OpenCloudOS-Kernel/drivers/nvdimm/pmem.c

465 lines
11 KiB
C
Raw Normal View History

/*
* Persistent Memory Driver
*
* Copyright (c) 2014-2015, Intel Corporation.
* Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
* Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
*
* 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 <asm/cacheflush.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#include <linux/moduleparam.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/pmem.h>
#include <linux/nd.h>
#include "pfn.h"
#include "nd.h"
struct pmem_device {
struct request_queue *pmem_queue;
struct gendisk *pmem_disk;
struct nd_namespace_common *ndns;
/* One contiguous memory region per device */
phys_addr_t phys_addr;
/* when non-zero this device is hosting a 'pfn' instance */
phys_addr_t data_offset;
void __pmem *virt_addr;
size_t size;
};
static int pmem_major;
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);
phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
if (rw == READ) {
memcpy_from_pmem(mem + off, pmem_addr, len);
flush_dcache_page(page);
} else {
flush_dcache_page(page);
memcpy_to_pmem(pmem_addr, mem + off, len);
}
kunmap_atomic(mem);
}
static blk_qc_t 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);
if (bio_data_dir(bio))
wmb_pmem();
bio_endio(bio);
return BLK_QC_T_NONE;
}
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
struct page *page, int rw)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
if (rw & WRITE)
wmb_pmem();
page_endio(page, rw & WRITE, 0);
return 0;
}
static long pmem_direct_access(struct block_device *bdev, sector_t sector,
void __pmem **kaddr, unsigned long *pfn)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
resource_size_t offset = sector * 512 + pmem->data_offset;
*kaddr = pmem->virt_addr + offset;
*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
return pmem->size - offset;
}
static const struct block_device_operations pmem_fops = {
.owner = THIS_MODULE,
.rw_page = pmem_rw_page,
.direct_access = pmem_direct_access,
.revalidate_disk = nvdimm_revalidate_disk,
};
static struct pmem_device *pmem_alloc(struct device *dev,
struct resource *res, int id)
{
struct pmem_device *pmem;
pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
if (!pmem)
return ERR_PTR(-ENOMEM);
pmem->phys_addr = res->start;
pmem->size = resource_size(res);
x86, pmem: clarify that ARCH_HAS_PMEM_API implies PMEM mapped WB Given that a write-back (WB) mapping plus non-temporal stores is expected to be the most efficient way to access PMEM, update the definition of ARCH_HAS_PMEM_API to imply arch support for WB-mapped-PMEM. This is needed as a pre-requisite for adding PMEM to the direct map and mapping it with struct page. The above clarification for X86_64 means that memcpy_to_pmem() is permitted to use the non-temporal arch_memcpy_to_pmem() rather than needlessly fall back to default_memcpy_to_pmem() when the pcommit instruction is not available. When arch_memcpy_to_pmem() is not guaranteed to flush writes out of cache, i.e. on older X86_32 implementations where non-temporal stores may just dirty cache, ARCH_HAS_PMEM_API is simply disabled. The default fall back for persistent memory handling remains. Namely, map it with the WT (write-through) cache-type and hope for the best. arch_has_pmem_api() is updated to only indicate whether the arch provides the proper helpers to meet the minimum "writes are visible outside the cache hierarchy after memcpy_to_pmem() + wmb_pmem()". Code that cares whether wmb_pmem() actually flushes writes to pmem must now call arch_has_wmb_pmem() directly. Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> [hch: set ARCH_HAS_PMEM_API=n on x86_32] Reviewed-by: Christoph Hellwig <hch@lst.de> [toshi: x86_32 compile fixes] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-08-25 06:29:38 +08:00
if (!arch_has_wmb_pmem())
dev_warn(dev, "unable to guarantee persistence of writes\n");
if (!devm_request_mem_region(dev, pmem->phys_addr, pmem->size,
dev_name(dev))) {
dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n",
&pmem->phys_addr, pmem->size);
return ERR_PTR(-EBUSY);
}
if (pmem_should_map_pages(dev))
pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res);
else
pmem->virt_addr = (void __pmem *) devm_memremap(dev,
pmem->phys_addr, pmem->size,
ARCH_MEMREMAP_PMEM);
if (IS_ERR(pmem->virt_addr))
return (void __force *) pmem->virt_addr;
return pmem;
}
static void pmem_detach_disk(struct pmem_device *pmem)
{
if (!pmem->pmem_disk)
return;
del_gendisk(pmem->pmem_disk);
put_disk(pmem->pmem_disk);
blk_cleanup_queue(pmem->pmem_queue);
}
static int pmem_attach_disk(struct device *dev,
struct nd_namespace_common *ndns, struct pmem_device *pmem)
{
int nid = dev_to_node(dev);
struct gendisk *disk;
pmem->pmem_queue = blk_alloc_queue_node(GFP_KERNEL, nid);
if (!pmem->pmem_queue)
return -ENOMEM;
blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
blk_queue_physical_block_size(pmem->pmem_queue, PAGE_SIZE);
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_node(0, nid);
if (!disk) {
blk_cleanup_queue(pmem->pmem_queue);
return -ENOMEM;
}
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;
nd_btt: atomic sector updates BTT stands for Block Translation Table, and is a way to provide power fail sector atomicity semantics for block devices that have the ability to perform byte granularity IO. It relies on the capability of libnvdimm namespace devices to do byte aligned IO. The BTT works as a stacked blocked device, and reserves a chunk of space from the backing device for its accounting metadata. It is a bio-based driver because all IO is done synchronously, and there is no queuing or asynchronous completions at either the device or the driver level. The BTT uses 'lanes' to index into various 'on-disk' data structures, and lanes also act as a synchronization mechanism in case there are more CPUs than available lanes. We did a comparison between two lane lock strategies - first where we kept an atomic counter around that tracked which was the last lane that was used, and 'our' lane was determined by atomically incrementing that. That way, for the nr_cpus > nr_lanes case, theoretically, no CPU would be blocked waiting for a lane. The other strategy was to use the cpu number we're scheduled on to and hash it to a lane number. Theoretically, this could block an IO that could've otherwise run using a different, free lane. But some fio workloads showed that the direct cpu -> lane hash performed faster than tracking 'last lane' - my reasoning is the cache thrash caused by moving the atomic variable made that approach slower than simply waiting out the in-progress IO. This supports the conclusion that the driver can be a very simple bio-based one that does synchronous IOs instead of queuing. 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> Cc: Neil Brown <neilb@suse.de> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg KH <gregkh@linuxfoundation.org> [jmoyer: fix nmi watchdog timeout in btt_map_init] [jmoyer: move btt initialization to module load path] [jmoyer: fix memory leak in the btt initialization path] [jmoyer: Don't overwrite corrupted arenas] Signed-off-by: Vishal Verma <vishal.l.verma@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-06-25 16:20:32 +08:00
nvdimm_namespace_disk_name(ndns, disk->disk_name);
disk->driverfs_dev = dev;
set_capacity(disk, (pmem->size - pmem->data_offset) / 512);
pmem->pmem_disk = disk;
add_disk(disk);
revalidate_disk(disk);
return 0;
}
static int pmem_rw_bytes(struct nd_namespace_common *ndns,
resource_size_t offset, void *buf, size_t size, int rw)
{
struct pmem_device *pmem = dev_get_drvdata(ndns->claim);
if (unlikely(offset + size > pmem->size)) {
dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
return -EFAULT;
}
if (rw == READ)
memcpy_from_pmem(buf, pmem->virt_addr + offset, size);
else {
memcpy_to_pmem(pmem->virt_addr + offset, buf, size);
wmb_pmem();
}
return 0;
}
static int nd_pfn_init(struct nd_pfn *nd_pfn)
{
struct nd_pfn_sb *pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
struct pmem_device *pmem = dev_get_drvdata(&nd_pfn->dev);
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_region *nd_region;
unsigned long npfns;
phys_addr_t offset;
u64 checksum;
int rc;
if (!pfn_sb)
return -ENOMEM;
nd_pfn->pfn_sb = pfn_sb;
rc = nd_pfn_validate(nd_pfn);
if (rc == 0 || rc == -EBUSY)
return rc;
/* section alignment for simple hotplug */
if (nvdimm_namespace_capacity(ndns) < ND_PFN_ALIGN
|| pmem->phys_addr & ND_PFN_MASK)
return -ENODEV;
nd_region = to_nd_region(nd_pfn->dev.parent);
if (nd_region->ro) {
dev_info(&nd_pfn->dev,
"%s is read-only, unable to init metadata\n",
dev_name(&nd_region->dev));
goto err;
}
memset(pfn_sb, 0, sizeof(*pfn_sb));
npfns = (pmem->size - SZ_8K) / SZ_4K;
/*
* Note, we use 64 here for the standard size of struct page,
* debugging options may cause it to be larger in which case the
* implementation will limit the pfns advertised through
* ->direct_access() to those that are included in the memmap.
*/
if (nd_pfn->mode == PFN_MODE_PMEM)
offset = ALIGN(SZ_8K + 64 * npfns, PMD_SIZE);
else if (nd_pfn->mode == PFN_MODE_RAM)
offset = SZ_8K;
else
goto err;
npfns = (pmem->size - offset) / SZ_4K;
pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
pfn_sb->dataoff = cpu_to_le64(offset);
pfn_sb->npfns = cpu_to_le64(npfns);
memcpy(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN);
memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
pfn_sb->version_major = cpu_to_le16(1);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
rc = nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
if (rc)
goto err;
return 0;
err:
nd_pfn->pfn_sb = NULL;
kfree(pfn_sb);
return -ENXIO;
}
static int nvdimm_namespace_detach_pfn(struct nd_namespace_common *ndns)
{
struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
struct pmem_device *pmem;
/* free pmem disk */
pmem = dev_get_drvdata(&nd_pfn->dev);
pmem_detach_disk(pmem);
/* release nd_pfn resources */
kfree(nd_pfn->pfn_sb);
nd_pfn->pfn_sb = NULL;
return 0;
}
static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
struct device *dev = &nd_pfn->dev;
struct vmem_altmap *altmap;
struct nd_region *nd_region;
struct nd_pfn_sb *pfn_sb;
struct pmem_device *pmem;
phys_addr_t offset;
int rc;
if (!nd_pfn->uuid || !nd_pfn->ndns)
return -ENODEV;
nd_region = to_nd_region(dev->parent);
rc = nd_pfn_init(nd_pfn);
if (rc)
return rc;
if (PAGE_SIZE != SZ_4K) {
dev_err(dev, "only supported on systems with 4K PAGE_SIZE\n");
return -ENXIO;
}
if (nsio->res.start & ND_PFN_MASK) {
dev_err(dev, "%s not memory hotplug section aligned\n",
dev_name(&ndns->dev));
return -ENXIO;
}
pfn_sb = nd_pfn->pfn_sb;
offset = le64_to_cpu(pfn_sb->dataoff);
nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
if (nd_pfn->mode == PFN_MODE_RAM) {
if (offset != SZ_8K)
return -EINVAL;
nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
altmap = NULL;
} else {
rc = -ENXIO;
goto err;
}
/* establish pfn range for lookup, and switch to direct map */
pmem = dev_get_drvdata(dev);
devm_memunmap(dev, (void __force *) pmem->virt_addr);
pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res);
if (IS_ERR(pmem->virt_addr)) {
rc = PTR_ERR(pmem->virt_addr);
goto err;
}
/* attach pmem disk in "pfn-mode" */
pmem->data_offset = offset;
rc = pmem_attach_disk(dev, ndns, pmem);
if (rc)
goto err;
return rc;
err:
nvdimm_namespace_detach_pfn(ndns);
return rc;
}
static int nd_pmem_probe(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_namespace_common *ndns;
struct nd_namespace_io *nsio;
struct pmem_device *pmem;
ndns = nvdimm_namespace_common_probe(dev);
if (IS_ERR(ndns))
return PTR_ERR(ndns);
nsio = to_nd_namespace_io(&ndns->dev);
pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
if (IS_ERR(pmem))
return PTR_ERR(pmem);
pmem->ndns = ndns;
dev_set_drvdata(dev, pmem);
ndns->rw_bytes = pmem_rw_bytes;
if (is_nd_btt(dev))
return nvdimm_namespace_attach_btt(ndns);
if (is_nd_pfn(dev))
return nvdimm_namespace_attach_pfn(ndns);
if (nd_btt_probe(ndns, pmem) == 0) {
/* we'll come back as btt-pmem */
return -ENXIO;
}
if (nd_pfn_probe(ndns, pmem) == 0) {
/* we'll come back as pfn-pmem */
return -ENXIO;
}
return pmem_attach_disk(dev, ndns, pmem);
}
static int nd_pmem_remove(struct device *dev)
{
struct pmem_device *pmem = dev_get_drvdata(dev);
if (is_nd_btt(dev))
nvdimm_namespace_detach_btt(pmem->ndns);
else if (is_nd_pfn(dev))
nvdimm_namespace_detach_pfn(pmem->ndns);
else
pmem_detach_disk(pmem);
return 0;
}
MODULE_ALIAS("pmem");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
static struct nd_device_driver nd_pmem_driver = {
.probe = nd_pmem_probe,
.remove = nd_pmem_remove,
.drv = {
.name = "nd_pmem",
},
.type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
};
static int __init pmem_init(void)
{
int error;
pmem_major = register_blkdev(0, "pmem");
if (pmem_major < 0)
return pmem_major;
error = nd_driver_register(&nd_pmem_driver);
if (error) {
unregister_blkdev(pmem_major, "pmem");
return error;
}
return 0;
}
module_init(pmem_init);
static void pmem_exit(void)
{
driver_unregister(&nd_pmem_driver.drv);
unregister_blkdev(pmem_major, "pmem");
}
module_exit(pmem_exit);
MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
MODULE_LICENSE("GPL v2");