Merge git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile

Pull arch/tile updates from Chris Metcalf:
 "These changes provide support for PCIe root complex and USB host mode
  for tilegx's on-chip I/Os.

  In addition, this pull provides the required underpinning for the
  on-chip networking support that was pulled into 3.5.  The changes have
  all been through LKML (with several rounds for PCIe RC) and on
  linux-next."

* git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
  tile: updates to pci root complex from community feedback
  bounce: allow use of bounce pool via config option
  usb: add host support for the tilegx architecture
  arch/tile: provide kernel support for the tilegx USB shim
  tile pci: enable IOMMU to support DMA for legacy devices
  arch/tile: enable ZONE_DMA for tilegx
  tilegx pci: support I/O to arbitrarily-cached pages
  tile: remove unused header
  arch/tile: tilegx PCI root complex support
  arch/tile: provide kernel support for the tilegx TRIO shim
  arch/tile: break out the "csum a long" function to <asm/checksum.h>
  arch/tile: provide kernel support for the tilegx mPIPE shim
  arch/tile: common DMA code for the GXIO IORPC subsystem
  arch/tile: support MMIO-based readb/writeb etc.
  arch/tile: introduce GXIO IORPC framework for tilegx

arch/tile/Kconfig

@@ -3,6 +3,8 @@
 
 config TILE
 	def_bool y
+	select HAVE_DMA_ATTRS
+	select HAVE_DMA_API_DEBUG
 	select HAVE_KVM if !TILEGX
 	select GENERIC_FIND_FIRST_BIT
 	select USE_GENERIC_SMP_HELPERS
@@ -79,6 +81,9 @@ config ARCH_DMA_ADDR_T_64BIT
 config NEED_DMA_MAP_STATE
 	def_bool y
 
+config ARCH_HAS_DMA_SET_COHERENT_MASK
+	bool
+
 config LOCKDEP_SUPPORT
 	def_bool y
 
@@ -212,6 +217,22 @@ config HIGHMEM
 
 	  If unsure, say "true".
 
+config ZONE_DMA
+	def_bool y
+
+config IOMMU_HELPER
+	bool
+
+config NEED_SG_DMA_LENGTH
+	bool
+
+config SWIOTLB
+	bool
+	default TILEGX
+	select IOMMU_HELPER
+	select NEED_SG_DMA_LENGTH
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
+
 # We do not currently support disabling NUMA.
 config NUMA
 	bool # "NUMA Memory Allocation and Scheduler Support"
@@ -345,6 +366,8 @@ config KERNEL_PL
 	  kernel will be built to run at.  Generally you should use
 	  the default value here.
 
+source "arch/tile/gxio/Kconfig"
+
 endmenu  # Tilera-specific configuration
 
 menu "Bus options"
@@ -354,6 +377,9 @@ config PCI
 	default y
 	select PCI_DOMAINS
 	select GENERIC_PCI_IOMAP
+	select TILE_GXIO_TRIO if TILEGX
+	select ARCH_SUPPORTS_MSI if TILEGX
+	select PCI_MSI if TILEGX
 	---help---
 	  Enable PCI root complex support, so PCIe endpoint devices can
 	  be attached to the Tile chip.  Many, but not all, PCI devices
@@ -370,6 +396,22 @@ config NO_IOPORT
 
 source "drivers/pci/Kconfig"
 
+config TILE_USB
+	tristate "Tilera USB host adapter support"
+	default y
+	depends on USB
+	depends on TILEGX
+	select TILE_GXIO_USB_HOST
+	---help---
+	  Provides USB host adapter support for the built-in EHCI and OHCI
+	  interfaces on TILE-Gx chips.
+
+# USB OHCI needs the bounce pool since tilegx will often have more
+# than 4GB of memory, but we don't currently use the IOTLB to present
+# a 32-bit address to OHCI.  So we need to use a bounce pool instead.
+config NEED_BOUNCE_POOL
+	def_bool USB_OHCI_HCD
+
 config HOTPLUG
 	bool "Support for hot-pluggable devices"
 	---help---

arch/tile/Makefile

@@ -59,6 +59,8 @@ libs-y		+= $(LIBGCC_PATH)
 # See arch/tile/Kbuild for content of core part of the kernel
 core-y		+= arch/tile/
 
+core-$(CONFIG_TILE_GXIO) += arch/tile/gxio/
+
 ifdef TILERA_ROOT
 INSTALL_PATH ?= $(TILERA_ROOT)/tile/boot
 endif

arch/tile/gxio/Kconfig

@@ -0,0 +1,28 @@
+# Support direct access to TILE-Gx hardware from user space, via the
+# gxio library, or from kernel space, via kernel IORPC support.
+config TILE_GXIO
+	bool
+	depends on TILEGX
+
+# Support direct access to the common I/O DMA facility within the
+# TILE-Gx mPIPE and Trio hardware from kernel space.
+config TILE_GXIO_DMA
+	bool
+	select TILE_GXIO
+
+# Support direct access to the TILE-Gx mPIPE hardware from kernel space.
+config TILE_GXIO_MPIPE
+	bool
+	select TILE_GXIO
+	select TILE_GXIO_DMA
+
+# Support direct access to the TILE-Gx TRIO hardware from kernel space.
+config TILE_GXIO_TRIO
+	bool
+	select TILE_GXIO
+	select TILE_GXIO_DMA
+
+# Support direct access to the TILE-Gx USB hardware from kernel space.
+config TILE_GXIO_USB_HOST
+	bool
+	select TILE_GXIO

arch/tile/gxio/Makefile

@@ -0,0 +1,9 @@
+#
+# Makefile for the Tile-Gx device access support.
+#
+
+obj-$(CONFIG_TILE_GXIO) += iorpc_globals.o kiorpc.o
+obj-$(CONFIG_TILE_GXIO_DMA) += dma_queue.o
+obj-$(CONFIG_TILE_GXIO_MPIPE) += mpipe.o iorpc_mpipe.o iorpc_mpipe_info.o
+obj-$(CONFIG_TILE_GXIO_TRIO) += trio.o iorpc_trio.o
+obj-$(CONFIG_TILE_GXIO_USB_HOST) += usb_host.o iorpc_usb_host.o

arch/tile/gxio/dma_queue.c

@@ -0,0 +1,176 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/io.h>
+#include <linux/atomic.h>
+#include <linux/module.h>
+#include <gxio/dma_queue.h>
+
+/* Wait for a memory read to complete. */
+#define wait_for_value(val)                             \
+  __asm__ __volatile__("move %0, %0" :: "r"(val))
+
+/* The index is in the low 16. */
+#define DMA_QUEUE_INDEX_MASK ((1 << 16) - 1)
+
+/*
+ * The hardware descriptor-ring type.
+ * This matches the types used by mpipe (MPIPE_EDMA_POST_REGION_VAL_t)
+ * and trio (TRIO_PUSH_DMA_REGION_VAL_t or TRIO_PULL_DMA_REGION_VAL_t).
+ * See those types for more documentation on the individual fields.
+ */
+typedef union {
+	struct {
+#ifndef __BIG_ENDIAN__
+		uint64_t ring_idx:16;
+		uint64_t count:16;
+		uint64_t gen:1;
+		uint64_t __reserved:31;
+#else
+		uint64_t __reserved:31;
+		uint64_t gen:1;
+		uint64_t count:16;
+		uint64_t ring_idx:16;
+#endif
+	};
+	uint64_t word;
+} __gxio_ring_t;
+
+void __gxio_dma_queue_init(__gxio_dma_queue_t *dma_queue,
+			   void *post_region_addr, unsigned int num_entries)
+{
+	/*
+	 * Limit 65536 entry rings to 65535 credits because we only have a
+	 * 16 bit completion counter.
+	 */
+	int64_t credits = (num_entries < 65536) ? num_entries : 65535;
+
+	memset(dma_queue, 0, sizeof(*dma_queue));
+
+	dma_queue->post_region_addr = post_region_addr;
+	dma_queue->hw_complete_count = 0;
+	dma_queue->credits_and_next_index = credits << DMA_QUEUE_CREDIT_SHIFT;
+}
+
+EXPORT_SYMBOL_GPL(__gxio_dma_queue_init);
+
+void __gxio_dma_queue_update_credits(__gxio_dma_queue_t *dma_queue)
+{
+	__gxio_ring_t val;
+	uint64_t count;
+	uint64_t delta;
+	uint64_t new_count;
+
+	/*
+	 * Read the 64-bit completion count without touching the cache, so
+	 * we later avoid having to evict any sharers of this cache line
+	 * when we update it below.
+	 */
+	uint64_t orig_hw_complete_count =
+		cmpxchg(&dma_queue->hw_complete_count,
+			-1, -1);
+
+	/* Make sure the load completes before we access the hardware. */
+	wait_for_value(orig_hw_complete_count);
+
+	/* Read the 16-bit count of how many packets it has completed. */
+	val.word = __gxio_mmio_read(dma_queue->post_region_addr);
+	count = val.count;
+
+	/*
+	 * Calculate the number of completions since we last updated the
+	 * 64-bit counter.  It's safe to ignore the high bits because the
+	 * maximum credit value is 65535.
+	 */
+	delta = (count - orig_hw_complete_count) & 0xffff;
+	if (delta == 0)
+		return;
+
+	/*
+	 * Try to write back the count, advanced by delta.  If we race with
+	 * another thread, this might fail, in which case we return
+	 * immediately on the assumption that some credits are (or at least
+	 * were) available.
+	 */
+	new_count = orig_hw_complete_count + delta;
+	if (cmpxchg(&dma_queue->hw_complete_count,
+		    orig_hw_complete_count,
+		    new_count) != orig_hw_complete_count)
+		return;
+
+	/*
+	 * We succeeded in advancing the completion count; add back the
+	 * corresponding number of egress credits.
+	 */
+	__insn_fetchadd(&dma_queue->credits_and_next_index,
+			(delta << DMA_QUEUE_CREDIT_SHIFT));
+}
+
+EXPORT_SYMBOL_GPL(__gxio_dma_queue_update_credits);
+
+/*
+ * A separate 'blocked' method for put() so that backtraces and
+ * profiles will clearly indicate that we're wasting time spinning on
+ * egress availability rather than actually posting commands.
+ */
+int64_t __gxio_dma_queue_wait_for_credits(__gxio_dma_queue_t *dma_queue,
+					  int64_t modifier)
+{
+	int backoff = 16;
+	int64_t old;
+
+	do {
+		int i;
+		/* Back off to avoid spamming memory networks. */
+		for (i = backoff; i > 0; i--)
+			__insn_mfspr(SPR_PASS);
+
+		/* Check credits again. */
+		__gxio_dma_queue_update_credits(dma_queue);
+		old = __insn_fetchaddgez(&dma_queue->credits_and_next_index,
+					 modifier);
+
+		/* Calculate bounded exponential backoff for next iteration. */
+		if (backoff < 256)
+			backoff *= 2;
+	} while (old + modifier < 0);
+
+	return old;
+}
+
+EXPORT_SYMBOL_GPL(__gxio_dma_queue_wait_for_credits);
+
+int64_t __gxio_dma_queue_reserve_aux(__gxio_dma_queue_t *dma_queue,
+				     unsigned int num, int wait)
+{
+	return __gxio_dma_queue_reserve(dma_queue, num, wait != 0, true);
+}
+
+EXPORT_SYMBOL_GPL(__gxio_dma_queue_reserve_aux);
+
+int __gxio_dma_queue_is_complete(__gxio_dma_queue_t *dma_queue,
+				 int64_t completion_slot, int update)
+{
+	if (update) {
+		if (ACCESS_ONCE(dma_queue->hw_complete_count) >
+		    completion_slot)
+			return 1;
+
+		__gxio_dma_queue_update_credits(dma_queue);
+	}
+
+	return ACCESS_ONCE(dma_queue->hw_complete_count) > completion_slot;
+}
+
+EXPORT_SYMBOL_GPL(__gxio_dma_queue_is_complete);

arch/tile/gxio/iorpc_globals.c

@@ -0,0 +1,89 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/* This file is machine-generated; DO NOT EDIT! */
+#include "gxio/iorpc_globals.h"
+
+struct arm_pollfd_param {
+	union iorpc_pollfd pollfd;
+};
+
+int __iorpc_arm_pollfd(int fd, int pollfd_cookie)
+{
+	struct arm_pollfd_param temp;
+	struct arm_pollfd_param *params = &temp;
+
+	params->pollfd.kernel.cookie = pollfd_cookie;
+
+	return hv_dev_pwrite(fd, 0, (HV_VirtAddr) params, sizeof(*params),
+			     IORPC_OP_ARM_POLLFD);
+}
+
+EXPORT_SYMBOL(__iorpc_arm_pollfd);
+
+struct close_pollfd_param {
+	union iorpc_pollfd pollfd;
+};
+
+int __iorpc_close_pollfd(int fd, int pollfd_cookie)
+{
+	struct close_pollfd_param temp;
+	struct close_pollfd_param *params = &temp;
+
+	params->pollfd.kernel.cookie = pollfd_cookie;
+
+	return hv_dev_pwrite(fd, 0, (HV_VirtAddr) params, sizeof(*params),
+			     IORPC_OP_CLOSE_POLLFD);
+}
+
+EXPORT_SYMBOL(__iorpc_close_pollfd);
+
+struct get_mmio_base_param {
+	HV_PTE base;
+};
+
+int __iorpc_get_mmio_base(int fd, HV_PTE *base)
+{
+	int __result;
+	struct get_mmio_base_param temp;
+	struct get_mmio_base_param *params = &temp;
+
+	__result =
+	    hv_dev_pread(fd, 0, (HV_VirtAddr) params, sizeof(*params),
+			 IORPC_OP_GET_MMIO_BASE);
+	*base = params->base;
+
+	return __result;
+}
+
+EXPORT_SYMBOL(__iorpc_get_mmio_base);
+
+struct check_mmio_offset_param {
+	unsigned long offset;
+	unsigned long size;
+};
+
+int __iorpc_check_mmio_offset(int fd, unsigned long offset, unsigned long size)
+{
+	struct check_mmio_offset_param temp;
+	struct check_mmio_offset_param *params = &temp;
+
+	params->offset = offset;
+	params->size = size;
+
+	return hv_dev_pwrite(fd, 0, (HV_VirtAddr) params, sizeof(*params),
+			     IORPC_OP_CHECK_MMIO_OFFSET);
+}
+
+EXPORT_SYMBOL(__iorpc_check_mmio_offset);