clk: tegra: Fix refcounting of gate clocks

The refcounting of the gate clocks has a bug causing the enable_refcnt
to underflow when unused clocks are disabled. This happens because clk
provider erroneously bumps the refcount if clock is enabled at a boot
time, which it shouldn't be doing, and it does this only for the gate
clocks, while peripheral clocks are using the same gate ops and the
peripheral clocks are missing the initial bump. Hence the refcount of
the peripheral clocks is 0 when unused clocks are disabled and then the
counter is decremented further by the gate ops, causing the integer
underflow.

Fix this problem by removing the erroneous bump and by implementing the
disable_unused() callback, which disables the unused gates properly.

The visible effect of the bug is such that the unused clocks are never
gated if a loaded kernel module grabs the unused clocks and starts to use
them. In practice this shouldn't cause any real problems for the drivers
and boards supported by the kernel today.

Acked-by: Thierry Reding <[e-mail]>
Signed-off-by: Dmitry Osipenko <[e-mail]>
Signed-off-by: Thierry Reding <[e-mail]>

drivers/clk/tegra/clk-periph-gate.c

···
 	return state;
 }
 
-static int clk_periph_enable(struct clk_hw *hw)
+static void clk_periph_enable_locked(struct clk_hw *hw)
 {
 	struct tegra_clk_periph_gate *gate = to_clk_periph_gate(hw);
-	unsigned long flags = 0;
-
-	spin_lock_irqsave(&periph_ref_lock, flags);
-
-	gate->enable_refcnt[gate->clk_num]++;
-	if (gate->enable_refcnt[gate->clk_num] > 1) {
-		spin_unlock_irqrestore(&periph_ref_lock, flags);
-		return 0;
-	}
 
 	write_enb_set(periph_clk_to_bit(gate), gate);
 	udelay(2);
···
 		udelay(1);
 		writel_relaxed(0, gate->clk_base + LVL2_CLK_GATE_OVRE);
 	}
+}
+
+static void clk_periph_disable_locked(struct clk_hw *hw)
+{
+	struct tegra_clk_periph_gate *gate = to_clk_periph_gate(hw);
+
+	/*
+	 * If peripheral is in the APB bus then read the APB bus to
+	 * flush the write operation in apb bus. This will avoid the
+	 * peripheral access after disabling clock
+	 */
+	if (gate->flags & TEGRA_PERIPH_ON_APB)
+		tegra_read_chipid();
+
+	write_enb_clr(periph_clk_to_bit(gate), gate);
+}
+
+static int clk_periph_enable(struct clk_hw *hw)
+{
+	struct tegra_clk_periph_gate *gate = to_clk_periph_gate(hw);
+	unsigned long flags = 0;
+
+	spin_lock_irqsave(&periph_ref_lock, flags);
+
+	if (!gate->enable_refcnt[gate->clk_num]++)
+		clk_periph_enable_locked(hw);
 
 	spin_unlock_irqrestore(&periph_ref_lock, flags);
 
···
 
 	spin_lock_irqsave(&periph_ref_lock, flags);
 
-	gate->enable_refcnt[gate->clk_num]--;
-	if (gate->enable_refcnt[gate->clk_num] > 0) {
-		spin_unlock_irqrestore(&periph_ref_lock, flags);
-		return;
-	}
+	WARN_ON(!gate->enable_refcnt[gate->clk_num]);
+
+	if (--gate->enable_refcnt[gate->clk_num] == 0)
+		clk_periph_disable_locked(hw);
+
+	spin_unlock_irqrestore(&periph_ref_lock, flags);
+}
+
+static void clk_periph_disable_unused(struct clk_hw *hw)
+{
+	struct tegra_clk_periph_gate *gate = to_clk_periph_gate(hw);
+	unsigned long flags = 0;
+
+	spin_lock_irqsave(&periph_ref_lock, flags);
 
 	/*
-	 * If peripheral is in the APB bus then read the APB bus to
-	 * flush the write operation in apb bus. This will avoid the
-	 * peripheral access after disabling clock
+	 * Some clocks are duplicated and some of them are marked as critical,
+	 * like fuse and fuse_burn for example, thus the enable_refcnt will
+	 * be non-zero here if the "unused" duplicate is disabled by CCF.
 	 */
-	if (gate->flags & TEGRA_PERIPH_ON_APB)
-		tegra_read_chipid();
-
-	write_enb_clr(periph_clk_to_bit(gate), gate);
+	if (!gate->enable_refcnt[gate->clk_num])
+		clk_periph_disable_locked(hw);
 
 	spin_unlock_irqrestore(&periph_ref_lock, flags);
 }
···
 	.is_enabled = clk_periph_is_enabled,
 	.enable = clk_periph_enable,
 	.disable = clk_periph_disable,
+	.disable_unused = clk_periph_disable_unused,
 };
 
 struct clk *tegra_clk_register_periph_gate(const char *name,
···
 	gate->flags = gate_flags;
 	gate->enable_refcnt = enable_refcnt;
 	gate->regs = pregs;
-
-	if (read_enb(gate) & periph_clk_to_bit(gate))
-		enable_refcnt[clk_num]++;
 
 	/* Data in .init is copied by clk_register(), so stack variable OK */
 	gate->hw.init = &init;

drivers/clk/tegra/clk-periph.c

···
 	gate_ops->disable(gate_hw);
 }
 
+static void clk_periph_disable_unused(struct clk_hw *hw)
+{
+	struct tegra_clk_periph *periph = to_clk_periph(hw);
+	const struct clk_ops *gate_ops = periph->gate_ops;
+	struct clk_hw *gate_hw = &periph->gate.hw;
+
+	gate_ops->disable_unused(gate_hw);
+}
+
 static void clk_periph_restore_context(struct clk_hw *hw)
 {
 	struct tegra_clk_periph *periph = to_clk_periph(hw);
···
 	.is_enabled = clk_periph_is_enabled,
 	.enable = clk_periph_enable,
 	.disable = clk_periph_disable,
+	.disable_unused = clk_periph_disable_unused,
 	.restore_context = clk_periph_restore_context,
 };
 
···
 	.is_enabled = clk_periph_is_enabled,
 	.enable = clk_periph_enable,
 	.disable = clk_periph_disable,
+	.disable_unused = clk_periph_disable_unused,
 	.restore_context = clk_periph_restore_context,
 };