All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mel Gorman <mel@csn.ul.ie>
To: Andrea Arcangeli <aarcange@redhat.com>
Cc: linux-mm@kvack.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Adam Litke <agl@us.ibm.com>, Avi Kivity <avi@redhat.com>,
	Hugh Dickins <hugh.dickins@tiscali.co.uk>,
	Rik van Riel <riel@redhat.com>,
	Dave Hansen <dave@linux.vnet.ibm.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Ingo Molnar <mingo@elte.hu>, Mike Travis <travis@sgi.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Christoph Lameter <cl@linux-foundation.org>,
	Chris Wright <chrisw@sous-sol.org>,
	bpicco@redhat.com,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
	Chris Mason <chris.mason@oracle.com>,
	Borislav Petkov <bp@alien8.de>
Subject: Re: [PATCH 06 of 66] alter compound get_page/put_page
Date: Fri, 26 Nov 2010 11:46:49 +0000	[thread overview]
Message-ID: <20101126114648.GN26037@csn.ul.ie> (raw)
In-Reply-To: <20101125164916.GP6118@random.random>

On Thu, Nov 25, 2010 at 05:49:16PM +0100, Andrea Arcangeli wrote:
> > > <SNIP>

The updates are fine.

> > > diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
> > > --- a/arch/x86/mm/gup.c
> > > +++ b/arch/x86/mm/gup.c
> > > @@ -105,6 +105,16 @@ static inline void get_head_page_multipl
> > >  	atomic_add(nr, &page->_count);
> > >  }
> > >  
> > > +static inline void pin_huge_page_tail(struct page *page)
> > > +{
> > > +	/*
> > > +	 * __split_huge_page_refcount() cannot run
> > > +	 * from under us.
> > > +	 */
> > > +	VM_BUG_ON(atomic_read(&page->_count) < 0);
> > > +	atomic_inc(&page->_count);
> > > +}
> > > +
> > 
> > This is identical to the x86 implementation. Any possibility they can be
> > shared?
> 
> There is no place for me today to put gup_fast "equal" bits so I'd
> need to create it and just doing it for a single inline function
> sounds overkill. I could add a asm-generic/gup_fast.h add move that
> function there and include the asm-generic/gup_fast.h from
> asm*/include/gup_fast.h, is that what we want just for one function?
> With all #ifdefs included I would end up writing more code than the
> function itself. No problem with me in doing it though.
> 

Now that you've explained what is necessary, it's not worth it as part of the
series. It's sizable enough as it is for review. Consider it as a follow-up
patch maybe.

> > >  static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
> > >  		unsigned long end, int write, struct page **pages, int *nr)
> > >  {
> > > @@ -128,6 +138,8 @@ static noinline int gup_huge_pmd(pmd_t p
> > >  	do {
> > >  		VM_BUG_ON(compound_head(page) != head);
> > >  		pages[*nr] = page;
> > > +		if (PageTail(page))
> > > +			pin_huge_page_tail(page);
> > >  		(*nr)++;
> > >  		page++;
> > >  		refs++;
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -351,9 +351,17 @@ static inline int page_count(struct page
> > >  
> > >  static inline void get_page(struct page *page)
> > >  {
> > > -	page = compound_head(page);
> > > -	VM_BUG_ON(atomic_read(&page->_count) == 0);
> > > +	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
> > 
> > Oof, this might need a comment. It's saying that getting a normal page or the
> > head of a compound page must already have an elevated reference count. If
> > we are getting a tail page, the reference count is stored in both the head
> > and the tail so the BUG check does not apply.
> 
> Ok.
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -353,8 +353,20 @@ static inline int page_count(struct page
>  
>  static inline void get_page(struct page *page)
>  {
> +	/*
> +	 * Getting a normal page or the head of a compound page
> +	 * requires to already have an elevated page->_count. Only if
> +	 * we're getting a tail page, the elevated page->_count is
> +	 * required only in the head page, so for tail pages the
> +	 * bugcheck only verifies that the page->_count isn't
> +	 * negative.
> +	 */
>  	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
>  	atomic_inc(&page->_count);
> +	/*
> +	 * Getting a tail page will elevate both the head and tail
> +	 * page->_count(s).
> +	 */
>  	if (unlikely(PageTail(page))) {
>  		/*
>  		 * This is safe only because

Much better.

> 
> > > diff --git a/mm/swap.c b/mm/swap.c
> > > --- a/mm/swap.c
> > > +++ b/mm/swap.c
> > > @@ -56,17 +56,83 @@ static void __page_cache_release(struct 
> > >  		del_page_from_lru(zone, page);
> > >  		spin_unlock_irqrestore(&zone->lru_lock, flags);
> > >  	}
> > > +}
> > > +
> > > +static void __put_single_page(struct page *page)
> > > +{
> > > +	__page_cache_release(page);
> > >  	free_hot_cold_page(page, 0);
> > >  }
> > >  
> > > +static void __put_compound_page(struct page *page)
> > > +{
> > > +	compound_page_dtor *dtor;
> > > +
> > > +	__page_cache_release(page);
> > > +	dtor = get_compound_page_dtor(page);
> > > +	(*dtor)(page);
> > > +}
> > > +
> > >  static void put_compound_page(struct page *page)
> > >  {
> > > -	page = compound_head(page);
> > > -	if (put_page_testzero(page)) {
> > > -		compound_page_dtor *dtor;
> > > -
> > > -		dtor = get_compound_page_dtor(page);
> > > -		(*dtor)(page);
> > > +	if (unlikely(PageTail(page))) {
> > > +		/* __split_huge_page_refcount can run under us */
> > 
> > So what? The fact you check PageTail twice is a hint as to what is
> > happening and that we are depending on the order of when the head and
> > tails bits get cleared but it's hard to be certain of that.
> 
> This is correct, we depend on the split_huge_page_refcount to clear
> PageTail before overwriting first_page.
> 
> +	 	/*
> +		 * 1) clear PageTail before overwriting first_page
> +		 * 2) clear PageTail before clearing PageHead for VM_BUG_ON
> +		 */
> +		smp_wmb();
> 

This helps. Less guesswork involved :)

> The first PageTail check is just to define the fast path and skip
> reading page->first_page and doing smb_rmb() for the much more common
> head pages (we're in unlikely branch).
> 
> So then we read first_page, we smb_rmb() and if pagetail is still set
> after that, we can be sure first_page isn't a dangling pointer.
> 
> > 
> > > +		struct page *page_head = page->first_page;
> > > +		smp_rmb();
> > > +		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
> > > +			unsigned long flags;
> > > +			if (unlikely(!PageHead(page_head))) {
> > > +				/* PageHead is cleared after PageTail */
> > > +				smp_rmb();
> > > +				VM_BUG_ON(PageTail(page));
> > > +				goto out_put_head;
> > > +			}
> > > +			/*
> > > +			 * Only run compound_lock on a valid PageHead,
> > > +			 * after having it pinned with
> > > +			 * get_page_unless_zero() above.
> > > +			 */
> > > +			smp_mb();
> > > +			/* page_head wasn't a dangling pointer */
> > > +			compound_lock_irqsave(page_head, &flags);
> > > +			if (unlikely(!PageTail(page))) {
> > > +				/* __split_huge_page_refcount run before us */
> > > +				compound_unlock_irqrestore(page_head, flags);
> > > +				VM_BUG_ON(PageHead(page_head));
> > > +			out_put_head:
> > > +				if (put_page_testzero(page_head))
> > > +					__put_single_page(page_head);
> > > +			out_put_single:
> > > +				if (put_page_testzero(page))
> > > +					__put_single_page(page);
> > > +				return;
> > > +			}
> > > +			VM_BUG_ON(page_head != page->first_page);
> > > +			/*
> > > +			 * We can release the refcount taken by
> > > +			 * get_page_unless_zero now that
> > > +			 * split_huge_page_refcount is blocked on the
> > > +			 * compound_lock.
> > > +			 */
> > > +			if (put_page_testzero(page_head))
> > > +				VM_BUG_ON(1);
> > > +			/* __split_huge_page_refcount will wait now */
> > > +			VM_BUG_ON(atomic_read(&page->_count) <= 0);
> > > +			atomic_dec(&page->_count);
> > > +			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
> > > +			compound_unlock_irqrestore(page_head, flags);
> > > +			if (put_page_testzero(page_head))
> > > +				__put_compound_page(page_head);
> > > +		} else {
> > > +			/* page_head is a dangling pointer */
> > > +			VM_BUG_ON(PageTail(page));
> > > +			goto out_put_single;
> > > +		}
> > > +	} else if (put_page_testzero(page)) {
> > > +		if (PageHead(page))
> > > +			__put_compound_page(page);
> > > +		else
> > > +			__put_single_page(page);
> > >  	}
> > >  }
> > >  
> > > @@ -75,7 +141,7 @@ void put_page(struct page *page)
> > >  	if (unlikely(PageCompound(page)))
> > >  		put_compound_page(page);
> > >  	else if (put_page_testzero(page))
> > > -		__page_cache_release(page);
> > > +		__put_single_page(page);
> > >  }
> > >  EXPORT_SYMBOL(put_page);
> > >  
> > 
> > Functionally, I don't see a problem so
> > 
> > Acked-by: Mel Gorman <mel@csn.ul.ie>
> > 
> > but some expansion on the leader and the comment, even if done as a
> > follow-on patch, would be nice.
> 
> diff --git a/mm/swap.c b/mm/swap.c
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -79,8 +79,18 @@ static void put_compound_page(struct pag
>  		/* __split_huge_page_refcount can run under us */
>  		struct page *page_head = page->first_page;
>  		smp_rmb();
> +		/*
> +		 * If PageTail is still set after smp_rmb() we can be sure
> +		 * that the page->first_page we read wasn't a dangling pointer.
> +		 * See __split_huge_page_refcount() smp_wmb().
> +		 */
>  		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
>  			unsigned long flags;
> +			/*
> +			 * Verify that our page_head wasn't converted
> +			 * to a a regular page before we got a
> +			 * reference on it.
> +			 */
>  			if (unlikely(!PageHead(page_head))) {
>  				/* PageHead is cleared after PageTail */
>  				smp_rmb();
> 

Thanks

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab

WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mel@csn.ul.ie>
To: Andrea Arcangeli <aarcange@redhat.com>
Cc: linux-mm@kvack.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Adam Litke <agl@us.ibm.com>, Avi Kivity <avi@redhat.com>,
	Hugh Dickins <hugh.dickins@tiscali.co.uk>,
	Rik van Riel <riel@redhat.com>,
	Dave Hansen <dave@linux.vnet.ibm.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Ingo Molnar <mingo@elte.hu>, Mike Travis <travis@sgi.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Christoph Lameter <cl@linux-foundation.org>,
	Chris Wright <chrisw@sous-sol.org>,
	bpicco@redhat.com,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
	Chris Mason <chris.mason@oracle.com>,
	Borislav Petkov <bp@alien8.de>
Subject: Re: [PATCH 06 of 66] alter compound get_page/put_page
Date: Fri, 26 Nov 2010 11:46:49 +0000	[thread overview]
Message-ID: <20101126114648.GN26037@csn.ul.ie> (raw)
In-Reply-To: <20101125164916.GP6118@random.random>

On Thu, Nov 25, 2010 at 05:49:16PM +0100, Andrea Arcangeli wrote:
> > > <SNIP>

The updates are fine.

> > > diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
> > > --- a/arch/x86/mm/gup.c
> > > +++ b/arch/x86/mm/gup.c
> > > @@ -105,6 +105,16 @@ static inline void get_head_page_multipl
> > >  	atomic_add(nr, &page->_count);
> > >  }
> > >  
> > > +static inline void pin_huge_page_tail(struct page *page)
> > > +{
> > > +	/*
> > > +	 * __split_huge_page_refcount() cannot run
> > > +	 * from under us.
> > > +	 */
> > > +	VM_BUG_ON(atomic_read(&page->_count) < 0);
> > > +	atomic_inc(&page->_count);
> > > +}
> > > +
> > 
> > This is identical to the x86 implementation. Any possibility they can be
> > shared?
> 
> There is no place for me today to put gup_fast "equal" bits so I'd
> need to create it and just doing it for a single inline function
> sounds overkill. I could add a asm-generic/gup_fast.h add move that
> function there and include the asm-generic/gup_fast.h from
> asm*/include/gup_fast.h, is that what we want just for one function?
> With all #ifdefs included I would end up writing more code than the
> function itself. No problem with me in doing it though.
> 

Now that you've explained what is necessary, it's not worth it as part of the
series. It's sizable enough as it is for review. Consider it as a follow-up
patch maybe.

