Merge tag 'libnvdimm-for-4.19_misc' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dave Jiang:
 "Collection of misc libnvdimm patches for 4.19 submission:

   - Adding support to read locked nvdimm capacity.

   - Change test code to make DSM failure code injection an override.

   - Add support for calculate maximum contiguous area for namespace.

   - Add support for queueing a short ARS when there is on going ARS for
     nvdimm.

   - Allow NULL to be passed in to ->direct_access() for kaddr and pfn
     params.

   - Improve smart injection support for nvdimm emulation testing.

   - Fix test code that supports for emulating controller temperature.

   - Fix hang on error before devm_memremap_pages()

   - Fix a bug that causes user memory corruption when data returned to
     user for ars_status.

   - Maintainer updates for Ross Zwisler emails and adding Jan Kara to
     fsdax"

* tag 'libnvdimm-for-4.19_misc' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm:
  libnvdimm: fix ars_status output length calculation
  device-dax: avoid hang on error before devm_memremap_pages()
  tools/testing/nvdimm: improve emulation of smart injection
  filesystem-dax: Do not request kaddr and pfn when not required
  md/dm-writecache: Don't request pointer dummy_addr when not required
  dax/super: Do not request a pointer kaddr when not required
  tools/testing/nvdimm: kaddr and pfn can be NULL to ->direct_access()
  s390, dcssblk: kaddr and pfn can be NULL to ->direct_access()
  libnvdimm, pmem: kaddr and pfn can be NULL to ->direct_access()
  acpi/nfit: queue issuing of ars when an uc error notification comes in
  libnvdimm: Export max available extent
  libnvdimm: Use max contiguous area for namespace size
  MAINTAINERS: Add Jan Kara for filesystem DAX
  MAINTAINERS: update Ross Zwisler's email address
  tools/testing/nvdimm: Fix support for emulating controller temperature
  tools/testing/nvdimm: Make DSM failure code injection an override
  acpi, nfit: Prefer _DSM over _LSR for namespace label reads
  libnvdimm: Introduce locked DIMM capacity support

14 files changed, 171 insertions, 24 deletions

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 7c479002e798..b072cfc5f20e 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1699,7 +1699,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 {
         struct acpi_device *adev, *adev_dimm;
         struct device *dev = acpi_desc->dev;
-        unsigned long dsm_mask;
+        unsigned long dsm_mask, label_mask;
         const guid_t *guid;
         int i;
         int family = -1;
@@ -1771,6 +1771,16 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
                                         1ULL << i))
                         set_bit(i, &nfit_mem->dsm_mask);
 
+        /*
+         * Prefer the NVDIMM_FAMILY_INTEL label read commands if present
+         * due to their better semantics handling locked capacity.
+         */
+        label_mask = 1 << ND_CMD_GET_CONFIG_SIZE | 1 << ND_CMD_GET_CONFIG_DATA
+                | 1 << ND_CMD_SET_CONFIG_DATA;
+        if (family == NVDIMM_FAMILY_INTEL
+                        && (dsm_mask & label_mask) == label_mask)
+                return 0;
+
         if (acpi_nvdimm_has_method(adev_dimm, "_LSI")
                         && acpi_nvdimm_has_method(adev_dimm, "_LSR")) {
                 dev_dbg(dev, "%s: has _LSR\n", dev_name(&adev_dimm->dev));
@@ -2559,7 +2569,12 @@ static void ars_complete(struct acpi_nfit_desc *acpi_desc,
                         test_bit(ARS_SHORT, &nfit_spa->ars_state)
                         ? "short" : "long");
         clear_bit(ARS_SHORT, &nfit_spa->ars_state);
-        set_bit(ARS_DONE, &nfit_spa->ars_state);
+        if (test_and_clear_bit(ARS_REQ_REDO, &nfit_spa->ars_state)) {
+                set_bit(ARS_SHORT, &nfit_spa->ars_state);
+                set_bit(ARS_REQ, &nfit_spa->ars_state);
+                dev_dbg(dev, "ARS: processing scrub request received while in progress\n");
+        } else
+                set_bit(ARS_DONE, &nfit_spa->ars_state);
 }
 
 static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc)
@@ -3256,9 +3271,10 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, unsigned long flags)
                 if (test_bit(ARS_FAILED, &nfit_spa->ars_state))
                         continue;
 
-                if (test_and_set_bit(ARS_REQ, &nfit_spa->ars_state))
+                if (test_and_set_bit(ARS_REQ, &nfit_spa->ars_state)) {
                         busy++;
-                else {
+                        set_bit(ARS_REQ_REDO, &nfit_spa->ars_state);
+                } else {
                         if (test_bit(ARS_SHORT, &flags))
                                 set_bit(ARS_SHORT, &nfit_spa->ars_state);
                         scheduled++;
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index a97ff42fe311..d1274ea2d251 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -119,6 +119,7 @@ enum nfit_dimm_notifiers {
 
 enum nfit_ars_state {
         ARS_REQ,
+        ARS_REQ_REDO,
         ARS_DONE,
         ARS_SHORT,
         ARS_FAILED,
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index fd49b24fd6af..99e2aace8078 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -105,15 +105,19 @@ static int dax_pmem_probe(struct device *dev)
         if (rc)
                 return rc;
 
-        rc = devm_add_action_or_reset(dev, dax_pmem_percpu_exit,
-                                                        &dax_pmem->ref);
-        if (rc)
+        rc = devm_add_action(dev, dax_pmem_percpu_exit, &dax_pmem->ref);
+        if (rc) {
+                percpu_ref_exit(&dax_pmem->ref);
                 return rc;
+        }
 
         dax_pmem->pgmap.ref = &dax_pmem->ref;
         addr = devm_memremap_pages(dev, &dax_pmem->pgmap);
-        if (IS_ERR(addr))
+        if (IS_ERR(addr)) {
+                devm_remove_action(dev, dax_pmem_percpu_exit, &dax_pmem->ref);
+                percpu_ref_exit(&dax_pmem->ref);
                 return PTR_ERR(addr);
+        }
 
         rc = devm_add_action_or_reset(dev, dax_pmem_percpu_kill,
                                                         &dax_pmem->ref);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 45276abf03aa..6e928f37d084 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -89,7 +89,6 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
         struct request_queue *q;
         pgoff_t pgoff;
         int err, id;
-        void *kaddr;
         pfn_t pfn;
         long len;
         char buf[BDEVNAME_SIZE];
@@ -122,7 +121,7 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
         }
 
         id = dax_read_lock();
-        len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
+        len = dax_direct_access(dax_dev, pgoff, 1, NULL, &pfn);
         dax_read_unlock(id);
 
         put_dax(dax_dev);
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 3a28a68f184c..5f1f80d424dd 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -268,9 +268,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
                 i = 0;
                 do {
                         long daa;
-                        void *dummy_addr;
                         daa = dax_direct_access(wc->ssd_dev->dax_dev, i, p - i,
-                                                &dummy_addr, &pfn);
+                                                NULL, &pfn);
                         if (daa <= 0) {
                                 r = daa ? daa : -EINVAL;
                                 goto err3;
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 6ee7fd7e4bbd..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);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index dd17acd8fe68..c23649867696 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -226,8 +226,11 @@ __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/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,
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index ed607288e696..23e526cda5c1 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -922,9 +922,11 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
         unsigned long dev_sz;
 
         dev_sz = dev_info->end - dev_info->start + 1;
-        *kaddr = (void *) dev_info->start + offset;
-        *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset),
-                        PFN_DEV|PFN_SPECIAL);
+        if (kaddr)
+                *kaddr = (void *) dev_info->start + offset;
+        if (pfn)
+                *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset),
+                                PFN_DEV|PFN_SPECIAL);
 
         return (dev_sz - offset) / PAGE_SIZE;
 }