Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Armin Wolf <W_Armin@gmx.de>
To:     pali@kernel.org
Cc:     jdelvare@suse.com, linux@roeck-us.net, linux-hwmon@vger.kernel.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH 5/7] hwmon: (dell-smm) Improve assembly code
Date:   Tue, 15 Feb 2022 20:11:11 +0100
Message-Id: <20220215191113.16640-6-W_Armin@gmx.de>
In-Reply-To: <20220215191113.16640-1-W_Armin@gmx.de>
References: <20220215191113.16640-1-W_Armin@gmx.de>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

The new assembly code works on both 32bit and 64bit cpus
and allows for more compiler optimisations by not
requiring smm_regs to be packed. Also since the
SMM handler seems to modify the carry flag, the new
code informs the compiler that the flags register
needs to be saved/restored.

Tested with 32 bit and 64 bit kernels on a Dell Inspiron 3505.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
=2D--
 drivers/hwmon/dell-smm-hwmon.c | 71 ++++++++--------------------------
 1 file changed, 17 insertions(+), 54 deletions(-)

diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon=
.c
index b7016971bb2e..04a41d59da60 100644
=2D-- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -123,7 +123,7 @@ struct smm_regs {
 	unsigned int edx;
 	unsigned int esi;
 	unsigned int edi;
-} __packed;
+};

 static const char * const temp_labels[] =3D {
 	"CPU",
@@ -175,59 +175,22 @@ static int i8k_smm_func(void *par)
 	if (smp_processor_id() !=3D 0)
 		return -EBUSY;

-#if defined(CONFIG_X86_64)
-	asm volatile("pushq %%rax\n\t"
-		"movl 0(%%rax),%%edx\n\t"
-		"pushq %%rdx\n\t"
-		"movl 4(%%rax),%%ebx\n\t"
-		"movl 8(%%rax),%%ecx\n\t"
-		"movl 12(%%rax),%%edx\n\t"
-		"movl 16(%%rax),%%esi\n\t"
-		"movl 20(%%rax),%%edi\n\t"
-		"popq %%rax\n\t"
-		"out %%al,$0xb2\n\t"
-		"out %%al,$0x84\n\t"
-		"xchgq %%rax,(%%rsp)\n\t"
-		"movl %%ebx,4(%%rax)\n\t"
-		"movl %%ecx,8(%%rax)\n\t"
-		"movl %%edx,12(%%rax)\n\t"
-		"movl %%esi,16(%%rax)\n\t"
-		"movl %%edi,20(%%rax)\n\t"
-		"popq %%rdx\n\t"
-		"movl %%edx,0(%%rax)\n\t"
-		"pushfq\n\t"
-		"popq %%rax\n\t"
-		"andl $1,%%eax\n"
-		: "=3Da"(rc)
-		:    "a"(regs)
-		:    "%ebx", "%ecx", "%edx", "%esi", "%edi", "memory");
-#else
-	asm volatile("pushl %%eax\n\t"
-	    "movl 0(%%eax),%%edx\n\t"
-	    "push %%edx\n\t"
-	    "movl 4(%%eax),%%ebx\n\t"
-	    "movl 8(%%eax),%%ecx\n\t"
-	    "movl 12(%%eax),%%edx\n\t"
-	    "movl 16(%%eax),%%esi\n\t"
-	    "movl 20(%%eax),%%edi\n\t"
-	    "popl %%eax\n\t"
-	    "out %%al,$0xb2\n\t"
-	    "out %%al,$0x84\n\t"
-	    "xchgl %%eax,(%%esp)\n\t"
-	    "movl %%ebx,4(%%eax)\n\t"
-	    "movl %%ecx,8(%%eax)\n\t"
-	    "movl %%edx,12(%%eax)\n\t"
-	    "movl %%esi,16(%%eax)\n\t"
-	    "movl %%edi,20(%%eax)\n\t"
-	    "popl %%edx\n\t"
-	    "movl %%edx,0(%%eax)\n\t"
-	    "lahf\n\t"
-	    "shrl $8,%%eax\n\t"
-	    "andl $1,%%eax\n"
-	    : "=3Da"(rc)
-	    :    "a"(regs)
-	    :    "%ebx", "%ecx", "%edx", "%esi", "%edi", "memory");
-#endif
+	asm volatile("out %%al,$0xb2\n\t"
+		     "out %%al,$0x84\n"
+		     : "=3Da" (regs->eax),
+		       "=3Db" (regs->ebx),
+		       "=3Dc" (regs->ecx),
+		       "=3Dd" (regs->edx),
+		       "=3DS" (regs->esi),
+		       "=3DD" (regs->edi),
+		       CC_OUT(c) (rc)
+		     : "a" (regs->eax),
+		       "b" (regs->ebx),
+		       "c" (regs->ecx),
+		       "d" (regs->edx),
+		       "S" (regs->esi),
+		       "D" (regs->edi));
+
 	if (rc !=3D 0 || (regs->eax & 0xffff) =3D=3D 0xffff || regs->eax =3D=3D =
eax)
 		rc =3D -EINVAL;

=2D-
2.30.2