Merge branch 'master' into for-linus

10 files changed, 182 insertions, 653 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 170d8ca901d8..5b916bc0fbae 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -181,9 +181,6 @@ config HAS_DMA
 config CHECK_SIGNATURE
 	bool
 
-config HAVE_LMB
-	boolean
-
 config CPUMASK_OFFSTACK
 	bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
 	help
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e722e9d62221..67fa774f9572 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -528,7 +528,7 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390
+	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select KALLSYMS_ALL
 
@@ -628,6 +628,19 @@ config DEBUG_INFO
 
 	  If unsure, say N.
 
+config DEBUG_INFO_REDUCED
+	bool "Reduce debugging information"
+	depends on DEBUG_INFO
+	help
+	  If you say Y here gcc is instructed to generate less debugging
+	  information for structure types. This means that tools that
+	  need full debugging information (like kgdb or systemtap) won't
+	  be happy. But if you merely need debugging information to
+	  resolve line numbers there is no loss. Advantage is that
+	  build directory object sizes shrink dramatically over a full
+	  DEBUG_INFO build and compile times are reduced too.
+	  Only works with newer gcc versions.
+
 config DEBUG_VM
 	bool "Debug VM"
 	depends on DEBUG_KERNEL
@@ -937,7 +950,7 @@ config FAIL_MAKE_REQUEST
 	  Provide fault-injection capability for disk IO.
 
 config FAIL_IO_TIMEOUT
-	bool "Faul-injection capability for faking disk interrupts"
+	bool "Fault-injection capability for faking disk interrupts"
 	depends on FAULT_INJECTION && BLOCK
 	help
 	  Provide fault-injection capability on end IO handling. This
@@ -958,13 +971,13 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !PPC && !S390
+	select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
 config LATENCYTOP
 	bool "Latency measuring infrastructure"
-	select FRAME_POINTER if !MIPS && !PPC && !S390
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select KALLSYMS_ALL
 	select STACKTRACE
diff --git a/lib/Makefile b/lib/Makefile
index 3f1062cbbff4..0bfabba1bb32 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -89,8 +89,6 @@ obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
 
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
-obj-$(CONFIG_HAVE_LMB) += lmb.o
-
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
 
 obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 250ed11d3ed2..44524cc8c32a 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -114,7 +114,7 @@ static __init int test_atomic64(void)
 	BUG_ON(v.counter != r);
 
 #if defined(CONFIG_X86) || defined(CONFIG_MIPS) || defined(CONFIG_PPC) || \
-    defined(CONFIG_S390) || defined(_ASM_GENERIC_ATOMIC64_H)
+    defined(CONFIG_S390) || defined(_ASM_GENERIC_ATOMIC64_H) || defined(CONFIG_ARM)
 	INIT(onestwos);
 	BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1));
 	r -= one;
diff --git a/lib/devres.c b/lib/devres.c
index 49368608f988..6efddf53b90c 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -328,7 +328,7 @@ EXPORT_SYMBOL(pcim_iomap_regions_request_all);
  * @pdev: PCI device to map IO resources for
  * @mask: Mask of BARs to unmap and release
  *
- * Unamp and release regions specified by @mask.
+ * Unmap and release regions specified by @mask.
  */
 void pcim_iounmap_regions(struct pci_dev *pdev, u16 mask)
 {
diff --git a/lib/lmb.c b/lib/lmb.c
deleted file mode 100644
index b1fc52606524..000000000000
--- a/lib/lmb.c
+++ /dev/null
@@ -1,541 +0,0 @@
-/*
- * Procedures for maintaining information about logical memory blocks.
- *
- * Peter Bergner, IBM Corp.	June 2001.
- * Copyright (C) 2001 Peter Bergner.
- *
- *      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; either version
- *      2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/bitops.h>
-#include <linux/lmb.h>
-
-#define LMB_ALLOC_ANYWHERE	0
-
-struct lmb lmb;
-
-static int lmb_debug;
-
-static int __init early_lmb(char *p)
-{
-	if (p && strstr(p, "debug"))
-		lmb_debug = 1;
-	return 0;
-}
-early_param("lmb", early_lmb);
-
-static void lmb_dump(struct lmb_region *region, char *name)
-{
-	unsigned long long base, size;
-	int i;
-
-	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
-
-	for (i = 0; i < region->cnt; i++) {
-		base = region->region[i].base;
-		size = region->region[i].size;
-
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
-		    name, i, base, base + size - 1, size);
-	}
-}
-
-void lmb_dump_all(void)
-{
-	if (!lmb_debug)
-		return;
-
-	pr_info("LMB configuration:\n");
-	pr_info(" rmo_size    = 0x%llx\n", (unsigned long long)lmb.rmo_size);
-	pr_info(" memory.size = 0x%llx\n", (unsigned long long)lmb.memory.size);
-
-	lmb_dump(&lmb.memory, "memory");
-	lmb_dump(&lmb.reserved, "reserved");
-}
-
-static unsigned long lmb_addrs_overlap(u64 base1, u64 size1, u64 base2,
-					u64 size2)
-{
-	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
-}
-
-static long lmb_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2)
-{
-	if (base2 == base1 + size1)
-		return 1;
-	else if (base1 == base2 + size2)
-		return -1;
-
-	return 0;
-}
-
-static long lmb_regions_adjacent(struct lmb_region *rgn,
-		unsigned long r1, unsigned long r2)
-{
-	u64 base1 = rgn->region[r1].base;
-	u64 size1 = rgn->region[r1].size;
-	u64 base2 = rgn->region[r2].base;
-	u64 size2 = rgn->region[r2].size;
-
-	return lmb_addrs_adjacent(base1, size1, base2, size2);
-}
-
-static void lmb_remove_region(struct lmb_region *rgn, unsigned long r)
-{
-	unsigned long i;
-
-	for (i = r; i < rgn->cnt - 1; i++) {
-		rgn->region[i].base = rgn->region[i + 1].base;
-		rgn->region[i].size = rgn->region[i + 1].size;
-	}
-	rgn->cnt--;
-}
-
-/* Assumption: base addr of region 1 < base addr of region 2 */
-static void lmb_coalesce_regions(struct lmb_region *rgn,
-		unsigned long r1, unsigned long r2)
-{
-	rgn->region[r1].size += rgn->region[r2].size;
