diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt
index d11eff61fc9a..5cd58439ad2d 100644
--- a/Documentation/x86/pti.txt
+++ b/Documentation/x86/pti.txt
@@ -78,7 +78,7 @@ this protection comes at a cost:
      non-PTI SYSCALL entry code, so requires mapping fewer
      things into the userspace page tables.  The downside is
      that stacks must be switched at entry time.
-  d. Global pages are disabled for all kernel structures not
+  c. Global pages are disabled for all kernel structures not
      mapped into both kernel and userspace page tables.  This
      feature of the MMU allows different processes to share TLB
      entries mapping the kernel.  Losing the feature means more
diff --git a/Makefile b/Makefile
index 4951305eb867..bf1a277a67a4 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 14
+SUBLEVEL = 15
 EXTRAVERSION =
 NAME = Petit Gorille
 
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index 37bd6d9b8eb9..a6bdc1da47ad 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -102,6 +102,15 @@ sio_pci_route(void)
 				   alpha_mv.sys.sio.route_tab);
 }
 
+static bool sio_pci_dev_irq_needs_level(const struct pci_dev *dev)
+{
+	if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
+	    (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+		return false;
+
+	return true;
+}
+
 static unsigned int __init
 sio_collect_irq_levels(void)
 {
@@ -110,8 +119,7 @@ sio_collect_irq_levels(void)
 
 	/* Iterate through the devices, collecting IRQ levels.  */
 	for_each_pci_dev(dev) {
-		if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
-		    (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+		if (!sio_pci_dev_irq_needs_level(dev))
 			continue;
 
 		if (dev->irq)
@@ -120,8 +128,7 @@ sio_collect_irq_levels(void)
 	return level_bits;
 }
 
-static void __init
-sio_fixup_irq_levels(unsigned int level_bits)
+static void __sio_fixup_irq_levels(unsigned int level_bits, bool reset)
 {
 	unsigned int old_level_bits;
 
@@ -139,12 +146,21 @@ sio_fixup_irq_levels(unsigned int level_bits)
 	 */
 	old_level_bits = inb(0x4d0) | (inb(0x4d1) << 8);
 
-	level_bits |= (old_level_bits & 0x71ff);
+	if (reset)
+		old_level_bits &= 0x71ff;
+
+	level_bits |= old_level_bits;
 
 	outb((level_bits >> 0) & 0xff, 0x4d0);
 	outb((level_bits >> 8) & 0xff, 0x4d1);
 }
 
+static inline void
+sio_fixup_irq_levels(unsigned int level_bits)
+{
+	__sio_fixup_irq_levels(level_bits, true);
+}
+
 static inline int
 noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
@@ -181,7 +197,14 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	const long min_idsel = 6, max_idsel = 14, irqs_per_slot = 5;
 	int irq = COMMON_TABLE_LOOKUP, tmp;
 	tmp = __kernel_extbl(alpha_mv.sys.sio.route_tab, irq);
-	return irq >= 0 ? tmp : -1;
+
+	irq = irq >= 0 ? tmp : -1;
+
+	/* Fixup IRQ level if an actual IRQ mapping is detected */
+	if (sio_pci_dev_irq_needs_level(dev) && irq >= 0)
+		__sio_fixup_irq_levels(1 << irq, false);
+
+	return irq;
 }
 
 static inline int
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
index cf2f5240e176..27cc913ca0f5 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a7.dts
@@ -53,7 +53,8 @@
 		};
 
 		pinctrl: pin-controller@10000 {
-			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>;
+			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header
+				     &pmx_gpio_header_gpo>;
 			pinctrl-names = "default";
 
 			pmx_uart0: pmx-uart0 {
@@ -85,11 +86,16 @@
 			 * ground.
 			 */
 			pmx_gpio_header: pmx-gpio-header {
-				marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28",
+				marvell,pins = "mpp17", "mpp29", "mpp28",
 					       "mpp35", "mpp34", "mpp40";
 				marvell,function = "gpio";
 			};
 
+			pmx_gpio_header_gpo: pxm-gpio-header-gpo {
+				marvell,pins = "mpp7";
+				marvell,function = "gpo";
+			};
+
 			pmx_gpio_init: pmx-init {
 				marvell,pins = "mpp38";
 				marvell,function = "gpio";
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 5caaf971fb50..df433abfcb02 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -10,6 +10,7 @@ CONFIG_SMP=y
 CONFIG_NR_CPUS=8
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
+CONFIG_CMA=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CPU_FREQ=y
@@ -33,6 +34,7 @@ CONFIG_CAN_SUN4I=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DMA_CMA=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_AHCI_SUNXI=y
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index c3276436b0ae..c12e7b572a41 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1656,6 +1656,7 @@ static struct omap_hwmod omap3xxx_mmc3_hwmod = {
 	.main_clk	= "mmchs3_fck",
 	.prcm		= {
 		.omap2 = {
+			.module_offs = CORE_MOD,
 			.prcm_reg_id = 1,
 			.module_bit = OMAP3430_EN_MMC3_SHIFT,
 			.idlest_reg_id = 1,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index f2aa2a81de4d..32690107c1cc 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -63,8 +63,10 @@
 			cpm_ethernet: ethernet@0 {
 				compatible = "marvell,armada-7k-pp22";
 				reg = <0x0 0x100000>, <0x129000 0xb000>;
-				clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>, <&cpm_clk 1 5>;
-				clock-names = "pp_clk", "gop_clk", "mg_clk";
+				clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>,
+					 <&cpm_clk 1 5>, <&cpm_clk 1 18>;
+				clock-names = "pp_clk", "gop_clk",
+					      "mg_clk","axi_clk";
 				marvell,system-controller = <&cpm_syscon0>;
 				status = "disabled";
 				dma-coherent;
@@ -114,7 +116,8 @@
 				#size-cells = <0>;
 				compatible = "marvell,orion-mdio";
 				reg = <0x12a200 0x10>;
-				clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>;
+				clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>,
+					 <&cpm_clk 1 6>, <&cpm_clk 1 18>;
 				status = "disabled";
 			};
 
@@ -295,8 +298,8 @@
 				compatible = "marvell,armada-cp110-sdhci";
 				reg = <0x780000 0x300>;
 				interrupts = <ICU_GRP_NSR 27 IRQ_TYPE_LEVEL_HIGH>;
-				clock-names = "core";
-				clocks = <&cpm_clk 1 4>;
+				clock-names = "core","axi";
+				clocks = <&cpm_clk 1 4>, <&cpm_clk 1 18>;
 				dma-coherent;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 4fe70323abb3..14e47c5c3816 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -63,8 +63,10 @@
 			cps_ethernet: ethernet@0 {
 				compatible = "marvell,armada-7k-pp22";
 				reg = <0x0 0x100000>, <0x129000 0xb000>;
-				clocks = <&cps_clk 1 3>, <&cps_clk 1 9>, <&cps_clk 1 5>;
-				clock-names = "pp_clk", "gop_clk", "mg_clk";
+				clocks = <&cps_clk 1 3>, <&cps_clk 1 9>,
+					 <&cps_clk 1 5>, <&cps_clk 1 18>;
+				clock-names = "pp_clk", "gop_clk",
+					      "mg_clk", "axi_clk";
 				marvell,system-controller = <&cps_syscon0>;
 				status = "disabled";
 				dma-coherent;
@@ -114,7 +116,8 @@
 				#size-cells = <0>;
 				compatible = "marvell,orion-mdio";
 				reg = <0x12a200 0x10>;
-				clocks = <&cps_clk 1 9>, <&cps_clk 1 5>;
+				clocks = <&cps_clk 1 9>, <&cps_clk 1 5>,
+					 <&cps_clk 1 6>, <&cps_clk 1 18>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 7debb74843a0..380261e258ef 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -44,7 +44,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
-		kvm_inject_undefined(vcpu);
+		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
 	}
 
@@ -53,7 +53,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_inject_undefined(vcpu);
+	vcpu_set_reg(vcpu, 0, ~0UL);
 	return 1;
 }
 
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 4674f1efbe7a..e1675c25d5d4 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -575,7 +575,7 @@ static int __init ar7_register_uarts(void)
 	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
-	uart_port.flags		= UPF_FIXED_TYPE;
+	uart_port.flags		= UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
 	uart_port.regshift	= 2;
 
 	uart_port.line		= 0;
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index dd5567b1e305..8f5bd04f320a 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -292,7 +292,6 @@ void mips_cm_lock_other(unsigned int cluster, unsigned int core,
 				  *this_cpu_ptr(&cm_core_lock_flags));
 	} else {
 		WARN_ON(cluster != 0);
-		WARN_ON(vp != 0);
 		WARN_ON(block != CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 
 		/*
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index a703452d67b6..555e22d5e07f 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -209,5 +209,11 @@ exc_##label##_book3e:
 	ori	r3,r3,vector_offset@l;		\
 	mtspr	SPRN_IVOR##vector_number,r3;
 
+#define RFI_TO_KERNEL							\
+	rfi
+
+#define RFI_TO_USER							\
+	rfi
+
 #endif /* _ASM_POWERPC_EXCEPTION_64E_H */
 
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 9a318973af05..ccf10c2f8899 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -69,6 +69,59 @@
  */
 #define EX_R3		EX_DAR
 
+/*
+ * Macros for annotating the expected destination of (h)rfid
+ *
+ * The nop instructions allow us to insert one or more instructions to flush the
+ * L1-D cache when returning to userspace or a guest.
+ */
+#define RFI_FLUSH_SLOT							\
+	RFI_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop
+
+#define RFI_TO_KERNEL							\
+	rfid
+
+#define RFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define HRFI_TO_KERNEL							\
+	hrfid
+
+#define HRFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_UNKNOWN							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
 #ifdef CONFIG_RELOCATABLE
 #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)			\
 	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
@@ -213,7 +266,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 #define EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	__EXCEPTION_PROLOG_PSERIES_1(label, h)
@@ -227,7 +280,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 
 #define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h)			\
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 8f88f771cc55..1e82eb3caabd 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -187,7 +187,20 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET label##1b-label##3b;		\
 	.popsection;
 
+#define RFI_FLUSH_FIXUP_SECTION				\
+951:							\
+	.pushsection __rfi_flush_fixup,"a";		\
+	.align 2;					\
+952:							\
+	FTR_ENTRY_OFFSET 951b-952b;			\
+	.popsection;
+
+
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
+
 void apply_feature_fixups(void);
 void setup_feature_keys(void);
 #endif
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index a409177be8bd..f0461618bf7b 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -241,6 +241,7 @@
 #define H_GET_HCA_INFO          0x1B8
 #define H_GET_PERF_COUNT        0x1BC
 #define H_MANAGE_TRACE          0x1C0
+#define H_GET_CPU_CHARACTERISTICS 0x1C8
 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4
 #define H_QUERY_INT_STATE       0x1E4
 #define H_POLL_PENDING		0x1D8
@@ -330,6 +331,17 @@
 #define H_SIGNAL_SYS_RESET_ALL_OTHERS		-2
 /* >= 0 values are CPU number */
 
+/* H_GET_CPU_CHARACTERISTICS return values */
+#define H_CPU_CHAR_SPEC_BAR_ORI31	(1ull << 63) // IBM bit 0
+#define H_CPU_CHAR_BCCTRL_SERIALISED	(1ull << 62) // IBM bit 1
+#define H_CPU_CHAR_L1D_FLUSH_ORI30	(1ull << 61) // IBM bit 2
+#define H_CPU_CHAR_L1D_FLUSH_TRIG2	(1ull << 60) // IBM bit 3
+#define H_CPU_CHAR_L1D_THREAD_PRIV	(1ull << 59) // IBM bit 4
+
+#define H_CPU_BEHAV_FAVOUR_SECURITY	(1ull << 63) // IBM bit 0
+#define H_CPU_BEHAV_L1D_FLUSH_PR	(1ull << 62) // IBM bit 1
+#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ull << 61) // IBM bit 2
+
 /* Flag values used in H_REGISTER_PROC_TBL hcall */
 #define PROC_TABLE_OP_MASK	0x18
 #define PROC_TABLE_DEREG	0x10
@@ -436,6 +448,11 @@ static inline unsigned int get_longbusy_msecs(int longbusy_rc)
 	}
 }
 
+struct h_cpu_char_result {
+	u64 character;
+	u64 behaviour;
+};
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_HVCALL_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 04b60af027ae..b8366df50d19 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -231,6 +231,16 @@ struct paca_struct {
 	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 #endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * rfi fallback flush must be in its own cacheline to prevent
+	 * other paca data leaking into the L1d
+	 */
+	u64 exrfi[EX_SIZE] __aligned(0x80);
+	void *rfi_flush_fallback_area;
+	u64 l1d_flush_congruence;
+	u64 l1d_flush_sets;
+#endif
 };
 
 extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 7f01b22fa6cb..55eddf50d149 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -326,4 +326,18 @@ static inline long plapr_signal_sys_reset(long cpu)
 	return plpar_hcall_norets(H_SIGNAL_SYS_RESET, cpu);
 }
 
+static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf);
+	if (rc == H_SUCCESS) {
+		p->character = retbuf[0];
+		p->behaviour = retbuf[1];
+	}
+
+	return rc;
+}
+
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index cf00ec26303a..469b7fdc9be4 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -39,6 +39,19 @@ static inline void pseries_big_endian_exceptions(void) {}
 static inline void pseries_little_endian_exceptions(void) {}
 #endif /* CONFIG_PPC_PSERIES */
 
+void rfi_flush_enable(bool enable);
+
+/* These are bit flags */
+enum l1d_flush_type {
+	L1D_FLUSH_NONE		= 0x1,
+	L1D_FLUSH_FALLBACK	= 0x2,
+	L1D_FLUSH_ORI		= 0x4,
+	L1D_FLUSH_MTTRIG	= 0x8,
+};
+
+void __init setup_rfi_flush(enum l1d_flush_type, bool enable);
+void do_rfi_flush_fixups(enum l1d_flush_type types);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8cfb20e38cfe..748cdc4bb89a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -237,6 +237,11 @@ int main(void)
 	OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp);
 	OFFSET(PACA_IN_MCE, paca_struct, in_mce);
 	OFFSET(PACA_IN_NMI, paca_struct, in_nmi);
+	OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area);
+	OFFSET(PACA_EXRFI, paca_struct, exrfi);
+	OFFSET(PACA_L1D_FLUSH_CONGRUENCE, paca_struct, l1d_flush_congruence);
+	OFFSET(PACA_L1D_FLUSH_SETS, paca_struct, l1d_flush_sets);
+
 #endif
 	OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
 	OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 4a0fd4f40245..8a8a6d7ddcc6 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -37,6 +37,11 @@
 #include <asm/tm.h>
 #include <asm/ppc-opcode.h>
 #include <asm/export.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
 
 /*
  * System calls.
@@ -262,13 +267,23 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
+	ld	r2,GPR2(r1)
+	ld	r1,GPR1(r1)
+	mtlr	r4
+	mtcr	r5
+	mtspr	SPRN_SRR0,r7
+	mtspr	SPRN_SRR1,r8
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+
+	/* exit to kernel */
 1:	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
 	mtlr	r4
 	mtcr	r5
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r8
-	RFI
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 .Lsyscall_error:
@@ -397,8 +412,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12
-
-	rfid
+	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 #endif
 _ASM_NOKPROBE_SYMBOL(system_call_common);
@@ -878,7 +892,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
 	REST_GPR(13, r1)
-1:
+
 	mtspr	SPRN_SRR1,r3
 
 	ld	r2,_CCR(r1)
@@ -891,8 +905,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ld	r3,GPR3(r1)
 	ld	r4,GPR4(r1)
 	ld	r1,GPR1(r1)
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
 
