x86/entry: Set FRED RSP0 on return to userspace instead of context switch

The FRED RSP0 MSR points to the top of the kernel stack for user level
event delivery. As this is the task stack it needs to be updated when a
task is scheduled in.

The update is done at context switch. That means it's also done when
switching to kernel threads, which is pointless as those never go out to
user space. For KVM threads this means there are two writes to FRED_RSP0 as
KVM has to switch to the guest value before VMENTER.

Defer the update to the exit to user space path and cache the per CPU
FRED_RSP0 value, so redundant writes can be avoided.

Provide fred_sync_rsp0() for KVM to keep the cache in sync with the actual
MSR value after returning from guest to host mode.

[ tglx: Massage change log ]

Suggested-by: Sean Christopherson <seanjc@google.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20240822073906.2176342-4-xin@zytor.com

Author: xinli-intel

arch/x86/include/asm/entry-common.h

@@ -8,6 +8,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/io_bitmap.h>
 #include <asm/fpu/api.h>
+#include <asm/fred.h>
 
 /* Check that the stack and regs on entry from user mode are sane. */
 static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs)
@@ -63,6 +64,8 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 	if (IS_ENABLED(CONFIG_X86_DEBUG_FPU) || unlikely(ti_work))
 		arch_exit_work(ti_work);
 
+	fred_update_rsp0();
+
 #ifdef CONFIG_COMPAT
 	/*
 	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before

arch/x86/include/asm/fred.h

@@ -36,6 +36,7 @@
 
 #ifdef CONFIG_X86_FRED
 #include <linux/kernel.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/ptrace.h>
 
@@ -87,12 +88,30 @@ void cpu_init_fred_exceptions(void);
 void cpu_init_fred_rsps(void);
 void fred_complete_exception_setup(void);
 
+DECLARE_PER_CPU(unsigned long, fred_rsp0);
+
+static __always_inline void fred_sync_rsp0(unsigned long rsp0)
+{
+	__this_cpu_write(fred_rsp0, rsp0);
+}
+
+static __always_inline void fred_update_rsp0(void)
+{
+	unsigned long rsp0 = (unsigned long) task_stack_page(current) + THREAD_SIZE;
+
+	if (cpu_feature_enabled(X86_FEATURE_FRED) && (__this_cpu_read(fred_rsp0) != rsp0)) {
+		wrmsrns(MSR_IA32_FRED_RSP0, rsp0);
+		__this_cpu_write(fred_rsp0, rsp0);
+	}
+}
 #else /* CONFIG_X86_FRED */
 static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; }
 static inline void cpu_init_fred_exceptions(void) { }
 static inline void cpu_init_fred_rsps(void) { }
 static inline void fred_complete_exception_setup(void) { }
-static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
+static inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
+static inline void fred_sync_rsp0(unsigned long rsp0) { }
+static inline void fred_update_rsp0(void) { }
 #endif /* CONFIG_X86_FRED */
 #endif /* !__ASSEMBLY__ */
 

arch/x86/include/asm/switch_to.h

@@ -70,12 +70,9 @@ static inline void update_task_stack(struct task_struct *task)
 #ifdef CONFIG_X86_32
 	this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
 #else
-	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
-		wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE);
-	} else if (cpu_feature_enabled(X86_FEATURE_XENPV)) {
+	if (!cpu_feature_enabled(X86_FEATURE_FRED) && cpu_feature_enabled(X86_FEATURE_XENPV))
 		/* Xen PV enters the kernel on the thread stack. */
 		load_sp0(task_top_of_stack(task));
-	}
 #endif
 }
 

arch/x86/kernel/fred.c

@@ -21,6 +21,9 @@
 
 #define FRED_STKLVL(vector, lvl)	((lvl) << (2 * (vector)))
 
+DEFINE_PER_CPU(unsigned long, fred_rsp0);
+EXPORT_PER_CPU_SYMBOL(fred_rsp0);
+
 void cpu_init_fred_exceptions(void)
 {
 	/* When FRED is enabled by default, remove this log message */