mm: convert totalram_pages and totalhigh_pages variables to atomic

totalram_pages and totalhigh_pages are made static inline function.

Main motivation was that managed_page_count_lock handling was complicating
things.  It was discussed in length here,
https://lore.kernel.org/patchwork/patch/995739/#1181785 So it seemes
better to remove the lock and convert variables to atomic, with preventing
poteintial store-to-read tearing as a bonus.

[akpm@linux-foundation.org: coding style fixes]
Link: http://lkml.kernel.org/r/1542090790-21750-4-git-send-email-arunks@codeaurora.org
Signed-off-by: Arun KS <arunks@codeaurora.org>
Suggested-by: Michal Hocko <mhocko@suse.com>
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/highmem.c

@@ -105,9 +105,8 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
 }
 #endif
 
-unsigned long totalhigh_pages __read_mostly;
-EXPORT_SYMBOL(totalhigh_pages);
-
+atomic_long_t _totalhigh_pages __read_mostly;
+EXPORT_SYMBOL(_totalhigh_pages);
 
 EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx);
 

mm/huge_memory.c

@@ -420,7 +420,7 @@ static int __init hugepage_init(void)
 	 * where the extra memory used could hurt more than TLB overhead
 	 * is likely to save.  The admin can still enable it through /sys.
 	 */
-	if (totalram_pages < (512 << (20 - PAGE_SHIFT))) {
+	if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) {
 		transparent_hugepage_flags = 0;
 		return 0;
 	}

mm/kasan/quarantine.c

@@ -237,7 +237,7 @@ void quarantine_reduce(void)
 	 * Update quarantine size in case of hotplug. Allocate a fraction of
 	 * the installed memory to quarantine minus per-cpu queue limits.
 	 */
-	total_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
+	total_size = (totalram_pages() << PAGE_SHIFT) /
 		QUARANTINE_FRACTION;
 	percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
 	new_quarantine_size = (total_size < percpu_quarantines) ?

mm/memblock.c

@@ -1576,7 +1576,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size)
 
 	for (; cursor < end; cursor++) {
 		memblock_free_pages(pfn_to_page(cursor), cursor, 0);
-		totalram_pages++;
+		totalram_pages_inc();
 	}
 }
 
@@ -1978,7 +1978,7 @@ unsigned long __init memblock_free_all(void)
 	reset_all_zones_managed_pages();
 
 	pages = free_low_memory_core_early();
-	totalram_pages += pages;
+	totalram_pages_add(pages);
 
 	return pages;
 }

mm/mm_init.c

@@ -146,7 +146,7 @@ static void __meminit mm_compute_batch(void)
 	s32 batch = max_t(s32, nr*2, 32);
 
 	/* batch size set to 0.4% of (total memory/#cpus), or max int32 */
-	memsized_batch = min_t(u64, (totalram_pages/nr)/256, 0x7fffffff);
+	memsized_batch = min_t(u64, (totalram_pages()/nr)/256, 0x7fffffff);
 
 	vm_committed_as_batch = max_t(s32, memsized_batch, batch);
 }

mm/oom_kill.c

@@ -269,7 +269,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc)
 	}
 
 	/* Default to all available memory */
-	oc->totalpages = totalram_pages + total_swap_pages;
+	oc->totalpages = totalram_pages() + total_swap_pages;
 
 	if (!IS_ENABLED(CONFIG_NUMA))
 		return CONSTRAINT_NONE;

mm/page_alloc.c

@@ -16,6 +16,7 @@
 
 #include <linux/stddef.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <linux/swap.h>
 #include <linux/interrupt.h>
 #include <linux/pagemap.h>
@@ -124,7 +125,8 @@ EXPORT_SYMBOL(node_states);
 /* Protect totalram_pages and zone->managed_pages */
 static DEFINE_SPINLOCK(managed_page_count_lock);
 
-unsigned long totalram_pages __read_mostly;
+atomic_long_t _totalram_pages __read_mostly;
+EXPORT_SYMBOL(_totalram_pages);
 unsigned long totalreserve_pages __read_mostly;
 unsigned long totalcma_pages __read_mostly;
 
@@ -4747,11 +4749,11 @@ EXPORT_SYMBOL_GPL(si_mem_available);
 
 void si_meminfo(struct sysinfo *val)
 {
-	val->totalram = totalram_pages;
+	val->totalram = totalram_pages();
 	val->sharedram = global_node_page_state(NR_SHMEM);
 	val->freeram = global_zone_page_state(NR_FREE_PAGES);
 	val->bufferram = nr_blockdev_pages();
-	val->totalhigh = totalhigh_pages;
+	val->totalhigh = totalhigh_pages();
 	val->freehigh = nr_free_highpages();
 	val->mem_unit = PAGE_SIZE;
 }
@@ -7077,10 +7079,10 @@ void adjust_managed_page_count(struct page *page, long count)
 {
 	spin_lock(&managed_page_count_lock);
 	atomic_long_add(count, &page_zone(page)->managed_pages);
-	totalram_pages += count;
+	totalram_pages_add(count);
 #ifdef CONFIG_HIGHMEM
 	if (PageHighMem(page))
-		totalhigh_pages += count;
+		totalhigh_pages_add(count);
 #endif
 	spin_unlock(&managed_page_count_lock);
 }
@@ -7123,9 +7125,9 @@ EXPORT_SYMBOL(free_reserved_area);
 void free_highmem_page(struct page *page)
 {
 	__free_reserved_page(page);
-	totalram_pages++;
+	totalram_pages_inc();
 	atomic_long_inc(&page_zone(page)->managed_pages);
-	totalhigh_pages++;
+	totalhigh_pages_inc();
 }
 #endif
 
@@ -7174,10 +7176,10 @@ void __init mem_init_print_info(const char *str)
 		physpages << (PAGE_SHIFT - 10),
 		codesize >> 10, datasize >> 10, rosize >> 10,
 		(init_data_size + init_code_size) >> 10, bss_size >> 10,
-		(physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT - 10),
+		(physpages - totalram_pages() - totalcma_pages) << (PAGE_SHIFT - 10),
 		totalcma_pages << (PAGE_SHIFT - 10),
 #ifdef	CONFIG_HIGHMEM
-		totalhigh_pages << (PAGE_SHIFT - 10),
+		totalhigh_pages() << (PAGE_SHIFT - 10),
 #endif
 		str ? ", " : "", str ? str : "");
 }

mm/shmem.c

@@ -109,13 +109,14 @@ struct shmem_falloc {
 #ifdef CONFIG_TMPFS
 static unsigned long shmem_default_max_blocks(void)
 {
-	return totalram_pages / 2;
+	return totalram_pages() / 2;
 }
 
 static unsigned long shmem_default_max_inodes(void)
 {
-	unsigned long nr_pages = totalram_pages;
-	return min(nr_pages - totalhigh_pages, nr_pages / 2);
+	unsigned long nr_pages = totalram_pages();
+
+	return min(nr_pages - totalhigh_pages(), nr_pages / 2);
 }
 #endif
 
@@ -3302,7 +3303,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			size = memparse(value,&rest);
 			if (*rest == '%') {
 				size <<= PAGE_SHIFT;
-				size *= totalram_pages;
+				size *= totalram_pages();
 				do_div(size, 100);
 				rest++;
 			}

mm/slab.c

@@ -1235,7 +1235,7 @@ void __init kmem_cache_init(void)
 	 * page orders on machines with more than 32MB of memory if
 	 * not overridden on the command line.
 	 */
-	if (!slab_max_order_set && totalram_pages > (32 << 20) >> PAGE_SHIFT)
+	if (!slab_max_order_set && totalram_pages() > (32 << 20) >> PAGE_SHIFT)
 		slab_max_order = SLAB_MAX_ORDER_HI;
 
 	/* Bootstrap is tricky, because several objects are allocated

mm/swap.c

@@ -1022,7 +1022,7 @@ EXPORT_SYMBOL(pagevec_lookup_range_nr_tag);
  */
 void __init swap_setup(void)
 {
-	unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
+	unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT);
 
 	/* Use a smaller cluster for small-memory machines */
 	if (megs < 16)

mm/util.c

@@ -593,7 +593,7 @@ unsigned long vm_commit_limit(void)
 	if (sysctl_overcommit_kbytes)
 		allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
 	else
-		allowed = ((totalram_pages - hugetlb_total_pages())
+		allowed = ((totalram_pages() - hugetlb_total_pages())
 			   * sysctl_overcommit_ratio / 100);
 	allowed += total_swap_pages;
 

mm/vmalloc.c

@@ -1634,7 +1634,7 @@ void *vmap(struct page **pages, unsigned int count,
 
 	might_sleep();
 
-	if (count > totalram_pages)
+	if (count > totalram_pages())
 		return NULL;
 
 	size = (unsigned long)count << PAGE_SHIFT;
@@ -1739,7 +1739,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	unsigned long real_size = size;
 
 	size = PAGE_ALIGN(size);
-	if (!size || (size >> PAGE_SHIFT) > totalram_pages)
+	if (!size || (size >> PAGE_SHIFT) > totalram_pages())
 		goto fail;
 
 	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |

mm/workingset.c

@@ -549,7 +549,7 @@ static int __init workingset_init(void)
 	 * double the initial memory by using totalram_pages as-is.
 	 */
 	timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
-	max_order = fls_long(totalram_pages - 1);
+	max_order = fls_long(totalram_pages() - 1);
 	if (max_order > timestamp_bits)
 		bucket_order = max_order - timestamp_bits;
 	pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",

mm/zswap.c

@@ -219,8 +219,8 @@ static const struct zpool_ops zswap_zpool_ops = {
 
 static bool zswap_is_full(void)
 {
-	return totalram_pages * zswap_max_pool_percent / 100 <
-		DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+	return totalram_pages() * zswap_max_pool_percent / 100 <
+			DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
 }
 
 static void zswap_update_total_size(void)