mm/memory_hotplug: remove memory block devices before arch_remove_memory()

Let's factor out removing of memory block devices, which is only
necessary for memory added via add_memory() and friends that created
memory block devices.  Remove the devices before calling
arch_remove_memory().

This finishes factoring out memory block device handling from
arch_add_memory() and arch_remove_memory().

Link: http://lkml.kernel.org/r/20190527111152.16324-10-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: "mike.travis@hpe.com" <mike.travis@hpe.com>
Cc: Andrew Banman <andrew.banman@hpe.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Mark Brown <broonie@kernel.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Arun KS <arunks@codeaurora.org>
Cc: Mathieu Malaterre <malat@debian.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chintan Pandya <cpandya@codeaurora.org>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jun Yao <yaojun8558363@gmail.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qian Cai <cai@lca.pw>
Cc: Rich Felker <dalias@libc.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/base/memory.c

@@ -759,32 +759,31 @@ int create_memory_block_devices(unsigned long start, unsigned long size)
 	return ret;
 }
 
-void unregister_memory_section(struct mem_section *section)
+/*
+ * Remove memory block devices for the given memory area. Start and size
+ * have to be aligned to memory block granularity. Memory block devices
+ * have to be offline.
+ */
+void remove_memory_block_devices(unsigned long start, unsigned long size)
 {
+	const int start_block_id = pfn_to_block_id(PFN_DOWN(start));
+	const int end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
 	struct memory_block *mem;
+	int block_id;
 
-	if (WARN_ON_ONCE(!present_section(section)))
+	if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) ||
+			 !IS_ALIGNED(size, memory_block_size_bytes())))
 		return;
 
 	mutex_lock(&mem_sysfs_mutex);
-
-	/*
-	 * Some users of the memory hotplug do not want/need memblock to
-	 * track all sections. Skip over those.
-	 */
-	mem = find_memory_block(section);
-	if (!mem)
-		goto out_unlock;
-
-	unregister_mem_sect_under_nodes(mem, __section_nr(section));
-
-	mem->section_count--;
-	if (mem->section_count == 0)
+	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
+		mem = find_memory_block_by_id(block_id, NULL);
+		if (WARN_ON_ONCE(!mem))
+			continue;
+		mem->section_count = 0;
+		unregister_memory_block_under_nodes(mem);
 		unregister_memory(mem);
-	else
-		put_device(&mem->dev);
-
-out_unlock:
+	}
 	mutex_unlock(&mem_sysfs_mutex);
 }
 

drivers/base/node.c

@@ -802,9 +802,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg)
 	return 0;
 }
 
-/* unregister memory section under all nodes that it spans */
-int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
-				    unsigned long phys_index)
+/*
+ * Unregister memory block device under all nodes that it spans.
+ */
+int unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 {
 	NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;
@@ -817,8 +818,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 		return -ENOMEM;
 	nodes_clear(*unlinked_nodes);
 
-	sect_start_pfn = section_nr_to_pfn(phys_index);
-	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int nid;
 

include/linux/memory.h

@@ -112,7 +112,7 @@ extern void unregister_memory_notifier(struct notifier_block *nb);
 extern int register_memory_isolate_notifier(struct notifier_block *nb);
 extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size);
-extern void unregister_memory_section(struct mem_section *);
+void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern int memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
 extern int memory_isolate_notify(unsigned long val, void *v);

include/linux/node.h

@@ -139,8 +139,7 @@ extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int register_mem_sect_under_node(struct memory_block *mem_blk,
 						void *arg);
-extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
-					   unsigned long phys_index);
+extern int unregister_memory_block_under_nodes(struct memory_block *mem_blk);
 
 extern int register_memory_node_under_compute_node(unsigned int mem_nid,
 						   unsigned int cpu_nid,
@@ -176,8 +175,7 @@ static inline int register_mem_sect_under_node(struct memory_block *mem_blk,
 {
 	return 0;
 }
-static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
-						  unsigned long phys_index)
+static inline int unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 {
 	return 0;
 }

mm/memory_hotplug.c

@@ -520,8 +520,6 @@ static void __remove_section(struct zone *zone, struct mem_section *ms,
 	if (WARN_ON_ONCE(!valid_section(ms)))
 		return;
 
-	unregister_memory_section(ms);
-
 	scn_nr = __section_nr(ms);
 	start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
 	__remove_zone(zone, start_pfn);
@@ -1834,6 +1832,9 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 	memblock_free(start, size);
 	memblock_remove(start, size);
 
+	/* remove memory block devices before removing memory */
+	remove_memory_block_devices(start, size);
+
 	arch_remove_memory(nid, start, size, NULL);
 	__release_memory_resource(start, size);