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

1 files changed, 30 insertions, 19 deletions

diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index b13e86b29426..6df1f15e0cd5 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -269,11 +269,9 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	struct task_struct *tsk = current;
 	struct fpu *fpu = &tsk->thread.fpu;
 	struct user_i387_ia32_struct env;
-	union fpregs_state *state;
 	u64 xfeatures = 0;
 	int fx_only = 0;
 	int ret = 0;
-	void *tmp;
 
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -308,14 +306,18 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		}
 	}
 
-	tmp = kzalloc(sizeof(*state) + fpu_kernel_xstate_size + 64, GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-	state = PTR_ALIGN(tmp, 64);
+	/*
+	 * The current state of the FPU registers does not matter. By setting
+	 * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate
+	 * is not modified on context switch and that the xstate is considered
+	 * to be loaded again on return to userland (overriding last_cpu avoids
+	 * the optimisation).
+	 */
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+	__fpu_invalidate_fpregs_state(fpu);
 
 	if ((unsigned long)buf_fx % 64)
 		fx_only = 1;
-
 	/*
 	 * For 32-bit frames with fxstate, copy the fxstate so it can be
 	 * reconstructed later.
@@ -331,43 +333,52 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		u64 init_bv = xfeatures_mask & ~xfeatures;
 
 		if (using_compacted_format()) {
-			ret = copy_user_to_xstate(&state->xsave, buf_fx);
+			ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
 		} else {
-			ret = __copy_from_user(&state->xsave, buf_fx, state_size);
+			ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
 
 			if (!ret && state_size > offsetof(struct xregs_state, header))
-				ret = validate_xstate_header(&state->xsave.header);
+				ret = validate_xstate_header(&fpu->state.xsave.header);
 		}
 		if (ret)
 			goto err_out;
 
-		sanitize_restored_xstate(state, envp, xfeatures, fx_only);
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
 
+		fpregs_lock();
 		if (unlikely(init_bv))
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-		ret = copy_kernel_to_xregs_err(&state->xsave, xfeatures);
+		ret = copy_kernel_to_xregs_err(&fpu->state.xsave, xfeatures);
 
 	} else if (use_fxsr()) {
-		ret = __copy_from_user(&state->fxsave, buf_fx, state_size);
-		if (ret)
+		ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
+		if (ret) {
+			ret = -EFAULT;
 			goto err_out;
+		}
+
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
 
-		sanitize_restored_xstate(state, envp, xfeatures, fx_only);
+		fpregs_lock();
 		if (use_xsave()) {
 			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 		}
 
-		ret = copy_kernel_to_fxregs_err(&state->fxsave);
+		ret = copy_kernel_to_fxregs_err(&fpu->state.fxsave);
 	} else {
-		ret = __copy_from_user(&state->fsave, buf_fx, state_size);
+		ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size);
 		if (ret)
 			goto err_out;
-		ret = copy_kernel_to_fregs_err(&state->fsave);
+
+		fpregs_lock();
+		ret = copy_kernel_to_fregs_err(&fpu->state.fsave);
 	}
+	if (!ret)
+		fpregs_mark_activate();
+	fpregs_unlock();
 
 err_out:
-	kfree(tmp);
 	if (ret)
 		fpu__clear(fpu);
 	return ret;