kernel-alx/patches-4.19/0178-4.19.79-all-fixes.patch

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e8ddf0ef232e..16607b178b47 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2503,8 +2503,8 @@
 			http://repo.or.cz/w/linux-2.6/mini2440.git
 
 	mitigations=
-			[X86,PPC,S390] Control optional mitigations for CPU
-			vulnerabilities.  This is a set of curated,
+			[X86,PPC,S390,ARM64] Control optional mitigations for
+			CPU vulnerabilities.  This is a set of curated,
 			arch-independent options, each of which is an
 			aggregation of existing arch-specific options.
 
@@ -2513,12 +2513,14 @@
 				improves system performance, but it may also
 				expose users to several CPU vulnerabilities.
 				Equivalent to: nopti [X86,PPC]
+					       kpti=0 [ARM64]
 					       nospectre_v1 [PPC]
 					       nobp=0 [S390]
 					       nospectre_v1 [X86]
-					       nospectre_v2 [X86,PPC,S390]
+					       nospectre_v2 [X86,PPC,S390,ARM64]
 					       spectre_v2_user=off [X86]
 					       spec_store_bypass_disable=off [X86,PPC]
+					       ssbd=force-off [ARM64]
 					       l1tf=off [X86]
 					       mds=off [X86]
 
@@ -2866,10 +2868,10 @@
 			(bounds check bypass). With this option data leaks
 			are possible in the system.
 
-	nospectre_v2	[X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2
-			(indirect branch prediction) vulnerability. System may
-			allow data leaks with this option, which is equivalent
-			to spectre_v2=off.
+	nospectre_v2	[X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
+			the Spectre variant 2 (indirect branch prediction)
+			vulnerability. System may allow data leaks with this
+			option.
 
 	nospec_store_bypass_disable
 			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt
index d6aff2c5e9e2..6feaffe90e22 100644
--- a/Documentation/arm64/elf_hwcaps.txt
+++ b/Documentation/arm64/elf_hwcaps.txt
@@ -178,3 +178,7 @@ HWCAP_ILRCPC
 HWCAP_FLAGM
 
     Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0001.
+
+HWCAP_SSBS
+
+    Functionality implied by ID_AA64PFR1_EL1.SSBS == 0b0010.
diff --git a/Makefile b/Makefile
index 440c5b5c4f4b..4d29c7370b46 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 19
-SUBLEVEL = 78
+SUBLEVEL = 79
 EXTRAVERSION =
 NAME = "People's Front"
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index e3ebece79617..51fe21f5d078 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -84,6 +84,7 @@ config ARM64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_MULTI_HANDLER
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 25ce9056cf64..c3de0bbf0e9a 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -52,7 +52,8 @@
 #define ARM64_MISMATCHED_CACHE_TYPE		31
 #define ARM64_HAS_STAGE2_FWB			32
 #define ARM64_WORKAROUND_1463225		33
+#define ARM64_SSBS				34
 
-#define ARM64_NCAPS				34
+#define ARM64_NCAPS				35
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 510f687d269a..dda6e5056810 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -525,11 +525,7 @@ static inline int arm64_get_ssbd_state(void)
 #endif
 }
 
-#ifdef CONFIG_ARM64_SSBD
 void arm64_set_ssbd_mitigation(bool state);
-#else
-static inline void arm64_set_ssbd_mitigation(bool state) {}
-#endif
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 6abe4002945f..367b2e0b6d76 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -398,6 +398,8 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
 DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
 
+void __kvm_enable_ssbs(void);
+
 static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
@@ -418,6 +420,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	 */
 	BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
 	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
+
+	/*
+	 * Disabling SSBD on a non-VHE system requires us to enable SSBS
+	 * at EL2.
+	 */
+	if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) &&
+	    arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+		kvm_call_hyp(__kvm_enable_ssbs);
+	}
 }
 
 static inline bool kvm_arch_check_sve_has_vhe(void)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index def5a5e807f0..773ea8e0e442 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -177,11 +177,25 @@ static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
 	regs->pc = pc;
 }
 
+static inline void set_ssbs_bit(struct pt_regs *regs)
+{
+	regs->pstate |= PSR_SSBS_BIT;
+}
+
+static inline void set_compat_ssbs_bit(struct pt_regs *regs)
+{
+	regs->pstate |= PSR_AA32_SSBS_BIT;
+}
+
 static inline void start_thread(struct pt_regs *regs, unsigned long pc,
 				unsigned long sp)
 {
 	start_thread_common(regs, pc);
 	regs->pstate = PSR_MODE_EL0t;
+
+	if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
+		set_ssbs_bit(regs);
+
 	regs->sp = sp;
 }
 
@@ -198,6 +212,9 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 	regs->pstate |= PSR_AA32_E_BIT;
 #endif
 
+	if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
+		set_compat_ssbs_bit(regs);
+
 	regs->compat_sp = sp;
 }
 #endif
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 177b851ca6d9..6bc43889d11e 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -50,6 +50,7 @@
 #define PSR_AA32_I_BIT		0x00000080
 #define PSR_AA32_A_BIT		0x00000100
 #define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_SSBS_BIT	0x00800000
 #define PSR_AA32_DIT_BIT	0x01000000
 #define PSR_AA32_Q_BIT		0x08000000
 #define PSR_AA32_V_BIT		0x10000000
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index c1470931b897..3091ae5975a3 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -86,11 +86,14 @@
 
 #define REG_PSTATE_PAN_IMM		sys_reg(0, 0, 4, 0, 4)
 #define REG_PSTATE_UAO_IMM		sys_reg(0, 0, 4, 0, 3)
+#define REG_PSTATE_SSBS_IMM		sys_reg(0, 3, 4, 0, 1)
 
 #define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM |	\
 				      (!!x)<<8 | 0x1f)
 #define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM |	\
 				      (!!x)<<8 | 0x1f)
+#define SET_PSTATE_SSBS(x) __emit_inst(0xd5000000 | REG_PSTATE_SSBS_IMM | \
+				       (!!x)<<8 | 0x1f)
 
 #define SYS_DC_ISW			sys_insn(1, 0, 7, 6, 2)
 #define SYS_DC_CSW			sys_insn(1, 0, 7, 10, 2)
@@ -419,6 +422,7 @@
 #define SYS_ICH_LR15_EL2		__SYS__LR8_EL2(7)
 
 /* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_DSSBS	(1UL << 44)
 #define SCTLR_ELx_EE    (1 << 25)
 #define SCTLR_ELx_IESB	(1 << 21)
 #define SCTLR_ELx_WXN	(1 << 19)
@@ -439,7 +443,7 @@
 			 (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \
 			 (1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \
 			 (1 << 27) | (1 << 30) | (1 << 31) | \
-			 (0xffffffffUL << 32))
+			 (0xffffefffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL2		SCTLR_ELx_EE
@@ -453,7 +457,7 @@
 #define SCTLR_EL2_SET	(SCTLR_ELx_IESB   | ENDIAN_SET_EL2   | SCTLR_EL2_RES1)
 #define SCTLR_EL2_CLEAR	(SCTLR_ELx_M      | SCTLR_ELx_A    | SCTLR_ELx_C   | \
 			 SCTLR_ELx_SA     | SCTLR_ELx_I    | SCTLR_ELx_WXN | \
-			 ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
+			 SCTLR_ELx_DSSBS | ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
 
 #if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffff
 #error "Inconsistent SCTLR_EL2 set/clear bits"
@@ -477,7 +481,7 @@
 			 (1 << 29))
 #define SCTLR_EL1_RES0  ((1 << 6)  | (1 << 10) | (1 << 13) | (1 << 17) | \
 			 (1 << 27) | (1 << 30) | (1 << 31) | \
-			 (0xffffffffUL << 32))
+			 (0xffffefffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL1		(SCTLR_EL1_E0E | SCTLR_ELx_EE)
@@ -494,7 +498,7 @@
 			 ENDIAN_SET_EL1 | SCTLR_EL1_UCI  | SCTLR_EL1_RES1)
 #define SCTLR_EL1_CLEAR	(SCTLR_ELx_A   | SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD    |\
 			 SCTLR_EL1_UMA | SCTLR_ELx_WXN     | ENDIAN_CLEAR_EL1 |\
-			 SCTLR_EL1_RES0)
+			 SCTLR_ELx_DSSBS | SCTLR_EL1_RES0)
 
 #if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffff
 #error "Inconsistent SCTLR_EL1 set/clear bits"
@@ -544,6 +548,13 @@
 #define ID_AA64PFR0_EL0_64BIT_ONLY	0x1
 #define ID_AA64PFR0_EL0_32BIT_64BIT	0x2
 
+/* id_aa64pfr1 */
+#define ID_AA64PFR1_SSBS_SHIFT		4
+
+#define ID_AA64PFR1_SSBS_PSTATE_NI	0
+#define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
+#define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
+
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_TGRAN4_SHIFT	28
 #define ID_AA64MMFR0_TGRAN64_SHIFT	24
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 17c65c8f33cb..2bcd6e4f3474 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -48,5 +48,6 @@
 #define HWCAP_USCAT		(1 << 25)
 #define HWCAP_ILRCPC		(1 << 26)
 #define HWCAP_FLAGM		(1 << 27)
+#define HWCAP_SSBS		(1 << 28)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 5dff8eccd17d..b0fd1d300154 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -46,6 +46,7 @@
 #define PSR_I_BIT	0x00000080
 #define PSR_A_BIT	0x00000100
 #define PSR_D_BIT	0x00000200
+#define PSR_SSBS_BIT	0x00001000
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
 #define PSR_V_BIT	0x10000000
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index dc6c535cbd13..9ccf16939d13 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -19,6 +19,7 @@
 #include <linux/arm-smccc.h>
 #include <linux/psci.h>
 #include <linux/types.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
@@ -87,7 +88,6 @@ cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
 
 atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 
@@ -109,9 +109,9 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
-				      const char *hyp_vecs_start,
-				      const char *hyp_vecs_end)
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
+				    const char *hyp_vecs_start,
+				    const char *hyp_vecs_end)
 {
 	static DEFINE_SPINLOCK(bp_lock);
 	int cpu, slot = -1;
@@ -138,7 +138,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 #define __smccc_workaround_1_smc_start		NULL
 #define __smccc_workaround_1_smc_end		NULL
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
 {
@@ -146,23 +146,6 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
-				     bp_hardening_cb_t fn,
-				     const char *hyp_vecs_start,
-				     const char *hyp_vecs_end)
-{
-	u64 pfr0;
-
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
-	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
-	if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
-		return;
-
-	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
-}
-
 #include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
 #include <linux/psci.h>
@@ -189,60 +172,83 @@ static void qcom_link_stack_sanitization(void)
 		     : "=&r" (tmp));
 }
 
-static void
-enable_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
+static bool __nospectre_v2;
+static int __init parse_nospectre_v2(char *str)
+{
+	__nospectre_v2 = true;
+	return 0;
+}
+early_param("nospectre_v2", parse_nospectre_v2);
+
+/*
+ * -1: No workaround
+ *  0: No workaround required
+ *  1: Workaround installed
+ */
+static int detect_harden_bp_fw(void)
 {
 	bp_hardening_cb_t cb;
 	void *smccc_start, *smccc_end;
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return;
+		return -1;
 
 	switch (psci_ops.conduit) {
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_hvc_arch_workaround_1;
-		/* This is a guest, no need to patch KVM vectors */
-		smccc_start = NULL;
-		smccc_end = NULL;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_hvc_arch_workaround_1;
+			/* This is a guest, no need to patch KVM vectors */
+			smccc_start = NULL;
+			smccc_end = NULL;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	case PSCI_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_smc_arch_workaround_1;
-		smccc_start = __smccc_workaround_1_smc_start;
-		smccc_end = __smccc_workaround_1_smc_end;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_smc_arch_workaround_1;
+			smccc_start = __smccc_workaround_1_smc_start;
+			smccc_end = __smccc_workaround_1_smc_end;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	default:
-		return;
+		return -1;
 	}
 
 	if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
 	    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1))
 		cb = qcom_link_stack_sanitization;
 
-	install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
+	if (IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR))
+		install_bp_hardening_cb(cb, smccc_start, smccc_end);
 
-	return;
+	return 1;
 }
-#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
-#ifdef CONFIG_ARM64_SSBD
 DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
 
 int ssbd_state __read_mostly = ARM64_SSBD_KERNEL;
+static bool __ssb_safe = true;
 
 static const struct ssbd_options {
 	const char	*str;
@@ -312,6 +318,19 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
 
 void arm64_set_ssbd_mitigation(bool state)
 {
+	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
+		pr_info_once("SSBD disabled by kernel configuration\n");
+		return;
+	}
+
+	if (this_cpu_has_cap(ARM64_SSBS)) {
+		if (state)
+			asm volatile(SET_PSTATE_SSBS(0));
+		else
+			asm volatile(SET_PSTATE_SSBS(1));
+		return;
+	}
+
 	switch (psci_ops.conduit) {
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
@@ -333,11 +352,28 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	struct arm_smccc_res res;
 	bool required = true;
 	s32 val;
+	bool this_cpu_safe = false;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
+	if (cpu_mitigations_off())
+		ssbd_state = ARM64_SSBD_FORCE_DISABLE;
+
+	/* delay setting __ssb_safe until we get a firmware response */
+	if (is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list))
+		this_cpu_safe = true;
+
+	if (this_cpu_has_cap(ARM64_SSBS)) {
+		if (!this_cpu_safe)
+			__ssb_safe = false;
+		required = false;
+		goto out_printmsg;
+	}
+
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -354,6 +390,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 
 	default:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -362,14 +400,18 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	switch (val) {
 	case SMCCC_RET_NOT_SUPPORTED:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 
+	/* machines with mixed mitigation requirements must not return this */
 	case SMCCC_RET_NOT_REQUIRED:
 		pr_info_once("%s mitigation not required\n", entry->desc);
 		ssbd_state = ARM64_SSBD_MITIGATED;
 		return false;
 
 	case SMCCC_RET_SUCCESS:
+		__ssb_safe = false;
 		required = true;
 		break;
 
@@ -379,12 +421,13 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 
 	default:
 		WARN_ON(1);
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
 	switch (ssbd_state) {
 	case ARM64_SSBD_FORCE_DISABLE:
-		pr_info_once("%s disabled from command-line\n", entry->desc);
 		arm64_set_ssbd_mitigation(false);
 		required = false;
 		break;
@@ -397,7 +440,6 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 		break;
 
 	case ARM64_SSBD_FORCE_ENABLE:
-		pr_info_once("%s forced from command-line\n", entry->desc);
 		arm64_set_ssbd_mitigation(true);
 		required = true;
 		break;
@@ -407,9 +449,27 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 		break;
 	}
 
+out_printmsg:
+	switch (ssbd_state) {
+	case ARM64_SSBD_FORCE_DISABLE:
+		pr_info_once("%s disabled from command-line\n", entry->desc);
+		break;
+
+	case ARM64_SSBD_FORCE_ENABLE:
+		pr_info_once("%s forced from command-line\n", entry->desc);
+		break;
+	}
+
 	return required;
 }
-#endif	/* CONFIG_ARM64_SSBD */
+
+/* known invulnerable cores */
+static const struct midr_range arm64_ssb_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	{},
+};
 
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
@@ -464,6 +524,10 @@ has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry,
 	.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,			\
 	CAP_MIDR_RANGE_LIST(midr_list)
 
+/* Track overall mitigation state. We are only mitigated if all cores are ok */
+static bool __hardenbp_enab = true;
+static bool __spectrev2_safe = true;
+
 /*
  * Generic helper for handling capabilties with multiple (match,enable) pairs
  * of call backs, sharing the same capability bit.
@@ -496,26 +560,63 @@ multi_entry_cap_cpu_enable(const struct arm64_cpu_capabilities *entry)
 			caps->cpu_enable(caps);
 }
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
-
 /*
- * List of CPUs where we need to issue a psci call to
- * harden the branch predictor.
+ * List of CPUs that do not need any Spectre-v2 mitigation at all.
  */
-static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
-	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
-	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
-	MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
-	{},
+static const struct midr_range spectre_v2_safe_list[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	{ /* sentinel */ }
 };
 
-#endif
+/*
+ * Track overall bp hardening for all heterogeneous cores in the machine.
+ * We are only considered "safe" if all booted cores are known safe.
+ */
+static bool __maybe_unused
+check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	int need_wa;
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	/* If the CPU has CSV2 set, we're safe */
+	if (cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64PFR0_EL1),
+						 ID_AA64PFR0_CSV2_SHIFT))
+		return false;
+
+	/* Alternatively, we have a list of unaffected CPUs */
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+		return false;
+
+	/* Fallback to firmware detection */
+	need_wa = detect_harden_bp_fw();
+	if (!need_wa)
+		return false;
+
+	__spectrev2_safe = false;
+
+	if (!IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) {
+		pr_warn_once("spectrev2 mitigation disabled by kernel configuration\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	/* forced off */
+	if (__nospectre_v2 || cpu_mitigations_off()) {
+		pr_info_once("spectrev2 mitigation disabled by command line option\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	if (need_wa < 0) {
+		pr_warn_once("ARM_SMCCC_ARCH_WORKAROUND_1 missing from firmware\n");
+		__hardenbp_enab = false;
+	}
+
+	return (need_wa > 0);
+}
 
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
@@ -674,13 +775,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 	},
 #endif
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
-		.cpu_enable = enable_smccc_arch_workaround_1,
-		ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = check_branch_predictor,
 	},
-#endif
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 	{
 		.desc = "EL2 vector hardening",
@@ -688,14 +787,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
 	},
 #endif
-#ifdef CONFIG_ARM64_SSBD
 	{
 		.desc = "Speculative Store Bypass Disable",
 		.capability = ARM64_SSBD,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_ssbd_mitigation,
+		.midr_range_list = arm64_ssb_cpus,
 	},
-#endif
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 	{
 		.desc = "ARM erratum 1463225",
@@ -707,3 +805,38 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 	}
 };
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	if (__spectrev2_safe)
+		return sprintf(buf, "Not affected\n");
+
+	if (__hardenbp_enab)
+		return sprintf(buf, "Mitigation: Branch predictor hardening\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (__ssb_safe)
+		return sprintf(buf, "Not affected\n");
+
+	switch (ssbd_state) {
+	case ARM64_SSBD_KERNEL:
+	case ARM64_SSBD_FORCE_ENABLE:
+		if (IS_ENABLED(CONFIG_ARM64_SSBD))
+			return sprintf(buf,
+			    "Mitigation: Speculative Store Bypass disabled via prctl\n");
+	}
+
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index a897efdb3ddd..ff5beb59b3dc 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -24,6 +24,7 @@
 #include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -164,6 +165,11 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	/*
 	 * We already refuse to boot CPUs that don't support our configured
@@ -379,7 +385,7 @@ static const struct __ftr_reg_entry {
 
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
-	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz),
+	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
 	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
@@ -669,7 +675,6 @@ void update_cpu_features(int cpu,
 
 	/*
 	 * EL3 is not our concern.
-	 * ID_AA64PFR1 is currently RES0.
 	 */
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
 				      info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
@@ -885,7 +890,7 @@ static bool has_cache_dic(const struct arm64_cpu_capabilities *entry,
 	return ctr & BIT(CTR_DIC_SHIFT);
 }
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static bool __meltdown_safe = true;
 static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
 
 static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
@@ -903,7 +908,17 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		{ /* sentinel */ }
 	};
-	char const *str = "command line option";
+	char const *str = "kpti command line option";
+	bool meltdown_safe;
+
+	meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list);
+
+	/* Defer to CPU feature registers */
+	if (has_cpuid_feature(entry, scope))
+		meltdown_safe = true;
+
+	if (!meltdown_safe)
+		__meltdown_safe = false;
 
 	/*
 	 * For reasons that aren't entirely clear, enabling KPTI on Cavium
@@ -915,6 +930,24 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		__kpti_forced = -1;
 	}
 
+	/* Useful for KASLR robustness */
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) {
+		if (!__kpti_forced) {
+			str = "KASLR";
+			__kpti_forced = 1;
+		}
+	}
+
+	if (cpu_mitigations_off() && !__kpti_forced) {
+		str = "mitigations=off";
+		__kpti_forced = -1;
+	}
+
+	if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) {
+		pr_info_once("kernel page table isolation disabled by kernel configuration\n");
+		return false;
+	}
+
 	/* Forced? */
 	if (__kpti_forced) {
 		pr_info_once("kernel page table isolation forced %s by %s\n",
@@ -922,18 +955,10 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		return __kpti_forced > 0;
 	}
 
-	/* Useful for KASLR robustness */
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		return true;
-
-	/* Don't force KPTI for CPUs that are not vulnerable */
-	if (is_midr_in_range_list(read_cpuid_id(), kpti_safe_list))
-		return false;
-
-	/* Defer to CPU feature registers */
-	return !has_cpuid_feature(entry, scope);
+	return !meltdown_safe;
 }
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static void
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
@@ -958,6 +983,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 
 	return;
 }
+#else
+static void
+kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
+{
+}
+#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 static int __init parse_kpti(char *str)
 {
@@ -971,7 +1002,6 @@ static int __init parse_kpti(char *str)
 	return 0;
 }
 early_param("kpti", parse_kpti);
-#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 static inline void __cpu_enable_hw_dbm(void)
@@ -1067,6 +1097,48 @@ static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused)
 	WARN_ON(val & (7 << 27 | 7 << 21));
 }
 
+#ifdef CONFIG_ARM64_SSBD
+static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
+{
+	if (user_mode(regs))
+		return 1;
+
+	if (instr & BIT(CRm_shift))
+		regs->pstate |= PSR_SSBS_BIT;
+	else
+		regs->pstate &= ~PSR_SSBS_BIT;
+
+	arm64_skip_faulting_instruction(regs, 4);
+	return 0;
+}
+
+static struct undef_hook ssbs_emulation_hook = {
+	.instr_mask	= ~(1U << CRm_shift),
+	.instr_val	= 0xd500001f | REG_PSTATE_SSBS_IMM,
+	.fn		= ssbs_emulation_handler,
+};
+
+static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused)
+{
+	static bool undef_hook_registered = false;
+	static DEFINE_SPINLOCK(hook_lock);
+
+	spin_lock(&hook_lock);
+	if (!undef_hook_registered) {
+		register_undef_hook(&ssbs_emulation_hook);
+		undef_hook_registered = true;
+	}
+	spin_unlock(&hook_lock);
+
+	if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+		sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
+		arm64_set_ssbd_mitigation(false);
+	} else {
+		arm64_set_ssbd_mitigation(true);
+	}
+}
+#endif /* CONFIG_ARM64_SSBD */
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -1150,7 +1222,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
 	},
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	{
 		.desc = "Kernel page table isolation (KPTI)",
 		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
@@ -1166,7 +1237,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = unmap_kernel_at_el0,
 		.cpu_enable = kpti_install_ng_mappings,
 	},
-#endif
 	{
 		/* FP/SIMD is not implemented */
 		.capability = ARM64_HAS_NO_FPSIMD,
@@ -1253,6 +1323,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_hw_dbm,
 		.cpu_enable = cpu_enable_hw_dbm,
 	},
+#endif
+#ifdef CONFIG_ARM64_SSBD
+	{
+		.desc = "Speculative Store Bypassing Safe (SSBS)",
+		.capability = ARM64_SSBS,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.field_pos = ID_AA64PFR1_SSBS_SHIFT,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY,
+		.cpu_enable = cpu_enable_ssbs,
+	},
 #endif
 	{},
 };
@@ -1299,6 +1382,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 #ifdef CONFIG_ARM64_SVE
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
 #endif
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS),
 	{},
 };
 
@@ -1793,3 +1877,15 @@ void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
 	/* Firmware may have left a deferred SError in this register. */
 	write_sysreg_s(0, SYS_DISR_EL1);
 }
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	if (__meltdown_safe)
+		return sprintf(buf, "Not affected\n");
+
+	if (arm64_kernel_unmapped_at_el0())
+		return sprintf(buf, "Mitigation: PTI\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index e9ab7b3ed317..dce971f2c167 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -81,6 +81,7 @@ static const char *const hwcap_str[] = {
 	"uscat",
 	"ilrcpc",
 	"flagm",
+	"ssbs",
 	NULL
 };
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7f1628effe6d..bc2226608e13 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -358,6 +358,10 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		if (IS_ENABLED(CONFIG_ARM64_UAO) &&
 		    cpus_have_const_cap(ARM64_HAS_UAO))
 			childregs->pstate |= PSR_UAO_BIT;
+
+		if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
+			set_ssbs_bit(childregs);
+
 		p->thread.cpu_context.x19 = stack_start;
 		p->thread.cpu_context.x20 = stk_sz;
 	}
@@ -397,6 +401,32 @@ void uao_thread_switch(struct task_struct *next)
 	}
 }
 
+/*
+ * Force SSBS state on context-switch, since it may be lost after migrating
+ * from a CPU which treats the bit as RES0 in a heterogeneous system.
+ */
+static void ssbs_thread_switch(struct task_struct *next)
+{
+	struct pt_regs *regs = task_pt_regs(next);
+
+	/*
+	 * Nothing to do for kernel threads, but 'regs' may be junk
+	 * (e.g. idle task) so check the flags and bail early.
+	 */
+	if (unlikely(next->flags & PF_KTHREAD))
+		return;
+
+	/* If the mitigation is enabled, then we leave SSBS clear. */
+	if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
+	    test_tsk_thread_flag(next, TIF_SSBD))
+		return;
+
+	if (compat_user_mode(regs))
+		set_compat_ssbs_bit(regs);
+	else if (user_mode(regs))
+		set_ssbs_bit(regs);
+}
+
 /*
  * We store our current task in sp_el0, which is clobbered by userspace. Keep a
  * shadow copy so that we can restore this upon entry from userspace.
@@ -425,6 +455,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	contextidr_thread_switch(next);
 	entry_task_switch(next);
 	uao_thread_switch(next);
+	ssbs_thread_switch(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6219486fa25f..0211c3c7533b 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1666,19 +1666,20 @@ void syscall_trace_exit(struct pt_regs *regs)
 }
 
 /*
- * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a
- * We also take into account DIT (bit 24), which is not yet documented, and
- * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be
- * allocated an EL0 meaning in future.
+ * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a.
+ * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is
+ * not described in ARM DDI 0487D.a.
+ * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may
+ * be allocated an EL0 meaning in future.
  * Userspace cannot use these until they have an architectural meaning.
  * Note that this follows the SPSR_ELx format, not the AArch32 PSR format.
  * We also reserve IL for the kernel; SS is handled dynamically.
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
-	 GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5))
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
+	 GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20))
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20))
 
 static int valid_compat_regs(struct user_pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c
index 388f8fc13080..f496fb2f7122 100644
--- a/arch/arm64/kernel/ssbd.c
+++ b/arch/arm64/kernel/ssbd.c
@@ -3,13 +3,31 @@
  * Copyright (C) 2018 ARM Ltd, All Rights Reserved.
  */
 
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/prctl.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/thread_info.h>
 
 #include <asm/cpufeature.h>
 
+static void ssbd_ssbs_enable(struct task_struct *task)
+{
+	u64 val = is_compat_thread(task_thread_info(task)) ?
+		  PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+	task_pt_regs(task)->pstate |= val;
+}
+
+static void ssbd_ssbs_disable(struct task_struct *task)
+{
+	u64 val = is_compat_thread(task_thread_info(task)) ?
+		  PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+	task_pt_regs(task)->pstate &= ~val;
+}
+
 /*
  * prctl interface for SSBD
  * FIXME: Drop the below ifdefery once merged in 4.18.
@@ -47,12 +65,14 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
 			return -EPERM;
 		task_clear_spec_ssb_disable(task);
 		clear_tsk_thread_flag(task, TIF_SSBD);
+		ssbd_ssbs_enable(task);
 		break;
 	case PR_SPEC_DISABLE:
 		if (state == ARM64_SSBD_FORCE_DISABLE)
 			return -EPERM;
 		task_set_spec_ssb_disable(task);
 		set_tsk_thread_flag(task, TIF_SSBD);
+		ssbd_ssbs_disable(task);
 		break;
 	case PR_SPEC_FORCE_DISABLE:
 		if (state == ARM64_SSBD_FORCE_DISABLE)
@@ -60,6 +80,7 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
 		task_set_spec_ssb_disable(task);
 		task_set_spec_ssb_force_disable(task);
 		set_tsk_thread_flag(task, TIF_SSBD);
+		ssbd_ssbs_disable(task);
 		break;
 	default:
 		return -ERANGE;
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 963d669ae3a2..7414b76191c2 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -293,3 +293,14 @@ void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.sysregs_loaded_on_cpu = false;
 }
+
+void __hyp_text __kvm_enable_ssbs(void)
+{
+	u64 tmp;
+
+	asm volatile(
+	"mrs	%0, sctlr_el2\n"
+	"orr	%0, %0, %1\n"
+	"msr	sctlr_el2, %0"
+	: "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
+}
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 0edba3e75747..4e2ee743088f 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -387,6 +387,22 @@
 #define cpu_has_dsp3		__ase(MIPS_ASE_DSP3)
 #endif
 
+#ifndef cpu_has_loongson_mmi
+#define cpu_has_loongson_mmi		__ase(MIPS_ASE_LOONGSON_MMI)
+#endif
+
+#ifndef cpu_has_loongson_cam
+#define cpu_has_loongson_cam		__ase(MIPS_ASE_LOONGSON_CAM)
+#endif
+
+#ifndef cpu_has_loongson_ext
+#define cpu_has_loongson_ext		__ase(MIPS_ASE_LOONGSON_EXT)
+#endif
+
+#ifndef cpu_has_loongson_ext2
+#define cpu_has_loongson_ext2		__ase(MIPS_ASE_LOONGSON_EXT2)
+#endif
+
 #ifndef cpu_has_mipsmt
 #define cpu_has_mipsmt		__isa_lt_and_ase(6, MIPS_ASE_MIPSMT)
 #endif
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index dacbdb84516a..2b4b14a56575 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -436,5 +436,9 @@ enum cpu_type_enum {
 #define MIPS_ASE_MSA		0x00000100 /* MIPS SIMD Architecture */
 #define MIPS_ASE_DSP3		0x00000200 /* Signal Processing ASE Rev 3*/
 #define MIPS_ASE_MIPS16E2	0x00000400 /* MIPS16e2 */
+#define MIPS_ASE_LOONGSON_MMI	0x00000800 /* Loongson MultiMedia extensions Instructions */
+#define MIPS_ASE_LOONGSON_CAM	0x00001000 /* Loongson CAM */
+#define MIPS_ASE_LOONGSON_EXT	0x00002000 /* Loongson EXTensions */
+#define MIPS_ASE_LOONGSON_EXT2	0x00004000 /* Loongson EXTensions R2 */
 
 #endif /* _ASM_CPU_H */
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 25cd8737e7fe..958b627592c3 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1489,6 +1489,8 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
 			set_isa(c, MIPS_CPU_ISA_M64R1);
+			c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
+				MIPS_ASE_LOONGSON_EXT);
 			break;
 		case PRID_REV_LOONGSON3B_R1:
 		case PRID_REV_LOONGSON3B_R2:
@@ -1496,6 +1498,8 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3b");
 			set_isa(c, MIPS_CPU_ISA_M64R1);
+			c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
+				MIPS_ASE_LOONGSON_EXT);
 			break;
 		}
 
@@ -1861,6 +1865,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		decode_configs(c);
 		c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
 		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
+		c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
+			MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2);
 		break;
 	default:
 		panic("Unknown Loongson Processor ID!");
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index b2de408a259e..f8d36710cd58 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -124,6 +124,10 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (cpu_has_eva)	seq_printf(m, "%s", " eva");
 	if (cpu_has_htw)	seq_printf(m, "%s", " htw");
 	if (cpu_has_xpa)	seq_printf(m, "%s", " xpa");
+	if (cpu_has_loongson_mmi)	seq_printf(m, "%s", " loongson-mmi");
+	if (cpu_has_loongson_cam)	seq_printf(m, "%s", " loongson-cam");
+	if (cpu_has_loongson_ext)	seq_printf(m, "%s", " loongson-ext");
+	if (cpu_has_loongson_ext2)	seq_printf(m, "%s", " loongson-ext2");
 	seq_printf(m, "\n");
 
 	if (cpu_has_mmips) {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 29f49a35d6ee..6a6804c2e1b0 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -212,7 +212,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x0000080000000000)
 #define CPU_FTR_P9_TM_HV_ASSIST		LONG_ASM_CONST(0x0000100000000000)
 #define CPU_FTR_P9_TM_XER_SO_BUG	LONG_ASM_CONST(0x0000200000000000)
-#define CPU_FTR_P9_TLBIE_BUG		LONG_ASM_CONST(0x0000400000000000)
+#define CPU_FTR_P9_TLBIE_STQ_BUG	LONG_ASM_CONST(0x0000400000000000)
 #define CPU_FTR_P9_TIDR			LONG_ASM_CONST(0x0000800000000000)
 
 #ifndef __ASSEMBLY__
@@ -460,7 +460,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
 	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
-	    CPU_FTR_P9_TLBIE_BUG | CPU_FTR_P9_TIDR)
+	    CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TIDR)
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
 #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1)
 #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index f432054234a4..f3b8e04eca9c 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -694,9 +694,35 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
 	return true;
 }
 
