Merge intel.com:/data/home/aegl/BK/Linus

into intel.com:/data/home/aegl/BK/linux-ia64-release-2.6.11

11 files changed, 239 insertions, 15 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 0b87da9d55b57a..bd846b6596d2fd 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -61,11 +61,12 @@ config IA64_GENERIC
 	  will run on any supported IA-64 system.  However, if you configure
 	  a kernel for your specific system, it will be faster and smaller.
 
-	  generic	 For any supported IA-64 system
-	  DIG-compliant	 For DIG ("Developer's Interface Guide") compliant systems
-	  HP-zx1/sx1000	 For HP systems
-	  SGI-SN2	 For SGI Altix systems
-	  Ski-simulator  For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
+	  generic		For any supported IA-64 system
+	  DIG-compliant		For DIG ("Developer's Interface Guide") compliant systems
+	  HP-zx1/sx1000		For HP systems
+	  HP-zx1/sx1000+swiotlb	For HP systems with (broken) DMA-constrained devices.
+	  SGI-SN2		For SGI Altix systems
+	  Ski-simulator		For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
 
 	  If you don't know what to do, choose "generic".
 
@@ -78,6 +79,15 @@ config IA64_HP_ZX1
 	  Build a kernel that runs on HP zx1 and sx1000 systems.  This adds
 	  support for the HP I/O MMU.
 
+config IA64_HP_ZX1_SWIOTLB
+	bool "HP-zx1/sx1000 with software I/O TLB"
+	help
+	  Build a kernel that runs on HP zx1 and sx1000 systems even when they
+	  have broken PCI devices which cannot DMA to full 32 bits.  Apart
+	  from support for the HP I/O MMU, this includes support for the software
+	  I/O TLB, which allows supporting the broken devices at the expense of
+	  wasting some kernel memory (about 2MB by default).
+
 config IA64_SGI_SN2
 	bool "SGI-SN2"
 	help
@@ -188,7 +198,7 @@ config HOLES_IN_ZONE
 
 config DISCONTIGMEM
 	bool "Discontiguous memory support"
-	depends on (IA64_DIG || IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1) && NUMA && VIRTUAL_MEM_MAP
+	depends on (IA64_DIG || IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB) && NUMA && VIRTUAL_MEM_MAP
 	default y if (IA64_SGI_SN2 || IA64_GENERIC) && NUMA
 	help
 	  Say Y to support efficient handling of discontiguous physical memory,
@@ -326,7 +336,7 @@ menu "Power management and ACPI"
 
 config PM
 	bool "Power Management support"
-	depends on IA64_GENERIC || IA64_DIG || IA64_HP_ZX1
+	depends on IA64_GENERIC || IA64_DIG || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB
 	default y
 	help
 	  "Power Management" means that parts of your computer are shut
diff --git a/arch/ia64/Kconfig.debug b/arch/ia64/Kconfig.debug
index 19edc8b2c61d8c..de9d507ba0fd46 100644
--- a/arch/ia64/Kconfig.debug
+++ b/arch/ia64/Kconfig.debug
@@ -16,7 +16,7 @@ config IA64_GRANULE_16MB
 
 config IA64_GRANULE_64MB
 	bool "64MB"
-	depends on !(IA64_GENERIC || IA64_HP_ZX1 || IA64_SGI_SN2)
+	depends on !(IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_SGI_SN2)
 
 endchoice
 
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index 2932ac71bd0b0f..c0b3d95d0f81fe 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -57,11 +57,13 @@ core-$(CONFIG_IA32_SUPPORT)	+= arch/ia64/ia32/
 core-$(CONFIG_IA64_DIG) 	+= arch/ia64/dig/
 core-$(CONFIG_IA64_GENERIC) 	+= arch/ia64/dig/
 core-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/dig/
+core-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += arch/ia64/dig/
 core-$(CONFIG_IA64_SGI_SN2)	+= arch/ia64/sn/
 
 drivers-$(CONFIG_PCI)		+= arch/ia64/pci/
 drivers-$(CONFIG_IA64_HP_SIM)	+= arch/ia64/hp/sim/
 drivers-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/
+drivers-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += arch/ia64/hp/common/ arch/ia64/hp/zx1/
 drivers-$(CONFIG_IA64_GENERIC)	+= arch/ia64/hp/common/ arch/ia64/hp/zx1/ arch/ia64/hp/sim/ arch/ia64/sn/
 drivers-$(CONFIG_OPROFILE)	+= arch/ia64/oprofile/
 
diff --git a/arch/ia64/hp/common/Makefile b/arch/ia64/hp/common/Makefile
index e7c7133c7ca773..f61a60057ff7dd 100644
--- a/arch/ia64/hp/common/Makefile
+++ b/arch/ia64/hp/common/Makefile
@@ -6,3 +6,5 @@
 #
 
 obj-y := sba_iommu.o
+obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += hwsw_iommu.o
+obj-$(CONFIG_IA64_GENERIC) += hwsw_iommu.o
diff --git a/arch/ia64/hp/zx1/Makefile b/arch/ia64/hp/zx1/Makefile
index 64e39aa82a3fd9..61e878729d1ed2 100644
--- a/arch/ia64/hp/zx1/Makefile
+++ b/arch/ia64/hp/zx1/Makefile
@@ -5,4 +5,4 @@
 # Copyright (C) Alex Williamson (alex_williamson@hp.com)
 #
 
-obj-$(CONFIG_IA64_GENERIC) += hpzx1_machvec.o
+obj-$(CONFIG_IA64_GENERIC) += hpzx1_machvec.o hpzx1_swiotlb_machvec.o
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 12d8bf976cc254..c1a02bbc252c7b 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -12,6 +12,7 @@ obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o i
 obj-$(CONFIG_IA64_BRL_EMU)	+= brl_emu.o
 obj-$(CONFIG_IA64_GENERIC)	+= acpi-ext.o
 obj-$(CONFIG_IA64_HP_ZX1)	+= acpi-ext.o
+obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += acpi-ext.o
 obj-$(CONFIG_IA64_PALINFO)	+= palinfo.o
 obj-$(CONFIG_IOSAPIC)		+= iosapic.o
 obj-$(CONFIG_MODULES)		+= module.o
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index baa9c1eee662a5..ca062b9628ab3c 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -113,6 +113,8 @@ acpi_get_sysname (void)
 	return "hpsim";
 # elif defined (CONFIG_IA64_HP_ZX1)
 	return "hpzx1";
+# elif defined (CONFIG_IA64_HP_ZX1_SWIOTLB)
+	return "hpzx1_swiotlb";
 # elif defined (CONFIG_IA64_SGI_SN2)
 	return "sn2";
 # elif defined (CONFIG_IA64_DIG)
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 7b2033bf09546b..d35bda31d23847 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -1,7 +1,7 @@
 /*
  * Architecture-specific setup.
  *
- * Copyright (C) 1998-2001, 2003 Hewlett-Packard Co
+ * Copyright (C) 1998-2001, 2003-2004 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  *	Stephane Eranian <eranian@hpl.hp.com>
  * Copyright (C) 2000, Rohit Seth <rohit.seth@intel.com>
@@ -312,7 +312,28 @@ setup_arch (char **cmdline_p)
 	io_port_init();
 
 #ifdef CONFIG_IA64_GENERIC
-	machvec_init(acpi_get_sysname());
+	{
+		const char *mvec_name = strstr (*cmdline_p, "machvec=");
+		char str[64];
+
+		if (mvec_name) {
+			const char *end;
+			size_t len;
+
+			mvec_name += 8;
+			end = strchr (mvec_name, ' ');
+			if (end)
+				len = end - mvec_name;
+			else
+				len = strlen (mvec_name);
+			len = min(len, sizeof (str) - 1);
+			strncpy (str, mvec_name, len);
+			str[len] = '\0';
+			mvec_name = str;
+		} else
+			mvec_name = acpi_get_sysname();
+		machvec_init(mvec_name);
+	}
 #endif
 
 	if (early_console_setup(*cmdline_p) == 0)
diff --git a/arch/ia64/lib/swiotlb.c b/arch/ia64/lib/swiotlb.c
index e4770828db5971..d38b01538184bd 100644
--- a/arch/ia64/lib/swiotlb.c
+++ b/arch/ia64/lib/swiotlb.c
@@ -61,9 +61,8 @@ static char *io_tlb_start, *io_tlb_end;
 /*
  * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and
  * io_tlb_end.  This is command line adjustable via setup_io_tlb_npages.
- * Default to 64MB.
  */
-static unsigned long io_tlb_nslabs = 32768;
+static unsigned long io_tlb_nslabs;
 
 /*
  * When the IOMMU overflows we return a fallback buffer. This sets the size.
@@ -113,10 +112,15 @@ __setup("swiotlb=", setup_io_tlb_npages);
  * structures for the software IO TLB used to implement the PCI DMA API.
  */
 void
-swiotlb_init(void)
+swiotlb_init_with_default_size (size_t default_size)
 {
 	unsigned long i;
 
+	if (!io_tlb_nslabs) {
+		io_tlb_nslabs = (default_size >> PAGE_SHIFT);
+		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+	}
+
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
@@ -145,6 +149,12 @@ swiotlb_init(void)
 	       virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end));
 }
 
+void
+swiotlb_init (void)
+{
+	swiotlb_init_with_default_size(64 * (1<<20));	/* default to 64MB */
+}
+
 static inline int
 address_needs_mapping(struct device *hwdev, dma_addr_t addr)
 {
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 01f8eabf3636be..edc8915bb4159b 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2002 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  *	Bjorn Helgaas <bjorn_helgaas@hp.com>
+ * Copyright (C) 2004 Silicon Graphics, Inc.
  *
  * Note: Above list of copyright holders is incomplete...
  */
@@ -526,7 +527,7 @@ pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 	 * Leave vm_pgoff as-is, the PCI space address is the physical
 	 * address on this platform.
 	 */
-	vma->vm_flags |= (VM_SHM | VM_LOCKED | VM_IO);
+	vma->vm_flags |= (VM_SHM | VM_RESERVED | VM_IO);
 
 	if (write_combine)
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
@@ -541,6 +542,117 @@ pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 }
 
 /**
+ * pci_mmap_legacy_page_range - map legacy memory space to userland
+ * @bus: bus whose legacy space we're mapping
+ * @vma: vma passed in by mmap
+ *
+ * Map legacy memory space for this device back to userspace using a machine
+ * vector to get the base address.
+ */
+int
+pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma)
+{
+	char *addr;
+
+	addr = pci_get_legacy_mem(bus);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
+	vma->vm_pgoff += (unsigned long)addr >> PAGE_SHIFT;
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_flags |= (VM_SHM | VM_RESERVED | VM_IO);
+
+	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			    vma->vm_end - vma->vm_start, vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+/**
+ * ia64_pci_get_legacy_mem - generic legacy mem routine
+ * @bus: bus to get legacy memory base address for
+ *
+ * Find the base of legacy memory for @bus.  This is typically the first
+ * megabyte of bus address space for @bus or is simply 0 on platforms whose
+ * chipsets support legacy I/O and memory routing.  Returns the base address
+ * or an error pointer if an error occurred.
+ *
+ * This is the ia64 generic version of this routine.  Other platforms
+ * are free to override it with a machine vector.
+ */
+char *ia64_pci_get_legacy_mem(struct pci_bus *bus)
+{
+	return (char *)__IA64_UNCACHED_OFFSET;
+}
+
+/**
+ * ia64_pci_legacy_read - read from legacy I/O space
+ * @bus: bus to read
+ * @port: legacy port value
+ * @val: caller allocated storage for returned value
+ * @size: number of bytes to read
+ *
+ * Simply reads @size bytes from @port and puts the result in @val.
+ *
+ * Again, this (and the write routine) are generic versions that can be
+ * overridden by the platform.  This is necessary on platforms that don't
+ * support legacy I/O routing or that hard fail on legacy I/O timeouts.
+ */
+int ia64_pci_legacy_read(struct pci_bus *bus, u16 port, u32 *val, u8 size)
+{
+	int ret = size;
+
+	switch (size) {
+	case 1:
+		*val = inb(port);
+		break;
+	case 2:
+		*val = inw(port);
+		break;
+	case 4:
+		*val = inl(port);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * ia64_pci_legacy_write - perform a legacy I/O write
+ * @bus: bus pointer
+ * @port: port to write
+ * @val: value to write
+ * @size: number of bytes to write from @val
+ *
+ * Simply writes @size bytes of @val to @port.
+ */
+int ia64_pci_legacy_write(struct pci_dev *bus, u16 port, u32 val, u8 size)
+{
+	int ret = 0;
+
+	switch (size) {
+	case 1:
+		outb(val, port);
+		break;
+	case 2:
+		outw(val, port);
+		break;
+	case 4:
+		outl(val, port);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+/**
  * pci_cacheline_size - determine cacheline size for PCI devices
  * @dev: void
  *
diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index 71f311dc04c3bd..4187f920d26d17 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -475,3 +475,67 @@ EXPORT_SYMBOL(sn_pci_alloc_consistent);
 EXPORT_SYMBOL(sn_pci_free_consistent);
 EXPORT_SYMBOL(sn_pci_dma_supported);
 EXPORT_SYMBOL(sn_dma_mapping_error);
+
+char *sn_pci_get_legacy_mem(struct pci_bus *bus)
+{
+	if (!SN_PCIBUS_BUSSOFT(bus))
+		return ERR_PTR(-ENODEV);
+
+	return (char *)(SN_PCIBUS_BUSSOFT(bus)->bs_legacy_mem | __IA64_UNCACHED_OFFSET);
+}
+
+int sn_pci_legacy_read(struct pci_bus *bus, u16 port, u32 *val, u8 size)
+{
+	unsigned long addr;
+	int ret;
+
+	if (!SN_PCIBUS_BUSSOFT(bus))
+		return -ENODEV;
+
+	addr = SN_PCIBUS_BUSSOFT(bus)->bs_legacy_io | __IA64_UNCACHED_OFFSET;
+	addr += port;
+
+	ret = ia64_sn_probe_mem(addr, (long)size, (void *)val);
+
+	if (ret == 2)
+		return -EINVAL;
+
+	if (ret == 1)
+		*val = -1;
+
+	return size;
+}
+
+int sn_pci_legacy_write(struct pci_bus *bus, u16 port, u32 val, u8 size)
+{
+	int ret = size;
+	unsigned long paddr;
+	unsigned long *addr;
+
+	if (!SN_PCIBUS_BUSSOFT(bus)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/* Put the phys addr in uncached space */
+	paddr = SN_PCIBUS_BUSSOFT(bus)->bs_legacy_io | __IA64_UNCACHED_OFFSET;
+	paddr += port;
+	addr = (unsigned long *)paddr;
+
+	switch (size) {
+	case 1:
+		*(volatile u8 *)(addr) = (u8)(val);
+		break;
+	case 2:
+		*(volatile u16 *)(addr) = (u16)(val);
+		break;
+	case 4:
+		*(volatile u32 *)(addr) = (u32)(val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+ out:
+	return ret;
+}