Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Fri, 24 Jun 2022 17:36:52 +0000
In-Reply-To: <20220624173656.2033256-1-jthoughton@google.com>
Message-Id: <20220624173656.2033256-23-jthoughton@google.com>
Mime-Version: 1.0
References: <20220624173656.2033256-1-jthoughton@google.com>
Subject: [RFC PATCH 22/26] madvise: add uapi for HugeTLB HGM collapse: MADV_COLLAPSE
From:   James Houghton <jthoughton@google.com>
To:     Mike Kravetz <mike.kravetz@oracle.com>,
        Muchun Song <songmuchun@bytedance.com>,
        Peter Xu <peterx@redhat.com>
Cc:     David Hildenbrand <david@redhat.com>,
        David Rientjes <rientjes@google.com>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Mina Almasry <almasrymina@google.com>,
        Jue Wang <juew@google.com>,
        Manish Mishra <manish.mishra@nutanix.com>,
        "Dr . David Alan Gilbert" <dgilbert@redhat.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        James Houghton <jthoughton@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

This commit is co-opting the same madvise mode that is being introduced
by zokeefe@google.com to manually collapse THPs[1].

As with the rest of the high-granularity mapping support, MADV_COLLAPSE
is only supported for shared VMAs right now.

[1] https://lore.kernel.org/linux-mm/20220604004004.954674-10-zokeefe@google.com/

Signed-off-by: James Houghton <jthoughton@google.com>
---
 include/uapi/asm-generic/mman-common.h |  2 ++
 mm/madvise.c                           | 23 +++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index 6c1aa92a92e4..b686920ca731 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -77,6 +77,8 @@
 
 #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
 
+#define MADV_COLLAPSE	25		/* collapse an address range into hugepages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/mm/madvise.c b/mm/madvise.c
index d7b4f2602949..c624c0f02276 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -59,6 +59,7 @@ static int madvise_need_mmap_write(int behavior)
 	case MADV_FREE:
 	case MADV_POPULATE_READ:
 	case MADV_POPULATE_WRITE:
+	case MADV_COLLAPSE:
 		return 0;
 	default:
 		/* be safe, default to 1. list exceptions explicitly */
@@ -981,6 +982,20 @@ static long madvise_remove(struct vm_area_struct *vma,
 	return error;
 }
 
+static int madvise_collapse(struct vm_area_struct *vma,
+			    struct vm_area_struct **prev,
+			    unsigned long start, unsigned long end)
+{
+	bool shared = vma->vm_flags & VM_SHARED;
+	*prev = vma;
+
+	/* Only allow collapsing for HGM-enabled, shared mappings. */
+	if (!is_vm_hugetlb_page(vma) || !hugetlb_hgm_enabled(vma) || !shared)
+		return -EINVAL;
+
+	return hugetlb_collapse(vma->vm_mm, vma, start, end);
+}
+
 /*
  * Apply an madvise behavior to a region of a vma.  madvise_update_vma
  * will handle splitting a vm area into separate areas, each area with its own
@@ -1011,6 +1026,8 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 	case MADV_POPULATE_READ:
 	case MADV_POPULATE_WRITE:
 		return madvise_populate(vma, prev, start, end, behavior);
+	case MADV_COLLAPSE:
+		return madvise_collapse(vma, prev, start, end);
 	case MADV_NORMAL:
 		new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
 		break;
@@ -1158,6 +1175,9 @@ madvise_behavior_valid(int behavior)
 #ifdef CONFIG_MEMORY_FAILURE
 	case MADV_SOFT_OFFLINE:
 	case MADV_HWPOISON:
+#endif
+#ifdef CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING
+	case MADV_COLLAPSE:
 #endif
 		return true;
 
@@ -1351,6 +1371,9 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
  *		triggering read faults if required
  *  MADV_POPULATE_WRITE - populate (prefault) page tables writable by
  *		triggering write faults if required
+ *  MADV_COLLAPSE - collapse a high-granularity HugeTLB mapping into huge
+ *		mappings. This is useful after an entire hugepage has been
+ *		mapped with individual small UFFDIO_CONTINUE operations.
  *
  * return values:
  *  zero    - success
-- 
2.37.0.rc0.161.g10f37bed90-goog