diff --git a/Makefile b/Makefile
index 1e04a9f8..d0db33d8 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 0
-SUBLEVEL = 21
+SUBLEVEL = 22
 EXTRAVERSION =
 NAME = Sneaky Weasel
 
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index f567965c..6e96e65e 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -308,7 +308,7 @@ int __init pci_xen_init(void)
 
 int __init pci_xen_hvm_init(void)
 {
-	if (!xen_feature(XENFEAT_hvm_pirqs))
+	if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
 		return 0;
 
 #ifdef CONFIG_ACPI
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 88f160b7..107f6f7b 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -31,11 +31,6 @@ static inline u64 Maj(u64 x, u64 y, u64 z)
         return (x & y) | (z & (x | y));
 }
 
-static inline u64 RORu64(u64 x, u64 y)
-{
-        return (x >> y) | (x << (64 - y));
-}
-
 static const u64 sha512_K[80] = {
         0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL,
         0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
@@ -66,10 +61,10 @@ static const u64 sha512_K[80] = {
         0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL,
 };
 
-#define e0(x)       (RORu64(x,28) ^ RORu64(x,34) ^ RORu64(x,39))
-#define e1(x)       (RORu64(x,14) ^ RORu64(x,18) ^ RORu64(x,41))
-#define s0(x)       (RORu64(x, 1) ^ RORu64(x, 8) ^ (x >> 7))
-#define s1(x)       (RORu64(x,19) ^ RORu64(x,61) ^ (x >> 6))
+#define e0(x)       (ror64(x,28) ^ ror64(x,34) ^ ror64(x,39))
+#define e1(x)       (ror64(x,14) ^ ror64(x,18) ^ ror64(x,41))
+#define s0(x)       (ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7))
+#define s1(x)       (ror64(x,19) ^ ror64(x,61) ^ (x >> 6))
 
 static inline void LOAD_OP(int I, u64 *W, const u8 *input)
 {
@@ -78,7 +73,7 @@ static inline void LOAD_OP(int I, u64 *W, const u8 *input)
 
 static inline void BLEND_OP(int I, u64 *W)
 {
-	W[I % 16] += s1(W[(I-2) % 16]) + W[(I-7) % 16] + s0(W[(I-15) % 16]);
+	W[I & 15] += s1(W[(I-2) & 15]) + W[(I-7) & 15] + s0(W[(I-15) & 15]);
 }
 
 static void
@@ -89,46 +84,42 @@ sha512_transform(u64 *state, const u8 *input)
 	int i;
 	u64 W[16];
 
-	/* load the input */
-        for (i = 0; i < 16; i++)
-                LOAD_OP(i, W, input);
-
 	/* load the state into our registers */
 	a=state[0];   b=state[1];   c=state[2];   d=state[3];
 	e=state[4];   f=state[5];   g=state[6];   h=state[7];
 
-#define SHA512_0_15(i, a, b, c, d, e, f, g, h)			\
-	t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[i];	\
-	t2 = e0(a) + Maj(a, b, c);				\
-	d += t1;						\
-	h = t1 + t2
-
-#define SHA512_16_79(i, a, b, c, d, e, f, g, h)			\
-	BLEND_OP(i, W);						\
-	t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[(i)%16];	\
-	t2 = e0(a) + Maj(a, b, c);				\
-	d += t1;						\
-	h = t1 + t2
-
-	for (i = 0; i < 16; i += 8) {
-		SHA512_0_15(i, a, b, c, d, e, f, g, h);
-		SHA512_0_15(i + 1, h, a, b, c, d, e, f, g);
-		SHA512_0_15(i + 2, g, h, a, b, c, d, e, f);
-		SHA512_0_15(i + 3, f, g, h, a, b, c, d, e);
-		SHA512_0_15(i + 4, e, f, g, h, a, b, c, d);
-		SHA512_0_15(i + 5, d, e, f, g, h, a, b, c);
-		SHA512_0_15(i + 6, c, d, e, f, g, h, a, b);
-		SHA512_0_15(i + 7, b, c, d, e, f, g, h, a);
-	}
-	for (i = 16; i < 80; i += 8) {
-		SHA512_16_79(i, a, b, c, d, e, f, g, h);
-		SHA512_16_79(i + 1, h, a, b, c, d, e, f, g);
-		SHA512_16_79(i + 2, g, h, a, b, c, d, e, f);
-		SHA512_16_79(i + 3, f, g, h, a, b, c, d, e);
-		SHA512_16_79(i + 4, e, f, g, h, a, b, c, d);
-		SHA512_16_79(i + 5, d, e, f, g, h, a, b, c);
-		SHA512_16_79(i + 6, c, d, e, f, g, h, a, b);
-		SHA512_16_79(i + 7, b, c, d, e, f, g, h, a);
+	/* now iterate */
+	for (i=0; i<80; i+=8) {
+		if (!(i & 8)) {
+			int j;
+
+			if (i < 16) {
+				/* load the input */
+				for (j = 0; j < 16; j++)
+					LOAD_OP(i + j, W, input);
+			} else {
+				for (j = 0; j < 16; j++) {
+					BLEND_OP(i + j, W);
+				}
+			}
+		}
+
+		t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i  ] + W[(i & 15)];
+		t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
+		t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[(i & 15) + 1];
+		t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
+		t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[(i & 15) + 2];
+		t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
+		t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[(i & 15) + 3];
+		t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
+		t1 = d + e1(a) + Ch(a,b,c) + sha512_K[i+4] + W[(i & 15) + 4];
+		t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
+		t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[(i & 15) + 5];
+		t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
+		t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[(i & 15) + 6];
+		t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
+		t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[(i & 15) + 7];
+		t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
 	}
 