+/*
+ * Handle POWER9 broadcast tlbie invalidation issue using
+ * cpu feature flag.
+ */
+static __init void update_tlbie_feature_flag(unsigned long pvr)
+{
+	if (PVR_VER(pvr) == PVR_POWER9) {
+		/*
+		 * Set the tlbie feature flag for anything below
+		 * Nimbus DD 2.3 and Cumulus DD 1.3
+		 */
+		if ((pvr & 0xe000) == 0) {
+			/* Nimbus */
+			if ((pvr & 0xfff) < 0x203)
+				cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		} else if ((pvr & 0xc000) == 0) {
+			/* Cumulus */
+			if ((pvr & 0xfff) < 0x103)
+				cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		} else {
+			WARN_ONCE(1, "Unknown PVR");
+			cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		}
+	}
+}
+
 static __init void cpufeatures_cpu_quirks(void)
 {
-	int version = mfspr(SPRN_PVR);
+	unsigned long version = mfspr(SPRN_PVR);
 
 	/*
 	 * Not all quirks can be derived from the cpufeatures device tree.
@@ -715,10 +741,10 @@ static __init void cpufeatures_cpu_quirks(void)
 
 	if ((version & 0xffff0000) == 0x004e0000) {
 		cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
-		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG;
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TIDR;
 	}
 
+	update_tlbie_feature_flag(version);
 	/*
 	 * PKEY was not in the initial base or feature node
 	 * specification, but it should become optional in the next
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index efdd16a79075..93e06778b136 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -45,6 +45,7 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],
 					mce_ue_event_queue);
 
 static void machine_check_process_queued_event(struct irq_work *work);
+static void machine_check_ue_irq_work(struct irq_work *work);
 void machine_check_ue_event(struct machine_check_event *evt);
 static void machine_process_ue_event(struct work_struct *work);
 
@@ -52,6 +53,10 @@ static struct irq_work mce_event_process_work = {
         .func = machine_check_process_queued_event,
 };
 
+static struct irq_work mce_ue_event_irq_work = {
+	.func = machine_check_ue_irq_work,
+};
+
 DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
 
 static void mce_set_error_info(struct machine_check_event *mce,
@@ -208,6 +213,10 @@ void release_mce_event(void)
 	get_mce_event(NULL, true);
 }
 
+static void machine_check_ue_irq_work(struct irq_work *work)
+{
+	schedule_work(&mce_ue_event_work);
+}
 
 /*
  * Queue up the MCE event which then can be handled later.
@@ -225,7 +234,7 @@ void machine_check_ue_event(struct machine_check_event *evt)
 	memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt));
 
 	/* Queue work to process this event later. */
-	schedule_work(&mce_ue_event_work);
+	irq_work_queue(&mce_ue_event_irq_work);
 }
 
 /*
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 3022d67f0c48..37a110b8e7e1 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -39,6 +39,7 @@
 static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
 {
 	pte_t *ptep;
+	unsigned int shift;
 	unsigned long flags;
 	struct mm_struct *mm;
 
@@ -48,13 +49,18 @@ static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
 		mm = &init_mm;
 
 	local_irq_save(flags);
-	if (mm == current->mm)
-		ptep = find_current_mm_pte(mm->pgd, addr, NULL, NULL);
-	else
-		ptep = find_init_mm_pte(addr, NULL);
+	ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift);
 	local_irq_restore(flags);
+
 	if (!ptep || pte_special(*ptep))
 		return ULONG_MAX;
+
+	if (shift > PAGE_SHIFT) {
+		unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+
+		return pte_pfn(__pte(pte_val(*ptep) | (addr & rpnmask)));
+	}
+
 	return pte_pfn(*ptep);
 }
 
@@ -339,7 +345,7 @@ static const struct mce_derror_table mce_p9_derror_table[] = {
   MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
 { 0, false, 0, 0, 0, 0 } };
 
-static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr,
+static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
 					uint64_t *phys_addr)
 {
 	/*
@@ -530,7 +536,8 @@ static int mce_handle_derror(struct pt_regs *regs,
 			 * kernel/exception-64s.h
 			 */
 			if (get_paca()->in_mce < MAX_MCE_DEPTH)
-				mce_find_instr_ea_and_pfn(regs, addr, phys_addr);
+				mce_find_instr_ea_and_phys(regs, addr,
+							   phys_addr);
 		}
 		found = 1;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 05b32cc12e41..3ae3e8d141e3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1407,7 +1407,14 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, vcpu->arch.pspb);
 		break;
 	case KVM_REG_PPC_DPDES:
-		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
+		/*
+		 * On POWER9, where we are emulating msgsndp etc.,
+		 * we return 1 bit for each vcpu, which can come from
+		 * either vcore->dpdes or doorbell_request.
+		 * On POWER8, doorbell_request is 0.
+		 */
+		*val = get_reg_val(id, vcpu->arch.vcore->dpdes |
+				   vcpu->arch.doorbell_request);
 		break;
 	case KVM_REG_PPC_VTB:
 		*val = get_reg_val(id, vcpu->arch.vcore->vtb);
@@ -2550,7 +2557,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads)
 		if (!spin_trylock(&pvc->lock))
 			continue;
 		prepare_threads(pvc);
-		if (!pvc->n_runnable) {
+		if (!pvc->n_runnable || !pvc->kvm->arch.mmu_ready) {
 			list_del_init(&pvc->preempt_list);
 			if (pvc->runner == NULL) {
 				pvc->vcore_state = VCORE_INACTIVE;
@@ -2571,15 +2578,20 @@ static void collect_piggybacks(struct core_info *cip, int target_threads)
 	spin_unlock(&lp->lock);
 }
 
-static bool recheck_signals(struct core_info *cip)
+static bool recheck_signals_and_mmu(struct core_info *cip)
 {
 	int sub, i;
 	struct kvm_vcpu *vcpu;
+	struct kvmppc_vcore *vc;
 
-	for (sub = 0; sub < cip->n_subcores; ++sub)
-		for_each_runnable_thread(i, vcpu, cip->vc[sub])
+	for (sub = 0; sub < cip->n_subcores; ++sub) {
+		vc = cip->vc[sub];
+		if (!vc->kvm->arch.mmu_ready)
+			return true;
+		for_each_runnable_thread(i, vcpu, vc)
 			if (signal_pending(vcpu->arch.run_task))
 				return true;
+	}
 	return false;
 }
 
@@ -2800,7 +2812,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	local_irq_disable();
 	hard_irq_disable();
 	if (lazy_irq_pending() || need_resched() ||
-	    recheck_signals(&core_info) || !vc->kvm->arch.mmu_ready) {
+	    recheck_signals_and_mmu(&core_info)) {
 		local_irq_enable();
 		vc->vcore_state = VCORE_INACTIVE;
 		/* Unlock all except the primary vcore */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index a67cf1cdeda4..7c68d834c94a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -452,7 +452,7 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
 		}
 
-		if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 			/*
 			 * Need the extra ptesync to make sure we don't
 			 * re-order the tlbie
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 68c7591f2b5f..f1878e13dd56 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2903,29 +2903,39 @@ kvm_cede_prodded:
 kvm_cede_exit:
 	ld	r9, HSTATE_KVM_VCPU(r13)
 #ifdef CONFIG_KVM_XICS
-	/* Abort if we still have a pending escalation */
+	/* are we using XIVE with single escalation? */
+	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
+	cmpdi	r10, 0
+	beq	3f
+	li	r6, XIVE_ESB_SET_PQ_00
+	/*
+	 * If we still have a pending escalation, abort the cede,
+	 * and we must set PQ to 10 rather than 00 so that we don't
+	 * potentially end up with two entries for the escalation
+	 * interrupt in the XIVE interrupt queue.  In that case
+	 * we also don't want to set xive_esc_on to 1 here in
+	 * case we race with xive_esc_irq().
+	 */
 	lbz	r5, VCPU_XIVE_ESC_ON(r9)
 	cmpwi	r5, 0
-	beq	1f
+	beq	4f
 	li	r0, 0
 	stb	r0, VCPU_CEDED(r9)
-1:	/* Enable XIVE escalation */
-	li	r5, XIVE_ESB_SET_PQ_00
+	li	r6, XIVE_ESB_SET_PQ_10
+	b	5f
+4:	li	r0, 1
+	stb	r0, VCPU_XIVE_ESC_ON(r9)
+	/* make sure store to xive_esc_on is seen before xive_esc_irq runs */
+	sync
+5:	/* Enable XIVE escalation */
 	mfmsr	r0
 	andi.	r0, r0, MSR_DR		/* in real mode? */
 	beq	1f
-	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
-	cmpdi	r10, 0
-	beq	3f
-	ldx	r0, r10, r5
+	ldx	r0, r10, r6
 	b	2f
 1:	ld	r10, VCPU_XIVE_ESC_RADDR(r9)
-	cmpdi	r10, 0
-	beq	3f
-	ldcix	r0, r10, r5
+	ldcix	r0, r10, r6
 2:	sync
-	li	r0, 1
-	stb	r0, VCPU_XIVE_ESC_ON(r9)
 #endif /* CONFIG_KVM_XICS */
 3:	b	guest_exit_cont
 
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index aae34f218ab4..031f07f048af 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -1037,20 +1037,22 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	/* Mask the VP IPI */
 	xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01);
 
-	/* Disable the VP */
-	xive_native_disable_vp(xc->vp_id);
-
-	/* Free the queues & associated interrupts */
+	/* Free escalations */
 	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
-		struct xive_q *q = &xc->queues[i];
-
-		/* Free the escalation irq */
 		if (xc->esc_virq[i]) {
 			free_irq(xc->esc_virq[i], vcpu);
 			irq_dispose_mapping(xc->esc_virq[i]);
 			kfree(xc->esc_virq_names[i]);
 		}
-		/* Free the queue */
+	}
+
+	/* Disable the VP */
+	xive_native_disable_vp(xc->vp_id);
+
+	/* Free the queues */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		struct xive_q *q = &xc->queues[i];
+
 		xive_native_disable_queue(xc->vp_id, q, i);
 		if (q->qpage) {
 			free_pages((unsigned long)q->qpage,
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index aaa28fd918fe..0c13561d8b80 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -203,7 +203,7 @@ static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 
 static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 		/* Need the extra ptesync to ensure we don't reorder tlbie*/
 		asm volatile("ptesync": : :"memory");
 		___tlbie(vpn, psize, apsize, ssize);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 29fd8940867e..b1007e9a31ba 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -37,6 +37,7 @@
 #include <linux/context_tracking.h>
 #include <linux/libfdt.h>
 #include <linux/pkeys.h>
+#include <linux/cpu.h>
 
 #include <asm/debugfs.h>
 #include <asm/processor.h>
@@ -1891,10 +1892,16 @@ static int hpt_order_get(void *data, u64 *val)
 
 static int hpt_order_set(void *data, u64 val)
 {
+	int ret;
+
 	if (!mmu_hash_ops.resize_hpt)
 		return -ENODEV;
 
-	return mmu_hash_ops.resize_hpt(val);
+	cpus_read_lock();
+	ret = mmu_hash_ops.resize_hpt(val);
+	cpus_read_unlock();
+
+	return ret;
 }
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n");
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index fef3e1eb3a19..0cddae4263f9 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -220,7 +220,7 @@ static inline void fixup_tlbie(void)
 	unsigned long pid = 0;
 	unsigned long va = ((1UL << 52) - 1);
 
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 		asm volatile("ptesync": : :"memory");
 		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
 	}
@@ -230,7 +230,7 @@ static inline void fixup_tlbie_lpid(unsigned long lpid)
 {
 	unsigned long va = ((1UL << 52) - 1);
 
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 		asm volatile("ptesync": : :"memory");
 		__tlbie_lpid_va(va, lpid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
 	}
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 38fe4087484a..edf9032e2e5c 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -680,7 +680,10 @@ static ssize_t symbol_map_read(struct file *fp, struct kobject *kobj,
 				       bin_attr->size);
 }
 
-static BIN_ATTR_RO(symbol_map, 0);
+static struct bin_attribute symbol_map_attr = {
+	.attr = {.name = "symbol_map", .mode = 0400},
+	.read = symbol_map_read
+};
 
 static void opal_export_symmap(void)
 {
@@ -697,10 +700,10 @@ static void opal_export_symmap(void)
 		return;
 
 	/* Setup attributes */
-	bin_attr_symbol_map.private = __va(be64_to_cpu(syms[0]));
-	bin_attr_symbol_map.size = be64_to_cpu(syms[1]);
+	symbol_map_attr.private = __va(be64_to_cpu(syms[0]));
+	symbol_map_attr.size = be64_to_cpu(syms[1]);
 
-	rc = sysfs_create_bin_file(opal_kobj, &bin_attr_symbol_map);
+	rc = sysfs_create_bin_file(opal_kobj, &symbol_map_attr);
 	if (rc)
 		pr_warn("Error %d creating OPAL symbols file\n", rc);
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index 29e66d6e5763..15a567128c0f 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -49,6 +49,9 @@ static __be64 *pnv_alloc_tce_level(int nid, unsigned int shift)
 	return addr;
 }
 
+static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
+		unsigned long size, unsigned int levels);
+
 static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
 {
 	__be64 *tmp = user ? tbl->it_userspace : (__be64 *) tbl->it_base;
@@ -58,9 +61,9 @@ static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
 
 	while (level) {
 		int n = (idx & mask) >> (level * shift);
-		unsigned long tce;
+		unsigned long oldtce, tce = be64_to_cpu(READ_ONCE(tmp[n]));
 
-		if (tmp[n] == 0) {
+		if (!tce) {
 			__be64 *tmp2;
 
 			if (!alloc)
@@ -71,10 +74,15 @@ static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
 			if (!tmp2)
 				return NULL;
 
-			tmp[n] = cpu_to_be64(__pa(tmp2) |
-					TCE_PCI_READ | TCE_PCI_WRITE);
+			tce = __pa(tmp2) | TCE_PCI_READ | TCE_PCI_WRITE;
+			oldtce = be64_to_cpu(cmpxchg(&tmp[n], 0,
+					cpu_to_be64(tce)));
+			if (oldtce) {
+				pnv_pci_ioda2_table_do_free_pages(tmp2,
+					ilog2(tbl->it_level_size) + 3, 1);
+				tce = oldtce;
+			}
 		}
-		tce = be64_to_cpu(tmp[n]);
 
 		tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE));
 		idx &= ~mask;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 9e52b686a8fa..ea602f7f97ce 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -647,7 +647,10 @@ static int pseries_lpar_resize_hpt_commit(void *data)
 	return 0;
 }
 
-/* Must be called in user context */
+/*
+ * Must be called in process context. The caller must hold the
+ * cpus_lock.
+ */
 static int pseries_lpar_resize_hpt(unsigned long shift)
 {
 	struct hpt_resize_state state = {
@@ -699,7 +702,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift)
 
 	t1 = ktime_get();
 
-	rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL);
+	rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit,
+				     &state, NULL);
 
 	t2 = ktime_get();
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index fa2c08e3c05e..a03821b2656a 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -171,9 +171,13 @@ ENTRY(handle_exception)
 	move a1, s4 /* scause */
 	tail do_IRQ
 1:
-	/* Exceptions run with interrupts enabled */
+	/* Exceptions run with interrupts enabled or disabled
+	   depending on the state of sstatus.SR_SPIE */
+	andi t0, s1, SR_SPIE
+	beqz t0, 1f
 	csrs sstatus, SR_SIE
 
+1:
 	/* Handle syscalls */
 	li t0, EXC_SYSCALL
 	beq s4, t0, handle_syscall
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 6e758bb6cd29..99ef537e548a 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -183,20 +183,30 @@ unsigned long get_wchan(struct task_struct *p)
 
 	if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
 		return 0;
+
+	if (!try_get_task_stack(p))
+		return 0;
+
 	low = task_stack_page(p);
 	high = (struct stack_frame *) task_pt_regs(p);
 	sf = (struct stack_frame *) p->thread.ksp;
-	if (sf <= low || sf > high)
-		return 0;
+	if (sf <= low || sf > high) {
+		return_address = 0;
+		goto out;
+	}
 	for (count = 0; count < 16; count++) {
 		sf = (struct stack_frame *) sf->back_chain;
-		if (sf <= low || sf > high)
-			return 0;
+		if (sf <= low || sf > high) {
+			return_address = 0;
+			goto out;
+		}
 		return_address = sf->gprs[8];
 		if (!in_sched_functions(return_address))
-			return return_address;
+			goto out;
 	}
-	return 0;
+out:
+	put_task_stack(p);
+	return return_address;
 }
 
 unsigned long arch_align_stack(unsigned long sp)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index e8184a15578a..7b96888974db 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -311,7 +311,8 @@ int arch_update_cpu_topology(void)
 	on_each_cpu(__arch_update_dedicated_flag, NULL, 0);
 	for_each_online_cpu(cpu) {
 		dev = get_cpu_device(cpu);
-		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+		if (dev)
+			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
 	}
 	return rc;
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e0551c948c59..fac1d4eaa426 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3890,7 +3890,7 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 	const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
 				    | KVM_S390_MEMOP_F_CHECK_ONLY;
 
