| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 25 Aug 2022 14:30:36 +0200
From: Vlastimil Babka <vbabka@...e.cz>
To: lizhe.67@...edance.com, akpm@...ux-foundation.org, mhocko@...e.com,
mhiramat@...nel.org, keescook@...omium.org, Jason@...c4.com,
mark-pk.tsai@...iatek.com, rostedt@...dmis.org, corbet@....net
Cc: linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, lizefan.x@...edance.com
Subject: Re: [PATCH v4] page_ext: introduce boot parameter 'early_page_ext'
On 8/25/22 12:27, lizhe.67@...edance.com wrote:
> From: Li Zhe <lizhe.67@...edance.com>
>
> In 'commit 2f1ee0913ce5 ("Revert "mm: use early_pfn_to_nid in page_ext_init"")',
> we call page_ext_init() after page_alloc_init_late() to avoid some panic
> problem. It seems that we cannot track early page allocations in current
> kernel even if page structure has been initialized early.
>
> This patch introduce a new boot parameter 'early_page_ext' to resolve this
> problem. If we pass it to kernel, function page_ext_init() will be moved
> up and feature 'deferred initialization of struct pages' will be disabled
> to initialize the page allocator early and prevent from the panic problem
> above. It can help us to catch early page allocations. This is useful
> especially when we find that the free memory value is not the same right
> after different kernel booting.
>
> Suggested-by: Michal Hocko <mhocko@...e.com>
> Signed-off-by: Li Zhe <lizhe.67@...edance.com>
Acked-by: Vlastimil Babka <vbabka@...e.cz>
> ---
> Changelogs:
>
> v1->v2:
> - use a cmd line parameter to move up function page_ext_init() instead of
> using CONFIG_DEFERRED_STRUCT_PAGE_INIT
> - fix oom problem[1]
>
> v2->v3:
> - move the judgment out of page_ext_init()
>
> v3->v4:
> - remove dependency on CONFIG_DEFERRED_STRUCT_PAGE_INIT
> - modify descriptions in git log && kernel-parameters.txt
>
> v1 patch: https://lore.kernel.org/lkml/Yv3r6Y1vh+6AbY4+@dhcp22.suse.cz/T/
> v2 patch: https://lore.kernel.org/lkml/20220824065058.81051-1-lizhe.67@bytedance.com/T/
> v3 patch: https://lore.kernel.org/linux-mm/20220825063102.92307-1-lizhe.67@bytedance.com/T/
>
> [1]: https://lore.kernel.org/linux-mm/YwHmXLu5txij+p35@xsang-OptiPlex-9020/
>
> Documentation/admin-guide/kernel-parameters.txt | 8 ++++++++
> include/linux/page_ext.h | 11 +++++++++++
> init/main.c | 6 +++++-
> mm/page_alloc.c | 2 ++
> mm/page_ext.c | 8 ++++++++
> 5 files changed, 34 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index d7f30902fda0..4f43fd5b324d 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1471,6 +1471,14 @@
> Permit 'security.evm' to be updated regardless of
> current integrity status.
>
> + early_page_ext [KNL] Enforces page_ext initialization to earlier
> + stages so cover more early boot allocations.
> + Please note that as side effect some optimizations
> + might be disabled to achieve that (e.g. parallelized
> + memory initialization is disabled) so the boot process
> + might take longer, especially on systems with a lot of
> + memory. Available with CONFIG_PAGE_EXTENSION=y.
> +
> failslab=
> fail_usercopy=
> fail_page_alloc=
> diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
> index fabb2e1e087f..884282a7f03a 100644
> --- a/include/linux/page_ext.h
> +++ b/include/linux/page_ext.h
> @@ -36,9 +36,15 @@ struct page_ext {
> unsigned long flags;
> };
>
> +extern bool early_page_ext;
> extern unsigned long page_ext_size;
> extern void pgdat_page_ext_init(struct pglist_data *pgdat);
>
> +static inline bool early_page_ext_enabled(void)
> +{
> + return early_page_ext;
> +}
> +
> #ifdef CONFIG_SPARSEMEM
> static inline void page_ext_init_flatmem(void)
> {
> @@ -67,6 +73,11 @@ static inline struct page_ext *page_ext_next(struct page_ext *curr)
> #else /* !CONFIG_PAGE_EXTENSION */
> struct page_ext;
>
> +static inline bool early_page_ext_enabled(void)
> +{
> + return false;
> +}
> +
> static inline void pgdat_page_ext_init(struct pglist_data *pgdat)
> {
> }
> diff --git a/init/main.c b/init/main.c
> index 91642a4e69be..b5e75f3288d7 100644
> --- a/init/main.c
> +++ b/init/main.c
> @@ -849,6 +849,9 @@ static void __init mm_init(void)
> pgtable_init();
> debug_objects_mem_init();
> vmalloc_init();
> + /* Should be run after vmap initialization */
> + if (early_page_ext_enabled())
> + page_ext_init();
> /* Should be run before the first non-init thread is created */
> init_espfix_bsp();
> /* Should be run after espfix64 is set up. */
> @@ -1606,7 +1609,8 @@ static noinline void __init kernel_init_freeable(void)
> padata_init();
> page_alloc_init_late();
> /* Initialize page ext after all struct pages are initialized. */
> - page_ext_init();
> + if (!early_page_ext_enabled())
> + page_ext_init();
>
> do_basic_setup();
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index e5486d47406e..e2faa52cd05d 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -482,6 +482,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
> {
> static unsigned long prev_end_pfn, nr_initialised;
>
> + if (early_page_ext_enabled())
> + return false;
> /*
> * prev_end_pfn static that contains the end of previous zone
> * No need to protect because called very early in boot before smp_init.
> diff --git a/mm/page_ext.c b/mm/page_ext.c
> index 3dc715d7ac29..6c28d623d951 100644
> --- a/mm/page_ext.c
> +++ b/mm/page_ext.c
> @@ -85,6 +85,14 @@ unsigned long page_ext_size = sizeof(struct page_ext);
>
> static unsigned long total_usage;
>
> +bool early_page_ext __meminitdata;
> +static int __init setup_early_page_ext(char *str)
> +{
> + early_page_ext = true;
> + return 0;
> +}
> +early_param("early_page_ext", setup_early_page_ext);
> +
> static bool __init invoke_need_callbacks(void)
> {
> int i;
Powered by blists - more mailing lists