Merge tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "The bulk of this has been in multiple -next releases. There were a few
  late breaking fixes and small features that got added in the last
  couple days, but the whole set has received a build success
  notification from the kbuild robot.

  Change summary:

   - Region media error reporting: A libnvdimm region device is the
     parent to one or more namespaces. To date, media errors have been
     reported via the "badblocks" attribute attached to pmem block
     devices for namespaces in "raw" or "memory" mode. Given that
     namespaces can be in "device-dax" or "btt-sector" mode this new
     interface reports media errors generically, i.e. independent of
     namespace modes or state.

     This subsequently allows userspace tooling to craft "ACPI 6.1
     Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error"
     requests and submit them via the ioctl path for NVDIMM root bus
     devices.

   - Introduce 'struct dax_device' and 'struct dax_operations': Prompted
     by a request from Linus and feedback from Christoph this allows for
     dax capable drivers to publish their own custom dax operations.
     This fixes the broken assumption that all dax operations are
     related to a persistent memory device, and makes it easier for
     other architectures and platforms to add customized persistent
     memory support.

   - 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is
     available for storage appliance applications to manually trigger
     memory controllers to drain write-pending buffers that would
     otherwise be flushed automatically by the platform ADR
     (asynchronous-DRAM-refresh) mechanism at a power loss event.
     Support for "locked" DIMMs is included to prevent namespaces from
     surfacing when the namespace label data area is locked. Finally,
     fixes for various reported deadlocks and crashes, also tagged for
     -stable.

   - ACPI / nfit driver updates: General updates of the nfit driver to
     add DSM command overrides, ACPI 6.1 health state flags support, DSM
     payload debug available by default, and various fixes.

  Acknowledgements that came after the branch was pushed:

   - commmit 565851c972b5 "device-dax: fix sysfs attribute deadlock":
     Tested-by: Yi Zhang <yizhan@redhat.com>

   - commit 23f498448362 "libnvdimm: rework region badblocks clearing"
     Tested-by: Toshi Kani <toshi.kani@hpe.com>"

* tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits)
  libnvdimm, pfn: fix 'npfns' vs section alignment
  libnvdimm: handle locked label storage areas
  libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED
  brd: fix uninitialized use of brd->dax_dev
  block, dax: use correct format string in bdev_dax_supported
  device-dax: fix sysfs attribute deadlock
  libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking"
  libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering
  libnvdimm: rework region badblocks clearing
  acpi, nfit: kill ACPI_NFIT_DEBUG
  libnvdimm: fix clear length of nvdimm_forget_poison()
  libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify
  libnvdimm, region: sysfs trigger for nvdimm_flush()
  libnvdimm: fix phys_addr for nvdimm_clear_poison
  x86, dax, pmem: remove indirection around memcpy_from_pmem()
  block: remove block_device_operations ->direct_access()
  block, dax: convert bdev_dax_supported() to dax_direct_access()
  filesystem-dax: convert to dax_direct_access()
  Revert "block: use DAX for partition table reads"
  ext2, ext4, xfs: retrieve dax_device for iomap operations
  ...

1 files changed, 111 insertions, 11 deletions

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 351bac8f6503..e9361bffe5ee 100644
--- 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;
@@ -171,6 +172,57 @@ void nvdimm_region_notify(struct nd_region *nd_region, enum nvdimm_event event)
 }
 EXPORT_SYMBOL_GPL(nvdimm_region_notify);
 
+struct clear_badblocks_context {
+	resource_size_t phys, cleared;
+};
+
+static int nvdimm_clear_badblocks_region(struct device *dev, void *data)
+{
+	struct clear_badblocks_context *ctx = 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 (ctx->phys < nd_region->ndr_start
+			|| (ctx->phys + ctx->cleared) > ndr_end)
+		return 0;
+
+	sector = (ctx->phys - nd_region->ndr_start) / 512;
+	badblocks_clear(&nd_region->bb, sector, ctx->cleared / 512);
+
+	return 0;
+}
+
+static void nvdimm_clear_badblocks_regions(struct nvdimm_bus *nvdimm_bus,
+		phys_addr_t phys, u64 cleared)
+{
+	struct clear_badblocks_context ctx = {
+		.phys = phys,
+		.cleared = cleared,
+	};
+
+	device_for_each_child(&nvdimm_bus->dev, &ctx,
+			nvdimm_clear_badblocks_region);
+}
+
+static void nvdimm_account_cleared_poison(struct nvdimm_bus *nvdimm_bus,
+		phys_addr_t phys, u64 cleared)
+{
+	if (cleared > 0)
+		nvdimm_forget_poison(nvdimm_bus, phys, cleared);
+
+	if (cleared > 0 && cleared / 512)
+		nvdimm_clear_badblocks_regions(nvdimm_bus, phys, cleared);
+}
+
 long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
 		unsigned int len)
 {
@@ -218,7 +270,8 @@ 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_account_cleared_poison(nvdimm_bus, phys, clear_err.cleared);
+
 	return clear_err.cleared;
 }
 EXPORT_SYMBOL_GPL(nvdimm_clear_poison);
@@ -286,6 +339,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
 	init_waitqueue_head(&nvdimm_bus->probe_wait);
 	nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
 	mutex_init(&nvdimm_bus->reconfig_mutex);
+	spin_lock_init(&nvdimm_bus->poison_lock);
 	if (nvdimm_bus->id < 0) {
 		kfree(nvdimm_bus);
 		return NULL;
@@ -354,9 +408,9 @@ static int nd_bus_remove(struct device *dev)
 	nd_synchronize();
 	device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
 
-	nvdimm_bus_lock(&nvdimm_bus->dev);
+	spin_lock(&nvdimm_bus->poison_lock);
 	free_poison_list(&nvdimm_bus->poison_list);
-	nvdimm_bus_unlock(&nvdimm_bus->dev);
+	spin_unlock(&nvdimm_bus->poison_lock);
 
 	nvdimm_bus_destroy_ndctl(nvdimm_bus);
 
@@ -769,16 +823,55 @@ 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 +885,8 @@ 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 +913,7 @@ 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 +1020,20 @@ 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;
+
+		nvdimm_account_cleared_poison(nvdimm_bus, clear_err->address,
+				clear_err->cleared);
+	}
 	nvdimm_bus_unlock(&nvdimm_bus->dev);
 
 	if (copy_to_user(p, buf, buf_len))