From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S940239AbdDSWhl (ORCPT ); Wed, 19 Apr 2017 18:37:41 -0400 Received: from mga07.intel.com ([134.134.136.100]:62770 "EHLO mga07.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S940221AbdDSWhi (ORCPT ); Wed, 19 Apr 2017 18:37:38 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.37,222,1488873600"; d="scan'208";a="251208840" Subject: [PATCH v3] dax: add a facility to lookup a dax device by 'host' device name From: Dan Williams To: linux-nvdimm@ml01.01.org Cc: linux-fsdevel@vger.kernel.org, linux-block@vger.kernel.org, dm-devel@redhat.com, linux-kernel@vger.kernel.org, hch@lst.de Date: Wed, 19 Apr 2017 15:31:53 -0700 Message-ID: <149264098308.36586.14533308558533384197.stgit@dwillia2-desk3.amr.corp.intel.com> User-Agent: StGit/0.17.1-9-g687f MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org For the current block_device based filesystem-dax path, we need a way for it to lookup the dax_device associated with a block_device. Add a 'host' property of a dax_device that can be used for this purpose. It is a free form string, but for a dax_device associated with a block device it is the bdev name. This is a stop-gap until filesystems are able to mount on a dax-inode directly. Signed-off-by: Dan Williams --- Changes since v2: * fixed slab corruption due to non-null dax_dev->host at dax_i_callback() time drivers/dax/dax.h | 2 + drivers/dax/device.c | 2 + drivers/dax/super.c | 87 ++++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/dax.h | 1 + 4 files changed, 86 insertions(+), 6 deletions(-) diff --git a/drivers/dax/dax.h b/drivers/dax/dax.h index 2472d9da96db..246a24d68d4c 100644 --- a/drivers/dax/dax.h +++ b/drivers/dax/dax.h @@ -13,7 +13,7 @@ #ifndef __DAX_H__ #define __DAX_H__ struct dax_device; -struct dax_device *alloc_dax(void *private); +struct dax_device *alloc_dax(void *private, const char *host); void put_dax(struct dax_device *dax_dev); bool dax_alive(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 19a42edbfa03..db68f4fa8ce0 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -645,7 +645,7 @@ struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region, goto err_id; } - dax_dev = alloc_dax(dev_dax); + dax_dev = alloc_dax(dev_dax, NULL); if (!dax_dev) goto err_dax; diff --git a/drivers/dax/super.c b/drivers/dax/super.c index c9f85f1c086e..8d446674c1da 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -30,6 +30,10 @@ static DEFINE_IDA(dax_minor_ida); static struct kmem_cache *dax_cache __read_mostly; static struct super_block *dax_superblock __read_mostly; +#define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head)) +static struct hlist_head dax_host_list[DAX_HASH_SIZE]; +static DEFINE_SPINLOCK(dax_host_lock); + int dax_read_lock(void) { return srcu_read_lock(&dax_srcu); @@ -46,12 +50,15 @@ EXPORT_SYMBOL_GPL(dax_read_unlock); * struct dax_device - anchor object for dax services * @inode: core vfs * @cdev: optional character interface for "device dax" + * @host: optional name for lookups where the device path is not available * @private: dax driver private data * @alive: !alive + rcu grace period == no new operations / mappings */ struct dax_device { + struct hlist_node list; struct inode inode; struct cdev cdev; + const char *host; void *private; bool alive; }; @@ -63,6 +70,11 @@ bool dax_alive(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(dax_alive); +static int dax_host_hash(const char *host) +{ + return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; +} + /* * Note, rcu is not protecting the liveness of dax_dev, rcu is ensuring * that any fault handlers or operations that might have seen @@ -75,7 +87,13 @@ void kill_dax(struct dax_device *dax_dev) return; dax_dev->alive = false; + synchronize_srcu(&dax_srcu); + + spin_lock(&dax_host_lock); + hlist_del_init(&dax_dev->list); + spin_unlock(&dax_host_lock); + dax_dev->private = NULL; } EXPORT_SYMBOL_GPL(kill_dax); @@ -98,6 +116,8 @@ static void dax_i_callback(struct rcu_head *head) struct inode *inode = container_of(head, struct inode, i_rcu); struct dax_device *dax_dev = to_dax_dev(inode); + kfree(dax_dev->host); + dax_dev->host = NULL; ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev)); kmem_cache_free(dax_cache, dax_dev); } @@ -169,26 +189,53 @@ static struct dax_device *dax_dev_get(dev_t devt) return dax_dev; } -struct dax_device *alloc_dax(void *private) +static void dax_add_host(struct dax_device *dax_dev, const char *host) +{ + int hash; + + /* + * Unconditionally init dax_dev since it's coming from a + * non-zeroed slab cache + */ + INIT_HLIST_NODE(&dax_dev->list); + dax_dev->host = host; + if (!host) + return; + + hash = dax_host_hash(host); + spin_lock(&dax_host_lock); + hlist_add_head(&dax_dev->list, &dax_host_list[hash]); + spin_unlock(&dax_host_lock); +} + +struct dax_device *alloc_dax(void *private, const char *__host) { struct dax_device *dax_dev; + const char *host; dev_t devt; int minor; + host = kstrdup(__host, GFP_KERNEL); + if (__host && !host) + return NULL; + minor = ida_simple_get(&dax_minor_ida, 0, nr_dax, GFP_KERNEL); if (minor < 0) - return NULL; + goto err_minor; devt = MKDEV(MAJOR(dax_devt), minor); dax_dev = dax_dev_get(devt); if (!dax_dev) - goto err_inode; + goto err_dev; + dax_add_host(dax_dev, host); dax_dev->private = private; return dax_dev; - err_inode: + err_dev: ida_simple_remove(&dax_minor_ida, minor); + err_minor: + kfree(host); return NULL; } EXPORT_SYMBOL_GPL(alloc_dax); @@ -202,6 +249,38 @@ void put_dax(struct dax_device *dax_dev) EXPORT_SYMBOL_GPL(put_dax); /** + * dax_get_by_host() - temporary lookup mechanism for filesystem-dax + * @host: alternate name for the device registered by a dax driver + */ +struct dax_device *dax_get_by_host(const char *host) +{ + struct dax_device *dax_dev, *found = NULL; + int hash, id; + + if (!host) + return NULL; + + hash = dax_host_hash(host); + + id = dax_read_lock(); + spin_lock(&dax_host_lock); + hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) { + if (!dax_alive(dax_dev) + || strcmp(host, dax_dev->host) != 0) + continue; + + if (igrab(&dax_dev->inode)) + found = dax_dev; + break; + } + spin_unlock(&dax_host_lock); + dax_read_unlock(id); + + return found; +} +EXPORT_SYMBOL_GPL(dax_get_by_host); + +/** * inode_dax: convert a public inode into its dax_dev * @inode: An inode with i_cdev pointing to a dax_dev * diff --git a/include/linux/dax.h b/include/linux/dax.h index 5b62f5d19aea..9b2d5ba10d7d 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -10,6 +10,7 @@ struct iomap_ops; int dax_read_lock(void); void dax_read_unlock(int id); +struct dax_device *dax_get_by_host(const char *host); /* * We use lowest available bit in exceptional entry for locking, one bit for