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 13/43] mm: PKRAM: free preserved pages pagetable
Date: Wed, 6 May 2020 17:41:39 -0700 [thread overview]
Message-ID: <1588812129-8596-14-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>
After the page ranges in the pagetable have been reserved the pagetable
is no longer needed. Rather than free it during early boot by unreserving
page-sized blocks which can be inefficient when dealing with a large number
of blocks, wait until the page structs have been initialized and free them
as pages.
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
arch/x86/mm/init_64.c | 1 +
include/linux/pkram.h | 3 ++
mm/pkram.c | 11 +++++++
mm/pkram_pagetable.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 97 insertions(+)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ae569ef6bd7d..72662615977b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1245,6 +1245,7 @@ void __init mem_init(void)
after_bootmem = 1;
x86_init.hyper.init_after_bootmem();
+ pkram_free_pgt();
totalram_pages_add(pkram_reserved_pages);
/*
* Must be done after boot memory is put on freelist, because here we
diff --git a/include/linux/pkram.h b/include/linux/pkram.h
index 1b475f6e1598..edc5d8bef9d3 100644
--- a/include/linux/pkram.h
+++ b/include/linux/pkram.h
@@ -39,6 +39,7 @@ struct pkram_pg_state {
};
void pkram_walk_pgt_rev(struct pkram_pg_state *st, pgd_t *pgd);
+void pkram_free_pgt_walk_pgd(pgd_t *pgd);
int pkram_prepare_save(struct pkram_stream *ps, const char *name,
gfp_t gfp_mask);
@@ -64,9 +65,11 @@ size_t pkram_read(struct pkram_stream *ps, void *buf, size_t count);
#ifdef CONFIG_PKRAM
extern unsigned long pkram_reserved_pages;
void pkram_reserve(void);
+void pkram_free_pgt(void);
#else
#define pkram_reserved_pages 0UL
static inline void pkram_reserve(void) { }
+static inline void pkram_free_pgt(void) { }
#endif
#endif /* _LINUX_PKRAM_H */
diff --git a/mm/pkram.c b/mm/pkram.c
index 2c323154df76..dd3c89614010 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -1227,3 +1227,14 @@ static int __init pkram_reserve_page_ranges(pgd_t *pgd)
return err;
}
+
+void pkram_free_pgt(void)
+{
+ if (!pkram_pgd)
+ return;
+
+ pkram_free_pgt_walk_pgd(pkram_pgd);
+
+ __free_pages_core(virt_to_page(pkram_pgd), 0);
+ pkram_pgd = NULL;
+}
diff --git a/mm/pkram_pagetable.c b/mm/pkram_pagetable.c
index d31aa36207ba..7033e9b1c47f 100644
--- a/mm/pkram_pagetable.c
+++ b/mm/pkram_pagetable.c
@@ -3,6 +3,8 @@
#include <asm/pgtable.h>
#include <linux/pkram.h>
+#include "internal.h"
+
#define pgd_none(a) (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
static int note_page_rev(struct pkram_pg_state *st, unsigned long curr_size, bool present)
@@ -167,3 +169,83 @@ void pkram_walk_pgt_rev(struct pkram_pg_state *st, pgd_t *pgd)
break;
}
}
+
+static void pkram_free_pgt_walk_pmd(pud_t addr)
+{
+ unsigned long bitmap_pa;
+ struct page *page;
+ pmd_t *start;
+ int i;
+
+ start = (pmd_t *)pud_page_vaddr(addr);
+ for (i = 0; i < PTRS_PER_PMD; i++, start++) {
+ if (!pmd_none(*start)) {
+ bitmap_pa = pte_val(pte_clrhuge(*(pte_t *)start));
+ if (pmd_large(*start) && !bitmap_pa)
+ continue;
+ page = virt_to_page(__va(bitmap_pa));
+ __free_pages_core(page, 0);
+ }
+ }
+}
+
+static void pkram_free_pgt_walk_pud(p4d_t addr)
+{
+ struct page *page;
+ pud_t *start;
+ int i;
+
+ start = (pud_t *)p4d_page_vaddr(addr);
+ for (i = 0; i < PTRS_PER_PUD; i++, start++) {
+ if (!pud_none(*start)) {
+ if (pud_large(*start)) {
+ WARN_ONCE(1, "PKRAM: unexpected pud hugepage\n");
+ continue;
+ }
+ pkram_free_pgt_walk_pmd(*start);
+ page = virt_to_page(__va(pud_val(*start)));
+ __free_pages_core(page, 0);
+ }
+ }
+}
+
+static void pkram_free_pgt_walk_p4d(pgd_t addr)
+{
+ struct page *page;
+ p4d_t *start;
+ int i;
+
+ if (PTRS_PER_P4D == 1)
+ return pkram_free_pgt_walk_pud(__p4d(pgd_val(addr)));
+
+ start = (p4d_t *)pgd_page_vaddr(addr);
+ for (i = 0; i < PTRS_PER_P4D; i++, start++) {
+ if (!p4d_none(*start)) {
+ if (p4d_large(*start)) {
+ WARN_ONCE(1, "PKRAM: unexpected p4d hugepage\n");
+ continue;
+ }
+ pkram_free_pgt_walk_pud(*start);
+ page = virt_to_page(__va(p4d_val(*start)));
+ __free_pages_core(page, 0);
+ }
+ }
+}
+
+/*
+ * Free the pagetable passed from the previous boot.
+ */
+void pkram_free_pgt_walk_pgd(pgd_t *pgd)
+{
+ pgd_t *start = pgd;
+ struct page *page;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PGD; i++, start++) {
+ if (!pgd_none(*start)) {
+ pkram_free_pgt_walk_p4d(*start);
+ page = virt_to_page(__va(pgd_val(*start)));
+ __free_pages_core(page, 0);
+ }
+ }
+}
--
2.13.3
next prev parent reply other threads:[~2020-05-07 0:44 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 ` [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 ` Anthony Yznaga [this message]
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=1588812129-8596-14-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).