Linux-libre 4.2.1-gnupck-4.2.1-gnu

17 files changed, 127 insertions, 145 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 1c5021002..ede2526ec 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -536,6 +536,7 @@ config ARCH_ORION5X
 	select MVEBU_MBUS
 	select PCI
 	select PLAT_ORION_LEGACY
+	select MULTI_IRQ_HANDLER
 	help
 	  Support for the following Marvell Orion 5x series SoCs:
 	  Orion-1 (5181), Orion-VoIP (5181L), Orion-NAS (5182),
diff --git a/arch/arm/boot/dts/exynos3250-rinato.dts b/arch/arm/boot/dts/exynos3250-rinato.dts
index 031853b75..baa9b2f52 100644
--- a/arch/arm/boot/dts/exynos3250-rinato.dts
+++ b/arch/arm/boot/dts/exynos3250-rinato.dts
@@ -182,7 +182,7 @@
 
 		display-timings {
 			timing-0 {
-				clock-frequency = <0>;
+				clock-frequency = <4600000>;
 				hactive = <320>;
 				vactive = <320>;
 				hfront-porch = <1>;
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 22316d004..858efd0c8 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -626,7 +626,7 @@
 		compatible = "rockchip,rk3288-wdt", "snps,dw-wdt";
 		reg = <0xff800000 0x100>;
 		clocks = <&cru PCLK_WDT>;
-		interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
 
diff --git a/arch/arm/mach-bcm/bcm63xx_smp.c b/arch/arm/mach-bcm/bcm63xx_smp.c
index 3f014f18c..b8e18cc8f 100644
--- a/arch/arm/mach-bcm/bcm63xx_smp.c
+++ b/arch/arm/mach-bcm/bcm63xx_smp.c
@@ -127,7 +127,7 @@ static int bcm63138_smp_boot_secondary(unsigned int cpu,
 	}
 
 	/* Locate the secondary CPU node */
-	dn = of_get_cpu_node(cpu_logical_map(cpu), NULL);
+	dn = of_get_cpu_node(cpu, NULL);
 	if (!dn) {
 		pr_err("SMP: failed to locate secondary CPU%d node\n", cpu);
 		ret = -ENODEV;
diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c
index 57d5df0c1..7581e036b 100644
--- a/arch/arm/mach-omap2/clockdomains7xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains7xx_data.c
@@ -331,7 +331,7 @@ static struct clockdomain l4per2_7xx_clkdm = {
 	.dep_bit	  = DRA7XX_L4PER2_STATDEP_SHIFT,
 	.wkdep_srcs	  = l4per2_wkup_sleep_deps,
 	.sleepdep_srcs	  = l4per2_wkup_sleep_deps,
-	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+	.flags		  = CLKDM_CAN_SWSUP,
 };
 
