Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Mime-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain; charset=UTF-8
Date:   Wed, 07 Sep 2022 14:26:52 +1000
Message-Id: <CMPVUZ3AI9Z5.3QHIUCJE5KOF@bobo>
Cc:     <linux-kernel@vger.kernel.org>, <linuxppc-dev@lists.ozlabs.org>
Subject: Re: [PATCH] powerpc/book3s: Inline first level of
 update_mmu_cache()
From:   "Nicholas Piggin" <npiggin@gmail.com>
To:     "Christophe Leroy" <christophe.leroy@csgroup.eu>,
        "Michael Ellerman" <mpe@ellerman.id.au>
References: <bea5ad0de7f83eff256116816d46c84fa0a444de.1662370698.git.christophe.leroy@csgroup.eu>
In-Reply-To: <bea5ad0de7f83eff256116816d46c84fa0a444de.1662370698.git.christophe.leroy@csgroup.eu>
Precedence: bulk

On Mon Sep 5, 2022 at 7:38 PM AEST, Christophe Leroy wrote:
> update_mmu_cache() voids when hash page tables are not used.
> On PPC32 that means when MMU_FTR_HPTE_TABLE is not defined.
> On PPC64 that means when RADIX is enabled.
>
> Rename core part of update_mmu_cache() as __update_mmu_cache()
> and include the initial verification in an inlined caller.

Reivewed-by: Nicholas Piggin <npiggin@gmail.com>

>
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
> ---
>  arch/powerpc/include/asm/book3s/pgtable.h | 15 ++++++++++-----
>  arch/powerpc/mm/book3s32/mmu.c            |  4 +---
>  arch/powerpc/mm/book3s64/hash_utils.c     |  5 +----
>  3 files changed, 12 insertions(+), 12 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/inc=
lude/asm/book3s/pgtable.h
> index e8269434ecbe..d18b748ea3ae 100644
> --- a/arch/powerpc/include/asm/book3s/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/pgtable.h
> @@ -25,7 +25,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file,=
 unsigned long pfn,
>  				     unsigned long size, pgprot_t vma_prot);
>  #define __HAVE_PHYS_MEM_ACCESS_PROT
> =20
> -#if defined(CONFIG_PPC32) || defined(CONFIG_PPC_64S_HASH_MMU)
> +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long addres=
s, pte_t *ptep);
> +
>  /*
>   * This gets called at the end of handling a page fault, when
>   * the kernel has put a new PTE into the page table for the process.
> @@ -35,10 +36,14 @@ extern pgprot_t phys_mem_access_prot(struct file *fil=
e, unsigned long pfn,
>   * corresponding HPTE into the hash table ahead of time, instead of
>   * waiting for the inevitable extra hash-table miss exception.
>   */
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,=
 pte_t *ptep);
> -#else
> -static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned=
 long address, pte_t *ptep) {}
> -#endif
> +static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned=
 long address, pte_t *ptep)
> +{
> +	if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE))
> +		return;
> +	if (radix_enabled())
> +		return;
> +	__update_mmu_cache(vma, address, ptep);
> +}
> =20
>  #endif /* __ASSEMBLY__ */
>  #endif
> diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mm=
u.c
> index a96b73006dfb..7053eb229b4f 100644
> --- a/arch/powerpc/mm/book3s32/mmu.c
> +++ b/arch/powerpc/mm/book3s32/mmu.c
> @@ -314,11 +314,9 @@ static void hash_preload(struct mm_struct *mm, unsig=
ned long ea)
>   *
>   * This must always be called with the pte lock held.
>   */
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
> +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long addres=
s,
>  		      pte_t *ptep)
>  {
> -	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
> -		return;
>  	/*
>  	 * We don't need to worry about _PAGE_PRESENT here because we are
>  	 * called with either mm->page_table_lock held or ptl lock held
> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book=
3s64/hash_utils.c
> index 363a9447d63d..ced1107b1677 100644
> --- a/arch/powerpc/mm/book3s64/hash_utils.c
> +++ b/arch/powerpc/mm/book3s64/hash_utils.c
> @@ -1781,7 +1781,7 @@ static void hash_preload(struct mm_struct *mm, pte_=
t *ptep, unsigned long ea,
>   *
>   * This must always be called with the pte lock held.
>   */
> -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
> +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long addres=
s,
>  		      pte_t *ptep)
>  {
>  	/*
> @@ -1791,9 +1791,6 @@ void update_mmu_cache(struct vm_area_struct *vma, u=
nsigned long address,
>  	unsigned long trap;
>  	bool is_exec;
> =20
> -	if (radix_enabled())
> -		return;
> -
>  	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
>  	if (!pte_young(*ptep) || address >=3D TASK_SIZE)
>  		return;
> --=20
> 2.37.1