From: Minchan Kim <minchan@kernel.org>
To: Joonsoo Kim <js1304@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH 4/5] mm, highmem: makes flush_all_zero_pkmaps() return index of last flushed entry
Date: Mon, 29 Oct 2012 11:06:31 +0900 [thread overview]
Message-ID: <20121029020631.GI15767@bbox> (raw)
In-Reply-To: <1351451576-2611-5-git-send-email-js1304@gmail.com>
On Mon, Oct 29, 2012 at 04:12:55AM +0900, Joonsoo Kim wrote:
> In current code, after flush_all_zero_pkmaps() is invoked,
> then re-iterate all pkmaps. It can be optimized if flush_all_zero_pkmaps()
> return index of flushed entry. With this index,
> we can immediately map highmem page to virtual address represented by index.
> So change return type of flush_all_zero_pkmaps()
> and return index of last flushed entry.
>
> Signed-off-by: Joonsoo Kim <js1304@gmail.com>
>
> diff --git a/include/linux/highmem.h b/include/linux/highmem.h
> index ef788b5..0683869 100644
> --- a/include/linux/highmem.h
> +++ b/include/linux/highmem.h
> @@ -32,6 +32,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
>
> #ifdef CONFIG_HIGHMEM
> #include <asm/highmem.h>
> +#define PKMAP_INDEX_INVAL (-1)
How about this?
#define PKMAP_INVALID_INDEX (-1)
>
> /* declarations for linux/mm/highmem.c */
> unsigned int nr_free_highpages(void);
> diff --git a/mm/highmem.c b/mm/highmem.c
> index 731cf9a..65beb9a 100644
> --- a/mm/highmem.c
> +++ b/mm/highmem.c
> @@ -106,10 +106,10 @@ struct page *kmap_to_page(void *vaddr)
> return virt_to_page(addr);
> }
>
> -static void flush_all_zero_pkmaps(void)
> +static int flush_all_zero_pkmaps(void)
> {
> int i;
> - int need_flush = 0;
> + int index = PKMAP_INDEX_INVAL;
>
> flush_cache_kmaps();
>
> @@ -141,10 +141,12 @@ static void flush_all_zero_pkmaps(void)
> &pkmap_page_table[i]);
>
> set_page_address(page, NULL);
> - need_flush = 1;
> + index = i;
How about returning first free index instead of last one?
and update last_pkmap_nr to it.
> }
> - if (need_flush)
> + if (index != PKMAP_INDEX_INVAL)
> flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
> +
> + return index;
> }
>
> /**
> @@ -160,6 +162,7 @@ void kmap_flush_unused(void)
> static inline unsigned long map_new_virtual(struct page *page)
> {
> unsigned long vaddr;
> + int index = PKMAP_INDEX_INVAL;
> int count;
>
> start:
> @@ -168,40 +171,45 @@ start:
> for (;;) {
> last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;
> if (!last_pkmap_nr) {
> - flush_all_zero_pkmaps();
> - count = LAST_PKMAP;
> + index = flush_all_zero_pkmaps();
> + if (index != PKMAP_INDEX_INVAL)
> + break; /* Found a usable entry */
> }
> - if (!pkmap_count[last_pkmap_nr])
> + if (!pkmap_count[last_pkmap_nr]) {
> + index = last_pkmap_nr;
> break; /* Found a usable entry */
> - if (--count)
> - continue;
> -
> - /*
> - * Sleep for somebody else to unmap their entries
> - */
> - {
> - DECLARE_WAITQUEUE(wait, current);
> -
> - __set_current_state(TASK_UNINTERRUPTIBLE);
> - add_wait_queue(&pkmap_map_wait, &wait);
> - unlock_kmap();
> - schedule();
> - remove_wait_queue(&pkmap_map_wait, &wait);
> - lock_kmap();
> -
> - /* Somebody else might have mapped it while we slept */
> - if (page_address(page))
> - return (unsigned long)page_address(page);
> -
> - /* Re-start */
> - goto start;
> }
> + if (--count == 0)
> + break;
> }
> - vaddr = PKMAP_ADDR(last_pkmap_nr);
> +
> + /*
> + * Sleep for somebody else to unmap their entries
> + */
> + if (index == PKMAP_INDEX_INVAL) {
> + DECLARE_WAITQUEUE(wait, current);
> +
> + __set_current_state(TASK_UNINTERRUPTIBLE);
> + add_wait_queue(&pkmap_map_wait, &wait);
> + unlock_kmap();
> + schedule();
> + remove_wait_queue(&pkmap_map_wait, &wait);
> + lock_kmap();
> +
> + /* Somebody else might have mapped it while we slept */
> + vaddr = (unsigned long)page_address(page);
> + if (vaddr)
> + return vaddr;
> +
> + /* Re-start */
> + goto start;
> + }
> +
> + vaddr = PKMAP_ADDR(index);
> set_pte_at(&init_mm, vaddr,
> - &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot));
> + &(pkmap_page_table[index]), mk_pte(page, kmap_prot));
>
> - pkmap_count[last_pkmap_nr] = 1;
> + pkmap_count[index] = 1;
> set_page_address(page, (void *)vaddr);
>
> return vaddr;
> --
> 1.7.9.5
>
> --
> 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>
--
Kind regards,
Minchan Kim
--
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:[~2012-10-29 2:00 UTC|newest]
Thread overview: 95+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <Yes>
2012-07-16 16:14 ` [PATCH 1/3] mm: correct return value of migrate_pages() Joonsoo Kim
2012-07-16 16:14 ` [PATCH 2/3] mm: fix possible incorrect return value of migrate_pages() syscall Joonsoo Kim
2012-07-16 17:26 ` Christoph Lameter
2012-07-16 17:40 ` Michal Nazarewicz
2012-07-16 17:59 ` JoonSoo Kim
2012-07-17 13:02 ` Michal Nazarewicz
2012-07-16 16:14 ` [PATCH 3/3] mm: fix return value in __alloc_contig_migrate_range() Joonsoo Kim
2012-07-16 17:29 ` Christoph Lameter
2012-07-16 17:40 ` Michal Nazarewicz
2012-07-16 18:40 ` JoonSoo Kim
2012-07-17 13:16 ` Michal Nazarewicz
2012-07-16 17:14 ` [PATCH 4] mm: fix possible incorrect return value of move_pages() syscall Joonsoo Kim
2012-07-16 17:30 ` Christoph Lameter
2012-07-16 17:23 ` [PATCH 1/3] mm: correct return value of migrate_pages() Christoph Lameter
2012-07-16 17:32 ` JoonSoo Kim
2012-07-16 17:37 ` Christoph Lameter
2012-07-16 17:40 ` Michal Nazarewicz
2012-07-16 17:57 ` JoonSoo Kim
2012-07-16 18:05 ` Christoph Lameter
2012-07-17 12:33 ` [PATCH 1/4 v2] mm: correct return value of migrate_pages() and migrate_huge_pages() Joonsoo Kim
2012-07-17 12:33 ` [PATCH 2/4 v2] mm: fix possible incorrect return value of migrate_pages() syscall Joonsoo Kim
2012-07-17 14:28 ` Christoph Lameter
2012-07-17 15:41 ` JoonSoo Kim
2012-07-17 12:33 ` [PATCH 3/4 v2] mm: fix return value in __alloc_contig_migrate_range() Joonsoo Kim
2012-07-17 13:25 ` Michal Nazarewicz
2012-07-17 15:45 ` JoonSoo Kim
2012-07-17 15:49 ` [PATCH 3/4 v3] " Joonsoo Kim
2012-07-17 12:33 ` [PATCH 4/4 v2] mm: fix possible incorrect return value of move_pages() syscall Joonsoo Kim
2012-07-27 17:55 ` [RESEND PATCH 1/4 v3] mm: correct return value of migrate_pages() and migrate_huge_pages() Joonsoo Kim
2012-07-27 17:55 ` [RESEND PATCH 2/4 v3] mm: fix possible incorrect return value of migrate_pages() syscall Joonsoo Kim
2012-07-27 20:57 ` Christoph Lameter
2012-07-28 6:16 ` JoonSoo Kim
2012-07-30 19:30 ` Christoph Lameter
2012-07-27 17:55 ` [RESEND PATCH 3/4 v3] mm: fix return value in __alloc_contig_migrate_range() Joonsoo Kim
2012-07-27 17:55 ` [RESEND PATCH 4/4 v3] mm: fix possible incorrect return value of move_pages() syscall Joonsoo Kim
2012-07-27 20:54 ` Christoph Lameter
2012-07-28 6:09 ` JoonSoo Kim
2012-07-30 19:29 ` Christoph Lameter
2012-07-31 3:34 ` JoonSoo Kim
2012-07-31 14:04 ` Christoph Lameter
2012-08-01 5:15 ` Michael Kerrisk
2012-08-01 18:00 ` Christoph Lameter
2012-08-02 5:52 ` Michael Kerrisk
2012-08-24 16:05 ` [PATCH 1/2] slub: rename cpu_partial to max_cpu_object Joonsoo Kim
2012-08-24 16:05 ` [PATCH 2/2] slub: correct the calculation of the number of cpu objects in get_partial_node Joonsoo Kim
2012-08-24 16:15 ` Christoph Lameter
2012-08-24 16:28 ` JoonSoo Kim
2012-08-24 16:31 ` Christoph Lameter
2012-08-24 16:40 ` JoonSoo Kim
2012-08-24 16:12 ` [PATCH 1/2] slub: rename cpu_partial to max_cpu_object Christoph Lameter
2012-08-25 14:11 ` [PATCH 1/2] slab: do ClearSlabPfmemalloc() for all pages of slab Joonsoo Kim
2012-08-25 14:11 ` [PATCH 2/2] slab: fix starting index for finding another object Joonsoo Kim
2012-09-03 10:08 ` [PATCH 1/2] slab: do ClearSlabPfmemalloc() for all pages of slab Mel Gorman
2012-10-20 15:48 ` [PATCH for-v3.7 1/2] slub: optimize poorly inlined kmalloc* functions Joonsoo Kim
2012-10-20 15:48 ` [PATCH for-v3.7 2/2] slub: optimize kmalloc* inlining for GFP_DMA Joonsoo Kim
2012-10-22 14:31 ` Christoph Lameter
2012-10-23 2:29 ` JoonSoo Kim
2012-10-23 6:16 ` Eric Dumazet
2012-10-23 16:12 ` JoonSoo Kim
2012-10-24 8:05 ` [PATCH for-v3.7 1/2] slub: optimize poorly inlined kmalloc* functions Pekka Enberg
2012-10-24 13:36 ` Christoph Lameter
2012-10-28 19:12 ` [PATCH 0/5] minor clean-up and optimize highmem related code Joonsoo Kim
2012-10-28 19:12 ` [PATCH 1/5] mm, highmem: use PKMAP_NR() to calculate an index of pkmap Joonsoo Kim
2012-10-29 1:48 ` Minchan Kim
2012-10-28 19:12 ` [PATCH 2/5] mm, highmem: remove useless pool_lock Joonsoo Kim
2012-10-29 1:52 ` Minchan Kim
2012-10-30 21:31 ` Andrew Morton
2012-10-31 5:14 ` Minchan Kim
2012-10-31 15:01 ` JoonSoo Kim
2012-10-28 19:12 ` [PATCH 3/5] mm, highmem: remove page_address_pool list Joonsoo Kim
2012-10-29 1:57 ` Minchan Kim
2012-10-28 19:12 ` [PATCH 4/5] mm, highmem: makes flush_all_zero_pkmaps() return index of last flushed entry Joonsoo Kim
2012-10-29 2:06 ` Minchan Kim [this message]
2012-10-29 13:12 ` JoonSoo Kim
2012-10-28 19:12 ` [PATCH 5/5] mm, highmem: get virtual address of the page using PKMAP_ADDR() Joonsoo Kim
2012-10-29 2:09 ` Minchan Kim
2012-10-29 2:12 ` [PATCH 0/5] minor clean-up and optimize highmem related code Minchan Kim
2012-10-29 13:15 ` JoonSoo Kim
2012-10-31 17:11 ` JoonSoo Kim
2012-10-31 16:56 ` [PATCH v2 " Joonsoo Kim
2012-10-31 16:56 ` [PATCH v2 1/5] mm, highmem: use PKMAP_NR() to calculate an index of pkmap Joonsoo Kim
2012-10-31 16:56 ` [PATCH v2 2/5] mm, highmem: remove useless pool_lock Joonsoo Kim
2012-10-31 16:56 ` [PATCH v2 3/5] mm, highmem: remove page_address_pool list Joonsoo Kim
2012-10-31 16:56 ` [PATCH v2 4/5] mm, highmem: makes flush_all_zero_pkmaps() return index of first flushed entry Joonsoo Kim
2012-11-01 5:03 ` Minchan Kim
2012-11-02 19:07 ` JoonSoo Kim
2012-11-02 22:42 ` Minchan Kim
2012-11-13 0:30 ` JoonSoo Kim
2012-11-13 12:49 ` Minchan Kim
2012-11-13 14:12 ` JoonSoo Kim
2012-11-13 15:01 ` Minchan Kim
2012-11-14 17:09 ` JoonSoo Kim
2012-11-19 23:46 ` Minchan Kim
2012-11-27 15:01 ` JoonSoo Kim
2012-10-31 16:56 ` [PATCH v2 5/5] mm, highmem: get virtual address of the page using PKMAP_ADDR() Joonsoo Kim
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=20121029020631.GI15767@bbox \
--to=minchan@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=js1304@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/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).