riscv: setup per-hart stack earlier

Harts need to use per-hart stack before any function call, even if that
function is a simple one. When the callee uses stack for register save/
restore, especially RA, if nested call, concurrent access by multiple
harts on the same stack will cause data-race.

This patch sets up SP before `board_init_f_alloc_reserve`. A side effect
of this is that the memory layout has changed as the following:

+----------------+        +----------------+ <----- SPL_STACK/
|  ......        |        |  hart 0 stack  |        SYS_INIT_SP_ADDR
|  malloc_base   |        +----------------+
+----------------+        |  hart 1 stack  |
|  GD            |        +----------------+ If not SMP, N=1
+----------------+        |  ......        |
|  hart 0 stack  |        +----------------+
+----------------+   ==>  |  hart N-1 stack|
|  hart 1 stack  |        +----------------+
+----------------+        |  ......        |
|  ......        |        |  malloc_base   |
+----------------+        +----------------+
|  hart N-1 stack|        |  GD            |
+----------------+        +----------------+
|                |        |                |

Signed-off-by: Bo Gan <ganboing@gmail.com>
Cc: Rick Chen <rick@andestech.com>
Cc: Leo <ycliang@andestech.com>
Cc: Sean Anderson <seanga2@gmail.com>
Cc: Bin Meng <bmeng.cn@gmail.com>
Cc: Lukas Auer <lukas.auer@aisec.fraunhofer.de>
Reviewed-by: Rick Chen <rick@andestech.com>
Reviewed-by: Leo Yu-Chi Liang <ycliang@andestech.com>

diff --git a/arch/riscv/cpu/start.S b/arch/riscv/cpu/start.S
index dad22bfea877a40c95527f594ad680fdd0a0e3b1..59d58a5a57bc50d8f69017ce39e8a7bcee4f58b7 100644 (file)
--- a/arch/riscv/cpu/start.S
+++ b/arch/riscv/cpu/start.S
@@ -91,16 +91,35 @@ _start:
  * Set stackpointer in internal/ex RAM to call board_init_f
  */
 call_board_init_f:
-       li      t0, -16
 #if defined(CONFIG_SPL_BUILD) && defined(CONFIG_SPL_STACK)
-       li      t1, CONFIG_SPL_STACK
+       li      t0, CONFIG_SPL_STACK
 #else
-       li      t1, SYS_INIT_SP_ADDR
+       li      t0, SYS_INIT_SP_ADDR
 #endif
-       and     sp, t1, t0              /* force 16 byte alignment */
+       and     t0, t0, -16             /* force 16 byte alignment */
+
+       /* setup stack */
+#if CONFIG_IS_ENABLED(SMP)
+       /* tp: hart id */
+       slli    t1, tp, CONFIG_STACK_SIZE_SHIFT
+       sub     sp, t0, t1
+#else
+       mv      sp, t0
+#endif
+/*
+ * Now sp points to the right stack belonging to current CPU.
+ * It's essential before any function call, otherwise, we get data-race.
+ */
 
 call_board_init_f_0:
-       mv      a0, sp
+       /* find top of reserve space */
+#if CONFIG_IS_ENABLED(SMP)
+       li      t1, CONFIG_NR_CPUS
+#else
+       li      t1, 1
+#endif
+       slli    t1, t1, CONFIG_STACK_SIZE_SHIFT
+       sub     a0, t0, t1              /* t1 -> size of all CPU stacks */
        jal     board_init_f_alloc_reserve
 
        /*
@@ -109,14 +128,6 @@ call_board_init_f_0:
         */
        mv      s0, a0
 
-       /* setup stack */
-#if CONFIG_IS_ENABLED(SMP)
-       /* tp: hart id */
-       slli    t0, tp, CONFIG_STACK_SIZE_SHIFT
-       sub     sp, a0, t0
-#else
-       mv      sp, a0
-#endif
 
        /* Configure proprietary settings and customized CSRs of harts */
 call_harts_early_init: