thunderbolt: Add initial cactus ridge NHI support

Thunderbolt hotplug is supposed to be handled by the firmware. But Apple
decided to implement thunderbolt at the operating system level. The
firmare only initializes thunderbolt devices that are present at boot
time. This driver enables hotplug of thunderbolt of non-chained
thunderbolt devices on Apple systems with a cactus ridge controller.

This first patch adds the Kconfig file as well the parts of the driver
which talk directly to the hardware (that is pci device setup, interrupt
handling and RX/TX ring management).
Signed-off-by: Andreas Noever <andreas.noever@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/Kconfig

@@ -176,4 +176,6 @@ source "drivers/powercap/Kconfig"
 
 source "drivers/mcb/Kconfig"
 
+source "drivers/thunderbolt/Kconfig"
+
 endmenu

drivers/Makefile

@@ -158,3 +158,4 @@ obj-$(CONFIG_NTB)		+= ntb/
 obj-$(CONFIG_FMC)		+= fmc/
 obj-$(CONFIG_POWERCAP)		+= powercap/
 obj-$(CONFIG_MCB)		+= mcb/
+obj-$(CONFIG_THUNDERBOLT)	+= thunderbolt/

drivers/thunderbolt/Kconfig

+menuconfig THUNDERBOLT
+	tristate "Thunderbolt support for Apple devices"
+	default no
+	help
+	  Cactus Ridge Thunderbolt Controller driver
+	  This driver is required if you want to hotplug Thunderbolt devices on
+	  Apple hardware.
+
+	  Device chaining is currently not supported.
+
+	  To compile this driver a module, choose M here. The module will be
+	  called thunderbolt.

drivers/thunderbolt/Makefile

+obj-${CONFIG_THUNDERBOLT} := thunderbolt.o
+thunderbolt-objs := nhi.o
+

drivers/thunderbolt/nhi.h

+/*
+ * Thunderbolt Cactus Ridge driver - NHI driver
+ *
+ * Copyright (c) 2014 Andreas Noever <andreas.noever@gmail.com>
+ */
+
+#ifndef DSL3510_H_
+#define DSL3510_H_
+
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+
+/**
+ * struct tb_nhi - thunderbolt native host interface
+ */
+struct tb_nhi {
+	struct mutex lock; /*
+			    * Must be held during ring creation/destruction.
+			    * Is acquired by interrupt_work when dispatching
+			    * interrupts to individual rings.
+			    **/
+	struct pci_dev *pdev;
+	void __iomem *iobase;
+	struct tb_ring **tx_rings;
+	struct tb_ring **rx_rings;
+	struct work_struct interrupt_work;
+	u32 hop_count; /* Number of rings (end point hops) supported by NHI. */
+};
+
+/**
+ * struct tb_ring - thunderbolt TX or RX ring associated with a NHI
+ */
+struct tb_ring {
+	struct mutex lock; /* must be acquired after nhi->lock */
+	struct tb_nhi *nhi;
+	int size;
+	int hop;
+	int head; /* write next descriptor here */
+	int tail; /* complete next descriptor here */
+	struct ring_desc *descriptors;
+	dma_addr_t descriptors_dma;
+	struct list_head queue;
+	struct list_head in_flight;
+	struct work_struct work;
+	bool is_tx:1; /* rx otherwise */
+	bool running:1;
+};
+
+struct ring_frame;
+typedef void (*ring_cb)(struct tb_ring*, struct ring_frame*, bool canceled);
+
+/**
+ * struct ring_frame - for use with ring_rx/ring_tx
+ */
+struct ring_frame {
+	dma_addr_t buffer_phy;
+	ring_cb callback;
+	struct list_head list;
+	u32 size:12; /* TX: in, RX: out*/
+	u32 flags:12; /* RX: out */
+	u32 eof:4; /* TX:in, RX: out */
+	u32 sof:4; /* TX:in, RX: out */
+};
+
+#define TB_FRAME_SIZE 0x100    /* minimum size for ring_rx */
+
+struct tb_ring *ring_alloc_tx(struct tb_nhi *nhi, int hop, int size);
+struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size);
+void ring_start(struct tb_ring *ring);
+void ring_stop(struct tb_ring *ring);
+void ring_free(struct tb_ring *ring);
+
+int __ring_enqueue(struct tb_ring *ring, struct ring_frame *frame);
+
+/**
+ * ring_rx() - enqueue a frame on an RX ring
+ *
+ * frame->buffer, frame->buffer_phy and frame->callback have to be set. The
+ * buffer must contain at least TB_FRAME_SIZE bytes.
+ *
+ * frame->callback will be invoked with frame->size, frame->flags, frame->eof,
+ * frame->sof set once the frame has been received.
+ *
+ * If ring_stop is called after the packet has been enqueued frame->callback
+ * will be called with canceled set to true.
+ *
+ * Return: Returns ESHUTDOWN if ring_stop has been called. Zero otherwise.
+ */
+static inline int ring_rx(struct tb_ring *ring, struct ring_frame *frame)
+{
+	WARN_ON(ring->is_tx);
+	return __ring_enqueue(ring, frame);
+}
+
+/**
+ * ring_tx() - enqueue a frame on an TX ring
+ *
+ * frame->buffer, frame->buffer_phy, frame->callback, frame->size, frame->eof
+ * and frame->sof have to be set.
+ *
+ * frame->callback will be invoked with once the frame has been transmitted.
+ *
+ * If ring_stop is called after the packet has been enqueued frame->callback
+ * will be called with canceled set to true.
+ *
+ * Return: Returns ESHUTDOWN if ring_stop has been called. Zero otherwise.
+ */
+static inline int ring_tx(struct tb_ring *ring, struct ring_frame *frame)
+{
+	WARN_ON(!ring->is_tx);
+	return __ring_enqueue(ring, frame);
+}
+
+#endif

