Re: [PATCH v2 0/5] mm: support parallel free of memory

[Aaron Lu <aaron.lu@intel.com>]

On Wed, Mar 15, 2017 at 03:56:02PM +0100, Vlastimil Babka wrote:
> I wonder if the difference would be larger if the parallelism was done
> on a higher level, something around unmap_page_range(). IIUC the current

I guess I misunderstand you in my last email - doing it at
unmap_page_range() level is essentially doing it at a per-VMA level
since it is the main function used in unmap_single_vma(). We have tried
that and felt that it's not flexible as the proposed approach since
it wouldn't parallize well for:
1 work load that uses only 1 or very few huge VMA;
2 work load that has a lot of small VMAs.

The code is nice and easy though(developed at v4.9 time frame):

>From f6d5cfde888b9e0356719fabe8754fdfe6fe236b Mon Sep 17 00:00:00 2001
From: Aaron Lu <aaron.lu@intel.com>
Date: Wed, 11 Jan 2017 15:56:06 +0800
Subject: [PATCH] mm: async free vma

---
 include/linux/mm_types.h |  6 ++++++
 mm/memory.c              | 23 ++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4a8acedf4b7d..d10d2ce8f8f4 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -358,6 +358,12 @@ struct vm_area_struct {
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+
+	struct vma_free_ctx {
+		unsigned long start_addr;
+		unsigned long end_addr;
+		struct work_struct work;
+	} free_ctx;
 };
 
 struct core_thread {
diff --git a/mm/memory.c b/mm/memory.c
index e18c57bdc75c..0fe4e45a044b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1345,6 +1345,17 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 	}
 }
 
+static void unmap_single_vma_work(struct work_struct *work)
+{
+	struct vma_free_ctx *ctx = container_of(work, struct vma_free_ctx, work);
+	struct vm_area_struct *vma = container_of(ctx, struct vm_area_struct, free_ctx);
+	struct mmu_gather tlb;
+
+	tlb_gather_mmu(&tlb, vma->vm_mm, ctx->start_addr, ctx->end_addr);
+	unmap_single_vma(&tlb, vma, ctx->start_addr, ctx->end_addr, NULL);
+	tlb_finish_mmu(&tlb, ctx->start_addr, ctx->end_addr);
+}
+
 /**
  * unmap_vmas - unmap a range of memory covered by a list of vma's
  * @tlb: address of the caller's struct mmu_gather
@@ -1368,10 +1379,20 @@ void unmap_vmas(struct mmu_gather *tlb,
 		unsigned long end_addr)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct vma_free_ctx *ctx;
+	struct vm_area_struct *tmp = vma;
 
 	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
+	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
+		ctx = &vma->free_ctx;
+		ctx->start_addr = start_addr;
+		ctx->end_addr = end_addr;
+		INIT_WORK(&ctx->work, unmap_single_vma_work);
+		queue_work(system_unbound_wq, &ctx->work);
+	}
+	vma = tmp;
 	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
-		unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
+		flush_work(&vma->free_ctx.work);
 	mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
 }
 
-- 
2.9.3