[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <mafs0tt0cnevi.fsf@kernel.org>
Date: Mon, 06 Oct 2025 19:01:37 +0200
From: Pratyush Yadav <pratyush@...nel.org>
To: Pasha Tatashin <pasha.tatashin@...een.com>
Cc: pratyush@...nel.org, jasonmiu@...gle.com, graf@...zon.com,
changyuanl@...gle.com, rppt@...nel.org, dmatlack@...gle.com,
rientjes@...gle.com, corbet@....net, rdunlap@...radead.org,
ilpo.jarvinen@...ux.intel.com, kanie@...ux.alibaba.com,
ojeda@...nel.org, aliceryhl@...gle.com, masahiroy@...nel.org,
akpm@...ux-foundation.org, tj@...nel.org, yoann.congal@...le.fr,
mmaurer@...gle.com, roman.gushchin@...ux.dev, chenridong@...wei.com,
axboe@...nel.dk, mark.rutland@....com, jannh@...gle.com,
vincent.guittot@...aro.org, hannes@...xchg.org,
dan.j.williams@...el.com, david@...hat.com, joel.granados@...nel.org,
rostedt@...dmis.org, anna.schumaker@...cle.com, song@...nel.org,
zhangguopeng@...inos.cn, linux@...ssschuh.net,
linux-kernel@...r.kernel.org, linux-doc@...r.kernel.org,
linux-mm@...ck.org, gregkh@...uxfoundation.org, tglx@...utronix.de,
mingo@...hat.com, bp@...en8.de, dave.hansen@...ux.intel.com,
x86@...nel.org, hpa@...or.com, rafael@...nel.org, dakr@...nel.org,
bartosz.golaszewski@...aro.org, cw00.choi@...sung.com,
myungjoo.ham@...sung.com, yesanishhere@...il.com,
Jonathan.Cameron@...wei.com, quic_zijuhu@...cinc.com,
aleksander.lobakin@...el.com, ira.weiny@...el.com,
andriy.shevchenko@...ux.intel.com, leon@...nel.org, lukas@...ner.de,
bhelgaas@...gle.com, wagi@...nel.org, djeffery@...hat.com,
stuart.w.hayes@...il.com, lennart@...ttering.net, brauner@...nel.org,
linux-api@...r.kernel.org, linux-fsdevel@...r.kernel.org,
saeedm@...dia.com, ajayachandra@...dia.com, jgg@...dia.com,
parav@...dia.com, leonro@...dia.com, witu@...dia.com,
hughd@...gle.com, skhawaja@...gle.com, chrisl@...nel.org,
steven.sistare@...cle.com
Subject: Re: [PATCH v4 03/30] kho: drop notifiers
On Mon, Sep 29 2025, Pasha Tatashin wrote:
> From: "Mike Rapoport (Microsoft)" <rppt@...nel.org>
>
> The KHO framework uses a notifier chain as the mechanism for clients to
> participate in the finalization process. While this works for a single,
> central state machine, it is too restrictive for kernel-internal
> components like pstore/reserve_mem or IMA. These components need a
> simpler, direct way to register their state for preservation (e.g.,
> during their initcall) without being part of a complex,
> shutdown-time notifier sequence. The notifier model forces all
> participants into a single finalization flow and makes direct
> preservation from an arbitrary context difficult.
> This patch refactors the client participation model by removing the
> notifier chain and introducing a direct API for managing FDT subtrees.
>
> The core kho_finalize() and kho_abort() state machine remains, but
> clients now register their data with KHO beforehand.
>
> Signed-off-by: Mike Rapoport (Microsoft) <rppt@...nel.org>
> Signed-off-by: Pasha Tatashin <pasha.tatashin@...een.com>
[...]
> diff --git a/mm/memblock.c b/mm/memblock.c
> index e23e16618e9b..c4b2d4e4c715 100644
> --- a/mm/memblock.c
> +++ b/mm/memblock.c
> @@ -2444,53 +2444,18 @@ int reserve_mem_release_by_name(const char *name)
> #define MEMBLOCK_KHO_FDT "memblock"
> #define MEMBLOCK_KHO_NODE_COMPATIBLE "memblock-v1"
> #define RESERVE_MEM_KHO_NODE_COMPATIBLE "reserve-mem-v1"
> -static struct page *kho_fdt;
> -
> -static int reserve_mem_kho_finalize(struct kho_serialization *ser)
> -{
> - int err = 0, i;
> -
> - for (i = 0; i < reserved_mem_count; i++) {
> - struct reserve_mem_table *map = &reserved_mem_table[i];
> - struct page *page = phys_to_page(map->start);
> - unsigned int nr_pages = map->size >> PAGE_SHIFT;
> -
> - err |= kho_preserve_pages(page, nr_pages);
> - }
> -
> - err |= kho_preserve_folio(page_folio(kho_fdt));
> - err |= kho_add_subtree(ser, MEMBLOCK_KHO_FDT, page_to_virt(kho_fdt));
> -
> - return notifier_from_errno(err);
> -}
> -
> -static int reserve_mem_kho_notifier(struct notifier_block *self,
> - unsigned long cmd, void *v)
> -{
> - switch (cmd) {
> - case KEXEC_KHO_FINALIZE:
> - return reserve_mem_kho_finalize((struct kho_serialization *)v);
> - case KEXEC_KHO_ABORT:
> - return NOTIFY_DONE;
> - default:
> - return NOTIFY_BAD;
> - }
> -}
> -
> -static struct notifier_block reserve_mem_kho_nb = {
> - .notifier_call = reserve_mem_kho_notifier,
> -};
>
> static int __init prepare_kho_fdt(void)
> {
> int err = 0, i;
> + struct page *fdt_page;
> void *fdt;
>
> - kho_fdt = alloc_page(GFP_KERNEL);
> - if (!kho_fdt)
> + fdt_page = alloc_page(GFP_KERNEL);
> + if (!fdt_page)
> return -ENOMEM;
>
> - fdt = page_to_virt(kho_fdt);
> + fdt = page_to_virt(fdt_page);
>
> err |= fdt_create(fdt, PAGE_SIZE);
> err |= fdt_finish_reservemap(fdt);
> @@ -2499,7 +2464,10 @@ static int __init prepare_kho_fdt(void)
> err |= fdt_property_string(fdt, "compatible", MEMBLOCK_KHO_NODE_COMPATIBLE);
> for (i = 0; i < reserved_mem_count; i++) {
> struct reserve_mem_table *map = &reserved_mem_table[i];
> + struct page *page = phys_to_page(map->start);
> + unsigned int nr_pages = map->size >> PAGE_SHIFT;
>
> + err |= kho_preserve_pages(page, nr_pages);
> err |= fdt_begin_node(fdt, map->name);
> err |= fdt_property_string(fdt, "compatible", RESERVE_MEM_KHO_NODE_COMPATIBLE);
> err |= fdt_property(fdt, "start", &map->start, sizeof(map->start));
> @@ -2507,13 +2475,14 @@ static int __init prepare_kho_fdt(void)
> err |= fdt_end_node(fdt);
> }
> err |= fdt_end_node(fdt);
> -
> err |= fdt_finish(fdt);
>
> + err |= kho_preserve_folio(page_folio(fdt_page));
> + err |= kho_add_subtree(MEMBLOCK_KHO_FDT, fdt);
> +
> if (err) {
> pr_err("failed to prepare memblock FDT for KHO: %d\n", err);
> - put_page(kho_fdt);
> - kho_fdt = NULL;
> + put_page(fdt_page);
This adds subtree to KHO even if the FDT might be invalid. And then
leaves a dangling reference in KHO to the FDT in case of an error. I
think you should either do this check after
kho_preserve_folio(page_folio(fdt_page)) and do a clean error check for
kho_add_subtree(), or call kho_remove_subtree() in the error block.
I prefer the former since if kho_add_subtree() is the one that fails,
there is little sense in removing a subtree that was never added.
> }
>
> return err;
> @@ -2529,13 +2498,6 @@ static int __init reserve_mem_init(void)
> err = prepare_kho_fdt();
> if (err)
> return err;
> -
> - err = register_kho_notifier(&reserve_mem_kho_nb);
> - if (err) {
> - put_page(kho_fdt);
> - kho_fdt = NULL;
> - }
> -
> return err;
> }
> late_initcall(reserve_mem_init);
--
Regards,
Pratyush Yadav
Powered by blists - more mailing lists