Merge tag 'v4.9.30' into linux-linaro-lsk-v4.9

 This is the 4.9.30 stable release

36 files changed, 344 insertions, 133 deletions

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index ffb93f49..4f95577 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1188,8 +1188,10 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 	if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur)))
 		return -EFAULT;
 
-	err = 0;
-	err |= put_user(status, ustatus);
+	err = put_user(status, ustatus);
+	if (ret < 0)
+		return err ? err : ret;
+
 	err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec);
 	err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec);
 	err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec);
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index c51fc65..5a53fcf 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -162,9 +162,10 @@
 			};
 
 			adc0: adc@f8018000 {
+				atmel,adc-vref = <3300>;
+				atmel,adc-channels-used = <0xfe>;
 				pinctrl-0 = <
 					&pinctrl_adc0_adtrg
-					&pinctrl_adc0_ad0
 					&pinctrl_adc0_ad1
 					&pinctrl_adc0_ad2
 					&pinctrl_adc0_ad3
@@ -172,8 +173,6 @@
 					&pinctrl_adc0_ad5
 					&pinctrl_adc0_ad6
 					&pinctrl_adc0_ad7
-					&pinctrl_adc0_ad8
-					&pinctrl_adc0_ad9
 					>;
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts
index 5bb8fd5..d71da30 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb.dts
@@ -12,23 +12,6 @@
 	model = "Freescale i.MX6 SoloX SDB RevB Board";
 };
 
-&cpu0 {
-	operating-points = <
-		/* kHz    uV */
-		996000  1250000
-		792000  1175000
-		396000  1175000
-		198000  1175000
-		>;
-	fsl,soc-operating-points = <
-		/* ARM kHz      SOC uV */
-		996000	1250000
-		792000	1175000
-		396000	1175000
-		198000  1175000
-	>;
-};
-
 &i2c1 {
 	clock-frequency = <100000>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/tegra20-paz00.dts b/arch/arm/boot/dts/tegra20-paz00.dts
index 4e361a8..b4bfa55 100644
--- a/arch/arm/boot/dts/tegra20-paz00.dts
+++ b/arch/arm/boot/dts/tegra20-paz00.dts
@@ -569,6 +569,7 @@
 			regulator-name = "+3VS,vdd_pnl";
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
+			regulator-boot-on;
 			gpio = <&gpio TEGRA_GPIO(A, 4) GPIO_ACTIVE_HIGH>;
 			enable-active-high;
 		};
diff --git a/arch/arm/include/asm/kvm_coproc.h b/arch/arm/include/asm/kvm_coproc.h
index 4917c2f..e74ab0f 100644
--- a/arch/arm/include/asm/kvm_coproc.h
+++ b/arch/arm/include/asm/kvm_coproc.h
@@ -31,7 +31,8 @@ void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table);
 int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index 464748b..ed23196 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -18,13 +18,18 @@ enum {
 };
 #endif
 
+struct mod_plt_sec {
+	struct elf32_shdr	*plt;
+	int			plt_count;
+};
+
 struct mod_arch_specific {
 #ifdef CONFIG_ARM_UNWIND
 	struct unwind_table *unwind[ARM_SEC_MAX];
 #endif
 #ifdef CONFIG_ARM_MODULE_PLTS
-	struct elf32_shdr   *plt;
-	int		    plt_count;
+	struct mod_plt_sec	core;
+	struct mod_plt_sec	init;
 #endif
 };
 
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
index 3a5cba9..3d0c2e4 100644
--- a/arch/arm/kernel/module-plts.c
+++ b/arch/arm/kernel/module-plts.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -31,9 +31,17 @@ struct plt_entries {
 	u32	lit[PLT_ENT_COUNT];
 };
 
+static bool in_init(const struct module *mod, unsigned long loc)
+{
+	return loc - (u32)mod->init_layout.base < mod->init_layout.size;
+}
+
 u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
 {
-	struct plt_entries *plt = (struct plt_entries *)mod->arch.plt->sh_addr;
+	struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
+							  &mod->arch.init;
+
+	struct plt_entries *plt = (struct plt_entries *)pltsec->plt->sh_addr;
 	int idx = 0;
 
 	/*
@@ -41,9 +49,9 @@ u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
 	 * relocations are sorted, this will be the last entry we allocated.
 	 * (if one exists).
 	 */
-	if (mod->arch.plt_count > 0) {
-		plt += (mod->arch.plt_count - 1) / PLT_ENT_COUNT;
-		idx = (mod->arch.plt_count - 1) % PLT_ENT_COUNT;
+	if (pltsec->plt_count > 0) {
+		plt += (pltsec->plt_count - 1) / PLT_ENT_COUNT;
+		idx = (pltsec->plt_count - 1) % PLT_ENT_COUNT;
 
 		if (plt->lit[idx] == val)
 			return (u32)&plt->ldr[idx];
@@ -53,8 +61,8 @@ u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
 			plt++;
 	}
 
-	mod->arch.plt_count++;
-	BUG_ON(mod->arch.plt_count * PLT_ENT_SIZE > mod->arch.plt->sh_size);
+	pltsec->plt_count++;
+	BUG_ON(pltsec->plt_count * PLT_ENT_SIZE > pltsec->plt->sh_size);
 
 	if (!idx)
 		/* Populate a new set of entries */
@@ -129,7 +137,7 @@ static bool duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num)
 
 /* Count how many PLT entries we may need */
 static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base,
-			       const Elf32_Rel *rel, int num)
+			       const Elf32_Rel *rel, int num, Elf32_Word dstidx)
 {
 	unsigned int ret = 0;
 	const Elf32_Sym *s;
@@ -144,13 +152,17 @@ static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base,
 		case R_ARM_THM_JUMP24:
 			/*
 			 * We only have to consider branch targets that resolve
-			 * to undefined symbols. This is not simply a heuristic,
-			 * it is a fundamental limitation, since the PLT itself
-			 * is part of the module, and needs to be within range
-			 * as well, so modules can never grow beyond that limit.
+			 * to symbols that are defined in a different section.
+			 * This is not simply a heuristic, it is a fundamental
+			 * limitation, since there is no guaranteed way to emit
+			 * PLT entries sufficiently close to the branch if the
+			 * section size exceeds the range of a branch
+			 * instruction. So ignore relocations against defined
+			 * symbols if they live in the same section as the
+			 * relocation target.
 			 */
 			s = syms + ELF32_R_SYM(rel[i].r_info);
-			if (s->st_shndx != SHN_UNDEF)
+			if (s->st_shndx == dstidx)
 				break;
 
 			/*
@@ -161,7 +173,12 @@ static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base,
 			 * So we need to support them, but there is no need to
 			 * take them into consideration when trying to optimize
 			 * this code. So let's only check for duplicates when
-			 * the addend is zero.
+			 * the addend is zero. (Note that calls into the core
+			 * module via init PLT entries could involve section
+			 * relative symbol references with non-zero addends, for
+			 * which we may end up emitting duplicates, but the init
+			 * PLT is released along with the rest of the .init
+			 * region as soon as module loading completes.)
 			 */
 			if (!is_zero_addend_relocation(base, rel + i) ||
 			    !duplicate_rel(base, rel, i))
@@ -174,7 +191,8 @@ static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base,
 int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			      char *secstrings, struct module *mod)
 {
-	unsigned long plts = 0;
+	unsigned long core_plts = 0;
+	unsigned long init_plts = 0;
 	Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
 	Elf32_Sym *syms = NULL;
 
@@ -184,13 +202,15 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	 */
 	for (s = sechdrs; s < sechdrs_end; ++s) {
 		if (strcmp(".plt", secstrings + s->sh_name) == 0)
-			mod->arch.plt = s;
+			mod->arch.core.plt = s;
+		else if (strcmp(".init.plt", secstrings + s->sh_name) == 0)
+			mod->arch.init.plt = s;
 		else if (s->sh_type == SHT_SYMTAB)
 			syms = (Elf32_Sym *)s->sh_addr;
 	}
 
