KVM: x86: avoid large stack allocations in em_fxrstor

em_fxstor previously called fxstor_fixup.  Both created instances of
struct fxregs_state on the stack, which triggered the warning:

arch/x86/kvm/emulate.c:4018:12: warning: stack frame size of 1080 bytes
in function
      'em_fxrstor' [-Wframe-larger-than=]
static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
           ^
with CONFIG_FRAME_WARN set to 1024.

This patch does the fixup in em_fxstor now, avoiding one additional
struct fxregs_state, and now fxstor_fixup can be removed as it has no
other call sites.

Further, the calculation for offsets into xmm_space can be shared
between em_fxstor and em_fxsave.

Signed-off-by: Nick Desaulniers <nick.desaulniers@gmail.com>
[Clean up calculation of offsets and fix it for 64-bit mode. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: nickdesaulniers

arch/x86/kvm/emulate.c

@@ -3940,6 +3940,25 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+/*
+ * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but does save
+ * and restore MXCSR.
+ */
+static size_t __fxstate_size(int nregs)
+{
+	return offsetof(struct fxregs_state, xmm_space[0]) + nregs * 16;
+}
+
+static inline size_t fxstate_size(struct x86_emulate_ctxt *ctxt)
+{
+	bool cr4_osfxsr;
+	if (ctxt->mode == X86EMUL_MODE_PROT64)
+		return __fxstate_size(16);
+
+	cr4_osfxsr = ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR;
+	return __fxstate_size(cr4_osfxsr ? 8 : 0);
+}
+
 /*
  * FXSAVE and FXRSTOR have 4 different formats depending on execution mode,
  *  1) 16 bit mode
@@ -3961,7 +3980,6 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt)
 static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 {
 	struct fxregs_state fx_state;
-	size_t size;
 	int rc;
 
 	rc = check_fxsr(ctxt);
@@ -3977,68 +3995,42 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)
-		size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]);
-	else
-		size = offsetof(struct fxregs_state, xmm_space[0]);
-
-	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
-}
-
-static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
-		struct fxregs_state *new)
-{
-	int rc = X86EMUL_CONTINUE;
-	struct fxregs_state old;
-
-	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old));
-	if (rc != X86EMUL_CONTINUE)
-		return rc;
-
-	/*
-	 * 64 bit host will restore XMM 8-15, which is not correct on non-64
-	 * bit guests.  Load the current values in order to preserve 64 bit
-	 * XMMs after fxrstor.
-	 */
-#ifdef CONFIG_X86_64
-	/* XXX: accessing XMM 8-15 very awkwardly */
-	memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16);
-#endif
-
-	/*
-	 * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but
-	 * does save and restore MXCSR.
-	 */
-	if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))
-		memcpy(new->xmm_space, old.xmm_space, 8 * 16);
-
-	return rc;
+	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state,
+		                   fxstate_size(ctxt));
 }
 
 static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 {
 	struct fxregs_state fx_state;
 	int rc;
+	size_t size;
 
 	rc = check_fxsr(ctxt);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
-	if (rc != X86EMUL_CONTINUE)
-		return rc;
+	ctxt->ops->get_fpu(ctxt);
 
-	if (fx_state.mxcsr >> 16)
-		return emulate_gp(ctxt, 0);
+	size = fxstate_size(ctxt);
+	if (size < __fxstate_size(16)) {
+		rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+		if (rc != X86EMUL_CONTINUE)
+			goto out;
+	}
 
-	ctxt->ops->get_fpu(ctxt);
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+	if (rc != X86EMUL_CONTINUE)
+		goto out;
 
-	if (ctxt->mode < X86EMUL_MODE_PROT64)
-		rc = fxrstor_fixup(ctxt, &fx_state);
+	if (fx_state.mxcsr >> 16) {
+		rc = emulate_gp(ctxt, 0);
+		goto out;
+	}
 
 	if (rc == X86EMUL_CONTINUE)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
+out:
 	ctxt->ops->put_fpu(ctxt);
 
 	return rc;