 static struct clockdomain mpu0_7xx_clkdm = {
diff --git a/arch/arm/mach-orion5x/include/mach/irqs.h b/arch/arm/mach-orion5x/include/mach/irqs.h
index a6fa9d8f1..2431d9923 100644
--- a/arch/arm/mach-orion5x/include/mach/irqs.h
+++ b/arch/arm/mach-orion5x/include/mach/irqs.h
@@ -16,42 +16,42 @@
 /*
  * Orion Main Interrupt Controller
  */
-#define IRQ_ORION5X_BRIDGE		0
-#define IRQ_ORION5X_DOORBELL_H2C	1
-#define IRQ_ORION5X_DOORBELL_C2H	2
-#define IRQ_ORION5X_UART0		3
-#define IRQ_ORION5X_UART1		4
-#define IRQ_ORION5X_I2C			5
-#define IRQ_ORION5X_GPIO_0_7		6
-#define IRQ_ORION5X_GPIO_8_15		7
-#define IRQ_ORION5X_GPIO_16_23		8
-#define IRQ_ORION5X_GPIO_24_31		9
-#define IRQ_ORION5X_PCIE0_ERR		10
-#define IRQ_ORION5X_PCIE0_INT		11
-#define IRQ_ORION5X_USB1_CTRL		12
-#define IRQ_ORION5X_DEV_BUS_ERR		14
-#define IRQ_ORION5X_PCI_ERR		15
-#define IRQ_ORION5X_USB_BR_ERR		16
-#define IRQ_ORION5X_USB0_CTRL		17
-#define IRQ_ORION5X_ETH_RX		18
-#define IRQ_ORION5X_ETH_TX		19
-#define IRQ_ORION5X_ETH_MISC		20
-#define IRQ_ORION5X_ETH_SUM		21
-#define IRQ_ORION5X_ETH_ERR		22
-#define IRQ_ORION5X_IDMA_ERR		23
-#define IRQ_ORION5X_IDMA_0		24
-#define IRQ_ORION5X_IDMA_1		25
-#define IRQ_ORION5X_IDMA_2		26
-#define IRQ_ORION5X_IDMA_3		27
-#define IRQ_ORION5X_CESA		28
-#define IRQ_ORION5X_SATA		29
-#define IRQ_ORION5X_XOR0		30
-#define IRQ_ORION5X_XOR1		31
+#define IRQ_ORION5X_BRIDGE		(1 + 0)
+#define IRQ_ORION5X_DOORBELL_H2C	(1 + 1)
+#define IRQ_ORION5X_DOORBELL_C2H	(1 + 2)
+#define IRQ_ORION5X_UART0		(1 + 3)
+#define IRQ_ORION5X_UART1		(1 + 4)
+#define IRQ_ORION5X_I2C			(1 + 5)
+#define IRQ_ORION5X_GPIO_0_7		(1 + 6)
+#define IRQ_ORION5X_GPIO_8_15		(1 + 7)
+#define IRQ_ORION5X_GPIO_16_23		(1 + 8)
+#define IRQ_ORION5X_GPIO_24_31		(1 + 9)
+#define IRQ_ORION5X_PCIE0_ERR		(1 + 10)
+#define IRQ_ORION5X_PCIE0_INT		(1 + 11)
+#define IRQ_ORION5X_USB1_CTRL		(1 + 12)
+#define IRQ_ORION5X_DEV_BUS_ERR		(1 + 14)
+#define IRQ_ORION5X_PCI_ERR		(1 + 15)
+#define IRQ_ORION5X_USB_BR_ERR		(1 + 16)
+#define IRQ_ORION5X_USB0_CTRL		(1 + 17)
+#define IRQ_ORION5X_ETH_RX		(1 + 18)
+#define IRQ_ORION5X_ETH_TX		(1 + 19)
+#define IRQ_ORION5X_ETH_MISC		(1 + 20)
+#define IRQ_ORION5X_ETH_SUM		(1 + 21)
+#define IRQ_ORION5X_ETH_ERR		(1 + 22)
+#define IRQ_ORION5X_IDMA_ERR		(1 + 23)
+#define IRQ_ORION5X_IDMA_0		(1 + 24)
+#define IRQ_ORION5X_IDMA_1		(1 + 25)
+#define IRQ_ORION5X_IDMA_2		(1 + 26)
+#define IRQ_ORION5X_IDMA_3		(1 + 27)
+#define IRQ_ORION5X_CESA		(1 + 28)
+#define IRQ_ORION5X_SATA		(1 + 29)
+#define IRQ_ORION5X_XOR0		(1 + 30)
+#define IRQ_ORION5X_XOR1		(1 + 31)
 
 /*
  * Orion General Purpose Pins
  */
-#define IRQ_ORION5X_GPIO_START	32
+#define IRQ_ORION5X_GPIO_START	33
 #define NR_GPIO_IRQS		32
 
 #define NR_IRQS			(IRQ_ORION5X_GPIO_START + NR_GPIO_IRQS)
diff --git a/arch/arm/mach-orion5x/irq.c b/arch/arm/mach-orion5x/irq.c
index cd4bac4d7..086ecb87d 100644
--- a/arch/arm/mach-orion5x/irq.c
+++ b/arch/arm/mach-orion5x/irq.c
@@ -42,7 +42,7 @@ __exception_irq_entry orion5x_legacy_handle_irq(struct pt_regs *regs)
 	stat = readl_relaxed(MAIN_IRQ_CAUSE);
 	stat &= readl_relaxed(MAIN_IRQ_MASK);
 	if (stat) {
-		unsigned int hwirq = __fls(stat);
+		unsigned int hwirq = 1 + __fls(stat);
 		handle_IRQ(hwirq, regs);
 		return;
 	}
@@ -51,7 +51,7 @@ __exception_irq_entry orion5x_legacy_handle_irq(struct pt_regs *regs)
 
 void __init orion5x_init_irq(void)
 {
-	orion_irq_init(0, MAIN_IRQ_MASK);
+	orion_irq_init(1, MAIN_IRQ_MASK);
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	set_handle_irq(orion5x_legacy_handle_irq);
diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c
index 8fcec1cc1..01b3e3683 100644
--- a/arch/arm/mach-rockchip/platsmp.c
+++ b/arch/arm/mach-rockchip/platsmp.c
@@ -72,29 +72,22 @@ static struct reset_control *rockchip_get_core_reset(int cpu)
 static int pmu_set_power_domain(int pd, bool on)
 {
 	u32 val = (on) ? 0 : BIT(pd);
+	struct reset_control *rstc = rockchip_get_core_reset(pd);
 	int ret;
 
