[ Upstream commit
8df1d0e4a265f25dc1e7e7624ccdbcb4a6630c89 ]
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).
Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mathieu Malaterre <malat@debian.org>
Cc: Pavel Tatashin <pavel.tatashin@microsoft.com>
Cc: YASUAKI ISHIMATSU <yasu.isimatu@gmail.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
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);
dlpar_release_drc(lmb->drc_index);
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()
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;
}
* 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) {
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 zone_for_memory(int nid, u64 start, u64 size, int zone_default,
return memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
}
-/* 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;
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;
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