x86/fpu: Defer FPU state load until return to userspace

Defer loading of FPU state until return to userspace. This gives
the kernel the potential to skip loading FPU state for tasks that
stay in kernel mode, or for tasks that end up with repeated
invocations of kernel_fpu_begin() & kernel_fpu_end().

The fpregs_lock/unlock() section ensures that the registers remain
unchanged. Otherwise a context switch or a bottom half could save the
registers to its FPU context and the processor's FPU registers would
became random if modified at the same time.

KVM swaps the host/guest registers on entry/exit path. This flow has
been kept as is. First it ensures that the registers are loaded and then
saves the current (host) state before it loads the guest's registers. The
swap is done at the very end with disabled interrupts so it should not
change anymore before theg guest is entered. The read/save version seems
to be cheaper compared to memcpy() in a micro benchmark.

Each thread gets TIF_NEED_FPU_LOAD set as part of fork() / fpu__copy().
For kernel threads, this flag gets never cleared which avoids saving /
restoring the FPU state for kernel threads and during in-kernel usage of
the FPU registers.

 [
   bp: Correct and update commit message and fix checkpatch warnings.
   s/register/registers/ where it is used in plural.
   minor comment corrections.
   remove unused trace_x86_fpu_activate_state() TP.
 ]

Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Dave Hansen <dave.hansen@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aubrey Li <aubrey.li@intel.com>
Cc: Babu Moger <Babu.Moger@amd.com>
Cc: "Chang S. Bae" <chang.seok.bae@intel.com>
Cc: Dmitry Safonov <dima@arista.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: kvm ML <kvm@vger.kernel.org>
Cc: Nicolai Stange <nstange@suse.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Waiman Long <longman@redhat.com>
Cc: x86-ml <x86@kernel.org>
Cc: Yi Wang <wang.yi59@zte.com.cn>
Link: https://lkml.kernel.org/r/20190403164156.19645-24-bigeasy@linutronix.de

2 files changed, 38 insertions, 11 deletions

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 73e684160f35..b774c52e5411 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -10,7 +10,7 @@
 
 #ifndef _ASM_X86_FPU_API_H
 #define _ASM_X86_FPU_API_H
-#include <linux/preempt.h>
+#include <linux/bottom_half.h>
 
 /*
  * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
@@ -22,17 +22,37 @@
 extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
 extern bool irq_fpu_usable(void);
+extern void fpregs_mark_activate(void);
 
+/*
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
+ * A context switch will (and softirq might) save CPU's FPU registers to
+ * fpu->state and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
+ * a random state.
+ */
 static inline void fpregs_lock(void)
 {
 	preempt_disable();
+	local_bh_disable();
 }
 
 static inline void fpregs_unlock(void)
 {
+	local_bh_enable();
 	preempt_enable();
 }
 
+#ifdef CONFIG_X86_DEBUG_FPU
+extern void fpregs_assert_state_consistent(void);
+#else
+static inline void fpregs_assert_state_consistent(void) { }
+#endif
+
+/*
+ * Load the task FPU state before returning to userspace.
+ */
+extern void switch_fpu_return(void);
+
 /*
  * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
  *
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 2cf04fbcba5d..0c8a5093647a 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -30,7 +30,7 @@ extern void fpu__prepare_write(struct fpu *fpu);
 extern void fpu__save(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
 extern void fpu__drop(struct fpu *fpu);
-extern int  fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern int  fpu__copy(struct task_struct *dst, struct task_struct *src);
 extern void fpu__clear(struct fpu *fpu);
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
@@ -531,13 +531,20 @@ static inline void fpregs_activate(struct fpu *fpu)
 /*
  * Internal helper, do not use directly. Use switch_fpu_return() instead.
  */
-static inline void __fpregs_load_activate(struct fpu *fpu, int cpu)
+static inline void __fpregs_load_activate(void)
 {
+	struct fpu *fpu = &current->thread.fpu;
+	int cpu = smp_processor_id();
+
+	if (WARN_ON_ONCE(current->mm == NULL))
+		return;
+
 	if (!fpregs_state_valid(fpu, cpu)) {
-		if (current->mm)
-			copy_kernel_to_fpregs(&fpu->state);
+		copy_kernel_to_fpregs(&fpu->state);
 		fpregs_activate(fpu);
+		fpu->last_cpu = cpu;
 	}
+	clear_thread_flag(TIF_NEED_FPU_LOAD);
 }
 
 /*
@@ -548,8 +555,8 @@ static inline void __fpregs_load_activate(struct fpu *fpu, int cpu)
  *  - switch_fpu_prepare() saves the old state.
  *    This is done within the context of the old process.
  *
- *  - switch_fpu_finish() restores the new state as
- *    necessary.
+ *  - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state
+ *    will get loaded on return to userspace, or when the kernel needs it.
  *
  * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers
  * are saved in the current thread's FPU register state.
@@ -581,10 +588,10 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu)
  */
 
 /*
- * Set up the userspace FPU context for the new task, if the task
- * has used the FPU.
+ * Load PKRU from the FPU context if available. Delay loading of the
+ * complete FPU state until the return to userland.
  */
-static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
+static inline void switch_fpu_finish(struct fpu *new_fpu)
 {
 	u32 pkru_val = init_pkru_value;
 	struct pkru_state *pk;
@@ -592,7 +599,7 @@ static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 	if (!static_cpu_has(X86_FEATURE_FPU))
 		return;
 
-	__fpregs_load_activate(new_fpu, cpu);
+	set_thread_flag(TIF_NEED_FPU_LOAD);
 
 	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
 		return;