Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Vitaly Kuznetsov <vkuznets@redhat.com>
To:     kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>
Cc:     Sean Christopherson <seanjc@google.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Michael Kelley <mikelley@microsoft.com>,
        Siddharth Chandrasekaran <sidcha@amazon.de>,
        linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v3 23/34] KVM: selftests: Better XMM read/write helpers
Date:   Thu, 14 Apr 2022 15:20:02 +0200
Message-Id: <20220414132013.1588929-24-vkuznets@redhat.com>
In-Reply-To: <20220414132013.1588929-1-vkuznets@redhat.com>
References: <20220414132013.1588929-1-vkuznets@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain
Content-Transfer-Encoding: 8bit
Precedence: bulk

set_xmm()/get_xmm() helpers are fairly useless as they only read 64 bits
from 128-bit registers. Moreover, these helpers are not used. Borrow
_kvm_read_sse_reg()/_kvm_write_sse_reg() from KVM limiting them to
XMM0-XMM8 for now.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 .../selftests/kvm/include/x86_64/processor.h  | 70 ++++++++++---------
 1 file changed, 36 insertions(+), 34 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 37db341d4cc5..9ad7602a257b 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -296,71 +296,73 @@ static inline void cpuid(uint32_t *eax, uint32_t *ebx,
 	    : "memory");
 }
 
-#define SET_XMM(__var, __xmm) \
-	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
+typedef u32		__attribute__((vector_size(16))) sse128_t;
+#define __sse128_u	union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; }
+#define sse128_lo(x)	({ __sse128_u t; t.vec = x; t.as_u64[0]; })
+#define sse128_hi(x)	({ __sse128_u t; t.vec = x; t.as_u64[1]; })
 
-static inline void set_xmm(int n, unsigned long val)
+static inline void read_sse_reg(int reg, sse128_t *data)
 {
-	switch (n) {
+	switch (reg) {
 	case 0:
-		SET_XMM(val, xmm0);
+		asm("movdqa %%xmm0, %0" : "=m"(*data));
 		break;
 	case 1:
-		SET_XMM(val, xmm1);
+		asm("movdqa %%xmm1, %0" : "=m"(*data));
 		break;
 	case 2:
-		SET_XMM(val, xmm2);
+		asm("movdqa %%xmm2, %0" : "=m"(*data));
 		break;
 	case 3:
-		SET_XMM(val, xmm3);
+		asm("movdqa %%xmm3, %0" : "=m"(*data));
 		break;
 	case 4:
-		SET_XMM(val, xmm4);
+		asm("movdqa %%xmm4, %0" : "=m"(*data));
 		break;
 	case 5:
-		SET_XMM(val, xmm5);
+		asm("movdqa %%xmm5, %0" : "=m"(*data));
 		break;
 	case 6:
-		SET_XMM(val, xmm6);
+		asm("movdqa %%xmm6, %0" : "=m"(*data));
 		break;
 	case 7:
-		SET_XMM(val, xmm7);
+		asm("movdqa %%xmm7, %0" : "=m"(*data));
 		break;
+	default:
+		BUG();
 	}
 }
 
-#define GET_XMM(__xmm)							\
-({									\
-	unsigned long __val;						\
-	asm volatile("movq %%"#__xmm", %0" : "=r"(__val));		\
-	__val;								\
-})
-
-static inline unsigned long get_xmm(int n)
+static inline void write_sse_reg(int reg, const sse128_t *data)
 {
-	assert(n >= 0 && n <= 7);
-
-	switch (n) {
+	switch (reg) {
 	case 0:
-		return GET_XMM(xmm0);
+		asm("movdqa %0, %%xmm0" : : "m"(*data));
+		break;
 	case 1:
-		return GET_XMM(xmm1);
+		asm("movdqa %0, %%xmm1" : : "m"(*data));
+		break;
 	case 2:
-		return GET_XMM(xmm2);
+		asm("movdqa %0, %%xmm2" : : "m"(*data));
+		break;
 	case 3:
-		return GET_XMM(xmm3);
+		asm("movdqa %0, %%xmm3" : : "m"(*data));
+		break;
 	case 4:
-		return GET_XMM(xmm4);
+		asm("movdqa %0, %%xmm4" : : "m"(*data));
+		break;
 	case 5:
-		return GET_XMM(xmm5);
+		asm("movdqa %0, %%xmm5" : : "m"(*data));
+		break;
 	case 6:
-		return GET_XMM(xmm6);
+		asm("movdqa %0, %%xmm6" : : "m"(*data));
+		break;
 	case 7:
-		return GET_XMM(xmm7);
+		asm("movdqa %0, %%xmm7" : : "m"(*data));
+		break;
+	default:
+		BUG();
 	}
-
-	/* never reached */
-	return 0;
 }
 
 static inline void cpu_relax(void)
-- 
2.35.1