[PATCH v1 2/6] mm/memory_hotplug: make add_memory() take the device_hotplug_lock

From: David Hildenbrand
Date: Tue Sep 18 2018 - 07:48:51 EST


add_memory() currently does not take the device_hotplug_lock, however
is aleady called under the lock from
arch/powerpc/platforms/pseries/hotplug-memory.c
drivers/acpi/acpi_memhotplug.c
to synchronize against CPU hot-remove and similar.

In general, we should hold the device_hotplug_lock when adding memory
to synchronize against online/offline request (e.g. from user space) -
which already resulted in lock inversions due to device_lock() and
mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory
hot-add deadlock"). add_memory()/add_memory_resource() will create memory
block devices, so this really feels like the right thing to do.

Holding the device_hotplug_lock makes sure that a memory block device
can really only be accessed (e.g. via .online/.state) from user space,
once the memory has been fully added to the system.

The lock is not held yet in
drivers/xen/balloon.c
arch/powerpc/platforms/powernv/memtrace.c
drivers/s390/char/sclp_cmd.c
drivers/hv/hv_balloon.c
So, let's either use the locked variants or take the lock.

Don't export add_memory_resource(), as it once was exported to be used
by XEN, which is never built as a module. If somebody requires it, we
also have to export a locked variant (as device_hotplug_lock is never
exported).

Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rjw@xxxxxxxxxxxxx>
Cc: Len Brown <lenb@xxxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Cc: Nathan Fontenot <nfont@xxxxxxxxxxxxxxxxxx>
Cc: John Allen <jallen@xxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Mathieu Malaterre <malat@xxxxxxxxxx>
Cc: Pavel Tatashin <pavel.tatashin@xxxxxxxxxxxxx>
Cc: YASUAKI ISHIMATSU <yasu.isimatu@xxxxxxxxx>
Reviewed-by: Pavel Tatashin <pavel.tatashin@xxxxxxxxxxxxx>
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
.../platforms/pseries/hotplug-memory.c | 2 +-
drivers/acpi/acpi_memhotplug.c | 2 +-
drivers/base/memory.c | 9 ++++++--
drivers/xen/balloon.c | 3 +++
include/linux/memory_hotplug.h | 1 +
mm/memory_hotplug.c | 22 ++++++++++++++++---
6 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index b3f54466e25f..2e6f41dc103a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -702,7 +702,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
nid = memory_add_physaddr_to_nid(lmb->base_addr);

/* Add the memory */
- rc = add_memory(nid, lmb->base_addr, block_sz);
+ rc = __add_memory(nid, lmb->base_addr, block_sz);
if (rc) {
dlpar_remove_device_tree_lmb(lmb);
return rc;
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 811148415993..8fe0960ea572 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -228,7 +228,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
if (node < 0)
node = memory_add_physaddr_to_nid(info->start_addr);

- result = add_memory(node, info->start_addr, info->length);
+ result = __add_memory(node, info->start_addr, info->length);

/*
* If the memory block has been used by the kernel, add_memory()
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 817320c7c4c1..40cac122ec73 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -519,15 +519,20 @@ memory_probe_store(struct device *dev, struct device_attribute *attr,
if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
return -EINVAL;

+ ret = lock_device_hotplug_sysfs();
+ if (ret)
+ goto out;
+
nid = memory_add_physaddr_to_nid(phys_addr);
- ret = add_memory(nid, phys_addr,
- MIN_MEMORY_BLOCK_SIZE * sections_per_block);
+ ret = __add_memory(nid, phys_addr,
+ MIN_MEMORY_BLOCK_SIZE * sections_per_block);

if (ret)
goto out;

ret = count;
out:
+ unlock_device_hotplug();
return ret;
}

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index e12bb256036f..6bab019a82b1 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -395,7 +395,10 @@ static enum bp_state reserve_additional_memory(void)
* callers drop the mutex before trying again.
*/
mutex_unlock(&balloon_mutex);
+ /* add_memory_resource() requires the device_hotplug lock */
+ lock_device_hotplug();
rc = add_memory_resource(nid, resource, memhp_auto_online);
+ unlock_device_hotplug();
mutex_lock(&balloon_mutex);

if (rc) {
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 1f096852f479..ffd9cd10fcf3 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -324,6 +324,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {}
extern void __ref free_area_init_core_hotplug(int nid);
extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
void *arg, int (*func)(struct memory_block *, void *));
+extern int __add_memory(int nid, u64 start, u64 size);
extern int add_memory(int nid, u64 start, u64 size);
extern int add_memory_resource(int nid, struct resource *resource, bool online);
extern int arch_add_memory(int nid, u64 start, u64 size,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b8b1bd970322..ef5444145c88 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1111,7 +1111,12 @@ static int online_memory_block(struct memory_block *mem, void *arg)
return device_online(&mem->dev);
}

-/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+/*
+ * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
+ * and online/offline operations (triggered e.g. by sysfs).
+ *
+ * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
+ */
int __ref add_memory_resource(int nid, struct resource *res, bool online)
{
u64 start, size;
@@ -1180,9 +1185,9 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
mem_hotplug_done();
return ret;
}
-EXPORT_SYMBOL_GPL(add_memory_resource);

-int __ref add_memory(int nid, u64 start, u64 size)
+/* requires device_hotplug_lock, see add_memory_resource() */
+int __ref __add_memory(int nid, u64 start, u64 size)
{
struct resource *res;
int ret;
@@ -1196,6 +1201,17 @@ int __ref add_memory(int nid, u64 start, u64 size)
release_memory_resource(res);
return ret;
}
+
+int add_memory(int nid, u64 start, u64 size)
+{
+ int rc;
+
+ lock_device_hotplug();
+ rc = __add_memory(nid, start, size);
+ unlock_device_hotplug();
+
+ return rc;
+}
EXPORT_SYMBOL_GPL(add_memory);

#ifdef CONFIG_MEMORY_HOTREMOVE
--
2.17.1