Merge tag 'libnvdimm-for-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:

 - Replace pcommit with ADR / directed-flushing.

   The pcommit instruction, which has not shipped on any product, is
   deprecated.  Instead, the requirement is that platforms implement
   either ADR, or provide one or more flush addresses per nvdimm.

   ADR (Asynchronous DRAM Refresh) flushes data in posted write buffers
   to the memory controller on a power-fail event.

   Flush addresses are defined in ACPI 6.x as an NVDIMM Firmware
   Interface Table (NFIT) sub-structure: "Flush Hint Address Structure".
   A flush hint is an mmio address that when written and fenced assures
   that all previous posted writes targeting a given dimm have been
   flushed to media.

 - On-demand ARS (address range scrub).

   Linux uses the results of the ACPI ARS commands to track bad blocks
   in pmem devices.  When latent errors are detected we re-scrub the
   media to refresh the bad block list, userspace can also request a
   re-scrub at any time.

 - Support for the Microsoft DSM (device specific method) command
   format.

 - Support for EDK2/OVMF virtual disk device memory ranges.

 - Various fixes and cleanups across the subsystem.

* tag 'libnvdimm-for-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (41 commits)
  libnvdimm-btt: Delete an unnecessary check before the function call "__nd_device_register"
  nfit: do an ARS scrub on hitting a latent media error
  nfit: move to nfit/ sub-directory
  nfit, libnvdimm: allow an ARS scrub to be triggered on demand
  libnvdimm: register nvdimm_bus devices with an nd_bus driver
  pmem: clarify a debug print in pmem_clear_poison
  x86/insn: remove pcommit
  Revert "KVM: x86: add pcommit support"
  nfit, tools/testing/nvdimm/: unify shutdown paths
  libnvdimm: move ->module to struct nvdimm_bus_descriptor
  nfit: cleanup acpi_nfit_init calling convention
  nfit: fix _FIT evaluation memory leak + use after free
  tools/testing/nvdimm: add manufacturing_{date|location} dimm properties
  tools/testing/nvdimm: add virtual ramdisk range
  acpi, nfit: treat virtual ramdisk SPA as pmem region
  pmem: kill __pmem address space
  pmem: kill wmb_pmem()
  libnvdimm, pmem: use nvdimm_flush() for namespace I/O writes
  fs/dax: remove wmb_pmem()
  libnvdimm, pmem: flush posted-write queues on shutdown
  ...

1 files changed, 51 insertions, 34 deletions

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 36cb39047d5b..b511099457db 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -29,27 +29,28 @@
 #include <linux/slab.h>
 #include <linux/pmem.h>
 #include <linux/nd.h>
+#include "pmem.h"
 #include "pfn.h"
 #include "nd.h"
 
-struct pmem_device {
-	/* One contiguous memory region per device */
-	phys_addr_t		phys_addr;
-	/* when non-zero this device is hosting a 'pfn' instance */
-	phys_addr_t		data_offset;
-	u64			pfn_flags;
-	void __pmem		*virt_addr;
-	/* immutable base size of the namespace */
-	size_t			size;
-	/* trim size when namespace capacity has been section aligned */
-	u32			pfn_pad;
-	struct badblocks	bb;
-};
+static struct device *to_dev(struct pmem_device *pmem)
+{
+	/*
+	 * nvdimm bus services need a 'dev' parameter, and we record the device
+	 * at init in bb.dev.
+	 */
+	return pmem->bb.dev;
+}
+
+static struct nd_region *to_region(struct pmem_device *pmem)
+{
+	return to_nd_region(to_dev(pmem)->parent);
+}
 
 static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 		unsigned int len)
 {
-	struct device *dev = pmem->bb.dev;
+	struct device *dev = to_dev(pmem);
 	sector_t sector;
 	long cleared;
 
@@ -57,7 +58,7 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 	cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len);
 
 	if (cleared > 0 && cleared / 512) {
-		dev_dbg(dev, "%s: %llx clear %ld sector%s\n",
+		dev_dbg(dev, "%s: %#llx clear %ld sector%s\n",
 				__func__, (unsigned long long) sector,
 				cleared / 512, cleared / 512 > 1 ? "s" : "");
 		badblocks_clear(&pmem->bb, sector, cleared / 512);
@@ -73,7 +74,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	bool bad_pmem = false;
 	void *mem = kmap_atomic(page);
 	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
-	void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
+	void *pmem_addr = pmem->virt_addr + pmem_off;
 
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
@@ -112,6 +113,11 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	return rc;
 }
 
+/* account for REQ_FLUSH rename, replace with REQ_PREFLUSH after v4.8-rc1 */
+#ifndef REQ_FLUSH
+#define REQ_FLUSH REQ_PREFLUSH
+#endif
+
 static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 {
 	int rc = 0;
@@ -120,6 +126,10 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	struct pmem_device *pmem = q->queuedata;
+	struct nd_region *nd_region = to_region(pmem);
+
+	if (bio->bi_rw & REQ_FLUSH)
+		nvdimm_flush(nd_region);
 
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
@@ -134,8 +144,8 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	if (do_acct)
 		nd_iostat_end(bio, start);
 
-	if (bio_data_dir(bio))
-		wmb_pmem();
+	if (bio->bi_rw & REQ_FUA)
+		nvdimm_flush(nd_region);
 
 	bio_endio(bio);
 	return BLK_QC_T_NONE;
@@ -148,8 +158,6 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	int rc;
 
 	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, rw, sector);
-	if (rw & WRITE)
-		wmb_pmem();
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -163,8 +171,9 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	return rc;
 }
 
-static long pmem_direct_access(struct block_device *bdev, sector_t sector,
-		      void __pmem **kaddr, pfn_t *pfn, long size)
+/* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
+__weak long pmem_direct_access(struct block_device *bdev, sector_t sector,
+		      void **kaddr, pfn_t *pfn, long size)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	resource_size_t offset = sector * 512 + pmem->data_offset;
@@ -195,7 +204,7 @@ static void pmem_release_queue(void *q)
 	blk_cleanup_queue(q);
 }
 
-void pmem_release_disk(void *disk)
+static void pmem_release_disk(void *disk)
 {
 	del_gendisk(disk);
 	put_disk(disk);
@@ -205,6 +214,7 @@ static int pmem_attach_disk(struct device *dev,
 		struct nd_namespace_common *ndns)
 {
 	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;
 	struct resource *res = &nsio->res;
 	struct nd_pfn *nd_pfn = NULL;
@@ -234,7 +244,7 @@ static int pmem_attach_disk(struct device *dev,
 	dev_set_drvdata(dev, pmem);
 	pmem->phys_addr = res->start;
 	pmem->size = resource_size(res);
-	if (!arch_has_wmb_pmem())
+	if (nvdimm_has_flush(nd_region) < 0)
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 
 	if (!devm_request_mem_region(dev, res->start, resource_size(res),
@@ -269,15 +279,14 @@ static int pmem_attach_disk(struct device *dev,
 	 * At release time the queue must be dead before
 	 * devm_memremap_pages is unwound
 	 */
-	if (devm_add_action(dev, pmem_release_queue, q)) {
-		blk_cleanup_queue(q);
+	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
 		return -ENOMEM;
-	}
 
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
-	pmem->virt_addr = (void __pmem *) addr;
+	pmem->virt_addr = addr;
 
+	blk_queue_write_cache(q, true, true);
 	blk_queue_make_request(q, pmem_make_request);
 	blk_queue_physical_block_size(q, PAGE_SIZE);
 	blk_queue_max_hw_sectors(q, UINT_MAX);
@@ -289,10 +298,6 @@ static int pmem_attach_disk(struct device *dev,
 	disk = alloc_disk_node(0, nid);
 	if (!disk)
 		return -ENOMEM;
-	if (devm_add_action(dev, pmem_release_disk, disk)) {
-		put_disk(disk);
-		return -ENOMEM;
-	}
 
 	disk->fops		= &pmem_fops;
 	disk->queue		= q;
@@ -302,9 +307,13 @@ static int pmem_attach_disk(struct device *dev,
 			/ 512);
 	if (devm_init_badblocks(dev, &pmem->bb))
 		return -ENOMEM;
-	nvdimm_badblocks_populate(to_nd_region(dev->parent), &pmem->bb, res);
+	nvdimm_badblocks_populate(nd_region, &pmem->bb, res);
 	disk->bb = &pmem->bb;
 	device_add_disk(dev, disk);
+
+	if (devm_add_action_or_reset(dev, pmem_release_disk, disk))
+		return -ENOMEM;
+
 	revalidate_disk(disk);
 
 	return 0;
@@ -340,13 +349,20 @@ static int nd_pmem_remove(struct device *dev)
 {
 	if (is_nd_btt(dev))
 		nvdimm_namespace_detach_btt(to_nd_btt(dev));
+	nvdimm_flush(to_nd_region(dev->parent));
+
 	return 0;
 }
 
+static void nd_pmem_shutdown(struct device *dev)
+{
+	nvdimm_flush(to_nd_region(dev->parent));
+}
+
 static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 {
-	struct nd_region *nd_region = to_nd_region(dev->parent);
 	struct pmem_device *pmem = dev_get_drvdata(dev);
+	struct nd_region *nd_region = to_region(pmem);
 	resource_size_t offset = 0, end_trunc = 0;
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_io *nsio;
@@ -382,6 +398,7 @@ static struct nd_device_driver nd_pmem_driver = {
 	.probe = nd_pmem_probe,
 	.remove = nd_pmem_remove,
 	.notify = nd_pmem_notify,
+	.shutdown = nd_pmem_shutdown,
 	.drv = {
 		.name = "nd_pmem",
 	},