| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20190617222156.v6eaujbdrmkz35wr@master>
Date: Mon, 17 Jun 2019 22:21:56 +0000
From: Wei Yang <richard.weiyang@...il.com>
To: Dan Williams <dan.j.williams@...el.com>
Cc: akpm@...ux-foundation.org, Michal Hocko <mhocko@...e.com>,
Vlastimil Babka <vbabka@...e.cz>,
Logan Gunthorpe <logang@...tatee.com>,
Oscar Salvador <osalvador@...e.de>,
Pavel Tatashin <pasha.tatashin@...een.com>,
Jane Chu <jane.chu@...cle.com>, linux-mm@...ck.org,
linux-nvdimm@...ts.01.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v9 02/12] mm/sparsemem: Add helpers track active portions
of a section at boot
On Wed, Jun 05, 2019 at 02:57:59PM -0700, Dan Williams wrote:
>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@...e.com>
>Cc: Vlastimil Babka <vbabka@...e.cz>
>Cc: Logan Gunthorpe <logang@...tatee.com>
>Cc: Oscar Salvador <osalvador@...e.de>
>Cc: Pavel Tatashin <pasha.tatashin@...een.com>
>Tested-by: Jane Chu <jane.chu@...cle.com>
>Signed-off-by: Dan Williams <dan.j.williams@...el.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);
>+ }
Just curious about why we set subsection here?
Function free_area_init_nodes() mostly handles pgdat, if I am correct. Setup
subsection here looks like touching some lower level system data structure.
>
> /* 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)
> {
--
Wei Yang
Help you, Help me
Powered by blists - more mailing lists