Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6

* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6: (27 commits)
  [IA64] swiotlb abstraction (e.g. for Xen)
  [IA64] swiotlb cleanup
  [IA64] make swiotlb use bus_to_virt/virt_to_bus
  [IA64] swiotlb bug fixes
  [IA64] Hook up getcpu system call for IA64
  [IA64] clean up sparsemem memory_present call
  [IA64] show_mem() for IA64 sparsemem NUMA
  [IA64] missing exports hwsw_sync_...
  [IA64] virt_to_page() can be called with NULL arg
  [IA64] alignment bug in ldscript
  [IA64] register memory ranges in a consistent manner
  [IA64] Enable SWIOTLB only when needed
  [IA64-SGI] Check for TIO errors on shub2 Altix
  [IA64] remove bogus prototype ia64_esi_init()
  [IA64] Clear IRQ affinity when unregistered
  [IA64] fix ACPI Kconfig issues
  [IA64] Fix NULL-pointer dereference in ia64_machine_kexec()
  [IA64] find thread for user rbs address
  [IA64] use snprintf() on features field of /proc/cpuinfo
  [IA64] enable singlestep on system call
  ...

arch/ia64/Kconfig

@@ -11,6 +11,8 @@ menu "Processor type and features"
 
 config IA64
 	bool
+	select PCI if (!IA64_HP_SIM)
+	select ACPI if (!IA64_HP_SIM)
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
@@ -28,7 +30,6 @@ config MMU
 
 config SWIOTLB
        bool
-       default y
 
 config RWSEM_XCHGADD_ALGORITHM
 	bool
@@ -84,10 +85,9 @@ choice
 
 config IA64_GENERIC
 	bool "generic"
-	select ACPI
-	select PCI
 	select NUMA
 	select ACPI_NUMA
+	select SWIOTLB
 	help
 	  This selects the system type of your hardware.  A "generic" kernel
 	  will run on any supported IA-64 system.  However, if you configure
@@ -104,6 +104,7 @@ config IA64_GENERIC
 
 config IA64_DIG
 	bool "DIG-compliant"
+	select SWIOTLB
 
 config IA64_HP_ZX1
 	bool "HP-zx1/sx1000"
@@ -113,6 +114,7 @@ config IA64_HP_ZX1
 
 config IA64_HP_ZX1_SWIOTLB
 	bool "HP-zx1/sx1000 with software I/O TLB"
+	select SWIOTLB
 	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
@@ -131,6 +133,7 @@ config IA64_SGI_SN2
 
 config IA64_HP_SIM
 	bool "Ski-simulator"
+	select SWIOTLB
 
 endchoice
 

arch/ia64/hp/common/hwsw_iommu.c

@@ -192,3 +192,7 @@ EXPORT_SYMBOL(hwsw_unmap_sg);
 EXPORT_SYMBOL(hwsw_dma_supported);
 EXPORT_SYMBOL(hwsw_alloc_coherent);
 EXPORT_SYMBOL(hwsw_free_coherent);
+EXPORT_SYMBOL(hwsw_sync_single_for_cpu);
+EXPORT_SYMBOL(hwsw_sync_single_for_device);
+EXPORT_SYMBOL(hwsw_sync_sg_for_cpu);
+EXPORT_SYMBOL(hwsw_sync_sg_for_device);

arch/ia64/kernel/crash.c

@@ -79,6 +79,7 @@ crash_save_this_cpu()
 	final_note(buf);
 }
 
+#ifdef CONFIG_SMP
 static int
 kdump_wait_cpu_freeze(void)
 {
@@ -91,6 +92,7 @@ kdump_wait_cpu_freeze(void)
 	}
 	return 1;
 }
+#endif
 
 void
 machine_crash_shutdown(struct pt_regs *pt)
@@ -116,6 +118,11 @@ machine_crash_shutdown(struct pt_regs *pt)
 static void
 machine_kdump_on_init(void)
 {
+	if (!ia64_kimage) {
+		printk(KERN_NOTICE "machine_kdump_on_init(): "
+				"kdump not configured\n");
+		return;
+	}
 	local_irq_disable();
 	kexec_disable_iosapic();
 	machine_kexec(ia64_kimage);
@@ -132,11 +139,12 @@ kdump_cpu_freeze(struct unw_frame_info *info, void *arg)
 	atomic_inc(&kdump_cpu_freezed);
 	kdump_status[cpuid] = 1;
 	mb();
-	if (cpuid == 0) {
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpuid != 0)
+		ia64_jump_to_sal(&sal_boot_rendez_state[cpuid]);
+#endif
 	for (;;)
 		cpu_relax();
-	} else
-		ia64_jump_to_sal(&sal_boot_rendez_state[cpuid]);
 }
 
 static int

arch/ia64/kernel/crash_dump.c

@@ -9,7 +9,8 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 
-#include <linux/uaccess.h>
+#include <asm/page.h>
+#include <asm/uaccess.h>
 
 /**
  * copy_oldmem_page - copy one page from "oldmem"

arch/ia64/kernel/efi.c

@@ -380,7 +380,7 @@ efi_get_pal_addr (void)
 #endif
 		return __va(md->phys_addr);
 	}
-	printk(KERN_WARNING "%s: no PAL-code memory-descriptor found",
+	printk(KERN_WARNING "%s: no PAL-code memory-descriptor found\n",
 	       __FUNCTION__);
 	return NULL;
 }

arch/ia64/kernel/entry.S

@@ -1610,5 +1610,7 @@ sys_call_table:
 	data8 sys_sync_file_range		// 1300
 	data8 sys_tee
 	data8 sys_vmsplice
+	data8 sys_ni_syscall			// reserved for move_pages
+	data8 sys_getcpu
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls

arch/ia64/kernel/iosapic.c

@@ -925,6 +925,11 @@ iosapic_unregister_intr (unsigned int gsi)
 			/* Clear the interrupt controller descriptor */
 			idesc->chip = &no_irq_type;
 
+#ifdef CONFIG_SMP
+			/* Clear affinity */
+			cpus_setall(idesc->affinity);
+#endif
+
 			/* Clear the interrupt information */
 			memset(&iosapic_intr_info[vector], 0,
 			       sizeof(struct iosapic_intr_info));

arch/ia64/kernel/machine_kexec.c

@@ -14,6 +14,7 @@
 #include <linux/kexec.h>
 #include <linux/cpu.h>
 #include <linux/irq.h>
+#include <linux/efi.h>
 #include <asm/mmu_context.h>
 #include <asm/setup.h>
 #include <asm/delay.h>
@@ -68,22 +69,10 @@ void machine_kexec_cleanup(struct kimage *image)
 {
 }
 
-void machine_shutdown(void)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (cpu != smp_processor_id())
-			cpu_down(cpu);
-	}
-	kexec_disable_iosapic();
-}
-
 /*
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-extern void *efi_get_pal_addr(void);
 static void ia64_machine_kexec(struct unw_frame_info *info, void *arg)
 {
 	struct kimage *image = arg;
@@ -93,6 +82,7 @@ static void ia64_machine_kexec(struct unw_frame_info *info, void *arg)
 	unsigned long vector;
 	int ii;
 
+	BUG_ON(!image);
 	if (image->type == KEXEC_TYPE_CRASH) {
 		crash_save_this_cpu();
 		current->thread.ksp = (__u64)info->sw - 16;
@@ -131,6 +121,7 @@ static void ia64_machine_kexec(struct unw_frame_info *info, void *arg)
 
 void machine_kexec(struct kimage *image)
 {
+	BUG_ON(!image);
 	unw_init_running(ia64_machine_kexec, image);
 	for(;;);
 }

arch/ia64/kernel/process.c

@@ -34,6 +34,7 @@
 #include <asm/ia32.h>
 #include <asm/irq.h>
 #include <asm/kdebug.h>
+#include <asm/kexec.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/sal.h>
@@ -803,6 +804,21 @@ cpu_halt (void)
 		ia64_pal_halt(min_power_state);
 }
 
+void machine_shutdown(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		if (cpu != smp_processor_id())
+			cpu_down(cpu);
+	}
+#endif
+#ifdef CONFIG_KEXEC
+	kexec_disable_iosapic();
+#endif
+}
+
 void
 machine_restart (char *restart_cmd)
 {

arch/ia64/kernel/ptrace.c

@@ -607,7 +607,7 @@ find_thread_for_addr (struct task_struct *child, unsigned long addr)
 	 */
  	list_for_each_safe(this, next, &current->children) {
 		p = list_entry(this, struct task_struct, sibling);
-		if (p->mm != mm)
+		if (p->tgid != child->tgid)
 			continue;
 		if (thread_matches(p, addr)) {
 			child = p;
@@ -1405,6 +1405,7 @@ ptrace_disable (struct task_struct *child)
 	struct ia64_psr *child_psr = ia64_psr(task_pt_regs(child));
 
 	/* make sure the single step/taken-branch trap bits are not set: */
+	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
 	child_psr->ss = 0;
 	child_psr->tb = 0;
 }
@@ -1525,6 +1526,7 @@ sys_ptrace (long request, pid_t pid, unsigned long addr, unsigned long data)
 		 * Make sure the single step/taken-branch trap bits
 		 * are not set:
 		 */
+		clear_tsk_thread_flag(child, TIF_SINGLESTEP);
 		ia64_psr(pt)->ss = 0;
 		ia64_psr(pt)->tb = 0;
 
@@ -1556,6 +1558,7 @@ sys_ptrace (long request, pid_t pid, unsigned long addr, unsigned long data)
 			goto out_tsk;
 
 		clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+		set_tsk_thread_flag(child, TIF_SINGLESTEP);
 		if (request == PTRACE_SINGLESTEP) {
 			ia64_psr(pt)->ss = 1;
 		} else {
@@ -1595,13 +1598,9 @@ sys_ptrace (long request, pid_t pid, unsigned long addr, unsigned long data)
 }
 
 
-void
+static void
 syscall_trace (void)
 {
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return;
-	if (!(current->ptrace & PT_PTRACED))
-		return;
 	/*
 	 * The 0x80 provides a way for the tracing parent to
 	 * distinguish between a syscall stop and SIGTRAP delivery.
@@ -1664,7 +1663,8 @@ syscall_trace_leave (long arg0, long arg1, long arg2, long arg3,
 		audit_syscall_exit(success, result);
 	}
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE)
+	if ((test_thread_flag(TIF_SYSCALL_TRACE)
+	    || test_thread_flag(TIF_SINGLESTEP))
 	    && (current->ptrace & PT_PTRACED))
 		syscall_trace();
 }

arch/ia64/kernel/setup.c

@@ -569,34 +569,31 @@ show_cpuinfo (struct seq_file *m, void *v)
 		{ 1UL << 1, "spontaneous deferral"},
 		{ 1UL << 2, "16-byte atomic ops" }
 	};
-	char features[128], *cp, sep;
+	char features[128], *cp, *sep;
 	struct cpuinfo_ia64 *c = v;
 	unsigned long mask;
 	unsigned long proc_freq;
-	int i;
+	int i, size;
 
 	mask = c->features;
 
 	/* build the feature string: */
-	memcpy(features, " standard", 10);
+	memcpy(features, "standard", 9);
 	cp = features;
-	sep = 0;
+	size = sizeof(features);
-	for (i = 0; i < (int) ARRAY_SIZE(feature_bits); ++i) {
+	sep = "";
+	for (i = 0; i < ARRAY_SIZE(feature_bits) && size > 1; ++i) {
 		if (mask & feature_bits[i].mask) {
-			if (sep)
+			cp += snprintf(cp, size, "%s%s", sep,
-				*cp++ = sep;
+				       feature_bits[i].feature_name),
-			sep = ',';
+			sep = ", ";
-			*cp++ = ' ';
-			strcpy(cp, feature_bits[i].feature_name);
-			cp += strlen(feature_bits[i].feature_name);
 			mask &= ~feature_bits[i].mask;
+			size = sizeof(features) - (cp - features);
 		}
 	}
-	if (mask) {
+	if (mask && size > 1) {
-		/* print unknown features as a hex value: */
+		/* print unknown features as a hex value */
-		if (sep)
+		snprintf(cp, size, "%s0x%lx", sep, mask);
-			*cp++ = sep;
-		sprintf(cp, " 0x%lx", mask);
 	}
 
