Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.32 as permitted sender) client-ip=23.128.96.32;
Message-ID: <a70f900a-164f-4155-b9f5-800878f7a446@sifive.com>
Date:   Sat, 28 Oct 2023 14:07:41 -0500
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v5 3/4] riscv: Make __flush_tlb_range() loop over pte
 instead of flushing the whole tlb
Content-Language: en-US
To:     Alexandre Ghiti <alexghiti@rivosinc.com>
Cc:     Andrew Jones <ajones@ventanamicro.com>,
        Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>,
        Will Deacon <will@kernel.org>,
        "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Nick Piggin <npiggin@gmail.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Mayuresh Chitale <mchitale@ventanamicro.com>,
        Vincent Chen <vincent.chen@sifive.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>, linux-arch@vger.kernel.org,
        linux-mm@kvack.org, linux-riscv@lists.infradead.org,
        linux-kernel@vger.kernel.org, Samuel Holland <samuel@sholland.org>,
        Lad Prabhakar <prabhakar.csengg@gmail.com>
References: <20231019140151.21629-1-alexghiti@rivosinc.com>
 <20231019140151.21629-4-alexghiti@rivosinc.com>
From:   Samuel Holland <samuel.holland@sifive.com>
In-Reply-To: <20231019140151.21629-4-alexghiti@rivosinc.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 2023-10-19 9:01 AM, Alexandre Ghiti wrote:
> Currently, when the range to flush covers more than one page (a 4K page or
> a hugepage), __flush_tlb_range() flushes the whole tlb. Flushing the whole
> tlb comes with a greater cost than flushing a single entry so we should
> flush single entries up to a certain threshold so that:
> threshold * cost of flushing a single entry < cost of flushing the whole
> tlb.
> 
> Co-developed-by: Mayuresh Chitale <mchitale@ventanamicro.com>
> Signed-off-by: Mayuresh Chitale <mchitale@ventanamicro.com>
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
> Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> # On RZ/Five SMARC
> ---
>  arch/riscv/include/asm/sbi.h      |   3 -
>  arch/riscv/include/asm/tlbflush.h |   3 +
>  arch/riscv/kernel/sbi.c           |  32 +++------
>  arch/riscv/mm/tlbflush.c          | 115 +++++++++++++++---------------
>  4 files changed, 72 insertions(+), 81 deletions(-)
> 
> diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
> index 12dfda6bb924..0892f4421bc4 100644
> --- a/arch/riscv/include/asm/sbi.h
> +++ b/arch/riscv/include/asm/sbi.h
> @@ -280,9 +280,6 @@ void sbi_set_timer(uint64_t stime_value);
>  void sbi_shutdown(void);
>  void sbi_send_ipi(unsigned int cpu);
>  int sbi_remote_fence_i(const struct cpumask *cpu_mask);
> -int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
> -			   unsigned long start,
> -			   unsigned long size);
>  
>  int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
>  				unsigned long start,
> diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
> index f5c4fb0ae642..170a49c531c6 100644
> --- a/arch/riscv/include/asm/tlbflush.h
> +++ b/arch/riscv/include/asm/tlbflush.h
> @@ -11,6 +11,9 @@
>  #include <asm/smp.h>
>  #include <asm/errata_list.h>
>  
> +#define FLUSH_TLB_MAX_SIZE      ((unsigned long)-1)
> +#define FLUSH_TLB_NO_ASID       ((unsigned long)-1)
> +
>  #ifdef CONFIG_MMU
>  extern unsigned long asid_mask;
>  
> diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
> index c672c8ba9a2a..5a62ed1da453 100644
> --- a/arch/riscv/kernel/sbi.c
> +++ b/arch/riscv/kernel/sbi.c
> @@ -11,6 +11,7 @@
>  #include <linux/reboot.h>
>  #include <asm/sbi.h>
>  #include <asm/smp.h>
> +#include <asm/tlbflush.h>
>  
>  /* default SBI version is 0.1 */
>  unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT;
> @@ -376,32 +377,15 @@ int sbi_remote_fence_i(const struct cpumask *cpu_mask)
>  }
>  EXPORT_SYMBOL(sbi_remote_fence_i);
>  
> -/**
> - * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
> - *			     harts for the specified virtual address range.
