Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

en_rx_am.c was deleted in 'net-next' but had a bug fixed in it in
'net'.

The esp{4,6}_offload.c conflicts were overlapping changes.
The 'out' label is removed so we just return ERR_PTR(-EINVAL)
directly.

Signed-off-by: David S. Miller <davem@davemloft.net>

31 files changed, 391 insertions, 48 deletions

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/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S
index 316a99aa9efe..1cfcfbbea6f0 100644
--- a/arch/alpha/lib/ev6-memset.S
+++ b/arch/alpha/lib/ev6-memset.S
@@ -18,7 +18,7 @@
  * The algorithm for the leading and trailing quadwords remains the same,
  * however the loop has been unrolled to enable better memory throughput,
  * and the code has been replicated for each of the entry points: __memset
- * and __memsetw to permit better scheduling to eliminate the stalling
+ * and __memset16 to permit better scheduling to eliminate the stalling
  * encountered during the mask replication.
  * A future enhancement might be to put in a byte store loop for really
  * small (say < 32 bytes) memset()s.  Whether or not that change would be
@@ -34,7 +34,7 @@
 	.globl memset
 	.globl __memset
 	.globl ___memset
-	.globl __memsetw
+	.globl __memset16
 	.globl __constant_c_memset
 
 	.ent ___memset
@@ -415,9 +415,9 @@ end:
 	 * to mask stalls.  Note that entry point names also had to change
 	 */
 	.align 5
-	.ent __memsetw
+	.ent __memset16
 
-__memsetw:
+__memset16:
 	.frame $30,0,$26,0
 	.prologue 0
 
@@ -596,8 +596,8 @@ end_w:
 	nop
 	ret $31,($26),1		# L0 :
 
-	.end __memsetw
-	EXPORT_SYMBOL(__memsetw)
+	.end __memset16
+	EXPORT_SYMBOL(__memset16)
 
 memset = ___memset
 __memset = ___memset
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 304203fa9e33..e60494f1eef9 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -45,7 +45,7 @@ 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;
 	}
 
@@ -54,7 +54,7 @@ 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/Kconfig b/arch/mips/Kconfig
index 350a990fc719..8e0b3702f1c0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -259,6 +259,7 @@ config BCM47XX
 	select LEDS_GPIO_REGISTER
 	select BCM47XX_NVRAM
 	select BCM47XX_SPROM
+	select BCM47XX_SSB if !BCM47XX_BCMA
 	help
 	 Support for BCM47XX based boards
 
@@ -389,6 +390,7 @@ config LANTIQ
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
+	select SYS_SUPPORTS_VPE_LOADER
 	select SYS_HAS_EARLY_PRINTK
 	select GPIOLIB
 	select SWAP_IO_SPACE
@@ -516,6 +518,7 @@ config MIPS_MALTA
 	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
 	select SYS_SUPPORTS_SMARTMIPS
+	select SYS_SUPPORTS_VPE_LOADER
 	select SYS_SUPPORTS_ZBOOT
 	select SYS_SUPPORTS_RELOCATABLE
 	select USE_OF
@@ -2281,9 +2284,16 @@ config MIPSR2_TO_R6_EMULATOR
 	  The only reason this is a build-time option is to save ~14K from the
 	  final kernel image.
 
+config SYS_SUPPORTS_VPE_LOADER
+	bool
+	depends on SYS_SUPPORTS_MULTITHREADING
+	help
+	  Indicates that the platform supports the VPE loader, and provides
+	  physical_memsize.
+
 config MIPS_VPE_LOADER
 	bool "VPE loader support."
-	depends on SYS_SUPPORTS_MULTITHREADING && MODULES
+	depends on SYS_SUPPORTS_VPE_LOADER && MODULES
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select MIPS_MT
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 464af5e025d6..0749c3724543 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -124,30 +124,36 @@ config SCACHE_DEBUGFS
 
 	  If unsure, say N.
 
-menuconfig MIPS_CPS_NS16550
+menuconfig MIPS_CPS_NS16550_BOOL
 	bool "CPS SMP NS16550 UART output"
 	depends on MIPS_CPS
 	help
 	  Output debug information via an ns16550 compatible UART if exceptions
 	  occur early in the boot process of a secondary core.
 
-if MIPS_CPS_NS16550
+if MIPS_CPS_NS16550_BOOL
+
+config MIPS_CPS_NS16550
+	def_bool MIPS_CPS_NS16550_BASE != 0
 
 config MIPS_CPS_NS16550_BASE
 	hex "UART Base Address"
 	default 0x1b0003f8 if MIPS_MALTA
+	default 0
 	help
 	  The base address of the ns16550 compatible UART on which to output
 	  debug information from the early stages of core startup.
 
