Merge tag 'x86-cpu-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu updates from Ingo Molar:

 - prepare for Intel's new SERIALIZE instruction

 - enable split-lock debugging on more CPUs

 - add more Intel CPU models

 - optimize stack canary initialization a bit

 - simplify the Spectre logic a bit

* tag 'x86-cpu-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Refactor sync_core() for readability
  x86/cpu: Relocate sync_core() to sync_core.h
  x86/cpufeatures: Add enumeration for SERIALIZE instruction
  x86/split_lock: Enable the split lock feature on Sapphire Rapids and Alder Lake CPUs
  x86/cpu: Add Lakefield, Alder Lake and Rocket Lake models to the to Intel CPU family
  x86/stackprotector: Pre-initialize canary for secondary CPUs
  x86/speculation: Merge one test in spectre_v2_user_select_mitigation()

arch/x86/include/asm/cpufeatures.h

@@ -367,6 +367,7 @@
 #define X86_FEATURE_SRBDS_CTRL		(18*32+ 9) /* "" SRBDS mitigation MSR available */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
+#define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */

arch/x86/include/asm/intel-family.h

@@ -89,8 +89,15 @@
 #define INTEL_FAM6_COMETLAKE		0xA5
 #define INTEL_FAM6_COMETLAKE_L		0xA6
 
+#define INTEL_FAM6_ROCKETLAKE		0xA7
+
 #define INTEL_FAM6_SAPPHIRERAPIDS_X	0x8F
 
+/* Hybrid Core/Atom Processors */
+
+#define	INTEL_FAM6_LAKEFIELD		0x8A
+#define INTEL_FAM6_ALDERLAKE		0x97
+
 /* "Small Core" Processors (Atom) */
 
 #define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */

arch/x86/include/asm/processor.h

@@ -678,70 +678,6 @@ static inline unsigned int cpuid_edx(unsigned int op)
 	return edx;
 }
 
-/*
- * This function forces the icache and prefetched instruction stream to
- * catch up with reality in two very specific cases:
- *
- *  a) Text was modified using one virtual address and is about to be executed
- *     from the same physical page at a different virtual address.
- *
- *  b) Text was modified on a different CPU, may subsequently be
- *     executed on this CPU, and you want to make sure the new version
- *     gets executed.  This generally means you're calling this in a IPI.
- *
- * If you're calling this for a different reason, you're probably doing
- * it wrong.
- */
-static inline void sync_core(void)
-{
-	/*
-	 * There are quite a few ways to do this.  IRET-to-self is nice
-	 * because it works on every CPU, at any CPL (so it's compatible
-	 * with paravirtualization), and it never exits to a hypervisor.
-	 * The only down sides are that it's a bit slow (it seems to be
-	 * a bit more than 2x slower than the fastest options) and that
-	 * it unmasks NMIs.  The "push %cs" is needed because, in
-	 * paravirtual environments, __KERNEL_CS may not be a valid CS
-	 * value when we do IRET directly.
-	 *
-	 * In case NMI unmasking or performance ever becomes a problem,
-	 * the next best option appears to be MOV-to-CR2 and an
-	 * unconditional jump.  That sequence also works on all CPUs,
-	 * but it will fault at CPL3 (i.e. Xen PV).
-	 *
-	 * CPUID is the conventional way, but it's nasty: it doesn't
-	 * exist on some 486-like CPUs, and it usually exits to a
-	 * hypervisor.
-	 *
-	 * Like all of Linux's memory ordering operations, this is a
-	 * compiler barrier as well.
-	 */
-#ifdef CONFIG_X86_32
-	asm volatile (
-		"pushfl\n\t"
-		"pushl %%cs\n\t"
-		"pushl $1f\n\t"
-		"iret\n\t"
-		"1:"
-		: ASM_CALL_CONSTRAINT : : "memory");
-#else
-	unsigned int tmp;
-
-	asm volatile (
-		"mov %%ss, %0\n\t"
-		"pushq %q0\n\t"
-		"pushq %%rsp\n\t"
-		"addq $8, (%%rsp)\n\t"
-		"pushfq\n\t"
-		"mov %%cs, %0\n\t"
-		"pushq %q0\n\t"
-		"pushq $1f\n\t"
-		"iretq\n\t"
-		"1:"
-		: "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
-#endif
-}
-
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
 extern void amd_e400_c1e_apic_setup(void);
 

arch/x86/include/asm/special_insns.h

@@ -234,7 +234,6 @@ static inline void clwb(volatile void *__p)
 
 #define nop() asm volatile ("nop")
 
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */

arch/x86/include/asm/stackprotector.h

@@ -90,6 +90,15 @@ static __always_inline void boot_init_stack_canary(void)
 #endif
 }
 
+static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
+{
+#ifdef CONFIG_X86_64
+	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
+#else
+	per_cpu(stack_canary.canary, cpu) = idle->stack_canary;
+#endif
+}
+
 static inline void setup_stack_canary_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -119,6 +128,9 @@ static inline void load_stack_canary_segment(void)
 static inline void setup_stack_canary_segment(int cpu)
 { }
 
+static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
+{ }
+
 static inline void load_stack_canary_segment(void)
 {
 #ifdef CONFIG_X86_32

arch/x86/include/asm/sync_core.h

@@ -6,6 +6,78 @@
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 
+#ifdef CONFIG_X86_32
+static inline void iret_to_self(void)
+{
+	asm volatile (
+		"pushfl\n\t"
+		"pushl %%cs\n\t"
+		"pushl $1f\n\t"
+		"iret\n\t"
+		"1:"
+		: ASM_CALL_CONSTRAINT : : "memory");
+}
+#else
+static inline void iret_to_self(void)
+{
+	unsigned int tmp;
+
+	asm volatile (
+		"mov %%ss, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq %%rsp\n\t"
+		"addq $8, (%%rsp)\n\t"
+		"pushfq\n\t"
+		"mov %%cs, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq $1f\n\t"
+		"iretq\n\t"
+		"1:"
+		: "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
+}
+#endif /* CONFIG_X86_32 */
+
+/*
+ * This function forces the icache and prefetched instruction stream to
+ * catch up with reality in two very specific cases:
+ *
+ *  a) Text was modified using one virtual address and is about to be executed
+ *     from the same physical page at a different virtual address.
+ *
+ *  b) Text was modified on a different CPU, may subsequently be
+ *     executed on this CPU, and you want to make sure the new version
+ *     gets executed.  This generally means you're calling this in a IPI.
+ *
+ * If you're calling this for a different reason, you're probably doing
+ * it wrong.
+ */
+static inline void sync_core(void)
+{
+	/*
+	 * There are quite a few ways to do this.  IRET-to-self is nice
+	 * because it works on every CPU, at any CPL (so it's compatible
+	 * with paravirtualization), and it never exits to a hypervisor.
+	 * The only down sides are that it's a bit slow (it seems to be
+	 * a bit more than 2x slower than the fastest options) and that
+	 * it unmasks NMIs.  The "push %cs" is needed because, in
+	 * paravirtual environments, __KERNEL_CS may not be a valid CS
+	 * value when we do IRET directly.
+	 *
+	 * In case NMI unmasking or performance ever becomes a problem,
+	 * the next best option appears to be MOV-to-CR2 and an
+	 * unconditional jump.  That sequence also works on all CPUs,
+	 * but it will fault at CPL3 (i.e. Xen PV).
+	 *
+	 * CPUID is the conventional way, but it's nasty: it doesn't
+	 * exist on some 486-like CPUs, and it usually exits to a
+	 * hypervisor.
+	 *
+	 * Like all of Linux's memory ordering operations, this is a
+	 * compiler barrier as well.
+	 */
+	iret_to_self();
+}
+
 /*
  * Ensure that a core serializing instruction is issued before returning
  * to user-mode. x86 implements return to user-space through sysexit,

arch/x86/kernel/alternative.c

@@ -16,6 +16,7 @@
 #include <linux/kprobes.h>
 #include <linux/mmu_context.h>
 #include <linux/bsearch.h>
+#include <linux/sync_core.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>

arch/x86/kernel/cpu/bugs.c

@@ -763,10 +763,12 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	}
 
 	/*
-	 * If enhanced IBRS is enabled or SMT impossible, STIBP is not
+	 * If no STIBP, enhanced IBRS is enabled or SMT impossible, STIBP is not
 	 * required.
 	 */
-	if (!smt_possible || spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+	if (!boot_cpu_has(X86_FEATURE_STIBP) ||
+	    !smt_possible ||
+	    spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
 		return;
 
 	/*
@@ -778,12 +780,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
 		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
 
-	/*
-	 * If STIBP is not available, clear the STIBP mode.
-	 */
-	if (!boot_cpu_has(X86_FEATURE_STIBP))
-		mode = SPECTRE_V2_USER_NONE;
-
 	spectre_v2_user_stibp = mode;
 
 set_mode:
@@ -1270,7 +1266,6 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		 * Indirect branch speculation is always disabled in strict
 		 * mode. It can neither be enabled if it was force-disabled
 		 * by a  previous prctl call.
-
 		 */
 		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
 		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||

arch/x86/kernel/cpu/intel.c

@@ -1156,6 +1156,8 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	1),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		1),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		1),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		1),
 	{}
 };
 

arch/x86/kernel/cpu/mce/core.c

@@ -42,6 +42,7 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/sync_core.h>
 #include <linux/task_work.h>
 #include <linux/hardirq.h>
 

arch/x86/kernel/smpboot.c

@@ -51,7 +51,6 @@
 #include <linux/err.h>
 #include <linux/nmi.h>
 #include <linux/tboot.h>
-#include <linux/stackprotector.h>
 #include <linux/gfp.h>
 #include <linux/cpuidle.h>
 #include <linux/numa.h>
@@ -81,6 +80,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/spec-ctrl.h>
 #include <asm/hw_irq.h>
+#include <asm/stackprotector.h>
 
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -260,21 +260,10 @@ static void notrace start_secondary(void *unused)
 	/* enable local interrupts */
 	local_irq_enable();
 
-	/* to prevent fake stack check failure in clock setup */
-	boot_init_stack_canary();
-
 	x86_cpuinit.setup_percpu_clockev();
 
 	wmb();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
-
-	/*
-	 * Prevent tail call to cpu_startup_entry() because the stack protector
-	 * guard has been changed a couple of function calls up, in
-	 * boot_init_stack_canary() and must not be checked before tail calling
-	 * another function.
-	 */
-	prevent_tail_call_optimization();
 }
 
 /**
@@ -1012,6 +1001,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	alternatives_enable_smp();
 
 	per_cpu(current_task, cpu) = idle;
+	cpu_init_stack_canary(cpu, idle);
 
 	/* Initialize the interrupt stack(s) */
 	ret = irq_init_percpu_irqstack(cpu);

arch/x86/xen/smp_pv.c

@@ -92,9 +92,7 @@ static void cpu_bringup(void)
 asmlinkage __visible void cpu_bringup_and_idle(void)
 {
 	cpu_bringup();
-	boot_init_stack_canary();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
-	prevent_tail_call_optimization();
 }
 
 void xen_smp_intr_free_pv(unsigned int cpu)

drivers/misc/sgi-gru/grufault.c

@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <linux/security.h>
+#include <linux/sync_core.h>
 #include <linux/prefetch.h>
 #include "gru.h"
 #include "grutables.h"

drivers/misc/sgi-gru/gruhandles.c

@@ -16,6 +16,7 @@
 #define GRU_OPERATION_TIMEOUT	(((cycles_t) local_cpu_data->itc_freq)*10)
 #define CLKS2NSEC(c)		((c) *1000000000 / local_cpu_data->itc_freq)
 #else
+#include <linux/sync_core.h>
 #include <asm/tsc.h>
 #define GRU_OPERATION_TIMEOUT	((cycles_t) tsc_khz*10*1000)
 #define CLKS2NSEC(c)		((c) * 1000000 / tsc_khz)

drivers/misc/sgi-gru/grukservices.c

@@ -16,6 +16,7 @@
 #include <linux/miscdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/interrupt.h>
+#include <linux/sync_core.h>
 #include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/export.h>