Merge branch 'x86/cpu' into perf/core, to pick up dependent patches

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

23 files changed, 791 insertions, 92 deletions

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 6adce15268bd..8e29c991ba3e 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -480,3 +480,16 @@ config CPU_SUP_UMC_32
 	  CPU might render the kernel unbootable.
 
 	  If unsure, say N.
+
+config CPU_SUP_ZHAOXIN
+	default y
+	bool "Support Zhaoxin processors" if PROCESSOR_SELECT
+	help
+	  This enables detection, tunings and quirks for Zhaoxin processors
+
+	  You need this enabled if you want your kernel to run on a
+	  Zhaoxin CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on a Zhaoxin
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index efb0d1b1f15f..d3fbe2dc03ea 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -6,6 +6,7 @@
 #include <asm/percpu.h>
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
+#include <asm/inst.h>
 
 /*
 
@@ -337,6 +338,12 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 .endm
 
+.macro SAVE_AND_SET_GSBASE scratch_reg:req save_reg:req
+	rdgsbase \save_reg
+	GET_PERCPU_BASE \scratch_reg
+	wrgsbase \scratch_reg
+.endm
+
 #endif /* CONFIG_X86_64 */
 
 .macro STACKLEAK_ERASE
@@ -345,6 +352,39 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 .endm
 
+#ifdef CONFIG_SMP
+
+/*
+ * CPU/node NR is loaded from the limit (size) field of a special segment
+ * descriptor entry in GDT.
+ */
+.macro LOAD_CPU_AND_NODE_SEG_LIMIT reg:req
+	movq	$__CPUNODE_SEG, \reg
+	lsl	\reg, \reg
+.endm
+
+/*
+ * Fetch the per-CPU GSBASE value for this processor and put it in @reg.
+ * We normally use %gs for accessing per-CPU data, but we are setting up
+ * %gs here and obviously can not use %gs itself to access per-CPU data.
+ */
+.macro GET_PERCPU_BASE reg:req
+	ALTERNATIVE \
+		"LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \
+		"RDPID	\reg", \
+		X86_FEATURE_RDPID
+	andq	$VDSO_CPUNODE_MASK, \reg
+	movq	__per_cpu_offset(, \reg, 8), \reg
+.endm
+
+#else
+
+.macro GET_PERCPU_BASE reg:req
+	movq	pcpu_unit_offsets(%rip), \reg
+.endm
+
+#endif /* CONFIG_SMP */
+
 /*
  * This does 'call enter_from_user_mode' unless we can avoid it based on
  * kernel config or using the static jump infrastructure.
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 11aa3b2afa4d..7f9f5119d6b1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -38,6 +38,7 @@
 #include <asm/export.h>
 #include <asm/frame.h>
 #include <asm/nospec-branch.h>
+#include <asm/fsgsbase.h>
 #include <linux/err.h>
 
 #include "calling.h"
@@ -947,7 +948,6 @@ ENTRY(\sym)
 	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
 	.endif
 
-	/* these procedures expect "no swapgs" flag in ebx */
 	.if \paranoid
 	jmp	paranoid_exit
 	.else
@@ -1164,24 +1164,21 @@ idtentry machine_check		do_mce			has_error_code=0	paranoid=1
 #endif
 
 /*
- * Save all registers in pt_regs, and switch gs if needed.
- * Use slow, but surefire "are we in kernel?" check.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ * Save all registers in pt_regs. Return GSBASE related information
+ * in EBX depending on the availability of the FSGSBASE instructions:
+ *
+ * FSGSBASE	R/EBX
+ *     N        0 -> SWAPGS on exit
+ *              1 -> no SWAPGS on exit
+ *
+ *     Y        GSBASE value at entry, must be restored in paranoid_exit
  */
 ENTRY(paranoid_entry)
 	UNWIND_HINT_FUNC
 	cld
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
-	movl	$1, %ebx
-	movl	$MSR_GS_BASE, %ecx
-	rdmsr
-	testl	%edx, %edx
-	js	1f				/* negative -> in kernel */
-	SWAPGS
-	xorl	%ebx, %ebx
 
-1:
 	/*
 	 * Always stash CR3 in %r14.  This value will be restored,
 	 * verbatim, at exit.  Needed if paranoid_entry interrupted
@@ -1191,9 +1188,49 @@ ENTRY(paranoid_entry)
 	 * This is also why CS (stashed in the "iret frame" by the
 	 * hardware at entry) can not be used: this may be a return
 	 * to kernel code, but with a user CR3 value.
+	 *
+	 * Switching CR3 does not depend on kernel GSBASE so it can
+	 * be done before switching to the kernel GSBASE. This is
+	 * required for FSGSBASE because the kernel GSBASE has to
+	 * be retrieved from a kernel internal table.
 	 */
 	SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
 
+        /*
+	 * Handling GSBASE depends on the availability of FSGSBASE.
+	 *
+	 * Without FSGSBASE the kernel enforces that negative GSBASE
+	 * values indicate kernel GSBASE. With FSGSBASE no assumptions
+	 * can be made about the GSBASE value when entering from user
+	 * space.
+	*/
+	ALTERNATIVE "jmp .Lparanoid_entry_checkgs", "", X86_FEATURE_FSGSBASE
+
+	/*
+	 * Read the current GSBASE and store it in in %rbx unconditionally,
+	 * retrieve and set the current CPUs kernel GSBASE. The stored value
+	 * has to be restored in paranoid_exit unconditionally.
+	 */
+	SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx
+	ret
+
+.Lparanoid_entry_checkgs:
+	/* EBX = 1 -> kernel GSBASE active, no restore required */
+	movl	$1, %ebx
+	/*
+	 * The kernel-enforced convention is a negative GSBASE indicates
+	 * a kernel value. No SWAPGS needed on entry and exit.
+	 */
+	movl	$MSR_GS_BASE, %ecx
+	rdmsr
+	testl	%edx, %edx
+	jns	.Lparanoid_entry_swapgs
+	ret
+
+.Lparanoid_entry_swapgs:
+	SWAPGS
+	/* EBX = 0 -> SWAPGS required on exit */
+	xorl	%ebx, %ebx
 	ret
 END(paranoid_entry)
 
@@ -1204,28 +1241,47 @@ END(paranoid_entry)
  *
  * We may be returning to very strange contexts (e.g. very early
  * in syscall entry), so checking for preemption here would
- * be complicated.  Fortunately, we there's no good reason
- * to try to handle preemption here.
+ * be complicated.  Fortunately, there's no good reason to try
+ * to handle preemption here.
+ *
+ * R/EBX contains the GSBASE related information depending on the
+ * availability of the FSGSBASE instructions:
+ *
+ * FSGSBASE	R/EBX
+ *     N        0 -> SWAPGS on exit
+ *              1 -> no SWAPGS on exit
  *
- * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
+ *     Y        User space GSBASE, must be restored unconditionally
  */
 ENTRY(paranoid_exit)
 	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF_DEBUG
-	testl	%ebx, %ebx			/* swapgs needed? */
+
+	/* Handle GS depending on FSGSBASE availability */
+	ALTERNATIVE "jmp .Lparanoid_exit_checkgs", "nop",X86_FEATURE_FSGSBASE
+
+	/* With FSGSBASE enabled, unconditionally restore GSBASE */
+	wrgsbase	%rbx
+	jmp	.Lparanoid_exit_no_swapgs;
+
+.Lparanoid_exit_checkgs:
+	/* On non-FSGSBASE systems, conditionally do SWAPGS */
+	testl	%ebx, %ebx
 	jnz	.Lparanoid_exit_no_swapgs
 	TRACE_IRQS_IRETQ
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	SWAPGS_UNSAFE_STACK
 	jmp	.Lparanoid_exit_restore
+
 .Lparanoid_exit_no_swapgs:
 	TRACE_IRQS_IRETQ_DEBUG
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
+
 .Lparanoid_exit_restore:
-	jmp restore_regs_and_return_to_kernel
+	jmp	restore_regs_and_return_to_kernel
 END(paranoid_exit)
 
 /*
@@ -1636,10 +1692,27 @@ end_repeat_nmi:
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
 
-	testl	%ebx, %ebx			/* swapgs needed? */
+	/*
+	 * The above invocation of paranoid_entry stored the GSBASE
+	 * related information in R/EBX depending on the availability
+	 * of FSGSBASE.
+	 *
+	 * If FSGSBASE is enabled, restore the saved GSBASE value
+	 * unconditionally, otherwise take the conditional SWAPGS path.
+	 */
+	ALTERNATIVE "jmp nmi_no_fsgsbase", "", X86_FEATURE_FSGSBASE
+
+	wrgsbase	%rbx
+	jmp	nmi_restore
+
+nmi_no_fsgsbase:
+	/* EBX == 0 -> invoke SWAPGS */
+	testl	%ebx, %ebx
 	jnz	nmi_restore
+
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
+
 nmi_restore:
 	POP_REGS
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1d337c51f7e6..58acda503817 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,8 +22,8 @@ enum cpuid_leafs
 	CPUID_LNX_3,
 	CPUID_7_0_EBX,
 	CPUID_D_1_EAX,
-	CPUID_F_0_EDX,
-	CPUID_F_1_EDX,
+	CPUID_LNX_4,
+	CPUID_7_1_EAX,
 	CPUID_8000_0008_EBX,
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 1017b9c7dfe0..998c2cc08363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -271,13 +271,19 @@
 #define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
 #define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
-#define X86_FEATURE_CQM_LLC		(11*32+ 1) /* LLC QoS if 1 */
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0xf, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CQM_LLC		(11*32+ 0) /* LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC	(11*32+ 1) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL	(11*32+ 2) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL	(11*32+ 3) /* LLC Local MBM monitoring */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC	(12*32+ 0) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL	(12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL	(12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
@@ -324,6 +330,7 @@
 #define X86_FEATURE_UMIP		(16*32+ 2) /* User Mode Instruction Protection */
 #define X86_FEATURE_PKU			(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG		(16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
 #define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
 #define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
 #define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index bca4c743de77..aefd53767a5d 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -19,36 +19,63 @@ extern unsigned long x86_gsbase_read_task(struct task_struct *task);
 extern void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase);
 extern void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase);
 
-/* Helper functions for reading/writing FS/GS base */
+/* Must be protected by X86_FEATURE_FSGSBASE check. */
 
-static inline unsigned long x86_fsbase_read_cpu(void)
+static __always_inline unsigned long rdfsbase(void)
 {
 	unsigned long fsbase;
 
-	rdmsrl(MSR_FS_BASE, fsbase);
+	asm volatile("rdfsbase %0" : "=r" (fsbase) :: "memory");
 
 	return fsbase;
 }
 
-static inline unsigned long x86_gsbase_read_cpu_inactive(void)
+static __always_inline unsigned long rdgsbase(void)
 {
 	unsigned long gsbase;
 
-	rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+	asm volatile("rdgsbase %0" : "=r" (gsbase) :: "memory");
 
 	return gsbase;
 }
 
-static inline void x86_fsbase_write_cpu(unsigned long fsbase)
+static __always_inline void wrfsbase(unsigned long fsbase)
 {
-	wrmsrl(MSR_FS_BASE, fsbase);
+	asm volatile("wrfsbase %0" :: "r" (fsbase) : "memory");
 }
 
-static inline void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
+static __always_inline void wrgsbase(unsigned long gsbase)
 {
-	wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+	asm volatile("wrgsbase %0" :: "r" (gsbase) : "memory");
 }
 
+#include <asm/cpufeature.h>
+
+/* Helper functions for reading/writing FS/GS base */
+
+static inline unsigned long x86_fsbase_read_cpu(void)
+{
+	unsigned long fsbase;
+
+	if (static_cpu_has(X86_FEATURE_FSGSBASE))
+		fsbase = rdfsbase();
+	else
+		rdmsrl(MSR_FS_BASE, fsbase);
+
+	return fsbase;
+}
+
+static inline void x86_fsbase_write_cpu(unsigned long fsbase)
+{
+	if (static_cpu_has(X86_FEATURE_FSGSBASE))
+		wrfsbase(fsbase);
+	else
+		wrmsrl(MSR_FS_BASE, fsbase);
+}
+
+extern unsigned long x86_gsbase_read_cpu_inactive(void);
+extern void x86_gsbase_write_cpu_inactive(unsigned long gsbase);
+
 #endif /* CONFIG_X86_64 */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index f5a796da07f8..d063841a17e3 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -306,6 +306,21 @@
 	.endif
 	MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2
 	.endm
+
+.macro RDPID opd
+	REG_TYPE rdpid_opd_type \opd
+	.if rdpid_opd_type == REG_TYPE_R64
+	R64_NUM rdpid_opd \opd
+	.else
+	R32_NUM rdpid_opd \opd
+	.endif
+	.byte 0xf3
+	.if rdpid_opd > 7
+	PFX_REX rdpid_opd 0
+	.endif
+	.byte 0x0f, 0xc7
+	MODRM 0xc0 rdpid_opd 0x7
+.endm
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index f60ddd655c78..0278aa66ef62 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -77,6 +77,7 @@
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C /* Apollo Lake */
 #define INTEL_FAM6_ATOM_GOLDMONT_X	0x5F /* Denverton */
 #define INTEL_FAM6_ATOM_GOLDMONT_PLUS	0x7A /* Gemini Lake */
+
 #define INTEL_FAM6_ATOM_TREMONT_X	0x86 /* Jacobsville */
 
 /* Xeon Phi */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 979ef971cc78..6b4fc2788078 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -61,6 +61,15 @@
 #define MSR_PLATFORM_INFO_CPUID_FAULT_BIT	31
 #define MSR_PLATFORM_INFO_CPUID_FAULT		BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
 
+#define MSR_IA32_UMWAIT_CONTROL			0xe1
+#define MSR_IA32_UMWAIT_CONTROL_C02_DISABLE	BIT(0)
+#define MSR_IA32_UMWAIT_CONTROL_RESERVED	BIT(1)
+/*
+ * The time field is bit[31:2], but representing a 32bit value with
+ * bit[1:0] zero.
+ */
+#define MSR_IA32_UMWAIT_CONTROL_TIME_MASK	(~0x03U)
+
 #define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6aba36bde57f..3eab6ece52b4 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -146,7 +146,8 @@ enum cpuid_regs_idx {
 #define X86_VENDOR_TRANSMETA	7
 #define X86_VENDOR_NSC		8
 #define X86_VENDOR_HYGON	9
-#define X86_VENDOR_NUM		10
+#define X86_VENDOR_ZHAOXIN	10
+#define X86_VENDOR_NUM		11
 
 #define X86_VENDOR_UNKNOWN	0xff
 
diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h
index 6ebaae90e207..c5ce54e749f6 100644
--- a/arch/x86/include/uapi/asm/hwcap2.h
+++ b/arch/x86/include/uapi/asm/hwcap2.h
@@ -5,4 +5,7 @@
 /* MONITOR/MWAIT enabled in Ring 3 */
 #define HWCAP2_RING3MWAIT		(1 << 0)
 
+/* Kernel allows FSGSBASE instructions available in Ring 3 */
+#define HWCAP2_FSGSBASE			BIT(1)
+
 #endif
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index a5e5484988fd..caf2edccbad2 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -64,6 +64,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 		    c->x86_stepping >= 0x0e))
 			flags->bm_check = 1;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All Zhaoxin CPUs that support C3 share cache.
+		 * And caches should not be flushed by software while
+		 * entering C3 type state.
+		 */
+		flags->bm_check = 1;
+		/*
+		 * On all recent Zhaoxin platforms, ARB_DISABLE is a nop.
+		 * So, set bm_control to zero to indicate that ARB_DISABLE
+		 * is not required while entering C3 type state.
+		 */
+		flags->bm_control = 0;
+	}
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5102bf7c8192..4b4eb06e117c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,6 +24,7 @@ obj-y			+= match.o
 obj-y			+= bugs.o
 obj-y			+= aperfmperf.o
 obj-y			+= cpuid-deps.o
+obj-y			+= umwait.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
@@ -38,6 +39,7 @@ obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
 obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
+obj-$(CONFIG_CPU_SUP_ZHAOXIN)		+= zhaoxin.o
 
 obj-$(CONFIG_X86_MCE)			+= mce/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index e71a6ff8a67e..e2f319dc992d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -13,6 +13,7 @@
 #include <linux/percpu.h>
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
+#include <linux/sched/isolation.h>
 
 #include "cpu.h"
 
@@ -85,6 +86,9 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		return 0;
+
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
 	return per_cpu(samples.khz, cpu);
 }
@@ -101,9 +105,12 @@ void arch_freq_prepare_all(void)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
+		if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+			continue;
 		if (!aperfmperf_snapshot_cpu(cpu, now, false))
 			wait = true;
+	}
 
 	if (wait)
 		msleep(APERFMPERF_REFRESH_DELAY_MS);
@@ -117,6 +124,9 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		return 0;
+
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
 		return per_cpu(samples.khz, cpu);
 
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 395d46f78582..c7503be92f35 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -658,8 +658,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
 	if (c->x86 < 0x17) {
 		/* LLC is at the node level. */
 		per_cpu(cpu_llc_id, cpu) = node_id;
-	} else if (c->x86 == 0x17 &&
-		   c->x86_model >= 0 && c->x86_model <= 0x1F) {
+	} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
 		/*
 		 * LLC is at the core complex level.
 		 * Core complex ID is ApicId[3] for these processors.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9375b3adc91a..0948fc25446a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -366,6 +366,22 @@ out:
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+static __init int x86_nofsgsbase_setup(char *arg)
+{
+	/* Require an exact match without trailing characters. */
+	if (strlen(arg))
+		return 0;
+
+	/* Do not emit a message if the feature is not present. */
+	if (!boot_cpu_has(X86_FEATURE_FSGSBASE))
+		return 1;
+
+	setup_clear_cpu_cap(X86_FEATURE_FSGSBASE);
+	pr_info("FSGSBASE disabled via kernel command line\n");
+	return 1;
+}
+__setup("nofsgsbase", x86_nofsgsbase_setup);
+
 /*
  * Protection Keys are not available in 32-bit mode.
  */
@@ -801,6 +817,30 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+		c->x86_cache_max_rmid  = -1;
+		c->x86_cache_occ_scale = -1;
+		return;
+	}
+
+	/* will be overridden if occupancy monitoring exists */
+	c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
+		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_cache_max_rmid  = ecx;
+		c->x86_cache_occ_scale = ebx;
+	}
+}
+
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -823,6 +863,12 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 		c->x86_capability[CPUID_7_ECX] = ecx;
 		c->x86_capability[CPUID_7_EDX] = edx;
+
+		/* Check valid sub-leaf index before accessing it */
+		if (eax >= 1) {
+			cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+			c->x86_capability[CPUID_7_1_EAX] = eax;
+		}
 	}
 
 	/* Extended state features: level 0x0000000d */
@@ -832,33 +878,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}
 
-	/* Additional Intel-defined flags: level 0x0000000F */
-	if (c->cpuid_level >= 0x0000000F) {
-
-		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
-		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
-		c->x86_capability[CPUID_F_0_EDX] = edx;
-
-		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
-			/* will be overridden if occupancy monitoring exists */
-			c->x86_cache_max_rmid = ebx;
-
-			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
-			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
-			c->x86_capability[CPUID_F_1_EDX] = edx;
-
-			if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
-			      ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
-			       (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
-				c->x86_cache_max_rmid = ecx;
-				c->x86_cache_occ_scale = ebx;
-			}
-		} else {
-			c->x86_cache_max_rmid = -1;
-			c->x86_cache_occ_scale = -1;
-		}
-	}
-
 	/* AMD-defined flags: level 0x80000001 */
 	eax = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = eax;
@@ -889,6 +908,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
+	init_cqm(c);
 
 	/*
 	 * Clear/Set all flags overridden by options, after probe.
@@ -1367,6 +1387,12 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	setup_smap(c);
 	setup_umip(c);
 
+	/* Enable FSGSBASE instructions if available. */
+	if (cpu_has(c, X86_FEATURE_FSGSBASE)) {
+		cr4_set_bits(X86_CR4_FSGSBASE);
+		elf_hwcap2 |= HWCAP2_FSGSBASE;
+	}
+
 	/*
 	 * The vendor-specific functions might have changed features.
 	 * Now we do "generic changes."
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 2c0bd38a44ab..a444028d8145 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -59,6 +59,10 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AVX512_4VNNIW,	X86_FEATURE_AVX512F   },
 	{ X86_FEATURE_AVX512_4FMAPS,	X86_FEATURE_AVX512F   },
 	{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_CQM_OCCUP_LLC,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_CQM_MBM_TOTAL,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_CQM_MBM_LOCAL,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_AVX512_BF16,	X86_FEATURE_AVX512VL  },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 94aa1c72ca98..adf9b71386ef 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,10 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },
+	{ X86_FEATURE_CQM_OCCUP_LLC,	CPUID_EDX,  0, 0x0000000f, 1 },
+	{ X86_FEATURE_CQM_MBM_TOTAL,	CPUID_EDX,  1, 0x0000000f, 1 },
+	{ X86_FEATURE_CQM_MBM_LOCAL,	CPUID_EDX,  2, 0x0000000f, 1 },
 	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
 	{ X86_FEATURE_CAT_L2,		CPUID_EBX,  2, 0x00000010, 0 },
 	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
new file mode 100644
index 000000000000..6a204e7336c1
--- /dev/null
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/cpu.h>
+
+#include <asm/msr.h>
+
+#define UMWAIT_C02_ENABLE	0
+
+#define UMWAIT_CTRL_VAL(max_time, c02_disable)				\
+	(((max_time) & MSR_IA32_UMWAIT_CONTROL_TIME_MASK) |		\
+	((c02_disable) & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE))
+
+/*
+ * Cache IA32_UMWAIT_CONTROL MSR. This is a systemwide control. By default,
+ * umwait max time is 100000 in TSC-quanta and C0.2 is enabled
+ */
+static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+
+/*
+ * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
+ * the sysfs write functions.
+ */
+static DEFINE_MUTEX(umwait_lock);
+
+static void umwait_update_control_msr(void * unused)
+{
+	lockdep_assert_irqs_disabled();
+	wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+}
+
+/*
+ * The CPU hotplug callback sets the control MSR to the global control
+ * value.
+ *
+ * Disable interrupts so the read of umwait_control_cached and the WRMSR
+ * are protected against a concurrent sysfs write. Otherwise the sysfs
+ * write could update the cached value after it had been read on this CPU
+ * and issue the IPI before the old value had been written. The IPI would
+ * interrupt, write the new value and after return from IPI the previous
+ * value would be written by this CPU.
+ *
+ * With interrupts disabled the upcoming CPU either sees the new control
+ * value or the IPI is updating this CPU to the new control value after
+ * interrupts have been reenabled.
+ */
+static int umwait_cpu_online(unsigned int cpu)
+{
+	local_irq_disable();
+	umwait_update_control_msr(NULL);
+	local_irq_enable();
+	return 0;
+}
+
+/*
+ * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
+ * is the only active CPU at this time. The MSR is set up on the APs via the
+ * CPU hotplug callback.
+ *
+ * This function is invoked on resume from suspend and hibernation. On
+ * resume from suspend the restore should be not required, but we neither
+ * trust the firmware nor does it matter if the same value is written
+ * again.
+ */
+static void umwait_syscore_resume(void)
+{
+	umwait_update_control_msr(NULL);
+}
+
+static struct syscore_ops umwait_syscore_ops = {
+	.resume	= umwait_syscore_resume,
+};
+
+/* sysfs interface */
+
+/*
+ * When bit 0 in IA32_UMWAIT_CONTROL MSR is 1, C0.2 is disabled.
+ * Otherwise, C0.2 is enabled.
+ */
+static inline bool umwait_ctrl_c02_enabled(u32 ctrl)
+{
+	return !(ctrl & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE);
+}
+
+static inline u32 umwait_ctrl_max_time(u32 ctrl)
+{
+	return ctrl & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+}
+
+static inline void umwait_update_control(u32 maxtime, bool c02_enable)
+{
+	u32 ctrl = maxtime & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+
+	if (!c02_enable)
+		ctrl |= MSR_IA32_UMWAIT_CONTROL_C02_DISABLE;
+
+	WRITE_ONCE(umwait_control_cached, ctrl);
+	/* Propagate to all CPUs */
+	on_each_cpu(umwait_update_control_msr, NULL, 1);
+}
+
+static ssize_t
+enable_c02_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	u32 ctrl = READ_ONCE(umwait_control_cached);
+
+	return sprintf(buf, "%d\n", umwait_ctrl_c02_enabled(ctrl));
+}
+
+static ssize_t enable_c02_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	bool c02_enable;
+	u32 ctrl;
+	int ret;
+
+	ret = kstrtobool(buf, &c02_enable);
+	if (ret)
+		return ret;
+
+	mutex_lock(&umwait_lock);
+
+	ctrl = READ_ONCE(umwait_control_cached);
+	if (c02_enable != umwait_ctrl_c02_enabled(ctrl))
+		umwait_update_control(ctrl, c02_enable);
+
+	mutex_unlock(&umwait_lock);
+
+	return count;
+}
+static DEVICE_ATTR_RW(enable_c02);
+
+static ssize_t
+max_time_show(struct device *kobj, struct device_attribute *attr, char *buf)
+{
+	u32 ctrl = READ_ONCE(umwait_control_cached);
+
+	return sprintf(buf, "%u\n", umwait_ctrl_max_time(ctrl));
+}
+
+static ssize_t max_time_store(struct device *kobj,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	u32 max_time, ctrl;
+	int ret;
+
+	ret = kstrtou32(buf, 0, &max_time);
+	if (ret)
+		return ret;
+
+	/* bits[1:0] must be zero */
+	if (max_time & ~MSR_IA32_UMWAIT_CONTROL_TIME_MASK)
+		return -EINVAL;
+
+	mutex_lock(&umwait_lock);
+
+	ctrl = READ_ONCE(umwait_control_cached);
+	if (max_time != umwait_ctrl_max_time(ctrl))
+		umwait_update_control(max_time, umwait_ctrl_c02_enabled(ctrl));
+
+	mutex_unlock(&umwait_lock);
+
+	return count;
+}
+static DEVICE_ATTR_RW(max_time);
+
+static struct attribute *umwait_attrs[] = {
+	&dev_attr_enable_c02.attr,
+	&dev_attr_max_time.attr,
+	NULL
+};
+
+static struct attribute_group umwait_attr_group = {
+	.attrs = umwait_attrs,
+	.name = "umwait_control",
+};
+
+static int __init umwait_init(void)
+{
+	struct device *dev;
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+		return -ENODEV;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
+				umwait_cpu_online, NULL);
+
+	register_syscore_ops(&umwait_syscore_ops);
+
+	/*
+	 * Add umwait control interface. Ignore failure, so at least the
+	 * default values are set up in case the machine manages to boot.
+	 */
+	dev = cpu_subsys.dev_root;
+	return sysfs_create_group(&dev->kobj, &umwait_attr_group);
+}
+device_initcall(umwait_init);
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
new file mode 100644
index 000000000000..8e6f2f4b4afe
--- /dev/null
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+
+#include <asm/cpufeature.h>
+
+#include "cpu.h"
+
+#define MSR_ZHAOXIN_FCR57 0x00001257
+
+#define ACE_PRESENT	(1 << 6)
+#define ACE_ENABLED	(1 << 7)
+#define ACE_FCR		(1 << 7)	/* MSR_ZHAOXIN_FCR */
+
+#define RNG_PRESENT	(1 << 2)
+#define RNG_ENABLED	(1 << 3)
+#define RNG_ENABLE	(1 << 8)	/* MSR_ZHAOXIN_RNG */
+
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW	0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI		0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS	0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+
+static void init_zhaoxin_cap(struct cpuinfo_x86 *c)
+{
+	u32  lo, hi;
+
+	/* Test for Extended Feature Flags presence */
+	if (cpuid_eax(0xC0000000) >= 0xC0000001) {
+		u32 tmp = cpuid_edx(0xC0000001);
+
+		/* Enable ACE unit, if present and disabled */
+		if ((tmp & (ACE_PRESENT | ACE_ENABLED)) == ACE_PRESENT) {
+			rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			/* Enable ACE unit */
+			lo |= ACE_FCR;
+			wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			pr_info("CPU: Enabled ACE h/w crypto\n");
+		}
+
+		/* Enable RNG unit, if present and disabled */
+		if ((tmp & (RNG_PRESENT | RNG_ENABLED)) == RNG_PRESENT) {
+			rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			/* Enable RNG unit */
+			lo |= RNG_ENABLE;
+			wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			pr_info("CPU: Enabled h/w RNG\n");
+		}
+
+		/*
+		 * Store Extended Feature Flags as word 5 of the CPU
+		 * capability bit array
+		 */
+		c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001);
+	}
+
+	if (c->x86 >= 0x6)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	cpu_detect_cache_sizes(c);
+}
+
+static void early_init_zhaoxin(struct cpuinfo_x86 *c)
+{
+	if (c->x86 >= 0x6)
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+#ifdef CONFIG_X86_64
+	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+#endif
+	if (c->x86_power & (1 << 8)) {
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+	}
+
+	if (c->cpuid_level >= 0x00000001) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
+		/*
+		 * If HTT (EDX[28]) is set EBX[16:23] contain the number of
+		 * apicids which are reserved per package. Store the resulting
+		 * shift value for the package management code.
+		 */
+		if (edx & (1U << 28))
+			c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
+	}
+
+}
+
+static void zhaoxin_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+	msr_ctl = vmx_msr_high | vmx_msr_low;
+
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+		set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+		set_cpu_cap(c, X86_FEATURE_VNMI);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+		      vmx_msr_low, vmx_msr_high);
+		msr_ctl2 = vmx_msr_high | vmx_msr_low;
+		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+			set_cpu_cap(c, X86_FEATURE_EPT);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+			set_cpu_cap(c, X86_FEATURE_VPID);
+	}
+}
+
+static void init_zhaoxin(struct cpuinfo_x86 *c)
+{
+	early_init_zhaoxin(c);
+	init_intel_cacheinfo(c);
+	detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+	detect_ht(c);
+#endif
+
+	if (c->cpuid_level > 9) {
+		unsigned int eax = cpuid_eax(10);
+
+		/*
+		 * Check for version and the number of counters
+		 * Version(eax[7:0]) can't be 0;
+		 * Counters(eax[15:8]) should be greater than 1;
+		 */
+		if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+	}
+
+	if (c->x86 >= 0x6)
+		init_zhaoxin_cap(c);
+#ifdef CONFIG_X86_64
+	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+#endif
+
+	if (cpu_has(c, X86_FEATURE_VMX))
+		zhaoxin_detect_vmx_virtcap(c);
+}
+
+#ifdef CONFIG_X86_32
+static unsigned int
+zhaoxin_size_cache(struct cpuinfo_x86 *c, unsigned int size)
+{
+	return size;
+}
+#endif
+
+static const struct cpu_dev zhaoxin_cpu_dev = {
+	.c_vendor	= "zhaoxin",
+	.c_ident	= { "  Shanghai  " },
+	.c_early_init	= early_init_zhaoxin,
+	.c_init		= init_zhaoxin,
+#ifdef CONFIG_X86_32
+	.legacy_cache_size = zhaoxin_size_cache,
+#endif
+	.c_x86_vendor	= X86_VENDOR_ZHAOXIN,
+};
+
+cpu_dev_register(zhaoxin_cpu_dev);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 250e4c4ac6d9..8f239091c15d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -162,6 +162,40 @@ enum which_selector {
 };
 
 /*
+ * Out of line to be protected from kprobes. It is not used on Xen
+ * paravirt. When paravirt support is needed, it needs to be renamed
+ * with native_ prefix.
+ */
+static noinline unsigned long __rdgsbase_inactive(void)
+{
+	unsigned long gsbase;
+
+	lockdep_assert_irqs_disabled();
+
+	native_swapgs();
+	gsbase = rdgsbase();
+	native_swapgs();
+
+	return gsbase;
+}
+NOKPROBE_SYMBOL(__rdgsbase_inactive);
+
+/*
+ * Out of line to be protected from kprobes. It is not used on Xen
+ * paravirt. When paravirt support is needed, it needs to be renamed
+ * with native_ prefix.
+ */
+static noinline void __wrgsbase_inactive(unsigned long gsbase)
+{
+	lockdep_assert_irqs_disabled();
+
+	native_swapgs();
+	wrgsbase(gsbase);
+	native_swapgs();
+}
+NOKPROBE_SYMBOL(__wrgsbase_inactive);
+
+/*
  * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are
  * not available.  The goal is to be reasonably fast on non-FSGSBASE systems.
  * It's forcibly inlined because it'll generate better code and this function
@@ -210,8 +244,22 @@ static __always_inline void save_fsgs(struct task_struct *task)
 {
 	savesegment(fs, task->thread.fsindex);
 	savesegment(gs, task->thread.gsindex);
-	save_base_legacy(task, task->thread.fsindex, FS);
-	save_base_legacy(task, task->thread.gsindex, GS);
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		unsigned long flags;
+
+		/*
+		 * If FSGSBASE is enabled, we can't make any useful guesses
+		 * about the base, and user code expects us to save the current
+		 * value.  Fortunately, reading the base directly is efficient.
+		 */
+		task->thread.fsbase = rdfsbase();
+		local_irq_save(flags);
+		task->thread.gsbase = __rdgsbase_inactive();
+		local_irq_restore(flags);
+	} else {
+		save_base_legacy(task, task->thread.fsindex, FS);
+		save_base_legacy(task, task->thread.gsindex, GS);
+	}
 }
 
 #if IS_ENABLED(CONFIG_KVM)
@@ -290,10 +338,22 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
 static __always_inline void x86_fsgsbase_load(struct thread_struct *prev,
 					      struct thread_struct *next)
 {
-	load_seg_legacy(prev->fsindex, prev->fsbase,
-			next->fsindex, next->fsbase, FS);
-	load_seg_legacy(prev->gsindex, prev->gsbase,
-			next->gsindex, next->gsbase, GS);
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		/* Update the FS and GS selectors if they could have changed. */
+		if (unlikely(prev->fsindex || next->fsindex))
+			loadseg(FS, next->fsindex);
+		if (unlikely(prev->gsindex || next->gsindex))
+			loadseg(GS, next->gsindex);
+
+		/* Update the bases. */
+		wrfsbase(next->fsbase);
+		__wrgsbase_inactive(next->gsbase);
+	} else {
+		load_seg_legacy(prev->fsindex, prev->fsbase,
+				next->fsindex, next->fsbase, FS);
+		load_seg_legacy(prev->gsindex, prev->gsbase,
+				next->gsindex, next->gsbase, GS);
+	}
 }
 
 static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
@@ -339,13 +399,46 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
 	return base;
 }
 
+unsigned long x86_gsbase_read_cpu_inactive(void)
+{
+	unsigned long gsbase;
+
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		unsigned long flags;
+
+		/* Interrupts are disabled here. */
+		local_irq_save(flags);
+		gsbase = __rdgsbase_inactive();
+		local_irq_restore(flags);
+	} else {
+		rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+	}
+
+	return gsbase;
+}
+
+void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
+{
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		unsigned long flags;
+
+		/* Interrupts are disabled here. */
+		local_irq_save(flags);
+		__wrgsbase_inactive(gsbase);
+		local_irq_restore(flags);
+	} else {
+		wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+	}
+}
+
 unsigned long x86_fsbase_read_task(struct task_struct *task)
 {
 	unsigned long fsbase;
 
 	if (task == current)
 		fsbase = x86_fsbase_read_cpu();
-	else if (task->thread.fsindex == 0)
+	else if (static_cpu_has(X86_FEATURE_FSGSBASE) ||
+		 (task->thread.fsindex == 0))
 		fsbase = task->thread.fsbase;
 	else
 		fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex);
@@ -359,7 +452,8 @@ unsigned long x86_gsbase_read_task(struct task_struct *task)
 
 	if (task == current)
 		gsbase = x86_gsbase_read_cpu_inactive();
-	else if (task->thread.gsindex == 0)
+	else if (static_cpu_has(X86_FEATURE_FSGSBASE) ||
+		 (task->thread.gsindex == 0))
 		gsbase = task->thread.gsbase;
 	else
 		gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex);
@@ -399,10 +493,11 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	p->thread.sp = (unsigned long) fork_frame;
 	p->thread.io_bitmap_ptr = NULL;
 
-	savesegment(gs, p->thread.gsindex);
-	p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase;
-	savesegment(fs, p->thread.fsindex);
-	p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase;
+	save_fsgs(me);
+	p->thread.fsindex = me->thread.fsindex;
+	p->thread.fsbase = me->thread.fsbase;
+	p->thread.gsindex = me->thread.gsindex;
+	p->thread.gsbase = me->thread.gsbase;
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
 	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a166c960bc9e..3108cdc00b29 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -397,22 +397,12 @@ static int putreg(struct task_struct *child,
 	case offsetof(struct user_regs_struct,fs_base):
 		if (value >= TASK_SIZE_MAX)
 			return -EIO;
-		/*
-		 * When changing the FS base, use do_arch_prctl_64()
-		 * to set the index to zero and to set the base
-		 * as requested.
-		 */
-		if (child->thread.fsbase != value)
-			return do_arch_prctl_64(child, ARCH_SET_FS, value);
+		x86_fsbase_write_task(child, value);
 		return 0;
 	case offsetof(struct user_regs_struct,gs_base):
-		/*
-		 * Exactly the same here as the %fs handling above.
-		 */
 		if (value >= TASK_SIZE_MAX)
 			return -EIO;
-		if (child->thread.gsbase != value)
-			return do_arch_prctl_64(child, ARCH_SET_GS, value);
+		x86_gsbase_write_task(child, value);
 		return 0;
 #endif
 	}
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 9a327d5b6d1f..d78a61408243 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,8 +47,6 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
 	[CPUID_7_0_EBX]       = {         7, 0, CPUID_EBX},
 	[CPUID_D_1_EAX]       = {       0xd, 1, CPUID_EAX},
-	[CPUID_F_0_EDX]       = {       0xf, 0, CPUID_EDX},
-	[CPUID_F_1_EDX]       = {       0xf, 1, CPUID_EDX},
 	[CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
 	[CPUID_6_EAX]         = {         6, 0, CPUID_EAX},
 	[CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},