> - * @cpu_mask: A cpu mask containing all the target harts.
> - * @start: Start of the virtual address
> - * @size: Total size of the virtual address range.
> - *
> - * Return: 0 on success, appropriate linux error code otherwise.
> - */
> -int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
> -			   unsigned long start,
> -			   unsigned long size)
> -{
> -	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
> -			    cpu_mask, start, size, 0, 0);
> -}
> -EXPORT_SYMBOL(sbi_remote_sfence_vma);
> -
>  /**
>   * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
> - * remote harts for a virtual address range belonging to a specific ASID.
> + * remote harts for a virtual address range belonging to a specific ASID or not.
>   *
>   * @cpu_mask: A cpu mask containing all the target harts.
>   * @start: Start of the virtual address
>   * @size: Total size of the virtual address range.
> - * @asid: The value of address space identifier (ASID).
> + * @asid: The value of address space identifier (ASID), or FLUSH_TLB_NO_ASID
> + * for flushing all address spaces.
>   *
>   * Return: 0 on success, appropriate linux error code otherwise.
>   */
> @@ -410,8 +394,12 @@ int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
>  				unsigned long size,
>  				unsigned long asid)
>  {
> -	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
> -			    cpu_mask, start, size, asid, 0);
> +	if (asid == FLUSH_TLB_NO_ASID)
> +		return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
> +				    cpu_mask, start, size, 0, 0);
> +	else
> +		return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
> +				    cpu_mask, start, size, asid, 0);
>  }
>  EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
>  
> diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
> index 5933744df91a..c27ba720e35f 100644
> --- a/arch/riscv/mm/tlbflush.c
> +++ b/arch/riscv/mm/tlbflush.c
> @@ -9,28 +9,50 @@
>  
>  static inline void local_flush_tlb_all_asid(unsigned long asid)
>  {
> -	__asm__ __volatile__ ("sfence.vma x0, %0"
> -			:
> -			: "r" (asid)
> -			: "memory");
> +	if (asid != FLUSH_TLB_NO_ASID)
> +		__asm__ __volatile__ ("sfence.vma x0, %0"
> +				:
> +				: "r" (asid)
> +				: "memory");
> +	else
> +		local_flush_tlb_all();
>  }
>  
>  static inline void local_flush_tlb_page_asid(unsigned long addr,
>  		unsigned long asid)
>  {
> -	__asm__ __volatile__ ("sfence.vma %0, %1"
> -			:
> -			: "r" (addr), "r" (asid)
> -			: "memory");
> +	if (asid != FLUSH_TLB_NO_ASID)
> +		__asm__ __volatile__ ("sfence.vma %0, %1"
> +				:
> +				: "r" (addr), "r" (asid)
> +				: "memory");
> +	else
> +		local_flush_tlb_page(addr);
>  }
>  
> -static inline void local_flush_tlb_range(unsigned long start,
> -		unsigned long size, unsigned long stride)
> +/*
> + * Flush entire TLB if number of entries to be flushed is greater
> + * than the threshold below.
> + */
> +static unsigned long tlb_flush_all_threshold __read_mostly = 64;
> +
> +static void local_flush_tlb_range_threshold_asid(unsigned long start,
> +						 unsigned long size,
> +						 unsigned long stride,
> +						 unsigned long asid)
>  {
> -	if (size <= stride)
> -		local_flush_tlb_page(start);
> -	else
> -		local_flush_tlb_all();
> +	u16 nr_ptes_in_range = DIV_ROUND_UP(size, stride);

The result of this division could easily overflow a u16, which makes this code
do the wrong thing if the remainder is small. With this fixed:

Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>

> +	int i;
> +
> +	if (nr_ptes_in_range > tlb_flush_all_threshold) {
> +		local_flush_tlb_all_asid(asid);
> +		return;
> +	}
> +
> +	for (i = 0; i < nr_ptes_in_range; ++i) {
> +		local_flush_tlb_page_asid(start, asid);
> +		start += stride;
> +	}
>  }
>  
>  static inline void local_flush_tlb_range_asid(unsigned long start,
> @@ -38,8 +60,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
>  {
>  	if (size <= stride)
>  		local_flush_tlb_page_asid(start, asid);
> -	else
> +	else if (size == FLUSH_TLB_MAX_SIZE)
>  		local_flush_tlb_all_asid(asid);
> +	else
> +		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
>  }
>  
>  static void __ipi_flush_tlb_all(void *info)
> @@ -52,7 +76,7 @@ void flush_tlb_all(void)
>  	if (riscv_use_ipi_for_rfence())
>  		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
>  	else
> -		sbi_remote_sfence_vma(NULL, 0, -1);
> +		sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID);
>  }
>  
>  struct flush_tlb_range_data {
> @@ -69,18 +93,12 @@ static void __ipi_flush_tlb_range_asid(void *info)
>  	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
>  }
>  
> -static void __ipi_flush_tlb_range(void *info)
> -{
> -	struct flush_tlb_range_data *d = info;
> -
> -	local_flush_tlb_range(d->start, d->size, d->stride);
> -}
> -
>  static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
>  			      unsigned long size, unsigned long stride)
>  {
>  	struct flush_tlb_range_data ftd;
>  	struct cpumask *cmask = mm_cpumask(mm);
> +	unsigned long asid = FLUSH_TLB_NO_ASID;
>  	unsigned int cpuid;
>  	bool broadcast;
>  
> @@ -90,39 +108,24 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
>  	cpuid = get_cpu();
>  	/* check if the tlbflush needs to be sent to other CPUs */
>  	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
> -	if (static_branch_unlikely(&use_asid_allocator)) {
> -		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
> -
> -		if (broadcast) {
> -			if (riscv_use_ipi_for_rfence()) {
> -				ftd.asid = asid;
> -				ftd.start = start;
> -				ftd.size = size;
> -				ftd.stride = stride;
> -				on_each_cpu_mask(cmask,
> -						 __ipi_flush_tlb_range_asid,
> -						 &ftd, 1);
> -			} else
> -				sbi_remote_sfence_vma_asid(cmask,
> -							   start, size, asid);
> -		} else {
> -			local_flush_tlb_range_asid(start, size, stride, asid);
> -		}
> +
> +	if (static_branch_unlikely(&use_asid_allocator))
> +		asid = atomic_long_read(&mm->context.id) & asid_mask;
> +
> +	if (broadcast) {
> +		if (riscv_use_ipi_for_rfence()) {
> +			ftd.asid = asid;
> +			ftd.start = start;
> +			ftd.size = size;
> +			ftd.stride = stride;
> +			on_each_cpu_mask(cmask,
> +					 __ipi_flush_tlb_range_asid,
> +					 &ftd, 1);
> +		} else
> +			sbi_remote_sfence_vma_asid(cmask,
> +						   start, size, asid);
>  	} else {
> -		if (broadcast) {
> -			if (riscv_use_ipi_for_rfence()) {
> -				ftd.asid = 0;
> -				ftd.start = start;
> -				ftd.size = size;
> -				ftd.stride = stride;
> -				on_each_cpu_mask(cmask,
> -						 __ipi_flush_tlb_range,
> -						 &ftd, 1);
> -			} else
> -				sbi_remote_sfence_vma(cmask, start, size);
> -		} else {
> -			local_flush_tlb_range(start, size, stride);
> -		}
> +		local_flush_tlb_range_asid(start, size, stride, asid);
>  	}
>  
>  	put_cpu();
> @@ -130,7 +133,7 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
>  
>  void flush_tlb_mm(struct mm_struct *mm)
>  {
> -	__flush_tlb_range(mm, 0, -1, PAGE_SIZE);
> +	__flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
>  }
>  
>  void flush_tlb_mm_range(struct mm_struct *mm,