提交 0b07ce87 编写于 作者: D Dan Williams 提交者: Linus Torvalds

device-dax: introduce 'mapping' devices

In support of interrogating the physical address layout of a device with
dis-contiguous ranges, introduce a sysfs directory with 'start', 'end',
and 'page_offset' attributes.  The alternative is trying to parse
/proc/iomem, and that file will not reflect the extent layout until the
device is enabled.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643104819.4062302.13691281391423291589.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106117446.30709.2751020815463722537.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 60e93dc0
......@@ -579,6 +579,167 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
}
EXPORT_SYMBOL_GPL(alloc_dax_region);
static void dax_mapping_release(struct device *dev)
{
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
ida_free(&dev_dax->ida, mapping->id);
kfree(mapping);
}
static void unregister_dax_mapping(void *data)
{
struct device *dev = data;
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
struct dax_region *dax_region = dev_dax->region;
dev_dbg(dev, "%s\n", __func__);
device_lock_assert(dax_region->dev);
dev_dax->ranges[mapping->range_id].mapping = NULL;
mapping->range_id = -1;
device_del(dev);
put_device(dev);
}
static struct dev_dax_range *get_dax_range(struct device *dev)
{
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
struct dax_region *dax_region = dev_dax->region;
device_lock(dax_region->dev);
if (mapping->range_id < 0) {
device_unlock(dax_region->dev);
return NULL;
}
return &dev_dax->ranges[mapping->range_id];
}
static void put_dax_range(struct dev_dax_range *dax_range)
{
struct dax_mapping *mapping = dax_range->mapping;
struct dev_dax *dev_dax = to_dev_dax(mapping->dev.parent);
struct dax_region *dax_region = dev_dax->region;
device_unlock(dax_region->dev);
}
static ssize_t start_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax_range *dax_range;
ssize_t rc;
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
rc = sprintf(buf, "%#llx\n", dax_range->range.start);
put_dax_range(dax_range);
return rc;
}
static DEVICE_ATTR(start, 0400, start_show, NULL);
static ssize_t end_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax_range *dax_range;
ssize_t rc;
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
rc = sprintf(buf, "%#llx\n", dax_range->range.end);
put_dax_range(dax_range);
return rc;
}
static DEVICE_ATTR(end, 0400, end_show, NULL);
static ssize_t pgoff_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax_range *dax_range;
ssize_t rc;
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
rc = sprintf(buf, "%#lx\n", dax_range->pgoff);
put_dax_range(dax_range);
return rc;
}
static DEVICE_ATTR(page_offset, 0400, pgoff_show, NULL);
static struct attribute *dax_mapping_attributes[] = {
&dev_attr_start.attr,
&dev_attr_end.attr,
&dev_attr_page_offset.attr,
NULL,
};
static const struct attribute_group dax_mapping_attribute_group = {
.attrs = dax_mapping_attributes,
};
static const struct attribute_group *dax_mapping_attribute_groups[] = {
&dax_mapping_attribute_group,
NULL,
};
static struct device_type dax_mapping_type = {
.release = dax_mapping_release,
.groups = dax_mapping_attribute_groups,
};
static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id)
{
struct dax_region *dax_region = dev_dax->region;
struct dax_mapping *mapping;
struct device *dev;
int rc;
device_lock_assert(dax_region->dev);
if (dev_WARN_ONCE(&dev_dax->dev, !dax_region->dev->driver,
"region disabled\n"))
return -ENXIO;
mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
if (!mapping)
return -ENOMEM;
mapping->range_id = range_id;
mapping->id = ida_alloc(&dev_dax->ida, GFP_KERNEL);
if (mapping->id < 0) {
kfree(mapping);
return -ENOMEM;
}
dev_dax->ranges[range_id].mapping = mapping;
dev = &mapping->dev;
device_initialize(dev);
dev->parent = &dev_dax->dev;
dev->type = &dax_mapping_type;
dev_set_name(dev, "mapping%d", mapping->id);
rc = device_add(dev);
if (rc) {
put_device(dev);
return rc;
}
rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_mapping,
dev);
if (rc)
return rc;
return 0;
}
static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
resource_size_t size)
{
......@@ -588,7 +749,7 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
struct dev_dax_range *ranges;
unsigned long pgoff = 0;
struct resource *alloc;
int i;
int i, rc;
device_lock_assert(dax_region->dev);
......@@ -633,6 +794,22 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
dev_dbg(dev, "alloc range[%d]: %pa:%pa\n", dev_dax->nr_range - 1,
&alloc->start, &alloc->end);
/*
* A dev_dax instance must be registered before mapping device
* children can be added. Defer to devm_create_dev_dax() to add
* the initial mapping device.
*/
if (!device_is_registered(&dev_dax->dev))
return 0;
rc = devm_register_dax_mapping(dev_dax, dev_dax->nr_range - 1);
if (rc) {
dev_dbg(dev, "delete range[%d]: %pa:%pa\n", dev_dax->nr_range - 1,
&alloc->start, &alloc->end);
dev_dax->nr_range--;
__release_region(res, alloc->start, resource_size(alloc));
return rc;
}
return 0;
}
......@@ -701,11 +878,14 @@ static int dev_dax_shrink(struct dev_dax *dev_dax, resource_size_t size)
for (i = dev_dax->nr_range - 1; i >= 0; i--) {
struct range *range = &dev_dax->ranges[i].range;
struct dax_mapping *mapping = dev_dax->ranges[i].mapping;
struct resource *adjust = NULL, *res;
resource_size_t shrink;
shrink = min_t(u64, to_shrink, range_len(range));
if (shrink >= range_len(range)) {
devm_release_action(dax_region->dev,
unregister_dax_mapping, &mapping->dev);
__release_region(&dax_region->res, range->start,
range_len(range));
dev_dax->nr_range--;
......@@ -1036,9 +1216,9 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
/* a device_dax instance is dead while the driver is not attached */
kill_dax(dax_dev);
/* from here on we're committed to teardown via dev_dax_release() */
dev_dax->dax_dev = dax_dev;
dev_dax->target_node = dax_region->target_node;
ida_init(&dev_dax->ida);
kref_get(&dax_region->kref);
inode = dax_inode(dax_dev);
......@@ -1061,6 +1241,13 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
if (rc)
return ERR_PTR(rc);
/* register mapping device for the initial allocation range */
if (dev_dax->nr_range && range_len(&dev_dax->ranges[0].range)) {
rc = devm_register_dax_mapping(dev_dax, 0);
if (rc)
return ERR_PTR(rc);
}
return dev_dax;
err_alloc_dax:
......
......@@ -40,6 +40,12 @@ struct dax_region {
struct device *youngest;
};
struct dax_mapping {
struct device dev;
int range_id;
int id;
};
/**
* struct dev_dax - instance data for a subdivision of a dax region, and
* data while the device is activated in the driver.
......@@ -47,6 +53,7 @@ struct dax_region {
* @dax_dev - core dax functionality
* @target_node: effective numa node if dev_dax memory range is onlined
* @id: ida allocated id
* @ida: mapping id allocator
* @dev - device core
* @pgmap - pgmap for memmap setup / lifetime (driver owned)
* @nr_range: size of @ranges
......@@ -57,12 +64,14 @@ struct dev_dax {
struct dax_device *dax_dev;
int target_node;
int id;
struct ida ida;
struct device dev;
struct dev_pagemap *pgmap;
int nr_range;
struct dev_dax_range {
unsigned long pgoff;
struct range range;
struct dax_mapping *mapping;
} *ranges;
};
......@@ -70,4 +79,9 @@ static inline struct dev_dax *to_dev_dax(struct device *dev)
{
return container_of(dev, struct dev_dax, dev);
}
static inline struct dax_mapping *to_dax_mapping(struct device *dev)
{
return container_of(dev, struct dax_mapping, dev);
}
#endif
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册