powerpc: Make it possible to move the interrupt handlers away from the kernel

This changes the way that the exception prologs transfer control to
the handlers in 64-bit kernels with the aim of making it possible to
have the prologs separate from the main body of the kernel.  Now,
instead of computing the address of the handler by taking the top
32 bits of the paca address (to get the 0xc0000000........ part) and
ORing in something in the bottom 16 bits, we get the base address of
the kernel by doing a load from the paca and add an offset.

This also replaces an mfmsr and an ori to compute the MSR value for
the handler with a load from the paca.  That makes it unnecessary to
have a separate version of EXCEPTION_PROLOG_PSERIES that forces 64-bit
mode.

We can no longer use a direct branches in the exception prolog code,
which means that the SLB miss handlers can't branch directly to
.slb_miss_realmode any more.  Instead we have to compute the address
and do an indirect branch.  This is conditional on CONFIG_RELOCATABLE;
for non-relocatable kernels we use a direct branch as before.  (A later
change will allow CONFIG_RELOCATABLE to be set on 64-bit powerpc.)

Since the secondary CPUs on pSeries start execution in the first 0x100
bytes of real memory and then have to get to wherever the kernel is,
we can't use a direct branch to get there.  Instead this changes
__secondary_hold_spinloop from a flag to a function pointer.  When it
is set to a non-NULL value, the secondary CPUs jump to the function
pointed to by that value.

Finally this eliminates one code difference between 32-bit and 64-bit
by making __secondary_hold be the text address of the secondary CPU
spinloop rather than a function descriptor for it.

Signed-off-by: Paul Mackerras <paulus@samba.org>

arch/powerpc/include/asm/exception.h

@@ -53,14 +53,8 @@
  * low halfword of the address, but for Kdump we need the whole low
  * word.
  */
-#ifdef CONFIG_CRASH_DUMP
 #define LOAD_HANDLER(reg, label)					\
-	oris	reg,reg,(label)@h;	/* virt addr of handler ... */	\
+	addi	reg,reg,(label)-_stext;	/* virt addr of handler ... */
-	ori	reg,reg,(label)@l;	/* .. and the rest */
-#else
-#define LOAD_HANDLER(reg, label)					\
-	ori	reg,reg,(label)@l;	/* virt addr of handler ... */
-#endif
 
 #define EXCEPTION_PROLOG_1(area)				\
 	mfspr	r13,SPRN_SPRG3;		/* get paca address into r13 */	\
@@ -72,37 +66,12 @@
 	std	r9,area+EX_R13(r13);					\
 	mfcr	r9
 
-/*
- * Equal to EXCEPTION_PROLOG_PSERIES, except that it forces 64bit mode.
- * The firmware calls the registered system_reset_fwnmi and
- * machine_check_fwnmi handlers in 32bit mode if the cpu happens to run
- * a 32bit application at the time of the event.
- * This firmware bug is present on POWER4 and JS20.
- */
-#define EXCEPTION_PROLOG_PSERIES_FORCE_64BIT(area, label)		\
-	EXCEPTION_PROLOG_1(area);					\
-	clrrdi	r12,r13,32;		/* get high part of &label */	\
-	mfmsr	r10;							\
-	/* force 64bit mode */						\
-	li	r11,5;			/* MSR_SF_LG|MSR_ISF_LG */	\
-	rldimi	r10,r11,61,0;		/* insert into top 3 bits */	\
-	/* done 64bit mode */						\
-	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
-	LOAD_HANDLER(r12,label)						\
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI;				\
-	mtspr	SPRN_SRR0,r12;						\
-	mfspr	r12,SPRN_SRR1;		/* and SRR1 */			\
-	mtspr	SPRN_SRR1,r10;						\
-	rfid;								\
-	b	.	/* prevent speculative execution */
-
 #define EXCEPTION_PROLOG_PSERIES(area, label)				\
 	EXCEPTION_PROLOG_1(area);					\
-	clrrdi	r12,r13,32;		/* get high part of &label */	\
+	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
-	mfmsr	r10;							\
+	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
 	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
 	LOAD_HANDLER(r12,label)						\
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI;				\
 	mtspr	SPRN_SRR0,r12;						\
 	mfspr	r12,SPRN_SRR1;		/* and SRR1 */			\
 	mtspr	SPRN_SRR1,r10;						\
@@ -210,11 +179,10 @@ label##_pSeries:							\
 	std	r10,PACA_EXGEN+EX_R13(r13);				\
 	std	r11,PACA_EXGEN+EX_R11(r13);				\
 	std	r12,PACA_EXGEN+EX_R12(r13);				\
-	clrrdi	r12,r13,32;		/* get high part of &label */	\
+	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
-	mfmsr	r10;							\
+	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
 	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
 	LOAD_HANDLER(r12,label##_common)				\
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI;				\
 	mtspr	SPRN_SRR0,r12;						\
 	mfspr	r12,SPRN_SRR1;		/* and SRR1 */			\
 	mtspr	SPRN_SRR1,r10;						\

arch/powerpc/include/asm/paca.h

@@ -62,6 +62,8 @@ struct paca_struct {
 	u16 paca_index;			/* Logical processor number */
 
 	u64 kernel_toc;			/* Kernel TOC address */
+	u64 kernelbase;			/* Base address of kernel */
+	u64 kernel_msr;			/* MSR while running in kernel */
 	u64 stab_real;			/* Absolute address of segment table */
 	u64 stab_addr;			/* Virtual address of segment table */
 	void *emergency_sp;		/* pointer to emergency stack */

arch/powerpc/kernel/asm-offsets.c

@@ -122,6 +122,8 @@ int main(void)
 	DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr));
 	DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1));
 	DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc));
+	DEFINE(PACAKBASE, offsetof(struct paca_struct, kernelbase));
+	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
 	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));

arch/powerpc/kernel/head_64.S

@@ -82,7 +82,11 @@ END_FTR_SECTION(0, 1)
 	/* Catch branch to 0 in real mode */
 	trap
 
-	/* Secondary processors spin on this value until it goes to 1. */
+	/* Secondary processors spin on this value until it becomes nonzero.
+	 * When it does it contains the real address of the descriptor
+	 * of the function that the cpu should jump to to continue
+	 * initialization.
+	 */
 	.globl  __secondary_hold_spinloop
 __secondary_hold_spinloop:
 	.llong	0x0
@@ -109,8 +113,11 @@ __secondary_hold_acknowledge:
  * before the bulk of the kernel has been relocated.  This code
  * is relocated to physical address 0x60 before prom_init is run.
  * All of it must fit below the first exception vector at 0x100.
+ * Use .globl here not _GLOBAL because we want __secondary_hold
+ * to be the actual text address, not a descriptor.
  */
-_GLOBAL(__secondary_hold)
+	.globl	__secondary_hold
+__secondary_hold:
 	mfmsr	r24
 	ori	r24,r24,MSR_RI
 	mtmsrd	r24			/* RI on */
@@ -126,11 +133,11 @@ _GLOBAL(__secondary_hold)
 
 	/* All secondary cpus wait here until told to start. */
 100:	ld	r4,__secondary_hold_spinloop@l(0)
-	cmpdi	0,r4,1
+	cmpdi	0,r4,0
-	bne	100b
+	beq	100b
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
-	LOAD_REG_IMMEDIATE(r4, .generic_secondary_smp_init)
+	ld	r4,0(r4)		/* deref function descriptor */
 	mtctr	r4
 	mr	r3,r24
 	bctr
@@ -147,6 +154,10 @@ exception_marker:
 /*
  * This is the start of the interrupt handlers for pSeries
  * This code runs with relocation off.
+ * Code from here to __end_interrupts gets copied down to real
+ * address 0x100 when we are running a relocatable kernel.
+ * Therefore any relative branches in this section must only
+ * branch to labels in this section.
  */
 	. = 0x100
 	.globl __start_interrupts
@@ -200,7 +211,20 @@ data_access_slb_pSeries:
 	mfspr	r10,SPRN_SPRG1
 	std	r10,PACA_EXSLB+EX_R13(r13)
 	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	b	.slb_miss_realmode	/* Rel. branch works in real mode */
+#ifndef CONFIG_RELOCATABLE
+	b	.slb_miss_realmode
+#else
+	/*
+	 * We can't just use a direct branch to .slb_miss_realmode
+	 * because the distance from here to there depends on where
+	 * the kernel ends up being put.
+	 */
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, .slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
 
 	STD_EXCEPTION_PSERIES(0x400, instruction_access)
 
@@ -225,7 +249,15 @@ instruction_access_slb_pSeries:
 	mfspr	r10,SPRN_SPRG1
 	std	r10,PACA_EXSLB+EX_R13(r13)
 	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	b	.slb_miss_realmode	/* Rel. branch works in real mode */
+#ifndef CONFIG_RELOCATABLE
+	b	.slb_miss_realmode
+#else
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, .slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
 
 	MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt)
 	STD_EXCEPTION_PSERIES(0x600, alignment)
@@ -244,14 +276,12 @@ BEGIN_FTR_SECTION
 	beq-	1f
 END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	mr	r9,r13
-	mfmsr	r10
 	mfspr	r13,SPRN_SPRG3
 	mfspr	r11,SPRN_SRR0
-	clrrdi	r12,r13,32
+	ld	r12,PACAKBASE(r13)
-	oris	r12,r12,system_call_common@h
+	ld	r10,PACAKMSR(r13)
-	ori	r12,r12,system_call_common@l
+	LOAD_HANDLER(r12, system_call_entry)
 	mtspr	SPRN_SRR0,r12
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
 	mfspr	r12,SPRN_SRR1
 	mtspr	SPRN_SRR1,r10
 	rfid
@@ -379,7 +409,10 @@ __end_interrupts:
 
 /*
  * Code from here down to __end_handlers is invoked from the
- * exception prologs above.
+ * exception prologs above.  Because the prologs assemble the
+ * addresses of these handlers using the LOAD_HANDLER macro,
+ * which uses an addi instruction, these handlers must be in
+ * the first 32k of the kernel image.
  */
 
 /*** Common interrupt handlers ***/
@@ -419,6 +452,10 @@ machine_check_common:
 	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception)
 #endif /* CONFIG_CBE_RAS */
 
+	.align	7
+system_call_entry:
+	b	system_call_common
+
 /*
  * Here we have detected that the kernel stack pointer is bad.
  * R9 contains the saved CR, r13 points to the paca,
@@ -562,6 +599,9 @@ unrecov_user_slb:
  */
 _GLOBAL(slb_miss_realmode)
 	mflr	r10
+#ifdef CONFIG_RELOCATABLE
+	mtctr	r11
+#endif
 
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
@@ -612,11 +652,10 @@ BEGIN_FW_FTR_SECTION
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
 #endif /* CONFIG_PPC_ISERIES */
 	mfspr	r11,SPRN_SRR0
-	clrrdi	r10,r13,32
+	ld	r10,PACAKBASE(r13)
 	LOAD_HANDLER(r10,unrecov_slb)
 	mtspr	SPRN_SRR0,r10
-	mfmsr	r10
+	ld	r10,PACAKMSR(r13)
-	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
 	mtspr	SPRN_SRR1,r10
 	rfid
 	b	.

arch/powerpc/kernel/paca.c

@@ -79,6 +79,8 @@ void __init initialise_pacas(void)
 		new_paca->lock_token = 0x8000;
 		new_paca->paca_index = cpu;
 		new_paca->kernel_toc = kernel_toc;
+		new_paca->kernelbase = KERNELBASE;
+		new_paca->kernel_msr = MSR_KERNEL;
 		new_paca->hw_cpu_id = 0xffff;
 		new_paca->slb_shadow_ptr = &slb_shadow[cpu];
 		new_paca->__current = &init_task;

arch/powerpc/kernel/prom_init.c

@@ -1321,7 +1321,7 @@ static void __init prom_initialize_tce_table(void)
  *
  * -- Cort
  */
-extern void __secondary_hold(void);
+extern char __secondary_hold;
 extern unsigned long __secondary_hold_spinloop;
 extern unsigned long __secondary_hold_acknowledge;
 
@@ -1342,13 +1342,7 @@ static void __init prom_hold_cpus(void)
 		= (void *) LOW_ADDR(__secondary_hold_spinloop);
 	unsigned long *acknowledge
 		= (void *) LOW_ADDR(__secondary_hold_acknowledge);
-#ifdef CONFIG_PPC64
-	/* __secondary_hold is actually a descriptor, not the text address */
-	unsigned long secondary_hold
-		= __pa(*PTRRELOC((unsigned long *)__secondary_hold));
-#else
 	unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
-#endif
 
 	prom_debug("prom_hold_cpus: start...\n");
 	prom_debug("    1) spinloop       = 0x%x\n", (unsigned long)spinloop);

arch/powerpc/kernel/setup_64.c

@@ -255,9 +255,11 @@ void early_setup_secondary(void)
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
+extern unsigned long __secondary_hold_spinloop;
+extern void generic_secondary_smp_init(void);
+
 void smp_release_cpus(void)
 {
-	extern unsigned long __secondary_hold_spinloop;
 	unsigned long *ptr;
 
 	DBG(" -> smp_release_cpus()\n");
@@ -266,12 +268,11 @@ void smp_release_cpus(void)
 	 * all now so they can start to spin on their individual paca
 	 * spinloops. For non SMP kernels, the secondary cpus never get out
 	 * of the common spinloop.
-	 * This is useless but harmless on iSeries, secondaries are already
+	 */
-	 * waiting on their paca spinloops. */
 
 	ptr  = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
 			- PHYSICAL_START);
-	*ptr = 1;
+	*ptr = __pa(generic_secondary_smp_init);
 	mb();
 
 	DBG(" <- smp_release_cpus()\n");