diff --git a/arch/um/kernel/exitcode.c b/arch/um/kernel/exitcode.c
index 829df49..41ebbfe 100644
--- a/arch/um/kernel/exitcode.c
+++ b/arch/um/kernel/exitcode.c
@@ -40,9 +40,11 @@
 		const char __user *buffer, size_t count, loff_t *pos)
 {
 	char *end, buf[sizeof("nnnnn\0")];
+	size_t size;
 	int tmp;
 
-	if (copy_from_user(buf, buffer, count))
+	size = min(count, sizeof(buf));
+	if (copy_from_user(buf, buffer, size))
 		return -EFAULT;
 
 	tmp = simple_strtol(buf, &end, 0);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0da5200..b3e18f8 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -128,7 +128,8 @@
 do {									\
 	typedef typeof(var) pao_T__;					\
 	const int pao_ID__ = (__builtin_constant_p(val) &&		\
-			      ((val) == 1 || (val) == -1)) ? (val) : 0;	\
+			      ((val) == 1 || (val) == -1)) ?		\
+				(int)(val) : 0;				\
 	if (0) {							\
 		pao_T__ pao_tmp__;					\
 		pao_tmp__ = (val);					\
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a0e2a8a..b2046e4 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -609,7 +609,7 @@
 
 struct dentry *kvm_init_debugfs(void)
 {
-	d_kvm_debug = debugfs_create_dir("kvm", NULL);
+	d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
 	if (!d_kvm_debug)
 		printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n");
 
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index de1dfa1..21dbe6b 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1122,7 +1122,7 @@
  * a3: exctable, original value in excsave1
  */
 
-fast_syscall_spill_registers_fixup:
+ENTRY(fast_syscall_spill_registers_fixup)
 
 	rsr	a2, windowbase	# get current windowbase (a2 is saved)
 	xsr	a0, depc	# restore depc and a0
@@ -1134,22 +1134,26 @@
 	 */
 
 	xsr	a3, excsave1	# get spill-mask
-	slli	a2, a3, 1	# shift left by one
+	slli	a3, a3, 1	# shift left by one
 
-	slli	a3, a2, 32-WSBITS
-	src	a2, a2, a3	# a1 = xxwww1yyxxxwww1yy......
+	slli	a2, a3, 32-WSBITS
+	src	a2, a3, a2	# a2 = xxwww1yyxxxwww1yy......
 	wsr	a2, windowstart	# set corrected windowstart
 
-	rsr	a3, excsave1
-	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE	# restore a2
-	l32i	a3, a3, EXC_TABLE_PARAM	# original WB (in user task)
+	srli	a3, a3, 1
+	rsr	a2, excsave1
+	l32i	a2, a2, EXC_TABLE_DOUBLE_SAVE	# restore a2
+	xsr	a2, excsave1
+	s32i	a3, a2, EXC_TABLE_DOUBLE_SAVE	# save a3
+	l32i	a3, a2, EXC_TABLE_PARAM	# original WB (in user task)
+	xsr	a2, excsave1
 
 	/* Return to the original (user task) WINDOWBASE.
 	 * We leave the following frame behind:
 	 * a0, a1, a2	same
-	 * a3:		trashed (saved in excsave_1)
+	 * a3:		trashed (saved in EXC_TABLE_DOUBLE_SAVE)
 	 * depc:	depc (we have to return to that address)
-	 * excsave_1:	a3
+	 * excsave_1:	exctable
 	 */
 
 	wsr	a3, windowbase
@@ -1159,9 +1163,9 @@
 	 *  a0: return address
 	 *  a1: used, stack pointer
 	 *  a2: kernel stack pointer
-	 *  a3: available, saved in EXCSAVE_1
+	 *  a3: available
 	 *  depc: exception address
-	 *  excsave: a3
+	 *  excsave: exctable
 	 * Note: This frame might be the same as above.
 	 */
 
@@ -1181,9 +1185,12 @@
 	rsr	a0, exccause
 	addx4	a0, a0, a3              	# find entry in table
 	l32i	a0, a0, EXC_TABLE_FAST_USER     # load handler
+	l32i	a3, a3, EXC_TABLE_DOUBLE_SAVE
 	jx	a0
 
-fast_syscall_spill_registers_fixup_return:
+ENDPROC(fast_syscall_spill_registers_fixup)
+
+ENTRY(fast_syscall_spill_registers_fixup_return)
 
 	/* When we return here, all registers have been restored (a2: DEPC) */
 
@@ -1191,13 +1198,13 @@
 
 	/* Restore fixup handler. */
 
-	xsr	a3, excsave1
-	movi	a2, fast_syscall_spill_registers_fixup
-	s32i	a2, a3, EXC_TABLE_FIXUP
-	s32i	a0, a3, EXC_TABLE_DOUBLE_SAVE
-	rsr	a2, windowbase
-	s32i	a2, a3, EXC_TABLE_PARAM
-	l32i	a2, a3, EXC_TABLE_KSTK
+	rsr	a2, excsave1
+	s32i	a3, a2, EXC_TABLE_DOUBLE_SAVE
+	movi	a3, fast_syscall_spill_registers_fixup
+	s32i	a3, a2, EXC_TABLE_FIXUP
+	rsr	a3, windowbase
+	s32i	a3, a2, EXC_TABLE_PARAM
+	l32i	a2, a2, EXC_TABLE_KSTK
 
 	/* Load WB at the time the exception occurred. */
 
@@ -1206,8 +1213,12 @@
 	wsr	a3, windowbase
 	rsync
 
+	rsr	a3, excsave1
+	l32i	a3, a3, EXC_TABLE_DOUBLE_SAVE
+
 	rfde
 
+ENDPROC(fast_syscall_spill_registers_fixup_return)
 
 /*
  * spill all registers.
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 718eca1..98b67d5 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -341,7 +341,7 @@
 
 	sp = regs->areg[1];
 
-	if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && ! on_sig_stack(sp)) {
+	if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && sas_ss_flags(sp) == 0) {
 		sp = current->sas_ss_sp + current->sas_ss_size;
 	}
 
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 56f88b7..e9e1aad 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -737,7 +737,8 @@
 		return 1;
 	}
 
-	if ((new = alloc_bootmem(sizeof new)) == NULL) {
+	new = alloc_bootmem(sizeof(*new));
+	if (new == NULL) {
 		printk("Alloc_bootmem failed\n");
 		return 1;
 	}
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index 51410c2..4d978a3 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -27,6 +27,14 @@
  */
 
 #define SRC_CR			0x00U
+#define SRC_CR_T0_ENSEL		BIT(15)
+#define SRC_CR_T1_ENSEL		BIT(17)
+#define SRC_CR_T2_ENSEL		BIT(19)
+#define SRC_CR_T3_ENSEL		BIT(21)
+#define SRC_CR_T4_ENSEL		BIT(23)
+#define SRC_CR_T5_ENSEL		BIT(25)
+#define SRC_CR_T6_ENSEL		BIT(27)
+#define SRC_CR_T7_ENSEL		BIT(29)
 #define SRC_XTALCR		0x0CU
 #define SRC_XTALCR_XTALTIMEN	BIT(20)
 #define SRC_XTALCR_SXTALDIS	BIT(19)
@@ -543,6 +551,19 @@
 		       __func__, np->name);
 		return;
 	}
+
+	/* Set all timers to use the 2.4 MHz TIMCLK */
+	val = readl(src_base + SRC_CR);
+	val |= SRC_CR_T0_ENSEL;
+	val |= SRC_CR_T1_ENSEL;
+	val |= SRC_CR_T2_ENSEL;
+	val |= SRC_CR_T3_ENSEL;
+	val |= SRC_CR_T4_ENSEL;
+	val |= SRC_CR_T5_ENSEL;
+	val |= SRC_CR_T6_ENSEL;
+	val |= SRC_CR_T7_ENSEL;
+	writel(val, src_base + SRC_CR);
+
 	val = readl(src_base + SRC_XTALCR);
 	pr_info("SXTALO is %s\n",
 		(val & SRC_XTALCR_SXTALDIS) ? "disabled" : "enabled");
diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c
index fc777bd..81a202d 100644
--- a/drivers/clk/mvebu/armada-370.c
+++ b/drivers/clk/mvebu/armada-370.c
@@ -39,8 +39,8 @@
 };
 
 static const u32 a370_tclk_freqs[] __initconst = {
-	16600000,
-	20000000,
+	166000000,
+	200000000,
 };
 
 static u32 __init a370_get_tclk_freq(void __iomem *sar)
diff --git a/drivers/clk/socfpga/clk.c b/drivers/clk/socfpga/clk.c
index 5bb848c..81dd31a 100644
--- a/drivers/clk/socfpga/clk.c
+++ b/drivers/clk/socfpga/clk.c
@@ -49,7 +49,7 @@
 #define SOCFPGA_L4_SP_CLK		"l4_sp_clk"
 #define SOCFPGA_NAND_CLK		"nand_clk"
 #define SOCFPGA_NAND_X_CLK		"nand_x_clk"
-#define SOCFPGA_MMC_CLK			"mmc_clk"
+#define SOCFPGA_MMC_CLK			"sdmmc_clk"
 #define SOCFPGA_DB_CLK			"gpio_db_clk"
 
 #define div_mask(width)	((1 << (width)) - 1)
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index 67ccf4a..f5e4c21 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -107,7 +107,7 @@
 
 	vco = icst_hz_to_vco(icst->params, rate);
 	icst->rate = icst_hz(icst->params, vco);
-	vco_set(icst->vcoreg, icst->lockreg, vco);
+	vco_set(icst->lockreg, icst->vcoreg, vco);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 05ad9ba..fe58d08 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -61,7 +61,7 @@
 
 /** Ioctl table */
 static const struct drm_ioctl_desc drm_ioctls[] = {
-	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index ea9022e..10d1de5 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -83,8 +83,7 @@
 	return true;
 }
 
