Linux-libre 4.4.3-gnu

5 files changed, 61 insertions, 29 deletions

diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index d34bd24c2..4a1515f4b 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -1181,7 +1181,7 @@ static inline bool overlap(void *addr, unsigned long len, void *start, void *end
 
 static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
 {
-	if (overlap(addr, len, _text, _etext) ||
+	if (overlap(addr, len, _stext, _etext) ||
 	    overlap(addr, len, __start_rodata, __end_rodata))
 		err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
 }
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 6745c6230..c30d07e99 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -25,6 +25,7 @@ static atomic_t dump_lock = ATOMIC_INIT(-1);
 
 asmlinkage __visible void dump_stack(void)
 {
+	unsigned long flags;
 	int was_locked;
 	int old;
 	int cpu;
@@ -33,9 +34,8 @@ asmlinkage __visible void dump_stack(void)
 	 * Permit this cpu to perform nested stack dumps while serialising
 	 * against other CPUs
 	 */
-	preempt_disable();
-
 retry:
+	local_irq_save(flags);
 	cpu = smp_processor_id();
 	old = atomic_cmpxchg(&dump_lock, -1, cpu);
 	if (old == -1) {
@@ -43,6 +43,7 @@ retry:
 	} else if (old == cpu) {
 		was_locked = 1;
 	} else {
+		local_irq_restore(flags);
 		cpu_relax();
 		goto retry;
 	}
@@ -52,7 +53,7 @@ retry:
 	if (!was_locked)
 		atomic_set(&dump_lock, -1);
 
-	preempt_enable();
+	local_irq_restore(flags);
 }
 #else
 asmlinkage __visible void dump_stack(void)
diff --git a/lib/klist.c b/lib/klist.c
index d74cf7a29..0507fa5d8 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i,
 			  struct klist_node *n)
 {
 	i->i_klist = k;
-	i->i_cur = n;
-	if (n)
-		kref_get(&n->n_ref);
+	i->i_cur = NULL;
+	if (n && kref_get_unless_zero(&n->n_ref))
+		i->i_cur = n;
 }
 EXPORT_SYMBOL_GPL(klist_iter_init_node);
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index fcf5d9857..6b79e9026 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 		return 0;
 
 	radix_tree_for_each_slot(slot, root, &iter, first_index) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}
@@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 		return 0;
 
 	radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 5939f63d9..5c88204b6 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -43,50 +43,73 @@ void string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 		[STRING_UNITS_10] = 1000,
 		[STRING_UNITS_2] = 1024,
 	};
-	int i, j;
-	u32 remainder = 0, sf_cap, exp;
+	static const unsigned int rounding[] = { 500, 50, 5 };
+	int i = 0, j;
+	u32 remainder = 0, sf_cap;
 	char tmp[8];
 	const char *unit;
 
 	tmp[0] = '\0';
-	i = 0;
-	if (!size)
+
+	if (blk_size == 0)
+		size = 0;
+	if (size == 0)
 		goto out;
 
-	while (blk_size >= divisor[units]) {
-		remainder = do_div(blk_size, divisor[units]);
+	/* This is Napier's algorithm.  Reduce the original block size to
+	 *
+	 * coefficient * divisor[units]^i
+	 *
+	 * we do the reduction so both coefficients are just under 32 bits so
+	 * that multiplying them together won't overflow 64 bits and we keep
+	 * as much precision as possible in the numbers.
+	 *
+	 * Note: it's safe to throw away the remainders here because all the
+	 * precision is in the coefficients.
+	 */
+	while (blk_size >> 32) {
+		do_div(blk_size, divisor[units]);
 		i++;
 	}
 
-	exp = divisor[units] / (u32)blk_size;
-	/*
-	 * size must be strictly greater than exp here to ensure that remainder
-	 * is greater than divisor[units] coming out of the if below.
-	 */
-	if (size > exp) {
-		remainder = do_div(size, divisor[units]);
-		remainder *= blk_size;
+	while (size >> 32) {
+		do_div(size, divisor[units]);
 		i++;
-	} else {
-		remainder *= size;
 	}
 
+	/* now perform the actual multiplication keeping i as the sum of the
+	 * two logarithms */
 	size *= blk_size;
-	size += remainder / divisor[units];
-	remainder %= divisor[units];
 
+	/* and logarithmically reduce it until it's just under the divisor */
 	while (size >= divisor[units]) {
 		remainder = do_div(size, divisor[units]);
 		i++;
 	}
 
+	/* work out in j how many digits of precision we need from the
+	 * remainder */
 	sf_cap = size;
 	for (j = 0; sf_cap*10 < 1000; j++)
 		sf_cap *= 10;
 
-	if (j) {
+	if (units == STRING_UNITS_2) {
+		/* express the remainder as a decimal.  It's currently the
+		 * numerator of a fraction whose denominator is
+		 * divisor[units], which is 1 << 10 for STRING_UNITS_2 */
 		remainder *= 1000;
-		remainder /= divisor[units];
+		remainder >>= 10;
+	}
+
+	/* add a 5 to the digit below what will be printed to ensure
+	 * an arithmetical round up and carry it through to size */
+	remainder += rounding[j];
+	if (remainder >= 1000) {
+		remainder -= 1000;
+		size += 1;
+	}
+
+	if (j) {
 		snprintf(tmp, sizeof(tmp), ".%03u", remainder);
 		tmp[j+1] = '\0';
 	}