Merge tag 'v3.19-rc6' into drm-fixes

Linux 3.19-rc6

pull in rc6 as the amdkfd fixes are based on it, and I'd rather
be doing the merges separately

62 files changed, 354 insertions, 242 deletions

diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index 076c35cd6cde..98a1525fa164 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -285,8 +285,12 @@ pcibios_claim_one_bus(struct pci_bus *b)
 			if (r->parent || !r->start || !r->flags)
 				continue;
 			if (pci_has_flag(PCI_PROBE_ONLY) ||
-			    (r->flags & IORESOURCE_PCI_FIXED))
-				pci_claim_resource(dev, i);
+			    (r->flags & IORESOURCE_PCI_FIXED)) {
+				if (pci_claim_resource(dev, i) == 0)
+					continue;
+
+				pci_claim_bridge_resource(dev, i);
+			}
 		}
 	}
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 22771bc1643a..63f8b007bdc5 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1257,6 +1257,8 @@
 				tx-fifo-resize;
 				maximum-speed = "super-speed";
 				dr_mode = "otg";
+				snps,dis_u3_susphy_quirk;
+				snps,dis_u2_susphy_quirk;
 			};
 		};
 
@@ -1278,6 +1280,8 @@
 				tx-fifo-resize;
 				maximum-speed = "high-speed";
 				dr_mode = "otg";
+				snps,dis_u3_susphy_quirk;
+				snps,dis_u2_susphy_quirk;
 			};
 		};
 
@@ -1299,6 +1303,8 @@
 				tx-fifo-resize;
 				maximum-speed = "high-speed";
 				dr_mode = "otg";
+				snps,dis_u3_susphy_quirk;
+				snps,dis_u2_susphy_quirk;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index d238676a9107..e4d3aecc4ed2 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -369,7 +369,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa0000 0x4000>;
-				clocks = <&clks 106>, <&clks 36>;
+				clocks = <&clks 106>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <36>;
 			};
@@ -388,7 +388,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa8000 0x4000>;
-				clocks = <&clks 107>, <&clks 36>;
+				clocks = <&clks 107>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <41>;
 			};
@@ -429,7 +429,7 @@
 			pwm4: pwm@53fc8000 {
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				reg = <0x53fc8000 0x4000>;
-				clocks = <&clks 108>, <&clks 36>;
+				clocks = <&clks 108>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <42>;
 			};
@@ -476,7 +476,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fe0000 0x4000>;
-				clocks = <&clks 105>, <&clks 36>;
+				clocks = <&clks 105>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <26>;
 			};
diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts
index ea282c7c0ca5..e2fed2712249 100644
--- a/arch/arm/boot/dts/tegra20-seaboard.dts
+++ b/arch/arm/boot/dts/tegra20-seaboard.dts
@@ -406,7 +406,7 @@
 		clock-frequency = <400000>;
 
 		magnetometer@c {
-			compatible = "ak,ak8975";
+			compatible = "asahi-kasei,ak8975";
 			reg = <0xc>;
 			interrupt-parent = <&gpio>;
 			interrupts = <TEGRA_GPIO(N, 5) IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 4176df721bf0..1a0045abead7 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -253,21 +253,22 @@
 	.endm
 
 	.macro	restore_user_regs, fast = 0, offset = 0
-	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
-	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
+	mov	r2, sp
+	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
+	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r1, r2, [sp]			@ clear the exclusive monitor
+	strex	r1, r2, [r2]			@ clear the exclusive monitor
 #endif
 	.if	\fast
-	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
+	ldmdb	r2, {r1 - lr}^			@ get calling r1 - lr
 	.else
-	ldmdb	sp, {r0 - lr}^			@ get calling r0 - lr
+	ldmdb	r2, {r0 - lr}^			@ get calling r0 - lr
 	.endif
 	mov	r0, r0				@ ARMv5T and earlier require a nop
 						@ after ldm {}^
-	add	sp, sp, #S_FRAME_SIZE - S_PC
+	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index f7c65adaa428..557e128e4df0 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -116,8 +116,14 @@ int armpmu_event_set_period(struct perf_event *event)
 		ret = 1;
 	}
 
-	if (left > (s64)armpmu->max_period)
-		left = armpmu->max_period;
+	/*
+	 * Limit the maximum period to prevent the counter value
+	 * from overtaking the one we are about to program. In
+	 * effect we are reducing max_period to account for
+	 * interrupt latency (and we are being very conservative).
+	 */
+	if (left > (armpmu->max_period >> 1))
+		left = armpmu->max_period >> 1;
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 715ae19bc7c8..e55408e96559 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -657,10 +657,13 @@ int __init arm_add_memory(u64 start, u64 size)
 
 	/*
 	 * Ensure that start/size are aligned to a page boundary.
-	 * Size is appropriately rounded down, start is rounded up.
+	 * Size is rounded down, start is rounded up.
 	 */
-	size -= start & ~PAGE_MASK;
 	aligned_start = PAGE_ALIGN(start);
+	if (aligned_start > start + size)
+		size = 0;
+	else
+		size -= aligned_start - start;
 
 #ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
 	if (aligned_start > ULONG_MAX) {
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 3585cb394e9b..caa21e9b8cd9 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -246,9 +246,14 @@ static int coherency_type(void)
 	return type;
 }
 
+/*
+ * As a precaution, we currently completely disable hardware I/O
+ * coherency, until enough testing is done with automatic I/O
+ * synchronization barriers to validate that it is a proper solution.
+ */
 int coherency_available(void)
 {
-	return coherency_type() != COHERENCY_FABRIC_TYPE_NONE;
+	return false;
 }
 
 int __init coherency_init(void)
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index db57741c9c8a..64e44d6d07c0 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -211,6 +211,7 @@ extern struct device *omap2_get_iva_device(void);
 extern struct device *omap2_get_l3_device(void);
 extern struct device *omap4_get_dsp_device(void);
 
+unsigned int omap4_xlate_irq(unsigned int hwirq);
 void omap_gic_of_init(void);
 
 #ifdef CONFIG_CACHE_L2X0
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index b7cb44abe49b..cc30e49a4cc2 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -256,6 +256,38 @@ static int __init omap4_sar_ram_init(void)
 }
 omap_early_initcall(omap4_sar_ram_init);
 
+static struct of_device_id gic_match[] = {
+	{ .compatible = "arm,cortex-a9-gic", },
+	{ .compatible = "arm,cortex-a15-gic", },
+	{ },
+};
+
+static struct device_node *gic_node;
+
+unsigned int omap4_xlate_irq(unsigned int hwirq)
+{
+	struct of_phandle_args irq_data;
+	unsigned int irq;
+
+	if (!gic_node)
+		gic_node = of_find_matching_node(NULL, gic_match);
+
+	if (WARN_ON(!gic_node))
+		return hwirq;
+
+	irq_data.np = gic_node;
+	irq_data.args_count = 3;
+	irq_data.args[0] = 0;
+	irq_data.args[1] = hwirq - OMAP44XX_IRQ_GIC_START;
+	irq_data.args[2] = IRQ_TYPE_LEVEL_HIGH;
+
+	irq = irq_create_of_mapping(&irq_data);
+	if (WARN_ON(!irq))
+		irq = hwirq;
+
+	return irq;
+}
+
 void __init omap_gic_of_init(void)
 {
 	struct device_node *np;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index cbb908dc5cf0..9025ffffd2dc 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -3534,9 +3534,15 @@ int omap_hwmod_fill_resources(struct omap_hwmod *oh, struct resource *res)
 
 	mpu_irqs_cnt = _count_mpu_irqs(oh);
 	for (i = 0; i < mpu_irqs_cnt; i++) {
+		unsigned int irq;
+
+		if (oh->xlate_irq)
+			irq = oh->xlate_irq((oh->mpu_irqs + i)->irq);
+		else
+			irq = (oh->mpu_irqs + i)->irq;
 		(res + r)->name = (oh->mpu_irqs + i)->name;
-		(res + r)->start = (oh->mpu_irqs + i)->irq;
-		(res + r)->end = (oh->mpu_irqs + i)->irq;
+		(res + r)->start = irq;
+		(res + r)->end = irq;
 		(res + r)->flags = IORESOURCE_IRQ;
 		r++;
 	}
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index 35ca6efbec31..5b42fafcaf55 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -676,6 +676,7 @@ struct omap_hwmod {
 	spinlock_t			_lock;
 	struct list_head		node;
 	struct omap_hwmod_ocp_if	*_mpu_port;
+	unsigned int			(*xlate_irq)(unsigned int);
 	u16				flags;
 	u8				mpu_rt_idx;
 	u8				response_lat;
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index c314b3c31117..f5e68a782025 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -479,6 +479,7 @@ static struct omap_hwmod omap44xx_dma_system_hwmod = {
 	.class		= &omap44xx_dma_hwmod_class,
 	.clkdm_name	= "l3_dma_clkdm",
 	.mpu_irqs	= omap44xx_dma_system_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.main_clk	= "l3_div_ck",
 	.prcm = {
 		.omap4 = {
@@ -640,6 +641,7 @@ static struct omap_hwmod omap44xx_dss_dispc_hwmod = {
 	.class		= &omap44xx_dispc_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
 	.mpu_irqs	= omap44xx_dss_dispc_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_dispc_sdma_reqs,
 	.main_clk	= "dss_dss_clk",
 	.prcm = {
@@ -693,6 +695,7 @@ static struct omap_hwmod omap44xx_dss_dsi1_hwmod = {
 	.class		= &omap44xx_dsi_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
 	.mpu_irqs	= omap44xx_dss_dsi1_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_dsi1_sdma_reqs,
 	.main_clk	= "dss_dss_clk",
 	.prcm = {
@@ -726,6 +729,7 @@ static struct omap_hwmod omap44xx_dss_dsi2_hwmod = {
 	.class		= &omap44xx_dsi_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
 	.mpu_irqs	= omap44xx_dss_dsi2_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_dsi2_sdma_reqs,
 	.main_clk	= "dss_dss_clk",
 	.prcm = {
@@ -784,6 +788,7 @@ static struct omap_hwmod omap44xx_dss_hdmi_hwmod = {
 	 */
 	.flags		= HWMOD_SWSUP_SIDLE,
 	.mpu_irqs	= omap44xx_dss_hdmi_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_hdmi_sdma_reqs,
 	.main_clk	= "dss_48mhz_clk",
 	.prcm = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index 3e9523084b2a..7c3fac035e93 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -288,6 +288,7 @@ static struct omap_hwmod omap54xx_dma_system_hwmod = {
 	.class		= &omap54xx_dma_hwmod_class,
 	.clkdm_name	= "dma_clkdm",
 	.mpu_irqs	= omap54xx_dma_system_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.main_clk	= "l3_iclk_div",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h
index a8e4b582c527..6163d66102a3 100644
--- a/arch/arm/mach-omap2/prcm-common.h
+++ b/arch/arm/mach-omap2/prcm-common.h
@@ -498,6 +498,7 @@ struct omap_prcm_irq_setup {
 	u8 nr_irqs;
 	const struct omap_prcm_irq *irqs;
 	int irq;
+	unsigned int (*xlate_irq)(unsigned int);
 	void (*read_pending_irqs)(unsigned long *events);
 	void (*ocp_barrier)(void);
 	void (*save_and_clear_irqen)(u32 *saved_mask);
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index cc170fb81ff7..408c64efb807 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -49,6 +49,7 @@ static struct omap_prcm_irq_setup omap4_prcm_irq_setup = {
 	.irqs			= omap4_prcm_irqs,
 	.nr_irqs		= ARRAY_SIZE(omap4_prcm_irqs),
 	.irq			= 11 + OMAP44XX_IRQ_GIC_START,
+	.xlate_irq		= omap4_xlate_irq,
 	.read_pending_irqs	= &omap44xx_prm_read_pending_irqs,
 	.ocp_barrier		= &omap44xx_prm_ocp_barrier,
 	.save_and_clear_irqen	= &omap44xx_prm_save_and_clear_irqen,
@@ -751,8 +752,10 @@ static int omap44xx_prm_late_init(void)
 		}
 
 		/* Once OMAP4 DT is filled as well */
-		if (irq_num >= 0)
+		if (irq_num >= 0) {
 			omap4_prcm_irq_setup.irq = irq_num;
+			omap4_prcm_irq_setup.xlate_irq = NULL;
+		}
 	}
 
 	omap44xx_prm_enable_io_wakeup();
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 779940cb6e56..dea2833ca627 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -187,6 +187,7 @@ int omap_prcm_event_to_irq(const char *name)
  */
 void omap_prcm_irq_cleanup(void)
 {
+	unsigned int irq;
 	int i;
 
 	if (!prcm_irq_setup) {
@@ -211,7 +212,11 @@ void omap_prcm_irq_cleanup(void)
 	kfree(prcm_irq_setup->priority_mask);
 	prcm_irq_setup->priority_mask = NULL;
 
-	irq_set_chained_handler(prcm_irq_setup->irq, NULL);
+	if (prcm_irq_setup->xlate_irq)
+		irq = prcm_irq_setup->xlate_irq(prcm_irq_setup->irq);
+	else
+		irq = prcm_irq_setup->irq;
+	irq_set_chained_handler(irq, NULL);
 
 	if (prcm_irq_setup->base_irq > 0)
 		irq_free_descs(prcm_irq_setup->base_irq,
@@ -259,6 +264,7 @@ int omap_prcm_register_chain_handler(struct omap_prcm_irq_setup *irq_setup)
 	int offset, i;
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
+	unsigned int irq;
 
 	if (!irq_setup)
 		return -EINVAL;
@@ -298,7 +304,11 @@ int omap_prcm_register_chain_handler(struct omap_prcm_irq_setup *irq_setup)
 				1 << (offset & 0x1f);
 	}
 
-	irq_set_chained_handler(irq_setup->irq, omap_prcm_irq_handler);
+	if (irq_setup->xlate_irq)
+		irq = irq_setup->xlate_irq(irq_setup->irq);
+	else
+		irq = irq_setup->irq;
+	irq_set_chained_handler(irq, omap_prcm_irq_handler);
 
 	irq_setup->base_irq = irq_alloc_descs(-1, 0, irq_setup->nr_regs * 32,
 		0);
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index 4457e731f7a4..292eca0e78ed 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -66,19 +66,24 @@ void __init omap_pmic_init(int bus, u32 clkrate,
 	omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
 }
 
+#ifdef CONFIG_ARCH_OMAP4
 void __init omap4_pmic_init(const char *pmic_type,
 		    struct twl4030_platform_data *pmic_data,
 		    struct i2c_board_info *devices, int nr_devices)
 {
 	/* PMIC part*/
+	unsigned int irq;
+
 	omap_mux_init_signal("sys_nirq1", OMAP_PIN_INPUT_PULLUP | OMAP_PIN_OFF_WAKEUPENABLE);
 	omap_mux_init_signal("fref_clk0_out.sys_drm_msecure", OMAP_PIN_OUTPUT);
-	omap_pmic_init(1, 400, pmic_type, 7 + OMAP44XX_IRQ_GIC_START, pmic_data);
+	irq = omap4_xlate_irq(7 + OMAP44XX_IRQ_GIC_START);
+	omap_pmic_init(1, 400, pmic_type, irq, pmic_data);
 
 	/* Register additional devices on i2c1 bus if needed */
 	if (devices)
 		i2c_register_board_info(1, devices, nr_devices);
 }
+#endif
 
 void __init omap_pmic_late_init(void)
 {
diff --git a/arch/arm/mach-shmobile/setup-r8a7778.c b/arch/arm/mach-shmobile/setup-r8a7778.c
index 170bd146ba17..cef8895a9b82 100644
--- a/arch/arm/mach-shmobile/setup-r8a7778.c
+++ b/arch/arm/mach-shmobile/setup-r8a7778.c
@@ -576,11 +576,18 @@ void __init r8a7778_init_irq_extpin(int irlm)
 void __init r8a7778_init_irq_dt(void)
 {
 	void __iomem *base = ioremap_nocache(0xfe700000, 0x00100000);
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	void __iomem *gic_dist_base = ioremap_nocache(0xfe438000, 0x1000);
+	void __iomem *gic_cpu_base = ioremap_nocache(0xfe430000, 0x1000);
+#endif
 
 	BUG_ON(!base);
 
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	gic_init(0, 29, gic_dist_base, gic_cpu_base);
+#else
 	irqchip_init();
-
+#endif
 	/* route all interrupts to ARM */
 	__raw_writel(0x73ffffff, base + INT2NTSR0);
 	__raw_writel(0xffffffff, base + INT2NTSR1);
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index 6156d172cf31..27dceaf9e688 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -720,10 +720,17 @@ static int r8a7779_set_wake(struct irq_data *data, unsigned int on)
 
 void __init r8a7779_init_irq_dt(void)
 {
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	void __iomem *gic_dist_base = ioremap_nocache(0xf0001000, 0x1000);
+	void __iomem *gic_cpu_base = ioremap_nocache(0xf0000100, 0x1000);
+#endif
 	gic_arch_extn.irq_set_wake = r8a7779_set_wake;
 
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	gic_init(0, 29, gic_dist_base, gic_cpu_base);
+#else
 	irqchip_init();
-
+#endif
 	/* route all interrupts to ARM */
 	__raw_writel(0xffffffff, INT2NTSR0);
 	__raw_writel(0x3fffffff, INT2NTSR1);
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 1c43cec971b5..066688863920 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -85,6 +85,7 @@ vdso_install:
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
+	$(Q)$(MAKE) $(clean)=$(boot)/dts
 
 define archhelp
   echo  '* Image.gz      - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 3b8d427c3985..c62b0f4d9ef6 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -3,6 +3,4 @@ dts-dirs += apm
 dts-dirs += arm
 dts-dirs += cavium
 
-always		:= $(dtb-y)
 subdir-y	:= $(dts-dirs)
-clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts
index cb3073e4e7a8..d429129ecb3d 100644
--- a/arch/arm64/boot/dts/arm/juno.dts
+++ b/arch/arm64/boot/dts/arm/juno.dts
@@ -22,7 +22,7 @@
 	};
 
 	chosen {
-		stdout-path = &soc_uart0;
+		stdout-path = "serial0:115200n8";
 	};
 
 	psci {
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index cf33f33333cc..d54dc9ac4b70 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -15,6 +15,7 @@
  */
 #include <linux/debugfs.h>
 #include <linux/fs.h>
+#include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c
index 2c9412908024..164efa009e5b 100644
--- a/arch/avr32/kernel/module.c
+++ b/arch/avr32/kernel/module.c
@@ -19,12 +19,10 @@
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
 
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
 	vfree(mod->arch.syminfo);
 	mod->arch.syminfo = NULL;
-
-	vfree(module_region);
 }
 
 static inline int check_rela(Elf32_Rela *rela, struct module *module,
@@ -291,12 +289,3 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
 
 	return ret;
 }
-
-int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
-		    struct module *module)
-{
-	vfree(module->arch.syminfo);
-	module->arch.syminfo = NULL;
-
-	return 0;
-}
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index 08a313fc2241..f772068d9e79 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -604,7 +604,7 @@ static ssize_t __sync_serial_read(struct file *file,
 				  struct timespec *ts)
 {
 	unsigned long flags;
-	int dev = MINOR(file->f_dentry->d_inode->i_rdev);
+	int dev = MINOR(file_inode(file)->i_rdev);
 	int avail;
 	struct sync_port *port;
 	unsigned char *start;
diff --git a/arch/cris/kernel/module.c b/arch/cris/kernel/module.c
index 51123f985eb5..af04cb6b6dc9 100644
--- a/arch/cris/kernel/module.c
+++ b/arch/cris/kernel/module.c
@@ -36,7 +36,7 @@ void *module_alloc(unsigned long size)
 }
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	kfree(module_region);
 }
diff --git a/arch/frv/mb93090-mb00/pci-frv.c b/arch/frv/mb93090-mb00/pci-frv.c
index 67b1d1685759..0635bd6c2af3 100644
--- a/arch/frv/mb93090-mb00/pci-frv.c
+++ b/arch/frv/mb93090-mb00/pci-frv.c
@@ -94,7 +94,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				r = &dev->resource[idx];
 				if (!r->start)
 					continue;
-				pci_claim_resource(dev, idx);
+				pci_claim_bridge_resource(dev, idx);
 			}
 		}
 		pcibios_allocate_bus_resources(&bus->children);
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 24603be24c14..29754aae5177 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -305,14 +305,12 @@ plt_target (struct plt_entry *plt)
 #endif /* !USE_BRL */
 
 void
-module_free (struct module *mod, void *module_region)
+module_arch_freeing_init (struct module *mod)
 {
-	if (mod && mod->arch.init_unw_table &&
-	    module_region == mod->module_init) {
+	if (mod->arch.init_unw_table) {
 		unw_remove_unwind_table(mod->arch.init_unw_table);
 		mod->arch.init_unw_table = NULL;
 	}
-	vfree(module_region);
 }
 
 /* Have we already seen one of these relocations? */
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 291a582777cf..900cc93e5409 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -487,45 +487,39 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 	return 0;
 }
 
-static int is_valid_resource(struct pci_dev *dev, int idx)
+void pcibios_fixup_device_resources(struct pci_dev *dev)
 {
-	unsigned int i, type_mask = IORESOURCE_IO | IORESOURCE_MEM;
-	struct resource *devr = &dev->resource[idx], *busr;
+	int idx;
 
 	if (!dev->bus)
-		return 0;
-
-	pci_bus_for_each_resource(dev->bus, busr, i) {
-		if (!busr || ((busr->flags ^ devr->flags) & type_mask))
-			continue;
-		if ((devr->start) && (devr->start >= busr->start) &&
-				(devr->end <= busr->end))
-			return 1;
-	}
-	return 0;
-}
+		return;
 
-static void pcibios_fixup_resources(struct pci_dev *dev, int start, int limit)
-{
-	int i;
+	for (idx = 0; idx < PCI_BRIDGE_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
 
-	for (i = start; i < limit; i++) {
-		if (!dev->resource[i].flags)
+		if (!r->flags || r->parent || !r->start)
 			continue;
-		if ((is_valid_resource(dev, i)))
-			pci_claim_resource(dev, i);
-	}
-}
 
-void pcibios_fixup_device_resources(struct pci_dev *dev)
-{
-	pcibios_fixup_resources(dev, 0, PCI_BRIDGE_RESOURCES);
+		pci_claim_resource(dev, idx);
+	}
 }
 EXPORT_SYMBOL_GPL(pcibios_fixup_device_resources);
 
 static void pcibios_fixup_bridge_resources(struct pci_dev *dev)
 {
-	pcibios_fixup_resources(dev, PCI_BRIDGE_RESOURCES, PCI_NUM_RESOURCES);
+	int idx;
+
+	if (!dev->bus)
+		return;
+
+	for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
+
+		if (!r->flags || r->parent || !r->start)
+			continue;
+
+		pci_claim_bridge_resource(dev, idx);
+	}
 }
 
 /*
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index b30e41c0c033..48528fb81eff 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -1026,6 +1026,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 pr, (pr && pr->name) ? pr->name : "nil");
 
 		if (pr && !(pr->flags & IORESOURCE_UNSET)) {
+			struct pci_dev *dev = bus->self;
+
 			if (request_resource(pr, res) == 0)
 				continue;
 			/*
@@ -1035,6 +1037,12 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 */
 			if (reparent_resources(pr, res) == 0)
 				continue;
+
+			if (dev && i < PCI_BRIDGE_RESOURCE_NUM &&
+			    pci_claim_bridge_resource(dev,
+						 i + PCI_BRIDGE_RESOURCES) == 0)
+				continue;
+
 		}
 		pr_warn("PCI: Cannot allocate resource region ");
 		pr_cont("%d of PCI bridge %d, will remap\n", i, bus->number);
@@ -1227,7 +1235,10 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
 				 (unsigned long long)r->end,
 				 (unsigned int)r->flags);
 
