2012-08-02 11:16:29 +03:00
/ *
* Coherency f a b r i c : l o w l e v e l f u n c t i o n s
*
* Copyright ( C ) 2 0 1 2 M a r v e l l
*
* Gregory C L E M E N T < g r e g o r y . c l e m e n t @free-electrons.com>
*
* This f i l e i s l i c e n s e d u n d e r t h e t e r m s o f t h e G N U G e n e r a l P u b l i c
* License v e r s i o n 2 . T h i s p r o g r a m i s l i c e n s e d " a s i s " w i t h o u t a n y
* warranty o f a n y k i n d , w h e t h e r e x p r e s s o r i m p l i e d .
*
* This f i l e i m p l e m e n t s t h e a s s e m b l y f u n c t i o n t o a d d a C P U t o t h e
* coherency f a b r i c . T h i s f u n c t i o n i s c a l l e d b y e a c h o f t h e s e c o n d a r y
* CPUs d u r i n g t h e i r e a r l y b o o t i n a n S M P k e r n e l , t h i s w h y t h i s
* function h a v e t o c a l l a b l e f r o m a s s e m b l y . I t c a n a l s o b e c a l l e d b y a
* primary C P U f r o m C c o d e d u r i n g i t s b o o t .
* /
# include < l i n u x / l i n k a g e . h >
# define A R M A D A _ X P _ C F B _ C T L _ R E G _ O F F S E T 0 x0
# define A R M A D A _ X P _ C F B _ C F G _ R E G _ O F F S E T 0 x4
2013-02-01 10:36:22 +00:00
# include < a s m / a s s e m b l e r . h >
2014-04-14 17:10:05 +02:00
# include < a s m / c p15 . h >
2013-02-01 10:36:22 +00:00
2012-08-02 11:16:29 +03:00
.text
ARM: mvebu: make the coherency_ll.S functions work with no coherency fabric
The ll_add_cpu_to_smp_group(), ll_enable_coherency() and
ll_disable_coherency() are used on Armada XP to control the coherency
fabric. However, they make the assumption that the coherency fabric is
always available, which is currently a correct assumption but will no
longer be true with a followup commit that disables the usage of the
coherency fabric when the conditions are not met to use it.
Therefore, this commit modifies those functions so that they check the
return value of ll_get_coherency_base(), and if the return value is 0,
they simply return without configuring anything in the coherency
fabric.
The ll_get_coherency_base() function is also modified to properly
return 0 when the function is called with the MMU disabled. In this
case, it normally returns the physical address of the coherency
fabric, but we now check if the virtual address is 0, and if that's
case, return a physical address of 0 to indicate that the coherency
fabric is not enabled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Link: https://lkml.kernel.org/r/1415871540-20302-2-git-send-email-thomas.petazzoni@free-electrons.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-11-13 10:38:56 +01:00
/ *
* Returns t h e c o h e r e n c y b a s e a d d r e s s i n r1 ( r0 i s u n t o u c h e d ) , o r 0 i f
* the c o h e r e n c y f a b r i c i s n o t e n a b l e d .
* /
2014-04-14 17:10:08 +02:00
ENTRY( l l _ g e t _ c o h e r e n c y _ b a s e )
2014-04-14 17:10:05 +02:00
mrc p15 , 0 , r1 , c1 , c0 , 0
tst r1 , #C R _ M @ C h e c k M M U b i t e n a b l e d
bne 1 f
2014-05-22 14:48:01 +02:00
/ *
* MMU i s d i s a b l e d , u s e t h e p h y s i c a l a d d r e s s o f t h e c o h e r e n c y
ARM: mvebu: make the coherency_ll.S functions work with no coherency fabric
The ll_add_cpu_to_smp_group(), ll_enable_coherency() and
ll_disable_coherency() are used on Armada XP to control the coherency
fabric. However, they make the assumption that the coherency fabric is
always available, which is currently a correct assumption but will no
longer be true with a followup commit that disables the usage of the
coherency fabric when the conditions are not met to use it.
Therefore, this commit modifies those functions so that they check the
return value of ll_get_coherency_base(), and if the return value is 0,
they simply return without configuring anything in the coherency
fabric.
The ll_get_coherency_base() function is also modified to properly
return 0 when the function is called with the MMU disabled. In this
case, it normally returns the physical address of the coherency
fabric, but we now check if the virtual address is 0, and if that's
case, return a physical address of 0 to indicate that the coherency
fabric is not enabled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Link: https://lkml.kernel.org/r/1415871540-20302-2-git-send-email-thomas.petazzoni@free-electrons.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-11-13 10:38:56 +01:00
* base a d d r e s s . H o w e v e r , i f t h e c o h e r e n c y f a b r i c i s n ' t m a p p e d
* ( i. e i t s v i r t u a l a d d r e s s i s z e r o ) , i t m e a n s c o h e r e n c y i s
* not e n a b l e d , s o w e r e t u r n 0 .
2014-05-22 14:48:01 +02:00
* /
ARM: mvebu: make the coherency_ll.S functions work with no coherency fabric
The ll_add_cpu_to_smp_group(), ll_enable_coherency() and
ll_disable_coherency() are used on Armada XP to control the coherency
fabric. However, they make the assumption that the coherency fabric is
always available, which is currently a correct assumption but will no
longer be true with a followup commit that disables the usage of the
coherency fabric when the conditions are not met to use it.
Therefore, this commit modifies those functions so that they check the
return value of ll_get_coherency_base(), and if the return value is 0,
they simply return without configuring anything in the coherency
fabric.
The ll_get_coherency_base() function is also modified to properly
return 0 when the function is called with the MMU disabled. In this
case, it normally returns the physical address of the coherency
fabric, but we now check if the virtual address is 0, and if that's
case, return a physical address of 0 to indicate that the coherency
fabric is not enabled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Link: https://lkml.kernel.org/r/1415871540-20302-2-git-send-email-thomas.petazzoni@free-electrons.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-11-13 10:38:56 +01:00
ldr r1 , =coherency_base
cmp r1 , #0
beq 2 f
2014-04-14 17:10:08 +02:00
adr r1 , 3 f
ldr r3 , [ r1 ]
ldr r1 , [ r1 , r3 ]
2014-04-14 17:10:05 +02:00
b 2 f
1 :
2014-05-22 14:48:01 +02:00
/ *
* MMU i s e n a b l e d , u s e t h e v i r t u a l a d d r e s s o f t h e c o h e r e n c y
* base a d d r e s s .
* /
2014-04-14 17:10:08 +02:00
ldr r1 , =coherency_base
ldr r1 , [ r1 ]
2014-04-14 17:10:05 +02:00
2 :
2014-06-30 16:29:12 +01:00
ret l r
2014-04-14 17:10:08 +02:00
ENDPROC( l l _ g e t _ c o h e r e n c y _ b a s e )
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
/ *
* Returns t h e c o h e r e n c y C P U m a s k i n r3 ( r0 i s u n t o u c h e d ) . T h i s
* coherency C P U m a s k c a n b e u s e d w i t h t h e c o h e r e n c y f a b r i c
* configuration a n d c o n t r o l r e g i s t e r s . N o t e t h a t t h e m a s k i s a l r e a d y
* endian- s w a p p e d a s a p p r o p r i a t e s o t h a t t h e c a l l i n g f u n c t i o n s d o n o t
* have t o c a r e a b o u t e n d i a n n e s s i s s u e s w h i l e a c c e s s i n g t h e c o h e r e n c y
* fabric r e g i s t e r s
* /
ENTRY( l l _ g e t _ c o h e r e n c y _ c p u m a s k )
2014-04-14 17:10:08 +02:00
mrc 1 5 , 0 , r3 , c r0 , c r0 , 5
and r3 , r3 , #15
2014-04-14 17:10:06 +02:00
mov r2 , #( 1 < < 2 4 )
2014-04-14 17:10:08 +02:00
lsl r3 , r2 , r3
2014-05-22 14:47:59 +02:00
ARM_ B E 8 ( r e v r3 , r3 )
2014-06-30 16:29:12 +01:00
ret l r
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
ENDPROC( l l _ g e t _ c o h e r e n c y _ c p u m a s k )
2012-08-02 11:16:29 +03:00
2014-05-22 14:48:01 +02:00
/ *
* ll_ a d d _ c p u _ t o _ s m p _ g r o u p ( ) , l l _ e n a b l e _ c o h e r e n c y ( ) a n d
* ll_ d i s a b l e _ c o h e r e n c y ( ) u s e t h e s t r e x / l d r e x i n s t r u c t i o n s w h i l e t h e
* MMU c a n b e d i s a b l e d . T h e A r m a d a X P S o C h a s a n e x c l u s i v e m o n i t o r
* that t r a c k s t r a n s a c t i o n s t o D e v i c e a n d / o r S O m e m o r y a n d t h a n k s t o
* that, e x c l u s i v e t r a n s a c t i o n s a r e f u n c t i o n a l e v e n w h e n t h e M M U i s
* disabled.
2014-04-14 17:10:08 +02:00
* /
2012-08-02 11:16:29 +03:00
2014-04-14 17:10:08 +02:00
ENTRY( l l _ a d d _ c p u _ t o _ s m p _ g r o u p )
/ *
2014-05-22 14:48:01 +02:00
* As r0 i s n o t m o d i f i e d b y l l _ g e t _ c o h e r e n c y _ b a s e ( ) a n d
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
* ll_ g e t _ c o h e r e n c y _ c p u m a s k ( ) , w e u s e i t t o t e m p o r a r l y s a v e l r
* and a v o i d i t b e i n g m o d i f i e d b y t h e b r a n c h a n d l i n k
* calls. T h i s f u n c t i o n i s u s e d v e r y e a r l y i n t h e s e c o n d a r y
* CPU b o o t , a n d n o s t a c k i s a v a i l a b l e a t t h i s p o i n t .
2014-04-14 17:10:08 +02:00
* /
2014-05-22 14:48:00 +02:00
mov r0 , l r
2014-04-14 17:10:08 +02:00
bl l l _ g e t _ c o h e r e n c y _ b a s e
ARM: mvebu: make the coherency_ll.S functions work with no coherency fabric
The ll_add_cpu_to_smp_group(), ll_enable_coherency() and
ll_disable_coherency() are used on Armada XP to control the coherency
fabric. However, they make the assumption that the coherency fabric is
always available, which is currently a correct assumption but will no
longer be true with a followup commit that disables the usage of the
coherency fabric when the conditions are not met to use it.
Therefore, this commit modifies those functions so that they check the
return value of ll_get_coherency_base(), and if the return value is 0,
they simply return without configuring anything in the coherency
fabric.
The ll_get_coherency_base() function is also modified to properly
return 0 when the function is called with the MMU disabled. In this
case, it normally returns the physical address of the coherency
fabric, but we now check if the virtual address is 0, and if that's
case, return a physical address of 0 to indicate that the coherency
fabric is not enabled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Link: https://lkml.kernel.org/r/1415871540-20302-2-git-send-email-thomas.petazzoni@free-electrons.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-11-13 10:38:56 +01:00
/* Bail out if the coherency is not enabled */
cmp r1 , #0
reteq r0
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
bl l l _ g e t _ c o h e r e n c y _ c p u m a s k
2014-05-22 14:48:00 +02:00
mov l r , r0
2014-04-14 17:10:08 +02:00
add r0 , r1 , #A R M A D A _ X P _ C F B _ C F G _ R E G _ O F F S E T
2013-05-23 10:54:02 +02:00
1 :
2014-04-14 17:10:08 +02:00
ldrex r2 , [ r0 ]
orr r2 , r2 , r3
strex r1 , r2 , [ r0 ]
cmp r1 , #0
bne 1 b
2014-06-30 16:29:12 +01:00
ret l r
2014-04-14 17:10:08 +02:00
ENDPROC( l l _ a d d _ c p u _ t o _ s m p _ g r o u p )
2012-08-02 11:16:29 +03:00
2014-04-14 17:10:08 +02:00
ENTRY( l l _ e n a b l e _ c o h e r e n c y )
/ *
2014-05-22 14:48:01 +02:00
* As r0 i s n o t m o d i f i e d b y l l _ g e t _ c o h e r e n c y _ b a s e ( ) a n d
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
* ll_ g e t _ c o h e r e n c y _ c p u m a s k ( ) , w e u s e i t t o t e m p o r a r l y s a v e l r
* and a v o i d i t b e i n g m o d i f i e d b y t h e b r a n c h a n d l i n k
* calls. T h i s f u n c t i o n i s u s e d v e r y e a r l y i n t h e s e c o n d a r y
* CPU b o o t , a n d n o s t a c k i s a v a i l a b l e a t t h i s p o i n t .
2014-04-14 17:10:08 +02:00
* /
mov r0 , l r
bl l l _ g e t _ c o h e r e n c y _ b a s e
ARM: mvebu: make the coherency_ll.S functions work with no coherency fabric
The ll_add_cpu_to_smp_group(), ll_enable_coherency() and
ll_disable_coherency() are used on Armada XP to control the coherency
fabric. However, they make the assumption that the coherency fabric is
always available, which is currently a correct assumption but will no
longer be true with a followup commit that disables the usage of the
coherency fabric when the conditions are not met to use it.
Therefore, this commit modifies those functions so that they check the
return value of ll_get_coherency_base(), and if the return value is 0,
they simply return without configuring anything in the coherency
fabric.
The ll_get_coherency_base() function is also modified to properly
return 0 when the function is called with the MMU disabled. In this
case, it normally returns the physical address of the coherency
fabric, but we now check if the virtual address is 0, and if that's
case, return a physical address of 0 to indicate that the coherency
fabric is not enabled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Link: https://lkml.kernel.org/r/1415871540-20302-2-git-send-email-thomas.petazzoni@free-electrons.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-11-13 10:38:56 +01:00
/* Bail out if the coherency is not enabled */
cmp r1 , #0
reteq r0
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
bl l l _ g e t _ c o h e r e n c y _ c p u m a s k
2014-04-14 17:10:08 +02:00
mov l r , r0
add r0 , r1 , #A R M A D A _ X P _ C F B _ C T L _ R E G _ O F F S E T
1 :
ldrex r2 , [ r0 ]
orr r2 , r2 , r3
strex r1 , r2 , [ r0 ]
cmp r1 , #0
bne 1 b
2012-08-02 11:16:29 +03:00
dsb
mov r0 , #0
2014-06-30 16:29:12 +01:00
ret l r
2014-04-14 17:10:08 +02:00
ENDPROC( l l _ e n a b l e _ c o h e r e n c y )
2014-04-14 17:10:09 +02:00
ENTRY( l l _ d i s a b l e _ c o h e r e n c y )
/ *
2014-05-22 14:48:01 +02:00
* As r0 i s n o t m o d i f i e d b y l l _ g e t _ c o h e r e n c y _ b a s e ( ) a n d
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
* ll_ g e t _ c o h e r e n c y _ c p u m a s k ( ) , w e u s e i t t o t e m p o r a r l y s a v e l r
* and a v o i d i t b e i n g m o d i f i e d b y t h e b r a n c h a n d l i n k
* calls. T h i s f u n c t i o n i s u s e d v e r y e a r l y i n t h e s e c o n d a r y
* CPU b o o t , a n d n o s t a c k i s a v a i l a b l e a t t h i s p o i n t .
2014-04-14 17:10:09 +02:00
* /
2014-05-22 14:48:00 +02:00
mov r0 , l r
2014-04-14 17:10:09 +02:00
bl l l _ g e t _ c o h e r e n c y _ b a s e
ARM: mvebu: make the coherency_ll.S functions work with no coherency fabric
The ll_add_cpu_to_smp_group(), ll_enable_coherency() and
ll_disable_coherency() are used on Armada XP to control the coherency
fabric. However, they make the assumption that the coherency fabric is
always available, which is currently a correct assumption but will no
longer be true with a followup commit that disables the usage of the
coherency fabric when the conditions are not met to use it.
Therefore, this commit modifies those functions so that they check the
return value of ll_get_coherency_base(), and if the return value is 0,
they simply return without configuring anything in the coherency
fabric.
The ll_get_coherency_base() function is also modified to properly
return 0 when the function is called with the MMU disabled. In this
case, it normally returns the physical address of the coherency
fabric, but we now check if the virtual address is 0, and if that's
case, return a physical address of 0 to indicate that the coherency
fabric is not enabled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Link: https://lkml.kernel.org/r/1415871540-20302-2-git-send-email-thomas.petazzoni@free-electrons.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-11-13 10:38:56 +01:00
/* Bail out if the coherency is not enabled */
cmp r1 , #0
reteq r0
ARM: mvebu: returns ll_get_cpuid() to ll_get_coherency_cpumask()
In the refactoring of the coherency fabric assembly code, a function
called ll_get_cpuid() was created to factorize common logic between
functions adding CPU to the SMP coherency group, enabling and
disabling the coherency.
However, the name of the function is highly misleading: ll_get_cpuid()
makes one think tat it returns the ID of the CPU, i.e 0 for CPU0, 1
for CPU1, etc. In fact, this is not at all what this function returns:
it returns a CPU mask for the current CPU, usable for the coherency
fabric configuration and control registers.
Therefore this commit renames this function to
ll_get_coherency_cpumask(), and adds additional comments on top of the
function to explain in more details what it does, and also how the
endianess issue is handled.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Link: https://lkml.kernel.org/r/1400762882-10116-5-git-send-email-thomas.petazzoni@free-electrons.com
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2014-05-22 14:48:02 +02:00
bl l l _ g e t _ c o h e r e n c y _ c p u m a s k
2014-05-22 14:48:00 +02:00
mov l r , r0
2014-04-14 17:10:09 +02:00
add r0 , r1 , #A R M A D A _ X P _ C F B _ C T L _ R E G _ O F F S E T
1 :
ldrex r2 , [ r0 ]
bic r2 , r2 , r3
strex r1 , r2 , [ r0 ]
cmp r1 , #0
bne 1 b
dsb
2014-06-30 16:29:12 +01:00
ret l r
2014-04-14 17:10:09 +02:00
ENDPROC( l l _ d i s a b l e _ c o h e r e n c y )
2014-04-14 17:10:05 +02:00
.align 2
3 :
.long coherency_phys_base - .
