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>,
linux-mm@kvack.org, linux-nvdimm@lists.01.org,
linux-kernel@vger.kernel.org
Subject: [PATCH v10 08/13] mm/sparsemem: Prepare for sub-section ranges
Date: Tue, 18 Jun 2019 22:52:17 -0700 [thread overview]
Message-ID: <156092353780.979959.9713046515562743194.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <156092349300.979959.17603710711957735135.stgit@dwillia2-desk3.amr.corp.intel.com>
Prepare the memory hot-{add,remove} paths for handling sub-section
ranges by plumbing the starting page frame and number of pages being
handled through arch_{add,remove}_memory() to
sparse_{add,remove}_one_section().
This is simply plumbing, small cleanups, and some identifier renames. No
intended functional changes.
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
include/linux/memory_hotplug.h | 5 +-
mm/memory_hotplug.c | 114 +++++++++++++++++++++++++---------------
mm/sparse.c | 16 ++----
3 files changed, 81 insertions(+), 54 deletions(-)
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 79e0add6a597..3ab0282b4fe5 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -348,9 +348,10 @@ extern int add_memory_resource(int nid, struct resource *resource);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
extern bool is_memblock_offlined(struct memory_block *mem);
-extern int sparse_add_one_section(int nid, unsigned long start_pfn,
- struct vmem_altmap *altmap);
+extern int sparse_add_section(int nid, unsigned long pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap);
extern void sparse_remove_one_section(struct mem_section *ms,
+ unsigned long pfn, unsigned long nr_pages,
unsigned long map_offset, struct vmem_altmap *altmap);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 4b882c57781a..399bf78bccc5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -252,51 +252,84 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
}
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
-static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
- struct vmem_altmap *altmap)
+static int __meminit __add_section(int nid, unsigned long pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap)
{
int ret;
- if (pfn_valid(phys_start_pfn))
+ if (pfn_valid(pfn))
return -EEXIST;
- ret = sparse_add_one_section(nid, phys_start_pfn, altmap);
+ ret = sparse_add_section(nid, pfn, nr_pages, altmap);
return ret < 0 ? ret : 0;
}
+static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
+ const char *reason)
+{
+ /*
+ * Disallow all operations smaller than a sub-section and only
+ * allow operations smaller than a section for
+ * SPARSEMEM_VMEMMAP. Note that check_hotplug_memory_range()
+ * enforces a larger memory_block_size_bytes() granularity for
+ * memory that will be marked online, so this check should only
+ * fire for direct arch_{add,remove}_memory() users outside of
+ * add_memory_resource().
+ */
+ unsigned long min_align;
+
+ if (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
+ min_align = PAGES_PER_SUBSECTION;
+ else
+ min_align = PAGES_PER_SECTION;
+ if (!IS_ALIGNED(pfn, min_align)
+ || !IS_ALIGNED(nr_pages, min_align)) {
+ WARN(1, "Misaligned __%s_pages start: %#lx end: #%lx\n",
+ reason, pfn, pfn + nr_pages - 1);
+ return -EINVAL;
+ }
+ return 0;
+}
+
/*
* Reasonably generic function for adding memory. It is
* expected that archs that support memory hotplug will
* call this function after deciding the zone to which to
* add the new pages.
*/
-int __ref __add_pages(int nid, unsigned long phys_start_pfn,
- unsigned long nr_pages, struct mhp_restrictions *restrictions)
+int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
+ struct mhp_restrictions *restrictions)
{
unsigned long i;
- int err = 0;
- int start_sec, end_sec;
+ int start_sec, end_sec, err;
struct vmem_altmap *altmap = restrictions->altmap;
- /* during initialize mem_map, align hot-added range to section */
- start_sec = pfn_to_section_nr(phys_start_pfn);
- end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
-
if (altmap) {
/*
* Validate altmap is within bounds of the total request
*/
- if (altmap->base_pfn != phys_start_pfn
+ if (altmap->base_pfn != pfn
|| vmem_altmap_offset(altmap) > nr_pages) {
pr_warn_once("memory add fail, invalid altmap\n");
- err = -EINVAL;
- goto out;
+ return -EINVAL;
}
altmap->alloc = 0;
}
+ err = check_pfn_span(pfn, nr_pages, "add");
+ if (err)
+ return err;
+
+ start_sec = pfn_to_section_nr(pfn);
+ end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
for (i = start_sec; i <= end_sec; i++) {
- err = __add_section(nid, section_nr_to_pfn(i), altmap);
+ unsigned long pfns;
+
+ pfns = min(nr_pages, PAGES_PER_SECTION
+ - (pfn & ~PAGE_SECTION_MASK));
+ err = __add_section(nid, pfn, pfns, altmap);
+ pfn += pfns;
+ nr_pages -= pfns;
/*
* EEXIST is finally dealt with by ioresource collision
@@ -309,7 +342,6 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn,
cond_resched();
}
vmemmap_populate_print_last();
-out:
return err;
}
@@ -487,10 +519,10 @@ static void shrink_pgdat_span(struct pglist_data *pgdat,
pgdat->node_spanned_pages = 0;
}
-static void __remove_zone(struct zone *zone, unsigned long start_pfn)
+static void __remove_zone(struct zone *zone, unsigned long start_pfn,
+ unsigned long nr_pages)
{
struct pglist_data *pgdat = zone->zone_pgdat;
- int nr_pages = PAGES_PER_SECTION;
unsigned long flags;
pgdat_resize_lock(zone->zone_pgdat, &flags);
@@ -499,27 +531,23 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn)
pgdat_resize_unlock(zone->zone_pgdat, &flags);
}
-static void __remove_section(struct zone *zone, struct mem_section *ms,
- unsigned long map_offset,
- struct vmem_altmap *altmap)
+static void __remove_section(struct zone *zone, unsigned long pfn,
+ unsigned long nr_pages, unsigned long map_offset,
+ struct vmem_altmap *altmap)
{
- unsigned long start_pfn;
- int scn_nr;
+ struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
if (WARN_ON_ONCE(!valid_section(ms)))
return;
- scn_nr = __section_nr(ms);
- start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
- __remove_zone(zone, start_pfn);
-
- sparse_remove_one_section(ms, map_offset, altmap);
+ __remove_zone(zone, pfn, nr_pages);
+ sparse_remove_one_section(ms, pfn, nr_pages, map_offset, altmap);
}
/**
* __remove_pages() - remove sections of pages from a zone
* @zone: zone from which pages need to be removed
- * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
+ * @pfn: starting pageframe (must be aligned to start of a section)
* @nr_pages: number of pages to remove (must be multiple of section size)
* @altmap: alternative device page map or %NULL if default memmap is used
*
@@ -528,31 +556,31 @@ static void __remove_section(struct zone *zone, struct mem_section *ms,
* sure that pages are marked reserved and zones are adjust properly by
* calling offline_pages().
*/
-void __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
+void __remove_pages(struct zone *zone, unsigned long pfn,
unsigned long nr_pages, struct vmem_altmap *altmap)
{
- unsigned long i;
unsigned long map_offset = 0;
- int sections_to_remove;
+ int i, start_sec, end_sec;
if (altmap)
map_offset = vmem_altmap_offset(altmap);
clear_zone_contiguous(zone);
- /*
- * We can only remove entire sections
- */
- BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
- BUG_ON(nr_pages % PAGES_PER_SECTION);
+ if (check_pfn_span(pfn, nr_pages, "remove"))
+ return;
- sections_to_remove = nr_pages / PAGES_PER_SECTION;
- for (i = 0; i < sections_to_remove; i++) {
- unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+ start_sec = pfn_to_section_nr(pfn);
+ end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+ for (i = start_sec; i <= end_sec; i++) {
+ unsigned long pfns;
cond_resched();
- __remove_section(zone, __pfn_to_section(pfn), map_offset,
- altmap);
+ pfns = min(nr_pages, PAGES_PER_SECTION
+ - (pfn & ~PAGE_SECTION_MASK));
+ __remove_section(zone, pfn, pfns, map_offset, altmap);
+ pfn += pfns;
+ nr_pages -= pfns;
map_offset = 0;
}
diff --git a/mm/sparse.c b/mm/sparse.c
index 49f0c03d15a3..ad47e25c8f94 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -728,8 +728,8 @@ static void free_map_bootmem(struct page *memmap)
* * -EEXIST - Section has been present.
* * -ENOMEM - Out of memory.
*/
-int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
- struct vmem_altmap *altmap)
+int __meminit sparse_add_section(int nid, unsigned long start_pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap)
{
unsigned long section_nr = pfn_to_section_nr(start_pfn);
struct mem_section_usage *usage;
@@ -834,8 +834,9 @@ static void free_section_usage(struct mem_section *ms, struct page *memmap,
free_map_bootmem(memmap);
}
-void sparse_remove_one_section(struct mem_section *ms, unsigned long map_offset,
- struct vmem_altmap *altmap)
+void sparse_remove_one_section(struct mem_section *ms, unsigned long pfn,
+ unsigned long nr_pages, unsigned long map_offset,
+ struct vmem_altmap *altmap)
{
struct page *memmap = NULL;
struct mem_section_usage *usage = NULL;
@@ -848,10 +849,7 @@ void sparse_remove_one_section(struct mem_section *ms, unsigned long map_offset,
ms->usage = NULL;
}
- clear_hwpoisoned_pages(memmap + map_offset,
- PAGES_PER_SECTION - map_offset);
- free_section_usage(ms, memmap, usage,
- section_nr_to_pfn(__section_nr(ms)),
- PAGES_PER_SECTION, altmap);
+ clear_hwpoisoned_pages(memmap + map_offset, nr_pages - map_offset);
+ free_section_usage(ms, memmap, usage, pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
next prev parent reply other threads:[~2019-06-19 6:06 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-19 5:51 [PATCH v10 00/13] mm: Sub-section memory hotplug support Dan Williams
2019-06-19 5:51 ` [PATCH v10 01/13] mm/sparsemem: Introduce struct mem_section_usage Dan Williams
2019-06-19 5:51 ` [PATCH v10 02/13] mm/sparsemem: Introduce a SECTION_IS_EARLY flag Dan Williams
2019-06-24 17:54 ` Oscar Salvador
2019-06-19 5:51 ` [PATCH v10 03/13] mm/sparsemem: Add helpers track active portions of a section at boot Dan Williams
2019-06-24 17:57 ` Oscar Salvador
2019-06-19 5:51 ` [PATCH v10 04/13] mm/hotplug: Prepare shrink_{zone, pgdat}_span for sub-section removal Dan Williams
2019-06-19 5:52 ` [PATCH v10 05/13] mm/sparsemem: Convert kmalloc_section_memmap() to populate_section_memmap() Dan Williams
2019-06-24 18:00 ` Oscar Salvador
2019-06-19 5:52 ` [PATCH v10 06/13] mm/hotplug: Kill is_dev_zone() usage in __remove_pages() Dan Williams
2019-06-19 5:52 ` [PATCH v10 07/13] mm: Kill is_dev_zone() helper Dan Williams
2019-06-19 5:52 ` Dan Williams [this message]
2019-06-20 10:31 ` [PATCH v10 08/13] mm/sparsemem: Prepare for sub-section ranges David Hildenbrand
2019-06-20 16:19 ` Dan Williams
2019-06-20 16:35 ` David Hildenbrand
2019-06-20 16:56 ` Dan Williams
2019-06-24 18:05 ` Oscar Salvador
2019-06-19 5:52 ` [PATCH v10 09/13] mm/sparsemem: Support sub-section hotplug Dan Williams
2019-06-24 20:45 ` Oscar Salvador
2019-06-19 5:52 ` [PATCH v10 10/13] mm: Document ZONE_DEVICE memory-model implications Dan Williams
2019-06-20 12:30 ` Mike Rapoport
2019-06-19 5:52 ` [PATCH v10 11/13] mm/devm_memremap_pages: Enable sub-section remap Dan Williams
2019-06-19 5:52 ` [PATCH v10 12/13] libnvdimm/pfn: Fix fsdax-mode namespace info-block zero-fields Dan Williams
2019-06-19 16:30 ` Aneesh Kumar K.V
2019-06-19 17:06 ` Dan Williams
2019-06-19 5:52 ` [PATCH v10 13/13] libnvdimm/pfn: Stop padding pmem namespaces to section alignment Dan Williams
2019-06-20 12:30 ` [PATCH v10 00/13] mm: Sub-section memory hotplug support Aneesh Kumar K.V
2019-06-20 16:30 ` Dan Williams
2019-06-20 17:00 ` Oscar Salvador
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=156092353780.979959.9713046515562743194.stgit@dwillia2-desk3.amr.corp.intel.com \
--to=dan.j.williams@intel.com \
--cc=akpm@linux-foundation.org \
--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).