Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 28 Aug 2018 15:46:38 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Nicholas Piggin <npiggin@gmail.com>
Cc:     Will Deacon <will.deacon@arm.com>, linux-kernel@vger.kernel.org,
        benh@au1.ibm.com, torvalds@linux-foundation.org,
        catalin.marinas@arm.com, linux-arm-kernel@lists.infradead.org
Subject: Re: [RFC PATCH 08/11] asm-generic/tlb: Track freeing of page-table
 directories in struct mmu_gather
Message-ID: <20180828134638.GK24082@hirez.programming.kicks-ass.net>
References: <1535125966-7666-1-git-send-email-will.deacon@arm.com>
 <1535125966-7666-9-git-send-email-will.deacon@arm.com>
 <20180827144457.3f4036e3@roar.ozlabs.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20180827144457.3f4036e3@roar.ozlabs.ibm.com>
User-Agent: Mutt/1.10.0 (2018-05-17)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Aug 27, 2018 at 02:44:57PM +1000, Nicholas Piggin wrote:

> powerpc may be able to use the unmap granule thing to improve
> its page size dependent flushes, but it might prefer to go
> a different way and track start-end for different page sizes.

I don't really see how tracking multiple ranges would help much with
THP. The ranges would end up being almost the same if there is a good
mix of page sizes.

But something like:

void tlb_flush_one(struct mmu_gather *tlb, unsigned long addr)
{
	if (tlb->cleared_ptes && (addr << BITS_PER_LONG - PAGE_SHIFT))
		tblie_pte(addr);
	if (tlb->cleared_pmds && (addr << BITS_PER_LONG - PMD_SHIFT))
		tlbie_pmd(addr);
	if (tlb->cleared_puds && (addr << BITS_PER_LONG - PUD_SHIFT))
		tlbie_pud(addr);
}

void tlb_flush_range(struct mmu_gather *tlb)
{
	unsigned long stride = 1UL << tlb_get_unmap_shift(tlb);
	unsigned long addr;

	for (addr = tlb->start; addr < tlb->end; addr += stride)
		tlb_flush_one(tlb, addr);

	ptesync();
}

Should workd I think. You'll only issue multiple TLBIEs on the
boundaries, not every stride.

And for hugetlb the above should be optimal, since stride and
tlb->cleared_* match up 1:1.