Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 1/1] mfd: Remove unused variable using Coccinelle
From: Shyam Saini @ 2016-10-10  1:36 UTC (permalink / raw)
  To: linux-arm-kernel

The variable err is initialized but never used otherwise.

The semantic patch that makes this change is as follows:

// <smpl>
@@
type T;
identifier i;
constant C;
@@

(
extern T i;
|
- T i;
  <+... when != i
- i = C;
  ...+>
)
// </smpl>

Signed-off-by: Shyam Saini <mayhs11saini@gmail.com>
---
 drivers/mfd/ab3100-core.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c
index 6a5a988..3ebb2f0 100644
--- a/drivers/mfd/ab3100-core.c
+++ b/drivers/mfd/ab3100-core.c
@@ -584,8 +584,6 @@ static struct dentry *ab3100_set_reg_file;
 
 static void ab3100_setup_debugfs(struct ab3100 *ab3100)
 {
-	int err;
-
 	ab3100_dir = debugfs_create_dir("ab3100", NULL);
 	if (!ab3100_dir)
 		goto exit_no_debugfs;
@@ -594,7 +592,6 @@ static void ab3100_setup_debugfs(struct ab3100 *ab3100)
 				S_IRUGO, ab3100_dir, ab3100,
 				&ab3100_registers_fops);
 	if (!ab3100_reg_file) {
-		err = -ENOMEM;
 		goto exit_destroy_dir;
 	}
 
@@ -604,7 +601,6 @@ static void ab3100_setup_debugfs(struct ab3100 *ab3100)
 				S_IWUSR, ab3100_dir, &ab3100_get_priv,
 				&ab3100_get_set_reg_fops);
 	if (!ab3100_get_reg_file) {
-		err = -ENOMEM;
 		goto exit_destroy_reg;
 	}
 
@@ -614,7 +610,6 @@ static void ab3100_setup_debugfs(struct ab3100 *ab3100)
 				S_IWUSR, ab3100_dir, &ab3100_set_priv,
 				&ab3100_get_set_reg_fops);
 	if (!ab3100_set_reg_file) {
-		err = -ENOMEM;
 		goto exit_destroy_get_reg;
 	}
 	return;
-- 
2.7.4

^ permalink raw reply related

* [PATCH 8/8] pinctrl: aspeed-g5: Add mux configuration for all pins
From: Rob Herring @ 2016-10-10  0:53 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <a17175fdeaf1656afa307a180a4ab4953d4ad19c.1474986045.git-series.andrew@aj.id.au>

On Wed, Sep 28, 2016 at 12:20:20AM +0930, Andrew Jeffery wrote:
> The patch introducing the g5 pinctrl driver implemented a smattering of
> pins to flesh out the implementation of the core and provide bare-bones
> support for some OpenPOWER platforms and the AST2500 evaluation board.
> Now, update the bindings document to reflect the complete functionality
> and implement the necessary pin configuration tables in the driver.
> 
> Signed-off-by: Andrew Jeffery <andrew@aj.id.au>
> ---
>  Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt |   17 +-

Acked-by: Rob Herring <robh@kernel.org>

>  drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c                   | 1476 ++++++-
>  drivers/pinctrl/aspeed/pinctrl-aspeed.h                      |    1 +-
>  3 files changed, 1487 insertions(+), 7 deletions(-)

^ permalink raw reply

* [PATCH 2/2] arm: futex: Use asm-generic/futex.h instead of redefining the entire header
From: Joel Porquet @ 2016-10-10  0:03 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161010000308.13212-1-joel@porquet.org>

"asm-generic/futex.h" was refactored and now allows arch ports to only
define arch-specific macros instead of redefining the entire header
file.

This patch adapts "asm/futex.h" for ARM by only defining the macros
required by the generic header (ie __futex_atomic_op_inuser() and
__futex_atomic_cmpxchg_inatomic()).

Compiled (SMP and !SMP) and booted on QEMU with a minimal busybox-based
system.

Signed-off-by: Joel Porquet <joel@porquet.org>
---
 arch/arm/include/asm/futex.h | 203 ++++++++++++++++++-------------------------
 1 file changed, 84 insertions(+), 119 deletions(-)

diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 6795368..d3db562 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -39,41 +39,30 @@
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory");					\
 	uaccess_restore(__ua_flags);				\
+	smp_mb();						\
 })
 
-static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-			      u32 oldval, u32 newval)
-{
-	unsigned int __ua_flags;
-	int ret;
-	u32 val;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
-	smp_mb();
-	/* Prefetching cannot fault */
-	prefetchw(uaddr);
-	__ua_flags = uaccess_save_and_enable();
-	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	ldrex	%1, [%4]\n"
-	"	teq	%1, %2\n"
-	"	ite	eq	@ explicit IT needed for the 2b label\n"
-	"2:	strexeq	%0, %3, [%4]\n"
-	"	movne	%0, #0\n"
-	"	teq	%0, #0\n"
-	"	bne	1b\n"
-	__futex_atomic_ex_table("%5")
-	: "=&r" (ret), "=&r" (val)
-	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
-	: "cc", "memory");
-	uaccess_restore(__ua_flags);
-	smp_mb();
-
-	*uval = val;
-	return ret;
-}
+#define __futex_atomic_cmpxchg_op(ret, val, uaddr, oldval, newval)		\
+({										\
+	unsigned int __ua_flags;						\
+	smp_mb();								\
+	prefetchw(uaddr);							\
+	__ua_flags = uaccess_save_and_enable();					\
+	__asm__ __volatile__(							\
+	"1:	ldrex	%1, [%4]\n"						\
+	"	teq	%1, %2\n"						\
+	"	ite	eq	@ explicit IT needed for the 2b label\n"	\
+	"2:	strexeq	%0, %3, [%4]\n"						\
+	"	movne	%0, #0\n"						\
+	"	teq	%0, #0\n"						\
+	"	bne	1b\n"							\
+	__futex_atomic_ex_table("%5")						\
+	: "=&r" (ret), "=&r" (val)						\
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)		\
+	: "cc", "memory");							\
+	uaccess_restore(__ua_flags);						\
+	smp_mb();								\
+})
 
 #else /* !SMP, we can work around lack of atomic ops by disabling preemption */
 
@@ -82,7 +71,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 ({								\
-	unsigned int __ua_flags = uaccess_save_and_enable();	\
+	unsigned int __ua_flags;				\
+	preempt_disable();					\
+	__ua_flags = uaccess_save_and_enable();			\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
@@ -93,98 +84,72 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory");					\
 	uaccess_restore(__ua_flags);				\
+	preempt_disable();					\
 })
 
-static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-			      u32 oldval, u32 newval)
-{
-	unsigned int __ua_flags;
-	int ret = 0;
-	u32 val;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
-	preempt_disable();
-	__ua_flags = uaccess_save_and_enable();
-	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	" TUSER(ldr) "	%1, [%4]\n"
-	"	teq	%1, %2\n"
-	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	" TUSER(streq) "	%3, [%4]\n"
-	__futex_atomic_ex_table("%5")
-	: "+r" (ret), "=&r" (val)
-	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
-	: "cc", "memory");
-	uaccess_restore(__ua_flags);
-
-	*uval = val;
-	preempt_enable();
-
-	return ret;
-}
+#define __futex_atomic_cmpxchg_op(ret, val, uaddr, oldval, newval)		\
+({										\
+	unsigned int __ua_flags;						\
+	preempt_disable();							\
+	__ua_flags = uaccess_save_and_enable();					\
+	__asm__ __volatile__(							\
+	"@futex_atomic_cmpxchg_inatomic\n"					\
+	"1:	" TUSER(ldr) "	%1, [%4]\n"					\
+	"	teq	%1, %2\n"						\
+	"	it	eq	@ explicit IT needed for the 2b label\n"	\
+	"2:	" TUSER(streq) "	%3, [%4]\n"				\
+	__futex_atomic_ex_table("%5")						\
+	: "+r" (ret), "=&r" (val)						\
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)		\
+	: "cc", "memory");							\
+	uaccess_restore(__ua_flags);						\
+	preempt_enable();							\
+})
 
