summaryrefslogtreecommitdiff
path: root/drivers/dax
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/dax')
-rw-r--r--drivers/dax/Kconfig1
-rw-r--r--drivers/dax/bus.c21
-rw-r--r--drivers/dax/dax-private.h16
-rw-r--r--drivers/dax/device.c50
-rw-r--r--drivers/dax/kmem.c46
-rw-r--r--drivers/dax/pmem/Makefile1
-rw-r--r--drivers/dax/pmem/core.c2
-rw-r--r--drivers/dax/super.c117
8 files changed, 145 insertions, 109 deletions
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index a59f338f520f..f33c73e4af41 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config DAX_DRIVER
select DAX
bool
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 2109cfe80219..8fafbeab510a 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -295,6 +295,22 @@ static ssize_t target_node_show(struct device *dev,
}
static DEVICE_ATTR_RO(target_node);
+static unsigned long long dev_dax_resource(struct dev_dax *dev_dax)
+{
+ struct dax_region *dax_region = dev_dax->region;
+
+ return dax_region->res.start;
+}
+
+static ssize_t resource_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dev_dax *dev_dax = to_dev_dax(dev);
+
+ return sprintf(buf, "%#llx\n", dev_dax_resource(dev_dax));
+}
+static DEVICE_ATTR_RO(resource);
+
static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -313,6 +329,8 @@ static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
if (a == &dev_attr_target_node.attr && dev_dax_target_node(dev_dax) < 0)
return 0;
+ if (a == &dev_attr_resource.attr)
+ return 0400;
return a->mode;
}
@@ -320,6 +338,7 @@ static struct attribute *dev_dax_attributes[] = {
&dev_attr_modalias.attr,
&dev_attr_size.attr,
&dev_attr_target_node.attr,
+ &dev_attr_resource.attr,
NULL,
};
@@ -388,7 +407,7 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id,
* No 'host' or dax_operations since there is no access to this
* device outside of mmap of the resulting character device.
*/
- dax_dev = alloc_dax(dev_dax, NULL, NULL);
+ dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
if (!dax_dev)
goto err;
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index a45612148ca0..6ccca3b890d6 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright(c) 2016 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 __DAX_PRIVATE_H__
#define __DAX_PRIVATE_H__
@@ -51,8 +43,7 @@ struct dax_region {
* @target_node: effective numa node if dev_dax memory range is onlined
* @dev - device core
* @pgmap - pgmap for memmap setup / lifetime (driver owned)
- * @ref: pgmap reference count (driver owned)
- * @cmp: @ref final put completion (driver owned)
+ * @dax_mem_res: physical address range of hotadded DAX memory
*/
struct dev_dax {
struct dax_region *region;
@@ -60,8 +51,7 @@ struct dev_dax {
int target_node;
struct device dev;
struct dev_pagemap pgmap;
- struct percpu_ref ref;
- struct completion cmp;
+ struct resource *dax_kmem_res;
};
static inline struct dev_dax *to_dev_dax(struct device *dev)
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 996d68ff992a..1af823b2fe6b 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -14,38 +14,6 @@
#include "dax-private.h"
#include "bus.h"
-static struct dev_dax *ref_to_dev_dax(struct percpu_ref *ref)
-{
- return container_of(ref, struct dev_dax, ref);
-}
-
-static void dev_dax_percpu_release(struct percpu_ref *ref)
-{
- struct dev_dax *dev_dax = ref_to_dev_dax(ref);
-
- dev_dbg(&dev_dax->dev, "%s\n", __func__);
- complete(&dev_dax->cmp);
-}
-
-static void dev_dax_percpu_exit(void *data)
-{
- struct percpu_ref *ref = data;
- struct dev_dax *dev_dax = ref_to_dev_dax(ref);
-
- dev_dbg(&dev_dax->dev, "%s\n", __func__);
- wait_for_completion(&dev_dax->cmp);
- percpu_ref_exit(ref);
-}
-
-static void dev_dax_percpu_kill(struct percpu_ref *data)
-{
- struct percpu_ref *ref = data;
- struct dev_dax *dev_dax = ref_to_dev_dax(ref);
-
- dev_dbg(&dev_dax->dev, "%s\n", __func__);
- percpu_ref_kill(ref);
-}
-
static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
const char *func)
{
@@ -460,24 +428,10 @@ int dev_dax_probe(struct device *dev)
return -EBUSY;
}
- init_completion(&dev_dax->cmp);
- rc = percpu_ref_init(&dev_dax->ref, dev_dax_percpu_release, 0,
- GFP_KERNEL);
- if (rc)
- return rc;
-
- rc = devm_add_action_or_reset(dev, dev_dax_percpu_exit, &dev_dax->ref);
- if (rc)
- return rc;
-
- dev_dax->pgmap.ref = &dev_dax->ref;
- dev_dax->pgmap.kill = dev_dax_percpu_kill;
+ dev_dax->pgmap.type = MEMORY_DEVICE_DEVDAX;
addr = devm_memremap_pages(dev, &dev_dax->pgmap);
- if (IS_ERR(addr)) {
- devm_remove_action(dev, dev_dax_percpu_exit, &dev_dax->ref);
- percpu_ref_exit(&dev_dax->ref);
+ if (IS_ERR(addr))
return PTR_ERR(addr);
- }
inode = dax_inode(dax_dev);
cdev = inode->i_cdev;
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index a02318c6d28a..3d0a7e702c94 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -66,23 +66,59 @@ int dev_dax_kmem_probe(struct device *dev)
new_res->name = dev_name(dev);
rc = add_memory(numa_node, new_res->start, resource_size(new_res));
- if (rc)
+ if (rc) {
+ release_resource(new_res);
+ kfree(new_res);
return rc;
+ }
+ dev_dax->dax_kmem_res = new_res;
return 0;
}
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static int dev_dax_kmem_remove(struct device *dev)
+{
+ struct dev_dax *dev_dax = to_dev_dax(dev);
+ struct resource *res = dev_dax->dax_kmem_res;
+ resource_size_t kmem_start = res->start;
+ resource_size_t kmem_size = resource_size(res);
+ int rc;
+
+ /*
+ * We have one shot for removing memory, if some memory blocks were not
+ * offline prior to calling this function remove_memory() will fail, and
+ * there is no way to hotremove this memory until reboot because device
+ * unbind will succeed even if we return failure.
+ */
+ rc = remove_memory(dev_dax->target_node, kmem_start, kmem_size);
+ if (rc) {
+ dev_err(dev,
+ "DAX region %pR cannot be hotremoved until the next reboot\n",
+ res);
+ return rc;
+ }
+
+ /* Release and free dax resources */
+ release_resource(res);
+ kfree(res);
+ dev_dax->dax_kmem_res = NULL;
+
+ return 0;
+}
+#else
static int dev_dax_kmem_remove(struct device *dev)
{
/*
- * Purposely leak the request_mem_region() for the device-dax
- * range and return '0' to ->remove() attempts. The removal of
- * the device from the driver always succeeds, but the region
- * is permanently pinned as reserved by the unreleased
+ * Without hotremove purposely leak the request_mem_region() for the
+ * device-dax range and return '0' to ->remove() attempts. The removal
+ * of the device from the driver always succeeds, but the region is
+ * permanently pinned as reserved by the unreleased
* request_mem_region().
*/
return 0;
}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
static struct dax_device_driver device_dax_kmem_driver = {
.drv = {
diff --git a/drivers/dax/pmem/Makefile b/drivers/dax/pmem/Makefile
index e2e79bd3fdcf..010269f61d41 100644
--- a/drivers/dax/pmem/Makefile
+++ b/drivers/dax/pmem/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o
obj-$(CONFIG_DEV_DAX_PMEM_COMPAT) += dax_pmem_compat.o
diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c
index f9f51786d556..6eb6dfdf19bf 100644
--- a/drivers/dax/pmem/core.c
+++ b/drivers/dax/pmem/core.c
@@ -16,7 +16,7 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
struct dev_dax *dev_dax;
struct nd_namespace_io *nsio;
struct dax_region *dax_region;
- struct dev_pagemap pgmap = { 0 };
+ struct dev_pagemap pgmap = { };
struct nd_namespace_common *ndns;
struct nd_dax *nd_dax = to_nd_dax(dev);
struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index a93225c0a623..26a654dbc69a 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright(c) 2017 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.
*/
#include <linux/pagemap.h>
#include <linux/module.h>
@@ -74,22 +66,12 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
#endif
-/**
- * __bdev_dax_supported() - Check if the device supports dax for filesystem
- * @bdev: block device to check
- * @blocksize: The block size of the device
- *
- * This is a library function for filesystems to check if the block device
- * can be mounted with dax option.
- *
- * Return: true if supported, false if unsupported
- */
-bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
+bool __generic_fsdax_supported(struct dax_device *dax_dev,
+ struct block_device *bdev, int blocksize, sector_t start,
+ sector_t sectors)
{
- struct dax_device *dax_dev;
bool dax_enabled = false;
pgoff_t pgoff, pgoff_end;
- struct request_queue *q;
char buf[BDEVNAME_SIZE];
void *kaddr, *end_kaddr;
pfn_t pfn, end_pfn;
@@ -103,21 +85,14 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
return false;
}
- q = bdev_get_queue(bdev);
- if (!q || !blk_queue_dax(q)) {
- pr_debug("%s: error: request queue doesn't support dax\n",
- bdevname(bdev, buf));
- return false;
- }
-
- err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
+ err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
if (err) {
pr_debug("%s: error: unaligned partition for dax\n",
bdevname(bdev, buf));
return false;
}
- last_page = PFN_DOWN(i_size_read(bdev->bd_inode) - 1) * 8;
+ 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_debug("%s: error: unaligned partition for dax\n",
@@ -125,20 +100,11 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
return false;
}
- dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
- if (!dax_dev) {
- pr_debug("%s: error: device does not support dax\n",
- bdevname(bdev, buf));
- 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);
dax_read_unlock(id);
- put_dax(dax_dev);
-
if (len < 1 || len2 < 1) {
pr_debug("%s: error: dax access failed (%ld)\n",
bdevname(bdev, buf), len < 1 ? len : len2);
@@ -179,6 +145,49 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
}
return true;
}
+EXPORT_SYMBOL_GPL(__generic_fsdax_supported);
+
+/**
+ * __bdev_dax_supported() - Check if the device supports dax for filesystem
+ * @bdev: block device to check
+ * @blocksize: The block size of the device
+ *
+ * This is a library function for filesystems to check if the block device
+ * can be mounted with dax option.
+ *
+ * Return: true if supported, false if unsupported
+ */
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
+{
+ struct dax_device *dax_dev;
+ struct request_queue *q;
+ char buf[BDEVNAME_SIZE];
+ bool ret;
+ int id;
+
+ q = bdev_get_queue(bdev);
+ if (!q || !blk_queue_dax(q)) {
+ pr_debug("%s: error: request queue doesn't support dax\n",
+ bdevname(bdev, buf));
+ return false;
+ }
+
+ dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ if (!dax_dev) {
+ pr_debug("%s: error: device does not support dax\n",
+ bdevname(bdev, buf));
+ return false;
+ }
+
+ id = dax_read_lock();
+ ret = dax_supported(dax_dev, bdev, blocksize, 0,
+ i_size_read(bdev->bd_inode) / 512);
+ dax_read_unlock(id);
+
+ put_dax(dax_dev);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(__bdev_dax_supported);
#endif
@@ -187,6 +196,8 @@ enum dax_device_flags {
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,
};
/**
@@ -304,6 +315,15 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
}
EXPORT_SYMBOL_GPL(dax_direct_access);
+bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
+ int blocksize, sector_t start, sector_t len)
+{
+ if (!dax_alive(dax_dev))
+ return false;
+
+ return dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, start, len);
+}
+
size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
size_t bytes, struct iov_iter *i)
{
@@ -355,6 +375,18 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev)
}
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);
@@ -512,7 +544,7 @@ static void dax_add_host(struct dax_device *dax_dev, const char *host)
}
struct dax_device *alloc_dax(void *private, const char *__host,
- const struct dax_operations *ops)
+ const struct dax_operations *ops, unsigned long flags)
{
struct dax_device *dax_dev;
const char *host;
@@ -535,6 +567,9 @@ struct dax_device *alloc_dax(void *private, const char *__host,
dax_add_host(dax_dev, host);
dax_dev->ops = ops;
dax_dev->private = private;
+ if (flags & DAXDEV_F_SYNC)
+ set_dax_synchronous(dax_dev);
+
return dax_dev;
err_dev: