xref: /openbmc/linux/drivers/dax/super.c (revision fb08a190)

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright(c) 2017 Intel Corporation. All rights reserved.
 */
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/magic.h>
#include <linux/pfn_t.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/uio.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include "dax-private.h"

/**
 * struct dax_device - anchor object for dax services
 * @inode: core vfs
 * @cdev: optional character interface for "device dax"
 * @private: dax driver private data
 * @flags: state and boolean properties
 */
struct dax_device {
	struct inode inode;
	struct cdev cdev;
	void *private;
	unsigned long flags;
	const struct dax_operations *ops;
};

static dev_t dax_devt;
DEFINE_STATIC_SRCU(dax_srcu);
static struct vfsmount *dax_mnt;
static DEFINE_IDA(dax_minor_ida);
static struct kmem_cache *dax_cache __read_mostly;
static struct super_block *dax_superblock __read_mostly;

int dax_read_lock(void)
{
	return srcu_read_lock(&dax_srcu);
}
EXPORT_SYMBOL_GPL(dax_read_lock);

void dax_read_unlock(int id)
{
	srcu_read_unlock(&dax_srcu, id);
}
EXPORT_SYMBOL_GPL(dax_read_unlock);

#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
#include <linux/blkdev.h>

static DEFINE_XARRAY(dax_hosts);

int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
{
	return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(dax_add_host);

void dax_remove_host(struct gendisk *disk)
{
	xa_erase(&dax_hosts, (unsigned long)disk);
}
EXPORT_SYMBOL_GPL(dax_remove_host);

int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
		pgoff_t *pgoff)
{
	sector_t start_sect = bdev ? get_start_sect(bdev) : 0;
	phys_addr_t phys_off = (start_sect + sector) * 512;

	if (pgoff)
		*pgoff = PHYS_PFN(phys_off);
	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
		return -EINVAL;
	return 0;
}
EXPORT_SYMBOL(bdev_dax_pgoff);

/**
 * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
 * @bdev: block device to find a dax_device for
 */
struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
{
	struct dax_device *dax_dev;
	int id;

	if (!blk_queue_dax(bdev->bd_disk->queue))
		return NULL;

	id = dax_read_lock();
	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
		dax_dev = NULL;
	dax_read_unlock(id);

	return dax_dev;
}
EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);

bool generic_fsdax_supported(struct dax_device *dax_dev,
		struct block_device *bdev, int blocksize, sector_t start,
		sector_t sectors)
{
	bool dax_enabled = false;
	pgoff_t pgoff, pgoff_end;
	void *kaddr, *end_kaddr;
	pfn_t pfn, end_pfn;
	sector_t last_page;
	long len, len2;
	int err, id;

	if (blocksize != PAGE_SIZE) {
		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
		return false;
	}

	if (!dax_dev) {
		pr_debug("%pg: error: dax unsupported by block device\n", bdev);
		return false;
	}

	err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
	if (err) {
		pr_info("%pg: error: unaligned partition for dax\n", bdev);
		return false;
	}

	last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512;
	err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end);
	if (err) {
		pr_info("%pg: error: unaligned partition for dax\n", bdev);
		return false;
	}

	id = dax_read_lock();
	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);

	if (len < 1 || len2 < 1) {
		pr_info("%pg: error: dax access failed (%ld)\n",
				bdev, len < 1 ? len : len2);
		dax_read_unlock(id);
		return false;
	}

	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
		/*
		 * An arch that has enabled the pmem api should also
		 * have its drivers support pfn_t_devmap()
		 *
		 * This is a developer warning and should not trigger in
		 * production. dax_flush() will crash since it depends
		 * on being able to do (page_address(pfn_to_page())).
		 */
		WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
		dax_enabled = true;
	} else if (pfn_t_devmap(pfn) && pfn_t_devmap(end_pfn)) {
		struct dev_pagemap *pgmap, *end_pgmap;

		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
		end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL);
		if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX
				&& pfn_t_to_page(pfn)->pgmap == pgmap
				&& pfn_t_to_page(end_pfn)->pgmap == pgmap
				&& pfn_t_to_pfn(pfn) == PHYS_PFN(__pa(kaddr))
				&& pfn_t_to_pfn(end_pfn) == PHYS_PFN(__pa(end_kaddr)))
			dax_enabled = true;
		put_dev_pagemap(pgmap);
		put_dev_pagemap(end_pgmap);

	}
	dax_read_unlock(id);

	if (!dax_enabled) {
		pr_info("%pg: error: dax support not enabled\n", bdev);
		return false;
	}
	return true;
}
EXPORT_SYMBOL_GPL(generic_fsdax_supported);

bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
		int blocksize, sector_t start, sector_t len)
{
	bool ret = false;
	int id;

	if (!dax_dev)
		return false;

	id = dax_read_lock();
	if (dax_alive(dax_dev) && dax_dev->ops->dax_supported)
		ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize,
						  start, len);
	dax_read_unlock(id);
	return ret;
}
EXPORT_SYMBOL_GPL(dax_supported);
#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */

enum dax_device_flags {
	/* !alive + rcu grace period == no new operations / mappings */
	DAXDEV_ALIVE,
	/* gate whether dax_flush() calls the low level flush routine */
	DAXDEV_WRITE_CACHE,
	/* flag to check if device supports synchronous flush */
	DAXDEV_SYNC,
};

/**
 * dax_direct_access() - translate a device pgoff to an absolute pfn
 * @dax_dev: a dax_device instance representing the logical memory range
 * @pgoff: offset in pages from the start of the device to translate
 * @nr_pages: number of consecutive pages caller can handle relative to @pfn
 * @kaddr: output parameter that returns a virtual address mapping of pfn
 * @pfn: output parameter that returns an absolute pfn translation of @pgoff
 *
 * Return: negative errno if an error occurs, otherwise the number of
 * pages accessible at the device relative @pgoff.
 */
long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
		void **kaddr, pfn_t *pfn)
{
	long avail;

	if (!dax_dev)
		return -EOPNOTSUPP;

	if (!dax_alive(dax_dev))
		return -ENXIO;

	if (nr_pages < 0)
		return -EINVAL;

	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
			kaddr, pfn);
	if (!avail)
		return -ERANGE;
	return min(avail, nr_pages);
}
EXPORT_SYMBOL_GPL(dax_direct_access);

size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
		size_t bytes, struct iov_iter *i)
{
	if (!dax_alive(dax_dev))
		return 0;

	return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i);
}
EXPORT_SYMBOL_GPL(dax_copy_from_iter);

size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
		size_t bytes, struct iov_iter *i)
{
	if (!dax_alive(dax_dev))
		return 0;

	return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i);
}
EXPORT_SYMBOL_GPL(dax_copy_to_iter);

int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
			size_t nr_pages)
{
	if (!dax_alive(dax_dev))
		return -ENXIO;
	/*
	 * There are no callers that want to zero more than one page as of now.
	 * Once users are there, this check can be removed after the
	 * device mapper code has been updated to split ranges across targets.
	 */
	if (nr_pages != 1)
		return -EIO;

	return dax_dev->ops->zero_page_range(dax_dev, pgoff, nr_pages);
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);

#ifdef CONFIG_ARCH_HAS_PMEM_API
void arch_wb_cache_pmem(void *addr, size_t size);
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
{
	if (unlikely(!dax_write_cache_enabled(dax_dev)))
		return;

	arch_wb_cache_pmem(addr, size);
}
#else
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
{
}
#endif
EXPORT_SYMBOL_GPL(dax_flush);

void dax_write_cache(struct dax_device *dax_dev, bool wc)
{
	if (wc)
		set_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
	else
		clear_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(dax_write_cache);

bool dax_write_cache_enabled(struct dax_device *dax_dev)
{
	return test_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(dax_write_cache_enabled);

bool __dax_synchronous(struct dax_device *dax_dev)
{
	return test_bit(DAXDEV_SYNC, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(__dax_synchronous);

void __set_dax_synchronous(struct dax_device *dax_dev)
{
	set_bit(DAXDEV_SYNC, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(__set_dax_synchronous);

bool dax_alive(struct dax_device *dax_dev)
{
	lockdep_assert_held(&dax_srcu);
	return test_bit(DAXDEV_ALIVE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(dax_alive);

/*
 * Note, rcu is not protecting the liveness of dax_dev, rcu is ensuring
 * that any fault handlers or operations that might have seen
 * dax_alive(), have completed.  Any operations that start after
 * synchronize_srcu() has run will abort upon seeing !dax_alive().
 */
void kill_dax(struct dax_device *dax_dev)
{
	if (!dax_dev)
		return;

	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
	synchronize_srcu(&dax_srcu);
}
EXPORT_SYMBOL_GPL(kill_dax);

void run_dax(struct dax_device *dax_dev)
{
	set_bit(DAXDEV_ALIVE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(run_dax);

static struct inode *dax_alloc_inode(struct super_block *sb)
{
	struct dax_device *dax_dev;
	struct inode *inode;

	dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
	if (!dax_dev)
		return NULL;

	inode = &dax_dev->inode;
	inode->i_rdev = 0;
	return inode;
}

static struct dax_device *to_dax_dev(struct inode *inode)
{
	return container_of(inode, struct dax_device, inode);
}

static void dax_free_inode(struct inode *inode)
{
	struct dax_device *dax_dev = to_dax_dev(inode);
	if (inode->i_rdev)
		ida_simple_remove(&dax_minor_ida, iminor(inode));
	kmem_cache_free(dax_cache, dax_dev);
}

static void dax_destroy_inode(struct inode *inode)
{
	struct dax_device *dax_dev = to_dax_dev(inode);
	WARN_ONCE(test_bit(DAXDEV_ALIVE, &dax_dev->flags),
			"kill_dax() must be called before final iput()\n");
}

static const struct super_operations dax_sops = {
	.statfs = simple_statfs,
	.alloc_inode = dax_alloc_inode,
	.destroy_inode = dax_destroy_inode,
	.free_inode = dax_free_inode,
	.drop_inode = generic_delete_inode,
};

static int dax_init_fs_context(struct fs_context *fc)
{
	struct pseudo_fs_context *ctx = init_pseudo(fc, DAXFS_MAGIC);
	if (!ctx)
		return -ENOMEM;
	ctx->ops = &dax_sops;
	return 0;
}

static struct file_system_type dax_fs_type = {
	.name		= "dax",
	.init_fs_context = dax_init_fs_context,
	.kill_sb	= kill_anon_super,
};

static int dax_test(struct inode *inode, void *data)
{
	dev_t devt = *(dev_t *) data;

	return inode->i_rdev == devt;
}

static int dax_set(struct inode *inode, void *data)
{
	dev_t devt = *(dev_t *) data;

	inode->i_rdev = devt;
	return 0;
}

static struct dax_device *dax_dev_get(dev_t devt)
{
	struct dax_device *dax_dev;
	struct inode *inode;

	inode = iget5_locked(dax_superblock, hash_32(devt + DAXFS_MAGIC, 31),
			dax_test, dax_set, &devt);

	if (!inode)
		return NULL;

	dax_dev = to_dax_dev(inode);
	if (inode->i_state & I_NEW) {
		set_bit(DAXDEV_ALIVE, &dax_dev->flags);
		inode->i_cdev = &dax_dev->cdev;
		inode->i_mode = S_IFCHR;
		inode->i_flags = S_DAX;
		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
		unlock_new_inode(inode);
	}

	return dax_dev;
}

struct dax_device *alloc_dax(void *private, const struct dax_operations *ops,
		unsigned long flags)
{
	struct dax_device *dax_dev;
	dev_t devt;
	int minor;

	if (WARN_ON_ONCE(ops && !ops->zero_page_range))
		return ERR_PTR(-EINVAL);

	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
	if (minor < 0)
		return ERR_PTR(-ENOMEM);

	devt = MKDEV(MAJOR(dax_devt), minor);
	dax_dev = dax_dev_get(devt);
	if (!dax_dev)
		goto err_dev;

	dax_dev->ops = ops;
	dax_dev->private = private;
	if (flags & DAXDEV_F_SYNC)
		set_dax_synchronous(dax_dev);

	return dax_dev;

 err_dev:
	ida_simple_remove(&dax_minor_ida, minor);
	return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL_GPL(alloc_dax);

void put_dax(struct dax_device *dax_dev)
{
	if (!dax_dev)
		return;
	iput(&dax_dev->inode);
}
EXPORT_SYMBOL_GPL(put_dax);

/**
 * inode_dax: convert a public inode into its dax_dev
 * @inode: An inode with i_cdev pointing to a dax_dev
 *
 * Note this is not equivalent to to_dax_dev() which is for private
 * internal use where we know the inode filesystem type == dax_fs_type.
 */
struct dax_device *inode_dax(struct inode *inode)
{
	struct cdev *cdev = inode->i_cdev;

	return container_of(cdev, struct dax_device, cdev);
}
EXPORT_SYMBOL_GPL(inode_dax);

struct inode *dax_inode(struct dax_device *dax_dev)
{
	return &dax_dev->inode;
}
EXPORT_SYMBOL_GPL(dax_inode);

void *dax_get_private(struct dax_device *dax_dev)
{
	if (!test_bit(DAXDEV_ALIVE, &dax_dev->flags))
		return NULL;
	return dax_dev->private;
}
EXPORT_SYMBOL_GPL(dax_get_private);

static void init_once(void *_dax_dev)
{
	struct dax_device *dax_dev = _dax_dev;
	struct inode *inode = &dax_dev->inode;

	memset(dax_dev, 0, sizeof(*dax_dev));
	inode_init_once(inode);
}

static int dax_fs_init(void)
{
	int rc;

	dax_cache = kmem_cache_create("dax_cache", sizeof(struct dax_device), 0,
			(SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
			 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
			init_once);
	if (!dax_cache)
		return -ENOMEM;

	dax_mnt = kern_mount(&dax_fs_type);
	if (IS_ERR(dax_mnt)) {
		rc = PTR_ERR(dax_mnt);
		goto err_mount;
	}
	dax_superblock = dax_mnt->mnt_sb;

	return 0;

 err_mount:
	kmem_cache_destroy(dax_cache);

	return rc;
}

static void dax_fs_exit(void)
{
	kern_unmount(dax_mnt);
	kmem_cache_destroy(dax_cache);
}

static int __init dax_core_init(void)
{
	int rc;

	rc = dax_fs_init();
	if (rc)
		return rc;

	rc = alloc_chrdev_region(&dax_devt, 0, MINORMASK+1, "dax");
	if (rc)
		goto err_chrdev;

	rc = dax_bus_init();
	if (rc)
		goto err_bus;
	return 0;

err_bus:
	unregister_chrdev_region(dax_devt, MINORMASK+1);
err_chrdev:
	dax_fs_exit();
	return 0;
}

static void __exit dax_core_exit(void)
{
	dax_bus_exit();
	unregister_chrdev_region(dax_devt, MINORMASK+1);
	ida_destroy(&dax_minor_ida);
	dax_fs_exit();
}

MODULE_AUTHOR("Intel Corporation");
MODULE_LICENSE("GPL v2");
subsys_initcall(dax_core_init);
module_exit(dax_core_exit);