-	rfid
+1:	mtspr	SPRN_SRR1,r3
+
+	ld	r2,_CCR(r1)
+	mtcrf	0xFF,r2
+	ld	r2,_NIP(r1)
+	mtspr	SPRN_SRR0,r2
+
+	ld	r0,GPR0(r1)
+	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r4,GPR4(r1)
+	ld	r1,GPR1(r1)
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 #endif /* CONFIG_PPC_BOOK3E */
@@ -1073,7 +1101,7 @@ __enter_rtas:
 	
 	mtspr	SPRN_SRR0,r5
 	mtspr	SPRN_SRR1,r6
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 rtas_return_loc:
@@ -1098,7 +1126,7 @@ rtas_return_loc:
 
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 _ASM_NOKPROBE_SYMBOL(__enter_rtas)
 _ASM_NOKPROBE_SYMBOL(rtas_return_loc)
@@ -1171,7 +1199,7 @@ _GLOBAL(enter_prom)
 	LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
 	andc	r11,r11,r12
 	mtsrr1	r11
-	rfid
+	RFI_TO_KERNEL
 #endif /* CONFIG_PPC_BOOK3E */
 
 1:	/* Return from OF */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 06598142d755..e9f72abc52b7 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -254,7 +254,7 @@ BEGIN_FTR_SECTION
 	LOAD_HANDLER(r12, machine_check_handle_early)
 1:	mtspr	SPRN_SRR0,r12
 	mtspr	SPRN_SRR1,r11
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 2:
 	/* Stack overflow. Stay on emergency stack and panic.
@@ -443,7 +443,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	li	r3,MSR_ME
 	andc	r10,r10,r3		/* Turn off MSR_ME */
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 2:
 	/*
@@ -461,7 +461,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	 */
 	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
-	rfid
+	RFI_TO_USER_OR_KERNEL
 9:
 	/* Deliver the machine check to host kernel in V mode. */
 	MACHINE_CHECK_HANDLER_WINDUP
@@ -596,6 +596,9 @@ EXC_COMMON_BEGIN(slb_miss_common)
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
 
+	andi.	r9,r11,MSR_PR	// Check for exception from userspace
+	cmpdi	cr4,r9,MSR_PR	// And save the result in CR4 for later
+
 	/*
 	 * Test MSR_RI before calling slb_allocate_realmode, because the
 	 * MSR in r11 gets clobbered. However we still want to allocate
@@ -622,9 +625,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	/* All done -- return from exception. */
 
+	bne	cr4,1f		/* returning to kernel */
+
 .machine	push
 .machine	"power4"
 	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
@@ -638,9 +644,30 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	ld	r11,PACA_EXSLB+EX_R11(r13)
 	ld	r12,PACA_EXSLB+EX_R12(r13)
 	ld	r13,PACA_EXSLB+EX_R13(r13)
-	rfid
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+1:
+.machine	push
+.machine	"power4"
+	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
+	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
+	mtcrf	0x02,r9		/* I/D indication is in cr6 */
+	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
+.machine	pop
+
+	RESTORE_CTR(r9, PACA_EXSLB)
+	RESTORE_PPR_PACA(PACA_EXSLB, r9)
+	mr	r3,r12
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
+
 2:	std     r3,PACA_EXSLB+EX_DAR(r13)
 	mr	r3,r12
 	mfspr	r11,SPRN_SRR0
@@ -649,7 +676,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 8:	std     r3,PACA_EXSLB+EX_DAR(r13)
@@ -660,7 +687,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 EXC_COMMON_BEGIN(unrecov_slb)
@@ -905,7 +932,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	mtspr	SPRN_SRR0,r10 ; 				\
 	ld	r10,PACAKMSR(r13) ;				\
 	mtspr	SPRN_SRR1,r10 ; 				\
-	rfid ; 							\
+	RFI_TO_KERNEL ;						\
 	b	. ;	/* prevent speculative execution */
 
 #define SYSCALL_FASTENDIAN					\
@@ -914,7 +941,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	xori	r12,r12,MSR_LE ;				\
 	mtspr	SPRN_SRR1,r12 ;					\
 	mr	r13,r9 ;					\
-	rfid ;		/* return to userspace */		\
+	RFI_TO_USER ;	/* return to userspace */		\
 	b	. ;	/* prevent speculative execution */
 
 #if defined(CONFIG_RELOCATABLE)
@@ -1299,7 +1326,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
 	ld	r13,PACA_EXGEN+EX_R13(r13)
-	HRFID
+	HRFI_TO_UNKNOWN
 	b	.
 #endif
 
@@ -1403,10 +1430,94 @@ masked_##_H##interrupt:					\
 	ld	r10,PACA_EXGEN+EX_R10(r13);		\
 	ld	r11,PACA_EXGEN+EX_R11(r13);		\
 	/* returns to kernel where r13 must be set up, so don't restore it */ \
-	##_H##rfid;					\
+	##_H##RFI_TO_KERNEL;				\
 	b	.;					\
 	MASKED_DEC_HANDLER(_H)
 
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	std	r12,PACA_EXRFI+EX_R12(r13)
+	std	r8,PACA_EXRFI+EX_R13(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SETS(r13)
+	ld	r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+	addi	r12,r12,8
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+1:	li	r8,0
+	.rept	8 /* 8-way set associative */
+	ldx	r11,r10,r8
+	add	r8,r8,r12
+	xor	r11,r11,r11	// Ensure r11 is 0 even if fallback area is not
+	add	r8,r8,r11	// Add 0, this creates a dependency on the ldx
+	.endr
+	addi	r10,r10,128 /* 128 byte cache line */
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	ld	r12,PACA_EXRFI+EX_R12(r13)
+	ld	r8,PACA_EXRFI+EX_R13(r13)
+	GET_SCRATCH0(r13);
+	rfid
+
+TRAMP_REAL_BEGIN(hrfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	std	r12,PACA_EXRFI+EX_R12(r13)
+	std	r8,PACA_EXRFI+EX_R13(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SETS(r13)
+	ld	r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+	addi	r12,r12,8
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+1:	li	r8,0
+	.rept	8 /* 8-way set associative */
+	ldx	r11,r10,r8
+	add	r8,r8,r12
+	xor	r11,r11,r11	// Ensure r11 is 0 even if fallback area is not
+	add	r8,r8,r11	// Add 0, this creates a dependency on the ldx
+	.endr
+	addi	r10,r10,128 /* 128 byte cache line */
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	ld	r12,PACA_EXRFI+EX_R12(r13)
+	ld	r8,PACA_EXRFI+EX_R13(r13)
+	GET_SCRATCH0(r13);
+	hrfid
+
 /*
  * Real mode exceptions actually use this too, but alternate
  * instruction code patches (which end up in the common .text area)
@@ -1426,7 +1537,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_SRR0, r13
 	GET_SCRATCH0(r13)
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
@@ -1438,7 +1549,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_HSRR0, r13
 	GET_SCRATCH0(r13)
-	hrfid
+	HRFI_TO_KERNEL
 	b	.
 #endif
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index b89c6aac48c9..935059cb9e40 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -784,3 +784,104 @@ static int __init disable_hardlockup_detector(void)
 	return 0;
 }
 early_initcall(disable_hardlockup_detector);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+static enum l1d_flush_type enabled_flush_types;
+static void *l1d_flush_fallback_area;
+static bool no_rfi_flush;
+bool rfi_flush;
+
+static int __init handle_no_rfi_flush(char *p)
+{
+	pr_info("rfi-flush: disabled on command line.");
+	no_rfi_flush = true;
+	return 0;
+}
+early_param("no_rfi_flush", handle_no_rfi_flush);
+
+/*
+ * The RFI flush is not KPTI, but because users will see doco that says to use
+ * nopti we hijack that option here to also disable the RFI flush.
+ */
+static int __init handle_no_pti(char *p)
+{
+	pr_info("rfi-flush: disabling due to 'nopti' on command line.\n");
+	handle_no_rfi_flush(NULL);
+	return 0;
+}
+early_param("nopti", handle_no_pti);
+
+static void do_nothing(void *unused)
+{
+	/*
+	 * We don't need to do the flush explicitly, just enter+exit kernel is
+	 * sufficient, the RFI exit handlers will do the right thing.
+	 */
+}
+
+void rfi_flush_enable(bool enable)
+{
+	if (rfi_flush == enable)
+		return;
+
+	if (enable) {
+		do_rfi_flush_fixups(enabled_flush_types);
+		on_each_cpu(do_nothing, NULL, 1);
+	} else
+		do_rfi_flush_fixups(L1D_FLUSH_NONE);
+
+	rfi_flush = enable;
+}
+
+static void init_fallback_flush(void)
+{
+	u64 l1d_size, limit;
+	int cpu;
+
+	l1d_size = ppc64_caches.l1d.size;
+	limit = min(safe_stack_limit(), ppc64_rma_size);
+
+	/*
+	 * Align to L1d size, and size it at 2x L1d size, to catch possible
+	 * hardware prefetch runoff. We don't have a recipe for load patterns to
+	 * reliably avoid the prefetcher.
+	 */
+	l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
+	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
+
+	for_each_possible_cpu(cpu) {
+		/*
+		 * The fallback flush is currently coded for 8-way
+		 * associativity. Different associativity is possible, but it
+		 * will be treated as 8-way and may not evict the lines as
+		 * effectively.
+		 *
+		 * 128 byte lines are mandatory.
+		 */
+		u64 c = l1d_size / 8;
+
+		paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
+		paca[cpu].l1d_flush_congruence = c;
+		paca[cpu].l1d_flush_sets = c / 128;
+	}
+}
+
+void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
+{
+	if (types & L1D_FLUSH_FALLBACK) {
+		pr_info("rfi-flush: Using fallback displacement flush\n");
+		init_fallback_flush();
+	}
+
+	if (types & L1D_FLUSH_ORI)
+		pr_info("rfi-flush: Using ori type flush\n");
+
+	if (types & L1D_FLUSH_MTTRIG)
+		pr_info("rfi-flush: Using mttrig type flush\n");
+
+	enabled_flush_types = types;
+
+	if (!no_rfi_flush)
+		rfi_flush_enable(enable);
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 0494e1566ee2..307843d23682 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -132,6 +132,15 @@ SECTIONS
 	/* Read-only data */
 	RO_DATA(PAGE_SIZE)
 
+#ifdef CONFIG_PPC64
+	. = ALIGN(8);
+	__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
+		__start___rfi_flush_fixup = .;
+		*(__rfi_flush_fixup)
+		__stop___rfi_flush_fixup = .;
+	}
+#endif
+
 	EXCEPTION_TABLE(0)
 
 	NOTES :kernel :notes
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 42639fba89e8..c85ac5c83bd4 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -78,7 +78,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mtmsrd	r0,1		/* clear RI in MSR */
 	mtsrr0	r5
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 kvmppc_call_hv_entry:
 	ld	r4, HSTATE_KVM_VCPU(r13)
@@ -187,7 +187,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtmsrd	r6, 1			/* Clear RI in MSR */
 	mtsrr0	r8
 	mtsrr1	r7
-	RFI
+	RFI_TO_KERNEL
 
 	/* Virtual-mode return */
 .Lvirt_return:
@@ -1131,8 +1131,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
-
-	hrfid
+	HRFI_TO_GUEST
 	b	.
 
 secondary_too_late:
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 42a4b237df5f..34a5adeff084 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -46,6 +46,9 @@
 
 #define FUNC(name)		name
 
+#define RFI_TO_KERNEL	RFI
+#define RFI_TO_GUEST	RFI
+
 .macro INTERRUPT_TRAMPOLINE intno
 
 .global kvmppc_trampoline_\intno
@@ -141,7 +144,7 @@ kvmppc_handler_skip_ins:
 	GET_SCRATCH0(r13)
 
 	/* And get back into the code */
-	RFI
+	RFI_TO_KERNEL
 #endif
 
 /*
@@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline)
 	ori	r5, r5, MSR_EE
 	mtsrr0	r7
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 #include "book3s_segment.S"
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 2a2b96d53999..93a180ceefad 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -156,7 +156,7 @@ no_dcbz32_on:
 	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r3, (SVCPU_R3)(r3)
 
-	RFI
+	RFI_TO_GUEST
 kvmppc_handler_trampoline_enter_end:
 
 
@@ -407,5 +407,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	cmpwi	r12, BOOK3S_INTERRUPT_DOORBELL
 	beqa	BOOK3S_INTERRUPT_DOORBELL
 
-	RFI
+	RFI_TO_KERNEL
 kvmppc_handler_trampoline_exit_end:
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 41cf5ae273cf..a95ea007d654 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -116,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_rfi_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___rfi_flush_fixup),
+	end = PTRRELOC(&__stop___rfi_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	if (types & L1D_FLUSH_FALLBACK)
+		/* b .+16 to fallback flush */
+		instrs[0] = 0x48000010;
+
+	i = 0;
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i);
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 {
 	long *start, *end;
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index bfe2aa702973..7966a314d93a 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -36,13 +36,62 @@
 #include <asm/opal.h>
 #include <asm/kexec.h>
 #include <asm/smp.h>
+#include <asm/setup.h>
 
 #include "powernv.h"
 
+static void pnv_setup_rfi_flush(void)
+{
+	struct device_node *np, *fw_features;
+	enum l1d_flush_type type;
+	int enable;
+
+	/* Default to fallback in case fw-features are not available */
+	type = L1D_FLUSH_FALLBACK;
+	enable = 1;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	fw_features = of_get_child_by_name(np, "fw-features");
+	of_node_put(np);
+
+	if (fw_features) {
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_MTTRIG;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_ORI;
+
+		of_node_put(np);
+
+		/* Enable unless firmware says NOT to */
+		enable = 2;
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+		of_node_put(fw_features);
+	}
+
+	setup_rfi_flush(type, enable > 0);
+}
+
 static void __init pnv_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
+	pnv_setup_rfi_flush();
+
 	/* Initialize SMP */
 	pnv_smp_init();
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index a8531e012658..ae4f596273b5 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -459,6 +459,39 @@ static void __init find_and_init_phbs(void)
 	of_pci_check_probe_only();
 }
 
+static void pseries_setup_rfi_flush(void)
+{
+	struct h_cpu_char_result result;
+	enum l1d_flush_type types;
+	bool enable;
+	long rc;
+
+	/* Enable by default */
+	enable = true;
+
+	rc = plpar_get_cpu_characteristics(&result);
+	if (rc == H_SUCCESS) {
+		types = L1D_FLUSH_NONE;
+
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2)
+			types |= L1D_FLUSH_MTTRIG;
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30)
+			types |= L1D_FLUSH_ORI;
+
+		/* Use fallback if nothing set in hcall */
+		if (types == L1D_FLUSH_NONE)
+			types = L1D_FLUSH_FALLBACK;
+
+		if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
+			enable = false;
+	} else {
+		/* Default to fallback if case hcall is not available */
+		types = L1D_FLUSH_FALLBACK;
+	}
+
+	setup_rfi_flush(types, enable);
+}
+
 static void __init pSeries_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
@@ -476,6 +509,8 @@ static void __init pSeries_setup_arch(void)
 
 	fwnmi_init();
 
+	pseries_setup_rfi_flush();
+
 	/* By default, only probe PCI (can be overridden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index a1f28a54f23a..60c4c342316c 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -244,6 +244,17 @@ ENTRY(__switch_to_asm)
 	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popl	%esi
 	popl	%edi
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f5fda5f26e34..be6b66464f6a 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -487,6 +487,17 @@ ENTRY(__switch_to_asm)
 	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popq	%r15
 	popq	%r14
@@ -1247,7 +1258,7 @@ idtentry async_page_fault	do_async_page_fault	has_error_code=1
 #endif
 
 #ifdef CONFIG_X86_MCE
-idtentry machine_check					has_error_code=0	paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check		do_mce			has_error_code=0	paranoid=1
 #endif
 
 /*
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f275447862f4..25b9375c1484 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -206,11 +206,11 @@
 #define X86_FEATURE_RETPOLINE		( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* Fill RSB on context switches */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -245,6 +245,7 @@
 #define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT		( 9*32+25) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 6a77c63540f7..e7d96c0766fe 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data);
 
 void __init sme_early_init(void);
 
-void __init sme_encrypt_kernel(void);
+void __init sme_encrypt_kernel(struct boot_params *bp);
 void __init sme_enable(struct boot_params *bp);
 
 /* Architecture __weak replacement functions */
@@ -61,7 +61,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
 
 static inline void __init sme_early_init(void) { }
 
-static inline void __init sme_encrypt_kernel(void) { }
+static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
 static inline void __init sme_enable(struct boot_params *bp) { }
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 402a11c803c3..4ad41087ce0e 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -11,7 +11,7 @@
  * Fill the CPU return stack buffer.
  *
  * Each entry in the RSB, if used for a speculative 'ret', contains an
- * infinite 'pause; jmp' loop to capture speculative execution.
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
  *
  * This is required in various cases for retpoline and IBRS-based
  * mitigations for the Spectre variant 2 vulnerability. Sometimes to
@@ -38,11 +38,13 @@
 	call	772f;				\
 773:	/* speculation trap */			\
 	pause;					\
+	lfence;					\
 	jmp	773b;				\
 772:						\
 	call	774f;				\
 775:	/* speculation trap */			\
 	pause;					\
+	lfence;					\
 	jmp	775b;				\
 774:						\
 	dec	reg;				\
@@ -73,6 +75,7 @@
 	call	.Ldo_rop_\@
 .Lspec_trap_\@:
 	pause
+	lfence
 	jmp	.Lspec_trap_\@
 .Ldo_rop_\@:
 	mov	\reg, (%_ASM_SP)
@@ -165,6 +168,7 @@
 	"       .align 16\n"					\
 	"901:	call   903f;\n"					\
 	"902:	pause;\n"					\
+	"    	lfence;\n"					\
 	"       jmp    902b;\n"					\
 	"       .align 16\n"					\
 	"903:	addl   $4, %%esp;\n"				\
@@ -190,6 +194,9 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS,
 };
 
+extern char __indirect_thunk_start[];
+extern char __indirect_thunk_end[];
+
 /*
  * On VMEXIT we must ensure that no RSB predictions learned in the guest
  * can be followed in the host, by overwriting the RSB completely. Both
@@ -199,16 +206,17 @@ enum spectre_v2_mitigation {
 static inline void vmexit_fill_RSB(void)
 {
 #ifdef CONFIG_RETPOLINE
-	unsigned long loops = RSB_CLEAR_LOOPS / 2;
+	unsigned long loops;
 
 	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
 		      ALTERNATIVE("jmp 910f",
 				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
 				  X86_FEATURE_RETPOLINE)
 		      "910:"
-		      : "=&r" (loops), ASM_CALL_CONSTRAINT
-		      : "r" (loops) : "memory" );
+		      : "=r" (loops), ASM_CALL_CONSTRAINT
+		      : : "memory" );
 #endif
 }
+
 #endif /* __ASSEMBLY__ */
 #endif /* __NOSPEC_BRANCH_H__ */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 31051f35cbb7..3de69330e6c5 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -88,6 +88,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif
+dotraplinkage void do_mce(struct pt_regs *, long);
 
 static inline int get_si_code(unsigned long condition)
 {
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 88c214e75a6b..2ce1c708b8ee 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -369,8 +369,11 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irq_data->hwirq = virq + i;
 		err = assign_irq_vector_policy(virq + i, node, data, info,
 					       irq_data);
-		if (err)
+		if (err) {
+			irq_data->chip_data = NULL;
+			free_apic_chip_data(data);
 			goto error;
+		}
 		/*
 		 * If the apic destination mode is physical, then the
 		 * effective affinity is restricted to a single target
@@ -383,7 +386,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	return 0;
 
 error:
-	x86_vector_free_irqs(domain, virq, i + 1);
+	x86_vector_free_irqs(domain, virq, i);
 	return err;
 }
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index e4dc26185aa7..390b3dc3d438 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -23,6 +23,7 @@
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
+#include <asm/intel-family.h>
 
 static void __init spectre_v2_select_mitigation(void);
 
@@ -155,6 +156,23 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	return SPECTRE_V2_CMD_NONE;
 }
 
+/* Check for Skylake-like CPUs (for RSB handling) */
+static bool __init is_skylake_era(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6) {
+		switch (boot_cpu_data.x86_model) {
+		case INTEL_FAM6_SKYLAKE_MOBILE:
+		case INTEL_FAM6_SKYLAKE_DESKTOP:
+		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_KABYLAKE_MOBILE:
+		case INTEL_FAM6_KABYLAKE_DESKTOP:
+			return true;
+		}
+	}
+	return false;
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -213,6 +231,24 @@ static void __init spectre_v2_select_mitigation(void)
 
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
+
+	/*
+	 * If neither SMEP or KPTI are available, there is a risk of
+	 * hitting userspace addresses in the RSB after a context switch
+	 * from a shallow call stack to a deeper one. To prevent this fill
+	 * the entire RSB, even when using IBRS.
+	 *
+	 * Skylake era CPUs have a separate issue with *underflow* of the
+	 * RSB, when they will predict 'ret' targets from the generic BTB.
+	 * The proper mitigation for this is IBRS. If IBRS is not supported
+	 * or deactivated in favour of retpolines the RSB fill on context
+	 * switch is required.
+	 */
+	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
+	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+		pr_info("Filling RSB on context switch\n");
+	}
 }
 
 #undef pr_fmt
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 88dcf8479013..99442370de40 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -525,10 +525,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		 */
 		if (static_branch_unlikely(&rdt_mon_enable_key))
 			rmdir_mondata_subdir_allrdtgrp(r, d->id);
-		kfree(d->ctrl_val);
-		kfree(d->rmid_busy_llc);
-		kfree(d->mbm_total);
-		kfree(d->mbm_local);
 		list_del(&d->list);
 		if (is_mbm_enabled())
 			cancel_delayed_work(&d->mbm_over);
@@ -545,6 +541,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 			cancel_delayed_work(&d->cqm_limbo);
 		}
 
+		kfree(d->ctrl_val);
+		kfree(d->rmid_busy_llc);
+		kfree(d->mbm_total);
+		kfree(d->mbm_local);
 		kfree(d);
 		return;
 	}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3b413065c613..a9e898b71208 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1788,6 +1788,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 void (*machine_check_vector)(struct pt_regs *, long error_code) =
 						unexpected_machine_check;
 
+dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+{
+	machine_check_vector(regs, error_code);
+}
+
 /*
  * Called for each booted CPU to set up machine checks.
  * Must be called with preempt off:
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 05459ad3db46..d0e69769abfd 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -21,7 +21,6 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
-	{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
 	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 6a5d757b9cfd..7ba5d819ebe3 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	p = fixup_pointer(&phys_base, physaddr);
 	*p += load_delta - sme_get_me_mask();
 
-	/* Encrypt the kernel (if SME is active) */
-	sme_encrypt_kernel();
+	/* Encrypt the kernel and related (if SME is active) */
+	sme_encrypt_kernel(bp);
 
 	/*
 	 * Return the SME encryption mask (if SME is active) to be used as a
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 014cb2fc47ff..236917bac5f2 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -56,7 +56,7 @@ struct idt_data {
  * Early traps running on the DEFAULT_STACK because the other interrupt
  * stacks work only after cpu_init().
  */
-static const __initdata struct idt_data early_idts[] = {
+static const __initconst struct idt_data early_idts[] = {
 	INTG(X86_TRAP_DB,		debug),
 	SYSG(X86_TRAP_BP,		int3),
 #ifdef CONFIG_X86_32
@@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = {
  * the traps which use them are reinitialized with IST after cpu_init() has
  * set up TSS.
  */
-static const __initdata struct idt_data def_idts[] = {
+static const __initconst struct idt_data def_idts[] = {
 	INTG(X86_TRAP_DE,		divide_error),
 	INTG(X86_TRAP_NMI,		nmi),
 	INTG(X86_TRAP_BR,		bounds),
@@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = {
 /*
  * The APIC and SMP idt entries
  */
-static const __initdata struct idt_data apic_idts[] = {
+static const __initconst struct idt_data apic_idts[] = {
 #ifdef CONFIG_SMP
 	INTG(RESCHEDULE_VECTOR,		reschedule_interrupt),
 	INTG(CALL_FUNCTION_VECTOR,	call_function_interrupt),
@@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = {
  * Early traps running on the DEFAULT_STACK because the other interrupt
  * stacks work only after cpu_init().
  */
-static const __initdata struct idt_data early_pf_idts[] = {
+static const __initconst struct idt_data early_pf_idts[] = {
 	INTG(X86_TRAP_PF,		page_fault),
 };
 
@@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = {
  * Override for the debug_idt. Same as the default, but with interrupt
  * stack set to DEFAULT_STACK (0). Required for NMI trap handling.
  */
-static const __initdata struct idt_data dbg_idts[] = {
+static const __initconst struct idt_data dbg_idts[] = {
 	INTG(X86_TRAP_DB,	debug),
 	INTG(X86_TRAP_BP,	int3),
 };
@@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
  * The exceptions which use Interrupt stacks. They are setup after
  * cpu_init() when the TSS has been initialized.
  */
-static const __initdata struct idt_data ist_idts[] = {
+static const __initconst struct idt_data ist_idts[] = {
 	ISTG(X86_TRAP_DB,	debug,		DEBUG_STACK),
 	ISTG(X86_TRAP_NMI,	nmi,		NMI_STACK),
 	SISTG(X86_TRAP_BP,	int3,		DEBUG_STACK),
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 4f98aad38237..3668f28cf5fc 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -40,6 +40,7 @@
 #include <asm/debugreg.h>
 #include <asm/set_memory.h>
 #include <asm/sections.h>
+#include <asm/nospec-branch.h>
 
 #include "common.h"
 
@@ -205,7 +206,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
 }
 
 /* Check whether insn is indirect jump */
-static int insn_is_indirect_jump(struct insn *insn)
+static int __insn_is_indirect_jump(struct insn *insn)
 {
 	return ((insn->opcode.bytes[0] == 0xff &&
 		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
@@ -239,6 +240,26 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
 	return (start <= target && target <= start + len);
 }
 
+static int insn_is_indirect_jump(struct insn *insn)
+{
+	int ret = __insn_is_indirect_jump(insn);
+
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * Jump to x86_indirect_thunk_* is treated as an indirect jump.
+	 * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with
+	 * older gcc may use indirect jump. So we add this check instead of
+	 * replace indirect-jump check.
+	 */
+	if (!ret)
+		ret = insn_jump_into_range(insn,
+				(unsigned long)__indirect_thunk_start,
+				(unsigned long)__indirect_thunk_end -
+				(unsigned long)__indirect_thunk_start);
+#endif
+	return ret;
+}
+
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3cb2486c47e4..8bd1d8292cf7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -380,19 +380,24 @@ void stop_this_cpu(void *dummy)
 	disable_local_APIC();
 	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 
+	/*
+	 * Use wbinvd on processors that support SME. This provides support
+	 * for performing a successful kexec when going from SME inactive
+	 * to SME active (or vice-versa). The cache must be cleared so that
+	 * if there are entries with the same physical address, both with and
+	 * without the encryption bit, they don't race each other when flushed
+	 * and potentially end up with the wrong entry being committed to
+	 * memory.
+	 */
+	if (boot_cpu_has(X86_FEATURE_SME))
+		native_wbinvd();
 	for (;;) {
 		/*
-		 * Use wbinvd followed by hlt to stop the processor. This
-		 * provides support for kexec on a processor that supports
-		 * SME. With kexec, going from SME inactive to SME active
-		 * requires clearing cache entries so that addresses without
-		 * the encryption bit set don't corrupt the same physical
-		 * address that has the encryption bit set when caches are
-		 * flushed. To achieve this a wbinvd is performed followed by
-		 * a hlt. Even if the processor is not in the kexec/SME
-		 * scenario this only adds a wbinvd to a halting processor.
+		 * Use native_halt() so that memory contents don't change
+		 * (stack usage and variables) after possibly issuing the
+		 * native_wbinvd() above.
 		 */
-		asm volatile("wbinvd; hlt" : : : "memory");
+		native_halt();
 	}
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0957dd73d127..e84cb4c75cd0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -376,14 +376,6 @@ static void __init reserve_initrd(void)
 	    !ramdisk_image || !ramdisk_size)
 		return;		/* No initrd provided by bootloader */
 
-	/*
-	 * If SME is active, this memory will be marked encrypted by the
-	 * kernel when it is accessed (including relocation). However, the
-	 * ramdisk image was loaded decrypted by the bootloader, so make
-	 * sure that it is encrypted before accessing it.
-	 */
-	sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);
-
 	initrd_start = 0;
 
 	mapped_size = memblock_mem_size(max_pfn_mapped);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ad2b925a808e..47506567435e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -602,7 +602,6 @@ unsigned long native_calibrate_tsc(void)
 		case INTEL_FAM6_KABYLAKE_DESKTOP:
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
-		case INTEL_FAM6_SKYLAKE_X:
 		case INTEL_FAM6_ATOM_DENVERTON:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
@@ -612,6 +611,8 @@ unsigned long native_calibrate_tsc(void)
 		}
 	}
 
+	if (crystal_khz == 0)
+		return 0;
 	/*
 	 * TSC frequency determined by CPUID is a "hardware reported"
 	 * frequency and is the most accurate one so far we have. This
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 1e413a9326aa..9b138a06c1a4 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -124,6 +124,12 @@ SECTIONS
 		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
 #endif
 
+#ifdef CONFIG_RETPOLINE
+		__indirect_thunk_start = .;
+		*(.text.__x86.indirect_thunk)
+		__indirect_thunk_end = .;
+#endif
+
 		/* End of text section */
 		_etext = .;
 	} :text = 0x9090
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index cb45c6cb465f..dfb2ba91b670 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -9,7 +9,7 @@
 #include <asm/nospec-branch.h>
 
 .macro THUNK reg
-	.section .text.__x86.indirect_thunk.\reg
+	.section .text.__x86.indirect_thunk
 
 ENTRY(__x86_indirect_thunk_\reg)
 	CFI_STARTPROC
@@ -25,7 +25,8 @@ ENDPROC(__x86_indirect_thunk_\reg)
  * than one per register with the correct names. So we do it
  * the simple and nasty way...
  */
-#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg)
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
 #define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
 
 GENERATE_THUNK(_ASM_AX)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3109ba6c6ede..b264b590eeec 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -173,14 +173,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
  * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
  *	     faulted on a pte with its pkey=4.
  */
-static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
+static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info,
+		u32 *pkey)
 {
 	/* This is effectively an #ifdef */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
 		return;
 
 	/* Fault not from Protection Keys: nothing to do */
-	if (si_code != SEGV_PKUERR)
+	if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV))
 		return;
 	/*
 	 * force_sig_info_fault() is called from a number of
@@ -219,7 +220,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 		lsb = PAGE_SHIFT;
 	info.si_addr_lsb = lsb;
 
-	fill_sig_info_pkey(si_code, &info, pkey);
+	fill_sig_info_pkey(si_signo, si_code, &info, pkey);
 
 	force_sig_info(si_signo, &info, tsk);
 }
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 47388f0c0e59..af6f2f9c6a26 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -21,10 +21,14 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES];
 
 static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
 
-static __init void *early_alloc(size_t size, int nid)
+static __init void *early_alloc(size_t size, int nid, bool panic)
 {
-	return memblock_virt_alloc_try_nid_nopanic(size, size,
-		__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	if (panic)
+		return memblock_virt_alloc_try_nid(size, size,
+			__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
+	else
+		return memblock_virt_alloc_try_nid_nopanic(size, size,
+			__pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid);
 }
 
 static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
@@ -38,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 		if (boot_cpu_has(X86_FEATURE_PSE) &&
 		    ((end - addr) == PMD_SIZE) &&
 		    IS_ALIGNED(addr, PMD_SIZE)) {
-			p = early_alloc(PMD_SIZE, nid);
+			p = early_alloc(PMD_SIZE, nid, false);
 			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
 				return;
 			else if (p)
 				memblock_free(__pa(p), PMD_SIZE);
 		}
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pmd_populate_kernel(&init_mm, pmd, p);
 	}
 
@@ -57,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 		if (!pte_none(*pte))
 			continue;
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -75,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
 		if (boot_cpu_has(X86_FEATURE_GBPAGES) &&
 		    ((end - addr) == PUD_SIZE) &&
 		    IS_ALIGNED(addr, PUD_SIZE)) {
-			p = early_alloc(PUD_SIZE, nid);
+			p = early_alloc(PUD_SIZE, nid, false);
 			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
 				return;
 			else if (p)
 				memblock_free(__pa(p), PUD_SIZE);
 		}
 
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pud_populate(&init_mm, pud, p);
 	}
 
@@ -101,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
 	unsigned long next;
 
 	if (p4d_none(*p4d)) {
-		void *p = early_alloc(PAGE_SIZE, nid);
+		void *p = early_alloc(PAGE_SIZE, nid, true);
 
 		p4d_populate(&init_mm, p4d, p);
 	}
@@ -122,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr,
 	unsigned long next;
 
 	if (pgd_none(*pgd)) {
-		p = early_alloc(PAGE_SIZE, nid);
+		p = early_alloc(PAGE_SIZE, nid, true);
 		pgd_populate(&init_mm, pgd, p);
 	}
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 0286327e65fa..48c03c74c7f4 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -213,37 +213,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size)
 	set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT);
 }
 
-static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start,
-				 unsigned long end)
+struct sme_populate_pgd_data {
+	void	*pgtable_area;
+	pgd_t	*pgd;
+
+	pmdval_t pmd_flags;
+	pteval_t pte_flags;
+	unsigned long paddr;
+
+	unsigned long vaddr;
+	unsigned long vaddr_end;
+};
+
+static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
 {
 	unsigned long pgd_start, pgd_end, pgd_size;
 	pgd_t *pgd_p;
 
-	pgd_start = start & PGDIR_MASK;
-	pgd_end = end & PGDIR_MASK;
+	pgd_start = ppd->vaddr & PGDIR_MASK;
+	pgd_end = ppd->vaddr_end & PGDIR_MASK;
 
-	pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1);
-	pgd_size *= sizeof(pgd_t);
+	pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t);
 
-	pgd_p = pgd_base + pgd_index(start);
+	pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
 
 	memset(pgd_p, 0, pgd_size);
 }
 
-#define PGD_FLAGS	_KERNPG_TABLE_NOENC
-#define P4D_FLAGS	_KERNPG_TABLE_NOENC
-#define PUD_FLAGS	_KERNPG_TABLE_NOENC
-#define PMD_FLAGS	(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+#define PGD_FLAGS		_KERNPG_TABLE_NOENC
+#define P4D_FLAGS		_KERNPG_TABLE_NOENC
+#define PUD_FLAGS		_KERNPG_TABLE_NOENC
+#define PMD_FLAGS		_KERNPG_TABLE_NOENC
+
+#define PMD_FLAGS_LARGE		(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+
+#define PMD_FLAGS_DEC		PMD_FLAGS_LARGE
+#define PMD_FLAGS_DEC_WP	((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+				 (_PAGE_PAT | _PAGE_PWT))
+
+#define PMD_FLAGS_ENC		(PMD_FLAGS_LARGE | _PAGE_ENC)
+
+#define PTE_FLAGS		(__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL)
+
+#define PTE_FLAGS_DEC		PTE_FLAGS
+#define PTE_FLAGS_DEC_WP	((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+				 (_PAGE_PAT | _PAGE_PWT))
+
+#define PTE_FLAGS_ENC		(PTE_FLAGS | _PAGE_ENC)
 
-static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
-				     unsigned long vaddr, pmdval_t pmd_val)
+static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
 {
 	pgd_t *pgd_p;
 	p4d_t *p4d_p;
 	pud_t *pud_p;
 	pmd_t *pmd_p;
 
-	pgd_p = pgd_base + pgd_index(vaddr);
+	pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
 	if (native_pgd_val(*pgd_p)) {
 		if (IS_ENABLED(CONFIG_X86_5LEVEL))
 			p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
@@ -253,15 +278,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
 		pgd_t pgd;
 
 		if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-			p4d_p = pgtable_area;
+			p4d_p = ppd->pgtable_area;
 			memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D);
-			pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
+			ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
 
 			pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS);
 		} else {
-			pud_p = pgtable_area;
+			pud_p = ppd->pgtable_area;
 			memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
-			pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+			ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
 
 			pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS);
 		}
@@ -269,58 +294,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
 	}
 
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
-		p4d_p += p4d_index(vaddr);
+		p4d_p += p4d_index(ppd->vaddr);
 		if (native_p4d_val(*p4d_p)) {
 			pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK);
 		} else {
 			p4d_t p4d;
 
-			pud_p = pgtable_area;
+			pud_p = ppd->pgtable_area;
 			memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
-			pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+			ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
 
 			p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS);
 			native_set_p4d(p4d_p, p4d);
 		}
 	}
 
-	pud_p += pud_index(vaddr);
+	pud_p += pud_index(ppd->vaddr);
 	if (native_pud_val(*pud_p)) {
 		if (native_pud_val(*pud_p) & _PAGE_PSE)
-			goto out;
+			return NULL;
 
 		pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK);
 	} else {
 		pud_t pud;
 
-		pmd_p = pgtable_area;
+		pmd_p = ppd->pgtable_area;
 		memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
-		pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
+		ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
 
 		pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS);
 		native_set_pud(pud_p, pud);
 	}
 
-	pmd_p += pmd_index(vaddr);
+	return pmd_p;
+}
+
+static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+{
+	pmd_t *pmd_p;
+
+	pmd_p = sme_prepare_pgd(ppd);
+	if (!pmd_p)
+		return;
+
+	pmd_p += pmd_index(ppd->vaddr);
 	if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE))
-		native_set_pmd(pmd_p, native_make_pmd(pmd_val));
+		native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags));
+}
+
+static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+{
+	pmd_t *pmd_p;
+	pte_t *pte_p;
+
+	pmd_p = sme_prepare_pgd(ppd);
+	if (!pmd_p)
+		return;
+
+	pmd_p += pmd_index(ppd->vaddr);
+	if (native_pmd_val(*pmd_p)) {
+		if (native_pmd_val(*pmd_p) & _PAGE_PSE)
+			return;
+
+		pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK);
+	} else {
+		pmd_t pmd;
+
+		pte_p = ppd->pgtable_area;
+		memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE);
+		ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE;
+
+		pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS);
+		native_set_pmd(pmd_p, pmd);
+	}
 
-out:
-	return pgtable_area;
+	pte_p += pte_index(ppd->vaddr);
+	if (!native_pte_val(*pte_p))
+		native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags));
+}
+
+static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+{
+	while (ppd->vaddr < ppd->vaddr_end) {
+		sme_populate_pgd_large(ppd);
+
+		ppd->vaddr += PMD_PAGE_SIZE;
+		ppd->paddr += PMD_PAGE_SIZE;
+	}
+}
+
+static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+{
+	while (ppd->vaddr < ppd->vaddr_end) {
+		sme_populate_pgd(ppd);
+
+		ppd->vaddr += PAGE_SIZE;
+		ppd->paddr += PAGE_SIZE;
+	}
+}
+
+static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+				   pmdval_t pmd_flags, pteval_t pte_flags)
+{
+	unsigned long vaddr_end;
+
+	ppd->pmd_flags = pmd_flags;
+	ppd->pte_flags = pte_flags;
+
+	/* Save original end value since we modify the struct value */
+	vaddr_end = ppd->vaddr_end;
+
+	/* If start is not 2MB aligned, create PTE entries */
+	ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
+	__sme_map_range_pte(ppd);
+
+	/* Create PMD entries */
+	ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
+	__sme_map_range_pmd(ppd);
+
+	/* If end is not 2MB aligned, create PTE entries */
+	ppd->vaddr_end = vaddr_end;
+	__sme_map_range_pte(ppd);
+}
+
+static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+{
+	__sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
+}
+
+static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+{
+	__sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
+}
+
+static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+{
+	__sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
 }
 
 static unsigned long __init sme_pgtable_calc(unsigned long len)
 {
-	unsigned long p4d_size, pud_size, pmd_size;
+	unsigned long p4d_size, pud_size, pmd_size, pte_size;
 	unsigned long total;
 
 	/*
 	 * Perform a relatively simplistic calculation of the pagetable
-	 * entries that are needed. That mappings will be covered by 2MB
-	 * PMD entries so we can conservatively calculate the required
+	 * entries that are needed. Those mappings will be covered mostly
+	 * by 2MB PMD entries so we can conservatively calculate the required
 	 * number of P4D, PUD and PMD structures needed to perform the
-	 * mappings. Incrementing the count for each covers the case where
-	 * the addresses cross entries.
+	 * mappings.  For mappings that are not 2MB aligned, PTE mappings
+	 * would be needed for the start and end portion of the address range
+	 * that fall outside of the 2MB alignment.  This results in, at most,
+	 * two extra pages to hold PTE entries for each range that is mapped.
+	 * Incrementing the count for each covers the case where the addresses
+	 * cross entries.
 	 */
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
 		p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
@@ -334,8 +461,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
 	}
 	pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1;
 	pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;
+	pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE;
 
-	total = p4d_size + pud_size + pmd_size;
+	total = p4d_size + pud_size + pmd_size + pte_size;
 
 	/*
 	 * Now calculate the added pagetable structures needed to populate
@@ -359,29 +487,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
 	return total;
 }
 
-void __init sme_encrypt_kernel(void)
+void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp)
 {
 	unsigned long workarea_start, workarea_end, workarea_len;
 	unsigned long execute_start, execute_end, execute_len;
 	unsigned long kernel_start, kernel_end, kernel_len;
+	unsigned long initrd_start, initrd_end, initrd_len;
+	struct sme_populate_pgd_data ppd;
 	unsigned long pgtable_area_len;
-	unsigned long paddr, pmd_flags;
 	unsigned long decrypted_base;
-	void *pgtable_area;
-	pgd_t *pgd;
 
 	if (!sme_active())
 		return;
 
 	/*
-	 * Prepare for encrypting the kernel by building new pagetables with
-	 * the necessary attributes needed to encrypt the kernel in place.
+	 * Prepare for encrypting the kernel and initrd by building new
+	 * pagetables with the necessary attributes needed to encrypt the
+	 * kernel in place.
 	 *
 	 *   One range of virtual addresses will map the memory occupied
-	 *   by the kernel as encrypted.
+	 *   by the kernel and initrd as encrypted.
 	 *
 	 *   Another range of virtual addresses will map the memory occupied
-	 *   by the kernel as decrypted and write-protected.
+	 *   by the kernel and initrd as decrypted and write-protected.
 	 *
 	 *     The use of write-protect attribute will prevent any of the
 	 *     memory from being cached.
@@ -392,6 +520,20 @@ void __init sme_encrypt_kernel(void)
 	kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
 	kernel_len = kernel_end - kernel_start;
 
+	initrd_start = 0;
+	initrd_end = 0;
+	initrd_len = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
+	initrd_len = (unsigned long)bp->hdr.ramdisk_size |
+		     ((unsigned long)bp->ext_ramdisk_size << 32);
+	if (initrd_len) {
+		initrd_start = (unsigned long)bp->hdr.ramdisk_image |
+			       ((unsigned long)bp->ext_ramdisk_image << 32);
+		initrd_end = PAGE_ALIGN(initrd_start + initrd_len);
+		initrd_len = initrd_end - initrd_start;
+	}
+#endif
+
 	/* Set the encryption workarea to be immediately after the kernel */
 	workarea_start = kernel_end;
 
@@ -414,16 +556,21 @@ void __init sme_encrypt_kernel(void)
 	 */
 	pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD;
 	pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2;
+	if (initrd_len)
+		pgtable_area_len += sme_pgtable_calc(initrd_len) * 2;
 
 	/* PUDs and PMDs needed in the current pagetables for the workarea */
 	pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len);
 
 	/*
 	 * The total workarea includes the executable encryption area and
-	 * the pagetable area.
+	 * the pagetable area. The start of the workarea is already 2MB
+	 * aligned, align the end of the workarea on a 2MB boundary so that
+	 * we don't try to create/allocate PTE entries from the workarea
+	 * before it is mapped.
 	 */
 	workarea_len = execute_len + pgtable_area_len;
-	workarea_end = workarea_start + workarea_len;
+	workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);
 
 	/*
 	 * Set the address to the start of where newly created pagetable
@@ -432,45 +579,30 @@ void __init sme_encrypt_kernel(void)
 	 * pagetables and when the new encrypted and decrypted kernel
 	 * mappings are populated.
 	 */
-	pgtable_area = (void *)execute_end;
+	ppd.pgtable_area = (void *)execute_end;
 
 	/*
 	 * Make sure the current pagetable structure has entries for
 	 * addressing the workarea.
 	 */
-	pgd = (pgd_t *)native_read_cr3_pa();
-	paddr = workarea_start;
-	while (paddr < workarea_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr,
-						paddr + PMD_FLAGS);
-
-		paddr += PMD_PAGE_SIZE;
-	}
+	ppd.pgd = (pgd_t *)native_read_cr3_pa();
+	ppd.paddr = workarea_start;
+	ppd.vaddr = workarea_start;
+	ppd.vaddr_end = workarea_end;
+	sme_map_range_decrypted(&ppd);
 
 	/* Flush the TLB - no globals so cr3 is enough */
 	native_write_cr3(__native_read_cr3());
 
 	/*
 	 * A new pagetable structure is being built to allow for the kernel
-	 * to be encrypted. It starts with an empty PGD that will then be
-	 * populated with new PUDs and PMDs as the encrypted and decrypted
-	 * kernel mappings are created.
+	 * and initrd to be encrypted. It starts with an empty PGD that will
+	 * then be populated with new PUDs and PMDs as the encrypted and
+	 * decrypted kernel mappings are created.
 	 */
-	pgd = pgtable_area;
-	memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD);
-	pgtable_area += sizeof(*pgd) * PTRS_PER_PGD;
-
-	/* Add encrypted kernel (identity) mappings */
-	pmd_flags = PMD_FLAGS | _PAGE_ENC;
-	paddr = kernel_start;
-	while (paddr < kernel_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr,
-						paddr + pmd_flags);
-
-		paddr += PMD_PAGE_SIZE;
-	}
+	ppd.pgd = ppd.pgtable_area;
+	memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD);
+	ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD;
 
 	/*
 	 * A different PGD index/entry must be used to get different
@@ -479,47 +611,79 @@ void __init sme_encrypt_kernel(void)
 	 * the base of the mapping.
 	 */
 	decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1);
+	if (initrd_len) {
+		unsigned long check_base;
+
+		check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1);
+		decrypted_base = max(decrypted_base, check_base);
+	}
 	decrypted_base <<= PGDIR_SHIFT;
 
+	/* Add encrypted kernel (identity) mappings */
+	ppd.paddr = kernel_start;
+	ppd.vaddr = kernel_start;
+	ppd.vaddr_end = kernel_end;
+	sme_map_range_encrypted(&ppd);
+
 	/* Add decrypted, write-protected kernel (non-identity) mappings */
-	pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT);
-	paddr = kernel_start;
-	while (paddr < kernel_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr + decrypted_base,
-						paddr + pmd_flags);
-
-		paddr += PMD_PAGE_SIZE;
+	ppd.paddr = kernel_start;
+	ppd.vaddr = kernel_start + decrypted_base;
+	ppd.vaddr_end = kernel_end + decrypted_base;
+	sme_map_range_decrypted_wp(&ppd);
+
+	if (initrd_len) {
+		/* Add encrypted initrd (identity) mappings */
+		ppd.paddr = initrd_start;
+		ppd.vaddr = initrd_start;
+		ppd.vaddr_end = initrd_end;
+		sme_map_range_encrypted(&ppd);
+		/*
+		 * Add decrypted, write-protected initrd (non-identity) mappings
+		 */
+		ppd.paddr = initrd_start;
+		ppd.vaddr = initrd_start + decrypted_base;
+		ppd.vaddr_end = initrd_end + decrypted_base;
+		sme_map_range_decrypted_wp(&ppd);
 	}
 
 	/* Add decrypted workarea mappings to both kernel mappings */
-	paddr = workarea_start;
-	while (paddr < workarea_end) {
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr,
-						paddr + PMD_FLAGS);
+	ppd.paddr = workarea_start;
+	ppd.vaddr = workarea_start;
+	ppd.vaddr_end = workarea_end;
+	sme_map_range_decrypted(&ppd);
 
-		pgtable_area = sme_populate_pgd(pgd, pgtable_area,
-						paddr + decrypted_base,
-						paddr + PMD_FLAGS);
-
-		paddr += PMD_PAGE_SIZE;
-	}
+	ppd.paddr = workarea_start;
+	ppd.vaddr = workarea_start + decrypted_base;
+	ppd.vaddr_end = workarea_end + decrypted_base;
+	sme_map_range_decrypted(&ppd);
 
 	/* Perform the encryption */
 	sme_encrypt_execute(kernel_start, kernel_start + decrypted_base,
-			    kernel_len, workarea_start, (unsigned long)pgd);
+			    kernel_len, workarea_start, (unsigned long)ppd.pgd);
+
+	if (initrd_len)
+		sme_encrypt_execute(initrd_start, initrd_start + decrypted_base,
+				    initrd_len, workarea_start,
+				    (unsigned long)ppd.pgd);
 
 	/*
 	 * At this point we are running encrypted.  Remove the mappings for
 	 * the decrypted areas - all that is needed for this is to remove
 	 * the PGD entry/entries.
 	 */
-	sme_clear_pgd(pgd, kernel_start + decrypted_base,
-		      kernel_end + decrypted_base);
+	ppd.vaddr = kernel_start + decrypted_base;
+	ppd.vaddr_end = kernel_end + decrypted_base;
+	sme_clear_pgd(&ppd);
+
+	if (initrd_len) {
+		ppd.vaddr = initrd_start + decrypted_base;
+		ppd.vaddr_end = initrd_end + decrypted_base;
+		sme_clear_pgd(&ppd);
+	}
 
-	sme_clear_pgd(pgd, workarea_start + decrypted_base,
-		      workarea_end + decrypted_base);
+	ppd.vaddr = workarea_start + decrypted_base;
+	ppd.vaddr_end = workarea_end + decrypted_base;
+	sme_clear_pgd(&ppd);
 
 	/* Flush the TLB - no globals so cr3 is enough */
 	native_write_cr3(__native_read_cr3());
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 730e6d541df1..01f682cf77a8 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute)
 
 	/*
 	 * Entry parameters:
-	 *   RDI - virtual address for the encrypted kernel mapping
-	 *   RSI - virtual address for the decrypted kernel mapping
-	 *   RDX - length of kernel
+	 *   RDI - virtual address for the encrypted mapping
+	 *   RSI - virtual address for the decrypted mapping
+	 *   RDX - length to encrypt
 	 *   RCX - virtual address of the encryption workarea, including:
 	 *     - stack page (PAGE_SIZE)
 	 *     - encryption routine page (PAGE_SIZE)
@@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute)
 	addq	$PAGE_SIZE, %rax	/* Workarea encryption routine */
 
 	push	%r12
-	movq	%rdi, %r10		/* Encrypted kernel */
-	movq	%rsi, %r11		/* Decrypted kernel */
-	movq	%rdx, %r12		/* Kernel length */
+	movq	%rdi, %r10		/* Encrypted area */
+	movq	%rsi, %r11		/* Decrypted area */
+	movq	%rdx, %r12		/* Area length */
 
 	/* Copy encryption routine into the workarea */
 	movq	%rax, %rdi				/* Workarea encryption routine */
@@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute)
 	rep	movsb
 
 	/* Setup registers for call */
-	movq	%r10, %rdi		/* Encrypted kernel */
-	movq	%r11, %rsi		/* Decrypted kernel */
+	movq	%r10, %rdi		/* Encrypted area */
+	movq	%r11, %rsi		/* Decrypted area */
 	movq	%r8, %rdx		/* Pagetables used for encryption */
-	movq	%r12, %rcx		/* Kernel length */
+	movq	%r12, %rcx		/* Area length */
 	movq	%rax, %r8		/* Workarea encryption routine */
 	addq	$PAGE_SIZE, %r8		/* Workarea intermediate copy buffer */
 
@@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute)
 
 ENTRY(__enc_copy)
 /*
- * Routine used to encrypt kernel.
+ * Routine used to encrypt memory in place.
  *   This routine must be run outside of the kernel proper since
  *   the kernel will be encrypted during the process. So this
  *   routine is defined here and then copied to an area outside
@@ -79,19 +79,19 @@ ENTRY(__enc_copy)
  *   during execution.
  *
  *   On entry the registers must be:
- *     RDI - virtual address for the encrypted kernel mapping
- *     RSI - virtual address for the decrypted kernel mapping
+ *     RDI - virtual address for the encrypted mapping
+ *     RSI - virtual address for the decrypted mapping
  *     RDX - address of the pagetables to use for encryption
- *     RCX - length of kernel
+ *     RCX - length of area
  *      R8 - intermediate copy buffer
  *
  *     RAX - points to this routine
  *
- * The kernel will be encrypted by copying from the non-encrypted
- * kernel space to an intermediate buffer and then copying from the
- * intermediate buffer back to the encrypted kernel space. The physical
- * addresses of the two kernel space mappings are the same which
- * results in the kernel being encrypted "in place".
+ * The area will be encrypted by copying from the non-encrypted
+ * memory space to an intermediate buffer and then copying from the
+ * intermediate buffer back to the encrypted memory space. The physical
+ * addresses of the two mappings are the same which results in the area
+ * being encrypted "in place".
  */
 	/* Enable the new page tables */
 	mov	%rdx, %cr3
@@ -103,47 +103,55 @@ ENTRY(__enc_copy)
 	orq	$X86_CR4_PGE, %rdx
 	mov	%rdx, %cr4
 
+	push	%r15
+	push	%r12
+
+	movq	%rcx, %r9		/* Save area length */
+	movq	%rdi, %r10		/* Save encrypted area address */
+	movq	%rsi, %r11		/* Save decrypted area address */
+
 	/* Set the PAT register PA5 entry to write-protect */
-	push	%rcx
 	movl	$MSR_IA32_CR_PAT, %ecx
 	rdmsr
-	push	%rdx			/* Save original PAT value */
+	mov	%rdx, %r15		/* Save original PAT value */
 	andl	$0xffff00ff, %edx	/* Clear PA5 */
 	orl	$0x00000500, %edx	/* Set PA5 to WP */
 	wrmsr
-	pop	%rdx			/* RDX contains original PAT value */
-	pop	%rcx
-
-	movq	%rcx, %r9		/* Save kernel length */
-	movq	%rdi, %r10		/* Save encrypted kernel address */
-	movq	%rsi, %r11		/* Save decrypted kernel address */
 
 	wbinvd				/* Invalidate any cache entries */
 
-	/* Copy/encrypt 2MB at a time */
+	/* Copy/encrypt up to 2MB at a time */
+	movq	$PMD_PAGE_SIZE, %r12
 1:
-	movq	%r11, %rsi		/* Source - decrypted kernel */
+	cmpq	%r12, %r9
+	jnb	2f
+	movq	%r9, %r12
+
+2:
+	movq	%r11, %rsi		/* Source - decrypted area */
 	movq	%r8, %rdi		/* Dest   - intermediate copy buffer */
-	movq	$PMD_PAGE_SIZE, %rcx	/* 2MB length */
+	movq	%r12, %rcx
 	rep	movsb
 
 	movq	%r8, %rsi		/* Source - intermediate copy buffer */
-	movq	%r10, %rdi		/* Dest   - encrypted kernel */
-	movq	$PMD_PAGE_SIZE, %rcx	/* 2MB length */
+	movq	%r10, %rdi		/* Dest   - encrypted area */
+	movq	%r12, %rcx
 	rep	movsb
 
-	addq	$PMD_PAGE_SIZE, %r11
-	addq	$PMD_PAGE_SIZE, %r10
-	subq	$PMD_PAGE_SIZE, %r9	/* Kernel length decrement */
+	addq	%r12, %r11
+	addq	%r12, %r10
+	subq	%r12, %r9		/* Kernel length decrement */
 	jnz	1b			/* Kernel length not zero? */
 
 	/* Restore PAT register */
-	push	%rdx			/* Save original PAT value */
 	movl	$MSR_IA32_CR_PAT, %ecx
 	rdmsr
-	pop	%rdx			/* Restore original PAT value */
+	mov	%r15, %rdx		/* Restore original PAT value */
 	wrmsr
 
+	pop	%r12
+	pop	%r15
+
 	ret
 .L__enc_copy_end:
 ENDPROC(__enc_copy)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index ee4c1ec9dca0..e7ded346d94b 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4439,6 +4439,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=121671
 	 */
 	{ "LITEON CX1-JB*-HP",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
+	{ "LITEON EP1-*",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
 
 	/* Devices we expect to fail diagnostics */
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
index a2978a37b4f3..700fc754f28a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
@@ -174,6 +174,7 @@ gf119_sor = {
 		.links = gf119_sor_dp_links,
 		.power = g94_sor_dp_power,
 		.pattern = gf119_sor_dp_pattern,
+		.drive = gf119_sor_dp_drive,
 		.vcpi = gf119_sor_dp_vcpi,
 		.audio = gf119_sor_dp_audio,
 		.audio_sym = gf119_sor_dp_audio_sym,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index b8a09807c5de..3824595fece1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -266,8 +266,8 @@ static const struct drm_connector_funcs vmw_legacy_connector_funcs = {
 	.set_property = vmw_du_connector_set_property,
 	.destroy = vmw_ldu_connector_destroy,
 	.reset = vmw_du_connector_reset,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = vmw_du_connector_duplicate_state,
+	.atomic_destroy_state = vmw_du_connector_destroy_state,
 	.atomic_set_property = vmw_du_connector_atomic_set_property,
 	.atomic_get_property = vmw_du_connector_atomic_get_property,
 };
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index d1552d3e0652..7ae38a67388c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -420,8 +420,8 @@ static const struct drm_connector_funcs vmw_sou_connector_funcs = {
 	.set_property = vmw_du_connector_set_property,
 	.destroy = vmw_sou_connector_destroy,
 	.reset = vmw_du_connector_reset,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = vmw_du_connector_duplicate_state,
+	.atomic_destroy_state = vmw_du_connector_destroy_state,
 	.atomic_set_property = vmw_du_connector_atomic_set_property,
 	.atomic_get_property = vmw_du_connector_atomic_get_property,
 };
diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c
index 10f00a82ec9d..e54a9b835b62 100644
--- a/drivers/i2c/i2c-core-smbus.c
+++ b/drivers/i2c/i2c-core-smbus.c
@@ -396,16 +396,17 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
 				   the underlying bus driver */
 		break;
 	case I2C_SMBUS_I2C_BLOCK_DATA:
+		if (data->block[0] > I2C_SMBUS_BLOCK_MAX) {
+			dev_err(&adapter->dev, "Invalid block %s size %d\n",
+				read_write == I2C_SMBUS_READ ? "read" : "write",
+				data->block[0]);
+			return -EINVAL;
+		}
+
 		if (read_write == I2C_SMBUS_READ) {
 			msg[1].len = data->block[0];
 		} else {
 			msg[0].len = data->block[0] + 1;
-			if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 1) {
-				dev_err(&adapter->dev,
-					"Invalid block write size %d\n",
-					data->block[0]);
-				return -EINVAL;
-			}
 			for (i = 1; i <= data->block[0]; i++)
 				msgbuf0[i] = data->block[i];
 		}
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index d9a1e9893136..fd28f09b4445 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -881,11 +881,11 @@ static int complete_subctxt(struct hfi1_filedata *fd)
 	}
 
 	if (ret) {
-		hfi1_rcd_put(fd->uctxt);
-		fd->uctxt = NULL;
 		spin_lock_irqsave(&fd->dd->uctxt_lock, flags);
 		__clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts);
 		spin_unlock_irqrestore(&fd->dd->uctxt_lock, flags);
+		hfi1_rcd_put(fd->uctxt);
+		fd->uctxt = NULL;
 	}
 
 	return ret;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index acb79d3a4f1d..756ece6118c0 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4303,12 +4303,11 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev,
 
 	memset(ah_attr, 0, sizeof(*ah_attr));
 
-	ah_attr->type = rdma_ah_find_type(&ibdev->ib_dev, path->port);
-	rdma_ah_set_port_num(ah_attr, path->port);
-	if (rdma_ah_get_port_num(ah_attr) == 0 ||
-	    rdma_ah_get_port_num(ah_attr) > MLX5_CAP_GEN(dev, num_ports))
+	if (!path->port || path->port > MLX5_CAP_GEN(dev, num_ports))
 		return;
 
+	ah_attr->type = rdma_ah_find_type(&ibdev->ib_dev, path->port);
+
 	rdma_ah_set_port_num(ah_attr, path->port);
 	rdma_ah_set_sl(ah_attr, path->dci_cfi_prio_sl & 0xf);
 
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index ceabdb85df8b..9d4785ba24cb 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -741,6 +741,7 @@ isert_connect_error(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
+	ib_drain_qp(isert_conn->qp);
 	list_del_init(&isert_conn->node);
 	isert_conn->cm_id = NULL;
 	isert_put_conn(isert_conn);
diff --git a/drivers/input/misc/twl4030-vibra.c b/drivers/input/misc/twl4030-vibra.c
index 6c51d404874b..c37aea9ac272 100644
--- a/drivers/input/misc/twl4030-vibra.c
+++ b/drivers/input/misc/twl4030-vibra.c
@@ -178,12 +178,14 @@ static SIMPLE_DEV_PM_OPS(twl4030_vibra_pm_ops,
 			 twl4030_vibra_suspend, twl4030_vibra_resume);
 
 static bool twl4030_vibra_check_coexist(struct twl4030_vibra_data *pdata,
-			      struct device_node *node)
+			      struct device_node *parent)
 {
+	struct device_node *node;
+
 	if (pdata && pdata->coexist)
 		return true;
 
-	node = of_find_node_by_name(node, "codec");
+	node = of_get_child_by_name(parent, "codec");
 	if (node) {
 		of_node_put(node);
 		return true;
diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c
index 5690eb7ff954..15e0d352c4cc 100644
--- a/drivers/input/misc/twl6040-vibra.c
+++ b/drivers/input/misc/twl6040-vibra.c
@@ -248,8 +248,7 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 	int vddvibr_uV = 0;
 	int error;
 
-	of_node_get(twl6040_core_dev->of_node);
-	twl6040_core_node = of_find_node_by_name(twl6040_core_dev->of_node,
+	twl6040_core_node = of_get_child_by_name(twl6040_core_dev->of_node,
 						 "vibra");
 	if (!twl6040_core_node) {
 		dev_err(&pdev->dev, "parent of node is missing?\n");
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 850b00e3ad8e..3d9c294e84db 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1250,29 +1250,32 @@ static int alps_decode_ss4_v2(struct alps_fields *f,
 	case SS4_PACKET_ID_MULTI:
 		if (priv->flags & ALPS_BUTTONPAD) {
 			if (IS_SS4PLUS_DEV(priv->dev_id)) {
-				f->mt[0].x = SS4_PLUS_BTL_MF_X_V2(p, 0);
-				f->mt[1].x = SS4_PLUS_BTL_MF_X_V2(p, 1);
+				f->mt[2].x = SS4_PLUS_BTL_MF_X_V2(p, 0);
+				f->mt[3].x = SS4_PLUS_BTL_MF_X_V2(p, 1);
+				no_data_x = SS4_PLUS_MFPACKET_NO_AX_BL;
 			} else {
 				f->mt[2].x = SS4_BTL_MF_X_V2(p, 0);
 				f->mt[3].x = SS4_BTL_MF_X_V2(p, 1);
+				no_data_x = SS4_MFPACKET_NO_AX_BL;
 			}
+			no_data_y = SS4_MFPACKET_NO_AY_BL;
 
 			f->mt[2].y = SS4_BTL_MF_Y_V2(p, 0);
 			f->mt[3].y = SS4_BTL_MF_Y_V2(p, 1);
-			no_data_x = SS4_MFPACKET_NO_AX_BL;
-			no_data_y = SS4_MFPACKET_NO_AY_BL;
 		} else {
 			if (IS_SS4PLUS_DEV(priv->dev_id)) {
-				f->mt[0].x = SS4_PLUS_STD_MF_X_V2(p, 0);
-				f->mt[1].x = SS4_PLUS_STD_MF_X_V2(p, 1);
+				f->mt[2].x = SS4_PLUS_STD_MF_X_V2(p, 0);
+				f->mt[3].x = SS4_PLUS_STD_MF_X_V2(p, 1);
+				no_data_x = SS4_PLUS_MFPACKET_NO_AX;
 			} else {
-				f->mt[0].x = SS4_STD_MF_X_V2(p, 0);
-				f->mt[1].x = SS4_STD_MF_X_V2(p, 1);
+				f->mt[2].x = SS4_STD_MF_X_V2(p, 0);
+				f->mt[3].x = SS4_STD_MF_X_V2(p, 1);
+				no_data_x = SS4_MFPACKET_NO_AX;
 			}
+			no_data_y = SS4_MFPACKET_NO_AY;
+
 			f->mt[2].y = SS4_STD_MF_Y_V2(p, 0);
 			f->mt[3].y = SS4_STD_MF_Y_V2(p, 1);
-			no_data_x = SS4_MFPACKET_NO_AX;
-			no_data_y = SS4_MFPACKET_NO_AY;
 		}
 
 		f->first_mp = 0;
diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h
index c80a7c76cb76..79b6d69d1486 100644
--- a/drivers/input/mouse/alps.h
+++ b/drivers/input/mouse/alps.h
@@ -141,10 +141,12 @@ enum SS4_PACKET_ID {
 #define SS4_TS_Z_V2(_b)		(s8)(_b[4] & 0x7F)
 
 
-#define SS4_MFPACKET_NO_AX	8160	/* X-Coordinate value */
-#define SS4_MFPACKET_NO_AY	4080	/* Y-Coordinate value */
-#define SS4_MFPACKET_NO_AX_BL	8176	/* Buttonless X-Coordinate value */
-#define SS4_MFPACKET_NO_AY_BL	4088	/* Buttonless Y-Coordinate value */
+#define SS4_MFPACKET_NO_AX		8160	/* X-Coordinate value */
+#define SS4_MFPACKET_NO_AY		4080	/* Y-Coordinate value */
+#define SS4_MFPACKET_NO_AX_BL		8176	/* Buttonless X-Coord value */
+#define SS4_MFPACKET_NO_AY_BL		4088	/* Buttonless Y-Coord value */
+#define SS4_PLUS_MFPACKET_NO_AX		4080	/* SS4 PLUS, X */
+#define SS4_PLUS_MFPACKET_NO_AX_BL	4088	/* Buttonless SS4 PLUS, X */
 
 /*
  * enum V7_PACKET_ID - defines the packet type for V7
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 4f2bb5947a4e..141ea228aac6 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -230,8 +230,10 @@ static irqreturn_t rmi_irq_fn(int irq, void *dev_id)
 		rmi_dbg(RMI_DEBUG_CORE, &rmi_dev->dev,
 			"Failed to process interrupt request: %d\n", ret);
 
-	if (count)
+	if (count) {
 		kfree(attn_data.data);
+		attn_data.data = NULL;
+	}
 
 	if (!kfifo_is_empty(&drvdata->attn_fifo))
 		return rmi_irq_fn(irq, dev_id);
diff --git a/drivers/input/touchscreen/88pm860x-ts.c b/drivers/input/touchscreen/88pm860x-ts.c
index 7ed828a51f4c..3486d9403805 100644
--- a/drivers/input/touchscreen/88pm860x-ts.c
+++ b/drivers/input/touchscreen/88pm860x-ts.c
@@ -126,7 +126,7 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
 	int data, n, ret;
 	if (!np)
 		return -ENODEV;
-	np = of_find_node_by_name(np, "touch");
+	np = of_get_child_by_name(np, "touch");
 	if (!np) {
 		dev_err(&pdev->dev, "Can't find touch node\n");
 		return -EINVAL;
@@ -144,13 +144,13 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
 	if (data) {
 		ret = pm860x_reg_write(i2c, PM8607_GPADC_MISC1, data);
 		if (ret < 0)
-			return -EINVAL;
+			goto err_put_node;
 	}
 	/* set tsi prebias time */
 	if (!of_property_read_u32(np, "marvell,88pm860x-tsi-prebias", &data)) {
 		ret = pm860x_reg_write(i2c, PM8607_TSI_PREBIAS, data);
 		if (ret < 0)
-			return -EINVAL;
+			goto err_put_node;
 	}
 	/* set prebias & prechg time of pen detect */
 	data = 0;
@@ -161,10 +161,18 @@ static int pm860x_touch_dt_init(struct platform_device *pdev,
 	if (data) {
 		ret = pm860x_reg_write(i2c, PM8607_PD_PREBIAS, data);
 		if (ret < 0)
-			return -EINVAL;
+			goto err_put_node;
 	}
 	of_property_read_u32(np, "marvell,88pm860x-resistor-X", res_x);
+
+	of_node_put(np);
+
 	return 0;
+
+err_put_node:
+	of_node_put(np);
+
+	return -EINVAL;
 }
 #else
 #define pm860x_touch_dt_init(x, y, z)	(-1)
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9fc12f556534..554d60394c06 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1954,10 +1954,15 @@ static int crypt_setkey(struct crypt_config *cc)
 	/* Ignore extra keys (which are used for IV etc) */
 	subkey_size = crypt_subkey_size(cc);
 
-	if (crypt_integrity_hmac(cc))
+	if (crypt_integrity_hmac(cc)) {
+		if (subkey_size < cc->key_mac_size)
+			return -EINVAL;
+
 		crypt_copy_authenckey(cc->authenc_key, cc->key,
 				      subkey_size - cc->key_mac_size,
 				      cc->key_mac_size);
+	}
+
 	for (i = 0; i < cc->tfms_count; i++) {
 		if (crypt_integrity_hmac(cc))
 			r = crypto_aead_setkey(cc->cipher_tfm.tfms_aead[i],
@@ -2053,9 +2058,6 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	ret = crypt_setkey(cc);
 
-	/* wipe the kernel key payload copy in each case */
-	memset(cc->key, 0, cc->key_size * sizeof(u8));
-
 	if (!ret) {
 		set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 		kzfree(cc->key_string);
@@ -2523,6 +2525,10 @@ static int crypt_ctr_cipher(struct dm_target *ti, char *cipher_in, char *key)
 		}
 	}
 
+	/* wipe the kernel key payload copy */
+	if (cc->key_string)
+		memset(cc->key, 0, cc->key_size * sizeof(u8));
+
 	return ret;
 }
 
@@ -2740,6 +2746,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 			cc->tag_pool_max_sectors * cc->on_disk_tag_size);
 		if (!cc->tag_pool) {
 			ti->error = "Cannot allocate integrity tags mempool";
+			ret = -ENOMEM;
 			goto bad;
 		}
 
@@ -2961,6 +2968,9 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
 				return ret;
 			if (cc->iv_gen_ops && cc->iv_gen_ops->init)
 				ret = cc->iv_gen_ops->init(cc);
+			/* wipe the kernel key payload copy */
+			if (cc->key_string)
+				memset(cc->key, 0, cc->key_size * sizeof(u8));
 			return ret;
 		}
 		if (argc == 2 && !strcasecmp(argv[1], "wipe")) {
@@ -3007,7 +3017,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 18, 0},
+	.version = {1, 18, 1},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 5e6737a44468..3cc2052f972c 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2558,7 +2558,8 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 	int r = 0;
 	unsigned i;
 	__u64 journal_pages, journal_desc_size, journal_tree_size;
-	unsigned char *crypt_data = NULL;
+	unsigned char *crypt_data = NULL, *crypt_iv = NULL;
+	struct skcipher_request *req = NULL;
 
 	ic->commit_ids[0] = cpu_to_le64(0x1111111111111111ULL);
 	ic->commit_ids[1] = cpu_to_le64(0x2222222222222222ULL);
@@ -2616,9 +2617,20 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 
 		if (blocksize == 1) {
 			struct scatterlist *sg;
-			SKCIPHER_REQUEST_ON_STACK(req, ic->journal_crypt);
-			unsigned char iv[ivsize];
-			skcipher_request_set_tfm(req, ic->journal_crypt);
+
+			req = skcipher_request_alloc(ic->journal_crypt, GFP_KERNEL);
+			if (!req) {
+				*error = "Could not allocate crypt request";
+				r = -ENOMEM;
+				goto bad;
+			}
+
+			crypt_iv = kmalloc(ivsize, GFP_KERNEL);
+			if (!crypt_iv) {
+				*error = "Could not allocate iv";
+				r = -ENOMEM;
+				goto bad;
+			}
 
 			ic->journal_xor = dm_integrity_alloc_page_list(ic);
 			if (!ic->journal_xor) {
@@ -2640,9 +2652,9 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 				sg_set_buf(&sg[i], va, PAGE_SIZE);
 			}
 			sg_set_buf(&sg[i], &ic->commit_ids, sizeof ic->commit_ids);
-			memset(iv, 0x00, ivsize);
+			memset(crypt_iv, 0x00, ivsize);
 
-			skcipher_request_set_crypt(req, sg, sg, PAGE_SIZE * ic->journal_pages + sizeof ic->commit_ids, iv);
+			skcipher_request_set_crypt(req, sg, sg, PAGE_SIZE * ic->journal_pages + sizeof ic->commit_ids, crypt_iv);
 			init_completion(&comp.comp);
 			comp.in_flight = (atomic_t)ATOMIC_INIT(1);
 			if (do_crypt(true, req, &comp))
@@ -2658,10 +2670,22 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 			crypto_free_skcipher(ic->journal_crypt);
 			ic->journal_crypt = NULL;
 		} else {
-			SKCIPHER_REQUEST_ON_STACK(req, ic->journal_crypt);
-			unsigned char iv[ivsize];
 			unsigned crypt_len = roundup(ivsize, blocksize);
 
+			req = skcipher_request_alloc(ic->journal_crypt, GFP_KERNEL);
+			if (!req) {
+				*error = "Could not allocate crypt request";
+				r = -ENOMEM;
+				goto bad;
+			}
+
+			crypt_iv = kmalloc(ivsize, GFP_KERNEL);
+			if (!crypt_iv) {
+				*error = "Could not allocate iv";
+				r = -ENOMEM;
+				goto bad;
+			}
+
 			crypt_data = kmalloc(crypt_len, GFP_KERNEL);
 			if (!crypt_data) {
 				*error = "Unable to allocate crypt data";
@@ -2669,8 +2693,6 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 				goto bad;
 			}
 
-			skcipher_request_set_tfm(req, ic->journal_crypt);
-
 			ic->journal_scatterlist = dm_integrity_alloc_journal_scatterlist(ic, ic->journal);
 			if (!ic->journal_scatterlist) {
 				*error = "Unable to allocate sg list";
@@ -2694,12 +2716,12 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 				struct skcipher_request *section_req;
 				__u32 section_le = cpu_to_le32(i);
 
-				memset(iv, 0x00, ivsize);
+				memset(crypt_iv, 0x00, ivsize);
 				memset(crypt_data, 0x00, crypt_len);
 				memcpy(crypt_data, &section_le, min((size_t)crypt_len, sizeof(section_le)));
 
 				sg_init_one(&sg, crypt_data, crypt_len);
-				skcipher_request_set_crypt(req, &sg, &sg, crypt_len, iv);
+				skcipher_request_set_crypt(req, &sg, &sg, crypt_len, crypt_iv);
 				init_completion(&comp.comp);
 				comp.in_flight = (atomic_t)ATOMIC_INIT(1);
 				if (do_crypt(true, req, &comp))
@@ -2757,6 +2779,9 @@ static int create_journal(struct dm_integrity_c *ic, char **error)
 	}
 bad:
 	kfree(crypt_data);
+	kfree(crypt_iv);
+	skcipher_request_free(req);
+
 	return r;
 }
 
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index d31d18d9727c..36ef284ad086 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -80,10 +80,14 @@
 #define SECTOR_TO_BLOCK_SHIFT 3
 
 /*
+ * For btree insert:
  *  3 for btree insert +
  *  2 for btree lookup used within space map
+ * For btree remove:
+ *  2 for shadow spine +
+ *  4 for rebalance 3 child node
  */
-#define THIN_MAX_CONCURRENT_LOCKS 5
+#define THIN_MAX_CONCURRENT_LOCKS 6
 
 /* This should be plenty */
 #define SPACE_MAP_ROOT_SIZE 128
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index f21ce6a3d4cf..58b319757b1e 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -683,23 +683,8 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
 	pn->keys[1] = rn->keys[0];
 	memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64));
 
-	/*
-	 * rejig the spine.  This is ugly, since it knows too
-	 * much about the spine
-	 */
-	if (s->nodes[0] != new_parent) {
-		unlock_block(s->info, s->nodes[0]);
-		s->nodes[0] = new_parent;
-	}
-	if (key < le64_to_cpu(rn->keys[0])) {
-		unlock_block(s->info, right);
-		s->nodes[1] = left;
-	} else {
-		unlock_block(s->info, left);
-		s->nodes[1] = right;
-	}
-	s->count = 2;
-
+	unlock_block(s->info, left);
+	unlock_block(s->info, right);
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 85140c9af581..8b941f814472 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -687,6 +687,20 @@ static inline void esdhc_pltfm_set_clock(struct sdhci_host *host,
 		return;
 	}
 
+	/* For i.MX53 eSDHCv3, SYSCTL.SDCLKFS may not be set to 0. */
+	if (is_imx53_esdhc(imx_data)) {
+		/*
+		 * According to the i.MX53 reference manual, if DLLCTRL[10] can
+		 * be set, then the controller is eSDHCv3, else it is eSDHCv2.
+		 */
+		val = readl(host->ioaddr + ESDHC_DLL_CTRL);
+		writel(val | BIT(10), host->ioaddr + ESDHC_DLL_CTRL);
+		temp = readl(host->ioaddr + ESDHC_DLL_CTRL);
+		writel(val, host->ioaddr + ESDHC_DLL_CTRL);
+		if (temp & BIT(10))
+			pre_div = 2;
+	}
+
 	temp = sdhci_readl(host, ESDHC_SYSTEM_CONTROL);
 	temp &= ~(ESDHC_CLOCK_IPGEN | ESDHC_CLOCK_HCKEN | ESDHC_CLOCK_PEREN
 		| ESDHC_CLOCK_MASK);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 7ccdc3e30c98..53d6bb045e9e 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -184,7 +184,7 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail)
 	void *cmd_head = pcan_usb_fd_cmd_buffer(dev);
 	int err = 0;
 	u8 *packet_ptr;
-	int i, n = 1, packet_len;
+	int packet_len;
 	ptrdiff_t cmd_len;
 
 	/* usb device unregistered? */
@@ -201,17 +201,13 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail)
 	}
 
 	packet_ptr = cmd_head;
+	packet_len = cmd_len;
 
 	/* firmware is not able to re-assemble 512 bytes buffer in full-speed */
-	if ((dev->udev->speed != USB_SPEED_HIGH) &&
-	    (cmd_len > PCAN_UFD_LOSPD_PKT_SIZE)) {
-		packet_len = PCAN_UFD_LOSPD_PKT_SIZE;
-		n += cmd_len / packet_len;
-	} else {
-		packet_len = cmd_len;
-	}
+	if (unlikely(dev->udev->speed != USB_SPEED_HIGH))
+		packet_len = min(packet_len, PCAN_UFD_LOSPD_PKT_SIZE);
 
