linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Jan Kara <jack@suse.cz>
To: John Hubbard <jhubbard@nvidia.com>
Cc: "Andrew Morton" <akpm@linux-foundation.org>,
	"Al Viro" <viro@zeniv.linux.org.uk>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Benjamin Herrenschmidt" <benh@kernel.crashing.org>,
	"Björn Töpel" <bjorn.topel@intel.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Dan Williams" <dan.j.williams@intel.com>,
	"Daniel Vetter" <daniel@ffwll.ch>,
	"Dave Chinner" <david@fromorbit.com>,
	"David Airlie" <airlied@linux.ie>,
	"David S . Miller" <davem@davemloft.net>,
	"Ira Weiny" <ira.weiny@intel.com>, "Jan Kara" <jack@suse.cz>,
	"Jason Gunthorpe" <jgg@ziepe.ca>, "Jens Axboe" <axboe@kernel.dk>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Jérôme Glisse" <jglisse@redhat.com>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>,
	"Mauro Carvalho Chehab" <mchehab@kernel.org>,
	"Michael Ellerman" <mpe@ellerman.id.au>,
	"Michal Hocko" <mhocko@suse.com>,
	"Mike Kravetz" <mike.kravetz@oracle.com>,
	"Paul Mackerras" <paulus@samba.org>,
	"Shuah Khan" <shuah@kernel.org>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	bpf@vger.kernel.org, dri-devel@lists.freedesktop.org,
	kvm@vger.kernel.org, linux-block@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kselftest@vger.kernel.org, linux-media@vger.kernel.org,
	linux-rdma@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	netdev@vger.kernel.org, linux-mm@kvack.org,
	LKML <linux-kernel@vger.kernel.org>,
	"Christoph Hellwig" <hch@lst.de>,
	"Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Subject: Re: [PATCH v6 02/24] mm/gup: factor out duplicate code from four routines
Date: Tue, 19 Nov 2019 11:19:10 +0100	[thread overview]
Message-ID: <20191119101910.GC25605@quack2.suse.cz> (raw)
In-Reply-To: <20191119081643.1866232-3-jhubbard@nvidia.com>

On Tue 19-11-19 00:16:21, John Hubbard wrote:
> There are four locations in gup.c that have a fair amount of code
> duplication. This means that changing one requires making the same
> changes in four places, not to mention reading the same code four
> times, and wondering if there are subtle differences.
> 
> Factor out the common code into static functions, thus reducing the
> overall line count and the code's complexity.
> 
> Also, take the opportunity to slightly improve the efficiency of the
> error cases, by doing a mass subtraction of the refcount, surrounded
> by get_page()/put_page().
> 
> Also, further simplify (slightly), by waiting until the the successful
> end of each routine, to increment *nr.
> 
> Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
> Cc: Jan Kara <jack@suse.cz>
> Cc: Ira Weiny <ira.weiny@intel.com>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> Signed-off-by: John Hubbard <jhubbard@nvidia.com>

Looks good to me now! You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
>  mm/gup.c | 91 ++++++++++++++++++++++----------------------------------
>  1 file changed, 36 insertions(+), 55 deletions(-)
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index 85caf76b3012..f3c7d6625817 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -1969,6 +1969,25 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
>  }
>  #endif
>  
> +static int __record_subpages(struct page *page, unsigned long addr,
> +			     unsigned long end, struct page **pages)
> +{
> +	int nr;
> +
> +	for (nr = 0; addr != end; addr += PAGE_SIZE)
> +		pages[nr++] = page++;
> +
> +	return nr;
> +}
> +
> +static void put_compound_head(struct page *page, int refs)
> +{
> +	/* Do a get_page() first, in case refs == page->_refcount */
> +	get_page(page);
> +	page_ref_sub(page, refs);
> +	put_page(page);
> +}
> +
>  #ifdef CONFIG_ARCH_HAS_HUGEPD
>  static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
>  				      unsigned long sz)
> @@ -1998,32 +2017,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
>  	/* hugepages are never "special" */
>  	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
>  
> -	refs = 0;
>  	head = pte_page(pte);
> -
>  	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
> -	do {
> -		VM_BUG_ON(compound_head(page) != head);
> -		pages[*nr] = page;
> -		(*nr)++;
> -		page++;
> -		refs++;
> -	} while (addr += PAGE_SIZE, addr != end);
> +	refs = __record_subpages(page, addr, end, pages + *nr);
>  
>  	head = try_get_compound_head(head, refs);
> -	if (!head) {
> -		*nr -= refs;
> +	if (!head)
>  		return 0;
> -	}
>  
>  	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
> -		/* Could be optimized better */
> -		*nr -= refs;
> -		while (refs--)
> -			put_page(head);
> +		put_compound_head(head, refs);
>  		return 0;
>  	}
>  
> +	*nr += refs;
>  	SetPageReferenced(head);
>  	return 1;
>  }
> @@ -2071,28 +2078,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
>  					     pages, nr);
>  	}
>  
> -	refs = 0;
>  	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
> -	do {
> -		pages[*nr] = page;
> -		(*nr)++;
> -		page++;
> -		refs++;
> -	} while (addr += PAGE_SIZE, addr != end);
> +	refs = __record_subpages(page, addr, end, pages + *nr);
>  
>  	head = try_get_compound_head(pmd_page(orig), refs);
> -	if (!head) {
> -		*nr -= refs;
> +	if (!head)
>  		return 0;
> -	}
>  
>  	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
> -		*nr -= refs;
> -		while (refs--)
> -			put_page(head);
> +		put_compound_head(head, refs);
>  		return 0;
>  	}
>  
> +	*nr += refs;
>  	SetPageReferenced(head);
>  	return 1;
>  }
> @@ -2114,28 +2112,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
>  					     pages, nr);
>  	}
>  
> -	refs = 0;
>  	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
> -	do {
> -		pages[*nr] = page;
> -		(*nr)++;
> -		page++;
> -		refs++;
> -	} while (addr += PAGE_SIZE, addr != end);
> +	refs = __record_subpages(page, addr, end, pages + *nr);
>  
>  	head = try_get_compound_head(pud_page(orig), refs);
> -	if (!head) {
> -		*nr -= refs;
> +	if (!head)
>  		return 0;
> -	}
>  
>  	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
> -		*nr -= refs;
> -		while (refs--)
> -			put_page(head);
> +		put_compound_head(head, refs);
>  		return 0;
>  	}
>  
> +	*nr += refs;
>  	SetPageReferenced(head);
>  	return 1;
>  }
> @@ -2151,28 +2140,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
>  		return 0;
>  
>  	BUILD_BUG_ON(pgd_devmap(orig));
> -	refs = 0;
> +
>  	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
> -	do {
> -		pages[*nr] = page;
> -		(*nr)++;
> -		page++;
> -		refs++;
> -	} while (addr += PAGE_SIZE, addr != end);
> +	refs = __record_subpages(page, addr, end, pages + *nr);
>  
>  	head = try_get_compound_head(pgd_page(orig), refs);
> -	if (!head) {
> -		*nr -= refs;
> +	if (!head)
>  		return 0;
> -	}
>  
>  	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
> -		*nr -= refs;
> -		while (refs--)
> -			put_page(head);
> +		put_compound_head(head, refs);
>  		return 0;
>  	}
>  
> +	*nr += refs;
>  	SetPageReferenced(head);
>  	return 1;
>  }
> -- 
> 2.24.0
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR


  reply	other threads:[~2019-11-19 10:19 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-19  8:16 [PATCH v6 00/24] mm/gup: track dma-pinned pages: FOLL_PIN John Hubbard
