diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 73bcf806af0ec..45b83aecc56c1 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -787,6 +787,21 @@ static void sunxi_pmx_set(struct pinctrl_dev *pctldev,
 	writel((readl(pctl->membase + reg) & ~mask) | config << shift,
 	       pctl->membase + reg);
 
+	/*
+	 * A pin muxed to gpio_out directly through a pinmux node bypasses
+	 * sunxi_pinctrl_gpio_set() and drives whatever its output latch
+	 * holds.  Now that the pin is in output mode the data register
+	 * reads back the latch, so refresh the shadow to keep such pins
+	 * driving their pre-existing level.
+	 */
+	if (config == SUN4I_FUNC_OUTPUT) {
+		u32 *shadow = &pctl->dat_shadow[pin / PINS_PER_BANK];
+
+		sunxi_data_reg(pctl, pin, &reg, &shift, &mask);
+		*shadow = (*shadow & ~mask) |
+			  (readl(pctl->membase + reg) & mask);
+	}
+
 	raw_spin_unlock_irqrestore(&pctl->lock, flags);
 }
 
@@ -943,21 +958,29 @@ static void sunxi_pinctrl_gpio_set(struct gpio_chip *chip,
 				unsigned offset, int value)
 {
 	struct sunxi_pinctrl *pctl = gpiochip_get_data(chip);
-	u32 reg, shift, mask, val;
+	u32 *shadow = &pctl->dat_shadow[offset / PINS_PER_BANK];
+	u32 reg, shift, mask;
 	unsigned long flags;
 
 	sunxi_data_reg(pctl, offset, &reg, &shift, &mask);
 
 	raw_spin_lock_irqsave(&pctl->lock, flags);
 
-	val = readl(pctl->membase + reg);
-
+	/*
+	 * Reading the data register returns the pin level, not the output
+	 * latch, for pins muxed as inputs.  A read-modify-write based on
+	 * the register would therefore corrupt the latches of input-muxed
+	 * pins in the same bank (e.g. an emulated open-drain I2C line
+	 * released high), making them drive the wrong level once switched
+	 * to output.  Base the read-modify-write on a shadow copy of the
+	 * latches instead.
+	 */
 	if (value)
-		val |= mask;
+		*shadow |= mask;
 	else
-		val &= ~mask;
+		*shadow &= ~mask;
 
-	writel(val, pctl->membase + reg);
+	writel(*shadow, pctl->membase + reg);
 
 	raw_spin_unlock_irqrestore(&pctl->lock, flags);
 }
@@ -1481,7 +1504,7 @@ int sunxi_pinctrl_init_with_variant(struct platform_device *pdev,
 	struct pinctrl_pin_desc *pins;
 	struct sunxi_pinctrl *pctl;
 	struct pinmux_ops *pmxops;
-	int i, ret, last_pin, pin_idx;
+	int i, ret, last_pin, pin_idx, nbanks;
 	struct clk *clk;
 
 	pctl = devm_kzalloc(&pdev->dev, sizeof(*pctl), GFP_KERNEL);
@@ -1515,6 +1538,28 @@ int sunxi_pinctrl_init_with_variant(struct platform_device *pdev,
 	if (!pctl->irq_array)
 		return -ENOMEM;
 
+	/*
+	 * Seed the output latch shadow from the hardware so pins the
+	 * bootloader left in output mode keep their state; see
+	 * sunxi_pinctrl_gpio_set() for why a shadow is needed.  This must
+	 * happen before the pinctrl device registers, as pin hogs can mux
+	 * pins to gpio_out and thereby update the shadow.
+	 */
+	last_pin = pctl->desc->pins[pctl->desc->npins - 1].pin.number;
+	nbanks = (round_up(last_pin, PINS_PER_BANK) - pctl->desc->pin_base) /
+		 PINS_PER_BANK;
+	pctl->dat_shadow = devm_kcalloc(&pdev->dev, nbanks,
+					sizeof(*pctl->dat_shadow), GFP_KERNEL);
+	if (!pctl->dat_shadow)
+		return -ENOMEM;
+
+	for (i = 0; i < nbanks; i++) {
+		u32 reg, shift, mask;
+
+		sunxi_data_reg(pctl, i * PINS_PER_BANK, &reg, &shift, &mask);
+		pctl->dat_shadow[i] = readl(pctl->membase + reg);
+	}
+
 	ret = sunxi_pinctrl_build_state(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "dt probe failed: %d\n", ret);
@@ -1569,7 +1614,6 @@ int sunxi_pinctrl_init_with_variant(struct platform_device *pdev,
 	if (!pctl->chip)
 		return -ENOMEM;
 
-	last_pin = pctl->desc->pins[pctl->desc->npins - 1].pin.number;
 	pctl->chip->owner = THIS_MODULE;
 	pctl->chip->request = gpiochip_generic_request;
 	pctl->chip->free = gpiochip_generic_free;
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
index a87a2f944d609..244b0039480a0 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
@@ -80,6 +80,7 @@
 #define IO_BIAS_MASK		GENMASK(3, 0)
 
 #define SUN4I_FUNC_INPUT	0
+#define SUN4I_FUNC_OUTPUT	1
 #define SUN4I_FUNC_IRQ		6
 
 #define PINCTRL_SUN5I_A10S	BIT(1)
@@ -173,6 +174,12 @@ struct sunxi_pinctrl {
 	int				*irq;
 	unsigned			*irq_array;
 	raw_spinlock_t			lock;
+	/*
+	 * Output latch shadow, one word per bank.  Seeded lockless at
+	 * probe before the pinctrl device registers, protected by @lock
+	 * afterwards.
+	 */
+	u32				*dat_shadow;
 	struct pinctrl_dev		*pctl_dev;
 	unsigned long			variant;
 	u32				bank_mem_size;