libnvdimm, nfit, nd_blk: driver for BLK-mode access persistent memory

The libnvdimm implementation handles allocating dimm address space (DPA)
between PMEM and BLK mode interfaces.  After DPA has been allocated from
a BLK-region to a BLK-namespace the nd_blk driver attaches to handle I/O
as a struct bio based block device. Unlike PMEM, BLK is required to
handle platform specific details like mmio register formats and memory
controller interleave.  For this reason the libnvdimm generic nd_blk
driver calls back into the bus provider to carry out the I/O.

This initial implementation handles the BLK interface defined by the
ACPI 6 NFIT [1] and the NVDIMM DSM Interface Example [2] composed from
DCR (dimm control region), BDW (block data window), IDT (interleave
descriptor) NFIT structures and the hardware register format.
[1]: http://www.uefi.org/sites/default/files/resources/ACPI_6.0.pdf
[2]: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf

Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/acpi/nfit.h

@@ -52,6 +52,11 @@ struct nfit_bdw {
 	struct list_head list;
 };
 
+struct nfit_idt {
+	struct acpi_nfit_interleave *idt;
+	struct list_head list;
+};
+
 struct nfit_memdev {
 	struct acpi_nfit_memory_map *memdev;
 	struct list_head list;
@@ -62,10 +67,13 @@ struct nfit_mem {
 	struct nvdimm *nvdimm;
 	struct acpi_nfit_memory_map *memdev_dcr;
 	struct acpi_nfit_memory_map *memdev_pmem;
+	struct acpi_nfit_memory_map *memdev_bdw;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_data_region *bdw;
 	struct acpi_nfit_system_address *spa_dcr;
 	struct acpi_nfit_system_address *spa_bdw;
+	struct acpi_nfit_interleave *idt_dcr;
+	struct acpi_nfit_interleave *idt_bdw;
 	struct list_head list;
 	struct acpi_device *adev;
 	unsigned long dsm_mask;
@@ -74,16 +82,57 @@ struct nfit_mem {
 struct acpi_nfit_desc {
 	struct nvdimm_bus_descriptor nd_desc;
 	struct acpi_table_nfit *nfit;
+	struct mutex spa_map_mutex;
+	struct list_head spa_maps;
 	struct list_head memdevs;
 	struct list_head dimms;
 	struct list_head spas;
 	struct list_head dcrs;
 	struct list_head bdws;
+	struct list_head idts;
 	struct nvdimm_bus *nvdimm_bus;
 	struct device *dev;
 	unsigned long dimm_dsm_force_en;
 };
 
+enum nd_blk_mmio_selector {
+	BDW,
+	DCR,
+};
+
+struct nfit_blk {
+	struct nfit_blk_mmio {
+		union {
+			void __iomem *base;
+			void *aperture;
+		};
+		u64 size;
+		u64 base_offset;
+		u32 line_size;
+		u32 num_lines;
+		u32 table_size;
+		struct acpi_nfit_interleave *idt;
+		struct acpi_nfit_system_address *spa;
+	} mmio[2];
+	struct nd_region *nd_region;
+	u64 bdw_offset; /* post interleave offset */
+	u64 stat_offset;
+	u64 cmd_offset;
+};
+
+struct nfit_spa_mapping {
+	struct acpi_nfit_desc *acpi_desc;
+	struct acpi_nfit_system_address *spa;
+	struct list_head list;
+	struct kref kref;
+	void __iomem *iomem;
+};
+
+static inline struct nfit_spa_mapping *to_spa_map(struct kref *kref)
+{
+	return container_of(kref, struct nfit_spa_mapping, kref);
+}
+
 static inline struct acpi_nfit_memory_map *__to_nfit_memdev(
 		struct nfit_mem *nfit_mem)
 {

drivers/nvdimm/Kconfig

@@ -34,6 +34,19 @@ config BLK_DEV_PMEM
 
 	  Say Y if you want to use an NVDIMM
 
+config ND_BLK
+	tristate "BLK: Block data window (aperture) device support"
+	default LIBNVDIMM
+	select ND_BTT if BTT
+	help
+	  Support NVDIMMs, or other devices, that implement a BLK-mode
+	  access capability.  BLK-mode access uses memory-mapped-i/o
+	  apertures to access persistent media.
+
+	  Say Y if your platform firmware emits an ACPI.NFIT table
+	  (CONFIG_ACPI_NFIT), or otherwise exposes BLK-mode
+	  capabilities.
+
 config ND_BTT
 	tristate
 

drivers/nvdimm/Makefile

@@ -1,11 +1,14 @@
 obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
 obj-$(CONFIG_ND_BTT) += nd_btt.o
+obj-$(CONFIG_ND_BLK) += nd_blk.o
 
 nd_pmem-y := pmem.o
 
 nd_btt-y := btt.o
 
+nd_blk-y := blk.o
+
 libnvdimm-y := core.o
 libnvdimm-y += bus.o
 libnvdimm-y += dimm_devs.o

drivers/nvdimm/blk.c

@@ -0,0 +1,245 @@
+/*
+ * NVDIMM Block Window Driver
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/blkdev.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/nd.h>
+#include <linux/sizes.h>
+#include "nd.h"
+
+struct nd_blk_device {
+	struct request_queue *queue;
+	struct gendisk *disk;
+	struct nd_namespace_blk *nsblk;
+	struct nd_blk_region *ndbr;
+	size_t disk_size;
+};
+
+static int nd_blk_major;
+
+static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
+				resource_size_t ns_offset, unsigned int len)
+{
+	int i;
+
+	for (i = 0; i < nsblk->num_resources; i++) {
+		if (ns_offset < resource_size(nsblk->res[i])) {
+			if (ns_offset + len > resource_size(nsblk->res[i])) {
+				dev_WARN_ONCE(&nsblk->common.dev, 1,
+					"illegal request\n");
+				return SIZE_MAX;
+			}
+			return nsblk->res[i]->start + ns_offset;
+		}
+		ns_offset -= resource_size(nsblk->res[i]);
+	}
+
+	dev_WARN_ONCE(&nsblk->common.dev, 1, "request out of range\n");
+	return SIZE_MAX;
+}
+
+static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct block_device *bdev = bio->bi_bdev;
+	struct gendisk *disk = bdev->bd_disk;
+	struct nd_namespace_blk *nsblk;
+	struct nd_blk_device *blk_dev;
+	struct nd_blk_region *ndbr;
+	struct bvec_iter iter;
+	struct bio_vec bvec;
+	int err = 0, rw;
+
+	blk_dev = disk->private_data;
+	nsblk = blk_dev->nsblk;
+	ndbr = blk_dev->ndbr;
+	rw = bio_data_dir(bio);
+	bio_for_each_segment(bvec, bio, iter) {
+		unsigned int len = bvec.bv_len;
+		resource_size_t	dev_offset;
+		void *iobuf;
+
+		BUG_ON(len > PAGE_SIZE);
+
+		dev_offset = to_dev_offset(nsblk,
+				iter.bi_sector << SECTOR_SHIFT, len);
+		if (dev_offset == SIZE_MAX) {
+			err = -EIO;
+			goto out;
+		}
+
+		iobuf = kmap_atomic(bvec.bv_page);
+		err = ndbr->do_io(ndbr, dev_offset, iobuf + bvec.bv_offset,
+				len, rw);
+		kunmap_atomic(iobuf);
+		if (err)
+			goto out;
+	}
+
+ out:
+	bio_endio(bio, err);
+}
+
+static int nd_blk_rw_bytes(struct nd_namespace_common *ndns,
+		resource_size_t offset, void *iobuf, size_t n, int rw)
+{
+	struct nd_blk_device *blk_dev = dev_get_drvdata(ndns->claim);
+	struct nd_namespace_blk *nsblk = blk_dev->nsblk;
+	struct nd_blk_region *ndbr = blk_dev->ndbr;
+	resource_size_t	dev_offset;
+
+	dev_offset = to_dev_offset(nsblk, offset, n);
+
+	if (unlikely(offset + n > blk_dev->disk_size)) {
+		dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
+		return -EFAULT;
+	}
+
+	if (dev_offset == SIZE_MAX)
+		return -EIO;
+
+	return ndbr->do_io(ndbr, dev_offset, iobuf, n, rw);
+}
+
+static const struct block_device_operations nd_blk_fops = {
+	.owner = THIS_MODULE,
+};
+
+static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
+		struct nd_blk_device *blk_dev)
+{
+	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(&ndns->dev);
+	struct gendisk *disk;
+
+	blk_dev->queue = blk_alloc_queue(GFP_KERNEL);
+	if (!blk_dev->queue)
+		return -ENOMEM;
+
+	blk_queue_make_request(blk_dev->queue, nd_blk_make_request);
+	blk_queue_max_hw_sectors(blk_dev->queue, UINT_MAX);
+	blk_queue_bounce_limit(blk_dev->queue, BLK_BOUNCE_ANY);
+	blk_queue_logical_block_size(blk_dev->queue, nsblk->lbasize);
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, blk_dev->queue);
+
+	disk = blk_dev->disk = alloc_disk(0);
+	if (!disk) {
+		blk_cleanup_queue(blk_dev->queue);
+		return -ENOMEM;
+	}
+
+	disk->driverfs_dev	= &ndns->dev;
+	disk->major		= nd_blk_major;
+	disk->first_minor	= 0;
+	disk->fops		= &nd_blk_fops;
+	disk->private_data	= blk_dev;
+	disk->queue		= blk_dev->queue;
+	disk->flags		= GENHD_FL_EXT_DEVT;
+	nvdimm_namespace_disk_name(ndns, disk->disk_name);
+	set_capacity(disk, blk_dev->disk_size >> SECTOR_SHIFT);
+	add_disk(disk);
+
+	return 0;
+}
+
+static int nd_blk_probe(struct device *dev)
+{
+	struct nd_namespace_common *ndns;
+	struct nd_blk_device *blk_dev;
+	int rc;
+
+	ndns = nvdimm_namespace_common_probe(dev);
+	if (IS_ERR(ndns))
+		return PTR_ERR(ndns);
+
+	blk_dev = kzalloc(sizeof(*blk_dev), GFP_KERNEL);
+	if (!blk_dev)
+		return -ENOMEM;
+
+	blk_dev->disk_size = nvdimm_namespace_capacity(ndns);
+	blk_dev->ndbr = to_nd_blk_region(dev->parent);
+	blk_dev->nsblk = to_nd_namespace_blk(&ndns->dev);
+	dev_set_drvdata(dev, blk_dev);
+
+	ndns->rw_bytes = nd_blk_rw_bytes;
+	if (is_nd_btt(dev))
+		rc = nvdimm_namespace_attach_btt(ndns);
+	else if (nd_btt_probe(ndns, blk_dev) == 0) {
+		/* we'll come back as btt-blk */
+		rc = -ENXIO;
+	} else
+		rc = nd_blk_attach_disk(ndns, blk_dev);
+	if (rc)
+		kfree(blk_dev);
+	return rc;
+}
+
+static void nd_blk_detach_disk(struct nd_blk_device *blk_dev)
+{
+	del_gendisk(blk_dev->disk);
+	put_disk(blk_dev->disk);
+	blk_cleanup_queue(blk_dev->queue);
+}
+
+static int nd_blk_remove(struct device *dev)
+{
+	struct nd_blk_device *blk_dev = dev_get_drvdata(dev);
+
+	if (is_nd_btt(dev))
+		nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns);
+	else
+		nd_blk_detach_disk(blk_dev);
+	kfree(blk_dev);
+
+	return 0;
+}
+
+static struct nd_device_driver nd_blk_driver = {
+	.probe = nd_blk_probe,
+	.remove = nd_blk_remove,
+	.drv = {
+		.name = "nd_blk",
+	},
+	.type = ND_DRIVER_NAMESPACE_BLK,
+};
+
+static int __init nd_blk_init(void)
+{
+	int rc;
+
+	rc = register_blkdev(0, "nd_blk");
+	if (rc < 0)
+		return rc;
+
+	nd_blk_major = rc;
+	rc = nd_driver_register(&nd_blk_driver);
+
+	if (rc < 0)
+		unregister_blkdev(nd_blk_major, "nd_blk");
+
+	return rc;
+}
+
+static void __exit nd_blk_exit(void)
+{
+	driver_unregister(&nd_blk_driver.drv);
+	unregister_blkdev(nd_blk_major, "nd_blk");
+}
+
+MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_BLK);
+module_init(nd_blk_init);
+module_exit(nd_blk_exit);

drivers/nvdimm/dimm_devs.c

@@ -209,6 +209,15 @@ struct nvdimm *to_nvdimm(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(to_nvdimm);
 
+struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr)
+{
+	struct nd_region *nd_region = &ndbr->nd_region;
+	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+
+	return nd_mapping->nvdimm;
+}
+EXPORT_SYMBOL_GPL(nd_blk_region_to_dimm);
+
 struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping)
 {
 	struct nvdimm *nvdimm = nd_mapping->nvdimm;