From 24e6d5a59ac7d31adc0322de2d0117dfa370936f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:53:53 +0100
Subject: mm: pass the vmem_altmap to arch_add_memory and __add_pages

We can just pass this on instead of having to do a radix tree lookup
without proper locking 2 levels into the callchain.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 kernel/memremap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 403ab9cdb949..8488cdeead16 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -382,6 +382,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (altmap) {
 		memcpy(&page_map->altmap, altmap, sizeof(*altmap));
 		pgmap->altmap = &page_map->altmap;
+		altmap = pgmap->altmap;
 	}
 	pgmap->ref = ref;
 	pgmap->res = &page_map->res;
@@ -427,7 +428,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		goto err_pfn_remap;
 
 	mem_hotplug_begin();
-	error = arch_add_memory(nid, align_start, align_size, false);
+	error = arch_add_memory(nid, align_start, align_size, altmap, false);
 	if (!error)
 		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 					align_start >> PAGE_SHIFT,
-- 
cgit v1.2.3


From da024512a1fa5c979257e442130ee1d468285057 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:53:55 +0100
Subject: mm: pass the vmem_altmap to arch_remove_memory and __remove_pages

We can just pass this on instead of having to do a radix tree lookup
without proper locking 2 levels into the callchain.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/ia64/mm/init.c            | 4 ++--
 arch/powerpc/mm/mem.c          | 6 ++----
 arch/s390/mm/init.c            | 2 +-
 arch/sh/mm/init.c              | 4 ++--
 arch/x86/mm/init_32.c          | 4 ++--
 arch/x86/mm/init_64.c          | 6 ++----
 include/linux/memory_hotplug.h | 5 +++--
 kernel/memremap.c              | 2 +-
 mm/hmm.c                       | 4 ++--
 mm/memory_hotplug.c            | 8 ++------
 10 files changed, 19 insertions(+), 26 deletions(-)

(limited to 'kernel')

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 2e2e4f532204..6a8ce9e1536e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -663,7 +663,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size)
+int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -671,7 +671,7 @@ int arch_remove_memory(u64 start, u64 size)
 	int ret;
 
 	zone = page_zone(pfn_to_page(start_pfn));
-	ret = __remove_pages(zone, start_pfn, nr_pages);
+	ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
 	if (ret)
 		pr_warn("%s: Problem encountered in __remove_pages() as"
 			" ret=%d\n", __func__,  ret);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index e670cfc2766e..22aa528b78a2 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -149,11 +149,10 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size)
+int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct vmem_altmap *altmap;
 	struct page *page;
 	int ret;
 
@@ -162,11 +161,10 @@ int arch_remove_memory(u64 start, u64 size)
 	 * when querying the zone.
 	 */
 	page = pfn_to_page(start_pfn);
-	altmap = to_vmem_altmap((unsigned long) page);
 	if (altmap)
 		page += vmem_altmap_offset(altmap);
 
-	ret = __remove_pages(page_zone(page), start_pfn, nr_pages);
+	ret = __remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
 	if (ret)
 		return ret;
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index e12c5af50cd7..3fa3e5323612 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -240,7 +240,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size)
+int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	/*
 	 * There is no hardware or firmware interface which could trigger a
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 552afbf55bad..ce0bbaa7e404 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -510,7 +510,7 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size)
+int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -518,7 +518,7 @@ int arch_remove_memory(u64 start, u64 size)
 	int ret;
 
 	zone = page_zone(pfn_to_page(start_pfn));
-	ret = __remove_pages(zone, start_pfn, nr_pages);
+	ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
 	if (unlikely(ret))
 		pr_warn("%s: Failed, __remove_pages() == %d\n", __func__,
 			ret);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8a3091511a71..79cb066f40c0 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -839,14 +839,14 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size)
+int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct zone *zone;
 
 	zone = page_zone(pfn_to_page(start_pfn));
-	return __remove_pages(zone, start_pfn, nr_pages);
+	return __remove_pages(zone, start_pfn, nr_pages, altmap);
 }
 #endif
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 594902ef56ef..3c046618cc7e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1132,21 +1132,19 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 	remove_pagetable(start, end, true);
 }
 
-int __ref arch_remove_memory(u64 start, u64 size)
+int __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct page *page = pfn_to_page(start_pfn);
-	struct vmem_altmap *altmap;
 	struct zone *zone;
 	int ret;
 
 	/* With altmap the first mapped page is offset from @start */
-	altmap = to_vmem_altmap((unsigned long) page);
 	if (altmap)
 		page += vmem_altmap_offset(altmap);
 	zone = page_zone(page);
-	ret = __remove_pages(zone, start_pfn, nr_pages);
+	ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
 	WARN_ON_ONCE(ret);
 	kernel_physical_mapping_remove(start, start + size);
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index cbdd6d52e877..e71927d0d46b 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -126,9 +126,10 @@ static inline bool movable_node_is_enabled(void)
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern bool is_pageblock_removable_nolock(struct page *page);
-extern int arch_remove_memory(u64 start, u64 size);
+extern int arch_remove_memory(u64 start, u64 size,
+		struct vmem_altmap *altmap);
 extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
-	unsigned long nr_pages);
+	unsigned long nr_pages, struct vmem_altmap *altmap);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 /* reasonably generic interface to expand the physical pages */
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 8488cdeead16..380fca1c4a02 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -304,7 +304,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 
 	mem_hotplug_begin();
-	arch_remove_memory(align_start, align_size);
+	arch_remove_memory(align_start, align_size, pgmap->altmap);
 	mem_hotplug_done();
 
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
diff --git a/mm/hmm.c b/mm/hmm.c
index 231aaacd1997..5d17ba89062f 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -838,10 +838,10 @@ static void hmm_devmem_release(struct device *dev, void *data)
 
 	mem_hotplug_begin();
 	if (resource->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY)
-		__remove_pages(zone, start_pfn, npages);
+		__remove_pages(zone, start_pfn, npages, NULL);
 	else
 		arch_remove_memory(start_pfn << PAGE_SHIFT,
-				   npages << PAGE_SHIFT);
+				   npages << PAGE_SHIFT, NULL);
 	mem_hotplug_done();
 
 	hmm_devmem_radix_release(resource);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b36f1822c432..eae6bf47caf7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -569,7 +569,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms,
  * calling offline_pages().
  */
 int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
-		 unsigned long nr_pages)
+		 unsigned long nr_pages, struct vmem_altmap *altmap)
 {
 	unsigned long i;
 	unsigned long map_offset = 0;
@@ -577,10 +577,6 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 
 	/* In the ZONE_DEVICE case device driver owns the memory region */
 	if (is_dev_zone(zone)) {
-		struct page *page = pfn_to_page(phys_start_pfn);
-		struct vmem_altmap *altmap;
-
-		altmap = to_vmem_altmap((unsigned long) page);
 		if (altmap)
 			map_offset = vmem_altmap_offset(altmap);
 	} else {
@@ -1890,7 +1886,7 @@ void __ref remove_memory(int nid, u64 start, u64 size)
 	memblock_free(start, size);
 	memblock_remove(start, size);
 
-	arch_remove_memory(start, size);
+	arch_remove_memory(start, size, NULL);
 
 	try_offline_node(nid);
 
-- 
cgit v1.2.3


From a99583e780c751003ac9c0105eec9a3b23ec3bc4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:53:57 +0100
Subject: mm: pass the vmem_altmap to memmap_init_zone

Pass the vmem_altmap two levels down instead of needing a lookup.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/ia64/mm/init.c            | 9 +++++----
 include/linux/memory_hotplug.h | 2 +-
 include/linux/mm.h             | 4 ++--
 kernel/memremap.c              | 2 +-
 mm/hmm.c                       | 2 +-
 mm/memory_hotplug.c            | 9 +++++----
 mm/page_alloc.c                | 6 +++---
 7 files changed, 18 insertions(+), 16 deletions(-)

(limited to 'kernel')

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 6a8ce9e1536e..18278b448530 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -501,7 +501,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
 				 args->nid, args->zone, page_to_pfn(map_start),
-				 MEMMAP_EARLY);
+				 MEMMAP_EARLY, NULL);
 	return 0;
 }
 
@@ -509,9 +509,10 @@ void __meminit
 memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
-	if (!vmem_map)
-		memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY);
-	else {
+	if (!vmem_map) {
+		memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY,
+				NULL);
+	} else {
 		struct page *start;
 		struct memmap_init_callback_data args;
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 20dd98ad44a0..aba5f86eb038 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -324,7 +324,7 @@ extern int add_memory_resource(int nid, struct resource *resource, bool online);
 extern int arch_add_memory(int nid, u64 start, u64 size,
 		struct vmem_altmap *altmap, bool want_memblock);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
-		unsigned long nr_pages);
+		unsigned long nr_pages, struct vmem_altmap *altmap);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern void remove_memory(int nid, u64 start, u64 size);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9d4cd4c1dc6d..fd01135324b6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2069,8 +2069,8 @@ static inline void zero_resv_unavail(void) {}
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long,
-				unsigned long, enum memmap_context);
+extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
+		enum memmap_context, struct vmem_altmap *);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 380fca1c4a02..64b12c806cc5 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -432,7 +432,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (!error)
 		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 					align_start >> PAGE_SHIFT,
-					align_size >> PAGE_SHIFT);
+					align_size >> PAGE_SHIFT, altmap);
 	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;
diff --git a/mm/hmm.c b/mm/hmm.c
index 5d17ba89062f..2f2e13c61040 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -942,7 +942,7 @@ static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
 	}
 	move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT);
+				align_size >> PAGE_SHIFT, NULL);
 	mem_hotplug_done();
 
 	for (pfn = devmem->pfn_first; pfn < devmem->pfn_last; pfn++) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a8dde9734120..12df8a5fadcc 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -798,8 +798,8 @@ static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned lon
 	pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn;
 }
 
-void __ref move_pfn_range_to_zone(struct zone *zone,
-		unsigned long start_pfn, unsigned long nr_pages)
+void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
+		unsigned long nr_pages, struct vmem_altmap *altmap)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	int nid = pgdat->node_id;
@@ -824,7 +824,8 @@ void __ref move_pfn_range_to_zone(struct zone *zone,
 	 * expects the zone spans the pfn range. All the pages in the range
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
-	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, MEMMAP_HOTPLUG);
+	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
+			MEMMAP_HOTPLUG, altmap);
 
 	set_zone_contiguous(zone);
 }
@@ -896,7 +897,7 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid,
 	struct zone *zone;
 
 	zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
-	move_pfn_range_to_zone(zone, start_pfn, nr_pages);
+	move_pfn_range_to_zone(zone, start_pfn, nr_pages, NULL);
 	return zone;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7e5e775e97f4..1748dd4a4b1b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5314,9 +5314,9 @@ void __ref build_all_zonelists(pg_data_t *pgdat)
  * done. Non-atomic initialization, single-pass.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn, enum memmap_context context)
+		unsigned long start_pfn, enum memmap_context context,
+		struct vmem_altmap *altmap)
 {
-	struct vmem_altmap *altmap = to_vmem_altmap(__pfn_to_phys(start_pfn));
 	unsigned long end_pfn = start_pfn + size;
 	pg_data_t *pgdat = NODE_DATA(nid);
 	unsigned long pfn;
@@ -5417,7 +5417,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 
 #ifndef __HAVE_ARCH_MEMMAP_INIT
 #define memmap_init(size, nid, zone, start_pfn) \
-	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
+	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY, NULL)
 #endif
 
 static int zone_batchsize(struct zone *zone)
-- 
cgit v1.2.3


From 0822acb86cf340cd45b3af6436cec7e3bb24ebd2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:54:00 +0100
Subject: mm: move get_dev_pagemap out of line
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is a pretty big function, which should be out of line in general,
and a no-op stub if CONFIG_ZONE_DEVICЕ is not set.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/memremap.h | 39 ++++-----------------------------------
 kernel/memremap.c        | 36 ++++++++++++++++++++++++++++++++++--
 2 files changed, 38 insertions(+), 37 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index d5a6736d9737..26e8aaba27d5 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -133,7 +133,8 @@ struct dev_pagemap {
 #ifdef CONFIG_ZONE_DEVICE
 void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap);
-struct dev_pagemap *find_dev_pagemap(resource_size_t phys);
+struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
+		struct dev_pagemap *pgmap);
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
@@ -153,7 +154,8 @@ static inline void *devm_memremap_pages(struct device *dev,
 	return ERR_PTR(-ENXIO);
 }
 
-static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
+static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
+		struct dev_pagemap *pgmap)
 {
 	return NULL;
 }
@@ -183,39 +185,6 @@ static inline bool is_device_public_page(const struct page *page)
 }
 #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
 
-/**
- * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
- * @pfn: page frame number to lookup page_map
- * @pgmap: optional known pgmap that already has a reference
- *
- * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the
- * same mapping.
- */
-static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
-		struct dev_pagemap *pgmap)
-{
-	const struct resource *res = pgmap ? pgmap->res : NULL;
-	resource_size_t phys = PFN_PHYS(pfn);
-
-	/*
-	 * In the cached case we're already holding a live reference so
-	 * we can simply do a blind increment
-	 */
-	if (res && phys >= res->start && phys <= res->end) {
-		percpu_ref_get(pgmap->ref);
-		return pgmap;
-	}
-
-	/* fall back to slow path lookup */
-	rcu_read_lock();
-	pgmap = find_dev_pagemap(phys);
-	if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
-		pgmap = NULL;
-	rcu_read_unlock();
-
-	return pgmap;
-}
-
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
 {
 	if (pgmap)
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 64b12c806cc5..3df6cd4ffb40 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -314,7 +314,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 }
 
 /* assumes rcu_read_lock() held at entry */
-struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
+static struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 {
 	struct page_map *page_map;
 
@@ -501,8 +501,40 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
 
 	return pgmap ? pgmap->altmap : NULL;
 }
-#endif /* CONFIG_ZONE_DEVICE */
 
+/**
+ * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
+ * @pfn: page frame number to lookup page_map
+ * @pgmap: optional known pgmap that already has a reference
+ *
+ * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the
+ * same mapping.
+ */
+struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
+		struct dev_pagemap *pgmap)
+{
+	const struct resource *res = pgmap ? pgmap->res : NULL;
+	resource_size_t phys = PFN_PHYS(pfn);
+
+	/*
+	 * In the cached case we're already holding a live reference so
+	 * we can simply do a blind increment
+	 */
+	if (res && phys >= res->start && phys <= res->end) {
+		percpu_ref_get(pgmap->ref);
+		return pgmap;
+	}
+
+	/* fall back to slow path lookup */
+	rcu_read_lock();
+	pgmap = find_dev_pagemap(phys);
+	if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
+		pgmap = NULL;
+	rcu_read_unlock();
+
+	return pgmap;
+}
+#endif /* CONFIG_ZONE_DEVICE */
 
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
 void put_zone_device_private_or_public_page(struct page *page)
-- 
cgit v1.2.3


From 832d7aa051106c927cae05ced29d3fd31459ed21 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:54:01 +0100
Subject: mm: optimize dev_pagemap reference counting around get_dev_pagemap

Change the calling convention so that get_dev_pagemap always consumes the
previous reference instead of doing this using an explicit earlier call to
put_dev_pagemap in the callers.

The callers will still need to put the final reference after finishing the
loop over the pages.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 kernel/memremap.c | 17 +++++++++--------
 mm/gup.c          |  7 +++++--
 2 files changed, 14 insertions(+), 10 deletions(-)

(limited to 'kernel')

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 3df6cd4ffb40..891c77487a6a 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -507,22 +507,23 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
  * @pfn: page frame number to lookup page_map
  * @pgmap: optional known pgmap that already has a reference
  *
- * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the
- * same mapping.
+ * If @pgmap is non-NULL and covers @pfn it will be returned as-is.  If @pgmap
+ * is non-NULL but does not cover @pfn the reference to it will be released.
  */
 struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 		struct dev_pagemap *pgmap)
 {
-	const struct resource *res = pgmap ? pgmap->res : NULL;
 	resource_size_t phys = PFN_PHYS(pfn);
 
 	/*
-	 * In the cached case we're already holding a live reference so
-	 * we can simply do a blind increment
+	 * In the cached case we're already holding a live reference.
 	 */
-	if (res && phys >= res->start && phys <= res->end) {
-		percpu_ref_get(pgmap->ref);
-		return pgmap;
+	if (pgmap) {
+		const struct resource *res = pgmap ? pgmap->res : NULL;
+
+		if (res && phys >= res->start && phys <= res->end)
+			return pgmap;
+		put_dev_pagemap(pgmap);
 	}
 
 	/* fall back to slow path lookup */
diff --git a/mm/gup.c b/mm/gup.c
index e0d82b6706d7..3affe7544b0c 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1410,7 +1410,6 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 
-		put_dev_pagemap(pgmap);
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
@@ -1420,6 +1419,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 	ret = 1;
 
 pte_unmap:
+	if (pgmap)
+		put_dev_pagemap(pgmap);
 	pte_unmap(ptem);
 	return ret;
 }
@@ -1459,10 +1460,12 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		get_page(page);
-		put_dev_pagemap(pgmap);
 		(*nr)++;
 		pfn++;
 	} while (addr += PAGE_SIZE, addr != end);
+
+	if (pgmap)
+		put_dev_pagemap(pgmap);
 	return 1;
 }
 
-- 
cgit v1.2.3


From 0628b8c650718f4dfedfcdc9ed136bf7e394aae7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:54:02 +0100
Subject: memremap: remove to_vmem_altmap

All callers are gone now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/memremap.h |  9 ---------
 kernel/memremap.c        | 26 --------------------------
 2 files changed, 35 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 26e8aaba27d5..3fddcfe57bb0 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -26,15 +26,6 @@ struct vmem_altmap {
 	unsigned long alloc;
 };
 
-#ifdef CONFIG_ZONE_DEVICE
-struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start);
-#else
-static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
-{
-	return NULL;
-}
-#endif
-
 /*
  * Specialize ZONE_DEVICE memory into multiple types each having differents
  * usage.
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 891c77487a6a..b09517439dec 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -476,32 +476,6 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
 	altmap->alloc -= nr_pfns;
 }
 
-struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
-{
-	/*
-	 * 'memmap_start' is the virtual address for the first "struct
-	 * page" in this range of the vmemmap array.  In the case of
-	 * CONFIG_SPARSEMEM_VMEMMAP a page_to_pfn conversion is simple
-	 * pointer arithmetic, so we can perform this to_vmem_altmap()
-	 * conversion without concern for the initialization state of
-	 * the struct page fields.
-	 */
-	struct page *page = (struct page *) memmap_start;
-	struct dev_pagemap *pgmap;
-
-	/*
-	 * Unconditionally retrieve a dev_pagemap associated with the
-	 * given physical address, this is only for use in the
-	 * arch_{add|remove}_memory() for setting up and tearing down
-	 * the memmap.
-	 */
-	rcu_read_lock();
-	pgmap = find_dev_pagemap(__pfn_to_phys(page_to_pfn(page)));
-	rcu_read_unlock();
-
-	return pgmap ? pgmap->altmap : NULL;
-}
-
 /**
  * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
  * @pfn: page frame number to lookup page_map
-- 
cgit v1.2.3


From 7003e3b1f64d0195ea9d31aed0b096ad38f3cb54 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:54:03 +0100
Subject: memremap: simplify duplicate region handling in devm_memremap_pages

__radix_tree_insert already checks for duplicates and returns -EEXIST in
that case, so remove the duplicate (and racy) duplicates check.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 kernel/memremap.c | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'kernel')

diff --git a/kernel/memremap.c b/kernel/memremap.c
index b09517439dec..12e78528fea4 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -396,17 +396,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	align_end = align_start + align_size - 1;
 
 	foreach_order_pgoff(res, order, pgoff) {
-		struct dev_pagemap *dup;
-
-		rcu_read_lock();
-		dup = find_dev_pagemap(res->start + PFN_PHYS(pgoff));
-		rcu_read_unlock();
-		if (dup) {
-			dev_err(dev, "%s: %pr collides with mapping for %s\n",
-					__func__, res, dev_name(dup->dev));
-			error = -EBUSY;
-			break;
-		}
 		error = __radix_tree_insert(&pgmap_radix,
 				PHYS_PFN(res->start) + pgoff, order, page_map);
 		if (error) {
-- 
cgit v1.2.3


From e7744aa25cffe26d3767c9ffcf4e130cca1dff00 Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Fri, 29 Dec 2017 08:54:04 +0100
Subject: memremap: drop private struct page_map

'struct page_map' is a private structure of 'struct dev_pagemap' but the
latter replicates all the same fields as the former so there isn't much
value in it. Thus drop it in favour of a completely public struct.

This is a clean up in preperation for a more generally useful
'devm_memeremap_pages' interface.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/memremap.h |  5 ++--
 kernel/memremap.c        | 68 ++++++++++++++++++------------------------------
 mm/hmm.c                 |  2 +-
 3 files changed, 30 insertions(+), 45 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 3fddcfe57bb0..1cb5f39d25c1 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -113,8 +113,9 @@ typedef void (*dev_page_free_t)(struct page *page, void *data);
 struct dev_pagemap {
 	dev_page_fault_t page_fault;
 	dev_page_free_t page_free;
-	struct vmem_altmap *altmap;
-	const struct resource *res;
+	struct vmem_altmap altmap;
+	bool altmap_valid;
+	struct resource res;
 	struct percpu_ref *ref;
 	struct device *dev;
 	void *data;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 12e78528fea4..9207c44cce20 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -188,13 +188,6 @@ static RADIX_TREE(pgmap_radix, GFP_KERNEL);
 #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
 #define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
 
-struct page_map {
-	struct resource res;
-	struct percpu_ref *ref;
-	struct dev_pagemap pgmap;
-	struct vmem_altmap altmap;
-};
-
 static unsigned long order_at(struct resource *res, unsigned long pgoff)
 {
 	unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
@@ -260,22 +253,21 @@ static void pgmap_radix_release(struct resource *res)
 	synchronize_rcu();
 }
 
-static unsigned long pfn_first(struct page_map *page_map)
+static unsigned long pfn_first(struct dev_pagemap *pgmap)
 {
-	struct dev_pagemap *pgmap = &page_map->pgmap;
-	const struct resource *res = &page_map->res;
-	struct vmem_altmap *altmap = pgmap->altmap;
+	const struct resource *res = &pgmap->res;
+	struct vmem_altmap *altmap = &pgmap->altmap;
 	unsigned long pfn;
 
 	pfn = res->start >> PAGE_SHIFT;
-	if (altmap)
+	if (pgmap->altmap_valid)
 		pfn += vmem_altmap_offset(altmap);
 	return pfn;
 }
 
-static unsigned long pfn_end(struct page_map *page_map)
+static unsigned long pfn_end(struct dev_pagemap *pgmap)
 {
-	const struct resource *res = &page_map->res;
+	const struct resource *res = &pgmap->res;
 
 	return (res->start + resource_size(res)) >> PAGE_SHIFT;
 }
@@ -285,13 +277,12 @@ static unsigned long pfn_end(struct page_map *page_map)
 
 static void devm_memremap_pages_release(struct device *dev, void *data)
 {
-	struct page_map *page_map = data;
-	struct resource *res = &page_map->res;
+	struct dev_pagemap *pgmap = data;
+	struct resource *res = &pgmap->res;
 	resource_size_t align_start, align_size;
-	struct dev_pagemap *pgmap = &page_map->pgmap;
 	unsigned long pfn;
 
-	for_each_device_pfn(pfn, page_map)
+	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
 
 	if (percpu_ref_tryget_live(pgmap->ref)) {
@@ -304,24 +295,22 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 
 	mem_hotplug_begin();
-	arch_remove_memory(align_start, align_size, pgmap->altmap);
+	arch_remove_memory(align_start, align_size, pgmap->altmap_valid ?
+			&pgmap->altmap : NULL);
 	mem_hotplug_done();
 
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
-	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
-			"%s: failed to free all reserved pages\n", __func__);
+	dev_WARN_ONCE(dev, pgmap->altmap.alloc,
+		      "%s: failed to free all reserved pages\n", __func__);
 }
 
 /* assumes rcu_read_lock() held at entry */
 static struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 {
-	struct page_map *page_map;
-
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	page_map = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
-	return page_map ? &page_map->pgmap : NULL;
+	return radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
 }
 
 /**
@@ -349,7 +338,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
-	struct page_map *page_map;
 	int error, nid, is_ram, i = 0;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
@@ -370,22 +358,20 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (!ref)
 		return ERR_PTR(-EINVAL);
 
-	page_map = devres_alloc_node(devm_memremap_pages_release,
-			sizeof(*page_map), GFP_KERNEL, dev_to_node(dev));
-	if (!page_map)
+	pgmap = devres_alloc_node(devm_memremap_pages_release,
+			sizeof(*pgmap), GFP_KERNEL, dev_to_node(dev));
+	if (!pgmap)
 		return ERR_PTR(-ENOMEM);
-	pgmap = &page_map->pgmap;
 
-	memcpy(&page_map->res, res, sizeof(*res));
+	memcpy(&pgmap->res, res, sizeof(*res));
 
 	pgmap->dev = dev;
 	if (altmap) {
-		memcpy(&page_map->altmap, altmap, sizeof(*altmap));
-		pgmap->altmap = &page_map->altmap;
-		altmap = pgmap->altmap;
+		memcpy(&pgmap->altmap, altmap, sizeof(*altmap));
+		pgmap->altmap_valid = true;
+		altmap = &pgmap->altmap;
 	}
 	pgmap->ref = ref;
-	pgmap->res = &page_map->res;
 	pgmap->type = MEMORY_DEVICE_HOST;
 	pgmap->page_fault = NULL;
 	pgmap->page_free = NULL;
@@ -397,7 +383,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 
 	foreach_order_pgoff(res, order, pgoff) {
 		error = __radix_tree_insert(&pgmap_radix,
-				PHYS_PFN(res->start) + pgoff, order, page_map);
+				PHYS_PFN(res->start) + pgoff, order, pgmap);
 		if (error) {
 			dev_err(dev, "%s: failed: %d\n", __func__, error);
 			break;
@@ -426,7 +412,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (error)
 		goto err_add_memory;
 
-	for_each_device_pfn(pfn, page_map) {
+	for_each_device_pfn(pfn, pgmap) {
 		struct page *page = pfn_to_page(pfn);
 
 		/*
@@ -441,7 +427,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		if (!(++i % 1024))
 			cond_resched();
 	}
-	devres_add(dev, page_map);
+	devres_add(dev, pgmap);
 	return __va(res->start);
 
  err_add_memory:
@@ -449,7 +435,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
  err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res);
-	devres_free(page_map);
+	devres_free(pgmap);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL(devm_memremap_pages);
@@ -482,9 +468,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 	 * In the cached case we're already holding a live reference.
 	 */
 	if (pgmap) {
-		const struct resource *res = pgmap ? pgmap->res : NULL;
-
-		if (res && phys >= res->start && phys <= res->end)
+		if (phys >= pgmap->res.start && phys <= pgmap->res.end)
 			return pgmap;
 		put_dev_pagemap(pgmap);
 	}
diff --git a/mm/hmm.c b/mm/hmm.c
index 2f2e13c61040..320fdc87f064 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -882,7 +882,7 @@ static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
 	else
 		devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
 
-	devmem->pagemap.res = devmem->resource;
+	devmem->pagemap.res = *devmem->resource;
 	devmem->pagemap.page_fault = hmm_devmem_fault;
 	devmem->pagemap.page_free = hmm_devmem_free;
 	devmem->pagemap.dev = devmem->device;
-- 
cgit v1.2.3


From e8d5134833006a46fcbefc5f4a84d0b62bd520e7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:54:05 +0100
Subject: memremap: change devm_memremap_pages interface to use struct
 dev_pagemap

This new interface is similar to how struct device (and many others)
work. The caller initializes a 'struct dev_pagemap' as required
and calls 'devm_memremap_pages'. This allows the pagemap structure to
be embedded in another structure and thus container_of can be used. In
this way application specific members can be stored in a containing
struct.

This will be used by the P2P infrastructure and HMM could probably
be cleaned up to use it as well (instead of having it's own, similar
'hmm_devmem_pages_create' function).

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/pmem.c                | 20 ++++++++-------
 drivers/nvdimm/nd.h               |  9 +++----
 drivers/nvdimm/pfn_devs.c         | 27 ++++++++++++---------
 drivers/nvdimm/pmem.c             | 37 +++++++++++++++-------------
 drivers/nvdimm/pmem.h             |  1 +
 include/linux/memremap.h          |  6 ++---
 kernel/memremap.c                 | 51 ++++++++++++++++-----------------------
 tools/testing/nvdimm/test/iomap.c |  7 +++---
 8 files changed, 77 insertions(+), 81 deletions(-)

(limited to 'kernel')

diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 8d8c852ba8f2..31b6ecce4c64 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -21,6 +21,7 @@
 struct dax_pmem {
 	struct device *dev;
 	struct percpu_ref ref;
+	struct dev_pagemap pgmap;
 	struct completion cmp;
 };
 
@@ -69,20 +70,23 @@ static int dax_pmem_probe(struct device *dev)
 	struct nd_namespace_common *ndns;
 	struct nd_dax *nd_dax = to_nd_dax(dev);
 	struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
-	struct vmem_altmap __altmap, *altmap = NULL;
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
 		return PTR_ERR(ndns);
 	nsio = to_nd_namespace_io(&ndns->dev);
 
+	dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL);
+	if (!dax_pmem)
+		return -ENOMEM;
+
 	/* parse the 'pfn' info block via ->rw_bytes */
 	rc = devm_nsio_enable(dev, nsio);
 	if (rc)
 		return rc;
-	altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap);
-	if (IS_ERR(altmap))
-		return PTR_ERR(altmap);
+	rc = nvdimm_setup_pfn(nd_pfn, &dax_pmem->pgmap);
+	if (rc)
+		return rc;
 	devm_nsio_disable(dev, nsio);
 
 	pfn_sb = nd_pfn->pfn_sb;
@@ -94,10 +98,6 @@ static int dax_pmem_probe(struct device *dev)
 		return -EBUSY;
 	}
 
-	dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL);
-	if (!dax_pmem)
-		return -ENOMEM;
-
 	dax_pmem->dev = dev;
 	init_completion(&dax_pmem->cmp);
 	rc = percpu_ref_init(&dax_pmem->ref, dax_pmem_percpu_release, 0,
@@ -110,7 +110,8 @@ static int dax_pmem_probe(struct device *dev)
 	if (rc)
 		return rc;
 
-	addr = devm_memremap_pages(dev, &res, &dax_pmem->ref, altmap);
+	dax_pmem->pgmap.ref = &dax_pmem->ref;
+	addr = devm_memremap_pages(dev, &dax_pmem->pgmap);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
 
@@ -120,6 +121,7 @@ static int dax_pmem_probe(struct device *dev)
 		return rc;
 
 	/* adjust the dax_region resource to the start of data */
+	memcpy(&res, &dax_pmem->pgmap.res, sizeof(res));
 	res.start += le64_to_cpu(pfn_sb->dataoff);
 
 	rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", &region_id, &id);
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index e958f3724c41..8d6375ee0fda 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -368,15 +368,14 @@ unsigned int pmem_sector_size(struct nd_namespace_common *ndns);
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
 		struct badblocks *bb, const struct resource *res);
 #if IS_ENABLED(CONFIG_ND_CLAIM)
-struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
-		struct resource *res, struct vmem_altmap *altmap);
+int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap);
 int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio);
 void devm_nsio_disable(struct device *dev, struct nd_namespace_io *nsio);
 #else
-static inline struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
-		struct resource *res, struct vmem_altmap *altmap)
+static inline int nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+				   struct dev_pagemap *pgmap)
 {
-	return ERR_PTR(-ENXIO);
+	return -ENXIO;
 }
 static inline int devm_nsio_enable(struct device *dev,
 		struct nd_namespace_io *nsio)
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 2adada1a5855..f5c4e8c6e29d 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -542,9 +542,10 @@ static unsigned long init_altmap_reserve(resource_size_t base)
 	return reserve;
 }
 
-static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
-		struct resource *res, struct vmem_altmap *altmap)
+static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 {
+	struct resource *res = &pgmap->res;
+	struct vmem_altmap *altmap = &pgmap->altmap;
 	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 	u64 offset = le64_to_cpu(pfn_sb->dataoff);
 	u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
@@ -561,11 +562,13 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
 	res->start += start_pad;
 	res->end -= end_trunc;
 
+	pgmap->type = MEMORY_DEVICE_HOST;
+
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < SZ_8K)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
-		altmap = NULL;
+		pgmap->altmap_valid = false;
 	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
 		nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res)
 					- offset) / PAGE_SIZE);
@@ -577,10 +580,11 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
 		memcpy(altmap, &__altmap, sizeof(*altmap));
 		altmap->free = PHYS_PFN(offset - SZ_8K);
 		altmap->alloc = 0;
+		pgmap->altmap_valid = true;
 	} else
-		return ERR_PTR(-ENXIO);
+		return -ENXIO;
 
-	return altmap;
+	return 0;
 }
 
 static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys)
@@ -708,19 +712,18 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
  * Determine the effective resource range and vmem_altmap from an nd_pfn
  * instance.
  */
-struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
-		struct resource *res, struct vmem_altmap *altmap)
+int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 {
 	int rc;
 
 	if (!nd_pfn->uuid || !nd_pfn->ndns)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	rc = nd_pfn_init(nd_pfn);
 	if (rc)
-		return ERR_PTR(rc);
+		return rc;
 
-	/* we need a valid pfn_sb before we can init a vmem_altmap */
-	return __nvdimm_setup_pfn(nd_pfn, res, altmap);
+	/* we need a valid pfn_sb before we can init a dev_pagemap */
+	return __nvdimm_setup_pfn(nd_pfn, pgmap);
 }
 EXPORT_SYMBOL_GPL(nvdimm_setup_pfn);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 7fbc5c5dc8e1..cf074b1ce219 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -298,34 +298,34 @@ 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 resource bb_res;
 	struct nd_pfn *nd_pfn = NULL;
 	struct dax_device *dax_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;
+	int rc;
+
+	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
+	if (!pmem)
+		return -ENOMEM;
 
 	/* while nsio_rw_bytes is active, parse a pfn info block if present */
 	if (is_nd_pfn(dev)) {
 		nd_pfn = to_nd_pfn(dev);
-		altmap = nvdimm_setup_pfn(nd_pfn, &pfn_res, &__altmap);
-		if (IS_ERR(altmap))
-			return PTR_ERR(altmap);
+		rc = nvdimm_setup_pfn(nd_pfn, &pmem->pgmap);
+		if (rc)
+			return rc;
 	}
 
 	/* we're attaching a block device, disable raw namespace access */
 	devm_nsio_disable(dev, nsio);
 
-	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
-	if (!pmem)
-		return -ENOMEM;
-
 	dev_set_drvdata(dev, pmem);
 	pmem->phys_addr = res->start;
 	pmem->size = resource_size(res);
@@ -350,19 +350,22 @@ static int pmem_attach_disk(struct device *dev,
 		return -ENOMEM;
 
 	pmem->pfn_flags = PFN_DEV;
+	pmem->pgmap.ref = &q->q_usage_counter;
 	if (is_nd_pfn(dev)) {
-		addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter,
-				altmap);
+		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		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);
+		pmem->pfn_pad = resource_size(res) -
+			resource_size(&pmem->pgmap.res);
 		pmem->pfn_flags |= PFN_MAP;
-		res = &pfn_res; /* for badblocks populate */
-		res->start += pmem->data_offset;
+		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
+		bb_res.start += pmem->data_offset;
 	} else if (pmem_should_map_pages(dev)) {
-		addr = devm_memremap_pages(dev, &nsio->res,
-				&q->q_usage_counter, NULL);
+		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
+		pmem->pgmap.altmap_valid = false;
+		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
+		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
 	} else
 		addr = devm_memremap(dev, pmem->phys_addr,
 				pmem->size, ARCH_MEMREMAP_PMEM);
@@ -401,7 +404,7 @@ static int pmem_attach_disk(struct device *dev,
 			/ 512);
 	if (devm_init_badblocks(dev, &pmem->bb))
 		return -ENOMEM;
-	nvdimm_badblocks_populate(nd_region, &pmem->bb, res);
+	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res);
 	disk->bb = &pmem->bb;
 
 	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops);
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index 6a3cd2a10db6..a64ebc78b5df 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -22,6 +22,7 @@ struct pmem_device {
 	struct badblocks	bb;
 	struct dax_device	*dax_dev;
 	struct gendisk		*disk;
+	struct dev_pagemap	pgmap;
 };
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 1cb5f39d25c1..7b4899c06f49 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -123,8 +123,7 @@ struct dev_pagemap {
 };
 
 #ifdef CONFIG_ZONE_DEVICE
-void *devm_memremap_pages(struct device *dev, struct resource *res,
-		struct percpu_ref *ref, struct vmem_altmap *altmap);
+void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
 struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 		struct dev_pagemap *pgmap);
 
@@ -134,8 +133,7 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
 static inline bool is_zone_device_page(const struct page *page);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
-		struct resource *res, struct percpu_ref *ref,
-		struct vmem_altmap *altmap)
+		struct dev_pagemap *pgmap)
 {
 	/*
 	 * Fail attempts to call devm_memremap_pages() without
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 9207c44cce20..a9a948cd3d7f 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -275,9 +275,10 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap)
 #define for_each_device_pfn(pfn, map) \
 	for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++)
 
-static void devm_memremap_pages_release(struct device *dev, void *data)
+static void devm_memremap_pages_release(void *data)
 {
 	struct dev_pagemap *pgmap = data;
+	struct device *dev = pgmap->dev;
 	struct resource *res = &pgmap->res;
 	resource_size_t align_start, align_size;
 	unsigned long pfn;
@@ -316,29 +317,34 @@ static struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 /**
  * devm_memremap_pages - remap and provide memmap backing for the given resource
  * @dev: hosting device for @res
- * @res: "host memory" address range
- * @ref: a live per-cpu reference count
- * @altmap: optional descriptor for allocating the memmap from @res
+ * @pgmap: pointer to a struct dev_pgmap
  *
  * Notes:
- * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
- *    (or devm release event). The expected order of events is that @ref has
+ * 1/ At a minimum the res, ref and type members of @pgmap must be initialized
+ *    by the caller before passing it to this function
+ *
+ * 2/ The altmap field may optionally be initialized, in which case altmap_valid
+ *    must be set to true
+ *
+ * 3/ pgmap.ref must be 'live' on entry and 'dead' before devm_memunmap_pages()
+ *    time (or devm release event). The expected order of events is that ref has
  *    been through percpu_ref_kill() before devm_memremap_pages_release(). The
  *    wait for the completion of all references being dropped and
  *    percpu_ref_exit() must occur after devm_memremap_pages_release().
  *
- * 2/ @res is expected to be a host memory range that could feasibly be
+ * 4/ res is expected to be a host memory range that could feasibly be
  *    treated as a "System RAM" range, i.e. not a device mmio range, but
  *    this is not enforced.
  */
-void *devm_memremap_pages(struct device *dev, struct resource *res,
-		struct percpu_ref *ref, struct vmem_altmap *altmap)
+void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
 	resource_size_t align_start, align_size, align_end;
+	struct vmem_altmap *altmap = pgmap->altmap_valid ?
+			&pgmap->altmap : NULL;
 	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
-	struct dev_pagemap *pgmap;
 	int error, nid, is_ram, i = 0;
+	struct resource *res = &pgmap->res;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -355,27 +361,10 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (is_ram == REGION_INTERSECTS)
 		return __va(res->start);
 
-	if (!ref)
+	if (!pgmap->ref)
 		return ERR_PTR(-EINVAL);
 
-	pgmap = devres_alloc_node(devm_memremap_pages_release,
-			sizeof(*pgmap), GFP_KERNEL, dev_to_node(dev));
-	if (!pgmap)
-		return ERR_PTR(-ENOMEM);
-
-	memcpy(&pgmap->res, res, sizeof(*res));
-
 	pgmap->dev = dev;
-	if (altmap) {
-		memcpy(&pgmap->altmap, altmap, sizeof(*altmap));
-		pgmap->altmap_valid = true;
-		altmap = &pgmap->altmap;
-	}
-	pgmap->ref = ref;
-	pgmap->type = MEMORY_DEVICE_HOST;
-	pgmap->page_fault = NULL;
-	pgmap->page_free = NULL;
-	pgmap->data = NULL;
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
@@ -423,11 +412,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		 */
 		list_del(&page->lru);
 		page->pgmap = pgmap;
-		percpu_ref_get(ref);
+		percpu_ref_get(pgmap->ref);
 		if (!(++i % 1024))
 			cond_resched();
 	}
-	devres_add(dev, pgmap);
+
+	devm_add_action(dev, devm_memremap_pages_release, pgmap);
+
 	return __va(res->start);
 
  err_add_memory:
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index e1f75a1914a1..ff9d3a5825e1 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -104,15 +104,14 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
 }
 EXPORT_SYMBOL(__wrap_devm_memremap);
 
-void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res,
-		struct percpu_ref *ref, struct vmem_altmap *altmap)
+void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
-	resource_size_t offset = res->start;
+	resource_size_t offset = pgmap->res.start;
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
 	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, pgmap);
 }
 EXPORT_SYMBOL(__wrap_devm_memremap_pages);
 
-- 
cgit v1.2.3


From e697c5b90e97792187e45f8d78fb2bfa62eb0496 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 29 Dec 2017 08:54:06 +0100
Subject: memremap: merge find_dev_pagemap into get_dev_pagemap

There is only one caller of the trivial function find_dev_pagemap left,
so just merge it into the caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 kernel/memremap.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

(limited to 'kernel')

diff --git a/kernel/memremap.c b/kernel/memremap.c
index a9a948cd3d7f..ada31b0d76d4 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -306,14 +306,6 @@ static void devm_memremap_pages_release(void *data)
 		      "%s: failed to free all reserved pages\n", __func__);
 }
 
-/* assumes rcu_read_lock() held at entry */
-static struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	return radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
-}
-
 /**
  * devm_memremap_pages - remap and provide memmap backing for the given resource
  * @dev: hosting device for @res
@@ -466,7 +458,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 
 	/* fall back to slow path lookup */
 	rcu_read_lock();
-	pgmap = find_dev_pagemap(phys);
+	pgmap = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
 	if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
 		pgmap = NULL;
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 10a0cd6e4932b5078215b1ec2c896597eec0eff9 Mon Sep 17 00:00:00 2001
From: "Jan H. Schönherr" <jschoenh@amazon.de>
Date: Fri, 19 Jan 2018 16:27:54 -0800
Subject: mm: Fix memory size alignment in devm_memremap_pages_release()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The functions devm_memremap_pages() and devm_memremap_pages_release() use
different ways to calculate the section-aligned amount of memory. The
latter function may use an incorrect size if the memory region is small
but straddles a section border.

Use the same code for both.

Cc: <stable@vger.kernel.org>
Fixes: 5f29a77cd957 ("mm: fix mixed zone detection in devm_memremap_pages")
Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 kernel/memremap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/memremap.c b/kernel/memremap.c
index ada31b0d76d4..4ef97525a4ff 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -293,7 +293,8 @@ static void devm_memremap_pages_release(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);
+	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
+		- align_start;
 
 	mem_hotplug_begin();
 	arch_remove_memory(align_start, align_size, pgmap->altmap_valid ?
-- 
cgit v1.2.3


From 77dd66a3c67c93ab401ccc15efff25578be281fd Mon Sep 17 00:00:00 2001
From: "Jan H. Schönherr" <jschoenh@amazon.de>
Date: Fri, 19 Jan 2018 16:26:33 -0800
Subject: mm: Fix devm_memremap_pages() collision handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If devm_memremap_pages() detects a collision while adding entries
to the radix-tree, we call pgmap_radix_release(). Unfortunately,
the function removes *all* entries for the range -- including the
entries that caused the collision in the first place.

Modify pgmap_radix_release() to take an additional argument to
indicate where to stop, so that only newly added entries are removed
from the tree.

Cc: <stable@vger.kernel.org>
Fixes: 9476df7d80df ("mm: introduce find_dev_pagemap()")
Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 kernel/memremap.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'kernel')

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 4ef97525a4ff..4849be5f9b3c 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -241,13 +241,16 @@ int device_private_entry_fault(struct vm_area_struct *vma,
 EXPORT_SYMBOL(device_private_entry_fault);
 #endif /* CONFIG_DEVICE_PRIVATE */
 
-static void pgmap_radix_release(struct resource *res)
+static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff)
 {
 	unsigned long pgoff, order;
 
 	mutex_lock(&pgmap_lock);
-	foreach_order_pgoff(res, order, pgoff)
+	foreach_order_pgoff(res, order, pgoff) {
+		if (pgoff >= end_pgoff)
+			break;
 		radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
+	}
 	mutex_unlock(&pgmap_lock);
 
 	synchronize_rcu();
@@ -302,7 +305,7 @@ static void devm_memremap_pages_release(void *data)
 	mem_hotplug_done();
 
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
-	pgmap_radix_release(res);
+	pgmap_radix_release(res, -1);
 	dev_WARN_ONCE(dev, pgmap->altmap.alloc,
 		      "%s: failed to free all reserved pages\n", __func__);
 }
@@ -418,7 +421,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
  err_pfn_remap:
  err_radix:
-	pgmap_radix_release(res);
+	pgmap_radix_release(res, pgoff);
 	devres_free(pgmap);
 	return ERR_PTR(error);
 }
-- 
cgit v1.2.3