19 files changed, 70 insertions, 56 deletions

diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index a3bf5be111ff..51ccc7232042 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -34,7 +34,7 @@
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
 #ifdef __SUBARCH_HAS_LWSYNC
 #    define SMPWMB      LWSYNC
@@ -89,5 +89,6 @@ do {									\
 
 #define smp_mb__before_atomic()     smp_mb()
 #define smp_mb__after_atomic()      smp_mb()
+#define smp_mb__before_spinlock()   smp_mb()
 
 #endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index d463c68fe7f0..ad6263cffb0f 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -144,7 +144,6 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 static __always_inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 5f1048eaa5b6..8b3b46b7b0f2 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -87,7 +87,7 @@ static inline int prrn_is_enabled(void)
 #include <asm/smp.h>
 
 #define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
-#define topology_thread_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
 #endif
diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h
index 5047659815a5..5d836b7c1176 100644
--- a/arch/powerpc/include/uapi/asm/tm.h
+++ b/arch/powerpc/include/uapi/asm/tm.h
@@ -11,7 +11,7 @@
 #define TM_CAUSE_RESCHED	0xde
 #define TM_CAUSE_TLBI		0xdc
 #define TM_CAUSE_FAC_UNAV	0xda
-#define TM_CAUSE_SYSCALL	0xd8
+#define TM_CAUSE_SYSCALL	0xd8  /* future use */
 #define TM_CAUSE_MISC		0xd6  /* future use */
 #define TM_CAUSE_SIGNAL		0xd4
 #define TM_CAUSE_ALIGNMENT	0xd2
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 44b480e3a5af..9ee61d15653d 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -749,21 +749,24 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 		eeh_unfreeze_pe(pe, false);
 		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 		eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev);
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 		break;
 	case pcie_hot_reset:
+		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
 		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
+		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
 		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
 	default:
-		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED);
 		return -EINVAL;
 	};
 
@@ -1058,6 +1061,9 @@ void eeh_add_device_early(struct pci_dn *pdn)
 	if (!edev || !eeh_enabled())
 		return;
 
+	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
+		return;
+
 	/* USB Bus children of PCI devices will not have BUID's */
 	phb = edev->phb;
 	if (NULL == phb ||
@@ -1112,6 +1118,9 @@ void eeh_add_device_late(struct pci_dev *dev)
 		return;
 	}
 
+	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
+		eeh_ops->probe(pdn, NULL);
+
 	/*
 	 * The EEH cache might not be removed correctly because of
 	 * unbalanced kref to the device during unplug time, which
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 8ca9434c40e6..afbc20019c2e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -34,7 +34,6 @@
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
 #include <asm/context_tracking.h>
-#include <asm/tm.h>
 
 /*
  * System calls.
@@ -146,24 +145,6 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
 	bne	syscall_dotrace
 .Lsyscall_dotrace_cont:
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
-	b	1f
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-	extrdi.	r11, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
-	beq+	1f
-
-	/* Doom the transaction and don't perform the syscall: */
-	mfmsr	r11
-	li	r12, 1
-	rldimi	r11, r12, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r11, 0
-	li	r11, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R11)
-
-	b	.Lsyscall_exit
-1:
-#endif
 	cmpldi	0,r0,NR_syscalls
 	bge-	syscall_enosys
 
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index eeaa0d5f69d5..ccde8f084ce4 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -501,9 +501,11 @@ BEGIN_FTR_SECTION
 	CHECK_HMI_INTERRUPT
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	ld	r1,PACAR1(r13)
+	ld	r6,_CCR(r1)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)
 	addi	r1,r1,INT_FRAME_SIZE
+	mtcr	r6
 	mtspr	SPRN_SRR1,r4
 	mtspr	SPRN_SRR0,r5
 	rfid
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 15c99b649b04..b2eb4686bd8f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -73,7 +73,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
 		    uint64_t nip, uint64_t addr)
 {
 	uint64_t srr1;
-	int index = __this_cpu_inc_return(mce_nest_count);
+	int index = __this_cpu_inc_return(mce_nest_count) - 1;
 	struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
 
