linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Mark Rutland <mark.rutland@arm.com>
To: Ryan Roberts <ryan.roberts@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>, Ard Biesheuvel <ardb@kernel.org>,
	Marc Zyngier <maz@kernel.org>, James Morse <james.morse@arm.com>,
	Andrey Ryabinin <ryabinin.a.a@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Matthew Wilcox <willy@infradead.org>,
	David Hildenbrand <david@redhat.com>,
	Kefeng Wang <wangkefeng.wang@huawei.com>,
	John Hubbard <jhubbard@nvidia.com>, Zi Yan <ziy@nvidia.com>,
	Barry Song <21cnbao@gmail.com>,
	Alistair Popple <apopple@nvidia.com>,
	Yang Shi <shy828301@gmail.com>,
	Nicholas Piggin <npiggin@gmail.com>,
	Christophe Leroy <christophe.leroy@csgroup.eu>,
	"Aneesh Kumar K.V" <aneesh.kumar@kernel.org>,
	"Naveen N. Rao" <naveen.n.rao@linux.ibm.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	linux-arm-kernel@lists.infradead.org, x86@kernel.org,
	linuxppc-dev@lists.ozlabs.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v5 21/25] arm64/mm: Implement new [get_and_]clear_full_ptes() batch APIs
Date: Tue, 13 Feb 2024 16:43:11 +0000	[thread overview]
Message-ID: <ZcucHyb1OBG677gx@FVFF77S0Q05N.cambridge.arm.com> (raw)
In-Reply-To: <20240202080756.1453939-22-ryan.roberts@arm.com>

On Fri, Feb 02, 2024 at 08:07:52AM +0000, Ryan Roberts wrote:
> Optimize the contpte implementation to fix some of the
> exit/munmap/dontneed performance regression introduced by the initial
> contpte commit. Subsequent patches will solve it entirely.
> 
> During exit(), munmap() or madvise(MADV_DONTNEED), mappings must be
> cleared. Previously this was done 1 PTE at a time. But the core-mm
> supports batched clear via the new [get_and_]clear_full_ptes() APIs. So
> let's implement those APIs and for fully covered contpte mappings, we no
> longer need to unfold the contpte. This significantly reduces unfolding
> operations, reducing the number of tlbis that must be issued.
> 
> Tested-by: John Hubbard <jhubbard@nvidia.com>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
>  arch/arm64/include/asm/pgtable.h | 67 ++++++++++++++++++++++++++++++++
>  arch/arm64/mm/contpte.c          | 17 ++++++++
>  2 files changed, 84 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> index c07f0d563733..ad04adb7b87f 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -965,6 +965,37 @@ static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
>  	return pte;
>  }
>  
> +static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr,
> +				pte_t *ptep, unsigned int nr, int full)
> +{
> +	for (;;) {
> +		__ptep_get_and_clear(mm, addr, ptep);
> +		if (--nr == 0)
> +			break;
> +		ptep++;
> +		addr += PAGE_SIZE;
> +	}
> +}

The loop construct is a bit odd; can't this be:

	while (nr--) {
		__ptep_get_and_clear(mm, addr, ptep);
		ptep++;
		addr += PAGE_SIZE;
	}

... or:

	do {
		__ptep_get_and_clear(mm, addr, ptep);
		ptep++;
		addr += PAGE_SIZE;
	} while (--nr);

... ?

Otherwise, this looks good to me.

Mark.

> +
> +static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm,
> +				unsigned long addr, pte_t *ptep,
> +				unsigned int nr, int full)
> +{
> +	pte_t pte, tmp_pte;
> +
> +	pte = __ptep_get_and_clear(mm, addr, ptep);
> +	while (--nr) {
> +		ptep++;
> +		addr += PAGE_SIZE;
> +		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
> +		if (pte_dirty(tmp_pte))
> +			pte = pte_mkdirty(pte);
> +		if (pte_young(tmp_pte))
> +			pte = pte_mkyoung(pte);
> +	}
> +	return pte;
> +}
> +
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
>  static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
> @@ -1167,6 +1198,11 @@ extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte);
>  extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep);
>  extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr,
>  				pte_t *ptep, pte_t pte, unsigned int nr);
> +extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr,
> +				pte_t *ptep, unsigned int nr, int full);
> +extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
> +				unsigned long addr, pte_t *ptep,
> +				unsigned int nr, int full);
>  extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
>  				unsigned long addr, pte_t *ptep);
>  extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
> @@ -1254,6 +1290,35 @@ static inline void pte_clear(struct mm_struct *mm,
>  	__pte_clear(mm, addr, ptep);
>  }
>  
> +#define clear_full_ptes clear_full_ptes
> +static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr,
> +				pte_t *ptep, unsigned int nr, int full)
> +{
> +	if (likely(nr == 1)) {
> +		contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
> +		__clear_full_ptes(mm, addr, ptep, nr, full);
> +	} else {
> +		contpte_clear_full_ptes(mm, addr, ptep, nr, full);
> +	}
> +}
> +
> +#define get_and_clear_full_ptes get_and_clear_full_ptes
> +static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm,
> +				unsigned long addr, pte_t *ptep,
> +				unsigned int nr, int full)
> +{
> +	pte_t pte;
> +
> +	if (likely(nr == 1)) {
> +		contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
> +		pte = __get_and_clear_full_ptes(mm, addr, ptep, nr, full);
> +	} else {
> +		pte = contpte_get_and_clear_full_ptes(mm, addr, ptep, nr, full);
> +	}
> +
> +	return pte;
> +}
> +
>  #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
>  static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
>  				unsigned long addr, pte_t *ptep)
> @@ -1338,6 +1403,8 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
>  #define set_pte					__set_pte
>  #define set_ptes				__set_ptes
>  #define pte_clear				__pte_clear
> +#define clear_full_ptes				__clear_full_ptes
> +#define get_and_clear_full_ptes			__get_and_clear_full_ptes
>  #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
>  #define ptep_get_and_clear			__ptep_get_and_clear
>  #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
> index c85e64baf03b..80346108450b 100644
> --- a/arch/arm64/mm/contpte.c
> +++ b/arch/arm64/mm/contpte.c
> @@ -207,6 +207,23 @@ void contpte_set_ptes(struct mm_struct *mm, unsigned long addr,
>  }
>  EXPORT_SYMBOL(contpte_set_ptes);
>  
> +void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr,
> +				pte_t *ptep, unsigned int nr, int full)
> +{
> +	contpte_try_unfold_partial(mm, addr, ptep, nr);
> +	__clear_full_ptes(mm, addr, ptep, nr, full);
> +}
> +EXPORT_SYMBOL(contpte_clear_full_ptes);
> +
> +pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
> +				unsigned long addr, pte_t *ptep,
> +				unsigned int nr, int full)
> +{
> +	contpte_try_unfold_partial(mm, addr, ptep, nr);
> +	return __get_and_clear_full_ptes(mm, addr, ptep, nr, full);
> +}
> +EXPORT_SYMBOL(contpte_get_and_clear_full_ptes);
> +
>  int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
>  					unsigned long addr, pte_t *ptep)
>  {
> -- 
> 2.25.1
> 


  reply	other threads:[~2024-02-13 16:43 UTC|newest]

Thread overview: 80+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-02  8:07 [PATCH v5 00/25] Transparent Contiguous PTEs for User Mappings Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 01/25] mm: Clarify the spec for set_ptes() Ryan Roberts
2024-02-12 12:03   ` David Hildenbrand
2024-02-02  8:07 ` [PATCH v5 02/25] mm: thp: Batch-collapse PMD with set_ptes() Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 03/25] mm: Make pte_next_pfn() a wrapper around pte_advance_pfn() Ryan Roberts
2024-02-12 12:14   ` David Hildenbrand
2024-02-12 14:10     ` Ryan Roberts
2024-02-12 14:29       ` David Hildenbrand
2024-02-12 21:34         ` Ryan Roberts
2024-02-13  9:54           ` David Hildenbrand
2024-02-02  8:07 ` [PATCH v5 04/25] arm/mm: Convert pte_next_pfn() to pte_advance_pfn() Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 05/25] arm64/mm: " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 06/25] powerpc/mm: " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 07/25] x86/mm: " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 08/25] mm: Remove pte_next_pfn() and replace with pte_advance_pfn() Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 09/25] arm64/mm: set_pte(): New layer to manage contig bit Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 10/25] arm64/mm: set_ptes()/set_pte_at(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 11/25] arm64/mm: pte_clear(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 12/25] arm64/mm: ptep_get_and_clear(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 13/25] arm64/mm: ptep_test_and_clear_young(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 14/25] arm64/mm: ptep_clear_flush_young(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 15/25] arm64/mm: ptep_set_wrprotect(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 16/25] arm64/mm: ptep_set_access_flags(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 17/25] arm64/mm: ptep_get(): " Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 18/25] arm64/mm: Split __flush_tlb_range() to elide trailing DSB Ryan Roberts
2024-02-12 12:44   ` David Hildenbrand
2024-02-12 13:05     ` Ryan Roberts
2024-02-12 13:15       ` David Hildenbrand
2024-02-12 13:27         ` Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 19/25] arm64/mm: Wire up PTE_CONT for user mappings Ryan Roberts
2024-02-12 12:00   ` Mark Rutland
2024-02-12 12:59     ` Ryan Roberts
2024-02-12 13:54       ` David Hildenbrand
2024-02-12 14:45         ` Ryan Roberts
2024-02-12 15:26           ` David Hildenbrand
2024-02-12 15:34             ` Ryan Roberts
2024-02-12 16:24               ` David Hildenbrand
2024-02-13 15:29                 ` Ryan Roberts
2024-02-12 15:30       ` Ryan Roberts
2024-02-12 20:38         ` Ryan Roberts
2024-02-13 10:01           ` David Hildenbrand
2024-02-13 12:06           ` Ryan Roberts
2024-02-13 12:19             ` David Hildenbrand
2024-02-13 13:06               ` Ryan Roberts
2024-02-13 13:13                 ` David Hildenbrand
2024-02-13 13:20                   ` Ryan Roberts
2024-02-13 13:22                     ` David Hildenbrand
2024-02-13 13:24                       ` Ryan Roberts
2024-02-13 13:33                     ` Ard Biesheuvel
2024-02-13 13:45                       ` David Hildenbrand
2024-02-13 14:02                         ` Ryan Roberts
2024-02-13 14:05                           ` David Hildenbrand
2024-02-13 14:08                             ` Ard Biesheuvel
2024-02-13 14:21                               ` Ryan Roberts
2024-02-13 12:02       ` Mark Rutland
2024-02-13 13:03         ` Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 20/25] arm64/mm: Implement new wrprotect_ptes() batch API Ryan Roberts
2024-02-13 16:31   ` Mark Rutland
2024-02-13 16:36     ` Ryan Roberts
2024-02-02  8:07 ` [PATCH v5 21/25] arm64/mm: Implement new [get_and_]clear_full_ptes() batch APIs Ryan Roberts
2024-02-13 16:43   ` Mark Rutland [this message]
2024-02-13 16:48     ` Ryan Roberts
2024-02-13 16:53       ` Mark Rutland
2024-02-02  8:07 ` [PATCH v5 22/25] mm: Add pte_batch_hint() to reduce scanning in folio_pte_batch() Ryan Roberts
2024-02-12 13:43   ` David Hildenbrand
2024-02-12 15:00     ` Ryan Roberts
2024-02-12 15:47     ` Ryan Roberts
2024-02-12 16:27       ` David Hildenbrand
2024-02-02  8:07 ` [PATCH v5 23/25] arm64/mm: Implement pte_batch_hint() Ryan Roberts
2024-02-12 13:46   ` David Hildenbrand
2024-02-13 16:54   ` Mark Rutland
2024-02-02  8:07 ` [PATCH v5 24/25] arm64/mm: __always_inline to improve fork() perf Ryan Roberts
2024-02-13 16:55   ` Mark Rutland
2024-02-02  8:07 ` [PATCH v5 25/25] arm64/mm: Automatically fold contpte mappings Ryan Roberts
2024-02-13 17:44   ` Mark Rutland
2024-02-13 18:05     ` Ryan Roberts
2024-02-08 17:34 ` [PATCH v5 00/25] Transparent Contiguous PTEs for User Mappings Mark Rutland
2024-02-09  8:54   ` Ryan Roberts
2024-02-09 22:16     ` David Hildenbrand
2024-02-09 23:52       ` Ryan Roberts

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=ZcucHyb1OBG677gx@FVFF77S0Q05N.cambridge.arm.com \
    --to=mark.rutland@arm.com \
    --cc=21cnbao@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@kernel.org \
    --cc=apopple@nvidia.com \
    --cc=ardb@kernel.org \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=christophe.leroy@csgroup.eu \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@redhat.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jhubbard@nvidia.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=maz@kernel.org \
    --cc=mingo@redhat.com \
    --cc=naveen.n.rao@linux.ibm.com \
    --cc=npiggin@gmail.com \
    --cc=ryabinin.a.a@gmail.com \
    --cc=ryan.roberts@arm.com \
    --cc=shy828301@gmail.com \
    --cc=tglx@linutronix.de \
    --cc=wangkefeng.wang@huawei.com \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --cc=ziy@nvidia.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;
as well as URLs for NNTP newsgroup(s).