 	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
diff --git a/drivers/gpio/pca953x.c b/drivers/gpio/pca953x.c
index 0451d7ac..532f6900 100644
--- a/drivers/gpio/pca953x.c
+++ b/drivers/gpio/pca953x.c
@@ -437,7 +437,7 @@ static irqreturn_t pca953x_irq_handler(int irq, void *devid)
 
 	do {
 		level = __ffs(pending);
-		generic_handle_irq(level + chip->irq_base);
+		handle_nested_irq(level + chip->irq_base);
 
 		pending &= ~(1 << level);
 	} while (pending);
@@ -481,8 +481,8 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 			int irq = lvl + chip->irq_base;
 
 			irq_set_chip_data(irq, chip);
-			irq_set_chip_and_handler(irq, &pca953x_irq_chip,
-						 handle_simple_irq);
+			irq_set_chip(irq, &pca953x_irq_chip);
+			irq_set_nested_thread(irq, true);
 #ifdef CONFIG_ARM
 			set_irq_flags(irq, IRQF_VALID);
 #else
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index b28f7bd9..21257f82 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -712,6 +712,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "i915GMm-HFS"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+                .ident = "AOpen i45GMx-I",
+                .matches = {
+                        DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"),
+                        DMI_MATCH(DMI_BOARD_NAME, "i45GMx-I"),
+                },
+        },
 	{
 		.callback = intel_no_lvds_dmi_callback,
 		.ident = "Aopen i945GTt-VFA",
diff --git a/drivers/hwmon/f75375s.c b/drivers/hwmon/f75375s.c
index 95cbfb3a..e4ab4918 100644
--- a/drivers/hwmon/f75375s.c
+++ b/drivers/hwmon/f75375s.c
@@ -159,7 +159,7 @@ static inline void f75375_write8(struct i2c_client *client, u8 reg,
 static inline void f75375_write16(struct i2c_client *client, u8 reg,
 		u16 value)
 {
-	int err = i2c_smbus_write_byte_data(client, reg, (value << 8));
+	int err = i2c_smbus_write_byte_data(client, reg, (value >> 8));
 	if (err)
 		return;
 	i2c_smbus_write_byte_data(client, reg + 1, (value & 0xFF));
@@ -311,7 +311,7 @@ static int set_pwm_enable_direct(struct i2c_client *client, int nr, int val)
 		fanmode  |= (3 << FAN_CTRL_MODE(nr));
 		break;
 	case 2: /* AUTOMATIC*/
-		fanmode  |= (2 << FAN_CTRL_MODE(nr));
+		fanmode  |= (1 << FAN_CTRL_MODE(nr));
 		break;
 	case 3: /* fan speed */
 		break;
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3ef66a2..fc8a3ffc 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -49,6 +49,26 @@ static inline unsigned long hweight_long(unsigned long w)
 	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
 }
 
+/**
+ * rol64 - rotate a 64-bit value left
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u64 rol64(__u64 word, unsigned int shift)
+{
+	return (word << shift) | (word >> (64 - shift));
+}
+
+/**
+ * ror64 - rotate a 64-bit value right
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u64 ror64(__u64 word, unsigned int shift)
+{
+	return (word >> shift) | (word << (64 - shift));
+}
+
 /**
  * rol32 - rotate a 32-bit value left
  * @word: value to rotate
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index cf793bbb..22653d7c 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -81,7 +81,11 @@ void prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl)
  * Limit the time part in order to ensure there are some bits left for the
  * cycle counter and fraction multiply.
  */
+#if BITS_PER_LONG == 32
 #define PROP_MAX_SHIFT (3*BITS_PER_LONG/4)
+#else
+#define PROP_MAX_SHIFT (BITS_PER_LONG/2)
+#endif
 
 #define PROP_FRAC_SHIFT		(BITS_PER_LONG - PROP_MAX_SHIFT - 1)
 #define PROP_FRAC_BASE		(1UL << PROP_FRAC_SHIFT)
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 4e249b92..9b60c6fc 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -23,7 +23,10 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(int, for_background)
 	),
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		struct device *dev = bdi->dev;
+		if (!dev)
+			dev = default_backing_dev_info.dev;
+		strncpy(__entry->name, dev_name(dev), 32);
 		__entry->nr_pages = work->nr_pages;
 		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
 		__entry->sync_mode = work->sync_mode;
diff --git a/kernel/relay.c b/kernel/relay.c
index 859ea5a9..2c242fb2 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -164,10 +164,14 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
  */
 static struct rchan_buf *relay_create_buf(struct rchan *chan)
 {
-	struct rchan_buf *buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
-	if (!buf)
+	struct rchan_buf *buf;
+
+	if (chan->n_subbufs > UINT_MAX / sizeof(size_t *))
 		return NULL;
 
+	buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
+	if (!buf)
+		return NULL;
 	buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL);
 	if (!buf->padding)
 		goto free_buf;
@@ -574,6 +578,8 @@ struct rchan *relay_open(const char *base_filename,
 
 	if (!(subbuf_size && n_subbufs))
 		return NULL;
+	if (subbuf_size > UINT_MAX / n_subbufs)
+		return NULL;
 
 	chan = kzalloc(sizeof(struct rchan), GFP_KERNEL);
 	if (!chan)
diff --git a/mm/slub.c b/mm/slub.c
index 03bc30b7..32430db3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1883,6 +1883,11 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	if (unlikely(!node_match(c, node)))
 		goto another_slab;
 
+	/* must check again c->freelist in case of cpu migration or IRQ */
+	object = c->freelist;
+	if (object)
+		goto update_freelist;
+
 	stat(s, ALLOC_REFILL);
 
 load_freelist:
@@ -1892,6 +1897,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	if (kmem_cache_debug(s))
 		goto debug;
 
+update_freelist:
 	c->freelist = get_freepointer(s, object);
 	page->inuse = page->objects;
 	page->freelist = NULL;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 378bd673..41000650 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -610,7 +610,7 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw,
 	index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) %
 						tid_agg_rx->buf_size;
 	if (!tid_agg_rx->reorder_buf[index] &&
-	    tid_agg_rx->stored_mpdu_num > 1) {
+	    tid_agg_rx->stored_mpdu_num) {
 		/*
 		 * No buffers ready to be released, but check whether any
 		 * frames in the reorder buffer have timed out.
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 6c896dbf..2e799a9a 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -2074,6 +2074,12 @@ static struct ac97_quirk ac97_quirks[] __devinitdata = {
 		.name = "MSI P4 ATX 645 Ultra",
 		.type = AC97_TUNE_HP_ONLY
 	},
+	{
+		.subvendor = 0x161f,
+		.subdevice = 0x202f,
+		.name = "Gateway M520",
+		.type = AC97_TUNE_INV_EAPD
+	},
 	{
 		.subvendor = 0x161f,
 		.subdevice = 0x203a,
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index a57b66e8..185a96d6 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,2 +1,8 @@
 
 #include "../../../arch/x86/lib/memcpy_64.S"
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0239eb87..ad2183c9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -348,6 +348,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
+	data->period = 1;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!sample_id_all)