Linux-libre 4.3.2-gnu

35 files changed, 2159 insertions, 266 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 3a2ef67db..f0df31810 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -53,9 +53,6 @@ config GENERIC_IO
 config STMP_DEVICE
 	bool
 
-config PERCPU_RWSEM
-	bool
-
 config ARCH_USE_CMPXCHG_LOCKREF
 	bool
 
@@ -223,6 +220,7 @@ config ZLIB_INFLATE
 
 config ZLIB_DEFLATE
 	tristate
+	select BITREVERSE
 
 config LZO_COMPRESS
 	tristate
@@ -460,16 +458,6 @@ config ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 config LRU_CACHE
 	tristate
 
-config AVERAGE
-	bool "Averaging functions"
-	help
-	  This option is provided for the case where no in-kernel-tree
-	  modules require averaging functions, but a module built outside
-	  the kernel tree does. Such modules that use library averaging
-	  functions require Y here.
-
-	  If unsure, say N.
-
 config CLZ_TAB
 	bool
 
@@ -521,6 +509,13 @@ config UCS2_STRING
 
 source "lib/fonts/Kconfig"
 
+config SG_SPLIT
+	def_bool n
+	help
+	 Provides a heler to split scatterlists into chunks, each chunk being a
+	 scatterlist. This should be selected by a driver or an API which
+	 whishes to split a scatterlist amongst multiple DMA channel.
+
 #
 # sg chaining option
 #
@@ -531,4 +526,7 @@ config ARCH_HAS_SG_CHAIN
 config ARCH_HAS_PMEM_API
 	bool
 
+config ARCH_HAS_MMIO_FLUSH
+	bool
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e2894b23e..1346c0d8e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -197,6 +197,7 @@ config ENABLE_MUST_CHECK
 config FRAME_WARN
 	int "Warn for stack frames larger than (needs gcc 4.4)"
 	range 0 8192
+	default 0 if KASAN
 	default 1024 if !64BIT
 	default 2048 if 64BIT
 	help
@@ -916,12 +917,6 @@ config DEBUG_RT_MUTEXES
 	 This allows rt mutex semantics violations and rt mutex related
 	 deadlocks (lockups) to be detected and reported automatically.
 
-config RT_MUTEX_TESTER
-	bool "Built-in scriptable tester for rt-mutexes"
-	depends on DEBUG_KERNEL && RT_MUTEXES && BROKEN
-	help
-	  This option enables a rt-mutex tester.
-
 config DEBUG_SPINLOCK
 	bool "Spinlock and rw-lock debugging: basic checks"
 	depends on DEBUG_KERNEL
@@ -1235,7 +1230,7 @@ config TORTURE_TEST
 
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
-	depends on DEBUG_KERNEL
+	depends on DEBUG_KERNEL && !SCHED_BFS
 	select TORTURE_TEST
 	select SRCU
 	select TASKS_RCU
@@ -1353,20 +1348,6 @@ config RCU_CPU_STALL_TIMEOUT
 	  RCU grace period persists, additional CPU stall warnings are
 	  printed at more widely spaced intervals.
 
-config RCU_CPU_STALL_INFO
-	bool "Print additional diagnostics on RCU CPU stall"
-	depends on (TREE_RCU || PREEMPT_RCU) && DEBUG_KERNEL
-	default y
-	help
-	  For each stalled CPU that is aware of the current RCU grace
-	  period, print out additional per-CPU diagnostic information
-	  regarding scheduling-clock ticks, idle state, and,
-	  for RCU_FAST_NO_HZ kernels, idle-entry state.
-
-	  Say N if you are unsure.
-
-	  Say Y if you want to enable such diagnostics.
-
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
@@ -1379,7 +1360,7 @@ config RCU_TRACE
 	  Say N if you are unsure.
 
 config RCU_EQS_DEBUG
-	bool "Use this when adding any sort of NO_HZ support to your arch"
+	bool "Provide debugging asserts for adding NO_HZ support to an arch"
 	depends on DEBUG_KERNEL
 	help
 	  This option provides consistency checks in RCU's handling of
@@ -1542,6 +1523,13 @@ config FAIL_MMC_REQUEST
 	  and to test how the mmc host driver handles retries from
 	  the block device.
 
+config FAIL_FUTEX
+	bool "Fault-injection capability for futexes"
+	select DEBUG_FS
+	depends on FAULT_INJECTION && FUTEX
+	help
+	  Provide fault-injection capability for futexes.
+
 config FAULT_INJECTION_DEBUG_FS
 	bool "Debugfs entries for fault-injection capabilities"
 	depends on FAULT_INJECTION && SYSFS && DEBUG_FS
@@ -1840,6 +1828,15 @@ config MEMTEST
 	        memtest=17, mean do 17 test patterns.
 	  If you are unsure how to answer this question, answer N.
 
+config TEST_STATIC_KEYS
+	tristate "Test static keys"
+	default n
+	depends on m
+	help
+	  Test the static key interfaces.
+
+	  If unsure, say N.
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
diff --git a/lib/Makefile b/lib/Makefile
index 89cb00bec..796466d3b 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 sha1.o md5.o irq_regs.o argv_split.o \
 	 proportions.o flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
-	 earlycpio.o seq_buf.o
+	 earlycpio.o seq_buf.o nmi_backtrace.o
 
 obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
 lib-$(CONFIG_MMU) += ioremap.o
@@ -39,6 +39,8 @@ obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_LKM) += test_module.o
 obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o
 obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o
+obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o
+obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -138,8 +140,6 @@ obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
 
 obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o
 
-obj-$(CONFIG_AVERAGE) += average.o
-
 obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
 obj-$(CONFIG_CORDIC) += cordic.o
@@ -160,6 +160,7 @@ obj-$(CONFIG_GENERIC_STRNLEN_USER) += strnlen_user.o
 
 obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
 
+obj-$(CONFIG_SG_SPLIT) += sg_split.o
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
 
 libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 1a000bb05..2b3f46c04 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -24,15 +24,20 @@ static const unsigned char asn1_op_lengths[ASN1_OP__NR] = {
 	[ASN1_OP_MATCH_JUMP]			= 1 + 1 + 1,
 	[ASN1_OP_MATCH_JUMP_OR_SKIP]		= 1 + 1 + 1,
 	[ASN1_OP_MATCH_ANY]			= 1,
+	[ASN1_OP_MATCH_ANY_OR_SKIP]		= 1,
 	[ASN1_OP_MATCH_ANY_ACT]			= 1         + 1,
+	[ASN1_OP_MATCH_ANY_ACT_OR_SKIP]		= 1         + 1,
 	[ASN1_OP_COND_MATCH_OR_SKIP]		= 1 + 1,
 	[ASN1_OP_COND_MATCH_ACT_OR_SKIP]	= 1 + 1     + 1,
 	[ASN1_OP_COND_MATCH_JUMP_OR_SKIP]	= 1 + 1 + 1,
 	[ASN1_OP_COND_MATCH_ANY]		= 1,
+	[ASN1_OP_COND_MATCH_ANY_OR_SKIP]	= 1,
 	[ASN1_OP_COND_MATCH_ANY_ACT]		= 1         + 1,
+	[ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP]	= 1         + 1,
 	[ASN1_OP_COND_FAIL]			= 1,
 	[ASN1_OP_COMPLETE]			= 1,
 	[ASN1_OP_ACT]				= 1         + 1,
+	[ASN1_OP_MAYBE_ACT]			= 1         + 1,
 	[ASN1_OP_RETURN]			= 1,
 	[ASN1_OP_END_SEQ]			= 1,
 	[ASN1_OP_END_SEQ_OF]			= 1     + 1,
@@ -177,6 +182,7 @@ int asn1_ber_decoder(const struct asn1_decoder *decoder,
 	unsigned char flags = 0;
 #define FLAG_INDEFINITE_LENGTH	0x01
 #define FLAG_MATCHED		0x02
+#define FLAG_LAST_MATCHED	0x04 /* Last tag matched */
 #define FLAG_CONS		0x20 /* Corresponds to CONS bit in the opcode tag
 				      * - ie. whether or not we are going to parse
 				      *   a compound type.
@@ -208,9 +214,9 @@ next_op:
 		unsigned char tmp;
 
 		/* Skip conditional matches if possible */
-		if ((op & ASN1_OP_MATCH__COND &&
-		     flags & FLAG_MATCHED) ||
-		    dp == datalen) {
+		if ((op & ASN1_OP_MATCH__COND && flags & FLAG_MATCHED) ||
+		    (op & ASN1_OP_MATCH__SKIP && dp == datalen)) {
+			flags &= ~FLAG_LAST_MATCHED;
 			pc += asn1_op_lengths[op];
 			goto next_op;
 		}
@@ -302,7 +308,9 @@ next_op:
 	/* Decide how to handle the operation */
 	switch (op) {
 	case ASN1_OP_MATCH_ANY_ACT:
+	case ASN1_OP_MATCH_ANY_ACT_OR_SKIP:
 	case ASN1_OP_COND_MATCH_ANY_ACT:
+	case ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP:
 		ret = actions[machine[pc + 1]](context, hdr, tag, data + dp, len);
 		if (ret < 0)
 			return ret;
@@ -319,8 +327,10 @@ next_op:
 	case ASN1_OP_MATCH:
 	case ASN1_OP_MATCH_OR_SKIP:
 	case ASN1_OP_MATCH_ANY:
+	case ASN1_OP_MATCH_ANY_OR_SKIP:
 	case ASN1_OP_COND_MATCH_OR_SKIP:
 	case ASN1_OP_COND_MATCH_ANY:
+	case ASN1_OP_COND_MATCH_ANY_OR_SKIP:
 	skip_data:
 		if (!(flags & FLAG_CONS)) {
 			if (flags & FLAG_INDEFINITE_LENGTH) {
@@ -422,8 +432,15 @@ next_op:
 		pc += asn1_op_lengths[op];
 		goto next_op;
 
+	case ASN1_OP_MAYBE_ACT:
+		if (!(flags & FLAG_LAST_MATCHED)) {
+			pc += asn1_op_lengths[op];
+			goto next_op;
+		}
 	case ASN1_OP_ACT:
 		ret = actions[machine[pc + 1]](context, hdr, tag, data + tdp, len);
+		if (ret < 0)
+			return ret;
 		pc += asn1_op_lengths[op];
 		goto next_op;
 
@@ -431,6 +448,7 @@ next_op:
 		if (unlikely(jsp <= 0))
 			goto jump_stack_underflow;
 		pc = jump_stack[--jsp];
+		flags |= FLAG_MATCHED | FLAG_LAST_MATCHED;
 		goto next_op;
 
 	default:
@@ -438,7 +456,8 @@ next_op:
 	}
 
 	/* Shouldn't reach here */
-	pr_err("ASN.1 decoder error: Found reserved opcode (%u)\n", op);
+	pr_err("ASN.1 decoder error: Found reserved opcode (%u) pc=%zu\n",
+	       op, pc);
 	return -EBADMSG;
 
 data_overrun_error:
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 1298c05ef..2886ebac6 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -102,6 +102,9 @@ EXPORT_SYMBOL(atomic64_##op##_return);
 
