Merge tag 'v5.0.19' into toradex_5.0.ytoradex_5.0.y

This is the 5.0.19 stable release

64 files changed, 467 insertions, 534 deletions

diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 4135abec3fb0..63e6e6504699 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -113,10 +113,24 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	}
 
 	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
-	if (cbcr.c)
+	if (cbcr.c) {
 		ioc_exists = 1;
-	else
+
+		/*
+		 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
+		 * simultaneously. This happens because as of today IOC aperture covers
+		 * only ZONE_NORMAL (low mem) and any dma transactions outside this
+		 * region won't be HW coherent.
+		 * If we want to use both IOC and ZONE_HIGHMEM we can use
+		 * bounce_buffer to handle dma transactions to HIGHMEM.
+		 * Also it is possible to modify dma_direct cache ops or increase IOC
+		 * aperture size if we are planning to use HIGHMEM without PAE.
+		 */
+		if (IS_ENABLED(CONFIG_HIGHMEM) || is_pae40_enabled())
+			ioc_enable = 0;
+	} else {
 		ioc_enable = 0;
+	}
 
 	/* HS 2.0 didn't have AUX_VOL */
 	if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1158,19 +1172,6 @@ noinline void __init arc_ioc_setup(void)
 	if (!ioc_enable)
 		return;
 
-	/*
-	 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
-	 * simultaneously. This happens because as of today IOC aperture covers
-	 * only ZONE_NORMAL (low mem) and any dma transactions outside this
-	 * region won't be HW coherent.
-	 * If we want to use both IOC and ZONE_HIGHMEM we can use
-	 * bounce_buffer to handle dma transactions to HIGHMEM.
-	 * Also it is possible to modify dma_direct cache ops or increase IOC
-	 * aperture size if we are planning to use HIGHMEM without PAE.
-	 */
-	if (IS_ENABLED(CONFIG_HIGHMEM))
-		panic("IOC and HIGHMEM can't be used simultaneously");
-
 	/* Flush + invalidate + disable L1 dcache */
 	__dc_disable();
 
diff --git a/arch/arm/boot/dts/exynos5260.dtsi b/arch/arm/boot/dts/exynos5260.dtsi
index 55167850619c..33a085ffc447 100644
--- a/arch/arm/boot/dts/exynos5260.dtsi
+++ b/arch/arm/boot/dts/exynos5260.dtsi
@@ -223,7 +223,7 @@
 			wakeup-interrupt-controller {
 				compatible = "samsung,exynos4210-wakeup-eint";
 				interrupt-parent = <&gic>;
-				interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi
index e84544b220b9..b90cea8b7368 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi
@@ -22,7 +22,7 @@
 			"Headphone Jack", "HPL",
 			"Headphone Jack", "HPR",
 			"Headphone Jack", "MICBIAS",
-			"IN1", "Headphone Jack",
+			"IN12", "Headphone Jack",
 			"Speakers", "SPKL",
 			"Speakers", "SPKR";
 
diff --git a/arch/arm/boot/dts/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom-ipq4019.dtsi
index 2d56008d8d6b..049fa8e3f2fd 100644
--- a/arch/arm/boot/dts/qcom-ipq4019.dtsi
+++ b/arch/arm/boot/dts/qcom-ipq4019.dtsi
@@ -393,8 +393,8 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 
-			ranges = <0x81000000 0 0x40200000 0x40200000 0 0x00100000
-				  0x82000000 0 0x40300000 0x40300000 0 0x400000>;
+			ranges = <0x81000000 0 0x40200000 0x40200000 0 0x00100000>,
+				 <0x82000000 0 0x40300000 0x40300000 0 0x00d00000>;
 
 			interrupts = <GIC_SPI 141 IRQ_TYPE_EDGE_RISING>;
 			interrupt-names = "msi";
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index 07e31941dc67..617c2c99ebfb 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -278,6 +278,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
 
diff --git a/arch/arm/mach-exynos/firmware.c b/arch/arm/mach-exynos/firmware.c
index d602e3bf3f96..2eaf2dbb8e81 100644
--- a/arch/arm/mach-exynos/firmware.c
+++ b/arch/arm/mach-exynos/firmware.c
@@ -196,6 +196,7 @@ bool __init exynos_secure_firmware_available(void)
 		return false;
 
 	addr = of_get_address(nd, 0, NULL, NULL);
+	of_node_put(nd);
 	if (!addr) {
 		pr_err("%s: No address specified.\n", __func__);
 		return false;
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index 0850505ac78b..9afb0c69db34 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -639,8 +639,10 @@ void __init exynos_pm_init(void)
 
 	if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
 		pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+		of_node_put(np);
 		return;
 	}
+	of_node_put(np);
 
 	pm_data = (const struct exynos_pm_data *) match->data;
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
index be78172abc09..8ed3104ade94 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
@@ -489,7 +489,7 @@
 	status = "okay";
 
 	bt656-supply = <&vcc1v8_dvp>;
-	audio-supply = <&vcca1v8_codec>;
+	audio-supply = <&vcc_3v0>;
 	sdmmc-supply = <&vcc_sdio>;
 	gpio1830-supply = <&vcc_3v0>;
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 6cc1c9fa4ea6..1bbf0da4e01d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -333,6 +333,7 @@
 		phys = <&emmc_phy>;
 		phy-names = "phy_arasan";
 		power-domains = <&power RK3399_PD_EMMC>;
+		disable-cqe-dcmd;
 		status = "disabled";
 	};
 
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index e7a95a566462..5cc248967387 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -304,6 +304,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
 
 	kernel_neon_begin();
 	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1);
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 067d8937d5af..1ed227bf6106 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -418,9 +418,11 @@ static int gcm_encrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const int blocks =
+				walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
+			int remaining = blocks;
 
 			do {
 				__aes_arm64_encrypt(ctx->aes_key.key_enc,
@@ -430,9 +432,9 @@ static int gcm_encrypt(struct aead_request *req)
 
 				dst += AES_BLOCK_SIZE;
 				src += AES_BLOCK_SIZE;
-			} while (--blocks > 0);
+			} while (--remaining > 0);
 
-			ghash_do_update(walk.nbytes / AES_BLOCK_SIZE, dg,
+			ghash_do_update(blocks, dg,
 					walk.dst.virt.addr, &ctx->ghash_key,
 					NULL);
 
@@ -553,7 +555,7 @@ static int gcm_decrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
 
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index f2a234d6516c..93e07512b4b6 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -148,18 +148,47 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	isb();
 }
 
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do {				\
+	u64 tmp, _val = (val);						\
+									\
+	asm volatile(							\
+	"	eor	%0, %1, %1\n"					\
+	"	add	%0, sp, %0\n"					\
+	"	ldr	xzr, [%0]"					\
+	: "=r" (tmp) : "r" (_val));					\
+} while (0)
+
 static inline u64 arch_counter_get_cntpct(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntpct_el0);
+	cnt = arch_timer_reg_read_stable(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
 static inline u64 arch_counter_get_cntvct(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntvct_el0);
+	cnt = arch_timer_reg_read_stable(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
+#undef arch_counter_enforce_ordering
+
 static inline int arch_timer_arch_init(void)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index f1a7ab18faf3..928f59340598 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -57,7 +57,15 @@
 #define TASK_SIZE_64		(UL(1) << vabits_user)
 
 #ifdef CONFIG_COMPAT
+#ifdef CONFIG_ARM64_64K_PAGES
+/*
+ * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
+ * by the compat vectors page.
+ */
 #define TASK_SIZE_32		UL(0x100000000)
+#else
+#define TASK_SIZE_32		(UL(0x100000000) - PAGE_SIZE)
+#endif /* CONFIG_ARM64_64K_PAGES */
 #define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
 #define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index d7bb6aefae0a..0fa6db521e44 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -135,6 +135,7 @@ NOKPROBE_SYMBOL(disable_debug_monitors);
  */
 static int clear_os_lock(unsigned int cpu)
 {
+	write_sysreg(0, osdlr_el1);
 	write_sysreg(0, oslar_el1);
 	isb();
 	return 0;
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index b44065fb1616..6f91e8116514 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -31,7 +31,7 @@
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, off_t, off)
+		unsigned long, fd, unsigned long, off)
 {
 	if (offset_in_page(off) != 0)
 		return -EINVAL;
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index c39872a7b03c..e8f60112818f 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -73,6 +73,13 @@ x_tmp		.req	x8
 	movn	x_tmp, #0xff00, lsl #48
 	and	\res, x_tmp, \res
 	mul	\res, \res, \mult
+	/*
+	 * Fake address dependency from the value computed from the counter
+	 * register to subsequent data page accesses so that the sequence
+	 * locking also orders the read of the counter.
+	 */
+	and	x_tmp, \res, xzr
+	add	vdso_data, vdso_data, x_tmp
 	.endm
 
 	/*
@@ -147,12 +154,12 @@ ENTRY(__kernel_gettimeofday)
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=1b
 
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=1b
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -211,13 +218,13 @@ realtime:
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=realtime
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=realtime
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 	clock_gettime_return, shift=1
@@ -231,7 +238,6 @@ monotonic:
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
 	ldp	x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
-	seqcnt_check fail=monotonic
 
 	/* All computations are done with left-shifted nsecs. */
 	lsl	x4, x4, x12
@@ -239,6 +245,7 @@ monotonic:
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -253,13 +260,13 @@ monotonic_raw:
 	/* w11 = cs_raw_mult, w12 = cs_shift */
 	ldp	w12, w11, [vdso_data, #VDSO_CS_SHIFT]
 	ldp	x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
-	seqcnt_check fail=monotonic_raw
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic_raw
 	get_ts_clock_raw res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, nsec_to_sec=x9
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 73886a5f1f30..19bc318b2fe9 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -76,24 +76,25 @@ ENTRY(cpu_do_suspend)
 	mrs	x2, tpidr_el0
 	mrs	x3, tpidrro_el0
 	mrs	x4, contextidr_el1
-	mrs	x5, cpacr_el1
-	mrs	x6, tcr_el1
-	mrs	x7, vbar_el1
-	mrs	x8, mdscr_el1
-	mrs	x9, oslsr_el1
-	mrs	x10, sctlr_el1
+	mrs	x5, osdlr_el1
+	mrs	x6, cpacr_el1
+	mrs	x7, tcr_el1
+	mrs	x8, vbar_el1
+	mrs	x9, mdscr_el1
+	mrs	x10, oslsr_el1
+	mrs	x11, sctlr_el1
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	x11, tpidr_el1
+	mrs	x12, tpidr_el1
 alternative_else
-	mrs	x11, tpidr_el2
+	mrs	x12, tpidr_el2
 alternative_endif
-	mrs	x12, sp_el0
+	mrs	x13, sp_el0
 	stp	x2, x3, [x0]
-	stp	x4, xzr, [x0, #16]
-	stp	x5, x6, [x0, #32]
-	stp	x7, x8, [x0, #48]
-	stp	x9, x10, [x0, #64]
-	stp	x11, x12, [x0, #80]
+	stp	x4, x5, [x0, #16]
+	stp	x6, x7, [x0, #32]
+	stp	x8, x9, [x0, #48]
+	stp	x10, x11, [x0, #64]
+	stp	x12, x13, [x0, #80]
 	ret
 ENDPROC(cpu_do_suspend)
 
@@ -116,8 +117,8 @@ ENTRY(cpu_do_resume)
 	msr	cpacr_el1, x6
 
 	/* Don't change t0sz here, mask those bits when restoring */
-	mrs	x5, tcr_el1
-	bfi	x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+	mrs	x7, tcr_el1
+	bfi	x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 
 	msr	tcr_el1, x8
 	msr	vbar_el1, x9
@@ -141,6 +142,7 @@ alternative_endif
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
 	 */
+	msr	osdlr_el1, x5
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 783de51a6c4e..6c881659ee8a 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -100,12 +100,6 @@
 #define A64_STXR(sf, Rt, Rn, Rs) \
 	A64_LSX(sf, Rt, Rn, Rs, STORE_EX)
 
-/* Prefetch */
-#define A64_PRFM(Rn, type, target, policy) \
-	aarch64_insn_gen_prefetch(Rn, AARCH64_INSN_PRFM_TYPE_##type, \
-				  AARCH64_INSN_PRFM_TARGET_##target, \
-				  AARCH64_INSN_PRFM_POLICY_##policy)
-
 /* Add/subtract (immediate) */
 #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \
 	aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 1542df00b23c..8d7ceec7f079 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -739,7 +739,6 @@ emit_cond_jmp:
 	case BPF_STX | BPF_XADD | BPF_DW:
 		emit_a64_mov_i(1, tmp, off, ctx);
 		emit(A64_ADD(1, tmp, tmp, dst), ctx);
-		emit(A64_PRFM(tmp, PST, L1, STRM), ctx);
 		emit(A64_LDXR(isdw, tmp2, tmp), ctx);
 		emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
 		emit(A64_STXR(isdw, tmp2, tmp, tmp3), ctx);
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 413863508f6f..d67fb64e908c 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -64,17 +64,11 @@ struct mips_perf_event {
 	#define CNTR_EVEN	0x55555555
 	#define CNTR_ODD	0xaaaaaaaa
 	#define CNTR_ALL	0xffffffff
-#ifdef CONFIG_MIPS_MT_SMP
 	enum {
 		T  = 0,
 		V  = 1,
 		P  = 2,
 	} range;
-#else
-	#define T
-	#define V
-	#define P
-#endif
 };
 
 static struct mips_perf_event raw_event;
@@ -325,9 +319,7 @@ static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 {
 	struct perf_event *event = container_of(evt, struct perf_event, hw);
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-#ifdef CONFIG_MIPS_MT_SMP
 	unsigned int range = evt->event_base >> 24;
-#endif /* CONFIG_MIPS_MT_SMP */
 
 	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
 
@@ -336,21 +328,15 @@ static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 		/* Make sure interrupt enabled. */
 		MIPS_PERFCTRL_IE;
 
-#ifdef CONFIG_CPU_BMIPS5000
-	{
+	if (IS_ENABLED(CONFIG_CPU_BMIPS5000)) {
 		/* enable the counter for the calling thread */
 		cpuc->saved_ctrl[idx] |=
 			(1 << (12 + vpe_id())) | BRCM_PERFCTRL_TC;
-	}
-#else
-#ifdef CONFIG_MIPS_MT_SMP
-	if (range > V) {
+	} else if (IS_ENABLED(CONFIG_MIPS_MT_SMP) && range > V) {
 		/* The counter is processor wide. Set it up to count all TCs. */
 		pr_debug("Enabling perf counter for all TCs\n");
 		cpuc->saved_ctrl[idx] |= M_TC_EN_ALL;
-	} else
-#endif /* CONFIG_MIPS_MT_SMP */
-	{
+	} else {
 		unsigned int cpu, ctrl;
 
 		/*
@@ -365,7 +351,6 @@ static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 		cpuc->saved_ctrl[idx] |= ctrl;
 		pr_debug("Enabling perf counter for CPU%d\n", cpu);
 	}
-#endif /* CONFIG_CPU_BMIPS5000 */
 	/*
 	 * We do not actually let the counter run. Leave it until start().
 	 */
diff --git a/arch/parisc/boot/compressed/head.S b/arch/parisc/boot/compressed/head.S
index 5aba20fa48aa..e8b798fd0cf0 100644
--- a/arch/parisc/boot/compressed/head.S
+++ b/arch/parisc/boot/compressed/head.S
@@ -22,7 +22,7 @@
 	__HEAD
 
 ENTRY(startup)
-	 .level LEVEL
+	 .level PA_ASM_LEVEL
 
 #define PSW_W_SM	0x200
 #define PSW_W_BIT       36
@@ -63,7 +63,7 @@ $bss_loop:
 	load32	BOOTADDR(decompress_kernel),%r3
 
 #ifdef CONFIG_64BIT
-	.level LEVEL
+	.level PA_ASM_LEVEL
 	ssm	PSW_W_SM, %r0		/* set W-bit */
 	depdi	0, 31, 32, %r3
 #endif
@@ -72,7 +72,7 @@ $bss_loop:
 
 startup_continue:
 #ifdef CONFIG_64BIT
-	.level LEVEL
+	.level PA_ASM_LEVEL
 	rsm	PSW_W_SM, %r0		/* clear W-bit */
 #endif
 
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index c17ec0ee6e7c..d85738a7bbe6 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -61,14 +61,14 @@
 #define LDCW		ldcw,co
 #define BL		b,l
 # ifdef CONFIG_64BIT
-#  define LEVEL		2.0w
+#  define PA_ASM_LEVEL	2.0w
 # else
-#  define LEVEL		2.0
+#  define PA_ASM_LEVEL	2.0
 # endif
 #else
 #define LDCW		ldcw
 #define BL		bl
-#define LEVEL		1.1
+#define PA_ASM_LEVEL	1.1
 #endif
 
 #ifdef __ASSEMBLY__
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
index 006fb939cac8..4016fe1c65a9 100644
--- a/arch/parisc/include/asm/cache.h
+++ b/arch/parisc/include/asm/cache.h
@@ -44,22 +44,22 @@ void parisc_setup_cache_timing(void);
 
 #define pdtlb(addr)	asm volatile("pdtlb 0(%%sr1,%0)" \
 			ALTERNATIVE(ALT_COND_NO_SMP, INSN_PxTLB) \
-			: : "r" (addr))
+			: : "r" (addr) : "memory")
 #define pitlb(addr)	asm volatile("pitlb 0(%%sr1,%0)" \
 			ALTERNATIVE(ALT_COND_NO_SMP, INSN_PxTLB) \
 			ALTERNATIVE(ALT_COND_NO_SPLIT_TLB, INSN_NOP) \
-			: : "r" (addr))
+			: : "r" (addr) : "memory")
 #define pdtlb_kernel(addr)  asm volatile("pdtlb 0(%0)"   \
 			ALTERNATIVE(ALT_COND_NO_SMP, INSN_PxTLB) \
-			: : "r" (addr))
+			: : "r" (addr) : "memory")
 
 #define asm_io_fdc(addr) asm volatile("fdc %%r0(%0)" \
 			ALTERNATIVE(ALT_COND_NO_DCACHE, INSN_NOP) \
 			ALTERNATIVE(ALT_COND_NO_IOC_FDC, INSN_NOP) \
-			: : "r" (addr))
+			: : "r" (addr) : "memory")
 #define asm_io_sync()	asm volatile("sync" \
 			ALTERNATIVE(ALT_COND_NO_DCACHE, INSN_NOP) \
-			ALTERNATIVE(ALT_COND_NO_IOC_FDC, INSN_NOP) :: )
+			ALTERNATIVE(ALT_COND_NO_IOC_FDC, INSN_NOP) :::"memory")
 
 #endif /* ! __ASSEMBLY__ */
 
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index fbb4e43fda05..f56cbab64ac1 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -22,7 +22,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
-	.level	LEVEL
+	.level	PA_ASM_LEVEL
 
 	__INITDATA
 ENTRY(boot_args)
@@ -258,7 +258,7 @@ stext_pdc_ret:
 	ldo		R%PA(fault_vector_11)(%r10),%r10
 
 $is_pa20:
-	.level		LEVEL /* restore 1.1 || 2.0w */
+	.level		PA_ASM_LEVEL /* restore 1.1 || 2.0w */
 #endif /*!CONFIG_64BIT*/
 	load32		PA(fault_vector_20),%r10
 
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 841db71958cd..97c206734e24 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -193,6 +193,7 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
  */
 
 int running_on_qemu __read_mostly;
+EXPORT_SYMBOL(running_on_qemu);
 
 void __cpuidle arch_cpu_idle_dead(void)
 {
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 4f77bd9be66b..93cc36d98875 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -48,7 +48,7 @@ registers).
 	 */
 #define KILL_INSN	break	0,0
 
