Linux 3.2.7

commit f2ea0f5f04 upstream.

Use standard ror64() instead of hand-written.
There is no standard ror64, so create it.

The difference is shift value being "unsigned int" instead of uint64_t
(for which there is no reason). gcc starts to emit native ROR instructions
which it doesn't do for some reason currently. This should make the code
faster.

Patch survives in-tree crypto test and ping flood with hmac(sha512) on.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 2
-SUBLEVEL = 6
+SUBLEVEL = 7
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

arch/x86/pci/xen.c

@@ -374,7 +374,7 @@ 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

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
+	/* now iterate */
+	for (i=0; i<80; i+=8) {
+		if (!(i & 8)) {
+			int j;
 
-#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
+			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);
+				}
+			}
+		}
 
-	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);
+		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;

drivers/gpu/drm/i915/intel_dp.c

@@ -208,17 +208,8 @@ intel_dp_link_clock(uint8_t link_bw)
  */
 
 static int
-intel_dp_link_required(struct intel_dp *intel_dp, int pixel_clock, int check_bpp)
+intel_dp_link_required(int pixel_clock, int bpp)
 {
-	struct drm_crtc *crtc = intel_dp->base.base.crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int bpp = 24;
-
-	if (check_bpp)
-		bpp = check_bpp;
-	else if (intel_crtc)
-		bpp = intel_crtc->bpp;
-
 	return (pixel_clock * bpp + 9) / 10;
 }
 
@@ -245,12 +236,11 @@ intel_dp_mode_valid(struct drm_connector *connector,
 			return MODE_PANEL;
 	}
 
-	mode_rate = intel_dp_link_required(intel_dp, mode->clock, 0);
+	mode_rate = intel_dp_link_required(mode->clock, 24);
 	max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
 
 	if (mode_rate > max_rate) {
-			mode_rate = intel_dp_link_required(intel_dp,
-							   mode->clock, 18);
+			mode_rate = intel_dp_link_required(mode->clock, 18);
 			if (mode_rate > max_rate)
 				return MODE_CLOCK_HIGH;
 			else
@@ -683,7 +673,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode,
 	int lane_count, clock;
 	int max_lane_count = intel_dp_max_lane_count(intel_dp);
 	int max_clock = intel_dp_max_link_bw(intel_dp) == DP_LINK_BW_2_7 ? 1 : 0;
-	int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 0;
+	int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 24;
 	static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 };
 
 	if (is_edp(intel_dp) && intel_dp->panel_fixed_mode) {
@@ -701,7 +691,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		for (clock = 0; clock <= max_clock; clock++) {
 			int link_avail = intel_dp_max_data_rate(intel_dp_link_clock(bws[clock]), lane_count);
 
-			if (intel_dp_link_required(intel_dp, mode->clock, bpp)
+			if (intel_dp_link_required(mode->clock, bpp)
 					<= link_avail) {
 				intel_dp->link_bw = bws[clock];
 				intel_dp->lane_count = lane_count;

drivers/gpu/drm/i915/intel_lvds.c

@@ -692,6 +692,14 @@ 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",

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;

drivers/mmc/host/atmel-mci.c

@@ -965,11 +965,14 @@ static void atmci_start_request(struct atmel_mci *host,
 	host->data_status = 0;
 
 	if (host->need_reset) {
+		iflags = atmci_readl(host, ATMCI_IMR);
+		iflags &= (ATMCI_SDIOIRQA | ATMCI_SDIOIRQB);
 		atmci_writel(host, ATMCI_CR, ATMCI_CR_SWRST);
 		atmci_writel(host, ATMCI_CR, ATMCI_CR_MCIEN);
 		atmci_writel(host, ATMCI_MR, host->mode_reg);
 		if (host->caps.has_cfg_reg)
 			atmci_writel(host, ATMCI_CFG, host->cfg_reg);
+		atmci_writel(host, ATMCI_IER, iflags);
 		host->need_reset = false;
 	}
 	atmci_writel(host, ATMCI_SDCR, slot->sdc_reg);

drivers/mmc/host/dw_mmc.c

@@ -22,7 +22,6 @@
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/scatterlist.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
@@ -502,8 +501,14 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 		host->dir_status = DW_MCI_SEND_STATUS;
 
 	if (dw_mci_submit_data_dma(host, data)) {
+		int flags = SG_MITER_ATOMIC;
+		if (host->data->flags & MMC_DATA_READ)
+			flags |= SG_MITER_TO_SG;
+		else
+			flags |= SG_MITER_FROM_SG;
+
+		sg_miter_start(&host->sg_miter, data->sg, data->sg_len, flags);
 		host->sg = data->sg;
-		host->pio_offset = 0;
 		host->part_buf_start = 0;
 		host->part_buf_count = 0;
 
@@ -953,6 +958,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 				 * generates a block interrupt, hence setting
 				 * the scatter-gather pointer to NULL.
 				 */
+				sg_miter_stop(&host->sg_miter);
 				host->sg = NULL;
 				ctrl = mci_readl(host, CTRL);
 				ctrl |= SDMMC_CTRL_FIFO_RESET;
@@ -1286,54 +1292,44 @@ static void dw_mci_pull_data(struct dw_mci *host, void *buf, int cnt)
 
 static void dw_mci_read_data_pio(struct dw_mci *host)
 {
-	struct scatterlist *sg = host->sg;
-	void *buf = sg_virt(sg);
-	unsigned int offset = host->pio_offset;
+	struct sg_mapping_iter *sg_miter = &host->sg_miter;
+	void *buf;
+	unsigned int offset;
 	struct mmc_data	*data = host->data;
 	int shift = host->data_shift;
 	u32 status;
 	unsigned int nbytes = 0, len;
+	unsigned int remain, fcnt;
 
 	do {
-		len = host->part_buf_count +
-			(SDMMC_GET_FCNT(mci_readl(host, STATUS)) << shift);
-		if (offset + len <= sg->length) {
-			dw_mci_pull_data(host, (void *)(buf + offset), len);
+		if (!sg_miter_next(sg_miter))
+			goto done;
 
+		host->sg = sg_miter->__sg;
+		buf = sg_miter->addr;
+		remain = sg_miter->length;
+		offset = 0;
+
+		do {
+			fcnt = (SDMMC_GET_FCNT(mci_readl(host, STATUS))
+					<< shift) + host->part_buf_count;
+			len = min(remain, fcnt);
+			if (!len)
+				break;
+			dw_mci_pull_data(host, (void *)(buf + offset), len);
 			offset += len;
 			nbytes += len;
-
-			if (offset == sg->length) {
-				flush_dcache_page(sg_page(sg));
-				host->sg = sg = sg_next(sg);
-				if (!sg)
-					goto done;
-
-				offset = 0;
-				buf = sg_virt(sg);
-			}
-		} else {
-			unsigned int remaining = sg->length - offset;
-			dw_mci_pull_data(host, (void *)(buf + offset),
-					 remaining);
-			nbytes += remaining;
-
-			flush_dcache_page(sg_page(sg));
-			host->sg = sg = sg_next(sg);
-			if (!sg)
-				goto done;
-
-			offset = len - remaining;
-			buf = sg_virt(sg);
-			dw_mci_pull_data(host, buf, offset);
-			nbytes += offset;
-		}
+			remain -= len;
+		} while (remain);
+		sg_miter->consumed = offset;
 
 		status = mci_readl(host, MINTSTS);
 		mci_writel(host, RINTSTS, SDMMC_INT_RXDR);
 		if (status & DW_MCI_DATA_ERROR_FLAGS) {
 			host->data_status = status;
 			data->bytes_xfered += nbytes;
+			sg_miter_stop(sg_miter);
+			host->sg = NULL;
 			smp_wmb();
 
 			set_bit(EVENT_DATA_ERROR, &host->pending_events);
@@ -1342,65 +1338,66 @@ static void dw_mci_read_data_pio(struct dw_mci *host)
 			return;
 		}
 	} while (status & SDMMC_INT_RXDR); /*if the RXDR is ready read again*/
-	host->pio_offset = offset;
 	data->bytes_xfered += nbytes;
+
+	if (!remain) {
+		if (!sg_miter_next(sg_miter))
+			goto done;
+		sg_miter->consumed = 0;
+	}
+	sg_miter_stop(sg_miter);
 	return;
 