-	for (i = 0; i < n; i++) {
+	do {
 		err = usb_bulk_msg(dev->udev,
 				   usb_sndbulkpipe(dev->udev,
 						   PCAN_USBPRO_EP_CMDOUT),
@@ -224,7 +220,12 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail)
 		}
 
 		packet_ptr += packet_len;
-	}
+		cmd_len -= packet_len;
+
+		if (cmd_len < PCAN_UFD_LOSPD_PKT_SIZE)
+			packet_len = cmd_len;
+
+	} while (packet_len > 0);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index fcf9ba5eb8d1..d147dc7d0f77 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -4552,11 +4552,6 @@ static void mvpp2_port_mii_gmac_configure_mode(struct mvpp2_port *port)
 		       MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
 		val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
 		writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
-
-		val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
-		val |= MVPP2_GMAC_DISABLE_PADDING;
-		val &= ~MVPP2_GMAC_FLOW_CTRL_MASK;
-		writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
 	} else if (phy_interface_mode_is_rgmii(port->phy_interface)) {
 		val = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
 		val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
@@ -4564,10 +4559,6 @@ static void mvpp2_port_mii_gmac_configure_mode(struct mvpp2_port *port)
 		       MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
 		val &= ~MVPP22_CTRL4_DP_CLK_SEL;
 		writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
-
-		val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
-		val &= ~MVPP2_GMAC_DISABLE_PADDING;
-		writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
 	}
 
 	/* The port is connected to a copper PHY */
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index a268f4d6f3e9..48a365e303e5 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -395,6 +395,10 @@ static struct phy *_of_phy_get(struct device_node *np, int index)
 	if (ret)
 		return ERR_PTR(-ENODEV);
 
+	/* This phy type handled by the usb-phy subsystem for now */
+	if (of_device_is_compatible(args.np, "usb-nop-xceiv"))
+		return ERR_PTR(-ENODEV);
+
 	mutex_lock(&phy_provider_mutex);
 	phy_provider = of_phy_provider_lookup(args.np);
 	if (IS_ERR(phy_provider) || !try_module_get(phy_provider->owner)) {
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index ea8ad06ff582..10b17da20176 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -486,15 +486,28 @@ static int sas_queue_reset(struct domain_device *dev, int reset_type,
 
 int sas_eh_abort_handler(struct scsi_cmnd *cmd)
 {
-	int res;
+	int res = TMF_RESP_FUNC_FAILED;
 	struct sas_task *task = TO_SAS_TASK(cmd);
 	struct Scsi_Host *host = cmd->device->host;
+	struct domain_device *dev = cmd_to_domain_dev(cmd);
 	struct sas_internal *i = to_sas_internal(host->transportt);
+	unsigned long flags;
 
 	if (!i->dft->lldd_abort_task)
 		return FAILED;
 
-	res = i->dft->lldd_abort_task(task);
+	spin_lock_irqsave(host->host_lock, flags);
+	/* We cannot do async aborts for SATA devices */
+	if (dev_is_sata(dev) && !host->host_eh_scheduled) {
+		spin_unlock_irqrestore(host->host_lock, flags);
+		return FAILED;
+	}
+	spin_unlock_irqrestore(host->host_lock, flags);
+
+	if (task)
+		res = i->dft->lldd_abort_task(task);
+	else
+		SAS_DPRINTK("no task to abort\n");
 	if (res == TMF_RESP_FUNC_SUCC || res == TMF_RESP_FUNC_COMPLETE)
 		return SUCCESS;
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 3909c55ed389..f0f4ab36c444 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1018,13 +1018,19 @@ const struct file_operations pipefifo_fops = {
 
 /*
  * Currently we rely on the pipe array holding a power-of-2 number
- * of pages.
+ * of pages. Returns 0 on error.
  */
 static inline unsigned int round_pipe_size(unsigned int size)
 {
 	unsigned long nr_pages;
 
+	if (size < pipe_min_size)
+		size = pipe_min_size;
+
 	nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (nr_pages == 0)
+		return 0;
+
 	return roundup_pow_of_two(nr_pages) << PAGE_SHIFT;
 }
 
@@ -1040,6 +1046,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
 	long ret = 0;
 
 	size = round_pipe_size(arg);
+	if (size == 0)
+		return -EINVAL;
 	nr_pages = size >> PAGE_SHIFT;
 
 	if (!nr_pages)
@@ -1123,13 +1131,18 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
 int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
 		 size_t *lenp, loff_t *ppos)
 {
+	unsigned int rounded_pipe_max_size;
 	int ret;
 
 	ret = proc_douintvec_minmax(table, write, buf, lenp, ppos);
 	if (ret < 0 || !write)
 		return ret;
 
-	pipe_max_size = round_pipe_size(pipe_max_size);
+	rounded_pipe_max_size = round_pipe_size(pipe_max_size);
+	if (rounded_pipe_max_size == 0)
+		return -EINVAL;
+
+	pipe_max_size = rounded_pipe_max_size;
 	return ret;
 }
 
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 9390032a11e1..e6094a15ef30 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -424,8 +424,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		 * safe because the task has stopped executing permanently.
 		 */
 		if (permitted && (task->flags & PF_DUMPCORE)) {
-			eip = KSTK_EIP(task);
-			esp = KSTK_ESP(task);
+			if (try_get_task_stack(task)) {
+				eip = KSTK_EIP(task);
+				esp = KSTK_ESP(task);
+				put_task_stack(task);
+			}
 		}
 	}
 
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 4178d2493547..5e335b6203f4 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -71,7 +71,7 @@ extern void delayacct_init(void);
 extern void __delayacct_tsk_init(struct task_struct *);
 extern void __delayacct_tsk_exit(struct task_struct *);
 extern void __delayacct_blkio_start(void);
-extern void __delayacct_blkio_end(void);
+extern void __delayacct_blkio_end(struct task_struct *);
 extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
 extern __u64 __delayacct_blkio_ticks(struct task_struct *);
 extern void __delayacct_freepages_start(void);
@@ -122,10 +122,10 @@ static inline void delayacct_blkio_start(void)
 		__delayacct_blkio_start();
 }
 
-static inline void delayacct_blkio_end(void)
+static inline void delayacct_blkio_end(struct task_struct *p)
 {
 	if (current->delays)
-		__delayacct_blkio_end();
+		__delayacct_blkio_end(p);
 	delayacct_clear_flag(DELAYACCT_PF_BLKIO);
 }
 
@@ -169,7 +169,7 @@ static inline void delayacct_tsk_free(struct task_struct *tsk)
 {}
 static inline void delayacct_blkio_start(void)
 {}
-static inline void delayacct_blkio_end(void)
+static inline void delayacct_blkio_end(struct task_struct *p)
 {}
 static inline int delayacct_add_tsk(struct taskstats *d,
 					struct task_struct *tsk)
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 9c5a2628d6ce..1d3877c39a00 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -124,6 +124,11 @@ static inline bool is_write_device_private_entry(swp_entry_t entry)
 	return unlikely(swp_type(entry) == SWP_DEVICE_WRITE);
 }
 
+static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry)
+{
+	return swp_offset(entry);
+}
+
 static inline struct page *device_private_entry_to_page(swp_entry_t entry)
 {
 	return pfn_to_page(swp_offset(entry));
@@ -154,6 +159,11 @@ static inline bool is_write_device_private_entry(swp_entry_t entry)
 	return false;
 }
 
+static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry)
+{
+	return 0;
+}
+
 static inline struct page *device_private_entry_to_page(swp_entry_t entry)
 {
 	return NULL;
@@ -189,6 +199,11 @@ static inline int is_write_migration_entry(swp_entry_t entry)
 	return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
 }
 
+static inline unsigned long migration_entry_to_pfn(swp_entry_t entry)
+{
+	return swp_offset(entry);
+}
+
 static inline struct page *migration_entry_to_page(swp_entry_t entry)
 {
 	struct page *p = pfn_to_page(swp_offset(entry));
@@ -218,6 +233,12 @@ static inline int is_migration_entry(swp_entry_t swp)
 {
 	return 0;
 }
+
+static inline unsigned long migration_entry_to_pfn(swp_entry_t entry)
+{
+	return 0;
+}
+
 static inline struct page *migration_entry_to_page(swp_entry_t entry)
 {
 	return NULL;
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index bae807eb2933..853291714ae0 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -31,11 +31,17 @@
 #else
 #define MODULE_RANDSTRUCT_PLUGIN
 #endif
+#ifdef RETPOLINE
+#define MODULE_VERMAGIC_RETPOLINE "retpoline "
+#else
+#define MODULE_VERMAGIC_RETPOLINE ""
+#endif
 
 #define VERMAGIC_STRING 						\
 	UTS_RELEASE " "							\
 	MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT 			\
 	MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS	\
 	MODULE_ARCH_VERMAGIC						\
-	MODULE_RANDSTRUCT_PLUGIN
+	MODULE_RANDSTRUCT_PLUGIN					\
+	MODULE_VERMAGIC_RETPOLINE
 
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 4a1c33416b6a..e2764d767f18 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -51,16 +51,16 @@ void __delayacct_tsk_init(struct task_struct *tsk)
  * Finish delay accounting for a statistic using its timestamps (@start),
  * accumalator (@total) and @count
  */
-static void delayacct_end(u64 *start, u64 *total, u32 *count)
+static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count)
 {
 	s64 ns = ktime_get_ns() - *start;
 	unsigned long flags;
 
 	if (ns > 0) {
-		spin_lock_irqsave(&current->delays->lock, flags);
+		spin_lock_irqsave(lock, flags);
 		*total += ns;
 		(*count)++;
-		spin_unlock_irqrestore(&current->delays->lock, flags);
+		spin_unlock_irqrestore(lock, flags);
 	}
 }
 
@@ -69,17 +69,25 @@ void __delayacct_blkio_start(void)
 	current->delays->blkio_start = ktime_get_ns();
 }
 
-void __delayacct_blkio_end(void)
+/*
+ * We cannot rely on the `current` macro, as we haven't yet switched back to
+ * the process being woken.
+ */
+void __delayacct_blkio_end(struct task_struct *p)
 {
-	if (current->delays->flags & DELAYACCT_PF_SWAPIN)
-		/* Swapin block I/O */
-		delayacct_end(&current->delays->blkio_start,
-			&current->delays->swapin_delay,
-			&current->delays->swapin_count);
-	else	/* Other block I/O */
-		delayacct_end(&current->delays->blkio_start,
-			&current->delays->blkio_delay,
-			&current->delays->blkio_count);
+	struct task_delay_info *delays = p->delays;
+	u64 *total;
+	u32 *count;
+
+	if (p->delays->flags & DELAYACCT_PF_SWAPIN) {
+		total = &delays->swapin_delay;
+		count = &delays->swapin_count;
+	} else {
+		total = &delays->blkio_delay;
+		count = &delays->blkio_count;
+	}
+
+	delayacct_end(&delays->lock, &delays->blkio_start, total, count);
 }
 
 int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
@@ -153,8 +161,10 @@ void __delayacct_freepages_start(void)
 
 void __delayacct_freepages_end(void)
 {
-	delayacct_end(&current->delays->freepages_start,
-			&current->delays->freepages_delay,
-			&current->delays->freepages_count);
+	delayacct_end(
+		&current->delays->lock,
+		&current->delays->freepages_start,
+		&current->delays->freepages_delay,
+		&current->delays->freepages_count);
 }
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 76ed5921117a..52b3f4703158 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1878,6 +1878,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_q *this, *next;
 	DEFINE_WAKE_Q(wake_q);
 
+	if (nr_wake < 0 || nr_requeue < 0)
+		return -EINVAL;
+
 	/*
 	 * When PI not supported: return -ENOSYS if requeue_pi is true,
 	 * consequently the compiler knows requeue_pi is always false past
@@ -2294,21 +2297,17 @@ static void unqueue_me_pi(struct futex_q *q)
 	spin_unlock(q->lock_ptr);
 }
 
-/*
- * Fixup the pi_state owner with the new owner.
- *
- * Must be called with hash bucket lock held and mm->sem held for non
- * private futexes.
- */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner)
+				struct task_struct *argowner)
 {
-	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
 	u32 uval, uninitialized_var(curval), newval;
-	struct task_struct *oldowner;
+	struct task_struct *oldowner, *newowner;
+	u32 newtid;
 	int ret;
 
+	lockdep_assert_held(q->lock_ptr);
+
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	oldowner = pi_state->owner;
@@ -2317,11 +2316,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 		newtid |= FUTEX_OWNER_DIED;
 
 	/*
-	 * We are here either because we stole the rtmutex from the
-	 * previous highest priority waiter or we are the highest priority
-	 * waiter but have failed to get the rtmutex the first time.
+	 * We are here because either:
+	 *
+	 *  - we stole the lock and pi_state->owner needs updating to reflect
+	 *    that (@argowner == current),
+	 *
+	 * or:
+	 *
+	 *  - someone stole our lock and we need to fix things to point to the
+	 *    new owner (@argowner == NULL).
 	 *
-	 * We have to replace the newowner TID in the user space variable.
+	 * Either way, we have to replace the TID in the user space variable.
 	 * This must be atomic as we have to preserve the owner died bit here.
 	 *
 	 * Note: We write the user space value _before_ changing the pi_state
@@ -2334,6 +2339,42 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	 * in the PID check in lookup_pi_state.
 	 */
 retry:
+	if (!argowner) {
+		if (oldowner != current) {
+			/*
+			 * We raced against a concurrent self; things are
+			 * already fixed up. Nothing to do.
+			 */
+			ret = 0;
+			goto out_unlock;
+		}
+
+		if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
+			/* We got the lock after all, nothing to fix. */
+			ret = 0;
+			goto out_unlock;
+		}
+
+		/*
+		 * Since we just failed the trylock; there must be an owner.
+		 */
+		newowner = rt_mutex_owner(&pi_state->pi_mutex);
+		BUG_ON(!newowner);
+	} else {
+		WARN_ON_ONCE(argowner != current);
+		if (oldowner == current) {
+			/*
+			 * We raced against a concurrent self; things are
+			 * already fixed up. Nothing to do.
+			 */
+			ret = 0;
+			goto out_unlock;
+		}
+		newowner = argowner;
+	}
+
+	newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
+
 	if (get_futex_value_locked(&uval, uaddr))
 		goto handle_fault;
 
@@ -2434,15 +2475,28 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * Got the lock. We might not be the anticipated owner if we
 		 * did a lock-steal - fix up the PI-state in that case:
 		 *
-		 * We can safely read pi_state->owner without holding wait_lock
-		 * because we now own the rt_mutex, only the owner will attempt
-		 * to change it.
+		 * Speculative pi_state->owner read (we don't hold wait_lock);
+		 * since we own the lock pi_state->owner == current is the
+		 * stable state, anything else needs more attention.
 		 */
 		if (q->pi_state->owner != current)
 			ret = fixup_pi_state_owner(uaddr, q, current);
 		goto out;
 	}
 
+	/*
+	 * If we didn't get the lock; check if anybody stole it from us. In
+	 * that case, we need to fix up the uval to point to them instead of
+	 * us, otherwise bad things happen. [10]
+	 *
+	 * Another speculative read; pi_state->owner == current is unstable
+	 * but needs our attention.
+	 */
+	if (q->pi_state->owner == current) {
+		ret = fixup_pi_state_owner(uaddr, q, NULL);
+		goto out;
+	}
+
 	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
 	 * the owner of the rt_mutex.
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 6f3dba6e4e9e..65cc0cb984e6 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1290,6 +1290,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	return ret;
 }
 
+static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock)
+{
+	int ret = try_to_take_rt_mutex(lock, current, NULL);
+
+	/*
+	 * try_to_take_rt_mutex() sets the lock waiters bit
+	 * unconditionally. Clean this up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	return ret;
+}
+
 /*
  * Slow path try-lock function:
  */
@@ -1312,13 +1325,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 	 */
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
-	ret = try_to_take_rt_mutex(lock, current, NULL);
-
-	/*
-	 * try_to_take_rt_mutex() sets the lock waiters bit
-	 * unconditionally. Clean this up.
-	 */
-	fixup_rt_mutex_waiters(lock);
+	ret = __rt_mutex_slowtrylock(lock);
 
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
@@ -1505,6 +1512,11 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
 	return rt_mutex_slowtrylock(lock);
 }
 
+int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock)
+{
+	return __rt_mutex_slowtrylock(lock);
+}
+
 /**
  * rt_mutex_timed_lock - lock a rt_mutex interruptible
  *			the timeout structure is provided
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 124e98ca0b17..68686b3ec3c1 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -148,6 +148,7 @@ extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 				 struct rt_mutex_waiter *waiter);
 
 extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+extern int __rt_mutex_futex_trylock(struct rt_mutex *l);
 
 extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
 extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8fa7b6f9e19b..55062461b2fd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2046,7 +2046,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	p->state = TASK_WAKING;
 
 	if (p->in_iowait) {
-		delayacct_blkio_end();
+		delayacct_blkio_end(p);
 		atomic_dec(&task_rq(p)->nr_iowait);
 	}
 
@@ -2059,7 +2059,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 #else /* CONFIG_SMP */
 
 	if (p->in_iowait) {
-		delayacct_blkio_end();
+		delayacct_blkio_end(p);
 		atomic_dec(&task_rq(p)->nr_iowait);
 	}
 
@@ -2112,7 +2112,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
 
 	if (!task_on_rq_queued(p)) {
 		if (p->in_iowait) {
-			delayacct_blkio_end();
+			delayacct_blkio_end(p);
 			atomic_dec(&rq->nr_iowait);
 		}
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 73e3cdbc61f1..db5e6daadd94 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1656,7 +1656,7 @@ void run_local_timers(void)
 	hrtimer_run_queues();
 	/* Raise the softirq only if required. */
 	if (time_before(jiffies, base->clk)) {
-		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON))
 			return;
 		/* CPU is awake, so check the deferrable base. */
 		base++;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 87468398b9ed..d53268a4e167 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2213,6 +2213,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
 	const char *last_system = NULL;
+	bool first = false;
 	int last_i;
 	int i;
 
@@ -2220,15 +2221,28 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
 		/* events are usually grouped together with systems */
 		if (!last_system || call->class->system != last_system) {
+			first = true;
 			last_i = 0;
 			last_system = call->class->system;
 		}
 
+		/*
+		 * Since calls are grouped by systems, the likelyhood that the
+		 * next call in the iteration belongs to the same system as the
+		 * previous call is high. As an optimization, we skip seaching
+		 * for a map[] that matches the call's system if the last call
+		 * was from the same system. That's what last_i is for. If the
+		 * call has the same system as the previous call, then last_i
+		 * will be the index of the first map[] that has a matching
+		 * system.
+		 */
 		for (i = last_i; i < len; i++) {
 			if (call->class->system == map[i]->system) {
 				/* Save the first system if need be */
-				if (!last_i)
+				if (first) {
 					last_i = i;
+					first = false;
+				}
 				update_event_printk(call, map[i]);
 			}
 		}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a2dccfe1acec..8365a52a74c5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -48,6 +48,7 @@
 #include <linux/nodemask.h>
 #include <linux/moduleparam.h>
 #include <linux/uaccess.h>
+#include <linux/nmi.h>
 
 #include "workqueue_internal.h"
 
@@ -4479,6 +4480,12 @@ void show_workqueue_state(void)
 			if (pwq->nr_active || !list_empty(&pwq->delayed_works))
 				show_pwq(pwq);
 			spin_unlock_irqrestore(&pwq->pool->lock, flags);
+			/*
+			 * We could be printing a lot from atomic context, e.g.
+			 * sysrq-t -> show_workqueue_state(). Avoid triggering
+			 * hard lockup.
+			 */
+			touch_nmi_watchdog();
 		}
 	}
 
@@ -4506,6 +4513,12 @@ void show_workqueue_state(void)
 		pr_cont("\n");
 	next_pool:
 		spin_unlock_irqrestore(&pool->lock, flags);
+		/*
+		 * We could be printing a lot from atomic context, e.g.
+		 * sysrq-t -> show_workqueue_state(). Avoid triggering
+		 * hard lockup.
+		 */
+		touch_nmi_watchdog();
 	}
 
 	rcu_read_unlock_sched();
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index d22b84310f6d..956015614395 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -30,10 +30,29 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
 	return true;
 }
 
+/**
+ * check_pte - check if @pvmw->page is mapped at the @pvmw->pte
+ *
+ * page_vma_mapped_walk() found a place where @pvmw->page is *potentially*
+ * mapped. check_pte() has to validate this.
+ *
+ * @pvmw->pte may point to empty PTE, swap PTE or PTE pointing to arbitrary
+ * page.
+ *
+ * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration
+ * entry that points to @pvmw->page or any subpage in case of THP.
+ *
+ * If PVMW_MIGRATION flag is not set, returns true if @pvmw->pte points to
+ * @pvmw->page or any subpage in case of THP.
+ *
+ * Otherwise, return false.
+ *
+ */
 static bool check_pte(struct page_vma_mapped_walk *pvmw)
 {
+	unsigned long pfn;
+
 	if (pvmw->flags & PVMW_MIGRATION) {
-#ifdef CONFIG_MIGRATION
 		swp_entry_t entry;
 		if (!is_swap_pte(*pvmw->pte))
 			return false;
@@ -41,37 +60,31 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 
 		if (!is_migration_entry(entry))
 			return false;
-		if (migration_entry_to_page(entry) - pvmw->page >=
-				hpage_nr_pages(pvmw->page)) {
-			return false;
-		}
-		if (migration_entry_to_page(entry) < pvmw->page)
-			return false;
-#else
-		WARN_ON_ONCE(1);
-#endif
-	} else {
-		if (is_swap_pte(*pvmw->pte)) {
-			swp_entry_t entry;
 
-			entry = pte_to_swp_entry(*pvmw->pte);
-			if (is_device_private_entry(entry) &&
-			    device_private_entry_to_page(entry) == pvmw->page)
-				return true;
-		}
+		pfn = migration_entry_to_pfn(entry);
+	} else if (is_swap_pte(*pvmw->pte)) {
+		swp_entry_t entry;
 
-		if (!pte_present(*pvmw->pte))
+		/* Handle un-addressable ZONE_DEVICE memory */
+		entry = pte_to_swp_entry(*pvmw->pte);
+		if (!is_device_private_entry(entry))
 			return false;
 
-		/* THP can be referenced by any subpage */
-		if (pte_page(*pvmw->pte) - pvmw->page >=
-				hpage_nr_pages(pvmw->page)) {
-			return false;
-		}
-		if (pte_page(*pvmw->pte) < pvmw->page)
+		pfn = device_private_entry_to_pfn(entry);
+	} else {
+		if (!pte_present(*pvmw->pte))
 			return false;
+
+		pfn = pte_pfn(*pvmw->pte);
 	}
 
+	if (pfn < page_to_pfn(pvmw->page))
+		return false;
+
+	/* THP can be referenced by any subpage */
+	if (pfn - page_to_pfn(pvmw->page) >= hpage_nr_pages(pvmw->page))
+		return false;
+
 	return true;
 }
 
diff --git a/net/can/af_can.c b/net/can/af_can.c
index ecd5c703d11e..e3626e8500c2 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -721,20 +721,16 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (WARN_ONCE(dev->type != ARPHRD_CAN ||
-		      skb->len != CAN_MTU ||
-		      cfd->len > CAN_MAX_DLEN,
-		      "PF_CAN: dropped non conform CAN skbuf: "
-		      "dev type %d, len %d, datalen %d\n",
-		      dev->type, skb->len, cfd->len))
-		goto drop;
+	if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU ||
+		     cfd->len > CAN_MAX_DLEN)) {
+		pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n",
+			     dev->type, skb->len, cfd->len);
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
 
 	can_receive(skb, dev);
 	return NET_RX_SUCCESS;
-
-drop:
-	kfree_skb(skb);
-	return NET_RX_DROP;
 }
 
 static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -742,20 +738,16 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (WARN_ONCE(dev->type != ARPHRD_CAN ||
-		      skb->len != CANFD_MTU ||
-		      cfd->len > CANFD_MAX_DLEN,
-		      "PF_CAN: dropped non conform CAN FD skbuf: "
-		      "dev type %d, len %d, datalen %d\n",
-		      dev->type, skb->len, cfd->len))
-		goto drop;
+	if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU ||
+		     cfd->len > CANFD_MAX_DLEN)) {
+		pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n",
+			     dev->type, skb->len, cfd->len);
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
 
 	can_receive(skb, dev);
 	return NET_RX_SUCCESS;
-
-drop:
-	kfree_skb(skb);
-	return NET_RX_DROP;
 }
 
 /*
diff --git a/net/key/af_key.c b/net/key/af_key.c
index a00d607e7224..2ad693232f74 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -401,6 +401,11 @@ static int verify_address_len(const void *p)
 #endif
 	int len;
 
+	if (sp->sadb_address_len <
+	    DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family),
+			 sizeof(uint64_t)))
+		return -EINVAL;
+
 	switch (addr->sa_family) {
 	case AF_INET:
 		len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t));
@@ -511,6 +516,9 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void *
 		uint16_t ext_type;
 		int ext_len;
 
+		if (len < sizeof(*ehdr))
+			return -EINVAL;
+
 		ext_len  = ehdr->sadb_ext_len;
 		ext_len *= sizeof(uint64_t);
 		ext_type = ehdr->sadb_ext_type;
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index e63af4e19382..6bed45dc2cb1 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -270,12 +270,18 @@ else
 objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable)
 endif
 
+ifdef CONFIG_MODVERSIONS
+objtool_o = $(@D)/.tmp_$(@F)
+else
+objtool_o = $(@)
+endif
+
 # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file
 cmd_objtool = $(if $(patsubst y%,, \
 	$(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \
-	$(__objtool_obj) $(objtool_args) "$(@)";)
+	$(__objtool_obj) $(objtool_args) "$(objtool_o)";)
 objtool_obj = $(if $(patsubst y%,, \
 	$(OBJECT_FILES_NON_STANDARD_$(basetarget).o)$(OBJECT_FILES_NON_STANDARD)n), \
 	$(__objtool_obj))
@@ -291,15 +297,15 @@ objtool_dep = $(objtool_obj)					\
 define rule_cc_o_c
 	$(call echo-cmd,checksrc) $(cmd_checksrc)			  \
 	$(call cmd_and_fixdep,cc_o_c)					  \
-	$(cmd_modversions_c)						  \
 	$(call echo-cmd,objtool) $(cmd_objtool)				  \
+	$(cmd_modversions_c)						  \
 	$(call echo-cmd,record_mcount) $(cmd_record_mcount)
 endef
 
 define rule_as_o_S
 	$(call cmd_and_fixdep,as_o_S)					  \
-	$(cmd_modversions_S)						  \
-	$(call echo-cmd,objtool) $(cmd_objtool)
+	$(call echo-cmd,objtool) $(cmd_objtool)				  \
+	$(cmd_modversions_S)
 endef
 
 # List module undefined symbols (or empty line if not enabled)
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index 1bf949c43b76..f6ab3ccf698f 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -96,6 +96,8 @@ def get_thread_info(task):
         thread_info_addr = task.address + ia64_task_size
         thread_info = thread_info_addr.cast(thread_info_ptr_type)
     else:
+        if task.type.fields()[0].type == thread_info_type.get_type():
+            return task['thread_info']
         thread_info = task['stack'].cast(thread_info_ptr_type)
     return thread_info.dereference()
 
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index db7894bb028c..faa67861cbc1 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -560,7 +560,6 @@ static inline unsigned int muldiv32(unsigned int a, unsigned int b,
 {
 	u_int64_t n = (u_int64_t) a * b;
 	if (c == 0) {
-		snd_BUG_ON(!n);
 		*r = 0;
 		return UINT_MAX;
 	}
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index d10c780dfd54..ac30fc1ab98b 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -221,6 +221,7 @@ static struct snd_seq_client *seq_create_client1(int client_index, int poolsize)
 	rwlock_init(&client->ports_lock);
 	mutex_init(&client->ports_mutex);
 	INIT_LIST_HEAD(&client->ports_list_head);
+	mutex_init(&client->ioctl_mutex);
 
 	/* find free slot in the client table */
 	spin_lock_irqsave(&clients_lock, flags);
@@ -2126,7 +2127,9 @@ static long snd_seq_ioctl(struct file *file, unsigned int cmd,
 			return -EFAULT;
 	}
 
+	mutex_lock(&client->ioctl_mutex);
 	err = handler->func(client, &buf);
+	mutex_unlock(&client->ioctl_mutex);
 	if (err >= 0) {
 		/* Some commands includes a bug in 'dir' field. */
 		if (handler->cmd == SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT ||
diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h
index c6614254ef8a..0611e1e0ed5b 100644
--- a/sound/core/seq/seq_clientmgr.h
+++ b/sound/core/seq/seq_clientmgr.h
@@ -61,6 +61,7 @@ struct snd_seq_client {
 	struct list_head ports_list_head;
 	rwlock_t ports_lock;
 	struct mutex ports_mutex;
+	struct mutex ioctl_mutex;
 	int convert32;		/* convert 32->64bit */
 
 	/* output pool */
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 80bbadc83721..d6e079f4ec09 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -408,6 +408,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = {
 	/*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/
 
 	/* codec SSID */
+	SND_PCI_QUIRK(0x106b, 0x0600, "iMac 14,1", CS420X_IMAC27_122),
 	SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81),
 	SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122),
 	SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index acdb196ddb44..145e92d6ca94 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6173,6 +6173,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
+	SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index ae0272f9a091..e6acc281dd37 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -46,7 +46,7 @@ $(OBJTOOL_IN): fixdep FORCE
 	@$(MAKE) $(build)=objtool
 
 $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
-	@./sync-check.sh
+	@$(CONFIG_SHELL) ./sync-check.sh
 	$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
 
 
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 8acfc47af70e..540a209b78ab 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -138,7 +138,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 			*type = INSN_STACK;
 			op->src.type = OP_SRC_ADD;
 			op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
-			op->dest.type = OP_SRC_REG;
+			op->dest.type = OP_DEST_REG;
 			op->dest.reg = CFI_SP;
 		}
 		break;
diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c
index 4c6b5c9ef073..91e8e19ff5e0 100644
--- a/tools/objtool/builtin-orc.c
+++ b/tools/objtool/builtin-orc.c
@@ -44,6 +44,9 @@ int cmd_orc(int argc, const char **argv)
 	const char *objname;
 
 	argc--; argv++;
+	if (argc <= 0)
+		usage_with_options(orc_usage, check_options);
+
 	if (!strncmp(argv[0], "gen", 3)) {
 		argc = parse_options(argc, argv, check_options, orc_usage, 0);
 		if (argc != 1)
@@ -52,7 +55,6 @@ int cmd_orc(int argc, const char **argv)
 		objname = argv[0];
 
 		return check(objname, no_fp, no_unreachable, true);
-
 	}
 
 	if (!strcmp(argv[0], "dump")) {
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 24460155c82c..c1c338661699 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -26,6 +26,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <errno.h>
 
 #include "elf.h"
 #include "warn.h"
@@ -358,7 +359,8 @@ struct elf *elf_open(const char *name, int flags)
 
 	elf->fd = open(name, flags);
 	if (elf->fd == -1) {
-		perror("open");
+		fprintf(stderr, "objtool: Can't open '%s': %s\n",
+			name, strerror(errno));
 		goto err;
 	}
 
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index e5ca31429c9b..e61fe703197b 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -165,6 +165,8 @@ int create_orc_sections(struct objtool_file *file)
 
 	/* create .orc_unwind_ip and .rela.orc_unwind_ip sections */
 	sec = elf_create_section(file->elf, ".orc_unwind_ip", sizeof(int), idx);
+	if (!sec)
+		return -1;
 
 	ip_relasec = elf_create_rela_section(file->elf, sec);
 	if (!ip_relasec)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index b4b69c2d1012..9dea96380339 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1310,7 +1310,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
-	if (is_vm_hugetlb_page(vma) && !logging_active) {
+	if (vma_kernel_pagesize(vma) == PMD_SIZE && !logging_active) {
 		hugetlb = true;
 		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
 	} else {