From: Dave Hansen <dave.hansen@linux.intel.com>
To: linux-kernel@vger.kernel.org
Cc: thomas.lendacky@amd.com, mhocko@suse.com,
linux-nvdimm@lists.01.org,
Dave Hansen <dave.hansen@linux.intel.com>,
ying.huang@intel.com, linux-mm@kvack.org, zwisler@kernel.org,
fengguang.wu@intel.com, akpm@linux-foundation.org
Subject: [PATCH 2/9] dax: kernel memory driver for mm ownership of DAX
Date: Mon, 22 Oct 2018 13:13:20 -0700 [thread overview]
Message-ID: <20181022201320.45C9785C@viggo.jf.intel.com> (raw)
In-Reply-To: <20181022201317.8558C1D8@viggo.jf.intel.com>
Add the actual driver to which will own the DAX range. This
allows very nice party with the other possible "owners" of
a DAX region: device DAX and filesystem DAX. It also greatly
simplifies the process of handing off control of the memory
between the different owners since it's just a matter of
unbinding and rebinding the device to different drivers.
I tried to do this all internally to the kernel and the
locking and "self-destruction" of the old device context was
a nightmare. Having userspace drive it is a wonderful
simplification.
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: linux-nvdimm@lists.01.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: Huang Ying <ying.huang@intel.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
---
b/drivers/dax/kmem.c | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 152 insertions(+)
diff -puN /dev/null drivers/dax/kmem.c
--- /dev/null 2018-09-18 12:39:53.059362935 -0700
+++ b/drivers/dax/kmem.c 2018-10-22 13:12:21.502930393 -0700
@@ -0,0 +1,152 @@
+// this just just a copy of drivers/dax/pmem.c with
+// s/dax_pmem/dax_kmem' for now.
+//
+// need real license
+/*
+ * Copyright(c) 2016-2018 Intel Corporation. All rights reserved.
+ */
+#include <linux/percpu-refcount.h>
+#include <linux/memremap.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "../nvdimm/pfn.h"
+#include "../nvdimm/nd.h"
+#include "device-dax.h"
+
+struct dax_kmem {
+ struct device *dev;
+ struct percpu_ref ref;
+ struct dev_pagemap pgmap;
+ struct completion cmp;
+};
+
+static struct dax_kmem *to_dax_kmem(struct percpu_ref *ref)
+{
+ return container_of(ref, struct dax_kmem, ref);
+}
+
+static void dax_kmem_percpu_release(struct percpu_ref *ref)
+{
+ struct dax_kmem *dax_kmem = to_dax_pmem(ref);
+
+ dev_dbg(dax_kmem->dev, "trace\n");
+ complete(&dax_kmem->cmp);
+}
+
+static void dax_kmem_percpu_exit(void *data)
+{
+ struct percpu_ref *ref = data;
+ struct dax_kmem *dax_kmem = to_dax_pmem(ref);
+
+ dev_dbg(dax_kmem->dev, "trace\n");
+ wait_for_completion(&dax_kmem->cmp);
+ percpu_ref_exit(ref);
+}
+
+static void dax_kmem_percpu_kill(void *data)
+{
+ struct percpu_ref *ref = data;
+ struct dax_kmem *dax_kmem = to_dax_pmem(ref);
+
+ dev_dbg(dax_kmem->dev, "trace\n");
+ percpu_ref_kill(ref);
+}
+
+static int dax_kmem_probe(struct device *dev)
+{
+ void *addr;
+ struct resource res;
+ int rc, id, region_id;
+ struct nd_pfn_sb *pfn_sb;
+ struct dev_dax *dev_dax;
+ struct dax_kmem *dax_kmem;
+ struct nd_namespace_io *nsio;
+ struct dax_region *dax_region;
+ struct nd_namespace_common *ndns;
+ struct nd_dax *nd_dax = to_nd_dax(dev);
+ struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
+
+ ndns = nvdimm_namespace_common_probe(dev);
+ if (IS_ERR(ndns))
+ return PTR_ERR(ndns);
+ nsio = to_nd_namespace_io(&ndns->dev);
+
+ dax_kmem = devm_kzalloc(dev, sizeof(*dax_kmem), GFP_KERNEL);
+ if (!dax_kmem)
+ return -ENOMEM;
+
+ /* parse the 'pfn' info block via ->rw_bytes */
+ rc = devm_nsio_enable(dev, nsio);
+ if (rc)
+ return rc;
+ rc = nvdimm_setup_pfn(nd_pfn, &dax_kmem->pgmap);
+ if (rc)
+ return rc;
+ devm_nsio_disable(dev, nsio);
+
+ pfn_sb = nd_pfn->pfn_sb;
+
+ if (!devm_request_mem_region(dev, nsio->res.start,
+ resource_size(&nsio->res),
+ dev_name(&ndns->dev))) {
+ dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
+ return -EBUSY;
+ }
+
+ dax_kmem->dev = dev;
+ init_completion(&dax_kmem->cmp);
+ rc = percpu_ref_init(&dax_kmem->ref, dax_kmem_percpu_release, 0,
+ GFP_KERNEL);
+ if (rc)
+ return rc;
+
+ rc = devm_add_action_or_reset(dev, dax_kmem_percpu_exit,
+ &dax_kmem->ref);
+ if (rc)
+ return rc;
+
+ dax_kmem->pgmap.ref = &dax_kmem->ref;
+ addr = devm_memremap_pages(dev, &dax_kmem->pgmap);
+ if (IS_ERR(addr))
+ return PTR_ERR(addr);
+
+ rc = devm_add_action_or_reset(dev, dax_kmem_percpu_kill,
+ &dax_kmem->ref);
+ if (rc)
+ return rc;
+
+ /* adjust the dax_region resource to the start of data */
+ memcpy(&res, &dax_kmem->pgmap.res, sizeof(res));
+ res.start += le64_to_cpu(pfn_sb->dataoff);
+
+ rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", ®ion_id, &id);
+ if (rc != 2)
+ return -EINVAL;
+
+ dax_region = alloc_dax_region(dev, region_id, &res,
+ le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
+ if (!dax_region)
+ return -ENOMEM;
+
+ /* TODO: support for subdividing a dax region... */
+ dev_dax = devm_create_dev_dax(dax_region, id, &res, 1);
+
+ /* child dev_dax instances now own the lifetime of the dax_region */
+ dax_region_put(dax_region);
+
+ return PTR_ERR_OR_ZERO(dev_dax);
+}
+
+static struct nd_device_driver dax_kmem_driver = {
+ .probe = dax_kmem_probe,
+ .drv = {
+ .name = "dax_kmem",
+ },
+ .type = ND_DRIVER_DAX_PMEM,
+};
+
+module_nd_driver(dax_kmem_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);
_
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
next prev parent reply other threads:[~2018-10-22 20:18 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-22 20:13 [PATCH 0/9] Allow persistent memory to be used like normal RAM Dave Hansen
2018-10-22 20:13 ` [PATCH 1/9] mm/resource: return real error codes from walk failures Dave Hansen
2018-10-22 20:13 ` Dave Hansen [this message]
2018-10-23 1:56 ` [PATCH 2/9] dax: kernel memory driver for mm ownership of DAX Randy Dunlap
2018-10-22 20:13 ` [PATCH 3/9] dax: add more kmem device infrastructure Dave Hansen
2018-10-22 20:13 ` [PATCH 4/9] dax/kmem: allow PMEM devices to bind to KMEM driver Dave Hansen
2018-10-22 20:13 ` [PATCH 5/9] dax/kmem: add more nd dax kmem infrastructure Dave Hansen
2018-10-22 20:13 ` [PATCH 6/9] mm/memory-hotplug: allow memory resources to be children Dave Hansen
2018-10-22 20:13 ` [PATCH 7/9] dax/kmem: actually perform memory hotplug Dave Hansen
2018-10-22 20:13 ` [PATCH 8/9] dax/kmem: let walk_system_ram_range() search child resources Dave Hansen
2018-10-22 20:13 ` [PATCH 9/9] dax/kmem: actually enable the code in Makefile Dave Hansen
2018-10-23 1:05 ` [PATCH 0/9] Allow persistent memory to be used like normal RAM Dan Williams
2018-10-23 1:11 ` Dan Williams
2018-10-26 8:03 ` Xishi Qiu
2018-10-26 13:58 ` Dave Hansen
2018-10-27 4:45 ` Dan Williams
2018-10-23 18:12 ` Elliott, Robert (Persistent Memory)
2018-10-23 18:16 ` Dave Hansen
2018-10-23 18:58 ` Dan Williams
2018-10-26 5:42 ` Xishi Qiu
2018-10-26 9:03 ` Fengguang Wu
2018-10-27 11:00 ` Fengguang Wu
2018-10-31 5:11 ` Yang Shi
2018-12-03 9:22 ` Brice Goglin
2018-12-03 16:56 ` Dave Hansen
2018-12-03 17:16 ` Dan Williams
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=20181022201320.45C9785C@viggo.jf.intel.com \
--to=dave.hansen@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=fengguang.wu@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvdimm@lists.01.org \
--cc=mhocko@suse.com \
--cc=thomas.lendacky@amd.com \
--cc=ying.huang@intel.com \
--cc=zwisler@kernel.org \
/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).