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

32 files changed, 366 insertions, 180 deletions

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 3f2eb76243e3..d5562f9ce600 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -148,7 +148,8 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->fullmm = !(start | (end+1));
@@ -166,8 +167,14 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 }
 
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+			unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->range_start = start;
+		tlb->range_end = end;
+	}
+
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index fced197b9626..cbe5ac3699bf 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -168,7 +168,8 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->max = ARRAY_SIZE(tlb->local);
@@ -185,8 +186,11 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
  * collected.
  */
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+			unsigned long start, unsigned long end, bool force)
 {
+	if (force)
+		tlb->need_flush = 1;
 	/*
 	 * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
 	 * tlb->end_addr.
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8dd20358464f..48d91d5be4e9 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2260,7 +2260,7 @@ config CPU_R4K_CACHE_TLB
 
 config MIPS_MT_SMP
 	bool "MIPS MT SMP support (1 TC on each available VPE)"
-	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6
+	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6 && !CPU_MICROMIPS
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select SYNC_R4K
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 04343625b929..bc2708c9ada4 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -243,8 +243,21 @@ include arch/mips/Kbuild.platforms
 ifdef CONFIG_PHYSICAL_START
 load-y					= $(CONFIG_PHYSICAL_START)
 endif
-entry-y				= 0x$(shell $(NM) vmlinux 2>/dev/null \
+
+entry-noisa-y				= 0x$(shell $(NM) vmlinux 2>/dev/null \
 					| grep "\bkernel_entry\b" | cut -f1 -d \ )
+ifdef CONFIG_CPU_MICROMIPS
+  #
+  # Set the ISA bit, since the kernel_entry symbol in the ELF will have it
+  # clear which would lead to images containing addresses which bootloaders may
+  # jump to as MIPS32 code.
+  #
+  entry-y = $(patsubst %0,%1,$(patsubst %2,%3,$(patsubst %4,%5, \
+              $(patsubst %6,%7,$(patsubst %8,%9,$(patsubst %a,%b, \
+              $(patsubst %c,%d,$(patsubst %e,%f,$(entry-noisa-y)))))))))
+else
+  entry-y = $(entry-noisa-y)
+endif
 
 cflags-y			+= -I$(srctree)/arch/mips/include/asm/mach-generic
 drivers-$(CONFIG_PCI)		+= arch/mips/pci/
diff --git a/arch/mips/boot/compressed/.gitignore b/arch/mips/boot/compressed/.gitignore
new file mode 100644
index 000000000000..ebae133f1d00
--- /dev/null
+++ b/arch/mips/boot/compressed/.gitignore
@@ -0,0 +1,2 @@
+ashldi3.c
+bswapsi.c
diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c
index 542be1cd0f32..bfdfaf32d2c4 100644
--- a/arch/mips/cavium-octeon/octeon-usb.c
+++ b/arch/mips/cavium-octeon/octeon-usb.c
@@ -13,9 +13,9 @@
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/of_platform.h>
+#include <linux/io.h>
 
 #include <asm/octeon/octeon.h>
-#include <asm/octeon/cvmx-gpio-defs.h>
 
 /* USB Control Register */
 union cvm_usbdrd_uctl_ctl {
diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S
index 1910223a9c02..cea2bb1621e6 100644
--- a/arch/mips/dec/int-handler.S
+++ b/arch/mips/dec/int-handler.S
@@ -147,23 +147,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1, cpu_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, cpu_mask_nr_tbl
 		lui	t1, %hi(cpu_mask_nr_tbl)
 		addiu	t1, %lo(cpu_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, cpu_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(cpu_mask_nr_tbl)
-		lui	AT, %hi(cpu_mask_nr_tbl)
-		daddiu	t1, t1, %higher(cpu_mask_nr_tbl)
-		daddiu	AT, AT, %lo(cpu_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 1:		lw	t2,(t1)
 		nop
@@ -214,23 +203,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1,asic_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, asic_mask_nr_tbl
 		lui	t1, %hi(asic_mask_nr_tbl)
 		addiu	t1, %lo(asic_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, asic_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(asic_mask_nr_tbl)
-		lui	AT, %hi(asic_mask_nr_tbl)
-		daddiu	t1, t1, %higher(asic_mask_nr_tbl)
-		daddiu	AT, AT, %lo(asic_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 2:		lw	t2,(t1)
 		nop
diff --git a/arch/mips/include/asm/cache.h b/arch/mips/include/asm/cache.h
index fc67947ed658..8b14c2706aa5 100644
--- a/arch/mips/include/asm/cache.h
+++ b/arch/mips/include/asm/cache.h
@@ -9,6 +9,8 @@
 #ifndef _ASM_CACHE_H
 #define _ASM_CACHE_H
 
+#include <kmalloc.h>
+
 #define L1_CACHE_SHIFT		CONFIG_MIPS_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 8baa9033b181..721b698bfe3c 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -428,6 +428,9 @@
 #ifndef cpu_scache_line_size
 #define cpu_scache_line_size()	cpu_data[0].scache.linesz
 #endif
+#ifndef cpu_tcache_line_size
+#define cpu_tcache_line_size()	cpu_data[0].tcache.linesz
+#endif
 
 #ifndef cpu_hwrena_impl_bits
 #define cpu_hwrena_impl_bits		0
diff --git a/arch/mips/include/asm/octeon/cvmx-l2c-defs.h b/arch/mips/include/asm/octeon/cvmx-l2c-defs.h
index d045973ddb33..3ea84acf1814 100644
--- a/arch/mips/include/asm/octeon/cvmx-l2c-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-l2c-defs.h
@@ -33,6 +33,10 @@
 #define CVMX_L2C_DBG (CVMX_ADD_IO_SEG(0x0001180080000030ull))
 #define CVMX_L2C_CFG (CVMX_ADD_IO_SEG(0x0001180080000000ull))
 #define CVMX_L2C_CTL (CVMX_ADD_IO_SEG(0x0001180080800000ull))
+#define CVMX_L2C_ERR_TDTX(block_id)					       \
+	(CVMX_ADD_IO_SEG(0x0001180080A007E0ull) + ((block_id) & 3) * 0x40000ull)
+#define CVMX_L2C_ERR_TTGX(block_id)					       \
+	(CVMX_ADD_IO_SEG(0x0001180080A007E8ull) + ((block_id) & 3) * 0x40000ull)
 #define CVMX_L2C_LCKBASE (CVMX_ADD_IO_SEG(0x0001180080000058ull))
 #define CVMX_L2C_LCKOFF (CVMX_ADD_IO_SEG(0x0001180080000060ull))
 #define CVMX_L2C_PFCTL (CVMX_ADD_IO_SEG(0x0001180080000090ull))
@@ -66,9 +70,40 @@
 		((offset) & 1) * 8)
 #define CVMX_L2C_WPAR_PPX(offset) (CVMX_ADD_IO_SEG(0x0001180080840000ull)    + \
 		((offset) & 31) * 8)
-#define CVMX_L2D_FUS3 (CVMX_ADD_IO_SEG(0x00011800800007B8ull))
 
 
+union cvmx_l2c_err_tdtx {
+	uint64_t u64;
+	struct cvmx_l2c_err_tdtx_s {
+		__BITFIELD_FIELD(uint64_t dbe:1,
+		__BITFIELD_FIELD(uint64_t sbe:1,
+		__BITFIELD_FIELD(uint64_t vdbe:1,
+		__BITFIELD_FIELD(uint64_t vsbe:1,
+		__BITFIELD_FIELD(uint64_t syn:10,
+		__BITFIELD_FIELD(uint64_t reserved_22_49:28,
+		__BITFIELD_FIELD(uint64_t wayidx:18,
+		__BITFIELD_FIELD(uint64_t reserved_2_3:2,
+		__BITFIELD_FIELD(uint64_t type:2,
+		;)))))))))
+	} s;
+};
+
+union cvmx_l2c_err_ttgx {
+	uint64_t u64;
+	struct cvmx_l2c_err_ttgx_s {
+		__BITFIELD_FIELD(uint64_t dbe:1,
+		__BITFIELD_FIELD(uint64_t sbe:1,
+		__BITFIELD_FIELD(uint64_t noway:1,
+		__BITFIELD_FIELD(uint64_t reserved_56_60:5,
+		__BITFIELD_FIELD(uint64_t syn:6,
+		__BITFIELD_FIELD(uint64_t reserved_22_49:28,
+		__BITFIELD_FIELD(uint64_t wayidx:15,
+		__BITFIELD_FIELD(uint64_t reserved_2_6:5,
+		__BITFIELD_FIELD(uint64_t type:2,
+		;)))))))))
+	} s;
+};
+
 union cvmx_l2c_cfg {
 	uint64_t u64;
 	struct cvmx_l2c_cfg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-l2d-defs.h b/arch/mips/include/asm/octeon/cvmx-l2d-defs.h
new file mode 100644
index 000000000000..a951ad5d65ad
--- /dev/null
+++ b/arch/mips/include/asm/octeon/cvmx-l2d-defs.h
@@ -0,0 +1,60 @@
+/***********************license start***************
+ * Author: Cavium Networks
+ *
+ * Contact: support@caviumnetworks.com
+ * This file is part of the OCTEON SDK
+ *
+ * Copyright (c) 2003-2017 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this file; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ * or visit http://www.gnu.org/licenses/.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium Networks for more information
+ ***********************license end**************************************/
+
+#ifndef __CVMX_L2D_DEFS_H__
+#define __CVMX_L2D_DEFS_H__
+
+#define CVMX_L2D_ERR	(CVMX_ADD_IO_SEG(0x0001180080000010ull))
+#define CVMX_L2D_FUS3	(CVMX_ADD_IO_SEG(0x00011800800007B8ull))
+
+
+union cvmx_l2d_err {
+	uint64_t u64;
+	struct cvmx_l2d_err_s {
+		__BITFIELD_FIELD(uint64_t reserved_6_63:58,
+		__BITFIELD_FIELD(uint64_t bmhclsel:1,
+		__BITFIELD_FIELD(uint64_t ded_err:1,
+		__BITFIELD_FIELD(uint64_t sec_err:1,
+		__BITFIELD_FIELD(uint64_t ded_intena:1,
+		__BITFIELD_FIELD(uint64_t sec_intena:1,
+		__BITFIELD_FIELD(uint64_t ecc_ena:1,
+		;)))))))
+	} s;
+};
+
+union cvmx_l2d_fus3 {
+	uint64_t u64;
+	struct cvmx_l2d_fus3_s {
+		__BITFIELD_FIELD(uint64_t reserved_40_63:24,
+		__BITFIELD_FIELD(uint64_t ema_ctl:3,
+		__BITFIELD_FIELD(uint64_t reserved_34_36:3,
+		__BITFIELD_FIELD(uint64_t q3fus:34,
+		;))))
+	} s;
+};
+
+#endif
diff --git a/arch/mips/include/asm/octeon/cvmx.h b/arch/mips/include/asm/octeon/cvmx.h
index 9742202f2a32..e638735cc3ac 100644
--- a/arch/mips/include/asm/octeon/cvmx.h
+++ b/arch/mips/include/asm/octeon/cvmx.h
@@ -62,6 +62,7 @@ enum cvmx_mips_space {
 #include <asm/octeon/cvmx-iob-defs.h>
 #include <asm/octeon/cvmx-ipd-defs.h>
 #include <asm/octeon/cvmx-l2c-defs.h>
+#include <asm/octeon/cvmx-l2d-defs.h>
 #include <asm/octeon/cvmx-l2t-defs.h>
 #include <asm/octeon/cvmx-led-defs.h>
 #include <asm/octeon/cvmx-mio-defs.h>
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 770d4d1516cb..6bace7695788 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -376,9 +376,6 @@ asmlinkage void start_secondary(void)
 	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
-	complete(&cpu_running);
-	synchronise_count_slave(cpu);
-
 	set_cpu_online(cpu, true);
 
 	set_cpu_sibling_map(cpu);
@@ -386,6 +383,9 @@ asmlinkage void start_secondary(void)
 
 	calculate_cpu_foreign_map();
 
