ARM: 7784/1: mm: ensure SMP alternates assemble to exactly 4 bytes with Thumb-2

Commit ae8a8b9553bd ("ARM: 7691/1: mm: kill unused TLB_CAN_READ_FROM_L1_CACHE
and use ALT_SMP instead") added early function returns for page table
cache flushing operations on ARMv7 SMP CPUs.

Unfortunately, when targetting Thumb-2, these `mov pc, lr' sequences
assemble to 2 bytes which can lead to corruption of the instruction
stream after code patching.

This patch fixes the alternates to use wide (32-bit) instructions for
Thumb-2, therefore ensuring that the patching code works correctly.

Cc: <stable@vger.kernel.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

3 files changed, 8 insertions, 7 deletions

diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index f64afb9f1bd5..bdd3be4be77a 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -110,7 +110,7 @@ ENTRY(cpu_v7_set_pte_ext)
  ARM(   str     r3, [r0, #2048]! )
  THUMB( add     r0, r0, #2048 )
  THUMB( str     r3, [r0] )
-        ALT_SMP(mov     pc,lr)
+        ALT_SMP(W(nop))
         ALT_UP (mcr     p15, 0, r0, c7, c10, 1)         @ flush_pte
 #endif
         mov     pc, lr
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index c36ac69488c8..01a719e18bb0 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -81,7 +81,7 @@ ENTRY(cpu_v7_set_pte_ext)
         tst     r3, #1 << (55 - 32)             @ L_PTE_DIRTY
         orreq   r2, #L_PTE_RDONLY
 1:      strd    r2, r3, [r0]
-        ALT_SMP(mov     pc, lr)
+        ALT_SMP(W(nop))
         ALT_UP (mcr     p15, 0, r0, c7, c10, 1)         @ flush_pte
 #endif
         mov     pc, lr
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 5c6d5a3050ea..73398bcf9bd8 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -75,13 +75,14 @@ ENTRY(cpu_v7_do_idle)
 ENDPROC(cpu_v7_do_idle)
 
 ENTRY(cpu_v7_dcache_clean_area)
-        ALT_SMP(mov     pc, lr)                 @ MP extensions imply L1 PTW
-        ALT_UP(W(nop))
-        dcache_line_size r2, r3
-1:      mcr     p15, 0, r0, c7, c10, 1          @ clean D entry
+        ALT_SMP(W(nop))                 @ MP extensions imply L1 PTW
+        ALT_UP_B(1f)
+        mov     pc, lr
+1:      dcache_line_size r2, r3
+2:      mcr     p15, 0, r0, c7, c10, 1          @ clean D entry
         add     r0, r0, r2
         subs    r1, r1, r2
-        bhi     1b
+        bhi     2b
         dsb
         mov     pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)