From: Dan Williams <dan.j.williams@intel.com>
To: linux-nvdimm@lists.01.org
Cc: Vishal Verma <vishal.l.verma@intel.com>,
peterz@infradead.org, dave.hansen@linux.intel.com,
ard.biesheuvel@linaro.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, linux-acpi@vger.kernel.org,
hch@lst.de, joao.m.martins@oracle.com
Subject: [PATCH v2 22/22] device-dax: Introduce 'mapping' devices
Date: Sun, 12 Jul 2020 09:28:04 -0700 [thread overview]
Message-ID: <159457128462.754248.10443613927921016089.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <159457116473.754248.7879464730875147365.stgit@dwillia2-desk3.amr.corp.intel.com>
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.
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/dax/bus.c | 191 +++++++++++++++++++++++++++++++++++++++++++++
drivers/dax/dax-private.h | 14 +++
2 files changed, 203 insertions(+), 2 deletions(-)
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index f342e36c69a1..8b6c4ddc5f42 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -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 < 1) {
+ 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);
@@ -630,6 +791,22 @@ 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;
}
@@ -698,11 +875,14 @@ 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(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--;
@@ -1033,9 +1213,9 @@ 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);
@@ -1058,6 +1238,13 @@ 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:
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index f863287107fd..13780f62b95e 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -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
next prev parent reply other threads:[~2020-07-12 16:44 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-12 16:26 [PATCH v2 00/22] device-dax: Support sub-dividing soft-reserved ranges Dan Williams
2020-07-12 16:26 ` [PATCH v2 01/22] x86/numa: Cleanup configuration dependent command-line options Dan Williams
2020-07-12 16:26 ` [PATCH v2 02/22] x86/numa: Add 'nohmat' option Dan Williams
2020-07-12 16:58 ` Randy Dunlap
2020-07-12 16:26 ` [PATCH v2 03/22] efi/fake_mem: Arrange for a resource entry per efi_fake_mem instance Dan Williams
2020-07-12 16:26 ` [PATCH v2 04/22] ACPI: HMAT: Refactor hmat_register_target_device to hmem_register_device Dan Williams
2020-07-12 16:26 ` [PATCH v2 05/22] resource: Report parent to walk_iomem_res_desc() callback Dan Williams
2020-07-12 16:26 ` [PATCH v2 06/22] x86: Move NUMA_KEEP_MEMINFO and related definition to x86-internals Dan Williams
2020-07-12 16:26 ` [PATCH v2 07/22] numa: Introduce a generic memory_add_physaddr_to_nid() Dan Williams
2020-07-13 6:58 ` Mike Rapoport
2020-07-13 15:42 ` Dan Williams
2020-07-12 16:26 ` [PATCH v2 08/22] memblock: Introduce a generic phys_addr_to_target_node() Dan Williams
2020-07-13 7:03 ` Mike Rapoport
2020-07-13 15:48 ` Dan Williams
2020-07-14 1:36 ` Justin He
2020-07-12 16:26 ` [PATCH v2 09/22] arm64: Convert to generic memblock for numa-info Dan Williams
2020-07-12 16:26 ` [PATCH v2 10/22] ACPI: HMAT: Attach a device for each soft-reserved range Dan Williams
2020-07-12 16:27 ` [PATCH v2 11/22] device-dax: Drop the dax_region.pfn_flags attribute Dan Williams
2020-07-12 16:27 ` [PATCH v2 12/22] device-dax: Move instance creation parameters to 'struct dev_dax_data' Dan Williams
2020-07-12 16:27 ` [PATCH v2 13/22] device-dax: Make pgmap optional for instance creation Dan Williams
2020-07-12 16:27 ` [PATCH v2 14/22] device-dax: Kill dax_kmem_res Dan Williams
2020-07-12 16:27 ` [PATCH v2 15/22] device-dax: Add an allocation interface for device-dax instances Dan Williams
2020-07-12 16:27 ` [PATCH v2 16/22] device-dax: Introduce 'seed' devices Dan Williams
2020-07-12 16:27 ` [PATCH v2 17/22] drivers/base: Make device_find_child_by_name() compatible with sysfs inputs Dan Williams
2020-07-12 17:09 ` Greg Kroah-Hartman
2020-07-13 15:39 ` Dan Williams
2020-07-13 15:52 ` Greg Kroah-Hartman
2020-07-13 16:09 ` Dan Williams
2020-07-13 16:12 ` Greg Kroah-Hartman
2020-07-13 16:36 ` Dan Williams
2020-07-12 16:27 ` [PATCH v2 18/22] device-dax: Add resize support Dan Williams
2020-07-12 16:27 ` [PATCH v2 19/22] mm/memremap_pages: Convert to 'struct range' Dan Williams
2020-07-13 16:36 ` Ralph Campbell
2020-07-13 16:54 ` Dan Williams
2020-07-12 16:27 ` [PATCH v2 20/22] mm/memremap_pages: Support multiple ranges per invocation Dan Williams
2020-07-12 16:27 ` [PATCH v2 21/22] device-dax: Add dis-contiguous resource support Dan Williams
2020-07-12 16:28 ` Dan Williams [this message]
2020-07-16 13:18 ` [PATCH v2 22/22] device-dax: Introduce 'mapping' devices Joao Martins
2020-07-16 16:00 ` Dan Williams
2020-07-16 19:04 ` Joao Martins
2020-07-16 17:29 ` [PATCH v1 0/4] device-dax: Further improvements to subdivision Joao Martins
2020-07-16 17:29 ` [PATCH v1 1/4] device-dax: Make align a per-device property Joao Martins
2020-07-16 17:29 ` [PATCH v1 2/4] device-dax: Add an 'align' attribute Joao Martins
2020-07-31 14:52 ` Dan Williams
2020-07-16 17:29 ` [PATCH v1 3/4] dax/hmem: Introduce dax_hmem.region_idle parameter Joao Martins
2020-07-16 17:29 ` [PATCH v1 4/4] device-dax: Add a range mapping allocation attribute Joao Martins
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=159457128462.754248.10443613927921016089.stgit@dwillia2-desk3.amr.corp.intel.com \
--to=dan.j.williams@intel.com \
--cc=ard.biesheuvel@linaro.org \
--cc=dave.hansen@linux.intel.com \
--cc=hch@lst.de \
--cc=joao.m.martins@oracle.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvdimm@lists.01.org \
--cc=peterz@infradead.org \
--cc=vishal.l.verma@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).