Fix cpusets update_cpumask

Cause writes to cpuset "cpus" file to update cpus_allowed for member tasks:

- collect batches of tasks under tasklist_lock and then call
  set_cpus_allowed() on them outside the lock (since this can sleep).

- add a simple generic priority heap type to allow efficient collection
  of batches of tasks to be processed without duplicating or missing any
  tasks in subsequent batches.

- make "cpus" file update a no-op if the mask hasn't changed

- fix race between update_cpumask() and sched_setaffinity() by making
  sched_setaffinity() post-check that it's not running on any cpus outside
  cpuset_cpus_allowed().

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Paul Menage <menage@google.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 71 insertions, 1 deletions

diff --git a/lib/Makefile b/lib/Makefile
index c5f215d509d..3a0983b7741 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -6,7 +6,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o \
 	 idr.o int_sqrt.o bitmap.o extable.o prio_tree.o \
 	 sha1.o irq_regs.o reciprocal_div.o argv_split.o \
-	 proportions.o
+	 proportions.o prio_heap.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
diff --git a/lib/prio_heap.c b/lib/prio_heap.c
new file mode 100644
index 00000000000..471944a54e2
--- /dev/null
+++ b/lib/prio_heap.c
@@ -0,0 +1,70 @@
+/*
+ * Simple insertion-only static-sized priority heap containing
+ * pointers, based on CLR, chapter 7
+ */
+
+#include <linux/slab.h>
+#include <linux/prio_heap.h>
+
+int heap_init(struct ptr_heap *heap, size_t size, gfp_t gfp_mask,
+	      int (*gt)(void *, void *))
+{
+	heap->ptrs = kmalloc(size, gfp_mask);
+	if (!heap->ptrs)
+		return -ENOMEM;
+	heap->size = 0;
+	heap->max = size / sizeof(void *);
+	heap->gt = gt;
+	return 0;
+}
+
+void heap_free(struct ptr_heap *heap)
+{
+	kfree(heap->ptrs);
+}
+
+void *heap_insert(struct ptr_heap *heap, void *p)
+{
+	void *res;
+	void **ptrs = heap->ptrs;
+	int pos;
+
+	if (heap->size < heap->max) {
+		/* Heap insertion */
+		int pos = heap->size++;
+		while (pos > 0 && heap->gt(p, ptrs[(pos-1)/2])) {
+			ptrs[pos] = ptrs[(pos-1)/2];
+			pos = (pos-1)/2;
+		}
+		ptrs[pos] = p;
+		return NULL;
+	}
+
+	/* The heap is full, so something will have to be dropped */
+
+	/* If the new pointer is greater than the current max, drop it */
+	if (heap->gt(p, ptrs[0]))
+		return p;
+
+	/* Replace the current max and heapify */
+	res = ptrs[0];
+	ptrs[0] = p;
+	pos = 0;
+
+	while (1) {
+		int left = 2 * pos + 1;
+		int right = 2 * pos + 2;
+		int largest = pos;
+		if (left < heap->size && heap->gt(ptrs[left], p))
+			largest = left;
+		if (right < heap->size && heap->gt(ptrs[right], ptrs[largest]))
+			largest = right;
+		if (largest == pos)
+			break;
+		/* Push p down the heap one level and bump one up */
+		ptrs[pos] = ptrs[largest];
+		ptrs[largest] = p;
+		pos = largest;
+	}
+	return res;
+}