1 files changed, 222 insertions, 91 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 348cf4821240..ffb181f959d2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1,4 +1,7 @@
-#include <linux/bootmem.h>
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
+#include <linux/memblock.h>
 #include <linux/linkage.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
@@ -66,6 +69,13 @@ cpumask_var_t cpu_callin_mask;
 /* representing cpus for which sibling maps can be computed */
 cpumask_var_t cpu_sibling_setup_mask;
 
+/* Number of siblings per CPU package */
+int smp_num_siblings = 1;
+EXPORT_SYMBOL(smp_num_siblings);
+
+/* Last level cache ID of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+
 /* correctly size the local cpu masks */
 void __init setup_cpu_local_masks(void)
 {
@@ -487,7 +497,7 @@ void load_percpu_segment(int cpu)
 	loadsegment(fs, __KERNEL_PERCPU);
 #else
 	__loadsegment_simple(gs, 0);
-	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
 #endif
 	load_stack_canary_segment();
 }
@@ -577,6 +587,19 @@ static void get_model_name(struct cpuinfo_x86 *c)
 	*(s + 1) = '\0';
 }
 
+void detect_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	c->x86_max_cores = 1;
+	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
+		return;
+
+	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
+	if (eax & 0x1f)
+		c->x86_max_cores = (eax >> 26) + 1;
+}
+
 void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 {
 	unsigned int n, dummy, ebx, ecx, edx, l2size;
@@ -638,33 +661,36 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
 }
 
-void detect_ht(struct cpuinfo_x86 *c)
+int detect_ht_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
-	int index_msb, core_bits;
-	static bool printed;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
-		return;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		goto out;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
-		return;
+		return -1;
 
 	cpuid(1, &eax, &ebx, &ecx, &edx);
 
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
-
-	if (smp_num_siblings == 1) {
+	if (smp_num_siblings == 1)
 		pr_info_once("CPU0: Hyper-Threading is disabled\n");
-		goto out;
-	}
+#endif
+	return 0;
+}
 
-	if (smp_num_siblings <= 1)
-		goto out;
+void detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	int index_msb, core_bits;
+
+	if (detect_ht_early(c) < 0)
+		return;
 
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
@@ -677,15 +703,6 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
 				       ((1 << core_bits) - 1);
-
-out:
-	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-			c->phys_proc_id);
-		pr_info("CPU: Processor Core ID: %d\n",
-			c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 }
 
@@ -757,17 +774,38 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	 * and they also have a different bit for STIBP support. Also,
 	 * a hypervisor might have set the individual AMD bits even on
 	 * Intel CPUs, for finer-grained selection of what's available.
-	 *
-	 * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
-	 * features, which are visible in /proc/cpuinfo and used by the
-	 * kernel. So set those accordingly from the Intel bits.
 	 */
 	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
 		set_cpu_cap(c, X86_FEATURE_IBRS);
 		set_cpu_cap(c, X86_FEATURE_IBPB);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
 	}
+
 	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
 		set_cpu_cap(c, X86_FEATURE_STIBP);
+
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
+	    cpu_has(c, X86_FEATURE_VIRT_SSBD))
+		set_cpu_cap(c, X86_FEATURE_SSBD);
+
+	if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
+		set_cpu_cap(c, X86_FEATURE_IBRS);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+	}
+
+	if (cpu_has(c, X86_FEATURE_AMD_IBPB))
+		set_cpu_cap(c, X86_FEATURE_IBPB);
+
+	if (cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+		set_cpu_cap(c, X86_FEATURE_STIBP);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+	}
+
+	if (cpu_has(c, X86_FEATURE_AMD_SSBD)) {
+		set_cpu_cap(c, X86_FEATURE_SSBD);
+		set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+		clear_cpu_cap(c, X86_FEATURE_VIRT_SSBD);
+	}
 }
 
 void get_cpu_cap(struct cpuinfo_x86 *c)
@@ -850,15 +888,8 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	if (c->extended_cpuid_level >= 0x80000008) {
 		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
-
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
 		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
 	}
-#ifdef CONFIG_X86_32
-	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
-		c->x86_phys_bits = 36;
-#endif
 
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
@@ -874,6 +905,23 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	apply_forced_caps(c);
 }
 
