Merge commit 'v3.5-rc2' into next

30 files changed, 1430 insertions, 289 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index ac9d8d3..8269d56 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -16,6 +16,12 @@ config BITREVERSE
 config RATIONAL
 	boolean
 
+config GENERIC_STRNCPY_FROM_USER
+	bool
+
+config GENERIC_STRNLEN_USER
+	bool
+
 config GENERIC_FIND_FIRST_BIT
 	bool
 
@@ -33,6 +39,9 @@ config GENERIC_IO
 	boolean
 	default n
 
+config STMP_DEVICE
+	bool
+
 config CRC_CCITT
 	tristate "CRC-CCITT functions"
 	help
@@ -353,6 +362,14 @@ config CORDIC
 	  This option provides an implementation of the CORDIC algorithm;
 	  calculations are in fixed point. Module will be called cordic.
 
+config DDR
+	bool "JEDEC DDR data"
+	help
+	  Data from JEDEC specs for DDR SDRAM memories,
+	  particularly the AC timing parameters and addressing
+	  information. This data is useful for drivers handling
+	  DDR SDRAM controllers.
+
 config MPILIB
 	tristate
 	select CLZ_TAB
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 6777153..a42d3ae 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -3,12 +3,16 @@ config PRINTK_TIME
 	bool "Show timing information on printks"
 	depends on PRINTK
 	help
-	  Selecting this option causes timing information to be
-	  included in printk output.  This allows you to measure
-	  the interval between kernel operations, including bootup
-	  operations.  This is useful for identifying long delays
-	  in kernel startup.  Or add printk.time=1 at boot-time.
-	  See Documentation/kernel-parameters.txt
+	  Selecting this option causes time stamps of the printk()
+	  messages to be added to the output of the syslog() system
+	  call and at the console.
+
+	  The timestamp is always recorded internally, and exported
+	  to /dev/kmsg. This flag just specifies if the timestamp should
+	  be included, not that the timestamp is recorded.
+
+	  The behavior is also controlled by the kernel command line
+	  parameter printk.time=1. See Documentation/kernel-parameters.txt
 
 config DEFAULT_MESSAGE_LOGLEVEL
 	int "Default message log level (1-7)"
@@ -70,6 +74,15 @@ config STRIP_ASM_SYMS
 	  that look like '.Lxxx') so they don't pollute the output of
 	  get_wchan() and suchlike.
 
+config READABLE_ASM
+        bool "Generate readable assembler code"
+        depends on DEBUG_KERNEL
+        help
+          Disable some compiler optimizations that tend to generate human unreadable
+          assembler output. This may make the kernel slightly slower, but it helps
+          to keep kernel developers who have to stare a lot at assembler listings
+          sane.
+
 config UNUSED_SYMBOLS
 	bool "Enable unused/obsolete exported symbols"
 	default y if X86
@@ -1205,8 +1218,13 @@ config DYNAMIC_DEBUG
 	  otherwise be available at runtime. These messages can then be
 	  enabled/disabled based on various levels of scope - per source file,
 	  function, module, format string, and line number. This mechanism
-	  implicitly enables all pr_debug() and dev_dbg() calls. The impact of
-	  this compile option is a larger kernel text size of about 2%.
+	  implicitly compiles in all pr_debug() and dev_dbg() calls, which
+	  enlarges the kernel text size by about 2%.
+
+	  If a source file is compiled with DEBUG flag set, any
+	  pr_debug() calls in it are enabled by default, but can be
+	  disabled at runtime as below.  Note that DEBUG flag is
+	  turned on by many CONFIG_*DEBUG* options.
 
 	  Usage:
 
@@ -1223,16 +1241,16 @@ config DYNAMIC_DEBUG
 	  lineno : line number of the debug statement
 	  module : module that contains the debug statement
 	  function : function that contains the debug statement
-          flags : 'p' means the line is turned 'on' for printing
+          flags : '=p' means the line is turned 'on' for printing
           format : the format used for the debug statement
 
 	  From a live system:
 
 		nullarbor:~ # cat <debugfs>/dynamic_debug/control
 		# filename:lineno [module]function flags format
-		fs/aio.c:222 [aio]__put_ioctx - "__put_ioctx:\040freeing\040%p\012"
-		fs/aio.c:248 [aio]ioctx_alloc - "ENOMEM:\040nr_events\040too\040high\012"
-		fs/aio.c:1770 [aio]sys_io_cancel - "calling\040cancel\012"
+		fs/aio.c:222 [aio]__put_ioctx =_ "__put_ioctx:\040freeing\040%p\012"
+		fs/aio.c:248 [aio]ioctx_alloc =_ "ENOMEM:\040nr_events\040too\040high\012"
+		fs/aio.c:1770 [aio]sys_io_cancel =_ "calling\040cancel\012"
 
 	  Example usage:
 
diff --git a/lib/Makefile b/lib/Makefile
index 18515f0..8c31a0c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -123,6 +123,13 @@ obj-$(CONFIG_SIGNATURE) += digsig.o
 
 obj-$(CONFIG_CLZ_TAB) += clz_tab.o
 
+obj-$(CONFIG_DDR) += jedec_ddr_data.o
+
+obj-$(CONFIG_GENERIC_STRNCPY_FROM_USER) += strncpy_from_user.o
+obj-$(CONFIG_GENERIC_STRNLEN_USER) += strnlen_user.o
+
+obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b5a8b6a..06fdfa1 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -369,7 +369,8 @@ EXPORT_SYMBOL(bitmap_find_next_zero_area);
  * @nmaskbits: size of bitmap, in bits
  *
  * Exactly @nmaskbits bits are displayed.  Hex digits are grouped into
- * comma-separated sets of eight digits per set.
+ * comma-separated sets of eight digits per set.  Returns the number of
+ * characters which were written to *buf, excluding the trailing \0.
  */
 int bitmap_scnprintf(char *buf, unsigned int buflen,
 	const unsigned long *maskp, int nmaskbits)
@@ -517,8 +518,8 @@ EXPORT_SYMBOL(bitmap_parse_user);
  *
  * Helper routine for bitmap_scnlistprintf().  Write decimal number
  * or range to buf, suppressing output past buf+buflen, with optional
- * comma-prefix.  Return len of what would be written to buf, if it
- * all fit.
+ * comma-prefix.  Return len of what was written to *buf, excluding the
+ * trailing \0.
  */
 static inline int bscnl_emit(char *buf, int buflen, int rbot, int rtop, int len)
 {
@@ -544,9 +545,8 @@ static inline int bscnl_emit(char *buf, int buflen, int rbot, int rtop, int len)
  * the range.  Output format is compatible with the format
  * accepted as input by bitmap_parselist().
  *
- * The return value is the number of characters which would be
- * generated for the given input, excluding the trailing '\0', as
- * per ISO C99.
+ * The return value is the number of characters which were written to *buf
+ * excluding the trailing '\0', as per ISO C99's scnprintf.
  */
 int bitmap_scnlistprintf(char *buf, unsigned int buflen,
 	const unsigned long *maskp, int nmaskbits)
diff --git a/lib/btree.c b/lib/btree.c
index e5ec1e9..f9a4846 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -319,8 +319,8 @@ void *btree_get_prev(struct btree_head *head, struct btree_geo *geo,
 
 	if (head->height == 0)
 		return NULL;
-retry:
 	longcpy(key, __key, geo->keylen);
+retry:
 	dec_key(geo, key);
 
 	node = head->node;
@@ -351,7 +351,7 @@ retry:
 	}
 miss:
 	if (retry_key) {
-		__key = retry_key;
+		longcpy(key, retry_key, geo->keylen);
 		retry_key = NULL;
 		goto retry;
 	}
@@ -509,6 +509,7 @@ retry:
 int btree_insert(struct btree_head *head, struct btree_geo *geo,
 		unsigned long *key, void *val, gfp_t gfp)
 {
+	BUG_ON(!val);
 	return btree_insert_level(head, geo, key, val, 1, gfp);
 }
 EXPORT_SYMBOL_GPL(btree_insert);
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 0ab9ae8..d11808c 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -79,30 +79,29 @@ static const char *obj_states[ODEBUG_STATE_MAX] = {
 	[ODEBUG_STATE_NOTAVAILABLE]	= "not available",
 };
 
-static int fill_pool(void)
+static void fill_pool(void)
 {
 	gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
 	struct debug_obj *new;
 	unsigned long flags;
 
 	if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL))
-		return obj_pool_free;
+		return;
 
 	if (unlikely(!obj_cache))
-		return obj_pool_free;
+		return;
 
 	while (obj_pool_free < ODEBUG_POOL_MIN_LEVEL) {
 
 		new = kmem_cache_zalloc(obj_cache, gfp);
 		if (!new)
-			return obj_pool_free;
+			return;
 
 		raw_spin_lock_irqsave(&pool_lock, flags);
 		hlist_add_head(&new->node, &obj_pool);
 		obj_pool_free++;
 		raw_spin_unlock_irqrestore(&pool_lock, flags);
 	}
-	return obj_pool_free;
 }
 
 /*
@@ -1052,10 +1051,10 @@ static int __init debug_objects_replace_static_objects(void)
 			cnt++;
 		}
 	}
+	local_irq_enable();
 
 	printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt,
 	       obj_pool_used);
-	local_irq_enable();
 	return 0;
 free:
 	hlist_for_each_entry_safe(obj, node, tmp, &objects, node) {
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 13ef233..518aea7 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -430,7 +430,7 @@ static struct dma_debug_entry *__dma_entry_alloc(void)
  */
 static struct dma_debug_entry *dma_entry_alloc(void)
 {
-	struct dma_debug_entry *entry = NULL;
+	struct dma_debug_entry *entry;
 	unsigned long flags;
 
 	spin_lock_irqsave(&free_entries_lock, flags);
@@ -438,11 +438,14 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	if (list_empty(&free_entries)) {
 		pr_err("DMA-API: debugging out of memory - disabling\n");
 		global_disable = true;
-		goto out;
+		spin_unlock_irqrestore(&free_entries_lock, flags);
+		return NULL;
 	}
 
 	entry = __dma_entry_alloc();
 
+	spin_unlock_irqrestore(&free_entries_lock, flags);
+
 #ifdef CONFIG_STACKTRACE
 	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
 	entry->stacktrace.entries = entry->st_entries;
@@ -450,9 +453,6 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	save_stack_trace(&entry->stacktrace);
 #endif
 
-out:
-	spin_unlock_irqrestore(&free_entries_lock, flags);
-
 	return entry;
 }
 
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 310c753..7ca29a0 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -107,20 +107,22 @@ static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
 	return buf;
 }
 
-#define vpr_info_dq(q, msg)						\
-do {									\
-	if (verbose)							\
-		/* trim last char off format print */			\
-		pr_info("%s: func=\"%s\" file=\"%s\" "			\
-			"module=\"%s\" format=\"%.*s\" "		\
-			"lineno=%u-%u",					\
-			msg,						\
-			q->function ? q->function : "",			\
-			q->filename ? q->filename : "",			\
-			q->module ? q->module : "",			\
-			(int)(q->format ? strlen(q->format) - 1 : 0),	\
-			q->format ? q->format : "",			\
-			q->first_lineno, q->last_lineno);		\
+#define vpr_info(fmt, ...) \
+	if (verbose) do { pr_info(fmt, ##__VA_ARGS__); } while (0)
+
+#define vpr_info_dq(q, msg)					\
+do {								\
+	/* trim last char off format print */			\
+	vpr_info("%s: func=\"%s\" file=\"%s\" "			\
+		"module=\"%s\" format=\"%.*s\" "		\
+		"lineno=%u-%u",					\
+		msg,						\
+		q->function ? q->function : "",			\
+		q->filename ? q->filename : "",			\
+		q->module ? q->module : "",			\
+		(int)(q->format ? strlen(q->format) - 1 : 0),	\
+		q->format ? q->format : "",			\
+		q->first_lineno, q->last_lineno);		\
 } while (0)
 
 /*
@@ -180,12 +182,11 @@ static int ddebug_change(const struct ddebug_query *query,
 			if (newflags == dp->flags)
 				continue;
 			dp->flags = newflags;
-			if (verbose)
-				pr_info("changed %s:%d [%s]%s =%s\n",
-					trim_prefix(dp->filename), dp->lineno,
-					dt->mod_name, dp->function,
-					ddebug_describe_flags(dp, flagbuf,
-							sizeof(flagbuf)));
+			vpr_info("changed %s:%d [%s]%s =%s\n",
+				trim_prefix(dp->filename), dp->lineno,
+				dt->mod_name, dp->function,
+				ddebug_describe_flags(dp, flagbuf,
+						sizeof(flagbuf)));
 		}
 	}
 	mutex_unlock(&ddebug_lock);
@@ -337,7 +338,7 @@ static int check_set(const char **dest, char *src, char *name)
  * Returns 0 on success, <0 on error.
  */
 static int ddebug_parse_query(char *words[], int nwords,
-			       struct ddebug_query *query)
+			struct ddebug_query *query, const char *modname)
 {
 	unsigned int i;
 	int rc;
@@ -347,6 +348,10 @@ static int ddebug_parse_query(char *words[], int nwords,
 		return -EINVAL;
 	memset(query, 0, sizeof(*query));
 
+	if (modname)
+		/* support $modname.dyndbg=<multiple queries> */
+		query->module = modname;
+
 	for (i = 0 ; i < nwords ; i += 2) {
 		if (!strcmp(words[i], "func"))
 			rc = check_set(&query->function, words[i+1], "func");
@@ -410,8 +415,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 	default:
 		return -EINVAL;
 	}
-	if (verbose)
-		pr_info("op='%c'\n", op);
+	vpr_info("op='%c'\n", op);
 
 	for ( ; *str ; ++str) {
 		for (i = ARRAY_SIZE(opt_array) - 1; i >= 0; i--) {
@@ -423,8 +427,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 		if (i < 0)
 			return -EINVAL;
 	}
-	if (verbose)
-		pr_info("flags=0x%x\n", flags);
+	vpr_info("flags=0x%x\n", flags);
 
 	/* calculate final *flagsp, *maskp according to mask and op */
 	switch (op) {
@@ -441,12 +444,11 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 		*flagsp = 0;
 		break;
 	}
-	if (verbose)
-		pr_info("*flagsp=0x%x *maskp=0x%x\n", *flagsp, *maskp);
+	vpr_info("*flagsp=0x%x *maskp=0x%x\n", *flagsp, *maskp);
 	return 0;
 }
 
-static int ddebug_exec_query(char *query_string)
+static int ddebug_exec_query(char *query_string, const char *modname)
 {
 	unsigned int flags = 0, mask = 0;
 	struct ddebug_query query;
@@ -457,7 +459,7 @@ static int ddebug_exec_query(char *query_string)
 	nwords = ddebug_tokenize(query_string, words, MAXWORDS);
 	if (nwords <= 0)
 		return -EINVAL;
-	if (ddebug_parse_query(words, nwords-1, &query))
+	if (ddebug_parse_query(words, nwords-1, &query, modname))
 		return -EINVAL;
 	if (ddebug_parse_flags(words[nwords-1], &flags, &mask))
 		return -EINVAL;
@@ -473,7 +475,7 @@ static int ddebug_exec_query(char *query_string)
    last error or number of matching callsites.  Module name is either
    in param (for boot arg) or perhaps in query string.
 */
-static int ddebug_exec_queries(char *query)
+static int ddebug_exec_queries(char *query, const char *modname)
 {
 	char *split;
 	int i, errs = 0, exitcode = 0, rc, nfound = 0;
@@ -487,10 +489,9 @@ static int ddebug_exec_queries(char *query)
 		if (!query || !*query || *query == '#')
 			continue;
 
-		if (verbose)
-			pr_info("query %d: \"%s\"\n", i, query);
+		vpr_info("query %d: \"%s\"\n", i, query);
 
-		rc = ddebug_exec_query(query);
+		rc = ddebug_exec_query(query, modname);
 		if (rc < 0) {
 			errs++;
 			exitcode = rc;
@@ -498,7 +499,7 @@ static int ddebug_exec_queries(char *query)
 			nfound += rc;
 		i++;
 	}
-	pr_info("processed %d queries, with %d matches, %d errs\n",
+	vpr_info("processed %d queries, with %d matches, %d errs\n",
 		 i, nfound, errs);
 
 	if (exitcode)
@@ -653,10 +654,9 @@ static ssize_t ddebug_proc_write(struct file *file, const char __user *ubuf,
 		return -EFAULT;
 	}
 	tmpbuf[len] = '\0';
-	if (verbose)
-		pr_info("read %d bytes from userspace\n", (int)len);
+	vpr_info("read %d bytes from userspace\n", (int)len);
 
-	ret = ddebug_exec_queries(tmpbuf);
+	ret = ddebug_exec_queries(tmpbuf, NULL);
 	kfree(tmpbuf);
 	if (ret < 0)
 		return ret;
@@ -717,8 +717,7 @@ static void *ddebug_proc_start(struct seq_file *m, loff_t *pos)
 	struct _ddebug *dp;
 	int n = *pos;
 
-	if (verbose)
-		pr_info("called m=%p *pos=%lld\n", m, (unsigned long long)*pos);
+	vpr_info("called m=%p *pos=%lld\n", m, (unsigned long long)*pos);
 
 	mutex_lock(&ddebug_lock);
 
@@ -742,9 +741,8 @@ static void *ddebug_proc_next(struct seq_file *m, void *p, loff_t *pos)
 	struct ddebug_iter *iter = m->private;
 	struct _ddebug *dp;
 
-	if (verbose)
-		pr_info("called m=%p p=%p *pos=%lld\n",
-			m, p, (unsigned long long)*pos);
+	vpr_info("called m=%p p=%p *pos=%lld\n",
+		m, p, (unsigned long long)*pos);
 
 	if (p == SEQ_START_TOKEN)
 		dp = ddebug_iter_first(iter);
@@ -766,8 +764,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 	struct _ddebug *dp = p;
 	char flagsbuf[10];
 
-	if (verbose)
-		pr_info("called m=%p p=%p\n", m, p);
+	vpr_info("called m=%p p=%p\n", m, p);
 
 	if (p == SEQ_START_TOKEN) {
 		seq_puts(m,
@@ -791,8 +788,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
  */
 static void ddebug_proc_stop(struct seq_file *m, void *p)
 {
-	if (verbose)
-		pr_info("called m=%p p=%p\n", m, p);
+	vpr_info("called m=%p p=%p\n", m, p);
 	mutex_unlock(&ddebug_lock);
 }
 
@@ -815,8 +811,7 @@ static int ddebug_proc_open(struct inode *inode, struct file *file)
 	struct ddebug_iter *iter;
 	int err;
 
-	if (verbose)
-		pr_info("called\n");
+	vpr_info("called\n");
 
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (iter == NULL)
@@ -866,12 +861,51 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 	list_add_tail(&dt->link, &ddebug_tables);
 	mutex_unlock(&ddebug_lock);
 
-	if (verbose)
-		pr_info("%u debug prints in module %s\n", n, dt->mod_name);
+	vpr_info("%u debug prints in module %s\n", n, dt->mod_name);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ddebug_add_module);
 
+/* helper for ddebug_dyndbg_(boot|module)_param_cb */
+static int ddebug_dyndbg_param_cb(char *param, char *val,
+				const char *modname, int on_err)
+{
+	char *sep;
+
+	sep = strchr(param, '.');
+	if (sep) {
+		/* needed only for ddebug_dyndbg_boot_param_cb */
+		*sep = '\0';
+		modname = param;
+		param = sep + 1;
+	}
+	if (strcmp(param, "dyndbg"))
+		return on_err; /* determined by caller */
+
+	ddebug_exec_queries((val ? val : "+p"), modname);
+
+	return 0; /* query failure shouldnt stop module load */
+}
+
+/* handle both dyndbg and $module.dyndbg params at boot */
+static int ddebug_dyndbg_boot_param_cb(char *param, char *val,
+				const char *unused)
+{
+	vpr_info("%s=\"%s\"\n", param, val);
+	return ddebug_dyndbg_param_cb(param, val, NULL, 0);
+}
+
+/*
+ * modprobe foo finds foo.params in boot-args, strips "foo.", and
+ * passes them to load_module().  This callback gets unknown params,
+ * processes dyndbg params, rejects others.
+ */
+int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *module)
+{
+	vpr_info("module: %s %s=\"%s\"\n", module, param, val);
+	return ddebug_dyndbg_param_cb(param, val, module, -ENOENT);
+}
+
 static void ddebug_table_free(struct ddebug_table *dt)
 {
 	list_del_init(&dt->link);
@@ -888,8 +922,7 @@ int ddebug_remove_module(const char *mod_name)
 	struct ddebug_table *dt, *nextdt;
 	int ret = -ENOENT;
 
-	if (verbose)
-		pr_info("removing module \"%s\"\n", mod_name);
+	vpr_info("removing module \"%s\"\n", mod_name);
 
 	mutex_lock(&ddebug_lock);
 	list_for_each_entry_safe(dt, nextdt, &ddebug_tables, link) {
@@ -940,8 +973,10 @@ static int __init dynamic_debug_init(void)
 {
 	struct _ddebug *iter, *iter_start;
 	const char *modname = NULL;
+	char *cmdline;
 	int ret = 0;
-	int n = 0;
+	int n = 0, entries = 0, modct = 0;
+	int verbose_bytes = 0;
 
 	if (__start___verbose == __stop___verbose) {
 		pr_warn("_ddebug table is empty in a "
@@ -952,10 +987,15 @@ static int __init dynamic_debug_init(void)
 	modname = iter->modname;
 	iter_start = iter;
 	for (; iter < __stop___verbose; iter++) {
+		entries++;
+		verbose_bytes += strlen(iter->modname) + strlen(iter->function)
+			+ strlen(iter->filename) + strlen(iter->format);
+
 		if (strcmp(modname, iter->modname)) {
+			modct++;
 			ret = ddebug_add_module(iter_start, n, modname);
 			if (ret)
-				goto out_free;
+				goto out_err;
 			n = 0;
 			modname = iter->modname;
 			iter_start = iter;
@@ -964,29 +1004,45 @@ static int __init dynamic_debug_init(void)
 	}
 	ret = ddebug_add_module(iter_start, n, modname);
 	if (ret)
-		goto out_free;
+		goto out_err;
+
+	ddebug_init_success = 1;
+	vpr_info("%d modules, %d entries and %d bytes in ddebug tables,"
+		" %d bytes in (readonly) verbose section\n",
+		modct, entries, (int)( modct * sizeof(struct ddebug_table)),
+		verbose_bytes + (int)(__stop___verbose - __start___verbose));
 
-	/* ddebug_query boot param got passed -> set it up */
+	/* apply ddebug_query boot param, dont unload tables on err */
 	if (ddebug_setup_string[0] != '\0') {
-		ret = ddebug_exec_queries(ddebug_setup_string);
+		pr_warn("ddebug_query param name is deprecated,"
+			" change it to dyndbg\n");
+		ret = ddebug_exec_queries(ddebug_setup_string, NULL);
 		if (ret < 0)
 			pr_warn("Invalid ddebug boot param %s",
 				ddebug_setup_string);
 		else
 			pr_info("%d changes by ddebug_query\n", ret);
-
-		/* keep tables even on ddebug_query parse error */
-		ret = 0;
 	}
+	/* now that ddebug tables are loaded, process all boot args
+	 * again to find and activate queries given in dyndbg params.
+	 * While this has already been done for known boot params, it
+	 * ignored the unknown ones (dyndbg in particular).  Reusing
+	 * parse_args avoids ad-hoc parsing.  This will also attempt
+	 * to activate queries for not-yet-loaded modules, which is
+	 * slightly noisy if verbose, but harmless.
+	 */
+	cmdline = kstrdup(saved_command_line, GFP_KERNEL);
+	parse_args("dyndbg params", cmdline, NULL,
+		   0, 0, 0, &ddebug_dyndbg_boot_param_cb);
+	kfree(cmdline);
+	return 0;
 
-out_free:
-	if (ret)
-		ddebug_remove_all_tables();
-	else
-		ddebug_init_success = 1;
+out_err:
+	ddebug_remove_all_tables();
 	return 0;
 }
 /* Allow early initialization for boot messages via boot param */
-arch_initcall(dynamic_debug_init);
+early_initcall(dynamic_debug_init);
+
 /* Debugfs setup must be done later */
-module_init(dynamic_debug_init_debugfs);
+fs_initcall(dynamic_debug_init_debugfs);
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index 6ab4587..0777c5a 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -10,23 +10,27 @@
 #include <linux/jiffies.h>
 #include <linux/dynamic_queue_limits.h>
 
-#define POSDIFF(A, B) ((A) > (B) ? (A) - (B) : 0)
+#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
+#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
 
 /* Records completed count and recalculates the queue limit */
 void dql_completed(struct dql *dql, unsigned int count)
 {
 	unsigned int inprogress, prev_inprogress, limit;
-	unsigned int ovlimit, all_prev_completed, completed;
+	unsigned int ovlimit, completed, num_queued;
+	bool all_prev_completed;
+
+	num_queued = ACCESS_ONCE(dql->num_queued);
 
 	/* Can't complete more than what's in queue */
-	BUG_ON(count > dql->num_queued - dql->num_completed);
+	BUG_ON(count > num_queued - dql->num_completed);
 
 	completed = dql->num_completed + count;
 	limit = dql->limit;
-	ovlimit = POSDIFF(dql->num_queued - dql->num_completed, limit);
-	inprogress = dql->num_queued - completed;
+	ovlimit = POSDIFF(num_queued - dql->num_completed, limit);
+	inprogress = num_queued - completed;
 	prev_inprogress = dql->prev_num_queued - dql->num_completed;
-	all_prev_completed = POSDIFF(completed, dql->prev_num_queued);
+	all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued);
 
 	if ((ovlimit && !inprogress) ||
 	    (dql->prev_ovlimit && all_prev_completed)) {
@@ -104,7 +108,7 @@ void dql_completed(struct dql *dql, unsigned int count)
 	dql->prev_ovlimit = ovlimit;
 	dql->prev_last_obj_cnt = dql->last_obj_cnt;
 	dql->num_completed = completed;
-	dql->prev_num_queued = dql->num_queued;
+	dql->prev_num_queued = num_queued;
 }
 EXPORT_SYMBOL(dql_completed);
 
diff --git a/lib/jedec_ddr_data.c b/lib/jedec_ddr_data.c
new file mode 100644
index 0000000..6d2cbf1
--- /dev/null
+++ b/lib/jedec_ddr_data.c
@@ -0,0 +1,135 @@
+/*
+ * DDR addressing details and AC timing parameters from JEDEC specs
+ *
+ * Copyright (C) 2012 Texas Instruments, Inc.
+ *
+ * Aneesh V <aneesh@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <memory/jedec_ddr.h>
+#include <linux/module.h>
+
+/* LPDDR2 addressing details from JESD209-2 section 2.4 */
+const struct lpddr2_addressing
+	lpddr2_jedec_addressing_table[NUM_DDR_ADDR_TABLE_ENTRIES] = {
+	{B4, T_REFI_15_6, T_RFC_90}, /* 64M */
+	{B4, T_REFI_15_6, T_RFC_90}, /* 128M */
+	{B4, T_REFI_7_8,  T_RFC_90}, /* 256M */
+	{B4, T_REFI_7_8,  T_RFC_90}, /* 512M */
+	{B8, T_REFI_7_8, T_RFC_130}, /* 1GS4 */
+	{B8, T_REFI_3_9, T_RFC_130}, /* 2GS4 */
+	{B8, T_REFI_3_9, T_RFC_130}, /* 4G */
+	{B8, T_REFI_3_9, T_RFC_210}, /* 8G */
+	{B4, T_REFI_7_8, T_RFC_130}, /* 1GS2 */
+	{B4, T_REFI_3_9, T_RFC_130}, /* 2GS2 */
+};
+EXPORT_SYMBOL_GPL(lpddr2_jedec_addressing_table);
+
+/* LPDDR2 AC timing parameters from JESD209-2 section 12 */
+const struct lpddr2_timings
+	lpddr2_jedec_timings[NUM_DDR_TIMING_TABLE_ENTRIES] = {
+	/* Speed bin 400(200 MHz) */
+	[0] = {
+		.max_freq	= 200000000,
+		.min_freq	= 10000000,
+		.tRPab		= 21000,
+		.tRCD		= 18000,
+		.tWR		= 15000,
+		.tRAS_min	= 42000,
+		.tRRD		= 10000,
+		.tWTR		= 10000,
+		.tXP		= 7500,
+		.tRTP		= 7500,
+		.tCKESR		= 15000,
+		.tDQSCK_max	= 5500,
+		.tFAW		= 50000,
+		.tZQCS		= 90000,
+		.tZQCL		= 360000,
+		.tZQinit	= 1000000,
+		.tRAS_max_ns	= 70000,
+		.tDQSCK_max_derated = 6000,
+	},
+	/* Speed bin 533(266 MHz) */
+	[1] = {
+		.max_freq	= 266666666,
+		.min_freq	= 10000000,
+		.tRPab		= 21000,
+		.tRCD		= 18000,
+		.tWR		= 15000,
+		.tRAS_min	= 42000,
+		.tRRD		= 10000,
+		.tWTR		= 7500,
+		.tXP		= 7500,
+		.tRTP		= 7500,
+		.tCKESR		= 15000,
+		.tDQSCK_max	= 5500,
+		.tFAW		= 50000,
+		.tZQCS		= 90000,
+		.tZQCL		= 360000,
+		.tZQinit	= 1000000,
+		.tRAS_max_ns	= 70000,
+		.tDQSCK_max_derated = 6000,
+	},
+	/* Speed bin 800(400 MHz) */
+	[2] = {
+		.max_freq	= 400000000,
+		.min_freq	= 10000000,
+		.tRPab		= 21000,
+		.tRCD		= 18000,
+		.tWR		= 15000,
+		.tRAS_min	= 42000,
+		.tRRD		= 10000,
+		.tWTR		= 7500,
+		.tXP		= 7500,
+		.tRTP		= 7500,
+		.tCKESR		= 15000,
+		.tDQSCK_max	= 5500,
+		.tFAW		= 50000,
+		.tZQCS		= 90000,
+		.tZQCL		= 360000,
+		.tZQinit	= 1000000,
+		.tRAS_max_ns	= 70000,
+		.tDQSCK_max_derated = 6000,
+	},
+	/* Speed bin 1066(533 MHz) */
+	[3] = {
+		.max_freq	= 533333333,
+		.min_freq	= 10000000,
+		.tRPab		= 21000,
+		.tRCD		= 18000,
+		.tWR		= 15000,
+		.tRAS_min	= 42000,
+		.tRRD		= 10000,
+		.tWTR		= 7500,
+		.tXP		= 7500,
+		.tRTP		= 7500,
+		.tCKESR		= 15000,
+		.tDQSCK_max	= 5500,
+		.tFAW		= 50000,
+		.tZQCS		= 90000,
+		.tZQCL		= 360000,
+		.tZQinit	= 1000000,
+		.tRAS_max_ns	= 70000,
+		.tDQSCK_max_derated = 5620,
+	},
+};
+EXPORT_SYMBOL_GPL(lpddr2_jedec_timings);
+
+const struct lpddr2_min_tck lpddr2_jedec_min_tck = {
+	.tRPab		= 3,
+	.tRCD		= 3,
+	.tWR		= 3,
+	.tRASmin	= 3,
+	.tRRD		= 2,
+	.tWTR		= 2,
+	.tXP		= 2,
+	.tRTP		= 2,
+	.tCKE		= 3,
+	.tCKESR		= 3,
+	.tFAW		= 8
+};
+EXPORT_SYMBOL_GPL(lpddr2_jedec_min_tck);
diff --git a/lib/kobject.c b/lib/kobject.c
index aeefa8b..e07ee1f 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -47,13 +47,11 @@ static int populate_dir(struct kobject *kobj)
 static int create_dir(struct kobject *kobj)
 {
 	int error = 0;
-	if (kobject_name(kobj)) {
-		error = sysfs_create_dir(kobj);
-		if (!error) {
-			error = populate_dir(kobj);
-			if (error)
-				sysfs_remove_dir(kobj);
-		}
+	error = sysfs_create_dir(kobj);
+	if (!error) {
+		error = populate_dir(kobj);
+		if (error)
+			sysfs_remove_dir(kobj);
 	}
 	return error;
 }
@@ -634,7 +632,7 @@ struct kobject *kobject_create(void)
 /**
  * kobject_create_and_add - create a struct kobject dynamically and register it with sysfs
  *
- * @name: the name for the kset
+ * @name: the name for the kobject
  * @parent: the parent kobject of this kobject, if any.
  *
  * This function creates a kobject structure dynamically and registers it
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 982b850..23a5e03 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -10,6 +10,7 @@
 #include <linux/list.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
+#include <linux/rculist.h>
 
