[POWERPC] Move to runtime allocated exception stacks

For the additonal exception levels (critical, debug, machine check) on
40x/book-e we were using "static" allocations of the stack in the
associated head.S.

Move to a runtime allocation to make the code a bit easier to read as
we mimic how we handle IRQ stacks.  Its also a bit easier to setup the
stack with a "dummy" thread_info in C code.

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Acked-by: Paul Mackerras <paulus@samba.org>

arch/powerpc/kernel/head_40x.S

@@ -148,14 +148,14 @@ _ENTRY(crit_r11)
 	mfcr	r10;			/* save CR in r10 for now	   */\
 	mfspr	r11,SPRN_SRR3;		/* check whether user or kernel    */\
 	andi.	r11,r11,MSR_PR;						     \
-	lis	r11,critical_stack_top@h;				     \
+	lis	r11,critirq_ctx@ha;					     \
-	ori	r11,r11,critical_stack_top@l;				     \
+	tophys(r11,r11);						     \
+	lwz	r11,critirq_ctx@l(r11);					     \
 	beq	1f;							     \
 	/* COMING FROM USER MODE */					     \
 	mfspr	r11,SPRN_SPRG3;		/* if from user, start at top of   */\
 	lwz	r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
-	addi	r11,r11,THREAD_SIZE;					     \
+1:	addi	r11,r11,THREAD_SIZE-INT_FRAME_SIZE; /* Alloc an excpt frm  */\
-1:	subi	r11,r11,INT_FRAME_SIZE;	/* Allocate an exception frame     */\
 	tophys(r11,r11);						     \
 	stw	r10,_CCR(r11);          /* save various registers	   */\
 	stw	r12,GPR12(r11);						     \
@@ -996,16 +996,6 @@ empty_zero_page:
 swapper_pg_dir:
 	.space	PGD_TABLE_SIZE
 
-
-/* Stack for handling critical exceptions from kernel mode */
-	.section .bss
-        .align 12
-exception_stack_bottom:
-	.space	4096
-critical_stack_top:
-	.globl	exception_stack_top
-exception_stack_top:
-
 /* Room for two PTE pointers, usually the kernel and current user pointers
  * to their respective root page table.
  */

arch/powerpc/kernel/head_44x.S

@@ -737,15 +737,6 @@ empty_zero_page:
 swapper_pg_dir:
 	.space	PGD_TABLE_SIZE
 
-/* Reserved 4k for the critical exception stack & 4k for the machine
- * check stack per CPU for kernel mode exceptions */
-	.section .bss
-        .align 12
-exception_stack_bottom:
-	.space	BOOKE_EXCEPTION_STACK_SIZE
-	.globl	exception_stack_top
-exception_stack_top:
-
 /*
  * Room for two PTE pointers, usually the kernel and current user pointers
  * to their respective root page table.

arch/powerpc/kernel/head_booke.h

@@ -43,9 +43,7 @@
 	SAVE_2GPRS(7, r11)
 
 /* To handle the additional exception priority levels on 40x and Book-E
- * processors we allocate a 4k stack per additional priority level. The various
+ * processors we allocate a stack per additional priority level.
- * head_xxx.S files allocate space (exception_stack_top) for each priority's
- * stack times the number of CPUs
  *
  * On 40x critical is the only additional level
  * On 44x/e500 we have critical and machine check
@@ -61,36 +59,31 @@
  * going to critical or their own debug level we aren't currently
  * providing configurations that micro-optimize space usage.
  */
-#ifdef CONFIG_44x
-#define NUM_EXCEPTION_LVLS	2
-#else
-#define NUM_EXCEPTION_LVLS	3
-#endif
-#define BOOKE_EXCEPTION_STACK_SIZE	(4096 * NUM_EXCEPTION_LVLS)
 
 /* CRIT_SPRG only used in critical exception handling */
 #define CRIT_SPRG	SPRN_SPRG2
 /* MCHECK_SPRG only used in machine check exception handling */
 #define MCHECK_SPRG	SPRN_SPRG6W
 
-#define MCHECK_STACK_TOP	(exception_stack_top - 4096)
+#define MCHECK_STACK_BASE	mcheckirq_ctx
-#define CRIT_STACK_TOP		(exception_stack_top)
+#define CRIT_STACK_BASE		critirq_ctx
 
 /* only on e200 for now */
-#define DEBUG_STACK_TOP		(exception_stack_top - 8192)
+#define DEBUG_STACK_BASE	dbgirq_ctx
 #define DEBUG_SPRG		SPRN_SPRG6W
 
 #ifdef CONFIG_SMP
 #define BOOKE_LOAD_EXC_LEVEL_STACK(level)		\
 	mfspr	r8,SPRN_PIR;				\
-	mulli	r8,r8,BOOKE_EXCEPTION_STACK_SIZE;	\
+	slwi	r8,r8,2;				\
-	neg	r8,r8;					\
+	addis	r8,r8,level##_STACK_BASE@ha;		\
-	addis	r8,r8,level##_STACK_TOP@ha;		\
+	lwz	r8,level##_STACK_BASE@l(r8);		\
-	addi	r8,r8,level##_STACK_TOP@l
+	addi	r8,r8,THREAD_SIZE;
 #else
 #define BOOKE_LOAD_EXC_LEVEL_STACK(level)		\
-	lis	r8,level##_STACK_TOP@h;			\
+	lis	r8,level##_STACK_BASE@ha;		\
-	ori	r8,r8,level##_STACK_TOP@l
+	lwz	r8,level##_STACK_BASE@l(r8);		\
+	addi	r8,r8,THREAD_SIZE;
 #endif
 
 /*

arch/powerpc/kernel/head_fsl_booke.S

@@ -1080,15 +1080,6 @@ empty_zero_page:
 swapper_pg_dir:
 	.space	PGD_TABLE_SIZE
 
-/* Reserved 4k for the critical exception stack & 4k for the machine
- * check stack per CPU for kernel mode exceptions */
-	.section .bss
-	.align 12
-exception_stack_bottom:
-	.space	BOOKE_EXCEPTION_STACK_SIZE * NR_CPUS
-	.globl	exception_stack_top
-exception_stack_top:
-
 /*
  * Room for two PTE pointers, usually the kernel and current user pointers
  * to their respective root page table.

arch/powerpc/kernel/irq.c

@@ -356,9 +356,42 @@ void __init init_IRQ(void)
 {
 	if (ppc_md.init_IRQ)
 		ppc_md.init_IRQ();
+
+	exc_lvl_ctx_init();
+
 	irq_ctx_init();
 }
 
+#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
+struct thread_info   *critirq_ctx[NR_CPUS] __read_mostly;
+struct thread_info    *dbgirq_ctx[NR_CPUS] __read_mostly;
+struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
+
+void exc_lvl_ctx_init(void)
+{
+	struct thread_info *tp;
+	int i;
+
+	for_each_possible_cpu(i) {
+		memset((void *)critirq_ctx[i], 0, THREAD_SIZE);
+		tp = critirq_ctx[i];
+		tp->cpu = i;
+		tp->preempt_count = 0;
+
+#ifdef CONFIG_BOOKE
+		memset((void *)dbgirq_ctx[i], 0, THREAD_SIZE);
+		tp = dbgirq_ctx[i];
+		tp->cpu = i;
+		tp->preempt_count = 0;
+
+		memset((void *)mcheckirq_ctx[i], 0, THREAD_SIZE);
+		tp = mcheckirq_ctx[i];
+		tp->cpu = i;
+		tp->preempt_count = HARDIRQ_OFFSET;
+#endif
+	}
+}
+#endif
 
 #ifdef CONFIG_IRQSTACKS
 struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;

arch/powerpc/kernel/setup_32.c

@@ -248,6 +248,28 @@ static void __init irqstack_early_init(void)
 #define irqstack_early_init()
 #endif
 
+#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
+static void __init exc_lvl_early_init(void)
+{
+	unsigned int i;
+
+	/* interrupt stacks must be in lowmem, we get that for free on ppc32
+	 * as the lmb is limited to lowmem by LMB_REAL_LIMIT */
+	for_each_possible_cpu(i) {
+		critirq_ctx[i] = (struct thread_info *)
+			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+#ifdef CONFIG_BOOKE
+		dbgirq_ctx[i] = (struct thread_info *)
+			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+		mcheckirq_ctx[i] = (struct thread_info *)
+			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+#endif
+	}
+}
+#else
+#define exc_lvl_early_init()
+#endif
+
 /* Warning, IO base is not yet inited */
 void __init setup_arch(char **cmdline_p)
 {
@@ -305,6 +327,8 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = klimit;
 
+	exc_lvl_early_init();
+
 	irqstack_early_init();
 
 	/* set up the bootmem stuff with available memory */

include/asm-powerpc/irq.h

@@ -619,6 +619,19 @@ struct pt_regs;
 
 #define __ARCH_HAS_DO_SOFTIRQ
 
+#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
+/*
+ * Per-cpu stacks for handling critical, debug and machine check
+ * level interrupts.
+ */
+extern struct thread_info *critirq_ctx[NR_CPUS];
+extern struct thread_info *dbgirq_ctx[NR_CPUS];
+extern struct thread_info *mcheckirq_ctx[NR_CPUS];
+extern void exc_lvl_ctx_init(void);
+#else
+#define exc_lvl_ctx_init()
+#endif
+
 #ifdef CONFIG_IRQSTACKS
 /*
  * Per-cpu stacks for handling hard and soft interrupts.