+	  This is only used if non-zero.
+
 config MIPS_CPS_NS16550_SHIFT
 	int "UART Register Shift"
-	default 0 if MIPS_MALTA
+	default 0
 	help
 	  The number of bits to shift ns16550 register indices by in order to
 	  form their addresses. That is, log base 2 of the span between
 	  adjacent ns16550 registers in the system.
 
-endif # MIPS_CPS_NS16550
+endif # MIPS_CPS_NS16550_BOOL
 
 endmenu
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/ath25/devices.c b/arch/mips/ath25/devices.c
index e1156347da53..301a9028273c 100644
--- a/arch/mips/ath25/devices.c
+++ b/arch/mips/ath25/devices.c
@@ -73,6 +73,7 @@ const char *get_system_type(void)
 
 void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
 {
+#ifdef CONFIG_SERIAL_8250_CONSOLE
 	struct uart_port s;
 
 	memset(&s, 0, sizeof(s));
@@ -85,6 +86,7 @@ void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
 	s.uartclk = uartclk;
 
 	early_serial_setup(&s);
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
 }
 
 int __init ath25_add_wmac(int nr, u32 base, int irq)
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/mips/lib/Makefile b/arch/mips/lib/Makefile
index 78c2affeabf8..e84e12655fa8 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000)		+= r3k_dump_tlb.o
 obj-$(CONFIG_CPU_TX39XX)	+= r3k_dump_tlb.o
 
 # libgcc-style stuff needed in the kernel
-obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o
+obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \
+	 ucmpdi2.o
diff --git a/arch/mips/lib/libgcc.h b/arch/mips/lib/libgcc.h
index 28002ed90c2c..199a7f96282f 100644
--- a/arch/mips/lib/libgcc.h
+++ b/arch/mips/lib/libgcc.h
@@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mode (__word__)));
 struct DWstruct {
 	int high, low;
 };
+
+struct TWstruct {
+	long long high, low;
+};
 #elif defined(__LITTLE_ENDIAN)
 struct DWstruct {
 	int low, high;
 };
+
+struct TWstruct {
+	long long low, high;
+};
 #else
 #error I feel sick.
 #endif
@@ -23,4 +31,13 @@ typedef union {
 	long long ll;
 } DWunion;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6)
+typedef int ti_type __attribute__((mode(TI)));
+
+typedef union {
+	struct TWstruct s;
+	ti_type ti;
+} TWunion;
+#endif
+
 #endif /* __ASM_LIBGCC_H */
diff --git a/arch/mips/lib/multi3.c b/arch/mips/lib/multi3.c
new file mode 100644
index 000000000000..111ad475aa0c
--- /dev/null
+++ b/arch/mips/lib/multi3.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+
+#include "libgcc.h"
+
+/*
+ * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that
+ * specific case only we'll implement it here.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
+ */
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7)
+
+/* multiply 64-bit values, low 64-bits returned */
+static inline long long notrace dmulu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */
+static inline long long notrace dmuhu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 128-bit values, low 128-bits returned */
+ti_type notrace __multi3(ti_type a, ti_type b)
+{
+	TWunion res, aa, bb;
+
+	aa.ti = a;
+	bb.ti = b;
+
+	/*
+	 * a * b =           (a.lo * b.lo)
+	 *         + 2^64  * (a.hi * b.lo + a.lo * b.hi)
+	 *        [+ 2^128 * (a.hi * b.hi)]
+	 */
+	res.s.low = dmulu(aa.s.low, bb.s.low);
+	res.s.high = dmuhu(aa.s.low, bb.s.low);
+	res.s.high += dmulu(aa.s.high, bb.s.low);
+	res.s.high += dmulu(aa.s.low, bb.s.high);
+
+	return res.ti;
+}
+EXPORT_SYMBOL(__multi3);
+
+#endif /* 64BIT && CPU_MIPSR6 && GCC7 */
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index cdb5a191b9d5..9bb6baa45da3 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -40,7 +40,7 @@
 
 #include "uasm.c"
 
