gpiolib: Identify arrays matching GPIO hardware

Certain GPIO array lookup results may map directly to GPIO pins of a
single GPIO chip in hardware order.  If that condition is recognized
and handled efficiently, significant performance gain of get/set array
functions may be possible.

While processing a request for an array of GPIO descriptors, identify
those which represent corresponding pins of a single GPIO chip.  Skip
over pins which require open source or open drain special processing.
Moreover, identify pins which require inversion.  Pass a pointer to
that information with the array to the caller so it can benefit from
enhanced performance as soon as get/set array functions can accept and
make efficient use of it.

Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Janusz Krzysztofik <jmkrzyszt@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

2 files changed, 80 insertions, 1 deletions

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index b66b2191c5c5..141f39308a53 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -4174,7 +4174,9 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 {
 	struct gpio_desc *desc;
 	struct gpio_descs *descs;
-	int count;
+	struct gpio_array *array_info = NULL;
+	struct gpio_chip *chip;
+	int count, bitmap_size;
 
 	count = gpiod_count(dev, con_id);
 	if (count < 0)
@@ -4190,9 +4192,77 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 			gpiod_put_array(descs);
 			return ERR_CAST(desc);
 		}
+
 		descs->desc[descs->ndescs] = desc;
+
+		chip = gpiod_to_chip(desc);
+		/*
+		 * Select a chip of first array member
+		 * whose index matches its pin hardware number
+		 * as a candidate for fast bitmap processing.
+		 */
+		if (!array_info && gpio_chip_hwgpio(desc) == descs->ndescs) {
+			struct gpio_descs *array;
+
+			bitmap_size = BITS_TO_LONGS(chip->ngpio > count ?
+						    chip->ngpio : count);
+
+			array = kzalloc(struct_size(descs, desc, count) +
+					struct_size(array_info, invert_mask,
+					3 * bitmap_size), GFP_KERNEL);
+			if (!array) {
+				gpiod_put_array(descs);
+				return ERR_PTR(-ENOMEM);
+			}
+
+			memcpy(array, descs,
+			       struct_size(descs, desc, descs->ndescs + 1));
+			kfree(descs);
+
+			descs = array;
+			array_info = (void *)(descs->desc + count);
+			array_info->get_mask = array_info->invert_mask +
+						  bitmap_size;
+			array_info->set_mask = array_info->get_mask +
+						  bitmap_size;
+
+			array_info->desc = descs->desc;
+			array_info->size = count;
+			array_info->chip = chip;
+			bitmap_set(array_info->get_mask, descs->ndescs,
+				   count - descs->ndescs);
+			bitmap_set(array_info->set_mask, descs->ndescs,
+				   count - descs->ndescs);
+			descs->info = array_info;
+		}
+		/*
+		 * Unmark members which don't qualify for fast bitmap
+		 * processing (different chip, not in hardware order)
+		 */
+		if (array_info && (chip != array_info->chip ||
+		    gpio_chip_hwgpio(desc) != descs->ndescs)) {
+			__clear_bit(descs->ndescs, array_info->get_mask);
+			__clear_bit(descs->ndescs, array_info->set_mask);
+		} else if (array_info) {
+			/* Exclude open drain or open source from fast output */
+			if (gpiochip_line_is_open_drain(chip, descs->ndescs) ||
+			    gpiochip_line_is_open_source(chip, descs->ndescs))
+				__clear_bit(descs->ndescs,
+					    array_info->set_mask);
+			/* Identify 'fast' pins which require invertion */
+			if (gpiod_is_active_low(desc))
+				__set_bit(descs->ndescs,
+					  array_info->invert_mask);
+		}
+
 		descs->ndescs++;
 	}
+	if (array_info)
+		dev_dbg(dev,
+			"GPIO array info: chip=%s, size=%d, get_mask=%lx, set_mask=%lx, invert_mask=%lx\n",
+			array_info->chip->label, array_info->size,
+			*array_info->get_mask, *array_info->set_mask,
+			*array_info->invert_mask);
 	return descs;
 }
 EXPORT_SYMBOL_GPL(gpiod_get_array);
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 11e83d2eef89..b60905d558b1 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -183,6 +183,15 @@ static inline bool acpi_can_fallback_to_crs(struct acpi_device *adev,
 }
 #endif
 
+struct gpio_array {
+	struct gpio_desc	**desc;
+	unsigned int		size;
+	struct gpio_chip	*chip;
+	unsigned long		*get_mask;
+	unsigned long		*set_mask;
+	unsigned long		invert_mask[];
+};
+
 struct gpio_desc *gpiochip_get_desc(struct gpio_chip *chip, u16 hwnum);
 int gpiod_get_array_value_complex(bool raw, bool can_sleep,
 				  unsigned int array_size,