All of lore.kernel.org
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: linux-mm@kvack.org
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Christoph Hellwig <hch@lst.de>,
	Uladzislau Rezki <urezki@gmail.com>,
	Lorenzo Stoakes <lstoakes@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Baoquan He <bhe@redhat.com>
Subject: [patch 3/6] mm/vmalloc: Prevent flushing dirty space over and over
Date: Tue, 23 May 2023 16:02:13 +0200 (CEST)	[thread overview]
Message-ID: <20230523140002.690874212@linutronix.de> (raw)
In-Reply-To: 20230523135902.517032811@linutronix.de

vmap blocks which have active mappings cannot be purged. Allocations which
have been freed are accounted for in vmap_block::dirty_min/max, so that
they can be detected in _vm_unmap_aliases() as potentially stale TLBs.

If there are several invocations of _vm_unmap_aliases() then each of them
will flush the dirty range. That's pointless and just increases the
probability of full TLB flushes.

Avoid that by resetting the flush range after accounting for it. That's
safe versus other invocations of _vm_unmap_aliases() because this is all
serialized with vmap_purge_lock.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 mm/vmalloc.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2224,7 +2224,7 @@ static void vb_free(unsigned long addr,
 
 	spin_lock(&vb->lock);
 
-	/* Expand dirty range */
+	/* Expand the not yet TLB flushed dirty range */
 	vb->dirty_min = min(vb->dirty_min, offset);
 	vb->dirty_max = max(vb->dirty_max, offset + (1UL << order));
 
@@ -2262,7 +2262,7 @@ static void _vm_unmap_aliases(unsigned l
 			 * space to be flushed.
 			 */
 			if (!purge_fragmented_block(vb, vbq, &purge_list) &&
-			    vb->dirty && vb->dirty != VMAP_BBMAP_BITS) {
+			    vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
 				unsigned long va_start = vb->va->va_start;
 				unsigned long s, e;
 
@@ -2272,6 +2272,10 @@ static void _vm_unmap_aliases(unsigned l
 				start = min(s, start);
 				end   = max(e, end);
 
+				/* Prevent that this is flushed more than once */
+				vb->dirty_min = VMAP_BBMAP_BITS;
+				vb->dirty_max = 0;
+
 				flush = 1;
 			}
 			spin_unlock(&vb->lock);



  parent reply	other threads:[~2023-05-23 14:04 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-23 14:02 [patch 0/6] mm/vmalloc: Assorted fixes and improvements Thomas Gleixner
2023-05-23 14:02 ` [patch 1/6] mm/vmalloc: Prevent stale TLBs in fully utilized blocks Thomas Gleixner
2023-05-23 15:17   ` Christoph Hellwig
2023-05-23 16:40     ` Thomas Gleixner
2023-05-23 16:47       ` Uladzislau Rezki
2023-05-23 19:18   ` Lorenzo Stoakes
2023-05-24  9:19     ` Uladzislau Rezki
2023-05-24  9:25   ` Baoquan He
2023-05-24  9:51     ` Thomas Gleixner
2023-05-24 11:24       ` Baoquan He
2023-05-24 11:26         ` Baoquan He
2023-05-24 11:36         ` Uladzislau Rezki
2023-05-24 12:49           ` Thomas Gleixner
2023-05-24 12:44         ` Thomas Gleixner
2023-05-24 13:41           ` Baoquan He
2023-05-24 14:31             ` Thomas Gleixner
2023-05-24  9:32   ` Baoquan He
2023-05-24  9:52     ` Thomas Gleixner
2023-05-24 14:10       ` Baoquan He
2023-05-24 14:35         ` Thomas Gleixner
2023-05-23 14:02 ` [patch 2/6] mm/vmalloc: Avoid iterating over per CPU vmap blocks twice Thomas Gleixner
2023-05-23 15:21   ` Christoph Hellwig
2023-05-23 14:02 ` Thomas Gleixner [this message]
2023-05-23 15:27   ` [patch 3/6] mm/vmalloc: Prevent flushing dirty space over and over Christoph Hellwig
2023-05-23 16:10     ` Thomas Gleixner
2023-05-24  9:43   ` Baoquan He
2023-05-23 14:02 ` [patch 4/6] mm/vmalloc: Check free space in vmap_block lockless Thomas Gleixner
2023-05-23 15:29   ` Christoph Hellwig
2023-05-23 16:17     ` Thomas Gleixner
2023-05-24  9:20       ` Uladzislau Rezki
2023-05-23 14:02 ` [patch 5/6] mm/vmalloc: Add missing READ/WRITE_ONCE() annotations Thomas Gleixner
2023-05-24  9:15   ` Uladzislau Rezki
2023-05-23 14:02 ` [patch 6/6] mm/vmalloc: Dont purge usable blocks unnecessarily Thomas Gleixner
2023-05-23 15:30   ` Christoph Hellwig
2023-05-24 10:34   ` Baoquan He
2023-05-24 12:55     ` Thomas Gleixner
2023-05-23 16:24 ` [patch 0/6] mm/vmalloc: Assorted fixes and improvements Uladzislau Rezki
2023-05-23 17:33   ` Thomas Gleixner
2023-05-23 17:39     ` Thomas Gleixner
2023-05-23 17:48       ` Uladzislau Rezki
2023-05-23 17:51         ` Uladzislau Rezki
2023-05-23 17:55         ` Uladzislau Rezki
2023-05-23 18:40           ` Thomas Gleixner

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=20230523140002.690874212@linutronix.de \
    --to=tglx@linutronix.de \
    --cc=akpm@linux-foundation.org \
    --cc=bhe@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-mm@kvack.org \
    --cc=lstoakes@gmail.com \
    --cc=peterz@infradead.org \
    --cc=urezki@gmail.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.