[PATCH 2/7] sparc64: honor queued spinlock layout in secondary startup

[Magnus Lindholm]

The trampoline's ldstub modifies the queue-tail byte of prom_entry_lock,
not its locked byte, because SPARC64 uses big-endian queued spinlocks.
Acquire the word with CASA, release byte three and poll while contended.
Retain the predicted-branch barriers for Spitfire erratum 51.

See qspinlock_types.h for the layout and JPS2 A.10/A.35 for CASA/MEMBAR.

Fixes: 145d97858597 ("arch/sparc: Enable queued spinlock support for SPARC")
Cc: stable@xxxxxxxxxxxxxxx

Signed-off-by: Magnus Lindholm <linmag7@xxxxxxxxx>
---
 arch/sparc/kernel/trampoline_64.S | 34 +++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index 51bf1eb92a36..62f404b3079a 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -106,9 +106,19 @@ startup_continue:
 	 * We lock 'num_kernel_image_mappings' consequetive entries.
 	 */
 	sethi		%hi(prom_entry_lock), %g2
-1:	ldstub		[%g2 + %lo(prom_entry_lock)], %g1
+	/* Big-endian qspinlock: acquire the whole 32-bit value, not byte 0. */
+	or		%g2, %lo(prom_entry_lock), %g2
+1:	lduw		[%g2], %g1
 	brnz,pn		%g1, 1b
 	 nop
+	mov		1, %g1
+	casa		[%g2] ASI_P, %g0, %g1
+	brnz,pn		%g1, 1b
+	 nop
+	/* Spitfire erratum 51: barrier in a predicted-taken delay slot. */
+	ba,pt		%xcc, 2f
+	 membar		#Sync
+2:
 
 	/* Get onto temporary stack which will be in the locked
 	 * kernel image.
@@ -212,7 +222,10 @@ startup_continue:
 	 nop
 
 	sethi		%hi(prom_entry_lock), %g2
-	stb		%g0, [%g2 + %lo(prom_entry_lock)]
+	/* Match membar_safe() for Spitfire erratum 51. */
+	ba,pt		%xcc, 2f
+	 membar		#StoreStore | #LoadStore
+2:	stb		%g0, [%g2 + %lo(prom_entry_lock) + 3]
 
 	ba,pt		%xcc, after_lock_tlb
 	 nop
@@ -326,9 +339,19 @@ after_lock_tlb:
 	wrpr		%g0, 0, %wstate
 
 	sethi		%hi(prom_entry_lock), %g2
-1:	ldstub		[%g2 + %lo(prom_entry_lock)], %g1
+	/* Big-endian qspinlock: acquire the whole 32-bit value, not byte 0. */
+	or		%g2, %lo(prom_entry_lock), %g2
+1:	lduw		[%g2], %g1
 	brnz,pn		%g1, 1b
 	 nop
+	mov		1, %g1
+	casa		[%g2] ASI_P, %g0, %g1
+	brnz,pn		%g1, 1b
+	 nop
+	/* Spitfire erratum 51: barrier in a predicted-taken delay slot. */
+	ba,pt		%xcc, 2f
+	 membar		#Sync
+2:
 
 	/* As a hack, put &init_thread_union into %g6.
 	 * prom_world() loads from here to restore the %asi
@@ -389,7 +412,10 @@ after_lock_tlb:
 	 add		%sp, (2047 + 128), %o0
 
 3:	sethi		%hi(prom_entry_lock), %g2
-	stb		%g0, [%g2 + %lo(prom_entry_lock)]
+	/* Match membar_safe() for Spitfire erratum 51. */
+	ba,pt		%xcc, 2f
+	 membar		#StoreStore | #LoadStore
+2:	stb		%g0, [%g2 + %lo(prom_entry_lock) + 3]
 
 	ldx		[%l0], %g6
 	ldx		[%g6 + TI_TASK], %g4
-- 
2.43.0