FROMLIST: mm: fs: Invalidate BH LRU during page migration

Pages containing buffer_heads that are in one of the per-CPU
buffer_head LRU caches will be pinned and thus cannot be migrated.
This can prevent CMA allocations from succeeding, which are often used
on platforms with co-processors (such as a DSP) that can only use
physically contiguous memory. It can also prevent memory
hot-unplugging from succeeding, which involves migrating at least
MIN_MEMORY_BLOCK_SIZE bytes of memory, which ranges from 8 MiB to 1
GiB based on the architecture in use.

Correspondingly, invalidate the BH LRU caches before a migration
starts and stop any buffer_head from being cached in the LRU caches,
until migration has finished.

Bug: 180018981
Link: https://lore.kernel.org/linux-mm/20210319175127.886124-3-minchan@kernel.org/
Tested-by: Oliver Sang <oliver.sang@intel.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Chris Goldsworthy <cgoldswo@codeaurora.org>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Minchan Kim <minchan@google.com>
Change-Id: Idb8279cb561812f5f1b43ddbb742c1808700754e

fs/buffer.c

@@ -1265,6 +1265,15 @@ static void bh_lru_install(struct buffer_head *bh)
 	int i;
 
 	check_irqs_on();
+	/*
+	 * the refcount of buffer_head in bh_lru prevents dropping the
+	 * attached page(i.e., try_to_free_buffers) so it could cause
+	 * failing page migration.
+	 * Skip putting upcoming bh into bh_lru until migration is done.
+	 */
+	if (lru_cache_disabled())
+		return;
+
 	bh_lru_lock();
 
 	b = this_cpu_ptr(&bh_lrus);
@@ -1405,6 +1414,15 @@ __bread_gfp(struct block_device *bdev, sector_t block,
 }
 EXPORT_SYMBOL(__bread_gfp);
 
+static void __invalidate_bh_lrus(struct bh_lru *b)
+{
+	int i;
+
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		brelse(b->bhs[i]);
+		b->bhs[i] = NULL;
+	}
+}
 /*
  * invalidate_bh_lrus() is called rarely - but not only at unmount.
  * This doesn't race because it runs in each cpu either in irq
@@ -1413,16 +1431,12 @@ EXPORT_SYMBOL(__bread_gfp);
 static void invalidate_bh_lru(void *arg)
 {
 	struct bh_lru *b = &get_cpu_var(bh_lrus);
-	int i;
 
-	for (i = 0; i < BH_LRU_SIZE; i++) {
+	__invalidate_bh_lrus(b);
-		brelse(b->bhs[i]);
-		b->bhs[i] = NULL;
-	}
 	put_cpu_var(bh_lrus);
 }
 
-static bool has_bh_in_lru(int cpu, void *dummy)
+bool has_bh_in_lru(int cpu, void *dummy)
 {
 	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
 	int i;
@@ -1484,6 +1498,16 @@ static void evict_bh_lrus(struct xarray *busy_bhs)
 			 busy_bhs, 1);
 }
 
+void invalidate_bh_lrus_cpu(int cpu)
+{
+	struct bh_lru *b;
+
+	bh_lru_lock();
+	b = per_cpu_ptr(&bh_lrus, cpu);
+	__invalidate_bh_lrus(b);
+	bh_lru_unlock();
+}
+
 void set_bh_page(struct buffer_head *bh,
 		struct page *page, unsigned long offset)
 {

include/linux/buffer_head.h

@@ -194,6 +194,8 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
+void invalidate_bh_lrus_cpu(int cpu);
+bool has_bh_in_lru(int cpu, void *dummy);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
@@ -406,6 +408,8 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void invalidate_bh_lrus_cpu(int cpu) {}
+static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; }
 #define buffer_heads_over_limit 0
 
 #endif /* CONFIG_BLOCK */

mm/swap.c

@@ -36,6 +36,7 @@
 #include <linux/hugetlb.h>
 #include <linux/page_idle.h>
 #include <linux/local_lock.h>
+#include <linux/buffer_head.h>
 
 #include "internal.h"
 
@@ -665,6 +666,7 @@ void lru_add_drain_cpu(int cpu)
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
 
 	activate_page_drain(cpu);
+	invalidate_bh_lrus_cpu(cpu);
 }
 
 /**
@@ -852,7 +854,8 @@ inline void __lru_add_drain_all(bool force_all_cpus)
 		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
 		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
 		    pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) ||
-		    need_activate_page_drain(cpu)) {
+		    need_activate_page_drain(cpu) ||
+		    has_bh_in_lru(cpu, NULL)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
 			__cpumask_set_cpu(cpu, &has_work);