summaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel/head.S
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/kernel/head.S')
-rw-r--r--arch/arm/kernel/head.S110
1 files changed, 92 insertions, 18 deletions
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 2c7cc1e0347..32f317e5828 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -77,6 +77,7 @@
__HEAD
ENTRY(stext)
+ ARM_BE8(setend be ) @ ensure we are in BE8 mode
THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM.
THUMB( bx r9 ) @ If this is a Thumb-2 kernel,
@@ -109,7 +110,7 @@ ENTRY(stext)
sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET)
add r8, r8, r4 @ PHYS_OFFSET
#else
- ldr r8, =PHYS_OFFSET @ always constant in this case
+ ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case
#endif
/*
@@ -352,6 +353,9 @@ ENTRY(secondary_startup)
* the processor type - there is no need to check the machine type
* as it has already been validated by the primary processor.
*/
+
+ ARM_BE8(setend be) @ ensure we are in BE8 mode
+
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install_secondary
#endif
@@ -487,7 +491,27 @@ __fixup_smp:
mrc p15, 0, r0, c0, c0, 5 @ read MPIDR
and r0, r0, #0xc0000000 @ multiprocessing extensions and
teq r0, #0x80000000 @ not part of a uniprocessor system?
- moveq pc, lr @ yes, assume SMP
+ bne __fixup_smp_on_up @ no, assume UP
+
+ @ Core indicates it is SMP. Check for Aegis SOC where a single
+ @ Cortex-A9 CPU is present but SMP operations fault.
+ mov r4, #0x41000000
+ orr r4, r4, #0x0000c000
+ orr r4, r4, #0x00000090
+ teq r3, r4 @ Check for ARM Cortex-A9
+ movne pc, lr @ Not ARM Cortex-A9,
+
+ @ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
+ @ below address check will need to be #ifdef'd or equivalent
+ @ for the Aegis platform.
+ mrc p15, 4, r0, c15, c0 @ get SCU base address
+ teq r0, #0x0 @ '0' on actual UP A9 hardware
+ beq __fixup_smp_on_up @ So its an A9 UP
+ ldr r0, [r0, #4] @ read SCU Config
+ARM_BE8(rev r0, r0) @ byteswap if big endian
+ and r0, r0, #0x3 @ number of CPUs
+ teq r0, #0x0 @ is 1?
+ movne pc, lr
__fixup_smp_on_up:
adr r0, 1f
@@ -536,6 +560,14 @@ ENTRY(fixup_smp)
ldmfd sp!, {r4 - r6, pc}
ENDPROC(fixup_smp)
+#ifdef __ARMEB__
+#define LOW_OFFSET 0x4
+#define HIGH_OFFSET 0x0
+#else
+#define LOW_OFFSET 0x0
+#define HIGH_OFFSET 0x4
+#endif
+
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
/* __fixup_pv_table - patch the stub instructions with the delta between
@@ -546,17 +578,20 @@ ENDPROC(fixup_smp)
__HEAD
__fixup_pv_table:
adr r0, 1f
- ldmia r0, {r3-r5, r7}
- sub r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET
+ ldmia r0, {r3-r7}
+ mvn ip, #0
+ subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET
add r4, r4, r3 @ adjust table start address
add r5, r5, r3 @ adjust table end address
- add r7, r7, r3 @ adjust __pv_phys_offset address
- str r8, [r7] @ save computed PHYS_OFFSET to __pv_phys_offset
+ add r6, r6, r3 @ adjust __pv_phys_offset address
+ add r7, r7, r3 @ adjust __pv_offset address
+ str r8, [r6, #LOW_OFFSET] @ save computed PHYS_OFFSET to __pv_phys_offset
+ strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits
mov r6, r3, lsr #24 @ constant for add/sub instructions
teq r3, r6, lsl #24 @ must be 16MiB aligned
THUMB( it ne @ cross section branch )
bne __error
- str r6, [r7, #4] @ save to __pv_offset
+ str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits
b __fixup_a_pv_table
ENDPROC(__fixup_pv_table)
@@ -565,10 +600,19 @@ ENDPROC(__fixup_pv_table)
.long __pv_table_begin
.long __pv_table_end
2: .long __pv_phys_offset
+ .long __pv_offset
.text
__fixup_a_pv_table:
+ adr r0, 3f
+ ldr r6, [r0]
+ add r6, r6, r3
+ ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word
+ ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word
+ mov r6, r6, lsr #24
+ cmn r0, #1
#ifdef CONFIG_THUMB2_KERNEL
+ moveq r0, #0x200000 @ set bit 21, mov to mvn instruction
lsls r6, #24
beq 2f
clz r7, r6
@@ -582,18 +626,46 @@ __fixup_a_pv_table:
b 2f
1: add r7, r3
ldrh ip, [r7, #2]
- and ip, 0x8f00
- orr ip, r6 @ mask in offset bits 31-24
+ARM_BE8(rev16 ip, ip)
+ tst ip, #0x4000
+ and ip, #0x8f00
+ orrne ip, r6 @ mask in offset bits 31-24
+ orreq ip, r0 @ mask in offset bits 7-0
+ARM_BE8(rev16 ip, ip)
strh ip, [r7, #2]
+ bne 2f
+ ldrh ip, [r7]
+ARM_BE8(rev16 ip, ip)
+ bic ip, #0x20
+ orr ip, ip, r0, lsr #16
+ARM_BE8(rev16 ip, ip)
+ strh ip, [r7]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
bcc 1b
bx lr
#else
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ moveq r0, #0x00004000 @ set bit 22, mov to mvn instruction
+#else
+ moveq r0, #0x400000 @ set bit 22, mov to mvn instruction
+#endif
b 2f
1: ldr ip, [r7, r3]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ @ in BE8, we load data in BE, but instructions still in LE
+ bic ip, ip, #0xff000000
+ tst ip, #0x000f0000 @ check the rotation field
+ orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24
+ biceq ip, ip, #0x00004000 @ clear bit 22
+ orreq ip, ip, r0 @ mask in offset bits 7-0
+#else
bic ip, ip, #0x000000ff
- orr ip, ip, r6 @ mask in offset bits 31-24
+ tst ip, #0xf00 @ check the rotation field
+ orrne ip, ip, r6 @ mask in offset bits 31-24
+ biceq ip, ip, #0x400000 @ clear bit 22
+ orreq ip, ip, r0 @ mask in offset bits 7-0
+#endif
str ip, [r7, r3]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
@@ -602,28 +674,30 @@ __fixup_a_pv_table:
#endif
ENDPROC(__fixup_a_pv_table)
+ .align
+3: .long __pv_offset
+
ENTRY(fixup_pv_table)
stmfd sp!, {r4 - r7, lr}
- ldr r2, 2f @ get address of __pv_phys_offset
mov r3, #0 @ no offset
mov r4, r0 @ r0 = table start
add r5, r0, r1 @ r1 = table size
- ldr r6, [r2, #4] @ get __pv_offset
bl __fixup_a_pv_table
ldmfd sp!, {r4 - r7, pc}
ENDPROC(fixup_pv_table)
- .align
-2: .long __pv_phys_offset
-
.data
.globl __pv_phys_offset
.type __pv_phys_offset, %object
__pv_phys_offset:
- .long 0
- .size __pv_phys_offset, . - __pv_phys_offset
+ .quad 0
+ .size __pv_phys_offset, . -__pv_phys_offset
+
+ .globl __pv_offset
+ .type __pv_offset, %object
__pv_offset:
- .long 0
+ .quad 0
+ .size __pv_offset, . -__pv_offset
#endif
#include "head-common.S"