-static void intel_crt_get_config(struct intel_encoder *encoder,
-				 struct intel_crtc_config *pipe_config)
+static unsigned int intel_crt_get_flags(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
@@ -102,7 +101,25 @@
 	else
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
-	pipe_config->adjusted_mode.flags |= flags;
+	return flags;
+}
+
+static void intel_crt_get_config(struct intel_encoder *encoder,
+				 struct intel_crtc_config *pipe_config)
+{
+	pipe_config->adjusted_mode.flags |= intel_crt_get_flags(encoder);
+}
+
+static void hsw_crt_get_config(struct intel_encoder *encoder,
+			       struct intel_crtc_config *pipe_config)
+{
+	intel_ddi_get_config(encoder, pipe_config);
+
+	pipe_config->adjusted_mode.flags &= ~(DRM_MODE_FLAG_PHSYNC |
+					      DRM_MODE_FLAG_NHSYNC |
+					      DRM_MODE_FLAG_PVSYNC |
+					      DRM_MODE_FLAG_NVSYNC);
+	pipe_config->adjusted_mode.flags |= intel_crt_get_flags(encoder);
 }
 
 /* Note: The caller is required to filter out dpms modes not supported by the
@@ -799,7 +816,10 @@
 	crt->base.mode_set = intel_crt_mode_set;
 	crt->base.disable = intel_disable_crt;
 	crt->base.enable = intel_enable_crt;
-	crt->base.get_config = intel_crt_get_config;
+	if (IS_HASWELL(dev))
+		crt->base.get_config = hsw_crt_get_config;
+	else
+		crt->base.get_config = intel_crt_get_config;
 	if (I915_HAS_HOTPLUG(dev))
 		crt->base.hpd_pin = HPD_CRT;
 	if (HAS_DDI(dev))
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 63de270..b53fff8 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1249,8 +1249,8 @@
 		intel_dp_check_link_status(intel_dp);
 }
 
-static void intel_ddi_get_config(struct intel_encoder *encoder,
-				 struct intel_crtc_config *pipe_config)
+void intel_ddi_get_config(struct intel_encoder *encoder,
+			  struct intel_crtc_config *pipe_config)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
@@ -1268,6 +1268,23 @@
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
 	pipe_config->adjusted_mode.flags |= flags;
+
+	switch (temp & TRANS_DDI_BPC_MASK) {
+	case TRANS_DDI_BPC_6:
+		pipe_config->pipe_bpp = 18;
+		break;
+	case TRANS_DDI_BPC_8:
+		pipe_config->pipe_bpp = 24;
+		break;
+	case TRANS_DDI_BPC_10:
+		pipe_config->pipe_bpp = 30;
+		break;
+	case TRANS_DDI_BPC_12:
+		pipe_config->pipe_bpp = 36;
+		break;
+	default:
+		break;
+	}
 }
 
 static void intel_ddi_destroy(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 581fb4b..d78d33f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2327,9 +2327,10 @@
 			   FDI_FE_ERRC_ENABLE);
 }
 
-static bool pipe_has_enabled_pch(struct intel_crtc *intel_crtc)
+static bool pipe_has_enabled_pch(struct intel_crtc *crtc)
 {
-	return intel_crtc->base.enabled && intel_crtc->config.has_pch_encoder;
+	return crtc->base.enabled && crtc->active &&
+		crtc->config.has_pch_encoder;
 }
 
 static void ivb_modeset_global_resources(struct drm_device *dev)
@@ -2979,6 +2980,48 @@
 		   I915_READ(VSYNCSHIFT(cpu_transcoder)));
 }
 
+static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t temp;
+
+	temp = I915_READ(SOUTH_CHICKEN1);
+	if (temp & FDI_BC_BIFURCATION_SELECT)
+		return;
+
+	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE);
+	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE);
+
+	temp |= FDI_BC_BIFURCATION_SELECT;
+	DRM_DEBUG_KMS("enabling fdi C rx\n");
+	I915_WRITE(SOUTH_CHICKEN1, temp);
+	POSTING_READ(SOUTH_CHICKEN1);
+}
+
+static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc)
+{
+	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	switch (intel_crtc->pipe) {
+	case PIPE_A:
+		break;
+	case PIPE_B:
+		if (intel_crtc->config.fdi_lanes > 2)
+			WARN_ON(I915_READ(SOUTH_CHICKEN1) & FDI_BC_BIFURCATION_SELECT);
+		else
+			cpt_enable_fdi_bc_bifurcation(dev);
+
+		break;
+	case PIPE_C:
+		cpt_enable_fdi_bc_bifurcation(dev);
+
+		break;
+	default:
+		BUG();
+	}
+}
+
 /*
  * Enable PCH resources required for PCH ports:
  *   - PCH PLLs
@@ -2997,6 +3040,9 @@
 
 	assert_pch_transcoder_disabled(dev_priv, pipe);
 
+	if (IS_IVYBRIDGE(dev))
+		ivybridge_update_fdi_bc_bifurcation(intel_crtc);
+
 	/* Write the TU size bits before fdi link training, so that error
 	 * detection works. */
 	I915_WRITE(FDI_RX_TUSIZE1(pipe),
@@ -4983,6 +5029,22 @@
 	if (!(tmp & PIPECONF_ENABLE))
 		return false;
 
+	if (IS_G4X(dev) || IS_VALLEYVIEW(dev)) {
+		switch (tmp & PIPECONF_BPC_MASK) {
+		case PIPECONF_6BPC:
+			pipe_config->pipe_bpp = 18;
+			break;
+		case PIPECONF_8BPC:
+			pipe_config->pipe_bpp = 24;
+			break;
+		case PIPECONF_10BPC:
+			pipe_config->pipe_bpp = 30;
+			break;
+		default:
+			break;
+		}
+	}
+
 	intel_get_pipe_timings(crtc, pipe_config);
 
 	i9xx_get_pfit_config(crtc, pipe_config);
@@ -5576,48 +5638,6 @@
 	return true;
 }
 
-static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t temp;
-
-	temp = I915_READ(SOUTH_CHICKEN1);
-	if (temp & FDI_BC_BIFURCATION_SELECT)
-		return;
-
-	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE);
-	WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE);
-
-	temp |= FDI_BC_BIFURCATION_SELECT;
-	DRM_DEBUG_KMS("enabling fdi C rx\n");
-	I915_WRITE(SOUTH_CHICKEN1, temp);
-	POSTING_READ(SOUTH_CHICKEN1);
-}
-
-static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc)
-{
-	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	switch (intel_crtc->pipe) {
-	case PIPE_A:
-		break;
-	case PIPE_B:
-		if (intel_crtc->config.fdi_lanes > 2)
-			WARN_ON(I915_READ(SOUTH_CHICKEN1) & FDI_BC_BIFURCATION_SELECT);
-		else
-			cpt_enable_fdi_bc_bifurcation(dev);
-
-		break;
-	case PIPE_C:
-		cpt_enable_fdi_bc_bifurcation(dev);
-
-		break;
-	default:
-		BUG();
-	}
-}
-
 int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp)
 {
 	/*
@@ -5811,9 +5831,6 @@
 					     &intel_crtc->config.fdi_m_n);
 	}
 
-	if (IS_IVYBRIDGE(dev))
-		ivybridge_update_fdi_bc_bifurcation(intel_crtc);
-
 	ironlake_set_pipeconf(crtc);
 
 	/* Set up the display plane register */
@@ -5881,6 +5898,23 @@
 	if (!(tmp & PIPECONF_ENABLE))
 		return false;
 
+	switch (tmp & PIPECONF_BPC_MASK) {
+	case PIPECONF_6BPC:
+		pipe_config->pipe_bpp = 18;
+		break;
+	case PIPECONF_8BPC:
+		pipe_config->pipe_bpp = 24;
+		break;
+	case PIPECONF_10BPC:
+		pipe_config->pipe_bpp = 30;
+		break;
+	case PIPECONF_12BPC:
+		pipe_config->pipe_bpp = 36;
+		break;
+	default:
+		break;
+	}
+
 	if (I915_READ(PCH_TRANSCONF(crtc->pipe)) & TRANS_ENABLE) {
 		struct intel_shared_dpll *pll;
 
@@ -8612,6 +8646,9 @@
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp0);
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp1);
 
+	if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5)
+		PIPE_CONF_CHECK_I(pipe_bpp);
+
 #undef PIPE_CONF_CHECK_X
 #undef PIPE_CONF_CHECK_I
 #undef PIPE_CONF_CHECK_FLAGS
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2c555f9..1a43137 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1401,6 +1401,26 @@
 		else
 			pipe_config->port_clock = 270000;
 	}
+
+	if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp &&
+	    pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) {
+		/*
+		 * This is a big fat ugly hack.
+		 *
+		 * Some machines in UEFI boot mode provide us a VBT that has 18
+		 * bpp and 1.62 GHz link bandwidth for eDP, which for reasons
+		 * unknown we fail to light up. Yet the same BIOS boots up with
+		 * 24 bpp and 2.7 GHz link. Use the same bpp as the BIOS uses as
+		 * max, not what it tells us to use.
+		 *
+		 * Note: This will still be broken if the eDP panel is not lit
+		 * up by the BIOS, and thus we can't get the mode at module
+		 * load.
+		 */
+		DRM_DEBUG_KMS("pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n",
+			      pipe_config->pipe_bpp, dev_priv->vbt.edp_bpp);
+		dev_priv->vbt.edp_bpp = pipe_config->pipe_bpp;
+	}
 }
 
 static bool is_edp_psr(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9b7b68f..7f2b384 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -765,6 +765,8 @@
 extern bool
 intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector);
 extern void intel_ddi_fdi_disable(struct drm_crtc *crtc);
+extern void intel_ddi_get_config(struct intel_encoder *encoder,
+				 struct intel_crtc_config *pipe_config);
 
 extern void intel_display_handle_reset(struct drm_device *dev);
 extern bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 831a5c0..b8af94a 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -700,6 +700,22 @@
 	},
 	{
 		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Intel D410PT",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+			DMI_MATCH(DMI_BOARD_NAME, "D410PT"),
+		},
+	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Intel D425KT",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "D425KT"),
+		},
+	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
 		.ident = "Intel D510MO",
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index fe1de85..57fcc4b 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -291,6 +291,7 @@
 	/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
 