drivers/thunderbolt/nhi_regs.h

+/*
+ * Thunderbolt Cactus Ridge driver - NHI registers
+ *
+ * Copyright (c) 2014 Andreas Noever <andreas.noever@gmail.com>
+ */
+
+#ifndef DSL3510_REGS_H_
+#define DSL3510_REGS_H_
+
+#include <linux/types.h>
+
+enum ring_flags {
+	RING_FLAG_ISOCH_ENABLE = 1 << 27, /* TX only? */
+	RING_FLAG_E2E_FLOW_CONTROL = 1 << 28,
+	RING_FLAG_PCI_NO_SNOOP = 1 << 29,
+	RING_FLAG_RAW = 1 << 30, /* ignore EOF/SOF mask, include checksum */
+	RING_FLAG_ENABLE = 1 << 31,
+};
+
+enum ring_desc_flags {
+	RING_DESC_ISOCH = 0x1, /* TX only? */
+	RING_DESC_COMPLETED = 0x2, /* set by NHI */
+	RING_DESC_POSTED = 0x4, /* always set this */
+	RING_DESC_INTERRUPT = 0x8, /* request an interrupt on completion */
+};
+
+/**
+ * struct ring_desc - TX/RX ring entry
+ *
+ * For TX set length/eof/sof.
+ * For RX length/eof/sof are set by the NHI.
+ */
+struct ring_desc {
+	u64 phys;
+	u32 length:12;
+	u32 eof:4;
+	u32 sof:4;
+	enum ring_desc_flags flags:12;
+	u32 time; /* write zero */
+} __packed;
+
+/* NHI registers in bar 0 */
+
+/*
+ * 16 bytes per entry, one entry for every hop (REG_HOP_COUNT)
+ * 00: physical pointer to an array of struct ring_desc
+ * 08: ring tail (set by NHI)
+ * 10: ring head (index of first non posted descriptor)
+ * 12: descriptor count
+ */
+#define REG_TX_RING_BASE	0x00000
+
+/*
+ * 16 bytes per entry, one entry for every hop (REG_HOP_COUNT)
+ * 00: physical pointer to an array of struct ring_desc
+ * 08: ring head (index of first not posted descriptor)
+ * 10: ring tail (set by NHI)
+ * 12: descriptor count
+ * 14: max frame sizes (anything larger than 0x100 has no effect)
+ */
+#define REG_RX_RING_BASE	0x08000
+
+/*
+ * 32 bytes per entry, one entry for every hop (REG_HOP_COUNT)
+ * 00: enum_ring_flags
+ * 04: isoch time stamp ?? (write 0)
+ * ..: unknown
+ */
+#define REG_TX_OPTIONS_BASE	0x19800
+
+/*
+ * 32 bytes per entry, one entry for every hop (REG_HOP_COUNT)
+ * 00: enum ring_flags
+ *     If RING_FLAG_E2E_FLOW_CONTROL is set then bits 13-23 must be set to
+ *     the corresponding TX hop id.
+ * 04: EOF/SOF mask (ignored for RING_FLAG_RAW rings)
+ * ..: unknown
+ */
+#define REG_RX_OPTIONS_BASE	0x29800
+
+/*
+ * three bitfields: tx, rx, rx overflow
+ * Every bitfield contains one bit for every hop (REG_HOP_COUNT). Registers are
+ * cleared on read. New interrupts are fired only after ALL registers have been
+ * read (even those containing only disabled rings).
+ */
+#define REG_RING_NOTIFY_BASE	0x37800
+#define RING_NOTIFY_REG_COUNT(nhi) ((31 + 3 * nhi->hop_count) / 32)
+
+/*
+ * two bitfields: rx, tx
+ * Both bitfields contains one bit for every hop (REG_HOP_COUNT). To
+ * enable/disable interrupts set/clear the corresponding bits.
+ */
+#define REG_RING_INTERRUPT_BASE	0x38200
+#define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32)
+
+/* The last 11 bits contain the number of hops supported by the NHI port. */
+#define REG_HOP_COUNT		0x39640
+
+#endif