libnvdimm: fix clear poison locking with spinlock and GFP_NOWAIT allocation

The following warning results from holding a lane spinlock,
preempt_disable(), or the btt map spinlock and then trying to take the
reconfig_mutex to walk the poison list and potentially add new entries.

BUG: sleeping function called from invalid context at kernel/locking/mutex.
c:747
in_atomic(): 1, irqs_disabled(): 0, pid: 17159, name: dd
[..]
Call Trace:
dump_stack+0x85/0xc8
___might_sleep+0x184/0x250
__might_sleep+0x4a/0x90
__mutex_lock+0x58/0x9b0
? nvdimm_bus_lock+0x21/0x30 [libnvdimm]
? __nvdimm_bus_badblocks_clear+0x2f/0x60 [libnvdimm]
? acpi_nfit_forget_poison+0x79/0x80 [nfit]
? _raw_spin_unlock+0x27/0x40
mutex_lock_nested+0x1b/0x20
nvdimm_bus_lock+0x21/0x30 [libnvdimm]
nvdimm_forget_poison+0x25/0x50 [libnvdimm]
nvdimm_clear_poison+0x106/0x140 [libnvdimm]
nsio_rw_bytes+0x164/0x270 [libnvdimm]
btt_write_pg+0x1de/0x3e0 [nd_btt]
? blk_queue_enter+0x30/0x290
btt_make_request+0x11a/0x310 [nd_btt]
? blk_queue_enter+0xb7/0x290
? blk_queue_enter+0x30/0x290
generic_make_request+0x118/0x3b0

A spinlock is introduced to protect the poison list. This allows us to not
having to acquire the reconfig_mutex for touching the poison list. The
add_poison() function has been broken out into two helper functions. One to
allocate the poison entry and the other to apppend the entry. This allows us
to unlock the poison_lock in non-I/O path and continue to be able to allocate
the poison entry with GFP_KERNEL. We will use GFP_NOWAIT in the I/O path in
order to satisfy being in atomic context.

Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 4 insertions, 3 deletions

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 5ad2e5909e1a..d214ac44d111 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -296,6 +296,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
 	init_waitqueue_head(&nvdimm_bus->probe_wait);
 	nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
 	mutex_init(&nvdimm_bus->reconfig_mutex);
+	spin_lock_init(&nvdimm_bus->poison_lock);
 	if (nvdimm_bus->id < 0) {
 		kfree(nvdimm_bus);
 		return NULL;
@@ -364,9 +365,9 @@ static int nd_bus_remove(struct device *dev)
 	nd_synchronize();
 	device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
 
-	nvdimm_bus_lock(&nvdimm_bus->dev);
+	spin_lock(&nvdimm_bus->poison_lock);
 	free_poison_list(&nvdimm_bus->poison_list);
-	nvdimm_bus_unlock(&nvdimm_bus->dev);
+	spin_unlock(&nvdimm_bus->poison_lock);
 
 	nvdimm_bus_destroy_ndctl(nvdimm_bus);
 
@@ -990,7 +991,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 
 		if (clear_err->cleared) {
 			/* clearing the poison list we keep track of */
-			__nvdimm_forget_poison(nvdimm_bus, clear_err->address,
+			nvdimm_forget_poison(nvdimm_bus, clear_err->address,
 					clear_err->cleared);
 
 			/* now sync the badblocks lists */