-	.level          LEVEL
+	.level          PA_ASM_LEVEL
 
 	.text
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 059187a3ded7..3d1305aa64b6 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -512,7 +512,7 @@ static void __init map_pages(unsigned long start_vaddr,
 
 void __init set_kernel_text_rw(int enable_read_write)
 {
-	unsigned long start = (unsigned long) _text;
+	unsigned long start = (unsigned long) __init_begin;
 	unsigned long end   = (unsigned long) &data_start;
 
 	map_pages(start, __pa(start), end-start,
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 6ee8195a2ffb..4a6dd3ba0b0b 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -237,7 +237,6 @@ extern void arch_exit_mmap(struct mm_struct *mm);
 #endif
 
 static inline void arch_unmap(struct mm_struct *mm,
-			      struct vm_area_struct *vma,
 			      unsigned long start, unsigned long end)
 {
 	if (start <= mm->context.vdso_base && mm->context.vdso_base < end)
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 532ab79734c7..d43e8fe6d424 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -543,14 +543,14 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	ret = kvmppc_tce_validate(stt, tce);
 	if (ret != H_SUCCESS)
-		return ret;
+		goto unlock_exit;
 
 	dir = iommu_tce_direction(tce);
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-
 	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
 		ret = H_PARAMETER;
 		goto unlock_exit;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5a066fc299e1..f17065f2c962 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3407,7 +3407,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
 	vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
 
-	mtspr(SPRN_PSSCR, host_psscr);
+	/* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+	mtspr(SPRN_PSSCR, host_psscr |
+	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
 	mtspr(SPRN_HFSCR, host_hfscr);
 	mtspr(SPRN_CIABR, host_ciabr);
 	mtspr(SPRN_DAWR, host_dawr);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ed554b09eb3f..6023021c9b23 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -148,6 +148,7 @@ config S390
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_GUP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 063732414dfb..861f2b63f290 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1203,42 +1203,79 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
 #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
 #define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
 
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-#define pgd_offset_raw(pgd, addr) ((pgd) + pgd_index(addr))
-
 #define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
 #define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
 #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
 #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
 
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+/*
+ * The pgd_offset function *always* adds the index for the top-level
+ * region/segment table. This is done to get a sequence like the
+ * following to work:
+ *	pgdp = pgd_offset(current->mm, addr);
+ *	pgd = READ_ONCE(*pgdp);
+ *	p4dp = p4d_offset(&pgd, addr);
+ *	...
+ * The subsequent p4d_offset, pud_offset and pmd_offset functions
+ * only add an index if they dereferenced the pointer.
+ */
+static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
 {
-	p4d_t *p4d = (p4d_t *) pgd;
+	unsigned long rste;
+	unsigned int shift;
 
-	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
-		p4d = (p4d_t *) pgd_deref(*pgd);
-	return p4d + p4d_index(address);
+	/* Get the first entry of the top level table */
+	rste = pgd_val(*pgd);
+	/* Pick up the shift from the table type of the first entry */
+	shift = ((rste & _REGION_ENTRY_TYPE_MASK) >> 2) * 11 + 20;
+	return pgd + ((address >> shift) & (PTRS_PER_PGD - 1));
 }
 
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+#define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
-	pud_t *pud = (pud_t *) p4d;
+	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+		return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
+	return (p4d_t *) pgd;
+}
 
-	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
-		pud = (pud_t *) p4d_deref(*p4d);
-	return pud + pud_index(address);
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+		return (pud_t *) p4d_deref(*p4d) + pud_index(address);
+	return (pud_t *) p4d;
 }
 
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 {
-	pmd_t *pmd = (pmd_t *) pud;
+	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+		return (pmd_t *) pud_deref(*pud) + pmd_index(address);
+	return (pmd_t *) pud;
+}
 
-	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		pmd = (pmd_t *) pud_deref(*pud);
-	return pmd + pmd_index(address);
+static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
+{
+	return (pte_t *) pmd_deref(*pmd) + pte_index(address);
 }
 
+#define pte_offset_kernel(pmd, address) pte_offset(pmd, address)
+#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
+#define pte_unmap(pte) do { } while (0)
+
+static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (end < start)
+		return false;
+	return end <= current->mm->context.asce_limit;
+}
+#define gup_fast_permitted gup_fast_permitted
+
 #define pfn_pte(pfn,pgprot) mk_pte_phys(__pa((pfn) << PAGE_SHIFT),(pgprot))
 #define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT)
 #define pte_page(x) pfn_to_page(pte_pfn(x))
@@ -1248,12 +1285,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d))
 #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
 
-/* Find an entry in the lowest level page table.. */
-#define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
-#define pte_offset_kernel(pmd, address) pte_offset(pmd,address)
-#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_unmap(pte) do { } while (0)
-
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
 	pmd_val(pmd) &= ~_SEGMENT_ENTRY_WRITE;
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index f5880bfd1b0c..3175413186b9 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -4,7 +4,7 @@
 #
 
 obj-y		:= init.o fault.o extmem.o mmap.o vmem.o maccess.o
-obj-y		+= page-states.o gup.o pageattr.o pgtable.o pgalloc.o
+obj-y		+= page-states.o pageattr.o pgtable.o pgalloc.o
 
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
deleted file mode 100644
index 2809d11c7a28..000000000000
--- a/arch/s390/mm/gup.c
+++ /dev/null
@@ -1,300 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  Lockless get_user_pages_fast for s390
- *
- *  Copyright IBM Corp. 2010
- *  Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	pte_t *ptep, pte;
-
-	mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
-
-	ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
-	do {
-		pte = *ptep;
-		barrier();
-		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_protnone(pte))
-			return 0;
-		if ((pte_val(pte) & mask) != 0)
-			return 0;
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			return 0;
-		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(head);
-			return 0;
-		}
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-
-	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 1;
-}
-
-static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
-	if ((pmd_val(pmd) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
-
-	refs = 0;
-	head = pmd_page(pmd);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-
-static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pmd_t *pmdp, pmd;
-
-	pmdp = (pmd_t *) pudp;
-	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		pmdp = (pmd_t *) pud_deref(pud);
-	pmdp += pmd_index(addr);
-	do {
-		pmd = *pmdp;
-		barrier();
-		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
-			return 0;
-		if (unlikely(pmd_large(pmd))) {
-			/*
-			 * NUMA hinting faults need to be handled in the GUP
-			 * slowpath for accounting purposes and so that they
-			 * can be serialised against THP migration.
-			 */
-			if (pmd_protnone(pmd))
-				return 0;
-			if (!gup_huge_pmd(pmdp, pmd, addr, next,
-					  write, pages, nr))
-				return 0;
-		} else if (!gup_pte_range(pmdp, pmd, addr, next,
-					  write, pages, nr))
-			return 0;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _REGION_ENTRY_PROTECT : 0) | _REGION_ENTRY_INVALID;
-	if ((pud_val(pud) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
-
-	refs = 0;
-	head = pud_page(pud);
-	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pud_val(pud) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-static inline int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pud_t *pudp, pud;
-
-	pudp = (pud_t *) p4dp;
-	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
-		pudp = (pud_t *) p4d_deref(p4d);
-	pudp += pud_index(addr);
-	do {
-		pud = *pudp;
-		barrier();
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			return 0;
-		if (unlikely(pud_large(pud))) {
-			if (!gup_huge_pud(pudp, pud, addr, next, write, pages,
-					  nr))
-				return 0;
-		} else if (!gup_pmd_range(pudp, pud, addr, next, write, pages,
-					  nr))
-			return 0;
-	} while (pudp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	p4d_t *p4dp, p4d;
-
-	p4dp = (p4d_t *) pgdp;
-	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
-		p4dp = (p4d_t *) pgd_deref(pgd);
-	p4dp += p4d_index(addr);
-	do {
-		p4d = *p4dp;
-		barrier();
-		next = p4d_addr_end(addr, end);
-		if (p4d_none(p4d))
-			return 0;
-		if (!gup_pud_range(p4dp, p4d, addr, next, write, pages, nr))
-			return 0;
-	} while (p4dp++, addr = next, addr != end);
-
-	return 1;
-}
-
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr, len, end;
-	unsigned long next, flags;
-	pgd_t *pgdp, pgd;
-	int nr = 0;
-
-	start &= PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-	if ((end <= start) || (end > mm->context.asce_limit))
-		return 0;
-	/*
-	 * local_irq_save() doesn't prevent pagetable teardown, but does
-	 * prevent the pagetables from being freed on s390.
-	 *
-	 * So long as we atomically load page table pointers versus teardown,
-	 * we can follow the address down to the the page and take a ref on it.
-	 */
-	local_irq_save(flags);
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd = *pgdp;
-		barrier();
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (!gup_p4d_range(pgdp, pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-	local_irq_restore(flags);
-
-	return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @write:	whether pages will be written to
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			struct page **pages)
-{
-	int nr, ret;
-
-	might_sleep();
-	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	if (nr == nr_pages)
-		return nr;
-
-	/* Try to get the remaining pages with get_user_pages */
-	start += nr << PAGE_SHIFT;
-	pages += nr;
-	ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
-				      write ? FOLL_WRITE : 0);
-	/* Have to be a bit careful with return values */
-	if (nr > 0)
-		ret = (ret < 0) ? nr : ret + nr;
-	return ret;
-}
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index fca34b2177e2..9f4b4bb78120 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -22,7 +22,6 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 }
 extern void arch_exit_mmap(struct mm_struct *mm);
 static inline void arch_unmap(struct mm_struct *mm,
-			struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
 }
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index 5c205a9cb5a6..9f06ea5466dd 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -88,7 +88,6 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm,
 }
 
 static inline void arch_unmap(struct mm_struct *mm,
-			struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
 }
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index cd4df9322501..7bbfe7d35da7 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -76,15 +76,14 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
-			u8 *out)
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
 {
 	if (irq_fpu_usable()) {
 		kernel_fpu_begin();
-		*(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_pcl(crc, data, len);
 		kernel_fpu_end();
 	} else
-		*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_generic(crc, data, len);
 	return 0;
 }
 
@@ -93,15 +92,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	return __chksum_finup(&ctx->crc, data, len, out);
+	return __chksum_finup(ctx->crc, data, len, out);
 }
 
 static int chksum_digest(struct shash_desc *desc, const u8 *data,
 			 unsigned int length, u8 *out)
 {
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
+	return __chksum_finup(0, data, length, out);
 }
 
 static struct shash_alg alg = {
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index d309f30cf7af..5fc76b755510 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -650,6 +650,7 @@ ENTRY(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	pushfl
 
 	/* switch stack */
 	movl	%esp, TASK_threadsp(%eax)
@@ -672,6 +673,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfl
 	popl	%esi
 	popl	%edi
 	popl	%ebx
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 1f0efdb7b629..b1d59a7c556e 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -291,6 +291,7 @@ ENTRY(__switch_to_asm)
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+	pushfq
 
 	/* switch stack */
 	movq	%rsp, TASK_threadsp(%rdi)
@@ -313,6 +314,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfq
 	popq	%r15
 	popq	%r14
 	popq	%r13
@@ -879,7 +881,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * @paranoid == 2 is special: the stub will never switch stacks.  This is for
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 create_gap=0
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
@@ -899,6 +901,20 @@ ENTRY(\sym)
 	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
 
+	.if \create_gap == 1
+	/*
+	 * If coming from kernel space, create a 6-word gap to allow the
+	 * int3 handler to emulate a call instruction.
+	 */
+	testb	$3, CS-ORIG_RAX(%rsp)
+	jnz	.Lfrom_usermode_no_gap_\@
+	.rept	6
+	pushq	5*8(%rsp)
+	.endr
+	UNWIND_HINT_IRET_REGS offset=8
+.Lfrom_usermode_no_gap_\@:
+	.endif
+
 	.if \paranoid
 	call	paranoid_entry
 	.else
@@ -1130,7 +1146,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \
 #endif /* CONFIG_HYPERV */
 
 idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3			do_int3			has_error_code=0
+idtentry int3			do_int3			has_error_code=0	create_gap=1
 idtentry stack_segment		do_stack_segment	has_error_code=1
 
 #ifdef CONFIG_XEN_PV
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 71fb8b7b2954..c87b06ad9f86 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2090,15 +2090,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
+
+	/*
+	 * Needs to be called after x86_pmu_disable_event,
+	 * so we don't trigger the event without PEBS bit set.
+	 */
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c1a812bd5a27..f7d562bd7dc7 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -209,16 +209,6 @@ static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
 #endif
 
-#ifdef CONFIG_X86_MCE_AMD
-void mce_amd_feature_init(struct cpuinfo_x86 *c);
-int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
-#else
-static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
-static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
-#endif
-
-static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); }
-
 int mce_available(struct cpuinfo_x86 *c);
 bool mce_is_memory_error(struct mce *m);
 bool mce_is_correctable(struct mce *m);
@@ -338,12 +328,19 @@ extern bool amd_mce_is_memory_error(struct mce *m);
 extern int mce_threshold_create_device(unsigned int cpu);
 extern int mce_threshold_remove_device(unsigned int cpu);
 
-#else
+void mce_amd_feature_init(struct cpuinfo_x86 *c);
+int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
 
-static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
-static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
-static inline bool amd_mce_is_memory_error(struct mce *m) { return false; };
+#else
 
+static inline int mce_threshold_create_device(unsigned int cpu)		{ return 0; };
+static inline int mce_threshold_remove_device(unsigned int cpu)		{ return 0; };
+static inline bool amd_mce_is_memory_error(struct mce *m)		{ return false; };
+static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)		{ }
+static inline int
+umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)	{ return -EINVAL; };
 #endif
 
+static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c)	{ return mce_amd_feature_init(c); }
+
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 19d18fae6ec6..41019af68adf 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -277,8 +277,8 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 	mpx_mm_init(mm);
 }
 
-static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
-			      unsigned long start, unsigned long end)
+static inline void arch_unmap(struct mm_struct *mm, unsigned long start,
+			      unsigned long end)
 {
 	/*
 	 * mpx_notify_unmap() goes and reads a rarely-hot
@@ -298,7 +298,7 @@ static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * consistently wrong.
 	 */
 	if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
-		mpx_notify_unmap(mm, vma, start, end);
+		mpx_notify_unmap(mm, start, end);
 }
 
 /*
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index d0b1434fb0b6..143a5c193ed3 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -64,12 +64,15 @@ struct mpx_fault_info {
 };
 
 #ifdef CONFIG_X86_INTEL_MPX
-int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs);
-int mpx_handle_bd_fault(void);
+
+extern int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs);
+extern int mpx_handle_bd_fault(void);
+
 static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 {
 	return (mm->context.bd_addr != MPX_INVALID_BOUNDS_DIR);
 }
+
 static inline void mpx_mm_init(struct mm_struct *mm)
 {
 	/*
@@ -78,11 +81,10 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 	 */
 	mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR;
 }
-void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
-		      unsigned long start, unsigned long end);
 
-unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len,
-		unsigned long flags);
+extern void mpx_notify_unmap(struct mm_struct *mm, unsigned long start, unsigned long end);
+extern unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, unsigned long flags);
+
 #else
 static inline int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
 {
@@ -100,7 +102,6 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 {
 }
 static inline void mpx_notify_unmap(struct mm_struct *mm,
-				    struct vm_area_struct *vma,
 				    unsigned long start, unsigned long end)
 {
 }
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 9c85b54bf03c..0bb566315621 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -259,8 +259,7 @@ extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
 extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
 
 #define gup_fast_permitted gup_fast_permitted
-static inline bool gup_fast_permitted(unsigned long start, int nr_pages,
-		int write)
+static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
 {
 	unsigned long len, end;
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 7cf1a270d891..157149d4129c 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -40,6 +40,7 @@ asmlinkage void ret_from_fork(void);
  * order of the fields must match the code in __switch_to_asm().
  */
 struct inactive_task_frame {
+	unsigned long flags;
 #ifdef CONFIG_X86_64
 	unsigned long r15;
 	unsigned long r14;
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index e85ff65c43c3..05861cc08787 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -39,4 +39,32 @@ extern int poke_int3_handler(struct pt_regs *regs);
 extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 extern int after_bootmem;
 
+static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
+{
+	regs->ip = ip;
+}
+
+#define INT3_INSN_SIZE 1
+#define CALL_INSN_SIZE 5
+
+#ifdef CONFIG_X86_64
+static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
+{
+	/*
+	 * The int3 handler in entry_64.S adds a gap between the
+	 * stack where the break point happened, and the saving of
+	 * pt_regs. We can extend the original stack because of
+	 * this gap. See the idtentry macro's create_gap option.
+	 */
+	regs->sp -= sizeof(unsigned long);
+	*(unsigned long *)regs->sp = val;
+}
+
+static inline void int3_emulate_call(struct pt_regs *regs, unsigned long func)
+{
+	int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE);
+	int3_emulate_jmp(regs, func);
+}
+#endif
+
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 89298c83de53..496033b01d26 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -545,6 +545,66 @@ out:
 	return offset;
 }
 
+bool amd_filter_mce(struct mce *m)
+{
+	enum smca_bank_types bank_type = smca_get_bank_type(m->bank);
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	u8 xec = (m->status >> 16) & 0x3F;
+
+	/* See Family 17h Models 10h-2Fh Erratum #1114. */
+	if (c->x86 == 0x17 &&
+	    c->x86_model >= 0x10 && c->x86_model <= 0x2F &&
+	    bank_type == SMCA_IF && xec == 10)
+		return true;
+
+	return false;
+}
+
+/*
+ * Turn off thresholding banks for the following conditions:
+ * - MC4_MISC thresholding is not supported on Family 0x15.
+ * - Prevent possible spurious interrupts from the IF bank on Family 0x17
+ *   Models 0x10-0x2F due to Erratum #1114.
+ */
+void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
+{
+	int i, num_msrs;
+	u64 hwcr;
+	bool need_toggle;
+	u32 msrs[NR_BLOCKS];
+
+	if (c->x86 == 0x15 && bank == 4) {
+		msrs[0] = 0x00000413; /* MC4_MISC0 */
+		msrs[1] = 0xc0000408; /* MC4_MISC1 */
+		num_msrs = 2;
+	} else if (c->x86 == 0x17 &&
+		   (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) {
+
+		if (smca_get_bank_type(bank) != SMCA_IF)
+			return;
+
+		msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank);
+		num_msrs = 1;
+	} else {
+		return;
+	}
+
+	rdmsrl(MSR_K7_HWCR, hwcr);
+
+	/* McStatusWrEn has to be set */
+	need_toggle = !(hwcr & BIT(18));
+	if (need_toggle)
+		wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
+
+	/* Clear CntP bit safely */
+	for (i = 0; i < num_msrs; i++)
+		msr_clear_bit(msrs[i], 62);
+
+	/* restore old settings */
+	if (need_toggle)
+		wrmsrl(MSR_K7_HWCR, hwcr);
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
@@ -556,6 +616,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 		if (mce_flags.smca)
 			smca_configure(bank, cpu);
 
+		disable_err_thresholding(c, bank);
+
 		for (block = 0; block < NR_BLOCKS; ++block) {
 			address = get_block_address(address, low, high, bank, block);
 			if (!address)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 6ce290c506d9..1a7084ba9a3b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1612,36 +1612,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		if (c->x86 == 0x15 && c->x86_model <= 0xf)
 			mce_flags.overflow_recov = 1;
 
-		/*
-		 * Turn off MC4_MISC thresholding banks on those models since
-		 * they're not supported there.
-		 */
-		if (c->x86 == 0x15 &&
-		    (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) {
-			int i;
-			u64 hwcr;
-			bool need_toggle;
-			u32 msrs[] = {
-				0x00000413, /* MC4_MISC0 */
-				0xc0000408, /* MC4_MISC1 */
-			};
-
-			rdmsrl(MSR_K7_HWCR, hwcr);
-
-			/* McStatusWrEn has to be set */
-			need_toggle = !(hwcr & BIT(18));
-
-			if (need_toggle)
-				wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
-
-			/* Clear CntP bit safely */
-			for (i = 0; i < ARRAY_SIZE(msrs); i++)
-				msr_clear_bit(msrs[i], 62);
-
-			/* restore old settings */
-			if (need_toggle)
-				wrmsrl(MSR_K7_HWCR, hwcr);
-		}
 	}
 
 	if (c->x86_vendor == X86_VENDOR_INTEL) {
@@ -1801,6 +1771,14 @@ static void __mcheck_cpu_init_timer(void)
 	mce_start_timer(t);
 }
 
+bool filter_mce(struct mce *m)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return amd_filter_mce(m);
+
+	return false;
+}
+
 /* Handle unconfigured int18 (should never happen) */
 static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index 3395549c51d3..64d1d5a00f39 100644
--- a/arch/x86/kernel/cpu/mce/genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -99,6 +99,9 @@ int mce_gen_pool_add(struct mce *mce)
 {
 	struct mce_evt_llist *node;
 
+	if (filter_mce(mce))
+		return -EINVAL;
+
 	if (!mce_evt_pool)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index af5eab1e65e2..a34b55baa7aa 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -173,4 +173,13 @@ struct mca_msr_regs {
 
 extern struct mca_msr_regs msr_ops;
 
+/* Decide whether to add MCE record to MCE event pool or filter it out. */
+extern bool filter_mce(struct mce *m);
+
+#ifdef CONFIG_X86_MCE_AMD
+extern bool amd_filter_mce(struct mce *m);
+#else
+static inline bool amd_filter_mce(struct mce *m)			{ return false; };
+#endif
+
 #endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 763d4264d16a..2ee4b12a70e8 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -29,6 +29,7 @@
 #include <asm/kprobes.h>
 #include <asm/ftrace.h>
 #include <asm/nops.h>
+#include <asm/text-patching.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -231,6 +232,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 }
 
 static unsigned long ftrace_update_func;
+static unsigned long ftrace_update_func_call;
 
 static int update_ftrace_func(unsigned long ip, void *new)
 {
@@ -259,6 +261,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	unsigned char *new;
 	int ret;
 
+	ftrace_update_func_call = (unsigned long)func;
+
 	new = ftrace_call_replace(ip, (unsigned long)func);
 	ret = update_ftrace_func(ip, new);
 
@@ -294,13 +298,28 @@ int ftrace_int3_handler(struct pt_regs *regs)
 	if (WARN_ON_ONCE(!regs))
 		return 0;
 
-	ip = regs->ip - 1;
-	if (!ftrace_location(ip) && !is_ftrace_caller(ip))
-		return 0;
+	ip = regs->ip - INT3_INSN_SIZE;
 
-	regs->ip += MCOUNT_INSN_SIZE - 1;
+#ifdef CONFIG_X86_64
+	if (ftrace_location(ip)) {
+		int3_emulate_call(regs, (unsigned long)ftrace_regs_caller);
+		return 1;
+	} else if (is_ftrace_caller(ip)) {
+		if (!ftrace_update_func_call) {
+			int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
+			return 1;
+		}
+		int3_emulate_call(regs, ftrace_update_func_call);
+		return 1;
+	}
+#else
+	if (ftrace_location(ip) || is_ftrace_caller(ip)) {
+		int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
+		return 1;
+	}
+#endif
 
-	return 1;
+	return 0;
 }
 
 static int ftrace_write(unsigned long ip, const char *val, int size)
@@ -858,6 +877,8 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 
 	func = ftrace_ops_get_func(ops);
 
+	ftrace_update_func_call = (unsigned long)func;
+
 	/* Do a safe modify in case the trampoline is executing */
 	new = ftrace_call_replace(ip, (unsigned long)func);
 	ret = update_ftrace_func(ip, new);
@@ -959,6 +980,7 @@ static int ftrace_mod_jmp(unsigned long ip, void *func)
 {
 	unsigned char *new;
 
+	ftrace_update_func_call = 0UL;
 	new = ftrace_jmp_replace(ip, (unsigned long)func);
 
 	return update_ftrace_func(ip, new);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e471d8e6f0b2..70933193878c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	struct task_struct *tsk;
 	int err;
 
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6a62f4af9fcf..026a43be9bd1 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -392,6 +392,14 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
+
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 85fe1870f873..9b7c4ca8f0a7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -58,7 +58,6 @@
 #include <asm/alternative.h>
 #include <asm/fpu/xstate.h>
 #include <asm/trace/mpx.h>
-#include <asm/nospec-branch.h>
 #include <asm/mpx.h>
 #include <asm/vm86.h>
 #include <asm/umip.h>
@@ -367,13 +366,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 		regs->ip = (unsigned long)general_protection;
 		regs->sp = (unsigned long)&gpregs->orig_ax;
 
-		/*
-		 * This situation can be triggered by userspace via
-		 * modify_ldt(2) and the return does not take the regular
-		 * user space exit, so a CPU buffer clear is required when
-		 * MDS mitigation is enabled.
-		 */
-		mds_user_clear_cpu_buffers();
 		return;
 	}
 #endif
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 371c669696d7..610c0f1fbdd7 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1371,7 +1371,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
 
 		valid_bank_mask = BIT_ULL(0);
 		sparse_banks[0] = flush.processor_mask;
-		all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+
+		/*
+		 * Work around possible WS2012 bug: it sends hypercalls
+		 * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear,
+		 * while also expecting us to flush something and crashing if
+		 * we don't. Let's treat processor_mask == 0 same as
+		 * HV_FLUSH_ALL_PROCESSORS.
+		 */
+		all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) ||
+			flush.processor_mask == 0;
 	} else {
 		if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
 					    sizeof(flush_ex))))
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 235687f3388f..6939eba2001a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1453,7 +1453,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	if (swait_active(q))
 		swake_up_one(q);
 
-	if (apic_lvtt_tscdeadline(apic))
+	if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3eeb7183fc09..0bbb21a49082 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1262,31 +1262,42 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	return 0;
 }
 
-bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
-	if (efer & efer_reserved_bits)
-		return false;
-
 	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
-			return false;
+		return false;
 
 	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
-			return false;
+		return false;
 
 	return true;
+
+}
+bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+	if (efer & efer_reserved_bits)
+		return false;
+
+	return __kvm_valid_efer(vcpu, efer);
 }
 EXPORT_SYMBOL_GPL(kvm_valid_efer);
 
-static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 old_efer = vcpu->arch.efer;
+	u64 efer = msr_info->data;
 
-	if (!kvm_valid_efer(vcpu, efer))
-		return 1;
+	if (efer & efer_reserved_bits)
+		return false;
 
-	if (is_paging(vcpu)
-	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
-		return 1;
+	if (!msr_info->host_initiated) {
+		if (!__kvm_valid_efer(vcpu, efer))
+			return 1;
+
+		if (is_paging(vcpu) &&
+		    (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+			return 1;
+	}
 
 	efer &= ~EFER_LMA;
 	efer |= vcpu->arch.efer & EFER_LMA;
@@ -2456,7 +2467,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.arch_capabilities = data;
 		break;
 	case MSR_EFER:
-		return set_efer(vcpu, data);
+		return set_efer(vcpu, msr_info);
 	case MSR_K7_HWCR:
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
 		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 140e61843a07..3cb3af51ec89 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -6,6 +6,18 @@
 # Produces uninteresting flaky coverage.
 KCOV_INSTRUMENT_delay.o	:= n
 
+# Early boot use of cmdline; don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KCOV_INSTRUMENT_cmdline.o := n
+KASAN_SANITIZE_cmdline.o  := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_cmdline.o = -pg
+endif
+
+CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector)
+endif
+
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
 quiet_cmd_inat_tables = GEN     $@
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index de1851d15699..ea17ff6c8588 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -881,9 +881,10 @@ static int mpx_unmap_tables(struct mm_struct *mm,
  * the virtual address region start...end have already been split if
  * necessary, and the 'vma' is the first vma in this range (start -> end).
  */
-void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long start, unsigned long end)
+void mpx_notify_unmap(struct mm_struct *mm, unsigned long start,
+		      unsigned long end)
 {
+	struct vm_area_struct *vma;
 	int ret;
 
 	/*
@@ -902,11 +903,12 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * which should not occur normally. Being strict about it here
 	 * helps ensure that we do not have an exploitable stack overflow.
 	 */
-	do {
+	vma = find_vma(mm, start);
+	while (vma && vma->vm_start < end) {
 		if (vma->vm_flags & VM_MPX)
 			return;
 		vma = vma->vm_next;
-	} while (vma && vma->vm_start < end);
+	}
 
 	ret = mpx_unmap_tables(mm, start, end);
 	if (ret)
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 62f5c7045944..1861a2ba0f2b 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -44,8 +44,6 @@ void __init __weak mem_map_via_hcall(struct boot_params *ptr __maybe_unused)
 
 static void __init init_pvh_bootparams(bool xen_guest)
 {
-	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
-
 	if ((pvh_start_info.version > 0) && (pvh_start_info.memmap_entries)) {
 		struct hvm_memmap_table_entry *ep;
 		int i;
@@ -103,7 +101,7 @@ static void __init init_pvh_bootparams(bool xen_guest)
  * If we are trying to boot a Xen PVH guest, it is expected that the kernel
  * will have been configured to provide the required override for this routine.
  */
-void __init __weak xen_pvh_init(void)
+void __init __weak xen_pvh_init(struct boot_params *boot_params)
 {
 	xen_raw_printk("Error: Missing xen PVH initialization\n");
 	BUG();
@@ -112,7 +110,7 @@ void __init __weak xen_pvh_init(void)
 static void hypervisor_specific_init(bool xen_guest)
 {
 	if (xen_guest)
-		xen_pvh_init();
+		xen_pvh_init(&pvh_bootparams);
 }
 
 /*
@@ -131,6 +129,8 @@ void __init xen_prepare_pvh(void)
 		BUG();
 	}
 
+	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+
 	hypervisor_specific_init(xen_guest);
 
 	init_pvh_bootparams(xen_guest);
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 1fbb629a9d78..0d3365cb64de 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -158,7 +158,7 @@ static enum efi_secureboot_mode xen_efi_get_secureboot(void)
 	return efi_secureboot_mode_unknown;
 }
 
-void __init xen_efi_init(void)
+void __init xen_efi_init(struct boot_params *boot_params)
 {
 	efi_system_table_t *efi_systab_xen;
 
@@ -167,12 +167,12 @@ void __init xen_efi_init(void)
 	if (efi_systab_xen == NULL)
 		return;
 
-	strncpy((char *)&boot_params.efi_info.efi_loader_signature, "Xen",
-			sizeof(boot_params.efi_info.efi_loader_signature));
-	boot_params.efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
-	boot_params.efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
+	strncpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
+			sizeof(boot_params->efi_info.efi_loader_signature));
+	boot_params->efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
+	boot_params->efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
 
-	boot_params.secure_boot = xen_efi_get_secureboot();
+	boot_params->secure_boot = xen_efi_get_secureboot();
 
 	set_bit(EFI_BOOT, &efi.flags);
 	set_bit(EFI_PARAVIRT, &efi.flags);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index c54a493e139a..4722ba2966ac 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1403,7 +1403,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/* We need this for printk timestamps */
 	xen_setup_runstate_info(0);
 
-	xen_efi_init();
+	xen_efi_init(&boot_params);
 
 	/* Start the world */
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 35b7599d2d0b..80a79db72fcf 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -13,6 +13,8 @@
 
 #include <xen/interface/memory.h>
 
+#include "xen-ops.h"
+
 /*
  * PVH variables.
  *
@@ -21,17 +23,20 @@
  */
 bool xen_pvh __attribute__((section(".data"))) = 0;
 
-void __init xen_pvh_init(void)
+void __init xen_pvh_init(struct boot_params *boot_params)
 {
 	u32 msr;
 	u64 pfn;
 
 	xen_pvh = 1;
+	xen_domain_type = XEN_HVM_DOMAIN;
 	xen_start_flags = pvh_start_info.flags;
 
 	msr = cpuid_ebx(xen_cpuid_base() + 2);
 	pfn = __pa(hypercall_page);
 	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+	xen_efi_init(boot_params);
 }
 
 void __init mem_map_via_hcall(struct boot_params *boot_params_p)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 0e60bd918695..2f111f47ba98 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -122,9 +122,9 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
 void __init xen_init_apic(void);
 
 #ifdef CONFIG_XEN_EFI
-extern void xen_efi_init(void);
+extern void xen_efi_init(struct boot_params *boot_params);
 #else
-static inline void __init xen_efi_init(void)
+static inline void __init xen_efi_init(struct boot_params *boot_params)
 {
 }
 #endif