 	proc_freq = cpufreq_quick_get(cpunum);
@@ -612,7 +609,7 @@ show_cpuinfo (struct seq_file *m, void *v)
 		   "model name : %s\n"
 		   "revision   : %u\n"
 		   "archrev    : %u\n"
-		   "features   :%s\n"	/* don't change this---it _is_ right! */
+		   "features   : %s\n"
 		   "cpu number : %lu\n"
 		   "cpu regs   : %u\n"
 		   "cpu MHz    : %lu.%06lu\n"

arch/ia64/kernel/vmlinux.lds.S

@@ -157,6 +157,7 @@ SECTIONS
 	}
 #endif
 
+  . = ALIGN(8);
    __con_initcall_start = .;
   .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET)
 	{ *(.con_initcall.init) }

arch/ia64/mm/contig.c

@@ -30,47 +30,69 @@ static unsigned long max_gap;
 #endif
 
 /**
- * show_mem - display a memory statistics summary
+ * show_mem - give short summary of memory stats
  *
- * Just walks the pages in the system and describes where they're allocated.
+ * Shows a simple page count of reserved and used pages in the system.
+ * For discontig machines, it does this on a per-pgdat basis.
  */
-void
+void show_mem(void)
-show_mem (void)
 {
-	int i, total = 0, reserved = 0;
+	int i, total_reserved = 0;
-	int shared = 0, cached = 0;
+	int total_shared = 0, total_cached = 0;
+	unsigned long total_present = 0;
+	pg_data_t *pgdat;
 
 	printk(KERN_INFO "Mem-info:\n");
 	show_free_areas();
-
 	printk(KERN_INFO "Free swap:       %6ldkB\n",
 	       nr_swap_pages<<(PAGE_SHIFT-10));
-	i = max_mapnr;
+	printk(KERN_INFO "Node memory in pages:\n");
-	for (i = 0; i < max_mapnr; i++) {
+	for_each_online_pgdat(pgdat) {
-		if (!pfn_valid(i)) {
+		unsigned long present;
+		unsigned long flags;
+		int shared = 0, cached = 0, reserved = 0;
+
+		pgdat_resize_lock(pgdat, &flags);
+		present = pgdat->node_present_pages;
+		for(i = 0; i < pgdat->node_spanned_pages; i++) {
+			struct page *page;
+			if (pfn_valid(pgdat->node_start_pfn + i))
+				page = pfn_to_page(pgdat->node_start_pfn + i);
+			else {
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 				if (max_gap < LARGE_GAP)
 					continue;
-			i = vmemmap_find_next_valid_pfn(0, i) - 1;
 #endif
+				i = vmemmap_find_next_valid_pfn(pgdat->node_id,
+					 i) - 1;
 				continue;
 			}
-		total++;
+			if (PageReserved(page))
-		if (PageReserved(mem_map+i))
 				reserved++;
-		else if (PageSwapCache(mem_map+i))
+			else if (PageSwapCache(page))
 				cached++;
-		else if (page_count(mem_map + i))
+			else if (page_count(page))
-			shared += page_count(mem_map + i) - 1;
+				shared += page_count(page)-1;
 		}
-	printk(KERN_INFO "%d pages of RAM\n", total);
+		pgdat_resize_unlock(pgdat, &flags);
-	printk(KERN_INFO "%d reserved pages\n", reserved);
+		total_present += present;
-	printk(KERN_INFO "%d pages shared\n", shared);
+		total_reserved += reserved;
-	printk(KERN_INFO "%d pages swap cached\n", cached);
+		total_cached += cached;
-	printk(KERN_INFO "%ld pages in page table cache\n",
+		total_shared += shared;
+		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
+		       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+		       present, reserved, shared, cached);
+	}
+	printk(KERN_INFO "%ld pages of RAM\n", total_present);
+	printk(KERN_INFO "%d reserved pages\n", total_reserved);
+	printk(KERN_INFO "%d pages shared\n", total_shared);
+	printk(KERN_INFO "%d pages swap cached\n", total_cached);
+	printk(KERN_INFO "Total of %ld pages in page table cache\n",
 	       pgtable_quicklist_total_size());
+	printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
 }
 
+
 /* physical address where the bootmem map is located */
 unsigned long bootmap_start;
 
@@ -177,7 +199,7 @@ find_memory (void)
 
 #ifdef CONFIG_CRASH_DUMP
 	/* If we are doing a crash dump, we still need to know the real mem
-	 * size before original memory map is * reset. */
+	 * size before original memory map is reset. */
 	saved_max_pfn = max_pfn;
 #endif
 }

arch/ia64/mm/discontig.c

@@ -412,37 +412,6 @@ static void __init memory_less_nodes(void)
 	return;
 }
 
-#ifdef CONFIG_SPARSEMEM
-/**
- * register_sparse_mem - notify SPARSEMEM that this memory range exists.
- * @start: physical start of range
- * @end: physical end of range
- * @arg: unused
- *
- * Simply calls SPARSEMEM to register memory section(s).
- */
-static int __init register_sparse_mem(unsigned long start, unsigned long end,
-	void *arg)
-{
-	int nid;
-
-	start = __pa(start) >> PAGE_SHIFT;
-	end = __pa(end) >> PAGE_SHIFT;
-	nid = early_pfn_to_nid(start);
-	memory_present(nid, start, end);
-
-	return 0;
-}
-
-static void __init arch_sparse_init(void)
-{
-	efi_memmap_walk(register_sparse_mem, NULL);
-	sparse_init();
-}
-#else
-#define arch_sparse_init() do {} while (0)
-#endif
-
 /**
  * find_memory - walk the EFI memory map and setup the bootmem allocator
  *
@@ -473,6 +442,9 @@ void __init find_memory(void)
 			node_clear(node, memory_less_mask);
 			mem_data[node].min_pfn = ~0UL;
 		}
+
+	efi_memmap_walk(register_active_ranges, NULL);
+
 	/*
 	 * Initialize the boot memory maps in reverse order since that's
 	 * what the bootmem allocator expects
@@ -506,6 +478,12 @@ void __init find_memory(void)
 	max_pfn = max_low_pfn;
 
 	find_initrd();
+
+#ifdef CONFIG_CRASH_DUMP
+	/* If we are doing a crash dump, we still need to know the real mem
+	 * size before original memory map is reset. */
+        saved_max_pfn = max_pfn;
+#endif
 }
 
 #ifdef CONFIG_SMP
@@ -654,7 +632,6 @@ static __init int count_node_pages(unsigned long start, unsigned long len, int n
 {
 	unsigned long end = start + len;
 
-	add_active_range(node, start >> PAGE_SHIFT, end >> PAGE_SHIFT);
 	mem_data[node].num_physpages += len >> PAGE_SHIFT;
 	if (start <= __pa(MAX_DMA_ADDRESS))
 		mem_data[node].num_dma_physpages +=
@@ -686,10 +663,11 @@ void __init paging_init(void)
 
 	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
-	arch_sparse_init();
-
 	efi_memmap_walk(filter_rsvd_memory, count_node_pages);
 
+	sparse_memory_present_with_active_regions(MAX_NUMNODES);
+	sparse_init();
+
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 	vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
 		sizeof(struct page));

arch/ia64/mm/init.c

@@ -19,6 +19,7 @@
 #include <linux/swap.h>
 #include <linux/proc_fs.h>
 #include <linux/bitops.h>
+#include <linux/kexec.h>
 
 #include <asm/a.out.h>
 #include <asm/dma.h>
@@ -128,6 +129,25 @@ lazy_mmu_prot_update (pte_t pte)
 	set_bit(PG_arch_1, &page->flags);	/* mark page as clean */
 }
 
+/*
+ * Since DMA is i-cache coherent, any (complete) pages that were written via
+ * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
+ * flush them when they get mapped into an executable vm-area.
+ */
+void
+dma_mark_clean(void *addr, size_t size)
+{
+	unsigned long pg_addr, end;
+
+	pg_addr = PAGE_ALIGN((unsigned long) addr);
+	end = (unsigned long) addr + size;
+	while (pg_addr + PAGE_SIZE <= end) {
+		struct page *page = virt_to_page(pg_addr);
+		set_bit(PG_arch_1, &page->flags);
+		pg_addr += PAGE_SIZE;
+	}
+}
+
 inline void
 ia64_set_rbs_bot (void)
 {
@@ -595,13 +615,27 @@ find_largest_hole (u64 start, u64 end, void *arg)
 	return 0;
 }
 
+#endif /* CONFIG_VIRTUAL_MEM_MAP */
+
 int __init
 register_active_ranges(u64 start, u64 end, void *arg)
 {
-	add_active_range(0, __pa(start) >> PAGE_SHIFT, __pa(end) >> PAGE_SHIFT);
+	int nid = paddr_to_nid(__pa(start));
+
+	if (nid < 0)
+		nid = 0;
+#ifdef CONFIG_KEXEC
+	if (start > crashk_res.start && start < crashk_res.end)
+		start = crashk_res.end;
+	if (end > crashk_res.start && end < crashk_res.end)
+		end = crashk_res.start;
+#endif
+
+	if (start < end)
+		add_active_range(nid, __pa(start) >> PAGE_SHIFT,
+			__pa(end) >> PAGE_SHIFT);
 	return 0;
 }
-#endif /* CONFIG_VIRTUAL_MEM_MAP */
 
 static int __init
 count_reserved_pages (u64 start, u64 end, void *arg)

arch/ia64/sn/kernel/huberror.c

@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 1992 - 1997, 2000,2002-2005 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 1992 - 1997, 2000,2002-2007 Silicon Graphics, Inc. All rights reserved.
  */
 
 #include <linux/types.h>
@@ -38,10 +38,18 @@ static irqreturn_t hub_eint_handler(int irq, void *arg)
 			(u64) nasid, 0, 0, 0, 0, 0, 0);
 
 		if ((int)ret_stuff.v0)
-			panic("hubii_eint_handler(): Fatal TIO Error");
+			panic("%s: Fatal %s Error", __FUNCTION__,
+				((nasid & 1) ? "TIO" : "HUBII"));
 
 		if (!(nasid & 1)) /* Not a TIO, handle CRB errors */
 			(void)hubiio_crb_error_handler(hubdev_info);
+	} else
+		if (nasid & 1) {	/* TIO errors */
+			SAL_CALL_NOLOCK(ret_stuff, SN_SAL_HUB_ERROR_INTERRUPT,
+				(u64) nasid, 0, 0, 0, 0, 0, 0);
+
+			if ((int)ret_stuff.v0)
+				panic("%s: Fatal TIO Error", __FUNCTION__);
 		} else
 			bte_error_handler((unsigned long)NODEPDA(nasid_to_cnodeid(nasid)));
 

arch/x86_64/kernel/pci-swiotlb.c

@@ -29,7 +29,7 @@ struct dma_mapping_ops swiotlb_dma_ops = {
 	.dma_supported = NULL,
 };
 
-void pci_swiotlb_init(void)
+void __init pci_swiotlb_init(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
 	if (!iommu_detected && !no_iommu && end_pfn > MAX_DMA32_PFN)

include/asm-ia64/dma.h

@@ -19,4 +19,6 @@ extern unsigned long MAX_DMA_ADDRESS;
 
 #define free_dma(x)
 
+void dma_mark_clean(void *addr, size_t size);
+
 #endif /* _ASM_IA64_DMA_H */

include/asm-ia64/esi.h

@@ -19,7 +19,6 @@ enum esi_proc_type {
 	ESI_PROC_REENTRANT	/* MP-safe and reentrant */
 };
 
-extern int ia64_esi_init (void);
 extern struct ia64_sal_retval esi_call_phys (void *, u64 *);
 extern int ia64_esi_call(efi_guid_t, struct ia64_sal_retval *,
 			 enum esi_proc_type,

include/asm-ia64/meminit.h

@@ -51,12 +51,13 @@ extern void efi_memmap_init(unsigned long *, unsigned long *);
 
 #define IGNORE_PFN0	1	/* XXX fix me: ignore pfn 0 until TLB miss handler is updated... */
 
+extern int register_active_ranges(u64 start, u64 end, void *arg);
+
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 # define LARGE_GAP	0x40000000 /* Use virtual mem map if hole is > than this */
   extern unsigned long vmalloc_end;
   extern struct page *vmem_map;
   extern int find_largest_hole (u64 start, u64 end, void *arg);
-  extern int register_active_ranges (u64 start, u64 end, void *arg);
   extern int create_mem_map_page_table (u64 start, u64 end, void *arg);
   extern int vmemmap_find_next_valid_pfn(int, int);
 #else

include/asm-ia64/pgalloc.h

@@ -137,7 +137,8 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t * pmd_entry, pte_t * pte)
 static inline struct page *pte_alloc_one(struct mm_struct *mm,
 					 unsigned long addr)
 {
-	return virt_to_page(pgtable_quicklist_alloc());
+	void *pg = pgtable_quicklist_alloc();
+	return pg ? virt_to_page(pg) : NULL;
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,

include/asm-ia64/swiotlb.h

@@ -0,0 +1,9 @@
+#ifndef _ASM_SWIOTLB_H
+#define _ASM_SWIOTLB_H 1
+
+#include <asm/machvec.h>
+
+#define SWIOTLB_ARCH_NEED_LATE_INIT
+#define SWIOTLB_ARCH_NEED_ALLOC
+
+#endif /* _ASM_SWIOTLB_H */

include/asm-ia64/thread_info.h

@@ -84,6 +84,7 @@ struct thread_info {
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
 #define TIF_SYSCALL_TRACE	3	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
+#define TIF_SINGLESTEP		5	/* restore singlestep on return to user mode */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		17
 #define TIF_MCA_INIT		18	/* this task is processing MCA or INIT */
@@ -92,7 +93,8 @@ struct thread_info {
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SYSCALL_TRACEAUDIT	(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_SYSCALL_TRACEAUDIT	(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)

include/asm-ia64/unistd.h

@@ -291,11 +291,13 @@
 #define __NR_sync_file_range		1300
 #define __NR_tee			1301
 #define __NR_vmsplice			1302
+/* 1303 reserved for move_pages */
+#define __NR_getcpu			1304
 
 #ifdef __KERNEL__
 
 
-#define NR_syscalls			279 /* length of syscall table */
+#define NR_syscalls			281 /* length of syscall table */
 
 #define __ARCH_WANT_SYS_RT_SIGACTION
 

include/asm-x86_64/swiotlb.h

@@ -1,6 +1,5 @@
 #ifndef _ASM_SWIOTLB_H
-#define _ASM_SWTIOLB_H 1
+#define _ASM_SWIOTLB_H 1
-
 
 #include <asm/dma-mapping.h>
 
@@ -45,6 +44,7 @@ extern void swiotlb_init(void);
 extern int swiotlb_force;
 
 #ifdef CONFIG_SWIOTLB
+#define SWIOTLB_ARCH_NEED_ALLOC
 extern int swiotlb;
 #else
 #define swiotlb 0
@@ -52,4 +52,6 @@ extern int swiotlb;
 
 extern void pci_swiotlb_init(void);
 
-#endif /* _ASM_SWTIOLB_H */
+static inline void dma_mark_clean(void *addr, size_t size) {}
+
+#endif /* _ASM_SWIOTLB_H */

lib/swiotlb.c

@@ -1,7 +1,7 @@
 /*
  * Dynamic DMA mapping support.
  *
- * This implementation is for IA-64 and EM64T platforms that do not support
+ * This implementation is a fallback for platforms that do not support
  * I/O TLBs (aka DMA address translation hardware).
  * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
  * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
@@ -28,6 +28,7 @@
 #include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/scatterlist.h>
+#include <asm/swiotlb.h>
 
 #include <linux/init.h>
 #include <linux/bootmem.h>
@@ -35,8 +36,10 @@
 #define OFFSET(val,align) ((unsigned long)	\
 	                   ( (val) & ( (align) - 1)))
 
+#ifndef SG_ENT_VIRT_ADDRESS
 #define SG_ENT_VIRT_ADDRESS(sg)	(page_address((sg)->page) + (sg)->offset)
-#define SG_ENT_PHYS_ADDRESS(SG)	virt_to_phys(SG_ENT_VIRT_ADDRESS(SG))
+#define SG_ENT_PHYS_ADDRESS(sg)	virt_to_bus(SG_ENT_VIRT_ADDRESS(sg))
+#endif
 
 /*
  * Maximum allowable number of contiguous slabs to map,
@@ -101,13 +104,25 @@ static unsigned int io_tlb_index;
  * We need to save away the original address corresponding to a mapped entry
  * for the sync operations.
  */
-static unsigned char **io_tlb_orig_addr;
+#ifndef SWIOTLB_ARCH_HAS_IO_TLB_ADDR_T
+typedef char *io_tlb_addr_t;
+#define swiotlb_orig_addr_null(buffer) (!(buffer))
+#define ptr_to_io_tlb_addr(ptr) (ptr)
+#define page_to_io_tlb_addr(pg, off) (page_address(pg) + (off))
+#define sg_to_io_tlb_addr(sg) SG_ENT_VIRT_ADDRESS(sg)
+#endif
+static io_tlb_addr_t *io_tlb_orig_addr;
 
 /*
  * Protect the above data structures in the map and unmap calls
  */
 static DEFINE_SPINLOCK(io_tlb_lock);
 
+#ifdef SWIOTLB_EXTRA_VARIABLES
+SWIOTLB_EXTRA_VARIABLES;
+#endif
+
+#ifndef SWIOTLB_ARCH_HAS_SETUP_IO_TLB_NPAGES
 static int __init
 setup_io_tlb_npages(char *str)
 {
@@ -122,30 +137,50 @@ setup_io_tlb_npages(char *str)
 		swiotlb_force = 1;
 	return 1;
 }
+#endif
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
+#ifndef swiotlb_adjust_size
+#define swiotlb_adjust_size(size) ((void)0)
+#endif
+
+#ifndef swiotlb_adjust_seg
+#define swiotlb_adjust_seg(start, size) ((void)0)
+#endif
+
+#ifndef swiotlb_print_info
+#define swiotlb_print_info(bytes) \
+	printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - " \
+	       "0x%lx\n", bytes >> 20, \
+	       virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end))
+#endif
+
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
  */
-void
+void __init
 swiotlb_init_with_default_size(size_t default_size)
 {
-	unsigned long i;
+	unsigned long i, bytes;
 
 	if (!io_tlb_nslabs) {
 		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
 		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
 	}
+	swiotlb_adjust_size(io_tlb_nslabs);
+	swiotlb_adjust_size(io_tlb_overflow);
+
+	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	io_tlb_start = alloc_bootmem_low_pages(io_tlb_nslabs * (1 << IO_TLB_SHIFT));
+	io_tlb_start = alloc_bootmem_low_pages(bytes);
 	if (!io_tlb_start)
 		panic("Cannot allocate SWIOTLB buffer");
-	io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT);
+	io_tlb_end = io_tlb_start + bytes;
 
 	/*
 	 * Allocate and initialize the free list array.  This array is used
@@ -153,25 +188,36 @@ swiotlb_init_with_default_size (size_t default_size)
 	 * between io_tlb_start and io_tlb_end.
 	 */
 	io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int));
-	for (i = 0; i < io_tlb_nslabs; i++)
+	for (i = 0; i < io_tlb_nslabs; i++) {
+		if ( !(i % IO_TLB_SEGSIZE) )
+			swiotlb_adjust_seg(io_tlb_start + (i << IO_TLB_SHIFT),
+				IO_TLB_SEGSIZE << IO_TLB_SHIFT);
  		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ 	}
 	io_tlb_index = 0;
-	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *));
+	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(io_tlb_addr_t));
 
 	/*
 	 * Get the overflow emergency buffer
 	 */
 	io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
-	printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n",
+	if (!io_tlb_overflow_buffer)
-	       virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end));
+		panic("Cannot allocate SWIOTLB overflow buffer!\n");
-}
+	swiotlb_adjust_seg(io_tlb_overflow_buffer, io_tlb_overflow);
 
-void
+	swiotlb_print_info(bytes);
+}
+#ifndef __swiotlb_init_with_default_size
+#define __swiotlb_init_with_default_size swiotlb_init_with_default_size
+#endif
+
+void __init
 swiotlb_init(void)
 {
-	swiotlb_init_with_default_size(64 * (1<<20));	/* default to 64MB */
+	__swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */
 }
 
+#ifdef SWIOTLB_ARCH_NEED_LATE_INIT
 /*
  * Systems with larger DMA zones (those that don't support ISA) can
  * initialize the swiotlb later using the slab allocator if needed.
@@ -180,7 +226,7 @@ swiotlb_init (void)
 int
 swiotlb_late_init_with_default_size(size_t default_size)
 {
-	unsigned long i, req_nslabs = io_tlb_nslabs;
+	unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
 	unsigned int order;
 
 	if (!io_tlb_nslabs) {
@@ -191,8 +237,9 @@ swiotlb_late_init_with_default_size (size_t default_size)
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	order = get_order(io_tlb_nslabs * (1 << IO_TLB_SHIFT));
+	order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
 	io_tlb_nslabs = SLABS_PER_PAGE << order;
+	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
 		io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
@@ -205,13 +252,14 @@ swiotlb_late_init_with_default_size (size_t default_size)
 	if (!io_tlb_start)
 		goto cleanup1;
 
-	if (order != get_order(io_tlb_nslabs * (1 << IO_TLB_SHIFT))) {
+	if (order != get_order(bytes)) {
 		printk(KERN_WARNING "Warning: only able to allocate %ld MB "
 		       "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
 		io_tlb_nslabs = SLABS_PER_PAGE << order;
+		bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 	}
-	io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT);
+	io_tlb_end = io_tlb_start + bytes;
-	memset(io_tlb_start, 0, io_tlb_nslabs * (1 << IO_TLB_SHIFT));
+	memset(io_tlb_start, 0, bytes);
 
 	/*
 	 * Allocate and initialize the free list array.  This array is used
@@ -227,12 +275,12 @@ swiotlb_late_init_with_default_size (size_t default_size)
  		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
 	io_tlb_index = 0;
 
-	io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL,
+	io_tlb_orig_addr = (io_tlb_addr_t *)__get_free_pages(GFP_KERNEL,
-	                           get_order(io_tlb_nslabs * sizeof(char *)));
+	                           get_order(io_tlb_nslabs * sizeof(io_tlb_addr_t)));
 	if (!io_tlb_orig_addr)
 		goto cleanup3;
 
-	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *));
+	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(io_tlb_addr_t));
 
 	/*
 	 * Get the overflow emergency buffer
@@ -242,29 +290,29 @@ swiotlb_late_init_with_default_size (size_t default_size)
 	if (!io_tlb_overflow_buffer)
 		goto cleanup4;
 
-	printk(KERN_INFO "Placing %ldMB software IO TLB between 0x%lx - "
+	swiotlb_print_info(bytes);
-	       "0x%lx\n", (io_tlb_nslabs * (1 << IO_TLB_SHIFT)) >> 20,
-	       virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end));
 
 	return 0;
 
 cleanup4:
-	free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
+	free_pages((unsigned long)io_tlb_orig_addr,
-	                                                      sizeof(char *)));
+		   get_order(io_tlb_nslabs * sizeof(io_tlb_addr_t)));
 	io_tlb_orig_addr = NULL;
 cleanup3:
-	free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+	free_pages((unsigned long)io_tlb_list,
-	                                                 sizeof(int)));
+		   get_order(io_tlb_nslabs * sizeof(int)));
 	io_tlb_list = NULL;
-	io_tlb_end = NULL;
 cleanup2:
+	io_tlb_end = NULL;
 	free_pages((unsigned long)io_tlb_start, order);
 	io_tlb_start = NULL;
 cleanup1:
 	io_tlb_nslabs = req_nslabs;
 	return -ENOMEM;
 }
+#endif
 
+#ifndef SWIOTLB_ARCH_HAS_NEEDS_MAPPING
 static inline int
 address_needs_mapping(struct device *hwdev, dma_addr_t addr)
 {
@@ -275,11 +323,35 @@ address_needs_mapping(struct device *hwdev, dma_addr_t addr)
 	return (addr & ~mask) != 0;
 }
 
