All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stefan Roesch <shr@devkernel.io>
To: kernel-team@fb.com
Cc: shr@devkernel.io, linux-mm@kvack.org, riel@surriel.com,
	mhocko@suse.com, david@redhat.com,
	linux-kselftest@vger.kernel.org, linux-doc@vger.kernel.org,
	akpm@linux-foundation.org
Subject: [RFC PATCH v2 04/19] mm: invoke madvise for all vmas in scan_get_next_rmap_item
Date: Fri, 10 Feb 2023 13:50:08 -0800	[thread overview]
Message-ID: <20230210215023.2740545-5-shr@devkernel.io> (raw)
In-Reply-To: <20230210215023.2740545-1-shr@devkernel.io>

If the new flag MMF_VM_MERGE_ANY has been set for a process, iterate
over all the vmas and enable ksm if possible. For the vmas that can be
ksm enabled this is only done once.

Signed-off-by: Stefan Roesch <shr@devkernel.io>
---
 mm/ksm.c | 27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/mm/ksm.c b/mm/ksm.c
index 3597ae52fe7b..efd8d3804de3 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1063,6 +1063,7 @@ static int unmerge_and_remove_all_rmap_items(void)
 
 			mm_slot_free(mm_slot_cache, mm_slot);
 			clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+			clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 			mmdrop(mm);
 		} else
 			spin_unlock(&ksm_mmlist_lock);
@@ -2329,6 +2330,17 @@ static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot,
 	return rmap_item;
 }
 
+static bool vma_ksm_mergeable(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_MERGEABLE)
+		return true;
+
+	if (test_bit(MMF_VM_MERGE_ANY, &vma->vm_mm->flags))
+		return true;
+
+	return false;
+}
+
 static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 {
 	struct mm_struct *mm;
@@ -2405,8 +2417,20 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 		goto no_vmas;
 
 	for_each_vma(vmi, vma) {
-		if (!(vma->vm_flags & VM_MERGEABLE))
+		if (!vma_ksm_mergeable(vma))
 			continue;
+		if (!(vma->vm_flags & VM_MERGEABLE)) {
+			unsigned long flags = vma->vm_flags;
+
+			/* madvise failed, use next vma */
+			if (ksm_madvise(vma, vma->vm_start, vma->vm_end, MADV_MERGEABLE, &flags))
+				continue;
+			/* vma, not supported as being mergeable */
+			if (!(flags & VM_MERGEABLE))
+				continue;
+
+			vm_flags_set(vma, VM_MERGEABLE);
+		}
 		if (ksm_scan.address < vma->vm_start)
 			ksm_scan.address = vma->vm_start;
 		if (!vma->anon_vma)
@@ -2491,6 +2515,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 
 		mm_slot_free(mm_slot_cache, mm_slot);
 		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 		mmap_read_unlock(mm);
 		mmdrop(mm);
 	} else {
-- 
2.30.2


  parent reply	other threads:[~2023-02-10 21:50 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-10 21:50 [RFC PATCH v2 00/19] mm: process/cgroup ksm support Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 01/19] mm: add new flag to enable ksm per process Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 02/19] mm: add flag to __ksm_enter Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 03/19] mm: add flag to __ksm_exit call Stefan Roesch
2023-02-10 21:50 ` Stefan Roesch [this message]
2023-02-10 21:50 ` [RFC PATCH v2 05/19] mm: support disabling of ksm for a process Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 06/19] mm: add new prctl option to get and set " Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 07/19] mm: split off pages_volatile function Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 08/19] mm: expose general_profit metric Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 09/19] docs: document general_profit sysfs knob Stefan Roesch
2023-02-11  8:17   ` Bagas Sanjaya
2023-02-15 23:00     ` Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 10/19] mm: calculate ksm process profit metric Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 11/19] mm: add ksm_merge_type() function Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 12/19] mm: expose ksm process profit metric in ksm_stat Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 13/19] mm: expose ksm merge type " Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 14/19] docs: document new procfs ksm knobs Stefan Roesch
2023-02-11  8:18   ` Bagas Sanjaya
2023-02-10 21:50 ` [RFC PATCH v2 15/19] tools: add new prctl flags to prctl in tools dir Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 16/19] selftests/vm: add KSM prctl merge test Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 17/19] selftests/vm: add KSM get merge type test Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 18/19] selftests/vm: add KSM fork test Stefan Roesch
2023-02-10 21:50 ` [RFC PATCH v2 19/19] selftests/vm: add two functions for debugging merge outcome Stefan Roesch
2023-02-10 23:23 ` [RFC PATCH v2 00/19] mm: process/cgroup ksm support Matthew Wilcox
2023-02-11  2:41   ` Rik van Riel
2023-02-21 16:10 ` Johannes Weiner
2023-02-21 17:59   ` Stefan Roesch

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=20230210215023.2740545-5-shr@devkernel.io \
    --to=shr@devkernel.io \
    --cc=akpm@linux-foundation.org \
    --cc=david@redhat.com \
    --cc=kernel-team@fb.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=riel@surriel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.