-	if (!mod->arch.plt) {
-		pr_err("%s: module PLT section missing\n", mod->name);
+	if (!mod->arch.core.plt || !mod->arch.init.plt) {
+		pr_err("%s: module PLT section(s) missing\n", mod->name);
 		return -ENOEXEC;
 	}
 	if (!syms) {
@@ -213,16 +233,29 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		/* sort by type and symbol index */
 		sort(rels, numrels, sizeof(Elf32_Rel), cmp_rel, NULL);
 
-		plts += count_plts(syms, dstsec->sh_addr, rels, numrels);
+		if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0)
+			core_plts += count_plts(syms, dstsec->sh_addr, rels,
+						numrels, s->sh_info);
+		else
+			init_plts += count_plts(syms, dstsec->sh_addr, rels,
+						numrels, s->sh_info);
 	}
 
-	mod->arch.plt->sh_type = SHT_NOBITS;
-	mod->arch.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
-	mod->arch.plt->sh_addralign = L1_CACHE_BYTES;
-	mod->arch.plt->sh_size = round_up(plts * PLT_ENT_SIZE,
-					  sizeof(struct plt_entries));
-	mod->arch.plt_count = 0;
-
-	pr_debug("%s: plt=%x\n", __func__, mod->arch.plt->sh_size);
+	mod->arch.core.plt->sh_type = SHT_NOBITS;
+	mod->arch.core.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.core.plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.core.plt->sh_size = round_up(core_plts * PLT_ENT_SIZE,
+					       sizeof(struct plt_entries));
+	mod->arch.core.plt_count = 0;
+
+	mod->arch.init.plt->sh_type = SHT_NOBITS;
+	mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.init.plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.init.plt->sh_size = round_up(init_plts * PLT_ENT_SIZE,
+					       sizeof(struct plt_entries));
+	mod->arch.init.plt_count = 0;
+
+	pr_debug("%s: plt=%x, init.plt=%x\n", __func__,
+		 mod->arch.core.plt->sh_size, mod->arch.init.plt->sh_size);
 	return 0;
 }
diff --git a/arch/arm/kernel/module.lds b/arch/arm/kernel/module.lds
index 05881e2..eacb5c6 100644
--- a/arch/arm/kernel/module.lds
+++ b/arch/arm/kernel/module.lds
@@ -1,3 +1,4 @@
 SECTIONS {
 	.plt : { BYTE(0) }
+	.init.plt : { BYTE(0) }
 }
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 3e5e419..c3ed6bd 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -93,12 +93,6 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	kvm_inject_undefined(vcpu);
-	return 1;
-}
-
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 {
 	/*
@@ -514,12 +508,7 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-/**
- * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run:  The kvm_run struct
- */
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_64bit_hsr(struct kvm_vcpu *vcpu)
 {
 	struct coproc_params params;
 
@@ -533,9 +522,38 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
 	params.CRm = 0;
 
+	return params;
+}
+
+/**
+ * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_64bit_hsr(vcpu);
+
 	return emulate_cp15(vcpu, &params);
 }
 
+/**
+ * kvm_handle_cp14_64 -- handles a mrrc/mcrr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_64bit_hsr(vcpu);
+
+	/* raz_wi cp14 */
+	pm_fake(vcpu, &params, NULL);
+
+	/* handled */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 1;
+}
+
 static void reset_coproc_regs(struct kvm_vcpu *vcpu,
 			      const struct coproc_reg *table, size_t num)
 {
@@ -546,12 +564,7 @@ static void reset_coproc_regs(struct kvm_vcpu *vcpu,
 			table[i].reset(vcpu, &table[i]);
 }
 
-/**
- * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
- * @vcpu: The VCPU pointer
- * @run:  The kvm_run struct
- */
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu)
 {
 	struct coproc_params params;
 
@@ -565,9 +578,37 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7;
 	params.Rt2 = 0;
 
+	return params;
+}
+
+/**
+ * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_32bit_hsr(vcpu);
 	return emulate_cp15(vcpu, &params);
 }
 
+/**
+ * kvm_handle_cp14_32 -- handles a mrc/mcr trap on a guest CP14 access
+ * @vcpu: The VCPU pointer
+ * @run:  The kvm_run struct
+ */
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	struct coproc_params params = decode_32bit_hsr(vcpu);
+
+	/* raz_wi cp14 */
+	pm_fake(vcpu, &params, NULL);
+
+	/* handled */
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	return 1;
+}
+
 /******************************************************************************
  * Userspace API
  *****************************************************************************/
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 4e40d19..066b6d4 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -83,9 +83,9 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
-	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_MR]	= kvm_handle_cp14_32,
 	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
-	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_64]	= kvm_handle_cp14_64,
 	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
 	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
 	[HSR_EC_HVC]		= handle_hvc,
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 3023bb5..8679405 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -2,6 +2,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
+ccflags-y += -fno-stack-protector
+
 KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c
index 92678b7..624a510 100644
--- a/arch/arm/kvm/hyp/switch.c
+++ b/arch/arm/kvm/hyp/switch.c
@@ -48,7 +48,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host)
 	write_sysreg(HSTR_T(15), HSTR);
 	write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR);
 	val = read_sysreg(HDCR);
-	write_sysreg(val | HDCR_TPM | HDCR_TPMCR, HDCR);
+	val |= HDCR_TPM | HDCR_TPMCR; /* trap performance monitors */
+	val |= HDCR_TDRA | HDCR_TDOSA | HDCR_TDA; /* trap debug regs */
+	write_sysreg(val, HDCR);
 }
 
 static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 8dea616..5049777 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -147,10 +147,10 @@ __v7m_setup_cont:
 
 	@ Configure caches (if implemented)
 	teq     r8, #0
-	stmneia	r12, {r0-r6, lr}	@ v7m_invalidate_l1 touches r0-r6
+	stmneia	sp, {r0-r6, lr}		@ v7m_invalidate_l1 touches r0-r6
 	blne	v7m_invalidate_l1
 	teq     r8, #0			@ re-evalutae condition
-	ldmneia	r12, {r0-r6, lr}
+	ldmneia	sp, {r0-r6, lr}
 
 	@ Configure the System Control Register to ensure 8-byte stack alignment
 	@ Note the STKALIGN bit is either RW or RAO.
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi
index 17839db..509a2ed 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi
@@ -772,6 +772,7 @@
 			clocks = <&sys_ctrl 2>, <&sys_ctrl 1>;
 			clock-names = "ciu", "biu";
 			resets = <&sys_ctrl PERIPH_RSTDIS0_MMC0>;
+			reset-names = "reset";
 			bus-width = <0x8>;
 			vmmc-supply = <&ldo19>;
 			pinctrl-names = "default";
@@ -795,6 +796,7 @@
 			clocks = <&sys_ctrl 4>, <&sys_ctrl 3>;
 			clock-names = "ciu", "biu";
 			resets = <&sys_ctrl PERIPH_RSTDIS0_MMC1>;
+			reset-names = "reset";
 			vqmmc-supply = <&ldo7>;
 			vmmc-supply = <&ldo10>;
 			bus-width = <0x4>;
@@ -813,6 +815,7 @@
 			clocks = <&sys_ctrl HI6220_MMC2_CIUCLK>, <&sys_ctrl HI6220_MMC2_CLK>;
 			clock-names = "ciu", "biu";
 			resets = <&sys_ctrl PERIPH_RSTDIS0_MMC2>;
+			reset-names = "reset";
 			bus-width = <0x4>;
 			broken-cd;
 			pinctrl-names = "default", "idle";
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 4e0497f..0fe7e43 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -42,25 +42,35 @@
 #define __smp_rmb()	dmb(ishld)
 #define __smp_wmb()	dmb(ishst)
 
-#define __smp_store_release(p, v)						\
+#define __smp_store_release(p, v)					\
 do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (__force typeof(*p)) (v) }; 			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u8 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u16 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u32 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u64 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	}								\
 } while (0)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 91b26d2..ae852ad 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -46,7 +46,7 @@ static inline unsigned long __xchg_case_##name(unsigned long x,		\
 	"	swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n"	\
 		__nops(3)						\
 	"	" #nop_lse)						\
-	: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)			\
+	: "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr)	\
 	: "r" (x)							\
 	: cl);								\
 									\
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 55d0adb..14cca10 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -93,11 +93,12 @@ static inline void set_fs(mm_segment_t fs)
  */
 #define __range_ok(addr, size)						\
 ({									\
+	unsigned long __addr = (unsigned long __force)(addr);		\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"		\
 		: "=&r" (flag), "=&r" (roksum)				\
-		: "1" (addr), "Ir" (size),				\
+		: "1" (__addr), "Ir" (size),				\
 		  "r" (current_thread_info()->addr_limit)		\
 		: "cc");						\
 	flag;								\
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index b0988bb..c0ede23 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -309,7 +309,8 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
 		CONFIG_ARM64_PAN)				\
 	: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2)	\
-	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT),		\
+	: "r" ((unsigned long)addr), "i" (-EAGAIN),		\
+	  "i" (-EFAULT),					\
 	  "i" (__SWP_LL_SC_LOOPS)				\
 	: "memory")
 
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index aaf42ae..14c4e3b 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -2,6 +2,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
+ccflags-y += -fno-stack-protector
+
 KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h
index 07238b3..3db3812 100644
--- a/arch/metag/include/asm/uaccess.h
+++ b/arch/metag/include/asm/uaccess.h
@@ -28,24 +28,32 @@
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
-/*
- * Explicitly allow NULL pointers here. Parts of the kernel such
- * as readv/writev use access_ok to validate pointers, but want
- * to allow NULL pointers for various reasons. NULL pointers are
- * safe to allow through because the first page is not mappable on
- * Meta.
- *
- * We also wish to avoid letting user code access the system area
- * and the kernel half of the address space.
- */
-#define __user_bad(addr, size) (((addr) > 0 && (addr) < META_MEMORY_BASE) || \
-				((addr) > PAGE_OFFSET &&		\
-				 (addr) < LINCORE_BASE))
-
 static inline int __access_ok(unsigned long addr, unsigned long size)
 {
-	return __kernel_ok || !__user_bad(addr, size);
+	/*
+	 * Allow access to the user mapped memory area, but not the system area
+	 * before it. The check extends to the top of the address space when
+	 * kernel access is allowed (there's no real reason to user copy to the
+	 * system area in any case).
+	 */
+	if (likely(addr >= META_MEMORY_BASE && addr < get_fs().seg &&
+		   size <= get_fs().seg - addr))
+		return true;
+	/*
+	 * Explicitly allow NULL pointers here. Parts of the kernel such
+	 * as readv/writev use access_ok to validate pointers, but want
+	 * to allow NULL pointers for various reasons. NULL pointers are
+	 * safe to allow through because the first page is not mappable on
+	 * Meta.
+	 */
+	if (!addr)
+		return true;
+	/* Allow access to core code memory area... */
+	if (addr >= LINCORE_CODE_BASE && addr <= LINCORE_CODE_LIMIT &&
+	    size <= LINCORE_CODE_LIMIT + 1 - addr)
+		return true;
+	/* ... but no other areas. */
+	return false;
 }
 
 #define access_ok(type, addr, size) __access_ok((unsigned long)(addr),	\
@@ -186,8 +194,13 @@ do {                                                            \
 extern long __must_check __strncpy_from_user(char *dst, const char __user *src,
 					     long count);
 
-#define strncpy_from_user(dst, src, count) __strncpy_from_user(dst, src, count)
-
+static inline long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	if (!access_ok(VERIFY_READ, src, 1))
+		return -EFAULT;
+	return __strncpy_from_user(dst, src, count);
+}
 /*
  * Return the size of a string (including the ending 0)
  *
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 5a4f2eb..5e844f6 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1368,6 +1368,7 @@ config CPU_LOONGSON3
 	select WEAK_ORDERING
 	select WEAK_REORDERING_BEYOND_LLSC
 	select MIPS_PGD_C0_CONTEXT
+	select MIPS_L1_CACHE_SHIFT_6
 	select GPIOLIB
 	help
 		The Loongson 3 processor implements the MIPS64R2 instruction
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b9e3f0a..0012f03 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -70,8 +70,9 @@ extern void drop_cop(unsigned long acop, struct mm_struct *mm);
  * switch_mm is the entry point called from the architecture independent
  * code in kernel/sched/core.c
  */
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
+static inline void switch_mm_irqs_off(struct mm_struct *prev,
+				      struct mm_struct *next,
+				      struct task_struct *tsk)
 {
 	/* Mark this context has been used on the new CPU */
 	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next)))
@@ -110,6 +111,18 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	switch_mmu_context(prev, next, tsk);
 }
 
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	switch_mm_irqs_off(prev, next, tsk);
+	local_irq_restore(flags);
+}
+#define switch_mm_irqs_off switch_mm_irqs_off
+
+
 #define deactivate_mm(tsk,mm)	do { } while (0)
 
 /*
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index a5dd493..6ef8f0b 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -724,7 +724,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
  */
 #define MAX_WAIT_FOR_RECOVERY 300
 
-static void eeh_handle_normal_event(struct eeh_pe *pe)
+static bool eeh_handle_normal_event(struct eeh_pe *pe)
 {
 	struct pci_bus *frozen_bus;
 	struct eeh_dev *edev, *tmp;
@@ -736,7 +736,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	if (!frozen_bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
-		return;
+		return false;
 	}
 
 	eeh_pe_update_time_stamp(pe);
@@ -870,7 +870,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	pr_info("EEH: Notify device driver to resume\n");
 	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
 
-	return;
+	return false;
 
 excess_failures:
 	/*
@@ -915,8 +915,12 @@ perm_error:
 			pci_lock_rescan_remove();
 			pci_hp_remove_devices(frozen_bus);
 			pci_unlock_rescan_remove();
+
+			/* The passed PE should no longer be used */
+			return true;
 		}
 	}
+	return false;
 }
 
 static void eeh_handle_special_event(void)
@@ -982,7 +986,14 @@ static void eeh_handle_special_event(void)
 		 */
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
-			eeh_handle_normal_event(pe);
+			/*
+			 * eeh_handle_normal_event() can make the PE stale if it
+			 * determines that the PE cannot possibly be recovered.
+			 * Don't modify the PE state if that's the case.
+			 */
+			if (eeh_handle_normal_event(pe))
+				continue;
+
 			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		} else {
 			pci_lock_rescan_remove();
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 38a1f96..ca03eb2 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -735,8 +735,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
+#ifdef CONFIG_RELOCATABLE
+	ld	r15,PACATOC(r13)
+	ld	r14,interrupt_base_book3e@got(r15)
+	ld	r15,__end_interrupts@got(r15)
+#else
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
 	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
 	blt+	cr0,1f
@@ -799,8 +805,14 @@ kernel_dbg_exc:
 	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
+#ifdef CONFIG_RELOCATABLE
+	ld	r15,PACATOC(r13)
+	ld	r14,interrupt_base_book3e@got(r15)
+	ld	r15,__end_interrupts@got(r15)
+#else
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
 	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
 	blt+	cr0,1f
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 5e7ece0..ea236bf 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -205,6 +205,8 @@ static void machine_check_process_queued_event(struct irq_work *work)
 {
 	int index;
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	/*
 	 * For now just print it to console.
 	 * TODO: log this error event to FSP or nvram.
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 49a680d..c716473 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -839,6 +839,25 @@ static void tm_reclaim_thread(struct thread_struct *thr,
 	if (!MSR_TM_SUSPENDED(mfmsr()))
 		return;
 
+	/*
+	 * If we are in a transaction and FP is off then we can't have
+	 * used FP inside that transaction. Hence the checkpointed
+	 * state is the same as the live state. We need to copy the
+	 * live state to the checkpointed state so that when the
+	 * transaction is restored, the checkpointed state is correct
+	 * and the aborted transaction sees the correct state. We use
+	 * ckpt_regs.msr here as that's what tm_reclaim will use to
+	 * determine if it's going to write the checkpointed state or
+	 * not. So either this will write the checkpointed registers,
+	 * or reclaim will. Similarly for VMX.
+	 */
+	if ((thr->ckpt_regs.msr & MSR_FP) == 0)
+		memcpy(&thr->ckfp_state, &thr->fp_state,
+		       sizeof(struct thread_fp_state));
+	if ((thr->ckpt_regs.msr & MSR_VEC) == 0)
+		memcpy(&thr->ckvr_state, &thr->vr_state,
+		       sizeof(struct thread_vr_state));
+
 	giveup_all(container_of(thr, struct task_struct, thread));
 
 	tm_reclaim(thr, thr->ckpt_regs.msr, cause);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 023a462..43021f8 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -302,8 +302,6 @@ long machine_check_early(struct pt_regs *regs)
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
-	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
 	return handled;
@@ -737,6 +735,8 @@ void machine_check_exception(struct pt_regs *regs)
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	/* See if any machine dependent calls. In theory, we would want
 	 * to call the CPU first, and call the ppc_md. one if the CPU
 	 * one returns a positive number. However there is existing code
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 7de7124..fd59680 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -81,7 +81,7 @@ struct page *new_iommu_non_cma_page(struct page *page, unsigned long private,
 	gfp_t gfp_mask = GFP_USER;
 	struct page *new_page;
 
-	if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
+	if (PageCompound(page))
 		return NULL;
 
 	if (PageHighMem(page))
@@ -100,7 +100,7 @@ static int mm_iommu_move_page_from_cma(struct page *page)
 	LIST_HEAD(cma_migrate_pages);
 
 	/* Ignore huge pages for now */
-	if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
+	if (PageCompound(page))
 		return -EBUSY;
 
 	lru_add_drain();
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 423e450..72ae2cd 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -288,7 +288,6 @@ int dlpar_detach_node(struct device_node *dn)
 	if (rc)
 		return rc;
 
-	of_node_put(dn); /* Must decrement the refcount */
 	return 0;
 }
 
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 408b4f4..5982544 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -427,6 +427,20 @@ static void *nt_vmcoreinfo(void *ptr)
 }
 
 /*
+ * Initialize final note (needed for /proc/vmcore code)
+ */
+static void *nt_final(void *ptr)
+{
+	Elf64_Nhdr *note;
+
+	note = (Elf64_Nhdr *) ptr;
+	note->n_namesz = 0;
+	note->n_descsz = 0;
+	note->n_type = 0;
+	return PTR_ADD(ptr, sizeof(Elf64_Nhdr));
+}
+
+/*
  * Initialize ELF header (new kernel)
  */
 static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
@@ -513,6 +527,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 		if (sa->prefix != 0)
 			ptr = fill_cpu_elf_notes(ptr, cpu++, sa);
 	ptr = nt_vmcoreinfo(ptr);
+	ptr = nt_final(ptr);
 	memset(phdr, 0, sizeof(*phdr));
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = notes_offset;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 49a3073..c438168 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -321,6 +321,7 @@ ENTRY(system_call)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lsysc_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -606,6 +607,7 @@ ENTRY(io_int_handler)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lio_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -1135,15 +1137,23 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_sysc_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_sysc_restore_insn)
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
 	je	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_sysc_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_sysc_restore_insn:
+	.quad	.Lsysc_exit_timer
 	.quad	.Lsysc_done - 4
 
 .Lcleanup_io_tif:
@@ -1151,15 +1161,20 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_io_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_io_restore_insn)
-	je	0f
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_io_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_io_restore_insn:
+	.quad	.Lio_exit_timer
 	.quad	.Lio_done - 4
 
 .Lcleanup_idle:
diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c
index 48bae81..6f6e789 100644
--- a/arch/um/kernel/initrd.c
+++ b/arch/um/kernel/initrd.c
@@ -14,7 +14,7 @@
 static char *initrd __initdata = NULL;
 static int load_initrd(char *filename, void *buf, int size);
 
-static int __init read_initrd(void)
+int __init read_initrd(void)
 {
 	void *area;
 	long long size;
@@ -46,8 +46,6 @@ static int __init read_initrd(void)
 	return 0;
 }
 
-__uml_postsetup(read_initrd);
-
 static int __init uml_initrd_setup(char *line, int *add)
 {
 	initrd = line;
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index e8175a8..26b47de 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -336,11 +336,17 @@ int __init linux_main(int argc, char **argv)
 	return start_uml();
 }
 
+int __init __weak read_initrd(void)
+{
+	return 0;
+}
+
 void __init setup_arch(char **cmdline_p)
 {
 	stack_protections((unsigned long) &init_thread_info);
 	setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
 	mem_total_pages(physmem_size, iomem_size, highmem);
+	read_initrd();
 
 	paging_init();
 	strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index faf3687..a300aa1 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -315,10 +315,10 @@ do {									\
 #define __get_user_asm_u64(x, ptr, retval, errret)			\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
-	asm volatile(ASM_STAC "\n"					\
+	asm volatile("\n"					\
 		     "1:	movl %2,%%eax\n"			\
 		     "2:	movl %3,%%edx\n"			\
-		     "3: " ASM_CLAC "\n"				\
+		     "3:\n"				\
 		     ".section .fixup,\"ax\"\n"				\
 		     "4:	mov %4,%0\n"				\
 		     "	xorl %%eax,%%eax\n"				\
@@ -327,7 +327,7 @@ do {									\
 		     ".previous\n"					\
 		     _ASM_EXTABLE(1b, 4b)				\
 		     _ASM_EXTABLE(2b, 4b)				\
-		     : "=r" (retval), "=A"(x)				\
+		     : "=r" (retval), "=&A"(x)				\
 		     : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1),	\
 		       "i" (errret), "0" (retval));			\
 })
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 2f2b8c7..6f0ab305 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -101,6 +101,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 43c1528..81bba3c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1735,6 +1735,7 @@ static u64 __get_kvmclock_ns(struct kvm *kvm)
 {
 	struct kvm_arch *ka = &kvm->arch;
 	struct pvclock_vcpu_time_info hv_clock;
+	u64 ret;
 
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	if (!ka->use_master_clock) {
@@ -1746,10 +1747,17 @@ static u64 __get_kvmclock_ns(struct kvm *kvm)
 	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
 	spin_unlock(&ka->pvclock_gtod_sync_lock);
 
+	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
+	get_cpu();
+
 	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
 			   &hv_clock.tsc_shift,
 			   &hv_clock.tsc_to_system_mul);
-	return __pvclock_read_cycles(&hv_clock, rdtsc());
+	ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+
+	put_cpu();
+
+	return ret;
 }
 
 u64 get_kvmclock_ns(struct kvm *kvm)
@@ -3231,11 +3239,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 	}
 }
 
+#define XSAVE_MXCSR_OFFSET 24
+
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		/*
@@ -3243,11 +3254,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~kvm_supported_xcr0())
+		if (xstate_bv & ~kvm_supported_xcr0() ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
-		if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+		if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
 			guest_xsave->region, sizeof(struct fxregs_state));
@@ -4750,16 +4763,20 @@ emul_write:
 
 static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 {
-	/* TODO: String I/O for in kernel device */
-	int r;
+	int r = 0, i;
 
-	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
-				    vcpu->arch.pio.size, pd);
-	else
-		r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
-				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
+	for (i = 0; i < vcpu->arch.pio.count; i++) {
+		if (vcpu->arch.pio.in)
+			r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+					    vcpu->arch.pio.size, pd);
+		else
+			r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+					     vcpu->arch.pio.port, vcpu->arch.pio.size,
+					     pd);
+		if (r)
+			break;
+		pd += vcpu->arch.pio.size;
+	}
 	return r;
 }
 
@@ -4797,6 +4814,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	if (vcpu->arch.pio.count)
 		goto data_avail;
 
+	memset(vcpu->arch.pio_data, 0, size * count);
+
 	ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
 	if (ret) {
 data_avail: