From: Dan Williams <dan.j.williams@intel.com>
To: akpm@linux-foundation.org
Cc: Michal Hocko <mhocko@suse.com>, Vlastimil Babka <vbabka@suse.cz>,
Logan Gunthorpe <logang@deltatee.com>,
Oscar Salvador <osalvador@suse.de>,
Pavel Tatashin <pasha.tatashin@soleen.com>,
Jane Chu <jane.chu@oracle.com>,
linux-mm@kvack.org, linux-nvdimm@lists.01.org,
linux-kernel@vger.kernel.org, osalvador@suse.de, mhocko@suse.com
Subject: [PATCH v9 02/12] mm/sparsemem: Add helpers track active portions of a section at boot
Date: Wed, 05 Jun 2019 14:57:59 -0700 [thread overview]
Message-ID: <155977187919.2443951.8925592545929008845.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <155977186863.2443951.9036044808311959913.stgit@dwillia2-desk3.amr.corp.intel.com>
Prepare for hot{plug,remove} of sub-ranges of a section by tracking a
sub-section active bitmask, each bit representing a PMD_SIZE span of the
architecture's memory hotplug section size.
The implications of a partially populated section is that pfn_valid()
needs to go beyond a valid_section() check and read the sub-section
active ranges from the bitmask. The expectation is that the bitmask
(subsection_map) fits in the same cacheline as the valid_section() data,
so the incremental performance overhead to pfn_valid() should be
negligible.
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Tested-by: Jane Chu <jane.chu@oracle.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
include/linux/mmzone.h | 29 ++++++++++++++++++++++++++++-
mm/page_alloc.c | 4 +++-
mm/sparse.c | 35 +++++++++++++++++++++++++++++++++++
3 files changed, 66 insertions(+), 2 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ac163f2f274f..6dd52d544857 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1199,6 +1199,8 @@ struct mem_section_usage {
unsigned long pageblock_flags[0];
};
+void subsection_map_init(unsigned long pfn, unsigned long nr_pages);
+
struct page;
struct page_ext;
struct mem_section {
@@ -1336,12 +1338,36 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
extern int __highest_present_section_nr;
+static inline int subsection_map_index(unsigned long pfn)
+{
+ return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION;
+}
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+ int idx = subsection_map_index(pfn);
+
+ return test_bit(idx, ms->usage->subsection_map);
+}
+#else
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+ return 1;
+}
+#endif
+
#ifndef CONFIG_HAVE_ARCH_PFN_VALID
static inline int pfn_valid(unsigned long pfn)
{
+ struct mem_section *ms;
+
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
- return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
+ ms = __nr_to_section(pfn_to_section_nr(pfn));
+ if (!valid_section(ms))
+ return 0;
+ return pfn_section_valid(ms, pfn);
}
#endif
@@ -1373,6 +1399,7 @@ void sparse_init(void);
#define sparse_init() do {} while (0)
#define sparse_index_init(_sec, _nid) do {} while (0)
#define pfn_present pfn_valid
+#define subsection_map_init(_pfn, _nr_pages) do {} while (0)
#endif /* CONFIG_SPARSEMEM */
/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c6d8224d792e..bd773efe5b82 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7292,10 +7292,12 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
/* Print out the early node map */
pr_info("Early memory node ranges\n");
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid,
(u64)start_pfn << PAGE_SHIFT,
((u64)end_pfn << PAGE_SHIFT) - 1);
+ subsection_map_init(start_pfn, end_pfn - start_pfn);
+ }
/* Initialise every node */
mminit_verify_pageflags_layout();
diff --git a/mm/sparse.c b/mm/sparse.c
index 71da15cc7432..0baa2e55cfdd 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -210,6 +210,41 @@ static inline unsigned long first_present_section_nr(void)
return next_present_section_nr(-1);
}
+void subsection_mask_set(unsigned long *map, unsigned long pfn,
+ unsigned long nr_pages)
+{
+ int idx = subsection_map_index(pfn);
+ int end = subsection_map_index(pfn + nr_pages - 1);
+
+ bitmap_set(map, idx, end - idx + 1);
+}
+
+void subsection_map_init(unsigned long pfn, unsigned long nr_pages)
+{
+ int end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+ int i, start_sec = pfn_to_section_nr(pfn);
+
+ if (!nr_pages)
+ return;
+
+ for (i = start_sec; i <= end_sec; i++) {
+ struct mem_section *ms;
+ unsigned long pfns;
+
+ pfns = min(nr_pages, PAGES_PER_SECTION
+ - (pfn & ~PAGE_SECTION_MASK));
+ ms = __nr_to_section(i);
+ subsection_mask_set(ms->usage->subsection_map, pfn, pfns);
+
+ pr_debug("%s: sec: %d pfns: %ld set(%d, %d)\n", __func__, i,
+ pfns, subsection_map_index(pfn),
+ subsection_map_index(pfn + pfns - 1));
+
+ pfn += pfns;
+ nr_pages -= pfns;
+ }
+}
+
/* Record a memory area against a node. */
void __init memory_present(int nid, unsigned long start, unsigned long end)
{
next prev parent reply other threads:[~2019-06-05 22:12 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-05 21:57 [PATCH v9 00/12] mm: Sub-section memory hotplug support Dan Williams
2019-06-05 21:57 ` [PATCH v9 01/12] mm/sparsemem: Introduce struct mem_section_usage Dan Williams
2019-06-06 17:34 ` Oscar Salvador
2019-06-16 13:11 ` Wei Yang
2019-06-18 21:56 ` Dan Williams
2019-06-19 2:13 ` Wei Yang
2019-06-05 21:57 ` Dan Williams [this message]
2019-06-06 16:55 ` [PATCH v9 02/12] mm/sparsemem: Add helpers track active portions of a section at boot Oscar Salvador
2019-06-17 22:21 ` Wei Yang
2019-06-17 22:32 ` Dan Williams
2019-06-18 1:03 ` Wei Yang
2019-06-19 3:15 ` Dan Williams
2019-06-05 21:58 ` [PATCH v9 03/12] mm/hotplug: Prepare shrink_{zone, pgdat}_span for sub-section removal Dan Williams
2019-06-18 1:42 ` Wei Yang
2019-06-19 3:40 ` Dan Williams
2019-06-05 21:58 ` [PATCH v9 04/12] mm/sparsemem: Convert kmalloc_section_memmap() to populate_section_memmap() Dan Williams
2019-06-06 17:02 ` Oscar Salvador
2019-06-16 6:06 ` Aneesh Kumar K.V
2019-06-05 21:58 ` [PATCH v9 05/12] mm/hotplug: Kill is_dev_zone() usage in __remove_pages() Dan Williams
2019-06-05 21:58 ` [PATCH v9 06/12] mm: Kill is_dev_zone() helper Dan Williams
2019-06-18 3:35 ` Wei Yang
2019-06-05 21:58 ` [PATCH v9 07/12] mm/sparsemem: Prepare for sub-section ranges Dan Williams
2019-06-06 17:21 ` Oscar Salvador
2019-06-06 18:16 ` Dan Williams
2019-06-14 8:39 ` David Hildenbrand
2019-06-05 21:58 ` [PATCH v9 08/12] mm/sparsemem: Support sub-section hotplug Dan Williams
2019-06-07 8:33 ` Oscar Salvador
2019-06-07 15:38 ` Dan Williams
2019-06-07 21:41 ` Oscar Salvador
2019-06-05 21:58 ` [PATCH v9 09/12] mm: Document ZONE_DEVICE memory-model implications Dan Williams
2019-06-05 21:58 ` [PATCH v9 10/12] mm/devm_memremap_pages: Enable sub-section remap Dan Williams
2019-06-07 8:56 ` Oscar Salvador
2019-06-16 7:49 ` Aneesh Kumar K.V
2019-06-05 21:58 ` [PATCH v9 11/12] libnvdimm/pfn: Fix fsdax-mode namespace info-block zero-fields Dan Williams
2019-06-06 21:46 ` Andrew Morton
2019-06-06 22:06 ` Dan Williams
2019-06-07 19:54 ` Andrew Morton
2019-06-07 20:09 ` Dan Williams
2019-06-12 9:41 ` Aneesh Kumar K.V
2019-06-05 21:59 ` [PATCH v9 12/12] libnvdimm/pfn: Stop padding pmem namespaces to section alignment Dan Williams
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=155977187919.2443951.8925592545929008845.stgit@dwillia2-desk3.amr.corp.intel.com \
--to=dan.j.williams@intel.com \
--cc=akpm@linux-foundation.org \
--cc=jane.chu@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvdimm@lists.01.org \
--cc=logang@deltatee.com \
--cc=mhocko@suse.com \
--cc=osalvador@suse.de \
--cc=pasha.tatashin@soleen.com \
--cc=vbabka@suse.cz \
/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).