Merge branch 'linus' into x86/urgent, to pick up dependent changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

19 files changed, 515 insertions, 346 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8dcbf6890714..9fc92e4539d8 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -197,7 +197,7 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 }
 
 static int __init
-acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
+acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end)
 {
 	struct acpi_madt_local_x2apic *processor = NULL;
 #ifdef CONFIG_X86_X2APIC
@@ -210,7 +210,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 	if (BAD_MADT_ENTRY(processor, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 #ifdef CONFIG_X86_X2APIC
 	apic_id = processor->local_apic_id;
@@ -242,7 +242,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 }
 
 static int __init
-acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_local_apic *processor = NULL;
 
@@ -251,7 +251,7 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
 	if (BAD_MADT_ENTRY(processor, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	/* Ignore invalid ID */
 	if (processor->id == 0xff)
@@ -272,7 +272,7 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
 }
 
 static int __init
-acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
+acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end)
 {
 	struct acpi_madt_local_sapic *processor = NULL;
 
@@ -281,7 +281,7 @@ acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
 	if (BAD_MADT_ENTRY(processor, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */
 			    processor->processor_id, /* ACPI ID */
@@ -291,7 +291,7 @@ acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
 }
 
 static int __init
-acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
+acpi_parse_lapic_addr_ovr(union acpi_subtable_headers * header,
 			  const unsigned long end)
 {
 	struct acpi_madt_local_apic_override *lapic_addr_ovr = NULL;
@@ -301,7 +301,7 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
 	if (BAD_MADT_ENTRY(lapic_addr_ovr, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	acpi_lapic_addr = lapic_addr_ovr->address;
 
@@ -309,7 +309,7 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
 }
 
 static int __init
-acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
+acpi_parse_x2apic_nmi(union acpi_subtable_headers *header,
 		      const unsigned long end)
 {
 	struct acpi_madt_local_x2apic_nmi *x2apic_nmi = NULL;
@@ -319,7 +319,7 @@ acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
 	if (BAD_MADT_ENTRY(x2apic_nmi, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	if (x2apic_nmi->lint != 1)
 		printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
@@ -328,7 +328,7 @@ acpi_parse_x2apic_nmi(struct acpi_subtable_header *header,
 }
 
 static int __init
-acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_local_apic_nmi *lapic_nmi = NULL;
 
@@ -337,7 +337,7 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e
 	if (BAD_MADT_ENTRY(lapic_nmi, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	if (lapic_nmi->lint != 1)
 		printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n");
@@ -449,7 +449,7 @@ static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
 }
 
 static int __init
-acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_ioapic(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_io_apic *ioapic = NULL;
 	struct ioapic_domain_cfg cfg = {
@@ -462,7 +462,7 @@ acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 	if (BAD_MADT_ENTRY(ioapic, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	/* Statically assign IRQ numbers for IOAPICs hosting legacy IRQs */
 	if (ioapic->global_irq_base < nr_legacy_irqs())
@@ -508,7 +508,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 }
 
 static int __init
-acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
+acpi_parse_int_src_ovr(union acpi_subtable_headers * header,
 		       const unsigned long end)
 {
 	struct acpi_madt_interrupt_override *intsrc = NULL;
@@ -518,7 +518,7 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
 	if (BAD_MADT_ENTRY(intsrc, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	if (intsrc->source_irq == acpi_gbl_FADT.sci_interrupt) {
 		acpi_sci_ioapic_setup(intsrc->source_irq,
@@ -550,7 +550,7 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
 }
 
 static int __init
-acpi_parse_nmi_src(struct acpi_subtable_header * header, const unsigned long end)
+acpi_parse_nmi_src(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_nmi_source *nmi_src = NULL;
 
@@ -559,7 +559,7 @@ acpi_parse_nmi_src(struct acpi_subtable_header * header, const unsigned long end
 	if (BAD_MADT_ENTRY(nmi_src, end))
 		return -EINVAL;
 
-	acpi_table_print_madt_entry(header);
+	acpi_table_print_madt_entry(&header->common);
 
 	/* TBD: Support nimsrc entries? */
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 2c0aa34af69c..bf7f13ea3c64 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -233,9 +233,6 @@ static dma_addr_t gart_map_page(struct device *dev, struct page *page,
 	unsigned long bus;
 	phys_addr_t paddr = page_to_phys(page) + offset;
 
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
 	if (!need_iommu(dev, paddr, size))
 		return paddr;
 
@@ -392,9 +389,6 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	if (nents == 0)
 		return 0;
 
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
 	out		= 0;
 	start		= 0;
 	start_sg	= sg;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 29630393f300..03b4cc0ec3a7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -37,6 +37,7 @@
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
+static void __init mds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -63,6 +64,13 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+/* Control MDS CPU buffer clear before returning to user space */
+DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+EXPORT_SYMBOL_GPL(mds_user_clear);
+/* Control MDS CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+EXPORT_SYMBOL_GPL(mds_idle_clear);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -101,6 +109,10 @@ void __init check_bugs(void)
 
 	l1tf_select_mitigation();
 
+	mds_select_mitigation();
+
+	arch_smt_update();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -207,6 +219,61 @@ static void x86_amd_ssb_disable(void)
 }
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"MDS: " fmt
+
+/* Default mitigation for MDS-affected CPUs */
+static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL;
+static bool mds_nosmt __ro_after_init = false;
+
+static const char * const mds_strings[] = {
+	[MDS_MITIGATION_OFF]	= "Vulnerable",
+	[MDS_MITIGATION_FULL]	= "Mitigation: Clear CPU buffers",
+	[MDS_MITIGATION_VMWERV]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
+};
+
+static void __init mds_select_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
+		mds_mitigation = MDS_MITIGATION_OFF;
+		return;
+	}
+
+	if (mds_mitigation == MDS_MITIGATION_FULL) {
+		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+			mds_mitigation = MDS_MITIGATION_VMWERV;
+
+		static_branch_enable(&mds_user_clear);
+
+		if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
+		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
+			cpu_smt_disable(false);
+	}
+
+	pr_info("%s\n", mds_strings[mds_mitigation]);
+}
+
+static int __init mds_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		mds_mitigation = MDS_MITIGATION_OFF;
+	else if (!strcmp(str, "full"))
+		mds_mitigation = MDS_MITIGATION_FULL;
+	else if (!strcmp(str, "full,nosmt")) {
+		mds_mitigation = MDS_MITIGATION_FULL;
+		mds_nosmt = true;
+	}
+
+	return 0;
+}
+early_param("mds", mds_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
@@ -575,9 +642,6 @@ specv2_set_mode:
 
 	/* Set up IBPB and STIBP depending on the general spectre V2 command */
 	spectre_v2_user_select_mitigation(cmd);
-
-	/* Enable STIBP if appropriate */
-	arch_smt_update();
 }
 
 static void update_stibp_msr(void * __unused)
@@ -611,6 +675,31 @@ static void update_indir_branch_cond(void)
 		static_branch_disable(&switch_to_cond_stibp);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+/* Update the static key controlling the MDS CPU buffer clear in idle */
+static void update_mds_branch_idle(void)
+{
+	/*
+	 * Enable the idle clearing if SMT is active on CPUs which are
+	 * affected only by MSBDS and not any other MDS variant.
+	 *
+	 * The other variants cannot be mitigated when SMT is enabled, so
+	 * clearing the buffers on idle just to prevent the Store Buffer
+	 * repartitioning leak would be a window dressing exercise.
+	 */
+	if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
+		return;
+
+	if (sched_smt_active())
+		static_branch_enable(&mds_idle_clear);
+	else
+		static_branch_disable(&mds_idle_clear);
+}
+
+#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+
 void arch_smt_update(void)
 {
 	/* Enhanced IBRS implies STIBP. No update required. */
@@ -632,6 +721,17 @@ void arch_smt_update(void)
 		break;
 	}
 
+	switch (mds_mitigation) {
+	case MDS_MITIGATION_FULL:
+	case MDS_MITIGATION_VMWERV:
+		if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
+			pr_warn_once(MDS_MSG_SMT);
+		update_mds_branch_idle();
+		break;
+	case MDS_MITIGATION_OFF:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -1043,7 +1143,7 @@ static void __init l1tf_select_mitigation(void)
 		pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
 				half_pa);
 		pr_info("However, doing so will make a part of your RAM unusable.\n");
-		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
+		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html might help you decide.\n");
 		return;
 	}
 
@@ -1076,6 +1176,7 @@ static int __init l1tf_cmdline(char *str)
 early_param("l1tf", l1tf_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt) fmt
 
 #ifdef CONFIG_SYSFS
 
@@ -1114,6 +1215,23 @@ static ssize_t l1tf_show_state(char *buf)
 }
 #endif
 
+static ssize_t mds_show_state(char *buf)
+{
+	if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+		return sprintf(buf, "%s; SMT Host state unknown\n",
+			       mds_strings[mds_mitigation]);
+	}
+
+	if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) {
+		return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+			       (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" :
+			        sched_smt_active() ? "mitigated" : "disabled"));
+	}
+
+	return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+		       sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1180,6 +1298,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
 			return l1tf_show_state(buf);
 		break;
+
+	case X86_BUG_MDS:
+		return mds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1211,4 +1333,9 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
 }
+
+ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 37640544e12f..d7f55ad2dfb1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -372,6 +372,8 @@ static bool pku_disabled;
 
 static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 {
+	struct pkru_state *pk;
+
 	/* check the boot processor, plus compile options for PKU: */
 	if (!cpu_feature_enabled(X86_FEATURE_PKU))
 		return;
@@ -382,6 +384,9 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 		return;
 
 	cr4_set_bits(X86_CR4_PKE);
+	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
+	if (pk)
+		pk->pkru = init_pkru_value;
 	/*
 	 * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
 	 * cpuid bit to be set.  We need to ensure that we
@@ -935,61 +940,77 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
-static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_CENTAUR,	5 },
-	{ X86_VENDOR_INTEL,	5 },
-	{ X86_VENDOR_NSC,	5 },
-	{ X86_VENDOR_ANY,	4 },
-	{}
-};
+#define NO_SPECULATION	BIT(0)
+#define NO_MELTDOWN	BIT(1)
+#define NO_SSB		BIT(2)
+#define NO_L1TF		BIT(3)
+#define NO_MDS		BIT(4)
+#define MSBDS_ONLY	BIT(5)
 
-static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
-	{ X86_VENDOR_AMD },
-	{ X86_VENDOR_HYGON },
-	{}
-};
+#define VULNWL(_vendor, _family, _model, _whitelist)	\
+	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
 
-/* Only list CPUs which speculate but are non susceptible to SSB */
-static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
-	{ X86_VENDOR_AMD,	0x12,					},
-	{ X86_VENDOR_AMD,	0x11,					},
-	{ X86_VENDOR_AMD,	0x10,					},
-	{ X86_VENDOR_AMD,	0xf,					},
-	{}
-};
+#define VULNWL_INTEL(model, whitelist)		\
+	VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
+
+#define VULNWL_AMD(family, whitelist)		\
+	VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
+
+#define VULNWL_HYGON(family, whitelist)		\
+	VULNWL(HYGON, family, X86_MODEL_ANY, whitelist)
+
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+	VULNWL(ANY,	4, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(CENTAUR,	5, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(INTEL,	5, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
+
+	/* Intel Family 6 */
+	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION),
 
-static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
-	/* in addition to cpu_no_speculation */
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_PLUS	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT_X,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+
+	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
+
+	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY),
+
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF),
+
+	/* AMD Family 0xf - 0x12 */
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+
+	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
 	{}
 };
 
+static bool __init cpu_matches(unsigned long which)
+{
+	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
+
+	return m && !!(m->driver_data & which);
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
-	if (x86_match_cpu(cpu_no_speculation))
+	if (cpu_matches(NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
@@ -998,15 +1019,20 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
 
-	if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
-	   !(ia32_cap & ARCH_CAP_SSB_NO) &&
+	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
-	if (x86_match_cpu(cpu_no_meltdown))
+	if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+		setup_force_cpu_bug(X86_BUG_MDS);
+		if (cpu_matches(MSBDS_ONLY))
+			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
+	}
+
+	if (cpu_matches(NO_MELTDOWN))
 		return;
 
 	/* Rogue Data Cache Load? No! */
@@ -1015,7 +1041,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	if (x86_match_cpu(cpu_no_l1tf))
+	if (cpu_matches(NO_L1TF))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_L1TF);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 8a4a7823451a..c321f4f513f9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -428,7 +428,7 @@ static int do_microcode_update(const void __user *buf, size_t size)
 
 static int microcode_open(struct inode *inode, struct file *file)
 {
-	return capable(CAP_SYS_RAWIO) ? nonseekable_open(inode, file) : -EPERM;
+	return capable(CAP_SYS_RAWIO) ? stream_open(inode, file) : -EPERM;
 }
 
 static ssize_t microcode_write(struct file *file, const char __user *buf,
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 50d5848bf22e..6c4f01540833 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -525,7 +525,8 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_I945G_IDS(&gen3_early_ops),
 	INTEL_I945GM_IDS(&gen3_early_ops),
 	INTEL_VLV_IDS(&gen6_early_ops),
-	INTEL_PINEVIEW_IDS(&gen3_early_ops),
+	INTEL_PINEVIEW_G_IDS(&gen3_early_ops),
+	INTEL_PINEVIEW_M_IDS(&gen3_early_ops),
 	INTEL_I965G_IDS(&gen3_early_ops),
 	INTEL_G33_IDS(&gen3_early_ops),
 	INTEL_I965GM_IDS(&gen3_early_ops),
@@ -547,6 +548,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_GLK_IDS(&gen9_early_ops),
 	INTEL_CNL_IDS(&gen9_early_ops),
 	INTEL_ICL_11_IDS(&gen11_early_ops),
+	INTEL_EHL_IDS(&gen11_early_ops),
 };
 
 struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2e5003fef51a..ce243f76bdb7 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -101,24 +101,21 @@ static void __kernel_fpu_begin(void)
 
 	kernel_fpu_disable();
 
-	if (fpu->initialized) {
-		/*
-		 * Ignore return value -- we don't care if reg state
-		 * is clobbered.
-		 */
-		copy_fpregs_to_fpstate(fpu);
-	} else {
-		__cpu_invalidate_fpregs_state();
+	if (current->mm) {
+		if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+			set_thread_flag(TIF_NEED_FPU_LOAD);
+			/*
+			 * Ignore return value -- we don't care if reg state
+			 * is clobbered.
+			 */
+			copy_fpregs_to_fpstate(fpu);
+		}
 	}
+	__cpu_invalidate_fpregs_state();
 }
 
 static void __kernel_fpu_end(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
-
-	if (fpu->initialized)
-		copy_kernel_to_fpregs(&fpu->state);
-
 	kernel_fpu_enable();
 }
 
@@ -145,15 +142,17 @@ void fpu__save(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	preempt_disable();
+	fpregs_lock();
 	trace_x86_fpu_before_save(fpu);
-	if (fpu->initialized) {
+
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
 		if (!copy_fpregs_to_fpstate(fpu)) {
 			copy_kernel_to_fpregs(&fpu->state);
 		}
 	}
+
 	trace_x86_fpu_after_save(fpu);
-	preempt_enable();
+	fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(fpu__save);
 
@@ -186,11 +185,14 @@ void fpstate_init(union fpregs_state *state)
 }
 EXPORT_SYMBOL_GPL(fpstate_init);
 
-int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+int fpu__copy(struct task_struct *dst, struct task_struct *src)
 {
+	struct fpu *dst_fpu = &dst->thread.fpu;
+	struct fpu *src_fpu = &src->thread.fpu;
+
 	dst_fpu->last_cpu = -1;
 
-	if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU))
+	if (!static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -202,16 +204,23 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
 
 	/*
-	 * Save current FPU registers directly into the child
-	 * FPU context, without any memory-to-memory copying.
+	 * If the FPU registers are not current just memcpy() the state.
+	 * Otherwise save current FPU registers directly into the child's FPU
+	 * context, without any memory-to-memory copying.
 	 *
 	 * ( The function 'fails' in the FNSAVE case, which destroys
-	 *   register contents so we have to copy them back. )
+	 *   register contents so we have to load them back. )
 	 */
-	if (!copy_fpregs_to_fpstate(dst_fpu)) {
-		memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size);
-		copy_kernel_to_fpregs(&src_fpu->state);
-	}
+	fpregs_lock();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size);
+
+	else if (!copy_fpregs_to_fpstate(dst_fpu))
+		copy_kernel_to_fpregs(&dst_fpu->state);
+
+	fpregs_unlock();
+
+	set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
 
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
@@ -223,20 +232,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
  * Activate the current task's in-memory FPU context,
  * if it has not been used before:
  */
-void fpu__initialize(struct fpu *fpu)
+static void fpu__initialize(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	if (!fpu->initialized) {
-		fpstate_init(&fpu->state);
-		trace_x86_fpu_init_state(fpu);
-
-		trace_x86_fpu_activate_state(fpu);
-		/* Safe to do for the current task: */
-		fpu->initialized = 1;
-	}
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+	fpstate_init(&fpu->state);
+	trace_x86_fpu_init_state(fpu);
 }
-EXPORT_SYMBOL_GPL(fpu__initialize);
 
 /*
  * This function must be called before we read a task's fpstate.
@@ -248,32 +251,20 @@ EXPORT_SYMBOL_GPL(fpu__initialize);
  *
  * - or it's called for stopped tasks (ptrace), in which case the
  *   registers were already saved by the context-switch code when
- *   the task scheduled out - we only have to initialize the registers
- *   if they've never been initialized.
+ *   the task scheduled out.
  *
  * If the task has used the FPU before then save it.
  */
 void fpu__prepare_read(struct fpu *fpu)
 {
-	if (fpu == &current->thread.fpu) {
+	if (fpu == &current->thread.fpu)
 		fpu__save(fpu);
-	} else {
-		if (!fpu->initialized) {
-			fpstate_init(&fpu->state);
-			trace_x86_fpu_init_state(fpu);
-
-			trace_x86_fpu_activate_state(fpu);
-			/* Safe to do for current and for stopped child tasks: */
-			fpu->initialized = 1;
-		}
-	}
 }
 
 /*
  * This function must be called before we write a task's fpstate.
  *
- * If the task has used the FPU before then invalidate any cached FPU registers.
- * If the task has not used the FPU before then initialize its fpstate.
+ * Invalidate any cached FPU registers.
  *
  * After this function call, after registers in the fpstate are
  * modified and the child task has woken up, the child task will
@@ -290,44 +281,11 @@ void fpu__prepare_write(struct fpu *fpu)
 	 */
 	WARN_ON_FPU(fpu == &current->thread.fpu);
 
-	if (fpu->initialized) {
-		/* Invalidate any cached state: */
-		__fpu_invalidate_fpregs_state(fpu);
-	} else {
-		fpstate_init(&fpu->state);
-		trace_x86_fpu_init_state(fpu);
-
-		trace_x86_fpu_activate_state(fpu);
-		/* Safe to do for stopped child tasks: */
-		fpu->initialized = 1;
-	}
+	/* Invalidate any cached state: */
+	__fpu_invalidate_fpregs_state(fpu);
 }
 
 /*
- * 'fpu__restore()' is called to copy FPU registers from
- * the FPU fpstate to the live hw registers and to activate
- * access to the hardware registers, so that FPU instructions
- * can be used afterwards.
- *
- * Must be called with kernel preemption disabled (for example
- * with local interrupts disabled, as it is in the case of
- * do_device_not_available()).
- */
-void fpu__restore(struct fpu *fpu)
-{
-	fpu__initialize(fpu);
-
-	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
-	kernel_fpu_disable();
-	trace_x86_fpu_before_restore(fpu);
-	fpregs_activate(fpu);
-	copy_kernel_to_fpregs(&fpu->state);
-	trace_x86_fpu_after_restore(fpu);
-	kernel_fpu_enable();
-}
-EXPORT_SYMBOL_GPL(fpu__restore);
-
-/*
  * Drops current FPU state: deactivates the fpregs and
  * the fpstate. NOTE: it still leaves previous contents
  * in the fpregs in the eager-FPU case.
@@ -341,17 +299,13 @@ void fpu__drop(struct fpu *fpu)
 	preempt_disable();
 
 	if (fpu == &current->thread.fpu) {
-		if (fpu->initialized) {
-			/* Ignore delayed exceptions from user space */
-			asm volatile("1: fwait\n"
-				     "2:\n"
-				     _ASM_EXTABLE(1b, 2b));
-			fpregs_deactivate(fpu);
-		}
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		fpregs_deactivate(fpu);
 	}
 
-	fpu->initialized = 0;
-
 	trace_x86_fpu_dropped(fpu);
 
 	preempt_enable();
@@ -363,6 +317,8 @@ void fpu__drop(struct fpu *fpu)
  */
 static inline void copy_init_fpstate_to_fpregs(void)
 {
+	fpregs_lock();
+
 	if (use_xsave())
 		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
 	else if (static_cpu_has(X86_FEATURE_FXSR))
@@ -372,6 +328,9 @@ static inline void copy_init_fpstate_to_fpregs(void)
 
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
 		copy_init_pkru_to_fpregs();
+
+	fpregs_mark_activate();
+	fpregs_unlock();
 }
 
 /*
@@ -389,16 +348,52 @@ void fpu__clear(struct fpu *fpu)
 	/*
 	 * Make sure fpstate is cleared and initialized.
 	 */
-	if (static_cpu_has(X86_FEATURE_FPU)) {
-		preempt_disable();
-		fpu__initialize(fpu);
-		user_fpu_begin();
+	fpu__initialize(fpu);
+	if (static_cpu_has(X86_FEATURE_FPU))
 		copy_init_fpstate_to_fpregs();
-		preempt_enable();
-	}
 }
 
 /*
+ * Load FPU context before returning to userspace.
+ */
+void switch_fpu_return(void)
+{
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return;
+
+	__fpregs_load_activate();
+}
+EXPORT_SYMBOL_GPL(switch_fpu_return);
+
+#ifdef CONFIG_X86_DEBUG_FPU
+/*
+ * If current FPU state according to its tracking (loaded FPU context on this
+ * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is
+ * loaded on return to userland.
+ */
+void fpregs_assert_state_consistent(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		return;
+
+	WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id()));
+}
+EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent);
+#endif
+
+void fpregs_mark_activate(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	fpregs_activate(fpu);
+	fpu->last_cpu = smp_processor_id();
+	clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+EXPORT_SYMBOL_GPL(fpregs_mark_activate);
+
+/*
  * x87 math exception handling:
  */
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 6abd83572b01..20d8fa7124c7 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -239,8 +239,6 @@ static void __init fpu__init_system_ctx_switch(void)
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
-
-	WARN_ON_FPU(current->thread.fpu.initialized);
 }
 
 /*
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index bc02f5144b95..d652b939ccfb 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -15,16 +15,12 @@
  */
 int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
-	struct fpu *target_fpu = &target->thread.fpu;
-
-	return target_fpu->initialized ? regset->n : 0;
+	return regset->n;
 }
 
 int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
-	struct fpu *target_fpu = &target->thread.fpu;
-
-	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized)
+	if (boot_cpu_has(X86_FEATURE_FXSR))
 		return regset->n;
 	else
 		return 0;
@@ -269,11 +265,10 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 		memcpy(&to[i], &from[i], sizeof(to[0]));
 }
 
-void convert_to_fxsr(struct task_struct *tsk,
+void convert_to_fxsr(struct fxregs_state *fxsave,
 		     const struct user_i387_ia32_struct *env)
 
 {
-	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
 	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
 	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
 	int i;
@@ -350,7 +345,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
 	if (!ret)
-		convert_to_fxsr(target, &env);
+		convert_to_fxsr(&target->thread.fpu.state.fxsave, &env);
 
 	/*
 	 * update the header bit in the xsave header, indicating the
@@ -371,16 +366,9 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
 {
 	struct task_struct *tsk = current;
-	struct fpu *fpu = &tsk->thread.fpu;
-	int fpvalid;
-
-	fpvalid = fpu->initialized;
-	if (fpvalid)
-		fpvalid = !fpregs_get(tsk, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      ufpu, NULL);
 
-	return fpvalid;
+	return !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct),
+			   ufpu, NULL);
 }
 EXPORT_SYMBOL(dump_fpu);
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index f6a1d299627c..5a8d118bc423 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -92,13 +92,13 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 		return err;
 
 	err |= __put_user(FP_XSTATE_MAGIC2,
-			  (__u32 *)(buf + fpu_user_xstate_size));
+			  (__u32 __user *)(buf + fpu_user_xstate_size));
 
 	/*
 	 * Read the xfeatures which we copied (directly from the cpu or
 	 * from the state in task struct) to the user buffers.
 	 */
-	err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+	err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
 
 	/*
 	 * For legacy compatible, we always set FP/SSE bits in the bit
@@ -113,7 +113,7 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 	 */
 	xfeatures |= XFEATURE_MASK_FPSSE;
 
-	err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+	err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
 
 	return err;
 }
@@ -144,9 +144,10 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
  *	buf != buf_fx for 32-bit frames with fxstate.
  *
- * If the fpu, extended register state is live, save the state directly
- * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
- * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ * Try to save it directly to the user frame with disabled page fault handler.
+ * If this fails then do the slow path where the FPU state is first saved to
+ * task's fpu->state and then copy it to the user frame pointed to by the
+ * aligned pointer 'buf_fx'.
  *
  * If this is a 32-bit frame with fxstate, put a fsave header before
  * the aligned state at 'buf_fx'.
@@ -156,10 +157,9 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  */
 int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 {
-	struct fpu *fpu = &current->thread.fpu;
-	struct xregs_state *xsave = &fpu->state.xsave;
 	struct task_struct *tsk = current;
 	int ia32_fxstate = (buf != buf_fx);
+	int ret;
 
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -172,28 +172,34 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 			sizeof(struct user_i387_ia32_struct), NULL,
 			(struct _fpstate_32 __user *) buf) ? -1 : 1;
 
-	if (fpu->initialized || using_compacted_format()) {
-		/* Save the live register state to the user directly. */
-		if (copy_fpregs_to_sigframe(buf_fx))
-			return -1;
-		/* Update the thread's fxstate to save the fsave header. */
-		if (ia32_fxstate)
-			copy_fxregs_to_kernel(fpu);
-	} else {
-		/*
-		 * It is a *bug* if kernel uses compacted-format for xsave
-		 * area and we copy it out directly to a signal frame. It
-		 * should have been handled above by saving the registers
-		 * directly.
-		 */
-		if (boot_cpu_has(X86_FEATURE_XSAVES)) {
-			WARN_ONCE(1, "x86/fpu: saving compacted-format xsave area to a signal frame!\n");
-			return -1;
-		}
-
-		fpstate_sanitize_xstate(fpu);
-		if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
-			return -1;
+retry:
+	/*
+	 * Load the FPU registers if they are not valid for the current task.
+	 * With a valid FPU state we can attempt to save the state directly to
+	 * userland's stack frame which will likely succeed. If it does not,
+	 * resolve the fault in the user memory and try again.
+	 */
+	fpregs_lock();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		__fpregs_load_activate();
+
+	pagefault_disable();
+	ret = copy_fpregs_to_sigframe(buf_fx);
+	pagefault_enable();
+	fpregs_unlock();
+
+	if (ret) {
+		int aligned_size;
+		int nr_pages;
+
+		aligned_size = offset_in_page(buf_fx) + fpu_user_xstate_size;
+		nr_pages = DIV_ROUND_UP(aligned_size, PAGE_SIZE);
+
+		ret = get_user_pages_unlocked((unsigned long)buf_fx, nr_pages,
+					      NULL, FOLL_WRITE);
+		if (ret == nr_pages)
+			goto retry;
+		return -EFAULT;
 	}
 
 	/* Save the fsave header for the 32-bit frames. */
@@ -207,11 +213,11 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 }
 
 static inline void
-sanitize_restored_xstate(struct task_struct *tsk,
+sanitize_restored_xstate(union fpregs_state *state,
 			 struct user_i387_ia32_struct *ia32_env,
 			 u64 xfeatures, int fx_only)
 {
-	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+	struct xregs_state *xsave = &state->xsave;
 	struct xstate_header *header = &xsave->header;
 
 	if (use_xsave()) {
@@ -238,17 +244,18 @@ sanitize_restored_xstate(struct task_struct *tsk,
 		 */
 		xsave->i387.mxcsr &= mxcsr_feature_mask;
 
-		convert_to_fxsr(tsk, ia32_env);
+		if (ia32_env)
+			convert_to_fxsr(&state->fxsave, ia32_env);
 	}
 }
 
 /*
  * Restore the extended state if present. Otherwise, restore the FP/SSE state.
  */
-static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
 {
 	if (use_xsave()) {
-		if ((unsigned long)buf % 64 || fx_only) {
+		if (fx_only) {
 			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 			return copy_user_to_fxregs(buf);
@@ -266,12 +273,15 @@ static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_
 
 static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 {
+	struct user_i387_ia32_struct *envp = NULL;
+	int state_size = fpu_kernel_xstate_size;
 	int ia32_fxstate = (buf != buf_fx);
 	struct task_struct *tsk = current;
 	struct fpu *fpu = &tsk->thread.fpu;
-	int state_size = fpu_kernel_xstate_size;
+	struct user_i387_ia32_struct env;
 	u64 xfeatures = 0;
 	int fx_only = 0;
+	int ret = 0;
 
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -284,8 +294,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	if (!access_ok(buf, size))
 		return -EACCES;
 
-	fpu__initialize(fpu);
-
 	if (!static_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_set(current, NULL,
 				       0, sizeof(struct user_i387_ia32_struct),
@@ -308,61 +316,101 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		}
 	}
 
+	/*
+	 * The current state of the FPU registers does not matter. By setting
+	 * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate
+	 * is not modified on context switch and that the xstate is considered
+	 * to be loaded again on return to userland (overriding last_cpu avoids
+	 * the optimisation).
+	 */
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+	__fpu_invalidate_fpregs_state(fpu);
+
+	if ((unsigned long)buf_fx % 64)
+		fx_only = 1;
+	/*
+	 * For 32-bit frames with fxstate, copy the fxstate so it can be
+	 * reconstructed later.
+	 */
 	if (ia32_fxstate) {
+		ret = __copy_from_user(&env, buf, sizeof(env));
+		if (ret)
+			goto err_out;
+		envp = &env;
+	} else {
 		/*
-		 * For 32-bit frames with fxstate, copy the user state to the
-		 * thread's fpu state, reconstruct fxstate from the fsave
-		 * header. Validate and sanitize the copied state.
+		 * Attempt to restore the FPU registers directly from user
+		 * memory. For that to succeed, the user access cannot cause
+		 * page faults. If it does, fall back to the slow path below,
+		 * going through the kernel buffer with the enabled pagefault
+		 * handler.
 		 */
-		struct user_i387_ia32_struct env;
-		int err = 0;
+		fpregs_lock();
+		pagefault_disable();
+		ret = copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only);
+		pagefault_enable();
+		if (!ret) {
+			fpregs_mark_activate();
+			fpregs_unlock();
+			return 0;
+		}
+		fpregs_unlock();
+	}
 
-		/*
-		 * Drop the current fpu which clears fpu->initialized. This ensures
-		 * that any context-switch during the copy of the new state,
-		 * avoids the intermediate state from getting restored/saved.
-		 * Thus avoiding the new restored state from getting corrupted.
-		 * We will be ready to restore/save the state only after
-		 * fpu->initialized is again set.
-		 */
-		fpu__drop(fpu);
+
+	if (use_xsave() && !fx_only) {
+		u64 init_bv = xfeatures_mask & ~xfeatures;
 
 		if (using_compacted_format()) {
-			err = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
+			ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
 		} else {
-			err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
+			ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
 
-			if (!err && state_size > offsetof(struct xregs_state, header))
-				err = validate_xstate_header(&fpu->state.xsave.header);
+			if (!ret && state_size > offsetof(struct xregs_state, header))
+				ret = validate_xstate_header(&fpu->state.xsave.header);
 		}
+		if (ret)
+			goto err_out;
 
-		if (err || __copy_from_user(&env, buf, sizeof(env))) {
-			fpstate_init(&fpu->state);
-			trace_x86_fpu_init_state(fpu);
-			err = -1;
-		} else {
-			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
+
+		fpregs_lock();
+		if (unlikely(init_bv))
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+		ret = copy_kernel_to_xregs_err(&fpu->state.xsave, xfeatures);
+
+	} else if (use_fxsr()) {
+		ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
+		if (ret) {
+			ret = -EFAULT;
+			goto err_out;
 		}
 
-		local_bh_disable();
-		fpu->initialized = 1;
-		fpu__restore(fpu);
-		local_bh_enable();
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
 
-		return err;
-	} else {
-		/*
-		 * For 64-bit frames and 32-bit fsave frames, restore the user
-		 * state to the registers directly (with exceptions handled).
-		 */
-		user_fpu_begin();
-		if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
-			fpu__clear(fpu);
-			return -1;
+		fpregs_lock();
+		if (use_xsave()) {
+			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 		}
+
+		ret = copy_kernel_to_fxregs_err(&fpu->state.fxsave);
+	} else {
+		ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size);
+		if (ret)
+			goto err_out;
+
+		fpregs_lock();
+		ret = copy_kernel_to_fregs_err(&fpu->state.fsave);
 	}
+	if (!ret)
+		fpregs_mark_activate();
+	fpregs_unlock();
 
-	return 0;
+err_out:
+	if (ret)
+		fpu__clear(fpu);
+	return ret;
 }
 
 static inline int xstate_sigframe_size(void)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d7432c2b1051..9c459fd1d38e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -805,20 +805,18 @@ void fpu__resume_cpu(void)
 }
 
 /*
- * Given an xstate feature mask, calculate where in the xsave
+ * Given an xstate feature nr, calculate where in the xsave
  * buffer the state is.  Callers should ensure that the buffer
  * is valid.
  */
-static void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
+static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 {
-	int feature_nr = fls64(xstate_feature_mask) - 1;
-
-	if (!xfeature_enabled(feature_nr)) {
+	if (!xfeature_enabled(xfeature_nr)) {
 		WARN_ON_FPU(1);
 		return NULL;
 	}
 
-	return (void *)xsave + xstate_comp_offsets[feature_nr];
+	return (void *)xsave + xstate_comp_offsets[xfeature_nr];
 }
 /*
  * Given the xsave area and a state inside, this function returns the
@@ -832,13 +830,13 @@ static void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask
  *
  * Inputs:
  *	xstate: the thread's storage area for all FPU data
- *	xstate_feature: state which is defined in xsave.h (e.g.
- *	XFEATURE_MASK_FP, XFEATURE_MASK_SSE, etc...)
+ *	xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP,
+ *	XFEATURE_SSE, etc...)
  * Output:
  *	address of the state in the xsave area, or NULL if the
  *	field is not present in the xsave buffer.
  */
-void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
+void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 {
 	/*
 	 * Do we even *have* xsave state?
@@ -851,11 +849,11 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 	 * have not enabled.  Remember that pcntxt_mask is
 	 * what we write to the XCR0 register.
 	 */
-	WARN_ONCE(!(xfeatures_mask & xstate_feature),
+	WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)),
 		  "get of unsupported state");
 	/*
 	 * This assumes the last 'xsave*' instruction to
-	 * have requested that 'xstate_feature' be saved.
+	 * have requested that 'xfeature_nr' be saved.
 	 * If it did not, we might be seeing and old value
 	 * of the field in the buffer.
 	 *
@@ -864,10 +862,10 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 	 * or because the "init optimization" caused it
 	 * to not be saved.
 	 */
-	if (!(xsave->header.xfeatures & xstate_feature))
+	if (!(xsave->header.xfeatures & BIT_ULL(xfeature_nr)))
 		return NULL;
 
-	return __raw_xsave_addr(xsave, xstate_feature);
+	return __raw_xsave_addr(xsave, xfeature_nr);
 }
 EXPORT_SYMBOL_GPL(get_xsave_addr);
 
@@ -882,25 +880,23 @@ EXPORT_SYMBOL_GPL(get_xsave_addr);
  * Note that this only works on the current task.
  *
  * Inputs:
- *	@xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP,
- *	XFEATURE_MASK_SSE, etc...)
+ *	@xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP,
+ *	XFEATURE_SSE, etc...)
  * Output:
  *	address of the state in the xsave area or NULL if the state
  *	is not present or is in its 'init state'.
  */
-const void *get_xsave_field_ptr(int xsave_state)
+const void *get_xsave_field_ptr(int xfeature_nr)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (!fpu->initialized)
-		return NULL;
 	/*
 	 * fpu__save() takes the CPU's xstate registers
 	 * and saves them off to the 'fpu memory buffer.
 	 */
 	fpu__save(fpu);
 
-	return get_xsave_addr(&fpu->state.xsave, xsave_state);
+	return get_xsave_addr(&fpu->state.xsave, xfeature_nr);
 }
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
@@ -1016,7 +1012,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
-			void *src = __raw_xsave_addr(xsave, 1 << i);
+			void *src = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1102,7 +1098,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
-			void *src = __raw_xsave_addr(xsave, 1 << i);
+			void *src = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1159,7 +1155,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
 		u64 mask = ((u64)1 << i);
 
 		if (hdr.xfeatures & mask) {
-			void *dst = __raw_xsave_addr(xsave, 1 << i);
+			void *dst = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
@@ -1213,7 +1209,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 		u64 mask = ((u64)1 << i);
 
 		if (hdr.xfeatures & mask) {
-			void *dst = __raw_xsave_addr(xsave, 1 << i);
+			void *dst = __raw_xsave_addr(xsave, i);
 
 			offset = xstate_offsets[i];
 			size = xstate_sizes[i];
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
index e47cd9390ab4..85de790583f9 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/arch/x86/kernel/ima_arch.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2018 IBM Corporation
  */
 #include <linux/efi.h>
+#include <linux/module.h>
 #include <linux/ima.h>
 
 extern struct boot_params boot_params;
@@ -64,12 +65,19 @@ static const char * const sb_arch_rules[] = {
 	"appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig",
 #endif /* CONFIG_KEXEC_VERIFY_SIG */
 	"measure func=KEXEC_KERNEL_CHECK",
+#if !IS_ENABLED(CONFIG_MODULE_SIG)
+	"appraise func=MODULE_CHECK appraise_type=imasig",
+#endif
+	"measure func=MODULE_CHECK",
 	NULL
 };
 
 const char * const *arch_get_ima_policy(void)
 {
-	if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot())
+	if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot()) {
+		if (IS_ENABLED(CONFIG_MODULE_SIG))
+			set_module_sig_enforced();
 		return sb_arch_rules;
+	}
 	return NULL;
 }
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 3755d0310026..05b09896cfaf 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -35,6 +35,7 @@
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/cache.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -551,6 +552,9 @@ nmi_restart:
 		write_cr2(this_cpu_read(nmi_cr2));
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
+
+	if (user_mode(regs))
+		mds_user_clear_cpu_buffers();
 }
 NOKPROBE_SYMBOL(do_nmi);
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index d460998ae828..dcd272dbd0a9 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -51,14 +51,6 @@ int iommu_pass_through __read_mostly;
 
 extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
-/* Dummy device used for NULL arguments (normally ISA). */
-struct device x86_dma_fallback_dev = {
-	.init_name = "fallback device",
-	.coherent_dma_mask = ISA_DMA_BIT_MASK,
-	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
-};
-EXPORT_SYMBOL(x86_dma_fallback_dev);
-
 void __init pci_iommu_alloc(void)
 {
 	struct iommu_table_entry *p;
@@ -77,18 +69,6 @@ void __init pci_iommu_alloc(void)
 	}
 }
 
-bool arch_dma_alloc_attrs(struct device **dev)
-{
-	if (!*dev)
-		*dev = &x86_dma_fallback_dev;
-
-	if (!is_device_dma_capable(*dev))
-		return false;
-	return true;
-
-}
-EXPORT_SYMBOL(arch_dma_alloc_attrs);
-
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
  * parameter documentation.
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d1d312d012a6..75fea0d48c0e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -101,7 +101,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	dst->thread.vm86 = NULL;
 #endif
 
-	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
+	return fpu__copy(dst, src);
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 70933193878c..2399e910d109 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -241,7 +241,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_fpu, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -274,9 +275,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
-	 * the GDT and LDT are properly updated, and must be
-	 * done before fpu__restore(), so the TS bit is up
-	 * to date.
+	 * the GDT and LDT are properly updated.
 	 */
 	arch_end_context_switch(next_p);
 
@@ -297,10 +296,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
-	switch_fpu_finish(next_fpu, cpu);
-
 	this_cpu_write(current_task, next_p);
 
+	switch_fpu_finish(next_fpu);
+
 	/* Load the Intel cache allocation PQR MSR. */
 	resctrl_sched_in();
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 844a28b29967..f8e1af380cdf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -521,7 +521,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
 		     this_cpu_read(irq_count) != -1);
 
-	switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_fpu, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -539,9 +540,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.  This
 	 * must be done after loading TLS entries in the GDT but before
-	 * loading segments that might reference them, and and it must
-	 * be done before fpu__restore(), so the TS bit is up to
-	 * date.
+	 * loading segments that might reference them.
 	 */
 	arch_end_context_switch(next_p);
 
@@ -569,14 +568,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	x86_fsgsbase_load(prev, next);
 
-	switch_fpu_finish(next_fpu, cpu);
-
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
 	this_cpu_write(current_task, next_p);
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
+	switch_fpu_finish(next_fpu);
+
 	/* Reload sp0. */
 	update_task_stack(next_p);
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index dff90fb6a9af..364813cea647 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -205,7 +205,7 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		put_user_ex(regs->ss, &sc->ss);
 #endif /* CONFIG_X86_32 */
 
-		put_user_ex(fpstate, &sc->fpstate);
+		put_user_ex(fpstate, (unsigned long __user *)&sc->fpstate);
 
 		/* non-iBCS2 extensions.. */
 		put_user_ex(mask, &sc->oldmask);
@@ -245,7 +245,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	unsigned long sp = regs->sp;
 	unsigned long buf_fx = 0;
 	int onsigstack = on_sig_stack(sp);
-	struct fpu *fpu = &current->thread.fpu;
+	int ret;
 
 	/* redzone */
 	if (IS_ENABLED(CONFIG_X86_64))
@@ -264,11 +264,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		sp = (unsigned long) ka->sa.sa_restorer;
 	}
 
-	if (fpu->initialized) {
-		sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
-					  &buf_fx, &math_size);
-		*fpstate = (void __user *)sp;
-	}
+	sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
+				  &buf_fx, &math_size);
+	*fpstate = (void __user *)sp;
 
 	sp = align_sigframe(sp - frame_size);
 
@@ -280,8 +278,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 
 	/* save i387 and extended state */
-	if (fpu->initialized &&
-	    copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
+	ret = copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size);
+	if (ret < 0)
 		return (void __user *)-1L;
 
 	return (void __user *)sp;
@@ -574,7 +572,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 			restorer = NULL;
 			err |= -EFAULT;
 		}
-		put_user_ex(restorer, &frame->pretcode);
+		put_user_ex(restorer, (unsigned long __user *)&frame->pretcode);
 	} put_user_catch(err);
 
 	err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
@@ -765,8 +763,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		if (fpu->initialized)
-			fpu__clear(fpu);
+		fpu__clear(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d26f9e9c3d83..7de466eb960b 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -58,6 +58,7 @@
 #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>
@@ -367,6 +368,13 @@ 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
@@ -456,7 +464,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	 * which is all zeros which indicates MPX was not
 	 * responsible for the exception.
 	 */
-	bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
 	if (!bndcsr)
 		goto exit_trap;