 #endif /* !SMP */
 
-static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
-{
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret, tmp;
+#define __futex_atomic_op_inuser(op, oldval, uaddr, oparg)		\
+({									\
+	int __ret, tmp;							\
+	pagefault_disable();						\
+	switch (op) {							\
+	case FUTEX_OP_SET:						\
+		__futex_atomic_op("mov	%0, %4",			\
+				__ret, oldval, tmp, uaddr, oparg);	\
+		break;							\
+	case FUTEX_OP_ADD:						\
+		__futex_atomic_op("add	%0, %1, %4",			\
+				__ret, oldval, tmp, uaddr, oparg);	\
+		break;							\
+	case FUTEX_OP_OR:						\
+		__futex_atomic_op("orr	%0, %1, %4",			\
+				__ret, oldval, tmp, uaddr, oparg);	\
+		break;							\
+	case FUTEX_OP_ANDN:						\
+		__futex_atomic_op("and	%0, %1, %4",			\
+				__ret, oldval, tmp, uaddr, ~oparg);	\
+		break;							\
+	case FUTEX_OP_XOR:						\
+		__futex_atomic_op("eor	%0, %1, %4",			\
+				__ret, oldval, tmp, uaddr, oparg);	\
+		break;							\
+	default:							\
+		ret = -ENOSYS;						\
+	}								\
+	pagefault_enable();						\
+	__ret;								\
+})
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
+#define __futex_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval)	\
+({									\
+	int __ret;							\
+	u32 val;							\
+	__futex_atomic_cmpxchg_op(__ret, val, uaddr, oldval, newval);	\
+	*uval = val;							\
+	__ret;								\
+})
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
-#ifndef CONFIG_SMP
-	preempt_disable();
-#endif
-	pagefault_disable();
-
-	switch (op) {
-	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%0, %4", ret, oldval, tmp, uaddr, oparg);
-		break;
-	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
-		break;
-	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
-		break;
-	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%0, %1, %4", ret, oldval, tmp, uaddr, ~oparg);
-		break;
-	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
-		break;
-	default:
-		ret = -ENOSYS;
-	}
-
-	pagefault_enable();
-#ifndef CONFIG_SMP
-	preempt_enable();
-#endif
-
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
-	return ret;
-}
+#include <asm-generic/futex.h>
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */
-- 
2.10.0

^ permalink raw reply related

* [PATCH 1/2] asm-generic/futex.h: code refactoring
From: Joel Porquet @ 2016-10-10  0:03 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161010000308.13212-1-joel@porquet.org>

The generic header "asm-generic/futex.h" defines the implementations of
atomic functions "futex_atomic_op_inuser()" and
"futex_atomic_cmpxchg_inatomic()". Currently, each of these functions is
actually defined twice: once for uniprocessor machines and once for
multiprocessor machines.

However, these {smp,!smp} implementations, especially for
"futex_atomic_op_inuser()", have some code in common that could be
refactored. Furthermore, most the arch ports usually redefine their own
"asm/futex.h" header completely, instead of using the generic header
even though a good chunk of the code is shared (once again, especially
for 'futex_atomic_op_inuser()').

This patch refactors the uniprocessor and multiprocessor implementations
of both functions into a single implementation, making the
machine-specific part a customizable macro.

As a (hopefully good) side-effect, this makes it possible for arch ports
to start including this generic header, instead of redefining it
completely, and only overload the macros with arch-specific routines.

Signed-off-by: Joel Porquet <joel@porquet.org>
---
 include/asm-generic/futex.h | 219 ++++++++++++++++++++++----------------------
 1 file changed, 112 insertions(+), 107 deletions(-)

diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index bf2d34c..a72b36b 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -6,12 +6,114 @@
 #include <asm/errno.h>
 
 #ifndef CONFIG_SMP
+
 /*
- * The following implementation only for uniprocessor machines.
- * It relies on preempt_disable() ensuring mutual exclusion.
- *
+ * The following implementations are for uniprocessor machines.
+ * They rely on preempt_disable() to ensure mutual exclusion.
  */
 
+#ifndef __futex_atomic_op_inuser
+#define __futex_atomic_op_inuser(op, oldval, uaddr, oparg)	\
+({								\
+	int __ret;						\
+	u32 tmp;						\
+								\
+	preempt_disable();					\
+	pagefault_disable();					\
+								\
+	__ret = -EFAULT;					\
+	if (unlikely(get_user(oldval, uaddr) != 0))		\
+		goto out_pagefault_enable;			\
+								\
+	__ret = 0;						\
+	tmp = oldval;						\
+								\
+	switch (op) {						\
+	case FUTEX_OP_SET:					\
+		tmp = oparg;					\
+		break;						\
+	case FUTEX_OP_ADD:					\
+		tmp += oparg;					\
+		break;						\
+	case FUTEX_OP_OR:					\
+		tmp |= oparg;					\
+		break;						\
+	case FUTEX_OP_ANDN:					\
+		tmp &= ~oparg;					\
+		break;						\
+	case FUTEX_OP_XOR:					\
+		tmp ^= oparg;					\
+		break;						\
+	default:						\
+		__ret = -ENOSYS;				\
+	}							\
+								\
+	if (__ret == 0 && unlikely(put_user(tmp, uaddr) != 0))	\
+		__ret = -EFAULT;				\
+								\
+out_pagefault_enable:						\
+	pagefault_enable();					\
+	preempt_enable();					\
+								\
+	__ret;							\
+})
+#endif
+
+#ifndef __futex_atomic_cmpxchg_inatomic
+#define __futex_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval)	\
+({									\
+	int __ret = 0;							\
+	u32 tmp;							\
+									\
+	preempt_disable();						\
+	if (unlikely(get_user(tmp, uaddr) != 0))			\
+		__ret = -EFAULT;					\
+									\
+	if (__ret == 0 && tmp == oldval &&				\
+			unlikely(put_user(newval, uaddr) != 0))		\
+		__ret = -EFAULT;					\
+									\
+	*uval = tmp;							\
+	preempt_enable();						\
+									\
+	__ret;								\
+})
+#endif
+
+#else
+
+/*
+ * For multiprocessor machines, these macro should be overloaded with
+ * implementations based on arch-specific atomic instructions to ensure proper
+ * mutual exclusion
+ */
+#ifndef __futex_atomic_op_inuser
+#define __futex_atomic_op_inuser(op, oldval, uaddr, oparg)	\
+({								\
+	int __ret;						\
+	switch (op) {						\
+	case FUTEX_OP_SET:					\
+	case FUTEX_OP_ADD:					\
+	case FUTEX_OP_OR:					\
+	case FUTEX_OP_ANDN:					\
+	case FUTEX_OP_XOR:					\
+	default:						\
+		__ret = -ENOSYS;				\
+	}							\
+	__ret;							\
+})
+#endif
+
+#ifndef __futex_atomic_cmpxchg_inatomic
+#define __futex_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval)	\
+({									\
+	int __ret = -ENOSYS;						\
+	__ret;								\
+})
+#endif
+
+#endif
+
 /**
  * futex_atomic_op_inuser() - Atomic arithmetic operation with constant
  *			  argument and comparison of the previous
@@ -31,48 +133,15 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
 	int cmparg = (encoded_op << 20) >> 20;
-	int oldval, ret;
-	u32 tmp;
+	int oldval = 0, ret;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	preempt_disable();
-	pagefault_disable();
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
 
-	ret = -EFAULT;
-	if (unlikely(get_user(oldval, uaddr) != 0))
-		goto out_pagefault_enable;
-
-	ret = 0;
-	tmp = oldval;
-
-	switch (op) {
-	case FUTEX_OP_SET:
-		tmp = oparg;
-		break;
-	case FUTEX_OP_ADD:
-		tmp += oparg;
-		break;
-	case FUTEX_OP_OR:
-		tmp |= oparg;
-		break;
-	case FUTEX_OP_ANDN:
-		tmp &= ~oparg;
-		break;
-	case FUTEX_OP_XOR:
-		tmp ^= oparg;
-		break;
-	default:
-		ret = -ENOSYS;
-	}
-
-	if (ret == 0 && unlikely(put_user(tmp, uaddr) != 0))
-		ret = -EFAULT;
-
-out_pagefault_enable:
-	pagefault_enable();
-	preempt_enable();
+	ret = __futex_atomic_op_inuser(op, oldval, uaddr, oparg);
 
 	if (ret == 0) {
 		switch (cmp) {
@@ -103,76 +172,12 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
  */
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-			      u32 oldval, u32 newval)
+		u32 oldval, u32 newval)
 {
-	u32 val;
-
-	preempt_disable();
-	if (unlikely(get_user(val, uaddr) != 0)) {
-		preempt_enable();
-		return -EFAULT;
-	}
-
-	if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) {
-		preempt_enable();
-		return -EFAULT;
-	}
-
-	*uval = val;
-	preempt_enable();
-
-	return 0;
-}
-
-#else
-static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
-{
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();
-
-	switch (op) {
-	case FUTEX_OP_SET:
-	case FUTEX_OP_ADD:
-	case FUTEX_OP_OR:
-	case FUTEX_OP_ANDN:
-	case FUTEX_OP_XOR:
-	default:
-		ret = -ENOSYS;
-	}
-
-	pagefault_enable();
-
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
-	return ret;
-}
-
-static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-			      u32 oldval, u32 newval)
-{
-	return -ENOSYS;
+	return __futex_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval);
 }
 
-#endif /* CONFIG_SMP */
 #endif
-- 
2.10.0

^ permalink raw reply related

* [PATCH 0/2] make asm-generic/futex.h usable for more arch ports
From: Joel Porquet @ 2016-10-10  0:03 UTC (permalink / raw)
  To: linux-arm-kernel

Hi all,

I've had a patch on my shelf for a couple of years, from when I ported Linux on
a new processor architecture for an academic project, and thought I could send
it and let you decide if it's worth taking or not.

During my port, I basically modified the generic header "asm-generic/futex.h"
and made it into a more generic version so that I could include it in my code
and only redefine the necessary arch-specific bits.

Right now, most of the arch ports redefine their own "asm/futex.h" completely
although, for example for "futex_atomic_op_inuser()", they often share the exact
same preamble and epilogue and could benefit from some code refactoring.

My (short) series is made of two patches: 1/ refactoring "asm-generic/futex.h"
in order to make the arch-specific routines into overload-able macros that arch
ports can redefine when required, 2/ an example of how to use this refactoring
with the ARM port.

Let me know what you think.

Cheers,
Jo?l

Joel Porquet (2):
  asm-generic/futex.h: code refactoring
  arm: futex: Use asm-generic/futex.h instead of redefining the entire
    header

 arch/arm/include/asm/futex.h | 203 +++++++++++++++++----------------------
 include/asm-generic/futex.h  | 219 ++++++++++++++++++++++---------------------
 2 files changed, 196 insertions(+), 226 deletions(-)

-- 
2.10.0

^ permalink raw reply

* [PATCH v3] arm64: mm: move zero page from .bss to right before swapper_pg_dir
From: Mark Rutland @ 2016-10-09 23:10 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <CAKv+Gu-V+OKoeNFqvHvQOOFYi4VLm5mLKrmf9Z5oZY4KQkirsQ@mail.gmail.com>

On Fri, Oct 07, 2016 at 10:31:14AM +0100, Ard Biesheuvel wrote:
> On 12 September 2016 at 17:15, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> > Move the statically allocated zero page from the .bss section to right
> > before swapper_pg_dir. This allows us to refer to its physical address
> > by simply reading TTBR1_EL1 (which always points to swapper_pg_dir and
> > always has its ASID field cleared), and subtracting PAGE_SIZE.
> >
> > To protect the zero page from inadvertent modification, carve out a
> > segment that covers it as well as idmap_pg_dir[], and mark it read-only
> > in both the primary and the linear mappings of the kernel.

[...]

> > -       map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data);
> > +       map_kernel_segment(pgd, _data, __robss_start, PAGE_KERNEL,
> > +                          &vmlinux_data);
> > +       map_kernel_segment(pgd, __robss_start, __robss_end, PAGE_KERNEL_RO,
> > +                          &vmlinux_robss);
> 
> I realised it is actually unnecessary to map the idmap and the zero
> page into the kernel mapping, so we could drop this line.

Given that drivers use the zero page, I wouldn't be entirely surprised to see
phys_to_virt(virt_to_phys(zero_page)) happen indirectly, and the end result
read. Are we sure that doesn't happen anywhere?

For the idmap, I think we might walk that were we to take a fault (though
perhaps we don't). Otherwise, unless we add a sysfs walker for it I guess we
don't strictly need it in the linear map.

Thanks,
Mark.

^ permalink raw reply

* [PATCH 1/2] host: ehci-exynos: Convert to use the SET_SYSTEM_SLEEP_PM_OPS
From: Alan Stern @ 2016-10-09 21:17 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161009163446.GA9672@kozik-lap>

On Sun, 9 Oct 2016, Krzysztof Kozlowski wrote:

> On Sun, Oct 09, 2016 at 02:34:14PM +0000, Anand Moon wrote:
> > Move the ehci-exynos system PM callbacks within #ifdef CONFIG_PM_SLEEP
> > as to avoid them being build when not used. This also allows us to use the
> > SET_SYSTEM_SLEEP_PM_OPS macro which simplifies the code.
> > 
> > Signed-off-by: Anand Moon <linux.amoon@gmail.com>
> > ---
> >  drivers/usb/host/ehci-exynos.c | 14 ++++++--------
> >  1 file changed, 6 insertions(+), 8 deletions(-)
> > 
> > diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
> > index 42e5b66..1899900 100644
> > --- a/drivers/usb/host/ehci-exynos.c
> > +++ b/drivers/usb/host/ehci-exynos.c
> > @@ -251,7 +251,7 @@ static int exynos_ehci_remove(struct platform_device *pdev)
> >  	return 0;
> >  }
> >  
> > -#ifdef CONFIG_PM
> > +#ifdef CONFIG_PM_SLEEP
> 
> Does not look like an equivalent change. How will it behave in a config
> with !SUSPEND && !HIBERNATE && PM?

It's hard to say what Anand originally had in mind.  To me, it looks
like it will behave exactly the same as before, the only difference
being that the object image will not contain unused exynos_ehci_suspend
and exynos_ehci_resume routines.  And the compiler won't issue a 
warning at build time that the routines are unused.

Alan Stern

^ permalink raw reply

* [PATCH] mm/vmalloc: reduce the number of lazy_max_pages to reduce latency
From: Chris Wilson @ 2016-10-09 19:26 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <CAEi0qNnozbib-92NwWpUV=_YiiUHYGzzBuuY8kDZY9gaZm-W7Q@mail.gmail.com>

On Sun, Oct 09, 2016 at 12:00:31PM -0700, Joel Fernandes wrote:
> Ok. So I'll submit a patch with mutex for purge_lock and use
> cond_resched_lock for the vmap_area_lock as you suggested. I'll also
> drop the lazy_max_pages to 8MB as Andi suggested to reduce the lock
> hold time. Let me know if you have any objections.

The downside of using a mutex here though, is that we may be called
from contexts that cannot sleep (alloc_vmap_area), or reschedule for
that matter! If we change the notion of purged, we can forgo the mutex
in favour of spinning on the direct reclaim path. That just leaves the
complication of whether to use cond_resched_lock() or a lock around
the individual __free_vmap_area().
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre

^ permalink raw reply

* [PATCH 1/2] host: ehci-exynos: Convert to use the SET_SYSTEM_SLEEP_PM_OPS
From: Anand Moon @ 2016-10-09 19:01 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161009183933.GA15270@kozik-lap>

hi Krzysztof,

On 10 October 2016 at 00:09, Krzysztof Kozlowski <krzk@kernel.org> wrote:
> On Sun, Oct 09, 2016 at 11:57:59PM +0530, Anand Moon wrote:
>> hi Krzysztof,
>>
>> On 9 October 2016 at 22:57, Krzysztof Kozlowski <krzk@kernel.org> wrote:
>> > On Sun, Oct 09, 2016 at 10:45:40PM +0530, Anand Moon wrote:
>> >> Hi Krzysztof,
>> >>
>> >> On 9 October 2016 at 22:04, Krzysztof Kozlowski <krzk@kernel.org> wrote:
>> >> > On Sun, Oct 09, 2016 at 02:34:14PM +0000, Anand Moon wrote:
>> >> >> Move the ehci-exynos system PM callbacks within #ifdef CONFIG_PM_SLEEP
>> >> >> as to avoid them being build when not used. This also allows us to use the
>> >> >> SET_SYSTEM_SLEEP_PM_OPS macro which simplifies the code.
>> >> >>
>> >> >> Signed-off-by: Anand Moon <linux.amoon@gmail.com>
>> >> >> ---
>> >> >>  drivers/usb/host/ehci-exynos.c | 14 ++++++--------
>> >> >>  1 file changed, 6 insertions(+), 8 deletions(-)
>> >> >>
>> >> >> diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
>> >> >> index 42e5b66..1899900 100644
>> >> >> --- a/drivers/usb/host/ehci-exynos.c
>> >> >> +++ b/drivers/usb/host/ehci-exynos.c
>> >> >> @@ -251,7 +251,7 @@ static int exynos_ehci_remove(struct platform_device *pdev)
>> >> >>       return 0;
>> >> >>  }
>> >> >>
>> >> >> -#ifdef CONFIG_PM
>> >> >> +#ifdef CONFIG_PM_SLEEP
>> >> >
>> >> > Does not look like an equivalent change. How will it behave in a config
>> >> > with !SUSPEND && !HIBERNATE && PM?
>> >> >
>> >>
>> >> [snip]
>> >>
>> >> I just wanted to update suspend and resume callback to use
>> >> SET_SYSTEM_SLEEP_PM_OPS
>> >> as they are define under CONFIG_PM_SLEEP so I update above to avoid
>> >> compilation warning/error.
>> >
>> Apologize: for not understanding your question.
>>
>> > First of all you did not answer to my question, so let me rephrase into
>> > two:
>> > 1. Is the code equivalent?
>>
>> No CONFIG_PM and CONFIG_PM_SLEEP are different options.
>> But I could not disable CONFIG_PM_SLEEP option with either in exynos_defconfig
>
> So the code is not equivalent...
>
>>
>> CONFIG_PM_SLEEP=n or
>> # CONFIG_PM_SLEEP is not set
>>
>> > 2. What will be the output with !SUSPEND && !HIBERNATE && PM?
>>
>> #
>> # Power management options
>> #
>> # CONFIG_SUSPEND is not set
>> # CONFIG_HIBERNATION is not set
>> # CONFIG_PM is not set
>>
>> When CONFIG_SUSPEND and CONFIG_HIBERNATION are not set
>> CONFIG_PM is disabled and so is CONFIG_PM_SLEEP.
>
> In my config, the CONFIG_PM was enabled thus the code changes the
> functionality... Maybe this was intented but I really don't get it from
> the commit message or from your explanations here.
>
> Krzysztof

Ok I will keep the changes to use CONFIG_PM,
but use the SET_SYSTEM_SLEEP_PM_OPS option in V2 patch.
Is that ok.

-Best Regards
-Anand Moon

^ permalink raw reply

* [PATCH] mm/vmalloc: reduce the number of lazy_max_pages to reduce latency
From: Joel Fernandes @ 2016-10-09 19:00 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161009124242.GA2718@nuc-i3427.alporthouse.com>

On Sun, Oct 9, 2016 at 5:42 AM, Chris Wilson <chris@chris-wilson.co.uk> wrote:
[..]
>> > My understanding is that
>> >
>> > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
>> > index 91f44e78c516..3f7c6d6969ac 100644
>> > --- a/mm/vmalloc.c
>> > +++ b/mm/vmalloc.c
>> > @@ -626,7 +626,6 @@ void set_iounmap_nonlazy(void)
>> >  static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
>> >                                         int sync, int force_flush)
>> >  {
>> > -       static DEFINE_SPINLOCK(purge_lock);
>> >         struct llist_node *valist;
>> >         struct vmap_area *va;
>> >         struct vmap_area *n_va;
>> > @@ -637,12 +636,6 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
>> >          * should not expect such behaviour. This just simplifies locking for
>> >          * the case that isn't actually used at the moment anyway.
>> >          */
>> > -       if (!sync && !force_flush) {
>> > -               if (!spin_trylock(&purge_lock))
>> > -                       return;
>> > -       } else
>> > -               spin_lock(&purge_lock);
>> > -
>> >         if (sync)
>> >                 purge_fragmented_blocks_allcpus();
>> >
>> > @@ -667,7 +660,6 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
>> >                         __free_vmap_area(va);
>> >                 spin_unlock(&vmap_area_lock);
>> >         }
>> > -       spin_unlock(&purge_lock);
>> >  }
>> >
>> [..]
>> > should now be safe. That should significantly reduce the preempt-disabled
>> > section, I think.
>>
>> I believe that the purge_lock is supposed to prevent concurrent purges
>> from happening.
>>
>> For the case where if you have another concurrent overflow happen in
>> alloc_vmap_area() between the spin_unlock and purge :
>>
>> spin_unlock(&vmap_area_lock);
>> if (!purged)
>>    purge_vmap_area_lazy();
>>
>> Then the 2 purges would happen at the same time and could subtract
>> vmap_lazy_nr twice.
>
> That itself is not the problem, as each instance of
> __purge_vmap_area_lazy() operates on its own freelist, and so there will
> be no double accounting.
>
> However, removing the lock removes the serialisation which does mean
> that alloc_vmap_area() will not block on another thread conducting the
> purge, and so it will try to reallocate before that is complete and the
> free area made available. It also means that we are doing the
> atomic_sub(vmap_lazy_nr) too early.
>
> That supports making the outer lock a mutex as you suggested. But I think
> cond_resched_lock() is better for the vmap_area_lock (just because it
> turns out to be an expensive loop and we may want the reschedule).
> -Chris

Ok. So I'll submit a patch with mutex for purge_lock and use
cond_resched_lock for the vmap_area_lock as you suggested. I'll also
drop the lazy_max_pages to 8MB as Andi suggested to reduce the lock
hold time. Let me know if you have any objections.

Thanks,
Joel

^ permalink raw reply

* [PATCH 1/2] host: ehci-exynos: Convert to use the SET_SYSTEM_SLEEP_PM_OPS
From: Krzysztof Kozlowski @ 2016-10-09 18:39 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <CANAwSgS9tbhPK4jwoqR6G1=iKAo15H3Dizu3Lp03KMGbQ4aj9A@mail.gmail.com>

On Sun, Oct 09, 2016 at 11:57:59PM +0530, Anand Moon wrote:
> hi Krzysztof,
> 
> On 9 October 2016 at 22:57, Krzysztof Kozlowski <krzk@kernel.org> wrote:
> > On Sun, Oct 09, 2016 at 10:45:40PM +0530, Anand Moon wrote:
> >> Hi Krzysztof,
> >>
> >> On 9 October 2016 at 22:04, Krzysztof Kozlowski <krzk@kernel.org> wrote:
> >> > On Sun, Oct 09, 2016 at 02:34:14PM +0000, Anand Moon wrote:
> >> >> Move the ehci-exynos system PM callbacks within #ifdef CONFIG_PM_SLEEP
> >> >> as to avoid them being build when not used. This also allows us to use the
> >> >> SET_SYSTEM_SLEEP_PM_OPS macro which simplifies the code.
> >> >>
> >> >> Signed-off-by: Anand Moon <linux.amoon@gmail.com>
> >> >> ---
> >> >>  drivers/usb/host/ehci-exynos.c | 14 ++++++--------
> >> >>  1 file changed, 6 insertions(+), 8 deletions(-)
> >> >>
> >> >> diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
> >> >> index 42e5b66..1899900 100644
> >> >> --- a/drivers/usb/host/ehci-exynos.c
> >> >> +++ b/drivers/usb/host/ehci-exynos.c
> >> >> @@ -251,7 +251,7 @@ static int exynos_ehci_remove(struct platform_device *pdev)
> >> >>       return 0;
> >> >>  }
> >> >>
> >> >> -#ifdef CONFIG_PM
> >> >> +#ifdef CONFIG_PM_SLEEP
> >> >
> >> > Does not look like an equivalent change. How will it behave in a config
> >> > with !SUSPEND && !HIBERNATE && PM?
> >> >
> >>
> >> [snip]
> >>
> >> I just wanted to update suspend and resume callback to use
> >> SET_SYSTEM_SLEEP_PM_OPS
> >> as they are define under CONFIG_PM_SLEEP so I update above to avoid
> >> compilation warning/error.
> >
> Apologize: for not understanding your question.
> 
> > First of all you did not answer to my question, so let me rephrase into
> > two:
> > 1. Is the code equivalent?
> 
> No CONFIG_PM and CONFIG_PM_SLEEP are different options.
> But I could not disable CONFIG_PM_SLEEP option with either in exynos_defconfig

So the code is not equivalent...

> 
> CONFIG_PM_SLEEP=n or
> # CONFIG_PM_SLEEP is not set
> 
> > 2. What will be the output with !SUSPEND && !HIBERNATE && PM?
> 
> #
> # Power management options
> #
> # CONFIG_SUSPEND is not set
> # CONFIG_HIBERNATION is not set
> # CONFIG_PM is not set
> 
> When CONFIG_SUSPEND and CONFIG_HIBERNATION are not set
> CONFIG_PM is disabled and so is CONFIG_PM_SLEEP.

In my config, the CONFIG_PM was enabled thus the code changes the
functionality... Maybe this was intented but I really don't get it from
the commit message or from your explanations here.

Krzysztof

^ permalink raw reply

* [PATCH 1/2] host: ehci-exynos: Convert to use the SET_SYSTEM_SLEEP_PM_OPS
From: Anand Moon @ 2016-10-09 18:27 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161009172757.GA11916@kozik-lap>

hi Krzysztof,

On 9 October 2016 at 22:57, Krzysztof Kozlowski <krzk@kernel.org> wrote:
> On Sun, Oct 09, 2016 at 10:45:40PM +0530, Anand Moon wrote:
>> Hi Krzysztof,
>>
>> On 9 October 2016 at 22:04, Krzysztof Kozlowski <krzk@kernel.org> wrote:
>> > On Sun, Oct 09, 2016 at 02:34:14PM +0000, Anand Moon wrote:
>> >> Move the ehci-exynos system PM callbacks within #ifdef CONFIG_PM_SLEEP
>> >> as to avoid them being build when not used. This also allows us to use the
>> >> SET_SYSTEM_SLEEP_PM_OPS macro which simplifies the code.
>> >>
>> >> Signed-off-by: Anand Moon <linux.amoon@gmail.com>
>> >> ---
>> >>  drivers/usb/host/ehci-exynos.c | 14 ++++++--------
>> >>  1 file changed, 6 insertions(+), 8 deletions(-)
>> >>
>> >> diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
>> >> index 42e5b66..1899900 100644
>> >> --- a/drivers/usb/host/ehci-exynos.c
>> >> +++ b/drivers/usb/host/ehci-exynos.c
>> >> @@ -251,7 +251,7 @@ static int exynos_ehci_remove(struct platform_device *pdev)
>> >>       return 0;
>> >>  }
>> >>
>> >> -#ifdef CONFIG_PM
>> >> +#ifdef CONFIG_PM_SLEEP
>> >
>> > Does not look like an equivalent change. How will it behave in a config
>> > with !SUSPEND && !HIBERNATE && PM?
>> >
>>
>> [snip]
>>
>> I just wanted to update suspend and resume callback to use
>> SET_SYSTEM_SLEEP_PM_OPS
>> as they are define under CONFIG_PM_SLEEP so I update above to avoid
>> compilation warning/error.
>
Apologize: for not understanding your question.

> First of all you did not answer to my question, so let me rephrase into
> two:
> 1. Is the code equivalent?

No CONFIG_PM and CONFIG_PM_SLEEP are different options.
But I could not disable CONFIG_PM_SLEEP option with either in exynos_defconfig

CONFIG_PM_SLEEP=n or
# CONFIG_PM_SLEEP is not set

> 2. What will be the output with !SUSPEND && !HIBERNATE && PM?

#
# Power management options
#
# CONFIG_SUSPEND is not set
# CONFIG_HIBERNATION is not set
# CONFIG_PM is not set

When CONFIG_SUSPEND and CONFIG_HIBERNATION are not set
CONFIG_PM is disabled and so is CONFIG_PM_SLEEP.

Best Regards
-Anand Moon

>
> You didn't mention compilation warning/error in message commit so I do
> not know what you are thinking about...
>
> Best regards,
> Krzysztof

^ permalink raw reply

* [PATCH v3 00/17] pinctrl: exynos/samsung: Add header with values used for configuration
From: Krzysztof Kozlowski @ 2016-10-09 17:52 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <CA+Ln22GgjF=wVzL3fF7xzvOZtJpiZjVcFTrvDQAu6T2RCfY89g@mail.gmail.com>

On Mon, Oct 10, 2016 at 02:49:01AM +0900, Tomasz Figa wrote:
> 2016-10-10 1:39 GMT+09:00 Krzysztof Kozlowski <krzk@kernel.org>:
> > On Sun, Oct 09, 2016 at 04:04:11PM +0900, Tomasz Figa wrote:
> >> Hi Krzysztof,
> >>
> >> 2016-09-04 20:04 GMT+09:00 Krzysztof Kozlowski <krzk@kernel.org>:
> >> >
> >> > Hi,
> >> >
> >> > Changes since v2
> >> > ================
> >> > 1. Combine separate patchsets into one. Previously I sent separately the fixes
> >> >    and changes for S3C platforms.
> >> > 2. Fix issues pointed during review.
> >> > 3. Add review tags.
> >> >
> >> > Changes since v1
> >> > ================
> >> > 1. Follow Arnd's suggestion about moving the macros to common place.
> >> > 2. Subjects: replace "GPIO" with "pinctrl".
> >> > 3. There were some major changes here so I did not add Javier's
> >> >    reviewed-by and tested-by tags.
> >> >
> >> > Merging
> >> > =======
> >> > Patches #1 and #2 should probably go through pinctrl tree. In that case I would
> >> > appreciate a stable branch/tag so DTS could base on top of it.
> >> >
> >> > Goal
> >> > ====
> >> > Increase readability:
> >> >         uart0_data: uart0-data {
> >> >                 samsung,pins = "gpa0-0", "gpa0-1";
> >> > -               samsung,pin-function = <2>;
> >> > -               samsung,pin-pud = <0>;
> >> > -               samsung,pin-drv = <0>;
> >> > +               samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
> >> > +               samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
> >> > +               samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
> >>
> >> I like the idea, thanks for cleaning this up. However I'd like to
> >> bikeshed the prefix a bit. Since the properties are already prefixed
> >> by "samsung,", I think it would make much more sense to also prefix
> >> the generic values with "SAMSUNG_". Of course for soc/family-specific
> >> values, the soc/family name prefix sounds right.
> >
> > I am lost. Sorry, I don't get what kind of final prefixes you would like
> > to have.
> >
> > SAMSUNG_EXYNOS4_PIN_DRV_LV1
> > SAMSUNG_EXYNOS5260_PIN_DRV_LV1
> > ?
> 
> For SoC-specific definitions:
> 
> EXYNOS4_PIN_DRV_LV1
> EXYNOS5260_PIN_DRV_LV1

ok... so no change needed in my patch.

> 
> >
> >> Similarly for rest of the value names, such as SAMSUNG_PIN_PUD instead
> >> of SAMSUNG_PIN_PULL, which obviously sounds more like correct English,
> >> however hurts the consistency and could confuse the people writing new
> >> dts files.
> >
> > SAMSUNG_S3C64XX_PIN_PUD_NONE
> > SAMSUNG_EXYNOS_PIN_PUD_NONE
> 
> For definitions common for the whole Samsung pinctrl driver:
> 
> SAMSUNG_PIN_PUD_NONE

These are not the same. The "none" is the same but rest is not.

> But actually I think I missed the fact that there is almost no common
> definitions. Is that correct? Was that the missing part of my
> understanding?

Yes. The only common definition for all Samsung SoCs would be the
function of a pin. On the other hand this will bring inconsistency:
everything prefixed with SoC except the function.

Best regards,
Krzysztof

^ permalink raw reply

* [PATCH v3 00/17] pinctrl: exynos/samsung: Add header with values used for configuration
From: Tomasz Figa @ 2016-10-09 17:49 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161009163910.GB9672@kozik-lap>

2016-10-10 1:39 GMT+09:00 Krzysztof Kozlowski <krzk@kernel.org>:
> On Sun, Oct 09, 2016 at 04:04:11PM +0900, Tomasz Figa wrote:
>> Hi Krzysztof,
>>
>> 2016-09-04 20:04 GMT+09:00 Krzysztof Kozlowski <krzk@kernel.org>:
>> >
>> > Hi,
>> >
>> > Changes since v2
>> > ================
>> > 1. Combine separate patchsets into one. Previously I sent separately the fixes
>> >    and changes for S3C platforms.
>> > 2. Fix issues pointed during review.
>> > 3. Add review tags.
>> >
>> > Changes since v1
>> > ================
>> > 1. Follow Arnd's suggestion about moving the macros to common place.
>> > 2. Subjects: replace "GPIO" with "pinctrl".
>> > 3. There were some major changes here so I did not add Javier's
>> >    reviewed-by and tested-by tags.
>> >
>> > Merging
>> > =======
>> > Patches #1 and #2 should probably go through pinctrl tree. In that case I would
>> > appreciate a stable branch/tag so DTS could base on top of it.
>> >
>> > Goal
>> > ====
>> > Increase readability:
>> >         uart0_data: uart0-data {
>> >                 samsung,pins = "gpa0-0", "gpa0-1";
>> > -               samsung,pin-function = <2>;
>> > -               samsung,pin-pud = <0>;
>> > -               samsung,pin-drv = <0>;
>> > +               samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
>> > +               samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
>> > +               samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
>>
>> I like the idea, thanks for cleaning this up. However I'd like to
>> bikeshed the prefix a bit. Since the properties are already prefixed
>> by "samsung,", I think it would make much more sense to also prefix
>> the generic values with "SAMSUNG_". Of course for soc/family-specific
>> values, the soc/family name prefix sounds right.
>
> I am lost. Sorry, I don't get what kind of final prefixes you would like
> to have.
>
> SAMSUNG_EXYNOS4_PIN_DRV_LV1
> SAMSUNG_EXYNOS5260_PIN_DRV_LV1
> ?

For SoC-specific definitions:

EXYNOS4_PIN_DRV_LV1
EXYNOS5260_PIN_DRV_LV1

>
>> Similarly for rest of the value names, such as SAMSUNG_PIN_PUD instead
>> of SAMSUNG_PIN_PULL, which obviously sounds more like correct English,
>> however hurts the consistency and could confuse the people writing new
>> dts files.
>
> SAMSUNG_S3C64XX_PIN_PUD_NONE
> SAMSUNG_EXYNOS_PIN_PUD_NONE

For definitions common for the whole Samsung pinctrl driver:

SAMSUNG_PIN_PUD_NONE

...

But actually I think I missed the fact that there is almost no common
definitions. Is that correct? Was that the missing part of my
understanding?

Best regards,
Tomasz

^ permalink raw reply

* [PATCH 6/6] crypto: arm64/aes-neon - fix for big endian
From: Ard Biesheuvel @ 2016-10-09 17:42 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1476034945-9186-1-git-send-email-ard.biesheuvel@linaro.org>

The AES implementation using pure NEON instructions relies on the generic
AES key schedule generation routines, which store the round keys as arrays
of 32-bit quantities stored in memory using native endianness. This means
we should refer to these round keys using 4x4 loads rather than 16x1 loads.
In addition, the ShiftRows tables are loading using a single scalar load,
which is also affected by endianness, so emit these tables in the correct
order depending on whether we are building for big endian or not.

Fixes: 49788fe2a128 ("arm64/crypto: AES-ECB/CBC/CTR/XTS using ARMv8 NEON and Crypto Extensions")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/aes-neon.S | 25 ++++++++++++--------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index b93170e1cc93..85f07ead7c5c 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #define AES_ENTRY(func)		ENTRY(neon_ ## func)
 #define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
@@ -83,13 +84,13 @@
 	.endm
 
 	.macro		do_block, enc, in, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
 	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
 	sub_bytes	\in
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -229,7 +230,7 @@
 	.endm
 
 	.macro		do_block_2x, enc, in0, in1 rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -237,7 +238,7 @@
 	sub_bytes_2x	\in0, \in1
 	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -254,7 +255,7 @@
 	.endm
 
 	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -266,7 +267,7 @@
 	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -306,12 +307,16 @@
 	.text
 	.align		4
 .LForward_ShiftRows:
-	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
-	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+CPU_LE(	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3	)
+CPU_LE(	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb	)
+CPU_BE(	.byte		0xb, 0x6, 0x1, 0xc, 0x7, 0x2, 0xd, 0x8	)
+CPU_BE(	.byte		0x3, 0xe, 0x9, 0x4, 0xf, 0xa, 0x5, 0x0	)
 
 .LReverse_ShiftRows:
-	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
-	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+CPU_LE(	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb	)
+CPU_LE(	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3	)
+CPU_BE(	.byte		0x3, 0x6, 0x9, 0xc, 0xf, 0x2, 0x5, 0x8	)
+CPU_BE(	.byte		0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0	)
 
 .LForward_Sbox:
 	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
-- 
2.7.4

^ permalink raw reply related

* [PATCH 5/6] crypto: arm64/aes-ccm-ce: fix for big endian
From: Ard Biesheuvel @ 2016-10-09 17:42 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1476034945-9186-1-git-send-email-ard.biesheuvel@linaro.org>

The AES-CCM implementation that uses ARMv8 Crypto Extensions instructions
refers to the AES round keys as pairs of 64-bit quantities, which causes
failures when building the code for big endian. In addition, it byte swaps
the input counter unconditionally, while this is only required for little
endian builds. So fix both issues.

Fixes: 12ac3efe74f8 ("arm64/crypto: use crypto instructions to generate AES key schedule")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/aes-ce-ccm-core.S | 53 ++++++++++----------
 1 file changed, 27 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index a2a7fbcacc14..3363560c79b7 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 	.text
 	.arch	armv8-a+crypto
@@ -19,7 +20,7 @@
 	 */
 ENTRY(ce_aes_ccm_auth_data)
 	ldr	w8, [x3]			/* leftover from prev round? */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cbz	w8, 1f
 	sub	w8, w8, #16
 	eor	v1.16b, v1.16b, v1.16b
@@ -31,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	8f				/* out of input? */
 	cbnz	w8, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.2d}, [x4]			/* load first round key */
+1:	ld1	{v3.16b}, [x4]			/* load first round key */
 	prfm	pldl1strm, [x1]
 	cmp	w5, #12				/* which key size? */
 	add	x6, x4, #16
@@ -41,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data)
 	mov	v5.16b, v3.16b
 	b	4f
 2:	mov	v4.16b, v3.16b
-	ld1	{v5.2d}, [x6], #16		/* load 2nd round key */
+	ld1	{v5.16b}, [x6], #16		/* load 2nd round key */
 3:	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
-4:	ld1	{v3.2d}, [x6], #16		/* load next round key */
+4:	ld1	{v3.16b}, [x6], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
-5:	ld1	{v4.2d}, [x6], #16		/* load next round key */
+5:	ld1	{v4.16b}, [x6], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
-	ld1	{v5.2d}, [x6], #16		/* load next round key */
+	ld1	{v5.16b}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
 	subs	w2, w2, #16			/* last data? */
@@ -60,7 +61,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	ld1	{v1.16b}, [x1], #16		/* load next input block */
 	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
 	bne	1b
-6:	st1	{v0.2d}, [x0]			/* store mac */
+6:	st1	{v0.16b}, [x0]			/* store mac */
 	beq	10f
 	adds	w2, w2, #16
 	beq	10f
@@ -79,7 +80,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.2d}, [x0]
+	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
@@ -89,27 +90,27 @@ ENDPROC(ce_aes_ccm_auth_data)
 	 * 			 u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_final)
-	ld1	{v3.2d}, [x2], #16		/* load first round key */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v3.16b}, [x2], #16		/* load first round key */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cmp	w3, #12				/* which key size? */
 	sub	w3, w3, #2			/* modified # of rounds */
-	ld1	{v1.2d}, [x1]			/* load 1st ctriv */
+	ld1	{v1.16b}, [x1]			/* load 1st ctriv */
 	bmi	0f
 	bne	3f
 	mov	v5.16b, v3.16b
 	b	2f
 0:	mov	v4.16b, v3.16b
-1:	ld1	{v5.2d}, [x2], #16		/* load next round key */
+1:	ld1	{v5.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
+2:	ld1	{v3.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
+3:	ld1	{v4.16b}, [x2], #16		/* load next round key */
 	subs	w3, w3, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
@@ -120,47 +121,47 @@ ENTRY(ce_aes_ccm_final)
 	aese	v1.16b, v4.16b
 	/* final round key cancels out */
 	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
-	st1	{v0.2d}, [x0]			/* store result */
+	st1	{v0.16b}, [x0]			/* store result */
 	ret
 ENDPROC(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
 	ldr	x8, [x6, #8]			/* load lower ctr */
-	ld1	{v0.2d}, [x5]			/* load mac */
-	rev	x8, x8				/* keep swabbed ctr in reg */
+	ld1	{v0.16b}, [x5]			/* load mac */
+CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
-	ld1	{v1.1d}, [x6]			/* load upper ctr */
+	ld1	{v1.8b}, [x6]			/* load upper ctr */
 	prfm	pldl1strm, [x1]
 	add	x8, x8, #1
 	rev	x9, x8
 	cmp	w4, #12				/* which key size? */
 	sub	w7, w4, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.2d}, [x3]			/* load first round key */
+	ld1	{v3.16b}, [x3]			/* load first round key */
 	add	x10, x3, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
 	b	3f
 1:	mov	v4.16b, v3.16b
-	ld1	{v5.2d}, [x10], #16		/* load 2nd round key */
+	ld1	{v5.16b}, [x10], #16		/* load 2nd round key */
 2:	/* inner loop: 3 rounds, 2x interleaved */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
+3:	ld1	{v3.16b}, [x10], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
+4:	ld1	{v4.16b}, [x10], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v3.16b
 	aesmc	v1.16b, v1.16b
-	ld1	{v5.2d}, [x10], #16		/* load next round key */
+	ld1	{v5.16b}, [x10], #16		/* load next round key */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b
@@ -177,14 +178,14 @@ ENDPROC(ce_aes_ccm_final)
 	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
 	st1	{v1.16b}, [x0], #16		/* write output block */
 	bne	0b
-	rev	x8, x8
-	st1	{v0.2d}, [x5]			/* store mac */
+CPU_LE(	rev	x8, x8			)
+	st1	{v0.16b}, [x5]			/* store mac */
 	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
 5:	ret
 
 6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
 	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
-	st1	{v0.2d}, [x5]			/* store mac */
+	st1	{v0.16b}, [x5]			/* store mac */
 	add	w2, w2, #16			/* process partial tail block */
 7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
 	umov	w6, v1.b[0]			/* get top crypted ctr byte */
-- 
2.7.4

^ permalink raw reply related

* [PATCH 4/6] crypto: arm64/sha2-ce - fix for big endian
From: Ard Biesheuvel @ 2016-10-09 17:42 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1476034945-9186-1-git-send-email-ard.biesheuvel@linaro.org>

The SHA256 digest is an array of 8 32-bit quantities, so we should refer
to them as such in order for this code to work correctly when built for
big endian. So replace 16 byte scalar loads and stores with 4x32 vector
ones where appropriate.

Fixes: 6ba6c74dfc6b ("arm64/crypto: SHA-224/SHA-256 using ARMv8 Crypto Extensions")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/sha2-ce-core.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 5df9d9d470ad..01cfee066837 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -85,7 +85,7 @@ ENTRY(sha2_ce_transform)
 	ld1		{v12.4s-v15.4s}, [x8]
 
 	/* load state */
-	ldp		dga, dgb, [x0]
+	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
 	ldr		w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
@@ -148,6 +148,6 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	b		1b
 
 	/* store new state */
-3:	stp		dga, dgb, [x0]
+3:	st1		{dgav.4s, dgbv.4s}, [x0]
 	ret
 ENDPROC(sha2_ce_transform)
-- 
2.7.4

^ permalink raw reply related

* [PATCH 3/6] crypto: arm64/sha1-ce - fix for big endian
From: Ard Biesheuvel @ 2016-10-09 17:42 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1476034945-9186-1-git-send-email-ard.biesheuvel@linaro.org>

The SHA1 digest is an array of 5 32-bit quantities, so we should refer
to them as such in order for this code to work correctly when built for
big endian. So replace 16 byte scalar loads and stores with 4x4 vector
ones where appropriate.

Fixes: 2c98833a42cd ("arm64/crypto: SHA-1 using ARMv8 Crypto Extensions")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/sha1-ce-core.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 033aae6d732a..c98e7e849f06 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -78,7 +78,7 @@ ENTRY(sha1_ce_transform)
 	ld1r		{k3.4s}, [x6]
 
 	/* load state */
-	ldr		dga, [x0]
+	ld1		{dgav.4s}, [x0]
 	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
@@ -144,7 +144,7 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	b		1b
 
 	/* store new state */
-3:	str		dga, [x0]
+3:	st1		{dgav.4s}, [x0]
 	str		dgb, [x0, #16]
 	ret
 ENDPROC(sha1_ce_transform)
-- 
2.7.4

^ permalink raw reply related

* [PATCH 2/6] crypto: arm64/ghash-ce - fix for big endian
From: Ard Biesheuvel @ 2016-10-09 17:42 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1476034945-9186-1-git-send-email-ard.biesheuvel@linaro.org>

The GHASH key and digest are both pairs of 64-bit quantities, but the
GHASH code does not always refer to them as such, causing failures when
built for big endian. So replace the 16x1 loads and stores with 2x8 ones.

Fixes: b913a6404ce2 ("arm64/crypto: improve performance of GHASH algorithm")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/ghash-ce-core.S | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index dc457015884e..f0bb9f0b524f 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -29,8 +29,8 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{SHASH.16b}, [x3]
-	ld1		{XL.16b}, [x1]
+	ld1		{SHASH.2d}, [x3]
+	ld1		{XL.2d}, [x1]
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	shl		MASK.2d, MASK.2d, #57
@@ -74,6 +74,6 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	cbnz		w0, 0b
 
-	st1		{XL.16b}, [x1]
+	st1		{XL.2d}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)
-- 
2.7.4

^ permalink raw reply related

* [PATCH 1/6] crypto: arm64/aes-ce - fix for big endian
From: Ard Biesheuvel @ 2016-10-09 17:42 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1476034945-9186-1-git-send-email-ard.biesheuvel@linaro.org>

The core AES cipher implementation that uses ARMv8 Crypto Extensions
instructions erroneously loads the round keys as 64-bit quantities,
which causes the algorithm to fail when built for big endian. In
addition, the key schedule generation routine fails to take endianness
into account as well, when loading the combining the input key with
the round constants. So fix both issues.

Fixes: 12ac3efe74f8 ("arm64/crypto: use crypto instructions to generate AES key schedule")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/aes-ce-cipher.c | 25 ++++++++++++--------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
index f7bd9bf0bbb3..50d9fe11d0c8 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -47,24 +47,24 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aese	v0.16b, v2.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aese	v0.16b, v3.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aese	v0.16b, v1.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aese	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -92,24 +92,24 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aesd	v0.16b, v2.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aesd	v0.16b, v3.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aesd	v0.16b, v1.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aesd	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -173,7 +173,12 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
+#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+#else
+		rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^
+			 rki[0];
+#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
-- 
2.7.4

^ permalink raw reply related

* [PATCH 0/6] crypto: arm64 - big endian fixes
From: Ard Biesheuvel @ 2016-10-09 17:42 UTC (permalink / raw)
  To: linux-arm-kernel

As it turns out, none of the accelerated crypto routines under arch/arm64/crypto
currently work, or have ever worked correctly when built for big endian. So this
series fixes all of them.

Each of these patches carries a fixes tag, and could be backported to stable.
However, for patches #1 and #5, the fixes tag denotes the oldest commit that the
fix is compatible with, not the patch that introduced the algorithm. This is due
to the fact that the key schedules are incompatible between generic AES and the
arm64 Crypto Extensions implementation (but only when building for big endian)
This is not a problem in practice, but it does mean that the AES-CCM and AES in
EBC/CBC/CTR/XTS mode implementations before v3.19 require a different fix, i.e.,
one that is compatible with the generic AES key schedule generation code (which
it currently no longer uses)

In any case, please apply with cc to stable.

Ard Biesheuvel (6):
  crypto: arm64/aes-ce - fix for big endian
  crypto: arm64/ghash-ce - fix for big endian
  crypto: arm64/sha1-ce - fix for big endian
  crypto: arm64/sha2-ce - fix for big endian
  crypto: arm64/aes-ccm-ce: fix for big endian
  crypto: arm64/aes-neon - fix for big endian

 arch/arm64/crypto/aes-ce-ccm-core.S | 53 ++++++++++----------
 arch/arm64/crypto/aes-ce-cipher.c   | 25 +++++----
 arch/arm64/crypto/aes-neon.S        | 25 +++++----
 arch/arm64/crypto/ghash-ce-core.S   |  6 +--
 arch/arm64/crypto/sha1-ce-core.S    |  4 +-
 arch/arm64/crypto/sha2-ce-core.S    |  4 +-
 6 files changed, 64 insertions(+), 53 deletions(-)

-- 
2.7.4

^ permalink raw reply

* [PATCH 1/2] host: ehci-exynos: Convert to use the SET_SYSTEM_SLEEP_PM_OPS
From: Krzysztof Kozlowski @ 2016-10-09 17:27 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <CANAwSgSr6-0x47=0P_NCiGCv=FSZR9dNT89JpY=9R_32U8HywQ@mail.gmail.com>

On Sun, Oct 09, 2016 at 10:45:40PM +0530, Anand Moon wrote:
> Hi Krzysztof,
> 
> On 9 October 2016 at 22:04, Krzysztof Kozlowski <krzk@kernel.org> wrote:
> > On Sun, Oct 09, 2016 at 02:34:14PM +0000, Anand Moon wrote:
> >> Move the ehci-exynos system PM callbacks within #ifdef CONFIG_PM_SLEEP
> >> as to avoid them being build when not used. This also allows us to use the
> >> SET_SYSTEM_SLEEP_PM_OPS macro which simplifies the code.
> >>
> >> Signed-off-by: Anand Moon <linux.amoon@gmail.com>
> >> ---
> >>  drivers/usb/host/ehci-exynos.c | 14 ++++++--------
> >>  1 file changed, 6 insertions(+), 8 deletions(-)
> >>
> >> diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
> >> index 42e5b66..1899900 100644
> >> --- a/drivers/usb/host/ehci-exynos.c
> >> +++ b/drivers/usb/host/ehci-exynos.c
> >> @@ -251,7 +251,7 @@ static int exynos_ehci_remove(struct platform_device *pdev)
> >>       return 0;
> >>  }
> >>
> >> -#ifdef CONFIG_PM
> >> +#ifdef CONFIG_PM_SLEEP
> >
> > Does not look like an equivalent change. How will it behave in a config
> > with !SUSPEND && !HIBERNATE && PM?
> >
> 
> [snip]
> 
> I just wanted to update suspend and resume callback to use
> SET_SYSTEM_SLEEP_PM_OPS
> as they are define under CONFIG_PM_SLEEP so I update above to avoid
> compilation warning/error.

First of all you did not answer to my question, so let me rephrase into
two:
1. Is the code equivalent?
2. What will be the output with !SUSPEND && !HIBERNATE && PM?

You didn't mention compilation warning/error in message commit so I do
not know what you are thinking about...

Best regards,
Krzysztof

^ permalink raw reply

* [PATCH 1/2] host: ehci-exynos: Convert to use the SET_SYSTEM_SLEEP_PM_OPS
From: Anand Moon @ 2016-10-09 17:15 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <20161009163446.GA9672@kozik-lap>

Hi Krzysztof,

On 9 October 2016 at 22:04, Krzysztof Kozlowski <krzk@kernel.org> wrote:
> On Sun, Oct 09, 2016 at 02:34:14PM +0000, Anand Moon wrote:
>> Move the ehci-exynos system PM callbacks within #ifdef CONFIG_PM_SLEEP
>> as to avoid them being build when not used. This also allows us to use the
>> SET_SYSTEM_SLEEP_PM_OPS macro which simplifies the code.
>>
>> Signed-off-by: Anand Moon <linux.amoon@gmail.com>
>> ---
>>  drivers/usb/host/ehci-exynos.c | 14 ++++++--------
>>  1 file changed, 6 insertions(+), 8 deletions(-)
>>
>> diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
>> index 42e5b66..1899900 100644
>> --- a/drivers/usb/host/ehci-exynos.c
>> +++ b/drivers/usb/host/ehci-exynos.c
>> @@ -251,7 +251,7 @@ static int exynos_ehci_remove(struct platform_device *pdev)
>>       return 0;
>>  }
>>
>> -#ifdef CONFIG_PM
>> +#ifdef CONFIG_PM_SLEEP
>
> Does not look like an equivalent change. How will it behave in a config
> with !SUSPEND && !HIBERNATE && PM?
>

[snip]

I just wanted to update suspend and resume callback to use
SET_SYSTEM_SLEEP_PM_OPS
as they are define under CONFIG_PM_SLEEP so I update above to avoid
compilation warning/error.

http://lxr.free-electrons.com/source/include/linux/pm.h#L321

-Best Regards
Anand Moon

^ permalink raw reply

* [PATCH v3 00/17] pinctrl: exynos/samsung: Add header with values used for configuration
From: Krzysztof Kozlowski @ 2016-10-09 16:39 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <CA+Ln22Eotn=dLyA8KYT_6Fnwvp1sTSxzP8DepAFB2P8EUMME6Q@mail.gmail.com>

On Sun, Oct 09, 2016 at 04:04:11PM +0900, Tomasz Figa wrote:
> Hi Krzysztof,
> 
> 2016-09-04 20:04 GMT+09:00 Krzysztof Kozlowski <krzk@kernel.org>:
> >
> > Hi,
> >
> > Changes since v2
> > ================
> > 1. Combine separate patchsets into one. Previously I sent separately the fixes
> >    and changes for S3C platforms.
> > 2. Fix issues pointed during review.
> > 3. Add review tags.
> >
> > Changes since v1
> > ================
> > 1. Follow Arnd's suggestion about moving the macros to common place.
> > 2. Subjects: replace "GPIO" with "pinctrl".
> > 3. There were some major changes here so I did not add Javier's
> >    reviewed-by and tested-by tags.
> >
> > Merging
> > =======
> > Patches #1 and #2 should probably go through pinctrl tree. In that case I would
> > appreciate a stable branch/tag so DTS could base on top of it.
> >
> > Goal
> > ====
> > Increase readability:
> >         uart0_data: uart0-data {
> >                 samsung,pins = "gpa0-0", "gpa0-1";
> > -               samsung,pin-function = <2>;
> > -               samsung,pin-pud = <0>;
> > -               samsung,pin-drv = <0>;
> > +               samsung,pin-function = <EXYNOS_PIN_FUNC_2>;
> > +               samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
> > +               samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
> 
> I like the idea, thanks for cleaning this up. However I'd like to
> bikeshed the prefix a bit. Since the properties are already prefixed
> by "samsung,", I think it would make much more sense to also prefix
> the generic values with "SAMSUNG_". Of course for soc/family-specific
> values, the soc/family name prefix sounds right.

I am lost. Sorry, I don't get what kind of final prefixes you would like
to have.

SAMSUNG_EXYNOS4_PIN_DRV_LV1
SAMSUNG_EXYNOS5260_PIN_DRV_LV1
?

> Similarly for rest of the value names, such as SAMSUNG_PIN_PUD instead
> of SAMSUNG_PIN_PULL, which obviously sounds more like correct English,
> however hurts the consistency and could confuse the people writing new
> dts files.

SAMSUNG_S3C64XX_PIN_PUD_NONE
SAMSUNG_EXYNOS_PIN_PUD_NONE

?

Best regards,
Krzysztof

^ permalink raw reply

* [PATCH 1/2] host: ehci-exynos: Convert to use the SET_SYSTEM_SLEEP_PM_OPS
From: Krzysztof Kozlowski @ 2016-10-09 16:34 UTC (permalink / raw)
  To: linux-arm-kernel
In-Reply-To: <1476023655-3232-1-git-send-email-linux.amoon@gmail.com>

On Sun, Oct 09, 2016 at 02:34:14PM +0000, Anand Moon wrote:
> Move the ehci-exynos system PM callbacks within #ifdef CONFIG_PM_SLEEP
> as to avoid them being build when not used. This also allows us to use the
> SET_SYSTEM_SLEEP_PM_OPS macro which simplifies the code.
> 
> Signed-off-by: Anand Moon <linux.amoon@gmail.com>
> ---
>  drivers/usb/host/ehci-exynos.c | 14 ++++++--------
>  1 file changed, 6 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
> index 42e5b66..1899900 100644
> --- a/drivers/usb/host/ehci-exynos.c
> +++ b/drivers/usb/host/ehci-exynos.c
> @@ -251,7 +251,7 @@ static int exynos_ehci_remove(struct platform_device *pdev)
>  	return 0;
>  }
>  
> -#ifdef CONFIG_PM
> +#ifdef CONFIG_PM_SLEEP

Does not look like an equivalent change. How will it behave in a config
with !SUSPEND && !HIBERNATE && PM?

Best regards,
Krzysztof

>  static int exynos_ehci_suspend(struct device *dev)
>  {
>  	struct usb_hcd *hcd = dev_get_drvdata(dev);
> @@ -292,15 +292,13 @@ static int exynos_ehci_resume(struct device *dev)
>  	ehci_resume(hcd, false);
>  	return 0;
>  }
> -#else
> -#define exynos_ehci_suspend	NULL
> -#define exynos_ehci_resume	NULL
> -#endif
>  
>  static const struct dev_pm_ops exynos_ehci_pm_ops = {
> -	.suspend	= exynos_ehci_suspend,
> -	.resume		= exynos_ehci_resume,
> +	SET_SYSTEM_SLEEP_PM_OPS(exynos_ehci_suspend, exynos_ehci_resume)
>  };
> +#endif /* CONFIG_PM_SLEEP */
> +
> +#define DEV_PM_OPS IS_ENABLED(CONFIG_PM_SLEEP) ? &exynos_ehci_pm_ops : NULL
>  
>  #ifdef CONFIG_OF
>  static const struct of_device_id exynos_ehci_match[] = {
> @@ -317,7 +315,7 @@ static struct platform_driver exynos_ehci_driver = {
>  	.shutdown	= usb_hcd_platform_shutdown,
>  	.driver = {
>  		.name	= "exynos-ehci",
> -		.pm	= &exynos_ehci_pm_ops,
> +		.pm	= DEV_PM_OPS,
>  		.of_match_table = of_match_ptr(exynos_ehci_match),
>  	}
>  };
> -- 
> 2.7.4
> 

^ permalink raw reply


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox