Merge branch 'timers/urgent' into timers/core

Pick up urgent fixes to apply dependent cleanup patch

14 files changed, 153 insertions, 53 deletions

diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h
index d1c2d2e658cf..2f3ff7a27881 100644
--- a/arch/powerpc/include/asm/powernv.h
+++ b/arch/powerpc/include/asm/powernv.h
@@ -15,7 +15,7 @@
 extern void powernv_set_nmmu_ptcr(unsigned long ptcr);
 extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 			unsigned long flags,
-			struct npu_context *(*cb)(struct npu_context *, void *),
+			void (*cb)(struct npu_context *, void *),
 			void *priv);
 extern void pnv_npu2_destroy_context(struct npu_context *context,
 				struct pci_dev *gpdev);
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 2d4956e97aa9..ee5a67d57aab 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -807,7 +807,8 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev)
 	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/* PCI Command: 0x4 */
-	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] |
+			      PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
 
 	/* Check the PCIe link is ready */
 	eeh_bridge_check_link(edev);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 79d005445c6c..e734f6e45abc 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -553,12 +553,12 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	lbz	r0,HSTATE_HWTHREAD_STATE(r13)
 	cmpwi	r0,KVM_HWTHREAD_IN_KERNEL
-	beq	1f
+	beq	0f
 	li	r0,KVM_HWTHREAD_IN_KERNEL
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 	/* Order setting hwthread_state vs. testing hwthread_req */
 	sync
-	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
+0:	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r0,0
 	beq	1f
 	b	kvm_start_guest
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index fe6fc63251fe..38c5b4764bfe 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -441,7 +441,6 @@ static int mce_handle_ierror(struct pt_regs *regs,
 					if (pfn != ULONG_MAX) {
 						*phys_addr =
 							(pfn << PAGE_SHIFT);
-						handled = 1;
 					}
 				}
 			}
@@ -532,9 +531,7 @@ static int mce_handle_derror(struct pt_regs *regs,
 			 * kernel/exception-64s.h
 			 */
 			if (get_paca()->in_mce < MAX_MCE_DEPTH)
-				if (!mce_find_instr_ea_and_pfn(regs, addr,
-								phys_addr))
-					handled = 1;
+				mce_find_instr_ea_and_pfn(regs, addr, phys_addr);
 		}
 		found = 1;
 	}
@@ -572,7 +569,7 @@ static long mce_handle_error(struct pt_regs *regs,
 		const struct mce_ierror_table itable[])
 {
 	struct mce_error_info mce_err = { 0 };
-	uint64_t addr, phys_addr;
+	uint64_t addr, phys_addr = ULONG_MAX;
 	uint64_t srr1 = regs->msr;
 	long handled;
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 44c30dd38067..b78f142a4148 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -890,6 +890,17 @@ static void __ref init_fallback_flush(void)
 		return;
 
 	l1d_size = ppc64_caches.l1d.size;
+
+	/*
+	 * If there is no d-cache-size property in the device tree, l1d_size
+	 * could be zero. That leads to the loop in the asm wrapping around to
+	 * 2^64-1, and then walking off the end of the fallback area and
+	 * eventually causing a page fault which is fatal. Just default to
+	 * something vaguely sane.
+	 */
+	if (!l1d_size)
+		l1d_size = (64 * 1024);
+
 	limit = min(ppc64_bolted_size(), ppc64_rma_size);
 
 	/*
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e16ec7b3b427..9ca7148b5881 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -566,10 +566,35 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 #endif
 
 #ifdef CONFIG_NMI_IPI
-static void stop_this_cpu(struct pt_regs *regs)
-#else
+static void nmi_stop_this_cpu(struct pt_regs *regs)
+{
+	/*
+	 * This is a special case because it never returns, so the NMI IPI
+	 * handling would never mark it as done, which makes any later
+	 * smp_send_nmi_ipi() call spin forever. Mark it done now.
+	 *
+	 * IRQs are already hard disabled by the smp_handle_nmi_ipi.
+	 */
+	nmi_ipi_lock();
+	nmi_ipi_busy_count--;
+	nmi_ipi_unlock();
+
+	/* Remove this CPU */
+	set_cpu_online(smp_processor_id(), false);
+
+	spin_begin();
+	while (1)
+		spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
+}
+
+#else /* CONFIG_NMI_IPI */
+
 static void stop_this_cpu(void *dummy)
-#endif
 {
 	/* Remove this CPU */
 	set_cpu_online(smp_processor_id(), false);
@@ -582,12 +607,22 @@ static void stop_this_cpu(void *dummy)
 
 void smp_send_stop(void)
 {
-#ifdef CONFIG_NMI_IPI
-	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000);
-#else
+	static bool stopped = false;
+
+	/*
+	 * Prevent waiting on csd lock from a previous smp_send_stop.
+	 * This is racy, but in general callers try to do the right
+	 * thing and only fire off one smp_send_stop (e.g., see
+	 * kernel/panic.c)
+	 */
+	if (stopped)
+		return;
+
+	stopped = true;
+
 	smp_call_function(stop_this_cpu, NULL, 0);
-#endif
 }
+#endif /* CONFIG_NMI_IPI */
 
 struct thread_info *current_set[NR_CPUS];
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6038e2e7aee0..876d4f294fdd 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -305,6 +305,13 @@ void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu)
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL);
 }
 
+#ifdef CONFIG_ALTIVEC
+void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu)
+{
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_UNAVAIL);
+}
+#endif
+
 void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
 {
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER);
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 35f80ab7cbd8..288fe4f0db4e 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -55,7 +55,7 @@ static int patch_alt_instruction(unsigned int *src, unsigned int *dest,
 		unsigned int *target = (unsigned int *)branch_target(src);
 
 		/* Branch within the section doesn't need translating */
-		if (target < alt_start || target >= alt_end) {
+		if (target < alt_start || target > alt_end) {
 			instr = translate_branch(dest, src);
 			if (!instr)
 				return 1;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 737f8a4632cc..c3c39b02b2ba 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -133,6 +133,7 @@ int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *
 			start, start + size, rc);
 		return -EFAULT;
 	}
+	flush_inval_dcache_range(start, start + size);
 
 	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
 }
@@ -159,6 +160,7 @@ int __meminit arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
+	flush_inval_dcache_range(start, start + size);
 	ret = remove_section_mapping(start, start + size);
 
 	/* Ensure all vmalloc mappings are flushed in case they also
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 9033c8194eda..ccc421503363 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1093,7 +1093,7 @@ static int show_spu_loadavg(struct seq_file *s, void *private)
 		LOAD_INT(c), LOAD_FRAC(c),
 		count_active_contexts(),
 		atomic_read(&nr_spu_contexts),
-		idr_get_cursor(&task_active_pid_ns(current)->idr));
+		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index de470caf0784..fc222a0c2ac4 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -82,19 +82,6 @@ static const struct file_operations memtrace_fops = {
 	.open	= simple_open,
 };
 
-static void flush_memory_region(u64 base, u64 size)
-{
-	unsigned long line_size = ppc64_caches.l1d.size;
-	u64 end = base + size;
-	u64 addr;
-
-	base = round_down(base, line_size);
-	end = round_up(end, line_size);
-
-	for (addr = base; addr < end; addr += line_size)
-		asm volatile("dcbf 0,%0" : "=r" (addr) :: "memory");
-}
-
 static int check_memblock_online(struct memory_block *mem, void *arg)
 {
 	if (mem->state != MEM_ONLINE)
@@ -132,10 +119,6 @@ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
 	walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
 			  change_memblock_state);
 
-	/* RCU grace period? */
-	flush_memory_region((u64)__va(start_pfn << PAGE_SHIFT),
-			    nr_pages << PAGE_SHIFT);
-
 	lock_device_hotplug();
 	remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
 	unlock_device_hotplug();
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 69a4f9e8bd55..525e966dce34 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -34,6 +34,19 @@
 #define npu_to_phb(x) container_of(x, struct pnv_phb, npu)
 
 /*
+ * spinlock to protect initialisation of an npu_context for a particular
+ * mm_struct.
+ */
+static DEFINE_SPINLOCK(npu_context_lock);
+
+/*
+ * When an address shootdown range exceeds this threshold we invalidate the
+ * entire TLB on the GPU for the given PID rather than each specific address in
+ * the range.
+ */
+#define ATSD_THRESHOLD (2*1024*1024)
+
+/*
  * Other types of TCE cache invalidation are not functional in the
  * hardware.
  */
@@ -401,7 +414,7 @@ struct npu_context {
 	bool nmmu_flush;
 
 	/* Callback to stop translation requests on a given GPU */
-	struct npu_context *(*release_cb)(struct npu_context *, void *);
+	void (*release_cb)(struct npu_context *context, void *priv);
 
 	/*
 	 * Private pointer passed to the above callback for usage by
@@ -671,11 +684,19 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 	unsigned long address;
 
-	for (address = start; address < end; address += PAGE_SIZE)
-		mmio_invalidate(npu_context, 1, address, false);
+	if (end - start > ATSD_THRESHOLD) {
+		/*
+		 * Just invalidate the entire PID if the address range is too
+		 * large.
+		 */
+		mmio_invalidate(npu_context, 0, 0, true);
+	} else {
+		for (address = start; address < end; address += PAGE_SIZE)
+			mmio_invalidate(npu_context, 1, address, false);
 
-	/* Do the flush only on the final addess == end */
-	mmio_invalidate(npu_context, 1, address, true);
+		/* Do the flush only on the final addess == end */
+		mmio_invalidate(npu_context, 1, address, true);
+	}
 }
 
 static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
@@ -696,11 +717,12 @@ static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
  * Returns an error if there no contexts are currently available or a
  * npu_context which should be passed to pnv_npu2_handle_fault().
  *
- * mmap_sem must be held in write mode.
+ * mmap_sem must be held in write mode and must not be called from interrupt
+ * context.
  */
 struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 			unsigned long flags,
-			struct npu_context *(*cb)(struct npu_context *, void *),
+			void (*cb)(struct npu_context *, void *),
 			void *priv)
 {
 	int rc;
@@ -743,7 +765,9 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 	/*
 	 * Setup the NPU context table for a particular GPU. These need to be
 	 * per-GPU as we need the tables to filter ATSDs when there are no
-	 * active contexts on a particular GPU.
+	 * active contexts on a particular GPU. It is safe for these to be
+	 * called concurrently with destroy as the OPAL call takes appropriate
+	 * locks and refcounts on init/destroy.
 	 */
 	rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags,
 				PCI_DEVID(gpdev->bus->number, gpdev->devfn));
@@ -754,8 +778,29 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 	 * We store the npu pci device so we can more easily get at the
 	 * associated npus.
 	 */
+	spin_lock(&npu_context_lock);
 	npu_context = mm->context.npu_context;
+	if (npu_context) {
+		if (npu_context->release_cb != cb ||
+			npu_context->priv != priv) {
+			spin_unlock(&npu_context_lock);
+			opal_npu_destroy_context(nphb->opal_id, mm->context.id,
+						PCI_DEVID(gpdev->bus->number,
+							gpdev->devfn));
+			return ERR_PTR(-EINVAL);
+		}
+
+		WARN_ON(!kref_get_unless_zero(&npu_context->kref));
+	}
+	spin_unlock(&npu_context_lock);
+
 	if (!npu_context) {
+		/*
+		 * We can set up these fields without holding the
+		 * npu_context_lock as the npu_context hasn't been returned to
+		 * the caller meaning it can't be destroyed. Parallel allocation
+		 * is protected against by mmap_sem.
+		 */
 		rc = -ENOMEM;
 		npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
 		if (npu_context) {
@@ -774,8 +819,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 		}
 
 		mm->context.npu_context = npu_context;
-	} else {
-		WARN_ON(!kref_get_unless_zero(&npu_context->kref));
 	}
 
 	npu_context->release_cb = cb;
@@ -814,15 +857,16 @@ static void pnv_npu2_release_context(struct kref *kref)
 		mm_context_remove_copro(npu_context->mm);
 
 	npu_context->mm->context.npu_context = NULL;
-	mmu_notifier_unregister(&npu_context->mn,
-				npu_context->mm);
-
-	kfree(npu_context);
 }
 
+/*
+ * Destroy a context on the given GPU. May free the npu_context if it is no
+ * longer active on any GPUs. Must not be called from interrupt context.
+ */
 void pnv_npu2_destroy_context(struct npu_context *npu_context,
 			struct pci_dev *gpdev)
 {
+	int removed;
 	struct pnv_phb *nphb;
 	struct npu *npu;
 	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
@@ -844,7 +888,21 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context,
 	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL);
 	opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
 				PCI_DEVID(gpdev->bus->number, gpdev->devfn));
-	kref_put(&npu_context->kref, pnv_npu2_release_context);
+	spin_lock(&npu_context_lock);
+	removed = kref_put(&npu_context->kref, pnv_npu2_release_context);
+	spin_unlock(&npu_context_lock);
+
+	/*
+	 * We need to do this outside of pnv_npu2_release_context so that it is
+	 * outside the spinlock as mmu_notifier_destroy uses SRCU.
+	 */
+	if (removed) {
+		mmu_notifier_unregister(&npu_context->mn,
+					npu_context->mm);
+
+		kfree(npu_context);
+	}
+
 }
 EXPORT_SYMBOL(pnv_npu2_destroy_context);
 
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index f8868864f373..aa2a5139462e 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -48,10 +48,12 @@ unsigned long __init opal_get_boot_time(void)
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
+		if (rc == OPAL_BUSY_EVENT) {
+			mdelay(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
-		else if (rc == OPAL_BUSY)
-			mdelay(10);
+		} else if (rc == OPAL_BUSY) {
+			mdelay(OPAL_BUSY_DELAY_MS);
+		}
 	}
 	if (rc != OPAL_SUCCESS)
 		return 0;
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index d22aeb0b69e1..b48454be5b98 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -389,6 +389,10 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
 	if (xive_pool_vps == XIVE_INVALID_VP)
 		return;
 
+	/* Check if pool VP already active, if it is, pull it */
+	if (in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2) & TM_QW2W2_VP)
+		in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
+
 	/* Enable the pool VP */
 	vp = xive_pool_vps + cpu;
 	pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp);