Merge tag 'asoc-v3.13-rc2' of...

Merge tag 'asoc-v3.13-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus

ASoC: Fixes for v3.13

A smattering of fixes here, some core ones for the rate combination
issues for things other than simple bitmasks, for readback of byte
controls and for updating the power of value muxes plus a bunch of
driver fixes of varying severity.

The warning fix in the i.MX FIQ driver is fixing a warning introduced
by a previous fix.

arch/s390/include/asm/vdso.h

@@ -26,8 +26,9 @@ struct vdso_data {
 	__u64 wtom_clock_nsec;		/*				0x28 */
 	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x30 */
 	__u32 tz_dsttime;		/* Type of dst correction	0x34 */
-	__u32 ectg_available;
-	__u32 ntp_mult;			/* NTP adjusted multiplier	0x3C */
+	__u32 ectg_available;		/* ECTG instruction present	0x38 */
+	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x3c */
+	__u32 tk_shift;			/* Shift used for xtime_nsec	0x40 */
 };
 
 struct vdso_per_cpu_data {

arch/s390/kernel/asm-offsets.c

@@ -65,7 +65,8 @@ int main(void)
 	DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
 	DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest));
 	DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available));
-	DEFINE(__VDSO_NTP_MULT, offsetof(struct vdso_data, ntp_mult));
+	DEFINE(__VDSO_TK_MULT, offsetof(struct vdso_data, tk_mult));
+	DEFINE(__VDSO_TK_SHIFT, offsetof(struct vdso_data, tk_shift));
 	DEFINE(__VDSO_ECTG_BASE, offsetof(struct vdso_per_cpu_data, ectg_timer_base));
 	DEFINE(__VDSO_ECTG_USER, offsetof(struct vdso_per_cpu_data, ectg_user_time));
 	/* constants used by the vdso */

arch/s390/kernel/compat_signal.c

@@ -194,7 +194,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 		return -EINVAL;
 
 	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
-	regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
+	regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) |
 		(__u64)(user_sregs.regs.psw.mask & PSW32_MASK_USER) << 32 |
 		(__u64)(user_sregs.regs.psw.mask & PSW32_MASK_RI) << 32 |
 		(__u64)(user_sregs.regs.psw.addr & PSW32_ADDR_AMODE);

arch/s390/kernel/pgm_check.S

@@ -78,7 +78,7 @@ PGM_CHECK_DEFAULT			/* 34 */
 PGM_CHECK_DEFAULT			/* 35 */
 PGM_CHECK_DEFAULT			/* 36 */
 PGM_CHECK_DEFAULT			/* 37 */
-PGM_CHECK_DEFAULT			/* 38 */
+PGM_CHECK_64BIT(do_dat_exception)	/* 38 */
 PGM_CHECK_64BIT(do_dat_exception)	/* 39 */
 PGM_CHECK_64BIT(do_dat_exception)	/* 3a */
 PGM_CHECK_64BIT(do_dat_exception)	/* 3b */

arch/s390/kernel/signal.c

@@ -94,7 +94,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 		return -EINVAL;
 
 	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
-	regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
+	regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) |
 		(user_sregs.regs.psw.mask & (PSW_MASK_USER | PSW_MASK_RI));
 	/* Check for invalid user address space control. */
 	if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_HOME)

arch/s390/kernel/time.c

@@ -108,20 +108,10 @@ static void fixup_clock_comparator(unsigned long long delta)
 	set_clock_comparator(S390_lowcore.clock_comparator);
 }
 
-static int s390_next_ktime(ktime_t expires,
+static int s390_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
 {
-	struct timespec ts;
-	u64 nsecs;
-
-	ts.tv_sec = ts.tv_nsec = 0;
-	monotonic_to_bootbased(&ts);
-	nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires));
-	do_div(nsecs, 125);
-	S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9);
-	/* Program the maximum value if we have an overflow (== year 2042) */
-	if (unlikely(S390_lowcore.clock_comparator < sched_clock_base_cc))
-		S390_lowcore.clock_comparator = -1ULL;
+	S390_lowcore.clock_comparator = get_tod_clock() + delta;
 	set_clock_comparator(S390_lowcore.clock_comparator);
 	return 0;
 }
@@ -146,15 +136,14 @@ void init_cpu_timer(void)
 	cpu = smp_processor_id();
 	cd = &per_cpu(comparators, cpu);
 	cd->name		= "comparator";
-	cd->features		= CLOCK_EVT_FEAT_ONESHOT |
-				  CLOCK_EVT_FEAT_KTIME;
+	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
 	cd->mult		= 16777;
 	cd->shift		= 12;
 	cd->min_delta_ns	= 1;
 	cd->max_delta_ns	= LONG_MAX;
 	cd->rating		= 400;
 	cd->cpumask		= cpumask_of(cpu);
-	cd->set_next_ktime	= s390_next_ktime;
+	cd->set_next_event	= s390_next_event;
 	cd->set_mode		= s390_set_mode;
 
 	clockevents_register_device(cd);
@@ -221,21 +210,30 @@ struct clocksource * __init clocksource_default_clock(void)
 	return &clocksource_tod;
 }
 
-void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
-			struct clocksource *clock, u32 mult)
+void update_vsyscall(struct timekeeper *tk)
 {
-	if (clock != &clocksource_tod)
+	u64 nsecps;
+
+	if (tk->clock != &clocksource_tod)
 		return;
 
 	/* Make userspace gettimeofday spin until we're done. */
 	++vdso_data->tb_update_count;
 	smp_wmb();
-	vdso_data->xtime_tod_stamp = clock->cycle_last;
-	vdso_data->xtime_clock_sec = wall_time->tv_sec;
-	vdso_data->xtime_clock_nsec = wall_time->tv_nsec;
-	vdso_data->wtom_clock_sec = wtm->tv_sec;
-	vdso_data->wtom_clock_nsec = wtm->tv_nsec;
-	vdso_data->ntp_mult = mult;
+	vdso_data->xtime_tod_stamp = tk->clock->cycle_last;
+	vdso_data->xtime_clock_sec = tk->xtime_sec;
+	vdso_data->xtime_clock_nsec = tk->xtime_nsec;
+	vdso_data->wtom_clock_sec =
+		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtom_clock_nsec = tk->xtime_nsec +
+		+ (tk->wall_to_monotonic.tv_nsec << tk->shift);
+	nsecps = (u64) NSEC_PER_SEC << tk->shift;
+	while (vdso_data->wtom_clock_nsec >= nsecps) {
+		vdso_data->wtom_clock_nsec -= nsecps;
+		vdso_data->wtom_clock_sec++;
+	}
+	vdso_data->tk_mult = tk->mult;
+	vdso_data->tk_shift = tk->shift;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }

arch/s390/kernel/vdso32/clock_gettime.S

@@ -38,25 +38,26 @@ __kernel_clock_gettime:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,2f
 	ahi	%r0,-1
-2:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
+2:	ms	%r0,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	lr	%r2,%r0
-	l	%r0,__VDSO_NTP_MULT(%r5)
+	l	%r0,__VDSO_TK_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	3f
-	a	%r0,__VDSO_NTP_MULT(%r5)
+	a	%r0,__VDSO_TK_MULT(%r5)
 3:	alr	%r0,%r2
-	srdl	%r0,12
-	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
 	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
 	brc	12,4f
 	ahi	%r0,1
-4:	l	%r2,__VDSO_XTIME_SEC+4(%r5)
-	al	%r0,__VDSO_WTOM_NSEC(%r5)	/*  + wall_to_monotonic */
+4:	al	%r0,__VDSO_WTOM_NSEC(%r5)	/*  + wall_to_monotonic.nsec */
 	al	%r1,__VDSO_WTOM_NSEC+4(%r5)
 	brc	12,5f
 	ahi	%r0,1
-5:	al	%r2,__VDSO_WTOM_SEC+4(%r5)
+5:	l	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srdl	%r0,0(%r2)			/*  >> tk->shift */
+	l	%r2,__VDSO_XTIME_SEC+4(%r5)
+	al	%r2,__VDSO_WTOM_SEC+4(%r5)
 	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
 	jne	1b
 	basr	%r5,0
@@ -86,20 +87,21 @@ __kernel_clock_gettime:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,12f
 	ahi	%r0,-1
-12:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
+12:	ms	%r0,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	lr	%r2,%r0
-	l	%r0,__VDSO_NTP_MULT(%r5)
+	l	%r0,__VDSO_TK_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	13f
-	a	%r0,__VDSO_NTP_MULT(%r5)
+	a	%r0,__VDSO_TK_MULT(%r5)
 13:	alr	%r0,%r2
-	srdl	%r0,12
-	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
 	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
 	brc	12,14f
 	ahi	%r0,1
-14:	l	%r2,__VDSO_XTIME_SEC+4(%r5)
+14:	l	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srdl	%r0,0(%r2)			/*  >> tk->shift */
+	l	%r2,__VDSO_XTIME_SEC+4(%r5)
 	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
 	jne	11b
 	basr	%r5,0

arch/s390/kernel/vdso32/gettimeofday.S

@@ -35,15 +35,14 @@ __kernel_gettimeofday:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,3f
 	ahi	%r0,-1
-3:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
+3:	ms	%r0,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	st	%r0,24(%r15)
-	l	%r0,__VDSO_NTP_MULT(%r5)
+	l	%r0,__VDSO_TK_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	4f
-	a	%r0,__VDSO_NTP_MULT(%r5)
+	a	%r0,__VDSO_TK_MULT(%r5)
 4:	al	%r0,24(%r15)
-	srdl	%r0,12
 	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
 	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
 	brc	12,5f
@@ -51,6 +50,8 @@ __kernel_gettimeofday:
 5:	mvc	24(4,%r15),__VDSO_XTIME_SEC+4(%r5)
 	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
 	jne	1b
+	l	%r4,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srdl	%r0,0(%r4)			/*  >> tk->shift */
 	l	%r4,24(%r15)			/* get tv_sec from stack */
 	basr	%r5,0
 6:	ltr	%r0,%r0

arch/s390/kernel/vdso64/clock_gettime.S

@@ -34,14 +34,15 @@ __kernel_clock_gettime:
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	0b
 	stck	48(%r15)			/* Store TOD clock */
+	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
+	alg	%r0,__VDSO_WTOM_SEC(%r5)	/*  + wall_to_monotonic.sec */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
-	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
-	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
-	lg	%r0,__VDSO_XTIME_SEC(%r5)
-	alg	%r1,__VDSO_WTOM_NSEC(%r5)	/*  + wall_to_monotonic */
-	alg	%r0,__VDSO_WTOM_SEC(%r5)
+	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
+	alg	%r1,__VDSO_WTOM_NSEC(%r5)	/*  + wall_to_monotonic.nsec */
+	srlg	%r1,%r1,0(%r2)			/*  >> tk->shift */
 	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
 	jne	0b
 	larl	%r5,13f
@@ -62,12 +63,13 @@ __kernel_clock_gettime:
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	5b
 	stck	48(%r15)			/* Store TOD clock */
+	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
-	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
-	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
-	lg	%r0,__VDSO_XTIME_SEC(%r5)
+	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
+	srlg	%r1,%r1,0(%r2)			/*  >> tk->shift */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
 	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
 	jne	5b
 	larl	%r5,13f

arch/s390/kernel/vdso64/gettimeofday.S

@@ -31,12 +31,13 @@ __kernel_gettimeofday:
 	stck	48(%r15)			/* Store TOD clock */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
-	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
-	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime.tv_nsec */
-	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* xtime.tv_sec */
+	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
 	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
 	jne	0b
+	lgf	%r5,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srlg	%r1,%r1,0(%r5)			/*  >> tk->shift */
 	larl	%r5,5f
 2:	clg	%r1,0(%r5)
 	jl	3f

arch/s390/lib/uaccess_pt.c

@@ -78,11 +78,14 @@ static size_t copy_in_kernel(size_t count, void __user *to,
  * contains the (negative) exception code.
  */
 #ifdef CONFIG_64BIT
+
 static unsigned long follow_table(struct mm_struct *mm,
 				  unsigned long address, int write)
 {
 	unsigned long *table = (unsigned long *)__pa(mm->pgd);
 
+	if (unlikely(address > mm->context.asce_limit - 1))
+		return -0x38UL;
 	switch (mm->context.asce_bits & _ASCE_TYPE_MASK) {
 	case _ASCE_TYPE_REGION1:
 		table = table + ((address >> 53) & 0x7ff);

arch/x86/crypto/Makefile

@@ -3,8 +3,9 @@
 #
 
 avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+				$(comma)4)$(comma)%ymm2,yes,no)
 
-obj-$(CONFIG_CRYPTO_ABLK_HELPER_X86) += ablk_helper.o
 obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
 
 obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o

arch/x86/crypto/aesni-intel_glue.c

@@ -34,7 +34,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/i387.h>
 #include <asm/crypto/aes.h>
-#include <asm/crypto/ablk_helper.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/aead.h>
 #include <linux/workqueue.h>

arch/x86/crypto/camellia_aesni_avx2_glue.c

@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
@@ -21,7 +22,6 @@
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 #include <asm/crypto/camellia.h>
-#include <asm/crypto/ablk_helper.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16

arch/x86/crypto/camellia_aesni_avx_glue.c

@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
@@ -21,7 +22,6 @@
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 #include <asm/crypto/camellia.h>
-#include <asm/crypto/ablk_helper.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAMELLIA_AESNI_PARALLEL_BLOCKS 16

arch/x86/crypto/cast5_avx_glue.c

@@ -26,13 +26,13 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/cast5.h>
 #include <crypto/cryptd.h>
 #include <crypto/ctr.h>
 #include <asm/xcr.h>
 #include <asm/xsave.h>
-#include <asm/crypto/ablk_helper.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST5_PARALLEL_BLOCKS 16

arch/x86/crypto/cast6_avx_glue.c

@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/cast6.h>
 #include <crypto/cryptd.h>
@@ -37,7 +38,6 @@
 #include <crypto/xts.h>
 #include <asm/xcr.h>
 #include <asm/xsave.h>
-#include <asm/crypto/ablk_helper.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST6_PARALLEL_BLOCKS 8

arch/x86/crypto/serpent_avx2_glue.c

@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
@@ -22,7 +23,6 @@
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 #include <asm/crypto/serpent-avx.h>
-#include <asm/crypto/ablk_helper.h>
 #include <asm/crypto/glue_helper.h>
 
 #define SERPENT_AVX2_PARALLEL_BLOCKS 16

arch/x86/crypto/serpent_avx_glue.c

@@ -28,6 +28,7 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/serpent.h>
 #include <crypto/cryptd.h>
@@ -38,7 +39,6 @@
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 #include <asm/crypto/serpent-avx.h>
-#include <asm/crypto/ablk_helper.h>
 #include <asm/crypto/glue_helper.h>
 
 /* 8-way parallel cipher functions */

arch/x86/crypto/serpent_sse2_glue.c

@@ -34,6 +34,7 @@
 #include <linux/types.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
+#include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <crypto/serpent.h>
 #include <crypto/cryptd.h>
@@ -42,7 +43,6 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <asm/crypto/serpent-sse2.h>
-#include <asm/crypto/ablk_helper.h>
 #include <asm/crypto/glue_helper.h>
 
 static void serpent_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src)