libnvdimm: add support for clear poison list and badblocks for device dax

Providing mechanism to clear poison list via the ndctl ND_CMD_CLEAR_ERROR
call. We will update the poison list and also the badblocks at region level
if the region is in dax mode or in pmem mode and not active. In other
words we force badblocks to be cleared through write requests if the
address is currently accessed through a block device, otherwise it can
only be done via the ioctl+dsm path.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 351bac8f65031edf831741159c01e860c89bb4a5..5ad2e5909e1a08fdb3b14bd443dbafa92b060a07 100644 (file)
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -27,6 +27,7 @@
 #include <linux/nd.h>
 #include "nd-core.h"
 #include "nd.h"
+#include "pfn.h"
 
 int nvdimm_major;
 static int nvdimm_bus_major;
@@ -218,11 +219,20 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
        if (cmd_rc < 0)
                return cmd_rc;
 
-       nvdimm_clear_from_poison_list(nvdimm_bus, phys, len);
+       nvdimm_forget_poison(nvdimm_bus, phys, len);
        return clear_err.cleared;
 }
 EXPORT_SYMBOL_GPL(nvdimm_clear_poison);
 
+void __nvdimm_bus_badblocks_clear(struct nvdimm_bus *nvdimm_bus,
+               struct resource *res)
+{
+       lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
+       device_for_each_child(&nvdimm_bus->dev, (void *)res,
+                       nvdimm_region_badblocks_clear);
+}
+EXPORT_SYMBOL_GPL(__nvdimm_bus_badblocks_clear);
+
 static int nvdimm_bus_match(struct device *dev, struct device_driver *drv);
 
 static struct bus_type nvdimm_bus_type = {
@@ -769,16 +779,55 @@ void wait_nvdimm_bus_probe_idle(struct device *dev)
        } while (true);
 }
 
-static int pmem_active(struct device *dev, void *data)
+static int nd_pmem_forget_poison_check(struct device *dev, void *data)
 {
-       if (is_nd_pmem(dev) && dev->driver)
+       struct nd_cmd_clear_error *clear_err =
+               (struct nd_cmd_clear_error *)data;
+       struct nd_btt *nd_btt = is_nd_btt(dev) ? to_nd_btt(dev) : NULL;
+       struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL;
+       struct nd_dax *nd_dax = is_nd_dax(dev) ? to_nd_dax(dev) : NULL;
+       struct nd_namespace_common *ndns = NULL;
+       struct nd_namespace_io *nsio;
+       resource_size_t offset = 0, end_trunc = 0, start, end, pstart, pend;
+
+       if (nd_dax || !dev->driver)
+               return 0;
+
+       start = clear_err->address;
+       end = clear_err->address + clear_err->cleared - 1;
+
+       if (nd_btt || nd_pfn || nd_dax) {
+               if (nd_btt)
+                       ndns = nd_btt->ndns;
+               else if (nd_pfn)
+                       ndns = nd_pfn->ndns;
+               else if (nd_dax)
+                       ndns = nd_dax->nd_pfn.ndns;
+
+               if (!ndns)
+                       return 0;
+       } else
+               ndns = to_ndns(dev);
+
+       nsio = to_nd_namespace_io(&ndns->dev);
+       pstart = nsio->res.start + offset;
+       pend = nsio->res.end - end_trunc;
+
+       if ((pstart >= start) && (pend <= end))
                return -EBUSY;
+
        return 0;
+
+}
+
+static int nd_ns_forget_poison_check(struct device *dev, void *data)
+{
+       return device_for_each_child(dev, data, nd_pmem_forget_poison_check);
 }
 
 /* set_config requires an idle interleave set */
 static int nd_cmd_clear_to_send(struct nvdimm_bus *nvdimm_bus,
-               struct nvdimm *nvdimm, unsigned int cmd)
+               struct nvdimm *nvdimm, unsigned int cmd, void *data)
 {
        struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
 
@@ -792,8 +841,8 @@ static int nd_cmd_clear_to_send(struct nvdimm_bus *nvdimm_bus,
 
        /* require clear error to go through the pmem driver */
        if (!nvdimm && cmd == ND_CMD_CLEAR_ERROR)
-               return device_for_each_child(&nvdimm_bus->dev, NULL,
-                               pmem_active);
+               return device_for_each_child(&nvdimm_bus->dev, data,
+                               nd_ns_forget_poison_check);
 
        if (!nvdimm || cmd != ND_CMD_SET_CONFIG_DATA)
                return 0;
@@ -820,7 +869,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
        const char *cmd_name, *dimm_name;
        unsigned long cmd_mask;
        void *buf;
-       int rc, i;
+       int rc, i, cmd_rc;
 
        if (nvdimm) {
                desc = nd_cmd_dimm_desc(cmd);
@@ -927,13 +976,29 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
        }
 
        nvdimm_bus_lock(&nvdimm_bus->dev);
-       rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, cmd);
+       rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, cmd, buf);
        if (rc)
                goto out_unlock;
 
-       rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len, NULL);
+       rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len, &cmd_rc);
        if (rc < 0)
                goto out_unlock;
+
+       if (!nvdimm && cmd == ND_CMD_CLEAR_ERROR && cmd_rc >= 0) {
+               struct nd_cmd_clear_error *clear_err = buf;
+               struct resource res;
+
+               if (clear_err->cleared) {
+                       /* clearing the poison list we keep track of */
+                       __nvdimm_forget_poison(nvdimm_bus, clear_err->address,
+                                       clear_err->cleared);
+
+                       /* now sync the badblocks lists */
+                       res.start = clear_err->address;
+                       res.end = clear_err->address + clear_err->cleared - 1;
+                       __nvdimm_bus_badblocks_clear(nvdimm_bus, &res);
+               }
+       }
        nvdimm_bus_unlock(&nvdimm_bus->dev);
 
        if (copy_to_user(p, buf, buf_len))

diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 9303cfeb8bee507c171c2060fb7602e7b0519267..40a3da088fd2506eda5ba8cce3c1b0369b67ed32 100644 (file)
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -574,14 +574,15 @@ int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 }
 EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison);
 
-void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus,
-               phys_addr_t start, unsigned int len)
+void __nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus, phys_addr_t start,
+               unsigned int len)
 {
        struct list_head *poison_list = &nvdimm_bus->poison_list;
        u64 clr_end = start + len - 1;
        struct nd_poison *pl, *next;
 
-       nvdimm_bus_lock(&nvdimm_bus->dev);
+       lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
+
        WARN_ON_ONCE(list_empty(poison_list));
 
        /*
@@ -634,9 +635,17 @@ void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus,
                        continue;
                }
        }
+}
+EXPORT_SYMBOL_GPL(__nvdimm_forget_poison);
+
+void nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus,
+               phys_addr_t start, unsigned int len)
+{
+       nvdimm_bus_lock(&nvdimm_bus->dev);
+       __nvdimm_forget_poison(nvdimm_bus, start, len);
        nvdimm_bus_unlock(&nvdimm_bus->dev);
 }
-EXPORT_SYMBOL_GPL(nvdimm_clear_from_poison_list);
+EXPORT_SYMBOL_GPL(nvdimm_forget_poison);
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)

diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c
index 869a886c292ebf94f963abb9f747b0c2802fb471..23c4307d254ca4c8e9f8eb98d725e53e194e27f4 100644 (file)
--- a/drivers/nvdimm/region.c
+++ b/drivers/nvdimm/region.c
@@ -131,6 +131,31 @@ static void nd_region_notify(struct device *dev, enum nvdimm_event event)
        device_for_each_child(dev, &event, child_notify);
 }
 
+int nvdimm_region_badblocks_clear(struct device *dev, void *data)
+{
+       struct resource *res = (struct resource *)data;
+       struct nd_region *nd_region;
+       resource_size_t ndr_end;
+       sector_t sector;
+
+       /* make sure device is a region */
+       if (!is_nd_pmem(dev))
+               return 0;
+
+       nd_region = to_nd_region(dev);
+       ndr_end = nd_region->ndr_start + nd_region->ndr_size - 1;
+
+       /* make sure we are in the region */
+       if (res->start < nd_region->ndr_start || res->end > ndr_end)
+               return 0;
+
+       sector = (res->start - nd_region->ndr_start) >> 9;
+       badblocks_clear(&nd_region->bb, sector, resource_size(res) >> 9);
+
+       return 0;
+}
+EXPORT_SYMBOL_GPL(nvdimm_region_badblocks_clear);
+
 static struct nd_device_driver nd_region_driver = {
        .probe = nd_region_probe,
        .remove = nd_region_remove,

diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 77e7af32543f698d0413286dc8702d7124bcf81b..1c609e89048a1e241515cd34b1d77ac262dfcb11 100644 (file)
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -120,7 +120,9 @@ static inline struct nd_blk_region_desc *to_blk_region_desc(
 }
 
 int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length);
-void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus,
+void nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus,
+               phys_addr_t start, unsigned int len);
+void __nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus,
                phys_addr_t start, unsigned int len);
 struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
                struct nvdimm_bus_descriptor *nfit_desc);
@@ -162,4 +164,7 @@ void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane);
 u64 nd_fletcher64(void *addr, size_t len, bool le);
 void nvdimm_flush(struct nd_region *nd_region);
 int nvdimm_has_flush(struct nd_region *nd_region);
+int nvdimm_region_badblocks_clear(struct device *dev, void *data);
+void __nvdimm_bus_badblocks_clear(struct nvdimm_bus *nvdimm_bus,
+               struct resource *res);
 #endif /* __LIBNVDIMM_H__ */