+static inline int range_needs_mapping(const void *ptr, size_t size)
+{
+	return swiotlb_force;
+}
+
+static inline int order_needs_mapping(unsigned int order)
+{
+	return 0;
+}
+#endif
+
+static void
+__sync_single(io_tlb_addr_t buffer, char *dma_addr, size_t size, int dir)
+{
+#ifndef SWIOTLB_ARCH_HAS_SYNC_SINGLE
+	if (dir == DMA_TO_DEVICE)
+		memcpy(dma_addr, buffer, size);
+	else
+		memcpy(buffer, dma_addr, size);
+#else
+	__swiotlb_arch_sync_single(buffer, dma_addr, size, dir);
+#endif
+}
+
 /*
  * Allocates bounce buffer and returns its kernel virtual address.
  */
 static void *
-map_single(struct device *hwdev, char *buffer, size_t size, int dir)
+map_single(struct device *hwdev, io_tlb_addr_t buffer, size_t size, int dir)
 {
 	unsigned long flags;
 	char *dma_addr;
@@ -352,7 +424,7 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
 	 */
 	io_tlb_orig_addr[index] = buffer;
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-		memcpy(dma_addr, buffer, size);
+		__sync_single(buffer, dma_addr, size, DMA_TO_DEVICE);
 
 	return dma_addr;
 }
@@ -366,17 +438,18 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
-	char *buffer = io_tlb_orig_addr[index];
+	io_tlb_addr_t buffer = io_tlb_orig_addr[index];
 
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
-	if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+	if (!swiotlb_orig_addr_null(buffer)
+	    && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
 		/*
 		 * bounce... copy the data back into the original buffer * and
 		 * delete the bounce buffer.
 		 */
-		memcpy(buffer, dma_addr, size);
+		__sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -409,18 +482,18 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size,
 	    int dir, int target)
 {
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
-	char *buffer = io_tlb_orig_addr[index];
+	io_tlb_addr_t buffer = io_tlb_orig_addr[index];
 
 	switch (target) {
 	case SYNC_FOR_CPU:
 		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
-			memcpy(buffer, dma_addr, size);
+			__sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE);
 		else
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
 		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-			memcpy(dma_addr, buffer, size);
+			__sync_single(buffer, dma_addr, size, DMA_TO_DEVICE);
 		else
 			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
@@ -429,11 +502,13 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size,
 	}
 }
 
+#ifdef SWIOTLB_ARCH_NEED_ALLOC
+
 void *
 swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		       dma_addr_t *dma_handle, gfp_t flags)
 {
-	unsigned long dev_addr;
+	dma_addr_t dev_addr;
 	void *ret;
 	int order = get_order(size);
 
@@ -444,8 +519,11 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	 */
 	flags |= GFP_DMA;
 
+	if (!order_needs_mapping(order))
 		ret = (void *)__get_free_pages(flags, order);
-	if (ret && address_needs_mapping(hwdev, virt_to_phys(ret))) {
+	else
+		ret = NULL;
+	if (ret && address_needs_mapping(hwdev, virt_to_bus(ret))) {
 		/*
 		 * The allocated memory isn't reachable by the device.
 		 * Fall back on swiotlb_map_single().
@@ -465,22 +543,24 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		if (swiotlb_dma_mapping_error(handle))
 			return NULL;
 
-		ret = phys_to_virt(handle);
+		ret = bus_to_virt(handle);
 	}
 
 	memset(ret, 0, size);
-	dev_addr = virt_to_phys(ret);
+	dev_addr = virt_to_bus(ret);
 
 	/* Confirm address can be DMA'd by device */
 	if (address_needs_mapping(hwdev, dev_addr)) {
-		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016lx\n",
+		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
-		       (unsigned long long)*hwdev->dma_mask, dev_addr);
+		       (unsigned long long)*hwdev->dma_mask,
+		       (unsigned long long)dev_addr);
 		panic("swiotlb_alloc_coherent: allocated memory is out of "
 		      "range for device");
 	}
 	*dma_handle = dev_addr;
 	return ret;
 }
+EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
 void
 swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
@@ -493,6 +573,9 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
 		swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE);
 }
+EXPORT_SYMBOL(swiotlb_free_coherent);
+
+#endif
 
 static void
 swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
@@ -504,7 +587,7 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
 	 * When the mapping is small enough return a static buffer to limit
 	 * the damage, or panic when the transfer is too big.
 	 */
-	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %lu bytes at "
+	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
 	       "device %s\n", size, dev ? dev->bus_id : "?");
 
 	if (size > io_tlb_overflow && do_panic) {
@@ -525,7 +608,7 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
 dma_addr_t
 swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
 {
-	unsigned long dev_addr = virt_to_phys(ptr);
+	dma_addr_t dev_addr = virt_to_bus(ptr);
 	void *map;
 
 	BUG_ON(dir == DMA_NONE);
@@ -534,19 +617,20 @@ swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force)
+	if (!range_needs_mapping(ptr, size)
+	    && !address_needs_mapping(hwdev, dev_addr))
 		return dev_addr;
 
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
-	map = map_single(hwdev, ptr, size, dir);
+	map = map_single(hwdev, ptr_to_io_tlb_addr(ptr), size, dir);
 	if (!map) {
 		swiotlb_full(hwdev, size, dir, 1);
 		map = io_tlb_overflow_buffer;
 	}
 
-	dev_addr = virt_to_phys(map);
+	dev_addr = virt_to_bus(map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
@@ -557,25 +641,6 @@ swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
 	return dev_addr;
 }
 