+void get_cpu_address_sizes(struct cpuinfo_x86 *c)
+{
+	u32 eax, ebx, ecx, edx;
+
+	if (c->extended_cpuid_level >= 0x80000008) {
+		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
+	}
+#ifdef CONFIG_X86_32
+	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
+		c->x86_phys_bits = 36;
+#endif
+	c->x86_cache_bits = c->x86_phys_bits;
+}
+
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_32
@@ -901,11 +949,11 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 }
 
 static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CEDARVIEW,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CLOVERVIEW,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_LINCROFT,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PENWELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PINEVIEW,	X86_FEATURE_ANY },
+	{ 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 },
@@ -915,24 +963,93 @@ static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
 
 static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 	{ X86_VENDOR_AMD },
+	{ X86_VENDOR_HYGON },
+	{}
+};
+
+/* 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,					},
+	{}
+};
+
+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		},
 	{}
 };
 
-static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
-	if (x86_match_cpu(cpu_no_meltdown))
-		return false;
+	if (x86_match_cpu(cpu_no_speculation))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
 	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) &&
+	   !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))
+		return;
+
 	/* Rogue Data Cache Load? No! */
 	if (ia32_cap & ARCH_CAP_RDCL_NO)
-		return false;
+		return;
+
+	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	return true;
+	if (x86_match_cpu(cpu_no_l1tf))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_L1TF);
+}
+
+/*
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
+ * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
+ */
+static void detect_nopl(void)
+{
+#ifdef CONFIG_X86_32
+	setup_clear_cpu_cap(X86_FEATURE_NOPL);
+#else
+	setup_force_cpu_cap(X86_FEATURE_NOPL);
+#endif
 }
 
 /*
@@ -957,14 +1074,18 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 #endif
 	c->x86_cache_alignment = c->x86_clflush_size;
 
-	memset(&c->x86_capability, 0, sizeof c->x86_capability);
+	memset(&c->x86_capability, 0, sizeof(c->x86_capability));
 	c->extended_cpuid_level = 0;
 
+	if (!have_cpuid_p())
+		identify_cpu_without_cpuid(c);
+
 	/* cyrix could have cpuid enabled via c_identify()*/
 	if (have_cpuid_p()) {
 		cpu_detect(c);
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
+		get_cpu_address_sizes(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
 
 		if (this_cpu->c_early_init)
@@ -976,18 +1097,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		if (this_cpu->c_bsp_init)
 			this_cpu->c_bsp_init(c);
 	} else {
-		identify_cpu_without_cpuid(c);
 		setup_clear_cpu_cap(X86_FEATURE_CPUID);
 	}
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
-	if (!x86_match_cpu(cpu_no_speculation)) {
-		if (cpu_vulnerable_to_meltdown(c))
-			setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
-		setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
-		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
-	}
+	cpu_set_bug_bits(c);
 
 	fpu__init_system(c);
 
@@ -998,6 +1113,23 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	setup_clear_cpu_cap(X86_FEATURE_PCID);
 #endif
+
+	/*
+	 * Later in the boot process pgtable_l5_enabled() relies on
+	 * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not
+	 * enabled by this point we need to clear the feature bit to avoid
+	 * false-positives at the later stage.
+	 *
+	 * pgtable_l5_enabled() can be false here for several reasons:
+	 *  - 5-level paging is disabled compile-time;
+	 *  - it's 32-bit kernel;
+	 *  - machine doesn't support 5-level paging;
+	 *  - user specified 'no5lvl' in kernel command line.
+	 */
+	if (!pgtable_l5_enabled())
+		setup_clear_cpu_cap(X86_FEATURE_LA57);
+
+	detect_nopl();
 }
 
 void __init early_cpu_init(void)
@@ -1033,24 +1165,6 @@ void __init early_cpu_init(void)
 	early_identify_cpu(&boot_cpu_data);
 }
 
-/*
- * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
- * unfortunately, that's not true in practice because of early VIA
- * chips and (more importantly) broken virtualizers that are not easy
- * to detect. In the latter case it doesn't even *fail* reliably, so
- * probing for it doesn't even work. Disable it completely on 32-bit
- * unless we can find a reliable way to detect all the broken cases.
- * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
- */
-static void detect_nopl(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_X86_32
-	clear_cpu_cap(c, X86_FEATURE_NOPL);
-#else
-	set_cpu_cap(c, X86_FEATURE_NOPL);
-#endif
-}
-
 static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_64
@@ -1097,6 +1211,8 @@ static void generic_identify(struct cpuinfo_x86 *c)
 
 	get_cpu_cap(c);
 
+	get_cpu_address_sizes(c);
+
 	if (c->cpuid_level >= 0x00000001) {
 		c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
 #ifdef CONFIG_X86_32
@@ -1111,8 +1227,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 
 	get_model_name(c); /* Default name */
 
-	detect_nopl(c);
-
 	detect_null_seg_behavior(c);
 
 	/*
@@ -1129,10 +1243,10 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	 * ESPFIX issue, we can change this.
 	 */
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_PARAVIRT
+# ifdef CONFIG_PARAVIRT_XXL
 	do {
 		extern void native_iret(void);
-		if (pv_cpu_ops.iret == native_iret)
+		if (pv_ops.cpu.iret == native_iret)
 			set_cpu_bug(c, X86_BUG_ESPFIX);
 	} while (0);
 # else
@@ -1203,7 +1317,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_virt_bits = 32;
 #endif
 	c->x86_cache_alignment = c->x86_clflush_size;
-	memset(&c->x86_capability, 0, sizeof c->x86_capability);
+	memset(&c->x86_capability, 0, sizeof(c->x86_capability));
 
 	generic_identify(c);
 
@@ -1347,6 +1461,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 #endif
 	mtrr_ap_init();
 	validate_apic_and_package_id(c);
+	x86_spec_ctrl_setup_ap();
 }
 
 static __init int setup_noclflush(char *arg)
@@ -1398,6 +1513,7 @@ __setup("clearcpuid=", setup_clearcpuid);
 #ifdef CONFIG_X86_64
 DEFINE_PER_CPU_FIRST(union irq_stack_union,
 		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
+EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
 
 /*
  * The following percpu variables are hot.  Align current_task to
@@ -1418,19 +1534,8 @@ EXPORT_PER_CPU_SYMBOL(__preempt_count);
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
-	extern char _entry_trampoline[];
-	extern char entry_SYSCALL_64_trampoline[];
-
-	int cpu = smp_processor_id();
-	unsigned long SYSCALL64_entry_trampoline =
-		(unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
-		(entry_SYSCALL_64_trampoline - _entry_trampoline);
-
 	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
-	if (static_cpu_has(X86_FEATURE_PTI))
-		wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
-	else
-		wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
 	wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
@@ -1441,7 +1546,8 @@ void syscall_init(void)
 	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+		    (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1507,7 +1613,7 @@ DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
 	(unsigned long)&init_thread_union + THREAD_SIZE;
 EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
 
-#ifdef CONFIG_CC_STACKPROTECTOR
+#ifdef CONFIG_STACKPROTECTOR
 DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
 
@@ -1556,6 +1662,29 @@ static void wait_for_master_cpu(int cpu)
 #endif
 }
 
+#ifdef CONFIG_X86_64
+static void setup_getcpu(int cpu)
+{
+	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
+	struct desc_struct d = { };
+
+	if (static_cpu_has(X86_FEATURE_RDTSCP))
+		write_rdtscp_aux(cpudata);
+
+	/* Store CPU and node number in limit. */
+	d.limit0 = cpudata;
+	d.limit1 = cpudata >> 16;
+
+	d.type = 5;		/* RO data, expand down, accessed */
+	d.dpl = 3;		/* Visible to user code */
+	d.s = 1;		/* Not a system segment */
+	d.p = 1;		/* Present */
+	d.d = 1;		/* 32-bit */
+
+	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S);
+}
+#endif
+
 /*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
@@ -1593,6 +1722,7 @@ void cpu_init(void)
 	    early_cpu_to_node(cpu) != NUMA_NO_NODE)
 		set_numa_node(early_cpu_to_node(cpu));
 #endif
+	setup_getcpu(cpu);
 
 	me = current;
 
@@ -1709,11 +1839,12 @@ void cpu_init(void)
 	enter_lazy_tlb(&init_mm, curr);
 
 	/*
-	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
-	 * task never enters user mode.
+	 * Initialize the TSS.  sp0 points to the entry trampoline stack
+	 * regardless of what task is running.
 	 */
 	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
+	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);