
-		memblock_free(__pa(old_array), old_size);
+	if (*in_slab)
+		kfree(old_array);
+	else if (old_array != memblock_memory_init_regions &&
+		 old_array != memblock_reserved_init_regions)
+		memblock_free(__pa(old_array), old_alloc_size);
+
+	/* Reserve the new array if that comes from the memblock.
+	 * Otherwise, we needn't do it
+	 */
+	if (!use_slab)
+		BUG_ON(memblock_reserve(addr, new_alloc_size));
+
+	/* Update slab flag */
+	*in_slab = use_slab;
 
 	return 0;
 }
@@ -387,7 +422,7 @@ repeat:
 	 */
 	if (!insert) {
 		while (type->cnt + nr_new > type->max)
-			if (memblock_double_array(type) < 0)
+			if (memblock_double_array(type, obase, size) < 0)
 				return -ENOMEM;
 		insert = true;
 		goto repeat;
@@ -438,7 +473,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 
 	/* we'll create at most two more regions */
 	while (type->cnt + 2 > type->max)
-		if (memblock_double_array(type) < 0)
+		if (memblock_double_array(type, base, size) < 0)
 			return -ENOMEM;
 
 	for (i = 0; i < type->cnt; i++) {
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 1983fb1c7026..218e6f95d44f 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
 		__free_pages_bootmem(pfn_to_page(i), 0);
 }
 
+static unsigned long __init __free_memory_core(phys_addr_t start,
+				 phys_addr_t end)
+{
+	unsigned long start_pfn = PFN_UP(start);
+	unsigned long end_pfn = min_t(unsigned long,
+				      PFN_DOWN(end), max_low_pfn);
+
+	if (start_pfn > end_pfn)
+		return 0;
+
+	__free_pages_memory(start_pfn, end_pfn);
+
+	return end_pfn - start_pfn;
+}
+
 unsigned long __init free_low_memory_core_early(int nodeid)
 {
 	unsigned long count = 0;
-	phys_addr_t start, end;
+	phys_addr_t start, end, size;
 	u64 i;
 
-	/* free reserved array temporarily so that it's treated as free area */
-	memblock_free_reserved_regions();
-
-	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
-		unsigned long start_pfn = PFN_UP(start);
-		unsigned long end_pfn = min_t(unsigned long,
-					      PFN_DOWN(end), max_low_pfn);
-		if (start_pfn < end_pfn) {
-			__free_pages_memory(start_pfn, end_pfn);
-			count += end_pfn - start_pfn;
-		}
-	}
+	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
+		count += __free_memory_core(start, end);
+
+	/* free range that is used for reserved array if we allocate it */
+	size = get_allocated_memblock_reserved_regions_info(&start);
+	if (size)
+		count += __free_memory_core(start, start + size);
 
-	/* put region array back? */
-	memblock_reserve_reserved_regions();
 	return count;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index f99ff3e50bd6..9d65a02a8799 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1365,6 +1365,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &page_cache_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -1453,7 +1454,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 
 	if (error > 0) {
 		*ppos += error;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0932dc27e19d..be5bc0af2e76 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3013,7 +3013,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 		 * them before going back to sleep.
 		 */
 		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
-		schedule();
+
+		if (!kthread_should_stop())
+			schedule();
+
 		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
 	} else {
 		if (remaining)
@@ -3279,14 +3282,17 @@ int kswapd_run(int nid)
 }
 
 /*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined.  Caller must
+ * hold lock_memory_hotplug().
  */
 void kswapd_stop(int nid)
 {
 	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
 
-	if (kswapd)
+	if (kswapd) {
 		kthread_stop(kswapd);
+		NODE_DATA(nid)->kswapd = NULL;
+	}
 }
 
 static int __init kswapd_init(void)