[PATCH v3 1/2] mm/vmalloc: Use batched page requests in bulk-allocator

[PATCH v3 1/2] mm/vmalloc: Use batched page requests in bulk-allocator

[Uladzislau Rezki (Sony)]

In case of simultaneous vmalloc allocations, for example it is 1GB and
12 CPUs my system is able to hit "BUG: soft lockup" for !CONFIG_PREEMPT
kernel.

<snip>
[   62.512621] RIP: 0010:__alloc_pages_bulk+0xa9f/0xbb0
[   62.512628] Code: ff 8b 44 24 48 44 29 f8 83 f8 01 0f 84 ea fe ff ff e9 07 f6 ff ff 48 8b 44 24 60 48 89 28 e9 00 f9 ff ff fb 66 0f 1f 44 00 00 <e9> e8 fd ff ff 65 48 01 51 10 e9 3e fe ff ff 48 8b 44 24 78 4d 89
[   62.512629] RSP: 0018:ffffa7bfc29ffd20 EFLAGS: 00000206
[   62.512631] RAX: 0000000000000200 RBX: ffffcd5405421888 RCX: ffff8c36ffdeb928
[   62.512632] RDX: 0000000000040000 RSI: ffffa896f06b2ff8 RDI: ffffcd5405421880
[   62.512633] RBP: ffffcd5405421880 R08: 000000000000007d R09: ffffffffffffffff
[   62.512634] R10: ffffffff9d63c084 R11: 00000000ffffffff R12: ffff8c373ffaeb80
[   62.512635] R13: ffff8c36ffdf65f8 R14: ffff8c373ffaeb80 R15: 0000000000040000
[   62.512637] FS:  0000000000000000(0000) GS:ffff8c36ffdc0000(0000) knlGS:0000000000000000
[   62.512638] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   62.512639] CR2: 000055c8e2fe8610 CR3: 0000000c13e10000 CR4: 00000000000006e0
[   62.512641] Call Trace:
[   62.512646]  __vmalloc_node_range+0x11c/0x2d0
[   62.512649]  ? full_fit_alloc_test+0x140/0x140 [test_vmalloc]
[   62.512654]  __vmalloc_node+0x4b/0x70
[   62.512656]  ? fix_size_alloc_test+0x44/0x60 [test_vmalloc]
[   62.512659]  fix_size_alloc_test+0x44/0x60 [test_vmalloc]
[   62.512662]  test_func+0xe7/0x1f0 [test_vmalloc]
[   62.512666]  ? fix_align_alloc_test+0x50/0x50 [test_vmalloc]
[   62.512668]  kthread+0x11a/0x140
[   62.512671]  ? set_kthread_struct+0x40/0x40
[   62.512672]  ret_from_fork+0x22/0x30
<snip>

To address this issue invoke a bulk-allocator many times until all pages
are obtained, i.e. do batched page requests adding cond_resched() meanwhile
to reschedule. Batched value is hard-coded and is 100 pages per call.

Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
 mm/vmalloc.c | 32 +++++++++++++++++++++++++++-----
 1 file changed, 27 insertions(+), 5 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index aaad569e8963..a9a6d28c8baa 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2775,7 +2775,7 @@ EXPORT_SYMBOL_GPL(vmap_pfn);
 
 static inline unsigned int
 vm_area_alloc_pages(gfp_t gfp, int nid,
-		unsigned int order, unsigned long nr_pages, struct page **pages)
+		unsigned int order, unsigned int nr_pages, struct page **pages)
 {
 	unsigned int nr_allocated = 0;
 
@@ -2785,10 +2785,32 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * to fails, fallback to a single page allocator that is
 	 * more permissive.
 	 */
-	if (!order)
-		nr_allocated = alloc_pages_bulk_array_node(
-			gfp, nid, nr_pages, pages);
-	else
+	if (!order) {
+		while (nr_allocated < nr_pages) {
+			unsigned int nr, nr_pages_request;
+
+			/*
+			 * A maximum allowed request is hard-coded and is 100
+			 * pages per call. That is done in order to prevent a
+			 * long preemption off scenario in the bulk-allocator
+			 * so the range is [1:100].
+			 */
+			nr_pages_request = min(100U, nr_pages - nr_allocated);
+
+			nr = alloc_pages_bulk_array_node(gfp, nid,
+				nr_pages_request, pages + nr_allocated);
+
+			nr_allocated += nr;
+			cond_resched();
+
+			/*
+			 * If zero or pages were obtained partly,
+			 * fallback to a single page allocator.
+			 */
+			if (nr != nr_pages_request)
+				break;
+		}
+	} else
 		/*
 		 * Compound pages required for remap_vmalloc_page if
 		 * high-order pages.
-- 
2.20.1

[PATCH v3 2/2] mm/vmalloc: Remove gfpflags_allow_blocking() check

[Uladzislau Rezki (Sony)]

Get rid of gfpflags_allow_blocking() check from the vmalloc() path
as it is supposed to be sleepable anyway. Thus remove it from the
alloc_vmap_area() as well as from the vm_area_alloc_pages().

Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
 mm/vmalloc.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a9a6d28c8baa..24a3955d5a36 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1479,6 +1479,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 				int node, gfp_t gfp_mask)
 {
 	struct vmap_area *va;
+	unsigned long freed;
 	unsigned long addr;
 	int purged = 0;
 	int ret;
@@ -1542,13 +1543,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 		goto retry;
 	}
 
-	if (gfpflags_allow_blocking(gfp_mask)) {
-		unsigned long freed = 0;
-		blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
-		if (freed > 0) {
-			purged = 0;
-			goto retry;
-		}
+	freed = 0;
+	blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
+
+	if (freed > 0) {
+		purged = 0;
+		goto retry;
 	}
 
 	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
@@ -2834,9 +2834,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 		for (i = 0; i < (1U << order); i++)
 			pages[nr_allocated + i] = page + i;
 
-		if (gfpflags_allow_blocking(gfp))
-			cond_resched();
-
+		cond_resched();
 		nr_allocated += 1U << order;
 	}
 
-- 
2.20.1