 /*
  * Insert a new entry between two known consecutive entries.
@@ -30,6 +31,9 @@ void __list_add(struct list_head *new,
 		"list_add corruption. prev->next should be "
 		"next (%p), but was %p. (prev=%p).\n",
 		next, prev->next, prev);
+	WARN(new == prev || new == next,
+	     "list_add double add: new=%p, prev=%p, next=%p.\n",
+	     new, prev, next);
 	next->prev = new;
 	new->next = next;
 	new->prev = prev;
@@ -75,3 +79,24 @@ void list_del(struct list_head *entry)
 	entry->prev = LIST_POISON2;
 }
 EXPORT_SYMBOL(list_del);
+
+/*
+ * RCU variants.
+ */
+void __list_add_rcu(struct list_head *new,
+		    struct list_head *prev, struct list_head *next)
+{
+	WARN(next->prev != prev,
+		"list_add_rcu corruption. next->prev should be "
+		"prev (%p), but was %p. (next=%p).\n",
+		prev, next->prev, next);
+	WARN(prev->next != next,
+		"list_add_rcu corruption. prev->next should be "
+		"next (%p), but was %p. (prev=%p).\n",
+		next, prev->next, prev);
+	new->next = next;
+	new->prev = prev;
+	rcu_assign_pointer(list_next_rcu(prev), new);
+	next->prev = new;
+}
+EXPORT_SYMBOL(__list_add_rcu);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 86516f5..e796429 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -73,11 +73,24 @@ static unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH + 1] __read_mostly;
 static struct kmem_cache *radix_tree_node_cachep;
 
 /*
+ * The radix tree is variable-height, so an insert operation not only has
+ * to build the branch to its corresponding item, it also has to build the
+ * branch to existing items if the size has to be increased (by
+ * radix_tree_extend).
+ *
+ * The worst case is a zero height tree with just a single item at index 0,
+ * and then inserting an item at index ULONG_MAX. This requires 2 new branches
+ * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared.
+ * Hence:
+ */
+#define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1)
+
+/*
  * Per-cpu pool of preloaded nodes
  */
 struct radix_tree_preload {
 	int nr;
-	struct radix_tree_node *nodes[RADIX_TREE_MAX_PATH];
+	struct radix_tree_node *nodes[RADIX_TREE_PRELOAD_SIZE];
 };
 static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
 
@@ -673,6 +686,9 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 	 * during iterating; it can be zero only at the beginning.
 	 * And we cannot overflow iter->next_index in a single step,
 	 * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
+	 *
+	 * This condition also used by radix_tree_next_slot() to stop
+	 * contiguous iterating, and forbid swithing to the next chunk.
 	 */
 	index = iter->next_index;
 	if (!index && iter->index)
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 8a38102..de06dfe 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -1,6 +1,6 @@
 obj-$(CONFIG_RAID6_PQ)	+= raid6_pq.o
 
-raid6_pq-y	+= algos.o recov.o tables.o int1.o int2.o int4.o \
+raid6_pq-y	+= algos.o recov.o recov_ssse3.o tables.o int1.o int2.o int4.o \
 		   int8.o int16.o int32.o altivec1.o altivec2.o altivec4.o \
 		   altivec8.o mmx.o sse1.o sse2.o
 hostprogs-y	+= mktables
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 8b02f60..589f5f5 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -17,11 +17,11 @@
  */
 
 #include <linux/raid/pq.h>
-#include <linux/module.h>
 #ifndef __KERNEL__
 #include <sys/mman.h>
 #include <stdio.h>
 #else
+#include <linux/module.h>
 #include <linux/gfp.h>
 #if !RAID6_USE_EMPTY_ZERO_PAGE
 /* In .bss so it's zeroed */
@@ -34,10 +34,6 @@ struct raid6_calls raid6_call;
 EXPORT_SYMBOL_GPL(raid6_call);
 
 const struct raid6_calls * const raid6_algos[] = {
-	&raid6_intx1,
-	&raid6_intx2,
-	&raid6_intx4,
-	&raid6_intx8,
 #if defined(__ia64__)
 	&raid6_intx16,
 	&raid6_intx32,
@@ -61,6 +57,24 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_altivec4,
 	&raid6_altivec8,
 #endif
+	&raid6_intx1,
+	&raid6_intx2,
+	&raid6_intx4,
+	&raid6_intx8,
+	NULL
+};
+
+void (*raid6_2data_recov)(int, size_t, int, int, void **);
+EXPORT_SYMBOL_GPL(raid6_2data_recov);
+
+void (*raid6_datap_recov)(int, size_t, int, void **);
+EXPORT_SYMBOL_GPL(raid6_datap_recov);
+
+const struct raid6_recov_calls *const raid6_recov_algos[] = {
+#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
+	&raid6_recov_ssse3,
+#endif
+	&raid6_recov_intx1,
 	NULL
 };
 
@@ -72,59 +86,55 @@ const struct raid6_calls * const raid6_algos[] = {
 #define time_before(x, y) ((x) < (y))
 #endif
 
-/* Try to pick the best algorithm */
-/* This code uses the gfmul table as convenient data set to abuse */
-
-int __init raid6_select_algo(void)
+static inline const struct raid6_recov_calls *raid6_choose_recov(void)
 {
-	const struct raid6_calls * const * algo;
-	const struct raid6_calls * best;
-	char *syndromes;
-	void *dptrs[(65536/PAGE_SIZE)+2];
-	int i, disks;
-	unsigned long perf, bestperf;
-	int bestprefer;
-	unsigned long j0, j1;
+	const struct raid6_recov_calls *const *algo;
+	const struct raid6_recov_calls *best;
 
-	disks = (65536/PAGE_SIZE)+2;
-	for ( i = 0 ; i < disks-2 ; i++ ) {
-		dptrs[i] = ((char *)raid6_gfmul) + PAGE_SIZE*i;
-	}
+	for (best = NULL, algo = raid6_recov_algos; *algo; algo++)
+		if (!best || (*algo)->priority > best->priority)
+			if (!(*algo)->valid || (*algo)->valid())
+				best = *algo;
 
-	/* Normal code - use a 2-page allocation to avoid D$ conflict */
-	syndromes = (void *) __get_free_pages(GFP_KERNEL, 1);
+	if (best) {
+		raid6_2data_recov = best->data2;
+		raid6_datap_recov = best->datap;
 
-	if ( !syndromes ) {
-		printk("raid6: Yikes!  No memory available.\n");
-		return -ENOMEM;
-	}
+		printk("raid6: using %s recovery algorithm\n", best->name);
+	} else
+		printk("raid6: Yikes! No recovery algorithm found!\n");
 
-	dptrs[disks-2] = syndromes;
-	dptrs[disks-1] = syndromes + PAGE_SIZE;
+	return best;
+}
+
+static inline const struct raid6_calls *raid6_choose_gen(
+	void *(*const dptrs)[(65536/PAGE_SIZE)+2], const int disks)
+{
+	unsigned long perf, bestperf, j0, j1;
+	const struct raid6_calls *const *algo;
+	const struct raid6_calls *best;
 
-	bestperf = 0;  bestprefer = 0;  best = NULL;
+	for (bestperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
+		if (!best || (*algo)->prefer >= best->prefer) {
+			if ((*algo)->valid && !(*algo)->valid())
+				continue;
 
-	for ( algo = raid6_algos ; *algo ; algo++ ) {
-		if ( !(*algo)->valid || (*algo)->valid() ) {
 			perf = 0;
 
 			preempt_disable();
 			j0 = jiffies;
-			while ( (j1 = jiffies) == j0 )
+			while ((j1 = jiffies) == j0)
 				cpu_relax();
 			while (time_before(jiffies,
 					    j1 + (1<<RAID6_TIME_JIFFIES_LG2))) {
-				(*algo)->gen_syndrome(disks, PAGE_SIZE, dptrs);
+				(*algo)->gen_syndrome(disks, PAGE_SIZE, *dptrs);
 				perf++;
 			}
 			preempt_enable();
 
-			if ( (*algo)->prefer > bestprefer ||
-			     ((*algo)->prefer == bestprefer &&
-			      perf > bestperf) ) {
-				best = *algo;
-				bestprefer = best->prefer;
+			if (perf > bestperf) {
 				bestperf = perf;
+				best = *algo;
 			}
 			printk("raid6: %-8s %5ld MB/s\n", (*algo)->name,
 			       (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
@@ -139,9 +149,46 @@ int __init raid6_select_algo(void)
 	} else
 		printk("raid6: Yikes!  No algorithm found!\n");
 
+	return best;
+}
+
+
+/* Try to pick the best algorithm */
+/* This code uses the gfmul table as convenient data set to abuse */
+
+int __init raid6_select_algo(void)
+{
+	const int disks = (65536/PAGE_SIZE)+2;
+
+	const struct raid6_calls *gen_best;
+	const struct raid6_recov_calls *rec_best;
+	char *syndromes;
+	void *dptrs[(65536/PAGE_SIZE)+2];
+	int i;
+
+	for (i = 0; i < disks-2; i++)
+		dptrs[i] = ((char *)raid6_gfmul) + PAGE_SIZE*i;
+
+	/* Normal code - use a 2-page allocation to avoid D$ conflict */
+	syndromes = (void *) __get_free_pages(GFP_KERNEL, 1);
+
+	if (!syndromes) {
+		printk("raid6: Yikes!  No memory available.\n");
+		return -ENOMEM;
+	}
+
+	dptrs[disks-2] = syndromes;
+	dptrs[disks-1] = syndromes + PAGE_SIZE;
+
+	/* select raid gen_syndrome function */
+	gen_best = raid6_choose_gen(&dptrs, disks);
+
+	/* select raid recover functions */
+	rec_best = raid6_choose_recov();
+
 	free_pages((unsigned long)syndromes, 1);
 
-	return best ? 0 : -EINVAL;
+	return gen_best && rec_best ? 0 : -EINVAL;
 }
 
 static void raid6_exit(void)
diff --git a/lib/raid6/mktables.c b/lib/raid6/mktables.c
index 8a37809..39787db 100644
--- a/lib/raid6/mktables.c
+++ b/lib/raid6/mktables.c
@@ -81,6 +81,31 @@ int main(int argc, char *argv[])
 	printf("EXPORT_SYMBOL(raid6_gfmul);\n");
 	printf("#endif\n");
 
+	/* Compute vector multiplication table */
+	printf("\nconst u8  __attribute__((aligned(256)))\n"
+		"raid6_vgfmul[256][32] =\n"
+		"{\n");
+	for (i = 0; i < 256; i++) {
+		printf("\t{\n");
+		for (j = 0; j < 16; j += 8) {
+			printf("\t\t");
+			for (k = 0; k < 8; k++)
+				printf("0x%02x,%c", gfmul(i, j + k),
+				       (k == 7) ? '\n' : ' ');
+		}
+		for (j = 0; j < 16; j += 8) {
+			printf("\t\t");
+			for (k = 0; k < 8; k++)
+				printf("0x%02x,%c", gfmul(i, (j + k) << 4),
+				       (k == 7) ? '\n' : ' ');
+		}
+		printf("\t},\n");
+	}
+	printf("};\n");
+	printf("#ifdef __KERNEL__\n");
+	printf("EXPORT_SYMBOL(raid6_vgfmul);\n");
+	printf("#endif\n");
+
 	/* Compute power-of-2 table (exponent) */
 	v = 1;
 	printf("\nconst u8 __attribute__((aligned(256)))\n"
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index fe275d7..a95bccb 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -22,8 +22,8 @@
 #include <linux/raid/pq.h>
 
 /* Recover two failed data blocks. */
-void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
-		       void **ptrs)
+static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila,
+		int failb, void **ptrs)
 {
 	u8 *p, *q, *dp, *dq;
 	u8 px, qx, db;
@@ -64,10 +64,10 @@ void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 		p++; q++;
 	}
 }
-EXPORT_SYMBOL_GPL(raid6_2data_recov);
 
 /* Recover failure of one data block plus the P block */
-void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila,
+		void **ptrs)
 {
 	u8 *p, *q, *dq;
 	const u8 *qmul;		/* Q multiplier table */
@@ -96,7 +96,15 @@ void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs)
 		q++; dq++;
 	}
 }
-EXPORT_SYMBOL_GPL(raid6_datap_recov);
+
+
+const struct raid6_recov_calls raid6_recov_intx1 = {
+	.data2 = raid6_2data_recov_intx1,
+	.datap = raid6_datap_recov_intx1,
+	.valid = NULL,
+	.name = "intx1",
+	.priority = 0,
+};
 
 #ifndef __KERNEL__
 /* Testing only */
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
new file mode 100644
index 0000000..ecb710c
--- /dev/null
+++ b/lib/raid6/recov_ssse3.c
@@ -0,0 +1,336 @@
+/*
+ * Copyright (C) 2012 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
+
+#include <linux/raid/pq.h>
+#include "x86.h"
+
+static int raid6_has_ssse3(void)
+{
+	return boot_cpu_has(X86_FEATURE_XMM) &&
+		boot_cpu_has(X86_FEATURE_XMM2) &&
+		boot_cpu_has(X86_FEATURE_SSSE3);
+}
+
+static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila,
+		int failb, void **ptrs)
+{
+	u8 *p, *q, *dp, *dq;
+	const u8 *pbmul;	/* P multiplier table for B data */
+	const u8 *qmul;		/* Q multiplier table (for both) */
+	static const u8 __aligned(16) x0f[16] = {
+		 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+		 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f};
+
+	p = (u8 *)ptrs[disks-2];
+	q = (u8 *)ptrs[disks-1];
+
+	/* Compute syndrome with zero for the missing data pages
+	   Use the dead data pages as temporary storage for
+	   delta p and delta q */
+	dp = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks-2] = dp;
+	dq = (u8 *)ptrs[failb];
+	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[disks-1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]   = dp;
+	ptrs[failb]   = dq;
+	ptrs[disks-2] = p;
+	ptrs[disks-1] = q;
+
+	/* Now, pick the proper data tables */
+	pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
+		raid6_gfexp[failb]]];
+
+	kernel_fpu_begin();
+
+	asm volatile("movdqa %0,%%xmm7" : : "m" (x0f[0]));
+
+#ifdef CONFIG_X86_64
+	asm volatile("movdqa %0,%%xmm6" : : "m" (qmul[0]));
+	asm volatile("movdqa %0,%%xmm14" : : "m" (pbmul[0]));
+	asm volatile("movdqa %0,%%xmm15" : : "m" (pbmul[16]));
+#endif
+
+	/* Now do it... */
+	while (bytes) {
+#ifdef CONFIG_X86_64
+		/* xmm6, xmm14, xmm15 */
+
+		asm volatile("movdqa %0,%%xmm1" : : "m" (q[0]));
+		asm volatile("movdqa %0,%%xmm9" : : "m" (q[16]));
+		asm volatile("movdqa %0,%%xmm0" : : "m" (p[0]));
+		asm volatile("movdqa %0,%%xmm8" : : "m" (p[16]));
+		asm volatile("pxor   %0,%%xmm1" : : "m" (dq[0]));
+		asm volatile("pxor   %0,%%xmm9" : : "m" (dq[16]));
+		asm volatile("pxor   %0,%%xmm0" : : "m" (dp[0]));
+		asm volatile("pxor   %0,%%xmm8" : : "m" (dp[16]));
+
+		/* xmm0/8 = px */
+
+		asm volatile("movdqa %xmm6,%xmm4");
+		asm volatile("movdqa %0,%%xmm5" : : "m" (qmul[16]));
+		asm volatile("movdqa %xmm6,%xmm12");
+		asm volatile("movdqa %xmm5,%xmm13");
+		asm volatile("movdqa %xmm1,%xmm3");
+		asm volatile("movdqa %xmm9,%xmm11");
+		asm volatile("movdqa %xmm0,%xmm2"); /* xmm2/10 = px */
+		asm volatile("movdqa %xmm8,%xmm10");
+		asm volatile("psraw  $4,%xmm1");
+		asm volatile("psraw  $4,%xmm9");
+		asm volatile("pand   %xmm7,%xmm3");
+		asm volatile("pand   %xmm7,%xmm11");
+		asm volatile("pand   %xmm7,%xmm1");
+		asm volatile("pand   %xmm7,%xmm9");
+		asm volatile("pshufb %xmm3,%xmm4");
+		asm volatile("pshufb %xmm11,%xmm12");
+		asm volatile("pshufb %xmm1,%xmm5");
+		asm volatile("pshufb %xmm9,%xmm13");
+		asm volatile("pxor   %xmm4,%xmm5");
+		asm volatile("pxor   %xmm12,%xmm13");
+
+		/* xmm5/13 = qx */
+
+		asm volatile("movdqa %xmm14,%xmm4");
+		asm volatile("movdqa %xmm15,%xmm1");
+		asm volatile("movdqa %xmm14,%xmm12");
+		asm volatile("movdqa %xmm15,%xmm9");
+		asm volatile("movdqa %xmm2,%xmm3");
+		asm volatile("movdqa %xmm10,%xmm11");
+		asm volatile("psraw  $4,%xmm2");
+		asm volatile("psraw  $4,%xmm10");
+		asm volatile("pand   %xmm7,%xmm3");
+		asm volatile("pand   %xmm7,%xmm11");
+		asm volatile("pand   %xmm7,%xmm2");
+		asm volatile("pand   %xmm7,%xmm10");
+		asm volatile("pshufb %xmm3,%xmm4");
+		asm volatile("pshufb %xmm11,%xmm12");
+		asm volatile("pshufb %xmm2,%xmm1");
+		asm volatile("pshufb %xmm10,%xmm9");
+		asm volatile("pxor   %xmm4,%xmm1");
+		asm volatile("pxor   %xmm12,%xmm9");
+
+		/* xmm1/9 = pbmul[px] */
+		asm volatile("pxor   %xmm5,%xmm1");
+		asm volatile("pxor   %xmm13,%xmm9");
+		/* xmm1/9 = db = DQ */
+		asm volatile("movdqa %%xmm1,%0" : "=m" (dq[0]));
+		asm volatile("movdqa %%xmm9,%0" : "=m" (dq[16]));
+
+		asm volatile("pxor   %xmm1,%xmm0");
+		asm volatile("pxor   %xmm9,%xmm8");
+		asm volatile("movdqa %%xmm0,%0" : "=m" (dp[0]));
+		asm volatile("movdqa %%xmm8,%0" : "=m" (dp[16]));
+
+		bytes -= 32;
+		p += 32;
+		q += 32;
+		dp += 32;
+		dq += 32;
+#else
+		asm volatile("movdqa %0,%%xmm1" : : "m" (*q));
+		asm volatile("movdqa %0,%%xmm0" : : "m" (*p));
+		asm volatile("pxor   %0,%%xmm1" : : "m" (*dq));
+		asm volatile("pxor   %0,%%xmm0" : : "m" (*dp));
+
+		/* 1 = dq ^ q
+		 * 0 = dp ^ p
+		 */
+		asm volatile("movdqa %0,%%xmm4" : : "m" (qmul[0]));
+		asm volatile("movdqa %0,%%xmm5" : : "m" (qmul[16]));
+
+		asm volatile("movdqa %xmm1,%xmm3");
+		asm volatile("psraw  $4,%xmm1");
+		asm volatile("pand   %xmm7,%xmm3");
+		asm volatile("pand   %xmm7,%xmm1");
+		asm volatile("pshufb %xmm3,%xmm4");
+		asm volatile("pshufb %xmm1,%xmm5");
+		asm volatile("pxor   %xmm4,%xmm5");
+
+		asm volatile("movdqa %xmm0,%xmm2"); /* xmm2 = px */
+
+		/* xmm5 = qx */
+
+		asm volatile("movdqa %0,%%xmm4" : : "m" (pbmul[0]));
+		asm volatile("movdqa %0,%%xmm1" : : "m" (pbmul[16]));
+		asm volatile("movdqa %xmm2,%xmm3");
+		asm volatile("psraw  $4,%xmm2");
+		asm volatile("pand   %xmm7,%xmm3");
+		asm volatile("pand   %xmm7,%xmm2");
+		asm volatile("pshufb %xmm3,%xmm4");
+		asm volatile("pshufb %xmm2,%xmm1");
+		asm volatile("pxor   %xmm4,%xmm1");
+
+		/* xmm1 = pbmul[px] */
+		asm volatile("pxor   %xmm5,%xmm1");
+		/* xmm1 = db = DQ */
+		asm volatile("movdqa %%xmm1,%0" : "=m" (*dq));
+
+		asm volatile("pxor   %xmm1,%xmm0");
+		asm volatile("movdqa %%xmm0,%0" : "=m" (*dp));
+
+		bytes -= 16;
+		p += 16;
+		q += 16;
+		dp += 16;
+		dq += 16;
+#endif
+	}
+
+	kernel_fpu_end();
+}
+
+
+static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila,
+		void **ptrs)
+{
+	u8 *p, *q, *dq;
+	const u8 *qmul;		/* Q multiplier table */
+	static const u8 __aligned(16) x0f[16] = {
+		 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+		 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f};
+
+	p = (u8 *)ptrs[disks-2];
+	q = (u8 *)ptrs[disks-1];
+
+	/* Compute syndrome with zero for the missing data page
+	   Use the dead data page as temporary storage for delta q */
+	dq = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks-1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]   = dq;
+	ptrs[disks-1] = q;
+
+	/* Now, pick the proper data tables */
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+	kernel_fpu_begin();
+
+	asm volatile("movdqa %0, %%xmm7" : : "m" (x0f[0]));
+
+	while (bytes) {
+#ifdef CONFIG_X86_64
+		asm volatile("movdqa %0, %%xmm3" : : "m" (dq[0]));
+		asm volatile("movdqa %0, %%xmm4" : : "m" (dq[16]));
+		asm volatile("pxor %0, %%xmm3" : : "m" (q[0]));
+		asm volatile("movdqa %0, %%xmm0" : : "m" (qmul[0]));
+
+		/* xmm3 = q[0] ^ dq[0] */
+
+		asm volatile("pxor %0, %%xmm4" : : "m" (q[16]));
+		asm volatile("movdqa %0, %%xmm1" : : "m" (qmul[16]));
+
+		/* xmm4 = q[16] ^ dq[16] */
+
+		asm volatile("movdqa %xmm3, %xmm6");
+		asm volatile("movdqa %xmm4, %xmm8");
+
+		/* xmm4 = xmm8 = q[16] ^ dq[16] */
+
+		asm volatile("psraw $4, %xmm3");
+		asm volatile("pand %xmm7, %xmm6");
+		asm volatile("pand %xmm7, %xmm3");
+		asm volatile("pshufb %xmm6, %xmm0");
+		asm volatile("pshufb %xmm3, %xmm1");
+		asm volatile("movdqa %0, %%xmm10" : : "m" (qmul[0]));
+		asm volatile("pxor %xmm0, %xmm1");
+		asm volatile("movdqa %0, %%xmm11" : : "m" (qmul[16]));
+
+		/* xmm1 = qmul[q[0] ^ dq[0]] */
+
+		asm volatile("psraw $4, %xmm4");
+		asm volatile("pand %xmm7, %xmm8");
+		asm volatile("pand %xmm7, %xmm4");
+		asm volatile("pshufb %xmm8, %xmm10");
+		asm volatile("pshufb %xmm4, %xmm11");
+		asm volatile("movdqa %0, %%xmm2" : : "m" (p[0]));
+		asm volatile("pxor %xmm10, %xmm11");
+		asm volatile("movdqa %0, %%xmm12" : : "m" (p[16]));
+
+		/* xmm11 = qmul[q[16] ^ dq[16]] */
+
+		asm volatile("pxor %xmm1, %xmm2");
+
+		/* xmm2 = p[0] ^ qmul[q[0] ^ dq[0]] */
+
+		asm volatile("pxor %xmm11, %xmm12");
+
+		/* xmm12 = p[16] ^ qmul[q[16] ^ dq[16]] */
+
+		asm volatile("movdqa %%xmm1, %0" : "=m" (dq[0]));
+		asm volatile("movdqa %%xmm11, %0" : "=m" (dq[16]));
+
+		asm volatile("movdqa %%xmm2, %0" : "=m" (p[0]));
+		asm volatile("movdqa %%xmm12, %0" : "=m" (p[16]));
+
+		bytes -= 32;
+		p += 32;
+		q += 32;
+		dq += 32;
+
+#else
+		asm volatile("movdqa %0, %%xmm3" : : "m" (dq[0]));
+		asm volatile("movdqa %0, %%xmm0" : : "m" (qmul[0]));
+		asm volatile("pxor %0, %%xmm3" : : "m" (q[0]));
+		asm volatile("movdqa %0, %%xmm1" : : "m" (qmul[16]));
+
+		/* xmm3 = *q ^ *dq */
+
+		asm volatile("movdqa %xmm3, %xmm6");
+		asm volatile("movdqa %0, %%xmm2" : : "m" (p[0]));
+		asm volatile("psraw $4, %xmm3");
+		asm volatile("pand %xmm7, %xmm6");
+		asm volatile("pand %xmm7, %xmm3");
+		asm volatile("pshufb %xmm6, %xmm0");
+		asm volatile("pshufb %xmm3, %xmm1");
+		asm volatile("pxor %xmm0, %xmm1");
+
+		/* xmm1 = qmul[*q ^ *dq */
+
+		asm volatile("pxor %xmm1, %xmm2");
+
+		/* xmm2 = *p ^ qmul[*q ^ *dq] */
+
+		asm volatile("movdqa %%xmm1, %0" : "=m" (dq[0]));
+		asm volatile("movdqa %%xmm2, %0" : "=m" (p[0]));
+
+		bytes -= 16;
+		p += 16;
+		q += 16;
+		dq += 16;
+#endif
+	}
+
+	kernel_fpu_end();
+}
+
+const struct raid6_recov_calls raid6_recov_ssse3 = {
+	.data2 = raid6_2data_recov_ssse3,
+	.datap = raid6_datap_recov_ssse3,
+	.valid = raid6_has_ssse3,
+#ifdef CONFIG_X86_64
+	.name = "ssse3x2",
+#else
+	.name = "ssse3x1",
+#endif
+	.priority = 1,
+};
+
+#endif
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index aa65169..c76151d 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -23,7 +23,7 @@ RANLIB	 = ranlib
 all:	raid6.a raid6test
 
 raid6.a: int1.o int2.o int4.o int8.o int16.o int32.o mmx.o sse1.o sse2.o \
-	 altivec1.o altivec2.o altivec4.o altivec8.o recov.o algos.o \
+	 altivec1.o altivec2.o altivec4.o altivec8.o recov.o recov_ssse3.o algos.o \
 	 tables.o
 	 rm -f $@
 	 $(AR) cq $@ $^
diff --git a/lib/raid6/test/test.c b/lib/raid6/test/test.c
index 7a93031..5a485b7 100644
--- a/lib/raid6/test/test.c
+++ b/lib/raid6/test/test.c
@@ -90,25 +90,35 @@ static int test_disks(int i, int j)
 int main(int argc, char *argv[])
 {
 	const struct raid6_calls *const *algo;
+	const struct raid6_recov_calls *const *ra;
 	int i, j;
 	int err = 0;
 
 	makedata();
 
-	for (algo = raid6_algos; *algo; algo++) {
-		if (!(*algo)->valid || (*algo)->valid()) {
-			raid6_call = **algo;
+	for (ra = raid6_recov_algos; *ra; ra++) {
+		if ((*ra)->valid  && !(*ra)->valid())
+			continue;
+		raid6_2data_recov = (*ra)->data2;
+		raid6_datap_recov = (*ra)->datap;
 
-			/* Nuke syndromes */
-			memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+		printf("using recovery %s\n", (*ra)->name);
 
-			/* Generate assumed good syndrome */
-			raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
-						(void **)&dataptrs);
+		for (algo = raid6_algos; *algo; algo++) {
+			if (!(*algo)->valid || (*algo)->valid()) {
+				raid6_call = **algo;
 
-			for (i = 0; i < NDISKS-1; i++)
-				for (j = i+1; j < NDISKS; j++)
-					err += test_disks(i, j);
+				/* Nuke syndromes */
+				memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+
+				/* Generate assumed good syndrome */
+				raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
+							(void **)&dataptrs);
+
+				for (i = 0; i < NDISKS-1; i++)
+					for (j = i+1; j < NDISKS; j++)
+						err += test_disks(i, j);
+			}
 		}
 		printf("\n");
 	}
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
index cb2a8c9..d55d632 100644
--- a/lib/raid6/x86.h
+++ b/lib/raid6/x86.h
@@ -35,24 +35,29 @@ static inline void kernel_fpu_end(void)
 {
 }
 
+#define __aligned(x) __attribute__((aligned(x)))
+
 #define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
 #define X86_FEATURE_FXSR	(0*32+24) /* FXSAVE and FXRSTOR instructions
 					   * (fast save and restore) */
 #define X86_FEATURE_XMM		(0*32+25) /* Streaming SIMD Extensions */
 #define X86_FEATURE_XMM2	(0*32+26) /* Streaming SIMD Extensions-2 */
+#define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_AVX	(4*32+28) /* Advanced Vector Extensions */
 #define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
 
 /* Should work well enough on modern CPUs for testing */
 static inline int boot_cpu_has(int flag)
 {
-	u32 eax = (flag >> 5) ? 0x80000001 : 1;
-	u32 edx;
+	u32 eax = (flag & 0x20) ? 0x80000001 : 1;
+	u32 ecx, edx;
 
 	asm volatile("cpuid"
-		     : "+a" (eax), "=d" (edx)
-		     : : "ecx", "ebx");
+		     : "+a" (eax), "=d" (edx), "=c" (ecx)
+		     : : "ebx");
 
-	return (edx >> (flag & 31)) & 1;
+	return ((flag & 0x80 ? ecx : edx) >> (flag & 31)) & 1;
 }
 
 #endif /* ndef __KERNEL__ */
diff --git a/lib/rational.c b/lib/rational.c
index d326da3..f0aa21c 100644
--- a/lib/rational.c
+++ b/lib/rational.c
@@ -1,7 +1,7 @@
 /*
  * rational fractions
  *
- * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <oskar@scara.com>
  *
  * helper functions when coping with rational numbers
  */
diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c
index 525d160..d0ec4f3 100644
--- a/lib/spinlock_debug.c
+++ b/lib/spinlock_debug.c
@@ -58,7 +58,7 @@ static void spin_dump(raw_spinlock_t *lock, const char *msg)
 	printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
 		msg, raw_smp_processor_id(),
 		current->comm, task_pid_nr(current));
-	printk(KERN_EMERG " lock: %p, .magic: %08x, .owner: %s/%d, "
+	printk(KERN_EMERG " lock: %ps, .magic: %08x, .owner: %s/%d, "
 			".owner_cpu: %d\n",
 		lock, lock->magic,
 		owner ? owner->comm : "<none>",
diff --git a/lib/stmp_device.c b/lib/stmp_device.c
new file mode 100644
index 0000000..8ac9bcc
--- /dev/null
+++ b/lib/stmp_device.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 1999 ARM Limited
+ * Copyright (C) 2000 Deep Blue Solutions Ltd
+ * Copyright 2006-2007,2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright 2008 Juergen Beisert, kernel@pengutronix.de
+ * Copyright 2009 Ilya Yanok, Emcraft Systems Ltd, yanok@emcraft.com
+ * Copyright (C) 2011 Wolfram Sang, Pengutronix e.K.
+ *
+ * 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/io.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/stmp_device.h>
+
+#define STMP_MODULE_CLKGATE	(1 << 30)
+#define STMP_MODULE_SFTRST	(1 << 31)
+
+/*
+ * Clear the bit and poll it cleared.  This is usually called with
+ * a reset address and mask being either SFTRST(bit 31) or CLKGATE
+ * (bit 30).
+ */
+static int stmp_clear_poll_bit(void __iomem *addr, u32 mask)
+{
+	int timeout = 0x400;
+
+	writel(mask, addr + STMP_OFFSET_REG_CLR);
+	udelay(1);
+	while ((readl(addr) & mask) && --timeout)
+		/* nothing */;
+
+	return !timeout;
+}
+
+int stmp_reset_block(void __iomem *reset_addr)
+{
+	int ret;
+	int timeout = 0x400;
+
+	/* clear and poll SFTRST */
+	ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_SFTRST);
+	if (unlikely(ret))
+		goto error;
+
+	/* clear CLKGATE */
+	writel(STMP_MODULE_CLKGATE, reset_addr + STMP_OFFSET_REG_CLR);
+
+	/* set SFTRST to reset the block */
+	writel(STMP_MODULE_SFTRST, reset_addr + STMP_OFFSET_REG_SET);
+	udelay(1);
+
+	/* poll CLKGATE becoming set */
+	while ((!(readl(reset_addr) & STMP_MODULE_CLKGATE)) && --timeout)
+		/* nothing */;
+	if (unlikely(!timeout))
+		goto error;
+
+	/* clear and poll SFTRST */
+	ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_SFTRST);
+	if (unlikely(ret))
+		goto error;
+
+	/* clear and poll CLKGATE */
+	ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_CLKGATE);
+	if (unlikely(ret))
+		goto error;
+
+	return 0;
+
+error:
+	pr_err("%s(%p): module reset timeout\n", __func__, reset_addr);
+	return -ETIMEDOUT;
+}
+EXPORT_SYMBOL(stmp_reset_block);
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index dd4ece3..1cffc22 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -23,15 +23,15 @@
 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",
+	static const char *units_10[] = { "B", "kB", "MB", "GB", "TB", "PB",
 				   "EB", "ZB", "YB", NULL};
-	const char *units_2[] = {"B", "KiB", "MiB", "GiB", "TiB", "PiB",
+	static const char *units_2[] = {"B", "KiB", "MiB", "GiB", "TiB", "PiB",
 				 "EiB", "ZiB", "YiB", NULL };
-	const char **units_str[] = {
+	static const char **units_str[] = {
 		[STRING_UNITS_10] =  units_10,
 		[STRING_UNITS_2] = units_2,
 	};
-	const unsigned int divisor[] = {
+	static const unsigned int divisor[] = {
 		[STRING_UNITS_10] = 1000,
 		[STRING_UNITS_2] = 1024,
 	};
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
new file mode 100644
index 0000000..bb2b201
--- /dev/null
+++ b/lib/strncpy_from_user.c
@@ -0,0 +1,113 @@
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+#include <asm/byteorder.h>
+#include <asm/word-at-a-time.h>
+
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#define IS_UNALIGNED(src, dst)	0
+#else
+#define IS_UNALIGNED(src, dst)	\
+	(((long) dst | (long) src) & (sizeof(long) - 1))
+#endif
+
+/*
+ * Do a strncpy, return length of string without final '\0'.
+ * 'count' is the user-supplied count (return 'count' if we
+ * hit it), 'max' is the address space maximum (and we return
+ * -EFAULT if we hit it).
+ */
+static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+{
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+	long res = 0;
+
+	/*
+	 * Truncate 'max' to the user-specified limit, so that
+	 * we only have one limit we need to check in the loop
+	 */
+	if (max > count)
+		max = count;
+
+	if (IS_UNALIGNED(src, dst))
+		goto byte_at_a_time;
+
+	while (max >= sizeof(unsigned long)) {
+		unsigned long c, data;
+
+		/* Fall back to byte-at-a-time if we get a page fault */
+		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+			break;
+		*(unsigned long *)(dst+res) = c;
+		if (has_zero(c, &data, &constants)) {
+			data = prep_zero_mask(c, data, &constants);
+			data = create_zero_mask(data);
+			return res + find_zero(data);
+		}
+		res += sizeof(unsigned long);
+		max -= sizeof(unsigned long);
+	}
+
+byte_at_a_time:
+	while (max) {
+		char c;
+
+		if (unlikely(__get_user(c,src+res)))
+			return -EFAULT;
+		dst[res] = c;
+		if (!c)
+			return res;
+		res++;
+		max--;
+	}
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, that's ok - we got as much as the user asked for.
+	 */
+	if (res >= count)
+		return res;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's an EFAULT.
+	 */
+	return -EFAULT;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	max_addr = user_addr_max();
+	src_addr = (unsigned long)src;
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		return do_strncpy_from_user(dst, src, count, max);
+	}
+	return -EFAULT;
+}
+EXPORT_SYMBOL(strncpy_from_user);
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
new file mode 100644
index 0000000..a28df52
--- /dev/null
+++ b/lib/strnlen_user.c
@@ -0,0 +1,138 @@
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+#include <asm/word-at-a-time.h>
+
+/* Set bits in the first 'n' bytes when loaded from memory */
+#ifdef __LITTLE_ENDIAN
+#  define aligned_byte_mask(n) ((1ul << 8*(n))-1)
+#else
+#  define aligned_byte_mask(n) (~0xfful << (BITS_PER_LONG - 8 - 8*(n)))
+#endif
+
+/*
+ * Do a strnlen, return length of string *with* final '\0'.
+ * 'count' is the user-supplied count, while 'max' is the
+ * address space maximum.
+ *
+ * Return 0 for exceptions (which includes hitting the address
+ * space maximum), or 'count+1' if hitting the user-supplied
+ * maximum count.
+ *
+ * NOTE! We can sometimes overshoot the user-supplied maximum
+ * if it fits in a aligned 'long'. The caller needs to check
+ * the return value against "> max".
+ */
+static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
+{
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+	long align, res = 0;
+	unsigned long c;
+
+	/*
+	 * Truncate 'max' to the user-specified limit, so that
+	 * we only have one limit we need to check in the loop
+	 */
+	if (max > count)
+		max = count;
+
+	/*
+	 * Do everything aligned. But that means that we
+	 * need to also expand the maximum..
+	 */
+	align = (sizeof(long) - 1) & (unsigned long)src;
+	src -= align;
+	max += align;
+
+	if (unlikely(__get_user(c,(unsigned long __user *)src)))
+		return 0;
+	c |= aligned_byte_mask(align);
+
+	for (;;) {
+		unsigned long data;
+		if (has_zero(c, &data, &constants)) {
+			data = prep_zero_mask(c, data, &constants);
+			data = create_zero_mask(data);
+			return res + find_zero(data) + 1 - align;
+		}
+		res += sizeof(unsigned long);
+		if (unlikely(max < sizeof(unsigned long)))
+			break;
+		max -= sizeof(unsigned long);
+		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+			return 0;
+	}
+	res -= align;
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, return the marker for "too long".
+	 */
+	if (res >= count)
+		return count+1;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's 0.
+	 */
+	return 0;
+}
+
+/**
+ * strnlen_user: - Get the size of a user string INCLUDING final NUL.
+ * @str: The string to measure.
+ * @count: Maximum count (including NUL character)
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * If the string is too long, returns 'count+1'.
+ * On exception (or invalid count), returns 0.
+ */
+long strnlen_user(const char __user *str, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	max_addr = user_addr_max();
+	src_addr = (unsigned long)str;
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		return do_strnlen_user(str, count, max);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(strnlen_user);
+
+/**
+ * strlen_user: - Get the size of a user string INCLUDING final NUL.
+ * @str: The string to measure.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * On exception, returns 0.
+ *
+ * If there is a limit on the length of a valid string, you may wish to
+ * consider using strnlen_user() instead.
+ */
+long strlen_user(const char __user *str)
+{
+	unsigned long max_addr, src_addr;
+
+	max_addr = user_addr_max();
+	src_addr = (unsigned long)str;
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		return do_strnlen_user(str, ~0ul, max);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(strlen_user);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 414f46e..45bc1f8 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -130,11 +130,9 @@ void swiotlb_print_info(void)
 	pstart = virt_to_phys(io_tlb_start);
 	pend = virt_to_phys(io_tlb_end);
 
-	printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n",
-	       bytes >> 20, io_tlb_start, io_tlb_end);
-	printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
-	       (unsigned long long)pstart,
-	       (unsigned long long)pend);
+	printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+	       (unsigned long long)pstart, (unsigned long long)pend - 1,
+	       bytes >> 20, io_tlb_start, io_tlb_end - 1);
 }
 
 void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
diff --git a/lib/test-kstrtox.c b/lib/test-kstrtox.c
index d55769d..bea3f3f 100644
--- a/lib/test-kstrtox.c
+++ b/lib/test-kstrtox.c
@@ -11,7 +11,7 @@ struct test_fail {
 };
 
 #define DEFINE_TEST_FAIL(test)	\
-	const struct test_fail test[] __initdata
+	const struct test_fail test[] __initconst
 
 #define DECLARE_TEST_OK(type, test_type)	\
 	test_type {				\
@@ -21,7 +21,7 @@ struct test_fail {
 	}
 
 #define DEFINE_TEST_OK(type, test)	\
-	const type test[] __initdata
+	const type test[] __initconst
 
 #define TEST_FAIL(fn, type, fmt, test)					\
 {									\
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index abbabec..c3f36d41 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -112,106 +112,199 @@ int skip_atoi(const char **s)
 /* Decimal conversion is by far the most typical, and is used
  * for /proc and /sys data. This directly impacts e.g. top performance
  * with many processes running. We optimize it for speed
- * using code from
- * http://www.cs.uiowa.edu/~jones/bcd/decimal.html
- * (with permission from the author, Douglas W. Jones). */
+ * using ideas described at <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
+ * (with permission from the author, Douglas W. Jones).
+ */
 
-/* Formats correctly any integer in [0,99999].
- * Outputs from one to five digits depending on input.
- * On i386 gcc 4.1.2 -O2: ~250 bytes of code. */
+#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
+/* Formats correctly any integer in [0, 999999999] */
 static noinline_for_stack
-char *put_dec_trunc(char *buf, unsigned q)
+char *put_dec_full9(char *buf, unsigned q)
 {
-	unsigned d3, d2, d1, d0;
-	d1 = (q>>4) & 0xf;
-	d2 = (q>>8) & 0xf;
-	d3 = (q>>12);
-
-	d0 = 6*(d3 + d2 + d1) + (q & 0xf);
-	q = (d0 * 0xcd) >> 11;
-	d0 = d0 - 10*q;
-	*buf++ = d0 + '0'; /* least significant digit */
-	d1 = q + 9*d3 + 5*d2 + d1;
-	if (d1 != 0) {
-		q = (d1 * 0xcd) >> 11;
-		d1 = d1 - 10*q;
-		*buf++ = d1 + '0'; /* next digit */
-
-		d2 = q + 2*d2;
-		if ((d2 != 0) || (d3 != 0)) {
-			q = (d2 * 0xd) >> 7;
-			d2 = d2 - 10*q;
-			*buf++ = d2 + '0'; /* next digit */
-
-			d3 = q + 4*d3;
-			if (d3 != 0) {
-				q = (d3 * 0xcd) >> 11;
-				d3 = d3 - 10*q;
-				*buf++ = d3 + '0';  /* next digit */
-				if (q != 0)
-					*buf++ = q + '0'; /* most sign. digit */
-			}
-		}
-	}
+	unsigned r;
 
+	/*
+	 * Possible ways to approx. divide by 10
+	 * (x * 0x1999999a) >> 32 x < 1073741829 (multiply must be 64-bit)
+	 * (x * 0xcccd) >> 19     x <      81920 (x < 262149 when 64-bit mul)
+	 * (x * 0x6667) >> 18     x <      43699
+	 * (x * 0x3334) >> 17     x <      16389
+	 * (x * 0x199a) >> 16     x <      16389
+	 * (x * 0x0ccd) >> 15     x <      16389
+	 * (x * 0x0667) >> 14     x <       2739
+	 * (x * 0x0334) >> 13     x <       1029
+	 * (x * 0x019a) >> 12     x <       1029
+	 * (x * 0x00cd) >> 11     x <       1029 shorter code than * 0x67 (on i386)
+	 * (x * 0x0067) >> 10     x <        179
+	 * (x * 0x0034) >>  9     x <         69 same
+	 * (x * 0x001a) >>  8     x <         69 same
+	 * (x * 0x000d) >>  7     x <         69 same, shortest code (on i386)
+	 * (x * 0x0007) >>  6     x <         19
+	 * See <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
+	 */
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 1 */
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 2 */
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 3 */
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 4 */
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 5 */
+	/* Now value is under 10000, can avoid 64-bit multiply */
+	q      = (r * 0x199a) >> 16;
+	*buf++ = (r - 10 * q)  + '0'; /* 6 */
+	r      = (q * 0xcd) >> 11;
+	*buf++ = (q - 10 * r)  + '0'; /* 7 */
+	q      = (r * 0xcd) >> 11;
+	*buf++ = (r - 10 * q) + '0'; /* 8 */
+	*buf++ = q + '0'; /* 9 */
 	return buf;
 }
-/* Same with if's removed. Always emits five digits */
+#endif
+
+/* Similar to above but do not pad with zeros.
+ * Code can be easily arranged to print 9 digits too, but our callers
+ * always call put_dec_full9() instead when the number has 9 decimal digits.
+ */
 static noinline_for_stack
-char *put_dec_full(char *buf, unsigned q)
+char *put_dec_trunc8(char *buf, unsigned r)
 {
-	/* BTW, if q is in [0,9999], 8-bit ints will be enough, */
-	/* but anyway, gcc produces better code with full-sized ints */
-	unsigned d3, d2, d1, d0;
-	d1 = (q>>4) & 0xf;
-	d2 = (q>>8) & 0xf;
-	d3 = (q>>12);
+	unsigned q;
+
+	/* Copy of previous function's body with added early returns */
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 2 */
+	if (q == 0)
+		return buf;
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 3 */
+	if (r == 0)
+		return buf;
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 4 */
+	if (q == 0)
+		return buf;
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 5 */
+	if (r == 0)
+		return buf;
+	q      = (r * 0x199a) >> 16;
+	*buf++ = (r - 10 * q)  + '0'; /* 6 */
+	if (q == 0)
+		return buf;
+	r      = (q * 0xcd) >> 11;
+	*buf++ = (q - 10 * r)  + '0'; /* 7 */
+	if (r == 0)
+		return buf;
+	q      = (r * 0xcd) >> 11;
+	*buf++ = (r - 10 * q) + '0'; /* 8 */
+	if (q == 0)
+		return buf;
+	*buf++ = q + '0'; /* 9 */
+	return buf;
+}
 
-	/*
-	 * Possible ways to approx. divide by 10
-	 * gcc -O2 replaces multiply with shifts and adds
-	 * (x * 0xcd) >> 11: 11001101 - shorter code than * 0x67 (on i386)
-	 * (x * 0x67) >> 10:  1100111
-	 * (x * 0x34) >> 9:    110100 - same
-	 * (x * 0x1a) >> 8:     11010 - same
-	 * (x * 0x0d) >> 7:      1101 - same, shortest code (on i386)
-	 */
-	d0 = 6*(d3 + d2 + d1) + (q & 0xf);
-	q = (d0 * 0xcd) >> 11;
-	d0 = d0 - 10*q;
-	*buf++ = d0 + '0';
-	d1 = q + 9*d3 + 5*d2 + d1;
-		q = (d1 * 0xcd) >> 11;
-		d1 = d1 - 10*q;
-		*buf++ = d1 + '0';
-
-		d2 = q + 2*d2;
-			q = (d2 * 0xd) >> 7;
-			d2 = d2 - 10*q;
-			*buf++ = d2 + '0';
-
-			d3 = q + 4*d3;
-				q = (d3 * 0xcd) >> 11; /* - shorter code */
-				/* q = (d3 * 0x67) >> 10; - would also work */
-				d3 = d3 - 10*q;
-				*buf++ = d3 + '0';
-					*buf++ = q + '0';
+/* There are two algorithms to print larger numbers.
+ * One is generic: divide by 1000000000 and repeatedly print
+ * groups of (up to) 9 digits. It's conceptually simple,
+ * but requires a (unsigned long long) / 1000000000 division.
+ *
+ * Second algorithm splits 64-bit unsigned long long into 16-bit chunks,
+ * manipulates them cleverly and generates groups of 4 decimal digits.
+ * It so happens that it does NOT require long long division.
+ *
+ * If long is > 32 bits, division of 64-bit values is relatively easy,
+ * and we will use the first algorithm.
+ * If long long is > 64 bits (strange architecture with VERY large long long),
+ * second algorithm can't be used, and we again use the first one.
+ *
+ * Else (if long is 32 bits and long long is 64 bits) we use second one.
+ */
 
-	return buf;
+#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
+
+/* First algorithm: generic */
+
+static
+char *put_dec(char *buf, unsigned long long n)
+{
+	if (n >= 100*1000*1000) {
+		while (n >= 1000*1000*1000)
+			buf = put_dec_full9(buf, do_div(n, 1000*1000*1000));
+		if (n >= 100*1000*1000)
+			return put_dec_full9(buf, n);
+	}
+	return put_dec_trunc8(buf, n);
 }
-/* No inlining helps gcc to use registers better */
+
+#else
+
+/* Second algorithm: valid only for 64-bit long longs */
+
 static noinline_for_stack
-char *put_dec(char *buf, unsigned long long num)
+char *put_dec_full4(char *buf, unsigned q)
 {
-	while (1) {
-		unsigned rem;
-		if (num < 100000)
-			return put_dec_trunc(buf, num);
-		rem = do_div(num, 100000);
-		buf = put_dec_full(buf, rem);
-	}
+	unsigned r;
+	r      = (q * 0xcccd) >> 19;
+	*buf++ = (q - 10 * r) + '0';
+	q      = (r * 0x199a) >> 16;
+	*buf++ = (r - 10 * q)  + '0';
+	r      = (q * 0xcd) >> 11;
+	*buf++ = (q - 10 * r)  + '0';
+	*buf++ = r + '0';
+	return buf;
+}
+
+/* Based on code by Douglas W. Jones found at
+ * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour>
+ * (with permission from the author).
+ * Performs no 64-bit division and hence should be fast on 32-bit machines.
+ */
+static
+char *put_dec(char *buf, unsigned long long n)
+{
+	uint32_t d3, d2, d1, q, h;
+
+	if (n < 100*1000*1000)
+		return put_dec_trunc8(buf, n);
+
+	d1  = ((uint32_t)n >> 16); /* implicit "& 0xffff" */
+	h   = (n >> 32);
+	d2  = (h      ) & 0xffff;
+	d3  = (h >> 16); /* implicit "& 0xffff" */
+
+	q   = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff);
+
+	buf = put_dec_full4(buf, q % 10000);
+	q   = q / 10000;
+
+	d1  = q + 7671 * d3 + 9496 * d2 + 6 * d1;
+	buf = put_dec_full4(buf, d1 % 10000);
+	q   = d1 / 10000;
+
+	d2  = q + 4749 * d3 + 42 * d2;
+	buf = put_dec_full4(buf, d2 % 10000);
+	q   = d2 / 10000;
+
+	d3  = q + 281 * d3;
+	if (!d3)
+		goto done;
+	buf = put_dec_full4(buf, d3 % 10000);
+	q   = d3 / 10000;
+	if (!q)
+		goto done;
+	buf = put_dec_full4(buf, q);
+ done:
+	while (buf[-1] == '0')
+		--buf;
+
+	return buf;
 }
 
+#endif
+
 /*
  * Convert passed number to decimal string.
  * Returns the length of string.  On buffer overflow, returns 0.
@@ -220,16 +313,22 @@ char *put_dec(char *buf, unsigned long long num)
  */
 int num_to_str(char *buf, int size, unsigned long long num)
 {
-	char tmp[21];		/* Enough for 2^64 in decimal */
+	char tmp[sizeof(num) * 3];
 	int idx, len;
 
-	len = put_dec(tmp, num) - tmp;
+	/* put_dec() may work incorrectly for num = 0 (generate "", not "0") */
+	if (num <= 9) {
+		tmp[0] = '0' + num;
+		len = 1;
+	} else {
+		len = put_dec(tmp, num) - tmp;
+	}
 
 	if (len > size)
 		return 0;
 	for (idx = 0; idx < len; ++idx)
 		buf[idx] = tmp[len - idx - 1];
-	return  len;
+	return len;
 }
 
 #define ZEROPAD	1		/* pad with zero */
@@ -284,6 +383,7 @@ char *number(char *buf, char *end, unsigned long long num,
 	char locase;
 	int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10);
 	int i;
+	bool is_zero = num == 0LL;
 
 	/* locase = 0 or 0x20. ORing digits or letters with 'locase'
 	 * produces same digits or (maybe lowercased) letters */
@@ -305,15 +405,16 @@ char *number(char *buf, char *end, unsigned long long num,
 		}
 	}
 	if (need_pfx) {
-		spec.field_width--;
 		if (spec.base == 16)
+			spec.field_width -= 2;
+		else if (!is_zero)
 			spec.field_width--;
 	}
 
 	/* generate full string in tmp[], in reverse order */
 	i = 0;
-	if (num == 0)
-		tmp[i++] = '0';
+	if (num < spec.base)
+		tmp[i++] = digits[num] | locase;
 	/* Generic code, for any base:
 	else do {
 		tmp[i++] = (digits[do_div(num,base)] | locase);
@@ -353,9 +454,11 @@ char *number(char *buf, char *end, unsigned long long num,
 	}
 	/* "0x" / "0" prefix */
 	if (need_pfx) {
-		if (buf < end)
-			*buf = '0';
-		++buf;
+		if (spec.base == 16 || !is_zero) {
+			if (buf < end)
+				*buf = '0';
+			++buf;
+		}
 		if (spec.base == 16) {
 			if (buf < end)
 				*buf = ('X' | locase);
@@ -436,7 +539,7 @@ char *symbol_string(char *buf, char *end, void *ptr,
 	else if (ext != 'f' && ext != 's')
 		sprint_symbol(sym, value);
 	else
-		kallsyms_lookup(value, NULL, NULL, NULL, sym);
+		sprint_symbol_no_offset(sym, value);
 
 	return string(buf, end, sym, spec);
 #else
@@ -607,7 +710,7 @@ char *ip4_string(char *p, const u8 *addr, const char *fmt)
 	}
 	for (i = 0; i < 4; i++) {
 		char temp[3];	/* hold each IP quad in reverse order */
-		int digits = put_dec_trunc(temp, addr[index]) - temp;
+		int digits = put_dec_trunc8(temp, addr[index]) - temp;
 		if (leading_zeros) {
 			if (digits < 3)
 				*p++ = '0';
@@ -866,13 +969,15 @@ static noinline_for_stack
 char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	      struct printf_spec spec)
 {
+	int default_width = 2 * sizeof(void *) + (spec.flags & SPECIAL ? 2 : 0);
+
 	if (!ptr && *fmt != 'K') {
 		/*
 		 * Print (null) with the same width as a pointer so it makes
 		 * tabular output look nice.
 		 */
 		if (spec.field_width == -1)
-			spec.field_width = 2 * sizeof(void *);
+			spec.field_width = default_width;
 		return string(buf, end, "(null)", spec);
 	}
 
@@ -927,7 +1032,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		 */
 		if (in_irq() || in_serving_softirq() || in_nmi()) {
 			if (spec.field_width == -1)
-				spec.field_width = 2 * sizeof(void *);
+				spec.field_width = default_width;
 			return string(buf, end, "pK-error", spec);
 		}
 		if (!((kptr_restrict == 0) ||
@@ -944,7 +1049,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
-		spec.field_width = 2 * sizeof(void *);
+		spec.field_width = default_width;
 		spec.flags |= ZEROPAD;
 	}
 	spec.base = 16;