 	/*
@@ -184,7 +184,7 @@ void machine_check_queue_event(void)
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
 
-	index = __this_cpu_inc_return(mce_queue_count);
+	index = __this_cpu_inc_return(mce_queue_count) - 1;
 	/* If queue is full, just return for now. */
 	if (index >= MAX_MC_EVT) {
 		__this_cpu_dec(mce_queue_count);
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index f096e72262f4..1db685104ffc 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -213,6 +213,7 @@ SECTIONS
 		*(.opd)
 	}
 
+	. = ALIGN(256);
 	.got : AT(ADDR(.got) - LOAD_OFFSET) {
 		__toc_start = .;
 #ifndef CONFIG_RELOCATABLE
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 48d3c5d2ecc9..df81caab7383 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1952,7 +1952,7 @@ static void post_guest_process(struct kvmppc_vcore *vc)
  */
 static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu, *vnext;
 	int i;
 	int srcu_idx;
 
@@ -1982,7 +1982,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	if ((threads_per_core > 1) &&
 	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
-		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
+		list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+					 arch.run_list) {
 			vcpu->arch.ret = -EBUSY;
 			kvmppc_remove_runnable(vc, vcpu);
 			wake_up(&vcpu->arch.cpu_run);
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 8f3e6cc54d95..c6ca7db64673 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -12,6 +12,7 @@
 #include <linux/err.h>
 #include <linux/gfp.h>
 #include <linux/anon_inodes.h>
+#include <linux/spinlock.h>
 
 #include <asm/uaccess.h>
 #include <asm/kvm_book3s.h>
@@ -20,7 +21,6 @@
 #include <asm/xics.h>
 #include <asm/debug.h>
 #include <asm/time.h>
-#include <asm/spinlock.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 3cf529ceec5b..ac93a3bd2730 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -27,11 +27,11 @@ int enter_vmx_usercopy(void)
 	if (in_interrupt())
 		return 0;
 
-	/* This acts as preempt_disable() as well and will make
-	 * enable_kernel_altivec(). We need to disable page faults
-	 * as they can call schedule and thus make us lose the VMX
-	 * context. So on page faults, we just fail which will cause
-	 * a fallback to the normal non-vmx copy.
+	preempt_disable();
+	/*
+	 * We need to disable page faults as they can call schedule and
+	 * thus make us lose the VMX context. So on page faults, we just
+	 * fail which will cause a fallback to the normal non-vmx copy.
 	 */
 	pagefault_disable();
 
@@ -47,6 +47,7 @@ int enter_vmx_usercopy(void)
 int exit_vmx_usercopy(void)
 {
 	pagefault_enable();
+	preempt_enable();
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index b396868d2aa7..6d535973b200 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -33,13 +33,13 @@
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
 #include <linux/hugetlb.h>
+#include <linux/uaccess.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
@@ -272,15 +272,16 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	if (in_atomic() || mm == NULL) {
+	if (faulthandler_disabled() || mm == NULL) {
 		if (!user_mode(regs)) {
 			rc = SIGSEGV;
 			goto bail;
 		}
-		/* in_atomic() in user mode is really bad,
+		/* faulthandler_disabled() in user mode is really bad,
 		   as is current->mm == NULL. */
 		printk(KERN_EMERG "Page fault in user mode with "
-		       "in_atomic() = %d mm = %p\n", in_atomic(), mm);
+		       "faulthandler_disabled() = %d mm = %p\n",
+		       faulthandler_disabled(), mm);
 		printk(KERN_EMERG "NIP = %lx  MSR = %lx\n",
 		       regs->nip, regs->msr);
 		die("Weird page fault", regs, SIGSEGV);
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
index e7450bdbe83a..e292c8a60952 100644
--- a/arch/powerpc/mm/highmem.c
+++ b/arch/powerpc/mm/highmem.c
@@ -34,7 +34,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -59,6 +59,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -82,5 +83,6 @@ void __kunmap_atomic(void *kvaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0ce968b00b7c..3385e3d0506e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -689,27 +689,34 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 {
-	pte_t *ptep;
-	struct page *page;
+	pte_t *ptep, pte;
 	unsigned shift;
 	unsigned long mask, flags;
+	struct page *page = ERR_PTR(-EINVAL);
+
+	local_irq_save(flags);
+	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+	if (!ptep)
+		goto no_page;
+	pte = READ_ONCE(*ptep);
 	/*
+	 * Verify it is a huge page else bail.
 	 * Transparent hugepages are handled by generic code. We can skip them
 	 * here.
 	 */
-	local_irq_save(flags);
-	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+	if (!shift || pmd_trans_huge(__pmd(pte_val(pte))))
+		goto no_page;
 
