From: Anthony Yznaga <anthony.yznaga@oracle.com>
To: Mike Rapoport <rppt@linux.ibm.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
willy@infradead.org, corbet@lwn.net, tglx@linutronix.de,
mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
dave.hansen@linux.intel.com, luto@kernel.org,
peterz@infradead.org, akpm@linux-foundation.org,
hughd@google.com, ebiederm@xmission.com, masahiroy@kernel.org,
ardb@kernel.org, ndesaulniers@google.com, dima@golovin.in,
daniel.kiper@oracle.com, nivedita@alum.mit.edu,
rafael.j.wysocki@intel.com, dan.j.williams@intel.com,
zhenzhong.duan@oracle.com, jroedel@suse.de, bhe@redhat.com,
guro@fb.com, Thomas.Lendacky@amd.com,
andriy.shevchenko@linux.intel.com, keescook@chromium.org,
hannes@cmpxchg.org, minchan@kernel.org, mhocko@kernel.org,
ying.huang@intel.com, yang.shi@linux.alibaba.com,
gustavo@embeddedor.com, ziqian.lzq@antfin.com,
vdavydov.dev@gmail.com, jason.zeng@intel.com,
kevin.tian@intel.com, zhiyuan.lv@intel.com, lei.l.li@intel.com,
paul.c.lai@intel.com, ashok.raj@intel.com,
linux-fsdevel@vger.kernel.org, linux-doc@vger.kernel.org,
kexec@lists.infradead.org
Subject: Re: [RFC 14/43] mm: memblock: PKRAM: prevent memblock resize from clobbering preserved pages
Date: Mon, 11 May 2020 16:29:33 -0700 [thread overview]
Message-ID: <54773d69-1a2b-1ab3-24d9-b322d580fb42@oracle.com> (raw)
In-Reply-To: <20200511135727.GA983798@linux.ibm.com>
On 5/11/20 6:57 AM, Mike Rapoport wrote:
> On Wed, May 06, 2020 at 05:41:40PM -0700, Anthony Yznaga wrote:
>> The size of the memblock reserved array may be increased while preserved
>> pages are being reserved. When this happens, preserved pages that have
>> not yet been reserved are at risk for being clobbered when space for a
>> larger array is allocated.
>> When called from memblock_double_array(), a wrapper around
>> memblock_find_in_range() walks the preserved pages pagetable to find
>> sufficiently sized ranges without preserved pages and passes them to
>> memblock_find_in_range().
> I'd suggest to create an array of memblock_region's that will contain
> the PKRAM ranges before kexec and pass this array to the new kernel.
> Then, somewhere in start_kerenel() replace replace
> memblock.reserved->regions with that array.
I'll look into doing this. Thanks!
Anthony
>
>> Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
>> ---
>> include/linux/pkram.h | 3 +++
>> mm/memblock.c | 15 +++++++++++++--
>> mm/pkram.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
>> 3 files changed, 67 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/linux/pkram.h b/include/linux/pkram.h
>> index edc5d8bef9d3..409022e1472f 100644
>> --- a/include/linux/pkram.h
>> +++ b/include/linux/pkram.h
>> @@ -62,6 +62,9 @@ struct page *pkram_load_page(struct pkram_stream *ps, unsigned long *index,
>> ssize_t pkram_write(struct pkram_stream *ps, const void *buf, size_t count);
>> size_t pkram_read(struct pkram_stream *ps, void *buf, size_t count);
>>
>> +phys_addr_t pkram_memblock_find_in_range(phys_addr_t start, phys_addr_t end,
>> + phys_addr_t size, phys_addr_t align);
>> +
>> #ifdef CONFIG_PKRAM
>> extern unsigned long pkram_reserved_pages;
>> void pkram_reserve(void);
>> diff --git a/mm/memblock.c b/mm/memblock.c
>> index c79ba6f9920c..69ae883b8d21 100644
>> --- a/mm/memblock.c
>> +++ b/mm/memblock.c
>> @@ -16,6 +16,7 @@
>> #include <linux/kmemleak.h>
>> #include <linux/seq_file.h>
>> #include <linux/memblock.h>
>> +#include <linux/pkram.h>
>>
>> #include <asm/sections.h>
>> #include <linux/io.h>
>> @@ -349,6 +350,16 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
>> return ret;
>> }
>>
>> +phys_addr_t __init_memblock __memblock_find_in_range(phys_addr_t start,
>> + phys_addr_t end, phys_addr_t size,
>> + phys_addr_t align)
>> +{
>> + if (IS_ENABLED(CONFIG_PKRAM))
>> + return pkram_memblock_find_in_range(start, end, size, align);
>> + else
>> + return memblock_find_in_range(start, end, size, align);
>> +}
>> +
>> static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
>> {
>> type->total_size -= type->regions[r].size;
>> @@ -447,11 +458,11 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
>> if (type != &memblock.reserved)
>> new_area_start = new_area_size = 0;
>>
>> - addr = memblock_find_in_range(new_area_start + new_area_size,
>> + addr = __memblock_find_in_range(new_area_start + new_area_size,
>> memblock.current_limit,
>> new_alloc_size, PAGE_SIZE);
>> if (!addr && new_area_size)
>> - addr = memblock_find_in_range(0,
>> + addr = __memblock_find_in_range(0,
>> min(new_area_start, memblock.current_limit),
>> new_alloc_size, PAGE_SIZE);
>>
>> diff --git a/mm/pkram.c b/mm/pkram.c
>> index dd3c89614010..e49c9bcd3854 100644
>> --- a/mm/pkram.c
>> +++ b/mm/pkram.c
>> @@ -1238,3 +1238,54 @@ void pkram_free_pgt(void)
>> __free_pages_core(virt_to_page(pkram_pgd), 0);
>> pkram_pgd = NULL;
>> }
>> +
>> +static int __init_memblock pkram_memblock_find_cb(struct pkram_pg_state *st, unsigned long base, unsigned long size)
>> +{
>> + unsigned long end = base + size;
>> + unsigned long addr;
>> +
>> + if (size < st->min_size)
>> + return 0;
>> +
>> + addr = memblock_find_in_range(base, end, st->min_size, PAGE_SIZE);
>> + if (!addr)
>> + return 0;
>> +
>> + st->retval = addr;
>> + return 1;
>> +}
>> +
>> +/*
>> + * It may be necessary to allocate a larger reserved memblock array
>> + * while populating it with ranges of preserved pages. To avoid
>> + * trampling preserved pages that have not yet been added to the
>> + * memblock reserved list this function implements a wrapper around
>> + * memblock_find_in_range() that restricts searches to subranges
>> + * that do not contain preserved pages.
>> + */
>> +phys_addr_t __init_memblock pkram_memblock_find_in_range(phys_addr_t start,
>> + phys_addr_t end, phys_addr_t size,
>> + phys_addr_t align)
>> +{
>> + struct pkram_pg_state st = {
>> + .range_cb = pkram_memblock_find_cb,
>> + .min_addr = start,
>> + .max_addr = end,
>> + .min_size = PAGE_ALIGN(size),
>> + .find_holes = true,
>> + };
>> +
>> + if (!pkram_reservation_in_progress)
>> + return memblock_find_in_range(start, end, size, align);
>> +
>> + if (!pkram_pgd) {
>> + WARN_ONCE(1, "No preserved pages pagetable\n");
>> + return memblock_find_in_range(start, end, size, align);
>> + }
>> +
>> + WARN_ONCE(memblock_bottom_up(), "PKRAM: bottom up memblock allocation not yet supported\n");
>> +
>> + pkram_walk_pgt_rev(&st, pkram_pgd);
>> +
>> + return st.retval;
>> +}
>> --
>> 2.13.3
>>
next prev parent reply other threads:[~2020-05-11 23:33 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-07 0:41 [RFC 00/43] PKRAM: Preserved-over-Kexec RAM Anthony Yznaga
2020-05-07 0:41 ` [RFC 01/43] mm: add PKRAM API stubs and Kconfig Anthony Yznaga
2020-05-07 0:41 ` [RFC 02/43] mm: PKRAM: implement node load and save functions Anthony Yznaga
2020-05-07 0:41 ` [RFC 03/43] mm: PKRAM: implement object " Anthony Yznaga
2020-05-07 0:41 ` [RFC 04/43] mm: PKRAM: implement page stream operations Anthony Yznaga
2020-05-07 0:41 ` [RFC 05/43] mm: PKRAM: support preserving transparent hugepages Anthony Yznaga
2020-05-07 0:41 ` [RFC 06/43] mm: PKRAM: implement byte stream operations Anthony Yznaga
2020-05-07 0:41 ` [RFC 07/43] mm: PKRAM: link nodes by pfn before reboot Anthony Yznaga
2020-05-07 0:41 ` [RFC 08/43] mm: PKRAM: introduce super block Anthony Yznaga
2020-05-07 0:41 ` [RFC 09/43] PKRAM: build a physical mapping pagetable of pages to be preserved Anthony Yznaga
2020-05-07 0:41 ` [RFC 10/43] PKRAM: add code for walking the preserved pages pagetable Anthony Yznaga
2020-05-07 0:41 ` [RFC 11/43] PKRAM: pass the preserved pages pagetable to the next kernel Anthony Yznaga
2020-05-07 0:41 ` [RFC 12/43] mm: PKRAM: reserve preserved memory at boot Anthony Yznaga
2020-05-07 0:41 ` [RFC 13/43] mm: PKRAM: free preserved pages pagetable Anthony Yznaga
2020-05-07 0:41 ` [RFC 14/43] mm: memblock: PKRAM: prevent memblock resize from clobbering preserved pages Anthony Yznaga
2020-05-11 13:57 ` Mike Rapoport
2020-05-11 23:29 ` Anthony Yznaga [this message]
2020-05-07 0:41 ` [RFC 15/43] PKRAM: provide a way to ban pages from use by PKRAM Anthony Yznaga
2020-05-07 0:41 ` [RFC 16/43] kexec: PKRAM: prevent kexec clobbering preserved pages in some cases Anthony Yznaga
2020-05-07 0:41 ` [RFC 17/43] PKRAM: provide a way to check if a memory range has preserved pages Anthony Yznaga
2020-05-07 0:41 ` [RFC 18/43] kexec: PKRAM: avoid clobbering already " Anthony Yznaga
2020-05-07 0:41 ` [RFC 19/43] mm: PKRAM: allow preserved memory to be freed from userspace Anthony Yznaga
2020-05-07 0:41 ` [RFC 20/43] PKRAM: disable feature when running the kdump kernel Anthony Yznaga
2020-05-07 0:41 ` [RFC 21/43] x86/KASLR: PKRAM: support physical kaslr Anthony Yznaga
2020-05-07 17:51 ` Kees Cook
2020-05-07 18:41 ` Anthony Yznaga
2020-05-07 0:41 ` [RFC 22/43] mm: shmem: introduce shmem_insert_page Anthony Yznaga
2020-05-07 0:41 ` [RFC 23/43] mm: shmem: enable saving to PKRAM Anthony Yznaga
2020-05-07 0:41 ` [RFC 24/43] mm: shmem: prevent swapping of PKRAM-enabled tmpfs pages Anthony Yznaga
