aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/xen
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/xen')
-rw-r--r--drivers/xen/Makefile2
-rw-r--r--drivers/xen/balloon.c86
-rw-r--r--drivers/xen/events/events_base.c18
-rw-r--r--drivers/xen/gntdev.c143
-rw-r--r--drivers/xen/grant-table.c120
-rw-r--r--drivers/xen/manage.c8
-rw-r--r--drivers/xen/preempt.c44
-rw-r--r--drivers/xen/privcmd.c2
-rw-r--r--drivers/xen/tmem.c2
-rw-r--r--drivers/xen/xen-acpi-memhotplug.c8
-rw-r--r--drivers/xen/xen-pciback/conf_space.c2
-rw-r--r--drivers/xen/xen-pciback/conf_space.h2
-rw-r--r--drivers/xen/xen-pciback/conf_space_header.c61
-rw-r--r--drivers/xen/xen-scsiback.c28
-rw-r--r--drivers/xen/xenbus/xenbus_dev_frontend.c11
15 files changed, 370 insertions, 167 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/balloon.c b/drivers/xen/balloon.c
index 3860d02729dc..0b52d92cb2e5 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -92,7 +92,6 @@ EXPORT_SYMBOL_GPL(balloon_stats);
/* We increase/decrease in batches which fit in a page */
static xen_pfn_t frame_list[PAGE_SIZE / sizeof(unsigned long)];
-static DEFINE_PER_CPU(struct page *, balloon_scratch_page);
/* List of ballooned pages, threaded through the mem_map array. */
@@ -423,22 +422,12 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
page = pfn_to_page(pfn);
#ifdef CONFIG_XEN_HAVE_PVMMU
- /*
- * Ballooned out frames are effectively replaced with
- * a scratch frame. Ensure direct mappings and the
- * p2m are consistent.
- */
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
if (!PageHighMem(page)) {
- struct page *scratch_page = get_balloon_scratch_page();
-
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
- pfn_pte(page_to_pfn(scratch_page),
- PAGE_KERNEL_RO), 0);
+ __pte_ma(0), 0);
BUG_ON(ret);
-
- put_balloon_scratch_page();
}
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
@@ -500,18 +489,6 @@ static void balloon_process(struct work_struct *work)
mutex_unlock(&balloon_mutex);
}
-struct page *get_balloon_scratch_page(void)
-{
- struct page *ret = get_cpu_var(balloon_scratch_page);
- BUG_ON(ret == NULL);
- return ret;
-}
-
-void put_balloon_scratch_page(void)
-{
- put_cpu_var(balloon_scratch_page);
-}
-
/* Resets the Xen limit, sets new target, and kicks off processing. */
void balloon_set_new_target(unsigned long target)
{
@@ -605,61 +582,13 @@ static void __init balloon_add_region(unsigned long start_pfn,
}
}
-static int alloc_balloon_scratch_page(int cpu)
-{
- if (per_cpu(balloon_scratch_page, cpu) != NULL)
- return 0;
-
- per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL);
- if (per_cpu(balloon_scratch_page, cpu) == NULL) {
- pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu);
- return -ENOMEM;
- }
-
- return 0;
-}
-
-
-static int balloon_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- int cpu = (long)hcpu;
- switch (action) {
- case CPU_UP_PREPARE:
- if (alloc_balloon_scratch_page(cpu))
- return NOTIFY_BAD;
- break;
- default:
- break;
- }
- return NOTIFY_OK;
-}
-
-static struct notifier_block balloon_cpu_notifier = {
- .notifier_call = balloon_cpu_notify,
-};
-
static int __init balloon_init(void)
{
- int i, cpu;
+ int i;
if (!xen_domain())
return -ENODEV;
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- register_cpu_notifier(&balloon_cpu_notifier);
-
- get_online_cpus();
- for_each_online_cpu(cpu) {
- if (alloc_balloon_scratch_page(cpu)) {
- put_online_cpus();
- unregister_cpu_notifier(&balloon_cpu_notifier);
- return -ENOMEM;
- }
- }
- put_online_cpus();
- }
-
pr_info("Initialising balloon driver\n");
balloon_stats.current_pages = xen_pv_domain()
@@ -696,15 +625,4 @@ static int __init balloon_init(void)
subsys_initcall(balloon_init);
-static int __init balloon_clear(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu)
- per_cpu(balloon_scratch_page, cpu) = NULL;
-
- return 0;
-}
-early_initcall(balloon_clear);
-
MODULE_LICENSE("GPL");
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index b4bca2d4a7e5..70fba973a107 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -526,20 +526,26 @@ static unsigned int __startup_pirq(unsigned int irq)
