linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
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 10/43] PKRAM: pass a list of preserved ranges to the next kernel
Date: Tue, 30 Mar 2021 14:35:45 -0700	[thread overview]
Message-ID: <1617140178-8773-11-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1617140178-8773-1-git-send-email-anthony.yznaga@oracle.com>

In order to build a new memblock reserved list during boot that
includes ranges preserved by the previous kernel, a list of preserved
ranges is passed to the next kernel via the pkram superblock. The
ranges are stored in ascending order in a linked list of pages. A more
complete memblock list is not prepared to avoid possible conflicts with
changes in a newer kernel and to avoid having to allocate a contiguous
range larger than a page.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 mm/pkram.c | 183 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 176 insertions(+), 7 deletions(-)

diff --git a/mm/pkram.c b/mm/pkram.c
index a9e6cd8ca084..4cfa236a4126 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -86,6 +86,20 @@ struct pkram_node {
 #define PKRAM_LOAD		2
 #define PKRAM_ACCMODE_MASK	3
 
+struct pkram_region {
+	phys_addr_t base;
+	phys_addr_t size;
+};
+
+struct pkram_region_list {
+	__u64	prev_pfn;
+	__u64	next_pfn;
+
+	struct pkram_region regions[0];
+};
+
+#define PKRAM_REGIONS_LIST_MAX \
+	((PAGE_SIZE-sizeof(struct pkram_region_list))/sizeof(struct pkram_region))
 /*
  * 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'
@@ -98,13 +112,20 @@ struct pkram_node {
  */
 struct pkram_super_block {
 	__u64	node_pfn;		/* first element of the node list */
+	__u64	region_list_pfn;
+	__u64	nr_regions;
 };
 
+static struct pkram_region_list *pkram_regions_list;
+static int pkram_init_regions_list(void);
+static unsigned long pkram_populate_regions_list(void);
+
 static unsigned long pkram_sb_pfn __initdata;
 static struct pkram_super_block *pkram_sb;
 
 extern int pkram_add_identity_map(struct page *page);
 extern void pkram_remove_identity_map(struct page *page);
+extern void pkram_find_preserved(unsigned long start, unsigned long end, void *private, int (*callback)(unsigned long base, unsigned long size, void *private));
 
 /*
  * For convenience sake PKRAM nodes are kept in an auxiliary doubly-linked list
@@ -862,21 +883,48 @@ static void __pkram_reboot(void)
 	struct page *page;
 	struct pkram_node *node;
 	unsigned long node_pfn = 0;
+	unsigned long rl_pfn = 0;
+	unsigned long nr_regions = 0;
+	int err = 0;
 
-	list_for_each_entry_reverse(page, &pkram_nodes, lru) {
-		node = page_address(page);
-		if (WARN_ON(node->flags & PKRAM_ACCMODE_MASK))
-			continue;
-		node->node_pfn = node_pfn;
-		node_pfn = page_to_pfn(page);
+	if (!list_empty(&pkram_nodes)) {
+		err = pkram_add_identity_map(virt_to_page(pkram_sb));
+		if (err) {
+			pr_err("PKRAM: failed to add super block to pagetable\n");
+			goto done;
+		}
+		list_for_each_entry_reverse(page, &pkram_nodes, lru) {
+			node = page_address(page);
+			if (WARN_ON(node->flags & PKRAM_ACCMODE_MASK))
+				continue;
+			node->node_pfn = node_pfn;
+			node_pfn = page_to_pfn(page);
+		}
+		err = pkram_init_regions_list();
+		if (err) {
+			pr_err("PKRAM: failed to init regions list\n");
+			goto done;
+		}
+		nr_regions = pkram_populate_regions_list();
+		if (IS_ERR_VALUE(nr_regions)) {
+			err = nr_regions;
+			pr_err("PKRAM: failed to populate regions list\n");
+			goto done;
+		}
+		rl_pfn = page_to_pfn(virt_to_page(pkram_regions_list));
 	}
 
+done:
 	/*
 	 * 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;
+	if (!err && node_pfn) {
+		pkram_sb->node_pfn = node_pfn;
+		pkram_sb->region_list_pfn = rl_pfn;
+		pkram_sb->nr_regions = nr_regions;
+	}
 }
 
 static int pkram_reboot(struct notifier_block *notifier,
@@ -952,3 +1000,124 @@ static int __init pkram_init(void)
 	return 0;
 }
 module_init(pkram_init);
+
+static int count_region_cb(unsigned long base, unsigned long size, void *private)
+{
+	unsigned long *nr_regions = (unsigned long *)private;
+
+	(*nr_regions)++;
+	return 0;
+}
+
+static unsigned long pkram_count_regions(void)
+{
+	unsigned long nr_regions = 0;
+
+	pkram_find_preserved(0, PHYS_ADDR_MAX, &nr_regions, count_region_cb);
+
+	return nr_regions;
+}
+
+/*
+ * To faciliate rapidly building a new memblock reserved list during boot
+ * with the addition of preserved memory ranges a regions list is built
+ * before reboot.
+ * The regions list is a linked list of pages with each page containing an
+ * array of preserved memory ranges.  The ranges are stored in each page
+ * and across the list in address order.  A linked list is used rather than
+ * a single contiguous range to mitigate against the possibility that a
+ * larger, contiguous allocation may fail due to fragmentation.
+ *
+ * Since the pages of the regions list must be preserved and the pkram
+ * pagetable is used to determine what ranges are preserved, the list pages
+ * must be allocated and represented in the pkram pagetable before they can
+ * be populated.  Rather than recounting the number of regions after
+ * allocating pages and repeating until a precise number of pages are
+ * are allocated, the number of pages needed is estimated.
+ */
+static int pkram_init_regions_list(void)
+{
+	struct pkram_region_list *rl;
+	unsigned long nr_regions;
+	unsigned long nr_lpages;
+	struct page *page;
+
+	nr_regions = pkram_count_regions();
+
+	nr_lpages = DIV_ROUND_UP(nr_regions, PKRAM_REGIONS_LIST_MAX);
+	nr_regions += nr_lpages;
+	nr_lpages = DIV_ROUND_UP(nr_regions, PKRAM_REGIONS_LIST_MAX);
+
+	for (; nr_lpages; nr_lpages--) {
+		page = pkram_alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			return -ENOMEM;
+		rl = page_address(page);
+		if (pkram_regions_list) {
+			rl->next_pfn = page_to_pfn(virt_to_page(pkram_regions_list));
+			pkram_regions_list->prev_pfn = page_to_pfn(page);
+		}
+		pkram_regions_list = rl;
+	}
+
+	return 0;
+}
+
+struct pkram_regions_priv {
+	struct pkram_region_list *curr;
+	struct pkram_region_list *last;
+	unsigned long nr_regions;
+	int idx;
+};
+
+static int add_region_cb(unsigned long base, unsigned long size, void *private)
+{
+	struct pkram_regions_priv *priv;
+	struct pkram_region_list *rl;
+	int i;
+
+	priv = (struct pkram_regions_priv *)private;
+	rl = priv->curr;
+	i = priv->idx;
+
+	if (!rl) {
+		WARN_ON(1);
+		return 1;
+	}
+
+	if (!i)
+		priv->last = priv->curr;
+
+	rl->regions[i].base = base;
+	rl->regions[i].size = size;
+
+	priv->nr_regions++;
+	i++;
+	if (i == PKRAM_REGIONS_LIST_MAX) {
+		u64 next_pfn = rl->next_pfn;
+
+		if (next_pfn)
+			priv->curr = pfn_to_kaddr(next_pfn);
+		else
+			priv->curr = NULL;
+
+		i = 0;
+	}
+	priv->idx = i;
+
+	return 0;
+}
+
+static unsigned long pkram_populate_regions_list(void)
+{
+	struct pkram_regions_priv priv = { .curr = pkram_regions_list };
+
+	pkram_find_preserved(0, PHYS_ADDR_MAX, &priv, add_region_cb);
+
+	/*
+	 * Link the first node to the last populated one.
+	 */
+	pkram_regions_list->prev_pfn = page_to_pfn(virt_to_page(priv.last));
+
+	return priv.nr_regions;
+}
-- 
1.8.3.1



  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 ` [RFC v2 02/43] mm: PKRAM: implement node load and save functions Anthony Yznaga
2021-03-30 21:35 ` [RFC v2 03/43] mm: PKRAM: implement object " 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 ` Anthony Yznaga [this message]
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=1617140178-8773-11-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;
as well as URLs for NNTP newsgroup(s).