-	if (mop->flags & ~supported_flags)
+	if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size)
 		return -EINVAL;
 
 	if (mop->size > MEM_OP_MAX_SIZE)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e83f4f6bfdac..6f7b3acdab26 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8801,7 +8801,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
 		if (kvm_write_guest_virt_system(vcpu, gva, &field_value,
 						(is_long_mode(vcpu) ? 8 : 4),
-						NULL))
+						&e))
 			kvm_inject_page_fault(vcpu, &e);
 	}
 
@@ -12574,7 +12574,7 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 		/* VM-entry exception error code */
 		if (has_error_code &&
-		    vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))
+		    vmcs12->vm_entry_exception_error_code & GENMASK(31, 16))
 			return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
 		/* VM-entry interruption-info field: reserved bits */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 05cb5855255e..6ae8a013af31 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -791,34 +791,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
-int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
-
 	if (cr4 & CR4_RESERVED_BITS)
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+		return -EINVAL;
+
+	return 0;
+}
+
+int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	unsigned long old_cr4 = kvm_read_cr4(vcpu);
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+
+	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -8237,10 +8245,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
 
 static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-			(sregs->cr4 & X86_CR4_OSXSAVE))
-		return  -EINVAL;
-
 	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
 		 * When EFER.LME and CR0.PG are set, the processor is in
@@ -8259,7 +8263,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 			return -EINVAL;
 	}
 
-	return 0;
+	return kvm_valid_cr4(vcpu, sregs->cr4);
 }
 
 static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 10fb42da0007..b81b5172cf99 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -23,6 +23,7 @@ KCOV_INSTRUMENT := n
 
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
 PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
+PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN)
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
 # in turn leaves some undefined symbols like __fentry__ in purgatory and not
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index b664cf867f5f..a8750b4ebf26 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -95,7 +95,7 @@ static inline u8 *skcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static void skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize)
+static int skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize)
 {
 	u8 *addr;
 
@@ -103,19 +103,21 @@ static void skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize)
 	addr = skcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize,
 			       (walk->flags & SKCIPHER_WALK_PHYS) ? 2 : 1);
+	return 0;
 }
 
 int skcipher_walk_done(struct skcipher_walk *walk, int err)
 {
-	unsigned int n; /* bytes processed */
-	bool more;
+	unsigned int n = walk->nbytes;
+	unsigned int nbytes = 0;
 
-	if (unlikely(err < 0))
+	if (!n)
 		goto finish;
 
-	n = walk->nbytes - err;
-	walk->total -= n;
-	more = (walk->total != 0);
+	if (likely(err >= 0)) {
+		n -= err;
+		nbytes = walk->total - n;
+	}
 
 	if (likely(!(walk->flags & (SKCIPHER_WALK_PHYS |
 				    SKCIPHER_WALK_SLOW |
@@ -131,7 +133,7 @@ unmap_src:
 		memcpy(walk->dst.virt.addr, walk->page, n);
 		skcipher_unmap_dst(walk);
 	} else if (unlikely(walk->flags & SKCIPHER_WALK_SLOW)) {
-		if (err) {
+		if (err > 0) {
 			/*
 			 * Didn't process all bytes.  Either the algorithm is
 			 * broken, or this was the last step and it turned out
@@ -139,27 +141,29 @@ unmap_src:
 			 * the algorithm requires it.
 			 */
 			err = -EINVAL;
-			goto finish;
-		}
-		skcipher_done_slow(walk, n);
-		goto already_advanced;
+			nbytes = 0;
+		} else
+			n = skcipher_done_slow(walk, n);
 	}
 
+	if (err > 0)
+		err = 0;
+
+	walk->total = nbytes;
+	walk->nbytes = 0;
+
 	scatterwalk_advance(&walk->in, n);
 	scatterwalk_advance(&walk->out, n);
-already_advanced:
-	scatterwalk_done(&walk->in, 0, more);
-	scatterwalk_done(&walk->out, 1, more);
+	scatterwalk_done(&walk->in, 0, nbytes);
+	scatterwalk_done(&walk->out, 1, nbytes);
 
-	if (more) {
+	if (nbytes) {
 		crypto_yield(walk->flags & SKCIPHER_WALK_SLEEP ?
 			     CRYPTO_TFM_REQ_MAY_SLEEP : 0);
 		return skcipher_walk_next(walk);
 	}
-	err = 0;
-finish:
-	walk->nbytes = 0;
 
+finish:
 	/* Short-circuit for the common/fast path. */
 	if (!((unsigned long)walk->buffer | (unsigned long)walk->page))
 		goto out;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index b1c7009de1f4..bc2fa4e85f0c 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -106,6 +106,7 @@ struct nbd_device {
 	struct nbd_config *config;
 	struct mutex config_lock;
 	struct gendisk *disk;
+	struct workqueue_struct *recv_workq;
 
 	struct list_head list;
 	struct task_struct *task_recv;
@@ -132,9 +133,10 @@ static struct dentry *nbd_dbg_dir;
 
 #define NBD_MAGIC 0x68797548
 
+#define NBD_DEF_BLKSIZE 1024
+
 static unsigned int nbds_max = 16;
 static int max_part = 16;
-static struct workqueue_struct *recv_workqueue;
 static int part_shift;
 
 static int nbd_dev_dbg_init(struct nbd_device *nbd);
@@ -1025,7 +1027,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 		/* We take the tx_mutex in an error path in the recv_work, so we
 		 * need to queue_work outside of the tx_mutex.
 		 */
-		queue_work(recv_workqueue, &args->work);
+		queue_work(nbd->recv_workq, &args->work);
 
 		atomic_inc(&config->live_connections);
 		wake_up(&config->conn_wait);
@@ -1126,6 +1128,10 @@ static void nbd_config_put(struct nbd_device *nbd)
 		kfree(nbd->config);
 		nbd->config = NULL;
 
+		if (nbd->recv_workq)
+			destroy_workqueue(nbd->recv_workq);
+		nbd->recv_workq = NULL;
+
 		nbd->tag_set.timeout = 0;
 		nbd->disk->queue->limits.discard_granularity = 0;
 		nbd->disk->queue->limits.discard_alignment = 0;
@@ -1154,6 +1160,14 @@ static int nbd_start_device(struct nbd_device *nbd)
 		return -EINVAL;
 	}
 
+	nbd->recv_workq = alloc_workqueue("knbd%d-recv",
+					  WQ_MEM_RECLAIM | WQ_HIGHPRI |
+					  WQ_UNBOUND, 0, nbd->index);
+	if (!nbd->recv_workq) {
+		dev_err(disk_to_dev(nbd->disk), "Could not allocate knbd recv work queue.\n");
+		return -ENOMEM;
+	}
+
 	blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
 	nbd->task_recv = current;
 
@@ -1184,7 +1198,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 		INIT_WORK(&args->work, recv_work);
 		args->nbd = nbd;
 		args->index = i;
-		queue_work(recv_workqueue, &args->work);
+		queue_work(nbd->recv_workq, &args->work);
 	}
 	nbd_size_update(nbd);
 	return error;
@@ -1204,8 +1218,10 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 	mutex_unlock(&nbd->config_lock);
 	ret = wait_event_interruptible(config->recv_wq,
 					 atomic_read(&config->recv_threads) == 0);
-	if (ret)
+	if (ret) {
 		sock_shutdown(nbd);
+		flush_workqueue(nbd->recv_workq);
+	}
 	mutex_lock(&nbd->config_lock);
 	nbd_bdev_reset(bdev);
 	/* user requested, ignore socket errors */
@@ -1227,6 +1243,14 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
 		nbd_config_put(nbd);
 }
 
+static bool nbd_is_valid_blksize(unsigned long blksize)
+{
+	if (!blksize || !is_power_of_2(blksize) || blksize < 512 ||
+	    blksize > PAGE_SIZE)
+		return false;
+	return true;
+}
+
 /* Must be called with config_lock held */
 static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		       unsigned int cmd, unsigned long arg)
@@ -1242,8 +1266,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	case NBD_SET_SOCK:
 		return nbd_add_socket(nbd, arg, false);
 	case NBD_SET_BLKSIZE:
-		if (!arg || !is_power_of_2(arg) || arg < 512 ||
-		    arg > PAGE_SIZE)
+		if (!arg)
+			arg = NBD_DEF_BLKSIZE;
+		if (!nbd_is_valid_blksize(arg))
 			return -EINVAL;
 		nbd_size_set(nbd, arg,
 			     div_s64(config->bytesize, arg));
@@ -1323,7 +1348,7 @@ static struct nbd_config *nbd_alloc_config(void)
 	atomic_set(&config->recv_threads, 0);
 	init_waitqueue_head(&config->recv_wq);
 	init_waitqueue_head(&config->conn_wait);
-	config->blksize = 1024;
+	config->blksize = NBD_DEF_BLKSIZE;
 	atomic_set(&config->live_connections, 0);
 	try_module_get(THIS_MODULE);
 	return config;
@@ -1759,6 +1784,12 @@ again:
 	if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
 		u64 bsize =
 			nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
+		if (!bsize)
+			bsize = NBD_DEF_BLKSIZE;
+		if (!nbd_is_valid_blksize(bsize)) {
+			ret = -EINVAL;
+			goto out;
+		}
 		nbd_size_set(nbd, bsize, div64_u64(config->bytesize, bsize));
 	}
 	if (info->attrs[NBD_ATTR_TIMEOUT]) {
@@ -1835,6 +1866,12 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd)
 	nbd_disconnect(nbd);
 	nbd_clear_sock(nbd);
 	mutex_unlock(&nbd->config_lock);
+	/*
+	 * Make sure recv thread has finished, so it does not drop the last
+	 * config ref and try to destroy the workqueue from inside the work
+	 * queue.
+	 */
+	flush_workqueue(nbd->recv_workq);
 	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
 			       &nbd->config->runtime_flags))
 		nbd_config_put(nbd);
@@ -2215,20 +2252,12 @@ static int __init nbd_init(void)
 
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
-	recv_workqueue = alloc_workqueue("knbd-recv",
-					 WQ_MEM_RECLAIM | WQ_HIGHPRI |
-					 WQ_UNBOUND, 0);
-	if (!recv_workqueue)
-		return -ENOMEM;
 
-	if (register_blkdev(NBD_MAJOR, "nbd")) {
-		destroy_workqueue(recv_workqueue);
+	if (register_blkdev(NBD_MAJOR, "nbd"))
 		return -EIO;
-	}
 
 	if (genl_register_family(&nbd_genl_family)) {
 		unregister_blkdev(NBD_MAJOR, "nbd");
-		destroy_workqueue(recv_workqueue);
 		return -EINVAL;
 	}
 	nbd_dbg_init();
@@ -2270,7 +2299,6 @@ static void __exit nbd_cleanup(void)
 
 	idr_destroy(&nbd_index_idr);
 	genl_unregister_family(&nbd_genl_family);
-	destroy_workqueue(recv_workqueue);
 	unregister_blkdev(NBD_MAJOR, "nbd");
 }
 
diff --git a/drivers/crypto/caam/caamalg_desc.c b/drivers/crypto/caam/caamalg_desc.c
index a408edd84f34..edacf9b39b63 100644
--- a/drivers/crypto/caam/caamalg_desc.c
+++ b/drivers/crypto/caam/caamalg_desc.c
@@ -509,6 +509,7 @@ void cnstr_shdsc_aead_givencap(u32 * const desc, struct alginfo *cdata,
 			       const bool is_qi, int era)
 {
 	u32 geniv, moveiv;
+	u32 *wait_cmd;
 
 	/* Note: Context registers are saved. */
 	init_sh_desc_key_aead(desc, cdata, adata, is_rfc3686, nonce, era);
@@ -604,6 +605,14 @@ copy_iv:
 
 	/* Will read cryptlen */
 	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+
+	/*
+	 * Wait for IV transfer (ofifo -> class2) to finish before starting
+	 * ciphertext transfer (ofifo -> external memory).
+	 */
+	wait_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL | JUMP_COND_NIFP);
+	set_jump_tgt_here(desc, wait_cmd);
+
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_BOTH | KEY_VLF |
 			     FIFOLD_TYPE_MSG1OUT2 | FIFOLD_TYPE_LASTBOTH);
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | KEY_VLF);
diff --git a/drivers/crypto/caam/caamalg_desc.h b/drivers/crypto/caam/caamalg_desc.h
index a917af5776ce..05516b0a4240 100644
--- a/drivers/crypto/caam/caamalg_desc.h
+++ b/drivers/crypto/caam/caamalg_desc.h
@@ -12,7 +12,7 @@
 #define DESC_AEAD_BASE			(4 * CAAM_CMD_SZ)
 #define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 11 * CAAM_CMD_SZ)
 #define DESC_AEAD_DEC_LEN		(DESC_AEAD_BASE + 15 * CAAM_CMD_SZ)
-#define DESC_AEAD_GIVENC_LEN		(DESC_AEAD_ENC_LEN + 7 * CAAM_CMD_SZ)
+#define DESC_AEAD_GIVENC_LEN		(DESC_AEAD_ENC_LEN + 8 * CAAM_CMD_SZ)
 #define DESC_QI_AEAD_ENC_LEN		(DESC_AEAD_ENC_LEN + 3 * CAAM_CMD_SZ)
 #define DESC_QI_AEAD_DEC_LEN		(DESC_AEAD_DEC_LEN + 3 * CAAM_CMD_SZ)
 #define DESC_QI_AEAD_GIVENC_LEN		(DESC_AEAD_GIVENC_LEN + 3 * CAAM_CMD_SZ)
diff --git a/drivers/crypto/cavium/zip/zip_main.c b/drivers/crypto/cavium/zip/zip_main.c
index 6183f9128a8a..ea901bc5733c 100644
--- a/drivers/crypto/cavium/zip/zip_main.c
+++ b/drivers/crypto/cavium/zip/zip_main.c
@@ -593,6 +593,7 @@ static const struct file_operations zip_stats_fops = {
 	.owner = THIS_MODULE,
 	.open  = zip_stats_open,
 	.read  = seq_read,
+	.release = single_release,
 };
 
 static int zip_clear_open(struct inode *inode, struct file *file)
@@ -604,6 +605,7 @@ static const struct file_operations zip_clear_fops = {
 	.owner = THIS_MODULE,
 	.open  = zip_clear_open,
 	.read  = seq_read,
+	.release = single_release,
 };
 
 static int zip_regs_open(struct inode *inode, struct file *file)
@@ -615,6 +617,7 @@ static const struct file_operations zip_regs_fops = {
 	.owner = THIS_MODULE,
 	.open  = zip_regs_open,
 	.read  = seq_read,
+	.release = single_release,
 };
 
 /* Root directory for thunderx_zip debugfs entry */
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index 0669033f5be5..aa6b45bc13b9 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -227,7 +227,7 @@ static void cc_aead_complete(struct device *dev, void *cc_req, int err)
 			/* In case of payload authentication failure, MUST NOT
 			 * revealed the decrypted message --> zero its memory.
 			 */
-			cc_zero_sgl(areq->dst, areq_ctx->cryptlen);
+			cc_zero_sgl(areq->dst, areq->cryptlen);
 			err = -EBADMSG;
 		}
 	} else { /*ENCRYPT*/
diff --git a/drivers/crypto/ccree/cc_fips.c b/drivers/crypto/ccree/cc_fips.c
index 09f708f6418e..bac278d274b0 100644
--- a/drivers/crypto/ccree/cc_fips.c
+++ b/drivers/crypto/ccree/cc_fips.c
@@ -21,7 +21,13 @@ static bool cc_get_tee_fips_status(struct cc_drvdata *drvdata)
 	u32 reg;
 
 	reg = cc_ioread(drvdata, CC_REG(GPR_HOST));
-	return (reg == (CC_FIPS_SYNC_TEE_STATUS | CC_FIPS_SYNC_MODULE_OK));
+	/* Did the TEE report status? */
+	if (reg & CC_FIPS_SYNC_TEE_STATUS)
+		/* Yes. Is it OK? */
+		return (reg & CC_FIPS_SYNC_MODULE_OK);
+
+	/* No. It's either not in use or will be reported later */
+	return true;
 }
 
 /*
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 5c4c0a253129..d78f8d5c89c3 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -95,7 +95,7 @@ struct service_hndl {
 
 static inline int get_current_node(void)
 {
-	return topology_physical_package_id(smp_processor_id());
+	return topology_physical_package_id(raw_smp_processor_id());
 }
 
 int adf_service_register(struct service_hndl *service);
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index c59d2eee5d30..06768074d2d8 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -486,11 +486,11 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 {
 	struct tegra_devfreq *tegra = dev_get_drvdata(dev);
 	struct dev_pm_opp *opp;
-	unsigned long rate = *freq * KHZ;
+	unsigned long rate;
 
-	opp = devfreq_recommended_opp(dev, &rate, flags);
+	opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(opp)) {
-		dev_err(dev, "Failed to find opp for %lu KHz\n", *freq);
+		dev_err(dev, "Failed to find opp for %lu Hz\n", *freq);
 		return PTR_ERR(opp);
 	}
 	rate = dev_pm_opp_get_freq(opp);
@@ -499,8 +499,6 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	clk_set_min_rate(tegra->emc_clock, rate);
 	clk_set_rate(tegra->emc_clock, 0);
 
-	*freq = rate;
-
 	return 0;
 }
 
@@ -510,7 +508,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 	struct tegra_devfreq *tegra = dev_get_drvdata(dev);
 	struct tegra_devfreq_device *actmon_dev;
 
-	stat->current_frequency = tegra->cur_freq;
+	stat->current_frequency = tegra->cur_freq * KHZ;
 
 	/* To be used by the tegra governor */
 	stat->private_data = tegra;
@@ -565,7 +563,7 @@ static int tegra_governor_get_target(struct devfreq *devfreq,
 		target_freq = max(target_freq, dev->target_freq);
 	}
 
-	*freq = target_freq;
+	*freq = target_freq * KHZ;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 51b5e977ca88..f4e9d1b10e3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -139,7 +139,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* ring tests don't use a job */
 	if (job) {
 		vm = job->vm;
-		fence_ctx = job->base.s_fence->scheduled.context;
+		fence_ctx = job->base.s_fence ?
+			job->base.s_fence->scheduled.context : 0;
 	} else {
 		vm = NULL;
 		fence_ctx = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index c0396e83f352..fc93b103f777 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -562,6 +562,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
 
+		if (info->read_mmr_reg.count > 128)
+			return -EINVAL;
+
 		regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL);
 		if (!regs)
 			return -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 663a7c9ca3d3..d0e216d85a22 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1276,9 +1276,6 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
 #define same_context(a, b) (((a)->context_id == (b)->context_id) && \
 		((a)->lrca == (b)->lrca))
 
-#define get_last_workload(q) \
-	(list_empty(q) ? NULL : container_of(q->prev, \
-	struct intel_vgpu_workload, list))
 /**
  * intel_vgpu_create_workload - create a vGPU workload
  * @vgpu: a vGPU
@@ -1297,7 +1294,7 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct list_head *q = workload_q_head(vgpu, ring_id);
-	struct intel_vgpu_workload *last_workload = get_last_workload(q);
+	struct intel_vgpu_workload *last_workload = NULL;
 	struct intel_vgpu_workload *workload = NULL;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	u64 ring_context_gpa;
@@ -1320,15 +1317,20 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 	head &= RB_HEAD_OFF_MASK;
 	tail &= RB_TAIL_OFF_MASK;
 
-	if (last_workload && same_context(&last_workload->ctx_desc, desc)) {
-		gvt_dbg_el("ring id %d cur workload == last\n", ring_id);
-		gvt_dbg_el("ctx head %x real head %lx\n", head,
-				last_workload->rb_tail);
-		/*
-		 * cannot use guest context head pointer here,
-		 * as it might not be updated at this time
-		 */
-		head = last_workload->rb_tail;
+	list_for_each_entry_reverse(last_workload, q, list) {
+
+		if (same_context(&last_workload->ctx_desc, desc)) {
+			gvt_dbg_el("ring id %d cur workload == last\n",
+					ring_id);
+			gvt_dbg_el("ctx head %x real head %lx\n", head,
+					last_workload->rb_tail);
+			/*
+			 * cannot use guest context head pointer here,
+			 * as it might not be updated at this time
+			 */
+			head = last_workload->rb_tail;
+			break;
+		}
 	}
 
 	gvt_dbg_el("ring id %d begin a new workload\n", ring_id);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 96fb5f635314..cc4ea5502d6c 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -429,15 +429,15 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 	}
 
 	msm_host->byte_clk_src = clk_get_parent(msm_host->byte_clk);
-	if (!msm_host->byte_clk_src) {
-		ret = -ENODEV;
+	if (IS_ERR(msm_host->byte_clk_src)) {
+		ret = PTR_ERR(msm_host->byte_clk_src);
 		pr_err("%s: can't find byte_clk clock. ret=%d\n", __func__, ret);
 		goto exit;
 	}
 
 	msm_host->pixel_clk_src = clk_get_parent(msm_host->pixel_clk);
-	if (!msm_host->pixel_clk_src) {
-		ret = -ENODEV;
+	if (IS_ERR(msm_host->pixel_clk_src)) {
+		ret = PTR_ERR(msm_host->pixel_clk_src);
 		pr_err("%s: can't find pixel_clk clock. ret=%d\n", __func__, ret);
 		goto exit;
 	}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 5e01bfb69d7a..10107e551fac 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -1517,7 +1517,8 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			nv_encoder->aux = aux;
 		}
 
-		if ((data = nvbios_dp_table(bios, &ver, &hdr, &cnt, &len)) &&
+		if (nv_connector->type != DCB_CONNECTOR_eDP &&
+		    (data = nvbios_dp_table(bios, &ver, &hdr, &cnt, &len)) &&
 		    ver >= 0x40 && (nvbios_rd08(bios, data + 0x08) & 0x04)) {
 			ret = nv50_mstm_new(nv_encoder, &nv_connector->aux, 16,
 					    nv_connector->base.base.id,
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index cb80ddaa19d2..7e9e2f064454 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1110,7 +1110,7 @@ static const struct dss_features omap34xx_dss_feats = {
 
 static const struct dss_features omap3630_dss_feats = {
 	.model			=	DSS_MODEL_OMAP3,
-	.fck_div_max		=	32,
+	.fck_div_max		=	31,
 	.fck_freq_max		=	173000000,
 	.dss_fck_multiplier	=	1,
 	.parent_clk_name	=	"dpll4_ck",
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 25b5407c74b5..d83310751a8e 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -340,8 +340,39 @@ static int radeon_kick_out_firmware_fb(struct pci_dev *pdev)
 static int radeon_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
+	unsigned long flags = 0;
 	int ret;
 
+	if (!ent)
+		return -ENODEV; /* Avoid NULL-ptr deref in drm_get_pci_dev */
+
+	flags = ent->driver_data;
+
+	if (!radeon_si_support) {
+		switch (flags & RADEON_FAMILY_MASK) {
+		case CHIP_TAHITI:
+		case CHIP_PITCAIRN:
+		case CHIP_VERDE:
+		case CHIP_OLAND:
+		case CHIP_HAINAN:
+			dev_info(&pdev->dev,
+				 "SI support disabled by module param\n");
+			return -ENODEV;
+		}
+	}
+	if (!radeon_cik_support) {
+		switch (flags & RADEON_FAMILY_MASK) {
+		case CHIP_KAVERI:
+		case CHIP_BONAIRE:
+		case CHIP_HAWAII:
+		case CHIP_KABINI:
+		case CHIP_MULLINS:
+			dev_info(&pdev->dev,
+				 "CIK support disabled by module param\n");
+			return -ENODEV;
+		}
+	}
+
 	if (vga_switcheroo_client_probe_defer(pdev))
 		return -EPROBE_DEFER;
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 6a8fb6fd183c..3ff835767ac5 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -95,31 +95,6 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	struct radeon_device *rdev;
 	int r, acpi_status;
 
-	if (!radeon_si_support) {
-		switch (flags & RADEON_FAMILY_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
-			dev_info(dev->dev,
-				 "SI support disabled by module param\n");
-			return -ENODEV;
-		}
-	}
-	if (!radeon_cik_support) {
-		switch (flags & RADEON_FAMILY_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
-			dev_info(dev->dev,
-				 "CIK support disabled by module param\n");
-			return -ENODEV;
-		}
-	}
-
 	rdev = kzalloc(sizeof(struct radeon_device), GFP_KERNEL);
 	if (rdev == NULL) {
 		return -ENOMEM;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 2bce7cf0b0af..e45b5ec2f451 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -174,6 +174,12 @@ static void etm4_enable_hw(void *info)
 	if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 0))
 		dev_err(drvdata->dev,
 			"timeout while waiting for Idle Trace Status\n");
+	/*
+	 * As recommended by section 4.3.7 ("Synchronization when using the
+	 * memory-mapped interface") of ARM IHI 0064D
+	 */
+	dsb(sy);
+	isb();
 
 	CS_LOCK(drvdata->base);
 
@@ -324,8 +330,12 @@ static void etm4_disable_hw(void *info)
 	/* EN, bit[0] Trace unit enable bit */
 	control &= ~0x1;
 
-	/* make sure everything completes before disabling */
-	mb();
+	/*
+	 * Make sure everything completes before disabling, as recommended
+	 * by section 7.3.77 ("TRCVICTLR, ViewInst Main Control Register,
+	 * SSTATUS") of ARM IHI 0064D
+	 */
+	dsb(sy);
 	isb();
 	writel_relaxed(control, drvdata->base + TRCPRGCTLR);
 
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index e5c598ae5f24..6627523e728b 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -480,7 +480,12 @@ static int esdhc_of_enable_dma(struct sdhci_host *host)
 		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
 
 	value = sdhci_readl(host, ESDHC_DMA_SYSCTL);
-	value |= ESDHC_DMA_SNOOP;
+
+	if (of_dma_is_coherent(dev->of_node))
+		value |= ESDHC_DMA_SNOOP;
+	else
+		value &= ~ESDHC_DMA_SNOOP;
+
 	sdhci_writel(host, value, ESDHC_DMA_SYSCTL);
 	return 0;
 }
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index eb33b892b484..e99d5632d8fa 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2720,6 +2720,7 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *intmask_p)
 static void sdhci_adma_show_error(struct sdhci_host *host)
 {
 	void *desc = host->adma_table;
+	dma_addr_t dma = host->adma_addr;
 
 	sdhci_dumpregs(host);
 
@@ -2727,18 +2728,21 @@ static void sdhci_adma_show_error(struct sdhci_host *host)
 		struct sdhci_adma2_64_desc *dma_desc = desc;
 
 		if (host->flags & SDHCI_USE_64_BIT_DMA)
-			DBG("%p: DMA 0x%08x%08x, LEN 0x%04x, Attr=0x%02x\n",
-			    desc, le32_to_cpu(dma_desc->addr_hi),
+			SDHCI_DUMP("%08llx: DMA 0x%08x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    (unsigned long long)dma,
+			    le32_to_cpu(dma_desc->addr_hi),
 			    le32_to_cpu(dma_desc->addr_lo),
 			    le16_to_cpu(dma_desc->len),
 			    le16_to_cpu(dma_desc->cmd));
 		else
-			DBG("%p: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
-			    desc, le32_to_cpu(dma_desc->addr_lo),
+			SDHCI_DUMP("%08llx: DMA 0x%08x, LEN 0x%04x, Attr=0x%02x\n",
+			    (unsigned long long)dma,
+			    le32_to_cpu(dma_desc->addr_lo),
 			    le16_to_cpu(dma_desc->len),
 			    le16_to_cpu(dma_desc->cmd));
 
 		desc += host->desc_sz;
+		dma += host->desc_sz;
 
 		if (dma_desc->cmd & cpu_to_le16(ADMA2_END))
 			break;
@@ -2814,7 +2818,8 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 			!= MMC_BUS_TEST_R)
 		host->data->error = -EILSEQ;
 	else if (intmask & SDHCI_INT_ADMA_ERROR) {
-		pr_err("%s: ADMA error\n", mmc_hostname(host->mmc));
+		pr_err("%s: ADMA error: 0x%08x\n", mmc_hostname(host->mmc),
+		       intmask);
 		sdhci_adma_show_error(host);
 		host->data->error = -EIO;
 		if (host->ops->adma_workaround)
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index fccb6bf21fad..de8d9dceb123 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -626,7 +626,7 @@ static int mcp251x_setup(struct net_device *net, struct spi_device *spi)
 static int mcp251x_hw_reset(struct spi_device *spi)
 {
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
-	u8 reg;
+	unsigned long timeout;
 	int ret;
 
 	/* Wait for oscillator startup timer after power up */
@@ -640,10 +640,19 @@ static int mcp251x_hw_reset(struct spi_device *spi)
 	/* Wait for oscillator startup timer after reset */
 	mdelay(MCP251X_OST_DELAY_MS);
 
-	reg = mcp251x_read_reg(spi, CANSTAT);
-	if ((reg & CANCTRL_REQOP_MASK) != CANCTRL_REQOP_CONF)
-		return -ENODEV;
-
+	/* Wait for reset to finish */
+	timeout = jiffies + HZ;
+	while ((mcp251x_read_reg(spi, CANSTAT) & CANCTRL_REQOP_MASK) !=
+	       CANCTRL_REQOP_CONF) {
+		usleep_range(MCP251X_OST_DELAY_MS * 1000,
+			     MCP251X_OST_DELAY_MS * 1000 * 2);
+
+		if (time_after(jiffies, timeout)) {
+			dev_err(&spi->dev,
+				"MCP251x didn't enter in conf mode after reset\n");
+			return -EBUSY;
+		}
+	}
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 22c572a09b32..c19e88efe958 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -272,6 +272,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 		port = nfp_port_alloc(app, port_type, repr);
 		if (IS_ERR(port)) {
 			err = PTR_ERR(port);
+			kfree(repr_priv);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index 4f684cbcdc57..078027bbe002 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -1140,10 +1140,11 @@ static void atusb_disconnect(struct usb_interface *interface)
 
 	ieee802154_unregister_hw(atusb->hw);
 
+	usb_put_dev(atusb->usb_dev);
+
 	ieee802154_free_hw(atusb->hw);
 
 	usb_set_intfdata(interface, NULL);
-	usb_put_dev(atusb->usb_dev);
 
 	pr_debug("%s done\n", __func__);
 }
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 2a9d6b0d1f19..80508da3c8b5 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -1373,7 +1373,7 @@ static int perf_setup_peer_mw(struct perf_peer *peer)
 	int ret;
 
 	/* Get outbound MW parameters and map it */
-	ret = ntb_peer_mw_get_addr(perf->ntb, peer->gidx, &phys_addr,
+	ret = ntb_peer_mw_get_addr(perf->ntb, perf->gidx, &phys_addr,
 				   &peer->outbuf_size);
 	if (ret)
 		return ret;
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 2ba22cd1331b..54a633e8cb5d 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -189,7 +189,7 @@ static int nvdimm_clear_badblocks_region(struct device *dev, void *data)
 	sector_t sector;
 
 	/* make sure device is a region */
-	if (!is_nd_pmem(dev))
+	if (!is_memory(dev))
 		return 0;
 
 	nd_region = to_nd_region(dev);
diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c
index f9130cc157e8..22224b21c34d 100644
--- a/drivers/nvdimm/region.c
+++ b/drivers/nvdimm/region.c
@@ -42,7 +42,7 @@ static int nd_region_probe(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (is_nd_pmem(&nd_region->dev)) {
+	if (is_memory(&nd_region->dev)) {
 		struct resource ndr_res;
 
 		if (devm_init_badblocks(dev, &nd_region->bb))
@@ -131,7 +131,7 @@ static void nd_region_notify(struct device *dev, enum nvdimm_event event)
 		struct nd_region *nd_region = to_nd_region(dev);
 		struct resource res;
 
-		if (is_nd_pmem(&nd_region->dev)) {
+		if (is_memory(&nd_region->dev)) {
 			res.start = nd_region->ndr_start;
 			res.end = nd_region->ndr_start +
 				nd_region->ndr_size - 1;
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 0303296e6d5b..609fc450522a 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -633,11 +633,11 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
 	if (!is_memory(dev) && a == &dev_attr_dax_seed.attr)
 		return 0;
 
-	if (!is_nd_pmem(dev) && a == &dev_attr_badblocks.attr)
+	if (!is_memory(dev) && a == &dev_attr_badblocks.attr)
 		return 0;
 
 	if (a == &dev_attr_resource.attr) {
-		if (is_nd_pmem(dev))
+		if (is_memory(dev))
 			return 0400;
 		else
 			return 0;
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index fd2dbd7eed7b..52d4fa4161dc 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -31,6 +31,9 @@
 #define PCI_REG_VMLOCK		0x70
 #define MB2_SHADOW_EN(vmlock)	(vmlock & 0x2)
 
+#define MB2_SHADOW_OFFSET	0x2000
+#define MB2_SHADOW_SIZE		16
+
 enum vmd_features {
 	/*
 	 * Device may contain registers which hint the physical location of the
@@ -600,7 +603,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 		u32 vmlock;
 		int ret;
 
-		membar2_offset = 0x2018;
+		membar2_offset = MB2_SHADOW_OFFSET + MB2_SHADOW_SIZE;
 		ret = pci_read_config_dword(vmd->dev, PCI_REG_VMLOCK, &vmlock);
 		if (ret || vmlock == ~0)
 			return -ENODEV;
@@ -612,9 +615,9 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 			if (!membar2)
 				return -ENOMEM;
 			offset[0] = vmd->dev->resource[VMD_MEMBAR1].start -
-						readq(membar2 + 0x2008);
+					readq(membar2 + MB2_SHADOW_OFFSET);
 			offset[1] = vmd->dev->resource[VMD_MEMBAR2].start -
-						readq(membar2 + 0x2010);
+					readq(membar2 + MB2_SHADOW_OFFSET + 8);
 			pci_iounmap(vmd->dev, membar2);
 		}
 	}
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index c65465385d8c..6384930a6749 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1366,7 +1366,7 @@ static void pci_restore_rebar_state(struct pci_dev *pdev)
 		pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
 		bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX;
 		res = pdev->resource + bar_idx;
-		size = order_base_2((resource_size(res) >> 20) | 1) - 1;
+		size = ilog2(resource_size(res)) - 20;
 		ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
 		ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT;
 		pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
diff --git a/drivers/power/supply/sbs-battery.c b/drivers/power/supply/sbs-battery.c
index 8ba6abf584de..3958ee03eec1 100644
--- a/drivers/power/supply/sbs-battery.c
+++ b/drivers/power/supply/sbs-battery.c
@@ -323,17 +323,22 @@ static int sbs_get_battery_presence_and_health(
 {
 	int ret;
 
-	if (psp == POWER_SUPPLY_PROP_PRESENT) {
-		/* Dummy command; if it succeeds, battery is present. */
-		ret = sbs_read_word_data(client, sbs_data[REG_STATUS].addr);
-		if (ret < 0)
-			val->intval = 0; /* battery disconnected */
-		else
-			val->intval = 1; /* battery present */
-	} else { /* POWER_SUPPLY_PROP_HEALTH */
+	/* Dummy command; if it succeeds, battery is present. */
+	ret = sbs_read_word_data(client, sbs_data[REG_STATUS].addr);
+
+	if (ret < 0) { /* battery not present*/
+		if (psp == POWER_SUPPLY_PROP_PRESENT) {
+			val->intval = 0;
+			return 0;
+		}
+		return ret;
+	}
+
+	if (psp == POWER_SUPPLY_PROP_PRESENT)
+		val->intval = 1; /* battery present */
+	else /* POWER_SUPPLY_PROP_HEALTH */
 		/* SBS spec doesn't have a general health command. */
 		val->intval = POWER_SUPPLY_HEALTH_UNKNOWN;
-	}
 
 	return 0;
 }
@@ -629,12 +634,14 @@ static int sbs_get_property(struct power_supply *psy,
 	switch (psp) {
 	case POWER_SUPPLY_PROP_PRESENT:
 	case POWER_SUPPLY_PROP_HEALTH:
-		if (client->flags & SBS_FLAGS_TI_BQ20Z75)
+		if (chip->flags & SBS_FLAGS_TI_BQ20Z75)
 			ret = sbs_get_ti_battery_presence_and_health(client,
 								     psp, val);
 		else
 			ret = sbs_get_battery_presence_and_health(client, psp,
 								  val);
+
+		/* this can only be true if no gpio is used */
 		if (psp == POWER_SUPPLY_PROP_PRESENT)
 			return 0;
 		break;
diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c
index 0059b24cfdc3..28e1f6413476 100644
--- a/drivers/pwm/pwm-stm32-lp.c
+++ b/drivers/pwm/pwm-stm32-lp.c
@@ -58,6 +58,12 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	/* Calculate the period and prescaler value */
 	div = (unsigned long long)clk_get_rate(priv->clk) * state->period;
 	do_div(div, NSEC_PER_SEC);
+	if (!div) {
+		/* Clock is too slow to achieve requested period. */
+		dev_dbg(priv->chip.dev, "Can't reach %u ns\n",	state->period);
+		return -EINVAL;
+	}
+
 	prd = div;
 	while (div > STM32_LPTIM_MAX_ARR) {
 		presc++;
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index 93b2862bd3fa..674d848e377c 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -372,7 +372,7 @@ int ccwgroup_create_dev(struct device *parent, struct ccwgroup_driver *gdrv,
 		goto error;
 	}
 	/* Check for trailing stuff. */
-	if (i == num_devices && strlen(buf) > 0) {
+	if (i == num_devices && buf && strlen(buf) > 0) {
 		rc = -EINVAL;
 		goto error;
 	}
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index aea502922646..df09ed53ab45 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -1213,6 +1213,8 @@ device_initcall(cio_settle_init);
 
 int sch_is_pseudo_sch(struct subchannel *sch)
 {
+	if (!sch->dev.parent)
+		return 0;
 	return sch == to_css(sch->dev.parent)->pseudo_subchannel;
 }
 
diff --git a/drivers/staging/erofs/dir.c b/drivers/staging/erofs/dir.c
index 0a089cf5c78f..fe6683effd05 100644
--- a/drivers/staging/erofs/dir.c
+++ b/drivers/staging/erofs/dir.c
@@ -100,8 +100,15 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 		unsigned nameoff, maxsize;
 
 		dentry_page = read_mapping_page(mapping, i, NULL);
-		if (IS_ERR(dentry_page))
-			continue;
+		if (dentry_page == ERR_PTR(-ENOMEM)) {
+			err = -ENOMEM;
+			break;
+		} else if (IS_ERR(dentry_page)) {
+			errln("fail to readdir of logical block %u of nid %llu",
+			      i, EROFS_V(dir)->nid);
+			err = PTR_ERR(dentry_page);
+			break;
+		}
 
 		lock_page(dentry_page);
 		de = (struct erofs_dirent *)kmap(dentry_page);
diff --git a/drivers/staging/erofs/unzip_vle.c b/drivers/staging/erofs/unzip_vle.c
index ad6fe6d9d00a..0f1558c6747e 100644
--- a/drivers/staging/erofs/unzip_vle.c
+++ b/drivers/staging/erofs/unzip_vle.c
@@ -311,7 +311,11 @@ z_erofs_vle_work_lookup(struct super_block *sb,
 	/* if multiref is disabled, `primary' is always true */
 	primary = true;
 
-	DBG_BUGON(work->pageofs != pageofs);
+	if (work->pageofs != pageofs) {
+		DBG_BUGON(1);
+		erofs_workgroup_put(egrp);
+		return ERR_PTR(-EIO);
+	}
 
 	/*
 	 * lock must be taken first to avoid grp->next == NIL between
@@ -853,6 +857,7 @@ repeat:
 	for (i = 0; i < nr_pages; ++i)
 		pages[i] = NULL;
 
+	err = 0;
 	z_erofs_pagevec_ctor_init(&ctor,
 		Z_EROFS_VLE_INLINE_PAGEVECS, work->pagevec, 0);
 
@@ -874,8 +879,17 @@ repeat:
 			pagenr = z_erofs_onlinepage_index(page);
 
 		DBG_BUGON(pagenr >= nr_pages);
-		DBG_BUGON(pages[pagenr]);
 
+		/*
+		 * currently EROFS doesn't support multiref(dedup),
+		 * so here erroring out one multiref page.
+		 */
+		if (pages[pagenr]) {
+			DBG_BUGON(1);
+			SetPageError(pages[pagenr]);
+			z_erofs_onlinepage_endio(pages[pagenr]);
+			err = -EIO;
+		}
 		pages[pagenr] = page;
 	}
 	sparsemem_pages = i;
@@ -885,7 +899,6 @@ repeat:
 	overlapped = false;
 	compressed_pages = grp->compressed_pages;
 
-	err = 0;
 	for (i = 0; i < clusterpages; ++i) {
 		unsigned pagenr;
 
@@ -911,7 +924,12 @@ repeat:
 			pagenr = z_erofs_onlinepage_index(page);
 
 			DBG_BUGON(pagenr >= nr_pages);
-			DBG_BUGON(pages[pagenr]);
+			if (pages[pagenr]) {
+				DBG_BUGON(1);
+				SetPageError(pages[pagenr]);
+				z_erofs_onlinepage_endio(pages[pagenr]);
+				err = -EIO;
+			}
 			++sparsemem_pages;
 			pages[pagenr] = page;
 
@@ -1335,19 +1353,18 @@ static int z_erofs_vle_normalaccess_readpage(struct file *file,
 	err = z_erofs_do_read_page(&f, page, &pagepool);
 	(void)z_erofs_vle_work_iter_end(&f.builder);
 
-	if (err) {
+	/* if some compressed cluster ready, need submit them anyway */
+	z_erofs_submit_and_unzip(&f, &pagepool, true);
+
+	if (err)
 		errln("%s, failed to read, err [%d]", __func__, err);
-		goto out;
-	}
 
-	z_erofs_submit_and_unzip(&f, &pagepool, true);
-out:
 	if (f.m_iter.mpage != NULL)
 		put_page(f.m_iter.mpage);
 
 	/* clean up the remaining free pages */
 	put_pages_list(&pagepool);
-	return 0;
+	return err;
 }
 
 static inline int __z_erofs_vle_normalaccess_readpages(
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index bf9721fc2824..be3eafc7682b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -296,7 +296,7 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
 		mod_delayed_work(system_freezable_wq, &tz->poll_queue,
 				 msecs_to_jiffies(delay));
 	else
-		cancel_delayed_work(&tz->poll_queue);
+		cancel_delayed_work_sync(&tz->poll_queue);
 }
 
 static void monitor_thermal_zone(struct thermal_zone_device *tz)
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index 40c69a533b24..dd5d8ee37928 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -87,13 +87,17 @@ static struct thermal_hwmon_device *
 thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz)
 {
 	struct thermal_hwmon_device *hwmon;
+	char type[THERMAL_NAME_LENGTH];
 
 	mutex_lock(&thermal_hwmon_list_lock);
-	list_for_each_entry(hwmon, &thermal_hwmon_list, node)
-		if (!strcmp(hwmon->type, tz->type)) {
+	list_for_each_entry(hwmon, &thermal_hwmon_list, node) {
+		strcpy(type, tz->type);
+		strreplace(type, '-', '_');
+		if (!strcmp(hwmon->type, type)) {
 			mutex_unlock(&thermal_hwmon_list_lock);
 			return hwmon;
 		}
+	}
 	mutex_unlock(&thermal_hwmon_list_lock);
 
 	return NULL;
diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c
index 1abe4d021fd2..ffde179a9bb2 100644
--- a/drivers/watchdog/aspeed_wdt.c
+++ b/drivers/watchdog/aspeed_wdt.c
@@ -38,6 +38,7 @@ static const struct aspeed_wdt_config ast2500_config = {
 static const struct of_device_id aspeed_wdt_of_table[] = {
 	{ .compatible = "aspeed,ast2400-wdt", .data = &ast2400_config },
 	{ .compatible = "aspeed,ast2500-wdt", .data = &ast2500_config },
+	{ .compatible = "aspeed,ast2600-wdt", .data = &ast2500_config },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, aspeed_wdt_of_table);
@@ -264,7 +265,8 @@ static int aspeed_wdt_probe(struct platform_device *pdev)
 		set_bit(WDOG_HW_RUNNING, &wdt->wdd.status);
 	}
 
-	if (of_device_is_compatible(np, "aspeed,ast2500-wdt")) {
+	if ((of_device_is_compatible(np, "aspeed,ast2500-wdt")) ||
+		(of_device_is_compatible(np, "aspeed,ast2600-wdt"))) {
 		u32 reg = readl(wdt->base + WDT_RESET_WIDTH);
 
 		reg &= config->ext_pulse_width_mask;
diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c
index 7e7bdcbbc741..9f3123b04536 100644
--- a/drivers/watchdog/imx2_wdt.c
+++ b/drivers/watchdog/imx2_wdt.c
@@ -55,7 +55,7 @@
 
 #define IMX2_WDT_WMCR		0x08		/* Misc Register */
 
-#define IMX2_WDT_MAX_TIME	128
+#define IMX2_WDT_MAX_TIME	128U
 #define IMX2_WDT_DEFAULT_TIME	60		/* in seconds */
 
 #define WDOG_SEC_TO_COUNT(s)	((s * 2 - 1) << 8)
@@ -180,7 +180,7 @@ static int imx2_wdt_set_timeout(struct watchdog_device *wdog,
 {
 	unsigned int actual;
 
-	actual = min(new_timeout, wdog->max_hw_heartbeat_ms * 1000);
+	actual = min(new_timeout, IMX2_WDT_MAX_TIME);
 	__imx2_wdt_set_timeout(wdog, actual);
 	wdog->timeout = new_timeout;
 	return 0;
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index 7494dbeb4409..db58aaa4dc59 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -29,6 +29,8 @@
 #include "../pci/pci.h"
 #ifdef CONFIG_PCI_MMCONFIG
 #include <asm/pci_x86.h>
+
+static int xen_mcfg_late(void);
 #endif
 
 static bool __read_mostly pci_seg_supported = true;
@@ -40,7 +42,18 @@ static int xen_add_device(struct device *dev)
 #ifdef CONFIG_PCI_IOV
 	struct pci_dev *physfn = pci_dev->physfn;
 #endif
-
+#ifdef CONFIG_PCI_MMCONFIG
+	static bool pci_mcfg_reserved = false;
+	/*
+	 * Reserve MCFG areas in Xen on first invocation due to this being
+	 * potentially called from inside of acpi_init immediately after
+	 * MCFG table has been finally parsed.
+	 */
+	if (!pci_mcfg_reserved) {
+		xen_mcfg_late();
+		pci_mcfg_reserved = true;
+	}
+#endif
 	if (pci_seg_supported) {
 		struct {
 			struct physdev_pci_device_add add;
@@ -213,7 +226,7 @@ static int __init register_xen_pci_notifier(void)
 arch_initcall(register_xen_pci_notifier);
 
 #ifdef CONFIG_PCI_MMCONFIG
-static int __init xen_mcfg_late(void)
+static int xen_mcfg_late(void)
 {
 	struct pci_mmcfg_region *cfg;
 	int rc;
@@ -252,8 +265,4 @@ static int __init xen_mcfg_late(void)
 	}
 	return 0;
 }
-/*
- * Needs to be done after acpi_init which are subsys_initcall.
- */
-subsys_initcall_sync(xen_mcfg_late);
 #endif
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 39c63152a358..454c6826abdb 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -55,6 +55,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/miscdevice.h>
+#include <linux/workqueue.h>
 
 #include <xen/xenbus.h>
 #include <xen/xen.h>
@@ -116,6 +117,8 @@ struct xenbus_file_priv {
 	wait_queue_head_t read_waitq;
 
 	struct kref kref;
+
+	struct work_struct wq;
 };
 
 /* Read out any raw xenbus messages queued up. */
@@ -300,14 +303,14 @@ static void watch_fired(struct xenbus_watch *watch,
 	mutex_unlock(&adap->dev_data->reply_mutex);
 }
 
-static void xenbus_file_free(struct kref *kref)
+static void xenbus_worker(struct work_struct *wq)
 {
 	struct xenbus_file_priv *u;
 	struct xenbus_transaction_holder *trans, *tmp;
 	struct watch_adapter *watch, *tmp_watch;
 	struct read_buffer *rb, *tmp_rb;
 
-	u = container_of(kref, struct xenbus_file_priv, kref);
+	u = container_of(wq, struct xenbus_file_priv, wq);
 
 	/*
 	 * No need for locking here because there are no other users,
@@ -333,6 +336,18 @@ static void xenbus_file_free(struct kref *kref)
 	kfree(u);
 }
 
+static void xenbus_file_free(struct kref *kref)
+{
+	struct xenbus_file_priv *u;
+
+	/*
+	 * We might be called in xenbus_thread().
+	 * Use workqueue to avoid deadlock.
+	 */
+	u = container_of(kref, struct xenbus_file_priv, kref);
+	schedule_work(&u->wq);
+}
+
 static struct xenbus_transaction_holder *xenbus_get_transaction(
 	struct xenbus_file_priv *u, uint32_t tx_id)
 {
@@ -652,6 +667,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp)
 	INIT_LIST_HEAD(&u->watches);
 	INIT_LIST_HEAD(&u->read_buffers);
 	init_waitqueue_head(&u->read_waitq);
+	INIT_WORK(&u->wq, xenbus_worker);
 
 	mutex_init(&u->reply_mutex);
 	mutex_init(&u->msgbuffer_mutex);
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 05454a7e22dc..550d0b169d7c 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -528,6 +528,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
 	v9inode = V9FS_I(inode);
 	mutex_lock(&v9inode->v_mutex);
 	if (!v9inode->writeback_fid &&
+	    (vma->vm_flags & VM_SHARED) &&
 	    (vma->vm_flags & VM_WRITE)) {
 		/*
 		 * clone a fid and add it to writeback_fid
@@ -629,6 +630,8 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
 			(vma->vm_end - vma->vm_start - 1),
 	};
 
+	if (!(vma->vm_flags & VM_SHARED))
+		return;
 
 	p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index c06845237cba..8196c21d8623 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -807,7 +807,12 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 
 	/* update inode */
 	inode->i_rdev = le32_to_cpu(info->rdev);
-	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+	/* directories have fl_stripe_unit set to zero */
+	if (le32_to_cpu(info->layout.fl_stripe_unit))
+		inode->i_blkbits =
+			fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+	else
+		inode->i_blkbits = CEPH_BLOCK_SHIFT;
 
 	__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index bfcf11c70bfa..09db6d08614d 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3640,7 +3640,9 @@ static void delayed_work(struct work_struct *work)
 				pr_info("mds%d hung\n", s->s_mds);
 			}
 		}
-		if (s->s_state < CEPH_MDS_SESSION_OPEN) {
+		if (s->s_state == CEPH_MDS_SESSION_NEW ||
+		    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
+		    s->s_state == CEPH_MDS_SESSION_REJECTED) {
 			/* this mds is failed or recovering, just wait */
 			ceph_put_mds_session(s);
 			continue;
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 8f68181256c0..f057c213c453 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -518,6 +518,7 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
 	rc = cuse_send_init(cc);
 	if (rc) {
 		fuse_dev_free(fud);
+		fuse_conn_put(&cc->fc);
 		return rc;
 	}
 	file->private_data = fud;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b7bde12d8cd5..1c0227c78a7b 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1171,7 +1171,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
 		} else
 			*p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
 	}
-	if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
+	if (label && (bmval[2] & FATTR4_WORD2_SECURITY_LABEL)) {
 		*p++ = cpu_to_be32(label->lfs);
 		*p++ = cpu_to_be32(label->pi);
 		*p++ = cpu_to_be32(label->len);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 4931c3a75f03..c818f9886f61 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1426,10 +1426,15 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	const nfs4_stateid *res_stateid = NULL;
 	struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
 
-	if (ret == 0) {
-		arg_stateid = &args->stateid;
+	switch (ret) {
+	case -NFS4ERR_NOMATCHING_LAYOUT:
+		break;
+	case 0:
 		if (res->lrs_present)
 			res_stateid = &res->stateid;
+		/* Fallthrough */
+	default:
+		arg_stateid = &args->stateid;
 	}
 	pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range,
 			res_stateid);
diff --git a/fs/statfs.c b/fs/statfs.c
index f0216629621d..56f655f757ff 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -304,19 +304,10 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *,
 static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
 {
 	struct compat_statfs64 buf;
-	if (sizeof(ubuf->f_bsize) == 4) {
-		if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
-		     kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
-			return -EOVERFLOW;
-		/* f_files and f_ffree may be -1; it's okay
-		 * to stuff that into 32 bits */
-		if (kbuf->f_files != 0xffffffffffffffffULL
-		 && (kbuf->f_files & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-		if (kbuf->f_ffree != 0xffffffffffffffffULL
-		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-	}
+
+	if ((kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
+		return -EOVERFLOW;
+
 	memset(&buf, 0, sizeof(struct compat_statfs64));
 	buf.f_type = kbuf->f_type;
 	buf.f_bsize = kbuf->f_bsize;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 9c03a7d5e400..c83478271c2e 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -3185,4 +3185,57 @@ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb)
 	return true;
 }
 
+struct element {
+	u8 id;
+	u8 datalen;
+	u8 data[];
+} __packed;
+
+/* element iteration helpers */
+#define for_each_element(_elem, _data, _datalen)			\
+	for (_elem = (const struct element *)(_data);			\
+	     (const u8 *)(_data) + (_datalen) - (const u8 *)_elem >=	\
+		(int)sizeof(*_elem) &&					\
+	     (const u8 *)(_data) + (_datalen) - (const u8 *)_elem >=	\
+		(int)sizeof(*_elem) + _elem->datalen;			\
+	     _elem = (const struct element *)(_elem->data + _elem->datalen))
+
+#define for_each_element_id(element, _id, data, datalen)		\
+	for_each_element(element, data, datalen)			\
+		if (element->id == (_id))
+
+#define for_each_element_extid(element, extid, data, datalen)		\
+	for_each_element(element, data, datalen)			\
+		if (element->id == WLAN_EID_EXTENSION &&		\
+		    element->datalen > 0 &&				\
+		    element->data[0] == (extid))
+
+#define for_each_subelement(sub, element)				\
+	for_each_element(sub, (element)->data, (element)->datalen)
+
+#define for_each_subelement_id(sub, id, element)			\
+	for_each_element_id(sub, id, (element)->data, (element)->datalen)
+
+#define for_each_subelement_extid(sub, extid, element)			\
+	for_each_element_extid(sub, extid, (element)->data, (element)->datalen)
+
+/**
+ * for_each_element_completed - determine if element parsing consumed all data
+ * @element: element pointer after for_each_element() or friends
+ * @data: same data pointer as passed to for_each_element() or friends
+ * @datalen: same data length as passed to for_each_element() or friends
+ *
+ * This function returns %true if all the data was parsed or considered
+ * while walking the elements. Only use this if your for_each_element()
+ * loop cannot be broken out of, otherwise it always returns %false.
+ *
+ * If some data was malformed, this returns %false since the last parsed
+ * element will not fill the whole remaining data.
+ */
+static inline bool for_each_element_completed(const struct element *element,
+					      const void *data, size_t datalen)
+{
+	return (const u8 *)element == (const u8 *)data + datalen;
+}
+
 #endif /* LINUX_IEEE80211_H */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 0d10b7ce0da7..e9d4e389aed9 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -330,6 +330,8 @@ enum {
 
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
+	if (current->mm != mm)
+		return;
 	if (likely(!(atomic_read(&mm->membarrier_state) &
 		     MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
 		return;
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index fdaaafdc7a00..5165e3b30899 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -353,6 +353,8 @@ struct device;
 #define SND_SOC_DAPM_WILL_PMD   0x80    /* called at start of sequence */
 #define SND_SOC_DAPM_PRE_POST_PMD \
 				(SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMD)
+#define SND_SOC_DAPM_PRE_POST_PMU \
+				(SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU)
 
 /* convenience event type detection */
 #define SND_SOC_DAPM_EVENT_ON(e)	\
diff --git a/kernel/elfcore.c b/kernel/elfcore.c
index fc482c8e0bd8..57fb4dcff434 100644
--- a/kernel/elfcore.c
+++ b/kernel/elfcore.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/binfmts.h>
+#include <linux/elfcore.h>
 
 Elf_Half __weak elf_core_extra_phdrs(void)
 {
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 5a0cf5f9008c..82104d3dd18e 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -271,7 +271,7 @@ pv_wait_early(struct pv_node *prev, int loop)
 	if ((loop & PV_PREV_CHECK_MASK) != 0)
 		return false;
 
-	return READ_ONCE(prev->state) != vcpu_running || vcpu_is_preempted(prev->cpu);
+	return READ_ONCE(prev->state) != vcpu_running;
 }
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f4e050681ba1..78ecdfae25b6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1077,7 +1077,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (cpumask_equal(&p->cpus_allowed, new_mask))
 		goto out;
 
-	if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
+	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
+	if (dest_cpu >= nr_cpu_ids) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1098,7 +1099,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
 	if (task_running(rq, p) || p->state == TASK_WAKING) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 76e0eaf4654e..dd27e632b1ba 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -235,7 +235,7 @@ static int membarrier_register_private_expedited(int flags)
 	 * groups, which use the same mm. (CLONE_VM but not
 	 * CLONE_THREAD).
 	 */
-	if (atomic_read(&mm->membarrier_state) & state)
+	if ((atomic_read(&mm->membarrier_state) & state) == state)
 		return 0;
 	atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED, &mm->membarrier_state);
 	if (flags & MEMBARRIER_FLAG_SYNC_CORE)
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index a59641fb88b6..a836efd34589 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -44,34 +44,39 @@ static int bc_shutdown(struct clock_event_device *evt)
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
-	int bc_moved;
 	/*
-	 * We try to cancel the timer first. If the callback is on
-	 * flight on some other cpu then we let it handle it. If we
-	 * were able to cancel the timer nothing can rearm it as we
-	 * own broadcast_lock.
+	 * This is called either from enter/exit idle code or from the
+	 * broadcast handler. In all cases tick_broadcast_lock is held.
 	 *
-	 * However we can also be called from the event handler of
-	 * ce_broadcast_hrtimer itself when it expires. We cannot
-	 * restart the timer because we are in the callback, but we
-	 * can set the expiry time and let the callback return
-	 * HRTIMER_RESTART.
+	 * hrtimer_cancel() cannot be called here neither from the
+	 * broadcast handler nor from the enter/exit idle code. The idle
+	 * code can run into the problem described in bc_shutdown() and the
+	 * broadcast handler cannot wait for itself to complete for obvious
+	 * reasons.
 	 *
-	 * Since we are in the idle loop at this point and because
-	 * hrtimer_{start/cancel} functions call into tracing,
-	 * calls to these functions must be bound within RCU_NONIDLE.
+	 * Each caller tries to arm the hrtimer on its own CPU, but if the
+	 * hrtimer callbback function is currently running, then
+	 * hrtimer_start() cannot move it and the timer stays on the CPU on
+	 * which it is assigned at the moment.
+	 *
+	 * As this can be called from idle code, the hrtimer_start()
+	 * invocation has to be wrapped with RCU_NONIDLE() as
+	 * hrtimer_start() can call into tracing.
 	 */
-	RCU_NONIDLE({
-			bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
-			if (bc_moved)
-				hrtimer_start(&bctimer, expires,
-					      HRTIMER_MODE_ABS_PINNED);});
-	if (bc_moved) {
-		/* Bind the "device" to the cpu */
-		bc->bound_on = smp_processor_id();
-	} else if (bc->bound_on == smp_processor_id()) {
-		hrtimer_set_expires(&bctimer, expires);
-	}
+	RCU_NONIDLE( {
+		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+		/*
+		 * The core tick broadcast mode expects bc->bound_on to be set
+		 * correctly to prevent a CPU which has the broadcast hrtimer
+		 * armed from going deep idle.
+		 *
+		 * As tick_broadcast_lock is held, nothing can change the cpu
+		 * base which was just established in hrtimer_start() above. So
+		 * the below access is safe even without holding the hrtimer
+		 * base lock.
+		 */
+		bc->bound_on = bctimer.base->cpu_base->cpu;
+	} );
 	return 0;
 }
 
@@ -97,10 +102,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 {
 	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
 
-	if (clockevent_state_oneshot(&ce_broadcast_hrtimer))
-		if (ce_broadcast_hrtimer.next_event != KTIME_MAX)
-			return HRTIMER_RESTART;
-
 	return HRTIMER_NORESTART;
 }
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index fa49cd753dea..ae64cb819a9a 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1590,24 +1590,26 @@ void timer_clear_idle(void)
 static int collect_expired_timers(struct timer_base *base,
 				  struct hlist_head *heads)
 {
+	unsigned long now = READ_ONCE(jiffies);
+
 	/*
 	 * NOHZ optimization. After a long idle sleep we need to forward the
 	 * base to current jiffies. Avoid a loop by searching the bitfield for
 	 * the next expiring timer.
 	 */
-	if ((long)(jiffies - base->clk) > 2) {
+	if ((long)(now - base->clk) > 2) {
 		unsigned long next = __next_timer_interrupt(base);
 
 		/*
 		 * If the next timer is ahead of time forward to current
 		 * jiffies, otherwise forward to the next expiry time:
 		 */
-		if (time_after(next, jiffies)) {
+		if (time_after(next, now)) {
 			/*
 			 * The call site will increment base->clk and then
 			 * terminate the expiry loop immediately.
 			 */
-			base->clk = jiffies;
+			base->clk = now;
 			return 0;
 		}
 		base->clk = next;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 3f34cfb66a85..bdf104596d12 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2526,6 +2526,8 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
 		return NULL;
 	}
 
+	alias->var_ref_idx = var_ref->var_ref_idx;
+
 	return alias;
 }
 
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 51411f9c4068..e81d11715d95 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -15,6 +15,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
@@ -231,7 +232,12 @@ static inline void check_heap_object(const void *ptr, unsigned long n,
 	if (!virt_addr_valid(ptr))
 		return;
 
-	page = virt_to_head_page(ptr);
+	/*
+	 * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the
+	 * highmem page or fallback to virt_to_page(). The following
+	 * is effectively a highmem-aware virt_to_head_page().
+	 */
+	page = compound_head(kmap_to_page((void *)ptr));
 
 	if (PageSlab(page)) {
 		/* Check slab allocator for flags and size. */
diff --git a/net/9p/client.c b/net/9p/client.c
index b615aae5a0f8..d62f83f93d7b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -296,6 +296,7 @@ p9_tag_alloc(struct p9_client *c, int8_t type, unsigned int max_size)
 
 	p9pdu_reset(&req->tc);
 	p9pdu_reset(&req->rc);
+	req->t_err = 0;
 	req->status = REQ_STATUS_ALLOC;
 	init_waitqueue_head(&req->wq);
 	INIT_LIST_HEAD(&req->req_list);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 2145581d7b3d..24fddf032279 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3429,8 +3429,11 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 			      NFT_SET_OBJECT))
 			return -EINVAL;
 		/* Only one of these operations is supported */
-		if ((flags & (NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT)) ==
-			     (NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT))
+		if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) ==
+			     (NFT_SET_MAP | NFT_SET_OBJECT))
+			return -EOPNOTSUPP;
+		if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) ==
+			     (NFT_SET_EVAL | NFT_SET_OBJECT))
 			return -EOPNOTSUPP;
 	}
 
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 161c3451a747..55754d9939b5 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -76,9 +76,6 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
-	if (set->flags & NFT_SET_EVAL)
-		return -EOPNOTSUPP;
-
 	priv->sreg = nft_parse_register(tb[NFTA_LOOKUP_SREG]);
 	err = nft_validate_register_load(priv->sreg, set->klen);
 	if (err < 0)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 6168db3c35e4..334e3181f1c5 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -200,6 +200,38 @@ cfg80211_get_dev_from_info(struct net *netns, struct genl_info *info)
 	return __cfg80211_rdev_from_attrs(netns, info->attrs);
 }
 
+static int validate_beacon_head(const struct nlattr *attr,
+				struct netlink_ext_ack *extack)
+{
+	const u8 *data = nla_data(attr);
+	unsigned int len = nla_len(attr);
+	const struct element *elem;
+	const struct ieee80211_mgmt *mgmt = (void *)data;
+	unsigned int fixedlen = offsetof(struct ieee80211_mgmt,
+					 u.beacon.variable);
+
+	if (len < fixedlen)
+		goto err;
+
+	if (ieee80211_hdrlen(mgmt->frame_control) !=
+	    offsetof(struct ieee80211_mgmt, u.beacon))
+		goto err;
+
+	data += fixedlen;
+	len -= fixedlen;
+
+	for_each_element(elem, data, len) {
+		/* nothing */
+	}
+
+	if (for_each_element_completed(elem, data, len))
+		return 0;
+
+err:
+	NL_SET_ERR_MSG_ATTR(extack, attr, "malformed beacon head");
+	return -EINVAL;
+}
+
 /* policy for the attributes */
 static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_WIPHY] = { .type = NLA_U32 },
@@ -2299,6 +2331,8 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 
 	control_freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]);
 
+	memset(chandef, 0, sizeof(*chandef));
+
 	chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq);
 	chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
 	chandef->center_freq1 = control_freq;
@@ -2819,7 +2853,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 
 	if (rdev->ops->get_channel) {
 		int ret;
-		struct cfg80211_chan_def chandef;
+		struct cfg80211_chan_def chandef = {};
 
 		ret = rdev_get_channel(rdev, wdev, &chandef);
 		if (ret == 0) {
@@ -4014,6 +4048,12 @@ static int nl80211_parse_beacon(struct nlattr *attrs[],
 	memset(bcn, 0, sizeof(*bcn));
 
 	if (attrs[NL80211_ATTR_BEACON_HEAD]) {
+		int ret = validate_beacon_head(attrs[NL80211_ATTR_BEACON_HEAD],
+					       NULL);
+
+		if (ret)
+			return ret;
+
 		bcn->head = nla_data(attrs[NL80211_ATTR_BEACON_HEAD]);
 		bcn->head_len = nla_len(attrs[NL80211_ATTR_BEACON_HEAD]);
 		if (!bcn->head_len)
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index d8ebf4f0ef6e..cccbf845079c 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2095,7 +2095,7 @@ static void reg_call_notifier(struct wiphy *wiphy,
 
 static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
 {
-	struct cfg80211_chan_def chandef;
+	struct cfg80211_chan_def chandef = {};
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	enum nl80211_iftype iftype;
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d0e7472dd9fd..e5d61ba837ad 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -484,6 +484,8 @@ const u8 *cfg80211_find_ie_match(u8 eid, const u8 *ies, int len,
 				 const u8 *match, int match_len,
 				 int match_offset)
 {
+	const struct element *elem;
+
 	/* match_offset can't be smaller than 2, unless match_len is
 	 * zero, in which case match_offset must be zero as well.
 	 */
@@ -491,14 +493,10 @@ const u8 *cfg80211_find_ie_match(u8 eid, const u8 *ies, int len,
 		    (!match_len && match_offset)))
 		return NULL;
 
-	while (len >= 2 && len >= ies[1] + 2) {
-		if ((ies[0] == eid) &&
-		    (ies[1] + 2 >= match_offset + match_len) &&
-		    !memcmp(ies + match_offset, match, match_len))
-			return ies;
-
-		len -= ies[1] + 2;
-		ies += ies[1] + 2;
+	for_each_element_id(elem, eid, ies, len) {
+		if (elem->datalen >= match_offset - 2 + match_len &&
+		    !memcmp(elem->data + match_offset - 2, match, match_len))
+			return (void *)elem;
 	}
 
 	return NULL;
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 06943d9c9835..4f0cfb8cc682 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -800,7 +800,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
-	struct cfg80211_chan_def chandef;
+	struct cfg80211_chan_def chandef = {};
 	int ret;
 
 	switch (wdev->iftype) {
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index d9e7728027c6..f63b4bd45d60 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -271,8 +271,16 @@ static int ima_calc_file_hash_atfm(struct file *file,
 		rbuf_len = min_t(loff_t, i_size - offset, rbuf_size[active]);
 		rc = integrity_kernel_read(file, offset, rbuf[active],
 					   rbuf_len);
-		if (rc != rbuf_len)
+		if (rc != rbuf_len) {
+			if (rc >= 0)
+				rc = -EINVAL;
+			/*
+			 * Forward current rc, do not overwrite with return value
+			 * from ahash_wait()
+			 */
+			ahash_wait(ahash_rc, &wait);
 			goto out3;
+		}
 
 		if (rbuf[1] && offset) {
 			/* Using two buffers, and it is not the first
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 18cddf1729a6..64a52d495b1f 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -31,6 +31,13 @@
 #define SGTL5000_DAP_REG_OFFSET	0x0100
 #define SGTL5000_MAX_REG_OFFSET	0x013A
 
+/* Delay for the VAG ramp up */
+#define SGTL5000_VAG_POWERUP_DELAY 500 /* ms */
+/* Delay for the VAG ramp down */
+#define SGTL5000_VAG_POWERDOWN_DELAY 500 /* ms */
+
+#define SGTL5000_OUTPUTS_MUTE (SGTL5000_HP_MUTE | SGTL5000_LINE_OUT_MUTE)
+
 /* default value of sgtl5000 registers */
 static const struct reg_default sgtl5000_reg_defaults[] = {
 	{ SGTL5000_CHIP_DIG_POWER,		0x0000 },
@@ -116,6 +123,13 @@ enum  {
 	I2S_LRCLK_STRENGTH_HIGH,
 };
 
+enum {
+	HP_POWER_EVENT,
+	DAC_POWER_EVENT,
+	ADC_POWER_EVENT,
+	LAST_POWER_EVENT = ADC_POWER_EVENT
+};
+
 /* sgtl5000 private structure in codec */
 struct sgtl5000_priv {
 	int sysclk;	/* sysclk rate */
@@ -129,8 +143,109 @@ struct sgtl5000_priv {
 	u8 micbias_resistor;
 	u8 micbias_voltage;
 	u8 lrclk_strength;
+	u16 mute_state[LAST_POWER_EVENT + 1];
 };
 
+static inline int hp_sel_input(struct snd_soc_component *component)
+{
+	return (snd_soc_component_read32(component, SGTL5000_CHIP_ANA_CTRL) &
+		SGTL5000_HP_SEL_MASK) >> SGTL5000_HP_SEL_SHIFT;
+}
+
+static inline u16 mute_output(struct snd_soc_component *component,
+			      u16 mute_mask)
+{
+	u16 mute_reg = snd_soc_component_read32(component,
+					      SGTL5000_CHIP_ANA_CTRL);
+
+	snd_soc_component_update_bits(component, SGTL5000_CHIP_ANA_CTRL,
+			    mute_mask, mute_mask);
+	return mute_reg;
+}
+
+static inline void restore_output(struct snd_soc_component *component,
+				  u16 mute_mask, u16 mute_reg)
+{
+	snd_soc_component_update_bits(component, SGTL5000_CHIP_ANA_CTRL,
+		mute_mask, mute_reg);
+}
+
+static void vag_power_on(struct snd_soc_component *component, u32 source)
+{
+	if (snd_soc_component_read32(component, SGTL5000_CHIP_ANA_POWER) &
+	    SGTL5000_VAG_POWERUP)
+		return;
+
+	snd_soc_component_update_bits(component, SGTL5000_CHIP_ANA_POWER,
+			    SGTL5000_VAG_POWERUP, SGTL5000_VAG_POWERUP);
+
+	/* When VAG powering on to get local loop from Line-In, the sleep
+	 * is required to avoid loud pop.
+	 */
+	if (hp_sel_input(component) == SGTL5000_HP_SEL_LINE_IN &&
+	    source == HP_POWER_EVENT)
+		msleep(SGTL5000_VAG_POWERUP_DELAY);
+}
+
+static int vag_power_consumers(struct snd_soc_component *component,
+			       u16 ana_pwr_reg, u32 source)
+{
+	int consumers = 0;
+
+	/* count dac/adc consumers unconditional */
+	if (ana_pwr_reg & SGTL5000_DAC_POWERUP)
+		consumers++;
+	if (ana_pwr_reg & SGTL5000_ADC_POWERUP)
+		consumers++;
+
+	/*
+	 * If the event comes from HP and Line-In is selected,
+	 * current action is 'DAC to be powered down'.
+	 * As HP_POWERUP is not set when HP muxed to line-in,
+	 * we need to keep VAG power ON.
+	 */
+	if (source == HP_POWER_EVENT) {
+		if (hp_sel_input(component) == SGTL5000_HP_SEL_LINE_IN)
+			consumers++;
+	} else {
+		if (ana_pwr_reg & SGTL5000_HP_POWERUP)
+			consumers++;
+	}
+
+	return consumers;
+}
+
+static void vag_power_off(struct snd_soc_component *component, u32 source)
+{
+	u16 ana_pwr = snd_soc_component_read32(component,
+					     SGTL5000_CHIP_ANA_POWER);
+
+	if (!(ana_pwr & SGTL5000_VAG_POWERUP))
+		return;
+
+	/*
+	 * This function calls when any of VAG power consumers is disappearing.
+	 * Thus, if there is more than one consumer at the moment, as minimum
+	 * one consumer will definitely stay after the end of the current
+	 * event.
+	 * Don't clear VAG_POWERUP if 2 or more consumers of VAG present:
+	 * - LINE_IN (for HP events) / HP (for DAC/ADC events)
+	 * - DAC
+	 * - ADC
+	 * (the current consumer is disappearing right now)
+	 */
+	if (vag_power_consumers(component, ana_pwr, source) >= 2)
+		return;
+
+	snd_soc_component_update_bits(component, SGTL5000_CHIP_ANA_POWER,
+		SGTL5000_VAG_POWERUP, 0);
+	/* In power down case, we need wait 400-1000 ms
+	 * when VAG fully ramped down.
+	 * As longer we wait, as smaller pop we've got.
+	 */
+	msleep(SGTL5000_VAG_POWERDOWN_DELAY);
+}
+
 /*
  * mic_bias power on/off share the same register bits with
  * output impedance of mic bias, when power on mic bias, we
@@ -162,36 +277,46 @@ static int mic_bias_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
-/*
- * As manual described, ADC/DAC only works when VAG powerup,
- * So enabled VAG before ADC/DAC up.
- * In power down case, we need wait 400ms when vag fully ramped down.
- */
-static int power_vag_event(struct snd_soc_dapm_widget *w,
-	struct snd_kcontrol *kcontrol, int event)
+static int vag_and_mute_control(struct snd_soc_component *component,
+				 int event, int event_source)
 {
-	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
-	const u32 mask = SGTL5000_DAC_POWERUP | SGTL5000_ADC_POWERUP;
+	static const u16 mute_mask[] = {
+		/*
+		 * Mask for HP_POWER_EVENT.
+		 * Muxing Headphones have to be wrapped with mute/unmute
+		 * headphones only.
+		 */
+		SGTL5000_HP_MUTE,
+		/*
+		 * Masks for DAC_POWER_EVENT/ADC_POWER_EVENT.
+		 * Muxing DAC or ADC block have to wrapped with mute/unmute
+		 * both headphones and line-out.
+		 */
+		SGTL5000_OUTPUTS_MUTE,
+		SGTL5000_OUTPUTS_MUTE
+	};
+
+	struct sgtl5000_priv *sgtl5000 =
+		snd_soc_component_get_drvdata(component);
 
 	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		sgtl5000->mute_state[event_source] =
+			mute_output(component, mute_mask[event_source]);
+		break;
 	case SND_SOC_DAPM_POST_PMU:
-		snd_soc_component_update_bits(component, SGTL5000_CHIP_ANA_POWER,
-			SGTL5000_VAG_POWERUP, SGTL5000_VAG_POWERUP);
-		msleep(400);
+		vag_power_on(component, event_source);
+		restore_output(component, mute_mask[event_source],
+			       sgtl5000->mute_state[event_source]);
 		break;
-
 	case SND_SOC_DAPM_PRE_PMD:
-		/*
-		 * Don't clear VAG_POWERUP, when both DAC and ADC are
-		 * operational to prevent inadvertently starving the
-		 * other one of them.
-		 */
-		if ((snd_soc_component_read32(component, SGTL5000_CHIP_ANA_POWER) &
-				mask) != mask) {
-			snd_soc_component_update_bits(component, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_VAG_POWERUP, 0);
-			msleep(400);
-		}
+		sgtl5000->mute_state[event_source] =
+			mute_output(component, mute_mask[event_source]);
+		vag_power_off(component, event_source);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		restore_output(component, mute_mask[event_source],
+			       sgtl5000->mute_state[event_source]);
 		break;
 	default:
 		break;
@@ -200,6 +325,41 @@ static int power_vag_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
+/*
+ * Mute Headphone when power it up/down.
+ * Control VAG power on HP power path.
+ */
+static int headphone_pga_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	return vag_and_mute_control(component, event, HP_POWER_EVENT);
+}
+
+/* As manual describes, ADC/DAC powering up/down requires
+ * to mute outputs to avoid pops.
+ * Control VAG power on ADC/DAC power path.
+ */
+static int adc_updown_depop(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	return vag_and_mute_control(component, event, ADC_POWER_EVENT);
+}
+
+static int dac_updown_depop(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	return vag_and_mute_control(component, event, DAC_POWER_EVENT);
+}
+
 /* input sources for ADC */
 static const char *adc_mux_text[] = {
 	"MIC_IN", "LINE_IN"
@@ -272,7 +432,10 @@ static const struct snd_soc_dapm_widget sgtl5000_dapm_widgets[] = {
 			    mic_bias_event,
 			    SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
 
-	SND_SOC_DAPM_PGA("HP", SGTL5000_CHIP_ANA_POWER, 4, 0, NULL, 0),
+	SND_SOC_DAPM_PGA_E("HP", SGTL5000_CHIP_ANA_POWER, 4, 0, NULL, 0,
+			   headphone_pga_event,
+			   SND_SOC_DAPM_PRE_POST_PMU |
+			   SND_SOC_DAPM_PRE_POST_PMD),
 	SND_SOC_DAPM_PGA("LO", SGTL5000_CHIP_ANA_POWER, 0, 0, NULL, 0),
 
 	SND_SOC_DAPM_MUX("Capture Mux", SND_SOC_NOPM, 0, 0, &adc_mux),
@@ -293,11 +456,12 @@ static const struct snd_soc_dapm_widget sgtl5000_dapm_widgets[] = {
 				0, SGTL5000_CHIP_DIG_POWER,
 				1, 0),
 
-	SND_SOC_DAPM_ADC("ADC", "Capture", SGTL5000_CHIP_ANA_POWER, 1, 0),
-	SND_SOC_DAPM_DAC("DAC", "Playback", SGTL5000_CHIP_ANA_POWER, 3, 0),
-
-	SND_SOC_DAPM_PRE("VAG_POWER_PRE", power_vag_event),
-	SND_SOC_DAPM_POST("VAG_POWER_POST", power_vag_event),
+	SND_SOC_DAPM_ADC_E("ADC", "Capture", SGTL5000_CHIP_ANA_POWER, 1, 0,
+			   adc_updown_depop, SND_SOC_DAPM_PRE_POST_PMU |
+			   SND_SOC_DAPM_PRE_POST_PMD),
+	SND_SOC_DAPM_DAC_E("DAC", "Playback", SGTL5000_CHIP_ANA_POWER, 3, 0,
+			   dac_updown_depop, SND_SOC_DAPM_PRE_POST_PMU |
+			   SND_SOC_DAPM_PRE_POST_PMD),
 };
 
 /* routes for sgtl5000 */
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 95a43ccb6dd0..bca0c9e5452c 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -259,8 +259,8 @@ endef
 
 define do_generate_dynamic_list_file
 	symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
-	xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\
-	if [ "$$symbol_type" = "U W w" ];then				\
+	xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
+	if [ "$$symbol_type" = "U W" ];then				\
 		(echo '{';						\
 		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
 		echo '};';						\
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 6ccfd13d5cf9..382e476629fb 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -254,10 +254,10 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 		errno = ENOMEM;
 		return -1;
 	}
+	pevent->cmdlines = cmdlines;
 
 	cmdlines[pevent->cmdline_count].comm = strdup(comm);
 	if (!cmdlines[pevent->cmdline_count].comm) {
-		free(cmdlines);
 		errno = ENOMEM;
 		return -1;
 	}
@@ -268,7 +268,6 @@ static int add_new_comm(struct tep_handle *pevent, const char *comm, int pid)
 		pevent->cmdline_count++;
 
 	qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
-	pevent->cmdlines = cmdlines;
 
 	return 0;
 }
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 849b3be15bd8..510caedd7319 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -837,7 +837,7 @@ ifndef NO_JVMTI
     JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
   else
     ifneq (,$(wildcard /usr/sbin/alternatives))
-      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed -e 's%/jre/bin/java.%%g' -e 's%/bin/java.%%g')
     endif
   endif
   ifndef JDIR
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 05920e3edf7a..47357973b55b 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <errno.h>
+#include "../../util/debug.h"
 #ifndef REMOTE_UNWIND_LIBUNWIND
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-#include "../../util/debug.h"
 #endif
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 789962565c9c..6aae10ff954c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -3090,8 +3090,11 @@ int cmd_stat(int argc, const char **argv)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
+		if (run_idx != 0)
+			perf_evlist__reset_prev_raw_counts(evsel_list);
+
 		status = run_perf_stat(argc, argv, run_idx);
-		if (forever && status != -1) {
+		if (forever && status != -1 && !interval) {
 			print_counters(NULL, argc, argv);
 			perf_stat__reset_stats();
 		}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0c70788593c8..3c0d74fc1ff2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1114,7 +1114,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 
 	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
 	if (sysfs__read_str(file, &cache->map, &len)) {
-		free(cache->map);
+		free(cache->size);
 		free(cache->type);
 		return -1;
 	}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index a0061e0b0fad..6917ba8a0024 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -154,6 +154,15 @@ static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 	evsel->prev_raw_counts = NULL;
 }
 
+static void perf_evsel__reset_prev_raw_counts(struct perf_evsel *evsel)
+{
+	if (evsel->prev_raw_counts) {
+		evsel->prev_raw_counts->aggr.val = 0;
+		evsel->prev_raw_counts->aggr.ena = 0;
+		evsel->prev_raw_counts->aggr.run = 0;
+       }
+}
+
 static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
@@ -204,6 +213,14 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist)
 	}
 }
 
+void perf_evlist__reset_prev_raw_counts(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		perf_evsel__reset_prev_raw_counts(evsel);
+}
+
 static void zero_per_pkg(struct perf_evsel *counter)
 {
 	if (counter->per_pkg_mask)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 36efb986f7fc..e19abb1635c4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -158,6 +158,7 @@ void perf_stat__collect_metric_expr(struct perf_evlist *);
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
 void perf_evlist__reset_stats(struct perf_evlist *evlist);
+void perf_evlist__reset_prev_raw_counts(struct perf_evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct perf_evsel *counter);
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index 33752e06ff8d..3de57cc8716b 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -12,6 +12,7 @@
  */
 #ifndef __NFIT_TEST_H__
 #define __NFIT_TEST_H__
+#include <linux/acpi.h>
 #include <linux/list.h>
 #include <linux/uuid.h>
 #include <linux/ioport.h>
@@ -234,9 +235,6 @@ struct nd_intel_lss {
 	__u32 status;
 } __packed;
 
-union acpi_object;
-typedef void *acpi_handle;
-
 typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t);
 typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle,
 		 const guid_t *guid, u64 rev, u64 func,