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-assembly@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2] hwmon: (dell-smm) Improve assembly code
Date:   Sat, 19 Feb 2022 22:10:11 +0100
Message-Id: <20220219211011.16600-1-W_Armin@gmx.de>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

The new assembly code works on both 32 bit and 64 bit
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. Since clang runs out of
registers on 32 bit x86 when using CC_OUT, we need
to execute "setc" ourself.
Also modify the debug message so we can still see
the result (eax) when the carry flag was set.

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

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
=2D--
Changes in v2:
- fix clang running out of registers on 32 bit x86
- modify debug message
=2D--
 drivers/hwmon/dell-smm-hwmon.c | 85 ++++++++++------------------------
 1 file changed, 25 insertions(+), 60 deletions(-)

diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon=
.c
index c5939e68586d..f1538a46bfc9 100644
=2D-- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -119,7 +119,7 @@ struct smm_regs {
 	unsigned int edx;
 	unsigned int esi;
 	unsigned int edi;
-} __packed;
+};

 static const char * const temp_labels[] =3D {
 	"CPU",
@@ -165,73 +165,38 @@ static int i8k_smm_func(void *par)
 	int eax =3D regs->eax;
 	int ebx =3D regs->ebx;
 	long long duration;
-	int rc;
+	bool carry;

 	/* SMM requires CPU 0 */
 	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
-	if (rc !=3D 0 || (regs->eax & 0xffff) =3D=3D 0xffff || regs->eax =3D=3D =
eax)
-		rc =3D -EINVAL;
+	asm volatile("out %%al,$0xb2\n\t"
+		     "out %%al,$0x84\n\t"
+		     "setc %0\n"
+		     : "=3Dmr" (carry),
+		       "=3Da" (regs->eax),
+		       "=3Db" (regs->ebx),
+		       "=3Dc" (regs->ecx),
+		       "=3Dd" (regs->edx),
+		       "=3DS" (regs->esi),
+		       "=3DD" (regs->edi)
+		     : "a" (regs->eax),
+		       "b" (regs->ebx),
+		       "c" (regs->ecx),
+		       "d" (regs->edx),
+		       "S" (regs->esi),
+		       "D" (regs->edi)
+		     : "cc");

 	duration =3D ktime_us_delta(ktime_get(), calltime);
-	pr_debug("smm(0x%.4x 0x%.4x) =3D 0x%.4x  (took %7lld usecs)\n", eax, ebx=
,
-		 (rc ? 0xffff : regs->eax & 0xffff), duration);
+	pr_debug("smm(0x%.4x 0x%.4x) =3D 0x%.4x carry: %d (took %7lld usecs)\n",
+		 eax, ebx, regs->eax & 0xffff, carry, duration);

-	return rc;
+	if (carry || (regs->eax & 0xffff) =3D=3D 0xffff || regs->eax =3D=3D eax)
+		return -EINVAL;
+
+	return 0;
 }

 /*
=2D-
2.30.2