92 lines
3.5 KiB
Diff
92 lines
3.5 KiB
Diff
|
From e9fc6950c9d253ab9243f662d20da3021da3cb03 Mon Sep 17 00:00:00 2001
|
||
|
|
From: tangbinzy <tangbin_yewu@cmss.chinamobile.com>
|
||
|
|
Date: Wed, 4 Sep 2024 06:03:35 +0000
|
||
|
|
Subject: [PATCH] KVM: use store-release to mark dirty pages as harvested
|
||
|
|
mainline inclusion commit 52281c6d11ec68b802e8a264780df2c4b981e6bc category:
|
||
|
|
bugfix
|
||
|
|
MIME-Version: 1.0
|
||
|
|
Content-Type: text/plain; charset=UTF-8
|
||
|
|
Content-Transfer-Encoding: 8bit
|
||
|
|
|
||
|
|
---------------------------------------------------------------
|
||
|
|
|
||
|
|
The following scenario can happen if QEMU sets more RESET flags while
|
||
|
|
the KVM_RESET_DIRTY_RINGS ioctl is ongoing on another host CPU:
|
||
|
|
|
||
|
|
CPU0 CPU1 CPU2
|
||
|
|
------------------------ ------------------ ------------------------
|
||
|
|
fill gfn0
|
||
|
|
store-rel flags for gfn0
|
||
|
|
fill gfn1
|
||
|
|
store-rel flags for gfn1
|
||
|
|
load-acq flags for gfn0
|
||
|
|
set RESET for gfn0
|
||
|
|
load-acq flags for gfn1
|
||
|
|
set RESET for gfn1
|
||
|
|
do ioctl! ----------->
|
||
|
|
ioctl(RESET_RINGS)
|
||
|
|
fill gfn2
|
||
|
|
store-rel flags for gfn2
|
||
|
|
load-acq flags for gfn2
|
||
|
|
set RESET for gfn2
|
||
|
|
process gfn0
|
||
|
|
process gfn1
|
||
|
|
process gfn2
|
||
|
|
do ioctl!
|
||
|
|
etc.
|
||
|
|
|
||
|
|
The three load-acquire in CPU0 synchronize with the three store-release
|
||
|
|
in CPU2, but CPU0 and CPU1 are only synchronized up to gfn1 and CPU1
|
||
|
|
may miss gfn2's fields other than flags.
|
||
|
|
|
||
|
|
The kernel must be able to cope with invalid values of the fields, and
|
||
|
|
userspace *will* invoke the ioctl once more. However, once the RESET flag
|
||
|
|
is cleared on gfn2, it is lost forever, therefore in the above scenario
|
||
|
|
CPU1 must read the correct value of gfn2's fields.
|
||
|
|
|
||
|
|
Therefore RESET must be set with a store-release, that will synchronize
|
||
|
|
with KVM's load-acquire in CPU1.
|
||
|
|
|
||
|
|
Cc: Gavin Shan <gshan@redhat.com>
|
||
|
|
Reviewed-by: Peter Xu <peterx@redhat.com>
|
||
|
|
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
|
||
|
|
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
||
|
|
|
||
|
|
Signed-off-by: tangbinzy <tangbin_yewu@cmss.chinamobile.com>
|
||
|
|
---
|
||
|
|
accel/kvm/kvm-all.c | 18 +++++++++++++++++-
|
||
|
|
1 file changed, 17 insertions(+), 1 deletion(-)
|
||
|
|
|
||
|
|
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
|
||
|
|
index 381e3c8552..3a09307a26 100644
|
||
|
|
--- a/accel/kvm/kvm-all.c
|
||
|
|
+++ b/accel/kvm/kvm-all.c
|
||
|
|
@@ -675,7 +675,23 @@ static bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn)
|
||
|
|
|
||
|
|
static void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn)
|
||
|
|
{
|
||
|
|
- gfn->flags = KVM_DIRTY_GFN_F_RESET;
|
||
|
|
+ /*
|
||
|
|
+ * Use a store-release so that the CPU that executes KVM_RESET_DIRTY_RINGS
|
||
|
|
+ * sees the full content of the ring:
|
||
|
|
+ *
|
||
|
|
+ * CPU0 CPU1 CPU2
|
||
|
|
+ * ------------------------------------------------------------------------------
|
||
|
|
+ * fill gfn0
|
||
|
|
+ * store-rel flags for gfn0
|
||
|
|
+ * load-acq flags for gfn0
|
||
|
|
+ * store-rel RESET for gfn0
|
||
|
|
+ * ioctl(RESET_RINGS)
|
||
|
|
+ * load-acq flags for gfn0
|
||
|
|
+ * check if flags have RESET
|
||
|
|
+ *
|
||
|
|
+ * The synchronization goes from CPU2 to CPU0 to CPU1.
|
||
|
|
+ */
|
||
|
|
+ qatomic_store_release(&gfn->flags, KVM_DIRTY_GFN_F_RESET);
|
||
|
|
}
|
||
|
|
|
||
|
|
/*
|
||
|
|
--
|
||
|
|
2.41.0.windows.1
|
||
|
|
|