2020-05-07 0:41 ` [RFC 25/43] mm: shmem: specify the mm to use when inserting pages Anthony Yznaga
2020-05-07 0:41 ` [RFC 26/43] mm: shmem: when inserting, handle pages already charged to a memcg Anthony Yznaga
2020-05-07 0:41 ` [RFC 27/43] x86/mm/numa: add numa_isolate_memblocks() Anthony Yznaga
2020-05-07 0:41 ` [RFC 28/43] PKRAM: ensure memblocks with preserved pages init'd for numa Anthony Yznaga
2020-05-07 0:41 ` [RFC 29/43] memblock: PKRAM: mark memblocks that contain preserved pages Anthony Yznaga
2020-05-07 0:41 ` [RFC 30/43] memblock: add for_each_reserved_mem_range() Anthony Yznaga
2020-05-07 0:41 ` [RFC 31/43] memblock, mm: defer initialization of preserved pages Anthony Yznaga
2020-05-07 0:41 ` [RFC 32/43] shmem: PKRAM: preserve shmem files a chunk at a time Anthony Yznaga
2020-05-07 0:41 ` [RFC 33/43] PKRAM: atomically add and remove link pages Anthony Yznaga
2020-05-07 0:42 ` [RFC 34/43] shmem: PKRAM: multithread preserving and restoring shmem pages Anthony Yznaga
2020-05-07 16:30 ` Randy Dunlap
2020-05-07 17:59 ` Anthony Yznaga
2020-05-07 0:42 ` [RFC 35/43] shmem: introduce shmem_insert_pages() Anthony Yznaga
2020-05-07 0:42 ` [RFC 36/43] PKRAM: add support for loading pages in bulk Anthony Yznaga
2020-05-07 0:42 ` [RFC 37/43] shmem: PKRAM: enable bulk loading of preserved pages into shmem Anthony Yznaga
2020-05-07 0:42 ` [RFC 38/43] mm: implement splicing a list of pages to the LRU Anthony Yznaga
2020-05-07 0:42 ` [RFC 39/43] shmem: optimize adding pages to the LRU in shmem_insert_pages() Anthony Yznaga
2020-05-07 0:42 ` [RFC 40/43] shmem: initial support for adding multiple pages to pagecache Anthony Yznaga
2020-05-07 0:42 ` [RFC 41/43] XArray: add xas_export_node() and xas_import_node() Anthony Yznaga
2020-05-07 0:42 ` [RFC 42/43] shmem: reduce time holding xa_lock when inserting pages Anthony Yznaga
2020-05-07 0:42 ` [RFC 43/43] PKRAM: improve index alignment of pkram_link entries Anthony Yznaga
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=54773d69-1a2b-1ab3-24d9-b322d580fb42@oracle.com \
--to=anthony.yznaga@oracle.com \
--cc=Thomas.Lendacky@amd.com \
--cc=akpm@linux-foundation.org \
--cc=andriy.shevchenko@linux.intel.com \
--cc=ardb@kernel.org \
--cc=ashok.raj@intel.com \
--cc=bhe@redhat.com \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=daniel.kiper@oracle.com \
--cc=dave.hansen@linux.intel.com \
--cc=dima@golovin.in \
--cc=ebiederm@xmission.com \
--cc=guro@fb.com \
--cc=gustavo@embeddedor.com \
--cc=hannes@cmpxchg.org \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jason.zeng@intel.com \
--cc=jroedel@suse.de \
--cc=keescook@chromium.org \
--cc=kevin.tian@intel.com \
--cc=kexec@lists.infradead.org \
--cc=lei.l.li@intel.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=masahiroy@kernel.org \
--cc=mhocko@kernel.org \
--cc=minchan@kernel.org \
--cc=mingo@redhat.com \
--cc=ndesaulniers@google.com \
--cc=nivedita@alum.mit.edu \
--cc=paul.c.lai@intel.com \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=rppt@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=vdavydov.dev@gmail.com \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
--cc=yang.shi@linux.alibaba.com \
--cc=ying.huang@intel.com \
--cc=zhenzhong.duan@oracle.com \
--cc=zhiyuan.lv@intel.com \
--cc=ziqian.lzq@antfin.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
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;
as well as URLs for NNTP newsgroup(s).