The commit 2d4f567103ff ("KVM: PPC: Introduce kvm_tmp framework") adds
kvm_tmp[] into the .bss section and then free the rest of unused spaces
back to the page allocator.
kernel_init
kvm_guest_init
kvm_free_tmp
free_reserved_area
free_unref_page
free_unref_page_prepare
With DEBUG_PAGEALLOC=y, it will unmap those pages from kernel. As the
result, kmemleak scan will trigger a panic when it scans the .bss
section with unmapped pages.
This patch creates dedicated kmemleak objects for the .data, .bss and
potentially .data..ro_after_init sections to allow partial freeing via
the kmemleak_free_part() in the powerpc kvm_free_tmp() function.
Acked-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx> (powerpc)
Reported-by: Qian Cai <cai@xxxxxx>
Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx>
---
Posting as a proper patch following the inlined one here:
http://lkml.kernel.org/r/20190320181656.GB38229@xxxxxxxxxxxxxxxxxxxx
Changes from the above:
- Added comment to the powerpc kmemleak_free_part() call
- Only register the .data..ro_after_init in kmemleak if not contained
within the .data sections (which seems to be the case for lots of
architectures)
I preserved part of Qian's original commit message but changed the
author since I rewrote the patch.
arch/powerpc/kernel/kvm.c | 7 +++++++
mm/kmemleak.c | 16 +++++++++++-----
2 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 683b5b3805bd..cd381e2291df 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -22,6 +22,7 @@
#include <linux/kvm_host.h>
#include <linux/init.h>
#include <linux/export.h>
+#include <linux/kmemleak.h>
#include <linux/kvm_para.h>
#include <linux/slab.h>
#include <linux/of.h>
@@ -712,6 +713,12 @@ static void kvm_use_magic_page(void)
static __init void kvm_free_tmp(void)
{
+ /*
+ * Inform kmemleak about the hole in the .bss section since the
+ * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y.
+ */
+ kmemleak_free_part(&kvm_tmp[kvm_tmp_index],
+ ARRAY_SIZE(kvm_tmp) - kvm_tmp_index);
free_reserved_area(&kvm_tmp[kvm_tmp_index],
&kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL);
}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 707fa5579f66..6c318f5ac234 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1529,11 +1529,6 @@ static void kmemleak_scan(void)
}
rcu_read_unlock();
- /* data/bss scanning */
- scan_large_block(_sdata, _edata);
- scan_large_block(__bss_start, __bss_stop);
- scan_large_block(__start_ro_after_init, __end_ro_after_init);
-
#ifdef CONFIG_SMP
/* per-cpu sections scanning */
for_each_possible_cpu(i)
@@ -2071,6 +2066,17 @@ void __init kmemleak_init(void)
}
local_irq_restore(flags);
+ /* register the data/bss sections */
+ create_object((unsigned long)_sdata, _edata - _sdata,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+ create_object((unsigned long)__bss_start, __bss_stop - __bss_start,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+ /* only register .data..ro_after_init if not within .data */
+ if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata)
+ create_object((unsigned long)__start_ro_after_init,
+ __end_ro_after_init - __start_ro_after_init,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+
/*
* This is the point where tracking allocations is safe. Automatic
* scanning is started during the late initcall. Add the early logged