-	/* Verify it is a huge page else bail. */
-	if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep)) {
-		local_irq_restore(flags);
-		return ERR_PTR(-EINVAL);
+	if (!pte_present(pte)) {
+		page = NULL;
+		goto no_page;
 	}
 	mask = (1UL << shift) - 1;
-	page = pte_page(*ptep);
+	page = pte_page(pte);
 	if (page)
 		page += (address & mask) / PAGE_SIZE;
 
+no_page:
 	local_irq_restore(flags);
 	return page;
 }
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 59daa5eeec25..6bfadf1aa5cb 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -839,6 +839,17 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	 * hash fault look at them.
 	 */
 	memset(pgtable, 0, PTE_FRAG_SIZE);
+	/*
+	 * Serialize against find_linux_pte_or_hugepte which does lock-less
+	 * lookup in page tables with local interrupts disabled. For huge pages
+	 * it casts pmd_t to pte_t. Since format of pte_t is different from
+	 * pmd_t we want to prevent transit from pmd pointing to page table
+	 * to pmd pointing to huge page (and back) while interrupts are disabled.
+	 * We clear pmd to possibly replace it with page table pointer in
+	 * different code paths. So make sure we wait for the parallel
+	 * find_linux_pte_or_hugepage to finish.
+	 */
+	kick_all_cpus_sync();
 	return old_pmd;
 }
 
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index cbd3d069897f..723a099f6be3 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -217,7 +217,7 @@ static DEFINE_RAW_SPINLOCK(tlbivax_lock);
 static int mm_is_core_local(struct mm_struct *mm)
 {
 	return cpumask_subset(mm_cpumask(mm),
-			      topology_thread_cpumask(smp_processor_id()));
+			      topology_sibling_cpumask(smp_processor_id()));
 }
 
 struct tlb_flush_param {
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 920c252d1f49..f8bc950efcae 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2693,7 +2693,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		hose->last_busno = 0xff;
 	}
 	hose->private_data = phb;
-	hose->controller_ops = pnv_pci_controller_ops;
 	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = ioda_type;
@@ -2812,6 +2811,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook;
 	pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment;
 	pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus;
+	hose->controller_ops = pnv_pci_controller_ops;
 
 #ifdef CONFIG_PCI_IOV
 	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index b4b11096ea8b..019d34aaf054 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -412,6 +412,10 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 	if (rc)
 		return -EINVAL;
 
+	rc = dlpar_acquire_drc(drc_index);
+	if (rc)
+		return -EINVAL;
+
 	parent = of_find_node_by_path("/cpus");
 	if (!parent)
 		return -ENODEV;
@@ -422,12 +426,6 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 
 	of_node_put(parent);
 
-	rc = dlpar_acquire_drc(drc_index);
-	if (rc) {
-		dlpar_free_cc_nodes(dn);
-		return -EINVAL;
-	}
-
 	rc = dlpar_attach_node(dn);
 	if (rc) {
 		dlpar_release_drc(drc_index);