 	WREG32(HDMI_ACR_PACKET_CONTROL + offset,
+	       HDMI_ACR_SOURCE | /* select SW CTS value */
 	       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	evergreen_hdmi_update_ACR(encoder, mode->clock);
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 7139906..b419055 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2635,7 +2635,7 @@
 	pi->caps_sclk_ds = true;
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
-	pi->bapm_enable = true;
+	pi->bapm_enable = false;
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a400ac1..24f4960 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1272,8 +1272,8 @@
 struct radeon_clock_and_voltage_limits {
 	u32 sclk;
 	u32 mclk;
-	u32 vddc;
-	u32 vddci;
+	u16 vddc;
+	u16 vddci;
 };
 
 struct radeon_clock_array {
diff --git a/drivers/input/input.c b/drivers/input/input.c
index c044699..e75d015 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1734,6 +1734,7 @@
  */
 struct input_dev *input_allocate_device(void)
 {
+	static atomic_t input_no = ATOMIC_INIT(0);
 	struct input_dev *dev;
 
 	dev = kzalloc(sizeof(struct input_dev), GFP_KERNEL);
@@ -1743,9 +1744,13 @@
 		device_initialize(&dev->dev);
 		mutex_init(&dev->mutex);
 		spin_lock_init(&dev->event_lock);
+		init_timer(&dev->timer);
 		INIT_LIST_HEAD(&dev->h_list);
 		INIT_LIST_HEAD(&dev->node);
 
+		dev_set_name(&dev->dev, "input%ld",
+			     (unsigned long) atomic_inc_return(&input_no) - 1);
+
 		__module_get(THIS_MODULE);
 	}
 
@@ -2019,7 +2024,6 @@
  */
 int input_register_device(struct input_dev *dev)
 {
-	static atomic_t input_no = ATOMIC_INIT(0);
 	struct input_devres *devres = NULL;
 	struct input_handler *handler;
 	unsigned int packet_size;
@@ -2059,7 +2063,6 @@
 	 * If delay and period are pre-set by the driver, then autorepeating
 	 * is handled by the driver itself and we don't do it in input.c.
 	 */
-	init_timer(&dev->timer);
 	if (!dev->rep[REP_DELAY] && !dev->rep[REP_PERIOD]) {
 		dev->timer.data = (long) dev;
 		dev->timer.function = input_repeat_key;
@@ -2073,9 +2076,6 @@
 	if (!dev->setkeycode)
 		dev->setkeycode = input_default_setkeycode;
 
-	dev_set_name(&dev->dev, "input%ld",
-		     (unsigned long) atomic_inc_return(&input_no) - 1);
-
 	error = device_add(&dev->dev);
 	if (error)
 		goto err_free_vals;
diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c
index 134c3b4..a2e758d 100644
--- a/drivers/input/keyboard/pxa27x_keypad.c
+++ b/drivers/input/keyboard/pxa27x_keypad.c
@@ -786,10 +786,17 @@
 	input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP);
 	input_set_capability(input_dev, EV_MSC, MSC_SCAN);
 
-	if (pdata)
+	if (pdata) {
 		error = pxa27x_keypad_build_keycode(keypad);
-	else
+	} else {
 		error = pxa27x_keypad_build_keycode_from_dt(keypad);
+		/*
+		 * Data that we get from DT resides in dynamically
+		 * allocated memory so we need to update our pdata
+		 * pointer.
+		 */
+		pdata = keypad->pdata;
+	}
 	if (error) {
 		dev_err(&pdev->dev, "failed to build keycode\n");
 		goto failed_put_clk;
diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c
index 082684e..9365535 100644
--- a/drivers/input/misc/cm109.c
+++ b/drivers/input/misc/cm109.c
@@ -351,7 +351,9 @@
 	if (status) {
 		if (status == -ESHUTDOWN)
 			return;
-		dev_err(&dev->intf->dev, "%s: urb status %d\n", __func__, status);
+		dev_err_ratelimited(&dev->intf->dev, "%s: urb status %d\n",
+				    __func__, status);
+		goto out;
 	}
 
 	/* Special keys */
@@ -418,8 +420,12 @@
 	     dev->ctl_data->byte[2],
 	     dev->ctl_data->byte[3]);
 
-	if (status)
-		dev_err(&dev->intf->dev, "%s: urb status %d\n", __func__, status);
+	if (status) {
+		if (status == -ESHUTDOWN)
+			return;
+		dev_err_ratelimited(&dev->intf->dev, "%s: urb status %d\n",
+				    __func__, status);
+	}
 
 	spin_lock(&dev->ctl_submit_lock);
 
@@ -427,7 +433,7 @@
 
 	if (likely(!dev->shutdown)) {
 
-		if (dev->buzzer_pending) {
+		if (dev->buzzer_pending || status) {
 			dev->buzzer_pending = 0;
 			dev->ctl_urb_pending = 1;
 			cm109_submit_buzz_toggle(dev);
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 7c5d72a..8365847 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -103,6 +103,7 @@
 	/* Dell Latitude E5500, E6400, E6500, Precision M4400 */
 	{ { 0x62, 0x02, 0x14 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf,
 		ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED },
+	{ { 0x73, 0x00, 0x14 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf, ALPS_DUALPOINT },		/* Dell XT2 */
 	{ { 0x73, 0x02, 0x50 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf, ALPS_FOUR_BUTTONS },		/* Dell Vostro 1400 */
 	{ { 0x52, 0x01, 0x14 }, 0x00, ALPS_PROTO_V2, 0xff, 0xff,
 		ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED },				/* Toshiba Tecra A11-11L */
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 78e4de4..52c9ebf 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -223,21 +223,26 @@
 {
 	unsigned long flags;
 	unsigned char data, str;
-	int i = 0;
+	int count = 0;
+	int retval = 0;
 
 	spin_lock_irqsave(&i8042_lock, flags);
 
-	while (((str = i8042_read_status()) & I8042_STR_OBF) && (i < I8042_BUFFER_SIZE)) {
-		udelay(50);
-		data = i8042_read_data();
-		i++;
-		dbg("%02x <- i8042 (flush, %s)\n",
-		    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
+	while ((str = i8042_read_status()) & I8042_STR_OBF) {
+		if (count++ < I8042_BUFFER_SIZE) {
+			udelay(50);
+			data = i8042_read_data();
+			dbg("%02x <- i8042 (flush, %s)\n",
+			    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
+		} else {
+			retval = -EIO;
+			break;
+		}
 	}
 
 	spin_unlock_irqrestore(&i8042_lock, flags);
 
-	return i;
+	return retval;
 }
 
 /*
@@ -849,7 +854,7 @@
 
 static int i8042_controller_check(void)
 {
-	if (i8042_flush() == I8042_BUFFER_SIZE) {
+	if (i8042_flush()) {
 		pr_err("No controller found\n");
 		return -ENODEV;
 	}
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index 79b69ea..e53416a 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -1031,6 +1031,7 @@
 }
 
 static enum power_supply_property wacom_battery_props[] = {
+	POWER_SUPPLY_PROP_SCOPE,
 	POWER_SUPPLY_PROP_CAPACITY
 };
 
@@ -1042,6 +1043,9 @@
 	int ret = 0;
 
 	switch (psp) {
+		case POWER_SUPPLY_PROP_SCOPE:
+			val->intval = POWER_SUPPLY_SCOPE_DEVICE;
+			break;
 		case POWER_SUPPLY_PROP_CAPACITY:
 			val->intval =
 				wacom->wacom_wac.battery_capacity * 100 / 31;
diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c
index b2aa503..c59b797 100644
--- a/drivers/input/tablet/wacom_wac.c
+++ b/drivers/input/tablet/wacom_wac.c
@@ -2054,6 +2054,12 @@
 static const struct wacom_features wacom_features_0x10D =
 	{ "Wacom ISDv4 10D",      WACOM_PKGLEN_MTTPC,     26202, 16325,  255,
 	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x10E =
+	{ "Wacom ISDv4 10E",      WACOM_PKGLEN_MTTPC,     27760, 15694,  255,
+	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x10F =
+	{ "Wacom ISDv4 10F",      WACOM_PKGLEN_MTTPC,     27760, 15694,  255,
+	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x4001 =
 	{ "Wacom ISDv4 4001",      WACOM_PKGLEN_MTTPC,     26202, 16325,  255,
 	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
@@ -2248,6 +2254,8 @@
 	{ USB_DEVICE_WACOM(0x100) },
 	{ USB_DEVICE_WACOM(0x101) },
 	{ USB_DEVICE_WACOM(0x10D) },
+	{ USB_DEVICE_WACOM(0x10E) },
+	{ USB_DEVICE_WACOM(0x10F) },
 	{ USB_DEVICE_WACOM(0x300) },
 	{ USB_DEVICE_WACOM(0x301) },
 	{ USB_DEVICE_WACOM(0x304) },
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index be12fbf..1ea7523 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -552,9 +552,8 @@
 	struct acpiphp_func *func;
 	int max, pass;
 	LIST_HEAD(add_list);
-	int nr_found;
 
-	nr_found = acpiphp_rescan_slot(slot);
+	acpiphp_rescan_slot(slot);
 	max = acpiphp_max_busnr(bus);
 	for (pass = 0; pass < 2; pass++) {
 		list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -574,9 +573,6 @@
 		}
 	}
 	__pci_bus_assign_resources(bus, &add_list, NULL);
-	/* Nothing more to do here if there are no new devices on this bus. */
-	if (!nr_found && (slot->flags & SLOT_ENABLED))
-		return;
 
 	acpiphp_sanitize_bus(bus);
 	acpiphp_set_hpp_values(bus);
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 408a42e..f0d432c1 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -771,6 +771,8 @@
 static int aac_compat_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	struct aac_dev *dev = (struct aac_dev *)sdev->host->hostdata;
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
 	return aac_compat_do_ioctl(dev, cmd, (unsigned long)arg);
 }
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 5cbc4bb..df5e961 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -105,8 +105,11 @@
 static int sg_add(struct device *, struct class_interface *);
 static void sg_remove(struct device *, struct class_interface *);
 
+static DEFINE_SPINLOCK(sg_open_exclusive_lock);
+
 static DEFINE_IDR(sg_index_idr);
-static DEFINE_RWLOCK(sg_index_lock);
+static DEFINE_RWLOCK(sg_index_lock);	/* Also used to lock
+							   file descriptor list for device */
 
 static struct class_interface sg_interface = {
 	.add_dev	= sg_add,
@@ -143,7 +146,8 @@
 } Sg_request;
 
 typedef struct sg_fd {		/* holds the state of a file descriptor */
-	struct list_head sfd_siblings; /* protected by sfd_lock of device */
+	/* sfd_siblings is protected by sg_index_lock */
+	struct list_head sfd_siblings;
 	struct sg_device *parentdp;	/* owning device */
 	wait_queue_head_t read_wait;	/* queue read until command done */
 	rwlock_t rq_list_lock;	/* protect access to list in req_arr */
@@ -166,12 +170,13 @@
 
 typedef struct sg_device { /* holds the state of each scsi generic device */
 	struct scsi_device *device;
+	wait_queue_head_t o_excl_wait;	/* queue open() when O_EXCL in use */
 	int sg_tablesize;	/* adapter's max scatter-gather table size */
 	u32 index;		/* device index number */
-	spinlock_t sfd_lock;	/* protect file descriptor list for device */
+	/* sfds is protected by sg_index_lock */
 	struct list_head sfds;
-	struct rw_semaphore o_sem;	/* exclude open should hold this rwsem */
 	volatile char detached;	/* 0->attached, 1->detached pending removal */
+	/* exclude protected by sg_open_exclusive_lock */
 	char exclude;		/* opened for exclusive access */
 	char sgdebug;		/* 0->off, 1->sense, 9->dump dev, 10-> all devs */
 	struct gendisk *disk;
@@ -220,14 +225,35 @@
 	return blk_verify_command(cmd, filp->f_mode & FMODE_WRITE);
 }
 
+static int get_exclude(Sg_device *sdp)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&sg_open_exclusive_lock, flags);
+	ret = sdp->exclude;
+	spin_unlock_irqrestore(&sg_open_exclusive_lock, flags);
+	return ret;
+}
+
+static int set_exclude(Sg_device *sdp, char val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&sg_open_exclusive_lock, flags);
+	sdp->exclude = val;
+	spin_unlock_irqrestore(&sg_open_exclusive_lock, flags);
+	return val;
+}
+
 static int sfds_list_empty(Sg_device *sdp)
 {
 	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&sdp->sfd_lock, flags);
+	read_lock_irqsave(&sg_index_lock, flags);
 	ret = list_empty(&sdp->sfds);
-	spin_unlock_irqrestore(&sdp->sfd_lock, flags);
+	read_unlock_irqrestore(&sg_index_lock, flags);
 	return ret;
 }
 
@@ -239,6 +265,7 @@
 	struct request_queue *q;
 	Sg_device *sdp;
 	Sg_fd *sfp;
+	int res;
 	int retval;
 
 	nonseekable_open(inode, filp);
@@ -267,52 +294,54 @@
 		goto error_out;
 	}
 
-	if ((flags & O_EXCL) && (O_RDONLY == (flags & O_ACCMODE))) {
-		retval = -EPERM; /* Can't lock it with read only access */
+	if (flags & O_EXCL) {
+		if (O_RDONLY == (flags & O_ACCMODE)) {
+			retval = -EPERM; /* Can't lock it with read only access */
+			goto error_out;
+		}
+		if (!sfds_list_empty(sdp) && (flags & O_NONBLOCK)) {
+			retval = -EBUSY;
+			goto error_out;
+		}
+		res = wait_event_interruptible(sdp->o_excl_wait,
+					   ((!sfds_list_empty(sdp) || get_exclude(sdp)) ? 0 : set_exclude(sdp, 1)));
+		if (res) {
+			retval = res;	/* -ERESTARTSYS because signal hit process */
+			goto error_out;
+		}
+	} else if (get_exclude(sdp)) {	/* some other fd has an exclusive lock on dev */
+		if (flags & O_NONBLOCK) {
+			retval = -EBUSY;
+			goto error_out;
+		}
+		res = wait_event_interruptible(sdp->o_excl_wait, !get_exclude(sdp));
+		if (res) {
+			retval = res;	/* -ERESTARTSYS because signal hit process */
+			goto error_out;
+		}
+	}
+	if (sdp->detached) {
+		retval = -ENODEV;
 		goto error_out;
 	}
-	if (flags & O_NONBLOCK) {
-		if (flags & O_EXCL) {
-			if (!down_write_trylock(&sdp->o_sem)) {
-				retval = -EBUSY;
-				goto error_out;
-			}
-		} else {
-			if (!down_read_trylock(&sdp->o_sem)) {
-				retval = -EBUSY;
-				goto error_out;
-			}
-		}
-	} else {
-		if (flags & O_EXCL)
-			down_write(&sdp->o_sem);
-		else
-			down_read(&sdp->o_sem);
-	}
-	/* Since write lock is held, no need to check sfd_list */
-	if (flags & O_EXCL)
-		sdp->exclude = 1;	/* used by release lock */
-
 	if (sfds_list_empty(sdp)) {	/* no existing opens on this device */
 		sdp->sgdebug = 0;
 		q = sdp->device->request_queue;
 		sdp->sg_tablesize = queue_max_segments(q);
 	}
-	sfp = sg_add_sfp(sdp, dev);
-	if (!IS_ERR(sfp))
+	if ((sfp = sg_add_sfp(sdp, dev)))
 		filp->private_data = sfp;
-		/* retval is already provably zero at this point because of the
-		 * check after retval = scsi_autopm_get_device(sdp->device))
-		 */
 	else {
-		retval = PTR_ERR(sfp);
-
 		if (flags & O_EXCL) {
-			sdp->exclude = 0;	/* undo if error */
-			up_write(&sdp->o_sem);
-		} else
-			up_read(&sdp->o_sem);
+			set_exclude(sdp, 0);	/* undo if error */
+			wake_up_interruptible(&sdp->o_excl_wait);
+		}
+		retval = -ENOMEM;
+		goto error_out;
+	}
+	retval = 0;
 error_out:
+	if (retval) {
 		scsi_autopm_put_device(sdp->device);
 sdp_put:
 		scsi_device_put(sdp->device);
@@ -329,18 +358,13 @@
 {
 	Sg_device *sdp;
 	Sg_fd *sfp;
-	int excl;
 
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
 	SCSI_LOG_TIMEOUT(3, printk("sg_release: %s\n", sdp->disk->disk_name));
 
-	excl = sdp->exclude;
-	sdp->exclude = 0;
-	if (excl)
-		up_write(&sdp->o_sem);
-	else
-		up_read(&sdp->o_sem);
+	set_exclude(sdp, 0);
+	wake_up_interruptible(&sdp->o_excl_wait);
 
 	scsi_autopm_put_device(sdp->device);
 	kref_put(&sfp->f_ref, sg_remove_sfp);
@@ -1391,9 +1415,8 @@
 	disk->first_minor = k;
 	sdp->disk = disk;
 	sdp->device = scsidp;
-	spin_lock_init(&sdp->sfd_lock);
 	INIT_LIST_HEAD(&sdp->sfds);
-	init_rwsem(&sdp->o_sem);
+	init_waitqueue_head(&sdp->o_excl_wait);
 	sdp->sg_tablesize = queue_max_segments(q);
 	sdp->index = k;
 	kref_init(&sdp->d_ref);
@@ -1526,13 +1549,11 @@
 
 	/* Need a write lock to set sdp->detached. */
 	write_lock_irqsave(&sg_index_lock, iflags);
-	spin_lock(&sdp->sfd_lock);
 	sdp->detached = 1;
 	list_for_each_entry(sfp, &sdp->sfds, sfd_siblings) {
 		wake_up_interruptible(&sfp->read_wait);
 		kill_fasync(&sfp->async_qp, SIGPOLL, POLL_HUP);
 	}
-	spin_unlock(&sdp->sfd_lock);
 	write_unlock_irqrestore(&sg_index_lock, iflags);
 
 	sysfs_remove_link(&scsidp->sdev_gendev.kobj, "generic");
@@ -2043,7 +2064,7 @@
 
 	sfp = kzalloc(sizeof(*sfp), GFP_ATOMIC | __GFP_NOWARN);
 	if (!sfp)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	init_waitqueue_head(&sfp->read_wait);
 	rwlock_init(&sfp->rq_list_lock);
@@ -2057,13 +2078,9 @@
 	sfp->cmd_q = SG_DEF_COMMAND_Q;
 	sfp->keep_orphan = SG_DEF_KEEP_ORPHAN;
 	sfp->parentdp = sdp;
-	spin_lock_irqsave(&sdp->sfd_lock, iflags);
-	if (sdp->detached) {
-		spin_unlock_irqrestore(&sdp->sfd_lock, iflags);
-		return ERR_PTR(-ENODEV);
-	}
+	write_lock_irqsave(&sg_index_lock, iflags);
 	list_add_tail(&sfp->sfd_siblings, &sdp->sfds);
-	spin_unlock_irqrestore(&sdp->sfd_lock, iflags);
+	write_unlock_irqrestore(&sg_index_lock, iflags);
 	SCSI_LOG_TIMEOUT(3, printk("sg_add_sfp: sfp=0x%p\n", sfp));
 	if (unlikely(sg_big_buff != def_reserved_size))
 		sg_big_buff = def_reserved_size;
@@ -2113,9 +2130,10 @@
 	struct sg_device *sdp = sfp->parentdp;
 	unsigned long iflags;
 
-	spin_lock_irqsave(&sdp->sfd_lock, iflags);
+	write_lock_irqsave(&sg_index_lock, iflags);
 	list_del(&sfp->sfd_siblings);
-	spin_unlock_irqrestore(&sdp->sfd_lock, iflags);
+	write_unlock_irqrestore(&sg_index_lock, iflags);
+	wake_up_interruptible(&sdp->o_excl_wait);
 
 	INIT_WORK(&sfp->ew.work, sg_remove_sfp_usercontext);
 	schedule_work(&sfp->ew.work);
@@ -2502,7 +2520,7 @@
 	return 0;
 }
 
-/* must be called while holding sg_index_lock and sfd_lock */
+/* must be called while holding sg_index_lock */
 static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
 {
 	int k, m, new_interface, blen, usg;
@@ -2587,26 +2605,22 @@
 
 	read_lock_irqsave(&sg_index_lock, iflags);
 	sdp = it ? sg_lookup_dev(it->index) : NULL;
-	if (sdp) {
-		spin_lock(&sdp->sfd_lock);
-		if (!list_empty(&sdp->sfds)) {
-			struct scsi_device *scsidp = sdp->device;
+	if (sdp && !list_empty(&sdp->sfds)) {
+		struct scsi_device *scsidp = sdp->device;
 
-			seq_printf(s, " >>> device=%s ", sdp->disk->disk_name);
-			if (sdp->detached)
-				seq_printf(s, "detached pending close ");
-			else
-				seq_printf
-				    (s, "scsi%d chan=%d id=%d lun=%d   em=%d",
-				     scsidp->host->host_no,
-				     scsidp->channel, scsidp->id,
-				     scsidp->lun,
-				     scsidp->host->hostt->emulated);
-			seq_printf(s, " sg_tablesize=%d excl=%d\n",
-				   sdp->sg_tablesize, sdp->exclude);
-			sg_proc_debug_helper(s, sdp);
-		}
-		spin_unlock(&sdp->sfd_lock);
+		seq_printf(s, " >>> device=%s ", sdp->disk->disk_name);
+		if (sdp->detached)
+			seq_printf(s, "detached pending close ");
+		else
+			seq_printf
+			    (s, "scsi%d chan=%d id=%d lun=%d   em=%d",
+			     scsidp->host->host_no,
+			     scsidp->channel, scsidp->id,
+			     scsidp->lun,
+			     scsidp->host->hostt->emulated);
+		seq_printf(s, " sg_tablesize=%d excl=%d\n",
+			   sdp->sg_tablesize, get_exclude(sdp));
+		sg_proc_debug_helper(s, sdp);
 	}
 	read_unlock_irqrestore(&sg_index_lock, iflags);
 	return 0;
diff --git a/drivers/staging/bcm/Bcmchar.c b/drivers/staging/bcm/Bcmchar.c
index f91bc1f..639ba96 100644
--- a/drivers/staging/bcm/Bcmchar.c
+++ b/drivers/staging/bcm/Bcmchar.c
@@ -1960,6 +1960,7 @@
 
 		BCM_DEBUG_PRINT(Adapter, DBG_TYPE_OTHERS, OSAL_DBG, DBG_LVL_ALL, "Called IOCTL_BCM_GET_DEVICE_DRIVER_INFO\n");
 
+		memset(&DevInfo, 0, sizeof(DevInfo));
 		DevInfo.MaxRDMBufferSize = BUFFER_4K;
 		DevInfo.u32DSDStartOffset = EEPROM_CALPARAM_START;
 		DevInfo.u32RxAlignmentCorrection = 0;
diff --git a/drivers/staging/ozwpan/ozcdev.c b/drivers/staging/ozwpan/ozcdev.c
index 6ccb64f..6ce0af9 100644
--- a/drivers/staging/ozwpan/ozcdev.c
+++ b/drivers/staging/ozwpan/ozcdev.c
@@ -155,6 +155,9 @@
 	struct oz_app_hdr *app_hdr;
 	struct oz_serial_ctx *ctx;
 
+	if (count > sizeof(ei->data) - sizeof(*elt) - sizeof(*app_hdr))
+		return -EINVAL;
+
 	spin_lock_bh(&g_cdev.lock);
 	pd = g_cdev.active_pd;
 	if (pd)
diff --git a/drivers/staging/sb105x/sb_pci_mp.c b/drivers/staging/sb105x/sb_pci_mp.c
index 23db32f..a10cdb1 100644
--- a/drivers/staging/sb105x/sb_pci_mp.c
+++ b/drivers/staging/sb105x/sb_pci_mp.c
@@ -1063,7 +1063,7 @@
 
 static int mp_get_count(struct sb_uart_state *state, struct serial_icounter_struct *icnt)
 {
-	struct serial_icounter_struct icount;
+	struct serial_icounter_struct icount = {};
 	struct sb_uart_icount cnow;
 	struct sb_uart_port *port = state->port;
 
diff --git a/drivers/staging/wlags49_h2/wl_priv.c b/drivers/staging/wlags49_h2/wl_priv.c
index c97e0e1..7e10dcd 100644
--- a/drivers/staging/wlags49_h2/wl_priv.c
+++ b/drivers/staging/wlags49_h2/wl_priv.c
@@ -570,6 +570,7 @@
 	ltv_t                   *pLtv;
 	bool_t                  ltvAllocated = FALSE;
 	ENCSTRCT                sEncryption;
+	size_t			len;
 
 #ifdef USE_WDS
 	hcf_16                  hcfPort  = HCF_PORT_0;
@@ -686,7 +687,8 @@
 					break;
 				case CFG_CNF_OWN_NAME:
 					memset(lp->StationName, 0, sizeof(lp->StationName));
-					memcpy((void *)lp->StationName, (void *)&pLtv->u.u8[2], (size_t)pLtv->u.u16[0]);
+					len = min_t(size_t, pLtv->u.u16[0], sizeof(lp->StationName));
+					strlcpy(lp->StationName, &pLtv->u.u8[2], len);
 					pLtv->u.u16[0] = CNV_INT_TO_LITTLE(pLtv->u.u16[0]);
 					break;
 				case CFG_CNF_LOAD_BALANCING:
@@ -1783,6 +1785,7 @@
 {
 	struct wl_private *lp = wl_priv(dev);
 	unsigned long flags;
+	size_t len;
 	int         ret = 0;
 	/*------------------------------------------------------------------------*/
 
@@ -1793,8 +1796,8 @@
 	wl_lock(lp, &flags);
 
 	memset(lp->StationName, 0, sizeof(lp->StationName));
-
-	memcpy(lp->StationName, extra, wrqu->data.length);
+	len = min_t(size_t, wrqu->data.length, sizeof(lp->StationName));
+	strlcpy(lp->StationName, extra, len);
 
 	/* Commit the adapter parameters */
 	wl_apply(lp);
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index d067285..6b0f75e 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1499,7 +1499,7 @@
 /*
  * Get ip name usart or uart
  */
-static int atmel_get_ip_name(struct uart_port *port)
+static void atmel_get_ip_name(struct uart_port *port)
 {
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
 	int name = UART_GET_IP_NAME(port);
@@ -1518,10 +1518,7 @@
 		atmel_port->is_usart = false;
 	} else {
 		dev_err(port->dev, "Not supported ip name, set to uart\n");
-		return -EINVAL;
 	}
-
-	return 0;
 }
 
 /*
@@ -2405,9 +2402,7 @@
 	/*
 	 * Get port name of usart or uart
 	 */
-	ret = atmel_get_ip_name(&port->uart);
-	if (ret < 0)
-		goto err_add_port;
+	atmel_get_ip_name(&port->uart);
 
 	return 0;
 
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index ba47563..0e808cf 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -642,16 +642,29 @@
 {
 	struct uio_device *idev = vma->vm_private_data;
 	int mi = uio_find_mem_index(vma);
+	struct uio_mem *mem;
 	if (mi < 0)
 		return -EINVAL;
+	mem = idev->info->mem + mi;
+
+	if (vma->vm_end - vma->vm_start > mem->size)
+		return -EINVAL;
 
 	vma->vm_ops = &uio_physical_vm_ops;
-
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
+	/*
+	 * We cannot use the vm_iomap_memory() helper here,
+	 * because vma->vm_pgoff is the map index we looked
+	 * up above in uio_find_mem_index(), rather than an
+	 * actual page offset into the mmap.
+	 *
+	 * So we just do the physical mmap without a page
+	 * offset.
+	 */
 	return remap_pfn_range(vma,
 			       vma->vm_start,
-			       idev->info->mem[mi].addr >> PAGE_SHIFT,
+			       mem->addr >> PAGE_SHIFT,
 			       vma->vm_end - vma->vm_start,
 			       vma->vm_page_prot);
 }
diff --git a/drivers/video/au1100fb.c b/drivers/video/au1100fb.c
index a54ccdc..22ad8524 100644
--- a/drivers/video/au1100fb.c
+++ b/drivers/video/au1100fb.c
@@ -361,37 +361,13 @@
 int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma)
 {
 	struct au1100fb_device *fbdev;
-	unsigned int len;
-	unsigned long start=0, off;
 
 	fbdev = to_au1100fb_device(fbi);
 
-	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) {
-		return -EINVAL;
-	}
-
-	start = fbdev->fb_phys & PAGE_MASK;
-	len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len);
-
-	off = vma->vm_pgoff << PAGE_SHIFT;
-
-	if ((vma->vm_end - vma->vm_start + off) > len) {
-		return -EINVAL;
-	}
-
-	off += start;
-	vma->vm_pgoff = off >> PAGE_SHIFT;
-
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	pgprot_val(vma->vm_page_prot) |= (6 << 9); //CCA=6
 
-	if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
-				vma->vm_end - vma->vm_start,
-				vma->vm_page_prot)) {
-		return -EAGAIN;
-	}
-
-	return 0;
+	return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len);
 }
 
 static struct fb_ops au1100fb_ops =
diff --git a/drivers/video/au1200fb.c b/drivers/video/au1200fb.c
index 301224e..1d02897 100644
--- a/drivers/video/au1200fb.c
+++ b/drivers/video/au1200fb.c
@@ -1233,34 +1233,13 @@
  * method mainly to allow the use of the TLB streaming flag (CCA=6)
  */
 static int au1200fb_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
-
 {
-	unsigned int len;
-	unsigned long start=0, off;
 	struct au1200fb_device *fbdev = info->par;
 
-	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) {
-		return -EINVAL;
-	}
-
-	start = fbdev->fb_phys & PAGE_MASK;
-	len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len);
-
-	off = vma->vm_pgoff << PAGE_SHIFT;
-
-	if ((vma->vm_end - vma->vm_start + off) > len) {
-		return -EINVAL;
-	}
-
-	off += start;
-	vma->vm_pgoff = off >> PAGE_SHIFT;
-
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	pgprot_val(vma->vm_page_prot) |= _CACHE_MASK; /* CCA=7 */
 
