From: Mike Rapoport <rppt@kernel•org>
To: Andrew Morton <akpm@linux-foundation•org>
Cc: Alexander Potapenko <glider@google•com>,
Alexander Viro <viro@zeniv•linux.org.uk>,
Andreas Larsson <andreas@gaisler•com>,
Ard Biesheuvel <ardb@kernel•org>, Borislav Petkov <bp@alien8•de>,
Brendan Jackman <jackmanb@google•com>,
"Christophe Leroy (CS GROUP)" <chleroy@kernel•org>,
Catalin Marinas <catalin.marinas@arm•com>,
Christian Brauner <brauner@kernel•org>,
"David S. Miller" <davem@davemloft•net>,
Dave Hansen <dave.hansen@linux•intel.com>,
David Hildenbrand <david@kernel•org>,
Dmitry Vyukov <dvyukov@google•com>,
Ilias Apalodimas <ilias.apalodimas@linaro•org>,
Ingo Molnar <mingo@redhat•com>, Jan Kara <jack@suse•cz>,
Johannes Weiner <hannes@cmpxchg•org>,
"Liam R. Howlett" <Liam.Howlett@oracle•com>,
Lorenzo Stoakes <lorenzo.stoakes@oracle•com>,
Madhavan Srinivasan <maddy@linux•ibm.com>,
Marco Elver <elver@google•com>,
Marek Szyprowski <m.szyprowski@samsung•com>,
Masami Hiramatsu <mhiramat@kernel•org>,
Michael Ellerman <mpe@ellerman•id.au>,
Michal Hocko <mhocko@suse•com>, Mike Rapoport <rppt@kernel•org>,
Nicholas Piggin <npiggin@gmail•com>,
"H. Peter Anvin" <hpa@zytor•com>, Rob Herring <robh@kernel•org>,
Robin Murphy <robin.murphy@arm•com>,
Saravana Kannan <saravanak@kernel•org>,
Suren Baghdasaryan <surenb@google•com>,
Thomas Gleixner <tglx@kernel•org>,
Vlastimil Babka <vbabka@kernel•org>,
Will Deacon <will@kernel•org>, Zi Yan <ziy@nvidia•com>,
devicetree@vger•kernel.org, iommu@lists•linux.dev,
kasan-dev@googlegroups•com, linux-arm-kernel@lists•infradead.org,
linux-efi@vger•kernel.org, linux-fsdevel@vger•kernel.org,
linux-kernel@vger•kernel.org, linux-mm@kvack•org,
linux-trace-kernel@vger•kernel.org,
linuxppc-dev@lists•ozlabs.org, sparclinux@vger•kernel.org,
x86@kernel•org
Subject: [PATCH v2 9/9] memblock: warn when freeing reserved memory before memory map is initialized
Date: Mon, 23 Mar 2026 09:48:36 +0200 [thread overview]
Message-ID: <20260323074836.3653702-10-rppt@kernel.org> (raw)
In-Reply-To: <20260323074836.3653702-1-rppt@kernel.org>
From: "Mike Rapoport (Microsoft)" <rppt@kernel•org>
When CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, freeing of reserved
memory before the memory map is fully initialized in deferred_init_memmap()
would cause access to uninitialized struct pages and may crash when
accessing spurious list pointers, like was recently discovered during
discussion about memory leaks in x86 EFI code [1].
The trace below is from an attempt to call free_reserved_page() before
page_alloc_init_late():
[ 0.076840] BUG: unable to handle page fault for address: ffffce1a005a0788
[ 0.078226] #PF: supervisor read access in kernel mode
[ 0.078226] #PF: error_code(0x0000) - not-present page
[ 0.078226] PGD 0 P4D 0
[ 0.078226] Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
[ 0.078226] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.68-92.123.amzn2023.x86_64 #1
[ 0.078226] Hardware name: Amazon EC2 t3a.nano/, BIOS 1.0 10/16/2017
[ 0.078226] RIP: 0010:__list_del_entry_valid_or_report+0x32/0xb0
...
[ 0.078226] __free_one_page+0x170/0x520
[ 0.078226] free_pcppages_bulk+0x151/0x1e0
[ 0.078226] free_unref_page_commit+0x263/0x320
[ 0.078226] free_unref_page+0x2c8/0x5b0
[ 0.078226] ? srso_return_thunk+0x5/0x5f
[ 0.078226] free_reserved_page+0x1c/0x30
[ 0.078226] memblock_free_late+0x6c/0xc0
Currently there are not many callers of free_reserved_area() and they all
appear to be at the right timings.
Still, in order to protect against problematic code moves or additions of
new callers add a warning that will inform that reserved pages cannot be
freed until the memory map is fully initialized.
[1] https://lore.kernel.org/all/e5d5a1105d90ee1e7fe7eafaed2ed03bbad0c46b.camel@kernel.crashing.org/
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel•org>
---
mm/internal.h | 10 ++++++++++
mm/memblock.c | 5 +++++
mm/page_alloc.c | 10 ----------
3 files changed, 15 insertions(+), 10 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h
index cb0af847d7d9..f60c1edb2e02 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1233,7 +1233,17 @@ static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
DECLARE_STATIC_KEY_TRUE(deferred_pages);
+static inline bool deferred_pages_enabled(void)
+{
+ return static_branch_unlikely(&deferred_pages);
+}
+
bool __init deferred_grow_zone(struct zone *zone, unsigned int order);
+#else
+static inline bool deferred_pages_enabled(void)
+{
+ return false;
+}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
void init_deferred_page(unsigned long pfn, int nid);
diff --git a/mm/memblock.c b/mm/memblock.c
index dc8811861c11..ab8f35c3bd41 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -899,6 +899,11 @@ static unsigned long __free_reserved_area(phys_addr_t start, phys_addr_t end,
{
unsigned long pages = 0, pfn;
+ if (deferred_pages_enabled()) {
+ WARN(1, "Cannot free reserved memory because of deferred initialization of the memory map");
+ return 0;
+ }
+
for_each_valid_pfn(pfn, PFN_UP(start), PFN_DOWN(end)) {
struct page *page = pfn_to_page(pfn);
void *direct_map_addr;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index df3d61253001..9ac47bab2ea7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -331,11 +331,6 @@ int page_group_by_mobility_disabled __read_mostly;
*/
DEFINE_STATIC_KEY_TRUE(deferred_pages);
-static inline bool deferred_pages_enabled(void)
-{
- return static_branch_unlikely(&deferred_pages);
-}
-
/*
* deferred_grow_zone() is __init, but it is called from
* get_page_from_freelist() during early boot until deferred_pages permanently
@@ -348,11 +343,6 @@ _deferred_grow_zone(struct zone *zone, unsigned int order)
return deferred_grow_zone(zone, order);
}
#else
-static inline bool deferred_pages_enabled(void)
-{
- return false;
-}
-
static inline bool _deferred_grow_zone(struct zone *zone, unsigned int order)
{
return false;
--
2.53.0
next prev parent reply other threads:[~2026-03-23 7:50 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-23 7:48 [PATCH v2 0/9] memblock: improve late freeing of reserved memory Mike Rapoport
2026-03-23 7:48 ` [PATCH v2 1/9] memblock: reserve_mem: fix end caclulation in reserve_mem_release_by_name() Mike Rapoport
2026-03-23 7:48 ` [PATCH v2 2/9] powerpc: fadump: pair alloc_pages_exact() with free_pages_exact() Mike Rapoport
2026-03-23 7:48 ` [PATCH v2 3/9] powerpc: opal-core: " Mike Rapoport
2026-03-23 7:48 ` [PATCH v2 4/9] mm: move free_reserved_area() to mm/memblock.c Mike Rapoport
2026-03-30 9:00 ` Vlastimil Babka (SUSE)
2026-03-23 7:48 ` [PATCH v2 5/9] memblock: make free_reserved_area() more robust Mike Rapoport
2026-03-23 7:48 ` [PATCH v2 6/9] memblock: extract page freeing from free_reserved_area() into a helper Mike Rapoport
2026-03-23 7:48 ` [PATCH v2 7/9] memblock: make free_reserved_area() update memblock if ARCH_KEEP_MEMBLOCK=y Mike Rapoport
2026-03-23 7:48 ` [PATCH v2 8/9] memblock, treewide: make memblock_free() handle late freeing Mike Rapoport
2026-03-23 7:48 ` Mike Rapoport [this message]
[not found] ` <20260327140109.7561-1-spasswolf@web.de>
2026-03-27 17:12 ` Warning from free_reserved_area() in next-20260325+ Mike Rapoport
2026-03-25 8:51 ` [PATCH v2 0/9] memblock: improve late freeing of reserved memory Mike Rapoport
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=20260323074836.3653702-10-rppt@kernel.org \
--to=rppt@kernel$(echo .)org \
--cc=Liam.Howlett@oracle$(echo .)com \
--cc=akpm@linux-foundation$(echo .)org \
--cc=andreas@gaisler$(echo .)com \
--cc=ardb@kernel$(echo .)org \
--cc=bp@alien8$(echo .)de \
--cc=brauner@kernel$(echo .)org \
--cc=catalin.marinas@arm$(echo .)com \
--cc=chleroy@kernel$(echo .)org \
--cc=dave.hansen@linux$(echo .)intel.com \
--cc=davem@davemloft$(echo .)net \
--cc=david@kernel$(echo .)org \
--cc=devicetree@vger$(echo .)kernel.org \
--cc=dvyukov@google$(echo .)com \
--cc=elver@google$(echo .)com \
--cc=glider@google$(echo .)com \
--cc=hannes@cmpxchg$(echo .)org \
--cc=hpa@zytor$(echo .)com \
--cc=ilias.apalodimas@linaro$(echo .)org \
--cc=iommu@lists$(echo .)linux.dev \
--cc=jack@suse$(echo .)cz \
--cc=jackmanb@google$(echo .)com \
--cc=kasan-dev@googlegroups$(echo .)com \
--cc=linux-arm-kernel@lists$(echo .)infradead.org \
--cc=linux-efi@vger$(echo .)kernel.org \
--cc=linux-fsdevel@vger$(echo .)kernel.org \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=linux-mm@kvack$(echo .)org \
--cc=linux-trace-kernel@vger$(echo .)kernel.org \
--cc=linuxppc-dev@lists$(echo .)ozlabs.org \
--cc=lorenzo.stoakes@oracle$(echo .)com \
--cc=m.szyprowski@samsung$(echo .)com \
--cc=maddy@linux$(echo .)ibm.com \
--cc=mhiramat@kernel$(echo .)org \
--cc=mhocko@suse$(echo .)com \
--cc=mingo@redhat$(echo .)com \
--cc=mpe@ellerman$(echo .)id.au \
--cc=npiggin@gmail$(echo .)com \
--cc=robh@kernel$(echo .)org \
--cc=robin.murphy@arm$(echo .)com \
--cc=saravanak@kernel$(echo .)org \
--cc=sparclinux@vger$(echo .)kernel.org \
--cc=surenb@google$(echo .)com \
--cc=tglx@kernel$(echo .)org \
--cc=vbabka@kernel$(echo .)org \
--cc=viro@zeniv$(echo .)linux.org.uk \
--cc=will@kernel$(echo .)org \
--cc=x86@kernel$(echo .)org \
--cc=ziy@nvidia$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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