-			pci_claim_resource(dev, i);
+			if (pci_claim_resource(dev, i) == 0)
+				continue;
+
+			pci_claim_bridge_resource(dev, i);
 		}
 	}
 
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 9fd6834a2172..5d6139390bf8 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1388,7 +1388,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/mn10300/unit-asb2305/pci-asb2305.c b/arch/mn10300/unit-asb2305/pci-asb2305.c
index febb9cd83177..b5b036f64275 100644
--- a/arch/mn10300/unit-asb2305/pci-asb2305.c
+++ b/arch/mn10300/unit-asb2305/pci-asb2305.c
@@ -106,7 +106,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				if (!r->flags)
 					continue;
 				if (!r->start ||
-				    pci_claim_resource(dev, idx) < 0) {
+				    pci_claim_bridge_resource(dev, idx) < 0) {
 					printk(KERN_ERR "PCI:"
 					       " Cannot allocate resource"
 					       " region %d of bridge %s\n",
diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c
index 6b4339f8c9c2..471ff398090c 100644
--- a/arch/mn10300/unit-asb2305/pci.c
+++ b/arch/mn10300/unit-asb2305/pci.c
@@ -281,42 +281,37 @@ static int __init pci_check_direct(void)
 	return -ENODEV;
 }
 
-static int is_valid_resource(struct pci_dev *dev, int idx)
+static void pcibios_fixup_device_resources(struct pci_dev *dev)
 {
-	unsigned int i, type_mask = IORESOURCE_IO | IORESOURCE_MEM;
-	struct resource *devr = &dev->resource[idx], *busr;
-
-	if (dev->bus) {
-		pci_bus_for_each_resource(dev->bus, busr, i) {
-			if (!busr || (busr->flags ^ devr->flags) & type_mask)
-				continue;
-
-			if (devr->start &&
-			    devr->start >= busr->start &&
-			    devr->end <= busr->end)
-				return 1;
-		}
-	}
+	int idx;
 
-	return 0;
+	if (!dev->bus)
+		return;
+
+	for (idx = 0; idx < PCI_BRIDGE_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
+
+		if (!r->flags || r->parent || !r->start)
+			continue;
+
+		pci_claim_resource(dev, idx);
+	}
 }
 
-static void pcibios_fixup_device_resources(struct pci_dev *dev)
+static void pcibios_fixup_bridge_resources(struct pci_dev *dev)
 {
-	int limit, i;
+	int idx;
 
-	if (dev->bus->number != 0)
+	if (!dev->bus)
 		return;
 
-	limit = (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) ?
-		PCI_BRIDGE_RESOURCES : PCI_NUM_RESOURCES;
+	for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
 
-	for (i = 0; i < limit; i++) {
-		if (!dev->resource[i].flags)
+		if (!r->flags || r->parent || !r->start)
 			continue;
 
-		if (is_valid_resource(dev, i))
-			pci_claim_resource(dev, i);
+		pci_claim_bridge_resource(dev, idx);
 	}
 }
 
@@ -330,7 +325,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 
 	if (bus->self) {
 		pci_read_bridge_bases(bus);
-		pcibios_fixup_device_resources(bus->self);
+		pcibios_fixup_bridge_resources(bus->self);
 	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list)
diff --git a/arch/nios2/kernel/module.c b/arch/nios2/kernel/module.c
index cc924a38f22a..e2e3f13f98d5 100644
--- a/arch/nios2/kernel/module.c
+++ b/arch/nios2/kernel/module.c
@@ -36,7 +36,7 @@ void *module_alloc(unsigned long size)
 }
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	kfree(module_region);
 }
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index f9d27883a714..2d0ea25be171 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -200,7 +200,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 
 	/* Set up to return from userspace; jump to fixed address sigreturn
 	   trampoline on kuser page.  */
-	regs->ra = (unsigned long) (0x1040);
+	regs->ra = (unsigned long) (0x1044);
 
 	/* Set up registers for signal handler */
 	regs->sp = (unsigned long) frame;
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index 50dfafc3f2c1..5822e8e200e6 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -298,14 +298,10 @@ static inline unsigned long count_stubs(const Elf_Rela *rela, unsigned long n)
 }
 #endif
 
-
-/* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
 	kfree(mod->arch.section);
 	mod->arch.section = NULL;
-
-	vfree(module_region);
 }
 
 /* Additional bytes needed in front of individual sections */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 37d512d35943..2a525c938158 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1184,6 +1184,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 pr, (pr && pr->name) ? pr->name : "nil");
 
 		if (pr && !(pr->flags & IORESOURCE_UNSET)) {
+			struct pci_dev *dev = bus->self;
+
 			if (request_resource(pr, res) == 0)
 				continue;
 			/*
@@ -1193,6 +1195,11 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 */
 			if (reparent_resources(pr, res) == 0)
 				continue;
+
+			if (dev && i < PCI_BRIDGE_RESOURCE_NUM &&
+			    pci_claim_bridge_resource(dev,
+						i + PCI_BRIDGE_RESOURCES) == 0)
+				continue;
 		}
 		pr_warning("PCI: Cannot allocate resource region "
 			   "%d of PCI bridge %d, will remap\n", i, bus->number);
@@ -1401,7 +1408,10 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
 				 (unsigned long long)r->end,
 				 (unsigned int)r->flags);
 
-			pci_claim_resource(dev, i);
+			if (pci_claim_resource(dev, i) == 0)
+				continue;
+
+			pci_claim_bridge_resource(dev, i);
 		}
 	}
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 1ca125b9c226..d1916b577f2c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -699,7 +699,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index b89b59158b95..409d152585be 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -55,14 +55,10 @@ void *module_alloc(unsigned long size)
 }
 #endif
 
-/* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
-	if (mod) {
-		vfree(mod->arch.syminfo);
-		mod->arch.syminfo = NULL;
-	}
-	vfree(module_region);
+	vfree(mod->arch.syminfo);
+	mod->arch.syminfo = NULL;
 }
 
 static void check_rela(Elf_Rela *rela, struct module *me)
diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S
index 7e45d13816c1..ba44c9f55346 100644
--- a/arch/s390/net/bpf_jit.S
+++ b/arch/s390/net/bpf_jit.S
@@ -22,8 +22,8 @@
  * skb_copy_bits takes 4 parameters:
  *   %r2 = skb pointer
  *   %r3 = offset into skb data
- *   %r4 = length to copy
- *   %r5 = pointer to temp buffer
+ *   %r4 = pointer to temp buffer
+ *   %r5 = length to copy
  */
 #define SKBDATA	%r8
 
@@ -44,8 +44,9 @@ ENTRY(sk_load_word)
 
 sk_load_word_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,4			# 4 bytes
-	la	%r5,160(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,160(%r15)		# pointer to temp buffer
+	lghi	%r5,4			# 4 bytes
 	brasl	%r14,skb_copy_bits	# get data from skb
 	l	%r5,160(%r15)		# load result from temp buffer
 	ltgr	%r2,%r2			# set cc to (%r2 != 0)
@@ -69,8 +70,9 @@ ENTRY(sk_load_half)
 
 sk_load_half_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,2			# 2 bytes
-	la	%r5,162(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,162(%r15)		# pointer to temp buffer
+	lghi	%r5,2			# 2 bytes
 	brasl	%r14,skb_copy_bits	# get data from skb
 	xc	160(2,%r15),160(%r15)
 	l	%r5,160(%r15)		# load result from temp buffer
@@ -95,8 +97,9 @@ ENTRY(sk_load_byte)
 
 sk_load_byte_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,1			# 1 bytes
-	la	%r5,163(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,163(%r15)		# pointer to temp buffer
+	lghi	%r5,1			# 1 byte
 	brasl	%r14,skb_copy_bits	# get data from skb
 	xc	160(3,%r15),160(%r15)
 	l	%r5,160(%r15)		# load result from temp buffer
@@ -104,11 +107,11 @@ sk_load_byte_slow:
 	lgr	%r2,%r9			# restore %r2
 	br	%r8
 
-	/* A = (*(u8 *)(skb->data+K) & 0xf) << 2 */
+	/* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */
 ENTRY(sk_load_byte_msh)
 	llgfr	%r1,%r3			# extend offset
 	clr	%r11,%r3		# hlen < offset ?
-	jle	sk_load_byte_slow
+	jle	sk_load_byte_msh_slow
 	lhi	%r12,0
 	ic	%r12,0(%r1,%r10)	# get byte from skb
 	nill	%r12,0x0f
@@ -118,8 +121,9 @@ ENTRY(sk_load_byte_msh)
 
 sk_load_byte_msh_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,2			# 2 bytes
-	la	%r5,162(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,163(%r15)		# pointer to temp buffer
+	lghi	%r5,1			# 1 byte
 	brasl	%r14,skb_copy_bits	# get data from skb
 	xc	160(3,%r15),160(%r15)
 	l	%r12,160(%r15)		# load result from temp buffer
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 524496d47ef5..bbd1981cc150 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -448,15 +448,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		mask = 0x800000; /* je */
 kbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
-			if (K <= 16383)
-				/* chi %r5,<K> */
-				EMIT4_IMM(0xa75e0000, K);
-			else if (test_facility(21))
+			if (test_facility(21))
 				/* clfi %r5,<K> */
 				EMIT6_IMM(0xc25f0000, K);
 			else
-				/* c %r5,<d(K)>(%r13) */
-				EMIT4_DISP(0x5950d000, EMIT_CONST(K));
+				/* cl %r5,<d(K)>(%r13) */
+				EMIT4_DISP(0x5550d000, EMIT_CONST(K));
 		}
 branch:		if (filter->jt == filter->jf) {
 			if (filter->jt == 0)
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index b36365f49478..9ce5afe167ff 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -639,7 +639,10 @@ static void pci_claim_bus_resources(struct pci_bus *bus)
 				       (unsigned long long)r->end,
 				       (unsigned int)r->flags);
 
-			pci_claim_resource(dev, i);
+			if (pci_claim_resource(dev, i) == 0)
+				continue;
+
+			pci_claim_bridge_resource(dev, i);
 		}
 	}
 
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index f33e7c7a3bf7..7931eeeb649a 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -776,7 +776,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 				if (unlikely(proglen + ilen > oldproglen)) {
 					pr_err("bpb_jit_compile fatal error\n");
 					kfree(addrs);
-					module_free(NULL, image);
+					module_memfree(image);
 					return;
 				}
 				memcpy(image + proglen, temp, ilen);
@@ -822,7 +822,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c
index 96447c9160a0..2305084c9b93 100644
--- a/arch/tile/kernel/module.c
+++ b/arch/tile/kernel/module.c
@@ -74,7 +74,7 @@ error:
 
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	vfree(module_region);
 
@@ -83,7 +83,7 @@ void module_free(struct module *mod, void *module_region)
 		     0, 0, 0, NULL, NULL, 0);
 
 	/*
-	 * FIXME: If module_region == mod->module_init, trim exception
+	 * FIXME: Add module_arch_freeing_init to trim exception
 	 * table entries.
 	 */
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba397bde7948..0dc9d0144a27 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -857,7 +857,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
+	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -868,6 +868,10 @@ config X86_UP_APIC
 	  performance counters), and the NMI watchdog which detects hard
 	  lockups.
 
+config X86_UP_APIC_MSI
+	def_bool y
+	select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI
+
 config X86_UP_IOAPIC
 	bool "IO-APIC support on uniprocessors"
 	depends on X86_UP_APIC
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index dcc1c536cc21..a950864a64da 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -373,6 +373,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned long output_len,
 				  unsigned long run_size)
 {
+	unsigned char *output_orig = output;
+
 	real_mode = rmode;
 
 	sanitize_boot_params(real_mode);
@@ -421,7 +423,12 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	debug_putstr("\nDecompressing Linux... ");
 	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	parse_elf(output);
-	handle_relocations(output, output_len);
+	/*
+	 * 32-bit always performs relocations. 64-bit relocations are only
+	 * needed if kASLR has chosen a different load address.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig)
+		handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
 	return output;
 }
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 0ab4f9fd2687..3a45668f6dc3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -50,6 +50,7 @@ void acpi_pic_sci_set_trigger(unsigned int, u16);
 
 extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
 				  int trigger, int polarity);
+extern void (*__acpi_unregister_gsi)(u32 gsi);
 
 static inline void disable_acpi(void)
 {
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 50d033a8947d..a94b82e8f156 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
 }
 
-#define _LDT_empty(info)				\
+/* This intentionally ignores lm, since 32-bit apps don't have that field. */
+#define LDT_empty(info)					\
 	((info)->base_addr		== 0	&&	\
 	 (info)->limit			== 0	&&	\
 	 (info)->contents		== 0	&&	\
@@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 	 (info)->seg_not_present	== 1	&&	\
 	 (info)->useable		== 0)
 
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
+/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */
+static inline bool LDT_zero(const struct user_desc *info)
+{
+	return (info->base_addr		== 0 &&
+		info->limit		== 0 &&
+		info->contents		== 0 &&
+		info->read_exec_only	== 0 &&
+		info->seg_32bit		== 0 &&
+		info->limit_in_pages	== 0 &&
+		info->seg_not_present	== 0 &&
+		info->useable		== 0);
+}
 
 static inline void clear_LDT(void)
 {
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 40269a2bf6f9..4b75d591eb5e 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -130,7 +130,25 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 			      unsigned long start, unsigned long end)
 {
-	mpx_notify_unmap(mm, vma, start, end);
+	/*
+	 * mpx_notify_unmap() goes and reads a rarely-hot
+	 * cacheline in the mm_struct.  That can be expensive
+	 * enough to be seen in profiles.
+	 *
+	 * The mpx_notify_unmap() call and its contents have been
+	 * observed to affect munmap() performance on hardware
+	 * where MPX is not present.
+	 *
+	 * The unlikely() optimizes for the fast case: no MPX
+	 * in the CPU, or no MPX use in the process.  Even if
+	 * we get this wrong (in the unlikely event that MPX
+	 * is widely enabled on some system) the overhead of
+	 * MPX itself (reading bounds tables) is expected to
+	 * overwhelm the overhead of getting this unlikely()
+	 * consistently wrong.
+	 */
+	if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
+		mpx_notify_unmap(mm, vma, start, end);
 }
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d1626364a28a..b9e30daa0881 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -611,20 +611,20 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
 
 int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
-	int irq;
-
-	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-		*irqp = gsi;
-	} else {
-		mutex_lock(&acpi_ioapic_lock);
-		irq = mp_map_gsi_to_irq(gsi,
-					IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
-		mutex_unlock(&acpi_ioapic_lock);
-		if (irq < 0)
-			return -1;
-		*irqp = irq;
+	int rc, irq, trigger, polarity;
+
+	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
+	if (rc == 0) {
+		trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+		polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+		irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+		if (irq >= 0) {
+			*irqp = irq;
+			return 0;
+		}
 	}
-	return 0;
+
+	return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a450373e8e91..939155ffdece 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -107,6 +107,7 @@ static struct clocksource hyperv_cs = {
 	.rating		= 400, /* use this when running on Hyperv*/
 	.read		= read_hv_clock,
 	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static void __init ms_hyperv_init_platform(void)
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 2142376dc8c6..8b7b0a51e742 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size)
 }
 static inline void tramp_free(void *tramp)
 {
-	module_free(NULL, tramp);
+	module_memfree(tramp);
 }
 #else
 /* Trampolines can only be created if modules are supported */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 6307a0f0cf17..705ef8d48e2d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -127,7 +127,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_puts(p, "  Machine check polls\n");
 #endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
-	seq_printf(p, "%*s: ", prec, "THR");
+	seq_printf(p, "%*s: ", prec, "HYP");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
 	seq_puts(p, "  Hypervisor callback interrupts\n");
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 4e942f31b1a7..7fc5e843f247 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -29,7 +29,28 @@ static int get_free_idx(void)
 
 static bool tls_desc_okay(const struct user_desc *info)
 {
-	if (LDT_empty(info))
+	/*
+	 * For historical reasons (i.e. no one ever documented how any
+	 * of the segmentation APIs work), user programs can and do
+	 * assume that a struct user_desc that's all zeros except for
+	 * entry_number means "no segment at all".  This never actually
+	 * worked.  In fact, up to Linux 3.19, a struct user_desc like
+	 * this would create a 16-bit read-write segment with base and
+	 * limit both equal to zero.
+	 *
+	 * That was close enough to "no segment at all" until we
+	 * hardened this function to disallow 16-bit TLS segments.  Fix
+	 * it up by interpreting these zeroed segments the way that they
+	 * were almost certainly intended to be interpreted.
+	 *
+	 * The correct way to ask for "no segment at all" is to specify
+	 * a user_desc that satisfies LDT_empty.  To keep everything
+	 * working, we accept both.
+	 *
+	 * Note that there's a similar kludge in modify_ldt -- look at
+	 * the distinction between modes 1 and 0x11.
+	 */
+	if (LDT_empty(info) || LDT_zero(info))
 		return true;
 
 	/*
@@ -71,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx,
 	cpu = get_cpu();
 
 	while (n-- > 0) {
-		if (LDT_empty(info))
+		if (LDT_empty(info) || LDT_zero(info))
 			desc->a = desc->b = 0;
 		else
 			fill_ldt(desc, info);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b7e50bba3bbb..505449700e0c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -617,7 +617,7 @@ static unsigned long quick_pit_calibrate(void)
 			goto success;
 		}
 	}
-	pr_err("Fast TSC calibration failed\n");
+	pr_info("Fast TSC calibration failed\n");
 	return 0;
 
 success:
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 169b09d76ddd..de12c1d379f1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2348,7 +2348,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	 * Not recognized on AMD in compat mode (but is recognized in legacy
 	 * mode).
 	 */
-	if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA)
+	if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA)
 	    && !vendor_intel(ctxt))
 		return emulate_ud(ctxt);
 
@@ -2359,25 +2359,13 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
-	switch (ctxt->mode) {
-	case X86EMUL_MODE_PROT32:
-		if ((msr_data & 0xfffc) == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	case X86EMUL_MODE_PROT64:
-		if (msr_data == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	default:
-		break;
-	}
+	if ((msr_data & 0xfffc) == 0x0)
+		return emulate_gp(ctxt, 0);
 
 	ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
-	cs_sel = (u16)msr_data;
-	cs_sel &= ~SELECTOR_RPL_MASK;
+	cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK;
 	ss_sel = cs_sel + 8;
-	ss_sel &= ~SELECTOR_RPL_MASK;
-	if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) {
+	if (efer & EFER_LMA) {
 		cs.d = 0;
 		cs.l = 1;
 	}
@@ -2386,10 +2374,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data);
-	ctxt->_eip = msr_data;
+	ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data;
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
-	*reg_write(ctxt, VCPU_REGS_RSP) = msr_data;
+	*reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
+							      (u32)msr_data;
 
 	return X86EMUL_CONTINUE;
 }
@@ -3791,8 +3780,8 @@ static const struct opcode group5[] = {
 };
 
 static const struct opcode group6[] = {
-	DI(Prot,	sldt),
-	DI(Prot,	str),
+	DI(Prot | DstMem,	sldt),
+	DI(Prot | DstMem,	str),
 	II(Prot | Priv | SrcMem16, em_lldt, lldt),
 	II(Prot | Priv | SrcMem16, em_ltr, ltr),
 	N, N, N, N,
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 08a7d313538a..079c3b6a3ff1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -43,7 +43,7 @@ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
 	[_PAGE_CACHE_MODE_WT]		= _PAGE_PCD,
 	[_PAGE_CACHE_MODE_WP]		= _PAGE_PCD,
 };
-EXPORT_SYMBOL_GPL(__cachemode2pte_tbl);
+EXPORT_SYMBOL(__cachemode2pte_tbl);
 uint8_t __pte2cachemode_tbl[8] = {
 	[__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB,
 	[__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC,
@@ -54,7 +54,7 @@ uint8_t __pte2cachemode_tbl[8] = {
 	[__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
 };
-EXPORT_SYMBOL_GPL(__pte2cachemode_tbl);
+EXPORT_SYMBOL(__pte2cachemode_tbl);
 
 static unsigned long __initdata pgt_buf_start;
 static unsigned long __initdata pgt_buf_end;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 67ebf5751222..c439ec478216 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -349,6 +349,12 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
 		return MPX_INVALID_BOUNDS_DIR;
 
 	/*
+	 * 32-bit binaries on 64-bit kernels are currently
+	 * unsupported.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
+		return MPX_INVALID_BOUNDS_DIR;
+	/*
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index edf299c8ff6c..7ac68698406c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -234,8 +234,13 @@ void pat_init(void)
 	      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
 
 	/* Boot CPU check */
-	if (!boot_pat_state)
+	if (!boot_pat_state) {
 		rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
+		if (!boot_pat_state) {
+			pat_disable("PAT read returns always zero, disabled.");
+			return;
+		}
+	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
 
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 9b18ef315a55..349c0d32cc0b 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -216,7 +216,7 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
 			continue;
 		if (r->parent)	/* Already allocated */
 			continue;
-		if (!r->start || pci_claim_resource(dev, idx) < 0) {
+		if (!r->start || pci_claim_bridge_resource(dev, idx) < 0) {
 			/*
 			 * Something is wrong with the region.
 			 * Invalidate the resource to prevent
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index c489ef2c1a39..9098d880c476 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -458,6 +458,7 @@ int __init pci_xen_hvm_init(void)
 	 * just how GSIs get registered.
 	 */
 	__acpi_register_gsi = acpi_register_gsi_xen_hvm;
+	__acpi_unregister_gsi = NULL;
 #endif
 
 #ifdef CONFIG_PCI_MSI
@@ -471,52 +472,6 @@ int __init pci_xen_hvm_init(void)
 }
 
 #ifdef CONFIG_XEN_DOM0
-static __init void xen_setup_acpi_sci(void)
-{
-	int rc;
-	int trigger, polarity;
-	int gsi = acpi_sci_override_gsi;
-	int irq = -1;
-	int gsi_override = -1;
-
-	if (!gsi)
-		return;
-
-	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
-	if (rc) {
-		printk(KERN_WARNING "xen: acpi_get_override_irq failed for acpi"
-				" sci, rc=%d\n", rc);
-		return;
-	}
-	trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
-	polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
-
-	printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d "
-			"polarity=%d\n", gsi, trigger, polarity);
-
-	/* Before we bind the GSI to a Linux IRQ, check whether
-	 * we need to override it with bus_irq (IRQ) value. Usually for
-	 * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so:
-	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level)
-	 * but there are oddballs where the IRQ != GSI:
-	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level)
-	 * which ends up being: gsi_to_irq[9] == 20
-	 * (which is what acpi_gsi_to_irq ends up calling when starting the
-	 * the ACPI interpreter and keels over since IRQ 9 has not been
-	 * setup as we had setup IRQ 20 for it).
-	 */
-	if (acpi_gsi_to_irq(gsi, &irq) == 0) {
-		/* Use the provided value if it's valid. */
-		if (irq >= 0)
-			gsi_override = irq;
-	}
-
-	gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity);
-	printk(KERN_INFO "xen: acpi sci %d\n", gsi);
-
-	return;
-}
-
 int __init pci_xen_initial_domain(void)
 {
 	int irq;
@@ -527,8 +482,8 @@ int __init pci_xen_initial_domain(void)
 	x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
 	pci_msi_ignore_mask = 1;
 #endif
-	xen_setup_acpi_sci();
 	__acpi_register_gsi = acpi_register_gsi_xen;
+	__acpi_unregister_gsi = NULL;
 	/* Pre-allocate legacy irqs */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++) {
 		int trigger, polarity;