[PATCH v2 3/3] MIPS: ath79: flush the DDR write buffers of an interrupt in parallel

[Rosen Penev]

When several devices share a CPU interrupt, plat_irq_dispatch() flushes
their DDR write buffers one after the other, waiting for each to drain
before starting the next.

Make ath79_ddr_wb_flush() take a mask of channels, and start the flush
of every channel before waiting for any of them, so that the write
buffers drain in parallel. For a single channel the sequence is
unchanged. Its only user is the built-in irqchip, so drop the export.

Keep flushing twice, as the AR7100 datasheet asks, and quote it instead
of the comment that it must be run twice.

Suggested-by: Thomas Gleixner <tglx@xxxxxxxxxx>
Signed-off-by: Rosen Penev <rosenp@xxxxxxxxx>
---
 arch/mips/ath79/common.c                 | 51 ++++++++++++++++++------
 arch/mips/include/asm/mach-ath79/ath79.h |  2 +-
 drivers/irqchip/irq-ath79-cpu.c          | 13 +++---
 3 files changed, 45 insertions(+), 21 deletions(-)

diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index 137abbc65c60..9c5e9cd6931a 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -9,6 +9,7 @@
  *  Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP
  */
 
+#include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/types.h>
@@ -53,21 +54,47 @@ void ath79_ddr_ctrl_init(void)
 }
 EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);
 
-void ath79_ddr_wb_flush(u32 reg)
+static void __ath79_ddr_wb_flush(unsigned long chans)
 {
-	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
-
-	/* Flush the DDR write buffer. */
-	__raw_writel(0x1, flush_reg);
-	while (__raw_readl(flush_reg) & 0x1)
-		;
+	u32 __iomem *base = ath79_ddr_wb_flush_base;
+	unsigned int chan;
+
+	/*
+	 * Start every flush before waiting for any of them, so that the
+	 * write buffers drain in parallel instead of one after the other.
+	 */
+	for_each_set_bit(chan, &chans, 32)
+		__raw_writel(0x1, base + chan);
+
+	for_each_set_bit(chan, &chans, 32)
+		while (__raw_readl(base + chan) & 0x1)
+			;
+}
 
-	/* It must be run twice. */
-	__raw_writel(0x1, flush_reg);
-	while (__raw_readl(flush_reg) & 0x1)
-		;
+/**
+ * ath79_ddr_wb_flush - flush DDR write buffers
+ * @chans: mask of the write buffer channels to flush
+ *
+ * Every DMA master of the SoC (the Ethernet MACs, USB, PCIe, WMAC) writes
+ * to DDR through its own write buffer in the DDR controller. The buffer
+ * may still hold data when the device raises its interrupt, so it has to
+ * be flushed before the interrupt handler looks at the DMA'd memory.
+ * Setting bit 0 of the channel's flush register starts the flush, and the
+ * controller clears it once the buffer is empty.
+ */
+void ath79_ddr_wb_flush(unsigned long chans)
+{
+	/*
+	 * The AR7100 datasheet says to flush twice, after reading the
+	 * interrupt status of the device, to ensure that its descriptor
+	 * updates have reached memory before software reads them. It does
+	 * not say why a single flush is not enough. The datasheets of the
+	 * later SoCs drop the note, but nothing says the need went away, so
+	 * flush twice on all of them.
+	 */
+	__ath79_ddr_wb_flush(chans);
+	__ath79_ddr_wb_flush(chans);
 }
-EXPORT_SYMBOL_GPL(ath79_ddr_wb_flush);
 
 void ath79_ddr_set_pci_windows(void)
 {
diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h
index 70cda74494a4..15897d0f570d 100644
--- a/arch/mips/include/asm/mach-ath79/ath79.h
+++ b/arch/mips/include/asm/mach-ath79/ath79.h
@@ -145,7 +145,7 @@ static inline int soc_is_qca956x(void)
 	return soc_is_qca9561() || soc_is_qca9563();
 }
 
-void ath79_ddr_wb_flush(unsigned int reg);
+void ath79_ddr_wb_flush(unsigned long chans);
 void ath79_ddr_set_pci_windows(void);
 
 extern void __iomem *ath79_pll_base;
diff --git a/drivers/irqchip/irq-ath79-cpu.c b/drivers/irqchip/irq-ath79-cpu.c
index ec39c37895c0..64272b15f4ed 100644
--- a/drivers/irqchip/irq-ath79-cpu.c
+++ b/drivers/irqchip/irq-ath79-cpu.c
@@ -10,7 +10,7 @@
  *  Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP
  */
 
-#include <linux/bitops.h>
+#include <linux/bits.h>
 #include <linux/interrupt.h>
 #include <linux/irqchip.h>
 #include <linux/of.h>
@@ -44,8 +44,8 @@ static u32 irq_wb_chans[8];
 
 asmlinkage void plat_irq_dispatch(void)
 {
-	unsigned long pending, chans;
-	int irq, chan;
+	unsigned long pending;
+	int irq;
 
 	pending = read_c0_status() & read_c0_cause() & ST0_IM;
 
@@ -57,11 +57,8 @@ asmlinkage void plat_irq_dispatch(void)
 	pending >>= CAUSEB_IP;
 	while (pending) {
 		irq = fls(pending) - 1;
-		if (irq < ARRAY_SIZE(irq_wb_chans)) {
-			chans = irq_wb_chans[irq];
-			for_each_set_bit(chan, &chans, 32)
-				ath79_ddr_wb_flush(chan);
-		}
+		if (irq < ARRAY_SIZE(irq_wb_chans) && irq_wb_chans[irq])
+			ath79_ddr_wb_flush(irq_wb_chans[irq]);
 		do_IRQ(MIPS_CPU_IRQ_BASE + irq);
 		pending &= ~BIT(irq);
 	}
-- 
2.56.0