2019-11-19  8:16 ` [PATCH v6 01/24] mm/gup: pass flags arg to __gup_device_* functions John Hubbard
2019-11-19  8:16 ` [PATCH v6 02/24] mm/gup: factor out duplicate code from four routines John Hubbard
2019-11-19 10:19   ` Jan Kara [this message]
2019-11-19  8:16 ` [PATCH v6 03/24] mm/gup: move try_get_compound_head() to top, fix minor issues John Hubbard
2019-11-19  8:16 ` [PATCH v6 04/24] mm: Cleanup __put_devmap_managed_page() vs ->page_free() John Hubbard
2019-11-19  8:16 ` [PATCH v6 05/24] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages John Hubbard
2019-11-19  8:16 ` [PATCH v6 06/24] goldish_pipe: rename local pin_user_pages() routine John Hubbard
2019-11-19  8:16 ` [PATCH v6 07/24] IB/umem: use get_user_pages_fast() to pin DMA pages John Hubbard
2019-11-19  8:16 ` [PATCH v6 08/24] media/v4l2-core: set pages dirty upon releasing DMA buffers John Hubbard
2019-11-19  8:16 ` [PATCH v6 09/24] vfio, mm: fix get_user_pages_remote() and FOLL_LONGTERM John Hubbard
2019-11-19  8:16 ` [PATCH v6 10/24] mm/gup: introduce pin_user_pages*() and FOLL_PIN John Hubbard
2019-11-19  8:16 ` [PATCH v6 11/24] goldish_pipe: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-19  8:16 ` [PATCH v6 12/24] IB/{core,hw,umem}: set FOLL_PIN via pin_user_pages*(), fix up ODP John Hubbard
2019-11-19  8:16 ` [PATCH v6 13/24] mm/process_vm_access: set FOLL_PIN via pin_user_pages_remote() John Hubbard
2019-11-19  8:16 ` [PATCH v6 14/24] drm/via: set FOLL_PIN via pin_user_pages_fast() John Hubbard
2019-11-19  8:16 ` [PATCH v6 15/24] fs/io_uring: set FOLL_PIN via pin_user_pages() John Hubbard
2019-11-19 16:10   ` Jens Axboe
2019-11-20  7:03     ` John Hubbard
2019-11-19  8:16 ` [PATCH v6 16/24] net/xdp: " John Hubbard
2019-11-19  8:16 ` [PATCH v6 17/24] mm/gup: track FOLL_PIN pages John Hubbard
2019-11-19 11:37   ` Jan Kara
2019-11-20  7:17     ` John Hubbard
2019-11-19  8:16 ` [PATCH v6 18/24] media/v4l2-core: pin_user_pages (FOLL_PIN) and put_user_page() conversion John Hubbard
2019-11-19  8:16 ` [PATCH v6 19/24] vfio, mm: " John Hubbard
2019-11-19  8:16 ` [PATCH v6 20/24] powerpc: book3s64: convert to pin_user_pages() and put_user_page() John Hubbard
2019-11-19  8:16 ` [PATCH v6 21/24] mm/gup_benchmark: use proper FOLL_WRITE flags instead of hard-coding "1" John Hubbard
2019-11-19  8:16 ` [PATCH v6 22/24] mm/gup_benchmark: support pin_user_pages() and related calls John Hubbard
2019-11-19  8:16 ` [PATCH v6 23/24] selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage John Hubbard
2019-11-19  8:16 ` [PATCH v6 24/24] mm, tree-wide: rename put_user_page*() to unpin_user_page*() John Hubbard
2019-11-19 11:39   ` Jan Kara

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=20191119101910.GC25605@quack2.suse.cz \
    --to=jack@suse.cz \
    --cc=airlied@linux.ie \
    --cc=akpm@linux-foundation.org \
    --cc=alex.williamson@redhat.com \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=axboe@kernel.dk \
    --cc=benh@kernel.crashing.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=daniel@ffwll.ch \
    --cc=davem@davemloft.net \
    --cc=david@fromorbit.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hch@infradead.org \
    --cc=hch@lst.de \
    --cc=ira.weiny@intel.com \
    --cc=jgg@ziepe.ca \
    --cc=jglisse@redhat.com \
    --cc=jhubbard@nvidia.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=magnus.karlsson@intel.com \
    --cc=mchehab@kernel.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=mpe@ellerman.id.au \
    --cc=netdev@vger.kernel.org \
    --cc=paulus@samba.org \
    --cc=shuah@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    /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).