 ATOMIC64_OPS(add, +=)
 ATOMIC64_OPS(sub, -=)
+ATOMIC64_OP(and, &=)
+ATOMIC64_OP(or, |=)
+ATOMIC64_OP(xor, ^=)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 0211d30d8..83c33a5bc 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -16,8 +16,39 @@
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 
+#define TEST(bit, op, c_op, val)				\
+do {								\
+	atomic##bit##_set(&v, v0);				\
+	r = v0;							\
+	atomic##bit##_##op(val, &v);				\
+	r c_op val;						\
+	WARN(atomic##bit##_read(&v) != r, "%Lx != %Lx\n",	\
+		(unsigned long long)atomic##bit##_read(&v),	\
+		(unsigned long long)r);				\
+} while (0)
+
+static __init void test_atomic(void)
+{
+	int v0 = 0xaaa31337;
+	int v1 = 0xdeadbeef;
+	int onestwos = 0x11112222;
+	int one = 1;
+
+	atomic_t v;
+	int r;
+
+	TEST(, add, +=, onestwos);
+	TEST(, add, +=, -one);
+	TEST(, sub, -=, onestwos);
+	TEST(, sub, -=, -one);
+	TEST(, or, |=, v1);
+	TEST(, and, &=, v1);
+	TEST(, xor, ^=, v1);
+	TEST(, andnot, &= ~, v1);
+}
+
 #define INIT(c) do { atomic64_set(&v, c); r = c; } while (0)
-static __init int test_atomic64(void)
+static __init void test_atomic64(void)
 {
 	long long v0 = 0xaaa31337c001d00dLL;
 	long long v1 = 0xdeadbeefdeafcafeLL;
@@ -34,15 +65,14 @@ static __init int test_atomic64(void)
 	BUG_ON(v.counter != r);
 	BUG_ON(atomic64_read(&v) != r);
 
-	INIT(v0);
-	atomic64_add(onestwos, &v);
-	r += onestwos;
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	atomic64_add(-one, &v);
-	r += -one;
-	BUG_ON(v.counter != r);
+	TEST(64, add, +=, onestwos);
+	TEST(64, add, +=, -one);
+	TEST(64, sub, -=, onestwos);
+	TEST(64, sub, -=, -one);
+	TEST(64, or, |=, v1);
+	TEST(64, and, &=, v1);
+	TEST(64, xor, ^=, v1);
+	TEST(64, andnot, &= ~, v1);
 
 	INIT(v0);
 	r += onestwos;
@@ -55,16 +85,6 @@ static __init int test_atomic64(void)
 	BUG_ON(v.counter != r);
 
 	INIT(v0);
-	atomic64_sub(onestwos, &v);
-	r -= onestwos;
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	atomic64_sub(-one, &v);
-	r -= -one;
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
 	r -= onestwos;
 	BUG_ON(atomic64_sub_return(onestwos, &v) != r);
 	BUG_ON(v.counter != r);
@@ -147,6 +167,12 @@ static __init int test_atomic64(void)
 	BUG_ON(!atomic64_inc_not_zero(&v));
 	r += one;
 	BUG_ON(v.counter != r);
+}
+
+static __init int test_atomics(void)
+{
+	test_atomic();
+	test_atomic64();
 
 #ifdef CONFIG_X86
 	pr_info("passed for %s platform %s CX8 and %s SSE\n",
@@ -166,4 +192,4 @@ static __init int test_atomic64(void)
 	return 0;
 }
 
-core_initcall(test_atomic64);
+core_initcall(test_atomics);
diff --git a/lib/average.c b/lib/average.c
deleted file mode 100644
index 114d1beae..000000000
--- a/lib/average.c
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * lib/average.c
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
- */
-
-#include <linux/export.h>
-#include <linux/average.h>
-#include <linux/kernel.h>
-#include <linux/bug.h>
-#include <linux/log2.h>
-
-/**
- * DOC: Exponentially Weighted Moving Average (EWMA)
- *
- * These are generic functions for calculating Exponentially Weighted Moving
- * Averages (EWMA). We keep a structure with the EWMA parameters and a scaled
- * up internal representation of the average value to prevent rounding errors.
- * The factor for scaling up and the exponential weight (or decay rate) have to
- * be specified thru the init fuction. The structure should not be accessed
- * directly but only thru the helper functions.
- */
-
-/**
- * ewma_init() - Initialize EWMA parameters
- * @avg: Average structure
- * @factor: Factor to use for the scaled up internal value. The maximum value
- *	of averages can be ULONG_MAX/(factor*weight). For performance reasons
- *	factor has to be a power of 2.
- * @weight: Exponential weight, or decay rate. This defines how fast the
- *	influence of older values decreases. For performance reasons weight has
- *	to be a power of 2.
- *
- * Initialize the EWMA parameters for a given struct ewma @avg.
- */
-void ewma_init(struct ewma *avg, unsigned long factor, unsigned long weight)
-{
-	WARN_ON(!is_power_of_2(weight) || !is_power_of_2(factor));
-
-	avg->weight = ilog2(weight);
-	avg->factor = ilog2(factor);
-	avg->internal = 0;
-}
-EXPORT_SYMBOL(ewma_init);
-
-/**
- * ewma_add() - Exponentially weighted moving average (EWMA)
- * @avg: Average structure
- * @val: Current value
- *
- * Add a sample to the average.
- */
-struct ewma *ewma_add(struct ewma *avg, unsigned long val)
-{
-	unsigned long internal = ACCESS_ONCE(avg->internal);
-
-	ACCESS_ONCE(avg->internal) = internal ?
-		(((internal << avg->weight) - internal) +
-			(val << avg->factor)) >> avg->weight :
-		(val << avg->factor);
-	return avg;
-}
-EXPORT_SYMBOL(ewma_add);
diff --git a/lib/bitmap.c b/lib/bitmap.c
index a578a0189..814814397 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -367,7 +367,8 @@ int __bitmap_parse(const char *buf, unsigned int buflen,
 
 	nchunks = nbits = totaldigits = c = 0;
 	do {
-		chunk = ndigits = 0;
+		chunk = 0;
+		ndigits = totaldigits;
 
 		/* Get the next chunk of the bitmap */
 		while (buflen) {
@@ -406,9 +407,9 @@ int __bitmap_parse(const char *buf, unsigned int buflen,
 				return -EOVERFLOW;
 
 			chunk = (chunk << 4) | hex_to_bin(c);
-			ndigits++; totaldigits++;
+			totaldigits++;
 		}
-		if (ndigits == 0)
+		if (ndigits == totaldigits)
 			return -EINVAL;
 		if (nchunks == 0 && chunk == 0)
 			continue;
@@ -505,7 +506,7 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 		int nmaskbits)
 {
 	unsigned a, b;
-	int c, old_c, totaldigits;
+	int c, old_c, totaldigits, ndigits;
 	const char __user __force *ubuf = (const char __user __force *)buf;
 	int at_start, in_range;
 
@@ -515,6 +516,7 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 		at_start = 1;
 		in_range = 0;
 		a = b = 0;
+		ndigits = totaldigits;
 
 		/* Get the next cpu# or a range of cpu#'s */
 		while (buflen) {
@@ -528,23 +530,27 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 			if (isspace(c))
 				continue;
 
-			/*
-			 * If the last character was a space and the current
-			 * character isn't '\0', we've got embedded whitespace.
-			 * This is a no-no, so throw an error.
-			 */
-			if (totaldigits && c && isspace(old_c))
-				return -EINVAL;
-
 			/* A '\0' or a ',' signal the end of a cpu# or range */
 			if (c == '\0' || c == ',')
 				break;
+			/*
+			* whitespaces between digits are not allowed,
+			* but it's ok if whitespaces are on head or tail.
+			* when old_c is whilespace,
+			* if totaldigits == ndigits, whitespace is on head.
+			* if whitespace is on tail, it should not run here.
+			* as c was ',' or '\0',
+			* the last code line has broken the current loop.
+			*/
+			if ((totaldigits != ndigits) && isspace(old_c))
+				return -EINVAL;
 
 			if (c == '-') {
 				if (at_start || in_range)
 					return -EINVAL;
 				b = 0;
 				in_range = 1;
+				at_start = 1;
 				continue;
 			}
 
@@ -557,15 +563,18 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 			at_start = 0;
 			totaldigits++;
 		}
+		if (ndigits == totaldigits)
+			continue;
+		/* if no digit is after '-', it's wrong*/
+		if (at_start && in_range)
+			return -EINVAL;
 		if (!(a <= b))
 			return -EINVAL;
 		if (b >= nmaskbits)
 			return -ERANGE;
-		if (!at_start) {
-			while (a <= b) {
-				set_bit(a, maskp);
-				a++;
-			}
+		while (a <= b) {
+			set_bit(a, maskp);
+			a++;
 		}
 	} while (buflen && c == ',');
 	return 0;
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index decb64629..ed7a1fd81 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -620,7 +620,7 @@ STATIC inline int INIT unlzma(unsigned char *buf, long in_len,
 
 	num_probs = LZMA_BASE_SIZE + (LZMA_LIT_SIZE << (lc + lp));
 	p = (uint16_t *) large_malloc(num_probs * sizeof(*p));
-	if (p == 0)
+	if (p == NULL)
 		goto exit_2;
 	num_probs = LZMA_LITERAL + (LZMA_LIT_SIZE << (lc + lp));
 	for (i = 0; i < num_probs; i++)
diff --git a/lib/devres.c b/lib/devres.c
index fbe2aac52..f13a2468f 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -119,10 +119,9 @@ EXPORT_SYMBOL(devm_iounmap);
  * @dev: generic device to handle the resource for
  * @res: resource to be handled
  *
- * Checks that a resource is a valid memory region, requests the memory region
- * and ioremaps it either as cacheable or as non-cacheable memory depending on
- * the resource's flags. All operations are managed and will be undone on
- * driver detach.
+ * Checks that a resource is a valid memory region, requests the memory
+ * region and ioremaps it. All operations are managed and will be undone
+ * on driver detach.
  *
  * Returns a pointer to the remapped memory or an ERR_PTR() encoded error code
  * on failure. Usage example:
@@ -153,11 +152,7 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res)
 		return IOMEM_ERR_PTR(-EBUSY);
 	}
 
-	if (res->flags & IORESOURCE_CACHEABLE)
-		dest_ptr = devm_ioremap(dev, res->start, size);
-	else
-		dest_ptr = devm_ioremap_nocache(dev, res->start, size);
-
+	dest_ptr = devm_ioremap(dev, res->start, size);
 	if (!dest_ptr) {
 		dev_err(dev, "ioremap failed for resource %pR\n", res);
 		devm_release_mem_region(dev, res->start, size);
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index f1cdeb024..6a823a53e 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -44,7 +44,7 @@ static void fail_dump(struct fault_attr *attr)
 		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n"
 		       "name %pd, interval %lu, probability %lu, "
 		       "space %d, times %d\n", attr->dname,
-		       attr->probability, attr->interval,
+		       attr->interval, attr->probability,
 		       atomic_read(&attr->space),
 		       atomic_read(&attr->times));
 		if (attr->verbose > 1)
diff --git a/lib/genalloc.c b/lib/genalloc.c
index daf0afb6d..116a166b0 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -160,6 +160,7 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
 		pool->min_alloc_order = min_alloc_order;
 		pool->algo = gen_pool_first_fit;
 		pool->data = NULL;
+		pool->name = NULL;
 	}
 	return pool;
 }
@@ -252,8 +253,8 @@ void gen_pool_destroy(struct gen_pool *pool)
 
 		kfree(chunk);
 	}
+	kfree_const(pool->name);
 	kfree(pool);
-	return;
 }
 EXPORT_SYMBOL(gen_pool_destroy);
 
@@ -570,53 +571,88 @@ static void devm_gen_pool_release(struct device *dev, void *res)
 	gen_pool_destroy(*(struct gen_pool **)res);
 }
 
