Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "146 patches.

  Subsystems affected by this patch series: kthread, ia64, scripts,
  ntfs, squashfs, ocfs2, vfs, and mm (slab-generic, slab, kmemleak,
  dax, kasan, debug, pagecache, gup, shmem, frontswap, memremap,
  memcg, selftests, pagemap, dma, vmalloc, memory-failure, hugetlb,
  userfaultfd, vmscan, mempolicy, oom-kill, hugetlbfs, migration, thp,
  ksm, page-poison, percpu, rmap, zswap, zram, cleanups, hmm, and
  damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (146 commits)
  mm/damon: hide kernel pointer from tracepoint event
  mm/damon/vaddr: hide kernel pointer from damon_va_three_regions() failure log
  mm/damon/vaddr: use pr_debug() for damon_va_three_regions() failure logging
  mm/damon/dbgfs: remove an unnecessary variable
  mm/damon: move the implementation of damon_insert_region to damon.h
  mm/damon: add access checking for hugetlb pages
  Docs/admin-guide/mm/damon/usage: update for schemes statistics
  mm/damon/dbgfs: support all DAMOS stats
  Docs/admin-guide/mm/damon/reclaim: document statistics parameters
  mm/damon/reclaim: provide reclamation statistics
  mm/damon/schemes: account how many times quota limit has exceeded
  mm/damon/schemes: account scheme actions that successfully applied
  mm/damon: remove a mistakenly added comment for a future feature
  Docs/admin-guide/mm/damon/usage: update for kdamond_pid and (mk|rm)_contexts
  Docs/admin-guide/mm/damon/usage: mention tracepoint at the beginning
  Docs/admin-guide/mm/damon/usage: remove redundant information
  Docs/admin-guide/mm/damon/usage: update for scheme quotas and watermarks
  mm/damon: convert macro functions to static inline functions
  mm/damon: modify damon_rand() macro to static inline function
  mm/damon: move damon_rand() definition into damon.h
  ...

3 files changed, 109 insertions, 50 deletions

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index ee4568ef757c..1dad813ee4a6 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -127,11 +127,35 @@ ATTRIBUTE_GROUPS(dax_drv);
 
 static int dax_bus_match(struct device *dev, struct device_driver *drv);
 
+/*
+ * Static dax regions are regions created by an external subsystem
+ * nvdimm where a single range is assigned. Its boundaries are by the external
+ * subsystem and are usually limited to one physical memory range. For example,
+ * for PMEM it is usually defined by NVDIMM Namespace boundaries (i.e. a
+ * single contiguous range)
+ *
+ * On dynamic dax regions, the assigned region can be partitioned by dax core
+ * into multiple subdivisions. A subdivision is represented into one
+ * /dev/daxN.M device composed by one or more potentially discontiguous ranges.
+ *
+ * When allocating a dax region, drivers must set whether it's static
+ * (IORESOURCE_DAX_STATIC).  On static dax devices, the @pgmap is pre-assigned
+ * to dax core when calling devm_create_dev_dax(), whereas in dynamic dax
+ * devices it is NULL but afterwards allocated by dax core on device ->probe().
+ * Care is needed to make sure that dynamic dax devices are torn down with a
+ * cleared @pgmap field (see kill_dev_dax()).
+ */
 static bool is_static(struct dax_region *dax_region)
 {
 	return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0;
 }
 
+bool static_dev_dax(struct dev_dax *dev_dax)
+{
+	return is_static(dev_dax->region);
+}
+EXPORT_SYMBOL_GPL(static_dev_dax);
+
 static u64 dev_dax_size(struct dev_dax *dev_dax)
 {
 	u64 size = 0;
@@ -361,6 +385,14 @@ void kill_dev_dax(struct dev_dax *dev_dax)
 
 	kill_dax(dax_dev);
 	unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+	/*
+	 * Dynamic dax region have the pgmap allocated via dev_kzalloc()
+	 * and thus freed by devm. Clear the pgmap to not have stale pgmap
+	 * ranges on probe() from previous reconfigurations of region devices.
+	 */
+	if (!static_dev_dax(dev_dax))
+		dev_dax->pgmap = NULL;
 }
 EXPORT_SYMBOL_GPL(kill_dev_dax);
 
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index 381cec9ff05c..fbb940293d6d 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -39,6 +39,7 @@ int __dax_driver_register(struct dax_device_driver *dax_drv,
 	__dax_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)
 void dax_driver_unregister(struct dax_device_driver *dax_drv);
 void kill_dev_dax(struct dev_dax *dev_dax);
+bool static_dev_dax(struct dev_dax *dev_dax);
 
 /*
  * While run_dax() is potentially a generic operation that could be
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index e58d597f0415..d33a0613ed0c 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -73,11 +73,39 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 	return -1;
 }
 
+static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn,
+			      unsigned long fault_size)
+{
+	unsigned long i, nr_pages = fault_size / PAGE_SIZE;
+	struct file *filp = vmf->vma->vm_file;
+	struct dev_dax *dev_dax = filp->private_data;
+	pgoff_t pgoff;
+
+	/* mapping is only set on the head */
+	if (dev_dax->pgmap->vmemmap_shift)
+		nr_pages = 1;
+
+	pgoff = linear_page_index(vmf->vma,
+			ALIGN(vmf->address, fault_size));
+
+	for (i = 0; i < nr_pages; i++) {
+		struct page *page = pfn_to_page(pfn_t_to_pfn(pfn) + i);
+
+		page = compound_head(page);
+		if (page->mapping)
+			continue;
+
+		page->mapping = filp->f_mapping;
+		page->index = pgoff + i;
+	}
+}
+
 static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
-				struct vm_fault *vmf, pfn_t *pfn)
+				struct vm_fault *vmf)
 {
 	struct device *dev = &dev_dax->dev;
 	phys_addr_t phys;
+	pfn_t pfn;
 	unsigned int fault_size = PAGE_SIZE;
 
 	if (check_vma(dev_dax, vmf->vma, __func__))
@@ -98,18 +126,21 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
+	pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
 
-	return vmf_insert_mixed(vmf->vma, vmf->address, *pfn);
+	dax_set_mapping(vmf, pfn, fault_size);
+
+	return vmf_insert_mixed(vmf->vma, vmf->address, pfn);
 }
 
 static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
-				struct vm_fault *vmf, pfn_t *pfn)
+				struct vm_fault *vmf)
 {
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	struct device *dev = &dev_dax->dev;
 	phys_addr_t phys;
 	pgoff_t pgoff;
+	pfn_t pfn;
 	unsigned int fault_size = PMD_SIZE;
 
 	if (check_vma(dev_dax, vmf->vma, __func__))
@@ -138,19 +169,22 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
+	pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
 
-	return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
+	dax_set_mapping(vmf, pfn, fault_size);
+
+	return vmf_insert_pfn_pmd(vmf, pfn, vmf->flags & FAULT_FLAG_WRITE);
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
-				struct vm_fault *vmf, pfn_t *pfn)
+				struct vm_fault *vmf)
 {
 	unsigned long pud_addr = vmf->address & PUD_MASK;
 	struct device *dev = &dev_dax->dev;
 	phys_addr_t phys;
 	pgoff_t pgoff;
+	pfn_t pfn;
 	unsigned int fault_size = PUD_SIZE;
 
 
@@ -180,13 +214,15 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	*pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
+	pfn = phys_to_pfn_t(phys, PFN_DEV|PFN_MAP);
 
-	return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
+	dax_set_mapping(vmf, pfn, fault_size);
+
+	return vmf_insert_pfn_pud(vmf, pfn, vmf->flags & FAULT_FLAG_WRITE);
 }
 #else
 static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
-				struct vm_fault *vmf, pfn_t *pfn)
+				struct vm_fault *vmf)
 {
 	return VM_FAULT_FALLBACK;
 }
@@ -196,10 +232,8 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
 	struct file *filp = vmf->vma->vm_file;
-	unsigned long fault_size;
 	vm_fault_t rc = VM_FAULT_SIGBUS;
 	int id;
-	pfn_t pfn;
 	struct dev_dax *dev_dax = filp->private_data;
 
 	dev_dbg(&dev_dax->dev, "%s: %s (%#lx - %#lx) size = %d\n", current->comm,
@@ -209,43 +243,18 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
 	id = dax_read_lock();
 	switch (pe_size) {
 	case PE_SIZE_PTE:
-		fault_size = PAGE_SIZE;
-		rc = __dev_dax_pte_fault(dev_dax, vmf, &pfn);
+		rc = __dev_dax_pte_fault(dev_dax, vmf);
 		break;
 	case PE_SIZE_PMD:
-		fault_size = PMD_SIZE;
-		rc = __dev_dax_pmd_fault(dev_dax, vmf, &pfn);
+		rc = __dev_dax_pmd_fault(dev_dax, vmf);
 		break;
 	case PE_SIZE_PUD:
-		fault_size = PUD_SIZE;
-		rc = __dev_dax_pud_fault(dev_dax, vmf, &pfn);
+		rc = __dev_dax_pud_fault(dev_dax, vmf);
 		break;
 	default:
 		rc = VM_FAULT_SIGBUS;
 	}
 
-	if (rc == VM_FAULT_NOPAGE) {
-		unsigned long i;
-		pgoff_t pgoff;
-
-		/*
-		 * In the device-dax case the only possibility for a
-		 * VM_FAULT_NOPAGE result is when device-dax capacity is
-		 * mapped. No need to consider the zero page, or racing
-		 * conflicting mappings.
-		 */
-		pgoff = linear_page_index(vmf->vma, vmf->address
-				& ~(fault_size - 1));
-		for (i = 0; i < fault_size / PAGE_SIZE; i++) {
-			struct page *page;
-
-			page = pfn_to_page(pfn_t_to_pfn(pfn) + i);
-			if (page->mapping)
-				continue;
-			page->mapping = filp->f_mapping;
-			page->index = pgoff + i;
-		}
-	}
 	dax_read_unlock(id);
 
 	return rc;
@@ -398,17 +407,34 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 	void *addr;
 	int rc, i;
 
-	pgmap = dev_dax->pgmap;
-	if (dev_WARN_ONCE(dev, pgmap && dev_dax->nr_range > 1,
-			"static pgmap / multi-range device conflict\n"))
-		return -EINVAL;
+	if (static_dev_dax(dev_dax))  {
+		if (dev_dax->nr_range > 1) {
+			dev_warn(dev,
+				"static pgmap / multi-range device conflict\n");
+			return -EINVAL;
+		}
 
-	if (!pgmap) {
-		pgmap = devm_kzalloc(dev, sizeof(*pgmap) + sizeof(struct range)
-				* (dev_dax->nr_range - 1), GFP_KERNEL);
+		pgmap = dev_dax->pgmap;
+	} else {
+		if (dev_dax->pgmap) {
+			dev_warn(dev,
+				 "dynamic-dax with pre-populated page map\n");
+			return -EINVAL;
+		}
+
+		pgmap = devm_kzalloc(dev,
+                       struct_size(pgmap, ranges, dev_dax->nr_range - 1),
+                       GFP_KERNEL);
 		if (!pgmap)
 			return -ENOMEM;
+
 		pgmap->nr_range = dev_dax->nr_range;
+		dev_dax->pgmap = pgmap;
+
+		for (i = 0; i < dev_dax->nr_range; i++) {
+			struct range *range = &dev_dax->ranges[i].range;
+			pgmap->ranges[i] = *range;
+		}
 	}
 
 	for (i = 0; i < dev_dax->nr_range; i++) {
@@ -420,12 +446,12 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 					i, range->start, range->end);
 			return -EBUSY;
 		}
-		/* don't update the range for static pgmap */
-		if (!dev_dax->pgmap)
-			pgmap->ranges[i] = *range;
 	}
 
 	pgmap->type = MEMORY_DEVICE_GENERIC;
+	if (dev_dax->align > PAGE_SIZE)
+		pgmap->vmemmap_shift =
+			order_base_2(dev_dax->align >> PAGE_SHIFT);
 	addr = devm_memremap_pages(dev, pgmap);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);