Re: [PATCH v4] memory_hotplug: Free pages as higher order

2018-10-05 Thread Arun KS 

On 2018-10-04 20:21, Michal Hocko wrote:

On Wed 03-10-18 19:09:39, Arun KS wrote:
[...]
+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 - 1UL, __ffs(start));
+
+   while (start + (1UL << order) > end)
+   order--;


this really made me scratch my head. Wouldn't it be much simpler to do
the following?
order = min(MAX_ORDER - 1, get_order(end - start))?


Yes. Much better. Will change to,

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 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;
unsigned int loop;

-   prefetchw(p);
-   for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
-   prefetchw(p + 1);
+   for (loop = 0; loop < nr_pages; loop++, p++) {
__ClearPageReserved(p);
set_page_count(p, 0);
}
-   __ClearPageReserved(p);
-   set_page_count(p, 0);

page_zone(page)->managed_pages += nr_pages;
set_page_refcounted(page);


I think this is wort a separate patch as it is unrelated to the patch.

Sure. Will split the patch.

Regards,
Arun
___
devel mailing list
de...@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel

Re: [PATCH v4] memory_hotplug: Free pages as higher order

2018-10-04 Thread Michal Hocko 
On Wed 03-10-18 19:09:39, Arun KS wrote:
[...]
> +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 - 1UL, __ffs(start));
> +
> + while (start + (1UL << order) > end)
> + order--;

this really made me scratch my head. Wouldn't it be much simpler to do
the following?
order = min(MAX_ORDER - 1, get_order(end - 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 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;
>   unsigned int loop;
>  
> - prefetchw(p);
> - for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
> - prefetchw(p + 1);
> + for (loop = 0; loop < nr_pages; loop++, p++) {
>   __ClearPageReserved(p);
>   set_page_count(p, 0);
>   }
> - __ClearPageReserved(p);
> - set_page_count(p, 0);
>  
>   page_zone(page)->managed_pages += nr_pages;
>   set_page_refcounted(page);

I think this is wort a separate patch as it is unrelated to the patch.

-- 
Michal Hocko
SUSE Labs
___
devel mailing list
de...@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel

[PATCH v4] memory_hotplug: Free pages as higher order

2018-10-03 Thread Arun KS 
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.
Also remove prefetch from __free_pages_core().

Signed-off-by: Arun KS 
---
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.

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| 44 ++
 mm/page_alloc.c| 14 +-
 6 files changed, 58 insertions(+), 32 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(_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(_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(_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(_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(_online_page);
+   set_online_page_callback(_bring_pgs_online);
register_memory_notifier(_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
+++