[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20221129152306.54b6d439e2a0ca7ece1d1afa@linux-foundation.org>
Date: Tue, 29 Nov 2022 15:23:06 -0800
From: Andrew Morton <akpm@...ux-foundation.org>
To: Yicong Yang <yangyicong@...wei.com>
Cc: <linux-mm@...ck.org>, <linux-arm-kernel@...ts.infradead.org>,
<x86@...nel.org>, <catalin.marinas@....com>, <will@...nel.org>,
<anshuman.khandual@....com>, <linux-doc@...r.kernel.org>,
<corbet@....net>, <peterz@...radead.org>, <arnd@...db.de>,
<punit.agrawal@...edance.com>, <linux-kernel@...r.kernel.org>,
<darren@...amperecomputing.com>, <yangyicong@...ilicon.com>,
<huzhanyuan@...o.com>, <lipeifeng@...o.com>,
<zhangshiming@...o.com>, <guojian@...o.com>, <realmz6@...il.com>,
<linux-mips@...r.kernel.org>, <openrisc@...ts.librecores.org>,
<linuxppc-dev@...ts.ozlabs.org>, <linux-riscv@...ts.infradead.org>,
<linux-s390@...r.kernel.org>, Barry Song <21cnbao@...il.com>,
<wangkefeng.wang@...wei.com>, <xhao@...ux.alibaba.com>,
<prime.zeng@...ilicon.com>,
Anshuman Khandual <khandual@...ux.vnet.ibm.com>,
Barry Song <baohua@...nel.org>
Subject: Re: [PATCH v7 1/2] mm/tlbbatch: Introduce
arch_tlbbatch_should_defer()
On Thu, 17 Nov 2022 16:26:47 +0800 Yicong Yang <yangyicong@...wei.com> wrote:
> From: Anshuman Khandual <khandual@...ux.vnet.ibm.com>
>
> The entire scheme of deferred TLB flush in reclaim path rests on the
> fact that the cost to refill TLB entries is less than flushing out
> individual entries by sending IPI to remote CPUs. But architecture
> can have different ways to evaluate that. Hence apart from checking
> TTU_BATCH_FLUSH in the TTU flags, rest of the decision should be
> architecture specific.
>
> ...
>
> --- a/arch/x86/include/asm/tlbflush.h
> +++ b/arch/x86/include/asm/tlbflush.h
> @@ -240,6 +240,18 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
> flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
> }
>
> +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
> +{
> + bool should_defer = false;
> +
> + /* If remote CPUs need to be flushed then defer batch the flush */
> + if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
> + should_defer = true;
> + put_cpu();
> +
> + return should_defer;
> +}
> +
> static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
> {
> /*
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 2ec925e5fa6a..a9ab10bc0144 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -685,17 +685,10 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
> */
> static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
> {
> - bool should_defer = false;
> -
> if (!(flags & TTU_BATCH_FLUSH))
> return false;
>
> - /* If remote CPUs need to be flushed then defer batch the flush */
> - if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
> - should_defer = true;
> - put_cpu();
> -
> - return should_defer;
> + return arch_tlbbatch_should_defer(mm);
> }
I think this conversion could have been done better.
should_defer_flush() is compiled if
CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH. So the patch implicitly
assumes that only x86 implements
CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH. Presently true, but what
happens if sparc (for example) wants to set
CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH? Now sparc needs its private
version of arch_tlbbatch_should_defer(), even if that is identical to
x86's.
Wouldn't it be better to make arch_tlbbatch_should_defer() a __weak
function in rmap.c, or a static inline inside #ifndef
ARCH_HAS_ARCH_TLBBATCH_SHOULD_DEFER, or whatever technique best fits?
Powered by blists - more mailing lists