[PATCH v2] pmem: Initial version of persistent memory driver

From: Boaz Harrosh
Date: Tue Sep 09 2014 - 12:23:27 EST


From: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>

PMEM is a new driver that presents a reserved range of memory as a
block device. This is useful for developing with NV-DIMMs, and
can be used with volatile memory as a development platform.

[boaz]
SQUASHME: pmem: Remove unused #include headers
SQUASHME: pmem: Request from fdisk 4k alignment
SQUASHME: pmem: Let each device manage private memory region
SQUASHME: pmem: Support of multiple memory regions

The API to pmem module a single string parameter named "map"
of the form:
map=mapS[,mapS...]

where mapS=nn[KMG]$ss[KMG],
or mapS=nn[KMG]@ss[KMG],

nn=size, ss=offset

Just like the Kernel command line map && memmap parameters,
so anything you did at grub just copy/paste to here.

The "@" form is exactly the same as the "$" form only that
at bash prompt we need to escape the "$" with \$ so also
support the '@' char for convenience.

For each specified mapS there will be a device created.

[This is the accumulated version of the driver developed by
multiple programmers. To see the real history of these
patches see:
git://git.open-osd.org/pmem.git
https://github.com/01org/prd
This patch is based on:
[673302b] pmem: KISS, remove register_blkdev
]

TODO: Add Documentation/blockdev/pmem.txt

Signed-off-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Signed-off-by: Boaz Harrosh <boaz@xxxxxxxxxxxxx>
---
MAINTAINERS | 6 +
drivers/block/Kconfig | 13 ++
drivers/block/Makefile | 1 +
drivers/block/pmem.c | 385 +++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 405 insertions(+)
create mode 100644 drivers/block/pmem.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 5e7866a..2724ede 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7504,6 +7504,12 @@ S: Maintained
F: Documentation/blockdev/ramdisk.txt
F: drivers/block/brd.c

+PERSISTENT MEMORY DRIVER
+M: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
+L: linux-nvdimm@xxxxxxxxxxxx
+S: Supported
+F: drivers/block/pmem.c
+
RANDOM NUMBER DRIVER
M: "Theodore Ts'o" <tytso@xxxxxxx>
S: Maintained
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 014a1cf..5da8cbf 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -403,6 +403,19 @@ config BLK_DEV_XIP
will prevent RAM block device backing store memory from being
allocated from highmem (only a problem for highmem systems).

+config BLK_DEV_PMEM
+ tristate "Persistent memory block device support"
+ help
+ Saying Y here will allow you to use a contiguous range of reserved
+ memory as one or more block devices. Memory for PMEM should be
+ reserved using the "memmap" kernel parameter.
+
+ To compile this driver as a module, choose M here: the module will be
+ called pmem.
+
+ Most normal users won't need this functionality, and can thus say N
+ here.
+
config CDROM_PKTCDVD
tristate "Packet writing on CD/DVD media"
depends on !UML
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 02b688d..9cc6c18 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_PS3_VRAM) += ps3vram.o
obj-$(CONFIG_ATARI_FLOPPY) += ataflop.o
obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o
obj-$(CONFIG_BLK_DEV_RAM) += brd.o
+obj-$(CONFIG_BLK_DEV_PMEM) += pmem.o
obj-$(CONFIG_BLK_DEV_LOOP) += loop.o
obj-$(CONFIG_BLK_CPQ_DA) += cpqarray.o
obj-$(CONFIG_BLK_CPQ_CISS_DA) += cciss.o
diff --git a/drivers/block/pmem.c b/drivers/block/pmem.c
new file mode 100644
index 0000000..0fcda58
--- /dev/null
+++ b/drivers/block/pmem.c
@@ -0,0 +1,385 @@
+/*
+ * Persistent Memory 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.
+ *
+ * This driver is heavily based on drivers/block/brd.c.
+ * Copyright (C) 2007 Nick Piggin
+ * Copyright (C) 2007 Novell Inc.
+ */
+
+#include <linux/blkdev.h>
+#include <linux/hdreg.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+
+#define SECTOR_SHIFT 9
+#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
+#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT)
+
+struct pmem_device {
+ struct request_queue *pmem_queue;
+ struct gendisk *pmem_disk;
+ struct list_head pmem_list;
+
+ /* One contiguous memory region per device */
+ phys_addr_t phys_addr;
+ void *virt_addr;
+ size_t size;
+};
+
+/*
+ * direct translation from (pmem,sector) => void*
+ * We do not require that sector be page aligned.
+ * The return value will point to the beginning of the page containing the
+ * given sector, not to the sector itself.
+ */
+static void *pmem_lookup_pg_addr(struct pmem_device *pmem, sector_t sector)
+{
+ size_t page_offset = sector >> PAGE_SECTORS_SHIFT;
+ size_t offset = page_offset << PAGE_SHIFT;
+
+ BUG_ON(offset >= pmem->size);
+ return pmem->virt_addr + offset;
+}
+
+/*
+ * sector is not required to be page aligned.
+ * n is at most a single page, but could be less.
+ */
+static void copy_to_pmem(struct pmem_device *pmem, const void *src,
+ sector_t sector, size_t n)
+{
+ void *dst;
+ unsigned int offset = (sector & (PAGE_SECTORS - 1)) << SECTOR_SHIFT;
+ size_t copy;
+
+ BUG_ON(n > PAGE_SIZE);
+
+ copy = min_t(size_t, n, PAGE_SIZE - offset);
+ dst = pmem_lookup_pg_addr(pmem, sector);
+ memcpy(dst + offset, src, copy);
+
+ if (copy < n) {
+ src += copy;
+ sector += copy >> SECTOR_SHIFT;
+ copy = n - copy;
+ dst = pmem_lookup_pg_addr(pmem, sector);
+ memcpy(dst, src, copy);
+ }
+}
+
+/*
+ * sector is not required to be page aligned.
+ * n is at most a single page, but could be less.
+ */
+static void copy_from_pmem(void *dst, struct pmem_device *pmem,
+ sector_t sector, size_t n)
+{
+ void *src;
+ unsigned int offset = (sector & (PAGE_SECTORS - 1)) << SECTOR_SHIFT;
+ size_t copy;
+
+ BUG_ON(n > PAGE_SIZE);
+
+ copy = min_t(size_t, n, PAGE_SIZE - offset);
+ src = pmem_lookup_pg_addr(pmem, sector);
+
+ memcpy(dst, src + offset, copy);
+
+ if (copy < n) {
+ dst += copy;
+ sector += copy >> SECTOR_SHIFT;
+ copy = n - copy;
+ src = pmem_lookup_pg_addr(pmem, sector);
+ memcpy(dst, src, copy);
+ }
+}
+
+static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
+ unsigned int len, unsigned int off, int rw,
+ sector_t sector)
+{
+ void *mem = kmap_atomic(page);
+
+ if (rw == READ) {
+ copy_from_pmem(mem + off, pmem, sector, len);
+ flush_dcache_page(page);
+ } else {
+ /*
+ * FIXME: Need more involved flushing to ensure that writes to
+ * NVDIMMs are actually durable before returning.
+ */
+ flush_dcache_page(page);
+ copy_to_pmem(pmem, mem + off, sector, len);
+ }
+
+ kunmap_atomic(mem);
+}
+
+static void pmem_make_request(struct request_queue *q, struct bio *bio)
+{
+ struct block_device *bdev = bio->bi_bdev;
+ struct pmem_device *pmem = bdev->bd_disk->private_data;
+ int rw;
+ struct bio_vec bvec;
+ sector_t sector;
+ struct bvec_iter iter;
+ int err = 0;
+
+ sector = bio->bi_iter.bi_sector;
+ if (bio_end_sector(bio) > get_capacity(bdev->bd_disk)) {
+ err = -EIO;
+ goto out;
+ }
+
+ BUG_ON(bio->bi_rw & REQ_DISCARD);
+
+ rw = bio_rw(bio);
+ if (rw == READA)
+ rw = READ;
+
+ bio_for_each_segment(bvec, bio, iter) {
+ unsigned int len = bvec.bv_len;
+
+ BUG_ON(len > PAGE_SIZE);
+ pmem_do_bvec(pmem, bvec.bv_page, len,
+ bvec.bv_offset, rw, sector);
+ sector += len >> SECTOR_SHIFT;
+ }
+
+out:
+ bio_endio(bio, err);
+}
+
+static const struct block_device_operations pmem_fops = {
+ .owner = THIS_MODULE,
+};
+
+/* Kernel module stuff */
+static char *map;
+module_param(map, charp, S_IRUGO);
+MODULE_PARM_DESC(map,
+ "pmem device mapping: map=mapS[,mapS...] where:\n"
+ "mapS=nn[KMG]$ss[KMG] or mapS=nn[KMG]@ss[KMG], nn=size, ss=offset.");
+
+static LIST_HEAD(pmem_devices);
+static int pmem_major;
+
+/* pmem->phys_addr and pmem->size need to be set.
+ * Will then set virt_addr if successful.
+ */
+int pmem_mapmem(struct pmem_device *pmem)
+{
+ struct resource *res_mem;
+ int err;
+
+ res_mem = request_mem_region_exclusive(pmem->phys_addr, pmem->size,
+ "pmem");
+ if (!res_mem) {
+ pr_warn("pmem: request_mem_region_exclusive phys=0x%llx size=0x%zx failed\n",
+ pmem->phys_addr, pmem->size);
+ return -EINVAL;
+ }
+
+ pmem->virt_addr = ioremap_cache(pmem->phys_addr, pmem->size);
+ if (unlikely(!pmem->virt_addr)) {
+ err = -ENXIO;
+ goto out_release;
+ }
+ return 0;
+
+out_release:
+ release_mem_region(pmem->phys_addr, pmem->size);
+ return err;
+}
+
+void pmem_unmapmem(struct pmem_device *pmem)
+{
+ if (unlikely(!pmem->virt_addr))
+ return;
+
+ iounmap(pmem->virt_addr);
+ release_mem_region(pmem->phys_addr, pmem->size);
+ pmem->virt_addr = NULL;
+}
+
+static struct pmem_device *pmem_alloc(phys_addr_t phys_addr, size_t disk_size,
+ int i)
+{
+ struct pmem_device *pmem;
+ struct gendisk *disk;
+ int err;
+
+ if (unlikely((phys_addr & ~PAGE_MASK) || (disk_size & ~PAGE_MASK))) {
+ pr_err("phys_addr=0x%llx disk_size=0x%zx must be 4k aligned\n",
+ phys_addr, disk_size);
+ err = -EINVAL;
+ goto out;
+ }
+
+ pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
+ if (unlikely(!pmem)) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ pmem->phys_addr = phys_addr;
+ pmem->size = disk_size;
+
+ err = pmem_mapmem(pmem);
+ if (unlikely(err))
+ goto out_free_dev;
+
+ pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL);
+ if (unlikely(!pmem->pmem_queue)) {
+ err = -ENOMEM;
+ goto out_unmap;
+ }
+
+ blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
+ blk_queue_max_hw_sectors(pmem->pmem_queue, 1024);
+ blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
+
+ /* This is so fdisk will align partitions on 4k, because of
+ * direct_access API needing 4k alignment, returning a PFN
+ */
+ blk_queue_physical_block_size(pmem->pmem_queue, PAGE_SIZE);
+ pmem->pmem_queue->limits.io_min = 512; /* Don't use the accessor */
+
+ disk = alloc_disk(0);
+ if (unlikely(!disk)) {
+ err = -ENOMEM;
+ goto out_free_queue;
+ }
+
+ disk->major = pmem_major;
+ disk->first_minor = 0;
+ disk->fops = &pmem_fops;
+ disk->private_data = pmem;
+ disk->queue = pmem->pmem_queue;
+ disk->flags = GENHD_FL_EXT_DEVT;
+ sprintf(disk->disk_name, "pmem%d", i);
+ set_capacity(disk, disk_size >> SECTOR_SHIFT);
+ pmem->pmem_disk = disk;
+
+ return pmem;
+
+out_free_queue:
+ blk_cleanup_queue(pmem->pmem_queue);
+out_unmap:
+ pmem_unmapmem(pmem);
+out_free_dev:
+ kfree(pmem);
+out:
+ return ERR_PTR(err);
+}
+
+static void pmem_free(struct pmem_device *pmem)
+{
+ put_disk(pmem->pmem_disk);
+ blk_cleanup_queue(pmem->pmem_queue);
+ pmem_unmapmem(pmem);
+ kfree(pmem);
+}
+
+static void pmem_del_one(struct pmem_device *pmem)
+{
+ list_del(&pmem->pmem_list);
+ del_gendisk(pmem->pmem_disk);
+ pmem_free(pmem);
+}
+
+static int pmem_parse_map_one(char *map, phys_addr_t *start, size_t *size)
+{
+ char *p = map;
+
+ *size = (size_t)memparse(p, &p);
+ if ((p == map) || ((*p != '$') && (*p != '@')))
+ return -EINVAL;
+
+ if (!*(++p))
+ return -EINVAL;
+
+ *start = (phys_addr_t)memparse(p, &p);
+
+ return *p == '\0' ? 0 : -EINVAL;
+}
+
+static int __init pmem_init(void)
+{
+ int result, i;
+ struct pmem_device *pmem, *next;
+ char *p, *pmem_map = map;
+
+ if (!pmem_map) {
+ pr_err("pmem: must specify map=nn@ss parameter.\n");
+ return -EINVAL;
+ }
+
+ result = register_blkdev(0, "pmem");
+ if (result < 0)
+ return -EIO;
+ else
+ pmem_major = result;
+
+ i = 0;
+ while ((p = strsep(&pmem_map, ",")) != NULL) {
+ phys_addr_t phys_addr;
+ size_t disk_size;
+
+ if (!*p)
+ continue;
+ result = pmem_parse_map_one(p, &phys_addr, &disk_size);
+ if (result)
+ goto out_free;
+ pmem = pmem_alloc(phys_addr, disk_size, i);
+ if (IS_ERR(pmem)) {
+ result = PTR_ERR(pmem);
+ goto out_free;
+ }
+ list_add_tail(&pmem->pmem_list, &pmem_devices);
+ ++i;
+ }
+
+ list_for_each_entry(pmem, &pmem_devices, pmem_list)
+ add_disk(pmem->pmem_disk);
+
+ pr_info("pmem: module loaded\n");
+ return 0;
+
+out_free:
+ list_for_each_entry_safe(pmem, next, &pmem_devices, pmem_list) {
+ list_del(&pmem->pmem_list);
+ pmem_free(pmem);
+ }
+ unregister_blkdev(pmem_major, "pmem");
+
+ return result;
+}
+
+static void __exit pmem_exit(void)
+{
+ struct pmem_device *pmem, *next;
+
+ list_for_each_entry_safe(pmem, next, &pmem_devices, pmem_list)
+ pmem_del_one(pmem);
+
+ unregister_blkdev(pmem_major, "pmem");
+ pr_info("pmem: module unloaded\n");
+}
+
+MODULE_AUTHOR("Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>");
+MODULE_LICENSE("GPL");
+module_init(pmem_init);
+module_exit(pmem_exit);
--
1.9.3


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