From: Coiby Xu <coxu@redhat.com>
To: Anthony Yznaga <anthony.yznaga@oracle.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
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, rppt@kernel.org,
akpm@linux-foundation.org, ebiederm@xmission.com,
keescook@chromium.org, graf@amazon.com, jason.zeng@intel.com,
lei.l.li@intel.com, steven.sistare@oracle.com,
fam.zheng@bytedance.com, mgalaxy@akamai.com,
kexec@lists.infradead.org
Subject: Re: [RFC v3 07/21] mm: PKRAM: introduce super block
Date: Mon, 5 Jun 2023 10:40:15 +0800 [thread overview]
Message-ID: <upgf3qmqxn7xzbnwwt6nxau4ugqkq7szdaheewzbok27xwch4e@6tdnhkqspok4> (raw)
In-Reply-To: <1682554137-13938-8-git-send-email-anthony.yznaga@oracle.com>
Hi Anthony,
On Wed, Apr 26, 2023 at 05:08:43PM -0700, Anthony Yznaga wrote:
>The PKRAM super block is the starting point for restoring preserved
>memory. By providing the super block to the new kernel at boot time,
>preserved memory can be reserved and made available to be restored.
>To point the kernel to the location of the super block, one passes
>its pfn via the 'pkram' boot param.
I'm curious to ask how will the 'pkram' boot param be passed. It seems I
can't find the answer in this patch set.
> For that purpose, the pkram super
>block pfn is exported via /sys/kernel/pkram. If none is passed, any
>preserved memory will not be kept, and a new super block will be
>allocated.
>
>Originally-by: Vladimir Davydov <vdavydov.dev@gmail.com>
>Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
>---
> mm/pkram.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 100 insertions(+), 2 deletions(-)
>
>diff --git a/mm/pkram.c b/mm/pkram.c
>index da166cb6afb7..c66b2ae4d520 100644
>--- a/mm/pkram.c
>+++ b/mm/pkram.c
>@@ -5,15 +5,18 @@
> #include <linux/init.h>
> #include <linux/io.h>
> #include <linux/kernel.h>
>+#include <linux/kobject.h>
> #include <linux/list.h>
> #include <linux/mm.h>
> #include <linux/module.h>
> #include <linux/mutex.h>
> #include <linux/notifier.h>
>+#include <linux/pfn.h>
> #include <linux/pkram.h>
> #include <linux/reboot.h>
> #include <linux/sched.h>
> #include <linux/string.h>
>+#include <linux/sysfs.h>
> #include <linux/types.h>
>
> #include "internal.h"
>@@ -82,12 +85,38 @@ struct pkram_node {
> #define PKRAM_ACCMODE_MASK 3
>
> /*
>+ * The PKRAM super block contains data needed to restore the preserved memory
>+ * structure on boot. The pointer to it (pfn) should be passed via the 'pkram'
>+ * boot param if one wants to restore preserved data saved by the previously
>+ * executing kernel. For that purpose the kernel exports the pfn via
>+ * /sys/kernel/pkram. If none is passed, preserved memory if any will not be
>+ * preserved and a new clean page will be allocated for the super block.
>+ *
>+ * The structure occupies a memory page.
>+ */
>+struct pkram_super_block {
>+ __u64 node_pfn; /* first element of the node list */
>+};
>+
>+static unsigned long pkram_sb_pfn __initdata;
>+static struct pkram_super_block *pkram_sb;
>+
>+/*
> * For convenience sake PKRAM nodes are kept in an auxiliary doubly-linked list
> * connected through the lru field of the page struct.
> */
> static LIST_HEAD(pkram_nodes); /* linked through page::lru */
> static DEFINE_MUTEX(pkram_mutex); /* serializes open/close */
>
>+/*
>+ * The PKRAM super block pfn, see above.
