[PATCH v8 05/17] x86/fsgsbase/64: Enable FSGSBASE instructions in helper functions

[Chang S. Bae]

Add CPU feature conditional FS/GS base access to the relevant helper
functions. That allows accelerating certain FS/GS base operations in
subsequent changes.

Note, that while possible, the user space entry/exit GS base operations are
not going to use the new FSGSBASE instructions. The reason is that it would
require additional storage for the user space value which adds more
complexity to the low level code and experiments have shown marginal
benefit. This may be revisited later but for now the SWAPGS based handling
in the entry code is preserved except for the paranoid entry/exit code.

To preserve the SWAPGS entry mechanism introduce __[rd|wr]gsbase_inactive()
helpers. Note, for Xen PV, paravirt hooks can be added later as they might
allow a very efficient but different implementation.

Signed-off-by: Chang S. Bae <chang.seok.bae@xxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
---

Changes from v7:
* Added interrupt-related warning messages by Thomas
* Massaged changelog by Thomas
* Used '[FS|GS] base' consistently, instead of '[FS|GS]BASE'
---
 arch/x86/include/asm/fsgsbase.h | 27 ++++++++---------
 arch/x86/kernel/process_64.c    | 66 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index fdd1177..aefd537 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -49,35 +49,32 @@ static __always_inline void wrgsbase(unsigned long 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;
 
-	rdmsrl(MSR_FS_BASE, fsbase);
+	if (static_cpu_has(X86_FEATURE_FSGSBASE))
+		fsbase = rdfsbase();
+	else
+		rdmsrl(MSR_FS_BASE, fsbase);
 
 	return fsbase;
 }
 
-static inline unsigned long x86_gsbase_read_cpu_inactive(void)
-{
-	unsigned long gsbase;
-
-	rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
-
-	return gsbase;
-}
-
 static inline void x86_fsbase_write_cpu(unsigned long fsbase)
 {
-	wrmsrl(MSR_FS_BASE, fsbase);
+	if (static_cpu_has(X86_FEATURE_FSGSBASE))
+		wrfsbase(fsbase);
+	else
+		wrmsrl(MSR_FS_BASE, fsbase);
 }
 
-static inline void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
-{
-	wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
-}
+extern unsigned long x86_gsbase_read_cpu_inactive(void);
+extern void x86_gsbase_write_cpu_inactive(unsigned long gsbase);
 
 #endif /* CONFIG_X86_64 */
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index af64519..c8a67bf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -152,6 +152,40 @@ 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
@@ -329,6 +363,38 @@ 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;
-- 
2.7.4