+static int devm_gen_pool_match(struct device *dev, void *res, void *data)
+{
+	struct gen_pool **p = res;
+
+	/* NULL data matches only a pool without an assigned name */
+	if (!data && !(*p)->name)
+		return 1;
+
+	if (!data || !(*p)->name)
+		return 0;
+
+	return !strcmp((*p)->name, data);
+}
+
+/**
+ * gen_pool_get - Obtain the gen_pool (if any) for a device
+ * @dev: device to retrieve the gen_pool from
+ * @name: name of a gen_pool or NULL, identifies a particular gen_pool on device
+ *
+ * Returns the gen_pool for the device if one is present, or NULL.
+ */
+struct gen_pool *gen_pool_get(struct device *dev, const char *name)
+{
+	struct gen_pool **p;
+
+	p = devres_find(dev, devm_gen_pool_release, devm_gen_pool_match,
+			(void *)name);
+	if (!p)
+		return NULL;
+	return *p;
+}
+EXPORT_SYMBOL_GPL(gen_pool_get);
+
 /**
  * devm_gen_pool_create - managed gen_pool_create
  * @dev: device that provides the gen_pool
  * @min_alloc_order: log base 2 of number of bytes each bitmap bit represents
- * @nid: node id of the node the pool structure should be allocated on, or -1
+ * @nid: node selector for allocated gen_pool, %NUMA_NO_NODE for all nodes
+ * @name: name of a gen_pool or NULL, identifies a particular gen_pool on device
  *
  * Create a new special memory pool that can be used to manage special purpose
  * memory not managed by the regular kmalloc/kfree interface. The pool will be
  * automatically destroyed by the device management code.
  */
 struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order,
-		int nid)
+				      int nid, const char *name)
 {
 	struct gen_pool **ptr, *pool;
+	const char *pool_name = NULL;
+
+	/* Check that genpool to be created is uniquely addressed on device */
+	if (gen_pool_get(dev, name))
+		return ERR_PTR(-EINVAL);
+
+	if (name) {
+		pool_name = kstrdup_const(name, GFP_KERNEL);
+		if (!pool_name)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	ptr = devres_alloc(devm_gen_pool_release, sizeof(*ptr), GFP_KERNEL);
 	if (!ptr)
-		return NULL;
+		goto free_pool_name;
 
 	pool = gen_pool_create(min_alloc_order, nid);
-	if (pool) {
-		*ptr = pool;
-		devres_add(dev, ptr);
-	} else {
-		devres_free(ptr);
-	}
+	if (!pool)
+		goto free_devres;
+
+	*ptr = pool;
+	pool->name = pool_name;
+	devres_add(dev, ptr);
 
 	return pool;
-}
-EXPORT_SYMBOL(devm_gen_pool_create);
 
-/**
- * gen_pool_get - Obtain the gen_pool (if any) for a device
- * @dev: device to retrieve the gen_pool from
- *
- * Returns the gen_pool for the device if one is present, or NULL.
- */
-struct gen_pool *gen_pool_get(struct device *dev)
-{
-	struct gen_pool **p = devres_find(dev, devm_gen_pool_release, NULL,
-					NULL);
+free_devres:
+	devres_free(ptr);
+free_pool_name:
+	kfree_const(pool_name);
 
-	if (!p)
-		return NULL;
-	return *p;
+	return ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL_GPL(gen_pool_get);
+EXPORT_SYMBOL(devm_gen_pool_create);
 
 #ifdef CONFIG_OF
 /**
@@ -633,16 +669,30 @@ struct gen_pool *of_gen_pool_get(struct device_node *np,
 	const char *propname, int index)
 {
 	struct platform_device *pdev;
-	struct device_node *np_pool;
+	struct device_node *np_pool, *parent;
+	const char *name = NULL;
+	struct gen_pool *pool = NULL;
 
 	np_pool = of_parse_phandle(np, propname, index);
 	if (!np_pool)
 		return NULL;
+
 	pdev = of_find_device_by_node(np_pool);
+	if (!pdev) {
+		/* Check if named gen_pool is created by parent node device */
+		parent = of_get_parent(np_pool);
+		pdev = of_find_device_by_node(parent);
+		of_node_put(parent);
+
+		of_property_read_string(np_pool, "label", &name);
+		if (!name)
+			name = np_pool->name;
+	}
+	if (pdev)
+		pool = gen_pool_get(&pdev->dev, name);
 	of_node_put(np_pool);
-	if (!pdev)
-		return NULL;
-	return gen_pool_get(&pdev->dev);
+
+	return pool;
 }
 EXPORT_SYMBOL_GPL(of_gen_pool_get);
 #endif /* CONFIG_OF */
diff --git a/lib/klist.c b/lib/klist.c
index 89b485a2a..d74cf7a29 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -324,6 +324,47 @@ static struct klist_node *to_klist_node(struct list_head *n)
 }
 
 /**
+ * klist_prev - Ante up prev node in list.
+ * @i: Iterator structure.
+ *
+ * First grab list lock. Decrement the reference count of the previous
+ * node, if there was one. Grab the prev node, increment its reference
+ * count, drop the lock, and return that prev node.
+ */
+struct klist_node *klist_prev(struct klist_iter *i)
+{
+	void (*put)(struct klist_node *) = i->i_klist->put;
+	struct klist_node *last = i->i_cur;
+	struct klist_node *prev;
+
+	spin_lock(&i->i_klist->k_lock);
+
+	if (last) {
+		prev = to_klist_node(last->n_node.prev);
+		if (!klist_dec_and_del(last))
+			put = NULL;
+	} else
+		prev = to_klist_node(i->i_klist->k_list.prev);
+
+	i->i_cur = NULL;
+	while (prev != to_klist_node(&i->i_klist->k_list)) {
+		if (likely(!knode_dead(prev))) {
+			kref_get(&prev->n_ref);
+			i->i_cur = prev;
+			break;
+		}
+		prev = to_klist_node(prev->n_node.prev);
+	}
+
+	spin_unlock(&i->i_klist->k_lock);
+
+	if (put && last)
+		put(last);
+	return i->i_cur;
+}
+EXPORT_SYMBOL_GPL(klist_prev);
+
+/**
  * klist_next - Ante up next node in list.
  * @i: Iterator structure.
  *
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index ec8da78df..94be244e8 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -152,7 +152,7 @@ int kstrtoll(const char *s, unsigned int base, long long *res)
 		rv = _kstrtoull(s + 1, base, &tmp);
 		if (rv < 0)
 			return rv;
-		if ((long long)(-tmp) >= 0)
+		if ((long long)-tmp > 0)
 			return -ERANGE;
 		*res = -tmp;
 	} else {
diff --git a/lib/lockref.c b/lib/lockref.c
index 494994bf1..5a92189ad 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -4,14 +4,6 @@
 #if USE_CMPXCHG_LOCKREF
 
 /*
- * Allow weakly-ordered memory architectures to provide barrier-less
- * cmpxchg semantics for lockref updates.
- */
-#ifndef cmpxchg64_relaxed
-# define cmpxchg64_relaxed cmpxchg64
-#endif
-
-/*
  * Note that the "cmpxchg()" reloads the "old" value for the
  * failure case.
  */
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index bc0a1da8a..95c52a952 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -146,18 +146,25 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 	uint8_t *p;
 	mpi_limb_t alimb;
 	unsigned int n = mpi_get_size(a);
-	int i;
+	int i, lzeros = 0;
 
-	if (buf_len < n || !buf)
+	if (buf_len < n || !buf || !nbytes)
 		return -EINVAL;
 
 	if (sign)
 		*sign = a->sign;
 
-	if (nbytes)
-		*nbytes = n;
+	p = (void *)&a->d[a->nlimbs] - 1;
+
+	for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) {
+		if (!*p)
+			lzeros++;
+		else
+			break;
+	}
 
 	p = buf;
+	*nbytes = n - lzeros;
 
 	for (i = a->nlimbs - 1; i >= 0; i--) {
 		alimb = a->d[i];
@@ -178,6 +185,19 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 #else
 #error please implement for this limb size.
 #endif
+
+		if (lzeros > 0) {
+			if (lzeros >= sizeof(alimb)) {
+				p -= sizeof(alimb);
+			} else {
+				mpi_limb_t *limb1 = (void *)p - sizeof(alimb);
+				mpi_limb_t *limb2 = (void *)p - sizeof(alimb)
+							+ lzeros;
+				*limb1 = *limb2;
+				p -= lzeros;
+			}
+			lzeros -= sizeof(alimb);
+		}
 	}
 	return 0;
 }
@@ -197,7 +217,7 @@ EXPORT_SYMBOL_GPL(mpi_read_buffer);
  */
 void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 {
-	uint8_t *buf, *p;
+	uint8_t *buf;
 	unsigned int n;
 	int ret;
 
@@ -220,14 +240,6 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 		kfree(buf);
 		return NULL;
 	}
-
-	/* this is sub-optimal but we need to do the shift operation
-	 * because the caller has to free the returned buffer */
-	for (p = buf; !*p && *nbytes; p++, --*nbytes)
-		;
-	if (p != buf)
-		memmove(buf, p, *nbytes);
-
 	return buf;
 }
 EXPORT_SYMBOL_GPL(mpi_get_buffer);
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
new file mode 100644
index 000000000..88d3d32e5
--- /dev/null
+++ b/lib/nmi_backtrace.c
@@ -0,0 +1,162 @@
+/*
+ *  NMI backtrace support
+ *
+ * Gratuitously copied from arch/x86/kernel/apic/hw_nmi.c by Russell King,
+ * with the following header:
+ *
+ *  HW NMI watchdog support
+ *
+ *  started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ *  Arch specific calls to support NMI watchdog
+ *
+ *  Bits copied from original nmi.c file
+ */
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+#include <linux/kprobes.h>
+#include <linux/nmi.h>
+#include <linux/seq_buf.h>
+
+#ifdef arch_trigger_all_cpu_backtrace
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+static cpumask_t printtrace_mask;
+
+#define NMI_BUF_SIZE		4096
+
+struct nmi_seq_buf {
+	unsigned char		buffer[NMI_BUF_SIZE];
+	struct seq_buf		seq;
+};
+
+/* Safe printing in NMI context */
+static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
+
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
+static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
+{
+	const char *buf = s->buffer + start;
+
+	printk("%.*s", (end - start) + 1, buf);
+}
+
+void nmi_trigger_all_cpu_backtrace(bool include_self,
+				   void (*raise)(cpumask_t *mask))
+{
+	struct nmi_seq_buf *s;
+	int i, cpu, this_cpu = get_cpu();
+
+	if (test_and_set_bit(0, &backtrace_flag)) {
+		/*
+		 * If there is already a trigger_all_cpu_backtrace() in progress
+		 * (backtrace_flag == 1), don't output double cpu dump infos.
+		 */
+		put_cpu();
+		return;
+	}
+
+	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+	if (!include_self)
+		cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
+
+	cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask));
+
+	/*
+	 * Set up per_cpu seq_buf buffers that the NMIs running on the other
+	 * CPUs will write to.
+	 */
+	for_each_cpu(cpu, to_cpumask(backtrace_mask)) {
+		s = &per_cpu(nmi_print_seq, cpu);
+		seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE);
+	}
+
+	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
+		pr_info("Sending NMI to %s CPUs:\n",
+			(include_self ? "all" : "other"));
+		raise(to_cpumask(backtrace_mask));
+	}
+
+	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
+	for (i = 0; i < 10 * 1000; i++) {
+		if (cpumask_empty(to_cpumask(backtrace_mask)))
+			break;
+		mdelay(1);
+		touch_softlockup_watchdog();
+	}
+
+	/*
+	 * Now that all the NMIs have triggered, we can dump out their
+	 * back traces safely to the console.
+	 */
+	for_each_cpu(cpu, &printtrace_mask) {
+		int len, last_i = 0;
+
+		s = &per_cpu(nmi_print_seq, cpu);
+		len = seq_buf_used(&s->seq);
+		if (!len)
+			continue;
+
+		/* Print line by line. */
+		for (i = 0; i < len; i++) {
+			if (s->buffer[i] == '\n') {
+				print_seq_line(s, last_i, i);
+				last_i = i + 1;
+			}
+		}
+		/* Check if there was a partial line. */
+		if (last_i < len) {
+			print_seq_line(s, last_i, len - 1);
+			pr_cont("\n");
+		}
+	}
+
+	clear_bit(0, &backtrace_flag);
+	smp_mb__after_atomic();
+	put_cpu();
+}
+
+/*
+ * It is not safe to call printk() directly from NMI handlers.
+ * It may be fine if the NMI detected a lock up and we have no choice
+ * but to do so, but doing a NMI on all other CPUs to get a back trace
+ * can be done with a sysrq-l. We don't want that to lock up, which
+ * can happen if the NMI interrupts a printk in progress.
+ *
+ * Instead, we redirect the vprintk() to this nmi_vprintk() that writes
+ * the content into a per cpu seq_buf buffer. Then when the NMIs are
+ * all done, we can safely dump the contents of the seq_buf to a printk()
+ * from a non NMI context.
+ */
+static int nmi_vprintk(const char *fmt, va_list args)
+{
+	struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
+	unsigned int len = seq_buf_used(&s->seq);
+
+	seq_buf_vprintf(&s->seq, fmt, args);
+	return seq_buf_used(&s->seq) - len;
+}
+
+bool nmi_cpu_backtrace(struct pt_regs *regs)
+{
+	int cpu = smp_processor_id();
+
+	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
+		printk_func_t printk_func_save = this_cpu_read(printk_func);
+
+		/* Replace printk to write into the NMI seq */
+		this_cpu_write(printk_func, nmi_vprintk);
+		pr_warn("NMI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
+		this_cpu_write(printk_func, printk_func_save);
+
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+		return true;
+	}
+
+	return false;
+}
+NOKPROBE_SYMBOL(nmi_cpu_backtrace);
+#endif
diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
index bcce5f149..c10fba461 100644
--- a/lib/pci_iomap.c
+++ b/lib/pci_iomap.c
@@ -41,17 +41,59 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
 		len = maxlen;
 	if (flags & IORESOURCE_IO)
 		return __pci_ioport_map(dev, start, len);
-	if (flags & IORESOURCE_MEM) {
-		if (flags & IORESOURCE_CACHEABLE)
-			return ioremap(start, len);
-		return ioremap_nocache(start, len);
-	}
+	if (flags & IORESOURCE_MEM)
+		return ioremap(start, len);
 	/* What? */
 	return NULL;
 }
 EXPORT_SYMBOL(pci_iomap_range);
 
 /**
+ * pci_iomap_wc_range - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @offset: map memory at the given offset in BAR
+ * @maxlen: max length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR from offset to the end, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
+				 int bar,
+				 unsigned long offset,
+				 unsigned long maxlen)
+{
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
+	unsigned long flags = pci_resource_flags(dev, bar);
+
+
+	if (flags & IORESOURCE_IO)
+		return NULL;
+
+	if (len <= offset || !start)
+		return NULL;
+
+	len -= offset;
+	start += offset;
+	if (maxlen && len > maxlen)
+		len = maxlen;
+
+	if (flags & IORESOURCE_MEM)
+		return ioremap_wc(start, len);
+
+	/* What? */
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc_range);
+
+/**
  * pci_iomap - create a virtual mapping cookie for a PCI BAR
  * @dev: PCI device that owns the BAR
  * @bar: BAR number
@@ -70,4 +112,25 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 	return pci_iomap_range(dev, bar, 0, maxlen);
 }
 EXPORT_SYMBOL(pci_iomap);
+
+/**
+ * pci_iomap_wc - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc);
 #endif /* CONFIG_PCI */
diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c
index d9ad6ee28..7076ef1ba 100644
--- a/lib/raid6/neon.c
+++ b/lib/raid6/neon.c
@@ -40,9 +40,20 @@
 					(unsigned long)bytes, ptrs);	\
 		kernel_neon_end();					\
 	}								\
+	static void raid6_neon ## _n ## _xor_syndrome(int disks,	\
+					int start, int stop, 		\
+					size_t bytes, void **ptrs)	\
+	{								\
+		void raid6_neon ## _n  ## _xor_syndrome_real(int,	\
+				int, int, unsigned long, void**);	\
+		kernel_neon_begin();					\
+		raid6_neon ## _n ## _xor_syndrome_real(disks,		\
+			start, stop, (unsigned long)bytes, ptrs);	\
+		kernel_neon_end();					\
+	}								\
 	struct raid6_calls const raid6_neonx ## _n = {			\
 		raid6_neon ## _n ## _gen_syndrome,			\
-		NULL,		/* XOR not yet implemented */		\
+		raid6_neon ## _n ## _xor_syndrome,			\
 		raid6_have_neon,					\
 		"neonx" #_n,						\
 		0							\
diff --git a/lib/raid6/neon.uc b/lib/raid6/neon.uc
index 1b9ed7933..4fa51b761 100644
--- a/lib/raid6/neon.uc
+++ b/lib/raid6/neon.uc
@@ -3,6 +3,7 @@
  *   neon.uc - RAID-6 syndrome calculation using ARM NEON instructions
  *
  *   Copyright (C) 2012 Rob Herring
+ *   Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  *   Based on altivec.uc:
  *     Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
@@ -78,3 +79,48 @@ void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
 		vst1q_u8(&q[d+NSIZE*$$], wq$$);
 	}
 }
+
+void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
+				    unsigned long bytes, void **ptrs)
+{
+	uint8_t **dptr = (uint8_t **)ptrs;
+	uint8_t *p, *q;
+	int d, z, z0;
+
+	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
+	const unative_t x1d = NBYTES(0x1d);
+
+	z0 = stop;		/* P/Q right side optimization */
+	p = dptr[disks-2];	/* XOR parity */
+	q = dptr[disks-1];	/* RS syndrome */
+
+	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+		wq$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
+		wp$$ = veorq_u8(vld1q_u8(&p[d+$$*NSIZE]), wq$$);
+
+		/* P/Q data pages */
+		for ( z = z0-1 ; z >= start ; z-- ) {
+			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
+			wp$$ = veorq_u8(wp$$, wd$$);
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+
+			w2$$ = vandq_u8(w2$$, x1d);
+			w1$$ = veorq_u8(w1$$, w2$$);
+			wq$$ = veorq_u8(w1$$, wd$$);
+		}
+		/* P/Q left side optimization */
+		for ( z = start-1 ; z >= 0 ; z-- ) {
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+
+			w2$$ = vandq_u8(w2$$, x1d);
+			wq$$ = veorq_u8(w1$$, w2$$);
+		}
+		w1$$ = vld1q_u8(&q[d+NSIZE*$$]);
+		wq$$ = veorq_u8(wq$$, w1$$);
+
+		vst1q_u8(&p[d+NSIZE*$$], wp$$);
+		vst1q_u8(&q[d+NSIZE*$$], wq$$);
+	}
+}
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index cc0c69710..a54ff8949 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -187,10 +187,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
 	head = rht_dereference_bucket(new_tbl->buckets[new_hash],
 				      new_tbl, new_hash);
 
-	if (rht_is_a_nulls(head))
-		INIT_RHT_NULLS_HEAD(entry->next, ht, new_hash);
-	else
-		RCU_INIT_POINTER(entry->next, head);
+	RCU_INIT_POINTER(entry->next, head);
 
 	rcu_assign_pointer(new_tbl->buckets[new_hash], entry);
 	spin_unlock(new_bucket_lock);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index d105a9f56..bafa9933f 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -105,16 +105,12 @@ EXPORT_SYMBOL(sg_nents_for_len);
  **/
 struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
 {
-#ifndef CONFIG_ARCH_HAS_SG_CHAIN
-	struct scatterlist *ret = &sgl[nents - 1];
-#else
 	struct scatterlist *sg, *ret = NULL;
 	unsigned int i;
 
 	for_each_sg(sgl, sg, nents, i)
 		ret = sg;
 
-#endif
 #ifdef CONFIG_DEBUG_SG
 	BUG_ON(sgl[0].sg_magic != SG_MAGIC);
 	BUG_ON(!sg_is_last(ret));
diff --git a/lib/sg_split.c b/lib/sg_split.c
new file mode 100644
index 000000000..b063410c3
--- /dev/null
+++ b/lib/sg_split.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2015 Robert Jarzmik <robert.jarzmik@free.fr>
+ *
+ * Scatterlist splitting helpers.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+
+struct sg_splitter {
+	struct scatterlist *in_sg0;
+	int nents;
+	off_t skip_sg0;
+	unsigned int length_last_sg;
+
+	struct scatterlist *out_sg;
+};
+
+static int sg_calculate_split(struct scatterlist *in, int nents, int nb_splits,
+			      off_t skip, const size_t *sizes,
+			      struct sg_splitter *splitters, bool mapped)
+{
+	int i;
+	unsigned int sglen;
+	size_t size = sizes[0], len;
+	struct sg_splitter *curr = splitters;
+	struct scatterlist *sg;
+
+	for (i = 0; i < nb_splits; i++) {
+		splitters[i].in_sg0 = NULL;
+		splitters[i].nents = 0;
+	}
+
+	for_each_sg(in, sg, nents, i) {
+		sglen = mapped ? sg_dma_len(sg) : sg->length;
+		if (skip > sglen) {
+			skip -= sglen;
+			continue;
+		}
+
+		len = min_t(size_t, size, sglen - skip);
+		if (!curr->in_sg0) {
+			curr->in_sg0 = sg;
+			curr->skip_sg0 = skip;
+		}
+		size -= len;
+		curr->nents++;
+		curr->length_last_sg = len;
+
+		while (!size && (skip + len < sglen) && (--nb_splits > 0)) {
+			curr++;
+			size = *(++sizes);
+			skip += len;
+			len = min_t(size_t, size, sglen - skip);
+
+			curr->in_sg0 = sg;
+			curr->skip_sg0 = skip;
+			curr->nents = 1;
+			curr->length_last_sg = len;
+			size -= len;
+		}
+		skip = 0;
+
+		if (!size && --nb_splits > 0) {
+			curr++;
+			size = *(++sizes);
+		}
+
+		if (!nb_splits)
+			break;
+	}
+
+	return (size || !splitters[0].in_sg0) ? -EINVAL : 0;
+}
+
+static void sg_split_phys(struct sg_splitter *splitters, const int nb_splits)
+{
+	int i, j;
+	struct scatterlist *in_sg, *out_sg;
+	struct sg_splitter *split;
+
+	for (i = 0, split = splitters; i < nb_splits; i++, split++) {
+		in_sg = split->in_sg0;
+		out_sg = split->out_sg;
+		for (j = 0; j < split->nents; j++, out_sg++) {
+			*out_sg = *in_sg;
+			if (!j) {
+				out_sg->offset += split->skip_sg0;
+				out_sg->length -= split->skip_sg0;
+			} else {
+				out_sg->offset = 0;
+			}
+			sg_dma_address(out_sg) = 0;
+			sg_dma_len(out_sg) = 0;
+			in_sg = sg_next(in_sg);
+		}
+		out_sg[-1].length = split->length_last_sg;
+		sg_mark_end(out_sg - 1);
+	}
+}
+
+static void sg_split_mapped(struct sg_splitter *splitters, const int nb_splits)
+{
+	int i, j;
+	struct scatterlist *in_sg, *out_sg;
+	struct sg_splitter *split;
+
+	for (i = 0, split = splitters; i < nb_splits; i++, split++) {
+		in_sg = split->in_sg0;
+		out_sg = split->out_sg;
+		for (j = 0; j < split->nents; j++, out_sg++) {
+			sg_dma_address(out_sg) = sg_dma_address(in_sg);
+			sg_dma_len(out_sg) = sg_dma_len(in_sg);
+			if (!j) {
+				sg_dma_address(out_sg) += split->skip_sg0;
+				sg_dma_len(out_sg) -= split->skip_sg0;
+			}
+			in_sg = sg_next(in_sg);
+		}
+		sg_dma_len(--out_sg) = split->length_last_sg;
+	}
+}
+
+/**
+ * sg_split - split a scatterlist into several scatterlists
+ * @in: the input sg list
+ * @in_mapped_nents: the result of a dma_map_sg(in, ...), or 0 if not mapped.
+ * @skip: the number of bytes to skip in the input sg list
+ * @nb_splits: the number of desired sg outputs
+ * @split_sizes: the respective size of each output sg list in bytes
+ * @out: an array where to store the allocated output sg lists
+ * @out_mapped_nents: the resulting sg lists mapped number of sg entries. Might
+ *                    be NULL if sglist not already mapped (in_mapped_nents = 0)
+ * @gfp_mask: the allocation flag
+ *
+ * This function splits the input sg list into nb_splits sg lists, which are
+ * allocated and stored into out.
+ * The @in is split into :
+ *  - @out[0], which covers bytes [@skip .. @skip + @split_sizes[0] - 1] of @in
+ *  - @out[1], which covers bytes [@skip + split_sizes[0] ..
+ *                                 @skip + @split_sizes[0] + @split_sizes[1] -1]
+ * etc ...
+ * It will be the caller's duty to kfree() out array members.
+ *
+ * Returns 0 upon success, or error code
+ */
+int sg_split(struct scatterlist *in, const int in_mapped_nents,
+	     const off_t skip, const int nb_splits,
+	     const size_t *split_sizes,
+	     struct scatterlist **out, int *out_mapped_nents,
+	     gfp_t gfp_mask)
+{
+	int i, ret;
+	struct sg_splitter *splitters;
+
+	splitters = kcalloc(nb_splits, sizeof(*splitters), gfp_mask);
+	if (!splitters)
+		return -ENOMEM;
+
+	ret = sg_calculate_split(in, sg_nents(in), nb_splits, skip, split_sizes,
+			   splitters, false);
+	if (ret < 0)
+		goto err;
+
+	ret = -ENOMEM;
+	for (i = 0; i < nb_splits; i++) {
+		splitters[i].out_sg = kmalloc_array(splitters[i].nents,
+						    sizeof(struct scatterlist),
+						    gfp_mask);
+		if (!splitters[i].out_sg)
+			goto err;
+	}
+
+	/*
+	 * The order of these 3 calls is important and should be kept.
+	 */
+	sg_split_phys(splitters, nb_splits);
+	ret = sg_calculate_split(in, in_mapped_nents, nb_splits, skip,
+				 split_sizes, splitters, true);
+	if (ret < 0)
+		goto err;
+	sg_split_mapped(splitters, nb_splits);
+
+	for (i = 0; i < nb_splits; i++) {
+		out[i] = splitters[i].out_sg;
+		if (out_mapped_nents)
+			out_mapped_nents[i] = splitters[i].nents;
+	}
+
+	kfree(splitters);
+	return 0;
+
+err:
+	for (i = 0; i < nb_splits; i++)
+		kfree(splitters[i].out_sg);
+	kfree(splitters);
+	return ret;
+}
+EXPORT_SYMBOL(sg_split);
diff --git a/lib/show_mem.c b/lib/show_mem.c
index adc98e182..1feed6a2b 100644
--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -38,11 +38,9 @@ void show_mem(unsigned int filter)
 
 	printk("%lu pages RAM\n", total);
 	printk("%lu pages HighMem/MovableOnly\n", highmem);
+	printk("%lu pages reserved\n", reserved);
 #ifdef CONFIG_CMA
-	printk("%lu pages reserved\n", (reserved - totalcma_pages));
 	printk("%lu pages cma reserved\n", totalcma_pages);
-#else
-	printk("%lu pages reserved\n", reserved);
 #endif
 #ifdef CONFIG_QUICKLIST
 	printk("%lu pages in pagetable cache\n",
diff --git a/lib/string.c b/lib/string.c
index 13d1e84dd..84775ba87 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -27,6 +27,10 @@
 #include <linux/bug.h>
 #include <linux/errno.h>
 
+#include <asm/byteorder.h>
+#include <asm/word-at-a-time.h>
+#include <asm/page.h>
+
 #ifndef __HAVE_ARCH_STRNCASECMP
 /**
  * strncasecmp - Case insensitive, length-limited string comparison
@@ -146,6 +150,91 @@ size_t strlcpy(char *dest, const char *src, size_t size)
 EXPORT_SYMBOL(strlcpy);
 #endif
 
+#ifndef __HAVE_ARCH_STRSCPY
+/**
+ * strscpy - Copy a C-string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @count: Size of destination buffer
+ *
+ * Copy the string, or as much of it as fits, into the dest buffer.
+ * The routine returns the number of characters copied (not including
+ * the trailing NUL) or -E2BIG if the destination buffer wasn't big enough.
+ * The behavior is undefined if the string buffers overlap.
+ * The destination buffer is always NUL terminated, unless it's zero-sized.
+ *
+ * Preferred to strlcpy() since the API doesn't require reading memory
+ * from the src string beyond the specified "count" bytes, and since
+ * the return value is easier to error-check than strlcpy()'s.
+ * In addition, the implementation is robust to the string changing out
+ * from underneath it, unlike the current strlcpy() implementation.
+ *
+ * Preferred to strncpy() since it always returns a valid string, and
+ * doesn't unnecessarily force the tail of the destination buffer to be
+ * zeroed.  If the zeroing is desired, it's likely cleaner to use strscpy()
+ * with an overflow test, then just memset() the tail of the dest buffer.
+ */
+ssize_t strscpy(char *dest, const char *src, size_t count)
+{
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+	size_t max = count;
+	long res = 0;
+
+	if (count == 0)
+		return -E2BIG;
+
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	/*
+	 * If src is unaligned, don't cross a page boundary,
+	 * since we don't know if the next page is mapped.
+	 */
+	if ((long)src & (sizeof(long) - 1)) {
+		size_t limit = PAGE_SIZE - ((long)src & (PAGE_SIZE - 1));
+		if (limit < max)
+			max = limit;
+	}
+#else
+	/* If src or dest is unaligned, don't do word-at-a-time. */
+	if (((long) dest | (long) src) & (sizeof(long) - 1))
+		max = 0;
+#endif
+
+	while (max >= sizeof(unsigned long)) {
+		unsigned long c, data;
+
+		c = *(unsigned long *)(src+res);
+		if (has_zero(c, &data, &constants)) {
+			data = prep_zero_mask(c, data, &constants);
+			data = create_zero_mask(data);
+			*(unsigned long *)(dest+res) = c & zero_bytemask(data);
+			return res + find_zero(data);
+		}
+		*(unsigned long *)(dest+res) = c;
+		res += sizeof(unsigned long);
+		count -= sizeof(unsigned long);
+		max -= sizeof(unsigned long);
+	}
+
+	while (count) {
+		char c;
+
+		c = src[res];
+		dest[res] = c;
+		if (!c)
+			return res;
+		res++;
+		count--;
+	}
+
+	/* Hit buffer length without finding a NUL; force NUL-termination. */
+	if (res)
+		dest[res-1] = '\0';
+
+	return -E2BIG;
+}
+EXPORT_SYMBOL(strscpy);
+#endif
+
 #ifndef __HAVE_ARCH_STRCAT
 /**
  * strcat - Append one %NUL-terminated string to another
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index c98ae818e..5939f63d9 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -59,7 +59,11 @@ void string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 	}
 
 	exp = divisor[units] / (u32)blk_size;
-	if (size >= exp) {
+	/*
+	 * size must be strictly greater than exp here to ensure that remainder
+	 * is greater than divisor[units] coming out of the if below.
+	 */
+	if (size > exp) {
 		remainder = do_div(size, divisor[units]);
 		remainder *= blk_size;
 		i++;
@@ -410,7 +414,7 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
  * @dst:	destination buffer (escaped)
  * @osz:	destination buffer size
  * @flags:	combination of the flags (bitwise OR):
- *	%ESCAPE_SPACE:
+ *	%ESCAPE_SPACE: (special white space, not space itself)
  *		'\f' - form feed
  *		'\n' - new line
  *		'\r' - carriage return
@@ -432,16 +436,18 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
  *		all previous together
  *	%ESCAPE_HEX:
  *		'\xHH' - byte with hexadecimal value HH (2 digits)
- * @esc:	NULL-terminated string of characters any of which, if found in
- *		the source, has to be escaped
+ * @only:	NULL-terminated string containing characters used to limit
+ *		the selected escape class. If characters are included in @only
+ *		that would not normally be escaped by the classes selected
+ *		in @flags, they will be copied to @dst unescaped.
  *
  * Description:
  * The process of escaping byte buffer includes several parts. They are applied
  * in the following sequence.
  *	1. The character is matched to the printable class, if asked, and in
  *	   case of match it passes through to the output.
- *	2. The character is not matched to the one from @esc string and thus
- *	   must go as is to the output.
+ *	2. The character is not matched to the one from @only string and thus
+ *	   must go as-is to the output.
  *	3. The character is checked if it falls into the class given by @flags.
  *	   %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any
  *	   character. Note that they actually can't go together, otherwise
@@ -458,11 +464,11 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
  * dst for a '\0' terminator if and only if ret < osz.
  */
 int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
-		      unsigned int flags, const char *esc)
+		      unsigned int flags, const char *only)
 {
 	char *p = dst;
 	char *end = p + osz;
-	bool is_dict = esc && *esc;
+	bool is_dict = only && *only;
 
 	while (isz--) {
 		unsigned char c = *src++;
@@ -471,7 +477,7 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
 		 * Apply rules in the following sequence:
 		 *	- the character is printable, when @flags has
 		 *	  %ESCAPE_NP bit set
-		 *	- the @esc string is supplied and does not contain a
+		 *	- the @only string is supplied and does not contain a
 		 *	  character under question
 		 *	- the character doesn't fall into a class of symbols
 		 *	  defined by given @flags
@@ -479,7 +485,7 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
 		 * output buffer.
 		 */
 		if ((flags & ESCAPE_NP && isprint(c)) ||
-		    (is_dict && !strchr(esc, c))) {
+		    (is_dict && !strchr(only, c))) {
 			/* do nothing */
 		} else {
 			if (flags & ESCAPE_SPACE && escape_space(c, &p, end))
diff --git a/lib/test-kstrtox.c b/lib/test-kstrtox.c
index 4137bca5f..f355f6716 100644
--- a/lib/test-kstrtox.c
+++ b/lib/test-kstrtox.c
@@ -260,6 +260,7 @@ static void __init test_kstrtoll_ok(void)
 		{"4294967297",	10,	4294967297LL},
 		{"9223372036854775807",	10,	9223372036854775807LL},
 
+		{"-0",	10,	0LL},
 		{"-1",	10,	-1LL},
 		{"-2",	10,	-2LL},
 		{"-9223372036854775808",	10,	LLONG_MIN},
@@ -277,11 +278,6 @@ static void __init test_kstrtoll_fail(void)
 		{"-9223372036854775809",	10},
 		{"-18446744073709551614",	10},
 		{"-18446744073709551615",	10},
-		/* negative zero isn't an integer in Linux */
-		{"-0",	0},
-		{"-0",	8},
-		{"-0",	10},
-		{"-0",	16},
 		/* sign is first character if any */
 		{"-+1", 0},
 		{"-+1", 8},
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 7f58c735d..d1377390b 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -18,10 +18,12 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/filter.h>
+#include <linux/bpf.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/random.h>
+#include <linux/highmem.h>
 
 /* General test specific settings */
 #define MAX_SUBTESTS	3
@@ -55,6 +57,7 @@
 /* Flags that can be passed to test cases */
 #define FLAG_NO_DATA		BIT(0)
 #define FLAG_EXPECTED_FAIL	BIT(1)
+#define FLAG_SKB_FRAG		BIT(2)
 
 enum {
 	CLASSIC  = BIT(6),	/* Old BPF instructions only. */
@@ -80,6 +83,7 @@ struct bpf_test {
 		__u32 result;
 	} test[MAX_SUBTESTS];
 	int (*fill_helper)(struct bpf_test *self);
+	__u8 frag_data[MAX_DATA];
 };
 
 /* Large test cases need separate allocation and fill handler. */
@@ -355,6 +359,81 @@ static int bpf_fill_ja(struct bpf_test *self)
 	return __bpf_fill_ja(self, 12, 9);
 }
 
+static int bpf_fill_ld_abs_get_processor_id(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct sock_filter *insn;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	for (i = 0; i < len - 1; i += 2) {
+		insn[i] = __BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 0);
+		insn[i + 1] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+					 SKF_AD_OFF + SKF_AD_CPU);
+	}
+
+	insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xbee);
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
+#define PUSH_CNT 68
+/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+static int bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn;
+	int i = 0, j, k = 0;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	insn[i++] = BPF_MOV64_REG(R6, R1);
+loop:
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(R1, R6);
+		insn[i++] = BPF_MOV64_IMM(R2, 1);
+		insn[i++] = BPF_MOV64_IMM(R3, 2);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 bpf_skb_vlan_push_proto.func - __bpf_call_base);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
+		i++;
+	}
+
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(R1, R6);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 bpf_skb_vlan_pop_proto.func - __bpf_call_base);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
+		i++;
+	}
+	if (++k < 5)
+		goto loop;
+
+	for (; i < len - 1; i++)
+		insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xbef);
+
+	insn[len - 1] = BPF_EXIT_INSN();
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
 static struct bpf_test tests[] = {
 	{
 		"TAX",
@@ -3674,6 +3753,9 @@ static struct bpf_test tests[] = {
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
 			BPF_ENDIAN(BPF_FROM_BE, R0, 32),
+			BPF_ALU64_REG(BPF_MOV, R1, R0),
+			BPF_ALU64_IMM(BPF_RSH, R1, 32),
+			BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
@@ -3708,6 +3790,9 @@ static struct bpf_test tests[] = {
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
 			BPF_ENDIAN(BPF_FROM_LE, R0, 32),
+			BPF_ALU64_REG(BPF_MOV, R1, R0),
+			BPF_ALU64_IMM(BPF_RSH, R1, 32),
+			BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
@@ -4392,6 +4477,618 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xababcbac } },
 		.fill_helper = bpf_fill_maxinsns11,
 	},
+	{
+		"BPF_MAXINSNS: ld_abs+get_processor_id",
+		{ },
+		CLASSIC,
+		{ },
+		{ { 1, 0xbee } },
+		.fill_helper = bpf_fill_ld_abs_get_processor_id,
+	},
+	{
+		"BPF_MAXINSNS: ld_abs+vlan_push/pop",
+		{ },
+		INTERNAL,
+		{ 0x34 },
+		{ { 1, 0xbef } },
+		.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
+	},
+	/*
+	 * LD_IND / LD_ABS on fragmented SKBs
+	 */
+	{
+		"LD_IND byte frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x42} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_IND halfword frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x4344} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_IND word frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x8),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x21071983} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_IND halfword mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x0519} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	{
+		"LD_IND word mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x40),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x25051982} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	{
+		"LD_ABS byte frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x40),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x42} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_ABS halfword frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x44),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x4344} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_ABS word frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x48),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ },
+		{ {0x40, 0x21071983} },
+		.frag_data = {
+			0x42, 0x00, 0x00, 0x00,
+			0x43, 0x44, 0x00, 0x00,
+			0x21, 0x07, 0x19, 0x83,
+		},
+	},
+	{
+		"LD_ABS halfword mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x0519} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	{
+		"LD_ABS word mixed head/frag",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_SKB_FRAG,
+		{ [0x3e] = 0x25, [0x3f] = 0x05, },
+		{ {0x40, 0x25051982} },
+		.frag_data = { 0x19, 0x82 },
+	},
+	/*
+	 * LD_IND / LD_ABS on non fragmented SKBs
+	 */
+	{
+		/*
+		 * this tests that the JIT/interpreter correctly resets X
+		 * before using it in an LD_IND instruction.
+		 */
+		"LD_IND byte default X",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x1] = 0x42 },
+		{ {0x40, 0x42 } },
+	},
+	{
+		"LD_IND byte positive offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 } },
+	},
+	{
+		"LD_IND byte negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x05 } },
+	},
+	{
+		"LD_IND halfword positive offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+		},
+		{ {0x40, 0xdd88 } },
+	},
+	{
+		"LD_IND halfword negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+		},
+		{ {0x40, 0xbb66 } },
+	},
+	{
+		"LD_IND halfword unaligned",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+		},
+		{ {0x40, 0x66cc } },
+	},
+	{
+		"LD_IND word positive offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xee99ffaa } },
+	},
+	{
+		"LD_IND word negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xaa55bb66 } },
+	},
+	{
+		"LD_IND word unaligned (addr & 3 == 2)",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x2),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xbb66cc77 } },
+	},
+	{
+		"LD_IND word unaligned (addr & 3 == 1)",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x3),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x55bb66cc } },
+	},
+	{
+		"LD_IND word unaligned (addr & 3 == 3)",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x66cc77dd } },
+	},
+	{
+		"LD_ABS byte",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x20),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xcc } },
+	},
+	{
+		"LD_ABS halfword",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x22),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xdd88 } },
+	},
+	{
+		"LD_ABS halfword unaligned",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x25),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x99ff } },
+	},
+	{
+		"LD_ABS word",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x1c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xaa55bb66 } },
+	},
+	{
+		"LD_ABS word unaligned (addr & 3 == 2)",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x22),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0xdd88ee99 } },
+	},
+	{
+		"LD_ABS word unaligned (addr & 3 == 1)",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x21),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x77dd88ee } },
+	},
+	{
+		"LD_ABS word unaligned (addr & 3 == 3)",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x23),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{
+			[0x1c] = 0xaa, [0x1d] = 0x55,
+			[0x1e] = 0xbb, [0x1f] = 0x66,
+			[0x20] = 0xcc, [0x21] = 0x77,
+			[0x22] = 0xdd, [0x23] = 0x88,
+			[0x24] = 0xee, [0x25] = 0x99,
+			[0x26] = 0xff, [0x27] = 0xaa,
+		},
+		{ {0x40, 0x88ee99ff } },
+	},
+	/*
+	 * verify that the interpreter or JIT correctly sets A and X
+	 * to 0.
+	 */
+	{
+		"ADD default X",
+		.u.insns = {
+			/*
+			 * A = 0x42
+			 * A = A + X
+			 * ret A
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x42),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
+	{
+		"ADD default A",
+		.u.insns = {
+			/*
+			 * A = A + 0x42
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 0x42),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
+	{
+		"SUB default X",
+		.u.insns = {
+			/*
+			 * A = 0x66
+			 * A = A - X
+			 * ret A
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x66),
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x66 } },
+	},
+	{
+		"SUB default A",
+		.u.insns = {
+			/*
+			 * A = A - -0x66
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_K, -0x66),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x66 } },
+	},
+	{
+		"MUL default X",
+		.u.insns = {
+			/*
+			 * A = 0x42
+			 * A = A * X
+			 * ret A
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x42),
+			BPF_STMT(BPF_ALU | BPF_MUL | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"MUL default A",
+		.u.insns = {
+			/*
+			 * A = A * 0x66
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_MUL | BPF_K, 0x66),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"DIV default X",
+		.u.insns = {
+			/*
+			 * A = 0x42
+			 * A = A / X ; this halt the filter execution if X is 0
+			 * ret 0x42
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x42),
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0x42),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"DIV default A",
+		.u.insns = {
+			/*
+			 * A = A / 1
+			 * ret A
+			 */
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_K, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x0 } },
+	},
+	{
+		"JMP EQ default A",
+		.u.insns = {
+			/*
+			 * cmp A, 0x0, 0, 1
+			 * ret 0x42
+			 * ret 0x66
+			 */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x0, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 0x42),
+			BPF_STMT(BPF_RET | BPF_K, 0x66),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
+	{
+		"JMP EQ default X",
+		.u.insns = {
+			/*
+			 * A = 0x0
+			 * cmp A, X, 0, 1
+			 * ret 0x42
+			 * ret 0x66
+			 */
+			BPF_STMT(BPF_LD | BPF_IMM, 0x0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_X, 0x0, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 0x42),
+			BPF_STMT(BPF_RET | BPF_K, 0x66),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{},
+		{ {0x1, 0x42 } },
+	},
 };
 
 static struct net_device dev;
@@ -4427,6 +5124,9 @@ static struct sk_buff *populate_skb(char *buf, int size)
 
 static void *generate_test_data(struct bpf_test *test, int sub)
 {
+	struct sk_buff *skb;
+	struct page *page;
+
 	if (test->aux & FLAG_NO_DATA)
 		return NULL;
 
@@ -4434,7 +5134,38 @@ static void *generate_test_data(struct bpf_test *test, int sub)
 	 * subtests generate skbs of different sizes based on
 	 * the same data.
 	 */
-	return populate_skb(test->data, test->test[sub].data_size);
+	skb = populate_skb(test->data, test->test[sub].data_size);
+	if (!skb)
+		return NULL;
+
+	if (test->aux & FLAG_SKB_FRAG) {
+		/*
+		 * when the test requires a fragmented skb, add a
+		 * single fragment to the skb, filled with
+		 * test->frag_data.
+		 */
+		void *ptr;
+
+		page = alloc_page(GFP_KERNEL);
+
+		if (!page)
+			goto err_kfree_skb;
+
+		ptr = kmap(page);
+		if (!ptr)
+			goto err_free_page;
+		memcpy(ptr, test->frag_data, MAX_DATA);
+		kunmap(page);
+		skb_add_rx_frag(skb, 0, page, 0, MAX_DATA, MAX_DATA);
+	}
+
+	return skb;
+
+err_free_page:
+	__free_page(page);
+err_kfree_skb:
+	kfree_skb(skb);
+	return NULL;
 }
 
 static void release_test_data(const struct bpf_test *test, void *data)
@@ -4515,6 +5246,8 @@ static struct bpf_prog *generate_filter(int which, int *err)
 		}
 
 		fp->len = flen;
+		/* Type doesn't really matter here as long as it's not unspec. */
+		fp->type = BPF_PROG_TYPE_SOCKET_FILTER;
 		memcpy(fp->insnsi, fptr, fp->len * sizeof(struct bpf_insn));
 
 		bpf_prog_select_runtime(fp);
@@ -4545,14 +5278,14 @@ static int __run_one(const struct bpf_prog *fp, const void *data,
 	u64 start, finish;
 	int ret = 0, i;
 
-	start = ktime_to_us(ktime_get());
+	start = ktime_get_ns();
 
 	for (i = 0; i < runs; i++)
 		ret = BPF_PROG_RUN(fp, data);
 
-	finish = ktime_to_us(ktime_get());
+	finish = ktime_get_ns();
 
-	*duration = (finish - start) * 1000ULL;
+	*duration = finish - start;
 	do_div(*duration, runs);
 
 	return ret;
@@ -4572,6 +5305,11 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test)
 			break;
 
 		data = generate_test_data(test, i);
+		if (!data && !(test->aux & FLAG_NO_DATA)) {
+			pr_cont("data generation failed ");
+			err_cnt++;
+			break;
+		}
 		ret = __run_one(fp, data, runs, &duration);
 		release_test_data(test, data);
 
@@ -4587,10 +5325,73 @@ static int run_one(const struct bpf_prog *fp, struct bpf_test *test)
 	return err_cnt;
 }
 
+static char test_name[64];
+module_param_string(test_name, test_name, sizeof(test_name), 0);
+
+static int test_id = -1;
+module_param(test_id, int, 0);
+
+static int test_range[2] = { 0, ARRAY_SIZE(tests) - 1 };
+module_param_array(test_range, int, NULL, 0);
+
+static __init int find_test_index(const char *test_name)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (!strcmp(tests[i].descr, test_name))
+			return i;
+	}
+	return -1;
+}
+
 static __init int prepare_bpf_tests(void)
 {
 	int i;
 
+	if (test_id >= 0) {
+		/*
+		 * if a test_id was specified, use test_range to
+		 * cover only that test.
+		 */
+		if (test_id >= ARRAY_SIZE(tests)) {
+			pr_err("test_bpf: invalid test_id specified.\n");
+			return -EINVAL;
+		}
+
+		test_range[0] = test_id;
+		test_range[1] = test_id;
+	} else if (*test_name) {
+		/*
+		 * if a test_name was specified, find it and setup
+		 * test_range to cover only that test.
+		 */
+		int idx = find_test_index(test_name);
+
+		if (idx < 0) {
+			pr_err("test_bpf: no test named '%s' found.\n",
+			       test_name);
+			return -EINVAL;
+		}
+		test_range[0] = idx;
+		test_range[1] = idx;
+	} else {
+		/*
+		 * check that the supplied test_range is valid.
+		 */
+		if (test_range[0] >= ARRAY_SIZE(tests) ||
+		    test_range[1] >= ARRAY_SIZE(tests) ||
+		    test_range[0] < 0 || test_range[1] < 0) {
+			pr_err("test_bpf: test_range is out of bound.\n");
+			return -EINVAL;
+		}
+
+		if (test_range[1] < test_range[0]) {
+			pr_err("test_bpf: test_range is ending before it starts.\n");
+			return -EINVAL;
+		}
+	}
+
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		if (tests[i].fill_helper &&
 		    tests[i].fill_helper(&tests[i]) < 0)
@@ -4610,6 +5411,11 @@ static __init void destroy_bpf_tests(void)
 	}
 }
 
+static bool exclude_test(int test_id)
+{
+	return test_id < test_range[0] || test_id > test_range[1];
+}
+
 static __init int test_bpf(void)
 {
 	int i, err_cnt = 0, pass_cnt = 0;
@@ -4619,6 +5425,9 @@ static __init int test_bpf(void)
 		struct bpf_prog *fp;
 		int err;
 
+		if (exclude_test(i))
+			continue;
+
 		pr_info("#%d %s ", i, tests[i].descr);
 
 		fp = generate_filter(i, &err);
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 098c08edd..c1efb1b61 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -65,7 +65,7 @@ static noinline void __init kmalloc_node_oob_right(void)
 	kfree(ptr);
 }
 
-static noinline void __init kmalloc_large_oob_rigth(void)
+static noinline void __init kmalloc_large_oob_right(void)
 {
 	char *ptr;
 	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
@@ -114,7 +114,7 @@ static noinline void __init kmalloc_oob_krealloc_less(void)
 		kfree(ptr1);
 		return;
 	}
-	ptr2[size1] = 'x';
+	ptr2[size2] = 'x';
 	kfree(ptr2);
 }
 
@@ -259,7 +259,7 @@ static int __init kmalloc_tests_init(void)
 	kmalloc_oob_right();
 	kmalloc_oob_left();
 	kmalloc_node_oob_right();
-	kmalloc_large_oob_rigth();
+	kmalloc_large_oob_right();
 	kmalloc_oob_krealloc_more();
 	kmalloc_oob_krealloc_less();
 	kmalloc_oob_16();
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index c90777eae..8c1ad1ced 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -16,10 +16,14 @@
 #include <linux/init.h>
 #include <linux/jhash.h>
 #include <linux/kernel.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/rhashtable.h>
+#include <linux/semaphore.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
 
 #define MAX_ENTRIES	1000000
 #define TEST_INSERT_FAIL INT_MAX
@@ -44,11 +48,21 @@ static int size = 8;
 module_param(size, int, 0);
 MODULE_PARM_DESC(size, "Initial size hint of table (default: 8)");
 
+static int tcount = 10;
+module_param(tcount, int, 0);
+MODULE_PARM_DESC(tcount, "Number of threads to spawn (default: 10)");
+
 struct test_obj {
 	int			value;
 	struct rhash_head	node;
 };
 
+struct thread_data {
+	int id;
+	struct task_struct *task;
+	struct test_obj *objs;
+};
+
 static struct test_obj array[MAX_ENTRIES];
 
 static struct rhashtable_params test_rht_params = {
@@ -59,6 +73,9 @@ static struct rhashtable_params test_rht_params = {
 	.nulls_base = (3U << RHT_BASE_SHIFT),
 };
 
+static struct semaphore prestart_sem;
+static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0);
+
 static int __init test_rht_lookup(struct rhashtable *ht)
 {
 	unsigned int i;
@@ -87,6 +104,8 @@ static int __init test_rht_lookup(struct rhashtable *ht)
 				return -EINVAL;
 			}
 		}
+
+		cond_resched_rcu();
 	}
 
 	return 0;
@@ -160,6 +179,8 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 		} else if (err) {
 			return err;
 		}
+
+		cond_resched();
 	}
 
 	if (insert_fails)
@@ -183,6 +204,8 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 
 			rhashtable_remove_fast(ht, &obj->node, test_rht_params);
 		}
+
+		cond_resched();
 	}
 
 	end = ktime_get_ns();
@@ -193,10 +216,97 @@ static s64 __init test_rhashtable(struct rhashtable *ht)
 
 static struct rhashtable ht;
 
+static int thread_lookup_test(struct thread_data *tdata)
+{
+	int i, err = 0;
+
+	for (i = 0; i < entries; i++) {
+		struct test_obj *obj;
+		int key = (tdata->id << 16) | i;
+
+		obj = rhashtable_lookup_fast(&ht, &key, test_rht_params);
+		if (obj && (tdata->objs[i].value == TEST_INSERT_FAIL)) {
+			pr_err("  found unexpected object %d\n", key);
+			err++;
+		} else if (!obj && (tdata->objs[i].value != TEST_INSERT_FAIL)) {
+			pr_err("  object %d not found!\n", key);
+			err++;
+		} else if (obj && (obj->value != key)) {
+			pr_err("  wrong object returned (got %d, expected %d)\n",
+			       obj->value, key);
+			err++;
+		}
+	}
+	return err;
+}
+
+static int threadfunc(void *data)
+{
+	int i, step, err = 0, insert_fails = 0;
+	struct thread_data *tdata = data;
+
+	up(&prestart_sem);
+	if (down_interruptible(&startup_sem))
+		pr_err("  thread[%d]: down_interruptible failed\n", tdata->id);
+
+	for (i = 0; i < entries; i++) {
+		tdata->objs[i].value = (tdata->id << 16) | i;
+		err = rhashtable_insert_fast(&ht, &tdata->objs[i].node,
+		                             test_rht_params);
+		if (err == -ENOMEM || err == -EBUSY) {
+			tdata->objs[i].value = TEST_INSERT_FAIL;
+			insert_fails++;
+		} else if (err) {
+			pr_err("  thread[%d]: rhashtable_insert_fast failed\n",
+			       tdata->id);
+			goto out;
+		}
+	}
+	if (insert_fails)
+		pr_info("  thread[%d]: %d insert failures\n",
+		        tdata->id, insert_fails);
+
+	err = thread_lookup_test(tdata);
+	if (err) {
+		pr_err("  thread[%d]: rhashtable_lookup_test failed\n",
+		       tdata->id);
+		goto out;
+	}
+
+	for (step = 10; step > 0; step--) {
+		for (i = 0; i < entries; i += step) {
+			if (tdata->objs[i].value == TEST_INSERT_FAIL)
+				continue;
+			err = rhashtable_remove_fast(&ht, &tdata->objs[i].node,
+			                             test_rht_params);
+			if (err) {
+				pr_err("  thread[%d]: rhashtable_remove_fast failed\n",
+				       tdata->id);
+				goto out;
+			}
+			tdata->objs[i].value = TEST_INSERT_FAIL;
+		}
+		err = thread_lookup_test(tdata);
+		if (err) {
+			pr_err("  thread[%d]: rhashtable_lookup_test (2) failed\n",
+			       tdata->id);
+			goto out;
+		}
+	}
+out:
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+	return err;
+}
+
 static int __init test_rht_init(void)
 {
-	int i, err;
+	int i, err, started_threads = 0, failed_threads = 0;
 	u64 total_time = 0;
+	struct thread_data *tdata;
+	struct test_obj *objs;
 
 	entries = min(entries, MAX_ENTRIES);
 
@@ -232,6 +342,57 @@ static int __init test_rht_init(void)
 	do_div(total_time, runs);
 	pr_info("Average test time: %llu\n", total_time);
 
+	if (!tcount)
+		return 0;
+
+	pr_info("Testing concurrent rhashtable access from %d threads\n",
+	        tcount);
+	sema_init(&prestart_sem, 1 - tcount);
+	tdata = vzalloc(tcount * sizeof(struct thread_data));
+	if (!tdata)
+		return -ENOMEM;
+	objs  = vzalloc(tcount * entries * sizeof(struct test_obj));
+	if (!objs) {
+		vfree(tdata);
+		return -ENOMEM;
+	}
+
+	err = rhashtable_init(&ht, &test_rht_params);
+	if (err < 0) {
+		pr_warn("Test failed: Unable to initialize hashtable: %d\n",
+			err);
+		vfree(tdata);
+		vfree(objs);
+		return -EINVAL;
+	}
+	for (i = 0; i < tcount; i++) {
+		tdata[i].id = i;
+		tdata[i].objs = objs + i * entries;
+		tdata[i].task = kthread_run(threadfunc, &tdata[i],
+		                            "rhashtable_thrad[%d]", i);
+		if (IS_ERR(tdata[i].task))
+			pr_err(" kthread_run failed for thread %d\n", i);
+		else
+			started_threads++;
+	}
+	if (down_interruptible(&prestart_sem))
+		pr_err("  down interruptible failed\n");
+	for (i = 0; i < tcount; i++)
+		up(&startup_sem);
+	for (i = 0; i < tcount; i++) {
+		if (IS_ERR(tdata[i].task))
+			continue;
+		if ((err = kthread_stop(tdata[i].task))) {
+			pr_warn("Test failed: thread %d returned: %d\n",
+			        i, err);
+			failed_threads++;
+		}
+	}
+	pr_info("Started %d threads, %d failed\n",
+	        started_threads, failed_threads);
+	rhashtable_destroy(&ht);
+	vfree(tdata);
+	vfree(objs);
 	return 0;
 }
 
diff --git a/lib/test_static_key_base.c b/lib/test_static_key_base.c
new file mode 100644
index 000000000..729447aea
--- /dev/null
+++ b/lib/test_static_key_base.c
@@ -0,0 +1,68 @@
+/*
+ * Kernel module for testing static keys.
+ *
+ * Copyright 2015 Akamai Technologies Inc. All Rights Reserved
+ *
+ * Authors:
+ *      Jason Baron       <jbaron@akamai.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/jump_label.h>
+
+/* old keys */
+struct static_key base_old_true_key = STATIC_KEY_INIT_TRUE;
+EXPORT_SYMBOL_GPL(base_old_true_key);
+struct static_key base_inv_old_true_key = STATIC_KEY_INIT_TRUE;
+EXPORT_SYMBOL_GPL(base_inv_old_true_key);
+struct static_key base_old_false_key = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(base_old_false_key);
+struct static_key base_inv_old_false_key = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(base_inv_old_false_key);
+
+/* new keys */
+DEFINE_STATIC_KEY_TRUE(base_true_key);
+EXPORT_SYMBOL_GPL(base_true_key);
+DEFINE_STATIC_KEY_TRUE(base_inv_true_key);
+EXPORT_SYMBOL_GPL(base_inv_true_key);
+DEFINE_STATIC_KEY_FALSE(base_false_key);
+EXPORT_SYMBOL_GPL(base_false_key);
+DEFINE_STATIC_KEY_FALSE(base_inv_false_key);
+EXPORT_SYMBOL_GPL(base_inv_false_key);
+
+static void invert_key(struct static_key *key)
+{
+	if (static_key_enabled(key))
+		static_key_disable(key);
+	else
+		static_key_enable(key);
+}
+
+static int __init test_static_key_base_init(void)
+{
+	invert_key(&base_inv_old_true_key);
+	invert_key(&base_inv_old_false_key);
+	invert_key(&base_inv_true_key.key);
+	invert_key(&base_inv_false_key.key);
+
+	return 0;
+}
+
+static void __exit test_static_key_base_exit(void)
+{
+}
+
+module_init(test_static_key_base_init);
+module_exit(test_static_key_base_exit);
+
+MODULE_AUTHOR("Jason Baron <jbaron@akamai.com>");
+MODULE_LICENSE("GPL");
diff --git a/lib/test_static_keys.c b/lib/test_static_keys.c
new file mode 100644
index 000000000..c61b299e3
--- /dev/null
+++ b/lib/test_static_keys.c
@@ -0,0 +1,225 @@
+/*
+ * Kernel module for testing static keys.
+ *
+ * Copyright 2015 Akamai Technologies Inc. All Rights Reserved
+ *
+ * Authors:
+ *      Jason Baron       <jbaron@akamai.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/jump_label.h>
+
+/* old keys */
+struct static_key old_true_key	= STATIC_KEY_INIT_TRUE;
+struct static_key old_false_key	= STATIC_KEY_INIT_FALSE;
+
+/* new api */
+DEFINE_STATIC_KEY_TRUE(true_key);
+DEFINE_STATIC_KEY_FALSE(false_key);
+
+/* external */
+extern struct static_key base_old_true_key;
+extern struct static_key base_inv_old_true_key;
+extern struct static_key base_old_false_key;
+extern struct static_key base_inv_old_false_key;
+
+/* new api */
+extern struct static_key_true base_true_key;
+extern struct static_key_true base_inv_true_key;
+extern struct static_key_false base_false_key;
+extern struct static_key_false base_inv_false_key;
+
+
+struct test_key {
+	bool			init_state;
+	struct static_key	*key;
+	bool			(*test_key)(void);
+};
+
+#define test_key_func(key, branch) \
+	({bool func(void) { return branch(key); } func;	})
+
+static void invert_key(struct static_key *key)
+{
+	if (static_key_enabled(key))
+		static_key_disable(key);
+	else
+		static_key_enable(key);
+}
+
+static void invert_keys(struct test_key *keys, int size)
+{
+	struct static_key *previous = NULL;
+	int i;
+
+	for (i = 0; i < size; i++) {
+		if (previous != keys[i].key) {
+			invert_key(keys[i].key);
+			previous = keys[i].key;
+		}
+	}
+}
+
+static int verify_keys(struct test_key *keys, int size, bool invert)
+{
+	int i;
+	bool ret, init;
+
+	for (i = 0; i < size; i++) {
+		ret = static_key_enabled(keys[i].key);
+		init = keys[i].init_state;
+		if (ret != (invert ? !init : init))
+			return -EINVAL;
+		ret = keys[i].test_key();
+		if (static_key_enabled(keys[i].key)) {
+			if (!ret)
+				return -EINVAL;
+		} else {
+			if (ret)
+				return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static int __init test_static_key_init(void)
+{
+	int ret;
+	int size;
+
+	struct test_key static_key_tests[] = {
+		/* internal keys - old keys */
+		{
+			.init_state	= true,
+			.key		= &old_true_key,
+			.test_key	= test_key_func(&old_true_key, static_key_true),
+		},
+		{
+			.init_state	= false,
+			.key		= &old_false_key,
+			.test_key	= test_key_func(&old_false_key, static_key_false),
+		},
+		/* internal keys - new keys */
+		{
+			.init_state	= true,
+			.key		= &true_key.key,
+			.test_key	= test_key_func(&true_key, static_branch_likely),
+		},
+		{
+			.init_state	= true,
+			.key		= &true_key.key,
+			.test_key	= test_key_func(&true_key, static_branch_unlikely),
+		},
+		{
+			.init_state	= false,
+			.key		= &false_key.key,
+			.test_key	= test_key_func(&false_key, static_branch_likely),
+		},
+		{
+			.init_state	= false,
+			.key		= &false_key.key,
+			.test_key	= test_key_func(&false_key, static_branch_unlikely),
+		},
+		/* external keys - old keys */
+		{
+			.init_state	= true,
+			.key		= &base_old_true_key,
+			.test_key	= test_key_func(&base_old_true_key, static_key_true),
+		},
+		{
+			.init_state	= false,
+			.key		= &base_inv_old_true_key,
+			.test_key	= test_key_func(&base_inv_old_true_key, static_key_true),
+		},
+		{
+			.init_state	= false,
+			.key		= &base_old_false_key,
+			.test_key	= test_key_func(&base_old_false_key, static_key_false),
+		},
+		{
+			.init_state	= true,
+			.key		= &base_inv_old_false_key,
+			.test_key	= test_key_func(&base_inv_old_false_key, static_key_false),
+		},
+		/* external keys - new keys */
+		{
+			.init_state	= true,
+			.key		= &base_true_key.key,
+			.test_key	= test_key_func(&base_true_key, static_branch_likely),
+		},
+		{
+			.init_state	= true,
+			.key		= &base_true_key.key,
+			.test_key	= test_key_func(&base_true_key, static_branch_unlikely),
+		},
+		{
+			.init_state	= false,
+			.key		= &base_inv_true_key.key,
+			.test_key	= test_key_func(&base_inv_true_key, static_branch_likely),
+		},
+		{
+			.init_state	= false,
+			.key		= &base_inv_true_key.key,
+			.test_key	= test_key_func(&base_inv_true_key, static_branch_unlikely),
+		},
+		{
+			.init_state	= false,
+			.key		= &base_false_key.key,
+			.test_key	= test_key_func(&base_false_key, static_branch_likely),
+		},
+		{
+			.init_state	= false,
+			.key		= &base_false_key.key,
+			.test_key	= test_key_func(&base_false_key, static_branch_unlikely),
+		},
+		{
+			.init_state	= true,
+			.key		= &base_inv_false_key.key,
+			.test_key	= test_key_func(&base_inv_false_key, static_branch_likely),
+		},
+		{
+			.init_state	= true,
+			.key		= &base_inv_false_key.key,
+			.test_key	= test_key_func(&base_inv_false_key, static_branch_unlikely),
+		},
+	};
+
+	size = ARRAY_SIZE(static_key_tests);
+
+	ret = verify_keys(static_key_tests, size, false);
+	if (ret)
+		goto out;
+
+	invert_keys(static_key_tests, size);
+	ret = verify_keys(static_key_tests, size, true);
+	if (ret)
+		goto out;
+
+	invert_keys(static_key_tests, size);
+	ret = verify_keys(static_key_tests, size, false);
+	if (ret)
+		goto out;
+	return 0;
+out:
+	return ret;
+}
+
+static void __exit test_static_key_exit(void)
+{
+}
+
+module_init(test_static_key_init);
+module_exit(test_static_key_exit);
+
+MODULE_AUTHOR("Jason Baron <jbaron@akamai.com>");
+MODULE_LICENSE("GPL");
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index da39c608a..95cd63b43 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -17,6 +17,7 @@
  */
 
 #include <stdarg.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/module.h>	/* for KSYM_SYMBOL_LEN */
 #include <linux/types.h>
diff --git a/lib/zlib_deflate/deftree.c b/lib/zlib_deflate/deftree.c
index ddf348299..9b1756b12 100644
--- a/lib/zlib_deflate/deftree.c
+++ b/lib/zlib_deflate/deftree.c
@@ -35,6 +35,7 @@
 /* #include "deflate.h" */
 
 #include <linux/zutil.h>
+#include <linux/bitrev.h>
 #include "defutil.h"
 
 #ifdef DEBUG_ZLIB
@@ -146,7 +147,6 @@ static void send_all_trees (deflate_state *s, int lcodes, int dcodes,
 static void compress_block (deflate_state *s, ct_data *ltree,
                            ct_data *dtree);
 static void set_data_type  (deflate_state *s);
-static unsigned bi_reverse (unsigned value, int length);
 static void bi_windup      (deflate_state *s);
 static void bi_flush       (deflate_state *s);
 static void copy_block     (deflate_state *s, char *buf, unsigned len,
@@ -284,7 +284,7 @@ static void tr_static_init(void)
     /* The static distance tree is trivial: */
     for (n = 0; n < D_CODES; n++) {
         static_dtree[n].Len = 5;
-        static_dtree[n].Code = bi_reverse((unsigned)n, 5);
+        static_dtree[n].Code = bitrev32((u32)n) >> (32 - 5);
     }
     static_init_done = 1;
 }
@@ -520,7 +520,7 @@ static void gen_codes(
         int len = tree[n].Len;
         if (len == 0) continue;
         /* Now reverse the bits */
-        tree[n].Code = bi_reverse(next_code[len]++, len);
+        tree[n].Code = bitrev32((u32)(next_code[len]++)) >> (32 - len);
 
         Tracecv(tree != static_ltree, (stderr,"\nn %3d %c l %2d c %4x (%x) ",
              n, (isgraph(n) ? n : ' '), len, tree[n].Code, next_code[len]-1));
diff --git a/lib/zlib_deflate/defutil.h b/lib/zlib_deflate/defutil.h
index b640b6402..a8c370897 100644
--- a/lib/zlib_deflate/defutil.h
+++ b/lib/zlib_deflate/defutil.h
@@ -293,22 +293,6 @@ void zlib_tr_stored_type_only (deflate_state *);
 }
 
 /* ===========================================================================
- * Reverse the first len bits of a code, using straightforward code (a faster
- * method would use a table)
- * IN assertion: 1 <= len <= 15
- */
-static inline unsigned bi_reverse(unsigned code, /* the value to invert */
-				  int len)       /* its bit length */
-{
-    register unsigned res = 0;
-    do {
-        res |= code & 1;
-        code >>= 1, res <<= 1;
-    } while (--len > 0);
-    return res >> 1;
-}
-
-/* ===========================================================================
  * Flush the bit buffer, keeping at most 7 bits in it.
  */
 static inline void bi_flush(deflate_state *s)