linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Dev Jain <dev.jain@arm.com>
To: akpm@linux-foundation.org, david@redhat.com, willy@infradead.org,
	kirill.shutemov@linux.intel.com
Cc: npache@redhat.com, ryan.roberts@arm.com,
	anshuman.khandual@arm.com, catalin.marinas@arm.com,
	cl@gentwo.org, vbabka@suse.cz, mhocko@suse.com,
	apopple@nvidia.com, dave.hansen@linux.intel.com, will@kernel.org,
	baohua@kernel.org, jack@suse.cz, srivatsa@csail.mit.edu,
	haowenchao22@gmail.com, hughd@google.com,
	aneesh.kumar@kernel.org, yang@os.amperecomputing.com,
	peterx@redhat.com, ioworker0@gmail.com,
	wangkefeng.wang@huawei.com, ziy@nvidia.com, jglisse@google.com,
	surenb@google.com, vishal.moola@gmail.com, zokeefe@google.com,
	zhengqi.arch@bytedance.com, jhubbard@nvidia.com,
	21cnbao@gmail.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, Dev Jain <dev.jain@arm.com>
Subject: [PATCH v2 16/17] khugepaged: Implement strict policy for mTHP collapse
Date: Tue, 11 Feb 2025 16:43:25 +0530	[thread overview]
Message-ID: <20250211111326.14295-17-dev.jain@arm.com> (raw)
In-Reply-To: <20250211111326.14295-1-dev.jain@arm.com>

As noted in the discussion thread ending at [1], avoid the creep problem by
collapsing to mTHPs only if max_ptes_none is zero or 511. Along with this,
make mTHP collapse conditions stricter by removing scaling of max_ptes_shared
and max_ptes_swap, and consider collapse only if there are no shared or
swap PTEs in the range.

[1] https://lore.kernel.org/all/8114d47b-b383-4d6e-ab65-a0e88b99c873@arm.com/

Signed-off-by: Dev Jain <dev.jain@arm.com>
---
 mm/khugepaged.c | 37 ++++++++++++++++++++++++++++++++-----
 1 file changed, 32 insertions(+), 5 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index d2bb008b95e7..b589f889bb5a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -417,6 +417,17 @@ static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
 
 static bool thp_enabled(void)
 {
+	bool anon_pmd_enabled = (test_bit(PMD_ORDER, &huge_anon_orders_always) ||
+				 test_bit(PMD_ORDER, &huge_anon_orders_madvise) ||
+			         (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
+			         hugepage_global_enabled()));
+
+	/*
+	 * If PMD_ORDER is ineligible for collapse, check if mTHP collapse policy is obeyed;
+	 * see Documentation/admin-guide/transhuge.rst
+	 */
+	bool anon_collapse_mthp = (khugepaged_max_ptes_none == 0 ||
+			      khugepaged_max_ptes_none == HPAGE_PMD_NR - 1);
 	/*
 	 * We cover the anon, shmem and the file-backed case here; file-backed
 	 * hugepages, when configured in, are determined by the global control.
@@ -427,8 +438,9 @@ static bool thp_enabled(void)
 	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
 	    hugepage_global_enabled())
 		return true;
-	if (huge_anon_orders_always || huge_anon_orders_madvise ||
-	    (huge_anon_orders_inherit && hugepage_global_enabled()))
+	if ((huge_anon_orders_always || huge_anon_orders_madvise ||
+	    (huge_anon_orders_inherit && hugepage_global_enabled())) &&
+	    (anon_pmd_enabled || anon_collapse_mthp))
 		return true;
 	if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled())
 		return true;
@@ -578,13 +590,16 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 	pte_t *_pte;
 	int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
 	bool writable = false;
-	unsigned int max_ptes_shared = khugepaged_max_ptes_shared >> (HPAGE_PMD_ORDER - order);
+	unsigned int max_ptes_shared = khugepaged_max_ptes_shared;
 	unsigned int max_ptes_none = khugepaged_max_ptes_none >> (HPAGE_PMD_ORDER - order);
 	bool all_pfns_present = true;
 	bool all_pfns_contig = true;
 	bool first_pfn_aligned = true;
 	pte_t prev_pteval;
 
+	if (order != HPAGE_PMD_ORDER)
+		max_ptes_shared = 0;
+
 	for (_pte = pte; _pte < pte + (1UL << order);
 	     _pte++, address += PAGE_SIZE) {
 		pte_t pteval = ptep_get(_pte);
@@ -1453,11 +1468,16 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 	order = highest_order(orders);
 	VM_BUG_ON(address & ((PAGE_SIZE << order) - 1));
 
+	max_ptes_none = khugepaged_max_ptes_none;
+	max_ptes_shared = khugepaged_max_ptes_shared;
+	max_ptes_swap = khugepaged_max_ptes_swap;
+
 scan_pte_range:
 
-	max_ptes_shared = khugepaged_max_ptes_shared >> (HPAGE_PMD_ORDER - order);
+	if (order != HPAGE_PMD_ORDER)
+		max_ptes_shared = max_ptes_swap = 0;
+
 	max_ptes_none = khugepaged_max_ptes_none >> (HPAGE_PMD_ORDER - order);
-	max_ptes_swap = khugepaged_max_ptes_swap >> (HPAGE_PMD_ORDER - order);
 	referenced = 0, shared = 0, none_or_zero = 0, unmapped = 0;
 	all_pfns_present = true, all_pfns_contig = true, first_pfn_aligned = true;
 
@@ -2651,6 +2671,11 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 	int order;
 	bool is_file_vma;
 	int prev_progress = 0;
+	bool collapse_mthp = true;
+
+	/* Avoid the creep problem; see Documentation/admin-guide/transhuge.rst */
+	if (khugepaged_max_ptes_none && khugepaged_max_ptes_none != HPAGE_PMD_NR - 1)
+		collapse_mthp = false;
 
 	VM_BUG_ON(!pages);
 	lockdep_assert_held(&khugepaged_mm_lock);
@@ -2710,6 +2735,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 			/* select the highest possible order for the VMA */
 			order = highest_order(orders);
 			while (orders) {
+				if (order != HPAGE_PMD_ORDER && !collapse_mthp)
+					goto skip;
 				hend = round_down(vma->vm_end, PAGE_SIZE << order);
 				if (khugepaged_scan.address <= hend)
 					break;
-- 
2.30.2



  parent reply	other threads:[~2025-02-11 11:16 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-11 11:13 [PATCH v2 00/17] khugepaged: Asynchronous " Dev Jain
2025-02-11 11:13 ` [PATCH v2 01/17] khugepaged: Generalize alloc_charge_folio() Dev Jain
2025-02-11 11:13 ` [PATCH v2 02/17] khugepaged: Generalize hugepage_vma_revalidate() Dev Jain
2025-02-11 11:13 ` [PATCH v2 03/17] khugepaged: Generalize __collapse_huge_page_swapin() Dev Jain
2025-02-11 11:13 ` [PATCH v2 04/17] khugepaged: Generalize __collapse_huge_page_isolate() Dev Jain
2025-02-11 11:13 ` [PATCH v2 05/17] khugepaged: Generalize __collapse_huge_page_copy() Dev Jain
2025-02-11 11:13 ` [PATCH v2 06/17] khugepaged: Abstract PMD-THP collapse Dev Jain
2025-02-11 11:13 ` [PATCH v2 07/17] khugepaged: Scan PTEs order-wise Dev Jain
2025-02-11 11:13 ` [PATCH v2 08/17] khugepaged: Introduce vma_collapse_anon_folio() Dev Jain
2025-02-11 11:13 ` [PATCH v2 09/17] khugepaged: Define collapse policy if a larger folio is already mapped Dev Jain
2025-02-11 11:13 ` [PATCH v2 10/17] khugepaged: Exit early on fully-mapped aligned mTHP Dev Jain
2025-02-11 11:13 ` [PATCH v2 11/17] khugepaged: Enable sysfs to control order of collapse Dev Jain
2025-02-11 11:13 ` [PATCH v2 12/17] khugepaged: Enable variable-sized VMA collapse Dev Jain
2025-02-11 11:13 ` [PATCH v2 13/17] khugepaged: Lock all VMAs mapping the PTE table Dev Jain
2025-02-11 11:13 ` [PATCH v2 14/17] khugepaged: Reset scan address to correct alignment Dev Jain
2025-02-11 11:13 ` [PATCH v2 15/17] khugepaged: Delay cond_resched() Dev Jain
2025-02-11 11:13 ` Dev Jain [this message]
2025-02-11 11:13 ` [PATCH v2 17/17] Documentation: transhuge: Define khugepaged mTHP collapse policy Dev Jain
2025-02-11 23:23 ` [PATCH v2 00/17] khugepaged: Asynchronous mTHP collapse Andrew Morton
2025-02-12  4:18   ` Dev Jain
2025-02-15  1:47 ` Nico Pache
2025-02-15  7:36   ` Dev Jain

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250211111326.14295-17-dev.jain@arm.com \
    --to=dev.jain@arm.com \
    --cc=21cnbao@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@kernel.org \
    --cc=anshuman.khandual@arm.com \
    --cc=apopple@nvidia.com \
    --cc=baohua@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=cl@gentwo.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@redhat.com \
    --cc=haowenchao22@gmail.com \
    --cc=hughd@google.com \
    --cc=ioworker0@gmail.com \
    --cc=jack@suse.cz \
    --cc=jglisse@google.com \
    --cc=jhubbard@nvidia.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=npache@redhat.com \
    --cc=peterx@redhat.com \
    --cc=ryan.roberts@arm.com \
    --cc=srivatsa@csail.mit.edu \
    --cc=surenb@google.com \
    --cc=vbabka@suse.cz \
    --cc=vishal.moola@gmail.com \
    --cc=wangkefeng.wang@huawei.com \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=yang@os.amperecomputing.com \
    --cc=zhengqi.arch@bytedance.com \
    --cc=ziy@nvidia.com \
    --cc=zokeefe@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox