Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/nvdimm/nvdimm

Pull nvdimm fixes from Dan Williams:
 "A small crop of lockdep, sleeping while atomic, and other fixes /
  band-aids in advance of the full-blown reworks targeting the next
  merge window. The largest change here is "libnvdimm: fix blk free
  space accounting" which deletes a pile of buggy code that better
  testing would have caught before merging. The next change that is
  borderline too big for a late rc is switching the device-dax locking
  from rcu to srcu, I couldn't think of a smaller way to make that fix.

  The __copy_user_nocache fix will have a full replacement in 4.12 to
  move those pmem special case considerations into the pmem driver. The
  "libnvdimm: band aid btt vs clear poison locking" commit admits that
  our error clearing support for btt went in broken, so we just disable
  it in 4.11 and -stable. A replacement / full fix is in the pipeline
  for 4.12

  Some of these would have been caught earlier had DEBUG_ATOMIC_SLEEP
  been enabled on my development station. I wonder if we should have:

      config DEBUG_ATOMIC_SLEEP
        default PROVE_LOCKING

  ...since I mistakenly thought I got both with PROVE_LOCKING=y.

  These have received a build success notification from the 0day robot,
  and some have appeared in a -next release with no reported issues"

* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  x86, pmem: fix broken __copy_user_nocache cache-bypass assumptions
  device-dax: switch to srcu, fix rcu_read_lock() vs pte allocation
  libnvdimm: band aid btt vs clear poison locking
  libnvdimm: fix reconfig_mutex, mmap_sem, and jbd2_handle lockdep splat
  libnvdimm: fix blk free space accounting
  acpi, nfit, libnvdimm: fix interleave set cookie calculation (64-bit comparison)

arch/x86/include/asm/pmem.h

@@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void arch_wb_cache_pmem(void *addr, size_t size)
 {
@@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(addr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				arch_wb_cache_pmem(addr, 1);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
 		arch_wb_cache_pmem(addr, bytes);
 
 	return len;

drivers/acpi/nfit/core.c

@@ -1617,7 +1617,11 @@ static int cmp_map(const void *m0, const void *m1)
 	const struct nfit_set_info_map *map0 = m0;
 	const struct nfit_set_info_map *map1 = m1;
 
-	return map0->region_offset - map1->region_offset;
+	if (map0->region_offset < map1->region_offset)
+		return -1;
+	else if (map0->region_offset > map1->region_offset)
+		return 1;
+	return 0;
 }
 
 /* Retrieve the nth entry referencing this spa */

drivers/dax/Kconfig

@@ -2,6 +2,7 @@ menuconfig DEV_DAX
 	tristate "DAX: direct access to differentiated memory"
 	default m if NVDIMM_DAX
 	depends on TRANSPARENT_HUGEPAGE
+	select SRCU
 	help
 	  Support raw access to differentiated (persistence, bandwidth,
 	  latency...) memory via an mmap(2) capable character

drivers/dax/dax.c

@@ -25,6 +25,7 @@
 #include "dax.h"
 
 static dev_t dax_devt;
+DEFINE_STATIC_SRCU(dax_srcu);
 static struct class *dax_class;
 static DEFINE_IDA(dax_minor_ida);
 static int nr_dax = CONFIG_NR_DEV_DAX;
@@ -60,7 +61,7 @@ struct dax_region {
  * @region - parent region
  * @dev - device backing the character device
  * @cdev - core chardev data
- * @alive - !alive + rcu grace period == no new mappings can be established
+ * @alive - !alive + srcu grace period == no new mappings can be established
  * @id - child id in the region
  * @num_resources - number of physical address extents in this device
  * @res - array of physical address ranges
@@ -569,7 +570,7 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 static int dax_dev_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
-	int rc;
+	int rc, id;
 	struct file *filp = vmf->vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
@@ -578,7 +579,7 @@ static int dax_dev_huge_fault(struct vm_fault *vmf,
 			? "write" : "read",
 			vmf->vma->vm_start, vmf->vma->vm_end);
 
-	rcu_read_lock();
+	id = srcu_read_lock(&dax_srcu);
 	switch (pe_size) {
 	case PE_SIZE_PTE:
 		rc = __dax_dev_pte_fault(dax_dev, vmf);
@@ -592,7 +593,7 @@ static int dax_dev_huge_fault(struct vm_fault *vmf,
 	default:
 		return VM_FAULT_FALLBACK;
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&dax_srcu, id);
 
 	return rc;
 }
@@ -713,11 +714,11 @@ static void unregister_dax_dev(void *dev)
 	 * Note, rcu is not protecting the liveness of dax_dev, rcu is
 	 * ensuring that any fault handlers that might have seen
 	 * dax_dev->alive == true, have completed.  Any fault handlers
-	 * that start after synchronize_rcu() has started will abort
+	 * that start after synchronize_srcu() has started will abort
 	 * upon seeing dax_dev->alive == false.
 	 */
 	dax_dev->alive = false;
-	synchronize_rcu();
+	synchronize_srcu(&dax_srcu);
 	unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1);
 	cdev_del(cdev);
 	device_unregister(dev);

