From: David Hildenbrand <[email protected]>
To: "Matthew Wilcox (Oracle)" <[email protected]>,
Andrew Morton <[email protected]>
Cc: Jens Axboe <[email protected]>,
[email protected], [email protected]
Subject: Re: [PATCH 2/9] mm: Call the hugetlb destructor directly
Date: Tue, 15 Aug 2023 09:36:47 +0200 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 15.08.23 05:26, Matthew Wilcox (Oracle) wrote:
> Indirect calls are expensive, thanks to Spectre. Convert this one to
> a direct call, and pass a folio instead of the head page to save a few
> more instructions.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
> ---
> include/linux/hugetlb.h | 3 ++-
> include/linux/mm.h | 6 +-----
> mm/hugetlb.c | 26 ++++++++++++--------------
> mm/page_alloc.c | 8 +++++---
> 4 files changed, 20 insertions(+), 23 deletions(-)
>
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index 0a393bc02f25..9555859537a3 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -26,6 +26,8 @@ typedef struct { unsigned long pd; } hugepd_t;
> #define __hugepd(x) ((hugepd_t) { (x) })
> #endif
>
> +void free_huge_page(struct folio *folio);
> +
> #ifdef CONFIG_HUGETLB_PAGE
>
> #include <linux/mempolicy.h>
> @@ -165,7 +167,6 @@ int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
> bool *migratable_cleared);
> void folio_putback_active_hugetlb(struct folio *folio);
> void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason);
> -void free_huge_page(struct page *page);
> void hugetlb_fix_reserve_counts(struct inode *inode);
> extern struct mutex *hugetlb_fault_mutex_table;
> u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 19493d6a2bb8..7fb529dbff31 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1278,13 +1278,9 @@ typedef void compound_page_dtor(struct page *);
> enum compound_dtor_id {
> NULL_COMPOUND_DTOR,
> COMPOUND_PAGE_DTOR,
> -#ifdef CONFIG_HUGETLB_PAGE
> HUGETLB_PAGE_DTOR,
> -#endif
> -#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> TRANSHUGE_PAGE_DTOR,
> -#endif
> - NR_COMPOUND_DTORS,
> + NR_COMPOUND_DTORS
> };
>
> static inline void folio_set_compound_dtor(struct folio *folio,
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index e327a5a7602c..bc340f5dbbd4 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1875,13 +1875,12 @@ struct hstate *size_to_hstate(unsigned long size)
> return NULL;
> }
>
> -void free_huge_page(struct page *page)
> +void free_huge_page(struct folio *folio)
free_huge_page" but passing a folio, hm. Maybe something like
"free_hugetlb_folio" would be better.
Apart from that LGTM.
--
Cheers,
David / dhildenb
next prev parent reply other threads:[~2023-08-15 7:38 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-15 3:26 [PATCH 0/9] Remove _folio_dtor and _folio_order Matthew Wilcox (Oracle)
2023-08-15 3:26 ` [PATCH 1/9] io_uring: Stop calling free_compound_page() Matthew Wilcox (Oracle)
2023-08-15 7:33 ` David Hildenbrand
2023-08-15 15:00 ` Jens Axboe
2023-08-15 15:36 ` Matthew Wilcox
2023-08-15 3:26 ` [PATCH 2/9] mm: Call the hugetlb destructor directly Matthew Wilcox (Oracle)
2023-08-15 7:36 ` David Hildenbrand [this message]
2023-08-15 3:26 ` [PATCH 3/9] mm: Call free_transhuge_folio() directly from destroy_large_folio() Matthew Wilcox (Oracle)
2023-08-15 6:13 ` kernel test robot
2023-08-15 7:40 ` David Hildenbrand
2023-08-15 14:06 ` Matthew Wilcox
2023-08-15 8:09 ` kernel test robot
2023-08-15 3:26 ` [PATCH 4/9] mm: Make free_compound_page() static Matthew Wilcox (Oracle)
2023-08-15 7:47 ` David Hildenbrand
2023-08-15 7:48 ` David Hildenbrand
2023-08-15 3:26 ` [PATCH 5/9] mm: Remove free_compound_page() Matthew Wilcox (Oracle)
2023-08-15 7:48 ` David Hildenbrand
2023-08-15 3:26 ` [PATCH 6/9] mm: Remove HUGETLB_PAGE_DTOR Matthew Wilcox (Oracle)
2023-08-15 7:50 ` David Hildenbrand
2023-08-15 3:26 ` [PATCH 7/9] mm: Add deferred_list page flag Matthew Wilcox (Oracle)
2023-08-15 7:54 ` David Hildenbrand
2023-08-15 15:32 ` Matthew Wilcox
2023-08-15 16:40 ` David Hildenbrand
2023-08-15 17:06 ` Matthew Wilcox
2023-08-15 17:27 ` David Hildenbrand
2023-08-15 19:58 ` Matthew Wilcox
2023-08-16 3:14 ` Matthew Wilcox
2023-08-16 10:12 ` David Hildenbrand
2023-08-16 12:05 ` Matthew Wilcox
2023-08-16 12:34 ` David Hildenbrand
2023-08-16 9:55 ` David Hildenbrand
2023-08-15 3:26 ` [PATCH 8/9] mm: Rearrange page flags Matthew Wilcox (Oracle)
2023-08-15 4:30 ` Yosry Ahmed
2023-08-15 19:24 ` Peter Xu
2023-08-15 20:07 ` Matthew Wilcox
2023-08-15 22:31 ` Yosry Ahmed
2023-08-15 23:01 ` Matthew Wilcox
2023-08-15 23:33 ` Yosry Ahmed
2023-08-15 3:26 ` [PATCH 9/9] mm: Free up a word in the first tail page Matthew Wilcox (Oracle)
2023-08-15 7:59 ` David Hildenbrand
2023-08-15 11:39 ` Matthew Wilcox
2023-08-15 19:21 ` Peter Xu
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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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