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:   Sun, 28 May 2023 23:28:52 -0700 (PDT)
From:   Hugh Dickins <hughd@google.com>
To:     Andrew Morton <akpm@linux-foundation.org>
cc:     Mike Kravetz <mike.kravetz@oracle.com>,
        Mike Rapoport <rppt@kernel.org>,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Matthew Wilcox <willy@infradead.org>,
        David Hildenbrand <david@redhat.com>,
        Suren Baghdasaryan <surenb@google.com>,
        Qi Zheng <zhengqi.arch@bytedance.com>,
        Yang Shi <shy828301@gmail.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Peter Xu <peterx@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Will Deacon <will@kernel.org>, Yu Zhao <yuzhao@google.com>,
        Alistair Popple <apopple@nvidia.com>,
        Ralph Campbell <rcampbell@nvidia.com>,
        Ira Weiny <ira.weiny@intel.com>,
        Steven Price <steven.price@arm.com>,
        SeongJae Park <sj@kernel.org>,
        Naoya Horiguchi <naoya.horiguchi@nec.com>,
        Christophe Leroy <christophe.leroy@csgroup.eu>,
        Zack Rusin <zackr@vmware.com>, Jason Gunthorpe <jgg@ziepe.ca>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Anshuman Khandual <anshuman.khandual@arm.com>,
        Pasha Tatashin <pasha.tatashin@soleen.com>,
        Miaohe Lin <linmiaohe@huawei.com>,
        Minchan Kim <minchan@kernel.org>,
        Christoph Hellwig <hch@infradead.org>,
        Song Liu <song@kernel.org>,
        Thomas Hellstrom <thomas.hellstrom@linux.intel.com>,
        Russell King <linux@armlinux.org.uk>,
        "David S. Miller" <davem@davemloft.net>,
        Michael Ellerman <mpe@ellerman.id.au>,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
        Heiko Carstens <hca@linux.ibm.com>,
        Christian Borntraeger <borntraeger@linux.ibm.com>,
        Claudio Imbrenda <imbrenda@linux.ibm.com>,
        Alexander Gordeev <agordeev@linux.ibm.com>,
        Jann Horn <jannh@google.com>,
        linux-arm-kernel@lists.infradead.org, sparclinux@vger.kernel.org,
        linuxppc-dev@lists.ozlabs.org, linux-s390@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH 11/12] mm/khugepaged: delete
 khugepaged_collapse_pte_mapped_thps()
In-Reply-To: <35e983f5-7ed3-b310-d949-9ae8b130cdab@google.com>
Message-ID: <1bf6f10-1f8d-d410-98b9-66cbf9a45c2@google.com>
References: <35e983f5-7ed3-b310-d949-9ae8b130cdab@google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Precedence: bulk

Now that retract_page_tables() can retract page tables reliably, without
depending on trylocks, delete all the apparatus for khugepaged to try
again later: khugepaged_collapse_pte_mapped_thps() etc; and free up the
per-mm memory which was set aside for that in the khugepaged_mm_slot.

But one part of that is worth keeping: when hpage_collapse_scan_file()
found SCAN_PTE_MAPPED_HUGEPAGE, that address was noted in the mm_slot
to be tried for retraction later - catching, for example, page tables
where a reversible mprotect() of a portion had required splitting the
pmd, but now it can be recollapsed.  Call collapse_pte_mapped_thp()
directly in this case (why was it deferred before?  I assume an issue
with needing mmap_lock for write, but now it's only needed for read).

Signed-off-by: Hugh Dickins <hughd@google.com>
---
 mm/khugepaged.c | 125 +++++++-----------------------------------------
 1 file changed, 16 insertions(+), 109 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 2999500abdd5..301c0e54a2ef 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -92,8 +92,6 @@ static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
 
 static struct kmem_cache *mm_slot_cache __read_mostly;
 
-#define MAX_PTE_MAPPED_THP 8
-
 struct collapse_control {
 	bool is_khugepaged;
 
@@ -107,15 +105,9 @@ struct collapse_control {
 /**
  * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned
  * @slot: hash lookup from mm to mm_slot
- * @nr_pte_mapped_thp: number of pte mapped THP
- * @pte_mapped_thp: address array corresponding pte mapped THP
  */
 struct khugepaged_mm_slot {
 	struct mm_slot slot;
-
-	/* pte-mapped THP in this mm */
-	int nr_pte_mapped_thp;
-	unsigned long pte_mapped_thp[MAX_PTE_MAPPED_THP];
 };
 
 /**
@@ -1441,50 +1433,6 @@ static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot)
 }
 
 #ifdef CONFIG_SHMEM
-/*
- * Notify khugepaged that given addr of the mm is pte-mapped THP. Then
- * khugepaged should try to collapse the page table.
- *
- * Note that following race exists:
- * (1) khugepaged calls khugepaged_collapse_pte_mapped_thps() for mm_struct A,
- *     emptying the A's ->pte_mapped_thp[] array.
- * (2) MADV_COLLAPSE collapses some file extent with target mm_struct B, and
- *     retract_page_tables() finds a VMA in mm_struct A mapping the same extent
- *     (at virtual address X) and adds an entry (for X) into mm_struct A's
- *     ->pte-mapped_thp[] array.
- * (3) khugepaged calls khugepaged_collapse_scan_file() for mm_struct A at X,
- *     sees a pte-mapped THP (SCAN_PTE_MAPPED_HUGEPAGE) and adds an entry
- *     (for X) into mm_struct A's ->pte-mapped_thp[] array.
- * Thus, it's possible the same address is added multiple times for the same
- * mm_struct.  Should this happen, we'll simply attempt
- * collapse_pte_mapped_thp() multiple times for the same address, under the same
- * exclusive mmap_lock, and assuming the first call is successful, subsequent
- * attempts will return quickly (without grabbing any additional locks) when
- * a huge pmd is found in find_pmd_or_thp_or_none().  Since this is a cheap
- * check, and since this is a rare occurrence, the cost of preventing this
- * "multiple-add" is thought to be more expensive than just handling it, should
- * it occur.
- */
-static bool khugepaged_add_pte_mapped_thp(struct mm_struct *mm,
-					  unsigned long addr)
-{
-	struct khugepaged_mm_slot *mm_slot;
-	struct mm_slot *slot;
-	bool ret = false;
-
-	VM_BUG_ON(addr & ~HPAGE_PMD_MASK);
-
-	spin_lock(&khugepaged_mm_lock);
-	slot = mm_slot_lookup(mm_slots_hash, mm);
-	mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot);
-	if (likely(mm_slot && mm_slot->nr_pte_mapped_thp < MAX_PTE_MAPPED_THP)) {
-		mm_slot->pte_mapped_thp[mm_slot->nr_pte_mapped_thp++] = addr;
-		ret = true;
-	}
-	spin_unlock(&khugepaged_mm_lock);
-	return ret;
-}
-
 /* hpage must be locked, and mmap_lock must be held */
 static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr,
 			pmd_t *pmdp, struct page *hpage)
@@ -1675,29 +1623,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	goto drop_hpage;
 }
 
-static void khugepaged_collapse_pte_mapped_thps(struct khugepaged_mm_slot *mm_slot)
-{
-	struct mm_slot *slot = &mm_slot->slot;
-	struct mm_struct *mm = slot->mm;
-	int i;
-
-	if (likely(mm_slot->nr_pte_mapped_thp == 0))
-		return;
-
-	if (!mmap_write_trylock(mm))
-		return;
-
-	if (unlikely(hpage_collapse_test_exit(mm)))
-		goto out;
-
-	for (i = 0; i < mm_slot->nr_pte_mapped_thp; i++)
-		collapse_pte_mapped_thp(mm, mm_slot->pte_mapped_thp[i], false);
-
-out:
-	mm_slot->nr_pte_mapped_thp = 0;
-	mmap_write_unlock(mm);
-}
-
 static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 {
 	struct vm_area_struct *vma;
@@ -2326,16 +2251,6 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 {
 	BUILD_BUG();
 }
-
-static void khugepaged_collapse_pte_mapped_thps(struct khugepaged_mm_slot *mm_slot)
-{
-}
-
-static bool khugepaged_add_pte_mapped_thp(struct mm_struct *mm,
-					  unsigned long addr)
-{
-	return false;
-}
 #endif
 
 static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
@@ -2365,7 +2280,6 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 		khugepaged_scan.mm_slot = mm_slot;
 	}
 	spin_unlock(&khugepaged_mm_lock);
-	khugepaged_collapse_pte_mapped_thps(mm_slot);
 
 	mm = slot->mm;
 	/*
@@ -2418,36 +2332,29 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 						khugepaged_scan.address);
 
 				mmap_read_unlock(mm);
-				*result = hpage_collapse_scan_file(mm,
-								   khugepaged_scan.address,
-								   file, pgoff, cc);
 				mmap_locked = false;
+				*result = hpage_collapse_scan_file(mm,
+					khugepaged_scan.address, file, pgoff, cc);
+				if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
+					mmap_read_lock(mm);
+					mmap_locked = true;
+					if (hpage_collapse_test_exit(mm)) {
+						fput(file);
+						goto breakouterloop;
+					}
+					*result = collapse_pte_mapped_thp(mm,
+						khugepaged_scan.address, false);
+					if (*result == SCAN_PMD_MAPPED)
+						*result = SCAN_SUCCEED;
+				}
 				fput(file);
 			} else {
 				*result = hpage_collapse_scan_pmd(mm, vma,
-								  khugepaged_scan.address,
-								  &mmap_locked,
-								  cc);
+					khugepaged_scan.address, &mmap_locked, cc);
 			}
-			switch (*result) {
-			case SCAN_PTE_MAPPED_HUGEPAGE: {
-				pmd_t *pmd;
 
-				*result = find_pmd_or_thp_or_none(mm,
-								  khugepaged_scan.address,
-								  &pmd);
-				if (*result != SCAN_SUCCEED)
-					break;
-				if (!khugepaged_add_pte_mapped_thp(mm,
-								   khugepaged_scan.address))
-					break;
-			} fallthrough;
-			case SCAN_SUCCEED:
+			if (*result == SCAN_SUCCEED)
 				++khugepaged_pages_collapsed;
-				break;
-			default:
-				break;
-			}
 
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
-- 
2.35.3