Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc

Pull sparc updates from David Miller:
 "Mostly more sparc64 THP bug fixes, and a refactoring of SMP bootup on
  sparc32 from Sam Ravnborg."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc:
  sparc32: refactor smp boot
  sparc64: Fix huge PMD to PTE translation for sun4u in TLB miss handler.
  sparc64: Fix tsb_grow() in atomic context.
  sparc64: Handle hugepage TSB being NULL.
  sparc64: Fix gfp_flags setting in tsb_grow().

arch/sparc/include/asm/hugetlb.h

@@ -12,7 +12,6 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 
 static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
 {
-	hugetlb_setup(mm);
 }
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,

arch/sparc/include/asm/page_64.h

@@ -27,8 +27,8 @@
 #ifndef __ASSEMBLY__
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-struct mm_struct;
-extern void hugetlb_setup(struct mm_struct *mm);
+struct pt_regs;
+extern void hugetlb_setup(struct pt_regs *regs);
 #endif
 
 #define WANT_PAGE_VIRTUAL

arch/sparc/include/asm/tsb.h

@@ -157,17 +157,26 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	add		REG1, REG2, REG1;
 
-	/* This macro exists only to make the PMD translator below easier
-	 * to read.  It hides the ELF section switch for the sun4v code
-	 * patching.
+	/* These macros exists only to make the PMD translator below
+	 * easier to read.  It hides the ELF section switch for the
+	 * sun4v code patching.
 	 */
-#define OR_PTE_BIT(REG, NAME)				\
+#define OR_PTE_BIT_1INSN(REG, NAME)			\
 661:	or		REG, _PAGE_##NAME##_4U, REG;	\
 	.section	.sun4v_1insn_patch, "ax";	\
 	.word		661b;				\
 	or		REG, _PAGE_##NAME##_4V, REG;	\
 	.previous;
 
+#define OR_PTE_BIT_2INSN(REG, TMP, NAME)		\
+661:	sethi		%hi(_PAGE_##NAME##_4U), TMP;	\
+	or		REG, TMP, REG;			\
+	.section	.sun4v_2insn_patch, "ax";	\
+	.word		661b;				\
+	mov		-1, TMP;			\
+	or		REG, _PAGE_##NAME##_4V, REG;	\
+	.previous;
+
 	/* Load into REG the PTE value for VALID, CACHE, and SZHUGE.  */
 #define BUILD_PTE_VALID_SZHUGE_CACHE(REG)				   \
 661:	sethi		%uhi(_PAGE_VALID|_PAGE_SZHUGE_4U), REG;		   \
@@ -214,12 +223,13 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 andn		REG1, PMD_HUGE_PROTBITS, REG2;			      \
 	sllx		REG2, PMD_PADDR_SHIFT, REG2;			      \
 	/* REG2 now holds PFN << PAGE_SHIFT */				      \
-	andcc		REG1, PMD_HUGE_EXEC, %g0;			      \
-	bne,a,pt	%xcc, 1f;					      \
-	 OR_PTE_BIT(REG2, EXEC);					      \
-1:	andcc		REG1, PMD_HUGE_WRITE, %g0;			      \
+	andcc		REG1, PMD_HUGE_WRITE, %g0;			      \
 	bne,a,pt	%xcc, 1f;					      \
-	 OR_PTE_BIT(REG2, W);						      \
+	 OR_PTE_BIT_1INSN(REG2, W);					      \
+1:	andcc		REG1, PMD_HUGE_EXEC, %g0;			      \
+	be,pt		%xcc, 1f;					      \
+	 nop;								      \
+	OR_PTE_BIT_2INSN(REG2, REG1, EXEC);				      \
 	/* REG1 can now be clobbered, build final PTE */		      \
 1:	BUILD_PTE_VALID_SZHUGE_CACHE(REG1);				      \
 	ba,pt		%xcc, PTE_LABEL;				      \

arch/sparc/kernel/kernel.h

@@ -48,6 +48,10 @@ extern void sun4m_init_IRQ(void);
 extern void sun4m_unmask_profile_irq(void);
 extern void sun4m_clear_profile_irq(int cpu);
 
+/* sun4m_smp.c */
+void sun4m_cpu_pre_starting(void *arg);
+void sun4m_cpu_pre_online(void *arg);
+
 /* sun4d_irq.c */
 extern spinlock_t sun4d_imsk_lock;
 
@@ -60,6 +64,14 @@ extern int show_sun4d_interrupts(struct seq_file *, void *);
 extern void sun4d_distribute_irqs(void);
 extern void sun4d_free_irq(unsigned int irq, void *dev_id);
 
+/* sun4d_smp.c */
+void sun4d_cpu_pre_starting(void *arg);
+void sun4d_cpu_pre_online(void *arg);
+
+/* leon_smp.c */
+void leon_cpu_pre_starting(void *arg);
+void leon_cpu_pre_online(void *arg);
+
 /* head_32.S */
 extern unsigned int t_nmi[];
 extern unsigned int linux_trap_ipi15_sun4d[];

arch/sparc/kernel/leon_smp.c

@@ -69,31 +69,19 @@ static inline unsigned long do_swap(volatile unsigned long *ptr,
 	return val;
 }
 
-void __cpuinit leon_callin(void)
+void __cpuinit leon_cpu_pre_starting(void *arg)
 {
-	int cpuid = hard_smp_processor_id();
-
-	local_ops->cache_all();
-	local_ops->tlb_all();
 	leon_configure_cache_smp();
+}
 
-	notify_cpu_starting(cpuid);
-
-	/* Get our local ticker going. */
-	register_percpu_ce(cpuid);
-
-	calibrate_delay();
-	smp_store_cpu_info(cpuid);
-
-	local_ops->cache_all();
-	local_ops->tlb_all();
+void __cpuinit leon_cpu_pre_online(void *arg)
+{
+	int cpuid = hard_smp_processor_id();
 
-	/*
-	 * Unblock the master CPU _only_ when the scheduler state
-	 * of all secondary CPUs will be up-to-date, so after
-	 * the SMP initialization the master will be just allowed
-	 * to call the scheduler code.
-	 * Allow master to continue.
+	/* Allow master to continue. The master will then give us the
+	 * go-ahead by setting the smp_commenced_mask and will wait without
+	 * timeouts until our setup is completed fully (signified by
+	 * our bit being set in the cpu_online_mask).
 	 */
 	do_swap(&cpu_callin_map[cpuid], 1);
 
@@ -110,9 +98,6 @@ void __cpuinit leon_callin(void)
 
 	while (!cpumask_test_cpu(cpuid, &smp_commenced_mask))
 		mb();
-
-	local_irq_enable();
-	set_cpu_online(cpuid, true);
 }
 
 /*

arch/sparc/kernel/smp_32.c

@@ -20,6 +20,7 @@
 #include <linux/seq_file.h>
 #include <linux/cache.h>
 #include <linux/delay.h>
+#include <linux/cpu.h>
 
 #include <asm/ptrace.h>
 #include <linux/atomic.h>
@@ -32,8 +33,10 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/cpudata.h>
+#include <asm/timer.h>
 #include <asm/leon.h>
 
+#include "kernel.h"
 #include "irq.h"
 
 volatile unsigned long cpu_callin_map[NR_CPUS] __cpuinitdata = {0,};
@@ -294,6 +297,89 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	return ret;
 }
 
+void __cpuinit arch_cpu_pre_starting(void *arg)
+{
+	local_ops->cache_all();
+	local_ops->tlb_all();
+
+	switch(sparc_cpu_model) {
+	case sun4m:
+		sun4m_cpu_pre_starting(arg);
+		break;
+	case sun4d:
+		sun4d_cpu_pre_starting(arg);
+		break;
+	case sparc_leon:
+		leon_cpu_pre_starting(arg);
+		break;
+	default:
+		BUG();
+	}
+}
+
+void __cpuinit arch_cpu_pre_online(void *arg)
+{
+	unsigned int cpuid = hard_smp_processor_id();
+
+	register_percpu_ce(cpuid);
+
+	calibrate_delay();
+	smp_store_cpu_info(cpuid);
+
+	local_ops->cache_all();
+	local_ops->tlb_all();
+
+	switch(sparc_cpu_model) {
+	case sun4m:
+		sun4m_cpu_pre_online(arg);
+		break;
+	case sun4d:
+		sun4d_cpu_pre_online(arg);
+		break;
+	case sparc_leon:
+		leon_cpu_pre_online(arg);
+		break;
+	default:
+		BUG();
+	}
+}
+
+void __cpuinit sparc_start_secondary(void *arg)
+{
+	unsigned int cpu;
+
+	/*
+	 * SMP booting is extremely fragile in some architectures. So run
+	 * the cpu initialization code first before anything else.
+	 */
+	arch_cpu_pre_starting(arg);
+
+	preempt_disable();
+	cpu = smp_processor_id();
+
+	/* Invoke the CPU_STARTING notifier callbacks */
+	notify_cpu_starting(cpu);
+
+	arch_cpu_pre_online(arg);
+
+	/* Set the CPU in the cpu_online_mask */
+	set_cpu_online(cpu, true);
+
+	/* Enable local interrupts now */
+	local_irq_enable();
+
+	wmb();
+	cpu_idle();
+
+	/* We should never reach here! */
+	BUG();
+}
+
+void __cpuinit smp_callin(void)
+{
+	sparc_start_secondary(NULL);
+}
+
 void smp_bogo(struct seq_file *m)
 {
 	int i;

arch/sparc/kernel/sun4d_smp.c

@@ -50,37 +50,30 @@ static inline void show_leds(int cpuid)
 			      "i" (ASI_M_CTL));
 }
 
-void __cpuinit smp4d_callin(void)
+void __cpuinit sun4d_cpu_pre_starting(void *arg)
 {
 	int cpuid = hard_smp_processor_id();
-	unsigned long flags;
 
 	/* Show we are alive */
 	cpu_leds[cpuid] = 0x6;
 	show_leds(cpuid);
 
 	/* Enable level15 interrupt, disable level14 interrupt for now */
 	cc_set_imsk((cc_get_imsk() & ~0x8000) | 0x4000);
+}
 
-	local_ops->cache_all();
-	local_ops->tlb_all();
+void __cpuinit sun4d_cpu_pre_online(void *arg)
+{
+	unsigned long flags;
+	int cpuid;
 
-	notify_cpu_starting(cpuid);
-	/*
-	 * Unblock the master CPU _only_ when the scheduler state
+	cpuid = hard_smp_processor_id();
+
+	/* Unblock the master CPU _only_ when the scheduler state
 	 * of all secondary CPUs will be up-to-date, so after
 	 * the SMP initialization the master will be just allowed
 	 * to call the scheduler code.
 	 */
-	/* Get our local ticker going. */
-	register_percpu_ce(cpuid);
-
-	calibrate_delay();
-	smp_store_cpu_info(cpuid);
-	local_ops->cache_all();
-	local_ops->tlb_all();
-
-	/* Allow master to continue. */
 	sun4d_swap((unsigned long *)&cpu_callin_map[cpuid], 1);
 	local_ops->cache_all();
 	local_ops->tlb_all();
@@ -106,16 +99,12 @@ void __cpuinit smp4d_callin(void)
 	local_ops->cache_all();
 	local_ops->tlb_all();
 
-	local_irq_enable();	/* We don't allow PIL 14 yet */
-
 	while (!cpumask_test_cpu(cpuid, &smp_commenced_mask))
 		barrier();
 
 	spin_lock_irqsave(&sun4d_imsk_lock, flags);
 	cc_set_imsk(cc_get_imsk() & ~0x4000); /* Allow PIL 14 as well */
 	spin_unlock_irqrestore(&sun4d_imsk_lock, flags);
-	set_cpu_online(cpuid, true);
-
 }
 
 /*

arch/sparc/kernel/sun4m_smp.c

@@ -34,30 +34,19 @@ swap_ulong(volatile unsigned long *ptr, unsigned long val)
 	return val;
 }
 
-void __cpuinit smp4m_callin(void)
+void __cpuinit sun4m_cpu_pre_starting(void *arg)
 {
-	int cpuid = hard_smp_processor_id();
-
-	local_ops->cache_all();
-	local_ops->tlb_all();
-
-	notify_cpu_starting(cpuid);
-
-	register_percpu_ce(cpuid);
-
-	calibrate_delay();
-	smp_store_cpu_info(cpuid);
+}
 
-	local_ops->cache_all();
-	local_ops->tlb_all();
+void __cpuinit sun4m_cpu_pre_online(void *arg)
+{
+	int cpuid = hard_smp_processor_id();
 
-	/*
-	 * Unblock the master CPU _only_ when the scheduler state
-	 * of all secondary CPUs will be up-to-date, so after
-	 * the SMP initialization the master will be just allowed
-	 * to call the scheduler code.
+	/* Allow master to continue. The master will then give us the
+	 * go-ahead by setting the smp_commenced_mask and will wait without
+	 * timeouts until our setup is completed fully (signified by
+	 * our bit being set in the cpu_online_mask).
 	 */
-	/* Allow master to continue. */
 	swap_ulong(&cpu_callin_map[cpuid], 1);
 
 	/* XXX: What's up with all the flushes? */
@@ -75,10 +64,6 @@ void __cpuinit smp4m_callin(void)
 
 	while (!cpumask_test_cpu(cpuid, &smp_commenced_mask))
 		mb();
-
-	local_irq_enable();
-
-	set_cpu_online(cpuid, true);
 }
 
 /*