-	return io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
-				  vma->vm_end - vma->vm_start,
-				  vma->vm_page_prot);
+	return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len);
 }
 
 static void set_global(u_int cmd, struct au1200_lcd_global_regs_t *pdata)
diff --git a/fs/dcache.c b/fs/dcache.c
index 20532cb..ae6ebb8 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -542,7 +542,7 @@
  * If ref is non-zero, then decrement the refcount too.
  * Returns dentry requiring refcount drop, or NULL if we're done.
  */
-static inline struct dentry *
+static struct dentry *
 dentry_kill(struct dentry *dentry, int unlock_on_failure)
 	__releases(dentry->d_lock)
 {
@@ -630,7 +630,8 @@
 			goto kill_it;
 	}
 
-	dentry->d_flags |= DCACHE_REFERENCED;
+	if (!(dentry->d_flags & DCACHE_REFERENCED))
+		dentry->d_flags |= DCACHE_REFERENCED;
 	dentry_lru_add(dentry);
 
 	dentry->d_lockref.count--;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 473e09d..810c28f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,7 +34,6 @@
 #include <linux/mutex.h>
 #include <linux/anon_inodes.h>
 #include <linux/device.h>
-#include <linux/freezer.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/mman.h>
@@ -1605,8 +1604,7 @@
 			}
 
 			spin_unlock_irqrestore(&ep->lock, flags);
-			if (!freezable_schedule_hrtimeout_range(to, slack,
-								HRTIMER_MODE_ABS))
+			if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
 				timed_out = 1;
 
 			spin_lock_irqsave(&ep->lock, flags);
diff --git a/fs/select.c b/fs/select.c
index 35d4adc7..dfd5cb1 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -238,8 +238,7 @@
 
 	set_current_state(state);
 	if (!pwq->triggered)
-		rc = freezable_schedule_hrtimeout_range(expires, slack,
-							HRTIMER_MODE_ABS);
+		rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
 	__set_current_state(TASK_RUNNING);
 
 	/*
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index cc88172..c74088a 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -332,7 +332,7 @@
 #endif
 
 #ifndef this_cpu_sub
-# define this_cpu_sub(pcp, val)		this_cpu_add((pcp), -(val))
+# define this_cpu_sub(pcp, val)		this_cpu_add((pcp), -(typeof(pcp))(val))
 #endif
 
 #ifndef this_cpu_inc
@@ -418,7 +418,7 @@
 # define this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
 #endif
 
-#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(val))
+#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(typeof(pcp))(val))
 #define this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
 #define this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
 
@@ -586,7 +586,7 @@
 #endif
 
 #ifndef __this_cpu_sub
-# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(val))
+# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(typeof(pcp))(val))
 #endif
 
 #ifndef __this_cpu_inc
@@ -668,7 +668,7 @@
 	__pcpu_size_call_return2(__this_cpu_add_return_, pcp, val)
 #endif
 
-#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(val))
+#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
 #define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
 #define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 06344d9..094f315 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -983,7 +983,7 @@
 
 config DEBUG_KOBJECT_RELEASE
 	bool "kobject release debugging"
-	depends on DEBUG_KERNEL
+	depends on DEBUG_OBJECTS_TIMERS
 	help
 	  kobjects are reference counted objects.  This means that their
 	  last reference count put is not predictable, and the kobject can
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index a685c8a..d16fa29 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -577,7 +577,8 @@
 		miter->__offset += miter->consumed;
 		miter->__remaining -= miter->consumed;
 
-		if (miter->__flags & SG_MITER_TO_SG)
+		if ((miter->__flags & SG_MITER_TO_SG) &&
+		    !PageSlab(miter->page))
 			flush_kernel_dcache_page(miter->page);
 
 		if (miter->__flags & SG_MITER_ATOMIC) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 610e3df..cca80d9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1278,64 +1278,90 @@
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	int page_nid = -1, this_nid = numa_node_id();
 	int target_nid;
-	int current_nid = -1;
-	bool migrated;
+	bool page_locked;
+	bool migrated = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
-	get_page(page);
-	current_nid = page_to_nid(page);
+	page_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
+	/*
+	 * Acquire the page lock to serialise THP migrations but avoid dropping
+	 * page_table_lock if at all possible
+	 */
+	page_locked = trylock_page(page);
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1) {
-		put_page(page);
-		goto clear_pmdnuma;
+		/* If the page was locked, there are no parallel migrations */
+		if (page_locked)
+			goto clear_pmdnuma;
+
+		/*
+		 * Otherwise wait for potential migrations and retry. We do
+		 * relock and check_same as the page may no longer be mapped.
+		 * As the fault is being retried, do not account for it.
+		 */
+		spin_unlock(&mm->page_table_lock);
+		wait_on_page_locked(page);
+		page_nid = -1;
+		goto out;
 	}
 
-	/* Acquire the page lock to serialise THP migrations */
+	/* Page is misplaced, serialise migrations and parallel THP splits */
+	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	lock_page(page);
+	if (!page_locked)
+		lock_page(page);
+	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
+		page_nid = -1;
 		goto out_unlock;
 	}
-	spin_unlock(&mm->page_table_lock);
 
-	/* Migrate the THP to the requested node */
+	/*
+	 * Migrate the THP to the requested node, returns with page unlocked
+	 * and pmd_numa cleared.
+	 */
+	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
-	if (!migrated)
-		goto check_same;
+	if (migrated)
+		page_nid = target_nid;
 
-	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
-	return 0;
-
-check_same:
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
-		goto out_unlock;
+	goto out;
 clear_pmdnuma:
+	BUG_ON(!PageLocked(page));
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	unlock_page(page);
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+
+out:
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
+
+	if (page_nid != -1)
+		task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+
 	return 0;
 }
 
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 7246791..72f9dec 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -81,8 +81,9 @@
 		 * decrement nr_to_walk first so that we don't livelock if we
 		 * get stuck on large numbesr of LRU_RETRY items
 		 */
-		if (--(*nr_to_walk) == 0)
+		if (!*nr_to_walk)
 			break;
+		--*nr_to_walk;
 
 		ret = isolate(item, &nlru->lock, cb_arg);
 		switch (ret) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 34d3ca9..13b9d0f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -54,6 +54,7 @@
 #include <linux/page_cgroup.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
+#include <linux/lockdep.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -2046,6 +2047,12 @@
 	return total;
 }
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map memcg_oom_lock_dep_map = {
+	.name = "memcg_oom_lock",
+};
+#endif
+
 static DEFINE_SPINLOCK(memcg_oom_lock);
 
 /*
@@ -2083,7 +2090,8 @@
 			}
 			iter->oom_lock = false;
 		}
-	}
+	} else
+		mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_);
 
 	spin_unlock(&memcg_oom_lock);
 
@@ -2095,6 +2103,7 @@
 	struct mem_cgroup *iter;
 
 	spin_lock(&memcg_oom_lock);
+	mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_);
 	for_each_mem_cgroup_tree(iter, memcg)
 		iter->oom_lock = false;
 	spin_unlock(&memcg_oom_lock);
@@ -2765,10 +2774,10 @@
 	*ptr = memcg;
 	return 0;
 nomem:
-	*ptr = NULL;
-	if (gfp_mask & __GFP_NOFAIL)
-		return 0;
-	return -ENOMEM;
+	if (!(gfp_mask & __GFP_NOFAIL)) {
+		*ptr = NULL;
+		return -ENOMEM;
+	}
 bypass:
 	*ptr = root_mem_cgroup;
 	return -EINTR;
@@ -3773,8 +3782,7 @@
 {
 	/* Update stat data for mem_cgroup */
 	preempt_disable();
-	WARN_ON_ONCE(from->stat->count[idx] < nr_pages);
-	__this_cpu_add(from->stat->count[idx], -nr_pages);
+	__this_cpu_sub(from->stat->count[idx], nr_pages);
 	__this_cpu_add(to->stat->count[idx], nr_pages);
 	preempt_enable();
 }
@@ -4950,31 +4958,18 @@
 	} while (usage > 0);
 }
 
-/*
- * This mainly exists for tests during the setting of set of use_hierarchy.
- * Since this is the very setting we are changing, the current hierarchy value
- * is meaningless
- */
-static inline bool __memcg_has_children(struct mem_cgroup *memcg)
-{
-	struct cgroup_subsys_state *pos;
-
-	/* bounce at first found */
-	css_for_each_child(pos, &memcg->css)
-		return true;
-	return false;
-}
-
-/*
- * Must be called with memcg_create_mutex held, unless the cgroup is guaranteed
- * to be already dead (as in mem_cgroup_force_empty, for instance).  This is
- * from mem_cgroup_count_children(), in the sense that we don't really care how
- * many children we have; we only need to know if we have any.  It also counts
- * any memcg without hierarchy as infertile.
- */
 static inline bool memcg_has_children(struct mem_cgroup *memcg)
 {
-	return memcg->use_hierarchy && __memcg_has_children(memcg);
+	lockdep_assert_held(&memcg_create_mutex);
+	/*
+	 * The lock does not prevent addition or deletion to the list
+	 * of children, but it prevents a new child from being
+	 * initialized based on this parent in css_online(), so it's
+	 * enough to decide whether hierarchically inherited
+	 * attributes can still be changed or not.
+	 */
+	return memcg->use_hierarchy &&
+		!list_empty(&memcg->css.cgroup->children);
 }
 
 /*
@@ -5054,7 +5049,7 @@
 	 */
 	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
 				(val == 1 || val == 0)) {
-		if (!__memcg_has_children(memcg))
+		if (list_empty(&memcg->css.cgroup->children))
 			memcg->use_hierarchy = val;
 		else
 			retval = -EBUSY;
diff --git a/mm/memory.c b/mm/memory.c
index 1311f26..d176154 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3521,12 +3521,12 @@
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-				unsigned long addr, int current_nid)
+				unsigned long addr, int page_nid)
 {
 	get_page(page);
 
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == numa_node_id())
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
 	return mpol_misplaced(page, vma, addr);
@@ -3537,7 +3537,7 @@
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid = -1;
+	int page_nid = -1;
 	int target_nid;
 	bool migrated = false;
 
@@ -3567,15 +3567,10 @@
 		return 0;
 	}
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	page_nid = page_to_nid(page);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
-		/*
-		 * Account for the fault against the current node if it not
-		 * being replaced regardless of where the page is located.
-		 */
-		current_nid = numa_node_id();
 		put_page(page);
 		goto out;
 	}
@@ -3583,11 +3578,11 @@
 	/* Migrate to the requested node */
 	migrated = migrate_misplaced_page(page, target_nid);
 	if (migrated)
-		current_nid = target_nid;
+		page_nid = target_nid;
 
 out:
-	if (current_nid != -1)
-		task_numa_fault(current_nid, 1, migrated);
+	if (page_nid != -1)
+		task_numa_fault(page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3602,7 +3597,6 @@
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int local_nid = numa_node_id();
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3625,9 +3619,10 @@
 	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
 		pte_t pteval = *pte;
 		struct page *page;
-		int curr_nid = local_nid;
+		int page_nid = -1;
 		int target_nid;
-		bool migrated;
+		bool migrated = false;
+
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3649,25 +3644,19 @@
 		if (unlikely(page_mapcount(page) != 1))
 			continue;
 
-		/*
-		 * Note that the NUMA fault is later accounted to either
-		 * the node that is currently running or where the page is
-		 * migrated to.
-		 */
-		curr_nid = local_nid;
-		target_nid = numa_migrate_prep(page, vma, addr,
-					       page_to_nid(page));
-		if (target_nid == -1) {
+		page_nid = page_to_nid(page);
+		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+		pte_unmap_unlock(pte, ptl);
+		if (target_nid != -1) {
+			migrated = migrate_misplaced_page(page, target_nid);
+			if (migrated)
+				page_nid = target_nid;
+		} else {
 			put_page(page);
-			continue;
 		}
 
-		/* Migrate to the requested node */
-		pte_unmap_unlock(pte, ptl);
-		migrated = migrate_misplaced_page(page, target_nid);
-		if (migrated)
-			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1, migrated);
+		if (page_nid != -1)
+			task_numa_fault(page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index 7a7325e..c046927 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1715,12 +1715,12 @@
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */
 
-		unlock_page(page);
+		/* Retake the callers reference and putback on LRU */
+		get_page(page);
 		putback_lru_page(page);
-
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		isolated = 0;
-		goto out;
+		mod_zone_page_state(page_zone(page),
+			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
+		goto out_fail;
 	}
 
 	/*
@@ -1737,9 +1737,9 @@
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
 
-	page_add_new_anon_rmap(new_page, vma, haddr);
-
+	pmdp_clear_flush(vma, haddr, pmd);
 	set_pmd_at(mm, haddr, pmd, entry);
+	page_add_new_anon_rmap(new_page, vma, haddr);
 	update_mmu_cache_pmd(vma, address, &entry);
 	page_remove_rmap(page);
 	/*
@@ -1758,7 +1758,6 @@
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
 
-out:
 	mod_zone_page_state(page_zone(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
@@ -1767,6 +1766,10 @@
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	entry = pmd_mknonnuma(entry);
+	set_pmd_at(mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, address, &entry);
+
 	unlock_page(page);
 	put_page(page);
 	return 0;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a3af058..412ba2b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -148,7 +148,7 @@
 				split_huge_page_pmd(vma, addr, pmd);
 			else if (change_huge_pmd(vma, pmd, addr, newprot,
 						 prot_numa)) {
-				pages += HPAGE_PMD_NR;
+				pages++;
 				continue;
 			}
 			/* fall through */
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 5da2cbc..2beeabf 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -242,7 +242,7 @@
 		if (err)
 			break;
 		pgd++;
-	} while (addr = next, addr != end);
+	} while (addr = next, addr < end);
 
 	return err;
 }
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e297b74..ca0d3d9 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -90,8 +90,20 @@
 	Number of mmap data pages. Must be a power of two.
 
 -g::
+	Enables call-graph (stack chain/backtrace) recording.
+
 --call-graph::
-	Do call-graph (stack chain/backtrace) recording.
+	Setup and enable call-graph (stack chain/backtrace) recording,
+	implies -g.
+
+	Allows specifying "fp" (frame pointer) or "dwarf"
+	(DWARF's CFI - Call Frame Information) as the method to collect
+	the information used to show the call graphs.
+
+	In some systems, where binaries are build with gcc
+	--fomit-frame-pointer, using the "fp" method will produce bogus
+	call graphs, using "dwarf", if available (perf tools linked to
+	the libunwind library) should be used instead.
 
 -q::
 --quiet::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 58d6598..6a118e7 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -140,20 +140,12 @@
 --asm-raw::
 	Show raw instruction encoding of assembly instructions.
 
--G [type,min,order]::
+-G::
+	Enables call-graph (stack chain/backtrace) recording.
+
 --call-graph::
-        Display call chains using type, min percent threshold and order.
-	type can be either:
-	- flat: single column, linear exposure of call chains.
-	- graph: use a graph tree, displaying absolute overhead rates.
-	- fractal: like graph, but displays relative rates. Each branch of
-		 the tree is considered as a new profiled object.
-
-	order can be either:
-	- callee: callee based call graph.
-	- caller: inverted caller based call graph.
-
-	Default: fractal,0.5,callee.
+	Setup and enable call-graph (stack chain/backtrace) recording,
+	implies -G.
 
 --ignore-callees=<regex>::
         Ignore callees of the function(s) matching the given regex.
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 935d522..fbc2888 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -888,11 +888,18 @@
 	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
 		err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
 		if (err) {
+			perf_evlist__mmap_consume(kvm->evlist, idx);
 			pr_err("Failed to parse sample\n");
 			return -1;
 		}
 
 		err = perf_session_queue_event(kvm->session, event, &sample, 0);
+		/*
+		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
+		 *        point to it, and it'll get possibly overwritten by the kernel.
+		 */
+		perf_evlist__mmap_consume(kvm->evlist, idx);
+
 		if (err) {
 			pr_err("Failed to enqueue sample: %d\n", err);
 			return -1;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a41ac415..d046514 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -712,21 +712,12 @@
 }
 #endif /* LIBUNWIND_SUPPORT */
 
-int record_parse_callchain_opt(const struct option *opt,
-			       const char *arg, int unset)
+int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
 {
-	struct perf_record_opts *opts = opt->value;
 	char *tok, *name, *saveptr = NULL;
 	char *buf;
 	int ret = -1;
 
-	/* --no-call-graph */
-	if (unset)
-		return 0;
-
-	/* We specified default option if none is provided. */
-	BUG_ON(!arg);
-
 	/* We need buffer that we know we can write to. */
 	buf = malloc(strlen(arg) + 1);
 	if (!buf)
@@ -764,13 +755,9 @@
 				ret = get_stack_size(tok, &size);
 				opts->stack_dump_size = size;
 			}
-
-			if (!ret)
-				pr_debug("callchain: stack dump size %d\n",
-					 opts->stack_dump_size);
 #endif /* LIBUNWIND_SUPPORT */
 		} else {
-			pr_err("callchain: Unknown -g option "
+			pr_err("callchain: Unknown --call-graph option "
 			       "value: %s\n", arg);
 			break;
 		}
@@ -778,13 +765,52 @@
 	} while (0);
 
 	free(buf);
+	return ret;
+}
 
+static void callchain_debug(struct perf_record_opts *opts)
+{
+	pr_debug("callchain: type %d\n", opts->call_graph);
+
+	if (opts->call_graph == CALLCHAIN_DWARF)
+		pr_debug("callchain: stack dump size %d\n",
+			 opts->stack_dump_size);
+}
+
+int record_parse_callchain_opt(const struct option *opt,
+			       const char *arg,
+			       int unset)
+{
+	struct perf_record_opts *opts = opt->value;
+	int ret;
+
+	/* --no-call-graph */
+	if (unset) {
+		opts->call_graph = CALLCHAIN_NONE;
+		pr_debug("callchain: disabled\n");
+		return 0;
+	}
+
+	ret = record_parse_callchain(arg, opts);
 	if (!ret)
-		pr_debug("callchain: type %d\n", opts->call_graph);
+		callchain_debug(opts);
 
 	return ret;
 }
 
+int record_callchain_opt(const struct option *opt,
+			 const char *arg __maybe_unused,
+			 int unset __maybe_unused)
+{
+	struct perf_record_opts *opts = opt->value;
+
+	if (opts->call_graph == CALLCHAIN_NONE)
+		opts->call_graph = CALLCHAIN_FP;
+
+	callchain_debug(opts);
+	return 0;
+}
+
 static const char * const record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -813,12 +839,12 @@
 	},
 };
 
-#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
+#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
 
 #ifdef LIBUNWIND_SUPPORT
-const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf";
 #else
-const char record_callchain_help[] = CALLCHAIN_HELP "[fp]";
+const char record_callchain_help[] = CALLCHAIN_HELP "fp";
 #endif
 
 /*
@@ -858,9 +884,12 @@
 		     "number of mmap data pages"),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts,
-			     "mode[,dump_size]", record_callchain_help,
-			     &record_parse_callchain_opt, "fp"),
+	OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
+			   NULL, "enables call-graph recording" ,
+			   &record_callchain_opt),
+	OPT_CALLBACK(0, "call-graph", &record.opts,
+		     "mode[,dump_size]", record_callchain_help,
+		     &record_parse_callchain_opt),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2122141..5a11f13 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -810,7 +810,7 @@
 		ret = perf_evlist__parse_sample(top->evlist, event, &sample);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
-			continue;
+			goto next_event;
 		}
 
 		evsel = perf_evlist__id2evsel(session->evlist, sample.id);
@@ -825,13 +825,13 @@
 		case PERF_RECORD_MISC_USER:
 			++top->us_samples;
 			if (top->hide_user_symbols)
-				continue;
+				goto next_event;
 			machine = &session->machines.host;
 			break;
 		case PERF_RECORD_MISC_KERNEL:
 			++top->kernel_samples;
 			if (top->hide_kernel_symbols)
-				continue;
+				goto next_event;
 			machine = &session->machines.host;
 			break;
 		case PERF_RECORD_MISC_GUEST_KERNEL:
@@ -847,7 +847,7 @@
 			 */
 			/* Fall thru */
 		default:
-			continue;
+			goto next_event;
 		}
 
 
@@ -859,6 +859,8 @@
 			machine__process_event(machine, event);
 		} else
 			++session->stats.nr_unknown_events;
+next_event:
+		perf_evlist__mmap_consume(top->evlist, idx);
 	}
 }
 
@@ -1016,16 +1018,16 @@
 }
 
 static int
+callchain_opt(const struct option *opt, const char *arg, int unset)
+{
+	symbol_conf.use_callchain = true;
+	return record_callchain_opt(opt, arg, unset);
+}
+
+static int
 parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	/*
-	 * --no-call-graph
-	 */
-	if (unset)
-		return 0;
-
 	symbol_conf.use_callchain = true;
-
 	return record_parse_callchain_opt(opt, arg, unset);
 }
 
@@ -1106,9 +1108,12 @@
 		   "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
-			     "mode[,dump_size]", record_callchain_help,
-			     &parse_callchain_opt, "fp"),
+	OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
+			   NULL, "enables call-graph recording",
+			   &callchain_opt),
+	OPT_CALLBACK(0, "call-graph", &top.record_opts,
+		     "mode[,dump_size]", record_callchain_help,
+		     &parse_callchain_opt),
 	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
 		   "ignore callees of these functions in call graphs",
 		   report_parse_ignore_callees_opt),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 71aa3e3..99c8d9a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -987,7 +987,7 @@
 			err = perf_evlist__parse_sample(evlist, event, &sample);
 			if (err) {
 				fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
-				continue;
+				goto next_event;
 			}
 
 			if (trace->base_time == 0)
@@ -1001,18 +1001,20 @@
 			evsel = perf_evlist__id2evsel(evlist, sample.id);
 			if (evsel == NULL) {
 				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
-				continue;
+				goto next_event;
 			}
 
 			if (sample.raw_data == NULL) {
 				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
 				       perf_evsel__name(evsel), sample.tid,
 				       sample.cpu, sample.raw_size);
-				continue;
+				goto next_event;
 			}
 
 			handler = evsel->handler.func;
 			handler(trace, evsel, &sample);
+next_event:
+			perf_evlist__mmap_consume(evlist, i);
 
 			if (done)
 				goto out_unmap_evlist;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 6fb781d..e3fedfa 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -290,6 +290,7 @@
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
+			perf_evlist__mmap_consume(evlist, i);
 			if (ret < 0)
 				return ret;
 		}
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index d444ea2..376c356 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -36,6 +36,7 @@
 			    (pid_t)event->comm.tid == getpid() &&
 			    strcmp(event->comm.comm, comm) == 0)
 				found += 1;
+			perf_evlist__mmap_consume(evlist, i);
 		}
 	}
 	return found;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index c4185b9..a7232c2 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -122,6 +122,7 @@
 			goto out_munmap;
 		}
 		nr_events[evsel->idx]++;
+		perf_evlist__mmap_consume(evlist, 0);
 	}
 
 	err = 0;
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index fc5b9fc..524b221 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -77,8 +77,10 @@
 
 				++nr_events;
 
-				if (type != PERF_RECORD_SAMPLE)
+				if (type != PERF_RECORD_SAMPLE) {
+					perf_evlist__mmap_consume(evlist, i);
 					continue;
+				}
 
 				err = perf_evsel__parse_sample(evsel, event, &sample);
 				if (err) {
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index b8a7056..7923b06 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -263,6 +263,8 @@
 						 type);
 					++errs;
 				}
+
+				perf_evlist__mmap_consume(evlist, i);
 			}
 		}
 
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 0ab61b1..4ca1b93 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -122,7 +122,7 @@
 			if (event->header.type != PERF_RECORD_COMM ||
 			    (pid_t)event->comm.pid != getpid() ||
 			    (pid_t)event->comm.tid != getpid())
-				continue;
+				goto next_event;
 
 			if (strcmp(event->comm.comm, comm1) == 0) {
 				CHECK__(perf_evsel__parse_sample(evsel, event,
@@ -134,6 +134,8 @@
 								 &sample));
 				comm2_time = sample.time;
 			}
+next_event:
+			perf_evlist__mmap_consume(evlist, i);
 		}
 	}
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 2e41e2d..6e2b44e 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE)
-			continue;
+			goto next_event;
 
 		err = perf_evlist__parse_sample(evlist, event, &sample);
 		if (err < 0) {
@@ -88,6 +88,8 @@
 
 		total_periods += sample.period;
 		nr_samples++;
+next_event:
+		perf_evlist__mmap_consume(evlist, 0);
 	}
 
 	if ((u64) nr_samples == total_periods) {
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 28fe589..a3e6487 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -96,10 +96,10 @@
 
 retry:
 	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
-		if (event->header.type != PERF_RECORD_EXIT)
-			continue;
+		if (event->header.type == PERF_RECORD_EXIT)
+			nr_exit++;
 
-		nr_exit++;
+		perf_evlist__mmap_consume(evlist, 0);
 	}
 
 	if (!exited || !nr_exit) {
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 194e2f4..6c15268 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -315,8 +315,7 @@
 }
 
 static int hist_entry__period_snprintf(struct perf_hpp *hpp,
-				       struct hist_entry *he,
-				       bool color)
+				       struct hist_entry *he)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
@@ -338,7 +337,7 @@
 		} else
 			first = false;
 
-		if (color && fmt->color)
+		if (perf_hpp__use_color() && fmt->color)
 			ret = fmt->color(fmt, hpp, he);
 		else
 			ret = fmt->entry(fmt, hpp, he);
@@ -358,12 +357,11 @@
 		.buf		= bf,
 		.size		= size,
 	};
-	bool color = !symbol_conf.field_sep;
 
 	if (size == 0 || size > bfsz)
 		size = hpp.size = bfsz;
 
-	ret = hist_entry__period_snprintf(&hpp, he, color);
+	ret = hist_entry__period_snprintf(&hpp, he);
 	hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
 
 	ret = fprintf(fp, "%s\n", bf);
@@ -482,6 +480,7 @@
 
 print_entries:
 	linesz = hists__sort_list_width(hists) + 3 + 1;
+	linesz += perf_hpp__color_overhead();
 	line = malloc(linesz);
 	if (line == NULL) {
 		ret = -1;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 2b585bc..9e99060 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -147,6 +147,9 @@
 
 struct option;
 
+int record_parse_callchain(const char *arg, struct perf_record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
+int record_callchain_opt(const struct option *opt, const char *arg, int unset);
+
 extern const char record_callchain_help[];
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 63df031..49096ea 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -213,7 +213,7 @@
 		       &event->mmap.pgoff,
 		       execname);
 
-		if (n != 8)
+		if (n != 5)
 			continue;
 
 		if (prot[2] != 'x')
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f9f77be..e584cd3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -545,12 +545,19 @@
 
 	md->prev = old;
 
-	if (!evlist->overwrite)
-		perf_mmap__write_tail(md, old);
-
 	return event;
 }
 
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+	if (!evlist->overwrite) {
+		struct perf_mmap *md = &evlist->mmap[idx];
+		unsigned int old = md->prev;
+
+		perf_mmap__write_tail(md, old);
+	}
+}
+
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 {
 	if (evlist->mmap[idx].base != NULL) {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 880d713..206d093 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -89,6 +89,8 @@
 
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
+
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 1329b6b..ce8dc61 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -5,6 +5,7 @@
 #include <pthread.h>
 #include "callchain.h"
 #include "header.h"
+#include "color.h"
 
 extern struct callchain_param callchain_param;
 
@@ -175,6 +176,18 @@
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
 
+static inline size_t perf_hpp__use_color(void)
+{
+	return !symbol_conf.field_sep;
+}
+
+static inline size_t perf_hpp__color_overhead(void)
+{
+	return perf_hpp__use_color() ?
+	       (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX
+	       : 0;
+}
+
 struct perf_evlist;
 
 struct hist_browser_timer {
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 71b5412..2ac4bc9 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -822,6 +822,8 @@
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
 
+		perf_evlist__mmap_consume(evlist, cpu);
+
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cc75a3c..95d91a0 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -56,6 +56,17 @@
 	Py_FatalError("problem in Python trace event handler");
 }
 
+/*
+ * Insert val into into the dictionary and decrement the reference counter.
+ * This is necessary for dictionaries since PyDict_SetItemString() does not 
+ * steal a reference, as opposed to PyTuple_SetItem().
+ */
+static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val)
+{
+	PyDict_SetItemString(dict, key, val);
+	Py_DECREF(val);
+}
+
 static void define_value(enum print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
@@ -279,11 +290,11 @@
 		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
 		PyTuple_SetItem(t, n++, PyString_FromString(comm));
 	} else {
-		PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu));
-		PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s));
-		PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns));
-		PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid));
-		PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm));
+		pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
+		pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
+		pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
+		pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
+		pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
 	}
 	for (field = event->format.fields; field; field = field->next) {
 		if (field->flags & FIELD_IS_STRING) {
@@ -313,7 +324,7 @@
 		if (handler)
 			PyTuple_SetItem(t, n++, obj);
 		else
-			PyDict_SetItemString(dict, field->name, obj);
+			pydict_set_item_string_decref(dict, field->name, obj);
 
 	}
 	if (!handler)
@@ -370,21 +381,21 @@
 	if (!handler || !PyCallable_Check(handler))
 		goto exit;
 
-	PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
-	PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
+	pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
 			(const char *)&evsel->attr, sizeof(evsel->attr)));
-	PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
 			(const char *)sample, sizeof(*sample)));
-	PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
 			(const char *)sample->raw_data, sample->raw_size));
-	PyDict_SetItemString(dict, "comm",
+	pydict_set_item_string_decref(dict, "comm",
 			PyString_FromString(thread->comm));
 	if (al->map) {
-		PyDict_SetItemString(dict, "dso",
+		pydict_set_item_string_decref(dict, "dso",
 			PyString_FromString(al->map->dso->name));
 	}
 	if (al->sym) {
-		PyDict_SetItemString(dict, "symbol",
+		pydict_set_item_string_decref(dict, "symbol",
 			PyString_FromString(al->sym->name));
 	}
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a9dd682..1cf9ccb 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3091,7 +3091,7 @@
 
 static int kvm_init_debug(void)
 {
-	int r = -EFAULT;
+	int r = -EEXIST;
 	struct kvm_stats_debugfs_item *p;
 
 	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);