summaryrefslogtreecommitdiff
path: root/drivers/nvdimm/pmem.c
diff options
context:
space:
mode:
authorAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-12-15 14:52:16 -0300
committerAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-12-15 14:52:16 -0300
commit8d91c1e411f55d7ea91b1183a2e9f8088fb4d5be (patch)
treee9891aa6c295060d065adffd610c4f49ecf884f3 /drivers/nvdimm/pmem.c
parenta71852147516bc1cb5b0b3cbd13639bfd4022dc8 (diff)
Linux-libre 4.3.2-gnu
Diffstat (limited to 'drivers/nvdimm/pmem.c')
-rw-r--r--drivers/nvdimm/pmem.c247
1 files changed, 210 insertions, 37 deletions
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index b796d1bd8..0ba6a978f 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -21,18 +21,24 @@
#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;
};
@@ -44,7 +50,7 @@ static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
sector_t sector)
{
void *mem = kmap_atomic(page);
- size_t pmem_off = sector << 9;
+ phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
if (rw == READ) {
@@ -77,7 +83,7 @@ static void pmem_make_request(struct request_queue *q, struct bio *bio)
if (bio_data_dir(bio))
wmb_pmem();
- bio_endio(bio, 0);
+ bio_endio(bio);
}
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
@@ -94,19 +100,26 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
}
static long pmem_direct_access(struct block_device *bdev, sector_t sector,
- void **kaddr, unsigned long *pfn, long size)
+ void __pmem **kaddr, unsigned long *pfn)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
- size_t offset = sector << 9;
-
- if (!pmem)
- return -ENODEV;
+ resource_size_t offset = sector * 512 + pmem->data_offset;
+ resource_size_t size;
+
+ if (pmem->data_offset) {
+ /*
+ * Limit the direct_access() size to what is covered by
+ * the memmap
+ */
+ size = (pmem->size - offset) & ~ND_PFN_MASK;
+ } else
+ size = pmem->size - offset;
/* FIXME convert DAX to comprehend that this mapping has a lifetime */
- *kaddr = (void __force *) pmem->virt_addr + offset;
+ *kaddr = pmem->virt_addr + offset;
*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
- return pmem->size - offset;
+ return size;
}
static const struct block_device_operations pmem_fops = {
@@ -121,27 +134,33 @@ static struct pmem_device *pmem_alloc(struct device *dev,
{
struct pmem_device *pmem;
- pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
+ pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
if (!pmem)
return ERR_PTR(-ENOMEM);
pmem->phys_addr = res->start;
pmem->size = resource_size(res);
- if (!arch_has_pmem_api())
+ if (!arch_has_wmb_pmem())
dev_warn(dev, "unable to guarantee persistence of writes\n");
- if (!request_mem_region(pmem->phys_addr, pmem->size, dev_name(dev))) {
+ 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);
- kfree(pmem);
return ERR_PTR(-EBUSY);
}
- pmem->virt_addr = memremap_pmem(pmem->phys_addr, pmem->size);
- if (!pmem->virt_addr) {
- release_mem_region(pmem->phys_addr, pmem->size);
- kfree(pmem);
- return ERR_PTR(-ENXIO);
+ if (pmem_should_map_pages(dev)) {
+ void *addr = devm_memremap_pages(dev, res);
+
+ if (IS_ERR(addr))
+ return addr;
+ pmem->virt_addr = (void __pmem *) addr;
+ } else {
+ pmem->virt_addr = memremap_pmem(dev, pmem->phys_addr,
+ pmem->size);
+ if (!pmem->virt_addr)
+ return ERR_PTR(-ENXIO);
}
return pmem;
@@ -149,13 +168,16 @@ static struct pmem_device *pmem_alloc(struct device *dev,
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 nd_namespace_common *ndns,
- struct pmem_device *pmem)
+static int pmem_attach_disk(struct device *dev,
+ struct nd_namespace_common *ndns, struct pmem_device *pmem)
{
struct gendisk *disk;
@@ -164,6 +186,7 @@ static int pmem_attach_disk(struct nd_namespace_common *ndns,
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);
@@ -181,8 +204,8 @@ static int pmem_attach_disk(struct nd_namespace_common *ndns,
disk->queue = pmem->pmem_queue;
disk->flags = GENHD_FL_EXT_DEVT;
nvdimm_namespace_disk_name(ndns, disk->disk_name);
- disk->driverfs_dev = &ndns->dev;
- set_capacity(disk, pmem->size >> 9);
+ disk->driverfs_dev = dev;
+ set_capacity(disk, (pmem->size - pmem->data_offset) / 512);
pmem->pmem_disk = disk;
add_disk(disk);
@@ -211,11 +234,152 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns,
return 0;
}
-static void pmem_free(struct pmem_device *pmem)
+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)
{
- memunmap_pmem(pmem->virt_addr);
- release_mem_region(pmem->phys_addr, pmem->size);
- kfree(pmem);
+ 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);
+ memunmap_pmem(dev, 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)
@@ -224,7 +388,6 @@ static int nd_pmem_probe(struct device *dev)
struct nd_namespace_common *ndns;
struct nd_namespace_io *nsio;
struct pmem_device *pmem;
- int rc;
ndns = nvdimm_namespace_common_probe(dev);
if (IS_ERR(ndns))
@@ -235,18 +398,27 @@ static int nd_pmem_probe(struct device *dev)
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))
- rc = nvdimm_namespace_attach_btt(ndns);
- else if (nd_btt_probe(ndns, pmem) == 0) {
+ 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 */
- rc = -ENXIO;
- } else
- rc = pmem_attach_disk(ndns, pmem);
- if (rc)
- pmem_free(pmem);
- return rc;
+ 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)
@@ -254,10 +426,11 @@ 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(to_nd_btt(dev)->ndns);
+ nvdimm_namespace_detach_btt(pmem->ndns);
+ else if (is_nd_pfn(dev))
+ nvdimm_namespace_detach_pfn(pmem->ndns);
else
pmem_detach_disk(pmem);
- pmem_free(pmem);
return 0;
}