xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Hongyan Xia <hx242@xen.org>
To: xen-devel@lists.xenproject.org
Cc: Stefano Stabellini <sstabellini@kernel.org>,
	julien@xen.org, Wei Liu <wl@xen.org>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Ian Jackson <ian.jackson@eu.citrix.com>,
	George Dunlap <george.dunlap@citrix.com>,
	Jan Beulich <jbeulich@suse.com>
Subject: [PATCH 15/16] x86/setup: vmap heap nodes when they are outside the direct map
Date: Thu, 30 Apr 2020 21:44:24 +0100	[thread overview]
Message-ID: <dfa5598b20c83ab496f33a7b0720f659d904cb50.1588278317.git.hongyxia@amazon.com> (raw)
In-Reply-To: <cover.1588278317.git.hongyxia@amazon.com>
In-Reply-To: <cover.1588278317.git.hongyxia@amazon.com>

From: Hongyan Xia <hongyxia@amazon.com>

When we do not have a direct map, arch_mfn_in_direct_map() will always
return false, thus init_node_heap() will allocate xenheap pages from an
existing node for the metadata of a new node. This means that the
metadata of a new node is in a different node, slowing down heap
allocation.

Since we now have early vmap, vmap the metadata locally in the new node.

Signed-off-by: Hongyan Xia <hongyxia@amazon.com>
---
 xen/common/page_alloc.c | 40 ++++++++++++++++++++++++++++++++--------
 1 file changed, 32 insertions(+), 8 deletions(-)

diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 1285fc5977..1e18b45caf 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -584,22 +584,46 @@ static unsigned long init_node_heap(int node, unsigned long mfn,
         needed = 0;
     }
     else if ( *use_tail && nr >= needed &&
-              arch_mfn_in_directmap(mfn + nr) &&
               (!xenheap_bits ||
                !((mfn + nr - 1) >> (xenheap_bits - PAGE_SHIFT))) )
     {
-        _heap[node] = mfn_to_virt(mfn + nr - needed);
-        avail[node] = mfn_to_virt(mfn + nr - 1) +
-                      PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        if ( arch_mfn_in_directmap(mfn + nr) )
+        {
+            _heap[node] = mfn_to_virt(mfn + nr - needed);
+            avail[node] = mfn_to_virt(mfn + nr - 1) +
+                          PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        }
+        else
+        {
+            mfn_t needed_start = _mfn(mfn + nr - needed);
+
+            _heap[node] = __vmap(&needed_start, needed, 1, 1, PAGE_HYPERVISOR,
+                                 VMAP_DEFAULT);
+            BUG_ON(!_heap[node]);
+            avail[node] = (void *)(_heap[node]) + (needed << PAGE_SHIFT) -
+                          sizeof(**avail) * NR_ZONES;
+        }
     }
     else if ( nr >= needed &&
-              arch_mfn_in_directmap(mfn + needed) &&
               (!xenheap_bits ||
                !((mfn + needed - 1) >> (xenheap_bits - PAGE_SHIFT))) )
     {
-        _heap[node] = mfn_to_virt(mfn);
-        avail[node] = mfn_to_virt(mfn + needed - 1) +
-                      PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        if ( arch_mfn_in_directmap(mfn + needed) )
+        {
+            _heap[node] = mfn_to_virt(mfn);
+            avail[node] = mfn_to_virt(mfn + needed - 1) +
+                          PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        }
+        else
+        {
+            mfn_t needed_start = _mfn(mfn);
+
+            _heap[node] = __vmap(&needed_start, needed, 1, 1, PAGE_HYPERVISOR,
+                                 VMAP_DEFAULT);
+            BUG_ON(!_heap[node]);
+            avail[node] = (void *)(_heap[node]) + (needed << PAGE_SHIFT) -
+                          sizeof(**avail) * NR_ZONES;
+        }
         *use_tail = false;
     }
     else if ( get_order_from_bytes(sizeof(**_heap)) ==
-- 
2.24.1.AMZN



  parent reply	other threads:[~2020-04-30 20:50 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-30 20:44 [PATCH 00/16] Remove the direct map Hongyan Xia
2020-04-30 20:44 ` [PATCH 01/16] x86/setup: move vm_init() before acpi calls Hongyan Xia
2020-04-30 20:44 ` [PATCH 02/16] acpi: vmap pages in acpi_os_alloc_memory Hongyan Xia
2020-05-01 12:02   ` Wei Liu
2020-05-01 12:46     ` Hongyan Xia
2020-05-01 21:35   ` Julien Grall
2020-05-04  8:27     ` Hongyan Xia
2020-04-30 20:44 ` [PATCH 03/16] x86/numa: vmap the pages for memnodemap Hongyan Xia
2020-04-30 20:44 ` [PATCH 04/16] x86/srat: vmap the pages for acpi_slit Hongyan Xia
2020-11-30 10:16   ` Jan Beulich
2020-11-30 18:11     ` Hongyan Xia
2020-12-01  7:37       ` Jan Beulich
2020-04-30 20:44 ` [PATCH 05/16] x86: map/unmap pages in restore_all_guests Hongyan Xia
2020-04-30 20:44 ` [PATCH 06/16] x86/pv: domheap pages should be mapped while relocating initrd Hongyan Xia
2020-04-30 20:44 ` [PATCH 07/16] x86/pv: rewrite how building PV dom0 handles domheap mappings Hongyan Xia
2020-04-30 20:44 ` [PATCH 08/16] x86: add Persistent Map (PMAP) infrastructure Hongyan Xia
2020-04-30 20:44 ` [PATCH 09/16] x86: lift mapcache variable to the arch level Hongyan Xia
2020-04-30 20:44 ` [PATCH 10/16] x86/mapcache: initialise the mapcache for the idle domain Hongyan Xia
2020-04-30 20:44 ` [PATCH 11/16] x86: add a boot option to enable and disable the direct map Hongyan Xia
2020-05-01  8:43   ` Julien Grall
2020-05-01 12:11   ` Wei Liu
2020-05-01 12:59     ` Hongyan Xia
2020-05-01 13:11       ` Wei Liu
2020-05-01 15:59         ` Julien Grall
2020-04-30 20:44 ` [PATCH 12/16] x86/domain_page: remove the fast paths when mfn is not in the directmap Hongyan Xia
2020-04-30 20:44 ` [PATCH 13/16] xen/page_alloc: add a path for xenheap when there is no direct map Hongyan Xia
2020-05-01  8:50   ` Julien Grall
2021-04-22 12:31   ` Jan Beulich
2021-04-28 11:04     ` Hongyan Xia
2021-04-28 11:51       ` Jan Beulich
2021-04-28 13:22         ` Hongyan Xia
2021-04-28 13:55           ` Jan Beulich
2020-04-30 20:44 ` [PATCH 14/16] x86/setup: leave early boot slightly earlier Hongyan Xia
2020-04-30 20:44 ` Hongyan Xia [this message]
2020-04-30 20:44 ` [PATCH 16/16] x86/setup: do not create valid mappings when directmap=no Hongyan Xia
2020-05-01 12:07 ` [PATCH 00/16] Remove the direct map Wei Liu
2020-05-01 13:53   ` Hongyan Xia
2020-06-02  9:08     ` Wei Liu
2021-04-28 10:14       ` Hongyan Xia

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=dfa5598b20c83ab496f33a7b0720f659d904cb50.1588278317.git.hongyxia@amazon.com \
    --to=hx242@xen.org \
    --cc=andrew.cooper3@citrix.com \
    --cc=george.dunlap@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=jbeulich@suse.com \
    --cc=julien@xen.org \
    --cc=sstabellini@kernel.org \
    --cc=wl@xen.org \
    --cc=xen-devel@lists.xenproject.org \
    /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;
as well as URLs for NNTP newsgroup(s).