Merge tag 'libnvdimm-for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "libnvdimm updates for the latest ACPI and UEFI specifications. This
  pull request also includes new 'struct dax_operations' enabling to
  undo the abuse of copy_user_nocache() for copy operations to pmem.

  The dax work originally missed 4.12 to address concerns raised by Al.

  Summary:

   - Introduce the _flushcache() family of memory copy helpers and use
     them for persistent memory write operations on x86. The
     _flushcache() semantic indicates that the cache is either bypassed
     for the copy operation (movnt) or any lines dirtied by the copy
     operation are written back (clwb, clflushopt, or clflush).

   - Extend dax_operations with ->copy_from_iter() and ->flush()
     operations. These operations and other infrastructure updates allow
     all persistent memory specific dax functionality to be pushed into
     libnvdimm and the pmem driver directly. It also allows dax-specific
     sysfs attributes to be linked to a host device, for example:
     /sys/block/pmem0/dax/write_cache

   - Add support for the new NVDIMM platform/firmware mechanisms
     introduced in ACPI 6.2 and UEFI 2.7. This support includes the v1.2
     namespace label format, extensions to the address-range-scrub
     command set, new error injection commands, and a new BTT
     (block-translation-table) layout. These updates support inter-OS
     and pre-OS compatibility.

   - Fix a longstanding memory corruption bug in nfit_test.

   - Make the pmem and nvdimm-region 'badblocks' sysfs files poll(2)
     capable.

   - Miscellaneous fixes and small updates across libnvdimm and the nfit
     driver.

  Acknowledgements that came after the branch was pushed: commit
  6aa734a2f38e ("libnvdimm, region, pmem: fix 'badblocks'
  sysfs_get_dirent() reference lifetime") was reviewed by Toshi Kani
  <toshi.kani@hpe.com>"

* tag 'libnvdimm-for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (42 commits)
  libnvdimm, namespace: record 'lbasize' for pmem namespaces
  acpi/nfit: Issue Start ARS to retrieve existing records
  libnvdimm: New ACPI 6.2 DSM functions
  acpi, nfit: Show bus_dsm_mask in sysfs
  libnvdimm, acpi, nfit: Add bus level dsm mask for pass thru.
  acpi, nfit: Enable DSM pass thru for root functions.
  libnvdimm: passthru functions clear to send
  libnvdimm, btt: convert some info messages to warn/err
  libnvdimm, region, pmem: fix 'badblocks' sysfs_get_dirent() reference lifetime
  libnvdimm: fix the clear-error check in nsio_rw_bytes
  libnvdimm, btt: fix btt_rw_page not returning errors
  acpi, nfit: quiet invalid block-aperture-region warnings
  libnvdimm, btt: BTT updates for UEFI 2.7 format
  acpi, nfit: constify *_attribute_group
  libnvdimm, pmem: disable dax flushing when pmem is fronting a volatile region
  libnvdimm, pmem, dax: export a cache control attribute
  dax: convert to bitmask for flags
  dax: remove default copy_from_iter fallback
  libnvdimm, nfit: enable support for volatile ranges
  libnvdimm, pmem: fix persistence warning
  ...

1 files changed, 57 insertions, 6 deletions

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 6b577afb1d44..f7099adaabc0 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -28,7 +28,7 @@
 #include <linux/blk-mq.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
-#include <linux/pmem.h>
+#include <linux/uio.h>
 #include <linux/dax.h>
 #include <linux/nd.h>
 #include "pmem.h"
@@ -68,9 +68,11 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
 				(unsigned long long) sector, cleared,
 				cleared > 1 ? "s" : "");
 		badblocks_clear(&pmem->bb, sector, cleared);
+		if (pmem->bb_state)
+			sysfs_notify_dirent(pmem->bb_state);
 	}
 
-	invalidate_pmem(pmem->virt_addr + offset, len);
+	arch_invalidate_pmem(pmem->virt_addr + offset, len);
 
 	return rc;
 }
@@ -80,7 +82,7 @@ static void write_pmem(void *pmem_addr, struct page *page,
 {
 	void *mem = kmap_atomic(page);
 
-	memcpy_to_pmem(pmem_addr, mem + off, len);
+	memcpy_flushcache(pmem_addr, mem + off, len);
 	kunmap_atomic(mem);
 }
 
@@ -235,8 +237,27 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
 	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
 }
 
+static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_from_iter_flushcache(addr, bytes, i);
+}
+
+static void pmem_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t size)
+{
+	arch_wb_cache_pmem(addr, size);
+}
+
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
+	.copy_from_iter = pmem_copy_from_iter,
+	.flush = pmem_dax_flush,
+};
+
+static const struct attribute_group *pmem_attribute_groups[] = {
+	&dax_attribute_group,
+	NULL,
 };
 
 static void pmem_release_queue(void *q)
@@ -265,14 +286,15 @@ static int pmem_attach_disk(struct device *dev,
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	struct vmem_altmap __altmap, *altmap = NULL;
+	int nid = dev_to_node(dev), fua, wbc;
 	struct resource *res = &nsio->res;
 	struct nd_pfn *nd_pfn = NULL;
 	struct dax_device *dax_dev;
-	int nid = dev_to_node(dev);
 	struct nd_pfn_sb *pfn_sb;
 	struct pmem_device *pmem;
 	struct resource pfn_res;
 	struct request_queue *q;
+	struct device *gendev;
 	struct gendisk *disk;
 	void *addr;
 
@@ -294,8 +316,12 @@ static int pmem_attach_disk(struct device *dev,
 	dev_set_drvdata(dev, pmem);
 	pmem->phys_addr = res->start;
 	pmem->size = resource_size(res);
-	if (nvdimm_has_flush(nd_region) < 0)
+	fua = nvdimm_has_flush(nd_region);
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) || fua < 0) {
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
+		fua = 0;
+	}
+	wbc = nvdimm_has_cache(nd_region);
 
 	if (!devm_request_mem_region(dev, res->start, resource_size(res),
 				dev_name(&ndns->dev))) {
@@ -339,9 +365,10 @@ static int pmem_attach_disk(struct device *dev,
 		return PTR_ERR(addr);
 	pmem->virt_addr = addr;
 
-	blk_queue_write_cache(q, true, true);
+	blk_queue_write_cache(q, wbc, fua);
 	blk_queue_make_request(q, pmem_make_request);
 	blk_queue_physical_block_size(q, PAGE_SIZE);
+	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
 	blk_queue_max_hw_sectors(q, UINT_MAX);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
 	queue_flag_set_unlocked(QUEUE_FLAG_DAX, q);
@@ -368,14 +395,23 @@ static int pmem_attach_disk(struct device *dev,
 		put_disk(disk);
 		return -ENOMEM;
 	}
+	dax_write_cache(dax_dev, wbc);
 	pmem->dax_dev = dax_dev;
 
+	gendev = disk_to_dev(disk);
+	gendev->groups = pmem_attribute_groups;
+
 	device_add_disk(dev, disk);
 	if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
 		return -ENOMEM;
 
 	revalidate_disk(disk);
 
+	pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd,
+					  "badblocks");
+	if (!pmem->bb_state)
+		dev_warn(dev, "'badblocks' notification disabled\n");
+
 	return 0;
 }
 
@@ -407,8 +443,18 @@ static int nd_pmem_probe(struct device *dev)
 
 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));
+	else {
+		/*
+		 * Note, this assumes device_lock() context to not race
+		 * nd_pmem_notify()
+		 */
+		sysfs_put(pmem->bb_state);
+		pmem->bb_state = NULL;
+	}
 	nvdimm_flush(to_nd_region(dev->parent));
 
 	return 0;
@@ -427,6 +473,7 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 	struct nd_namespace_io *nsio;
 	struct resource res;
 	struct badblocks *bb;
+	struct kernfs_node *bb_state;
 
 	if (event != NVDIMM_REVALIDATE_POISON)
 		return;
@@ -438,11 +485,13 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 		nd_region = to_nd_region(ndns->dev.parent);
 		nsio = to_nd_namespace_io(&ndns->dev);
 		bb = &nsio->bb;
+		bb_state = NULL;
 	} else {
 		struct pmem_device *pmem = dev_get_drvdata(dev);
 
 		nd_region = to_region(pmem);
 		bb = &pmem->bb;
+		bb_state = pmem->bb_state;
 
 		if (is_nd_pfn(dev)) {
 			struct nd_pfn *nd_pfn = to_nd_pfn(dev);
@@ -462,6 +511,8 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 	res.start = nsio->res.start + offset;
 	res.end = nsio->res.end - end_trunc;
 	nvdimm_badblocks_populate(nd_region, bb, &res);
+	if (bb_state)
+		sysfs_notify_dirent(bb_state);
 }
 
 MODULE_ALIAS("pmem");