Merge remote-tracking branch 'lsk/linux-linaro-lsk-v3.18' into linux-linaro-lsk-v3.18-rtlsk-v3.18-16.09-rtlinux-linaro-lsk-v3.18-rt-test

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>

Conflicts:
	kernel/futex.c
	kernel/printk/printk.c
	kernel/softirq.c
	mm/slub.c
	mm/swap.c

12 files changed, 148 insertions, 80 deletions

diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 2140398a2a8c..2ccd3592d41f 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -2,7 +2,7 @@ ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),)
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 endif
 obj-$(CONFIG_X86)			+= fallback.o
-obj-y	+= grant-table.o features.o balloon.o manage.o
+obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o
 obj-y	+= events/
 obj-y	+= xenbus/
 
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 38387950490e..4bf7a34f6a4c 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -483,9 +483,20 @@ static void eoi_pirq(struct irq_data *data)
 	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
 	int rc = 0;
 
-	irq_move_irq(data);
+	if (!VALID_EVTCHN(evtchn))
+		return;
 
-	if (VALID_EVTCHN(evtchn))
+	if (unlikely(irqd_is_setaffinity_pending(data)) &&
+	    likely(!irqd_irq_disabled(data))) {
+		int masked = test_and_set_mask(evtchn);
+
+		clear_evtchn(evtchn);
+
+		irq_move_masked_irq(data);
+
+		if (!masked)
+			unmask_evtchn(evtchn);
+	} else
 		clear_evtchn(evtchn);
 
 	if (pirq_needs_eoi(data->irq)) {
@@ -1360,9 +1371,20 @@ static void ack_dynirq(struct irq_data *data)
 {
 	int evtchn = evtchn_from_irq(data->irq);
 
-	irq_move_irq(data);
+	if (!VALID_EVTCHN(evtchn))
+		return;
 
-	if (VALID_EVTCHN(evtchn))
+	if (unlikely(irqd_is_setaffinity_pending(data)) &&
+	    likely(!irqd_irq_disabled(data))) {
+		int masked = test_and_set_mask(evtchn);
+
+		clear_evtchn(evtchn);
+
+		irq_move_masked_irq(data);
+
+		if (!masked)
+			unmask_evtchn(evtchn);
+	} else
 		clear_evtchn(evtchn);
 }
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 073b4a19a8b0..91cc44611062 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -67,7 +67,7 @@ struct gntdev_priv {
 	 * Only populated if populate_freeable_maps == 1 */
 	struct list_head freeable_maps;
 	/* lock protects maps and freeable_maps */
-	spinlock_t lock;
+	struct mutex lock;
 	struct mm_struct *mm;
 	struct mmu_notifier mn;
 };
@@ -216,9 +216,9 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
 	}
 
 	if (populate_freeable_maps && priv) {
-		spin_lock(&priv->lock);
+		mutex_lock(&priv->lock);
 		list_del(&map->next);
-		spin_unlock(&priv->lock);
+		mutex_unlock(&priv->lock);
 	}
 
 	if (map->pages && !use_ptemod)
@@ -387,9 +387,9 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 		 * not do any unmapping, since that has been done prior to
 		 * closing the vma, but it may still iterate the unmap_ops list.
 		 */
-		spin_lock(&priv->lock);
+		mutex_lock(&priv->lock);
 		map->vma = NULL;
-		spin_unlock(&priv->lock);
+		mutex_unlock(&priv->lock);
 	}
 	vma->vm_private_data = NULL;
 	gntdev_put_map(priv, map);
@@ -433,14 +433,14 @@ static void mn_invl_range_start(struct mmu_notifier *mn,
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
 	struct grant_map *map;
 
-	spin_lock(&priv->lock);
+	mutex_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
 		unmap_if_in_range(map, start, end);
 	}
 	list_for_each_entry(map, &priv->freeable_maps, next) {
 		unmap_if_in_range(map, start, end);
 	}
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 }
 
 static void mn_invl_page(struct mmu_notifier *mn,
@@ -457,7 +457,7 @@ static void mn_release(struct mmu_notifier *mn,
 	struct grant_map *map;
 	int err;
 
-	spin_lock(&priv->lock);
+	mutex_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
 		if (!map->vma)
 			continue;
@@ -476,7 +476,7 @@ static void mn_release(struct mmu_notifier *mn,
 		err = unmap_grant_pages(map, /* offset */ 0, map->count);
 		WARN_ON(err);
 	}
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 }
 
 static struct mmu_notifier_ops gntdev_mmu_ops = {
@@ -498,7 +498,7 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 
 	INIT_LIST_HEAD(&priv->maps);
 	INIT_LIST_HEAD(&priv->freeable_maps);
-	spin_lock_init(&priv->lock);
+	mutex_init(&priv->lock);
 
 	if (use_ptemod) {
 		priv->mm = get_task_mm(current);
@@ -529,12 +529,14 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 
 	pr_debug("priv %p\n", priv);
 
+	mutex_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
 		map = list_entry(priv->maps.next, struct grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
 	WARN_ON(!list_empty(&priv->freeable_maps));
+	mutex_unlock(&priv->lock);
 
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
@@ -572,10 +574,10 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 		return -EFAULT;
 	}
 
-	spin_lock(&priv->lock);
+	mutex_lock(&priv->lock);
 	gntdev_add_map(priv, map);
 	op.index = map->index << PAGE_SHIFT;
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 
 	if (copy_to_user(u, &op, sizeof(op)) != 0)
 		return -EFAULT;
@@ -594,7 +596,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 		return -EFAULT;
 	pr_debug("priv %p, del %d+%d\n", priv, (int)op.index, (int)op.count);
 
-	spin_lock(&priv->lock);
+	mutex_lock(&priv->lock);
 	map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
 	if (map) {
 		list_del(&map->next);
@@ -602,7 +604,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 			list_add_tail(&map->next, &priv->freeable_maps);
 		err = 0;
 	}
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 	if (map)
 		gntdev_put_map(priv, map);
 	return err;
@@ -670,7 +672,7 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 	out_flags = op.action;
 	out_event = op.event_channel_port;
 
-	spin_lock(&priv->lock);
+	mutex_lock(&priv->lock);
 
 	list_for_each_entry(map, &priv->maps, next) {
 		uint64_t begin = map->index << PAGE_SHIFT;
@@ -698,7 +700,7 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 	rc = 0;
 
  unlock_out:
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 
 	/* Drop the reference to the event channel we did not save in the map */
 	if (out_flags & UNMAP_NOTIFY_SEND_EVENT)
@@ -748,7 +750,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	pr_debug("map %d+%d at %lx (pgoff %lx)\n",
 			index, count, vma->vm_start, vma->vm_pgoff);
 
-	spin_lock(&priv->lock);
+	mutex_lock(&priv->lock);
 	map = gntdev_find_map_index(priv, index, count);
 	if (!map)
 		goto unlock_out;
@@ -783,7 +785,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 			map->flags |= GNTMAP_readonly;
 	}
 
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 
 	if (use_ptemod) {
 		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
@@ -811,11 +813,11 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	return 0;
 
 unlock_out:
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 	return err;
 
 out_unlock_put:
-	spin_unlock(&priv->lock);
+	mutex_unlock(&priv->lock);
 out_put_map:
 	if (use_ptemod)
 		map->vma = NULL;
diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
new file mode 100644
index 000000000000..a1800c150839
--- /dev/null
+++ b/drivers/xen/preempt.c
@@ -0,0 +1,44 @@
+/*
+ * Preemptible hypercalls
+ *
+ * Copyright (C) 2014 Citrix Systems R&D ltd.
+ *
+ * This source code is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <xen/xen-ops.h>
+
+#ifndef CONFIG_PREEMPT
+
+/*
+ * Some hypercalls issued by the toolstack can take many 10s of
+ * seconds. Allow tasks running hypercalls via the privcmd driver to
+ * be voluntarily preempted even if full kernel preemption is
+ * disabled.
+ *
+ * Such preemptible hypercalls are bracketed by
+ * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
+ * calls.
+ */
+
+DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
+EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
+
+asmlinkage __visible void xen_maybe_preempt_hcall(void)
+{
+	if (unlikely(__this_cpu_read(xen_in_preemptible_hcall)
+		     && should_resched())) {
+		/*
+		 * Clear flag as we may be rescheduled on a different
+		 * cpu.
+		 */
+		__this_cpu_write(xen_in_preemptible_hcall, false);
+		_cond_resched();
+		__this_cpu_write(xen_in_preemptible_hcall, true);
+	}
+}
+#endif /* CONFIG_PREEMPT */
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 569a13b9e856..59ac71c4a043 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -56,10 +56,12 @@ static long privcmd_ioctl_hypercall(void __user *udata)
 	if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
 		return -EFAULT;
 
+	xen_preemptible_hcall_begin();
 	ret = privcmd_call(hypercall.op,
 			   hypercall.arg[0], hypercall.arg[1],
 			   hypercall.arg[2], hypercall.arg[3],
 			   hypercall.arg[4]);
+	xen_preemptible_hcall_end();
 
 	return ret;
 }
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 59fc190f1e92..b96e207bf250 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -423,36 +423,7 @@ upload:
 
 	return 0;
 }
-static int __init check_prereq(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (!xen_initial_domain())
-		return -ENODEV;
-
-	if (!acpi_gbl_FADT.smi_command)
-		return -ENODEV;
-
-	if (c->x86_vendor == X86_VENDOR_INTEL) {
-		if (!cpu_has(c, X86_FEATURE_EST))
-			return -ENODEV;
 
-		return 0;
-	}
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* Copied from powernow-k8.h, can't include ../cpufreq/powernow
-		 * as we get compile warnings for the static functions.
-		 */
-#define CPUID_FREQ_VOLT_CAPABILITIES    0x80000007
-#define USE_HW_PSTATE                   0x00000080
-		u32 eax, ebx, ecx, edx;
-		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
-		if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE)
-			return -ENODEV;
-		return 0;
-	}
-	return -ENODEV;
-}
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance __percpu *acpi_perf_data;
 
@@ -509,10 +480,10 @@ struct notifier_block xen_acpi_processor_resume_nb = {
 static int __init xen_acpi_processor_init(void)
 {
 	unsigned int i;
-	int rc = check_prereq();
+	int rc;
 
-	if (rc)
-		return rc;
+	if (!xen_initial_domain())
+		return -ENODEV;
 
 	nr_acpi_bits = get_max_acpi_id() + 1;
 	acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 9c234209d8b5..47a4177b16d2 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -183,8 +183,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			err = conf_space_read(dev, cfg_entry, field_start,
 					      &tmp_val);
 			if (err)
@@ -230,8 +229,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			tmp_val = 0;
 
 			err = xen_pcibk_config_read(dev, field_start,
diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h
index f72af87640e0..560b3ecbcba8 100644
--- a/drivers/xen/xen-pciback/pciback.h
+++ b/drivers/xen/xen-pciback/pciback.h
@@ -37,6 +37,7 @@ struct xen_pcibk_device {
 	struct xen_pci_sharedinfo *sh_info;
 	unsigned long flags;
 	struct work_struct op_work;
+	struct xen_pci_op op;
 };
 
 struct xen_pcibk_dev_data {
diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index c4a0666de6f5..7eb8f8895a24 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -197,13 +197,26 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
 	struct xen_pcibk_dev_data *dev_data;
 	int i, result;
 	struct msix_entry *entries;
+	u16 cmd;
 
 	if (unlikely(verbose_request))
 		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI-X\n",
 		       pci_name(dev));
+
 	if (op->value > SH_INFO_MAX_VEC)
 		return -EINVAL;
 
+	if (dev->msix_enabled)
+		return -EALREADY;
+
+	/*
+	 * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able
+	 * to access the BARs where the MSI-X entries reside.
+	 */
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY))
+		return -ENXIO;
+
 	entries = kmalloc(op->value * sizeof(*entries), GFP_KERNEL);
 	if (entries == NULL)
 		return -ENOMEM;
@@ -298,9 +311,11 @@ void xen_pcibk_do_op(struct work_struct *data)
 		container_of(data, struct xen_pcibk_device, op_work);
 	struct pci_dev *dev;
 	struct xen_pcibk_dev_data *dev_data = NULL;
-	struct xen_pci_op *op = &pdev->sh_info->op;
+	struct xen_pci_op *op = &pdev->op;
 	int test_intx = 0;
 
+	*op = pdev->sh_info->op;
+	barrier();
 	dev = xen_pcibk_get_pci_dev(pdev, op->domain, op->bus, op->devfn);
 
 	if (dev == NULL)
@@ -342,6 +357,17 @@ void xen_pcibk_do_op(struct work_struct *data)
 		if ((dev_data->enable_intx != test_intx))
 			xen_pcibk_control_isr(dev, 0 /* no reset */);
 	}
+	pdev->sh_info->op.err = op->err;
+	pdev->sh_info->op.value = op->value;
+#ifdef CONFIG_PCI_MSI
+	if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) {
+		unsigned int i;
+
+		for (i = 0; i < op->value; i++)
+			pdev->sh_info->op.msix_entries[i].vector =
+				op->msix_entries[i].vector;
+	}
+#endif
 	/* Tell the driver domain that we're done. */
 	wmb();
 	clear_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index d30c6b246342..7dec1407f1c7 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -947,12 +947,12 @@ out:
 	spin_unlock_irqrestore(&info->v2p_lock, flags);
 
 out_free:
-	mutex_lock(&tpg->tv_tpg_mutex);
-	tpg->tv_tpg_fe_count--;
-	mutex_unlock(&tpg->tv_tpg_mutex);
-
-	if (err)
+	if (err) {
+		mutex_lock(&tpg->tv_tpg_mutex);
+		tpg->tv_tpg_fe_count--;
+		mutex_unlock(&tpg->tv_tpg_mutex);
 		kfree(new);
+	}
 
 	return err;
 }
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 85534ea63555..531e76474983 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -316,26 +316,31 @@ static int xenbus_write_transaction(unsigned msg_type,
 			rc = -ENOMEM;
 			goto out;
 		}
+	} else {
+		list_for_each_entry(trans, &u->transactions, list)
+			if (trans->handle.id == u->u.msg.tx_id)
+				break;
+		if (&trans->list == &u->transactions)
+			return -ESRCH;
 	}
 
 	reply = xenbus_dev_request_and_reply(&u->u.msg);
 	if (IS_ERR(reply)) {
-		kfree(trans);
+		if (msg_type == XS_TRANSACTION_START)
+			kfree(trans);
 		rc = PTR_ERR(reply);
 		goto out;
 	}
 
 	if (msg_type == XS_TRANSACTION_START) {
-		trans->handle.id = simple_strtoul(reply, NULL, 0);
-
-		list_add(&trans->list, &u->transactions);
-	} else if (msg_type == XS_TRANSACTION_END) {
-		list_for_each_entry(trans, &u->transactions, list)
-			if (trans->handle.id == u->u.msg.tx_id)
-				break;
-		BUG_ON(&trans->list == &u->transactions);
+		if (u->u.msg.type == XS_ERROR)
+			kfree(trans);
+		else {
+			trans->handle.id = simple_strtoul(reply, NULL, 0);
+			list_add(&trans->list, &u->transactions);
+		}
+	} else if (u->u.msg.type == XS_TRANSACTION_END) {
 		list_del(&trans->list);
-
 		kfree(trans);
 	}
 
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index ba804f3d8278..ce65591b4168 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -250,9 +250,6 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 
 	mutex_unlock(&xs_state.request_mutex);
 
-	if (IS_ERR(ret))
-		return ret;
-
 	if ((msg->type == XS_TRANSACTION_END) ||
 	    ((req_msg.type == XS_TRANSACTION_START) &&
 	     (msg->type == XS_ERROR)))