mm, memory_hotplug: provide a more generic restrictions for memory hotplug

arch_add_memory, __add_pages take a want_memblock which controls whether
the newly added memory should get the sysfs memblock user API (e.g.
ZONE_DEVICE users do not want/need this interface).  Some callers even
want to control where do we allocate the memmap from by configuring
altmap.

Add a more generic hotplug context for arch_add_memory and __add_pages.
struct mhp_restrictions contains flags which contains additional features
to be enabled by the memory hotplug (MHP_MEMBLOCK_API currently) and
altmap for alternative memmap allocator.

This patch shouldn't introduce any functional change.

[akpm@linux-foundation.org: build fix]
Link: http://lkml.kernel.org/r/20190408082633.2864-3-osalvador@suse.de
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

10 files changed, 63 insertions, 37 deletions

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index ef82312860ac..ef32d4839c3f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1065,8 +1065,8 @@ int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		    bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	int flags = 0;
 
@@ -1077,6 +1077,6 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
 
 	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
-			   altmap, want_memblock);
+			   restrictions);
 }
 #endif
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index e49200e31750..379eb1f9adc9 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -666,14 +666,14 @@ mem_init (void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
 	if (ret)
 		printk("%s: Problem encountered in __add_pages() as ret=%d\n",
 		       __func__,  ret);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 20266898f3a8..de5c591a550d 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -109,8 +109,8 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end)
 	return -ENODEV;
 }
 
-int __ref arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-			  bool want_memblock)
+int __ref arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -127,7 +127,7 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altm
 	}
 	flush_inval_dcache_range(start, start + size);
 
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 5f48fc7e61d5..06bd05137a00 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -219,8 +219,8 @@ device_initcall(s390_cma_mem_init);
 
 #endif /* CONFIG_CMA */
 
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+		struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long size_pages = PFN_DOWN(size);
@@ -230,7 +230,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 	if (rc)
 		return rc;
 
-	rc = __add_pages(nid, start_pfn, size_pages, altmap, want_memblock);
+	rc = __add_pages(nid, start_pfn, size_pages, restrictions);
 	if (rc)
 		vmem_remove_mapping(start, size);
 	return rc;
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index aeb9f45c7a39..d3cd07bd2dc1 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -404,15 +404,15 @@ void __init mem_init(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
 	/* We only have ZONE_NORMAL, so this is easy.. */
-	ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
 	if (unlikely(ret))
 		printk("%s: Failed, __add_pages() == %d\n", __func__, ret);
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 85c94f9a87f8..755dbed85531 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -850,13 +850,13 @@ void __init mem_init(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bccff68e3267..db42c11b48fb 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -777,11 +777,11 @@ static void update_end_of_memory_vars(u64 start, u64 size)
 }
 
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap, bool want_memblock)
+				struct mhp_restrictions *restrictions)
 {
 	int ret;
 
-	ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
 	WARN_ON_ONCE(ret);
 
 	/* update max_pfn, max_low_pfn and high_memory */
@@ -791,15 +791,15 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	return ret;
 }
 
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
 	init_memory_mapping(start, start + size);
 
-	return add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #define PAGE_INUSE 0xFD
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 3c8cf347804c..b24aca54353e 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -54,6 +54,16 @@ enum {
 };
 
 /*
+ * Restrictions for the memory hotplug:
+ * flags:  MHP_ flags
+ * altmap: alternative allocator for memmap array
+ */
+struct mhp_restrictions {
+	unsigned long flags;
+	struct vmem_altmap *altmap;
+};
+
+/*
  * Zone resizing functions
  *
  * Note: any attempt to resize a zone should has pgdat_resize_lock()
@@ -101,6 +111,8 @@ extern void __online_page_free(struct page *page);
 
 extern int try_online_node(int nid);
 
+extern int arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions);
 extern u64 max_mem_size;
 
 extern bool memhp_auto_online;
@@ -118,20 +130,27 @@ extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
 	unsigned long nr_pages, struct vmem_altmap *altmap);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
+/*
+ * Do we want sysfs memblock files created. This will allow userspace to online
+ * and offline memory explicitly. Lack of this bit means that the caller has to
+ * call move_pfn_range_to_zone to finish the initialization.
+ */
+
+#define MHP_MEMBLOCK_API               (1<<0)
+
 /* reasonably generic interface to expand the physical pages */
 extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap, bool want_memblock);
+		       struct mhp_restrictions *restrictions);
 
 #ifndef CONFIG_ARCH_HAS_ADD_PAGES
 static inline int add_pages(int nid, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap,
-		bool want_memblock)
+		unsigned long nr_pages, struct mhp_restrictions *restrictions)
 {
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 #else /* ARCH_HAS_ADD_PAGES */
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap, bool want_memblock);
+	      struct mhp_restrictions *restrictions);
 #endif /* ARCH_HAS_ADD_PAGES */
 
 #ifdef CONFIG_NUMA
@@ -332,8 +351,6 @@ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 extern int __add_memory(int nid, u64 start, u64 size);
 extern int add_memory(int nid, u64 start, u64 size);
 extern int add_memory_resource(int nid, struct resource *resource);
-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, struct vmem_altmap *altmap);
 extern bool is_memblock_offlined(struct memory_block *mem);
diff --git a/kernel/memremap.c b/kernel/memremap.c
index a856cb5ff192..4e59d29245f4 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -148,6 +148,12 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 			&pgmap->altmap : NULL;
 	struct resource *res = &pgmap->res;
 	struct dev_pagemap *conflict_pgmap;
+	struct mhp_restrictions restrictions = {
+		/*
+		 * We do not want any optional features only our own memmap
+		*/
+		.altmap = altmap,
+	};
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
 
@@ -214,7 +220,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	 */
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		error = add_pages(nid, align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT, NULL, false);
+				align_size >> PAGE_SHIFT, &restrictions);
 	} else {
 		error = kasan_add_zero_shadow(__va(align_start), align_size);
 		if (error) {
@@ -222,8 +228,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 			goto err_kasan;
 		}
 
-		error = arch_add_memory(nid, align_start, align_size, altmap,
-				false);
+		error = arch_add_memory(nid, align_start, align_size,
+					&restrictions);
 	}
 
 	if (!error) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 75f9f6590677..339d5a62d5d5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -273,12 +273,12 @@ static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
  * add the new pages.
  */
 int __ref __add_pages(int nid, unsigned long phys_start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap,
-		bool want_memblock)
+		unsigned long nr_pages, struct mhp_restrictions *restrictions)
 {
 	unsigned long i;
 	int err = 0;
 	int start_sec, end_sec;
+	struct vmem_altmap *altmap = restrictions->altmap;
 
 	/* during initialize mem_map, align hot-added range to section */
 	start_sec = pfn_to_section_nr(phys_start_pfn);
@@ -299,7 +299,7 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn,
 
 	for (i = start_sec; i <= end_sec; i++) {
 		err = __add_section(nid, section_nr_to_pfn(i), altmap,
-				want_memblock);
+				restrictions->flags & MHP_MEMBLOCK_API);
 
 		/*
 		 * EEXIST is finally dealt with by ioresource collision
@@ -1097,6 +1097,9 @@ static int online_memory_block(struct memory_block *mem, void *arg)
  */
 int __ref add_memory_resource(int nid, struct resource *res)
 {
+	struct mhp_restrictions restrictions = {
+		.flags = MHP_MEMBLOCK_API,
+	};
 	u64 start, size;
 	bool new_node = false;
 	int ret;
@@ -1124,7 +1127,7 @@ int __ref add_memory_resource(int nid, struct resource *res)
 	new_node = ret;
 
 	/* call arch's memory hotadd */
-	ret = arch_add_memory(nid, start, size, NULL, true);
+	ret = arch_add_memory(nid, start, size, &restrictions);
 	if (ret < 0)
 		goto error;