Merge branch 'fixes' into next

There's a non-trivial dependency between some commits we want to put in
next and the KVM prefetch work around that went into fixes. So merge
fixes into next.

arch/powerpc/Makefile

@@ -59,6 +59,19 @@ machine-$(CONFIG_PPC64) += 64
 machine-$(CONFIG_CPU_LITTLE_ENDIAN) += le
 UTS_MACHINE := $(subst $(space),,$(machine-y))
 
+# XXX This needs to be before we override LD below
+ifdef CONFIG_PPC32
+KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
+else
+ifeq ($(call ld-ifversion, -ge, 225000000, y),y)
+# Have the linker provide sfpr if possible.
+# There is a corresponding test in arch/powerpc/lib/Makefile
+KBUILD_LDFLAGS_MODULE += --save-restore-funcs
+else
+KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
+endif
+endif
+
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 override LD	+= -EL
 LDEMULATION	:= lppc
@@ -190,18 +203,6 @@ else
 CHECKFLAGS	+= -D__LITTLE_ENDIAN__
 endif
 
-ifdef CONFIG_PPC32
-KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
-else
-ifeq ($(call ld-ifversion, -ge, 225000000, y),y)
-# Have the linker provide sfpr if possible.
-# There is a corresponding test in arch/powerpc/lib/Makefile
-KBUILD_LDFLAGS_MODULE += --save-restore-funcs
-else
-KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
-endif
-endif
-
 ifeq ($(CONFIG_476FPE_ERR46),y)
 	KBUILD_LDFLAGS_MODULE += --ppc476-workaround \
 		-T $(srctree)/arch/powerpc/platforms/44x/ppc476_modules.lds

arch/powerpc/boot/Makefile

@@ -25,12 +25,20 @@ compress-$(CONFIG_KERNEL_XZ)   := CONFIG_KERNEL_XZ
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -Os -msoft-float -pipe \
 		 -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 -isystem $(shell $(CROSS32CC) -print-file-name=include) \
 		 -D$(compress-y)
 
+BOOTCC := $(CC)
 ifdef CONFIG_PPC64_BOOT_WRAPPER
 BOOTCFLAGS	+= -m64
+else
+BOOTCFLAGS	+= -m32
+ifdef CROSS32_COMPILE
+    BOOTCC := $(CROSS32_COMPILE)gcc
+endif
 endif
+
+BOOTCFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
+
 ifdef CONFIG_CPU_BIG_ENDIAN
 BOOTCFLAGS	+= -mbig-endian
 else
@@ -183,10 +191,10 @@ clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \
 		empty.c zImage.coff.lds zImage.ps3.lds zImage.lds
 
 quiet_cmd_bootcc = BOOTCC  $@
-      cmd_bootcc = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
+      cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
 
 quiet_cmd_bootas = BOOTAS  $@
-      cmd_bootas = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
+      cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
 
 quiet_cmd_bootar = BOOTAR  $@
       cmd_bootar = $(CROSS32AR) -cr$(KBUILD_ARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@

arch/powerpc/configs/powernv_defconfig

@@ -293,7 +293,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y

arch/powerpc/configs/ppc64_defconfig

@@ -324,7 +324,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y

arch/powerpc/configs/pseries_defconfig

@@ -291,7 +291,8 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -59,13 +59,14 @@ extern struct patb_entry *partition_tb;
 #define PRTS_MASK	0x1f		/* process table size field */
 #define PRTB_MASK	0x0ffffffffffff000UL
 
-/*
- * Limit process table to PAGE_SIZE table. This
- * also limit the max pid we can support.
- * MAX_USER_CONTEXT * 16 bytes of space.
- */
-#define PRTB_SIZE_SHIFT	(CONTEXT_BITS + 4)
-#define PRTB_ENTRIES	(1ul << CONTEXT_BITS)
+/* Number of supported PID bits */
+extern unsigned int mmu_pid_bits;
+
+/* Base PID to allocate from */
+extern unsigned int mmu_base_pid;
+
+#define PRTB_SIZE_SHIFT	(mmu_pid_bits + 4)
+#define PRTB_ENTRIES	(1ul << mmu_pid_bits)
 
 /*
  * Power9 currently only support 64K partition table size.

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -614,9 +614,17 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP);
 }
 
+/*
+ * This is potentially called with a pmd as the argument, in which case it's not
+ * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set.
+ * That's because the bit we use for _PAGE_DEVMAP is not reserved for software
+ * use in page directory entries (ie. non-ptes).
+ */
 static inline int pte_devmap(pte_t pte)
 {
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DEVMAP));
+	u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE);
+
+	return (pte_raw(pte) & mask) == mask;
 }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)

arch/powerpc/include/asm/mmu_context.h

@@ -67,6 +67,12 @@ extern void __destroy_context(unsigned long context_id);
 extern void mmu_context_init(void);
 #endif
 
+#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
+extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
+#else
+static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
+#endif
+
 extern void switch_cop(struct mm_struct *next);
 extern int use_cop(unsigned long acop, struct mm_struct *mm);
 extern void drop_cop(unsigned long acop, struct mm_struct *mm);
@@ -79,10 +85,32 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev,
 				      struct mm_struct *next,
 				      struct task_struct *tsk)
 {
+	bool new_on_cpu = false;
+
 	/* Mark this context has been used on the new CPU */
-	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next)))
+	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) {
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
 
+		/*
+		 * This full barrier orders the store to the cpumask above vs
+		 * a subsequent operation which allows this CPU to begin loading
+		 * translations for next.
+		 *
+		 * When using the radix MMU that operation is the load of the
+		 * MMU context id, which is then moved to SPRN_PID.
+		 *
+		 * For the hash MMU it is either the first load from slb_cache
+		 * in switch_slb(), and/or the store of paca->mm_ctx_id in
+		 * copy_mm_to_paca().
+		 *
+		 * On the read side the barrier is in pte_xchg(), which orders
+		 * the store to the PTE vs the load of mm_cpumask.
+		 */
+		smp_mb();
+
+		new_on_cpu = true;
+	}
+
 	/* 32-bit keeps track of the current PGDIR in the thread struct */
 #ifdef CONFIG_PPC32
 	tsk->thread.pgdir = next->pgd;
@@ -103,6 +131,10 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev,
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		asm volatile ("dssall");
 #endif /* CONFIG_ALTIVEC */
+
+	if (new_on_cpu)
+		radix_kvm_prefetch_workaround(next);
+
 	/*
 	 * The actual HW switching method differs between the various
 	 * sub architectures. Out of line for now

arch/powerpc/include/asm/pgtable-be-types.h

@@ -87,6 +87,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
 	unsigned long *p = (unsigned long *)ptep;
 	__be64 prev;
 
+	/* See comment in switch_mm_irqs_off() */
 	prev = (__force __be64)__cmpxchg_u64(p, (__force unsigned long)pte_raw(old),
 					     (__force unsigned long)pte_raw(new));
 

arch/powerpc/include/asm/pgtable-types.h

@@ -62,6 +62,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
 {
 	unsigned long *p = (unsigned long *)ptep;
 
+	/* See comment in switch_mm_irqs_off() */
 	return pte_val(old) == __cmpxchg_u64(p, pte_val(old), pte_val(new));
 }
 #endif

arch/powerpc/kernel/entry_64.S

@@ -223,17 +223,27 @@ system_call_exit:
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	.Lsyscall_exit_work
 
-	/* If MSR_FP and MSR_VEC are set in user msr, then no need to restore */
-	li	r7,MSR_FP
+	andi.	r0,r8,MSR_FP
+	beq 2f
 #ifdef CONFIG_ALTIVEC
-	oris	r7,r7,MSR_VEC@h
+	andis.	r0,r8,MSR_VEC@h
+	bne	3f
+#endif
+2:	addi    r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_PPC_BOOK3S
+	li	r10,MSR_RI
+	mtmsrd	r10,1		/* Restore RI */
 #endif
-	and	r0,r8,r7
-	cmpd	r0,r7
-	bne	.Lsyscall_restore_math
-.Lsyscall_restore_math_cont:
+	bl	restore_math
+#ifdef CONFIG_PPC_BOOK3S
+	li	r11,0
+	mtmsrd	r11,1
+#endif
+	ld	r8,_MSR(r1)
+	ld	r3,RESULT(r1)
+	li	r11,-MAX_ERRNO
 
-	cmpld	r3,r11
+3:	cmpld	r3,r11
 	ld	r5,_CCR(r1)
 	bge-	.Lsyscall_error
 .Lsyscall_error_cont:
@@ -267,40 +277,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	std	r5,_CCR(r1)
 	b	.Lsyscall_error_cont
 
-.Lsyscall_restore_math:
-	/*
-	 * Some initial tests from restore_math to avoid the heavyweight
-	 * C code entry and MSR manipulations.
-	 */
-	LOAD_REG_IMMEDIATE(r0, MSR_TS_MASK)
-	and.	r0,r0,r8
-	bne	1f
-
-	ld	r7,PACACURRENT(r13)
-	lbz	r0,THREAD+THREAD_LOAD_FP(r7)
-#ifdef CONFIG_ALTIVEC
-	lbz	r6,THREAD+THREAD_LOAD_VEC(r7)
-	add	r0,r0,r6
-#endif
-	cmpdi	r0,0
-	beq	.Lsyscall_restore_math_cont
-
-1:	addi    r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_PPC_BOOK3S
-	li	r10,MSR_RI
-	mtmsrd	r10,1		/* Restore RI */
-#endif
-	bl	restore_math
-#ifdef CONFIG_PPC_BOOK3S
-	li	r11,0
-	mtmsrd	r11,1
-#endif
-	/* Restore volatiles, reload MSR from updated one */
-	ld	r8,_MSR(r1)
-	ld	r3,RESULT(r1)
-	li	r11,-MAX_ERRNO
-	b	.Lsyscall_restore_math_cont
-
 /* Traced system call support */
 .Lsyscall_dotrace:
 	bl	save_nvgprs

arch/powerpc/kernel/exceptions-64s.S

@@ -1325,10 +1325,18 @@ EXC_VIRT_NONE(0x5800, 0x100)
 	std	r10,PACA_EXGEN+EX_R13(r13);		\
 	EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H)
 
+/*
+ * Branch to soft_nmi_interrupt using the emergency stack. The emergency
+ * stack is one that is usable by maskable interrupts so long as MSR_EE
+ * remains off. It is used for recovery when something has corrupted the
+ * normal kernel stack, for example. The "soft NMI" must not use the process
+ * stack because we want irq disabled sections to avoid touching the stack
+ * at all (other than PMU interrupts), so use the emergency stack for this,
+ * and run it entirely with interrupts hard disabled.
+ */
 EXC_COMMON_BEGIN(soft_nmi_common)
 	mr	r10,r1
 	ld	r1,PACAEMERGSP(r13)
-	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
 	EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900,
 			system_reset, soft_nmi_interrupt,

arch/powerpc/kernel/idle_book3s.S

@@ -514,11 +514,17 @@ pnv_restore_hyp_resource_arch300:
 	/*
 	 * Workaround for POWER9, if we lost resources, the ERAT
 	 * might have been mixed up and needs flushing. We also need
-	 * to reload MMCR0 (see comment above).
+	 * to reload MMCR0 (see comment above). We also need to set
+	 * then clear bit 60 in MMCRA to ensure the PMU starts running.
 	 */
 	blt	cr3,1f
 	PPC_INVALIDATE_ERAT
 	ld	r1,PACAR1(r13)
+	mfspr	r4,SPRN_MMCRA
+	ori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4
+	xori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4
 	ld	r4,_MMCR0(r1)
 	mtspr	SPRN_MMCR0,r4
 1:

arch/powerpc/kernel/irq.c

@@ -145,6 +145,19 @@ notrace unsigned int __check_irq_replay(void)
 
 	/* Clear bit 0 which we wouldn't clear otherwise */
 	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	if (happened & PACA_IRQ_HARD_DIS) {
+		/*
+		 * We may have missed a decrementer interrupt if hard disabled.
+		 * Check the decrementer register in case we had a rollover
+		 * while hard disabled.
+		 */
+		if (!(happened & PACA_IRQ_DEC)) {
+			if (decrementer_check_overflow()) {
+				local_paca->irq_happened |= PACA_IRQ_DEC;
+				happened |= PACA_IRQ_DEC;
+			}
+		}
+	}
 
 	/*
 	 * Force the delivery of pending soft-disabled interrupts on PS3.
@@ -170,7 +183,7 @@ notrace unsigned int __check_irq_replay(void)
 	 * in case we also had a rollover while hard disabled
 	 */
 	local_paca->irq_happened &= ~PACA_IRQ_DEC;
-	if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
+	if (happened & PACA_IRQ_DEC)
 		return 0x900;
 
 	/* Finally check if an external interrupt happened */

arch/powerpc/kernel/process.c

@@ -363,7 +363,8 @@ void enable_kernel_vsx(void)
 
 	cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
 
-	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) {
+	if (current->thread.regs &&
+	    (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) {
 		check_if_tm_restore_required(current);
 		/*
 		 * If a thread has already been reclaimed then the
@@ -383,7 +384,7 @@ void flush_vsx_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
 		preempt_disable();
-		if (tsk->thread.regs->msr & MSR_VSX) {
+		if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) {
 			BUG_ON(tsk != current);
 			giveup_vsx(tsk);
 		}
@@ -505,10 +506,6 @@ void restore_math(struct pt_regs *regs)
 {
 	unsigned long msr;
 
-	/*
-	 * Syscall exit makes a similar initial check before branching
-	 * to restore_math. Keep them in synch.
-	 */
 	if (!msr_tm_active(regs->msr) &&
 		!current->thread.load_fp && !loadvec(current->thread))
 		return;

arch/powerpc/kernel/ptrace.c

@@ -127,12 +127,19 @@ static void flush_tmregs_to_thread(struct task_struct *tsk)
 	 * If task is not current, it will have been flushed already to
 	 * it's thread_struct during __switch_to().
 	 *
-	 * A reclaim flushes ALL the state.
+	 * A reclaim flushes ALL the state or if not in TM save TM SPRs
+	 * in the appropriate thread structures from live.
 	 */
 
-	if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
-		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	if (tsk != current)
+		return;
 
+	if (MSR_TM_SUSPENDED(mfmsr())) {
+		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	} else {
+		tm_enable();
+		tm_save_sprs(&(tsk->thread));
+	}
 }
 #else
 static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }

arch/powerpc/kernel/smp.c

@@ -351,7 +351,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 	hard_irq_disable();
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
 		raw_local_irq_restore(*flags);
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 		raw_local_irq_save(*flags);
 		hard_irq_disable();
 	}
@@ -360,7 +360,7 @@ static void nmi_ipi_lock_start(unsigned long *flags)
 static void nmi_ipi_lock(void)
 {
 	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
-		cpu_relax();
+		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
 }
 
 static void nmi_ipi_unlock(void)
@@ -475,7 +475,7 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
 	nmi_ipi_lock_start(&flags);
 	while (nmi_ipi_busy_count) {
 		nmi_ipi_unlock_end(&flags);
-		cpu_relax();
+		spin_until_cond(nmi_ipi_busy_count == 0);
 		nmi_ipi_lock_start(&flags);
 	}
 
@@ -1003,21 +1003,13 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 	{ NULL, },
 };
 
-static __init long smp_setup_cpu_workfn(void *data __always_unused)
-{
-	smp_ops->setup_cpu(boot_cpuid);
-	return 0;
-}
-
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	/*
-	 * We want the setup_cpu() here to be called on the boot CPU, but
-	 * init might run on any CPU, so make sure it's invoked on the boot
-	 * CPU.
+	 * We are running pinned to the boot CPU, see rest_init().
 	 */
 	if (smp_ops && smp_ops->setup_cpu)
-		work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
+		smp_ops->setup_cpu(boot_cpuid);
 
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();

arch/powerpc/kernel/watchdog.c

@@ -71,15 +71,20 @@ static inline void wd_smp_lock(unsigned long *flags)
 	 * This may be called from low level interrupt handlers at some
 	 * point in future.
 	 */
-	local_irq_save(*flags);
-	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock)))
-		cpu_relax();
+	raw_local_irq_save(*flags);
+	hard_irq_disable(); /* Make it soft-NMI safe */
+	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) {
+		raw_local_irq_restore(*flags);
+		spin_until_cond(!test_bit(0, &__wd_smp_lock));
+		raw_local_irq_save(*flags);
+		hard_irq_disable();
+	}
 }
 
 static inline void wd_smp_unlock(unsigned long *flags)
 {
 	clear_bit_unlock(0, &__wd_smp_lock);
-	local_irq_restore(*flags);
+	raw_local_irq_restore(*flags);
 }
 
 static void wd_lockup_ipi(struct pt_regs *regs)
@@ -96,10 +101,10 @@ static void wd_lockup_ipi(struct pt_regs *regs)
 		nmi_panic(regs, "Hard LOCKUP");
 }
 
-static void set_cpu_stuck(int cpu, u64 tb)
+static void set_cpumask_stuck(const struct cpumask *cpumask, u64 tb)
 {
-	cpumask_set_cpu(cpu, &wd_smp_cpus_stuck);
-	cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+	cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask);
+	cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask);
 	if (cpumask_empty(&wd_smp_cpus_pending)) {
 		wd_smp_last_reset_tb = tb;
 		cpumask_andnot(&wd_smp_cpus_pending,
@@ -107,6 +112,10 @@ static void set_cpu_stuck(int cpu, u64 tb)
 				&wd_smp_cpus_stuck);
 	}
 }
+static void set_cpu_stuck(int cpu, u64 tb)
+{
+	set_cpumask_stuck(cpumask_of(cpu), tb);
+}
 
 static void watchdog_smp_panic(int cpu, u64 tb)
 {
@@ -135,11 +144,9 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 	}
 	smp_flush_nmi_ipi(1000000);
 
-	/* Take the stuck CPU out of the watch group */
-	for_each_cpu(c, &wd_smp_cpus_pending)
-		set_cpu_stuck(c, tb);
+	/* Take the stuck CPUs out of the watch group */
+	set_cpumask_stuck(&wd_smp_cpus_pending, tb);
 
-out:
 	wd_smp_unlock(&flags);
 
 	printk_safe_flush();
@@ -152,6 +159,11 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 
 	if (hardlockup_panic)
 		nmi_panic(NULL, "Hard LOCKUP");
+
+	return;
+
+out:
+	wd_smp_unlock(&flags);
 }
 
 static void wd_smp_clear_cpu_pending(int cpu, u64 tb)
@@ -261,8 +273,10 @@ static void wd_timer_fn(unsigned long data)
 
 void arch_touch_nmi_watchdog(void)
 {
+	unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000;
 	int cpu = smp_processor_id();
 
+	if (get_tb() - per_cpu(wd_timer_tb, cpu) >= ticks)
 		watchdog_timer_interrupt(cpu);
 }
 EXPORT_SYMBOL(arch_touch_nmi_watchdog);
@@ -286,6 +300,8 @@ static void stop_watchdog_timer_on(unsigned int cpu)
 
 static int start_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
 		WARN_ON(1);
 		return 0;
@@ -300,12 +316,14 @@ static int start_wd_on_cpu(unsigned int cpu)
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
+	wd_smp_lock(&flags);
 	cpumask_set_cpu(cpu, &wd_cpus_enabled);
 	if (cpumask_weight(&wd_cpus_enabled) == 1) {
 		cpumask_set_cpu(cpu, &wd_smp_cpus_pending);
 		wd_smp_last_reset_tb = get_tb();
 	}
-	smp_wmb();
+	wd_smp_unlock(&flags);
+
 	start_watchdog_timer_on(cpu);
 
 	return 0;
@@ -313,12 +331,17 @@ static int start_wd_on_cpu(unsigned int cpu)
 
 static int stop_wd_on_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
 		return 0; /* Can happen in CPU unplug case */
 
 	stop_watchdog_timer_on(cpu);
 
+	wd_smp_lock(&flags);
 	cpumask_clear_cpu(cpu, &wd_cpus_enabled);
+	wd_smp_unlock(&flags);
+
 	wd_smp_clear_cpu_pending(cpu, get_tb());
 
 	return 0;

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1443,12 +1443,14 @@ mc_cont:
 	ori	r6,r6,1
 	mtspr	SPRN_CTRLT,r6
 4:
-	/* Read the guest SLB and save it away */
+	/* Check if we are running hash or radix and store it in cr2 */
 	ld	r5, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r5)
-	cmpwi	r0, 0
+	cmpwi	cr2,r0,0
+
+	/* Read the guest SLB and save it away */
 	li	r5, 0
-	bne	3f			/* for radix, save 0 entries */
+	bne	cr2, 3f			/* for radix, save 0 entries */
 	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
 	mtctr	r0
 	li	r6,0
@@ -1712,11 +1714,6 @@ BEGIN_FTR_SECTION_NESTED(96)
 END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 22:
-	/* Clear out SLB */
-	li	r5,0
-	slbmte	r5,r5
-	slbia
-	ptesync
 
 	/* Restore host values of some registers */
 BEGIN_FTR_SECTION
@@ -1737,10 +1734,56 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_PID, r7
 	mtspr	SPRN_IAMR, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+#ifdef CONFIG_PPC_RADIX_MMU
+	/*
+	 * Are we running hash or radix ?
+	 */
+	beq	cr2,3f
+
+	/* Radix: Handle the case where the guest used an illegal PID */
+	LOAD_REG_ADDR(r4, mmu_base_pid)
+	lwz	r3, VCPU_GUEST_PID(r9)
+	lwz	r5, 0(r4)
+	cmpw	cr0,r3,r5
+	blt	2f
+
+	/*
+	 * Illegal PID, the HW might have prefetched and cached in the TLB
+	 * some translations for the  LPID 0 / guest PID combination which
+	 * Linux doesn't know about, so we need to flush that PID out of
+	 * the TLB. First we need to set LPIDR to 0 so tlbiel applies to
+	 * the right context.
+	*/
+	li	r0,0
+	mtspr	SPRN_LPID,r0
+	isync
+
+	/* Then do a congruence class local flush */
+	ld	r6,VCPU_KVM(r9)
+	lwz	r0,KVM_TLB_SETS(r6)
+	mtctr	r0
+	li	r7,0x400		/* IS field = 0b01 */
+	ptesync
+	sldi	r0,r3,32		/* RS has PID */
+1:	PPC_TLBIEL(7,0,2,1,1)		/* RIC=2, PRS=1, R=1 */
+	addi	r7,r7,0x1000
+	bdnz	1b
+	ptesync
+
+2:	/* Flush the ERAT on radix P9 DD1 guest exit */
 BEGIN_FTR_SECTION
 	PPC_INVALIDATE_ERAT
 END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
+	b	4f
+#endif /* CONFIG_PPC_RADIX_MMU */
 
+	/* Hash: clear out SLB */
+3:	li	r5,0
+	slbmte	r5,r5
+	slbia
+	ptesync
+4:
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do

arch/powerpc/mm/mmu_context_book3s64.c

@@ -124,9 +124,10 @@ static int hash__init_new_context(struct mm_struct *mm)
 static int radix__init_new_context(struct mm_struct *mm)
 {
 	unsigned long rts_field;
-	int index;
+	int index, max_id;
 
-	index = alloc_context_id(1, PRTB_ENTRIES - 1);
+	max_id = (1 << mmu_pid_bits) - 1;
+	index = alloc_context_id(mmu_base_pid, max_id);
 	if (index < 0)
 		return index;
 

arch/powerpc/mm/pgtable-radix.c

@@ -25,6 +25,9 @@
 
 #include <trace/events/thp.h>
 
+unsigned int mmu_pid_bits;
+unsigned int mmu_base_pid;
+
 static int native_register_process_table(unsigned long base, unsigned long pg_sz,
 					 unsigned long table_size)
 {
@@ -265,11 +268,34 @@ static void __init radix_init_pgtable(void)
 	for_each_memblock(memory, reg)
 		WARN_ON(create_physical_mapping(reg->base,
 						reg->base + reg->size));
+
+	/* Find out how many PID bits are supported */
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		if (!mmu_pid_bits)
+			mmu_pid_bits = 20;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		/*
+		 * When KVM is possible, we only use the top half of the
+		 * PID space to avoid collisions between host and guest PIDs
+		 * which can cause problems due to prefetch when exiting the
+		 * guest with AIL=3
+		 */
+		mmu_base_pid = 1 << (mmu_pid_bits - 1);
+#else
+		mmu_base_pid = 1;
+#endif
+	} else {
+		/* The guest uses the bottom half of the PID space */
+		if (!mmu_pid_bits)
+			mmu_pid_bits = 19;
+		mmu_base_pid = 1;
+	}
+
 	/*
 	 * Allocate Partition table and process table for the
 	 * host.
 	 */
-	BUILD_BUG_ON_MSG((PRTB_SIZE_SHIFT > 36), "Process table size too large.");
+	BUG_ON(PRTB_SIZE_SHIFT > 36);
 	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
 	/*
 	 * Fill in the process table.
@@ -343,6 +369,12 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
 	if (type == NULL || strcmp(type, "cpu") != 0)
 		return 0;
 
+	/* Find MMU PID size */
+	prop = of_get_flat_dt_prop(node, "ibm,mmu-pid-bits", &size);
+	if (prop && size == 4)
+		mmu_pid_bits = be32_to_cpup(prop);
+
+	/* Grab page size encodings */
 	prop = of_get_flat_dt_prop(node, "ibm,processor-radix-AP-encodings", &size);
 	if (!prop)
 		return 0;

arch/powerpc/mm/subpage-prot.c

@@ -36,7 +36,7 @@ void subpage_prot_free(struct mm_struct *mm)
 		}
 	}
 	addr = 0;
-	for (i = 0; i < 2; ++i) {
+	for (i = 0; i < (TASK_SIZE_USER64 >> 43); ++i) {
 		p = spt->protptrs[i];
 		if (!p)
 			continue;

arch/powerpc/mm/tlb-radix.c

@@ -12,12 +12,12 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
-#include <asm/ppc-opcode.h>
 
+#include <asm/ppc-opcode.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/trace.h>
-
+#include <asm/cputhreads.h>
 
 #define RIC_FLUSH_TLB 0
 #define RIC_FLUSH_PWC 1
@@ -478,3 +478,44 @@ void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
 	else
 		radix__flush_tlb_page_psize(mm, address, mmu_virtual_psize);
 }
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
+{
+	unsigned int pid = mm->context.id;
+
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		return;
+
+	/*
+	 * If this context hasn't run on that CPU before and KVM is
+	 * around, there's a slim chance that the guest on another
+	 * CPU just brought in obsolete translation into the TLB of
+	 * this CPU due to a bad prefetch using the guest PID on
+	 * the way into the hypervisor.
+	 *
+	 * We work around this here. If KVM is possible, we check if
+	 * any sibling thread is in KVM. If it is, the window may exist
+	 * and thus we flush that PID from the core.
+	 *
+	 * A potential future improvement would be to mark which PIDs
+	 * have never been used on the system and avoid it if the PID
+	 * is new and the process has no other cpumask bit set.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE) && radix_enabled()) {
+		int cpu = smp_processor_id();
+		int sib = cpu_first_thread_sibling(cpu);
+		bool flush = false;
+
+		for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
+			if (sib == cpu)
+				continue;
+			if (paca[sib].kvm_hstate.kvm_vcpu)
+				flush = true;
+		}
+		if (flush)
+			_tlbiel_pid(pid, RIC_FLUSH_ALL);
+	}
+}
+EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */

arch/powerpc/platforms/83xx/mpc832x_rdb.c

@@ -89,7 +89,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk,
 			goto err;
 
 		ret = of_irq_to_resource(np, 0, &res[1]);
-		if (!ret)
+		if (ret <= 0)
 			goto err;
 
 		pdev = platform_device_alloc("mpc83xx_spi", i);

arch/powerpc/platforms/powernv/idle.c

@@ -56,6 +56,7 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
  */
 static u64 pnv_deepest_stop_psscr_val;
 static u64 pnv_deepest_stop_psscr_mask;
+static u64 pnv_deepest_stop_flag;
 static bool deepest_stop_found;
 
 static int pnv_save_sprs_for_deep_states(void)
@@ -185,8 +186,40 @@ static void pnv_alloc_idle_core_states(void)
 
 	update_subcore_sibling_mask();
 
-	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
-		pnv_save_sprs_for_deep_states();
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
+		int rc = pnv_save_sprs_for_deep_states();
+
+		if (likely(!rc))
+			return;
+
+		/*
+		 * The stop-api is unable to restore hypervisor
+		 * resources on wakeup from platform idle states which
+		 * lose full context. So disable such states.
+		 */
+		supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
+		pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
+		pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
+
+		if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+		    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
+			/*
+			 * Use the default stop state for CPU-Hotplug
+			 * if available.
+			 */
+			if (default_stop_found) {
+				pnv_deepest_stop_psscr_val =
+					pnv_default_stop_val;
+				pnv_deepest_stop_psscr_mask =
+					pnv_default_stop_mask;
+				pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
+					pnv_deepest_stop_psscr_val);
+			} else { /* Fallback to snooze loop for CPU-Hotplug */
+				deepest_stop_found = false;
+				pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
+			}
+		}
+	}
 }
 
 u32 pnv_get_supported_cpuidle_states(void)
@@ -397,7 +430,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 						pnv_deepest_stop_psscr_val;
 		srr1 = power9_idle_stop(psscr);
 
-	} else if (idle_states & OPAL_PM_WINKLE_ENABLED) {
+	} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
+		   (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
 		srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
 	} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
 		   (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
@@ -585,6 +619,7 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags,
 			max_residency_ns = residency_ns[i];
 			pnv_deepest_stop_psscr_val = psscr_val[i];
 			pnv_deepest_stop_psscr_mask = psscr_mask[i];
+			pnv_deepest_stop_flag = flags[i];
 			deepest_stop_found = true;
 		}
 

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1851,6 +1851,14 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 			/* 4GB offset bypasses 32-bit space */
 			set_dma_offset(&pdev->dev, (1ULL << 32));
 			set_dma_ops(&pdev->dev, &dma_direct_ops);
+		} else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) {
+			/*
+			 * Fail the request if a DMA mask between 32 and 64 bits
+			 * was requested but couldn't be fulfilled. Ideally we
+			 * would do this for 64-bits but historically we have
+			 * always fallen back to 32-bits.
+			 */
+			return -ENOMEM;
 		} else {
 			dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 			set_dma_ops(&pdev->dev, &dma_iommu_ops);

arch/powerpc/platforms/pseries/reconfig.c

@@ -82,7 +82,6 @@ static int pSeries_reconfig_remove_node(struct device_node *np)
 
 	of_detach_node(np);
 	of_node_put(parent);
-	of_node_put(np); /* Must decrement the refcount */
 	return 0;
 }
 

drivers/cpuidle/cpuidle-powernv.c

@@ -235,6 +235,7 @@ static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
 	return -1;
 }
 
+extern u32 pnv_get_supported_cpuidle_states(void);
 static int powernv_add_idle_states(void)
 {
 	struct device_node *power_mgt;
@@ -248,6 +249,8 @@ static int powernv_add_idle_states(void)
 	const char *names[CPUIDLE_STATE_MAX];
 	u32 has_stop_states = 0;
 	int i, rc;
+	u32 supported_flags = pnv_get_supported_cpuidle_states();
+
 
 	/* Currently we have snooze statically defined */
 
@@ -362,6 +365,13 @@ static int powernv_add_idle_states(void)
 	for (i = 0; i < dt_idle_states; i++) {
 		unsigned int exit_latency, target_residency;
 		bool stops_timebase = false;
+
+		/*
+		 * Skip the platform idle state whose flag isn't in
+		 * the supported_cpuidle_states flag mask.
+		 */
+		if ((flags[i] & supported_flags) != flags[i])
+			continue;
 		/*
 		 * If an idle state has exit latency beyond
 		 * POWERNV_THRESHOLD_LATENCY_NS then don't use it