Merge tag 'v4.9.87' into fslc_4.9-1.0.x-imx

This is the 4.9.87 stable release

 Conflicts:
	drivers/dma/fsl-edma.c

34 files changed, 382 insertions, 68 deletions

diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 4f2c5ec75714..e262fa9ef334 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -97,6 +97,8 @@
 };
 
 &i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <2600000>;
 
 	twl: twl@48 {
@@ -215,7 +217,12 @@
 		>;
 	};
 
-
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
+			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
+		>;
+	};
 };
 
 &omap3_pmx_wkup {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index efe53998c961..08f0a35dc0d1 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -100,6 +100,8 @@
 };
 
 &i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <2600000>;
 
 	twl: twl@48 {
@@ -207,6 +209,12 @@
 			OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0)	/* hsusb0_data7.hsusb0_data7 */
 		>;
 	};
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
+			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
+		>;
+	};
 };
 
 &uart2 {
diff --git a/arch/arm/boot/dts/ls1021a-qds.dts b/arch/arm/boot/dts/ls1021a-qds.dts
index 940875316d0f..67b4de0e3439 100644
--- a/arch/arm/boot/dts/ls1021a-qds.dts
+++ b/arch/arm/boot/dts/ls1021a-qds.dts
@@ -215,7 +215,7 @@
 				reg = <0x2a>;
 				VDDA-supply = <&reg_3p3v>;
 				VDDIO-supply = <&reg_3p3v>;
-				clocks = <&sys_mclk 1>;
+				clocks = <&sys_mclk>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/ls1021a-twr.dts b/arch/arm/boot/dts/ls1021a-twr.dts
index a8b148ad1dd2..44715c8ef756 100644
--- a/arch/arm/boot/dts/ls1021a-twr.dts
+++ b/arch/arm/boot/dts/ls1021a-twr.dts
@@ -187,7 +187,7 @@
 		reg = <0x0a>;
 		VDDA-supply = <&reg_3p3v>;
 		VDDIO-supply = <&reg_3p3v>;
-		clocks = <&sys_mclk 1>;
+		clocks = <&sys_mclk>;
 	};
 };
 
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 92eab1d51785..61049216e4d5 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -6,6 +6,8 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
 
 KVM=../../../../virt/kvm
 
+CFLAGS_ARMV7VE		   :=$(call cc-option, -march=armv7ve)
+
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
@@ -14,7 +16,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
 obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += vfp.o
 obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o
+CFLAGS_banked-sr.o	   += $(CFLAGS_ARMV7VE)
+
 obj-$(CONFIG_KVM_ARM_HOST) += entry.o
 obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
 obj-$(CONFIG_KVM_ARM_HOST) += switch.o
+CFLAGS_switch.o		   += $(CFLAGS_ARMV7VE)
 obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c
index 111bda8cdebd..be4b8b0a40ad 100644
--- a/arch/arm/kvm/hyp/banked-sr.c
+++ b/arch/arm/kvm/hyp/banked-sr.c
@@ -20,6 +20,10 @@
 
 #include <asm/kvm_hyp.h>
 
+/*
+ * gcc before 4.9 doesn't understand -march=armv7ve, so we have to
+ * trick the assembler.
+ */
 __asm__(".arch_extension     virt");
 
 void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt)
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 2a35c1963f6d..7f868d9bb5ed 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1284,7 +1284,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
-	if (vma_kernel_pagesize(vma) && !logging_active) {
+	if (vma_kernel_pagesize(vma) == PMD_SIZE && !logging_active) {
 		hugetlb = true;
 		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
 	} else {
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1712f132b80d..b83fdc06286a 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -85,7 +85,11 @@
 		.pushsection .text.fixup,"ax"
 		.align	4
 9001:		mov	r4, #-EFAULT
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		ldr	r5, [sp, #9*4]		@ *err_ptr
+#else
 		ldr	r5, [sp, #8*4]		@ *err_ptr
+#endif
 		str	r4, [r5]
 		ldmia	sp, {r1, r2}		@ retrieve dst, len
 		add	r2, r2, r1
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 541647f57192..895c0746fe50 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -42,7 +42,7 @@ config MACH_ARMADA_375
 	depends on ARCH_MULTI_V7
 	select ARMADA_370_XP_IRQ
 	select ARM_ERRATA_720789
-	select ARM_ERRATA_753970
+	select PL310_ERRATA_753970
 	select ARM_GIC
 	select ARMADA_375_CLK
 	select HAVE_ARM_SCU
@@ -58,7 +58,7 @@ config MACH_ARMADA_38X
 	bool "Marvell Armada 380/385 boards"
 	depends on ARCH_MULTI_V7
 	select ARM_ERRATA_720789
-	select ARM_ERRATA_753970
+	select PL310_ERRATA_753970
 	select ARM_GIC
 	select ARMADA_370_XP_IRQ
 	select ARMADA_38X_CLK
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c743d1fd8286..5963be2e05f0 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -50,7 +50,7 @@ static const char *handler[]= {
 	"Error"
 };
 
-int show_unhandled_signals = 1;
+int show_unhandled_signals = 0;
 
 /*
  * Dump out the contents of some kernel memory nicely...
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index d8199e12fb6e..b47a26f4290c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -234,8 +234,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	off = offsetof(struct bpf_array, map.max_entries);
 	emit_a64_mov_i64(tmp, off, ctx);
 	emit(A64_LDR32(tmp, r2, tmp), ctx);
+	emit(A64_MOV(0, r3, r3), ctx);
 	emit(A64_CMP(0, r3, tmp), ctx);
-	emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_CS, jmp_offset), ctx);
 
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *     goto out;
@@ -243,7 +244,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
 	emit(A64_CMP(1, tcc, tmp), ctx);
-	emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_HI, jmp_offset), ctx);
 	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
 
 	/* prog = array->ptrs[index];
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 0344e575f522..fba4ca56e46a 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -15,4 +15,5 @@ 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 05909d58e2fe..56ea0df60a44 100644
--- a/arch/mips/lib/libgcc.h
+++ b/arch/mips/lib/libgcc.h
@@ -9,10 +9,18 @@ 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
@@ -22,4 +30,13 @@ 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/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 1d8c24dc04d4..88290d32b956 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -25,6 +25,7 @@ void flush_user_icache_range_asm(unsigned long, unsigned long);
 void flush_kernel_icache_range_asm(unsigned long, unsigned long);
 void flush_user_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
+void purge_kernel_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_page_asm(void *);
 void flush_kernel_icache_page(void *);
 void flush_user_dcache_range(unsigned long, unsigned long);
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index df757c9675e6..025afe5f17a7 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -464,10 +464,10 @@ EXPORT_SYMBOL(copy_user_page);
 int __flush_tlb_range(unsigned long sid, unsigned long start,
 		      unsigned long end)
 {
-	unsigned long flags, size;
+	unsigned long flags;
 
-	size = (end - start);
-	if (size >= parisc_tlb_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
 		return 1;
 	}
@@ -538,13 +538,11 @@ void flush_cache_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	pgd_t *pgd;
 
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
-		flush_tlb_all();
-
 	/* Flushing the whole cache on each cpu takes forever on
 	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
-	if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    mm_total_size(mm) >= parisc_cache_flush_threshold) {
+		flush_tlb_all();
 		flush_cache_all();
 		return;
 	}
@@ -552,9 +550,9 @@ void flush_cache_mm(struct mm_struct *mm)
 	if (mm->context == mfsp(3)) {
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
-			if ((vma->vm_flags & VM_EXEC) == 0)
-				continue;
-			flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			if (vma->vm_flags & VM_EXEC)
+				flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			flush_tlb_range(vma, vma->vm_start, vma->vm_end);
 		}
 		return;
 	}
@@ -598,14 +596,9 @@ flush_user_icache_range(unsigned long start, unsigned long end)
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
-	BUG_ON(!vma->vm_mm->context);
-
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_cache_flush_threshold) {
 		flush_tlb_range(vma, start, end);
-
-	if ((end - start) >= parisc_cache_flush_threshold
-	    || vma->vm_mm->context != mfsp(3)) {
 		flush_cache_all();
 		return;
 	}
@@ -613,6 +606,7 @@ void flush_cache_range(struct vm_area_struct *vma,
 	flush_user_dcache_range_asm(start, end);
 	if (vma->vm_flags & VM_EXEC)
 		flush_user_icache_range_asm(start, end);
+	flush_tlb_range(vma, start, end);
 }
 
 void
@@ -621,8 +615,7 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 	BUG_ON(!vma->vm_mm->context);
 
 	if (pfn_valid(pfn)) {
-		if (parisc_requires_coherency())
-			flush_tlb_page(vma, vmaddr);
+		flush_tlb_page(vma, vmaddr);
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }
@@ -630,21 +623,33 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 void flush_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	flush_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(flush_kernel_vmap_range);
 
 void invalidate_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	purge_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 2d40c4ff3f69..67b0f7532e83 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -1110,6 +1110,28 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
 	.procend
 ENDPROC_CFI(flush_kernel_dcache_range_asm)
 
+ENTRY_CFI(purge_kernel_dcache_range_asm)
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil		L%dcache_stride, %r1
+	ldw		R%dcache_stride(%r1), %r23
+	ldo		-1(%r23), %r21
+	ANDCM		%r26, %r21, %r26
+
+1:      cmpb,COND(<<),n	%r26, %r25,1b
+	pdc,m		%r23(%r26)
+
+	sync
+	syncdma
+	bv		%r0(%r2)
+	nop
+	.exit
+
+	.procend
+ENDPROC_CFI(purge_kernel_dcache_range_asm)
+
 ENTRY_CFI(flush_user_icache_range_asm)
 	.proc
 	.callinfo NO_CALLS
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 0fe98a567125..be9d968244ad 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -245,6 +245,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	 *   goto out;
 	 */
 	PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries));
+	PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31);
 	PPC_CMPLW(b2p_index, b2p[TMP_REG_1]);
 	PPC_BCC(COND_GE, out);
 
diff --git a/arch/sh/boards/mach-se/770x/setup.c b/arch/sh/boards/mach-se/770x/setup.c
index 658326f44df8..5e0267624d8d 100644
--- a/arch/sh/boards/mach-se/770x/setup.c
+++ b/arch/sh/boards/mach-se/770x/setup.c
@@ -8,6 +8,7 @@
  */
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/sh_eth.h>
 #include <mach-se/mach/se.h>
 #include <mach-se/mach/mrshpc.h>
 #include <asm/machvec.h>
@@ -114,6 +115,11 @@ static struct platform_device heartbeat_device = {
 #if defined(CONFIG_CPU_SUBTYPE_SH7710) ||\
 	defined(CONFIG_CPU_SUBTYPE_SH7712)
 /* SH771X Ethernet driver */
+static struct sh_eth_plat_data sh_eth_plat = {
+	.phy = PHY_ID,
+	.phy_interface = PHY_INTERFACE_MODE_MII,
+};
+
 static struct resource sh_eth0_resources[] = {
 	[0] = {
 		.start = SH_ETH0_BASE,
@@ -131,7 +137,7 @@ static struct platform_device sh_eth0_device = {
 	.name = "sh771x-ether",
 	.id = 0,
 	.dev = {
-		.platform_data = PHY_ID,
+		.platform_data = &sh_eth_plat,
 	},
 	.num_resources = ARRAY_SIZE(sh_eth0_resources),
 	.resource = sh_eth0_resources,
@@ -154,7 +160,7 @@ static struct platform_device sh_eth1_device = {
 	.name = "sh771x-ether",
 	.id = 1,
 	.dev = {
-		.platform_data = PHY_ID,
+		.platform_data = &sh_eth_plat,
 	},
 	.num_resources = ARRAY_SIZE(sh_eth1_resources),
 	.resource = sh_eth1_resources,
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index db5009ce065a..8d7e4d48db0d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -176,13 +176,26 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	pushq	%r8				/* pt_regs->r8 */
 	pushq	%r9				/* pt_regs->r9 */
 	pushq	%r10				/* pt_regs->r10 */
+	/*
+	 * Clear extra registers that a speculation attack might
+	 * otherwise want to exploit. Interleave XOR with PUSH
+	 * for better uop scheduling:
+	 */
+	xorq	%r10, %r10			/* nospec   r10 */
 	pushq	%r11				/* pt_regs->r11 */
+	xorq	%r11, %r11			/* nospec   r11 */
 	pushq	%rbx				/* pt_regs->rbx */
+	xorl	%ebx, %ebx			/* nospec   rbx */
 	pushq	%rbp				/* pt_regs->rbp */
+	xorl	%ebp, %ebp			/* nospec   rbp */
 	pushq	%r12				/* pt_regs->r12 */
+	xorq	%r12, %r12			/* nospec   r12 */
 	pushq	%r13				/* pt_regs->r13 */
+	xorq	%r13, %r13			/* nospec   r13 */
 	pushq	%r14				/* pt_regs->r14 */
+	xorq	%r14, %r14			/* nospec   r14 */
 	pushq	%r15				/* pt_regs->r15 */
+	xorq	%r15, %r15			/* nospec   r15 */
 
 	/* IRQs are off. */
 	movq	%rsp, %rdi
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7bb29a416b77..f35f246a26bf 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -128,6 +128,7 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#ifndef __BPF__
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -137,5 +138,6 @@
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
+#endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 8b272a08d1a8..e2e09347ee3c 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,12 +3,18 @@
 
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/atomic.h>
 
 /*
- * The x86 doesn't have a mmu context, but
- * we put the segment information here.
+ * x86 has arch-specific MMU state beyond what lives in mm_struct.
  */
 typedef struct {
+	/*
+	 * ctx_id uniquely identifies this mm_struct.  A ctx_id will never
+	 * be reused, and zero is not a valid ctx_id.
+	 */
+	u64 ctx_id;
+
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 #endif
@@ -33,6 +39,11 @@ typedef struct {
 #endif
 } mm_context_t;
 
+#define INIT_MM_CONTEXT(mm)						\
+	.context = {							\
+		.ctx_id = 1,						\
+	}
+
 void leave_mm(int cpu);
 
 #endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index d23e35584f15..5a295bb97103 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -12,6 +12,9 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/mpx.h>
+
+extern atomic64_t last_mm_ctx_id;
+
 #ifndef CONFIG_PARAVIRT
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
@@ -106,6 +109,8 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
+
 	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 76b058533e47..81a1be326571 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -177,4 +177,41 @@ static inline void indirect_branch_prediction_barrier(void)
 }
 
 #endif /* __ASSEMBLY__ */
+
+/*
+ * Below is used in the eBPF JIT compiler and emits the byte sequence
+ * for the following assembly:
+ *
+ * With retpolines configured:
+ *
+ *    callq do_rop
+ *  spec_trap:
+ *    pause
+ *    lfence
+ *    jmp spec_trap
+ *  do_rop:
+ *    mov %rax,(%rsp)
+ *    retq
+ *
+ * Without retpolines configured:
+ *
+ *    jmp *%rax
+ */
+#ifdef CONFIG_RETPOLINE
+# define RETPOLINE_RAX_BPF_JIT_SIZE	17
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
+	/* spec_trap: */					\
+	EMIT2(0xF3, 0x90);       /* pause */			\
+	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
+	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
+	/* do_rop: */						\
+	EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */	\
+	EMIT1(0xC3);             /* retq */
+#else
+# define RETPOLINE_RAX_BPF_JIT_SIZE	2
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT2(0xFF, 0xE0);	 /* jmp *%rax */
+#endif
+
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 94146f665a3c..99185a064978 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -68,6 +68,8 @@ static inline void invpcid_flush_all_nonglobals(void)
 struct tlb_state {
 	struct mm_struct *active_mm;
 	int state;
+	/* last user mm's ctx id */
+	u64 last_ctx_id;
 
 	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index b5229abd1629..4922ab66fd29 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -93,8 +93,12 @@ out_data:
 	return NULL;
 }
 
-static void free_apic_chip_data(struct apic_chip_data *data)
+static void free_apic_chip_data(unsigned int virq, struct apic_chip_data *data)
 {
+#ifdef	CONFIG_X86_IO_APIC
+	if (virq  < nr_legacy_irqs())
+		legacy_irq_data[virq] = NULL;
+#endif
 	if (data) {
 		free_cpumask_var(data->domain);
 		free_cpumask_var(data->old_domain);
@@ -318,11 +322,7 @@ static void x86_vector_free_irqs(struct irq_domain *domain,
 			apic_data = irq_data->chip_data;
 			irq_domain_reset_irq_data(irq_data);
 			raw_spin_unlock_irqrestore(&vector_lock, flags);
-			free_apic_chip_data(apic_data);
-#ifdef	CONFIG_X86_IO_APIC
-			if (virq + i < nr_legacy_irqs())
-				legacy_irq_data[virq + i] = NULL;
-#endif
+			free_apic_chip_data(virq + i, apic_data);
 		}
 	}
 }
@@ -363,7 +363,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		err = assign_irq_vector_policy(virq + i, node, data, info);
 		if (err) {
 			irq_data->chip_data = NULL;
-			free_apic_chip_data(data);
+			free_apic_chip_data(virq + i, data);
 			goto error;
 		}
 	}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index be644afab1bb..24d2a3ee743f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -44,6 +44,7 @@
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
+#include <asm/microcode.h>
 #include <asm/nospec-branch.h>
 
 #include <asm/virtext.h>
@@ -4919,7 +4920,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 * being speculatively taken.
 	 */
 	if (svm->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
 
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
@@ -5028,11 +5029,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
-		rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
 	if (svm->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c51aaac953b4..0f3bb4632310 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -49,6 +49,7 @@
 #include <asm/kexec.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/microcode.h>
 #include <asm/nospec-branch.h>
 
 #include "trace.h"
@@ -8906,7 +8907,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * being speculatively taken.
 	 */
 	if (vmx->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
@@ -9041,11 +9042,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
-		rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
 	if (vmx->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 578973ade71b..eac92e2d171b 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -10,6 +10,7 @@
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/nospec-branch.h>
 #include <asm/cache.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
@@ -29,6 +30,8 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
+atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
+
 struct flush_tlb_info {
 	struct mm_struct *flush_mm;
 	unsigned long flush_start;
@@ -104,6 +107,28 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	unsigned cpu = smp_processor_id();
 
 	if (likely(prev != next)) {
+		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
+
+		/*
+		 * Avoid user/user BTB poisoning by flushing the branch
+		 * predictor when switching between processes. This stops
+		 * one process from doing Spectre-v2 attacks on another.
+		 *
+		 * As an optimization, flush indirect branches only when
+		 * switching into processes that disable dumping. This
+		 * protects high value processes like gpg, without having
+		 * too high performance overhead. IBPB is *expensive*!
+		 *
+		 * This will not flush branches when switching into kernel
+		 * threads. It will also not flush if we switch to idle
+		 * thread and back to the same process. It will flush if we
+		 * switch to a different non-dumpable process.
+		 */
+		if (tsk && tsk->mm &&
+		    tsk->mm->context.ctx_id != last_ctx_id &&
+		    get_dumpable(tsk->mm) != SUID_DUMP_USER)
+			indirect_branch_prediction_barrier();
+
 		if (IS_ENABLED(CONFIG_VMAP_STACK)) {
 			/*
 			 * If our current stack is in vmalloc space and isn't
@@ -118,6 +143,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 				set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
 		}
 
+		/*
+		 * Record last user mm's context id, so we can avoid
+		 * flushing branch buffer with IBPB if we switch back
+		 * to the same user.
+		 */
+		if (next != &init_mm)
+			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		this_cpu_write(cpu_tlbstate.active_mm, next);
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7840331d3056..1f7ed2ed6ff7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -12,6 +12,7 @@
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
 #include <asm/cacheflush.h>
+#include <asm/nospec-branch.h>
 #include <linux/bpf.h>
 
 int bpf_jit_enable __read_mostly;
@@ -281,7 +282,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 43 /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -290,7 +291,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 */
 	EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 32
+#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
@@ -304,7 +305,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 *   goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
-#define OFFSET3 10
+#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
 	label3 = cnt;
 
@@ -317,7 +318,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 * rdi == ctx (1st arg)
 	 * rax == prog->bpf_func + prologue_size
 	 */
-	EMIT2(0xFF, 0xE0);                        /* jmp rax */
+	RETPOLINE_RAX_BPF_JIT();
 
 	/* out: */
 	BUILD_BUG_ON(cnt - label1 != OFFSET1);
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 28c04123b6dd..842ca3cab6b3 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -472,7 +472,7 @@ static int nmi_setup(void)
 		goto fail;
 
 	for_each_possible_cpu(cpu) {
-		if (!cpu)
+		if (!IS_ENABLED(CONFIG_SMP) || !cpu)
 			continue;
 
 		memcpy(per_cpu(cpu_msrs, cpu).counters,
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 7850128f0026..834783bc6752 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -79,7 +79,7 @@ static void intel_mid_power_off(void)
 
 static void intel_mid_reboot(void)
 {
-	intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+	intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
 }
 
 static unsigned long __init intel_mid_calibrate_tsc(void)
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 7f664c416faf..4ecd0de08557 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,11 +1,14 @@
 #include <linux/types.h>
 #include <linux/tick.h>
+#include <linux/percpu-defs.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
 #include <xen/events.h>
 
+#include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 #include <asm/fixmap.h>
@@ -68,6 +71,8 @@ static void xen_pv_post_suspend(int suspend_cancelled)
 	xen_mm_unpin_all();
 }
 
+static DEFINE_PER_CPU(u64, spec_ctrl);
+
 void xen_arch_pre_suspend(void)
 {
 	if (xen_pv_domain())
@@ -84,6 +89,9 @@ void xen_arch_post_suspend(int cancelled)
 
 static void xen_vcpu_notify_restore(void *data)
 {
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+		wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+
 	/* Boot processor notified via generic timekeeping_resume() */
 	if (smp_processor_id() == 0)
 		return;
@@ -93,7 +101,15 @@ static void xen_vcpu_notify_restore(void *data)
 
 static void xen_vcpu_notify_suspend(void *data)
 {
+	u64 tmp;
+
 	tick_suspend_local();
+
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
+		rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+		this_cpu_write(spec_ctrl, tmp);
+		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+	}
 }
 
 void xen_arch_resume(void)
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 80e4cfb2471a..d5abdf8878fe 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -77,19 +77,75 @@ void __init zones_init(void)
 	free_area_init_node(0, zones_size, ARCH_PFN_OFFSET, NULL);
 }
 
+#ifdef CONFIG_HIGHMEM
+static void __init free_area_high(unsigned long pfn, unsigned long end)
+{
+	for (; pfn < end; pfn++)
+		free_highmem_page(pfn_to_page(pfn));
+}
+
+static void __init free_highpages(void)
+{
+	unsigned long max_low = max_low_pfn;
+	struct memblock_region *mem, *res;
+
+	reset_all_zones_managed_pages();
+	/* set highmem page free */
+	for_each_memblock(memory, mem) {
+		unsigned long start = memblock_region_memory_base_pfn(mem);
+		unsigned long end = memblock_region_memory_end_pfn(mem);
+
+		/* Ignore complete lowmem entries */
+		if (end <= max_low)
+			continue;
+
+		if (memblock_is_nomap(mem))
+			continue;
+
+		/* Truncate partial highmem entries */
+		if (start < max_low)
+			start = max_low;
+
+		/* Find and exclude any reserved regions */
+		for_each_memblock(reserved, res) {
+			unsigned long res_start, res_end;
+
+			res_start = memblock_region_reserved_base_pfn(res);
+			res_end = memblock_region_reserved_end_pfn(res);
+
+			if (res_end < start)
+				continue;
+			if (res_start < start)
+				res_start = start;
+			if (res_start > end)
+				res_start = end;
+			if (res_end > end)
+				res_end = end;
+			if (res_start != start)
+				free_area_high(start, res_start);
+			start = res_end;
+			if (start == end)
+				break;
+		}
+
+		/* And now free anything which remains */
+		if (start < end)
+			free_area_high(start, end);
+	}
+}
+#else
+static void __init free_highpages(void)
+{
+}
+#endif
+
 /*
  * Initialize memory pages.
  */
 
 void __init mem_init(void)
 {
-#ifdef CONFIG_HIGHMEM
-	unsigned long tmp;
-
-	reset_all_zones_managed_pages();
-	for (tmp = max_low_pfn; tmp < max_pfn; tmp++)
-		free_highmem_page(pfn_to_page(tmp));
-#endif
+	free_highpages();
 
 	max_mapnr = max_pfn - ARCH_PFN_OFFSET;
 	high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT);