[tip: x86/cpu] x86/gsseg: Use the LKGS instruction if available for load_gs_index()

[tip-bot2 for H. Peter Anvin (Intel)]

The following commit has been merged into the x86/cpu branch of tip:

Commit-ID:     92cbbadf73f45c5d8bb26ed8668ff59671ff21e6
Gitweb:        https://git.kernel.org/tip/92cbbadf73f45c5d8bb26ed8668ff59671ff21e6
Author:        H. Peter Anvin (Intel) <hpa@xxxxxxxxx>
AuthorDate:    Wed, 11 Jan 2023 23:20:32 -08:00
Committer:     Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Fri, 13 Jan 2023 10:07:27 +01:00

x86/gsseg: Use the LKGS instruction if available for load_gs_index()

The LKGS instruction atomically loads a segment descriptor into the
%gs descriptor registers, *except* that %gs.base is unchanged, and the
base is instead loaded into MSR_IA32_KERNEL_GS_BASE, which is exactly
what we want this function to do.

Signed-off-by: H. Peter Anvin (Intel) <hpa@xxxxxxxxx>
Signed-off-by: Xin Li <xin3.li@xxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20230112072032.35626-6-xin3.li@xxxxxxxxx
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/gsseg.h | 33 +++++++++++++++++++++++++++++----
 arch/x86/kernel/cpu/common.c |  1 +
 arch/x86/xen/enlighten_pv.c  |  1 +
 3 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/gsseg.h b/arch/x86/include/asm/gsseg.h
index d15577c..ab6a595 100644
--- a/arch/x86/include/asm/gsseg.h
+++ b/arch/x86/include/asm/gsseg.h
@@ -14,17 +14,42 @@
 
 extern asmlinkage void asm_load_gs_index(u16 selector);
 
+/* Replace with "lkgs %di" once binutils support LKGS instruction */
+#define LKGS_DI _ASM_BYTES(0xf2,0x0f,0x00,0xf7)
+
+static inline void native_lkgs(unsigned int selector)
+{
+	u16 sel = selector;
+	asm_inline volatile("1: " LKGS_DI
+			    _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k[sel])
+			    : [sel] "+D" (sel));
+}
+
 static inline void native_load_gs_index(unsigned int selector)
 {
-	unsigned long flags;
+	if (cpu_feature_enabled(X86_FEATURE_LKGS)) {
+		native_lkgs(selector);
+	} else {
+		unsigned long flags;
 
-	local_irq_save(flags);
-	asm_load_gs_index(selector);
-	local_irq_restore(flags);
+		local_irq_save(flags);
+		asm_load_gs_index(selector);
+		local_irq_restore(flags);
+	}
 }
 
 #endif /* CONFIG_X86_64 */
 
+static inline void __init lkgs_init(void)
+{
+#ifdef CONFIG_PARAVIRT_XXL
+#ifdef CONFIG_X86_64
+	if (cpu_feature_enabled(X86_FEATURE_LKGS))
+		pv_ops.cpu.load_gs_index = native_lkgs;
+#endif
+#endif
+}
+
 #ifndef CONFIG_PARAVIRT_XXL
 
 static inline void load_gs_index(unsigned int selector)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9cfca3d..b7ac85a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1960,6 +1960,7 @@ void __init identify_boot_cpu(void)
 	setup_cr_pinning();
 
 	tsx_init();
+	lkgs_init();
 }
 
 void identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5b13796..ce2f19e 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -276,6 +276,7 @@ static void __init xen_init_capabilities(void)
 	setup_clear_cpu_cap(X86_FEATURE_ACC);
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 	setup_clear_cpu_cap(X86_FEATURE_SME);
+	setup_clear_cpu_cap(X86_FEATURE_LKGS);
 
 	/*
 	 * Xen PV would need some work to support PCID: CR3 handling as well