pirq_query_unmask(irq);
rc = set_evtchn_to_irq(evtchn, irq);
- if (rc != 0) {
- pr_err("irq%d: Failed to set port to irq mapping (%d)\n",
- irq, rc);
- xen_evtchn_close(evtchn);
- return 0;
- }
+ if (rc)
+ goto err;
+
bind_evtchn_to_cpu(evtchn, 0);
info->evtchn = evtchn;
+ rc = xen_evtchn_port_setup(info);
+ if (rc)
+ goto err;
+
out:
unmask_evtchn(evtchn);
eoi_pirq(irq_get_irq_data(irq));
return 0;
+
+err:
+ pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc);
+ xen_evtchn_close(evtchn);
+ return 0;
}
static unsigned int startup_pirq(struct irq_data *data)
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 073b4a19a8b0..d5bb1a33d0a3 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;
};
@@ -91,7 +91,9 @@ struct grant_map {
struct gnttab_map_grant_ref *map_ops;
struct gnttab_unmap_grant_ref *unmap_ops;
struct gnttab_map_grant_ref *kmap_ops;
+ struct gnttab_unmap_grant_ref *kunmap_ops;
struct page **pages;
+ unsigned long pages_vm_start;
};
static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
@@ -118,12 +120,13 @@ static void gntdev_free_map(struct grant_map *map)
return;
if (map->pages)
- free_xenballooned_pages(map->count, map->pages);
+ gnttab_free_pages(map->count, map->pages);
kfree(map->pages);
kfree(map->grants);
kfree(map->map_ops);
kfree(map->unmap_ops);
kfree(map->kmap_ops);
+ kfree(map->kunmap_ops);
kfree(map);
}
@@ -140,21 +143,24 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
add->map_ops = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
add->kmap_ops = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
+ add->kunmap_ops = kcalloc(count, sizeof(add->kunmap_ops[0]), GFP_KERNEL);
add->pages = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
if (NULL == add->grants ||
NULL == add->map_ops ||
NULL == add->unmap_ops ||
NULL == add->kmap_ops ||
+ NULL == add->kunmap_ops ||
NULL == add->pages)
goto err;
- if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */))
+ if (gnttab_alloc_pages(count, add->pages))
goto err;
for (i = 0; i < count; i++) {
add->map_ops[i].handle = -1;
add->unmap_ops[i].handle = -1;
add->kmap_ops[i].handle = -1;
+ add->kunmap_ops[i].handle = -1;
}
add->index = 0;
@@ -216,9 +222,9 @@ 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)
@@ -239,6 +245,14 @@ static int find_grant_ptes(pte_t *pte, pgtable_t token,
BUG_ON(pgnr >= map->count);
pte_maddr = arbitrary_virt_to_machine(pte).maddr;
+ /*
+ * Set the PTE as special to force get_user_pages_fast() fall
+ * back to the slow path. If this is not supported as part of
+ * the grant map, it will be done afterwards.
+ */
+ if (xen_feature(XENFEAT_gnttab_map_avail_bits))
+ flags |= (1 << _GNTMAP_guest_avail0);
+
gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags,
map->grants[pgnr].ref,
map->grants[pgnr].domid);
@@ -247,6 +261,15 @@ static int find_grant_ptes(pte_t *pte, pgtable_t token,
return 0;
}
+#ifdef CONFIG_X86
+static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token,
+ unsigned long addr, void *data)
+{
+ set_pte_at(current->mm, addr, pte, pte_mkspecial(*pte));
+ return 0;
+}
+#endif
+
static int map_grant_pages(struct grant_map *map)
{
int i, err = 0;
@@ -280,6 +303,8 @@ static int map_grant_pages(struct grant_map *map)
map->flags | GNTMAP_host_map,
map->grants[i].ref,
map->grants[i].domid);
+ gnttab_set_unmap_op(&map->kunmap_ops[i], address,
+ map->flags | GNTMAP_host_map, -1);
}
}
@@ -290,20 +315,42 @@ static int map_grant_pages(struct grant_map *map)
return err;
for (i = 0; i < map->count; i++) {
- if (map->map_ops[i].status)
+ if (map->map_ops[i].status) {
err = -EINVAL;
- else {
- BUG_ON(map->map_ops[i].handle == -1);
- map->unmap_ops[i].handle = map->map_ops[i].handle;
- pr_debug("map handle=%d\n", map->map_ops[i].handle);
+ continue;
}
+
+ map->unmap_ops[i].handle = map->map_ops[i].handle;
+ if (use_ptemod)
+ map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
}
return err;
}
+struct unmap_grant_pages_callback_data
+{
+ struct completion completion;
+ int result;
+};
+
+static void unmap_grant_callback(int result,