>+ */
>+static int __init parse_pkram_sb_pfn(char *arg)
>+{
>+ return kstrtoul(arg, 16, &pkram_sb_pfn);
>+}
>+early_param("pkram", parse_pkram_sb_pfn);
>+
> static inline struct page *pkram_alloc_page(gfp_t gfp_mask)
> {
> return alloc_page(gfp_mask);
>@@ -270,6 +299,7 @@ static void pkram_stream_init(struct pkram_stream *ps,
> * @gfp_mask specifies the memory allocation mask to be used when saving data.
> *
> * Error values:
>+ * %ENODEV: PKRAM not available
> * %ENAMETOOLONG: name len >= PKRAM_NAME_MAX
> * %ENOMEM: insufficient memory available
> * %EEXIST: node with specified name already exists
>@@ -285,6 +315,9 @@ int pkram_prepare_save(struct pkram_stream *ps, const char *name, gfp_t gfp_mask
> struct pkram_node *node;
> int err = 0;
>
>+ if (!pkram_sb)
>+ return -ENODEV;
>+
> if (strlen(name) >= PKRAM_NAME_MAX)
> return -ENAMETOOLONG;
>
>@@ -404,6 +437,7 @@ void pkram_discard_save(struct pkram_stream *ps)
> * Returns 0 on success, -errno on failure.
> *
> * Error values:
>+ * %ENODEV: PKRAM not available
> * %ENOENT: node with specified name does not exist
> * %EBUSY: save to required node has not finished yet
> *
>@@ -414,6 +448,9 @@ int pkram_prepare_load(struct pkram_stream *ps, const char *name)
> struct pkram_node *node;
> int err = 0;
>
>+ if (!pkram_sb)
>+ return -ENODEV;
>+
> mutex_lock(&pkram_mutex);
> node = pkram_find_node(name);
> if (!node) {
>@@ -825,6 +862,13 @@ static void __pkram_reboot(void)
> node->node_pfn = node_pfn;
> node_pfn = page_to_pfn(page);
> }
>+
>+ /*
>+ * Zero out pkram_sb completely since it may have been passed from
>+ * the previous boot.
>+ */
>+ memset(pkram_sb, 0, PAGE_SIZE);
>+ pkram_sb->node_pfn = node_pfn;
> }
>
> static int pkram_reboot(struct notifier_block *notifier,
>@@ -832,7 +876,8 @@ static int pkram_reboot(struct notifier_block *notifier,
> {
> if (val != SYS_RESTART)
> return NOTIFY_DONE;
>- __pkram_reboot();
>+ if (pkram_sb)
>+ __pkram_reboot();
> return NOTIFY_OK;
> }
>
>@@ -840,9 +885,62 @@ static int pkram_reboot(struct notifier_block *notifier,
> .notifier_call = pkram_reboot,
> };
>
>+static ssize_t show_pkram_sb_pfn(struct kobject *kobj,
>+ struct kobj_attribute *attr, char *buf)
>+{
>+ unsigned long pfn = pkram_sb ? PFN_DOWN(__pa(pkram_sb)) : 0;
>+
>+ return sprintf(buf, "%lx\n", pfn);
>+}
>+
>+static struct kobj_attribute pkram_sb_pfn_attr =
>+ __ATTR(pkram, 0444, show_pkram_sb_pfn, NULL);
>+
>+static struct attribute *pkram_attrs[] = {
>+ &pkram_sb_pfn_attr.attr,
>+ NULL,
>+};
>+
>+static struct attribute_group pkram_attr_group = {
>+ .attrs = pkram_attrs,
>+};
>+
>+/* returns non-zero on success */
>+static int __init pkram_init_sb(void)
>+{
>+ unsigned long pfn;
>+ struct pkram_node *node;
>+
>+ if (!pkram_sb) {
>+ struct page *page;
>+
>+ page = pkram_alloc_page(GFP_KERNEL | __GFP_ZERO);
>+ if (!page) {
>+ pr_err("PKRAM: Failed to allocate super block\n");
>+ return 0;
>+ }
>+ pkram_sb = page_address(page);
>+ }
>+
>+ /*
>+ * Build auxiliary doubly-linked list of nodes connected through
>+ * page::lru for convenience sake.
