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 10/43] PKRAM: add code for walking the preserved pages pagetable
Date: Wed,  6 May 2020 17:41:36 -0700	[thread overview]
Message-ID: <1588812129-8596-11-git-send-email-anthony.yznaga@oracle.com> (raw)
In-Reply-To: <1588812129-8596-1-git-send-email-anthony.yznaga@oracle.com>

Add the ability to walk the pkram pagetable from high to low addresses
and execute a callback for each contiguous range of preserved or not
preserved memory found.  The reason for walking high to low is to align
with high to low memblock allocation when finding holes that memblocks
can safely be allocated from as will be seen in a later patch.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 include/linux/pkram.h |  15 +++++
 mm/Makefile           |   2 +-
 mm/pkram_pagetable.c  | 169 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 185 insertions(+), 1 deletion(-)
 create mode 100644 mm/pkram_pagetable.c

diff --git a/include/linux/pkram.h b/include/linux/pkram.h
index a58dd2ea835a..b6fa973d37cc 100644
--- a/include/linux/pkram.h
+++ b/include/linux/pkram.h
@@ -25,6 +25,21 @@ struct pkram_stream {
 
 #define PKRAM_NAME_MAX		256	/* including nul */
 
+struct pkram_pg_state {
+	int (*range_cb)(struct pkram_pg_state *state, unsigned long base,
+			unsigned long size);
+	unsigned long curr_addr;
+	unsigned long end_addr;
+	unsigned long min_addr;
+	unsigned long max_addr;
+	unsigned long min_size;
+	bool tracking;
+	bool find_holes;
+	unsigned long retval;
+};
+
+void pkram_walk_pgt_rev(struct pkram_pg_state *st, pgd_t *pgd);
+
 int pkram_prepare_save(struct pkram_stream *ps, const char *name,
 		       gfp_t gfp_mask);
 int pkram_prepare_save_obj(struct pkram_stream *ps);
diff --git a/mm/Makefile b/mm/Makefile
index 59cd381194af..c4ad1c56e237 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -112,4 +112,4 @@ obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
 obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
 obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
-obj-$(CONFIG_PKRAM) += pkram.o
+obj-$(CONFIG_PKRAM) += pkram.o pkram_pagetable.o
diff --git a/mm/pkram_pagetable.c b/mm/pkram_pagetable.c
new file mode 100644
index 000000000000..d31aa36207ba
--- /dev/null
+++ b/mm/pkram_pagetable.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bitops.h>
+#include <asm/pgtable.h>
+#include <linux/pkram.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)
+{
+	unsigned long curr_addr = st->curr_addr;
+	bool track_page = present ^ st->find_holes;
+
+	if (!st->tracking && track_page) {
+		unsigned long end_addr = curr_addr + curr_size;
+
+		if (end_addr <= st->min_addr)
+			return 1;
+
+		st->end_addr = min(end_addr, st->max_addr);
+		st->tracking = true;
+	} else if (st->tracking) {
+		unsigned long base, size;
+
+		/* Continue tracking if lower bound has not been reached */
+		if (track_page && curr_addr && curr_addr >= st->min_addr)
+			return 0;
+
+		if (!track_page)
+			base = max(curr_addr + curr_size, st->min_addr);
+		else
+			base = st->min_addr;
+
+		size = st->end_addr - base;
+		st->tracking = false;
+
+		return st->range_cb(st, base, size);
+	}
+
+	return 0;
+}
+
+static int walk_pte_level_rev(struct pkram_pg_state *st, pmd_t addr, unsigned long P)
+{
+	unsigned long *bitmap;
+	int present;
+	int i, ret;
+
+	bitmap = __va(pmd_val(addr));
+	for (i = PTRS_PER_PTE - 1; i >= 0; i--) {
+		unsigned long curr_addr = P + i * PAGE_SIZE;
+
+		if (curr_addr >= st->max_addr)
+			continue;
+		st->curr_addr = curr_addr;
+
+		present = test_bit(i, bitmap);
+		ret = note_page_rev(st, PAGE_SIZE, present);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int walk_pmd_level_rev(struct pkram_pg_state *st, pud_t addr, unsigned long P)
+{
+	pmd_t *start;
+	int i, ret;
+
+	start = (pmd_t *)pud_page_vaddr(addr) + PTRS_PER_PMD - 1;
+	for (i = PTRS_PER_PMD - 1; i >= 0; i--, start--) {
+		unsigned long curr_addr = P + i * PMD_SIZE;
+
+		if (curr_addr >= st->max_addr)
+			continue;
+		st->curr_addr = curr_addr;
+
+		if (!pmd_none(*start)) {
+			if (pmd_large(*start))
+				ret = note_page_rev(st, PMD_SIZE, true);
+			else
+				ret = walk_pte_level_rev(st, *start, curr_addr);
+		} else
+			ret = note_page_rev(st, PMD_SIZE, false);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int walk_pud_level_rev(struct pkram_pg_state *st, p4d_t addr, unsigned long P)
+{
+	pud_t *start;
+	int i, ret;
+
+	start = (pud_t *)p4d_page_vaddr(addr) + PTRS_PER_PUD - 1;
+	for (i = PTRS_PER_PUD - 1; i >= 0 ; i--, start--) {
+		unsigned long curr_addr = P + i * PUD_SIZE;
+
+		if (curr_addr >= st->max_addr)
+			continue;
+		st->curr_addr = curr_addr;
+
+		if (!pud_none(*start)) {
+			if (pud_large(*start))
+				ret = note_page_rev(st, PUD_SIZE, true);
+			else
+				ret = walk_pmd_level_rev(st, *start, curr_addr);
+		} else
+			ret = note_page_rev(st, PUD_SIZE, false);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int walk_p4d_level_rev(struct pkram_pg_state *st, pgd_t addr, unsigned long P)
+{
+	p4d_t *start;
+	int i, ret;
+
+	if (PTRS_PER_P4D == 1)
+		return walk_pud_level_rev(st, __p4d(pgd_val(addr)), P);
+
+	start = (p4d_t *)pgd_page_vaddr(addr) + PTRS_PER_P4D - 1;
+	for (i = PTRS_PER_P4D - 1; i >= 0; i--, start--) {
+		unsigned long curr_addr = P + i * P4D_SIZE;
+
+		if (curr_addr >= st->max_addr)
+			continue;
+		st->curr_addr = curr_addr;
+
+		if (!p4d_none(*start)) {
+			if (p4d_large(*start))
+				ret = note_page_rev(st, P4D_SIZE, true);
+			else
+				ret = walk_pud_level_rev(st, *start, curr_addr);
+		} else
+			ret = note_page_rev(st, P4D_SIZE, false);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+void pkram_walk_pgt_rev(struct pkram_pg_state *st, pgd_t *pgd)
+{
+	pgd_t *start;
+	int i, ret;
+
+	start = pgd + PTRS_PER_PGD - 1;
+	for (i = PTRS_PER_PGD - 1; i >= 0; i--, start--) {
+		unsigned long curr_addr = i * PGDIR_SIZE;
+
+		if (curr_addr >= st->max_addr)
+			continue;
+		st->curr_addr = curr_addr;
+
+		if (!pgd_none(*start))
+			ret = walk_p4d_level_rev(st, *start, curr_addr);
+		else
+			ret = note_page_rev(st, PGDIR_SIZE, false);
+		if (ret)
+			break;
+	}
+}
-- 
2.13.3


  parent reply	other threads:[~2020-05-07  0:46 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 ` Anthony Yznaga [this message]
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=1588812129-8596-11-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 10/43] PKRAM: add code for walking the preserved pages pagetable' \
    /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).