Merge branch 'linus' into x86/xen

Conflicts:
	arch/x86/kernel/cpu/common.c
	arch/x86/kernel/process_64.c
	arch/x86/xen/enlighten.c

lib/Kconfig.debug

@@ -597,6 +597,19 @@ config RCU_TORTURE_TEST_RUNNABLE
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
+config RCU_CPU_STALL_DETECTOR
+	bool "Check for stalled CPUs delaying RCU grace periods"
+	depends on CLASSIC_RCU
+	default n
+	help
+	  This option causes RCU to printk information on which
+	  CPUs are delaying the current grace period, but only when
+	  the grace period extends for excessive time periods.
+
+	  Say Y if you want RCU to perform such checks.
+
+	  Say N if you are unsure.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL
@@ -624,6 +637,28 @@ config BACKTRACE_SELF_TEST
 
 	  Say N if you are unsure.
 
+config DEBUG_BLOCK_EXT_DEVT
+        bool "Force extended block device numbers and spread them"
+	depends on DEBUG_KERNEL
+	depends on BLOCK
+	default n
+	help
+	  Conventionally, block device numbers are allocated from
+	  predetermined contiguous area.  However, extended block area
+	  may introduce non-contiguous block device numbers.  This
+	  option forces most block device numbers to be allocated from
+	  the extended space and spreads them to discover kernel or
+	  userland code paths which assume predetermined contiguous
+	  device number allocation.
+
+	  Note that turning on this debug option shuffles all the
+	  device numbers for all IDE and SCSI devices including libata
+	  ones, so root partition specified using device number
+	  directly (via rdev or root=MAJ:MIN) won't work anymore.
+	  Textual device names (root=/dev/sdXn) will continue to work.
+
+	  Say N if you are unsure.
+
 config LKDTM
 	tristate "Linux Kernel Dump Test Tool Module"
 	depends on DEBUG_KERNEL
@@ -661,10 +696,21 @@ config FAIL_PAGE_ALLOC
 
 config FAIL_MAKE_REQUEST
 	bool "Fault-injection capability for disk IO"
-	depends on FAULT_INJECTION
+	depends on FAULT_INJECTION && BLOCK
 	help
 	  Provide fault-injection capability for disk IO.
 
+config FAIL_IO_TIMEOUT
+	bool "Faul-injection capability for faking disk interrupts"
+	depends on FAULT_INJECTION && BLOCK
+	help
+	  Provide fault-injection capability on end IO handling. This
+	  will make the block layer "forget" an interrupt as configured,
+	  thus exercising the error handling.
+
+	  Only works with drivers that use the generic timeout handling,
+	  for others it wont do anything.
+
 config FAULT_INJECTION_DEBUG_FS
 	bool "Debugfs entries for fault-injection capabilities"
 	depends on FAULT_INJECTION && SYSFS && DEBUG_FS

lib/Makefile

@@ -19,7 +19,8 @@ lib-$(CONFIG_SMP) += cpumask.o
 lib-y	+= kobject.o kref.o klist.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
-	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o
+	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
+	 string_helpers.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG

lib/iommu-helper.c

@@ -30,8 +30,7 @@ again:
 	return index;
 }
 
-static inline void set_bit_area(unsigned long *map, unsigned long i,
-				int len)
+void iommu_area_reserve(unsigned long *map, unsigned long i, int len)
 {
 	unsigned long end = i + len;
 	while (i < end) {
@@ -64,7 +63,7 @@ again:
 			start = index + 1;
 			goto again;
 		}
-		set_bit_area(map, index, nr);
+		iommu_area_reserve(map, index, nr);
 	}
 	return index;
 }

lib/klist.c

@@ -37,6 +37,37 @@
 #include <linux/klist.h>
 #include <linux/module.h>
 
+/*
+ * Use the lowest bit of n_klist to mark deleted nodes and exclude
+ * dead ones from iteration.
+ */
+#define KNODE_DEAD		1LU
+#define KNODE_KLIST_MASK	~KNODE_DEAD
+
+static struct klist *knode_klist(struct klist_node *knode)
+{
+	return (struct klist *)
+		((unsigned long)knode->n_klist & KNODE_KLIST_MASK);
+}
+
+static bool knode_dead(struct klist_node *knode)
+{
+	return (unsigned long)knode->n_klist & KNODE_DEAD;
+}
+
+static void knode_set_klist(struct klist_node *knode, struct klist *klist)
+{
+	knode->n_klist = klist;
+	/* no knode deserves to start its life dead */
+	WARN_ON(knode_dead(knode));
+}
+
+static void knode_kill(struct klist_node *knode)
+{
+	/* and no knode should die twice ever either, see we're very humane */
+	WARN_ON(knode_dead(knode));
+	*(unsigned long *)&knode->n_klist |= KNODE_DEAD;
+}
 
 /**
  * klist_init - Initialize a klist structure.
@@ -79,7 +110,7 @@ static void klist_node_init(struct klist *k, struct klist_node *n)
 	INIT_LIST_HEAD(&n->n_node);
 	init_completion(&n->n_removed);
 	kref_init(&n->n_ref);
-	n->n_klist = k;
+	knode_set_klist(n, k);
 	if (k->get)
 		k->get(n);
 }
@@ -115,7 +146,7 @@ EXPORT_SYMBOL_GPL(klist_add_tail);
  */
 void klist_add_after(struct klist_node *n, struct klist_node *pos)
 {
-	struct klist *k = pos->n_klist;
+	struct klist *k = knode_klist(pos);
 
 	klist_node_init(k, n);
 	spin_lock(&k->k_lock);
@@ -131,7 +162,7 @@ EXPORT_SYMBOL_GPL(klist_add_after);
  */
 void klist_add_before(struct klist_node *n, struct klist_node *pos)
 {
-	struct klist *k = pos->n_klist;
+	struct klist *k = knode_klist(pos);
 
 	klist_node_init(k, n);
 	spin_lock(&k->k_lock);
@@ -144,9 +175,10 @@ static void klist_release(struct kref *kref)
 {
 	struct klist_node *n = container_of(kref, struct klist_node, n_ref);
 
+	WARN_ON(!knode_dead(n));
 	list_del(&n->n_node);
 	complete(&n->n_removed);
-	n->n_klist = NULL;
+	knode_set_klist(n, NULL);
 }
 
 static int klist_dec_and_del(struct klist_node *n)
@@ -154,21 +186,28 @@ static int klist_dec_and_del(struct klist_node *n)
 	return kref_put(&n->n_ref, klist_release);
 }
 
+static void klist_put(struct klist_node *n, bool kill)
+{
+	struct klist *k = knode_klist(n);
+	void (*put)(struct klist_node *) = k->put;
+
+	spin_lock(&k->k_lock);
+	if (kill)
+		knode_kill(n);
+	if (!klist_dec_and_del(n))
+		put = NULL;
+	spin_unlock(&k->k_lock);
+	if (put)
+		put(n);
+}
+
 /**
  * klist_del - Decrement the reference count of node and try to remove.
  * @n: node we're deleting.
  */
 void klist_del(struct klist_node *n)
 {
-	struct klist *k = n->n_klist;
-	void (*put)(struct klist_node *) = k->put;
-
-	spin_lock(&k->k_lock);
-	if (!klist_dec_and_del(n))
-		put = NULL;
-	spin_unlock(&k->k_lock);
-	if (put)
-		put(n);
+	klist_put(n, true);
 }
 EXPORT_SYMBOL_GPL(klist_del);
 
@@ -206,7 +245,6 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i,
 			  struct klist_node *n)
 {
 	i->i_klist = k;
-	i->i_head = &k->k_list;
 	i->i_cur = n;
 	if (n)
 		kref_get(&n->n_ref);
@@ -237,7 +275,7 @@ EXPORT_SYMBOL_GPL(klist_iter_init);
 void klist_iter_exit(struct klist_iter *i)
 {
 	if (i->i_cur) {
-		klist_del(i->i_cur);
+		klist_put(i->i_cur, false);
 		i->i_cur = NULL;
 	}
 }
@@ -258,27 +296,33 @@ static struct klist_node *to_klist_node(struct list_head *n)
  */
 struct klist_node *klist_next(struct klist_iter *i)
 {
-	struct list_head *next;
-	struct klist_node *lnode = i->i_cur;
-	struct klist_node *knode = NULL;
 	void (*put)(struct klist_node *) = i->i_klist->put;
+	struct klist_node *last = i->i_cur;
+	struct klist_node *next;
 
 	spin_lock(&i->i_klist->k_lock);
-	if (lnode) {
-		next = lnode->n_node.next;
-		if (!klist_dec_and_del(lnode))
+
+	if (last) {
+		next = to_klist_node(last->n_node.next);
+		if (!klist_dec_and_del(last))
 			put = NULL;
 	} else
-		next = i->i_head->next;
+		next = to_klist_node(i->i_klist->k_list.next);
 
-	if (next != i->i_head) {
-		knode = to_klist_node(next);
-		kref_get(&knode->n_ref);
+	i->i_cur = NULL;
+	while (next != to_klist_node(&i->i_klist->k_list)) {
+		if (likely(!knode_dead(next))) {
+			kref_get(&next->n_ref);
+			i->i_cur = next;
+			break;
+		}
+		next = to_klist_node(next->n_node.next);
 	}
-	i->i_cur = knode;
+
 	spin_unlock(&i->i_klist->k_lock);
-	if (put && lnode)
-		put(lnode);
-	return knode;
+
+	if (put && last)
+		put(last);
+	return i->i_cur;
 }
 EXPORT_SYMBOL_GPL(klist_next);

lib/percpu_counter.c

@@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add);
  * Add up all the per-cpu counts, return the result.  This is a more accurate
  * but much slower version of percpu_counter_read_positive()
  */
-s64 __percpu_counter_sum(struct percpu_counter *fbc, int set)
+s64 __percpu_counter_sum(struct percpu_counter *fbc)
 {
 	s64 ret;
 	int cpu;
@@ -62,11 +62,9 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc, int set)
 	for_each_online_cpu(cpu) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
-		if (set)
-			*pcount = 0;
+		*pcount = 0;
 	}
-	if (set)
-		fbc->count = ret;
+	fbc->count = ret;
 
 	spin_unlock(&fbc->lock);
 	return ret;

lib/string_helpers.c

@@ -0,0 +1,64 @@
+/*
+ * Helpers for formatting and printing strings
+ *
+ * Copyright 31 August 2008 James Bottomley
+ */
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/string_helpers.h>
+
+/**
+ * string_get_size - get the size in the specified units
+ * @size:	The size to be converted
+ * @units:	units to use (powers of 1000 or 1024)
+ * @buf:	buffer to format to
+ * @len:	length of buffer
+ *
+ * This function returns a string formatted to 3 significant figures
+ * giving the size in the required units.  Returns 0 on success or
+ * error on failure.  @buf is always zero terminated.
+ *
+ */
+int string_get_size(u64 size, const enum string_size_units units,
+		    char *buf, int len)
+{
+	const char *units_10[] = { "B", "KB", "MB", "GB", "TB", "PB",
+				   "EB", "ZB", "YB", NULL};
+	const char *units_2[] = {"B", "KiB", "MiB", "GiB", "TiB", "PiB",
+				 "EiB", "ZiB", "YiB", NULL };
+	const char **units_str[] = {
+		[STRING_UNITS_10] =  units_10,
+		[STRING_UNITS_2] = units_2,
+	};
+	const int divisor[] = {
+		[STRING_UNITS_10] = 1000,
+		[STRING_UNITS_2] = 1024,
+	};
+	int i, j;
+	u64 remainder = 0, sf_cap;
+	char tmp[8];
+
+	tmp[0] = '\0';
+
+	for (i = 0; size > divisor[units] && units_str[units][i]; i++)
+		remainder = do_div(size, divisor[units]);
+
+	sf_cap = size;
+	for (j = 0; sf_cap*10 < 1000; j++)
+		sf_cap *= 10;
+
+	if (j) {
+		remainder *= 1000;
+		do_div(remainder, divisor[units]);
+		snprintf(tmp, sizeof(tmp), ".%03lld",
+			 (unsigned long long)remainder);
+		tmp[j+1] = '\0';
+	}
+
+	snprintf(buf, len, "%lld%s%s", (unsigned long long)size,
+		 tmp, units_str[units][i]);
+
+	return 0;
+}
+EXPORT_SYMBOL(string_get_size);

lib/swiotlb.c

@@ -274,13 +274,14 @@ cleanup1:
 }
 
 static int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr)
+address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
 {
-	dma_addr_t mask = 0xffffffff;
-	/* If the device has a mask, use it, otherwise default to 32 bits */
-	if (hwdev && hwdev->dma_mask)
-		mask = *hwdev->dma_mask;
-	return (addr & ~mask) != 0;
+	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+}
+
+static int is_swiotlb_buffer(char *addr)
+{
+	return addr >= io_tlb_start && addr < io_tlb_end;
 }
 
 /*
@@ -467,15 +468,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	void *ret;
 	int order = get_order(size);
 
-	/*
-	 * XXX fix me: the DMA API should pass us an explicit DMA mask
-	 * instead, or use ZONE_DMA32 (ia64 overloads ZONE_DMA to be a ~32
-	 * bit range instead of a 16MB one).
-	 */
-	flags |= GFP_DMA;
-
 	ret = (void *)__get_free_pages(flags, order);
-	if (ret && address_needs_mapping(hwdev, virt_to_bus(ret))) {
+	if (ret && address_needs_mapping(hwdev, virt_to_bus(ret), size)) {
 		/*
 		 * The allocated memory isn't reachable by the device.
 		 * Fall back on swiotlb_map_single().
@@ -490,19 +484,16 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 * swiotlb_map_single(), which will grab memory from
 		 * the lowest available address range.
 		 */
-		dma_addr_t handle;
-		handle = swiotlb_map_single(hwdev, NULL, size, DMA_FROM_DEVICE);
-		if (swiotlb_dma_mapping_error(hwdev, handle))
+		ret = map_single(hwdev, NULL, size, DMA_FROM_DEVICE);
+		if (!ret)
 			return NULL;
-
-		ret = bus_to_virt(handle);
 	}
 
 	memset(ret, 0, size);
 	dev_addr = virt_to_bus(ret);
 
 	/* Confirm address can be DMA'd by device */
-	if (address_needs_mapping(hwdev, dev_addr)) {
+	if (address_needs_mapping(hwdev, dev_addr, size)) {
 		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
 		       (unsigned long long)*hwdev->dma_mask,
 		       (unsigned long long)dev_addr);
@@ -518,12 +509,11 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 		      dma_addr_t dma_handle)
 {
 	WARN_ON(irqs_disabled());
-	if (!(vaddr >= (void *)io_tlb_start
-                    && vaddr < (void *)io_tlb_end))
+	if (!is_swiotlb_buffer(vaddr))
 		free_pages((unsigned long) vaddr, get_order(size));
 	else
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE);
+		unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
 }
 
 static void
@@ -567,7 +557,7 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force)
+	if (!address_needs_mapping(hwdev, dev_addr, size) && !swiotlb_force)
 		return dev_addr;
 
 	/*
@@ -584,7 +574,7 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
-	if (address_needs_mapping(hwdev, dev_addr))
+	if (address_needs_mapping(hwdev, dev_addr, size))
 		panic("map_single: bounce buffer is not DMA'ble");
 
 	return dev_addr;
@@ -612,7 +602,7 @@ swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t 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)
+	if (is_swiotlb_buffer(dma_addr))
 		unmap_single(hwdev, dma_addr, size, dir);
 	else if (dir == DMA_FROM_DEVICE)
 		dma_mark_clean(dma_addr, size);
@@ -642,7 +632,7 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t 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)
+	if (is_swiotlb_buffer(dma_addr))
 		sync_single(hwdev, dma_addr, size, dir, target);
 	else if (dir == DMA_FROM_DEVICE)
 		dma_mark_clean(dma_addr, size);
@@ -673,7 +663,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
 	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)
+	if (is_swiotlb_buffer(dma_addr))
 		sync_single(hwdev, dma_addr, size, dir, target);
 	else if (dir == DMA_FROM_DEVICE)
 		dma_mark_clean(dma_addr, size);
@@ -727,7 +717,8 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 	for_each_sg(sgl, sg, nelems, i) {
 		addr = SG_ENT_VIRT_ADDRESS(sg);
 		dev_addr = virt_to_bus(addr);
-		if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
+		if (swiotlb_force ||
+		    address_needs_mapping(hwdev, dev_addr, sg->length)) {
 			void *map = map_single(hwdev, addr, sg->length, dir);
 			if (!map) {
 				/* Don't panic here, we expect map_sg users