> > >  static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
> > >  		unsigned long end, int write, struct page **pages, int *nr)
> > >  {
> > > @@ -128,6 +138,8 @@ static noinline int gup_huge_pmd(pmd_t p
> > >  	do {
> > >  		VM_BUG_ON(compound_head(page) != head);
> > >  		pages[*nr] = page;
> > > +		if (PageTail(page))
> > > +			pin_huge_page_tail(page);
> > >  		(*nr)++;
> > >  		page++;
> > >  		refs++;
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -351,9 +351,17 @@ static inline int page_count(struct page
> > >  
> > >  static inline void get_page(struct page *page)
> > >  {
> > > -	page = compound_head(page);
> > > -	VM_BUG_ON(atomic_read(&page->_count) == 0);
> > > +	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
> > 
> > Oof, this might need a comment. It's saying that getting a normal page or the
> > head of a compound page must already have an elevated reference count. If
> > we are getting a tail page, the reference count is stored in both the head
> > and the tail so the BUG check does not apply.
> 
> Ok.
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -353,8 +353,20 @@ static inline int page_count(struct page
>  
>  static inline void get_page(struct page *page)
>  {
> +	/*
> +	 * Getting a normal page or the head of a compound page
> +	 * requires to already have an elevated page->_count. Only if
> +	 * we're getting a tail page, the elevated page->_count is
> +	 * required only in the head page, so for tail pages the
> +	 * bugcheck only verifies that the page->_count isn't
> +	 * negative.
> +	 */
>  	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
>  	atomic_inc(&page->_count);
> +	/*
> +	 * Getting a tail page will elevate both the head and tail
> +	 * page->_count(s).
> +	 */
>  	if (unlikely(PageTail(page))) {
>  		/*
>  		 * This is safe only because

Much better.

> 
> > > diff --git a/mm/swap.c b/mm/swap.c
> > > --- a/mm/swap.c
> > > +++ b/mm/swap.c
> > > @@ -56,17 +56,83 @@ static void __page_cache_release(struct 
> > >  		del_page_from_lru(zone, page);
> > >  		spin_unlock_irqrestore(&zone->lru_lock, flags);
> > >  	}
> > > +}
> > > +
> > > +static void __put_single_page(struct page *page)
> > > +{
> > > +	__page_cache_release(page);
> > >  	free_hot_cold_page(page, 0);
> > >  }
> > >  
> > > +static void __put_compound_page(struct page *page)
> > > +{
> > > +	compound_page_dtor *dtor;
> > > +
> > > +	__page_cache_release(page);
> > > +	dtor = get_compound_page_dtor(page);
> > > +	(*dtor)(page);
> > > +}
> > > +
> > >  static void put_compound_page(struct page *page)
> > >  {
> > > -	page = compound_head(page);
> > > -	if (put_page_testzero(page)) {
> > > -		compound_page_dtor *dtor;
> > > -
> > > -		dtor = get_compound_page_dtor(page);
> > > -		(*dtor)(page);
> > > +	if (unlikely(PageTail(page))) {
> > > +		/* __split_huge_page_refcount can run under us */
> > 
> > So what? The fact you check PageTail twice is a hint as to what is
> > happening and that we are depending on the order of when the head and
> > tails bits get cleared but it's hard to be certain of that.
> 
> This is correct, we depend on the split_huge_page_refcount to clear
> PageTail before overwriting first_page.
> 
> +	 	/*
> +		 * 1) clear PageTail before overwriting first_page
> +		 * 2) clear PageTail before clearing PageHead for VM_BUG_ON
> +		 */
> +		smp_wmb();
> 

This helps. Less guesswork involved :)

> The first PageTail check is just to define the fast path and skip
> reading page->first_page and doing smb_rmb() for the much more common
> head pages (we're in unlikely branch).
> 
> So then we read first_page, we smb_rmb() and if pagetail is still set
> after that, we can be sure first_page isn't a dangling pointer.
> 
> > 
> > > +		struct page *page_head = page->first_page;
> > > +		smp_rmb();
> > > +		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
> > > +			unsigned long flags;
> > > +			if (unlikely(!PageHead(page_head))) {
> > > +				/* PageHead is cleared after PageTail */
> > > +				smp_rmb();
> > > +				VM_BUG_ON(PageTail(page));
> > > +				goto out_put_head;
> > > +			}
> > > +			/*
> > > +			 * Only run compound_lock on a valid PageHead,
> > > +			 * after having it pinned with
> > > +			 * get_page_unless_zero() above.
> > > +			 */
> > > +			smp_mb();
> > > +			/* page_head wasn't a dangling pointer */
> > > +			compound_lock_irqsave(page_head, &flags);
> > > +			if (unlikely(!PageTail(page))) {
> > > +				/* __split_huge_page_refcount run before us */
> > > +				compound_unlock_irqrestore(page_head, flags);
> > > +				VM_BUG_ON(PageHead(page_head));
> > > +			out_put_head:
> > > +				if (put_page_testzero(page_head))
> > > +					__put_single_page(page_head);
> > > +			out_put_single:
> > > +				if (put_page_testzero(page))
> > > +					__put_single_page(page);
> > > +				return;
> > > +			}
> > > +			VM_BUG_ON(page_head != page->first_page);
> > > +			/*
> > > +			 * We can release the refcount taken by
> > > +			 * get_page_unless_zero now that
> > > +			 * split_huge_page_refcount is blocked on the
> > > +			 * compound_lock.
> > > +			 */
> > > +			if (put_page_testzero(page_head))
> > > +				VM_BUG_ON(1);
> > > +			/* __split_huge_page_refcount will wait now */
> > > +			VM_BUG_ON(atomic_read(&page->_count) <= 0);
> > > +			atomic_dec(&page->_count);
> > > +			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
> > > +			compound_unlock_irqrestore(page_head, flags);
> > > +			if (put_page_testzero(page_head))
> > > +				__put_compound_page(page_head);
> > > +		} else {
> > > +			/* page_head is a dangling pointer */
> > > +			VM_BUG_ON(PageTail(page));
> > > +			goto out_put_single;
> > > +		}
> > > +	} else if (put_page_testzero(page)) {
> > > +		if (PageHead(page))
> > > +			__put_compound_page(page);
> > > +		else
> > > +			__put_single_page(page);
> > >  	}
> > >  }
> > >  
> > > @@ -75,7 +141,7 @@ void put_page(struct page *page)
> > >  	if (unlikely(PageCompound(page)))
> > >  		put_compound_page(page);
> > >  	else if (put_page_testzero(page))
> > > -		__page_cache_release(page);
> > > +		__put_single_page(page);
> > >  }
> > >  EXPORT_SYMBOL(put_page);
> > >  
> > 
> > Functionally, I don't see a problem so
> > 
> > Acked-by: Mel Gorman <mel@csn.ul.ie>
> > 
> > but some expansion on the leader and the comment, even if done as a
> > follow-on patch, would be nice.
> 
> diff --git a/mm/swap.c b/mm/swap.c
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -79,8 +79,18 @@ static void put_compound_page(struct pag
>  		/* __split_huge_page_refcount can run under us */
>  		struct page *page_head = page->first_page;
>  		smp_rmb();
> +		/*
> +		 * If PageTail is still set after smp_rmb() we can be sure
> +		 * that the page->first_page we read wasn't a dangling pointer.
> +		 * See __split_huge_page_refcount() smp_wmb().
> +		 */
>  		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
>  			unsigned long flags;
> +			/*
> +			 * Verify that our page_head wasn't converted
> +			 * to a a regular page before we got a
> +			 * reference on it.
> +			 */
>  			if (unlikely(!PageHead(page_head))) {
>  				/* PageHead is cleared after PageTail */
>  				smp_rmb();
> 

Thanks

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab

--
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/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2010-11-26 11:47 UTC|newest]

Thread overview: 331+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-03 15:27 [PATCH 00 of 66] Transparent Hugepage Support #32 Andrea Arcangeli
2010-11-03 15:27 ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 01 of 66] disable lumpy when compaction is enabled Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-09  3:18   ` KOSAKI Motohiro
2010-11-09  3:18     ` KOSAKI Motohiro
2010-11-09 21:30     ` Andrea Arcangeli
2010-11-09 21:30       ` Andrea Arcangeli
2010-11-09 21:38       ` Mel Gorman
2010-11-09 21:38         ` Mel Gorman
2010-11-09 22:22         ` Andrea Arcangeli
2010-11-09 22:22           ` Andrea Arcangeli
2010-11-10 14:27           ` Mel Gorman
2010-11-10 14:27             ` Mel Gorman
2010-11-10 16:03             ` Andrea Arcangeli
2010-11-10 16:03               ` Andrea Arcangeli
2010-11-18  8:30   ` Mel Gorman
2010-11-18  8:30     ` Mel Gorman
2010-11-03 15:27 ` [PATCH 02 of 66] mm, migration: Fix race between shift_arg_pages and rmap_walk by guaranteeing rmap_walk finds PTEs created within the temporary stack Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-09  3:01   ` KOSAKI Motohiro
2010-11-09  3:01     ` KOSAKI Motohiro
2010-11-09 21:36     ` Andrea Arcangeli
2010-11-09 21:36       ` Andrea Arcangeli
2010-11-18 11:13   ` Mel Gorman
2010-11-18 11:13     ` Mel Gorman
2010-11-18 17:13     ` Mel Gorman
2010-11-18 17:13       ` Mel Gorman
2010-11-19 17:38     ` Andrea Arcangeli
2010-11-19 17:38       ` Andrea Arcangeli
2010-11-19 17:54       ` Linus Torvalds
2010-11-19 17:54         ` Linus Torvalds
2010-11-19 19:26         ` Andrea Arcangeli
2010-11-19 19:26           ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 03 of 66] transparent hugepage support documentation Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 11:41   ` Mel Gorman
2010-11-18 11:41     ` Mel Gorman
2010-11-25 14:35     ` Andrea Arcangeli
2010-11-25 14:35       ` Andrea Arcangeli
2010-11-26 11:40       ` Mel Gorman
2010-11-26 11:40         ` Mel Gorman
2010-11-03 15:27 ` [PATCH 04 of 66] define MADV_HUGEPAGE Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 11:44   ` Mel Gorman
2010-11-18 11:44     ` Mel Gorman
2010-11-03 15:27 ` [PATCH 05 of 66] compound_lock Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 11:49   ` Mel Gorman
2010-11-18 11:49     ` Mel Gorman
2010-11-18 17:28     ` Linus Torvalds
2010-11-18 17:28       ` Linus Torvalds
2010-11-25 16:21       ` Andrea Arcangeli
2010-11-25 16:21         ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 06 of 66] alter compound get_page/put_page Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 12:37   ` Mel Gorman
2010-11-18 12:37     ` Mel Gorman
2010-11-25 16:49     ` Andrea Arcangeli
2010-11-25 16:49       ` Andrea Arcangeli
2010-11-26 11:46       ` Mel Gorman [this message]
2010-11-26 11:46         ` Mel Gorman
2010-11-03 15:27 ` [PATCH 07 of 66] update futex compound knowledge Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 08 of 66] fix bad_page to show the real reason the page is bad Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-09  3:03   ` KOSAKI Motohiro
2010-11-09  3:03     ` KOSAKI Motohiro
2010-11-18 12:40   ` Mel Gorman
2010-11-18 12:40     ` Mel Gorman
2010-11-03 15:27 ` [PATCH 09 of 66] clear compound mapping Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 10 of 66] add native_set_pmd_at Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 11 of 66] add pmd paravirt ops Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-26 18:01   ` Andrea Arcangeli
2010-11-26 18:01     ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 12 of 66] no paravirt version of pmd ops Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 13 of 66] export maybe_mkwrite Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2011-01-17 14:14   ` Michal Simek
2011-01-17 14:14     ` Michal Simek
2011-01-17 14:33     ` Andrea Arcangeli
2011-01-17 14:33       ` Andrea Arcangeli
2011-01-18 14:29       ` Michal Simek
2011-01-18 14:29         ` Michal Simek
2011-01-18 20:32         ` Andrea Arcangeli
2011-01-18 20:32           ` Andrea Arcangeli
2011-01-20  7:03           ` Michal Simek
2010-11-03 15:27 ` [PATCH 14 of 66] comment reminder in destroy_compound_page Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 15 of 66] config_transparent_hugepage Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 16 of 66] special pmd_trans_* functions Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 12:51   ` Mel Gorman
2010-11-18 12:51     ` Mel Gorman
2010-11-25 17:10     ` Andrea Arcangeli
2010-11-25 17:10       ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 17 of 66] add pmd mangling generic functions Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 12:52   ` Mel Gorman
2010-11-18 12:52     ` Mel Gorman
2010-11-18 17:32     ` Linus Torvalds
2010-11-18 17:32       ` Linus Torvalds
2010-11-25 17:35       ` Andrea Arcangeli
2010-11-25 17:35         ` Andrea Arcangeli
2010-11-26 22:24         ` Linus Torvalds
2010-11-26 22:24           ` Linus Torvalds
2010-12-02 17:50           ` Andrea Arcangeli
2010-12-02 17:50             ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 18 of 66] add pmd mangling functions to x86 Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 13:04   ` Mel Gorman
2010-11-18 13:04     ` Mel Gorman
2010-11-26 17:57     ` Andrea Arcangeli
2010-11-26 17:57       ` Andrea Arcangeli
2010-11-29 10:23       ` Mel Gorman
2010-11-29 10:23         ` Mel Gorman
2010-11-29 16:59         ` Andrea Arcangeli
2010-11-29 16:59           ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 19 of 66] bail out gup_fast on splitting pmd Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 20 of 66] pte alloc trans splitting Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 21 of 66] add pmd mmu_notifier helpers Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:27 ` [PATCH 22 of 66] clear page compound Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 13:11   ` Mel Gorman
2010-11-18 13:11     ` Mel Gorman
2010-11-03 15:27 ` [PATCH 23 of 66] add pmd_huge_pte to mm_struct Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-18 13:13   ` Mel Gorman
2010-11-18 13:13     ` Mel Gorman
2010-11-03 15:27 ` [PATCH 24 of 66] split_huge_page_mm/vma Andrea Arcangeli
2010-11-03 15:27   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 25 of 66] split_huge_page paging Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 26 of 66] clear_copy_huge_page Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 27 of 66] kvm mmu transparent hugepage support Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 28 of 66] _GFP_NO_KSWAPD Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 13:18   ` Mel Gorman
2010-11-18 13:18     ` Mel Gorman
2010-11-29 19:03     ` Andrea Arcangeli
2010-11-29 19:03       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 29 of 66] don't alloc harder for gfp nomemalloc even if nowait Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-09  3:05   ` KOSAKI Motohiro
2010-11-09  3:05     ` KOSAKI Motohiro
2010-11-18 13:19   ` Mel Gorman
2010-11-18 13:19     ` Mel Gorman
2010-11-03 15:28 ` [PATCH 30 of 66] transparent hugepage core Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 15:12   ` Mel Gorman
2010-11-18 15:12     ` Mel Gorman
2010-12-07 21:24     ` Andrea Arcangeli
2010-12-07 21:24       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 31 of 66] split_huge_page anon_vma ordering dependency Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 15:13   ` Mel Gorman
2010-11-18 15:13     ` Mel Gorman
2010-11-03 15:28 ` [PATCH 32 of 66] verify pmd_trans_huge isn't leaking Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 15:15   ` Mel Gorman
2010-11-18 15:15     ` Mel Gorman
2010-11-03 15:28 ` [PATCH 33 of 66] madvise(MADV_HUGEPAGE) Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 15:19   ` Mel Gorman
2010-11-18 15:19     ` Mel Gorman
2010-12-09 17:14     ` Andrea Arcangeli
2010-12-09 17:14       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 34 of 66] add PageTransCompound Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 15:20   ` Mel Gorman
2010-11-18 15:20     ` Mel Gorman
2010-11-03 15:28 ` [PATCH 35 of 66] pmd_trans_huge migrate bugcheck Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 36 of 66] memcg compound Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 15:26   ` Mel Gorman
2010-11-18 15:26     ` Mel Gorman
2010-11-19  1:10     ` KAMEZAWA Hiroyuki
2010-11-19  1:10       ` KAMEZAWA Hiroyuki
2010-12-14 17:38       ` Andrea Arcangeli
2010-12-14 17:38         ` Andrea Arcangeli
2010-12-15  0:12         ` KAMEZAWA Hiroyuki
2010-12-15  0:12           ` KAMEZAWA Hiroyuki
2010-12-15  5:29           ` Andrea Arcangeli
2010-12-15  5:29             ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 37 of 66] transhuge-memcg: commit tail pages at charge Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 38 of 66] memcontrol: try charging huge pages from stock Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-19  1:14   ` KAMEZAWA Hiroyuki
2010-11-19  1:14     ` KAMEZAWA Hiroyuki
2010-12-14 17:38     ` Andrea Arcangeli
2010-12-14 17:38       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 39 of 66] memcg huge memory Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-19  1:19   ` KAMEZAWA Hiroyuki
2010-11-19  1:19     ` KAMEZAWA Hiroyuki
2010-12-14 17:38     ` Andrea Arcangeli
2010-12-14 17:38       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 40 of 66] transparent hugepage vmstat Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 41 of 66] khugepaged Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 42 of 66] khugepaged vma merge Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 43 of 66] don't leave orhpaned swap cache after ksm merging Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-09  3:08   ` KOSAKI Motohiro
2010-11-09  3:08     ` KOSAKI Motohiro
2010-11-09 21:40     ` Andrea Arcangeli
2010-11-09 21:40       ` Andrea Arcangeli
2010-11-10  7:49       ` Hugh Dickins
2010-11-10  7:49         ` Hugh Dickins
2010-11-10 16:08         ` Andrea Arcangeli
2010-11-10 16:08           ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 44 of 66] skip transhuge pages in ksm for now Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 16:06   ` Mel Gorman
2010-11-18 16:06     ` Mel Gorman
2010-12-09 18:13     ` Andrea Arcangeli
2010-12-09 18:13       ` Andrea Arcangeli
2010-12-10 12:17       ` Mel Gorman
2010-12-10 12:17         ` Mel Gorman
2010-11-03 15:28 ` [PATCH 45 of 66] remove PG_buddy Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 16:08   ` Mel Gorman
2010-11-18 16:08     ` Mel Gorman
