From: Arun KS <arunks@codeaurora.org>
To: kys@microsoft.com, haiyangz@microsoft.com,
sthemmin@microsoft.com, boris.ostrovsky@oracle.com,
jgross@suse.com, akpm@linux-foundation.org,
dan.j.williams@intel.com, mhocko@suse.com, vbabka@suse.cz,
iamjoonsoo.kim@lge.com, gregkh@linuxfoundation.org,
osalvador@suse.de, malat@debian.org,
kirill.shutemov@linux.intel.com, jrdr.linux@gmail.com,
yasu.isimatu@gmail.com, mgorman@techsingularity.net,
aaron.lu@intel.com, devel@linuxdriverproject.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
xen-devel@lists.xenproject.org
Cc: vatsa@codeaurora.org, vinmenon@codeaurora.org,
getarunks@gmail.com, Arun KS <arunks@codeaurora.org>
Subject: [PATCH v5 1/2] memory_hotplug: Free pages as higher order
Date: Fri, 5 Oct 2018 13:40:05 +0530 [thread overview]
Message-ID: <1538727006-5727-1-git-send-email-arunks@codeaurora.org> (raw)
When free pages are done with higher order, time spend on
coalescing pages by buddy allocator can be reduced. With
section size of 256MB, hot add latency of a single section
shows improvement from 50-60 ms to less than 1 ms, hence
improving the hot add latency by 60%. Modify external
providers of online callback to align with the change.
Signed-off-by: Arun KS <arunks@codeaurora.org>
---
Changes since v4:
- As suggested by Michal Hocko,
- Simplify logic in online_pages_block() by using get_order().
- Seperate out removal of prefetch from __free_pages_core().
Changes since v3:
- Renamed _free_pages_boot_core -> __free_pages_core.
- Removed prefetch from __free_pages_core.
- Removed xen_online_page().
Changes since v2:
- Reuse code from __free_pages_boot_core().
Changes since v1:
- Removed prefetch().
Changes since RFC:
- Rebase.
- As suggested by Michal Hocko remove pages_per_block.
- Modifed external providers of online_page_callback.
v4: https://lore.kernel.org/patchwork/patch/995111/
v3: https://lore.kernel.org/patchwork/patch/992348/
v2: https://lore.kernel.org/patchwork/patch/991363/
v1: https://lore.kernel.org/patchwork/patch/989445/
RFC: https://lore.kernel.org/patchwork/patch/984754/
---
drivers/hv/hv_balloon.c | 6 ++++--
drivers/xen/balloon.c | 23 +++++++++++++++--------
include/linux/memory_hotplug.h | 2 +-
mm/internal.h | 1 +
mm/memory_hotplug.c | 42 ++++++++++++++++++++++++++++++------------
mm/page_alloc.c | 8 ++++----
6 files changed, 55 insertions(+), 27 deletions(-)
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b1b7880..c5bc0b5 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -771,7 +771,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
}
}
-static void hv_online_page(struct page *pg)
+static int hv_online_page(struct page *pg, unsigned int order)
{
struct hv_hotadd_state *has;
unsigned long flags;
@@ -783,10 +783,12 @@ static void hv_online_page(struct page *pg)
if ((pfn < has->start_pfn) || (pfn >= has->end_pfn))
continue;
- hv_page_online_one(has, pg);
+ hv_bring_pgs_online(has, pfn, (1UL << order));
break;
}
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
+
+ return 0;
}
static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index e12bb25..58ddf48 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -390,8 +390,8 @@ static enum bp_state reserve_additional_memory(void)
/*
* add_memory_resource() will call online_pages() which in its turn
- * will call xen_online_page() callback causing deadlock if we don't
- * release balloon_mutex here. Unlocking here is safe because the
+ * will call xen_bring_pgs_online() callback causing deadlock if we
+ * don't release balloon_mutex here. Unlocking here is safe because the
* callers drop the mutex before trying again.
*/
mutex_unlock(&balloon_mutex);
@@ -411,15 +411,22 @@ static enum bp_state reserve_additional_memory(void)
return BP_ECANCELED;
}
-static void xen_online_page(struct page *page)
+static int xen_bring_pgs_online(struct page *pg, unsigned int order)
{
- __online_page_set_limits(page);
+ unsigned long i, size = (1 << order);
+ unsigned long start_pfn = page_to_pfn(pg);
+ struct page *p;
+ pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn);
mutex_lock(&balloon_mutex);
-
- __balloon_append(page);
-
+ for (i = 0; i < size; i++) {
+ p = pfn_to_page(start_pfn + i);
+ __online_page_set_limits(p);
+ __balloon_append(p);
+ }
mutex_unlock(&balloon_mutex);
+
+ return 0;
}
static int xen_memory_notifier(struct notifier_block *nb, unsigned long val, void *v)
@@ -744,7 +751,7 @@ static int __init balloon_init(void)
balloon_stats.max_retry_count = RETRY_UNLIMITED;
#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
- set_online_page_callback(&xen_online_page);
+ set_online_page_callback(&xen_bring_pgs_online);
register_memory_notifier(&xen_memory_nb);
register_sysctl_table(xen_root);
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 34a2822..7b04c1d 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -87,7 +87,7 @@ extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
unsigned long *valid_start, unsigned long *valid_end);
extern void __offline_isolated_pages(unsigned long, unsigned long);
-typedef void (*online_page_callback_t)(struct page *page);
+typedef int (*online_page_callback_t)(struct page *page, unsigned int order);
extern int set_online_page_callback(online_page_callback_t callback);
extern int restore_online_page_callback(online_page_callback_t callback);
diff --git a/mm/internal.h b/mm/internal.h
index 87256ae..636679c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -163,6 +163,7 @@ static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
extern int __isolate_free_page(struct page *page, unsigned int order);
extern void __free_pages_bootmem(struct page *page, unsigned long pfn,
unsigned int order);
+extern void __free_pages_core(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned int order);
extern void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 38d94b7..e379e85 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -47,7 +47,7 @@
* and restore_online_page_callback() for generic callback restore.
*/
-static void generic_online_page(struct page *page);
+static int generic_online_page(struct page *page, unsigned int order);
static online_page_callback_t online_page_callback = generic_online_page;
static DEFINE_MUTEX(online_page_callback_lock);
@@ -655,26 +655,44 @@ void __online_page_free(struct page *page)
}
EXPORT_SYMBOL_GPL(__online_page_free);
-static void generic_online_page(struct page *page)
+static int generic_online_page(struct page *page, unsigned int order)
{
- __online_page_set_limits(page);
- __online_page_increment_counters(page);
- __online_page_free(page);
+ __free_pages_core(page, order);
+ totalram_pages += (1UL << order);
+#ifdef CONFIG_HIGHMEM
+ if (PageHighMem(page))
+ totalhigh_pages += (1UL << order);
+#endif
+ return 0;
+}
+
+static int online_pages_blocks(unsigned long start, unsigned long nr_pages)
+{
+ unsigned long end = start + nr_pages;
+ int order, ret, onlined_pages = 0;
+
+ while (start < end) {
+ order = min(MAX_ORDER - 1,
+ get_order(PFN_PHYS(end) - PFN_PHYS(start)));
+
+ ret = (*online_page_callback)(pfn_to_page(start), order);
+ if (!ret)
+ onlined_pages += (1UL << order);
+ else if (ret > 0)
+ onlined_pages += ret;
+
+ start += (1UL << order);
+ }
+ return onlined_pages;
}
static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
void *arg)
{
- unsigned long i;
unsigned long onlined_pages = *(unsigned long *)arg;
- struct page *page;
if (PageReserved(pfn_to_page(start_pfn)))
- for (i = 0; i < nr_pages; i++) {
- page = pfn_to_page(start_pfn + i);
- (*online_page_callback)(page);
- onlined_pages++;
- }
+ onlined_pages = online_pages_blocks(start_pfn, nr_pages);
online_mem_sections(start_pfn, start_pfn + nr_pages);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 89d2a2a..7ab5274 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1252,7 +1252,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
local_irq_restore(flags);
}
-static void __init __free_pages_boot_core(struct page *page, unsigned int order)
+void __free_pages_core(struct page *page, unsigned int order)
{
unsigned int nr_pages = 1 << order;
struct page *p = page;
@@ -1331,7 +1331,7 @@ void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
{
if (early_page_uninitialised(pfn))
return;
- return __free_pages_boot_core(page, order);
+ return __free_pages_core(page, order);
}
/*
@@ -1421,14 +1421,14 @@ static void __init deferred_free_range(unsigned long pfn,
if (nr_pages == pageblock_nr_pages &&
(pfn & (pageblock_nr_pages - 1)) == 0) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- __free_pages_boot_core(page, pageblock_order);
+ __free_pages_core(page, pageblock_order);
return;
}
for (i = 0; i < nr_pages; i++, page++, pfn++) {
if ((pfn & (pageblock_nr_pages - 1)) == 0)
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- __free_pages_boot_core(page, 0);
+ __free_pages_core(page, 0);
}
}
--
1.9.1
next reply other threads:[~2018-10-05 8:10 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-05 8:10 Arun KS [this message]
2018-10-05 8:10 ` [PATCH v5 2/2] mm/page_alloc: remove software prefetching in __free_pages_core Arun KS
2018-10-09 9:30 ` Michal Hocko
2018-10-10 16:36 ` Vlastimil Babka
2018-10-08 7:34 ` [PATCH v5 1/2] memory_hotplug: Free pages as higher order Oscar Salvador
2018-10-09 9:29 ` Michal Hocko
2018-10-09 9:54 ` Arun KS
2018-10-09 11:06 ` Michal Hocko
2018-10-10 8:07 ` Oscar Salvador
2018-10-10 10:51 ` Arun KS
2018-10-10 11:01 ` Oscar Salvador
2018-10-10 15:30 ` Vlastimil Babka
2018-10-10 16:56 ` Arun KS
2018-10-10 17:33 ` Michal Hocko
2018-10-11 2:29 ` Arun KS
2018-10-11 7:55 ` Michal Hocko
2018-10-19 2:18 ` Andrew Morton
2018-10-19 8:07 ` Michal Hocko
2018-10-22 10:33 ` Arun KS
2018-11-05 9:42 ` Arun KS
2018-11-05 21:44 ` Andrew Morton
2018-11-06 5:31 ` Arun KS
2018-10-11 8:07 ` Vlastimil Babka
2018-10-11 8:15 ` Michal Hocko
2018-11-19 22:15 ` Wei Yang
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=1538727006-5727-1-git-send-email-arunks@codeaurora.org \
--to=arunks@codeaurora.org \
--cc=aaron.lu@intel.com \
--cc=akpm@linux-foundation.org \
--cc=boris.ostrovsky@oracle.com \
--cc=dan.j.williams@intel.com \
--cc=devel@linuxdriverproject.org \
--cc=getarunks@gmail.com \
--cc=gregkh@linuxfoundation.org \
--cc=haiyangz@microsoft.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=jgross@suse.com \
--cc=jrdr.linux@gmail.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kys@microsoft.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=malat@debian.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@suse.com \
--cc=osalvador@suse.de \
--cc=sthemmin@microsoft.com \
--cc=vatsa@codeaurora.org \
--cc=vbabka@suse.cz \
--cc=vinmenon@codeaurora.org \
--cc=xen-devel@lists.xenproject.org \
--cc=yasu.isimatu@gmail.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).