[HMM v13 02/18] mm/ZONE_DEVICE/unaddressable: add support for un-addressable device memory

[JÃrÃme Glisse]

This add support for un-addressable device memory. Such memory is hotpluged
only so we can have struct page but should never be map. This patch add code
to mm page fault code path to catch any such mapping and SIGBUS on such event.

Signed-off-by: JÃrÃme Glisse <jglisse@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
---
 drivers/dax/pmem.c                |  3 ++-
 drivers/nvdimm/pmem.c             |  5 +++--
 include/linux/memremap.h          | 23 ++++++++++++++++++++---
 kernel/memremap.c                 | 12 +++++++++---
 mm/memory.c                       |  9 +++++++++
 tools/testing/nvdimm/test/iomap.c |  2 +-
 6 files changed, 44 insertions(+), 10 deletions(-)

diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 1f01e98..1b42aef 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -107,7 +107,8 @@ static int dax_pmem_probe(struct device *dev)
 	if (rc)
 		return rc;
 
-	addr = devm_memremap_pages(dev, &res, &dax_pmem->ref, altmap);
+	addr = devm_memremap_pages(dev, &res, &dax_pmem->ref,
+				   altmap, NULL, MEMORY_DEVICE);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 571a6c7..5ffd937 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -260,7 +260,7 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->pfn_flags = PFN_DEV;
 	if (is_nd_pfn(dev)) {
 		addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter,
-				altmap);
+					   altmap, NULL, MEMORY_DEVICE);
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
 		pmem->pfn_pad = resource_size(res) - resource_size(&pfn_res);
@@ -269,7 +269,8 @@ static int pmem_attach_disk(struct device *dev,
 		res->start += pmem->data_offset;
 	} else if (pmem_should_map_pages(dev)) {
 		addr = devm_memremap_pages(dev, &nsio->res,
-				&q->q_usage_counter, NULL);
+					   &q->q_usage_counter,
+					   NULL, NULL, MEMORY_DEVICE);
 		pmem->pfn_flags |= PFN_MAP;
 	} else
 		addr = devm_memremap(dev, pmem->phys_addr,
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 9341619..fe61dca 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -41,22 +41,34 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
  * @res: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
  * @dev: host device of the mapping for debug
+ * @flags: memory flags (look for MEMORY_FLAGS_NONE in memory_hotplug.h)
  */
 struct dev_pagemap {
 	struct vmem_altmap *altmap;
 	const struct resource *res;
 	struct percpu_ref *ref;
 	struct device *dev;
+	int flags;
 };
 
 #ifdef CONFIG_ZONE_DEVICE
 void *devm_memremap_pages(struct device *dev, struct resource *res,
-		struct percpu_ref *ref, struct vmem_altmap *altmap);
+			  struct percpu_ref *ref, struct vmem_altmap *altmap,
+			  struct dev_pagemap **ppgmap, int flags);
 struct dev_pagemap *find_dev_pagemap(resource_size_t phys);
+
+static inline bool is_addressable_page(const struct page *page)
+{
+	return ((page_zonenum(page) != ZONE_DEVICE) ||
+		!(page->pgmap->flags & MEMORY_UNADDRESSABLE));
+}
 #else
 static inline void *devm_memremap_pages(struct device *dev,
-		struct resource *res, struct percpu_ref *ref,
-		struct vmem_altmap *altmap)
+					struct resource *res,
+					struct percpu_ref *ref,
+					struct vmem_altmap *altmap,
+					struct dev_pagemap **ppgmap,
+					int flags)
 {
 	/*
 	 * Fail attempts to call devm_memremap_pages() without
@@ -71,6 +83,11 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 {
 	return NULL;
 }
+
+static inline bool is_addressable_page(const struct page *page)
+{
+	return true;
+}
 #endif
 
 /**
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 07665eb..438a73aa2 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -246,7 +246,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
-	arch_remove_memory(align_start, align_size, MEMORY_DEVICE);
+	arch_remove_memory(align_start, align_size, pgmap->flags);
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
 	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
@@ -270,6 +270,8 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
  * @res: "host memory" address range
  * @ref: a live per-cpu reference count
  * @altmap: optional descriptor for allocating the memmap from @res
+ * @ppgmap: pointer set to new page dev_pagemap on success
+ * @flags: flag for memory (look for MEMORY_FLAGS_NONE in memory_hotplug.h)
  *
  * Notes:
  * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
@@ -280,7 +282,8 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
  *    this is not enforced.
  */
 void *devm_memremap_pages(struct device *dev, struct resource *res,
-		struct percpu_ref *ref, struct vmem_altmap *altmap)
+			  struct percpu_ref *ref, struct vmem_altmap *altmap,
+			  struct dev_pagemap **ppgmap, int flags)
 {
 	resource_size_t key, align_start, align_size, align_end;
 	pgprot_t pgprot = PAGE_KERNEL;
@@ -322,6 +325,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	}
 	pgmap->ref = ref;
 	pgmap->res = &page_map->res;
+	pgmap->flags = flags | MEMORY_DEVICE;
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
@@ -358,7 +362,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (error)
 		goto err_pfn_remap;
 
-	error = arch_add_memory(nid, align_start, align_size, MEMORY_DEVICE);
+	error = arch_add_memory(nid, align_start, align_size, pgmap->flags);
 	if (error)
 		goto err_add_memory;
 
@@ -375,6 +379,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		page->pgmap = pgmap;
 	}
 	devres_add(dev, page_map);
+	if (ppgmap)
+		*ppgmap = pgmap;
 	return __va(res->start);
 
  err_add_memory:
diff --git a/mm/memory.c b/mm/memory.c
index 840adc6..15f2908 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -45,6 +45,7 @@
 #include <linux/swap.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/memremap.h>
 #include <linux/ksm.h>
 #include <linux/rmap.h>
 #include <linux/export.h>
@@ -3482,6 +3483,7 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma)
 static int handle_pte_fault(struct fault_env *fe)
 {
 	pte_t entry;
+	struct page *page;
 
 	if (unlikely(pmd_none(*fe->pmd))) {
 		/*
@@ -3533,6 +3535,13 @@ static int handle_pte_fault(struct fault_env *fe)
 	if (pte_protnone(entry) && vma_is_accessible(fe->vma))
 		return do_numa_page(fe, entry);
 
+	/* Catch mapping of un-addressable memory this should never happen */
+	page = pfn_to_page(pte_pfn(entry));
+	if (!is_addressable_page(page)) {
+		print_bad_pte(fe->vma, fe->address, entry, page);
+		return VM_FAULT_SIGBUS;
+	}
+
 	fe->ptl = pte_lockptr(fe->vma->vm_mm, fe->pmd);
 	spin_lock(fe->ptl);
 	if (unlikely(!pte_same(*fe->pte, entry)))
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index c29f8dc..899d6a8 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -108,7 +108,7 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res,
 
 	if (nfit_res)
 		return nfit_res->buf + offset - nfit_res->res->start;
-	return devm_memremap_pages(dev, res, ref, altmap);
+	return devm_memremap_pages(dev, res, ref, altmap, MEMORY_DEVICE);
 }
 EXPORT_SYMBOL(__wrap_devm_memremap_pages);
 
-- 
2.4.3