2010-12-09 18:15     ` Andrea Arcangeli
2010-12-09 18:15       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 46 of 66] add x86 32bit support Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 47 of 66] mincore transparent hugepage support Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 48 of 66] add pmd_modify Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 49 of 66] mprotect: pass vma down to page table walkers Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 50 of 66] mprotect: transparent huge page support Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 51 of 66] set recommended min free kbytes Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 16:16   ` Mel Gorman
2010-11-18 16:16     ` Mel Gorman
2010-12-09 18:47     ` Andrea Arcangeli
2010-12-09 18:47       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 52 of 66] enable direct defrag Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 16:17   ` Mel Gorman
2010-11-18 16:17     ` Mel Gorman
2010-12-09 18:57     ` Andrea Arcangeli
2010-12-09 18:57       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 53 of 66] add numa awareness to hugepage allocations Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-29  5:38   ` Daisuke Nishimura
2010-11-29  5:38     ` Daisuke Nishimura
2010-11-29 16:11     ` Andrea Arcangeli
2010-11-29 16:11       ` Andrea Arcangeli
2010-11-30  0:38       ` Daisuke Nishimura
2010-11-30  0:38         ` Daisuke Nishimura
2010-11-30 19:01         ` Andrea Arcangeli
2010-11-30 19:01           ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 54 of 66] transparent hugepage config choice Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 55 of 66] select CONFIG_COMPACTION if TRANSPARENT_HUGEPAGE enabled Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-09  6:20   ` KOSAKI Motohiro
2010-11-09  6:20     ` KOSAKI Motohiro
2010-11-09 21:11     ` Andrea Arcangeli
2010-11-09 21:11       ` Andrea Arcangeli
2010-11-14  5:07       ` KOSAKI Motohiro
2010-11-14  5:07         ` KOSAKI Motohiro
2010-11-15 15:13         ` Andrea Arcangeli
2010-11-15 15:13           ` Andrea Arcangeli
2010-11-18 16:22       ` Mel Gorman
2010-11-18 16:22         ` Mel Gorman
2010-12-09 19:04         ` Andrea Arcangeli
2010-12-09 19:04           ` Andrea Arcangeli
2010-12-14  9:45           ` Mel Gorman
2010-12-14  9:45             ` Mel Gorman
2010-12-14 16:06             ` Andrea Arcangeli
2010-12-14 16:06               ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 56 of 66] transhuge isolate_migratepages() Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 16:25   ` Mel Gorman
2010-11-18 16:25     ` Mel Gorman
2010-11-03 15:28 ` [PATCH 57 of 66] avoid breaking huge pmd invariants in case of vma_adjust failures Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 58 of 66] don't allow transparent hugepage support without PSE Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 59 of 66] mmu_notifier_test_young Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 60 of 66] freeze khugepaged and ksmd Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 61 of 66] use compaction for GFP_ATOMIC order > 0 Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-09 10:27   ` KOSAKI Motohiro
2010-11-09 10:27     ` KOSAKI Motohiro
2010-11-09 21:49     ` Andrea Arcangeli
2010-11-09 21:49       ` Andrea Arcangeli
2010-11-18 16:31   ` Mel Gorman
2010-11-18 16:31     ` Mel Gorman
2010-12-09 19:10     ` Andrea Arcangeli
2010-12-09 19:10       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 62 of 66] disable transparent hugepages by default on small systems Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 16:34   ` Mel Gorman
2010-11-18 16:34     ` Mel Gorman
2010-11-03 15:28 ` [PATCH 63 of 66] fix anon memory statistics with transparent hugepages Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 64 of 66] scale nr_rotated to balance memory pressure Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-09  6:16   ` KOSAKI Motohiro
2010-11-09  6:16     ` KOSAKI Motohiro
2010-11-18 19:15     ` Andrea Arcangeli
2010-11-18 19:15       ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 65 of 66] transparent hugepage sysfs meminfo Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-03 15:28 ` [PATCH 66 of 66] add debug checks for mapcount related invariants Andrea Arcangeli
2010-11-03 15:28   ` Andrea Arcangeli
2010-11-18 16:39 ` [PATCH 00 of 66] Transparent Hugepage Support #32 Mel Gorman
2010-11-18 16:39   ` Mel Gorman

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=20101126114648.GN26037@csn.ul.ie \
    --to=mel@csn.ul.ie \
    --cc=aarcange@redhat.com \
    --cc=agl@us.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=avi@redhat.com \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=bp@alien8.de \
    --cc=bpicco@redhat.com \
    --cc=chris.mason@oracle.com \
    --cc=chrisw@sous-sol.org \
    --cc=cl@linux-foundation.org \
    --cc=dave@linux.vnet.ibm.com \
    --cc=hannes@cmpxchg.org \
    --cc=hugh.dickins@tiscali.co.uk \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mingo@elte.hu \
    --cc=mst@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=nishimura@mxp.nes.nec.co.jp \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    --cc=torvalds@linux-foundation.org \
    --cc=travis@sgi.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.