 done:
 	data->bytes_xfered += nbytes;
+	sg_miter_stop(sg_miter);
+	host->sg = NULL;
 	smp_wmb();
 	set_bit(EVENT_XFER_COMPLETE, &host->pending_events);
 }
 
 static void dw_mci_write_data_pio(struct dw_mci *host)
 {
-	struct scatterlist *sg = host->sg;
-	void *buf = sg_virt(sg);
-	unsigned int offset = host->pio_offset;
+	struct sg_mapping_iter *sg_miter = &host->sg_miter;
+	void *buf;
+	unsigned int offset;
 	struct mmc_data	*data = host->data;
 	int shift = host->data_shift;
 	u32 status;
 	unsigned int nbytes = 0, len;
+	unsigned int fifo_depth = host->fifo_depth;
+	unsigned int remain, fcnt;
 
 	do {
-		len = ((host->fifo_depth -
-			SDMMC_GET_FCNT(mci_readl(host, STATUS))) << shift)
-			- host->part_buf_count;
-		if (offset + len <= sg->length) {
-			host->push_data(host, (void *)(buf + offset), len);
+		if (!sg_miter_next(sg_miter))
+			goto done;
 
+		host->sg = sg_miter->__sg;
+		buf = sg_miter->addr;
+		remain = sg_miter->length;
+		offset = 0;
+
+		do {
+			fcnt = ((fifo_depth -
+				 SDMMC_GET_FCNT(mci_readl(host, STATUS)))
+					<< shift) - host->part_buf_count;
+			len = min(remain, fcnt);
+			if (!len)
+				break;
+			host->push_data(host, (void *)(buf + offset), len);
 			offset += len;
 			nbytes += len;
-			if (offset == sg->length) {
-				host->sg = sg = sg_next(sg);
-				if (!sg)
-					goto done;
-
-				offset = 0;
-				buf = sg_virt(sg);
-			}
-		} else {
-			unsigned int remaining = sg->length - offset;
-
-			host->push_data(host, (void *)(buf + offset),
-					remaining);
-			nbytes += remaining;
-
-			host->sg = sg = sg_next(sg);
-			if (!sg)
-				goto done;
-
-			offset = len - remaining;
-			buf = sg_virt(sg);
-			host->push_data(host, (void *)buf, offset);
-			nbytes += offset;
-		}
+			remain -= len;
+		} while (remain);
+		sg_miter->consumed = offset;
 
 		status = mci_readl(host, MINTSTS);
 		mci_writel(host, RINTSTS, SDMMC_INT_TXDR);
 		if (status & DW_MCI_DATA_ERROR_FLAGS) {
 			host->data_status = status;
 			data->bytes_xfered += nbytes;
+			sg_miter_stop(sg_miter);
+			host->sg = NULL;
 
 			smp_wmb();
 
@@ -1410,12 +1407,20 @@ static void dw_mci_write_data_pio(struct dw_mci *host)
 			return;
 		}
 	} while (status & SDMMC_INT_TXDR); /* if TXDR write again */
-	host->pio_offset = offset;
 	data->bytes_xfered += nbytes;
+
+	if (!remain) {
+		if (!sg_miter_next(sg_miter))
+			goto done;
+		sg_miter->consumed = 0;
+	}
+	sg_miter_stop(sg_miter);
 	return;
 
 done:
 	data->bytes_xfered += nbytes;
+	sg_miter_stop(sg_miter);
+	host->sg = NULL;
 	smp_wmb();
 	set_bit(EVENT_XFER_COMPLETE, &host->pending_events);
 }
@@ -1618,6 +1623,7 @@ static void dw_mci_work_routine_card(struct work_struct *work)
 				 * block interrupt, hence setting the
 				 * scatter-gather pointer to NULL.
 				 */
+				sg_miter_stop(&host->sg_miter);
 				host->sg = NULL;
 
 				ctrl = mci_readl(host, CTRL);

drivers/net/ethernet/intel/igb/igb_main.c

@@ -4965,7 +4965,8 @@ static int igb_find_enabled_vfs(struct igb_adapter *adapter)
 	vf_devfn = pdev->devfn + 0x80;
 	pvfdev = pci_get_device(hw->vendor_id, device_id, NULL);
 	while (pvfdev) {
-		if (pvfdev->devfn == vf_devfn)
+		if (pvfdev->devfn == vf_devfn &&
+		    (pvfdev->bus->number >= pdev->bus->number))
 			vfs_found++;
 		vf_devfn += vf_stride;
 		pvfdev = pci_get_device(hw->vendor_id,

drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c

@@ -67,7 +67,8 @@ static int ixgbe_find_enabled_vfs(struct ixgbe_adapter *adapter)
 	vf_devfn = pdev->devfn + 0x80;
 	pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL);
 	while (pvfdev) {
-		if (pvfdev->devfn == vf_devfn)
+		if (pvfdev->devfn == vf_devfn &&
+		    (pvfdev->bus->number >= pdev->bus->number))
 			vfs_found++;
 		vf_devfn += 2;
 		pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID,

drivers/net/ethernet/toshiba/Kconfig

@@ -5,7 +5,7 @@
 config NET_VENDOR_TOSHIBA
 	bool "Toshiba devices"
 	default y
-	depends on PCI && (PPC_IBM_CELL_BLADE || PPC_CELLEB) || PPC_PS3
+	depends on PCI && (PPC_IBM_CELL_BLADE || PPC_CELLEB || MIPS) || PPC_PS3
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y
 	  and read the Ethernet-HOWTO, available from

drivers/net/wireless/ath/ath9k/hw.c

@@ -1034,13 +1034,16 @@ void ath9k_hw_init_global_settings(struct ath_hw *ah)
 
 	/*
 	 * Workaround for early ACK timeouts, add an offset to match the
-	 * initval's 64us ack timeout value.
+	 * initval's 64us ack timeout value. Use 48us for the CTS timeout.
 	 * This was initially only meant to work around an issue with delayed
 	 * BA frames in some implementations, but it has been found to fix ACK
 	 * timeout issues in other cases as well.
 	 */
-	if (conf->channel && conf->channel->band == IEEE80211_BAND_2GHZ)
+	if (conf->channel && conf->channel->band == IEEE80211_BAND_2GHZ) {
 		acktimeout += 64 - sifstime - ah->slottime;
+		ctstimeout += 48 - sifstime - ah->slottime;
+	}
+
 
 	ath9k_hw_set_sifs_time(ah, sifstime);
 	ath9k_hw_setslottime(ah, slottime);

drivers/net/wireless/ath/ath9k/init.c

@@ -775,6 +775,11 @@ int ath9k_init_device(u16 devid, struct ath_softc *sc,
 		ARRAY_SIZE(ath9k_tpt_blink));
 #endif
 
+	INIT_WORK(&sc->hw_reset_work, ath_reset_work);
+	INIT_WORK(&sc->hw_check_work, ath_hw_check);
+	INIT_WORK(&sc->paprd_work, ath_paprd_calibrate);
+	INIT_DELAYED_WORK(&sc->hw_pll_work, ath_hw_pll_work);
+
 	/* Register with mac80211 */
 	error = ieee80211_register_hw(hw);
 	if (error)
@@ -793,10 +798,6 @@ int ath9k_init_device(u16 devid, struct ath_softc *sc,
 			goto error_world;
 	}
 
-	INIT_WORK(&sc->hw_reset_work, ath_reset_work);
-	INIT_WORK(&sc->hw_check_work, ath_hw_check);
-	INIT_WORK(&sc->paprd_work, ath_paprd_calibrate);
-	INIT_DELAYED_WORK(&sc->hw_pll_work, ath_hw_pll_work);
 	sc->last_rssi = ATH_RSSI_DUMMY_MARKER;
 
 	ath_init_leds(sc);

drivers/net/wireless/ath/ath9k/recv.c

@@ -824,6 +824,14 @@ static bool ath9k_rx_accept(struct ath_common *common,
 		(ATH9K_RXERR_DECRYPT | ATH9K_RXERR_CRC | ATH9K_RXERR_MIC |
 		 ATH9K_RXERR_KEYMISS));
 
+	/*
+	 * Key miss events are only relevant for pairwise keys where the
+	 * descriptor does contain a valid key index. This has been observed
+	 * mostly with CCMP encryption.
+	 */
+	if (rx_stats->rs_keyix == ATH9K_RXKEYIX_INVALID)
+		rx_stats->rs_status &= ~ATH9K_RXERR_KEYMISS;
+
 	if (!rx_stats->rs_datalen)
 		return false;
         /*

fs/cifs/connect.c

@@ -756,10 +756,11 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		cifs_dump_mem("Bad SMB: ", buf,
 			min_t(unsigned int, server->total_read, 48));
 
-	if (mid)
-		handle_mid(mid, server, smb_buffer, length);
+	if (!mid)
+		return length;
 
-	return length;
+	handle_mid(mid, server, smb_buffer, length);
+	return 0;
 }
 
 static int

fs/cifs/dir.c

@@ -492,7 +492,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 {
 	int xid;
 	int rc = 0; /* to get around spurious gcc warning, set to zero here */
-	__u32 oplock = 0;
+	__u32 oplock = enable_oplocks ? REQ_OPLOCK : 0;
 	__u16 fileHandle = 0;
 	bool posix_open = false;
 	struct cifs_sb_info *cifs_sb;

fs/fs-writeback.c

@@ -47,14 +47,6 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
-/*
- * Include the creation of the trace points after defining the
- * wb_writeback_work structure so that the definition remains local to this
- * file.
- */
-#define CREATE_TRACE_POINTS
-#include <trace/events/writeback.h>
-
 /*
  * We don't actually have pdflush, but this one is exported though /proc...
  */
@@ -87,6 +79,14 @@ static inline struct inode *wb_inode(struct list_head *head)
 	return list_entry(head, struct inode, i_wb_list);
 }
 
+/*
+ * Include the creation of the trace points after defining the
+ * wb_writeback_work structure and inline functions so that the definition
+ * remains local to this file.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/writeback.h>
+
 /* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
 static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
 {

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

include/linux/mmc/dw_mmc.h

@@ -14,6 +14,8 @@
 #ifndef LINUX_MMC_DW_MMC_H
 #define LINUX_MMC_DW_MMC_H
 
+#include <linux/scatterlist.h>
+
 #define MAX_MCI_SLOTS	2
 
 enum dw_mci_state {
@@ -40,7 +42,7 @@ struct mmc_data;
  * @lock: Spinlock protecting the queue and associated data.
  * @regs: Pointer to MMIO registers.
  * @sg: Scatterlist entry currently being processed by PIO code, if any.
- * @pio_offset: Offset into the current scatterlist entry.
+ * @sg_miter: PIO mapping scatterlist iterator.
  * @cur_slot: The slot which is currently using the controller.
  * @mrq: The request currently being processed on @cur_slot,
  *	or NULL if the controller is idle.
@@ -115,7 +117,7 @@ struct dw_mci {
 	void __iomem		*regs;
 
 	struct scatterlist	*sg;
-	unsigned int		pio_offset;
+	struct sg_mapping_iter	sg_miter;
 
 	struct dw_mci_slot	*cur_slot;
 	struct mmc_request	*mrq;

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)

include/trace/events/writeback.h

@@ -47,7 +47,10 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(int, reason)
 	),
 	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;
@@ -418,7 +421,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 
 	TP_fast_assign(
 		strncpy(__entry->name,
-			dev_name(inode->i_mapping->backing_dev_info->dev), 32);
+			dev_name(inode_to_bdi(inode)->dev), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->dirtied_when	= inode->dirtied_when;

kernel/relay.c

@@ -164,10 +164,14 @@ depopulate:
  */
 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)

mm/backing-dev.c

@@ -318,7 +318,7 @@ static void wakeup_timer_fn(unsigned long data)
 	if (bdi->wb.task) {
 		trace_writeback_wake_thread(bdi);
 		wake_up_process(bdi->wb.task);
-	} else {
+	} else if (bdi->dev) {
 		/*
 		 * When bdi tasks are inactive for long time, they are killed.
 		 * In this case we have to wake-up the forker thread which
@@ -584,6 +584,8 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
+	struct task_struct *task;
+
 	if (!bdi_cap_writeback_dirty(bdi))
 		return;
 
@@ -604,9 +606,14 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 * unfreeze of the thread before calling kthread_stop(), otherwise
 	 * it would never exet if it is currently stuck in the refrigerator.
 	 */
-	if (bdi->wb.task) {
-		thaw_process(bdi->wb.task);
-		kthread_stop(bdi->wb.task);
+	spin_lock_bh(&bdi->wb_lock);
+	task = bdi->wb.task;
+	bdi->wb.task = NULL;
+	spin_unlock_bh(&bdi->wb_lock);
+
+	if (task) {
+		thaw_process(task);
+		kthread_stop(task);
 	}
 }
 
@@ -627,7 +634,9 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	if (bdi->dev) {
+	struct device *dev = bdi->dev;
+
+	if (dev) {
 		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
@@ -636,8 +645,12 @@ void bdi_unregister(struct backing_dev_info *bdi)
 		if (!bdi_cap_flush_forker(bdi))
 			bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
-		device_unregister(bdi->dev);
+
+		spin_lock_bh(&bdi->wb_lock);
 		bdi->dev = NULL;
+		spin_unlock_bh(&bdi->wb_lock);
+
+		device_unregister(dev);
 	}
 }
 EXPORT_SYMBOL(bdi_unregister);

net/mac80211/rx.c

@@ -616,7 +616,7 @@ 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.

sound/pci/hda/patch_realtek.c

@@ -4213,8 +4213,26 @@ enum {
 	PINFIX_PB_M5210,
 	PINFIX_ACER_ASPIRE_7736,
 	PINFIX_ASUS_W90V,
+	ALC889_FIXUP_DAC_ROUTE,
 };
 
+/* Fix the connection of some pins for ALC889:
+ * At least, Acer Aspire 5935 shows the connections to DAC3/4 don't
+ * work correctly (bko#42740)
+ */
+static void alc889_fixup_dac_route(struct hda_codec *codec,
+				   const struct alc_fixup *fix, int action)
+{
+	if (action == ALC_FIXUP_ACT_PRE_PROBE) {
+		hda_nid_t conn1[2] = { 0x0c, 0x0d };
+		hda_nid_t conn2[2] = { 0x0e, 0x0f };
+		snd_hda_override_conn_list(codec, 0x14, 2, conn1);
+		snd_hda_override_conn_list(codec, 0x15, 2, conn1);
+		snd_hda_override_conn_list(codec, 0x18, 2, conn2);
+		snd_hda_override_conn_list(codec, 0x1a, 2, conn2);
+	}
+}
+
 static const struct alc_fixup alc882_fixups[] = {
 	[PINFIX_ABIT_AW9D_MAX] = {
 		.type = ALC_FIXUP_PINS,
@@ -4251,10 +4269,15 @@ static const struct alc_fixup alc882_fixups[] = {
 			{ }
 		}
 	},
+	[ALC889_FIXUP_DAC_ROUTE] = {
+		.type = ALC_FIXUP_FUNC,
+		.v.func = alc889_fixup_dac_route,
+	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0155, "Packard-Bell M5120", PINFIX_PB_M5210),
+	SND_PCI_QUIRK(0x1025, 0x0259, "Acer Aspire 5935", ALC889_FIXUP_DAC_ROUTE),
 	SND_PCI_QUIRK(0x1043, 0x1873, "ASUS W90V", PINFIX_ASUS_W90V),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", PINFIX_LENOVO_Y530),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", PINFIX_ABIT_AW9D_MAX),

sound/pci/hda/patch_via.c

@@ -665,6 +665,9 @@ static void via_auto_init_analog_input(struct hda_codec *codec)
 	/* init input-src */
 	for (i = 0; i < spec->num_adc_nids; i++) {
 		int adc_idx = spec->inputs[spec->cur_mux[i]].adc_idx;
+		/* secondary ADCs must have the unique MUX */
+		if (i > 0 && !spec->mux_nids[i])
+			break;
 		if (spec->mux_nids[adc_idx]) {
 			int mux_idx = spec->inputs[spec->cur_mux[i]].mux_idx;
 			snd_hda_codec_write(codec, spec->mux_nids[adc_idx], 0,

sound/pci/intel8x0.c

@@ -2100,6 +2100,12 @@ 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,

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

tools/perf/util/evsel.c

@@ -390,6 +390,7 @@ 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)