aboutsummaryrefslogtreecommitdiff
path: root/drivers/nvdimm
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvdimm')
-rw-r--r--drivers/nvdimm/btt.c12
-rw-r--r--drivers/nvdimm/bus.c4
-rw-r--r--drivers/nvdimm/dimm.c24
-rw-r--r--drivers/nvdimm/dimm_devs.c31
-rw-r--r--drivers/nvdimm/namespace_devs.c29
-rw-r--r--drivers/nvdimm/nd-core.h8
-rw-r--r--drivers/nvdimm/nd.h8
-rw-r--r--drivers/nvdimm/pmem.c46
-rw-r--r--drivers/nvdimm/pmem.h13
-rw-r--r--drivers/nvdimm/region_devs.c40
10 files changed, 189 insertions, 26 deletions
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 85de8053aa34..0360c015f658 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
struct page *page, unsigned int len, unsigned int off,
- bool is_write, sector_t sector)
+ unsigned int op, sector_t sector)
{
int ret;
- if (!is_write) {
+ if (!op_is_write(op)) {
ret = btt_read_pg(btt, bip, page, off, sector, len);
flush_dcache_page(page);
} else {
@@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
}
err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
- op_is_write(bio_op(bio)), iter.bi_sector);
+ bio_op(bio), iter.bi_sector);
if (err) {
dev_err(&btt->nd_btt->dev,
"io error in %s sector %lld, len %d,\n",
@@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
}
static int btt_rw_page(struct block_device *bdev, sector_t sector,
- struct page *page, bool is_write)
+ struct page *page, unsigned int op)
{
struct btt *btt = bdev->bd_disk->private_data;
int rc;
unsigned int len;
len = hpage_nr_pages(page) * PAGE_SIZE;
- rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
+ rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
if (rc == 0)
- page_endio(page, is_write, 0);
+ page_endio(page, op_is_write(op), 0);
return rc;
}
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 27902a8799b1..8aae6dcc839f 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -812,9 +812,9 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
* overshoots the remainder by 4 bytes, assume it was
* including 'status'.
*/
- if (out_field[1] - 8 == remainder)
+ if (out_field[1] - 4 == remainder)
return remainder;
- return out_field[1] - 4;
+ return out_field[1] - 8;
} else if (cmd == ND_CMD_CALL) {
struct nd_cmd_pkg *pkg = (struct nd_cmd_pkg *) in_field;
diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c
index 233907889f96..6c8fb7590838 100644
--- a/drivers/nvdimm/dimm.c
+++ b/drivers/nvdimm/dimm.c
@@ -34,6 +34,9 @@ static int nvdimm_probe(struct device *dev)
return rc;
}
+ /* reset locked, to be validated below... */
+ nvdimm_clear_locked(dev);
+
ndd = kzalloc(sizeof(*ndd), GFP_KERNEL);
if (!ndd)
return -ENOMEM;
@@ -48,12 +51,30 @@ static int nvdimm_probe(struct device *dev)
get_device(dev);
kref_init(&ndd->kref);
+ /*
+ * EACCES failures reading the namespace label-area-properties
+ * are interpreted as the DIMM capacity being locked but the
+ * namespace labels themselves being accessible.
+ */
rc = nvdimm_init_nsarea(ndd);
- if (rc == -EACCES)
+ if (rc == -EACCES) {
+ /*
+ * See nvdimm_namespace_common_probe() where we fail to
+ * allow namespaces to probe while the DIMM is locked,
+ * but we do allow for namespace enumeration.
+ */
nvdimm_set_locked(dev);
+ rc = 0;
+ }
if (rc)
goto err;
+ /*
+ * EACCES failures reading the namespace label-data are
+ * interpreted as the label area being locked in addition to the
+ * DIMM capacity. We fail the dimm probe to prevent regions from
+ * attempting to parse the label area.
+ */
rc = nvdimm_init_config_data(ndd);
if (rc == -EACCES)
nvdimm_set_locked(dev);
@@ -72,7 +93,6 @@ static int nvdimm_probe(struct device *dev)
if (rc == 0)
nvdimm_set_aliasing(dev);
}
- nvdimm_clear_locked(dev);
nvdimm_bus_unlock(dev);
if (rc)
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index 8d348b22ba45..863cabc35215 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -537,6 +537,37 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
}
/**
+ * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ * contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+ struct nd_mapping *nd_mapping)
+{
+ struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+ struct nvdimm_bus *nvdimm_bus;
+ resource_size_t max = 0;
+ struct resource *res;
+
+ /* if a dimm is disabled the available capacity is zero */
+ if (!ndd)
+ return 0;
+
+ nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
+ if (__reserve_free_pmem(&nd_region->dev, nd_mapping->nvdimm))
+ return 0;
+ for_each_dpa_resource(ndd, res) {
+ if (strcmp(res->name, "pmem-reserve") != 0)
+ continue;
+ if (resource_size(res) > max)
+ max = resource_size(res);
+ }
+ release_free_pmem(nvdimm_bus, nd_mapping);
+ return max;
+}
+
+/**
* nd_pmem_available_dpa - for the given dimm+region account unallocated dpa
* @nd_mapping: container of dpa-resource-root + labels
* @nd_region: constrain available space check to this reference region
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 28afdd668905..4a4266250c28 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -799,7 +799,7 @@ static int merge_dpa(struct nd_region *nd_region,
return 0;
}
-static int __reserve_free_pmem(struct device *dev, void *data)
+int __reserve_free_pmem(struct device *dev, void *data)
{
struct nvdimm *nvdimm = data;
struct nd_region *nd_region;
@@ -836,7 +836,7 @@ static int __reserve_free_pmem(struct device *dev, void *data)
return 0;
}
-static void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
+void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
struct nd_mapping *nd_mapping)
{
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
@@ -1032,7 +1032,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
allocated += nvdimm_allocated_dpa(ndd, &label_id);
}
- available = nd_region_available_dpa(nd_region);
+ available = nd_region_allocatable_dpa(nd_region);
if (val > available + allocated)
return -ENOSPC;
@@ -1144,6 +1144,26 @@ resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
}
EXPORT_SYMBOL(nvdimm_namespace_capacity);
+bool nvdimm_namespace_locked(struct nd_namespace_common *ndns)
+{
+ int i;
+ bool locked = false;
+ struct device *dev = &ndns->dev;
+ struct nd_region *nd_region = to_nd_region(dev->parent);
+
+ for (i = 0; i < nd_region->ndr_mappings; i++) {
+ struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+ struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+ if (test_bit(NDD_LOCKED, &nvdimm->flags)) {
+ dev_dbg(dev, "%s locked\n", nvdimm_name(nvdimm));
+ locked = true;
+ }
+ }
+ return locked;
+}
+EXPORT_SYMBOL(nvdimm_namespace_locked);
+
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -1695,6 +1715,9 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
}
}
+ if (nvdimm_namespace_locked(ndns))
+ return ERR_PTR(-EACCES);
+
size = nvdimm_namespace_capacity(ndns);
if (size < ND_MIN_NAMESPACE_SIZE) {
dev_dbg(&ndns->dev, "%pa, too small must be at least %#x\n",
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 79274ead54fb..ac68072fb8cd 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -100,6 +100,14 @@ struct nd_region;
struct nvdimm_drvdata;
struct nd_mapping;
void nd_mapping_free_labels(struct nd_mapping *nd_mapping);
+
+int __reserve_free_pmem(struct device *dev, void *data);
+void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
+ struct nd_mapping *nd_mapping);
+
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+ struct nd_mapping *nd_mapping);
+resource_size_t nd_region_allocatable_dpa(struct nd_region *nd_region);
resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, resource_size_t *overlap);
resource_size_t nd_blk_available_dpa(struct nd_region *nd_region);
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 32e0364b48b9..98317e7ce5b5 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -357,6 +357,7 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd,
struct nd_label_id *label_id, resource_size_t start,
resource_size_t n);
resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns);
+bool nvdimm_namespace_locked(struct nd_namespace_common *ndns);
struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev);
int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns);
int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt);
@@ -396,16 +397,15 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
return false;
*start = jiffies;
- generic_start_io_acct(disk->queue, bio_data_dir(bio),
- bio_sectors(bio), &disk->part0);
+ generic_start_io_acct(disk->queue, bio_op(bio), bio_sectors(bio),
+ &disk->part0);
return true;
}
static inline void nd_iostat_end(struct bio *bio, unsigned long start)
{
struct gendisk *disk = bio->bi_disk;
- generic_end_io_acct(disk->queue, bio_data_dir(bio), &disk->part0,
- start);
+ generic_end_io_acct(disk->queue, bio_op(bio), &disk->part0, start);
}
static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector,
unsigned int len)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8b1fd7f1a224..6071e2942053 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -20,6 +20,7 @@
#include <linux/hdreg.h>
#include <linux/init.h>
#include <linux/platform_device.h>
+#include <linux/set_memory.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/badblocks.h>
@@ -51,6 +52,30 @@ static struct nd_region *to_region(struct pmem_device *pmem)
return to_nd_region(to_dev(pmem)->parent);
}
+static void hwpoison_clear(struct pmem_device *pmem,
+ phys_addr_t phys, unsigned int len)
+{
+ unsigned long pfn_start, pfn_end, pfn;
+
+ /* only pmem in the linear map supports HWPoison */
+ if (is_vmalloc_addr(pmem->virt_addr))
+ return;
+
+ pfn_start = PHYS_PFN(phys);
+ pfn_end = pfn_start + PHYS_PFN(len);
+ for (pfn = pfn_start; pfn < pfn_end; pfn++) {
+ struct page *page = pfn_to_page(pfn);
+
+ /*
+ * Note, no need to hold a get_dev_pagemap() reference
+ * here since we're in the driver I/O path and
+ * outstanding I/O requests pin the dev_pagemap.
+ */
+ if (test_and_clear_pmem_poison(page))
+ clear_mce_nospec(pfn);
+ }
+}
+
static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
phys_addr_t offset, unsigned int len)
{
@@ -65,6 +90,7 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
if (cleared < len)
rc = BLK_STS_IOERR;
if (cleared > 0 && cleared / 512) {
+ hwpoison_clear(pmem, pmem->phys_addr + offset, cleared);
cleared /= 512;
dev_dbg(dev, "%#llx clear %ld sector%s\n",
(unsigned long long) sector, cleared,
@@ -120,7 +146,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
}
static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
- unsigned int len, unsigned int off, bool is_write,
+ unsigned int len, unsigned int off, unsigned int op,
sector_t sector)
{
blk_status_t rc = BLK_STS_OK;
@@ -131,7 +157,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
bad_pmem = true;
- if (!is_write) {
+ if (!op_is_write(op)) {
if (unlikely(bad_pmem))
rc = BLK_STS_IOERR;
else {
@@ -180,8 +206,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
do_acct = nd_iostat_start(bio, &start);
bio_for_each_segment(bvec, bio, iter) {
rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
- bvec.bv_offset, op_is_write(bio_op(bio)),
- iter.bi_sector);
+ bvec.bv_offset, bio_op(bio), iter.bi_sector);
if (rc) {
bio->bi_status = rc;
break;
@@ -198,13 +223,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
}
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
- struct page *page, bool is_write)
+ struct page *page, unsigned int op)
{
struct pmem_device *pmem = bdev->bd_queue->queuedata;
blk_status_t rc;
rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
- 0, is_write, sector);
+ 0, op, sector);
/*
* The ->rw_page interface is subtle and tricky. The core
@@ -213,7 +238,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
* caused by double completion.
*/
if (rc == 0)
- page_endio(page, is_write, 0);
+ page_endio(page, op_is_write(op), 0);
return blk_status_to_errno(rc);
}
@@ -227,8 +252,11 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512,
PFN_PHYS(nr_pages))))
return -EIO;
- *kaddr = pmem->virt_addr + offset;
- *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
+
+ if (kaddr)
+ *kaddr = pmem->virt_addr + offset;
+ if (pfn)
+ *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
/*
* If badblocks are present, limit known good range to the
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index a64ebc78b5df..59cfe13ea8a8 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NVDIMM_PMEM_H__
#define __NVDIMM_PMEM_H__
+#include <linux/page-flags.h>
#include <linux/badblocks.h>
#include <linux/types.h>
#include <linux/pfn_t.h>
@@ -27,4 +28,16 @@ struct pmem_device {
long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
long nr_pages, void **kaddr, pfn_t *pfn);
+
+#ifdef CONFIG_MEMORY_FAILURE
+static inline bool test_and_clear_pmem_poison(struct page *page)
+{
+ return TestClearPageHWPoison(page);
+}
+#else
+static inline bool test_and_clear_pmem_poison(struct page *page)
+{
+ return false;
+}
+#endif
#endif /* __NVDIMM_PMEM_H__ */
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index ec3543b83330..fa37afcd43ff 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -389,6 +389,30 @@ resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
return available;
}
+resource_size_t nd_region_allocatable_dpa(struct nd_region *nd_region)
+{
+ resource_size_t available = 0;
+ int i;
+
+ if (is_memory(&nd_region->dev))
+ available = PHYS_ADDR_MAX;
+
+ WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+ for (i = 0; i < nd_region->ndr_mappings; i++) {
+ struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+
+ if (is_memory(&nd_region->dev))
+ available = min(available,
+ nd_pmem_max_contiguous_dpa(nd_region,
+ nd_mapping));
+ else if (is_nd_blk(&nd_region->dev))
+ available += nd_blk_available_dpa(nd_region);
+ }
+ if (is_memory(&nd_region->dev))
+ return available * nd_region->ndr_mappings;
+ return available;
+}
+
static ssize_t available_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -410,6 +434,21 @@ static ssize_t available_size_show(struct device *dev,
}
static DEVICE_ATTR_RO(available_size);
+static ssize_t max_available_extent_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_region *nd_region = to_nd_region(dev);
+ unsigned long long available = 0;
+
+ nvdimm_bus_lock(dev);
+ wait_nvdimm_bus_probe_idle(dev);
+ available = nd_region_allocatable_dpa(nd_region);
+ nvdimm_bus_unlock(dev);
+
+ return sprintf(buf, "%llu\n", available);
+}
+static DEVICE_ATTR_RO(max_available_extent);
+
static ssize_t init_namespaces_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -561,6 +600,7 @@ static struct attribute *nd_region_attributes[] = {
&dev_attr_read_only.attr,
&dev_attr_set_cookie.attr,
&dev_attr_available_size.attr,
+ &dev_attr_max_available_extent.attr,
&dev_attr_namespace_seed.attr,
&dev_attr_init_namespaces.attr,
&dev_attr_badblocks.attr,
Powered by cgit, Gruvboxed by Blaster4385.