>+ */
>+ pfn = pkram_sb->node_pfn;
>+ while (pfn) {
>+ node = pfn_to_kaddr(pfn);
>+ pkram_insert_node(node);
>+ pfn = node->node_pfn;
>+ }
>+ return 1;
>+}
>+
> static int __init pkram_init(void)
> {
>- register_reboot_notifier(&pkram_reboot_notifier);
>+ if (pkram_init_sb()) {
>+ register_reboot_notifier(&pkram_reboot_notifier);
>+ sysfs_update_group(kernel_kobj, &pkram_attr_group);
>+ }
> return 0;
> }
> module_init(pkram_init);
>--
>1.9.4
>
>
>_______________________________________________
>kexec mailing list
>kexec@lists.infradead.org
>http://lists.infradead.org/mailman/listinfo/kexec
>
--
Best regards,
Coiby
_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec
next prev parent reply other threads:[~2023-06-05 2:45 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-27 0:08 [RFC v3 00/21] Preserved-over-Kexec RAM Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 01/21] mm: add PKRAM API stubs and Kconfig Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 02/21] mm: PKRAM: implement node load and save functions Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 03/21] mm: PKRAM: implement object " Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 04/21] mm: PKRAM: implement folio stream operations Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 05/21] mm: PKRAM: implement byte " Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 06/21] mm: PKRAM: link nodes by pfn before reboot Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 07/21] mm: PKRAM: introduce super block Anthony Yznaga
2023-06-05 2:40 ` Coiby Xu [this message]
2023-06-06 2:01 ` Anthony Yznaga
2023-06-06 2:55 ` Coiby Xu
2023-06-06 3:12 ` Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 08/21] PKRAM: track preserved pages in a physical mapping pagetable Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 09/21] PKRAM: pass a list of preserved ranges to the next kernel Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 10/21] PKRAM: prepare for adding preserved ranges to memblock reserved Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 11/21] mm: PKRAM: reserve preserved memory at boot Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 12/21] PKRAM: free the preserved ranges list Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 13/21] PKRAM: prevent inadvertent use of a stale superblock Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 14/21] PKRAM: provide a way to ban pages from use by PKRAM Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 15/21] kexec: PKRAM: prevent kexec clobbering preserved pages in some cases Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 16/21] PKRAM: provide a way to check if a memory range has preserved pages Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 17/21] kexec: PKRAM: avoid clobbering already " Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 18/21] mm: PKRAM: allow preserved memory to be freed from userspace Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 19/21] PKRAM: disable feature when running the kdump kernel Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 20/21] x86/KASLR: PKRAM: support physical kaslr Anthony Yznaga
2023-04-27 0:08 ` [RFC v3 21/21] x86/boot/compressed/64: use 1GB pages for mappings Anthony Yznaga
2023-04-27 18:40 ` H. Peter Anvin
2023-04-27 22:38 ` Anthony Yznaga
2023-05-26 13:57 ` [RFC v3 00/21] Preserved-over-Kexec RAM Gowans, James
2023-05-31 23:14 ` Anthony Yznaga
2023-06-01 2:15 ` Baoquan He
2023-06-01 23:58 ` 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=upgf3qmqxn7xzbnwwt6nxau4ugqkq7szdaheewzbok27xwch4e@6tdnhkqspok4 \
--to=coxu@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=anthony.yznaga@oracle.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=ebiederm@xmission.com \
--cc=fam.zheng@bytedance.com \
--cc=graf@amazon.com \
--cc=hpa@zytor.com \
--cc=jason.zeng@intel.com \
--cc=keescook@chromium.org \
--cc=kexec@lists.infradead.org \
--cc=lei.l.li@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mgalaxy@akamai.com \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rppt@kernel.org \
--cc=steven.sistare@oracle.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/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).