From: Anthony Yznaga <anthony.yznaga@oracle.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: 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, rppt@kernel.org, akpm@linux-foundation.org,
hughd@google.com, ebiederm@xmission.com, keescook@chromium.org,
ardb@kernel.org, nivedita@alum.mit.edu, jroedel@suse.de,
masahiroy@kernel.org, nathan@kernel.org, terrelln@fb.com,
vincenzo.frascino@arm.com, martin.b.radev@gmail.com,
andreyknvl@google.com, daniel.kiper@oracle.com,
rafael.j.wysocki@intel.com, dan.j.williams@intel.com,
Jonathan.Cameron@huawei.com, bhe@redhat.com, rminnich@gmail.com,
ashish.kalra@amd.com, guro@fb.com, hannes@cmpxchg.org,
mhocko@kernel.org, iamjoonsoo.kim@lge.com, vbabka@suse.cz,
alex.shi@linux.alibaba.com, david@redhat.com,
richard.weiyang@gmail.com, vdavydov.dev@gmail.com,
graf@amazon.com, jason.zeng@intel.com, lei.l.li@intel.com,
daniel.m.jordan@oracle.com, steven.sistare@oracle.com,
linux-fsdevel@vger.kernel.org, linux-doc@vger.kernel.org,
kexec@lists.infradead.org
Subject: [RFC v2 02/43] mm: PKRAM: implement node load and save functions
Date: Tue, 30 Mar 2021 14:35:37 -0700 [thread overview]
Message-ID: <1617140178-8773-3-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1617140178-8773-1-git-send-email-anthony.yznaga@oracle.com>
Preserved memory is divided into nodes which can be saved and loaded
independently of each other. PKRAM nodes are kept on a list and
identified by unique names. Whenever a save operation is initiated by
calling pkram_prepare_save(), a new node is created and linked to the
list. When the save operation has been committed by calling
pkram_finish_save(), the node becomes loadable. A load operation can be
then initiated by calling pkram_prepare_load() which deletes the node
from the list and prepares the corresponding stream for loading data
from it. After the load has been finished, the pkram_finish_load()
function must be called to free the node. Nodes are also deleted when a
save operation is discarded, i.e. pkram_discard_save() is called instead
of pkram_finish_save().
Originally-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
include/linux/pkram.h | 8 ++-
mm/pkram.c | 148 ++++++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 150 insertions(+), 6 deletions(-)
diff --git a/include/linux/pkram.h b/include/linux/pkram.h
index a575da2d6c79..01055a876450 100644
--- a/include/linux/pkram.h
+++ b/include/linux/pkram.h
@@ -6,6 +6,8 @@
#include <linux/types.h>
#include <linux/mm_types.h>
+struct pkram_node;
+
/**
* enum pkram_data_flags - definition of data types contained in a pkram obj
* @PKRAM_DATA_none: No data types configured
@@ -14,7 +16,11 @@ enum pkram_data_flags {
PKRAM_DATA_none = 0x0, /* No data types configured */
};
-struct pkram_stream;
+struct pkram_stream {
+ gfp_t gfp_mask;
+ struct pkram_node *node;
+};
+
struct pkram_access;
#define PKRAM_NAME_MAX 256 /* including nul */
diff --git a/mm/pkram.c b/mm/pkram.c
index 59e4661b2fb7..21976df6e0ea 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -2,16 +2,85 @@
#include <linux/err.h>
#include <linux/gfp.h>
#include <linux/kernel.h>
+#include <linux/list.h>
#include <linux/mm.h>
+#include <linux/mutex.h>
#include <linux/pkram.h>
+#include <linux/string.h>
#include <linux/types.h>
+/*
+ * Preserved memory is divided into nodes that can be saved or loaded
+ * independently of each other. The nodes are identified by unique name
+ * strings.
+ *
+ * The structure occupies a memory page.
+ */
+struct pkram_node {
+ __u32 flags;
+
+ __u8 name[PKRAM_NAME_MAX];
+};
+
+#define PKRAM_SAVE 1
+#define PKRAM_LOAD 2
+#define PKRAM_ACCMODE_MASK 3
+
+static LIST_HEAD(pkram_nodes); /* linked through page::lru */
+static DEFINE_MUTEX(pkram_mutex); /* serializes open/close */
+
+static inline struct page *pkram_alloc_page(gfp_t gfp_mask)
+{
+ return alloc_page(gfp_mask);
+}
+
+static inline void pkram_free_page(void *addr)
+{
+ free_page((unsigned long)addr);
+}
+
+static inline void pkram_insert_node(struct pkram_node *node)
+{
+ list_add(&virt_to_page(node)->lru, &pkram_nodes);
+}
+
+static inline void pkram_delete_node(struct pkram_node *node)
+{
+ list_del(&virt_to_page(node)->lru);
+}
+
+static struct pkram_node *pkram_find_node(const char *name)
+{
+ struct page *page;
+ struct pkram_node *node;
+
+ list_for_each_entry(page, &pkram_nodes, lru) {
+ node = page_address(page);
+ if (strcmp(node->name, name) == 0)
+ return node;
+ }
+ return NULL;
+}
+
+static void pkram_stream_init(struct pkram_stream *ps,
+ struct pkram_node *node, gfp_t gfp_mask)
+{
+ memset(ps, 0, sizeof(*ps));
+ ps->gfp_mask = gfp_mask;
+ ps->node = node;
+}
+
/**
* Create a preserved memory node with name @name and initialize stream @ps
* for saving data to it.
*
* @gfp_mask specifies the memory allocation mask to be used when saving data.
*
+ * Error values:
+ * %ENAMETOOLONG: name len >= PKRAM_NAME_MAX
+ * %ENOMEM: insufficient memory available
+ * %EEXIST: node with specified name already exists
+ *
* Returns 0 on success, -errno on failure.
*
* After the save has finished, pkram_finish_save() (or pkram_discard_save() in
@@ -19,7 +88,34 @@
*/
int pkram_prepare_save(struct pkram_stream *ps, const char *name, gfp_t gfp_mask)
{
- return -ENOSYS;
+ struct page *page;
+ struct pkram_node *node;
+ int err = 0;
+
+ if (strlen(name) >= PKRAM_NAME_MAX)
+ return -ENAMETOOLONG;
+
+ page = pkram_alloc_page(gfp_mask | __GFP_ZERO);
+ if (!page)
+ return -ENOMEM;
+ node = page_address(page);
+
+ node->flags = PKRAM_SAVE;
+ strcpy(node->name, name);
+
+ mutex_lock(&pkram_mutex);
+ if (!pkram_find_node(name))
+ pkram_insert_node(node);
+ else
+ err = -EEXIST;
+ mutex_unlock(&pkram_mutex);
+ if (err) {
+ pkram_free_page(node);
+ return err;
+ }
+
+ pkram_stream_init(ps, node, gfp_mask);
+ return 0;
}
/**
@@ -50,7 +146,12 @@ void pkram_finish_save_obj(struct pkram_stream *ps)
*/
void pkram_finish_save(struct pkram_stream *ps)
{
- BUG();
+ struct pkram_node *node = ps->node;
+
+ BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_SAVE);
+
+ smp_wmb();
+ node->flags &= ~PKRAM_ACCMODE_MASK;
}
/**
@@ -60,7 +161,15 @@ void pkram_finish_save(struct pkram_stream *ps)
*/
void pkram_discard_save(struct pkram_stream *ps)
{
- BUG();
+ struct pkram_node *node = ps->node;
+
+ BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_SAVE);
+
+ mutex_lock(&pkram_mutex);
+ pkram_delete_node(node);
+ mutex_unlock(&pkram_mutex);
+
+ pkram_free_page(node);
}
/**
@@ -69,11 +178,36 @@ void pkram_discard_save(struct pkram_stream *ps)
*
* Returns 0 on success, -errno on failure.
*
+ * Error values:
+ * %ENOENT: node with specified name does not exist
+ * %EBUSY: save to required node has not finished yet
+ *
* After the load has finished, pkram_finish_load() is to be called.
*/
int pkram_prepare_load(struct pkram_stream *ps, const char *name)
{
- return -ENOSYS;
+ struct pkram_node *node;
+ int err = 0;
+
+ mutex_lock(&pkram_mutex);
+ node = pkram_find_node(name);
+ if (!node) {
+ err = -ENOENT;
+ goto out_unlock;
+ }
+ if (node->flags & PKRAM_ACCMODE_MASK) {
+ err = -EBUSY;
+ goto out_unlock;
+ }
+ pkram_delete_node(node);
+out_unlock:
+ mutex_unlock(&pkram_mutex);
+ if (err)
+ return err;
+
+ node->flags |= PKRAM_LOAD;
+ pkram_stream_init(ps, node, 0);
+ return 0;
}
/**
@@ -106,7 +240,11 @@ void pkram_finish_load_obj(struct pkram_stream *ps)
*/
void pkram_finish_load(struct pkram_stream *ps)
{
- BUG();
+ struct pkram_node *node = ps->node;
+
+ BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_LOAD);
+
+ pkram_free_page(node);
}
/**
--
1.8.3.1
next prev parent reply other threads:[~2021-03-30 21:26 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-30 21:35 [RFC v2 00/43] PKRAM: Preserved-over-Kexec RAM Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 01/43] mm: add PKRAM API stubs and Kconfig Anthony Yznaga
2021-03-31 18:43 ` Randy Dunlap
2021-03-31 20:28 ` Anthony Yznaga
2021-03-30 21:35 ` Anthony Yznaga [this message]
2021-03-30 21:35 ` [RFC v2 03/43] mm: PKRAM: implement object load and save functions Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 04/43] mm: PKRAM: implement page stream operations Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 05/43] mm: PKRAM: support preserving transparent hugepages Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 06/43] mm: PKRAM: implement byte stream operations Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 07/43] mm: PKRAM: link nodes by pfn before reboot Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 08/43] mm: PKRAM: introduce super block Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 09/43] PKRAM: track preserved pages in a physical mapping pagetable Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 10/43] PKRAM: pass a list of preserved ranges to the next kernel Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 11/43] PKRAM: prepare for adding preserved ranges to memblock reserved Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 12/43] mm: PKRAM: reserve preserved memory at boot Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 13/43] PKRAM: free the preserved ranges list Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 14/43] PKRAM: prevent inadvertent use of a stale superblock Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 15/43] PKRAM: provide a way to ban pages from use by PKRAM Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 16/43] kexec: PKRAM: prevent kexec clobbering preserved pages in some cases Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 17/43] PKRAM: provide a way to check if a memory range has preserved pages Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 18/43] kexec: PKRAM: avoid clobbering already " Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 19/43] mm: PKRAM: allow preserved memory to be freed from userspace Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 20/43] PKRAM: disable feature when running the kdump kernel Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 21/43] x86/KASLR: PKRAM: support physical kaslr Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 22/43] x86/boot/compressed/64: use 1GB pages for mappings Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 23/43] mm: shmem: introduce shmem_insert_page Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 24/43] mm: shmem: enable saving to PKRAM Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 25/43] mm: shmem: prevent swapping of PKRAM-enabled tmpfs pages Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 26/43] mm: shmem: specify the mm to use when inserting pages Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 27/43] mm: shmem: when inserting, handle pages already charged to a memcg Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 28/43] x86/mm/numa: add numa_isolate_memblocks() Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 29/43] PKRAM: ensure memblocks with preserved pages init'd for numa Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 30/43] memblock: PKRAM: mark memblocks that contain preserved pages Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 31/43] memblock, mm: defer initialization of " Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 32/43] shmem: preserve shmem files a chunk at a time Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 33/43] PKRAM: atomically add and remove link pages Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 34/43] shmem: PKRAM: multithread preserving and restoring shmem pages Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 35/43] shmem: introduce shmem_insert_pages() Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 36/43] PKRAM: add support for loading pages in bulk Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 37/43] shmem: PKRAM: enable bulk loading of preserved pages into shmem Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 38/43] mm: implement splicing a list of pages to the LRU Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 39/43] shmem: optimize adding pages to the LRU in shmem_insert_pages() Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 40/43] shmem: initial support for adding multiple pages to pagecache Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 41/43] XArray: add xas_export_node() and xas_import_node() Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 42/43] shmem: reduce time holding xa_lock when inserting pages Anthony Yznaga
2021-03-30 21:36 ` [RFC v2 43/43] PKRAM: improve index alignment of pkram_link entries Anthony Yznaga
2021-06-05 13:39 ` [RFC v2 00/43] PKRAM: Preserved-over-Kexec RAM Pavel Tatashin
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=1617140178-8773-3-git-send-email-anthony.yznaga@oracle.com \
--to=anthony.yznaga@oracle.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=alex.shi@linux.alibaba.com \
--cc=andreyknvl@google.com \
--cc=ardb@kernel.org \
--cc=ashish.kalra@amd.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=daniel.m.jordan@oracle.com \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=ebiederm@xmission.com \
--cc=graf@amazon.com \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=jason.zeng@intel.com \
--cc=jroedel@suse.de \
--cc=keescook@chromium.org \
--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=martin.b.radev@gmail.com \
--cc=masahiroy@kernel.org \
--cc=mhocko@kernel.org \
--cc=mingo@redhat.com \
--cc=nathan@kernel.org \
--cc=nivedita@alum.mit.edu \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=richard.weiyang@gmail.com \
--cc=rminnich@gmail.com \
--cc=rppt@kernel.org \
--cc=steven.sistare@oracle.com \
--cc=terrelln@fb.com \
--cc=tglx@linutronix.de \
--cc=vbabka@suse.cz \
--cc=vdavydov.dev@gmail.com \
--cc=vincenzo.frascino@arm.com \
--cc=willy@infradead.org \
--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