+	if (IS_ERR(rstc) && read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) {
+		pr_err("%s: could not get reset control for core %d\n",
+		       __func__, pd);
+		return PTR_ERR(rstc);
+	}
+
 	/*
 	 * We need to soft reset the cpu when we turn off the cpu power domain,
 	 * or else the active processors might be stalled when the individual
 	 * processor is powered down.
 	 */
-	if (read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) {
-		struct reset_control *rstc = rockchip_get_core_reset(pd);
-
-		if (IS_ERR(rstc)) {
-			pr_err("%s: could not get reset control for core %d\n",
-			       __func__, pd);
-			return PTR_ERR(rstc);
-		}
-
-		if (on)
-			reset_control_deassert(rstc);
-		else
-			reset_control_assert(rstc);
-
-		reset_control_put(rstc);
-	}
+	if (!IS_ERR(rstc) && !on)
+		reset_control_assert(rstc);
 
 	ret = regmap_update_bits(pmu, PMU_PWRDN_CON, BIT(pd), val);
 	if (ret < 0) {
@@ -112,6 +105,12 @@ static int pmu_set_power_domain(int pd, bool on)
 		}
 	}
 
+	if (!IS_ERR(rstc)) {
+		if (on)
+			reset_control_deassert(rstc);
+		reset_control_put(rstc);
+	}
+
 	return 0;
 }
 
@@ -146,8 +145,12 @@ static int rockchip_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		 * the mailbox:
 		 * sram_base_addr + 4: 0xdeadbeaf
 		 * sram_base_addr + 8: start address for pc
+		 * The cpu0 need to wait the other cpus other than cpu0 entering
+		 * the wfe state.The wait time is affected by many aspects.
+		 * (e.g: cpu frequency, bootrom frequency, sram frequency, ...)
 		 * */
-		udelay(10);
+		mdelay(1); /* ensure the cpus other than cpu0 to startup */
+
 		writel(virt_to_phys(secondary_startup), sram_base_addr + 8);
 		writel(0xDEADBEAF, sram_base_addr + 4);
 		dsb_sev();
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index b027a8973..c6d601cc9 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -421,14 +421,20 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
 	v = pte & ~HPTE_V_HVLOCK;
 	if (v & HPTE_V_VALID) {
-		u64 pte1;
-
-		pte1 = be64_to_cpu(hpte[1]);
 		hpte[0] &= ~cpu_to_be64(HPTE_V_VALID);
-		rb = compute_tlbie_rb(v, pte1, pte_index);
+		rb = compute_tlbie_rb(v, be64_to_cpu(hpte[1]), pte_index);
 		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
-		/* Read PTE low word after tlbie to get final R/C values */
-		remove_revmap_chain(kvm, pte_index, rev, v, pte1);
+		/*
+		 * The reference (R) and change (C) bits in a HPT
+		 * entry can be set by hardware at any time up until
+		 * the HPTE is invalidated and the TLB invalidation
+		 * sequence has completed.  This means that when
+		 * removing a HPTE, we need to re-read the HPTE after
+		 * the invalidation sequence has completed in order to
+		 * obtain reliable values of R and C.
+		 */
+		remove_revmap_chain(kvm, pte_index, rev, v,
+				    be64_to_cpu(hpte[1]));
 	}
 	r = rev->guest_rpte & ~HPTE_GR_RESERVED;
 	note_hpte_modification(kvm, rev);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index faa86e9c0..76408cf0a 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1127,6 +1127,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
 	bne	3f
 	lbz	r0, HSTATE_HOST_IPI(r13)
+	cmpwi	r0, 0
 	beq	4f
 	b	guest_exit_cont
 3:
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ca070d260..b80512b9e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -688,7 +688,7 @@ static void __init setup_memory(void)
 /*
  * Setup hardware capabilities.
  */
-static void __init setup_hwcaps(void)
+static int __init setup_hwcaps(void)
 {
 	static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 };
 	struct cpuid cpu_id;
@@ -754,9 +754,11 @@ static void __init setup_hwcaps(void)
 		elf_hwcap |= HWCAP_S390_TE;
 
 	/*
-	 * Vector extension HWCAP_S390_VXRS is bit 11.
+	 * Vector extension HWCAP_S390_VXRS is bit 11. The Vector extension
+	 * can be disabled with the "novx" parameter. Use MACHINE_HAS_VX
+	 * instead of facility bit 129.
 	 */
-	if (test_facility(129))
+	if (MACHINE_HAS_VX)
 		elf_hwcap |= HWCAP_S390_VXRS;
 	get_cpu_id(&cpu_id);
 	add_device_randomness(&cpu_id, sizeof(cpu_id));
@@ -793,7 +795,9 @@ static void __init setup_hwcaps(void)
 		strcpy(elf_platform, "z13");
 		break;
 	}
+	return 0;
 }
+arch_initcall(setup_hwcaps);
 
 /*
  * Add system information as device randomness
@@ -881,11 +885,6 @@ void __init setup_arch(char **cmdline_p)
         cpu_init();
 
 	/*
-	 * Setup capabilities (ELF_HWCAP & ELF_PLATFORM).
-	 */
-	setup_hwcaps();
-
-	/*
 	 * Create kernel page tables and switch to virtual addressing.
 	 */
         paging_init();
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 64d7cf1b5..440df0c7a 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -294,6 +294,7 @@ static struct ahash_alg ghash_async_alg = {
 			.cra_name		= "ghash",
 			.cra_driver_name	= "ghash-clmulni",
 			.cra_priority		= 400,
+			.cra_ctxsize		= sizeof(struct ghash_async_ctx),
 			.cra_flags		= CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
 			.cra_blocksize		= GHASH_BLOCK_SIZE,
 			.cra_type		= &crypto_ahash_type,
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index e49ee24da..939389671 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -445,6 +445,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 		polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
 
 	mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+	acpi_penalize_sci_irq(bus_irq, trigger, polarity);
 
 	/*
 	 * stash over-ride to indicate we've been here
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 844f56c56..c93c27df9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -146,6 +146,27 @@ void mce_intel_hcpu_update(unsigned long cpu)
 	per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
 }
 
+static void cmci_toggle_interrupt_mode(bool on)
+{
+	unsigned long flags, *owned;
+	int bank;
+	u64 val;
+
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	owned = this_cpu_ptr(mce_banks_owned);
+	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
+		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+
+		if (on)
+			val |= MCI_CTL2_CMCI_EN;
+		else
+			val &= ~MCI_CTL2_CMCI_EN;
+
+		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	}
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
 unsigned long cmci_intel_adjust_timer(unsigned long interval)
 {
 	if ((this_cpu_read(cmci_backoff_cnt) > 0) &&
@@ -175,7 +196,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
 		 */
 		if (!atomic_read(&cmci_storm_on_cpus)) {
 			__this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
-			cmci_reenable();
+			cmci_toggle_interrupt_mode(true);
 			cmci_recheck();
 		}
 		return CMCI_POLL_INTERVAL;
@@ -186,22 +207,6 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval)
 	}
 }
 
-static void cmci_storm_disable_banks(void)
-{
-	unsigned long flags, *owned;
-	int bank;
-	u64 val;
-
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	owned = this_cpu_ptr(mce_banks_owned);
-	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
-		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
-		val &= ~MCI_CTL2_CMCI_EN;
-		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	}
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
-
 static bool cmci_storm_detect(void)
 {
 	unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
@@ -223,7 +228,7 @@ static bool cmci_storm_detect(void)
 	if (cnt <= CMCI_STORM_THRESHOLD)
 		return false;
 
-	cmci_storm_disable_banks();
+	cmci_toggle_interrupt_mode(false);
 	__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
 	r = atomic_add_return(1, &cmci_storm_on_cpus);
 	mce_timer_kick(CMCI_STORM_INTERVAL);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 44171462b..82362ad2f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -357,12 +357,6 @@ static u64 __get_spte_lockless(u64 *sptep)
 {
 	return ACCESS_ONCE(*sptep);
 }
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
-	/* It is valid if the spte is zapped. */
-	return spte == 0ull;
-}
 #else
 union split_spte {
 	struct {
@@ -478,23 +472,6 @@ retry:
 
 	return spte.spte;
 }
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
-	union split_spte sspte = (union split_spte)spte;
-	u32 high_mmio_mask = shadow_mmio_mask >> 32;
-
-	/* It is valid if the spte is zapped. */
-	if (spte == 0ull)
-		return true;
-
-	/* It is valid if the spte is being zapped. */
-	if (sspte.spte_low == 0ull &&
-	    (sspte.spte_high & high_mmio_mask) == high_mmio_mask)
-		return true;
-
-	return false;
-}
 #endif
 
 static bool spte_is_locklessly_modifiable(u64 spte)
@@ -3299,21 +3276,6 @@ static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 	return vcpu_match_mmio_gva(vcpu, addr);
 }
 
-
-/*
- * On direct hosts, the last spte is only allows two states
- * for mmio page fault:
- *   - It is the mmio spte
- *   - It is zapped or it is being zapped.
- *
- * This function completely checks the spte when the last spte
- * is not the mmio spte.
- */
-static bool check_direct_spte_mmio_pf(u64 spte)
-{
-	return __check_direct_spte_mmio_pf(spte);
-}
-
 static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
 {
 	struct kvm_shadow_walk_iterator iterator;
@@ -3356,13 +3318,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 	}
 
 	/*
-	 * It's ok if the gva is remapped by other cpus on shadow guest,
-	 * it's a BUG if the gfn is not a mmio page.
-	 */
-	if (direct && !check_direct_spte_mmio_pf(spte))
-		return RET_MMIO_PF_BUG;
-
-	/*
 	 * If the page table is zapped by other cpus, let CPU fault again on
 	 * the address.
 	 */
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 677bfcf4e..28f33a8b7 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -25,30 +25,39 @@ static inline void spill_registers(void)
 {
 #if XCHAL_NUM_AREGS > 16
 	__asm__ __volatile__ (
-		"	call12	1f\n"
+		"	call8	1f\n"
 		"	_j	2f\n"
 		"	retw\n"
 		"	.align	4\n"
 		"1:\n"
+#if XCHAL_NUM_AREGS == 32
+		"	_entry	a1, 32\n"
+		"	addi	a8, a0, 3\n"
+		"	_entry	a1, 16\n"
+		"	mov	a12, a12\n"
+		"	retw\n"
+#else
 		"	_entry	a1, 48\n"
-		"	addi	a12, a0, 3\n"
-#if XCHAL_NUM_AREGS > 32
-		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+		"	call12	1f\n"
+		"	retw\n"
+		"	.align	4\n"
+		"1:\n"
+		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 16) / 12\n"
 		"	_entry	a1, 48\n"
 		"	mov	a12, a0\n"
 		"	.endr\n"
-#endif
-		"	_entry	a1, 48\n"
+		"	_entry	a1, 16\n"
 #if XCHAL_NUM_AREGS % 12 == 0
-		"	mov	a8, a8\n"
-#elif XCHAL_NUM_AREGS % 12 == 4
 		"	mov	a12, a12\n"
-#elif XCHAL_NUM_AREGS % 12 == 8
+#elif XCHAL_NUM_AREGS % 12 == 4
 		"	mov	a4, a4\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+		"	mov	a8, a8\n"
 #endif
 		"	retw\n"
+#endif
 		"2:\n"
-		: : : "a12", "a13", "memory");
+		: : : "a8", "a9", "memory");
 #else
 	__asm__ __volatile__ (
 		"	mov	a12, a12\n"
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 82bbfa5a0..a2a902140 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -568,12 +568,13 @@ user_exception_exit:
 	 *	 (if we have restored WSBITS-1 frames).
 	 */
 
+2:
 #if XCHAL_HAVE_THREADPTR
 	l32i	a3, a1, PT_THREADPTR
 	wur	a3, threadptr
 #endif
 
-2:	j	common_exception_exit
+	j	common_exception_exit
 
 	/* This is the kernel exception exit.
 	 * We avoided to do a MOVSP when we entered the exception, but we
@@ -1820,7 +1821,7 @@ ENDPROC(system_call)
 	mov	a12, a0
 	.endr
 #endif
-	_entry	a1, 48
+	_entry	a1, 16
 #if XCHAL_NUM_AREGS % 12 == 0
 	mov	a8, a8
 #elif XCHAL_NUM_AREGS % 12 == 4
@@ -1844,7 +1845,7 @@ ENDPROC(system_call)
 
 ENTRY(_switch_to)
 
-	entry	a1, 16
+	entry	a1, 48
 
 	mov	a11, a3			# and 'next' (a3)