Linux-Fsdevel Archive on lore.kernel.org
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@linux.ibm.com,
	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: [RFC 04/43] mm: PKRAM: implement page stream operations
Date: Wed,  6 May 2020 17:41:30 -0700	[thread overview]
Message-ID: <1588812129-8596-5-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>

Using the pkram_save_page() function, one can populate PKRAM objects with
memory pages which can later be loaded using the pkram_load_page()
function. Saving a memory page to PKRAM is accomplished by recording
its pfn and incrementing its refcount so that it will not be freed after
the last user puts it.

Originally-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 include/linux/pkram.h |   5 ++
 mm/pkram.c            | 219 +++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 221 insertions(+), 3 deletions(-)

diff --git a/include/linux/pkram.h b/include/linux/pkram.h
index fabde2cd8203..f338d1c2aeb6 100644
--- a/include/linux/pkram.h
+++ b/include/linux/pkram.h
@@ -12,6 +12,11 @@ struct pkram_stream {
 	gfp_t gfp_mask;
 	struct pkram_node *node;
 	struct pkram_obj *obj;
+
+	struct pkram_link *link;		/* current link */
+	unsigned int entry_idx;		/* next entry in link */
+
+	unsigned long next_index;
 };
 
 #define PKRAM_NAME_MAX		256	/* including nul */
diff --git a/mm/pkram.c b/mm/pkram.c
index 4934ffd8b019..ab3053ca3539 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/err.h>
 #include <linux/gfp.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mm.h>
@@ -10,8 +11,38 @@
 #include <linux/string.h>
 #include <linux/types.h>
 
+#include "internal.h"
+
+
+/*
+ * Represents a reference to a data page saved to PKRAM.
+ */
+typedef __u64 pkram_entry_t;
+
+#define PKRAM_ENTRY_FLAGS_SHIFT	0x5
+#define PKRAM_ENTRY_FLAGS_MASK	0x7f
+
+/*
+ * Keeps references to data pages saved to PKRAM.
+ * The structure occupies a memory page.
+ */
+struct pkram_link {
+	__u64	link_pfn;	/* points to the next link of the object */
+	__u64	index;		/* mapping index of first pkram_entry_t */
+
+	/*
+	 * the array occupies the rest of the link page; if the link is not
+	 * full, the rest of the array must be filled with zeros
+	 */
+	pkram_entry_t entry[0];
+};
+
+#define PKRAM_LINK_ENTRIES_MAX \
+	((PAGE_SIZE-sizeof(struct pkram_link))/sizeof(pkram_entry_t))
+
 struct pkram_obj {
-	__u64   obj_pfn;	/* points to the next object in the list */
+	__u64	link_pfn;	/* points to the first link of the object */
+	__u64	obj_pfn;	/* points to the next object in the list */
 };
 
 /*
@@ -19,6 +50,10 @@ struct pkram_obj {
  * independently of each other. The nodes are identified by unique name
  * strings.
  *
+ * References to data pages saved to a preserved memory node are kept in a
+ * singly-linked list of PKRAM link structures (see above), the node has a
+ * pointer to the head of.
+ *
  * The structure occupies a memory page.
  */
 struct pkram_node {
@@ -68,6 +103,37 @@ static struct pkram_node *pkram_find_node(const char *name)
 	return NULL;
 }
 
+static void pkram_truncate_link(struct pkram_link *link)
+{
+	struct page *page;
+	pkram_entry_t p;
+	int i;
+
+	for (i = 0; i < PKRAM_LINK_ENTRIES_MAX; i++) {
+		p = link->entry[i];
+		if (!p)
+			continue;
+		page = pfn_to_page(PHYS_PFN(p));
+		put_page(page);
+	}
+}
+
+static void pkram_truncate_obj(struct pkram_obj *obj)
+{
+	unsigned long link_pfn;
+	struct pkram_link *link;
+
+	link_pfn = obj->link_pfn;
+	while (link_pfn) {
+		link = pfn_to_kaddr(link_pfn);
+		pkram_truncate_link(link);
+		link_pfn = link->link_pfn;
+		pkram_free_page(link);
+		cond_resched();
+	}
+	obj->link_pfn = 0;
+}
+
 static void pkram_truncate_node(struct pkram_node *node)
 {
 	unsigned long obj_pfn;
@@ -76,6 +142,7 @@ static void pkram_truncate_node(struct pkram_node *node)
 	obj_pfn = node->obj_pfn;
 	while (obj_pfn) {
 		obj = pfn_to_kaddr(obj_pfn);
+		pkram_truncate_obj(obj);
 		obj_pfn = obj->obj_pfn;
 		pkram_free_page(obj);
 		cond_resched();
@@ -83,6 +150,26 @@ static void pkram_truncate_node(struct pkram_node *node)
 	node->obj_pfn = 0;
 }
 
+static void pkram_add_link(struct pkram_link *link, struct pkram_obj *obj)
+{
+	link->link_pfn = obj->link_pfn;
+	obj->link_pfn = page_to_pfn(virt_to_page(link));
+}
+
+static struct pkram_link *pkram_remove_link(struct pkram_obj *obj)
+{
+	struct pkram_link *current_link;
+
+	if (!obj->link_pfn)
+		return NULL;
+
+	current_link = pfn_to_kaddr(obj->link_pfn);
+	obj->link_pfn = current_link->link_pfn;
+	current_link->link_pfn = 0;
+
+	return current_link;
+}
+
 static void pkram_stream_init(struct pkram_stream *ps,
 			     struct pkram_node *node, gfp_t gfp_mask)
 {
@@ -94,6 +181,9 @@ static void pkram_stream_init(struct pkram_stream *ps,
 static void pkram_stream_init_obj(struct pkram_stream *ps, struct pkram_obj *obj)
 {
 	ps->obj = obj;
+	ps->link = NULL;
+	ps->entry_idx = 0;
+	ps->next_index = 0;
 }
 
 /**
@@ -295,9 +385,28 @@ void pkram_finish_load_obj(struct pkram_stream *ps)
 {
 	struct pkram_node *node = ps->node;
 	struct pkram_obj *obj = ps->obj;
+	struct pkram_link *link = ps->link;
 
 	BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_LOAD);
 
+	/*
+	 * If link is not null, then loading stopped within a pkram_link
+	 * unexpectedly.
+	 */
+	if (link) {
+		unsigned long link_pfn;
+
+		link_pfn = page_to_pfn(virt_to_page(link));
+		while (link_pfn) {
+			link = pfn_to_kaddr(link_pfn);
+			pkram_truncate_link(link);
+			link_pfn = link->link_pfn;
+			pkram_free_page(link);
+			cond_resched();
+		}
+	}
+
+	pkram_truncate_obj(obj);
 	pkram_free_page(obj);
 }
 
@@ -316,6 +425,44 @@ void pkram_finish_load(struct pkram_stream *ps)
 	pkram_free_page(node);
 }
 
+/*
+ * Insert page to PKRAM node allocating a new PKRAM link if necessary.
+ */
+static int __pkram_save_page(struct pkram_stream *ps,
+			    struct page *page, short flags, unsigned long index)
+{
+	struct pkram_link *link = ps->link;
+	struct pkram_obj *obj = ps->obj;
+	pkram_entry_t p;
+
+	if (!link || ps->entry_idx >= PKRAM_LINK_ENTRIES_MAX ||
+	    index != ps->next_index) {
+		struct page *link_page;
+
+		link_page = pkram_alloc_page((ps->gfp_mask & GFP_RECLAIM_MASK) |
+					    __GFP_ZERO);
+		if (!link_page)
+			return -ENOMEM;
+
+		ps->link = link = page_address(link_page);
+		pkram_add_link(link, obj);
+
+		ps->entry_idx = 0;
+
+		ps->next_index = link->index = index;
+	}
+
+	ps->next_index++;
+
+	get_page(page);
+	p = page_to_phys(page);
+	p |= ((flags & PKRAM_ENTRY_FLAGS_MASK) << PKRAM_ENTRY_FLAGS_SHIFT);
+	link->entry[ps->entry_idx] = p;
+	ps->entry_idx++;
+
+	return 0;
+}
+
 /**
  * Save page @page to the preserved memory node and object associated with
  * stream @ps. The stream must have been initialized with pkram_prepare_save()
@@ -324,10 +471,72 @@ void pkram_finish_load(struct pkram_stream *ps)
  * @flags specifies supplemental page state to be preserved.
  *
  * Returns 0 on success, -errno on failure.
+ *
+ * Error values:
+ *	%ENOMEM: insufficient amount of memory available
+ *
+ * Saving a page to preserved memory is simply incrementing its refcount so
+ * that it will not get freed after the last user puts it. That means it is
+ * safe to use the page as usual after it has been saved.
  */
 int pkram_save_page(struct pkram_stream *ps, struct page *page, short flags)
 {
-	return -ENOSYS;
+	struct pkram_node *node = ps->node;
+
+	BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_SAVE);
+
+	BUG_ON(PageCompound(page));
+
+	return __pkram_save_page(ps, page, flags, page->index);
+}
+
+/*
+ * Extract the next page from preserved memory freeing a PKRAM link if it
+ * becomes empty.
+ */
+static struct page *__pkram_load_page(struct pkram_stream *ps, unsigned long *index, short *flags)
+{
+	struct pkram_link *link = ps->link;
+	struct page *page;
+	pkram_entry_t p;
+	short flgs;
+
+	if (!link) {
+		link = pkram_remove_link(ps->obj);
+		if (!link)
+			return NULL;
+
+		ps->link = link;
+		ps->entry_idx = 0;
+		ps->next_index = link->index;
+	}
+
+	BUG_ON(ps->entry_idx >= PKRAM_LINK_ENTRIES_MAX);
+
+	p = link->entry[ps->entry_idx];
+	BUG_ON(!p);
+
+	flgs = (p >> PKRAM_ENTRY_FLAGS_SHIFT) & PKRAM_ENTRY_FLAGS_MASK;
+	page = pfn_to_page(PHYS_PFN(p));
+
+	if (flags)
+		*flags = flgs;
+	if (index)
+		*index = ps->next_index;
+
+	ps->next_index++;
+
+	/* clear to avoid double free (see pkram_truncate_link()) */
+	link->entry[ps->entry_idx] = 0;
+
+	ps->entry_idx++;
+	if (ps->entry_idx >= PKRAM_LINK_ENTRIES_MAX ||
+	    !link->entry[ps->entry_idx]) {
+		ps->link = NULL;
+		pkram_free_page(link);
+	}
+
+	return page;
 }
 
 /**
@@ -346,7 +555,11 @@ int pkram_save_page(struct pkram_stream *ps, struct page *page, short flags)
  */
 struct page *pkram_load_page(struct pkram_stream *ps, unsigned long *index, short *flags)
 {
-	return NULL;
+	struct pkram_node *node = ps->node;
+
+	BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_LOAD);
+
+	return __pkram_load_page(ps, index, flags);
 }
 
 /**
-- 
2.13.3


  parent reply	other threads:[~2020-05-07  0:47 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 ` Anthony Yznaga [this message]
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
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=1588812129-8596-5-git-send-email-anthony.yznaga@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 \
    --subject='Re: [RFC 04/43] mm: PKRAM: implement page stream operations' \
    /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

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).