Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 16 Mar 2021 15:14:27 GMT
From:      Mark Johnston <markj@FreeBSD.org>
To:        src-committers@FreeBSD.org, dev-commits-src-all@FreeBSD.org, dev-commits-src-branches@FreeBSD.org
Subject:   git: 03984bdfa033 - stable/13 - vm: Round up npages and alignment for contig reclamation
Message-ID:  <202103161514.12GFERCd074449@gitrepo.freebsd.org>

next in thread | raw e-mail | index | archive | help
The branch stable/13 has been updated by markj:

URL: https://cgit.FreeBSD.org/src/commit/?id=03984bdfa033efe0597aa6adac85dba6e7ddb9a8

commit 03984bdfa033efe0597aa6adac85dba6e7ddb9a8
Author:     Mark Johnston <markj@FreeBSD.org>
AuthorDate: 2021-03-02 15:19:53 +0000
Commit:     Mark Johnston <markj@FreeBSD.org>
CommitDate: 2021-03-16 15:14:09 +0000

    vm: Round up npages and alignment for contig reclamation
    
    When searching for runs to reclaim, we need to ensure that the entire
    run will be added to the buddy allocator as a single unit.  Otherwise,
    it will not be visible to vm_phys_alloc_contig() as it is currently
    implemented.  This is a problem for allocation requests that are not a
    power of 2 in size, as with 9KB jumbo mbuf clusters.
    
    Reported by:    alc
    Reviewed by:    alc
    Sponsored by:   The FreeBSD Foundation
    Differential Revision:  https://reviews.freebsd.org/D28924
    
    (cherry picked from commit 0401989282d1bb9972ae2bf4862c2c6c92ae5f27)
---
 sys/vm/vm_page.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/sys/vm/vm_page.c b/sys/vm/vm_page.c
index c36b8cdc5762..da62e6795c81 100644
--- a/sys/vm/vm_page.c
+++ b/sys/vm/vm_page.c
@@ -2972,17 +2972,29 @@ vm_page_reclaim_contig_domain(int domain, int req, u_long npages,
 	struct vm_domain *vmd;
 	vm_paddr_t curr_low;
 	vm_page_t m_run, m_runs[NRUNS];
-	u_long count, reclaimed;
+	u_long count, minalign, reclaimed;
 	int error, i, options, req_class;
 
 	KASSERT(npages > 0, ("npages is 0"));
 	KASSERT(powerof2(alignment), ("alignment is not a power of 2"));
 	KASSERT(powerof2(boundary), ("boundary is not a power of 2"));
-	req_class = req & VM_ALLOC_CLASS_MASK;
+
+	/*
+	 * The caller will attempt an allocation after some runs have been
+	 * reclaimed and added to the vm_phys buddy lists.  Due to limitations
+	 * of vm_phys_alloc_contig(), round up the requested length to the next
+	 * power of two or maximum chunk size, and ensure that each run is
+	 * suitably aligned.
+	 */
+	minalign = 1ul << imin(flsl(npages - 1), VM_NFREEORDER - 1);
+	npages = roundup2(npages, minalign);
+	if (alignment < ptoa(minalign))
+		alignment = ptoa(minalign);
 
 	/*
 	 * The page daemon is allowed to dig deeper into the free page list.
 	 */
+	req_class = req & VM_ALLOC_CLASS_MASK;
 	if (curproc == pageproc && req_class != VM_ALLOC_INTERRUPT)
 		req_class = VM_ALLOC_SYSTEM;
 



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?202103161514.12GFERCd074449>