-	lmb_remove_region(rgn, r2);
-}
-
-void __init lmb_init(void)
-{
-	/* Create a dummy zero size LMB which will get coalesced away later.
-	 * This simplifies the lmb_add() code below...
-	 */
-	lmb.memory.region[0].base = 0;
-	lmb.memory.region[0].size = 0;
-	lmb.memory.cnt = 1;
-
-	/* Ditto. */
-	lmb.reserved.region[0].base = 0;
-	lmb.reserved.region[0].size = 0;
-	lmb.reserved.cnt = 1;
-}
-
-void __init lmb_analyze(void)
-{
-	int i;
-
-	lmb.memory.size = 0;
-
-	for (i = 0; i < lmb.memory.cnt; i++)
-		lmb.memory.size += lmb.memory.region[i].size;
-}
-
-static long lmb_add_region(struct lmb_region *rgn, u64 base, u64 size)
-{
-	unsigned long coalesced = 0;
-	long adjacent, i;
-
-	if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
-		return 0;
-	}
-
-	/* First try and coalesce this LMB with another. */
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-
-		if ((rgnbase == base) && (rgnsize == size))
-			/* Already have this region, so we're done */
-			return 0;
-
-		adjacent = lmb_addrs_adjacent(base, size, rgnbase, rgnsize);
-		if (adjacent > 0) {
-			rgn->region[i].base -= size;
-			rgn->region[i].size += size;
-			coalesced++;
-			break;
-		} else if (adjacent < 0) {
-			rgn->region[i].size += size;
-			coalesced++;
-			break;
-		}
-	}
-
-	if ((i < rgn->cnt - 1) && lmb_regions_adjacent(rgn, i, i+1)) {
-		lmb_coalesce_regions(rgn, i, i+1);
-		coalesced++;
-	}
-
-	if (coalesced)
-		return coalesced;
-	if (rgn->cnt >= MAX_LMB_REGIONS)
-		return -1;
-
-	/* Couldn't coalesce the LMB, so add it to the sorted table. */
-	for (i = rgn->cnt - 1; i >= 0; i--) {
-		if (base < rgn->region[i].base) {
-			rgn->region[i+1].base = rgn->region[i].base;
-			rgn->region[i+1].size = rgn->region[i].size;
-		} else {
-			rgn->region[i+1].base = base;
-			rgn->region[i+1].size = size;
-			break;
-		}
-	}
-
-	if (base < rgn->region[0].base) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
-	}
-	rgn->cnt++;
-
-	return 0;
-}
-
-long lmb_add(u64 base, u64 size)
-{
-	struct lmb_region *_rgn = &lmb.memory;
-
-	/* On pSeries LPAR systems, the first LMB is our RMO region. */
-	if (base == 0)
-		lmb.rmo_size = size;
-
-	return lmb_add_region(_rgn, base, size);
-
-}
-
-static long __lmb_remove(struct lmb_region *rgn, u64 base, u64 size)
-{
-	u64 rgnbegin, rgnend;
-	u64 end = base + size;
-	int i;
-
-	rgnbegin = rgnend = 0; /* supress gcc warnings */
-
-	/* Find the region where (base, size) belongs to */
-	for (i=0; i < rgn->cnt; i++) {
-		rgnbegin = rgn->region[i].base;
-		rgnend = rgnbegin + rgn->region[i].size;
-
-		if ((rgnbegin <= base) && (end <= rgnend))
-			break;
-	}
-
-	/* Didn't find the region */
-	if (i == rgn->cnt)
-		return -1;
-
-	/* Check to see if we are removing entire region */
-	if ((rgnbegin == base) && (rgnend == end)) {
-		lmb_remove_region(rgn, i);
-		return 0;
-	}
-
-	/* Check to see if region is matching at the front */
-	if (rgnbegin == base) {
-		rgn->region[i].base = end;
-		rgn->region[i].size -= size;
-		return 0;
-	}
-
-	/* Check to see if the region is matching at the end */
-	if (rgnend == end) {
-		rgn->region[i].size -= size;
-		return 0;
-	}
-
-	/*
-	 * We need to split the entry -  adjust the current one to the
-	 * beginging of the hole and add the region after hole.
-	 */
-	rgn->region[i].size = base - rgn->region[i].base;
-	return lmb_add_region(rgn, end, rgnend - end);
-}
-
-long lmb_remove(u64 base, u64 size)
-{
-	return __lmb_remove(&lmb.memory, base, size);
-}
-
-long __init lmb_free(u64 base, u64 size)
-{
-	return __lmb_remove(&lmb.reserved, base, size);
-}
-
-long __init lmb_reserve(u64 base, u64 size)
-{
-	struct lmb_region *_rgn = &lmb.reserved;
-
-	BUG_ON(0 == size);
-
-	return lmb_add_region(_rgn, base, size);
-}
-
-long lmb_overlaps_region(struct lmb_region *rgn, u64 base, u64 size)
-{
-	unsigned long i;
-
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-		if (lmb_addrs_overlap(base, size, rgnbase, rgnsize))
-			break;
-	}
-
-	return (i < rgn->cnt) ? i : -1;
-}
-
-static u64 lmb_align_down(u64 addr, u64 size)
-{
-	return addr & ~(size - 1);
-}
-
-static u64 lmb_align_up(u64 addr, u64 size)
-{
-	return (addr + (size - 1)) & ~(size - 1);
-}
-
-static u64 __init lmb_alloc_nid_unreserved(u64 start, u64 end,
-					   u64 size, u64 align)
-{
-	u64 base, res_base;
-	long j;
-
-	base = lmb_align_down((end - size), align);
-	while (start <= base) {
-		j = lmb_overlaps_region(&lmb.reserved, base, size);
-		if (j < 0) {
-			/* this area isn't reserved, take it */
-			if (lmb_add_region(&lmb.reserved, base, size) < 0)
-				base = ~(u64)0;
-			return base;
-		}
-		res_base = lmb.reserved.region[j].base;
-		if (res_base < size)
-			break;
-		base = lmb_align_down(res_base - size, align);
-	}
-
-	return ~(u64)0;
-}
-
-static u64 __init lmb_alloc_nid_region(struct lmb_property *mp,
-				       u64 (*nid_range)(u64, u64, int *),
-				       u64 size, u64 align, int nid)
-{
-	u64 start, end;
-
-	start = mp->base;
-	end = start + mp->size;
-
-	start = lmb_align_up(start, align);
-	while (start < end) {
-		u64 this_end;
-		int this_nid;
-
-		this_end = nid_range(start, end, &this_nid);
-		if (this_nid == nid) {
-			u64 ret = lmb_alloc_nid_unreserved(start, this_end,
-							   size, align);
-			if (ret != ~(u64)0)
-				return ret;
-		}
-		start = this_end;
-	}
-
-	return ~(u64)0;
-}
-
-u64 __init lmb_alloc_nid(u64 size, u64 align, int nid,
-			 u64 (*nid_range)(u64 start, u64 end, int *nid))
-{
-	struct lmb_region *mem = &lmb.memory;
-	int i;
-
-	BUG_ON(0 == size);
-
-	size = lmb_align_up(size, align);
-
-	for (i = 0; i < mem->cnt; i++) {
-		u64 ret = lmb_alloc_nid_region(&mem->region[i],
-					       nid_range,
-					       size, align, nid);
-		if (ret != ~(u64)0)
-			return ret;
-	}
-
-	return lmb_alloc(size, align);
-}
-
-u64 __init lmb_alloc(u64 size, u64 align)
-{
-	return lmb_alloc_base(size, align, LMB_ALLOC_ANYWHERE);
-}
-
-u64 __init lmb_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	u64 alloc;
-
-	alloc = __lmb_alloc_base(size, align, max_addr);
-
-	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
-
-	return alloc;
-}
-
-u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	long i, j;
-	u64 base = 0;
-	u64 res_base;
-
-	BUG_ON(0 == size);
-
-	size = lmb_align_up(size, align);
-
-	/* On some platforms, make sure we allocate lowmem */
-	/* Note that LMB_REAL_LIMIT may be LMB_ALLOC_ANYWHERE */
-	if (max_addr == LMB_ALLOC_ANYWHERE)
-		max_addr = LMB_REAL_LIMIT;
-
-	for (i = lmb.memory.cnt - 1; i >= 0; i--) {
-		u64 lmbbase = lmb.memory.region[i].base;
-		u64 lmbsize = lmb.memory.region[i].size;
-
-		if (lmbsize < size)
-			continue;
-		if (max_addr == LMB_ALLOC_ANYWHERE)
-			base = lmb_align_down(lmbbase + lmbsize - size, align);
-		else if (lmbbase < max_addr) {
-			base = min(lmbbase + lmbsize, max_addr);
-			base = lmb_align_down(base - size, align);
-		} else
-			continue;
-
-		while (base && lmbbase <= base) {
-			j = lmb_overlaps_region(&lmb.reserved, base, size);
-			if (j < 0) {
-				/* this area isn't reserved, take it */
-				if (lmb_add_region(&lmb.reserved, base, size) < 0)
-					return 0;
-				return base;
-			}
-			res_base = lmb.reserved.region[j].base;
-			if (res_base < size)
-				break;
-			base = lmb_align_down(res_base - size, align);
-		}
-	}
-	return 0;
-}
-
-/* You must call lmb_analyze() before this. */
-u64 __init lmb_phys_mem_size(void)
-{
-	return lmb.memory.size;
-}
-
-u64 lmb_end_of_DRAM(void)
-{
-	int idx = lmb.memory.cnt - 1;
-
-	return (lmb.memory.region[idx].base + lmb.memory.region[idx].size);
-}
-
-/* You must call lmb_analyze() after this. */
-void __init lmb_enforce_memory_limit(u64 memory_limit)
-{
-	unsigned long i;
-	u64 limit;
-	struct lmb_property *p;
-
-	if (!memory_limit)
-		return;
-
-	/* Truncate the lmb regions to satisfy the memory limit. */
-	limit = memory_limit;
-	for (i = 0; i < lmb.memory.cnt; i++) {
-		if (limit > lmb.memory.region[i].size) {
-			limit -= lmb.memory.region[i].size;
-			continue;
-		}
-
-		lmb.memory.region[i].size = limit;
-		lmb.memory.cnt = i + 1;
-		break;
-	}
-
-	if (lmb.memory.region[0].size < lmb.rmo_size)
-		lmb.rmo_size = lmb.memory.region[0].size;
-
-	memory_limit = lmb_end_of_DRAM();
-
-	/* And truncate any reserves above the limit also. */
-	for (i = 0; i < lmb.reserved.cnt; i++) {
-		p = &lmb.reserved.region[i];
-
-		if (p->base > memory_limit)
-			p->size = 0;
-		else if ((p->base + p->size) > memory_limit)
-			p->size = memory_limit - p->base;
-
-		if (p->size == 0) {
-			lmb_remove_region(&lmb.reserved, i);
-			i--;
-		}
-	}
-}
-
-int __init lmb_is_reserved(u64 addr)
-{
-	int i;
-
-	for (i = 0; i < lmb.reserved.cnt; i++) {
-		u64 upper = lmb.reserved.region[i].base +
-			lmb.reserved.region[i].size - 1;
-		if ((addr >= lmb.reserved.region[i].base) && (addr <= upper))
-			return 1;
-	}
-	return 0;
-}
-
-int lmb_is_region_reserved(u64 base, u64 size)
-{
-	return lmb_overlaps_region(&lmb.reserved, base, size);
-}
-
-/*
- * Given a <base, len>, find which memory regions belong to this range.
- * Adjust the request and return a contiguous chunk.
- */
-int lmb_find(struct lmb_property *res)
-{
-	int i;
-	u64 rstart, rend;
-
-	rstart = res->base;
-	rend = rstart + res->size - 1;
-
-	for (i = 0; i < lmb.memory.cnt; i++) {
-		u64 start = lmb.memory.region[i].base;
-		u64 end = start + lmb.memory.region[i].size - 1;
-
-		if (start > rend)
-			return -1;
-
-		if ((end >= rstart) && (start < rend)) {
-			/* adjust the request */
-			if (rstart < start)
-				rstart = start;
-			if (rend > end)
-				rend = end;
-			res->base = rstart;
-			res->size = rend - rstart + 1;
-			return 0;
-		}
-	}
-	return -1;
-}
diff --git a/lib/random32.c b/lib/random32.c
index 870dc3fc0f0f..fc3545a32771 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -127,7 +127,7 @@ core_initcall(random32_init);
 
 /*
  *	Generate better values after random number generator
- *	is fully initalized.
+ *	is fully initialized.
  */
 static int __init random32_reseed(void)
 {
diff --git a/lib/rbtree.c b/lib/rbtree.c
index 15e10b1afdd2..4693f79195d3 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -44,11 +44,6 @@ static void __rb_rotate_left(struct rb_node *node, struct rb_root *root)
 	else
 		root->rb_node = right;
 	rb_set_parent(node, right);
-
-	if (root->augment_cb) {
-		root->augment_cb(node);
-		root->augment_cb(right);
-	}
 }
 
 static void __rb_rotate_right(struct rb_node *node, struct rb_root *root)
@@ -72,20 +67,12 @@ static void __rb_rotate_right(struct rb_node *node, struct rb_root *root)
 	else
 		root->rb_node = left;
 	rb_set_parent(node, left);
-
-	if (root->augment_cb) {
-		root->augment_cb(node);
-		root->augment_cb(left);
-	}
 }
 
 void rb_insert_color(struct rb_node *node, struct rb_root *root)
 {
 	struct rb_node *parent, *gparent;
 
-	if (root->augment_cb)
-		root->augment_cb(node);
-
 	while ((parent = rb_parent(node)) && rb_is_red(parent))
 	{
 		gparent = rb_parent(parent);
@@ -240,15 +227,12 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 	else
 	{
 		struct rb_node *old = node, *left;
-		int old_parent_cb = 0;
-		int successor_parent_cb = 0;
 
 		node = node->rb_right;
 		while ((left = node->rb_left) != NULL)
 			node = left;
 
 		if (rb_parent(old)) {
-			old_parent_cb = 1;
 			if (rb_parent(old)->rb_left == old)
 				rb_parent(old)->rb_left = node;
 			else
@@ -263,10 +247,8 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 		if (parent == old) {
 			parent = node;
 		} else {
-			successor_parent_cb = 1;
 			if (child)
 				rb_set_parent(child, parent);
-
 			parent->rb_left = child;
 
 			node->rb_right = old->rb_right;
@@ -277,24 +259,6 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 		node->rb_left = old->rb_left;
 		rb_set_parent(old->rb_left, node);
 
-		if (root->augment_cb) {
-			/*
-			 * Here, three different nodes can have new children.
-			 * The parent of the successor node that was selected
-			 * to replace the node to be erased.
-			 * The node that is getting erased and is now replaced
-			 * by its successor.
-			 * The parent of the node getting erased-replaced.
-			 */
-			if (successor_parent_cb)
-				root->augment_cb(parent);
-
-			root->augment_cb(node);
-
-			if (old_parent_cb)
-				root->augment_cb(rb_parent(old));
-		}
-
 		goto color;
 	}
 
@@ -303,19 +267,15 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 
 	if (child)
 		rb_set_parent(child, parent);
-
-	if (parent) {
+	if (parent)
+	{
 		if (parent->rb_left == node)
 			parent->rb_left = child;
 		else
 			parent->rb_right = child;
-
-		if (root->augment_cb)
-			root->augment_cb(parent);
-
-	} else {
-		root->rb_node = child;
 	}
+	else
+		root->rb_node = child;
 
  color:
 	if (color == RB_BLACK)
@@ -323,6 +283,74 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
 }
 EXPORT_SYMBOL(rb_erase);
 
+static void rb_augment_path(struct rb_node *node, rb_augment_f func, void *data)
+{
+	struct rb_node *parent;
+
+up:
+	func(node, data);
+	parent = rb_parent(node);
+	if (!parent)
+		return;
+
+	if (node == parent->rb_left && parent->rb_right)
+		func(parent->rb_right, data);
+	else if (parent->rb_left)
+		func(parent->rb_left, data);
+
+	node = parent;
+	goto up;
+}
+
+/*
+ * after inserting @node into the tree, update the tree to account for
+ * both the new entry and any damage done by rebalance
+ */
+void rb_augment_insert(struct rb_node *node, rb_augment_f func, void *data)
+{
+	if (node->rb_left)
+		node = node->rb_left;
+	else if (node->rb_right)
+		node = node->rb_right;
+
+	rb_augment_path(node, func, data);
+}
+
+/*
+ * before removing the node, find the deepest node on the rebalance path
+ * that will still be there after @node gets removed
+ */
+struct rb_node *rb_augment_erase_begin(struct rb_node *node)
+{
+	struct rb_node *deepest;
+
+	if (!node->rb_right && !node->rb_left)
+		deepest = rb_parent(node);
+	else if (!node->rb_right)
+		deepest = node->rb_left;
+	else if (!node->rb_left)
+		deepest = node->rb_right;
+	else {
+		deepest = rb_next(node);
+		if (deepest->rb_right)
+			deepest = deepest->rb_right;
+		else if (rb_parent(deepest) != node)
+			deepest = rb_parent(deepest);
+	}
+
+	return deepest;
+}
+
+/*
+ * after removal, update the tree to account for the removed entry
+ * and any rebalance damage.
+ */
+void rb_augment_erase_end(struct rb_node *node, rb_augment_f func, void *data)
+{
+	if (node)
+		rb_augment_path(node, func, data);
+}
+
 /*
  * This function returns the first node (in sort order) of the tree.
  */
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index a009055140ec..34e3082632d8 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -50,19 +50,11 @@
  */
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 
-/*
- * Enumeration for sync targets
- */
-enum dma_sync_target {
-	SYNC_FOR_CPU = 0,
-	SYNC_FOR_DEVICE = 1,
-};
-
 int swiotlb_force;
 
 /*
- * Used to do a quick range check in unmap_single and
- * sync_single_*, to see if the memory was in fact allocated by this
+ * Used to do a quick range check in swiotlb_tbl_unmap_single and
+ * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
  * API.
  */
 static char *io_tlb_start, *io_tlb_end;
@@ -140,28 +132,14 @@ void swiotlb_print_info(void)
 	       (unsigned long long)pend);
 }
 
-/*
- * Statically reserve bounce buffer space and initialize bounce buffer data
- * structures for the software IO TLB used to implement the DMA API.
- */
-void __init
-swiotlb_init_with_default_size(size_t default_size, int verbose)
+void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 {
 	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);
-	}
-
-	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+	bytes = nslabs << IO_TLB_SHIFT;
 
-	/*
-	 * Get IO TLB memory from the low pages
-	 */
-	io_tlb_start = alloc_bootmem_low_pages(bytes);
-	if (!io_tlb_start)
-		panic("Cannot allocate SWIOTLB buffer");
+	io_tlb_nslabs = nslabs;
+	io_tlb_start = tlb;
 	io_tlb_end = io_tlb_start + bytes;
 
 	/*
@@ -185,6 +163,32 @@ swiotlb_init_with_default_size(size_t default_size, int verbose)
 		swiotlb_print_info();
 }
 
+/*
+ * Statically reserve bounce buffer space and initialize bounce buffer data
+ * structures for the software IO TLB used to implement the DMA API.
+ */
+void __init
+swiotlb_init_with_default_size(size_t default_size, int verbose)
+{
+	unsigned long bytes;
+
+	if (!io_tlb_nslabs) {
+		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
+		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+	}
+
+	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+	/*
+	 * Get IO TLB memory from the low pages
+	 */
+	io_tlb_start = alloc_bootmem_low_pages(bytes);
+	if (!io_tlb_start)
+		panic("Cannot allocate SWIOTLB buffer");
+
+	swiotlb_init_with_tbl(io_tlb_start, io_tlb_nslabs, verbose);
+}
+
 void __init
 swiotlb_init(int verbose)
 {
@@ -323,8 +327,8 @@ static int is_swiotlb_buffer(phys_addr_t paddr)
 /*
  * Bounce: copy the swiotlb buffer back to the original dma location
  */
-static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
-			   enum dma_data_direction dir)
+void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
+		    enum dma_data_direction dir)
 {
 	unsigned long pfn = PFN_DOWN(phys);
 
@@ -360,26 +364,25 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
 			memcpy(phys_to_virt(phys), dma_addr, size);
 	}
 }
+EXPORT_SYMBOL_GPL(swiotlb_bounce);
 
-/*
- * Allocates bounce buffer and returns its kernel virtual address.
- */
-static void *
-map_single(struct device *hwdev, phys_addr_t phys, size_t size, int dir)
+void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr,
+			     phys_addr_t phys, size_t size,
+			     enum dma_data_direction dir)
 {
 	unsigned long flags;
 	char *dma_addr;
 	unsigned int nslots, stride, index, wrap;
 	int i;
-	unsigned long start_dma_addr;
 	unsigned long mask;
 	unsigned long offset_slots;
 	unsigned long max_slots;
 
 	mask = dma_get_seg_boundary(hwdev);
-	start_dma_addr = swiotlb_virt_to_bus(hwdev, io_tlb_start) & mask;
 
-	offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	tbl_dma_addr &= mask;
+
+	offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 
 	/*
  	 * Carefully handle integer overflow which can occur when mask == ~0UL.
@@ -466,12 +469,27 @@ found:
 
 	return dma_addr;
 }
+EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single);
+
+/*
+ * Allocates bounce buffer and returns its kernel virtual address.
+ */
+
+static void *
+map_single(struct device *hwdev, phys_addr_t phys, size_t size,
+	   enum dma_data_direction dir)
+{
+	dma_addr_t start_dma_addr = swiotlb_virt_to_bus(hwdev, io_tlb_start);
+
+	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, dir);
+}
 
 /*
  * dma_addr is the kernel virtual address of the bounce buffer to unmap.
  */
-static void
-do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
+void
+swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size,
+			enum dma_data_direction dir)
 {
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
@@ -509,10 +527,12 @@ do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 	}
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 }
+EXPORT_SYMBOL_GPL(swiotlb_tbl_unmap_single);
 
-static void
-sync_single(struct device *hwdev, char *dma_addr, size_t size,
-	    int dir, int target)
+void
+swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size,
+			enum dma_data_direction dir,
+			enum dma_sync_target target)
 {
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t phys = io_tlb_orig_addr[index];
@@ -536,6 +556,7 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size,
 		BUG();
 	}
 }
+EXPORT_SYMBOL_GPL(swiotlb_tbl_sync_single);
 
 void *
 swiotlb_alloc_coherent(struct device *hwdev, size_t size,
@@ -559,8 +580,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	}
 	if (!ret) {
 		/*
-		 * We are either out of memory or the device can't DMA
-		 * to GFP_DMA memory; fall back on map_single(), which
+		 * We are either out of memory or the device can't DMA to
+		 * GFP_DMA memory; fall back on map_single(), which
 		 * will grab memory from the lowest available address range.
 		 */
 		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
@@ -578,7 +599,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		       (unsigned long long)dev_addr);
 
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
+		swiotlb_tbl_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
 		return NULL;
 	}
 	*dma_handle = dev_addr;
@@ -596,13 +617,14 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	if (!is_swiotlb_buffer(paddr))
 		free_pages((unsigned long)vaddr, get_order(size));
 	else
-		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
+		/* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */
+		swiotlb_tbl_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
 }
 EXPORT_SYMBOL(swiotlb_free_coherent);
 
 static void
-swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
+swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
+	     int do_panic)
 {
 	/*
 	 * Ran out of IOMMU space for this operation. This is very bad.
@@ -680,14 +702,14 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
  * whatever the device wrote there.
  */
 static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
-			 size_t size, int dir)
+			 size_t size, enum dma_data_direction dir)
 {
 	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 
 	if (is_swiotlb_buffer(paddr)) {
-		do_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
 		return;
 	}
 
@@ -723,14 +745,16 @@ EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
  */
 static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
-		    size_t size, int dir, int target)
+		    size_t size, enum dma_data_direction dir,
+		    enum dma_sync_target target)
 {
 	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 
 	if (is_swiotlb_buffer(paddr)) {
-		sync_single(hwdev, phys_to_virt(paddr), size, dir, target);
+		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
+				       target);
 		return;
 	}
 
@@ -809,7 +833,7 @@ EXPORT_SYMBOL(swiotlb_map_sg_attrs);
 
 int
 swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
-	       int dir)
+	       enum dma_data_direction dir)
 {
 	return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
 }
@@ -836,7 +860,7 @@ EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
 
 void
 swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
-		 int dir)
+		 enum dma_data_direction dir)
 {
 	return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
 }
@@ -851,7 +875,8 @@ EXPORT_SYMBOL(swiotlb_unmap_sg);
  */
 static void
 swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
-		int nelems, int dir, int target)
+		int nelems, enum dma_data_direction dir,
+		enum dma_sync_target target)
 {
 	struct scatterlist *sg;
 	int i;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index b8a2f549ab0e..4ee19d0d3910 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -980,6 +980,11 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
  *             [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15]
  *           little endian output byte order is:
  *             [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15]
+ * - 'V' For a struct va_format which contains a format string * and va_list *,
+ *       call vsnprintf(->format, *->va_list).
+ *       Implements a "recursive vsnprintf".
+ *       Do not use this feature without some mechanism to verify the
+ *       correctness of the format string and va_list arguments.
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -1025,6 +1030,10 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		break;
 	case 'U':
 		return uuid_string(buf, end, ptr, spec, fmt);
+	case 'V':
+		return buf + vsnprintf(buf, end - buf,
+				       ((struct va_format *)ptr)->fmt,
+				       *(((struct va_format *)ptr)->va));
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {