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 09/43] PKRAM: build a physical mapping pagetable of pages to be preserved
Date: Wed, 6 May 2020 17:41:35 -0700 [thread overview]
Message-ID: <1588812129-8596-10-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>
Future patches will need a way to efficiently identify physically
contiguous ranges of preserved pages regardless of their virtual
addresses as well as a way to identify ranges that do not contain
preserved pages. To facilitate this all pages to be preserved across
kexec are added to an identity mapping-style pagetable that is passed
to the next kernel.
The pagetable makes use of the existing architecture definitions for
building a memory mapping pagetable with the primary difference being
that a bitmap is used to represent the presence or absence of preserved
pages at the PTE level.
In general both metadata pages and data pages must be added to the
pagetable. A mapping for a metadata page can be added when the page is
allocated, but there is an exception: for the pagetable pages themselves
mappings are added after they are allocated to avoid recursion.
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
mm/pkram.c | 233 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 230 insertions(+), 3 deletions(-)
diff --git a/mm/pkram.c b/mm/pkram.c
index 70f2219e6218..5a7b8f61a55d 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -99,6 +99,12 @@ struct pkram_super_block {
static unsigned long pkram_sb_pfn __initdata;
static struct pkram_super_block *pkram_sb;
+static pgd_t *pkram_pgd;
+static DEFINE_SPINLOCK(pkram_pgd_lock);
+
+static int pkram_add_identity_map(struct page *page);
+static void pkram_remove_identity_map(struct page *page);
+
/*
* For convenience sake PKRAM nodes are kept in an auxiliary doubly-linked list
* connected through the lru field of the page struct.
@@ -115,13 +121,31 @@ static int __init parse_pkram_sb_pfn(char *arg)
}
early_param("pkram", parse_pkram_sb_pfn);
+static inline struct page *__pkram_alloc_page(gfp_t gfp_mask, bool add_to_map)
+{
+ struct page *page;
+ int err;
+
+ page = alloc_page(gfp_mask);
+ if (page && add_to_map) {
+ err = pkram_add_identity_map(page);
+ if (err) {
+ __free_page(page);
+ page = NULL;
+ }
+ }
+
+ return page;
+}
+
static inline struct page *pkram_alloc_page(gfp_t gfp_mask)
{
- return alloc_page(gfp_mask);
+ return __pkram_alloc_page(gfp_mask, true);
}
static inline void pkram_free_page(void *addr)
{
+ pkram_remove_identity_map(virt_to_page(addr));
free_page((unsigned long)addr);
}
@@ -159,6 +183,7 @@ static void pkram_truncate_link(struct pkram_link *link)
if (!p)
continue;
page = pfn_to_page(PHYS_PFN(p));
+ pkram_remove_identity_map(page);
put_page(page);
}
}
@@ -547,10 +572,15 @@ static int __pkram_save_page(struct pkram_stream *ps,
int pkram_save_page(struct pkram_stream *ps, struct page *page, short flags)
{
struct pkram_node *node = ps->node;
+ int err;
BUG_ON((node->flags & PKRAM_ACCMODE_MASK) != PKRAM_SAVE);
- return __pkram_save_page(ps, page, flags, page->index);
+ err = __pkram_save_page(ps, page, flags, page->index);
+ if (!err)
+ err = pkram_add_identity_map(page);
+
+ return err;
}
/*
@@ -599,6 +629,8 @@ static struct page *__pkram_load_page(struct pkram_stream *ps, unsigned long *in
/* clear to avoid double free (see pkram_truncate_link()) */
link->entry[ps->entry_idx] = 0;
+ pkram_remove_identity_map(page);
+
ps->entry_idx++;
if (ps->entry_idx >= PKRAM_LINK_ENTRIES_MAX ||
!link->entry[ps->entry_idx]) {
@@ -791,7 +823,7 @@ static int __init pkram_init_sb(void)
if (!pkram_sb) {
struct page *page;
- page = pkram_alloc_page(GFP_KERNEL | __GFP_ZERO);
+ page = __pkram_alloc_page(GFP_KERNEL | __GFP_ZERO, false);
if (!page) {
pr_err("PKRAM: Failed to allocate super block\n");
return 0;
@@ -821,3 +853,198 @@ static int __init pkram_init(void)
return 0;
}
module_init(pkram_init);
+
+static unsigned long *pkram_alloc_pte_bitmap(void)
+{
+ return page_address(__pkram_alloc_page(GFP_KERNEL | __GFP_ZERO, false));
+}
+
+static void pkram_free_pte_bitmap(void *bitmap)
+{
+ pkram_remove_identity_map(virt_to_page(bitmap));
+ free_page((unsigned long)bitmap);
+}
+
+#define set_p4d(p4dp, p4d) WRITE_ONCE(*(p4dp), (p4d))
+
+static int pkram_add_identity_map(struct page *page)
+{
+ unsigned long orig_paddr, paddr;
+ unsigned long *bitmap;
+ int result = -ENOMEM;
+ unsigned int index;
+ struct page *pg;
+ LIST_HEAD(list);
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ if (!pkram_pgd) {
+ spin_lock(&pkram_pgd_lock);
+ if (!pkram_pgd) {
+ pg = __pkram_alloc_page(GFP_KERNEL | __GFP_ZERO, false);
+ if (!pg)
+ goto err;
+ pkram_pgd = page_address(pg);
+ }
+ spin_unlock(&pkram_pgd_lock);
+ }
+
+ orig_paddr = paddr = __pa(page_address(page));
+again:
+ pgd = pkram_pgd;
+ pgd += pgd_index(paddr);
+ if (pgd_none(*pgd)) {
+ spin_lock(&pkram_pgd_lock);
+ if (pgd_none(*pgd)) {
+ pg = __pkram_alloc_page(GFP_KERNEL|__GFP_ZERO, false);
+ if (!pg)
+ goto err;
+ list_add(&pg->lru, &list);
+ p4d = page_address(pg);
+ set_pgd(pgd, __pgd(__pa(p4d)));
+ }
+ spin_unlock(&pkram_pgd_lock);
+ }
+ p4d = p4d_offset(pgd, paddr);
+ if (p4d_none(*p4d)) {
+ spin_lock(&pkram_pgd_lock);
+ if (p4d_none(*p4d)) {
+ pg = __pkram_alloc_page(GFP_KERNEL|__GFP_ZERO, false);
+ if (!pg)
+ goto err;
+ list_add(&pg->lru, &list);
+ pud = page_address(pg);
+ set_p4d(p4d, __p4d(__pa(pud)));
+ }
+ spin_unlock(&pkram_pgd_lock);
+ }
+ pud = pud_offset(p4d, paddr);
+ if (pud_none(*pud)) {
+ spin_lock(&pkram_pgd_lock);
+ if (pud_none(*pud)) {
+ pg = __pkram_alloc_page(GFP_KERNEL|__GFP_ZERO, false);
+ if (!pg)
+ goto err;
+ list_add(&pg->lru, &list);
+ pmd = page_address(pg);
+ set_pud(pud, __pud(__pa(pmd)));
+ }
+ spin_unlock(&pkram_pgd_lock);
+ }
+ pmd = pmd_offset(pud, paddr);
+ if (pmd_none(*pmd)) {
+ spin_lock(&pkram_pgd_lock);
+ if (pmd_none(*pmd)) {
+ if (PageTransHuge(page)) {
+ set_pmd(pmd, pmd_mkhuge(*pmd));
+ spin_unlock(&pkram_pgd_lock);
+ goto next;
+ }
+ bitmap = pkram_alloc_pte_bitmap();
+ if (!bitmap)
+ goto err;
+ pg = virt_to_page(bitmap);
+ list_add(&pg->lru, &list);
+ set_pmd(pmd, __pmd(__pa(bitmap)));
+ } else {
+ BUG_ON(pmd_large(*pmd));
+ bitmap = __va(pmd_val(*pmd));
+ }
+ spin_unlock(&pkram_pgd_lock);
+ } else {
+ BUG_ON(pmd_large(*pmd));
+ bitmap = __va(pmd_val(*pmd));
+ }
+
+ index = pte_index(paddr);
+ BUG_ON(test_bit(index, bitmap));
+ set_bit(index, bitmap);
+ smp_mb__after_atomic();
+ if (bitmap_full(bitmap, PTRS_PER_PTE))
+ set_pmd(pmd, pmd_mkhuge(*pmd));
+next:
+ /* Add mappings for any pagetable pages that were allocated */
+ if (!list_empty(&list)) {
+ page = list_first_entry(&list, struct page, lru);
+ list_del_init(&page->lru);
+ paddr = __pa(page_address(page));
+ goto again;
+ }
+
+ return 0;
+err:
+ spin_unlock(&pkram_pgd_lock);
+ while (!list_empty(&list)) {
+ pg = list_first_entry(&list, struct page, lru);
+ list_del_init(&pg->lru);
+ }
+ return result;
+}
+
+static void pkram_remove_identity_map(struct page *page)
+{
+ unsigned long *bitmap;
+ unsigned long paddr;
+ unsigned int index;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ /*
+ * pkram_pgd will be null when freeing metadata pages after a reboot
+ */
+ if (!pkram_pgd)
+ return;
+
+ paddr = __pa(page_address(page));
+ pgd = pkram_pgd;
+ pgd += pgd_index(paddr);
+ if (pgd_none(*pgd)) {
+ WARN_ONCE(1, "PKRAM: %s: no pgd for 0x%lx\n", __func__, paddr);
+ return;
+ }
+ p4d = p4d_offset(pgd, paddr);
+ if (p4d_none(*p4d)) {
+ WARN_ONCE(1, "PKRAM: %s: no p4d for 0x%lx\n", __func__, paddr);
+ return;
+ }
+ pud = pud_offset(p4d, paddr);
+ if (pud_none(*pud)) {
+ WARN_ONCE(1, "PKRAM: %s: no pud for 0x%lx\n", __func__, paddr);
+ return;
+ }
+ pmd = pmd_offset(pud, paddr);
+ if (pmd_none(*pmd)) {
+ WARN_ONCE(1, "PKRAM: %s: no pmd for 0x%lx\n", __func__, paddr);
+ return;
+ }
+ if (PageTransHuge(page)) {
+ BUG_ON(!pmd_large(*pmd));
+ pmd_clear(pmd);
+ return;
+ }
+
+ if (pmd_large(*pmd)) {
+ spin_lock(&pkram_pgd_lock);
+ if (pmd_large(*pmd))
+ set_pmd(pmd, __pmd(pte_val(pte_clrhuge(*(pte_t *)pmd))));
+ spin_unlock(&pkram_pgd_lock);
+ }
+
+ bitmap = __va(pmd_val(*pmd));
+ index = pte_index(paddr);
+ clear_bit(index, bitmap);
+ smp_mb__after_atomic();
+
+ spin_lock(&pkram_pgd_lock);
+ if (!pmd_none(*pmd) && bitmap_empty(bitmap, PTRS_PER_PTE)) {
+ pmd_clear(pmd);
+ spin_unlock(&pkram_pgd_lock);
+ pkram_free_pte_bitmap(bitmap);
+ } else {
+ spin_unlock(&pkram_pgd_lock);
+ }
+}
--
2.13.3
next prev parent reply other threads:[~2020-05-07 0:43 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 ` Anthony Yznaga [this message]
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=1588812129-8596-10-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 \
/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).