linux/drivers/nvdimm/nd-core.h
Dave Jiang b3b454f694 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>
2017-04-13 14:23:51 -07:00

119 lines
4.6 KiB
C

/*
* Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#ifndef __ND_CORE_H__
#define __ND_CORE_H__
#include <linux/libnvdimm.h>
#include <linux/device.h>
#include <linux/libnvdimm.h>
#include <linux/sizes.h>
#include <linux/mutex.h>
#include <linux/nd.h>
extern struct list_head nvdimm_bus_list;
extern struct mutex nvdimm_bus_list_mutex;
extern int nvdimm_major;
struct nvdimm_bus {
struct nvdimm_bus_descriptor *nd_desc;
wait_queue_head_t probe_wait;
struct list_head list;
struct device dev;
int id, probe_active;
struct list_head poison_list;
struct list_head mapping_list;
struct mutex reconfig_mutex;
spinlock_t poison_lock;
};
struct nvdimm {
unsigned long flags;
void *provider_data;
unsigned long cmd_mask;
struct device dev;
atomic_t busy;
int id, num_flush;
struct resource *flush_wpq;
};
/**
* struct blk_alloc_info - tracking info for BLK dpa scanning
* @nd_mapping: blk region mapping boundaries
* @available: decremented in alias_dpa_busy as aliased PMEM is scanned
* @busy: decremented in blk_dpa_busy to account for ranges already
* handled by alias_dpa_busy
* @res: alias_dpa_busy interprets this a free space range that needs to
* be truncated to the valid BLK allocation starting DPA, blk_dpa_busy
* treats it as a busy range that needs the aliased PMEM ranges
* truncated.
*/
struct blk_alloc_info {
struct nd_mapping *nd_mapping;
resource_size_t available, busy;
struct resource *res;
};
bool is_nvdimm(struct device *dev);
bool is_nd_pmem(struct device *dev);
bool is_nd_blk(struct device *dev);
struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
int __init nvdimm_bus_init(void);
void nvdimm_bus_exit(void);
void nvdimm_devs_exit(void);
void nd_region_devs_exit(void);
void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev);
struct nd_region;
void nd_region_create_ns_seed(struct nd_region *nd_region);
void nd_region_create_btt_seed(struct nd_region *nd_region);
void nd_region_create_pfn_seed(struct nd_region *nd_region);
void nd_region_create_dax_seed(struct nd_region *nd_region);
void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev);
int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);
void nd_synchronize(void);
int nvdimm_bus_register_dimms(struct nvdimm_bus *nvdimm_bus);
int nvdimm_bus_register_regions(struct nvdimm_bus *nvdimm_bus);
int nvdimm_bus_init_interleave_sets(struct nvdimm_bus *nvdimm_bus);
void __nd_device_register(struct device *dev);
int nd_match_dimm(struct device *dev, void *data);
struct nd_label_id;
char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags);
bool nd_is_uuid_unique(struct device *dev, u8 *uuid);
struct nd_region;
struct nvdimm_drvdata;
struct nd_mapping;
void nd_mapping_free_labels(struct nd_mapping *nd_mapping);
resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, resource_size_t *overlap);
resource_size_t nd_blk_available_dpa(struct nd_region *nd_region);
resource_size_t nd_region_available_dpa(struct nd_region *nd_region);
resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd,
struct nd_label_id *label_id);
int alias_dpa_busy(struct device *dev, void *data);
struct resource *nsblk_add_resource(struct nd_region *nd_region,
struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk,
resource_size_t start);
int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd);
void get_ndd(struct nvdimm_drvdata *ndd);
resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns);
void nd_detach_ndns(struct device *dev, struct nd_namespace_common **_ndns);
void __nd_detach_ndns(struct device *dev, struct nd_namespace_common **_ndns);
bool nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
struct nd_namespace_common **_ndns);
bool __nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
struct nd_namespace_common **_ndns);
ssize_t nd_namespace_store(struct device *dev,
struct nd_namespace_common **_ndns, const char *buf,
size_t len);
struct nd_pfn *to_nd_pfn_safe(struct device *dev);
#endif /* __ND_CORE_H__ */