-static const struct insn const insn_table_MM[insn_invalid] = {
+static const struct insn insn_table_MM[insn_invalid] = {
 	[insn_addu]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD},
 	[insn_addiu]	= {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
 	[insn_and]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD},
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
index d4469b20d176..4f46a4509f79 100644
--- a/arch/mips/ralink/timer.c
+++ b/arch/mips/ralink/timer.c
@@ -109,9 +109,9 @@ static int rt_timer_probe(struct platform_device *pdev)
 	}
 
 	rt->irq = platform_get_irq(pdev, 0);
-	if (!rt->irq) {
+	if (rt->irq < 0) {
 		dev_err(&pdev->dev, "failed to load irq\n");
-		return -ENOENT;
+		return rt->irq;
 	}
 
 	rt->membase = devm_ioremap_resource(&pdev->dev, res);
diff --git a/arch/mips/rb532/Makefile b/arch/mips/rb532/Makefile
index efdecdb6e3ea..8186afca2234 100644
--- a/arch/mips/rb532/Makefile
+++ b/arch/mips/rb532/Makefile
@@ -2,4 +2,6 @@
 # Makefile for the RB532 board specific parts of the kernel
 #
 
-obj-y	 += irq.o time.o setup.o serial.o prom.o gpio.o devices.o
+obj-$(CONFIG_SERIAL_8250_CONSOLE) += serial.o
+
+obj-y	 += irq.o time.o setup.o prom.o gpio.o devices.o
diff --git a/arch/mips/rb532/devices.c b/arch/mips/rb532/devices.c
index 32ea3e6731d6..354d258396ff 100644
--- a/arch/mips/rb532/devices.c
+++ b/arch/mips/rb532/devices.c
@@ -310,6 +310,8 @@ static int __init plat_setup_devices(void)
 	return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs));
 }
 
+#ifdef CONFIG_NET
+
 static int __init setup_kmac(char *s)
 {
 	printk(KERN_INFO "korina mac = %s\n", s);
@@ -322,4 +324,6 @@ static int __init setup_kmac(char *s)
 
 __setup("kmac=", setup_kmac);
 
+#endif /* CONFIG_NET */
+
 arch_initcall(plat_setup_devices);
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 61d6049f4c1e..637b7263cb86 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
 	__u32	ap_encodings[8];
 };
 
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31		(1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED	(1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30	(1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2	(1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV	(1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1915e86cef6f..0a7c88786ec0 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,6 +39,10 @@
 #include <asm/iommu.h>
 #include <asm/switch_to.h>
 #include <asm/xive.h>
+#ifdef CONFIG_PPC_PSERIES
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#endif
 
 #include "timing.h"
 #include "irq.h"
@@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS:
 #endif
+	case KVM_CAP_PPC_GET_CPU_CHAR:
 		r = 1;
 		break;
 
@@ -1759,6 +1764,124 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return r;
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * These functions check whether the underlying hardware is safe
+ * against attacks based on observing the effects of speculatively
+ * executed instructions, and whether it supplies instructions for
+ * use in workarounds.  The information comes from firmware, either
+ * via the device tree on powernv platforms or from an hcall on
+ * pseries platforms.
+ */
+#ifdef CONFIG_PPC_PSERIES
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct h_cpu_char_result c;
+	unsigned long rc;
+
+	if (!machine_is(pseries))
+		return -ENOTTY;
+
+	rc = plpar_get_cpu_characteristics(&c);
+	if (rc == H_SUCCESS) {
+		cp->character = c.character;
+		cp->behaviour = c.behaviour;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_BR_HINT_HONOURED |
+			KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+	}
+	return 0;
+}
+#else
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	return -ENOTTY;
+}
+#endif
+
+static inline bool have_fw_feat(struct device_node *fw_features,
+				const char *state, const char *name)
+{
+	struct device_node *np;
+	bool r = false;
+
+	np = of_get_child_by_name(fw_features, name);
+	if (np) {
+		r = of_property_read_bool(np, state);
+		of_node_put(np);
+	}
+	return r;
+}
+
+static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct device_node *np, *fw_features;
+	int r;
+
+	memset(cp, 0, sizeof(*cp));
+	r = pseries_get_cpu_char(cp);
+	if (r != -ENOTTY)
+		return r;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	if (np) {
+		fw_features = of_get_child_by_name(np, "fw-features");
+		of_node_put(np);
+		if (!fw_features)
+			return 0;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-spec-barrier-ori31,31,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-bcctrl-serialized"))
+			cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-ori30,30,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-trig2"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-l1d-thread-split"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-count-cache-disabled"))
+			cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+
+		if (have_fw_feat(fw_features, "enabled",
+				 "speculation-policy-favor-security"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-l1d-flush-msr-pr-0-to-1"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-spec-barrier-for-bound-checks"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+
+		of_node_put(fw_features);
+	}
+
+	return 0;
+}
+#endif
+
 long kvm_arch_vm_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
 {
@@ -1861,6 +1984,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_PPC_GET_CPU_CHAR: {
+		struct kvm_ppc_cpu_char cpuchar;
+
+		r = kvmppc_get_cpu_char(&cpuchar);
+		if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar)))
+			r = -EFAULT;
+		break;
+	}
 	default: {
 		struct kvm *kvm = filp->private_data;
 		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e14f381757f6..c1b0a9ac1dc8 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -207,7 +207,8 @@ struct kvm_s390_sie_block {
 	__u16	ipa;			/* 0x0056 */
 	__u32	ipb;			/* 0x0058 */
 	__u32	scaoh;			/* 0x005c */
-	__u8	reserved60;		/* 0x0060 */
+#define FPF_BPBC 	0x20
+	__u8	fpf;			/* 0x0060 */
 #define ECB_GS		0x40
 #define ECB_TE		0x10
 #define ECB_SRSI	0x04
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 38535a57fef8..4cdaa55fabfe 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -224,6 +224,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_RICCB  (1UL << 7)
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
+#define KVM_SYNC_BPBC   (1UL << 10)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -247,7 +248,9 @@ struct kvm_sync_regs {
 	};
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
-	__u8 padding1[52];	/* riccb needs to be 64byte aligned */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
+	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
 	union {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2c93cbbcd15e..2598cf243b86 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -421,6 +421,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_GS:
 		r = test_facility(133);
 		break;
+	case KVM_CAP_S390_BPB:
+		r = test_facility(82);
+		break;
 	default:
 		r = 0;
 	}
@@ -2198,6 +2201,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
 	if (test_kvm_facility(vcpu->kvm, 133))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
 	/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2339,6 +2344,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
@@ -3298,6 +3304,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
 		vcpu->arch.gs_enabled = 1;
 	}
+	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+	    test_kvm_facility(vcpu->kvm, 82)) {
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+	}
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	/* save host (userspace) fprs/vrs */
@@ -3344,6 +3355,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
 	/* Save guest register state */
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 5d6ae0326d9e..751348348477 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -223,6 +223,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	memcpy(scb_o->gcr, scb_s->gcr, 128);
 	scb_o->pp = scb_s->pp;
 
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82)) {
+		scb_o->fpf &= ~FPF_BPBC;
+		scb_o->fpf |= scb_s->fpf & FPF_BPBC;
+	}
+
 	/* interrupt intercept */
 	switch (scb_s->icptcode) {
 	case ICPT_PROGI:
@@ -265,6 +271,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	scb_s->ecb3 = 0;
 	scb_s->ecd = 0;
 	scb_s->fac = 0;
+	scb_s->fpf = 0;
 
 	rc = prepare_cpuflags(vcpu, vsie_page);
 	if (rc)
@@ -324,6 +331,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			prefix_unmapped(vsie_page);
 		scb_s->ecb |= scb_o->ecb & ECB_TE;
 	}
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82))
+		scb_s->fpf |= scb_o->fpf & FPF_BPBC;
 	/* SIMD */
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		scb_s->eca |= scb_o->eca & ECA_VX;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index aa15b4c0e3d1..ff6f8022612c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1264,7 +1264,7 @@ 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/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7b45d8424150..4ad41087ce0e 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -194,6 +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
@@ -203,16 +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/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b1d616d08eee..868e412b4f0c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1785,6 +1785,11 @@ 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/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index e941136e24d8..203d398802a3 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"
 
@@ -203,7 +204,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
 }
 
 /* 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 */
@@ -237,6 +238,26 @@ 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 832a6acd730f..cb368c2a22ab 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/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/kvm/x86.c b/arch/x86/kvm/x86.c
index 1cec2c62a0b0..c53298dfbf50 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7496,13 +7496,13 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
 
 int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) {
+	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
 		 * When EFER.LME and CR0.PG are set, the processor is in
 		 * 64-bit mode (though maybe in a 32-bit code segment).
 		 * CR4.PAE and EFER.LMA must be set.
 		 */
-		if (!(sregs->cr4 & X86_CR4_PAE_BIT)
+		if (!(sregs->cr4 & X86_CR4_PAE)
 		    || !(sregs->efer & EFER_LMA))
 			return -EINVAL;
 	} else {
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/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 3ef362f598e3..e1d61e8500f9 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -738,7 +738,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
 	return total;
 }
 
-void __init sme_encrypt_kernel(struct boot_params *bp)
+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;