Linux-libre 4.4.4-gnupck-4.4.4-gnu

33 files changed, 339 insertions, 231 deletions

diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index 258b0e5ad..68b609234 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -22,6 +22,7 @@
 #define AUX_IRQ_CTRL		0x00E
 #define AUX_IRQ_ACT		0x043	/* Active Intr across all levels */
 #define AUX_IRQ_LVL_PEND	0x200	/* Pending Intr across all levels */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
 #define AUX_IRQ_PRIORITY	0x206
 #define ICAUSE			0x40a
 #define AUX_IRQ_SELECT		0x40b
@@ -112,6 +113,16 @@ static inline int arch_irqs_disabled(void)
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
+static inline void arc_softirq_trigger(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, irq);
+}
+
+static inline void arc_softirq_clear(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, 0);
+}
+
 #else
 
 .macro IRQ_DISABLE  scratch
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index cbfec7913..c1264607b 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -45,11 +45,12 @@ VECTOR	reserved		; Reserved slots
 VECTOR	handle_interrupt	; (16) Timer0
 VECTOR	handle_interrupt	; unused (Timer1)
 VECTOR	handle_interrupt	; unused (WDT)
-VECTOR	handle_interrupt	; (19) ICI (inter core interrupt)
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt	; (23) End of fixed IRQs
+VECTOR	handle_interrupt	; (19) Inter core Interrupt (IPI)
+VECTOR	handle_interrupt	; (20) perf Interrupt
+VECTOR	handle_interrupt	; (21) Software Triggered Intr (Self IPI)
+VECTOR	handle_interrupt	; unused
+VECTOR	handle_interrupt	; (23) unused
+# End of fixed IRQs
 
 .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8
 	VECTOR	handle_interrupt
@@ -211,7 +212,11 @@ debug_marker_syscall:
 ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig
 ; entry was via Exception in DS which got preempted in kernel).
 ;
-; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling
+; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround
+;
+; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline
+; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly
+
 .Lintr_ret_to_delay_slot:
 debug_marker_ds:
 
@@ -222,18 +227,23 @@ debug_marker_ds:
 	ld	r2, [sp, PT_ret]
 	ld	r3, [sp, PT_status32]
 
+	; STAT32 for Int return created from scratch
+	; (No delay dlot, disable Further intr in trampoline)
+
 	bic  	r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK
 	st	r0, [sp, PT_status32]
 
 	mov	r1, .Lintr_ret_to_delay_slot_2
 	st	r1, [sp, PT_ret]
 
+	; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots
 	st	r2, [sp, 0]
 	st	r3, [sp, 4]
 
 	b	.Lisr_ret_fast_path
 
 .Lintr_ret_to_delay_slot_2:
+	; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP
 	sub	sp, sp, SZ_PT_REGS
 	st	r9, [sp, -4]
 
@@ -243,11 +253,19 @@ debug_marker_ds:
 	ld	r9, [sp, 4]
 	sr	r9, [erstatus]
 
+	; restore AUX_USER_SP if returning to U mode
+	bbit0	r9, STATUS_U_BIT, 1f
+	ld	r9, [sp, PT_sp]
+	sr	r9, [AUX_USER_SP]
+
+1:
 	ld	r9, [sp, 8]
 	sr	r9, [erbta]
 
 	ld	r9, [sp, -4]
 	add	sp, sp, SZ_PT_REGS
+
+	; return from pure kernel mode to delay slot
 	rtie
 
 END(ret_from_exception)
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index bd237acdf..30d806ce0 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -11,9 +11,12 @@
 #include <linux/smp.h>
 #include <linux/irq.h>
 #include <linux/spinlock.h>
+#include <asm/irqflags-arcv2.h>
 #include <asm/mcip.h>
 #include <asm/setup.h>
 
+#define SOFTIRQ_IRQ	21
+
 static char smp_cpuinfo_buf[128];
 static int idu_detected;
 
@@ -22,6 +25,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock);
 static void mcip_setup_per_cpu(int cpu)
 {
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
+	smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ);
 }
 
 static void mcip_ipi_send(int cpu)
@@ -29,6 +33,12 @@ static void mcip_ipi_send(int cpu)
 	unsigned long flags;
 	int ipi_was_pending;
 
+	/* ARConnect can only send IPI to others */
+	if (unlikely(cpu == raw_smp_processor_id())) {
+		arc_softirq_trigger(SOFTIRQ_IRQ);
+		return;
+	}
+
 	/*
 	 * NOTE: We must spin here if the other cpu hasn't yet
 	 * serviced a previous message. This can burn lots
@@ -63,6 +73,11 @@ static void mcip_ipi_clear(int irq)
 	unsigned long flags;
 	unsigned int __maybe_unused copy;
 
+	if (unlikely(irq == SOFTIRQ_IRQ)) {
+		arc_softirq_clear(irq);
+		return;
+	}
+
 	raw_spin_lock_irqsave(&mcip_lock, flags);
 
 	/* Who sent the IPI */
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 259c0ca9c..ddbb36126 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -162,10 +162,9 @@ choice
 		  mobile SoCs in the Kona family of chips (e.g. bcm28155,
 		  bcm11351, etc...)
 
-	config DEBUG_BCM63XX
+	config DEBUG_BCM63XX_UART
 		bool "Kernel low-level debugging on BCM63XX UART"
 		depends on ARCH_BCM_63XX
-		select DEBUG_UART_BCM63XX
 
 	config DEBUG_BERLIN_UART
 		bool "Marvell Berlin SoC Debug UART"
@@ -1348,7 +1347,7 @@ config DEBUG_LL_INCLUDE
 	default "debug/vf.S" if DEBUG_VF_UART
 	default "debug/vt8500.S" if DEBUG_VT8500_UART0
 	default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1
-	default "debug/bcm63xx.S" if DEBUG_UART_BCM63XX
+	default "debug/bcm63xx.S" if DEBUG_BCM63XX_UART
 	default "debug/digicolor.S" if DEBUG_DIGICOLOR_UA0
 	default "mach/debug-macro.S"
 
@@ -1364,10 +1363,6 @@ config DEBUG_UART_8250
 		ARCH_IOP33X || ARCH_IXP4XX || \
 		ARCH_LPC32XX || ARCH_MV78XX0 || ARCH_ORION5X || ARCH_RPC
 
-# Compatibility options for BCM63xx
-config DEBUG_UART_BCM63XX
-	def_bool ARCH_BCM_63XX
-
 config DEBUG_UART_PHYS
 	hex "Physical base address of debug UART"
 	default 0x00100a00 if DEBUG_NETX_UART
@@ -1462,7 +1457,7 @@ config DEBUG_UART_PHYS
 	default 0xfffb0000 if DEBUG_OMAP1UART1 || DEBUG_OMAP7XXUART1
 	default 0xfffb0800 if DEBUG_OMAP1UART2 || DEBUG_OMAP7XXUART2
 	default 0xfffb9800 if DEBUG_OMAP1UART3 || DEBUG_OMAP7XXUART3
-	default 0xfffe8600 if DEBUG_UART_BCM63XX
+	default 0xfffe8600 if DEBUG_BCM63XX_UART
 	default 0xfffff700 if ARCH_IOP33X
 	depends on ARCH_EP93XX || \
 	        DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
@@ -1474,7 +1469,7 @@ config DEBUG_UART_PHYS
 		DEBUG_RCAR_GEN2_SCIF0 || DEBUG_RCAR_GEN2_SCIF2 || \
 		DEBUG_RMOBILE_SCIFA0 || DEBUG_RMOBILE_SCIFA1 || \
 		DEBUG_RMOBILE_SCIFA4 || DEBUG_S3C24XX_UART || \
-		DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \
+		DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \
 		DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 || \
 		DEBUG_AT91_UART
 
@@ -1515,7 +1510,7 @@ config DEBUG_UART_VIRT
 	default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT
 	default 0xfc40ab00 if DEBUG_BRCMSTB_UART
 	default 0xfc705000 if DEBUG_ZTE_ZX
-	default 0xfcfe8600 if DEBUG_UART_BCM63XX
+	default 0xfcfe8600 if DEBUG_BCM63XX_UART
 	default 0xfd000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX
 	default 0xfd000000 if ARCH_SPEAR13XX
 	default 0xfd012000 if ARCH_MV78XX0
@@ -1566,7 +1561,7 @@ config DEBUG_UART_VIRT
 		DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \
 		DEBUG_NETX_UART || \
 		DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \
-		DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \
+		DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \
 		DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0
 
 config DEBUG_UART_8250_SHIFT
diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h
index 1afe24629..b0c912fea 100644
--- a/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/arch/arm/boot/dts/sama5d2-pinfunc.h
@@ -90,7 +90,7 @@
 #define PIN_PA14__I2SC1_MCK		PINMUX_PIN(PIN_PA14, 4, 2)
 #define PIN_PA14__FLEXCOM3_IO2		PINMUX_PIN(PIN_PA14, 5, 1)
 #define PIN_PA14__D9			PINMUX_PIN(PIN_PA14, 6, 2)
-#define PIN_PA15			14
+#define PIN_PA15			15
 #define PIN_PA15__GPIO			PINMUX_PIN(PIN_PA15, 0, 0)
 #define PIN_PA15__SPI0_MOSI		PINMUX_PIN(PIN_PA15, 1, 1)
 #define PIN_PA15__TF1			PINMUX_PIN(PIN_PA15, 2, 1)
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index 68ee3ce17..b4c6d9936 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,7 +16,7 @@
 
 extern struct smp_operations psci_smp_ops;
 
-#ifdef CONFIG_ARM_PSCI
+#if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI)
 bool psci_smp_available(void);
 #else
 static inline bool psci_smp_available(void) { return false; }
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index 0375c8caa..9408a994c 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page);
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
 	/*
-	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * multiple Xen page, it's not possible to have a mix of local and
-	 * foreign Xen page. So if the first xen_pfn == mfn the page is local
-	 * otherwise it's a foreign page grant-mapped in dom0. If the page is
-	 * local we can safely call the native dma_ops function, otherwise we
-	 * call the xen specific function.
+	 * Dom0 is mapped 1:1, while the Linux page can span across
+	 * multiple Xen pages, it's not possible for it to contain a
+	 * mix of local and foreign Xen pages. So if the first xen_pfn
+	 * == mfn the page is local otherwise it's a foreign page
+	 * grant-mapped in dom0. If the page is local we can safely
+	 * call the native dma_ops function, otherwise we call the xen
+	 * specific function.
 	 */
 	if (local)
 		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 7b76ce01c..8633c7035 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base)
 
 static void set_onenand_cfg(void __iomem *onenand_base)
 {
-	u32 reg;
+	u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT;
 
-	reg = readw(onenand_base + ONENAND_REG_SYS_CFG1);
-	reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9));
 	reg |=	(latency << ONENAND_SYS_CFG1_BRL_SHIFT) |
 		ONENAND_SYS_CFG1_BL_16;
 	if (onenand_flags & ONENAND_FLAG_SYNCREAD)
@@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base)
 		reg |= ONENAND_SYS_CFG1_VHF;
 	else
 		reg &= ~ONENAND_SYS_CFG1_VHF;
+
 	writew(reg, onenand_base + ONENAND_REG_SYS_CFG1);
 }
 
@@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base)
 		}
 	}
 
+	onenand_async.sync_write = true;
 	omap2_onenand_calc_async_timings(&t);
 
 	ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async);
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index cd822d845..b6c90e500 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -27,6 +27,7 @@ $(warning LSE atomics not supported by binutils)
 endif
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr)
+KBUILD_CFLAGS	+= $(call cc-option, -mpc-relative-literal-loads)
 KBUILD_AFLAGS	+= $(lseinstr)
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index 2046c0230..21ed7150f 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -33,7 +33,7 @@
 #define PAGE_SHIFT	16
 #endif
 #define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK	(~(PAGE_SIZE - 1))
+#define PAGE_MASK	(~((1 << PAGE_SHIFT) - 1))
 
 /*
  * This is used for calculating the real page sizes
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 8957f15e2..18826aa15 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -353,7 +353,7 @@ static inline pte_t pte_mkdirty(pte_t pte)
 static inline pte_t pte_mkyoung(pte_t pte)
 {
 	pte_val(pte) |= _PAGE_ACCESSED;
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	if (!(pte_val(pte) & _PAGE_NO_READ))
 		pte_val(pte) |= _PAGE_SILENT_READ;
 	else
@@ -560,7 +560,7 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
 	pmd_val(pmd) |= _PAGE_ACCESSED;
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	if (!(pmd_val(pmd) & _PAGE_NO_READ))
 		pmd_val(pmd) |= _PAGE_SILENT_READ;
 	else
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6499d93ae..47bc45a67 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
 	if ((config_enabled(CONFIG_32BIT) ||
 	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
-	    (regs->regs[2] == __NR_syscall)) {
+	    (regs->regs[2] == __NR_syscall))
 		i++;
-		n++;
-	}
 
 	while (n--)
 		ret |= mips_get_syscall_arg(args++, task, regs, i++);
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index bf9f1a77f..a2631a52c 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -13,6 +13,9 @@
 #define SMBUS_PCI_REG64		0x64
 #define SMBUS_PCI_REGB4		0xb4
 
+#define HPET_MIN_CYCLES		64
+#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+
 static DEFINE_SPINLOCK(hpet_lock);
 DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
 
@@ -161,8 +164,9 @@ static int hpet_next_event(unsigned long delta,
 	cnt += delta;
 	hpet_write(HPET_T0_CMP, cnt);
 
-	res = ((int)(hpet_read(HPET_COUNTER) - cnt) > 0) ? -ETIME : 0;
-	return res;
+	res = (int)(cnt - hpet_read(HPET_COUNTER));
+
+	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
 
 static irqreturn_t hpet_irq_handler(int irq, void *data)
@@ -237,7 +241,7 @@ void __init setup_hpet_timer(void)
 	cd->cpumask = cpumask_of(cpu);
 	clockevent_set_clock(cd, HPET_FREQ);
 	cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
-	cd->min_delta_ns = 5000;
+	cd->min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, cd);
 
 	clockevents_register_device(cd);
 	setup_irq(HPET_T0_IRQ, &hpet_irq);
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 1a4738a8f..509832a98 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -30,13 +30,13 @@
 #include "smp.h"
 
 DEFINE_PER_CPU(int, cpu_state);
-DEFINE_PER_CPU(uint32_t, core0_c0count);
 
 static void *ipi_set0_regs[16];
 static void *ipi_clear0_regs[16];
 static void *ipi_status0_regs[16];
 static void *ipi_en0_regs[16];
 static void *ipi_mailbox_buf[16];
+static uint32_t core0_c0count[NR_CPUS];
 
 /* read a 32bit value from ipi register */
 #define loongson3_ipi_read32(addr) readl(addr)
@@ -275,12 +275,14 @@ void loongson3_ipi_interrupt(struct pt_regs *regs)
 	if (action & SMP_ASK_C0COUNT) {
 		BUG_ON(cpu != 0);
 		c0count = read_c0_count();
-		for (i = 1; i < num_possible_cpus(); i++)
-			per_cpu(core0_c0count, i) = c0count;
+		c0count = c0count ? c0count : 1;
+		for (i = 1; i < nr_cpu_ids; i++)
+			core0_c0count[i] = c0count;
+		__wbflush(); /* Let others see the result ASAP */
 	}
 }
 
-#define MAX_LOOPS 1111
+#define MAX_LOOPS 800
 /*
  * SMP init and finish on secondary CPUs
  */
@@ -305,16 +307,20 @@ static void loongson3_init_secondary(void)
 		cpu_logical_map(cpu) / loongson_sysconf.cores_per_package;
 
 	i = 0;
-	__this_cpu_write(core0_c0count, 0);
+	core0_c0count[cpu] = 0;
 	loongson3_send_ipi_single(0, SMP_ASK_C0COUNT);
-	while (!__this_cpu_read(core0_c0count)) {
+	while (!core0_c0count[cpu]) {
 		i++;
 		cpu_relax();
 	}
 
 	if (i > MAX_LOOPS)
 		i = MAX_LOOPS;
-	initcount = __this_cpu_read(core0_c0count) + i;
+	if (cpu_data[cpu].package)
+		initcount = core0_c0count[cpu] + i;
+	else /* Local access is faster for loops */
+		initcount = core0_c0count[cpu] + i/2;
+
 	write_c0_count(initcount);
 }
 
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 32e0be276..29f73e002 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -242,7 +242,7 @@ static void output_pgtable_bits_defines(void)
 	pr_define("_PAGE_HUGE_SHIFT %d\n", _PAGE_HUGE_SHIFT);
 	pr_define("_PAGE_SPLITTING_SHIFT %d\n", _PAGE_SPLITTING_SHIFT);
 #endif
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	if (cpu_has_rixi) {
 #ifdef _PAGE_NO_EXEC_SHIFT
 		pr_define("_PAGE_NO_EXEC_SHIFT %d\n", _PAGE_NO_EXEC_SHIFT);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index f69ecaa7c..52c1e273f 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 		eeh_pcid_put(dev);
 		if (driver->err_handler &&
 		    driver->err_handler->error_detected &&
-		    driver->err_handler->slot_reset &&
-		    driver->err_handler->resume)
+		    driver->err_handler->slot_reset)
 			return NULL;
 	}
 
diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h
index 2559b16da..17d9dcd29 100644
--- a/arch/s390/include/asm/fpu/internal.h
+++ b/arch/s390/include/asm/fpu/internal.h
@@ -48,6 +48,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs)
 static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
 	fpregs->pad = 0;
+	fpregs->fpc = fpu->fpc;
 	if (MACHINE_HAS_VX)
 		convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
 	else
@@ -57,6 +58,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 
 static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
+	fpu->fpc = fpregs->fpc;
 	if (MACHINE_HAS_VX)
 		convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
 	else
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index efaac2c3b..e9a983f40 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -506,7 +506,6 @@ struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
 	unsigned int      host_acrs[NUM_ACRS];
 	struct fpu	  host_fpregs;
-	struct fpu	  guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 9cd248f63..dc6c9c604 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -181,6 +181,7 @@ int main(void)
 	OFFSET(__LC_PSW_SAVE_AREA, _lowcore, psw_save_area);
 	OFFSET(__LC_PREFIX_SAVE_AREA, _lowcore, prefixreg_save_area);
 	OFFSET(__LC_FP_CREG_SAVE_AREA, _lowcore, fpt_creg_save_area);
+	OFFSET(__LC_TOD_PROGREG_SAVE_AREA, _lowcore, tod_progreg_save_area);
 	OFFSET(__LC_CPU_TIMER_SAVE_AREA, _lowcore, cpu_timer_save_area);
 	OFFSET(__LC_CLOCK_COMP_SAVE_AREA, _lowcore, clock_comp_save_area);
 	OFFSET(__LC_AREGS_SAVE_AREA, _lowcore, access_regs_save_area);
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 66c94417c..4af60374e 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs,
 
 	/* Restore high gprs from signal stack */
 	if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high,
-			     sizeof(&sregs_ext->gprs_high)))
+			     sizeof(sregs_ext->gprs_high)))
 		return -EFAULT;
 	for (i = 0; i < NUM_GPRS; i++)
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 846589281..a08d0afd5 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1268,44 +1268,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-/*
- * Backs up the current FP/VX register save area on a particular
- * destination.  Used to switch between different register save
- * areas.
- */
-static inline void save_fpu_to(struct fpu *dst)
-{
-	dst->fpc = current->thread.fpu.fpc;
-	dst->regs = current->thread.fpu.regs;
-}
-
-/*
- * Switches the FP/VX register save area from which to lazy
- * restore register contents.
- */
-static inline void load_fpu_from(struct fpu *from)
-{
-	current->thread.fpu.fpc = from->fpc;
-	current->thread.fpu.regs = from->regs;
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Save host register state */
 	save_fpu_regs();
-	save_fpu_to(&vcpu->arch.host_fpregs);
-
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-		/*
-		 * Use the register save area in the SIE-control block
-		 * for register restore and save in kvm_arch_vcpu_put()
-		 */
-		current->thread.fpu.vxrs =
-			(__vector128 *)&vcpu->run->s.regs.vrs;
-	} else
-		load_fpu_from(&vcpu->arch.guest_fpregs);
+	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
+	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
 
+	/* Depending on MACHINE_HAS_VX, data stored to vrs either
+	 * has vector register or floating point register format.
+	 */
+	current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
 		current->thread.fpu.fpc = 0;
@@ -1321,19 +1295,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 
+	/* Save guest register state */
 	save_fpu_regs();
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 
-	if (test_kvm_facility(vcpu->kvm, 129))
-		/*
-		 * kvm_arch_vcpu_load() set up the register save area to
-		 * the &vcpu->run->s.regs.vrs and, thus, the vector registers
-		 * are already saved.  Only the floating-point control must be
-		 * copied.
-		 */
-		vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-	else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
-	load_fpu_from(&vcpu->arch.host_fpregs);
+	/* Restore host register state */
+	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
+	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
 
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
@@ -1351,8 +1319,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
 	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
 	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
-	vcpu->arch.guest_fpregs.fpc = 0;
-	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+	/* make sure the new fpc will be lazily loaded */
+	save_fpu_regs();
+	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1501,19 +1470,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
 
-	/*
-	 * Allocate a save area for floating-point registers.  If the vector
-	 * extension is available, register contents are saved in the SIE
-	 * control block.  The allocated save area is still required in
-	 * particular places, for example, in kvm_s390_vcpu_store_status().
-	 */
-	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
-					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs) {
-		rc = -ENOMEM;
-		goto out_free_sie_block;
-	}
-
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
 		goto out_free_sie_block;
@@ -1734,19 +1690,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
+	/* make sure the new values will be lazily loaded */
+	save_fpu_regs();
 	if (test_fp_ctl(fpu->fpc))
 		return -EINVAL;
-	memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
-	save_fpu_regs();
-	load_fpu_from(&vcpu->arch.guest_fpregs);
+	current->thread.fpu.fpc = fpu->fpc;
+	if (MACHINE_HAS_VX)
+		convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+	else
+		memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
-	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+	/* make sure we have the latest values */
+	save_fpu_regs();
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+	else
+		memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+	fpu->fpc = current->thread.fpu.fpc;
 	return 0;
 }
 
@@ -2266,41 +2230,50 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 {
 	unsigned char archmode = 1;
+	freg_t fprs[NUM_FPRS];
 	unsigned int px;
 	u64 clkcomp;
 	int rc;
 
+	px = kvm_s390_get_prefix(vcpu);
 	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
 		if (write_guest_abs(vcpu, 163, &archmode, 1))
 			return -EFAULT;
-		gpa = SAVE_AREA_BASE;
+		gpa = 0;
 	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
 		if (write_guest_real(vcpu, 163, &archmode, 1))
 			return -EFAULT;
-		gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE);
+		gpa = px;
+	} else
+		gpa -= __LC_FPREGS_SAVE_AREA;
+
+	/* manually convert vector registers if necessary */
+	if (MACHINE_HAS_VX) {
+		convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     fprs, 128);
+	} else {
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     vcpu->run->s.regs.vrs, 128);
 	}
-	rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs),
-			     vcpu->arch.guest_fpregs.fprs, 128);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs),
+	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw),
+	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
 			      &vcpu->arch.sie_block->gpsw, 16);
-	px = kvm_s390_get_prefix(vcpu);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
+	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
 			      &px, 4);
-	rc |= write_guest_abs(vcpu,
-			      gpa + offsetof(struct save_area, fp_ctrl_reg),
-			      &vcpu->arch.guest_fpregs.fpc, 4);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg),
+	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
+			      &vcpu->run->s.regs.fpc, 4);
+	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer),
+	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
 			      &vcpu->arch.sie_block->cputm, 8);
 	clkcomp = vcpu->arch.sie_block->ckc >> 8;
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp),
+	rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
 			      &clkcomp, 8);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs),
+	rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA,
 			      &vcpu->run->s.regs.acrs, 64);
-	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs),
+	rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA,
 			      &vcpu->arch.sie_block->gcr, 128);
 	return rc ? -EFAULT : 0;
 }
@@ -2313,19 +2286,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	 * it into the save area
 	 */
 	save_fpu_regs();
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		/*
-		 * If the vector extension is available, the vector registers
-		 * which overlaps with floating-point registers are saved in
-		 * the SIE-control block.  Hence, extract the floating-point
-		 * registers and the FPC value and store them in the
-		 * guest_fpregs structure.
-		 */
-		vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc;
-		convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs,
-				 current->thread.fpu.vxrs);
-	} else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);
diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c
index 4d1ee8886..18c8b819b 100644
--- a/arch/s390/mm/extable.c
+++ b/arch/s390/mm/extable.c
@@ -52,12 +52,16 @@ void sort_extable(struct exception_table_entry *start,
 	int i;
 
 	/* Normalize entries to being relative to the start of the section */
-	for (p = start, i = 0; p < finish; p++, i += 8)
+	for (p = start, i = 0; p < finish; p++, i += 8) {
 		p->insn += i;
+		p->fixup += i + 4;
+	}
 	sort(start, finish - start, sizeof(*start), cmp_ex, NULL);
 	/* Denormalize all entries */
-	for (p = start, i = 0; p < finish; p++, i += 8)
+	for (p = start, i = 0; p < finish; p++, i += 8) {
 		p->insn -= i;
+		p->fixup -= i + 4;
+	}
 }
 
 #ifdef CONFIG_MODULES
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 30e7ddb27..c690c8e16 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -413,7 +413,7 @@ out:
 
 SYSCALL_DEFINE1(sparc64_personality, unsigned long, personality)
 {
-	int ret;
+	long ret;
 
 	if (personality(current->personality) == PER_LINUX32 &&
 	    personality(personality) == PER_LINUX)
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index 47f1ff056..22a358ef1 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -94,6 +94,8 @@ static int start_ptraced_child(void)
 {
 	int pid, n, status;
 
+	fflush(stdout);
+
 	pid = fork();
 	if (pid == 0)
 		ptrace_child();
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 6a1ae3751..15cfebaa7 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -267,6 +267,7 @@ ENTRY(entry_INT80_compat)
 	 * Interrupts are off on entry.
 	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	ASM_CLAC			/* Do this early to minimize exposure */
 	SWAPGS
 
 	/*
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 881b47686..e7de5c9a4 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu);
 
 #define __ARCH_HAS_DO_SOFTIRQ
 
+struct irq_desc;
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern int check_irq_vectors_for_cpu_disable(void);
 extern void fixup_irqs(void);
-extern void irq_force_complete_move(int);
+extern void irq_force_complete_move(struct irq_desc *desc);
 #endif
 
 #ifdef CONFIG_HAVE_KVM
@@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
 extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
 
-struct irq_desc;
 extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs);
 
 extern __visible unsigned int do_IRQ(struct pt_regs *regs);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f25321894..fdb0fbfb1 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
 	const struct cpumask *mask;
+	struct irq_desc *desc;
 	struct irq_data *idata;
 	struct irq_chip *chip;
 
@@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void)
 		if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq))
 			continue;
 
-		idata = irq_get_irq_data(irq);
+		desc = irq_to_desc(irq);
+		raw_spin_lock_irq(&desc->lock);
+		idata = irq_desc_get_irq_data(desc);
 
 		/*
 		 * Honour affinities which have been set in early boot
@@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void)
 		/* Might be lapic_chip for irq 0 */
 		if (chip->irq_set_affinity)
 			chip->irq_set_affinity(idata, mask, false);
+		raw_spin_unlock_irq(&desc->lock);
 	}
 }
 #endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 861bc59c8..a35f6b547 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -30,7 +30,7 @@ struct apic_chip_data {
 
 struct irq_domain *x86_vector_domain;
 static DEFINE_RAW_SPINLOCK(vector_lock);
-static cpumask_var_t vector_cpumask;
+static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask;
 static struct irq_chip lapic_controller;
 #ifdef	CONFIG_X86_IO_APIC
 static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
@@ -116,35 +116,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d,
 	 */
 	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
 	static int current_offset = VECTOR_OFFSET_START % 16;
-	int cpu, err;
+	int cpu, vector;
 
-	if (d->move_in_progress)
+	/*
+	 * If there is still a move in progress or the previous move has not
+	 * been cleaned up completely, tell the caller to come back later.
+	 */
+	if (d->move_in_progress ||
+	    cpumask_intersects(d->old_domain, cpu_online_mask))
 		return -EBUSY;
 
 	/* Only try and allocate irqs on cpus that are present */
-	err = -ENOSPC;
 	cpumask_clear(d->old_domain);
+	cpumask_clear(searched_cpumask);
 	cpu = cpumask_first_and(mask, cpu_online_mask);
 	while (cpu < nr_cpu_ids) {
-		int new_cpu, vector, offset;
+		int new_cpu, offset;
 
+		/* Get the possible target cpus for @mask/@cpu from the apic */
 		apic->vector_allocation_domain(cpu, vector_cpumask, mask);
 
+		/*
+		 * Clear the offline cpus from @vector_cpumask for searching
+		 * and verify whether the result overlaps with @mask. If true,
+		 * then the call to apic->cpu_mask_to_apicid_and() will
+		 * succeed as well. If not, no point in trying to find a
+		 * vector in this mask.
+		 */
+		cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask);
+		if (!cpumask_intersects(vector_searchmask, mask))
+			goto next_cpu;
+
 		if (cpumask_subset(vector_cpumask, d->domain)) {
-			err = 0;
 			if (cpumask_equal(vector_cpumask, d->domain))
-				break;
+				goto success;
 			/*
-			 * New cpumask using the vector is a proper subset of
-			 * the current in use mask. So cleanup the vector
-			 * allocation for the members that are not used anymore.
+			 * Mark the cpus which are not longer in the mask for
+			 * cleanup.
 			 */
-			cpumask_andnot(d->old_domain, d->domain,
-				       vector_cpumask);
-			d->move_in_progress =
-			   cpumask_intersects(d->old_domain, cpu_online_mask);
-			cpumask_and(d->domain, d->domain, vector_cpumask);
-			break;
+			cpumask_andnot(d->old_domain, d->domain, vector_cpumask);
+			vector = d->cfg.vector;
+			goto update;
 		}
 
 		vector = current_vector;
@@ -156,45 +168,60 @@ next:
 			vector = FIRST_EXTERNAL_VECTOR + offset;
 		}
 
-		if (unlikely(current_vector == vector)) {
-			cpumask_or(d->old_domain, d->old_domain,
-				   vector_cpumask);
-			cpumask_andnot(vector_cpumask, mask, d->old_domain);
-			cpu = cpumask_first_and(vector_cpumask,
-						cpu_online_mask);
-			continue;
-		}
+		/* If the search wrapped around, try the next cpu */
+		if (unlikely(current_vector == vector))
+			goto next_cpu;
 
 		if (test_bit(vector, used_vectors))
 			goto next;
 
-		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
+		for_each_cpu(new_cpu, vector_searchmask) {
 			if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
 				goto next;
 		}
 		/* Found one! */
 		current_vector = vector;
 		current_offset = offset;
-		if (d->cfg.vector) {
+		/* Schedule the old vector for cleanup on all cpus */
+		if (d->cfg.vector)
 			cpumask_copy(d->old_domain, d->domain);
-			d->move_in_progress =
-			   cpumask_intersects(d->old_domain, cpu_online_mask);
-		}
-		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
+		for_each_cpu(new_cpu, vector_searchmask)
 			per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
-		d->cfg.vector = vector;
-		cpumask_copy(d->domain, vector_cpumask);
-		err = 0;
-		break;
-	}
+		goto update;
 
-	if (!err) {
-		/* cache destination APIC IDs into cfg->dest_apicid */
-		err = apic->cpu_mask_to_apicid_and(mask, d->domain,
-						   &d->cfg.dest_apicid);
+next_cpu:
+		/*
+		 * We exclude the current @vector_cpumask from the requested
+		 * @mask and try again with the next online cpu in the
+		 * result. We cannot modify @mask, so we use @vector_cpumask
+		 * as a temporary buffer here as it will be reassigned when
+		 * calling apic->vector_allocation_domain() above.
+		 */
+		cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask);
+		cpumask_andnot(vector_cpumask, mask, searched_cpumask);
+		cpu = cpumask_first_and(vector_cpumask, cpu_online_mask);
+		continue;
 	}
+	return -ENOSPC;
 
-	return err;
+update:
+	/*
+	 * Exclude offline cpus from the cleanup mask and set the
+	 * move_in_progress flag when the result is not empty.
+	 */
+	cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
+	d->move_in_progress = !cpumask_empty(d->old_domain);
+	d->cfg.vector = vector;
+	cpumask_copy(d->domain, vector_cpumask);
+success:
+	/*
+	 * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail
+	 * as we already established, that mask & d->domain & cpu_online_mask
+	 * is not empty.
+	 */
+	BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain,
+					    &d->cfg.dest_apicid));
+	return 0;
 }
 
 static int assign_irq_vector(int irq, struct apic_chip_data *data,
@@ -224,10 +251,8 @@ static int assign_irq_vector_policy(int irq, int node,
 static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
 	struct irq_desc *desc;
-	unsigned long flags;
 	int cpu, vector;
 
-	raw_spin_lock_irqsave(&vector_lock, flags);
 	BUG_ON(!data->cfg.vector);
 
 	vector = data->cfg.vector;
@@ -237,10 +262,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 	data->cfg.vector = 0;
 	cpumask_clear(data->domain);
 
-	if (likely(!data->move_in_progress)) {
-		raw_spin_unlock_irqrestore(&vector_lock, flags);
+	/*
+	 * If move is in progress or the old_domain mask is not empty,
+	 * i.e. the cleanup IPI has not been processed yet, we need to remove
+	 * the old references to desc from all cpus vector tables.
+	 */
+	if (!data->move_in_progress && cpumask_empty(data->old_domain))
 		return;
-	}
 
 	desc = irq_to_desc(irq);
 	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
@@ -253,7 +281,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 		}
 	}
 	data->move_in_progress = 0;
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
 }
 
 void init_irq_alloc_info(struct irq_alloc_info *info,
@@ -274,19 +301,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
 static void x86_vector_free_irqs(struct irq_domain *domain,
 				 unsigned int virq, unsigned int nr_irqs)
 {
+	struct apic_chip_data *apic_data;
 	struct irq_data *irq_data;
+	unsigned long flags;
 	int i;
 
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
 		if (irq_data && irq_data->chip_data) {
+			raw_spin_lock_irqsave(&vector_lock, flags);
 			clear_irq_vector(virq + i, irq_data->chip_data);
-			free_apic_chip_data(irq_data->chip_data);
+			apic_data = irq_data->chip_data;
+			irq_domain_reset_irq_data(irq_data);
+			raw_spin_unlock_irqrestore(&vector_lock, flags);
+			free_apic_chip_data(apic_data);
 #ifdef	CONFIG_X86_IO_APIC
 			if (virq + i < nr_legacy_irqs())
 				legacy_irq_data[virq + i] = NULL;
 #endif
-			irq_domain_reset_irq_data(irq_data);
 		}
 	}
 }
@@ -404,6 +436,8 @@ int __init arch_early_irq_init(void)
 	arch_init_htirq_domain(x86_vector_domain);
 
 	BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL));
 
 	return arch_early_ioapic_init();
 }
@@ -492,14 +526,7 @@ static int apic_set_affinity(struct irq_data *irq_data,
 		return -EINVAL;
 
 	err = assign_irq_vector(irq, data, dest);
-	if (err) {
-		if (assign_irq_vector(irq, data,
-				      irq_data_get_affinity_mask(irq_data)))
-			pr_err("Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
-
-	return IRQ_SET_MASK_OK;
+	return err ? err : IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip lapic_controller = {
@@ -511,20 +538,12 @@ static struct irq_chip lapic_controller = {
 #ifdef CONFIG_SMP
 static void __send_cleanup_vector(struct apic_chip_data *data)
 {
-	cpumask_var_t cleanup_mask;
-
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-
-		for_each_cpu_and(i, data->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i),
-					    IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
+	raw_spin_lock(&vector_lock);
+	cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
 	data->move_in_progress = 0;
+	if (!cpumask_empty(data->old_domain))
+		apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR);
+	raw_spin_unlock(&vector_lock);
 }
 
 void send_cleanup_vector(struct irq_cfg *cfg)
@@ -568,12 +587,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			goto unlock;
 
 		/*
-		 * Check if the irq migration is in progress. If so, we
-		 * haven't received the cleanup request yet for this irq.
+		 * Nothing to cleanup if irq migration is in progress
+		 * or this cpu is not set in the cleanup mask.
 		 */
-		if (data->move_in_progress)
+		if (data->move_in_progress ||
+		    !cpumask_test_cpu(me, data->old_domain))
 			goto unlock;
 
+		/*
+		 * We have two cases to handle here:
+		 * 1) vector is unchanged but the target mask got reduced
+		 * 2) vector and the target mask has changed
+		 *
+		 * #1 is obvious, but in #2 we have two vectors with the same
+		 * irq descriptor: the old and the new vector. So we need to
+		 * make sure that we only cleanup the old vector. The new
+		 * vector has the current @vector number in the config and
+		 * this cpu is part of the target mask. We better leave that
+		 * one alone.
+		 */
 		if (vector == data->cfg.vector &&
 		    cpumask_test_cpu(me, data->domain))
 			goto unlock;
@@ -591,6 +623,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			goto unlock;
 		}
 		__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+		cpumask_clear_cpu(me, data->old_domain);
 unlock:
 		raw_spin_unlock(&desc->lock);
 	}
@@ -619,12 +652,48 @@ void irq_complete_move(struct irq_cfg *cfg)
 	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
 }
 
-void irq_force_complete_move(int irq)
+/*
+ * Called with @desc->lock held and interrupts disabled.
+ */
+void irq_force_complete_move(struct irq_desc *desc)
 {
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_data *irqdata = irq_desc_get_irq_data(desc);
+	struct apic_chip_data *data = apic_chip_data(irqdata);
+	struct irq_cfg *cfg = data ? &data->cfg : NULL;
 
-	if (cfg)
-		__irq_complete_move(cfg, cfg->vector);
+	if (!cfg)
+		return;
+
+	__irq_complete_move(cfg, cfg->vector);
+
+	/*
+	 * This is tricky. If the cleanup of @data->old_domain has not been
+	 * done yet, then the following setaffinity call will fail with
+	 * -EBUSY. This can leave the interrupt in a stale state.
+	 *
+	 * The cleanup cannot make progress because we hold @desc->lock. So in
+	 * case @data->old_domain is not yet cleaned up, we need to drop the
+	 * lock and acquire it again. @desc cannot go away, because the
+	 * hotplug code holds the sparse irq lock.
+	 */
+	raw_spin_lock(&vector_lock);
+	/* Clean out all offline cpus (including ourself) first. */
+	cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
+	while (!cpumask_empty(data->old_domain)) {
+		raw_spin_unlock(&vector_lock);
+		raw_spin_unlock(&desc->lock);
+		cpu_relax();
+		raw_spin_lock(&desc->lock);
+		/*
+		 * Reevaluate apic_chip_data. It might have been cleared after
+		 * we dropped @desc->lock.
+		 */
+		data = apic_chip_data(irqdata);
+		if (!data)
+			return;
+		raw_spin_lock(&vector_lock);
+	}
+	raw_spin_unlock(&vector_lock);
 }
 #endif
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index f8062aaf5..61521dc19 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -462,7 +462,7 @@ void fixup_irqs(void)
 		 * non intr-remapping case, we can't wait till this interrupt
 		 * arrives at this cpu before completing the irq move.
 		 */
-		irq_force_complete_move(irq);
+		irq_force_complete_move(desc);
 
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			break_affinity = 1;
@@ -470,6 +470,15 @@ void fixup_irqs(void)
 		}
 
 		chip = irq_data_get_irq_chip(data);
+		/*
+		 * The interrupt descriptor might have been cleaned up
+		 * already, but it is not yet removed from the radix tree
+		 */
+		if (!chip) {
+			raw_spin_unlock(&desc->lock);
+			continue;
+		}
+
 		if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
 			chip->irq_mask(data);
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1505587d0..b9b09fec1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 	u16 sel;
 
 	la = seg_base(ctxt, addr.seg) + addr.ea;
-	*linear = la;
 	*max_size = 0;
 	switch (mode) {
 	case X86EMUL_MODE_PROT64:
+		*linear = la;
 		if (is_noncanonical_address(la))
 			goto bad;
 
@@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 			goto bad;
 		break;
 	default:
+		*linear = la = (u32)la;
 		usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL,
 						addr.seg);
 		if (!usable)
@@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 			if (size > *max_size)
 				goto bad;
 		}
-		la &= (u32)-1;
 		break;
 	}
 	if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 3058a22a6..7be8a2513 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 			return ret;
 
 		kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
-		walker->ptes[level] = pte;
+		walker->ptes[level - 1] = pte;
 	}
 	return 0;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a2ed8904..6ef3856aa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2736,6 +2736,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+	vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b2fd67da1..ef05755a1 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
 		break;
 	}
 
-	if (regno > nr_registers) {
+	if (regno >= nr_registers) {
 		WARN_ONCE(1, "decoded an instruction with an invalid register");
 		return -EINVAL;
 	}