+ struct gntab_unmap_queue_data *data)
+{
+ struct unmap_grant_pages_callback_data* d = data->data;
+
+ d->result = result;
+ complete(&d->completion);
+}
+
static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
{
int i, err = 0;
+ struct gntab_unmap_queue_data unmap_data;
+ struct unmap_grant_pages_callback_data data;
+
+ init_completion(&data.completion);
+ unmap_data.data = &data;
+ unmap_data.done= &unmap_grant_callback;
if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
int pgno = (map->notify.addr >> PAGE_SHIFT);
@@ -315,11 +362,16 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
}
}
- err = gnttab_unmap_refs(map->unmap_ops + offset,
- use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset,
- pages);
- if (err)
- return err;
+ unmap_data.unmap_ops = map->unmap_ops + offset;
+ unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL;
+ unmap_data.pages = map->pages + offset;
+ unmap_data.count = pages;
+
+ gnttab_unmap_refs_async(&unmap_data);
+
+ wait_for_completion(&data.completion);
+ if (data.result)
+ return data.result;
for (i = 0; i < pages; i++) {
if (map->unmap_ops[offset+i].status)
@@ -387,17 +439,26 @@ 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);
}
+static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ struct grant_map *map = vma->vm_private_data;
+
+ return map->pages[(addr - map->pages_vm_start) >> PAGE_SHIFT];
+}
+
static struct vm_operations_struct gntdev_vmops = {
.open = gntdev_vma_open,
.close = gntdev_vma_close,
+ .find_special_page = gntdev_vma_find_special_page,
};
/* ------------------------------------------------------------------ */
@@ -433,14 +494,14 @@ 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 +518,7 @@ 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 +537,7 @@ 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 +559,7 @@ 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);
@@ -572,10 +633,10 @@ 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 +655,7 @@ 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 +663,7 @@ 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 +731,7 @@ 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 +759,7 @@ 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 +809,7 @@ 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 +844,7 @@ 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,
@@ -806,16 +867,34 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
if (err)
goto out_put_map;
}
+ } else {
+#ifdef CONFIG_X86
+ /*
+ * If the PTEs were not made special by the grant map
+ * hypercall, do so here.
+ *
+ * This is racy since the mapping is already visible
+ * to userspace but userspace should be well-behaved
+ * enough to not touch it until the mmap() call
+ * returns.
+ */
+ if (!xen_feature(XENFEAT_gnttab_map_avail_bits)) {
+ apply_to_page_range(vma->vm_mm, vma->vm_start,
+ vma->vm_end - vma->vm_start,
+ set_grant_ptes_as_special, NULL);
+ }
+#endif
+ map->pages_vm_start = vma->vm_start;
}
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/grant-table.c b/drivers/xen/grant-table.c
index 7786291ba229..17972fbacddc 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -42,6 +42,7 @@
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/hardirq.h>
+#include <linux/workqueue.h>
#include <xen/xen.h>
#include <xen/interface/xen.h>
@@ -50,6 +51,7 @@
#include <xen/interface/memory.h>
#include <xen/hvc-console.h>
#include <xen/swiotlb-xen.h>
+#include <xen/balloon.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/interface.h>
@@ -671,6 +673,59 @@ void gnttab_free_auto_xlat_frames(void)
}
EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
+/**
+ * gnttab_alloc_pages - alloc pages suitable for grant mapping into
+ * @nr_pages: number of pages to alloc
+ * @pages: returns the pages
+ */
+int gnttab_alloc_pages(int nr_pages, struct page **pages)
+{
+ int i;
+ int ret;
+
+ ret = alloc_xenballooned_pages(nr_pages, pages, false);
+ if (ret < 0)
+ return ret;
+
+ for (i = 0; i < nr_pages; i++) {
+#if BITS_PER_LONG < 64
+ struct xen_page_foreign *foreign;
+
+ foreign = kzalloc(sizeof(*foreign), GFP_KERNEL);
+ if (!foreign) {
+ gnttab_free_pages(nr_pages, pages);
+ return -ENOMEM;
+ }
+ set_page_private(pages[i], (unsigned long)foreign);
+#endif
+ SetPagePrivate(pages[i]);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(gnttab_alloc_pages);
+
+/**
+ * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
+ * @nr_pages; number of pages to free
+ * @pages: the pages
+ */
+void gnttab_free_pages(int nr_pages, struct page **pages)
+{
+ int i;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (PagePrivate(pages[i])) {
+#if BITS_PER_LONG < 64
+ kfree((void *)page_private(pages[i]));
+#endif
+ ClearPagePrivate(pages[i]);
+ }
+ }
+ free_xenballooned_pages(nr_pages, pages);
+}
+EXPORT_SYMBOL(gnttab_free_pages);
+
/* Handling of paged out grant targets (GNTST_eagain) */
#define MAX_DELAY 256
static inline void
@@ -727,30 +782,87 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
if (ret)
return ret;
- /* Retry eagain maps */
- for (i = 0; i < count; i++)
+ for (i = 0; i < count; i++) {
+ /* Retry eagain maps */
if (map_ops[i].status == GNTST_eagain)
gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
&map_ops[i].status, __func__);
+ if (map_ops[i].status == GNTST_okay) {
+ struct xen_page_foreign *foreign;
+
+ SetPageForeign(pages[i]);
+ foreign = xen_page_foreign(pages[i]);
+ foreign->domid = map_ops[i].dom;
+ foreign->gref = map_ops[i].ref;
+ }
+ }
+
return set_foreign_p2m_mapping(map_ops, kmap_ops, pages, count);
}
EXPORT_SYMBOL_GPL(gnttab_map_refs);
int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
- struct gnttab_map_grant_ref *kmap_ops,
+ struct gnttab_unmap_grant_ref *kunmap_ops,
struct page **pages, unsigned int count)
{
+ unsigned int i;
int ret;
ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
if (ret)
return ret;
- return clear_foreign_p2m_mapping(unmap_ops, kmap_ops, pages, count);
+ for (i = 0; i < count; i++)
+ ClearPageForeign(pages[i]);
+
+ return clear_foreign_p2m_mapping(unmap_ops, kunmap_ops, pages, count);
}
EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
+#define GNTTAB_UNMAP_REFS_DELAY 5
+
+static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item);
+
+static void gnttab_unmap_work(struct work_struct *work)
+{
+ struct gntab_unmap_queue_data
+ *unmap_data = container_of(work,
+ struct gntab_unmap_queue_data,
+ gnttab_work.work);
+ if (unmap_data->age != UINT_MAX)
+ unmap_data->age++;
+ __gnttab_unmap_refs_async(unmap_data);
+}
+
+static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
+{
+ int ret;
+ int pc;
+
+ for (pc = 0; pc < item->count; pc++) {
+ if (page_count(item->pages[pc]) > 1) {
+ unsigned long delay = GNTTAB_UNMAP_REFS_DELAY * (item->age + 1);
+ schedule_delayed_work(&item->gnttab_work,
+ msecs_to_jiffies(delay));
+ return;
+ }
+ }
+
+ ret = gnttab_unmap_refs(item->unmap_ops, item->kunmap_ops,
+ item->pages, item->count);
+ item->done(ret, item);
+}
+
+void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
+{
+ INIT_DELAYED_WORK(&item->gnttab_work, gnttab_unmap_work);
+ item->age = 0;
+
+ __gnttab_unmap_refs_async(item);
+}
+EXPORT_SYMBOL_GPL(gnttab_unmap_refs_async);
+
static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes)
{
int rc;
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index f8bb36f9d9ce..bf1940706422 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -105,10 +105,16 @@ static void do_suspend(void)
err = freeze_processes();
if (err) {
- pr_err("%s: freeze failed %d\n", __func__, err);
+ pr_err("%s: freeze processes failed %d\n", __func__, err);
goto out;
}
+ err = freeze_kernel_threads();
+ if (err) {
+ pr_err("%s: freeze kernel threads failed %d\n", __func__, err);
+ goto out_thaw;
+ }
+
err = dpm_suspend_start(PMSG_FREEZE);
if (err) {
pr_err("%s: dpm_suspend_start %d\n", __func__, err);
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/tmem.c b/drivers/xen/tmem.c
index 83b5c53bec6b..8a65423bc696 100644
--- a/drivers/xen/tmem.c
+++ b/drivers/xen/tmem.c
@@ -374,7 +374,7 @@ static struct frontswap_ops tmem_frontswap_ops = {
};
#endif
-static int xen_tmem_init(void)
+static int __init xen_tmem_init(void)
{
if (!xen_domain())
return 0;
diff --git a/drivers/xen/xen-acpi-memhotplug.c b/drivers/xen/xen-acpi-memhotplug.c
index 34e40b733f9a..4fc886cd5586 100644
--- a/drivers/xen/xen-acpi-memhotplug.c
+++ b/drivers/xen/xen-acpi-memhotplug.c
@@ -117,8 +117,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context)
list_for_each_entry(info, &mem_device->res_list, list) {
if ((info->caching == address64.info.mem.caching) &&
(info->write_protect == address64.info.mem.write_protect) &&
- (info->start_addr + info->length == address64.minimum)) {
- info->length += address64.address_length;
+ (info->start_addr + info->length == address64.address.minimum)) {
+ info->length += address64.address.address_length;
return AE_OK;
}
}
@@ -130,8 +130,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context)
INIT_LIST_HEAD(&new->list);
new->caching = address64.info.mem.caching;
new->write_protect = address64.info.mem.write_protect;
- new->start_addr = address64.minimum;
- new->length = address64.address_length;
+ new->start_addr = address64.address.minimum;
+ new->length = address64.address.address_length;
list_add_tail(&new->list, &mem_device->res_list);
return AE_OK;
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 46ae0f9f02ad..75fe3d466515 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -16,7 +16,7 @@
#include "conf_space.h"
#include "conf_space_quirks.h"
-static bool permissive;
+bool permissive;
module_param(permissive, bool, 0644);
/* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word,
diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h
index e56c934ad137..2e1d73d1d5d0 100644
--- a/drivers/xen/xen-pciback/conf_space.h
+++ b/drivers/xen/xen-pciback/conf_space.h
@@ -64,6 +64,8 @@ struct config_field_entry {
void *data;
};
+extern bool permissive;
+
#define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
/* Add fields to a device - the add_fields macro expects to get a pointer to
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
index c5ee82587e8c..2d7369391472 100644
--- a/drivers/xen/xen-pciback/conf_space_header.c
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -11,6 +11,10 @@
#include "pciback.h"
#include "conf_space.h"
+struct pci_cmd_info {
+ u16 val;
+};
+
struct pci_bar_info {
u32 val;
u32 len_val;
@@ -20,22 +24,36 @@ struct pci_bar_info {
#define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO))
#define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER)
-static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data)
+/* Bits guests are allowed to control in permissive mode. */
+#define PCI_COMMAND_GUEST (PCI_COMMAND_MASTER|PCI_COMMAND_SPECIAL| \
+ PCI_COMMAND_INVALIDATE|PCI_COMMAND_VGA_PALETTE| \
+ PCI_COMMAND_WAIT|PCI_COMMAND_FAST_BACK)
+
+static void *command_init(struct pci_dev *dev, int offset)
{
- int i;
- int ret;
-
- ret = xen_pcibk_read_config_word(dev, offset, value, data);
- if (!pci_is_enabled(dev))
- return ret;
-
- for (i = 0; i < PCI_ROM_RESOURCE; i++) {
- if (dev->resource[i].flags & IORESOURCE_IO)
- *value |= PCI_COMMAND_IO;
- if (dev->resource[i].flags & IORESOURCE_MEM)
- *value |= PCI_COMMAND_MEMORY;
+ struct pci_cmd_info *cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+ int err;
+
+ if (!cmd)
+ return ERR_PTR(-ENOMEM);
+
+ err = pci_read_config_word(dev, PCI_COMMAND, &cmd->val);
+ if (err) {
+ kfree(cmd);
+ return ERR_PTR(err);
}
+ return cmd;
+}
+
+static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data)
+{
+ int ret = pci_read_config_word(dev, offset, value);
+ const struct pci_cmd_info *cmd = data;
+
+ *value &= PCI_COMMAND_GUEST;
+ *value |= cmd->val & ~PCI_COMMAND_GUEST;
+
return ret;
}
@@ -43,6 +61,8 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
{
struct xen_pcibk_dev_data *dev_data;
int err;
+ u16 val;
+ struct pci_cmd_info *cmd = data;
dev_data = pci_get_drvdata(dev);
if (!pci_is_enabled(dev) && is_enable_cmd(value)) {
@@ -83,6 +103,19 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
}
}
+ cmd->val = value;
+
+ if (!permissive && (!dev_data || !dev_data->permissive))
+ return 0;
+
+ /* Only allow the guest to control certain bits. */
+ err = pci_read_config_word(dev, offset, &val);
+ if (err || val == value)
+ return err;
+
+ value &= PCI_COMMAND_GUEST;
+ value |= val & ~PCI_COMMAND_GUEST;
+
return pci_write_config_word(dev, offset, value);
}
@@ -282,6 +315,8 @@ static const struct config_field header_common[] = {
{
.offset = PCI_COMMAND,
.size = 2,
+ .init = command_init,
+ .release = bar_release,
.u.w.read = command_read,
.u.w.write = command_write,
},
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index e999496eda3e..42bd55a6c237 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -47,6 +47,7 @@
#include <generated/utsrelease.h>
+#include <scsi/scsi.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_tcq.h>
@@ -227,7 +228,7 @@ static void put_free_pages(struct page **page, int num)
return;
if (i > scsiback_max_buffer_pages) {
n = min(num, i - scsiback_max_buffer_pages);
- free_xenballooned_pages(n, page + num - n);
+ gnttab_free_pages(n, page + num - n);
n = num - n;
}
spin_lock_irqsave(&free_pages_lock, flags);
@@ -244,7 +245,7 @@ static int get_free_page(struct page **page)
spin_lock_irqsave(&free_pages_lock, flags);
if (list_empty(&scsiback_free_pages)) {
spin_unlock_irqrestore(&free_pages_lock, flags);
- return alloc_xenballooned_pages(1, page, false);
+ return gnttab_alloc_pages(1, page);
}
page[0] = list_first_entry(&scsiback_free_pages, struct page, lru);
list_del(&page[0]->lru);
@@ -708,12 +709,11 @@ static int prepare_pending_reqs(struct vscsibk_info *info,
static int scsiback_do_cmd_fn(struct vscsibk_info *info)
{
struct vscsiif_back_ring *ring = &info->ring;
- struct vscsiif_request *ring_req;
+ struct vscsiif_request ring_req;
struct vscsibk_pend *pending_req;
RING_IDX rc, rp;
int err, more_to_do;
uint32_t result;
- uint8_t act;
rc = ring->req_cons;
rp = ring->sring->req_prod;
@@ -734,11 +734,10 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
if (!pending_req)
return 1;
- ring_req = RING_GET_REQUEST(ring, rc);
+ ring_req = *RING_GET_REQUEST(ring, rc);
ring->req_cons = ++rc;
- act = ring_req->act;
- err = prepare_pending_reqs(info, ring_req, pending_req);
+ err = prepare_pending_reqs(info, &ring_req, pending_req);
if (err) {
switch (err) {
case -ENODEV:
@@ -754,9 +753,9 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
return 1;
}
- switch (act) {
+ switch (ring_req.act) {
case VSCSIIF_ACT_SCSI_CDB:
- if (scsiback_gnttab_data_map(ring_req, pending_req)) {
+ if (scsiback_gnttab_data_map(&ring_req, pending_req)) {
scsiback_fast_flush_area(pending_req);
scsiback_do_resp_with_sense(NULL,
DRIVER_ERROR << 24, 0, pending_req);
@@ -767,7 +766,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info)
break;
case VSCSIIF_ACT_SCSI_ABORT:
scsiback_device_action(pending_req, TMR_ABORT_TASK,
- ring_req->ref_rqid);
+ ring_req.ref_rqid);
break;
case VSCSIIF_ACT_SCSI_RESET:
scsiback_device_action(pending_req, TMR_LUN_RESET, 0);
@@ -1660,11 +1659,8 @@ static int scsiback_make_nexus(struct scsiback_tpg *tpg,
name);
goto out;
}
- /*
- * Now register the TCM pvscsi virtual I_T Nexus as active with the
- * call to __transport_register_session()
- */
- __transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
+ /* Now register the TCM pvscsi virtual I_T Nexus as active. */
+ transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
tv_nexus->tvn_se_sess, tv_nexus);
tpg->tpg_nexus = tv_nexus;
@@ -2106,7 +2102,7 @@ static void __exit scsiback_exit(void)
while (free_pages_num) {
if (get_free_page(&page))
BUG();
- free_xenballooned_pages(1, &page);
+ gnttab_free_pages(1, &page);
}
scsiback_deregister_configfs();
xenbus_unregister_driver(&scsiback_driver);
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 85534ea63555..9433e46518c8 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -326,10 +326,13 @@ static int xenbus_write_transaction(unsigned msg_type,
}
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) {
+ 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_for_each_entry(trans, &u->transactions, list)
if (trans->handle.id == u->u.msg.tx_id)
break;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.