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 4/6] mm/vmalloc: Check free space in vmap_block lockless
Date: Tue, 23 May 2023 16:02:14 +0200 (CEST)	[thread overview]
Message-ID: <20230523140002.747157575@linutronix.de> (raw)
In-Reply-To: 20230523135902.517032811@linutronix.de

vb_alloc() unconditionally locks a vmap_block on the free list to check the
free space.

This can be done locklessly because vmap_block::free never increases, it's
only decreased on allocations.

Check the free space lockless and only if that succeeds, recheck under the
lock.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 mm/vmalloc.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2166,6 +2166,9 @@ static void *vb_alloc(unsigned long size
 	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
 		unsigned long pages_off;
 
+		if (READ_ONCE(vb->free) < (1UL << order))
+			continue;
+
 		spin_lock(&vb->lock);
 		if (vb->free < (1UL << order)) {
 			spin_unlock(&vb->lock);
@@ -2174,7 +2177,7 @@ static void *vb_alloc(unsigned long size
 
 		pages_off = VMAP_BBMAP_BITS - vb->free;
 		vaddr = vmap_block_vaddr(vb->va->va_start, pages_off);
-		vb->free -= 1UL << order;
+		WRITE_ONCE(vb->free, vb->free - (1UL << order));
 		bitmap_set(vb->used_map, pages_off, (1UL << order));
 		if (vb->free == 0) {
 			spin_lock(&vbq->lock);



  parent reply	other threads:[~2023-05-23 14:05 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 ` [patch 3/6] mm/vmalloc: Prevent flushing dirty space over and over Thomas Gleixner
2023-05-23 15:27   ` Christoph Hellwig
2023-05-23 16:10     ` Thomas Gleixner
2023-05-24  9:43   ` Baoquan He
2023-05-23 14:02 ` Thomas Gleixner [this message]
2023-05-23 15:29   ` [patch 4/6] mm/vmalloc: Check free space in vmap_block lockless 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=20230523140002.747157575@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.