Merge tag 'lsk-v3.18-15.08' of http://git.linaro.org/kernel/linux-linaro-stable into linux-linaro-lng-v3.18linux-lng-3.18.20-2015.09 linux-linaro-lng-v3.18-test

LSK 15.08 v3.18 Signed-off-by: Gary S. Robertson <gary.robertson@linaro.org> Conflicts: drivers/clocksource/exynos_mct.c
author: Gary S. Robertson <gary.robertson@linaro.org> 2015-09-09 14:34:49 -0500
committer: Gary S. Robertson <gary.robertson@linaro.org> 2015-09-09 14:34:49 -0500
commit: 60f13d2d65b7c0c4096321ee88670e56954ee215 (patch)
tree: d00f8c8159913c76970b2da3b2942ba08909bd1e /arch
parent: fc6c8563fb89aaaab437f8215894219e54dfc5df (diff)
parent: 417f54239f760856db32c520ae542ff288145c13 (diff)
46 files changed, 322 insertions, 121 deletions
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 9917a45fc430..20b7dc17979e 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -43,6 +43,12 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	unsigned int temp;						\
 									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	__asm__ __volatile__(						\
 	"1:	llock   %0, [%1]	\n"				\
 	"	" #asm_op " %0, %0, %2	\n"				\
@@ -52,6 +58,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	: "r"(&v->counter), "ir"(i)					\
 	: "cc");							\
 									\
+	smp_mb();							\
+									\
 	return temp;							\
 }
 
@@ -105,6 +113,9 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	unsigned long flags;						\
 	unsigned long temp;						\
 									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
 	atomic_ops_lock(flags);						\
 	temp = v->counter;						\
 	temp c_op i;							\
@@ -142,9 +153,19 @@ ATOMIC_OP(and, &=, and)
 #define __atomic_add_unless(v, a, u)					\
 ({									\
 	int c, old;							\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
 	c = atomic_read(v);						\
 	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
 		c = old;						\
+									\
+	smp_mb();							\
+									\
 	c;								\
 })
 
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 1a5bf07eefe2..89fbbb0db51b 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -103,6 +103,12 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	/*
+	 * Explicit full memory barrier needed before/after as
+	 * LLOCK/SCOND themselves don't provide any such semantics
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bset    %1, %0, %3	\n"
@@ -112,6 +118,8 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 
@@ -125,6 +133,8 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bclr    %1, %0, %3	\n"
@@ -134,6 +144,8 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *m)
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 
@@ -147,6 +159,8 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%2]	\n"
 	"	bxor    %1, %0, %3	\n"
@@ -156,6 +170,8 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *m)
 	: "r"(m), "ir"(nr)
 	: "cc");
 
+	smp_mb();
+
 	return (old & (1 << nr)) != 0;
 }
 
@@ -235,6 +251,9 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m)
 	if (__builtin_constant_p(nr))
 		nr &= 0x1f;
 
+	/*
+	 * spin lock/unlock provide the needed smp_mb() before/after
+	 */
 	bitops_lock(flags);
 
 	old = *m;
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index 03cd6894855d..44fd531f4d7b 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -10,6 +10,8 @@
 #define __ASM_ARC_CMPXCHG_H
 
 #include <linux/types.h>
+
+#include <asm/barrier.h>
 #include <asm/smp.h>
 
 #ifdef CONFIG_ARC_HAS_LLSC
@@ -19,16 +21,25 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
 {
 	unsigned long prev;
 
+	/*
+	 * Explicit full memory barrier needed before/after as
+	 * LLOCK/SCOND thmeselves don't provide any such semantics
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	llock   %0, [%1]	\n"
 	"	brne    %0, %2, 2f	\n"
 	"	scond   %3, [%1]	\n"
 	"	bnz     1b		\n"
 	"2:				\n"
-	: "=&r"(prev)
-	: "r"(ptr), "ir"(expected),
-	  "r"(new) /* can't be "ir". scond can't take limm for "b" */
-	: "cc");
+	: "=&r"(prev)	/* Early clobber, to prevent reg reuse */
+	: "r"(ptr),	/* Not "m": llock only supports reg direct addr mode */
+	  "ir"(expected),
+	  "r"(new)	/* can't be "ir". scond can't take LIMM for "b" */
+	: "cc", "memory"); /* so that gcc knows memory is being written here */
+
+	smp_mb();
 
 	return prev;
 }
@@ -42,6 +53,9 @@ __cmpxchg(volatile void *ptr, unsigned long expected, unsigned long new)
 	int prev;
 	volatile unsigned long *p = ptr;
 
+	/*
+	 * spin lock/unlock provide the needed smp_mb() before/after
+	 */
 	atomic_ops_lock(flags);
 	prev = *p;
 	if (prev == expected)
@@ -77,12 +91,16 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
 
 	switch (size) {
 	case 4:
+		smp_mb();
+
 		__asm__ __volatile__(
 		"	ex  %0, [%1]	\n"
 		: "+r"(val)
 		: "r"(ptr)
 		: "memory");
 
+		smp_mb();
+
 		return val;
 	}
 	return __xchg_bad_pointer();
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index b6a8c2dfbe6e..e1651df6a93d 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -22,24 +22,46 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	/*
+	 * This smp_mb() is technically superfluous, we only need the one
+	 * after the lock for providing the ACQUIRE semantics.
+	 * However doing the "right" thing was regressing hackbench
+	 * so keeping this, pending further investigation
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
 	: "+&r" (tmp)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
+
+	/*
+	 * ACQUIRE barrier to ensure load/store after taking the lock
+	 * don't "bleed-up" out of the critical section (leak-in is allowed)
+	 * http://www.spinics.net/lists/kernel/msg2010409.html
+	 *
+	 * ARCv2 only has load-load, store-store and all-all barrier
+	 * thus need the full all-all barrier
+	 */
+	smp_mb();
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
 
+	smp_mb();
+
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	smp_mb();
+
 	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
@@ -47,12 +69,22 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
 
+	/*
+	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
+	 * is the only option
+	 */
+	smp_mb();
+
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
 	: "+r" (tmp)
 	: "r"(&(lock->slock))
 	: "memory");
 
+	/*
+	 * superfluous, but keeping for now - see pairing version in
+	 * arch_spin_lock above
+	 */
 	smp_mb();
 }
 
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 83286ec9702c..84366cddaa8e 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -225,7 +225,6 @@
 			};
 
 			eth0: ethernet@70000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x70000 0x4000>;
 				interrupts = <8>;
 				clocks = <&gateclk 4>;
@@ -241,7 +240,6 @@
 			};
 
 			eth1: ethernet@74000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x74000 0x4000>;
 				interrupts = <10>;
 				clocks = <&gateclk 3>;
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 7513410f7b89..b6e02689c61b 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -302,6 +302,14 @@
 					dmacap,memset;
 				};
 			};
+
+			ethernet@70000 {
+				compatible = "marvell,armada-370-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-370-neta";
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 480e237a870f..677160effbb0 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -296,7 +296,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index 2c7b1fef4703..e143776b78ec 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -334,7 +334,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index bff9f6c18db1..66d25b788067 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -125,7 +125,7 @@
 			};
 
 			eth2: ethernet@30000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x30000 0x4000>;
 				interrupts = <12>;
 				clocks = <&gateclk 2>;
@@ -168,6 +168,14 @@
 				};
 			};
 
+			ethernet@70000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
 			xor@f0900 {
 				compatible = "marvell,orion-xor";
 				reg = <0xF0900 0x100
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index b5b84006469e..d7f6ae4e5b98 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -108,8 +108,8 @@
 			mmc0: mmc@f8000000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_cd>;
-				slot@1 {
-					reg = <1>;
+				slot@0 {
+					reg = <0>;
 					bus-width = <4>;
 					cd-gpios = <&pioE 5 0>;
 				};
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 01dcb0e752d9..d66d608f7ce7 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -159,13 +159,9 @@ __kvm_vcpu_return:
 	@ Don't trap coprocessor accesses for host kernel
 	set_hstr vmexit
 	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
 
 #ifdef CONFIG_VFPv3
-	@ Save floating point registers we if let guest use them.
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	bne	after_vfp_restore
-
 	@ Switch VFP/NEON hardware state to the host's
 	add	r7, vcpu, #VCPU_VFP_GUEST
 	store_vfp_state r7
@@ -177,6 +173,8 @@ after_vfp_restore:
 	@ Restore FPEXC_EN which we clobbered on entry
 	pop	{r2}
 	VFPFMXR FPEXC, r2
+#else
+after_vfp_restore:
 #endif
 
 	@ Reset Hyp-role
@@ -472,7 +470,7 @@ switch_to_guest_vfp:
 	push	{r3-r7}
 
 	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
 
 	@ Switch VFP/NEON hardware state to the guest's
 	add	r7, r0, #VCPU_VFP_HOST
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 14d488388480..f6f14812d106 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -599,8 +599,13 @@ ARM_BE8(rev	r6, r6  )
 .endm
 
 /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2. */
-.macro set_hcptr operation, mask
+ * (hardware reset value is 0). Keep previous value in r2.
+ * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
+ * VFP wasn't already enabled (always executed on vmtrap).
+ * If a label is specified with vmexit, it is branched to if VFP wasn't
+ * enabled.
+ */
+.macro set_hcptr operation, mask, label = none
 	mrc	p15, 4, r2, c1, c1, 2
 	ldr	r3, =\mask
 	.if \operation == vmentry
@@ -609,6 +614,17 @@ ARM_BE8(rev	r6, r6  )
 	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
 	.endif
 	mcr	p15, 4, r3, c1, c1, 2
+	.if \operation != vmentry
+	.if \operation == vmexit
+	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	beq	1f
+	.endif
+	isb
+	.if \label != none
+	b	\label
+	.endif
+1:
+	.endif
 .endm
 
 /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 58cb3248d277..4d0d89e342f9 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -237,10 +237,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	case PSCI_0_2_FN64_AFFINITY_INFO:
 		val = kvm_psci_vcpu_affinity_info(vcpu);
 		break;
-	case PSCI_0_2_FN_MIGRATE:
-	case PSCI_0_2_FN64_MIGRATE:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
 		/*
 		 * Trusted OS is MP hence does not require migration
@@ -249,10 +245,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		 */
 		val = PSCI_0_2_TOS_MP;
 		break;
-	case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
-	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_SYSTEM_OFF:
 		kvm_psci_system_off(vcpu);
 		/*
@@ -278,7 +270,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		ret = 0;
 		break;
 	default:
-		return -EINVAL;
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
@@ -298,12 +291,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 	case KVM_PSCI_FN_CPU_ON:
 		val = kvm_psci_vcpu_on(vcpu);
 		break;
-	case KVM_PSCI_FN_CPU_SUSPEND:
-	case KVM_PSCI_FN_MIGRATE:
+	default:
 		val = PSCI_RET_NOT_SUPPORTED;
 		break;
-	default:
-		return -EINVAL;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 2daef619d053..5474a76803f0 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -439,7 +439,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_GPMI_IO]      = imx_clk_gate2("gpmi_io",       "enfc",              base + 0x78, 28);
 	clk[IMX6QDL_CLK_GPMI_APB]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
 	clk[IMX6QDL_CLK_ROM]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
-	clk[IMX6QDL_CLK_SATA]         = imx_clk_gate2("sata",          "ipg",               base + 0x7c, 4);
+	clk[IMX6QDL_CLK_SATA]         = imx_clk_gate2("sata",          "ahb",               base + 0x7c, 4);
 	clk[IMX6QDL_CLK_SDMA]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clk[IMX6QDL_CLK_SPBA]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
 	clk[IMX6QDL_CLK_SPDIF]        = imx_clk_gate2("spdif",         "spdif_podf",        base + 0x7c, 14);
diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c
index b30bf5cba65b..f209e9c507e2 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra20.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra20.c
@@ -35,6 +35,7 @@
 #include "iomap.h"
 #include "irq.h"
 #include "pm.h"
+#include "reset.h"
 #include "sleep.h"
 
 #ifdef CONFIG_PM_SLEEP
@@ -72,15 +73,13 @@ static struct cpuidle_driver tegra_idle_driver = {
 
 #ifdef CONFIG_PM_SLEEP
 #ifdef CONFIG_SMP
-static void __iomem *pmc = IO_ADDRESS(TEGRA_PMC_BASE);
-
 static int tegra20_reset_sleeping_cpu_1(void)
 {
 	int ret = 0;
 
 	tegra_pen_lock();
 
-	if (readl(pmc + PMC_SCRATCH41) == CPU_RESETTABLE)
+	if (readb(tegra20_cpu1_resettable_status) == CPU_RESETTABLE)
 		tegra20_cpu_shutdown(1);
 	else
 		ret = -EINVAL;
diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
index 71be4af5e975..e3070fdab80b 100644
--- a/arch/arm/mach-tegra/reset-handler.S
+++ b/arch/arm/mach-tegra/reset-handler.S
@@ -169,10 +169,10 @@ after_errata:
 	cmp	r6, #TEGRA20
 	bne	1f
 	/* If not CPU0, don't let CPU0 reset CPU1 now that CPU1 is coming up. */
-	mov32	r5, TEGRA_PMC_BASE
-	mov	r0, #0
+	mov32	r5, TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET
+	mov	r0, #CPU_NOT_RESETTABLE
 	cmp	r10, #0
-	strne	r0, [r5, #PMC_SCRATCH41]
+	strneb	r0, [r5, #__tegra20_cpu1_resettable_status_offset]
 1:
 #endif
 
@@ -281,6 +281,10 @@ __tegra_cpu_reset_handler_data:
 	.rept	TEGRA_RESET_DATA_SIZE
 	.long	0
 	.endr
+	.globl	__tegra20_cpu1_resettable_status_offset
+	.equ	__tegra20_cpu1_resettable_status_offset, \
+					. - __tegra_cpu_reset_handler_start
+	.byte	0
 	.align L1_CACHE_SHIFT
 
 ENTRY(__tegra_cpu_reset_handler_end)
diff --git a/arch/arm/mach-tegra/reset.h b/arch/arm/mach-tegra/reset.h
index 76a93434c6ee..29c3dec0126a 100644
--- a/arch/arm/mach-tegra/reset.h
+++ b/arch/arm/mach-tegra/reset.h
@@ -35,6 +35,7 @@ extern unsigned long __tegra_cpu_reset_handler_data[TEGRA_RESET_DATA_SIZE];
 
 void __tegra_cpu_reset_handler_start(void);
 void __tegra_cpu_reset_handler(void);
+void __tegra20_cpu1_resettable_status_offset(void);
 void __tegra_cpu_reset_handler_end(void);
 void tegra_secondary_startup(void);
 
@@ -47,6 +48,9 @@ void tegra_secondary_startup(void);
 	(IO_ADDRESS(TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET + \
 	((u32)&__tegra_cpu_reset_handler_data[TEGRA_RESET_MASK_LP2] - \
 	 (u32)__tegra_cpu_reset_handler_start)))
+#define tegra20_cpu1_resettable_status \
+	(IO_ADDRESS(TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET + \
+	 (u32)__tegra20_cpu1_resettable_status_offset))
 #endif
 
 #define tegra_cpu_reset_handler_offset \
diff --git a/arch/arm/mach-tegra/sleep-tegra20.S b/arch/arm/mach-tegra/sleep-tegra20.S
index be4bc5f853f5..e6b684e14322 100644
--- a/arch/arm/mach-tegra/sleep-tegra20.S
+++ b/arch/arm/mach-tegra/sleep-tegra20.S
@@ -97,9 +97,10 @@ ENDPROC(tegra20_hotplug_shutdown)
 ENTRY(tegra20_cpu_shutdown)
 	cmp	r0, #0
 	reteq	lr			@ must not be called for CPU 0
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
 	mov	r12, #CPU_RESETTABLE
-	str	r12, [r1]
+	strb	r12, [r1, r2]
 
 	cpu_to_halt_reg r1, r0
 	ldr	r3, =TEGRA_FLOW_CTRL_VIRT
@@ -182,38 +183,41 @@ ENDPROC(tegra_pen_unlock)
 /*
  * tegra20_cpu_clear_resettable(void)
  *
- * Called to clear the "resettable soon" flag in PMC_SCRATCH41 when
+ * Called to clear the "resettable soon" flag in IRAM variable when
  * it is expected that the secondary CPU will be idle soon.
  */
 ENTRY(tegra20_cpu_clear_resettable)
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
 	mov	r12, #CPU_NOT_RESETTABLE
-	str	r12, [r1]
+	strb	r12, [r1, r2]
 	ret	lr
 ENDPROC(tegra20_cpu_clear_resettable)
 
 /*
  * tegra20_cpu_set_resettable_soon(void)
  *
- * Called to set the "resettable soon" flag in PMC_SCRATCH41 when
+ * Called to set the "resettable soon" flag in IRAM variable when
  * it is expected that the secondary CPU will be idle soon.
  */
 ENTRY(tegra20_cpu_set_resettable_soon)
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
 	mov	r12, #CPU_RESETTABLE_SOON
-	str	r12, [r1]
+	strb	r12, [r1, r2]
 	ret	lr
 ENDPROC(tegra20_cpu_set_resettable_soon)
 
 /*
  * tegra20_cpu_is_resettable_soon(void)
  *
- * Returns true if the "resettable soon" flag in PMC_SCRATCH41 has been
+ * Returns true if the "resettable soon" flag in IRAM variable has been
  * set because it is expected that the secondary CPU will be idle soon.
  */
 ENTRY(tegra20_cpu_is_resettable_soon)
-	mov32	r1, TEGRA_PMC_VIRT + PMC_SCRATCH41
-	ldr	r12, [r1]
+	mov32	r1, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r2, =__tegra20_cpu1_resettable_status_offset
+	ldrb	r12, [r1, r2]
 	cmp	r12, #CPU_RESETTABLE_SOON
 	moveq	r0, #1
 	movne	r0, #0
@@ -256,9 +260,10 @@ ENTRY(tegra20_sleep_cpu_secondary_finish)
 	mov	r0, #TEGRA_FLUSH_CACHE_LOUIS
 	bl	tegra_disable_clean_inv_dcache
 
-	mov32	r0, TEGRA_PMC_VIRT + PMC_SCRATCH41
+	mov32	r0, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r4, =__tegra20_cpu1_resettable_status_offset
 	mov	r3, #CPU_RESETTABLE
-	str	r3, [r0]
+	strb	r3, [r0, r4]
 
 	bl	tegra_cpu_do_idle
 
@@ -274,10 +279,10 @@ ENTRY(tegra20_sleep_cpu_secondary_finish)
 
 	bl	tegra_pen_lock
 
-	mov32	r3, TEGRA_PMC_VIRT
-	add	r0, r3, #PMC_SCRATCH41
+	mov32	r0, TEGRA_IRAM_RESET_BASE_VIRT
+	ldr	r4, =__tegra20_cpu1_resettable_status_offset
 	mov	r3, #CPU_NOT_RESETTABLE
-	str	r3, [r0]
+	strb	r3, [r0, r4]
 
 	bl	tegra_pen_unlock
 
diff --git a/arch/arm/mach-tegra/sleep.h b/arch/arm/mach-tegra/sleep.h
index 92d46ec1361a..0d59360d891d 100644
--- a/arch/arm/mach-tegra/sleep.h
+++ b/arch/arm/mach-tegra/sleep.h
@@ -18,6 +18,7 @@
 #define __MACH_TEGRA_SLEEP_H
 
 #include "iomap.h"
+#include "irammap.h"
 
 #define TEGRA_ARM_PERIF_VIRT (TEGRA_ARM_PERIF_BASE - IO_CPU_PHYS \
 					+ IO_CPU_VIRT)
@@ -29,6 +30,9 @@
 					+ IO_APB_VIRT)
 #define TEGRA_PMC_VIRT	(TEGRA_PMC_BASE - IO_APB_PHYS + IO_APB_VIRT)
 
+#define TEGRA_IRAM_RESET_BASE_VIRT (IO_IRAM_VIRT + \
+				TEGRA_IRAM_RESET_HANDLER_OFFSET)
+
 /* PMC_SCRATCH37-39 and 41 are used for tegra_pen_lock and idle */
 #define PMC_SCRATCH37	0x130
 #define PMC_SCRATCH38	0x134
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7fd3e27e3ccc..8afb863f5a9e 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,6 +18,7 @@
 #ifndef __ARM64_KVM_ARM_H__
 #define __ARM64_KVM_ARM_H__
 
+#include <asm/memory.h>
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -160,9 +161,9 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_TTEE	(1 << 16)
@@ -185,13 +186,13 @@
 
 /* Exception Syndrome Register (ESR) bits */
 #define ESR_EL2_EC_SHIFT	(26)
-#define ESR_EL2_EC		(0x3fU << ESR_EL2_EC_SHIFT)
-#define ESR_EL2_IL		(1U << 25)
+#define ESR_EL2_EC		(UL(0x3f) << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL		(UL(1) << 25)
 #define ESR_EL2_ISS		(ESR_EL2_IL - 1)
 #define ESR_EL2_ISV_SHIFT	(24)
-#define ESR_EL2_ISV		(1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_ISV		(UL(1) << ESR_EL2_ISV_SHIFT)
 #define ESR_EL2_SAS_SHIFT	(22)
-#define ESR_EL2_SAS		(3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SAS		(UL(3) << ESR_EL2_SAS_SHIFT)
 #define ESR_EL2_SSE		(1 << 21)
 #define ESR_EL2_SRT_SHIFT	(16)
 #define ESR_EL2_SRT_MASK	(0x1f << ESR_EL2_SRT_SHIFT)
@@ -205,16 +206,16 @@
 #define ESR_EL2_FSC_TYPE	(0x3c)
 
 #define ESR_EL2_CV_SHIFT	(24)
-#define ESR_EL2_CV		(1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_CV		(UL(1) << ESR_EL2_CV_SHIFT)
 #define ESR_EL2_COND_SHIFT	(20)
-#define ESR_EL2_COND		(0xfU << ESR_EL2_COND_SHIFT)
+#define ESR_EL2_COND		(UL(0xf) << ESR_EL2_COND_SHIFT)
 
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
-#define HPFAR_MASK	(~0xFUL)
+#define HPFAR_MASK	(~UL(0xf))
 
 #define ESR_EL2_EC_UNKNOWN	(0x00)
 #define ESR_EL2_EC_WFI		(0x01)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 2b0f3d5e11c7..6c99b4664b40 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -517,6 +517,7 @@ el0_sp_pc:
 	mrs	x26, far_el1
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index ff3bddea482d..f6fe17d88da5 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -15,6 +15,10 @@ ccflags-y := -shared -fno-common -fno-builtin
 ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
 		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 
+# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
+# down to collect2, resulting in silent corruption of the vDSO image.
+ccflags-y += -Wl,-shared
+
 obj-y += vdso.o
 extra-y += vdso.lds vdso-offsets.h
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index baa758d37021..76c1e6cd36fc 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -92,6 +92,14 @@ static void reset_context(void *info)
 	unsigned int cpu = smp_processor_id();
 	struct mm_struct *mm = current->active_mm;
 
+	/*
+	 * current->active_mm could be init_mm for the idle thread immediately
+	 * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to
+	 * the reserved value, so no need to reset any context.
+	 */
+	if (mm == &init_mm)
+		return;
+
 	smp_rmb();
 	asid = cpu_last_asid + cpu;
 
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 2de9d2e59d96..0eeb4f0930a0 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -40,13 +40,13 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 
 int pmd_huge(pmd_t pmd)
 {
-	return !(pmd_val(pmd) & PMD_TABLE_BIT);
+	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
 
 int pud_huge(pud_t pud)
 {
 #ifndef __PAGETABLE_PMD_FOLDED
-	return !(pud_val(pud) & PUD_TABLE_BIT);
+	return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
 #else
 	return 0;
 #endif
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index c95464a33f36..f752943f75d2 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -238,7 +238,7 @@ static void __init free_unused_memmap(void)
 		 * memmap entries are valid from the bank end aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		prev_end = ALIGN(start + __phys_to_pfn(reg->size),
+		prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
 				 MAX_ORDER_NR_PAGES);
 	}
 
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index 9488fa5f8866..afc96ecb9004 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -94,7 +94,11 @@
 #endif
 
 #ifndef FIXADDR_TOP
+#ifdef CONFIG_KVM_GUEST
+#define FIXADDR_TOP		((unsigned long)(long)(int)0x7ffe0000)
+#else
 #define FIXADDR_TOP		((unsigned long)(long)(int)0xfffe0000)
 #endif
+#endif
 
 #endif /* __ASM_MACH_GENERIC_SPACES_H */
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index d2bfbc2e8995..be15e52a47a0 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -109,7 +109,7 @@ void __init init_IRQ(void)
 #endif
 }
 
-#ifdef DEBUG_STACKOVERFLOW
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
 static inline void check_stack_overflow(void)
 {
 	unsigned long sp;
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 39074fb83bad..a53eaf50c224 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -784,7 +784,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
-		memslot = &kvm->memslots->memslots[log->slot];
+		memslot = id_to_memslot(kvm->memslots, log->slot);
 
 		ga = memslot->base_gfn << PAGE_SHIFT;
 		ga_end = ga + (memslot->npages << PAGE_SHIFT);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index a6995d4e93d4..ffa07eb5fff0 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -131,7 +131,16 @@ static void pmao_restore_workaround(bool ebb) { }
 
 static bool regs_use_siar(struct pt_regs *regs)
 {
-	return !!regs->result;
+	/*
+	 * When we take a performance monitor exception the regs are setup
+	 * using perf_read_regs() which overloads some fields, in particular
+	 * regs->result to tell us whether to use SIAR.
+	 *
+	 * However if the regs are from another exception, eg. a syscall, then
+	 * they have not been setup using perf_read_regs() and so regs->result
+	 * is something random.
+	 */
+	return ((TRAP(regs) == 0xf00) && regs->result);
 }
 
 /*
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 9f73c8059022..49b74454d7ee 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -415,7 +415,7 @@ static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
 	ptr += len;
 	/* Copy lower halves of SIMD registers 0-15 */
 	for (i = 0; i < 16; i++) {
-		memcpy(ptr, &vx_regs[i], 8);
+		memcpy(ptr, &vx_regs[i].u[2], 8);
 		ptr += 8;
 	}
 	return ptr;
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 4310332872d4..71762565513e 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -2307,7 +2307,7 @@ void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
 	if (len & (8UL - 1))
 		return ERR_PTR(-EINVAL);
 
-	buf = kzalloc(len, GFP_KERNEL);
+	buf = kzalloc(len, GFP_ATOMIC);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3635fff7b32d..c9148e268512 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -173,7 +173,7 @@ config SBUS
 
 config NEED_DMA_MAP_STATE
 	def_bool y
-	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG
+	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB
 
 config NEED_SG_DMA_LENGTH
 	def_bool y
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6c0709ff2f38..306d152336cd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -571,7 +571,7 @@ struct kvm_arch {
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
-	int vapics_in_nmi_mode;
+	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
 
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 6f1c3a8a33ab..bcc9a2f46c62 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -212,10 +212,21 @@
 #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
 
 #ifdef __KERNEL__
+
+/*
+ * early_idt_handler_array is an array of entry points referenced in the
+ * early IDT.  For simplicity, it's a real array with one entry point
+ * every nine bytes.  That leaves room for an optional 'push $0' if the
+ * vector has no error code (two bytes), a 'push $vector_number' (two
+ * bytes), and a jump to the common entry code (up to five bytes).
+ */
+#define EARLY_IDT_HANDLER_SIZE 9
+
 #ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+
+extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 #ifdef CONFIG_TRACING
-#define trace_early_idt_handlers early_idt_handlers
+# define trace_early_idt_handler_array early_idt_handler_array
 #endif
 
 /*
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index ec9df6f9cd47..5e109a31f62b 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -321,7 +321,7 @@ get_matching_model_microcode(int cpu, unsigned long start,
 	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
 	int i;
 
-	while (leftover) {
+	while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
 		mc_header = (struct microcode_header_intel *)ucode_ptr;
 
 		mc_size = get_totalsize(mc_header);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 498b6d967138..df11583a9041 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2604,13 +2604,13 @@ __init int intel_pmu_init(void)
 		 * counter, so do not extend mask to generic counters
 		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != FIXED_EVENT_FLAGS
-			    || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-				continue;
+			if (c->cmask == FIXED_EVENT_FLAGS
+			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
-
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 &=
+				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+			c->weight = hweight64(c->idxmsk64);
 		}
 	}
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 344b63f18d14..3dddb89ba320 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:	mov %esp, %eax
 	call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  ret_from_intr
 	CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index f1dc27f457f1..e36d9815ef56 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1173,6 +1173,9 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
 	popq %rsp
 	CFI_DEF_CFA_REGISTER rsp
 	decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  error_exit
 	CFI_ENDPROC
 END(xen_do_hypervisor_callback)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 3b241f0ca005..957fdb5eb2e3 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -164,7 +164,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	clear_bss();
 
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
-		set_intr_gate(i, early_idt_handlers[i]);
+		set_intr_gate(i, early_idt_handler_array[i]);
 	load_idt((const struct desc_ptr *)&idt_descr);
 
 	copy_bootdata(__va(real_mode_data));
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index f36bd42d6f0c..e7be5290fe1f 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -61,9 +61,16 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
-/* Number of possible pages in the lowmem region */
-LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
-	
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
+
 /* Enough space to fit pagetables for the low memory linear map */
 MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
 
@@ -477,21 +484,22 @@ is486:
 __INIT
 setup_once:
 	/*
-	 * Set up a idt with 256 entries pointing to ignore_int,
-	 * interrupt gates. It doesn't actually load idt - that needs
-	 * to be done on each CPU. Interrupts are enabled elsewhere,
-	 * when we can be relatively sure everything is ok.
+	 * Set up a idt with 256 interrupt gates that push zero if there
+	 * is no error code and then jump to early_idt_handler_common.
+	 * It doesn't actually load the idt - that needs to be done on
+	 * each CPU. Interrupts are enabled elsewhere, when we can be
+	 * relatively sure everything is ok.
 	 */
 
 	movl $idt_table,%edi
-	movl $early_idt_handlers,%eax
+	movl $early_idt_handler_array,%eax
 	movl $NUM_EXCEPTION_VECTORS,%ecx
 1:
 	movl %eax,(%edi)
 	movl %eax,4(%edi)
 	/* interrupt gate, dpl=0, present */
 	movl $(0x8E000000 + __KERNEL_CS),2(%edi)
-	addl $9,%eax
+	addl $EARLY_IDT_HANDLER_SIZE,%eax
 	addl $8,%edi
 	loop 1b
 
@@ -523,26 +531,28 @@ setup_once:
 	andl $0,setup_once_ref	/* Once is enough, thanks */
 	ret
 
-ENTRY(early_idt_handlers)
+ENTRY(early_idt_handler_array)
 	# 36(%esp) %eflags
 	# 32(%esp) %cs
 	# 28(%esp) %eip
 	# 24(%rsp) error code
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
-	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
-	ASM_NOP2
-	.else
+	.ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
 	pushl $0		# Dummy error code, to make stack frame uniform
 	.endif
 	pushl $i		# 20(%esp) Vector number
-	jmp early_idt_handler
+	jmp early_idt_handler_common
 	i = i + 1
+	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
-ENDPROC(early_idt_handlers)
+ENDPROC(early_idt_handler_array)
 	
-	/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+	/*
+	 * The stack is the hardware frame, an error code or zero, and the
+	 * vector number.
+	 */
 	cld
 
 	cmpl $2,(%esp)		# X86_TRAP_NMI
@@ -602,7 +612,7 @@ ex_entry:
 is_nmi:
 	addl $8,%esp		/* drop vector number and error code */
 	iret
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
 
 /* This is the default interrupt "handler" :-) */
 	ALIGN
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a468c0a65c42..a2dc0add72ed 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -321,26 +321,28 @@ bad_address:
 	jmp bad_address
 
 	__INIT
-	.globl early_idt_handlers
-early_idt_handlers:
+ENTRY(early_idt_handler_array)
 	# 104(%rsp) %rflags
 	#  96(%rsp) %cs
 	#  88(%rsp) %rip
 	#  80(%rsp) error code
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
-	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
-	ASM_NOP2
-	.else
+	.ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
 	pushq $0		# Dummy error code, to make stack frame uniform
 	.endif
 	pushq $i		# 72(%rsp) Vector number
-	jmp early_idt_handler
+	jmp early_idt_handler_common
 	i = i + 1
+	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
+ENDPROC(early_idt_handler_array)
 
-/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+	/*
+	 * The stack is the hardware frame, an error code or zero, and the
+	 * vector number.
+	 */
 	cld
 
 	cmpl $2,(%rsp)		# X86_TRAP_NMI
@@ -412,7 +414,7 @@ ENTRY(early_idt_handler)
 is_nmi:
 	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
 
 	__INITDATA
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 93d2c04c6f8f..f2e281cf8c19 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -330,13 +330,16 @@ int __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
+	int length;
 
 	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
 	insn_get_length(&insn);
+	length = insn.length;
+
 	/* Another subsystem puts a breakpoint, failed to recover */
 	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
-	memcpy(dest, insn.kaddr, insn.length);
+	memcpy(dest, insn.kaddr, length);
 
 #ifdef CONFIG_X86_64
 	if (insn_rip_relative(&insn)) {
@@ -366,7 +369,7 @@ int __copy_instruction(u8 *dest, u8 *src)
 		*(s32 *) disp = (s32) newdisp;
 	}
 #endif
-	return insn.length;
+	return length;
 }
 
 static int arch_copy_kprobe(struct kprobe *p)
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 298781d4cfb4..1406ffde3e35 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -305,7 +305,7 @@ static void pit_do_work(struct kthread_work *work)
 		 * LVT0 to NMI delivery. Other PIC interrupts are just sent to
 		 * VCPU0, and only if its LVT0 is in EXTINT mode.
 		 */
-		if (kvm->arch.vapics_in_nmi_mode > 0)
+		if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0)
 			kvm_for_each_vcpu(i, vcpu, kvm)
 				kvm_apic_nmi_wd_deliver(vcpu);
 	}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b8345dd41b25..de8e50040124 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1112,10 +1112,10 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 		if (!nmi_wd_enabled) {
 			apic_debug("Receive NMI setting on APIC_LVT0 "
 				   "for cpu %d\n", apic->vcpu->vcpu_id);
-			apic->vcpu->kvm->arch.vapics_in_nmi_mode++;
+			atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
 		}
 	} else if (nmi_wd_enabled)
-		apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
+		atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
 }
 
 static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
@@ -1687,6 +1687,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 170e7d49ba65..b83bff87408f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -511,8 +511,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->vmcb->control.next_rip != 0)
+	if (svm->vmcb->control.next_rip != 0) {
+		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
+	}
 
 	if (!svm->next_rip) {
 		if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
@@ -4306,7 +4308,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	vmcb->control.next_rip  = info->next_rip;
+	/* TODO: Advertise NRIPS to guest hypervisor unconditionally */
+	if (static_cpu_has(X86_FEATURE_NRIPS))
+		vmcb->control.next_rip  = info->next_rip;
 	vmcb->control.exit_code = icpt_info.exit_code;
 	vmexit = nested_svm_exit_handled(svm);
 
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index cfd1b132b8e3..a3e94b4108bf 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -84,6 +84,17 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
 		},
 	},
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */
+	{
+		.callback = set_use_crs,
+		.ident = "Foxconn K8M890-8237A",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"),
+			DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"),
+			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+		},
+	},
 
 	/* Now for the blacklist.. */
 
@@ -124,8 +135,10 @@ void __init pci_acpi_crs_quirks(void)
 {
 	int year;
 
-	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
-		pci_use_crs = false;
+	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) {
+		if (iomem_resource.end <= 0xffffffff)
+			pci_use_crs = false;
+	}
 
 	dmi_check_system(pci_crs_quirks);
author	Gary S. Robertson <gary.robertson@linaro.org>	2015-09-09 14:34:49 -0500
committer	Gary S. Robertson <gary.robertson@linaro.org>	2015-09-09 14:34:49 -0500
commit	60f13d2d65b7c0c4096321ee88670e56954ee215 (patch)
tree	d00f8c8159913c76970b2da3b2942ba08909bd1e /arch
parent	fc6c8563fb89aaaab437f8215894219e54dfc5df (diff)
parent	417f54239f760856db32c520ae542ff288145c13 (diff)