drivers/nvdimm/bus.c

@@ -934,8 +934,14 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len, NULL);
 	if (rc < 0)
 		goto out_unlock;
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+
 	if (copy_to_user(p, buf, buf_len))
 		rc = -EFAULT;
+
+	vfree(buf);
+	return rc;
+
  out_unlock:
 	nvdimm_bus_unlock(&nvdimm_bus->dev);
  out:

drivers/nvdimm/claim.c

@@ -243,7 +243,15 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	}
 
 	if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
-		if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)) {
+		/*
+		 * FIXME: nsio_rw_bytes() may be called from atomic
+		 * context in the btt case and nvdimm_clear_poison()
+		 * takes a sleeping lock. Until the locking can be
+		 * reworked this capability requires that the namespace
+		 * is not claimed by btt.
+		 */
+		if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)
+				&& (!ndns->claim || !is_nd_btt(ndns->claim))) {
 			long cleared;
 
 			cleared = nvdimm_clear_poison(&ndns->dev, offset, size);

drivers/nvdimm/dimm_devs.c

@@ -395,7 +395,7 @@ EXPORT_SYMBOL_GPL(nvdimm_create);
 
 int alias_dpa_busy(struct device *dev, void *data)
 {
-	resource_size_t map_end, blk_start, new, busy;
+	resource_size_t map_end, blk_start, new;
 	struct blk_alloc_info *info = data;
 	struct nd_mapping *nd_mapping;
 	struct nd_region *nd_region;
@@ -436,29 +436,19 @@ int alias_dpa_busy(struct device *dev, void *data)
  retry:
 	/*
 	 * Find the free dpa from the end of the last pmem allocation to
-	 * the end of the interleave-set mapping that is not already
-	 * covered by a blk allocation.
+	 * the end of the interleave-set mapping.
 	 */
-	busy = 0;
 	for_each_dpa_resource(ndd, res) {
+		if (strncmp(res->name, "pmem", 4) != 0)
+			continue;
 		if ((res->start >= blk_start && res->start < map_end)
 				|| (res->end >= blk_start
 					&& res->end <= map_end)) {
-			if (strncmp(res->name, "pmem", 4) == 0) {
-				new = max(blk_start, min(map_end + 1,
-							res->end + 1));
-				if (new != blk_start) {
-					blk_start = new;
-					goto retry;
-				}
-			} else
-				busy += min(map_end, res->end)
-					- max(nd_mapping->start, res->start) + 1;
-		} else if (nd_mapping->start > res->start
-				&& map_end < res->end) {
-			/* total eclipse of the PMEM region mapping */
-			busy += nd_mapping->size;
-			break;
+			new = max(blk_start, min(map_end + 1, res->end + 1));
+			if (new != blk_start) {
+				blk_start = new;
+				goto retry;
+			}
 		}
 	}
 
@@ -470,52 +460,11 @@ int alias_dpa_busy(struct device *dev, void *data)
 		return 1;
 	}
 
-	info->available -= blk_start - nd_mapping->start + busy;
+	info->available -= blk_start - nd_mapping->start;
 
 	return 0;
 }
 
-static int blk_dpa_busy(struct device *dev, void *data)
-{
-	struct blk_alloc_info *info = data;
-	struct nd_mapping *nd_mapping;
-	struct nd_region *nd_region;
-	resource_size_t map_end;
-	int i;
-
-	if (!is_nd_pmem(dev))
-		return 0;
-
-	nd_region = to_nd_region(dev);
-	for (i = 0; i < nd_region->ndr_mappings; i++) {
-		nd_mapping  = &nd_region->mapping[i];
-		if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
-			break;
-	}
-
-	if (i >= nd_region->ndr_mappings)
-		return 0;
-
-	map_end = nd_mapping->start + nd_mapping->size - 1;
-	if (info->res->start >= nd_mapping->start
-			&& info->res->start < map_end) {
-		if (info->res->end <= map_end) {
-			info->busy = 0;
-			return 1;
-		} else {
-			info->busy -= info->res->end - map_end;
-			return 0;
-		}
-	} else if (info->res->end >= nd_mapping->start
-			&& info->res->end <= map_end) {
-		info->busy -= nd_mapping->start - info->res->start;
-		return 0;
-	} else {
-		info->busy -= nd_mapping->size;
-		return 0;
-	}
-}
-
 /**
  * nd_blk_available_dpa - account the unused dpa of BLK region
  * @nd_mapping: container of dpa-resource-root + labels
@@ -545,11 +494,7 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
 	for_each_dpa_resource(ndd, res) {
 		if (strncmp(res->name, "blk", 3) != 0)
 			continue;
-
-		info.res = res;
-		info.busy = resource_size(res);
-		device_for_each_child(&nvdimm_bus->dev, &info, blk_dpa_busy);
-		info.available -= info.busy;
+		info.available -= resource_size(res);
 	}
 
 	return info.available;