diff mbox series

[3/4] riscv: enable MMU_GATHER_RCU_TABLE_FREE for SMP && MMU

Message ID 20231219175046.2496-4-jszhang@kernel.org (mailing list archive)
State Accepted
Commit 69be3fb111e73bd025ce6d2322371da5aa497c70
Headers show
Series riscv: support fast gup | expand

Checks

Context Check Description
conchuod/vmtest-for-next-PR success PR summary
conchuod/patch-3-test-1 success .github/scripts/patches/tests/build_rv32_defconfig.sh
conchuod/patch-3-test-2 success .github/scripts/patches/tests/build_rv64_clang_allmodconfig.sh
conchuod/patch-3-test-3 success .github/scripts/patches/tests/build_rv64_gcc_allmodconfig.sh
conchuod/patch-3-test-4 success .github/scripts/patches/tests/build_rv64_nommu_k210_defconfig.sh
conchuod/patch-3-test-5 success .github/scripts/patches/tests/build_rv64_nommu_virt_defconfig.sh
conchuod/patch-3-test-6 success .github/scripts/patches/tests/checkpatch.sh
conchuod/patch-3-test-7 success .github/scripts/patches/tests/dtb_warn_rv64.sh
conchuod/patch-3-test-8 success .github/scripts/patches/tests/header_inline.sh
conchuod/patch-3-test-9 success .github/scripts/patches/tests/kdoc.sh
conchuod/patch-3-test-10 success .github/scripts/patches/tests/module_param.sh
conchuod/patch-3-test-11 success .github/scripts/patches/tests/verify_fixes.sh
conchuod/patch-3-test-12 success .github/scripts/patches/tests/verify_signedoff.sh

Commit Message

Jisheng Zhang Dec. 19, 2023, 5:50 p.m. UTC
In order to implement fast gup we need to ensure that the page
table walker is protected from page table pages being freed from
under it.

riscv situation is more complicated than other architectures: some
riscv platforms may use IPI to perform TLB shootdown, for example,
those platforms which support AIA, usually the riscv_ipi_for_rfence is
true on these platforms; some riscv platforms may rely on the SBI to
perform TLB shootdown, usually the riscv_ipi_for_rfence is false on
these platforms. To keep software pagetable walkers safe in this case
we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in
include/asm-generic/tlb.h for more details.

This patch enables MMU_GATHER_RCU_TABLE_FREE, then use

*tlb_remove_page_ptdesc() for those platforms which use IPI to perform
TLB shootdown;

*tlb_remove_ptdesc() for those platforms which use SBI to perform TLB
shootdown;

Both case mean that disabling interrupts will block the free and
protect the fast gup page walker.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
---
 arch/riscv/Kconfig               |  1 +
 arch/riscv/include/asm/pgalloc.h | 23 ++++++++++++++++++-----
 arch/riscv/include/asm/tlb.h     | 18 ++++++++++++++++++
 3 files changed, 37 insertions(+), 5 deletions(-)

Comments

Alexandre Ghiti Dec. 31, 2023, 6:32 a.m. UTC | #1
On 19/12/2023 18:50, Jisheng Zhang wrote:
> In order to implement fast gup we need to ensure that the page
> table walker is protected from page table pages being freed from
> under it.
>
> riscv situation is more complicated than other architectures: some
> riscv platforms may use IPI to perform TLB shootdown, for example,
> those platforms which support AIA, usually the riscv_ipi_for_rfence is
> true on these platforms; some riscv platforms may rely on the SBI to
> perform TLB shootdown, usually the riscv_ipi_for_rfence is false on
> these platforms. To keep software pagetable walkers safe in this case
> we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
> comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in
> include/asm-generic/tlb.h for more details.
>
> This patch enables MMU_GATHER_RCU_TABLE_FREE, then use
>
> *tlb_remove_page_ptdesc() for those platforms which use IPI to perform
> TLB shootdown;
>
> *tlb_remove_ptdesc() for those platforms which use SBI to perform TLB
> shootdown;


Can you elaborate a bit more on what those functions do differently and 
why we need to differentiate IPI vs SBI TLB shootdown? I don't 
understand this.

Thanks,

Alex


> Both case mean that disabling interrupts will block the free and
> protect the fast gup page walker.
>
> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> ---
>   arch/riscv/Kconfig               |  1 +
>   arch/riscv/include/asm/pgalloc.h | 23 ++++++++++++++++++-----
>   arch/riscv/include/asm/tlb.h     | 18 ++++++++++++++++++
>   3 files changed, 37 insertions(+), 5 deletions(-)
>
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index 24c1799e2ec4..d3555173d9f4 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -147,6 +147,7 @@ config RISCV
>   	select IRQ_FORCED_THREADING
>   	select KASAN_VMALLOC if KASAN
>   	select LOCK_MM_AND_FIND_VMA
> +	select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU
>   	select MODULES_USE_ELF_RELA if MODULES
>   	select MODULE_SECTIONS if MODULES
>   	select OF
> diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
> index 3c5e3bd15f46..deaf971253a2 100644
> --- a/arch/riscv/include/asm/pgalloc.h
> +++ b/arch/riscv/include/asm/pgalloc.h
> @@ -102,7 +102,10 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
>   		struct ptdesc *ptdesc = virt_to_ptdesc(pud);
>   
>   		pagetable_pud_dtor(ptdesc);
> -		tlb_remove_page_ptdesc(tlb, ptdesc);
> +		if (riscv_use_ipi_for_rfence())
> +			tlb_remove_page_ptdesc(tlb, ptdesc);
> +		else
> +			tlb_remove_ptdesc(tlb, ptdesc);
>   	}
>   }
>   
> @@ -136,8 +139,12 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
>   static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
>   				  unsigned long addr)
>   {
> -	if (pgtable_l5_enabled)
> -		tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
> +	if (pgtable_l5_enabled) {
> +		if (riscv_use_ipi_for_rfence())
> +			tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
> +		else
> +			tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
> +	}
>   }
>   #endif /* __PAGETABLE_PMD_FOLDED */
>   
> @@ -169,7 +176,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
>   	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
>   
>   	pagetable_pmd_dtor(ptdesc);
> -	tlb_remove_page_ptdesc(tlb, ptdesc);
> +	if (riscv_use_ipi_for_rfence())
> +		tlb_remove_page_ptdesc(tlb, ptdesc);
> +	else
> +		tlb_remove_ptdesc(tlb, ptdesc);
>   }
>   
>   #endif /* __PAGETABLE_PMD_FOLDED */
> @@ -180,7 +190,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
>   	struct ptdesc *ptdesc = page_ptdesc(pte);
>   
>   	pagetable_pte_dtor(ptdesc);
> -	tlb_remove_page_ptdesc(tlb, ptdesc);
> +	if (riscv_use_ipi_for_rfence())
> +		tlb_remove_page_ptdesc(tlb, ptdesc);
> +	else
> +		tlb_remove_ptdesc(tlb, ptdesc);
>   }
>   #endif /* CONFIG_MMU */
>   
> diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
> index 1eb5682b2af6..a0b8b853503f 100644
> --- a/arch/riscv/include/asm/tlb.h
> +++ b/arch/riscv/include/asm/tlb.h
> @@ -10,6 +10,24 @@ struct mmu_gather;
>   
>   static void tlb_flush(struct mmu_gather *tlb);
>   
> +#ifdef CONFIG_MMU
> +#include <linux/swap.h>
> +
> +/*
> + * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
> + * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
> + * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
> + * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
> + * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
> + * for more details.
> + */
> +static inline void __tlb_remove_table(void *table)
> +{
> +	free_page_and_swap_cache(table);
> +}
> +
> +#endif /* CONFIG_MMU */
> +
>   #define tlb_flush tlb_flush
>   #include <asm-generic/tlb.h>
>
Jisheng Zhang Jan. 2, 2024, 3:23 a.m. UTC | #2
On Sun, Dec 31, 2023 at 07:32:47AM +0100, Alexandre Ghiti wrote:
> On 19/12/2023 18:50, Jisheng Zhang wrote:
> > In order to implement fast gup we need to ensure that the page
> > table walker is protected from page table pages being freed from
> > under it.
> > 
> > riscv situation is more complicated than other architectures: some
> > riscv platforms may use IPI to perform TLB shootdown, for example,
> > those platforms which support AIA, usually the riscv_ipi_for_rfence is
> > true on these platforms; some riscv platforms may rely on the SBI to
> > perform TLB shootdown, usually the riscv_ipi_for_rfence is false on
> > these platforms. To keep software pagetable walkers safe in this case
> > we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
> > comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in
> > include/asm-generic/tlb.h for more details.
> > 
> > This patch enables MMU_GATHER_RCU_TABLE_FREE, then use
> > 
> > *tlb_remove_page_ptdesc() for those platforms which use IPI to perform
> > TLB shootdown;
> > 
> > *tlb_remove_ptdesc() for those platforms which use SBI to perform TLB
> > shootdown;
> 
>
> Can you elaborate a bit more on what those functions do differently and why
> we need to differentiate IPI vs SBI TLB shootdown? I don't understand this.

Hi Alex,

If IPI, the local_irq_save in lockless_pages_from_mm() of fast gup code
path will block page table pages from being freed, I think the comments
there is execellent.

If SBI, the local_irq_save in lockless_pages_from_mm() can't acchieve
the goal however. Because local_irq_save() only disable S-privilege IPI irq,
it can't disable M-privilege's, which the SBI implementation use to
shootdown TLB entry. So we need MMU_GATHER_RCU_TABLE_FREE helper for
SBI case.

Thanks
 
> 
> > Both case mean that disabling interrupts will block the free and
> > protect the fast gup page walker.
> > 
> > Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> > ---
> >   arch/riscv/Kconfig               |  1 +
> >   arch/riscv/include/asm/pgalloc.h | 23 ++++++++++++++++++-----
> >   arch/riscv/include/asm/tlb.h     | 18 ++++++++++++++++++
> >   3 files changed, 37 insertions(+), 5 deletions(-)
> > 
> > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > index 24c1799e2ec4..d3555173d9f4 100644
> > --- a/arch/riscv/Kconfig
> > +++ b/arch/riscv/Kconfig
> > @@ -147,6 +147,7 @@ config RISCV
> >   	select IRQ_FORCED_THREADING
> >   	select KASAN_VMALLOC if KASAN
> >   	select LOCK_MM_AND_FIND_VMA
> > +	select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU
> >   	select MODULES_USE_ELF_RELA if MODULES
> >   	select MODULE_SECTIONS if MODULES
> >   	select OF
> > diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
> > index 3c5e3bd15f46..deaf971253a2 100644
> > --- a/arch/riscv/include/asm/pgalloc.h
> > +++ b/arch/riscv/include/asm/pgalloc.h
> > @@ -102,7 +102,10 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
> >   		struct ptdesc *ptdesc = virt_to_ptdesc(pud);
> >   		pagetable_pud_dtor(ptdesc);
> > -		tlb_remove_page_ptdesc(tlb, ptdesc);
> > +		if (riscv_use_ipi_for_rfence())
> > +			tlb_remove_page_ptdesc(tlb, ptdesc);
> > +		else
> > +			tlb_remove_ptdesc(tlb, ptdesc);
> >   	}
> >   }
> > @@ -136,8 +139,12 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
> >   static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
> >   				  unsigned long addr)
> >   {
> > -	if (pgtable_l5_enabled)
> > -		tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
> > +	if (pgtable_l5_enabled) {
> > +		if (riscv_use_ipi_for_rfence())
> > +			tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
> > +		else
> > +			tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
> > +	}
> >   }
> >   #endif /* __PAGETABLE_PMD_FOLDED */
> > @@ -169,7 +176,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
> >   	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
> >   	pagetable_pmd_dtor(ptdesc);
> > -	tlb_remove_page_ptdesc(tlb, ptdesc);
> > +	if (riscv_use_ipi_for_rfence())
> > +		tlb_remove_page_ptdesc(tlb, ptdesc);
> > +	else
> > +		tlb_remove_ptdesc(tlb, ptdesc);
> >   }
> >   #endif /* __PAGETABLE_PMD_FOLDED */
> > @@ -180,7 +190,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
> >   	struct ptdesc *ptdesc = page_ptdesc(pte);
> >   	pagetable_pte_dtor(ptdesc);
> > -	tlb_remove_page_ptdesc(tlb, ptdesc);
> > +	if (riscv_use_ipi_for_rfence())
> > +		tlb_remove_page_ptdesc(tlb, ptdesc);
> > +	else
> > +		tlb_remove_ptdesc(tlb, ptdesc);
> >   }
> >   #endif /* CONFIG_MMU */
> > diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
> > index 1eb5682b2af6..a0b8b853503f 100644
> > --- a/arch/riscv/include/asm/tlb.h
> > +++ b/arch/riscv/include/asm/tlb.h
> > @@ -10,6 +10,24 @@ struct mmu_gather;
> >   static void tlb_flush(struct mmu_gather *tlb);
> > +#ifdef CONFIG_MMU
> > +#include <linux/swap.h>
> > +
> > +/*
> > + * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
> > + * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
> > + * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
> > + * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
> > + * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
> > + * for more details.
> > + */
> > +static inline void __tlb_remove_table(void *table)
> > +{
> > +	free_page_and_swap_cache(table);
> > +}
> > +
> > +#endif /* CONFIG_MMU */
> > +
> >   #define tlb_flush tlb_flush
> >   #include <asm-generic/tlb.h>
Alexandre Ghiti Jan. 4, 2024, 10:45 a.m. UTC | #3
Hi Jisheng,

On 02/01/2024 04:23, Jisheng Zhang wrote:
> On Sun, Dec 31, 2023 at 07:32:47AM +0100, Alexandre Ghiti wrote:
>> On 19/12/2023 18:50, Jisheng Zhang wrote:
>>> In order to implement fast gup we need to ensure that the page
>>> table walker is protected from page table pages being freed from
>>> under it.
>>>
>>> riscv situation is more complicated than other architectures: some
>>> riscv platforms may use IPI to perform TLB shootdown, for example,
>>> those platforms which support AIA, usually the riscv_ipi_for_rfence is
>>> true on these platforms; some riscv platforms may rely on the SBI to
>>> perform TLB shootdown, usually the riscv_ipi_for_rfence is false on
>>> these platforms. To keep software pagetable walkers safe in this case
>>> we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
>>> comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in
>>> include/asm-generic/tlb.h for more details.
>>>
>>> This patch enables MMU_GATHER_RCU_TABLE_FREE, then use
>>>
>>> *tlb_remove_page_ptdesc() for those platforms which use IPI to perform
>>> TLB shootdown;
>>>
>>> *tlb_remove_ptdesc() for those platforms which use SBI to perform TLB
>>> shootdown;
>>
>> Can you elaborate a bit more on what those functions do differently and why
>> we need to differentiate IPI vs SBI TLB shootdown? I don't understand this.
> Hi Alex,
>
> If IPI, the local_irq_save in lockless_pages_from_mm() of fast gup code
> path will block page table pages from being freed, I think the comments
> there is execellent.
>
> If SBI, the local_irq_save in lockless_pages_from_mm() can't acchieve
> the goal however. Because local_irq_save() only disable S-privilege IPI irq,
> it can't disable M-privilege's, which the SBI implementation use to
> shootdown TLB entry. So we need MMU_GATHER_RCU_TABLE_FREE helper for
> SBI case.


Ok, I get it now, can you add the following link to your commit 
description 
https://elixir.bootlin.com/linux/v6.6/source/mm/mmu_gather.c#L162 ? It 
describes the problem very clearly.


> Thanks
>   
>>> Both case mean that disabling interrupts will block the free and
>>> protect the fast gup page walker.
>>>
>>> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
>>> ---
>>>    arch/riscv/Kconfig               |  1 +
>>>    arch/riscv/include/asm/pgalloc.h | 23 ++++++++++++++++++-----
>>>    arch/riscv/include/asm/tlb.h     | 18 ++++++++++++++++++
>>>    3 files changed, 37 insertions(+), 5 deletions(-)
>>>
>>> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
>>> index 24c1799e2ec4..d3555173d9f4 100644
>>> --- a/arch/riscv/Kconfig
>>> +++ b/arch/riscv/Kconfig
>>> @@ -147,6 +147,7 @@ config RISCV
>>>    	select IRQ_FORCED_THREADING
>>>    	select KASAN_VMALLOC if KASAN
>>>    	select LOCK_MM_AND_FIND_VMA
>>> +	select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU
>>>    	select MODULES_USE_ELF_RELA if MODULES
>>>    	select MODULE_SECTIONS if MODULES
>>>    	select OF
>>> diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
>>> index 3c5e3bd15f46..deaf971253a2 100644
>>> --- a/arch/riscv/include/asm/pgalloc.h
>>> +++ b/arch/riscv/include/asm/pgalloc.h
>>> @@ -102,7 +102,10 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
>>>    		struct ptdesc *ptdesc = virt_to_ptdesc(pud);
>>>    		pagetable_pud_dtor(ptdesc);
>>> -		tlb_remove_page_ptdesc(tlb, ptdesc);
>>> +		if (riscv_use_ipi_for_rfence())
>>> +			tlb_remove_page_ptdesc(tlb, ptdesc);
>>> +		else
>>> +			tlb_remove_ptdesc(tlb, ptdesc);
>>>    	}
>>>    }
>>> @@ -136,8 +139,12 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
>>>    static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
>>>    				  unsigned long addr)
>>>    {
>>> -	if (pgtable_l5_enabled)
>>> -		tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
>>> +	if (pgtable_l5_enabled) {
>>> +		if (riscv_use_ipi_for_rfence())
>>> +			tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
>>> +		else
>>> +			tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
>>> +	}
>>>    }
>>>    #endif /* __PAGETABLE_PMD_FOLDED */
>>> @@ -169,7 +176,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
>>>    	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
>>>    	pagetable_pmd_dtor(ptdesc);
>>> -	tlb_remove_page_ptdesc(tlb, ptdesc);
>>> +	if (riscv_use_ipi_for_rfence())
>>> +		tlb_remove_page_ptdesc(tlb, ptdesc);
>>> +	else
>>> +		tlb_remove_ptdesc(tlb, ptdesc);
>>>    }
>>>    #endif /* __PAGETABLE_PMD_FOLDED */
>>> @@ -180,7 +190,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
>>>    	struct ptdesc *ptdesc = page_ptdesc(pte);
>>>    	pagetable_pte_dtor(ptdesc);
>>> -	tlb_remove_page_ptdesc(tlb, ptdesc);
>>> +	if (riscv_use_ipi_for_rfence())
>>> +		tlb_remove_page_ptdesc(tlb, ptdesc);
>>> +	else
>>> +		tlb_remove_ptdesc(tlb, ptdesc);
>>>    }
>>>    #endif /* CONFIG_MMU */
>>> diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
>>> index 1eb5682b2af6..a0b8b853503f 100644
>>> --- a/arch/riscv/include/asm/tlb.h
>>> +++ b/arch/riscv/include/asm/tlb.h
>>> @@ -10,6 +10,24 @@ struct mmu_gather;
>>>    static void tlb_flush(struct mmu_gather *tlb);
>>> +#ifdef CONFIG_MMU
>>> +#include <linux/swap.h>
>>> +
>>> +/*
>>> + * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
>>> + * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
>>> + * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
>>> + * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
>>> + * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h


A direct link would be better, I did not find the comment you mention 
here and even though, it can still move around later.

And then you can add:

Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>

Thanks!

Alex


>>> + * for more details.
>>> + */
>>> +static inline void __tlb_remove_table(void *table)
>>> +{
>>> +	free_page_and_swap_cache(table);
>>> +}
>>> +
>>> +#endif /* CONFIG_MMU */
>>> +
>>>    #define tlb_flush tlb_flush
>>>    #include <asm-generic/tlb.h>
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv
diff mbox series

Patch

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 24c1799e2ec4..d3555173d9f4 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -147,6 +147,7 @@  config RISCV
 	select IRQ_FORCED_THREADING
 	select KASAN_VMALLOC if KASAN
 	select LOCK_MM_AND_FIND_VMA
+	select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU
 	select MODULES_USE_ELF_RELA if MODULES
 	select MODULE_SECTIONS if MODULES
 	select OF
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index 3c5e3bd15f46..deaf971253a2 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -102,7 +102,10 @@  static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 		struct ptdesc *ptdesc = virt_to_ptdesc(pud);
 
 		pagetable_pud_dtor(ptdesc);
-		tlb_remove_page_ptdesc(tlb, ptdesc);
+		if (riscv_use_ipi_for_rfence())
+			tlb_remove_page_ptdesc(tlb, ptdesc);
+		else
+			tlb_remove_ptdesc(tlb, ptdesc);
 	}
 }
 
@@ -136,8 +139,12 @@  static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				  unsigned long addr)
 {
-	if (pgtable_l5_enabled)
-		tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
+	if (pgtable_l5_enabled) {
+		if (riscv_use_ipi_for_rfence())
+			tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
+		else
+			tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
+	}
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
@@ -169,7 +176,10 @@  static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
 
 	pagetable_pmd_dtor(ptdesc);
-	tlb_remove_page_ptdesc(tlb, ptdesc);
+	if (riscv_use_ipi_for_rfence())
+		tlb_remove_page_ptdesc(tlb, ptdesc);
+	else
+		tlb_remove_ptdesc(tlb, ptdesc);
 }
 
 #endif /* __PAGETABLE_PMD_FOLDED */
@@ -180,7 +190,10 @@  static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	struct ptdesc *ptdesc = page_ptdesc(pte);
 
 	pagetable_pte_dtor(ptdesc);
-	tlb_remove_page_ptdesc(tlb, ptdesc);
+	if (riscv_use_ipi_for_rfence())
+		tlb_remove_page_ptdesc(tlb, ptdesc);
+	else
+		tlb_remove_ptdesc(tlb, ptdesc);
 }
 #endif /* CONFIG_MMU */
 
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 1eb5682b2af6..a0b8b853503f 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -10,6 +10,24 @@  struct mmu_gather;
 
 static void tlb_flush(struct mmu_gather *tlb);
 
+#ifdef CONFIG_MMU
+#include <linux/swap.h>
+
+/*
+ * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
+ * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
+ * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
+ * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
+ * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
+ * for more details.
+ */
+static inline void __tlb_remove_table(void *table)
+{
+	free_page_and_swap_cache(table);
+}
+
+#endif /* CONFIG_MMU */
+
 #define tlb_flush tlb_flush
 #include <asm-generic/tlb.h>