From: Dave Hansen <dave@sr71.net>
To: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org, akpm@linux-foundation.org,
mgorman@suse.de, tim.c.chen@linux.intel.com, minchan@kernel.org,
Dave Hansen <dave@sr71.net>
Subject: [v5][PATCH 2/6] mm: swap: make 'struct page' and swp_entry_t variants of swapcache_free().
Date: Mon, 03 Jun 2013 13:02:05 -0700 [thread overview]
Message-ID: <20130603200205.23A23517@viggo.jf.intel.com> (raw)
In-Reply-To: <20130603200202.7F5FDE07@viggo.jf.intel.com>
From: Dave Hansen <dave.hansen@linux.intel.com>
swapcache_free() takes two arguments:
void swapcache_free(swp_entry_t entry, struct page *page)
Most of its callers (5/7) are from error handling paths haven't
even instantiated a page, so they pass page=NULL. Both of the
callers that call in with a 'struct page' create and pass in a
temporary swp_entry_t.
Now that we are deferring clearing page_private() until after
swapcache_free() has been called, we can just create a variant
that takes a 'struct page' and does the temporary variable in the
helper.
That leaves all the other callers doing
swapcache_free(entry, NULL)
so create another helper for them that makes it clear that they
need only pass in a swp_entry_t.
One downside here is that delete_from_swap_cache() now calls
swap_address_space() via page_mapping() instead of calling
swap_address_space() directly. In doing so, it removes one more
case of the swap cache code being special-cased, which is a good
thing in my book. But it does cost us a function call.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Minchan Kin <minchan@kernel.org>
---
linux.git-davehans/drivers/staging/zcache/zcache-main.c | 2 +-
linux.git-davehans/include/linux/swap.h | 3 ++-
linux.git-davehans/mm/shmem.c | 2 +-
linux.git-davehans/mm/swap_state.c | 15 +++++----------
linux.git-davehans/mm/swapfile.c | 15 ++++++++++++++-
linux.git-davehans/mm/vmscan.c | 5 +----
6 files changed, 24 insertions(+), 18 deletions(-)
diff -puN drivers/staging/zcache/zcache-main.c~make-page-and-swp_entry_t-variants drivers/staging/zcache/zcache-main.c
--- linux.git/drivers/staging/zcache/zcache-main.c~make-page-and-swp_entry_t-variants 2013-06-03 12:41:30.590715114 -0700
+++ linux.git-davehans/drivers/staging/zcache/zcache-main.c 2013-06-03 12:41:30.602715646 -0700
@@ -961,7 +961,7 @@ static int zcache_get_swap_cache_page(in
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
- swapcache_free(entry, NULL);
+ swapcache_free_entry(entry);
/* FIXME: is it possible to get here without err==-ENOMEM?
* If not, we can dispense with the do loop, use goto retry */
} while (err != -ENOMEM);
diff -puN include/linux/swap.h~make-page-and-swp_entry_t-variants include/linux/swap.h
--- linux.git/include/linux/swap.h~make-page-and-swp_entry_t-variants 2013-06-03 12:41:30.591715158 -0700
+++ linux.git-davehans/include/linux/swap.h 2013-06-03 12:41:30.602715646 -0700
@@ -385,7 +385,8 @@ extern void swap_shmem_alloc(swp_entry_t
extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t);
-extern void swapcache_free(swp_entry_t, struct page *page);
+extern void swapcache_free_entry(swp_entry_t entry);
+extern void swapcache_free_page_entry(struct page *page);
extern int free_swap_and_cache(swp_entry_t);
extern int swap_type_of(dev_t, sector_t, struct block_device **);
extern unsigned int count_swap_pages(int, int);
diff -puN mm/shmem.c~make-page-and-swp_entry_t-variants mm/shmem.c
--- linux.git/mm/shmem.c~make-page-and-swp_entry_t-variants 2013-06-03 12:41:30.593715247 -0700
+++ linux.git-davehans/mm/shmem.c 2013-06-03 12:41:30.603715690 -0700
@@ -872,7 +872,7 @@ static int shmem_writepage(struct page *
}
mutex_unlock(&shmem_swaplist_mutex);
- swapcache_free(swap, NULL);
+ swapcache_free_entry(swap);
redirty:
set_page_dirty(page);
if (wbc->for_reclaim)
diff -puN mm/swapfile.c~make-page-and-swp_entry_t-variants mm/swapfile.c
--- linux.git/mm/swapfile.c~make-page-and-swp_entry_t-variants 2013-06-03 12:41:30.595715336 -0700
+++ linux.git-davehans/mm/swapfile.c 2013-06-03 12:41:30.604715734 -0700
@@ -637,7 +637,7 @@ void swap_free(swp_entry_t entry)
/*
* Called after dropping swapcache to decrease refcnt to swap entries.
*/
-void swapcache_free(swp_entry_t entry, struct page *page)
+static void __swapcache_free(swp_entry_t entry, struct page *page)
{
struct swap_info_struct *p;
unsigned char count;
@@ -651,6 +651,19 @@ void swapcache_free(swp_entry_t entry, s
}
}
+void swapcache_free_entry(swp_entry_t entry)
+{
+ __swapcache_free(entry, NULL);
+}
+
+void swapcache_free_page_entry(struct page *page)
+{
+ swp_entry_t entry = { .val = page_private(page) };
+ __swapcache_free(entry, page);
+ set_page_private(page, 0);
+ ClearPageSwapCache(page);
+}
+
/*
* How many references to page are currently swapped out?
* This does not give an exact answer when swap count is continued,
diff -puN mm/swap_state.c~make-page-and-swp_entry_t-variants mm/swap_state.c
--- linux.git/mm/swap_state.c~make-page-and-swp_entry_t-variants 2013-06-03 12:41:30.596715380 -0700
+++ linux.git-davehans/mm/swap_state.c 2013-06-03 12:41:30.605715778 -0700
@@ -174,7 +174,7 @@ int add_to_swap(struct page *page, struc
if (unlikely(PageTransHuge(page)))
if (unlikely(split_huge_page_to_list(page, list))) {
- swapcache_free(entry, NULL);
+ swapcache_free_entry(entry);
return 0;
}
@@ -200,7 +200,7 @@ int add_to_swap(struct page *page, struc
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
- swapcache_free(entry, NULL);
+ swapcache_free_entry(entry);
return 0;
}
}
@@ -213,19 +213,14 @@ int add_to_swap(struct page *page, struc
*/
void delete_from_swap_cache(struct page *page)
{
- swp_entry_t entry;
struct address_space *address_space;
- entry.val = page_private(page);
-
- address_space = swap_address_space(entry);
+ address_space = page_mapping(page);
spin_lock_irq(&address_space->tree_lock);
__delete_from_swap_cache(page);
spin_unlock_irq(&address_space->tree_lock);
- swapcache_free(entry, page);
- set_page_private(page, 0);
- ClearPageSwapCache(page);
+ swapcache_free_page_entry(page);
page_cache_release(page);
}
@@ -370,7 +365,7 @@ struct page *read_swap_cache_async(swp_e
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
- swapcache_free(entry, NULL);
+ swapcache_free_entry(entry);
} while (err != -ENOMEM);
if (new_page)
diff -puN mm/vmscan.c~make-page-and-swp_entry_t-variants mm/vmscan.c
--- linux.git/mm/vmscan.c~make-page-and-swp_entry_t-variants 2013-06-03 12:41:30.598715468 -0700
+++ linux.git-davehans/mm/vmscan.c 2013-06-03 12:41:30.606715822 -0700
@@ -490,12 +490,9 @@ static int __remove_mapping(struct addre
}
if (PageSwapCache(page)) {
- swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
spin_unlock_irq(&mapping->tree_lock);
- swapcache_free(swap, page);
- set_page_private(page, 0);
- ClearPageSwapCache(page);
+ swapcache_free_page_entry(page);
} else {
void (*freepage)(struct page *);
_
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2013-06-03 20:02 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-03 20:02 [v5][PATCH 0/6] mm: vmscan: Batch page reclamation under shink_page_list Dave Hansen
2013-06-03 20:02 ` [v5][PATCH 1/6] mm: swap: defer clearing of page_private() for swap cache pages Dave Hansen
2013-07-14 23:47 ` Wanpeng Li
2013-07-14 23:47 ` Wanpeng Li
2013-06-03 20:02 ` Dave Hansen [this message]
2013-07-14 23:48 ` [v5][PATCH 2/6] mm: swap: make 'struct page' and swp_entry_t variants of swapcache_free() Wanpeng Li
2013-07-14 23:48 ` Wanpeng Li
2013-06-03 20:02 ` [v5][PATCH 3/6] mm: vmscan: break up __remove_mapping() Dave Hansen
2013-07-14 23:49 ` Wanpeng Li
2013-07-14 23:49 ` Wanpeng Li
2013-06-03 20:02 ` [v5][PATCH 4/6] mm: vmscan: break out mapping "freepage" code Dave Hansen
2013-07-14 23:49 ` Wanpeng Li
2013-07-14 23:49 ` Wanpeng Li
2013-06-03 20:02 ` [v5][PATCH 5/6] mm: vmscan: batch shrink_page_list() locking operations Dave Hansen
2013-06-04 1:17 ` Hillf Danton
2013-06-04 5:07 ` Minchan Kim
2013-06-04 15:22 ` Dave Hansen
2013-06-05 7:28 ` Hillf Danton
2013-06-05 7:57 ` Minchan Kim
2013-06-05 14:24 ` Dave Hansen
2013-06-04 5:01 ` Minchan Kim
2013-06-04 6:02 ` Minchan Kim
2013-06-04 15:29 ` Dave Hansen
2013-06-04 23:32 ` Minchan Kim
2013-06-04 6:10 ` Dave Hansen
2013-06-04 6:59 ` Minchan Kim
2013-07-14 23:50 ` Wanpeng Li
2013-07-14 23:50 ` Wanpeng Li
2013-06-03 20:02 ` [v5][PATCH 6/6] mm: vmscan: drain batch list during long operations Dave Hansen
2013-06-04 6:05 ` Minchan Kim
2013-06-04 15:24 ` Dave Hansen
2013-06-04 23:23 ` Minchan Kim
2013-06-04 23:31 ` Dave Hansen
2013-06-04 23:36 ` Minchan Kim
2013-06-04 23:37 ` Minchan Kim
2013-07-14 23:51 ` Wanpeng Li
2013-07-14 23:51 ` Wanpeng Li
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=20130603200205.23A23517@viggo.jf.intel.com \
--to=dave@sr71.net \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=minchan@kernel.org \
--cc=tim.c.chen@linux.intel.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