+	complete(&cpu_running);
+	synchronise_count_slave(cpu);
+
 	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
 	 * is dangerous.
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 3f74f6c1f065..9fea6c6bbf49 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -48,7 +48,7 @@
 
 #include "uasm.c"
 
-static const struct insn const insn_table[insn_invalid] = {
+static const struct insn insn_table[insn_invalid] = {
 	[insn_addiu]	= {M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM},
 	[insn_addu]	= {M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD},
 	[insn_and]	= {M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD},
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index bd67ac74fe2d..9632436d74d7 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -28,16 +28,15 @@ EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
 
 static int __init pcibios_set_cache_line_size(void)
 {
-	struct cpuinfo_mips *c = &current_cpu_data;
 	unsigned int lsize;
 
 	/*
 	 * Set PCI cacheline size to that of the highest level in the
 	 * cache hierarchy.
 	 */
-	lsize = c->dcache.linesz;
-	lsize = c->scache.linesz ? : lsize;
-	lsize = c->tcache.linesz ? : lsize;
+	lsize = cpu_dcache_line_size();
+	lsize = cpu_scache_line_size() ? : lsize;
+	lsize = cpu_tcache_line_size() ? : lsize;
 
 	BUG_ON(!lsize);
 
diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c
index 974276e828b2..e2690d7ca4dd 100644
--- a/arch/mips/vdso/gettimeofday.c
+++ b/arch/mips/vdso/gettimeofday.c
@@ -35,7 +35,8 @@ static __always_inline long gettimeofday_fallback(struct timeval *_tv,
 	"       syscall\n"
 	: "=r" (ret), "=r" (error)
 	: "r" (tv), "r" (tz), "r" (nr)
-	: "memory");
+	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
+	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
 
 	return error ? -ret : ret;
 }
@@ -55,7 +56,8 @@ static __always_inline long clock_gettime_fallback(clockid_t _clkid,
 	"       syscall\n"
 	: "=r" (ret), "=r" (error)
 	: "r" (clkid), "r" (ts), "r" (nr)
-	: "memory");
+	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
+	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
 
 	return error ? -ret : ret;
 }
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 0695ce047d56..34fc9bbfca9e 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -293,7 +293,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 5175028c56ce..c5246d29f385 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -324,7 +324,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 1a61aa20dfba..fd5d98a0b95c 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -291,7 +291,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 49d8422767b4..e925c1c99c71 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -223,17 +223,27 @@ system_call_exit:
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	.Lsyscall_exit_work
 
-	/* If MSR_FP and MSR_VEC are set in user msr, then no need to restore */
-	li	r7,MSR_FP
+	andi.	r0,r8,MSR_FP
+	beq 2f
 #ifdef CONFIG_ALTIVEC
-	oris	r7,r7,MSR_VEC@h
+	andis.	r0,r8,MSR_VEC@h
+	bne	3f
 #endif
-	and	r0,r8,r7
-	cmpd	r0,r7
-	bne	.Lsyscall_restore_math
-.Lsyscall_restore_math_cont:
+2:	addi    r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_PPC_BOOK3S
+	li	r10,MSR_RI
+	mtmsrd	r10,1		/* Restore RI */
+#endif
+	bl	restore_math
+#ifdef CONFIG_PPC_BOOK3S
+	li	r11,0
+	mtmsrd	r11,1
+#endif
+	ld	r8,_MSR(r1)
+	ld	r3,RESULT(r1)
+	li	r11,-MAX_ERRNO
 
-	cmpld	r3,r11
+3:	cmpld	r3,r11
 	ld	r5,_CCR(r1)
 	bge-	.Lsyscall_error
 .Lsyscall_error_cont:
@@ -267,40 +277,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	std	r5,_CCR(r1)
 	b	.Lsyscall_error_cont
 
-.Lsyscall_restore_math:
-	/*
-	 * Some initial tests from restore_math to avoid the heavyweight
-	 * C code entry and MSR manipulations.
-	 */
-	LOAD_REG_IMMEDIATE(r0, MSR_TS_MASK)
-	and.	r0,r0,r8
-	bne	1f
-
-	ld	r7,PACACURRENT(r13)
-	lbz	r0,THREAD+THREAD_LOAD_FP(r7)
-#ifdef CONFIG_ALTIVEC
-	lbz	r6,THREAD+THREAD_LOAD_VEC(r7)
-	add	r0,r0,r6
-#endif
-	cmpdi	r0,0
-	beq	.Lsyscall_restore_math_cont
-
-1:	addi    r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_PPC_BOOK3S
-	li	r10,MSR_RI
-	mtmsrd	r10,1		/* Restore RI */
-#endif
-	bl	restore_math
-#ifdef CONFIG_PPC_BOOK3S
-	li	r11,0
-	mtmsrd	r11,1
-#endif
-	/* Restore volatiles, reload MSR from updated one */
-	ld	r8,_MSR(r1)
-	ld	r3,RESULT(r1)
-	li	r11,-MAX_ERRNO
-	b	.Lsyscall_restore_math_cont
-
 /* Traced system call support */
 .Lsyscall_dotrace:
 	bl	save_nvgprs
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9f3e2c932dcc..ec480966f9bf 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -511,10 +511,6 @@ void restore_math(struct pt_regs *regs)
 {
 	unsigned long msr;
 
-	/*
-	 * Syscall exit makes a similar initial check before branching
-	 * to restore_math. Keep them in synch.
-	 */
 	if (!msr_tm_active(regs->msr) &&
 		!current->thread.load_fp && !loadvec(current->thread))
 		return;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index cf0e1245b8cc..8d3320562c70 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -351,7 +351,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 	hard_irq_disable();
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
 		raw_local_irq_restore(*flags);
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 		raw_local_irq_save(*flags);
 		hard_irq_disable();
 	}
@@ -360,7 +360,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 static void nmi_ipi_lock(void)
 {
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 }
 
 static void nmi_ipi_unlock(void)
@@ -475,7 +475,7 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
 	nmi_ipi_lock_start(&flags);
 	while (nmi_ipi_busy_count) {
 		nmi_ipi_unlock_end(&flags);
-		cpu_relax();
+		spin_until_cond(nmi_ipi_busy_count == 0);
 		nmi_ipi_lock_start(&flags);
 	}
 
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index b67f8b03a32d..34721a257a77 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -71,15 +71,20 @@ static inline void wd_smp_lock(unsigned long *flags)
 	 * This may be called from low level interrupt handlers at some
 	 * point in future.
 	 */
-	local_irq_save(*flags);
-	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock)))
-		cpu_relax();
+	raw_local_irq_save(*flags);
+	hard_irq_disable(); /* Make it soft-NMI safe */
+	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) {
+		raw_local_irq_restore(*flags);
+		spin_until_cond(!test_bit(0, &__wd_smp_lock));
+		raw_local_irq_save(*flags);
+		hard_irq_disable();
+	}
 }
 
 static inline void wd_smp_unlock(unsigned long *flags)
 {
 	clear_bit_unlock(0, &__wd_smp_lock);
-	local_irq_restore(*flags);
+	raw_local_irq_restore(*flags);
 }
 
 static void wd_lockup_ipi(struct pt_regs *regs)
@@ -96,10 +101,10 @@ static void wd_lockup_ipi(struct pt_regs *regs)
 		nmi_panic(regs, "Hard LOCKUP");
 }
 
-static void set_cpu_stuck(int cpu, u64 tb)
+static void set_cpumask_stuck(const struct cpumask *cpumask, u64 tb)
 {
-	cpumask_set_cpu(cpu, &wd_smp_cpus_stuck);
-	cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+	cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask);
+	cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask);
 	if (cpumask_empty(&wd_smp_cpus_pending)) {
 		wd_smp_last_reset_tb = tb;
 		cpumask_andnot(&wd_smp_cpus_pending,
@@ -107,6 +112,10 @@ static void set_cpu_stuck(int cpu, u64 tb)
 				&wd_smp_cpus_stuck);
 	}
 }
+static void set_cpu_stuck(int cpu, u64 tb)
+{
+	set_cpumask_stuck(cpumask_of(cpu), tb);
+}
 
 static void watchdog_smp_panic(int cpu, u64 tb)
 {
@@ -135,11 +144,9 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 	}
 	smp_flush_nmi_ipi(1000000);
 
-	/* Take the stuck CPU out of the watch group */
-	for_each_cpu(c, &wd_smp_cpus_pending)
-		set_cpu_stuck(c, tb);
+	/* Take the stuck CPUs out of the watch group */
+	set_cpumask_stuck(&wd_smp_cpus_pending, tb);
 
-out:
 	wd_smp_unlock(&flags);
 
 	printk_safe_flush();
@@ -152,6 +159,11 @@ out:
 
 	if (hardlockup_panic)
 		nmi_panic(NULL, "Hard LOCKUP");
+
+	return;
+
+out:
+	wd_smp_unlock(&flags);
 }
 
 static void wd_smp_clear_cpu_pending(int cpu, u64 tb)
@@ -258,9 +270,11 @@ static void wd_timer_fn(unsigned long data)
 
 void arch_touch_nmi_watchdog(void)
 {
+	unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000;
 	int cpu = smp_processor_id();
 
-	watchdog_timer_interrupt(cpu);
+	if (get_tb() - per_cpu(wd_timer_tb, cpu) >= ticks)
+		watchdog_timer_interrupt(cpu);
 }
 EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
@@ -283,6 +297,8 @@ static void stop_watchdog_timer_on(unsigned int cpu)
 
 static int start_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
 		WARN_ON(1);
 		return 0;
@@ -297,12 +313,14 @@ static int start_wd_on_cpu(unsigned int cpu)
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
+	wd_smp_lock(&flags);
 	cpumask_set_cpu(cpu, &wd_cpus_enabled);
 	if (cpumask_weight(&wd_cpus_enabled) == 1) {
 		cpumask_set_cpu(cpu, &wd_smp_cpus_pending);
 		wd_smp_last_reset_tb = get_tb();
 	}
-	smp_wmb();
+	wd_smp_unlock(&flags);
+
 	start_watchdog_timer_on(cpu);
 
 	return 0;
@@ -310,12 +328,17 @@ static int start_wd_on_cpu(unsigned int cpu)
 
 static int stop_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
 		return 0; /* Can happen in CPU unplug case */
 
 	stop_watchdog_timer_on(cpu);
 
+	wd_smp_lock(&flags);
 	cpumask_clear_cpu(cpu, &wd_cpus_enabled);
+	wd_smp_unlock(&flags);
+
 	wd_smp_clear_cpu_pending(cpu, get_tb());
 
 	return 0;
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 2abee070373f..a553aeea7af6 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -56,6 +56,7 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
  */
 static u64 pnv_deepest_stop_psscr_val;
 static u64 pnv_deepest_stop_psscr_mask;
+static u64 pnv_deepest_stop_flag;
 static bool deepest_stop_found;
 
 static int pnv_save_sprs_for_deep_states(void)
@@ -185,8 +186,40 @@ static void pnv_alloc_idle_core_states(void)
 
 	update_subcore_sibling_mask();
 
-	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
-		pnv_save_sprs_for_deep_states();
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
+		int rc = pnv_save_sprs_for_deep_states();
+
+		if (likely(!rc))
+			return;
+
+		/*
+		 * The stop-api is unable to restore hypervisor
+		 * resources on wakeup from platform idle states which
+		 * lose full context. So disable such states.
+		 */
+		supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
+		pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
+		pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
+
+		if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+		    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
+			/*
+			 * Use the default stop state for CPU-Hotplug
+			 * if available.
+			 */
+			if (default_stop_found) {
+				pnv_deepest_stop_psscr_val =
+					pnv_default_stop_val;
+				pnv_deepest_stop_psscr_mask =
+					pnv_default_stop_mask;
+				pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
+					pnv_deepest_stop_psscr_val);
+			} else { /* Fallback to snooze loop for CPU-Hotplug */
+				deepest_stop_found = false;
+				pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
+			}
+		}
+	}
 }
 
 u32 pnv_get_supported_cpuidle_states(void)
@@ -375,7 +408,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 						pnv_deepest_stop_psscr_val;
 		srr1 = power9_idle_stop(psscr);
 
-	} else if (idle_states & OPAL_PM_WINKLE_ENABLED) {
+	} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
+		   (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
 		srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
 	} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
 		   (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
@@ -553,6 +587,7 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 			max_residency_ns = residency_ns[i];
 			pnv_deepest_stop_psscr_val = psscr_val[i];
 			pnv_deepest_stop_psscr_mask = psscr_mask[i];
+			pnv_deepest_stop_flag = flags[i];
 			deepest_stop_found = true;
 		}
 
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 7317b3108a88..2eb8ff0d6fca 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -47,10 +47,9 @@ struct mmu_table_batch {
 extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
-static inline void tlb_gather_mmu(struct mmu_gather *tlb,
-				  struct mm_struct *mm,
-				  unsigned long start,
-				  unsigned long end)
+static inline void
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+			unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -76,9 +75,15 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 	tlb_flush_mmu_free(tlb);
 }
 
-static inline void tlb_finish_mmu(struct mmu_gather *tlb,
-				  unsigned long start, unsigned long end)
+static inline void
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->start = start;
+		tlb->end = end;
+	}
+
 	tlb_flush_mmu(tlb);
 }
 
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 46e0d635e36f..51a8bc967e75 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -36,7 +36,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -47,9 +48,10 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 }
 
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
-	if (tlb->fullmm)
+	if (tlb->fullmm || force)
 		flush_tlb_mm(tlb->mm);
 
 	/* keep the page table cache within bounds */
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 600a2e9bfee2..344d95619d03 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -45,7 +45,8 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
+arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+		unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->start = start;
@@ -80,13 +81,19 @@ tlb_flush_mmu(struct mmu_gather *tlb)
 	tlb_flush_mmu_free(tlb);
 }
 
-/* tlb_finish_mmu
+/* arch_tlb_finish_mmu
  *	Called at the end of the shootdown operation to free up any resources
  *	that were required.
  */
 static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
+	if (force) {
+		tlb->start = start;
+		tlb->end = end;
+		tlb->need_flush = 1;
+	}
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1cd792db15ef..1eab79c9ac48 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index f960a043cdeb..fc61739150e7 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
 
 static bool avx2_usable(void)
 {
-	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 21126155a739..0ead9dbb9130 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -43,6 +43,9 @@ struct hypervisor_x86 {
 
 	/* pin current vcpu to specified physical cpu (run rarely) */
 	void		(*pin_vcpu)(int);
+
+	/* called during init_mem_mapping() to setup early mappings. */
+	void		(*init_mem_mapping)(void);
 };
 
 extern const struct hypervisor_x86 *x86_hyper;
@@ -57,8 +60,15 @@ extern const struct hypervisor_x86 x86_hyper_kvm;
 extern void init_hypervisor_platform(void);
 extern bool hypervisor_x2apic_available(void);
 extern void hypervisor_pin_vcpu(int cpu);
+
+static inline void hypervisor_init_mem_mapping(void)
+{
+	if (x86_hyper && x86_hyper->init_mem_mapping)
+		x86_hyper->init_mem_mapping();
+}
 #else
 static inline void init_hypervisor_platform(void) { }
 static inline bool hypervisor_x2apic_available(void) { return false; }
+static inline void hypervisor_init_mem_mapping(void) { }
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 673541eb3b3f..bf3f1065d6ad 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -18,6 +18,7 @@
 #include <asm/dma.h>		/* for MAX_DMA_PFN */
 #include <asm/microcode.h>
 #include <asm/kaslr.h>
+#include <asm/hypervisor.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -636,6 +637,8 @@ void __init init_mem_mapping(void)
 	load_cr3(swapper_pg_dir);
 	__flush_tlb_all();
 
+	hypervisor_init_mem_mapping();
+
 	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
 }
 
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 87d791356ea9..de503c225ae1 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -12,6 +12,7 @@
 #include <asm/setup.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
+#include <asm/early_ioremap.h>
 
 #include <asm/xen/cpuid.h>
 #include <asm/xen/hypervisor.h>
@@ -21,38 +22,50 @@
 #include "mmu.h"
 #include "smp.h"
 
-void __ref xen_hvm_init_shared_info(void)
+static unsigned long shared_info_pfn;
+
+void xen_hvm_init_shared_info(void)
 {
 	struct xen_add_to_physmap xatp;
-	u64 pa;
-
-	if (HYPERVISOR_shared_info == &xen_dummy_shared_info) {
-		/*
-		 * Search for a free page starting at 4kB physical address.
-		 * Low memory is preferred to avoid an EPT large page split up
-		 * by the mapping.
-		 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
-		 * the BIOS used for HVM guests is well behaved and won't
-		 * clobber memory other than the first 4kB.
-		 */
-		for (pa = PAGE_SIZE;
-		     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
-		     memblock_is_reserved(pa);
-		     pa += PAGE_SIZE)
-			;
-
-		memblock_reserve(pa, PAGE_SIZE);
-		HYPERVISOR_shared_info = __va(pa);
-	}
 
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info);
+	xatp.gpfn = shared_info_pfn;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 }
 
+static void __init reserve_shared_info(void)
+{
+	u64 pa;
+
+	/*
+	 * Search for a free page starting at 4kB physical address.
+	 * Low memory is preferred to avoid an EPT large page split up
+	 * by the mapping.
+	 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
+	 * the BIOS used for HVM guests is well behaved and won't
+	 * clobber memory other than the first 4kB.
+	 */
+	for (pa = PAGE_SIZE;
+	     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
+	     memblock_is_reserved(pa);
+	     pa += PAGE_SIZE)
+		;
+
+	shared_info_pfn = PHYS_PFN(pa);
+
+	memblock_reserve(pa, PAGE_SIZE);
+	HYPERVISOR_shared_info = early_memremap(pa, PAGE_SIZE);
+}
+
+static void __init xen_hvm_init_mem_mapping(void)
+{
+	early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE);
+	HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+}
+
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
@@ -153,6 +166,7 @@ static void __init xen_hvm_guest_init(void)
 
 	init_hvm_pv_info();
 
+	reserve_shared_info();
 	xen_hvm_init_shared_info();
 
 	/*
@@ -218,5 +232,6 @@ const struct hypervisor_x86 x86_hyper_xen_hvm = {
 	.init_platform          = xen_hvm_guest_init,
 	.pin_vcpu               = xen_pin_vcpu,
 	.x2apic_available       = xen_x2apic_para_available,
+	.init_mem_mapping	= xen_hvm_init_mem_mapping,
 };
 EXPORT_SYMBOL(x86_hyper_xen_hvm);