-/*
- * Since DMA is i-cache coherent, any (complete) pages that were written via
- * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
- * flush them when they get mapped into an executable vm-area.
- */
-static void
-mark_clean(void *addr, size_t size)
-{
-	unsigned long pg_addr, end;
-
-	pg_addr = PAGE_ALIGN((unsigned long) addr);
-	end = (unsigned long) addr + size;
-	while (pg_addr + PAGE_SIZE <= end) {
-		struct page *page = virt_to_page(pg_addr);
-		set_bit(PG_arch_1, &page->flags);
-		pg_addr += PAGE_SIZE;
-	}
-}
-
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
  * match what was provided for in a previous swiotlb_map_single call.  All
@@ -588,13 +653,13 @@ void
 swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
 		     int dir)
 {
-	char *dma_addr = phys_to_virt(dev_addr);
+	char *dma_addr = bus_to_virt(dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
 		unmap_single(hwdev, dma_addr, size, dir);
 	else if (dir == DMA_FROM_DEVICE)
-		mark_clean(dma_addr, size);
+		dma_mark_clean(dma_addr, size);
 }
 
 /*
@@ -611,13 +676,13 @@ static inline void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 		    size_t size, int dir, int target)
 {
-	char *dma_addr = phys_to_virt(dev_addr);
+	char *dma_addr = bus_to_virt(dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
 		sync_single(hwdev, dma_addr, size, dir, target);
 	else if (dir == DMA_FROM_DEVICE)
-		mark_clean(dma_addr, size);
+		dma_mark_clean(dma_addr, size);
 }
 
 void
@@ -642,13 +707,13 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
 			  unsigned long offset, size_t size,
 			  int dir, int target)
 {
-	char *dma_addr = phys_to_virt(dev_addr) + offset;
+	char *dma_addr = bus_to_virt(dev_addr) + offset;
 
 	BUG_ON(dir == DMA_NONE);
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
 		sync_single(hwdev, dma_addr, size, dir, target);
 	else if (dir == DMA_FROM_DEVICE)
-		mark_clean(dma_addr, size);
+		dma_mark_clean(dma_addr, size);
 }
 
 void
@@ -687,18 +752,16 @@ int
 swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
 	       int dir)
 {
-	void *addr;
+	dma_addr_t dev_addr;
-	unsigned long dev_addr;
 	int i;
 
 	BUG_ON(dir == DMA_NONE);
 
 	for (i = 0; i < nelems; i++, sg++) {
-		addr = SG_ENT_VIRT_ADDRESS(sg);
+		dev_addr = SG_ENT_PHYS_ADDRESS(sg);
-		dev_addr = virt_to_phys(addr);
+		if (range_needs_mapping(SG_ENT_VIRT_ADDRESS(sg), sg->length)
-		if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
+		    || address_needs_mapping(hwdev, dev_addr)) {
-			void *map = map_single(hwdev, addr, sg->length, dir);
+			void *map = map_single(hwdev, sg_to_io_tlb_addr(sg), sg->length, dir);
-			sg->dma_address = virt_to_bus(map);
 			if (!map) {
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
@@ -707,6 +770,7 @@ swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
 				sg[0].dma_length = 0;
 				return 0;
 			}
+			sg->dma_address = virt_to_bus(map);
 		} else
 			sg->dma_address = dev_addr;
 		sg->dma_length = sg->length;
@@ -728,9 +792,10 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
 
 	for (i = 0; i < nelems; i++, sg++)
 		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
-			unmap_single(hwdev, (void *) phys_to_virt(sg->dma_address), sg->dma_length, dir);
+			unmap_single(hwdev, bus_to_virt(sg->dma_address),
+				     sg->dma_length, dir);
 		else if (dir == DMA_FROM_DEVICE)
-			mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+			dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
 }
 
 /*
@@ -750,8 +815,10 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg,
 
 	for (i = 0; i < nelems; i++, sg++)
 		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
-			sync_single(hwdev, (void *) sg->dma_address,
+			sync_single(hwdev, bus_to_virt(sg->dma_address),
 				    sg->dma_length, dir, target);
+		else if (dir == DMA_FROM_DEVICE)
+			dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
 }
 
 void
@@ -768,10 +835,48 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
 }
 
+#ifdef SWIOTLB_ARCH_NEED_MAP_PAGE
+
+dma_addr_t
+swiotlb_map_page(struct device *hwdev, struct page *page,
+		 unsigned long offset, size_t size,
+		 enum dma_data_direction direction)
+{
+	dma_addr_t dev_addr;
+	char *map;
+
+	dev_addr = page_to_bus(page) + offset;
+	if (address_needs_mapping(hwdev, dev_addr)) {
+		map = map_single(hwdev, page_to_io_tlb_addr(page, offset), size, direction);
+		if (!map) {
+			swiotlb_full(hwdev, size, direction, 1);
+			map = io_tlb_overflow_buffer;
+		}
+		dev_addr = virt_to_bus(map);
+	}
+
+	return dev_addr;
+}
+
+void
+swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+		   size_t size, enum dma_data_direction direction)
+{
+	char *dma_addr = bus_to_virt(dev_addr);
+
+	BUG_ON(direction == DMA_NONE);
+	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
+		unmap_single(hwdev, dma_addr, size, direction);
+	else if (direction == DMA_FROM_DEVICE)
+		dma_mark_clean(dma_addr, size);
+}
+
+#endif
+
 int
 swiotlb_dma_mapping_error(dma_addr_t dma_addr)
 {
-	return (dma_addr == virt_to_phys(io_tlb_overflow_buffer));
+	return (dma_addr == virt_to_bus(io_tlb_overflow_buffer));
 }
 
 /*
@@ -780,10 +885,13 @@ swiotlb_dma_mapping_error(dma_addr_t dma_addr)
  * during bus mastering, then you would pass 0x00ffffff as the mask to
  * this function.
  */
+#ifndef __swiotlb_dma_supported
+#define __swiotlb_dma_supported(hwdev, mask) (virt_to_bus(io_tlb_end - 1) <= (mask))
+#endif
 int
 swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return (virt_to_phys (io_tlb_end) - 1) <= mask;
+	return __swiotlb_dma_supported(hwdev, mask);
 }
 
 EXPORT_SYMBOL(swiotlb_init);
@@ -798,6 +906,4 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
 EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
 EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
 EXPORT_SYMBOL(swiotlb_dma_mapping_error);
-EXPORT_SYMBOL(swiotlb_alloc_coherent);
-EXPORT_SYMBOL(swiotlb_free_coherent);
 EXPORT_SYMBOL(swiotlb_dma_supported);