Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1171989 > unrolled thread

[PATCH v2 00/17] libnvdimm: ->rw_bytes(), BLK, BTT, PMEM api, and unit tests

Started byDan Williams <dan.j.williams@intel.com>
First post2015-06-25 11:50 +0200
Last post2015-06-25 11:50 +0200
Articles 7 — 2 participants

Back to article view | Back to linux.kernel

Contents

  [PATCH v2 00/17] libnvdimm: ->rw_bytes(), BLK, BTT, PMEM api,  and unit tests Dan Williams <dan.j.williams@intel.com> - 2015-06-25 11:50 +0200
    [PATCH v2 16/17] libnvdimm: Add sysfs numa_node to NVDIMM devices Dan Williams <dan.j.williams@intel.com> - 2015-06-25 11:50 +0200
      Re: [PATCH v2 16/17] libnvdimm: Add sysfs numa_node to NVDIMM  devices Toshi Kani <toshi.kani@hp.com> - 2015-06-26 04:30 +0200
    [PATCH v2 06/17] fs/block_dev.c: skip rw_page if bdev has integrity Dan Williams <dan.j.williams@intel.com> - 2015-06-25 11:50 +0200
    [PATCH v2 14/17] acpi: Add acpi_map_pxm_to_online_node() Dan Williams <dan.j.williams@intel.com> - 2015-06-25 11:50 +0200
    [PATCH v2 12/17] pmem: flag pmem block devices as non-rotational Dan Williams <dan.j.williams@intel.com> - 2015-06-25 11:50 +0200
    [PATCH v2 11/17] libnvdimm: enable iostat Dan Williams <dan.j.williams@intel.com> - 2015-06-25 11:50 +0200

#1171989 — [PATCH v2 00/17] libnvdimm: ->rw_bytes(), BLK, BTT, PMEM api, and unit tests

FromDan Williams <dan.j.williams@intel.com>
Date2015-06-25 11:50 +0200
Subject[PATCH v2 00/17] libnvdimm: ->rw_bytes(), BLK, BTT, PMEM api, and unit tests
Message-ID<pFbXc-4YO-11@gated-at.bofh.it>
->rw_bytes() is a byte-aligned interface for accessing persistent memory
namespaces.  The primary consumer of the ->rw_bytes() interface is the
BTT library.

BTT is a library that converts a byte-accessible namespace into a disk
with atomic sector update semantics (prevents sector tearing on crash or
power loss).  The sinister aspect of sector tearing is that most
applications do not know they have a atomic sector dependency.  At least
today's disk's rarely ever tear sectors and if they do you almost
certainly get a CRC error on access.  NVDIMMs will always tear and
always silently.

BLK is a driver for NVDIMMs that provide sliding mmio windows to access
persistent memory.

The PMEM api defines ensures writes have hit persistent media relative
to the completion of an i/o.

Changes since v1 [1]:

1/ The ->rw_bytes() interface has been removed from struct
block_device_operations and is now a common operation of NVDIMM
namespace devices.  Accordingly a BTT instance is now a libnvdimm
device-model peer of a namespace rather than a stacked block device
driver.  The BTT is no longer a driver in its own right, instead it is a
extension library used by a BLK or PMEM namespace.  This clarifies the
device model and reduced the core implementation by a couple hundred
lines of code.  (Christoph)

2/ Kill ND_MAX_REGIONS and ND_IOSTAT Kconfig options. (Christoph)

3/ Killed the access out of range check separately in PMEM, BLK, and BTT
(Christoph)

4/ Kill the central helper for blk queue properties (Christoph)

5/ Added Toshi's numa patches with a change to set the numa info at
device create time rather than driver probe time.

6/ Cherry picked the PMEM api.  The wider arch cleanups in the full
pmem-api series are too large / invasive to pick up at this late date.
The keeps the pmem.c driver x86-only for one more cycle.

[1]: https://lists.01.org/pipermail/linux-nvdimm/2015-June/001246.html

Diffstat since v1:

 Documentation/nvdimm/btt.txt      |  24 ++-
 Documentation/nvdimm/nvdimm.txt   |  79 ++++----
 arch/x86/Kconfig                  |   1 +
 arch/x86/include/asm/cacheflush.h |  72 +++++++
 arch/x86/include/asm/io.h         |   6 +
 drivers/acpi/nfit.c               |  17 +-
 drivers/acpi/numa.c               |  50 ++++-
 drivers/nvdimm/Kconfig            |  56 ++----
 drivers/nvdimm/Makefile           |   2 +-
 drivers/nvdimm/blk.c              | 148 +++++++-------
 drivers/nvdimm/btt.c              | 166 ++++------------
 drivers/nvdimm/btt_devs.c         | 403 +++++++++++++++++---------------------
 drivers/nvdimm/bus.c              | 190 ++++--------------
 drivers/nvdimm/core.c             |  30 ---
 drivers/nvdimm/label.c            |   5 +-
 drivers/nvdimm/namespace_devs.c   | 252 +++++++++++++++++++-----
 drivers/nvdimm/nd-core.h          |  47 +----
 drivers/nvdimm/nd.h               |  51 +++--
 drivers/nvdimm/pmem.c             | 185 ++++++++---------
 drivers/nvdimm/region.c           |  85 +-------
 drivers/nvdimm/region_devs.c      | 182 +++++++++++++----
 include/linux/acpi.h              |   5 +
 include/linux/blkdev.h            |  44 -----
 include/linux/compiler.h          |   2 +
 include/linux/libnvdimm.h         |   2 +
 include/linux/nd.h                |  63 +++++-
 include/linux/pmem.h              | 153 +++++++++++++++
 include/uapi/linux/ndctl.h        |   2 -
 lib/Kconfig                       |   3 +
 tools/testing/nvdimm/Kbuild       |   2 +-
 tools/testing/nvdimm/test/nfit.c  |   1 +
 31 files changed, 1272 insertions(+), 1056 deletions(-)
 create mode 100644 include/linux/pmem.h

---

Dan Williams (8):
      libnvdimm: infrastructure for btt devices
      tools/testing/nvdimm: libnvdimm unit test infrastructure
      libnvdimm: Non-Volatile Devices
      libnvdimm, pmem: fix up max_hw_sectors
      pmem: make_request cleanups
      libnvdimm: enable iostat
      pmem: flag pmem block devices as non-rotational
      libnvdimm, nfit: handle unarmed dimms, mark namespaces read-only

Ross Zwisler (2):
      libnvdimm, nfit, nd_blk: driver for BLK-mode access persistent memory
      arch, x86: pmem api for ensuring durability of persistent memory updates

Toshi Kani (3):
      acpi: Add acpi_map_pxm_to_online_node()
      libnvdimm: Set numa_node to NVDIMM devices
      libnvdimm: Add sysfs numa_node to NVDIMM devices

Vishal Verma (4):
      nd_btt: atomic sector updates
      fs/block_dev.c: skip rw_page if bdev has integrity
      libnvdimm, btt: add support for blk integrity
      libnvdimm, blk: add support for blk integrity


 Documentation/nvdimm/btt.txt          |  283 ++++++
 Documentation/nvdimm/nvdimm.txt       |  808 ++++++++++++++++++
 MAINTAINERS                           |   39 +
 arch/x86/Kconfig                      |    1 
 arch/x86/include/asm/cacheflush.h     |   72 ++
 arch/x86/include/asm/io.h             |    6 
 drivers/acpi/nfit.c                   |  498 +++++++++++
 drivers/acpi/nfit.h                   |   58 +
 drivers/acpi/numa.c                   |   50 +
 drivers/nvdimm/Kconfig                |   42 +
 drivers/nvdimm/Makefile               |    7 
 drivers/nvdimm/blk.c                  |  384 +++++++++
 drivers/nvdimm/btt.c                  | 1479 +++++++++++++++++++++++++++++++++
 drivers/nvdimm/btt.h                  |  185 ++++
 drivers/nvdimm/btt_devs.c             |  426 ++++++++++
 drivers/nvdimm/bus.c                  |   60 +
 drivers/nvdimm/core.c                 |   69 ++
 drivers/nvdimm/dimm_devs.c            |    9 
 drivers/nvdimm/label.c                |    5 
 drivers/nvdimm/namespace_devs.c       |  295 ++++++-
 drivers/nvdimm/nd-core.h              |    5 
 drivers/nvdimm/nd.h                   |   86 ++
 drivers/nvdimm/pmem.c                 |  181 ++--
 drivers/nvdimm/region.c               |   28 +
 drivers/nvdimm/region_devs.c          |  238 +++++
 fs/block_dev.c                        |    4 
 include/linux/acpi.h                  |    5 
 include/linux/compiler.h              |    2 
 include/linux/libnvdimm.h             |   32 +
 include/linux/nd.h                    |   63 +
 include/linux/pmem.h                  |  153 +++
 lib/Kconfig                           |    3 
 tools/testing/nvdimm/Kbuild           |   40 +
 tools/testing/nvdimm/Makefile         |    7 
 tools/testing/nvdimm/config_check.c   |   15 
 tools/testing/nvdimm/test/Kbuild      |    8 
 tools/testing/nvdimm/test/iomap.c     |  151 +++
 tools/testing/nvdimm/test/nfit.c      | 1116 +++++++++++++++++++++++++
 tools/testing/nvdimm/test/nfit_test.h |   29 +
 39 files changed, 6759 insertions(+), 183 deletions(-)
 create mode 100644 Documentation/nvdimm/btt.txt
 create mode 100644 Documentation/nvdimm/nvdimm.txt
 create mode 100644 drivers/nvdimm/blk.c
 create mode 100644 drivers/nvdimm/btt.c
 create mode 100644 drivers/nvdimm/btt.h
 create mode 100644 drivers/nvdimm/btt_devs.c
 create mode 100644 include/linux/pmem.h
 create mode 100644 tools/testing/nvdimm/Kbuild
 create mode 100644 tools/testing/nvdimm/Makefile
 create mode 100644 tools/testing/nvdimm/config_check.c
 create mode 100644 tools/testing/nvdimm/test/Kbuild
 create mode 100644 tools/testing/nvdimm/test/iomap.c
 create mode 100644 tools/testing/nvdimm/test/nfit.c
 create mode 100644 tools/testing/nvdimm/test/nfit_test.h
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1171990 — [PATCH v2 16/17] libnvdimm: Add sysfs numa_node to NVDIMM devices

FromDan Williams <dan.j.williams@intel.com>
Date2015-06-25 11:50 +0200
Subject[PATCH v2 16/17] libnvdimm: Add sysfs numa_node to NVDIMM devices
Message-ID<pFbXe-4YO-37@gated-at.bofh.it>
In reply to#1171989
From: Toshi Kani <toshi.kani@hp.com>

Add support of sysfs 'numa_node' to I/O-related NVDIMM devices
under /sys/bus/nd/devices, regionN, namespaceN.0, and bttN.
When bttN is not set up, its numa_node returns -1 (NUMA_NO_NODE).

An example of numa_node values on a 2-socket system with a single
NVDIMM range on each socket is shown below.
  /sys/bus/nd/devices
  |-- btt0/numa_node:-1
  |-- btt1/numa_node:0
  |-- namespace0.0/numa_node:0
  |-- namespace1.0/numa_node:1
  |-- region0/numa_node:0
  |-- region1/numa_node:1

These numa_node files are then linked under the block class of
their device names.
  /sys/class/block/pmem0/device/numa_node:0
  /sys/class/block/pmem0s/device/numa_node:0
  /sys/class/block/pmem1/device/numa_node:1

This enables numactl(8) to accept 'block:' and 'file:' paths of
pmem and btt devices as shown in the examples below.
  numactl --preferred block:pmem0 --show
  numactl --preferred file:/dev/pmem0s --show

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit.c             |    1 +
 drivers/nvdimm/btt_devs.c       |    1 +
 drivers/nvdimm/bus.c            |   30 ++++++++++++++++++++++++++++++
 drivers/nvdimm/namespace_devs.c |    1 +
 include/linux/libnvdimm.h       |    1 +
 5 files changed, 34 insertions(+)

diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index d96c8fe974dd..2161fa178c8d 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -873,6 +873,7 @@ static const struct attribute_group *acpi_nfit_region_attribute_groups[] = {
 	&nd_region_attribute_group,
 	&nd_mapping_attribute_group,
 	&nd_device_attribute_group,
+	&nd_numa_attribute_group,
 	&acpi_nfit_region_attribute_group,
 	NULL,
 };
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index b6724cfbcfca..2dfb529f4d35 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -294,6 +294,7 @@ static struct attribute_group nd_btt_attribute_group = {
 static const struct attribute_group *nd_btt_attribute_groups[] = {
 	&nd_btt_attribute_group,
 	&nd_device_attribute_group,
+	&nd_numa_attribute_group,
 	NULL,
 };
 
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index ec59f1f26d95..1380954a6593 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -274,6 +274,36 @@ struct attribute_group nd_device_attribute_group = {
 };
 EXPORT_SYMBOL_GPL(nd_device_attribute_group);
 
+static ssize_t numa_node_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev_to_node(dev));
+}
+static DEVICE_ATTR_RO(numa_node);
+
+static struct attribute *nd_numa_attributes[] = {
+	&dev_attr_numa_node.attr,
+	NULL,
+};
+
+static umode_t nd_numa_attr_visible(struct kobject *kobj, struct attribute *a,
+		int n)
+{
+	if (!IS_ENABLED(CONFIG_NUMA))
+		return 0;
+
+	return a->mode;
+}
+
+/**
+ * nd_numa_attribute_group - NUMA attributes for all devices on an nd bus
+ */
+struct attribute_group nd_numa_attribute_group = {
+	.attrs = nd_numa_attributes,
+	.is_visible = nd_numa_attr_visible,
+};
+EXPORT_SYMBOL_GPL(nd_numa_attribute_group);
+
 int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus)
 {
 	dev_t devt = MKDEV(nvdimm_bus_major, nvdimm_bus->id);
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 27d69bd3b4d6..fef0dd80d4ad 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1228,6 +1228,7 @@ static struct attribute_group nd_namespace_attribute_group = {
 static const struct attribute_group *nd_namespace_attribute_groups[] = {
 	&nd_device_attribute_group,
 	&nd_namespace_attribute_group,
+	&nd_numa_attribute_group,
 	NULL,
 };
 
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 30b3deaafd51..75e3af01ee32 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -38,6 +38,7 @@ enum {
 extern struct attribute_group nvdimm_bus_attribute_group;
 extern struct attribute_group nvdimm_attribute_group;
 extern struct attribute_group nd_device_attribute_group;
+extern struct attribute_group nd_numa_attribute_group;
 extern struct attribute_group nd_region_attribute_group;
 extern struct attribute_group nd_mapping_attribute_group;
 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1172565 — Re: [PATCH v2 16/17] libnvdimm: Add sysfs numa_node to NVDIMM devices

FromToshi Kani <toshi.kani@hp.com>
Date2015-06-26 04:30 +0200
SubjectRe: [PATCH v2 16/17] libnvdimm: Add sysfs numa_node to NVDIMM devices
Message-ID<pFryV-2a2-17@gated-at.bofh.it>
In reply to#1171990
On Thu, 2015-06-25 at 05:37 -0400, Dan Williams wrote:
> From: Toshi Kani <toshi.kani@hp.com>
> 
> Add support of sysfs 'numa_node' to I/O-related NVDIMM devices
> under /sys/bus/nd/devices, regionN, namespaceN.0, and bttN.
> When bttN is not set up, its numa_node returns -1 (NUMA_NO_NODE).
> 
> An example of numa_node values on a 2-socket system with a single
> NVDIMM range on each socket is shown below.
>   /sys/bus/nd/devices
>   |-- btt0/numa_node:-1
>   |-- btt1/numa_node:0
>   |-- namespace0.0/numa_node:0
>   |-- namespace1.0/numa_node:1
>   |-- region0/numa_node:0
>   |-- region1/numa_node:1
> 
> These numa_node files are then linked under the block class of
> their device names.
>   /sys/class/block/pmem0/device/numa_node:0
>   /sys/class/block/pmem0s/device/numa_node:0
>   /sys/class/block/pmem1/device/numa_node:1
> 
> This enables numactl(8) to accept 'block:' and 'file:' paths of
> pmem and btt devices as shown in the examples below.
>   numactl --preferred block:pmem0 --show
>   numactl --preferred file:/dev/pmem0s --show
> 
> Signed-off-by: Toshi Kani <toshi.kani@hp.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Can you please update the commit log with the following?  It reflects
the changes in sysfs btt files.

Thanks,
-Toshi

=====
From: Toshi Kani <toshi.kani@hp.com>

Add support of sysfs 'numa_node' to I/O-related NVDIMM devices
under /sys/bus/nd/devices, regionN, namespaceN.0, and bttN.x.

An example of numa_node values on a 2-socket system with a single
NVDIMM range on each socket is shown below.
  /sys/bus/nd/devices
  |-- btt0.0/numa_node:0
  |-- btt1.0/numa_node:1
  |-- btt1.1/numa_node:1
  |-- namespace0.0/numa_node:0
  |-- namespace1.0/numa_node:1
  |-- region0/numa_node:0
  |-- region1/numa_node:1

These numa_node files are then linked under the block class of
their device names.
  /sys/class/block/pmem0/device/numa_node:0
  /sys/class/block/pmem1s/device/numa_node:1

This enables numactl(8) to accept 'block:' and 'file:' paths of
pmem and btt devices as shown in the examples below.
  numactl --preferred block:pmem0 --show
  numactl --preferred file:/dev/pmem1s --show

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1171991 — [PATCH v2 06/17] fs/block_dev.c: skip rw_page if bdev has integrity

FromDan Williams <dan.j.williams@intel.com>
Date2015-06-25 11:50 +0200
Subject[PATCH v2 06/17] fs/block_dev.c: skip rw_page if bdev has integrity
Message-ID<pFbXe-4YO-39@gated-at.bofh.it>
In reply to#1171989
From: Vishal Verma <vishal.l.verma@intel.com>

If a block device has bio integrity enabled, rw_page will bypass the
integrity payload, which is undesirable. Skip rw_page if this is the
case.

Currently brd and zram provide rw_page, and the proposed 'nd' drivers
will too.

Cc: Jens Axboe <axboe@fb.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Suggested-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 fs/block_dev.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index c7e4163ede87..054ef1bbb821 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -376,7 +376,7 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 			struct page *page)
 {
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
-	if (!ops->rw_page)
+	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
 	return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
 }
@@ -407,7 +407,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 	int result;
 	int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
-	if (!ops->rw_page)
+	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
 	set_page_writeback(page);
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1171993 — [PATCH v2 14/17] acpi: Add acpi_map_pxm_to_online_node()

FromDan Williams <dan.j.williams@intel.com>
Date2015-06-25 11:50 +0200
Subject[PATCH v2 14/17] acpi: Add acpi_map_pxm_to_online_node()
Message-ID<pFbXe-4YO-45@gated-at.bofh.it>
In reply to#1171989
From: Toshi Kani <toshi.kani@hp.com>

The kernel initializes CPU & memory's NUMA topology from ACPI
SRAT table.  Some other ACPI tables, such as NFIT and DMAR, also
contain proximity IDs for their device's NUMA topology.  This
information can be used to improve performance of these devices.

This patch introduces acpi_map_pxm_to_online_node(), which is
similar to acpi_map_pxm_to_node(), but always returns an online
node.  When the mapped node from a given proximity ID is offline,
it looks up the node distance table and returns the nearest
online node.

ACPI device drivers, which are called after the NUMA initialization
has completed in the kernel, can call this interface to obtain their
device NUMA topology from ACPI tables.  Such drivers do not have to
deal with offline nodes.  A node may be offline when a device
proximity ID is unique, SRAT memory entry does not exist, or NUMA is
disabled, ex. "numa=off" on x86.

This patch also moves the pxm range check from acpi_get_node() to
acpi_map_pxm_to_node().

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa.c  |   50 +++++++++++++++++++++++++++++++++++++++++++++++---
 include/linux/acpi.h |    5 +++++
 2 files changed, 52 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 1333cbdc3ea2..acaa3b4ea504 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -29,6 +29,8 @@
 #include <linux/errno.h>
 #include <linux/acpi.h>
 #include <linux/numa.h>
+#include <linux/nodemask.h>
+#include <linux/topology.h>
 
 #define PREFIX "ACPI: "
 
@@ -70,7 +72,12 @@ static void __acpi_map_pxm_to_node(int pxm, int node)
 
 int acpi_map_pxm_to_node(int pxm)
 {
-	int node = pxm_to_node_map[pxm];
+	int node;
+
+	if (pxm < 0 || pxm >= MAX_PXM_DOMAINS)
+		return NUMA_NO_NODE;
+
+	node = pxm_to_node_map[pxm];
 
 	if (node == NUMA_NO_NODE) {
 		if (nodes_weight(nodes_found_map) >= MAX_NUMNODES)
@@ -83,6 +90,45 @@ int acpi_map_pxm_to_node(int pxm)
 	return node;
 }
 
+/**
+ * acpi_map_pxm_to_online_node - Map proximity ID to online node
+ * @pxm: ACPI proximity ID
+ *
+ * This is similar to acpi_map_pxm_to_node(), but always returns an online
+ * node.  When the mapped node from a given proximity ID is offline, it
+ * looks up the node distance table and returns the nearest online node.
+ *
+ * ACPI device drivers, which are called after the NUMA initialization has
+ * completed in the kernel, can call this interface to obtain their device
+ * NUMA topology from ACPI tables.  Such drivers do not have to deal with
+ * offline nodes.  A node may be offline when a device proximity ID is
+ * unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
+ * "numa=off" on x86.
+ */
+int acpi_map_pxm_to_online_node(int pxm)
+{
+	int node, n, dist, min_dist;
+
+	node = acpi_map_pxm_to_node(pxm);
+
+	if (node == NUMA_NO_NODE)
+		node = 0;
+
+	if (!node_online(node)) {
+		min_dist = INT_MAX;
+		for_each_online_node(n) {
+			dist = node_distance(node, n);
+			if (dist < min_dist) {
+				min_dist = dist;
+				node = n;
+			}
+		}
+	}
+
+	return node;
+}
+EXPORT_SYMBOL(acpi_map_pxm_to_online_node);
+
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {
@@ -328,8 +374,6 @@ int acpi_get_node(acpi_handle handle)
 	int pxm;
 
 	pxm = acpi_get_pxm(handle);
-	if (pxm < 0 || pxm >= MAX_PXM_DOMAINS)
-		return NUMA_NO_NODE;
 
 	return acpi_map_pxm_to_node(pxm);
 }
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index e4da5e35e29c..1b3bbb11d11c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -289,8 +289,13 @@ extern void acpi_dmi_osi_linux(int enable, const struct dmi_system_id *d);
 extern void acpi_osi_setup(char *str);
 
 #ifdef CONFIG_ACPI_NUMA
+int acpi_map_pxm_to_online_node(int pxm);
 int acpi_get_node(acpi_handle handle);
 #else
+static inline int acpi_map_pxm_to_online_node(int pxm)
+{
+	return 0;
+}
 static inline int acpi_get_node(acpi_handle handle)
 {
 	return 0;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1171994 — [PATCH v2 12/17] pmem: flag pmem block devices as non-rotational

FromDan Williams <dan.j.williams@intel.com>
Date2015-06-25 11:50 +0200
Subject[PATCH v2 12/17] pmem: flag pmem block devices as non-rotational
Message-ID<pFbXe-4YO-49@gated-at.bofh.it>
In reply to#1171989
...since they are effectively SSDs as far as userspace is concerned.

Reviewed-by: Vishal Verma <vishal.l.verma@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/pmem.c |    1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 09195e3b7453..a9709db0704c 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -158,6 +158,7 @@ static int pmem_attach_disk(struct nd_namespace_common *ndns,
 	blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
 	blk_queue_max_hw_sectors(pmem->pmem_queue, UINT_MAX);
 	blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, pmem->pmem_queue);
 
 	disk = alloc_disk(0);
 	if (!disk) {

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1171995 — [PATCH v2 11/17] libnvdimm: enable iostat

FromDan Williams <dan.j.williams@intel.com>
Date2015-06-25 11:50 +0200
Subject[PATCH v2 11/17] libnvdimm: enable iostat
Message-ID<pFbXf-4YO-51@gated-at.bofh.it>
In reply to#1171989
This is disabled by default as the overhead is prohibitive, but if the
user takes the action to turn it on we'll oblige.

Reviewed-by: Vishal Verma <vishal.l.verma@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/blk.c  |    7 ++++++-
 drivers/nvdimm/btt.c  |    7 ++++++-
 drivers/nvdimm/core.c |   29 +++++++++++++++++++++++++++++
 drivers/nvdimm/nd.h   |   13 +++++++++++++
 drivers/nvdimm/pmem.c |    5 +++++
 5 files changed, 59 insertions(+), 2 deletions(-)

diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 5c44e067652f..96ef38ceeceb 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -168,8 +168,10 @@ static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	struct bio_integrity_payload *bip;
 	struct nd_blk_device *blk_dev;
 	struct bvec_iter iter;
+	unsigned long start;
 	struct bio_vec bvec;
 	int err = 0, rw;
+	bool do_acct;
 
 	/*
 	 * bio_integrity_enabled also checks if the bio already has an
@@ -185,6 +187,7 @@ static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
 	bip = bio_integrity(bio);
 	blk_dev = disk->private_data;
 	rw = bio_data_dir(bio);
+	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 
@@ -196,9 +199,11 @@ static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
 					"io error in %s sector %lld, len %d,\n",
 					(rw == READ) ? "READ" : "WRITE",
 					(unsigned long long) iter.bi_sector, len);
-			goto out;
+			break;
 		}
 	}
+	if (do_acct)
+		nd_iostat_end(bio, start);
 
  out:
 	bio_endio(bio, err);
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 18a2463c2300..c02065aed03d 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1177,8 +1177,10 @@ static void btt_make_request(struct request_queue *q, struct bio *bio)
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct btt *btt = q->queuedata;
 	struct bvec_iter iter;
+	unsigned long start;
 	struct bio_vec bvec;
 	int err = 0, rw;
+	bool do_acct;
 
 	/*
 	 * bio_integrity_enabled also checks if the bio already has an
@@ -1191,6 +1193,7 @@ static void btt_make_request(struct request_queue *q, struct bio *bio)
 		goto out;
 	}
 
+	do_acct = nd_iostat_start(bio, &start);
 	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
@@ -1208,9 +1211,11 @@ static void btt_make_request(struct request_queue *q, struct bio *bio)
 					"io error in %s sector %lld, len %d,\n",
 					(rw == READ) ? "READ" : "WRITE",
 					(unsigned long long) iter.bi_sector, len);
-			goto out;
+			break;
 		}
 	}
+	if (do_acct)
+		nd_iostat_end(bio, start);
 
 out:
 	bio_endio(bio, err);
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 4288169432de..cb62ec6a12d0 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -214,6 +214,35 @@ ssize_t nd_sector_size_store(struct device *dev, const char *buf,
 	}
 }
 
+void __nd_iostat_start(struct bio *bio, unsigned long *start)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	const int rw = bio_data_dir(bio);
+	int cpu = part_stat_lock();
+
+	*start = jiffies;
+	part_round_stats(cpu, &disk->part0);
+	part_stat_inc(cpu, &disk->part0, ios[rw]);
+	part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio));
+	part_inc_in_flight(&disk->part0, rw);
+	part_stat_unlock();
+}
+EXPORT_SYMBOL(__nd_iostat_start);
+
+void nd_iostat_end(struct bio *bio, unsigned long start)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	unsigned long duration = jiffies - start;
+	const int rw = bio_data_dir(bio);
+	int cpu = part_stat_lock();
+
+	part_stat_add(cpu, &disk->part0, ticks[rw], duration);
+	part_round_stats(cpu, &disk->part0);
+	part_dec_in_flight(&disk->part0, rw);
+	part_stat_unlock();
+}
+EXPORT_SYMBOL(nd_iostat_end);
+
 static ssize_t commands_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index e73c34dcd935..cf6849b72c4f 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -13,6 +13,7 @@
 #ifndef __ND_H__
 #define __ND_H__
 #include <linux/libnvdimm.h>
+#include <linux/blkdev.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
 #include <linux/ndctl.h>
@@ -201,5 +202,17 @@ int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns);
 const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 		char *name);
 int nd_blk_region_init(struct nd_region *nd_region);
+void __nd_iostat_start(struct bio *bio, unsigned long *start);
+static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+
+	if (!blk_queue_io_stat(disk->queue))
+		return false;
+
+	__nd_iostat_start(bio, start);
+	return true;
+}
+void nd_iostat_end(struct bio *bio, unsigned long start);
 resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk);
 #endif /* __ND_H__ */
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index e846a627ebdf..09195e3b7453 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -58,14 +58,19 @@ static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 
 static void pmem_make_request(struct request_queue *q, struct bio *bio)
 {
+	bool do_acct;
+	unsigned long start;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	struct block_device *bdev = bio->bi_bdev;
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 
+	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter)
 		pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, bvec.bv_offset,
 				bio_data_dir(bio), iter.bi_sector);
+	if (do_acct)
+		nd_iostat_end(bio, start);
 	bio_endio(bio, 0);
 }
 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web