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:   Sun, 28 Jul 2019 23:26:17 +0530
From:   Bharath Vedartham <linux.bhar@gmail.com>
To:     Hillf Danton <hdanton@sina.com>
Cc:     sivanich@sgi.com, arnd@arndb.de, ira.weiny@intel.com,
        jhubbard@nvidia.com, jglisse@redhat.com,
        gregkh@linuxfoundation.org, william.kucharski@oracle.com,
        hch@lst.de, linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH v3 1/1] sgi-gru: Remove *pte_lookup functions
Message-ID: <20190728175617.GA5391@bharath12345-Inspiron-5559>
References: <1564170120-11882-1-git-send-email-linux.bhar@gmail.com>
 <1564170120-11882-2-git-send-email-linux.bhar@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1564170120-11882-2-git-send-email-linux.bhar@gmail.com>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Sat, Jul 27, 2019 at 05:22:28PM +0800, Hillf Danton wrote:
> 
> On Fri, 26 Jul 2019 12:42:26 -0700 (PDT) Bharath Vedartham wrote:
> > 
> >  static int gru_vtop(struct gru_thread_state *gts, unsigned long vaddr,
> >  		    int write, int atomic, unsigned long *gpa, int *pageshift)
> >  {
> >  	struct mm_struct *mm = gts->ts_mm;
> >  	struct vm_area_struct *vma;
> >  	unsigned long paddr;
> > -	int ret, ps;
> > +	int ret;
> > +	struct page *page;
> >  
> >  	vma = find_vma(mm, vaddr);
> >  	if (!vma)
> > @@ -263,21 +187,33 @@ static int gru_vtop(struct gru_thread_state *gts, unsigned long vaddr,
> >  
> >  	/*
> >  	 * Atomic lookup is faster & usually works even if called in non-atomic
> > -	 * context.
> > +	 * context. get_user_pages_fast does atomic lookup before falling back to
> > +	 * slow gup.
> >  	 */
> >  	rmb();	/* Must/check ms_range_active before loading PTEs */
> > -	ret = atomic_pte_lookup(vma, vaddr, write, &paddr, &ps);
> > -	if (ret) {
> > -		if (atomic)
> > +	if (atomic) {
> > +		ret = __get_user_pages_fast(vaddr, 1, write, &page);
> > +		if (!ret)
> >  			goto upm;
> > -		if (non_atomic_pte_lookup(vma, vaddr, write, &paddr, &ps))
> > +	} else {
> > +		ret = get_user_pages_fast(vaddr, 1, write, &page);
> > +		if (!ret)
> >  			goto inval;
> >  	}
> > +
> > +	paddr = page_to_phys(page);
> 
> You may drop find_vma() above if PageHuge(page) makes sense here.
I don't think it does. Hugepage support is still incomplete for this
driver.

Thank you
Bharath
> > +	put_user_page(page);
> > +
> > +	if (unlikely(is_vm_hugetlb_page(vma)))
> > +		*pageshift = HPAGE_SHIFT;
> > +	else
> > +		*pageshift = PAGE_SHIFT;
> > +
> >  	if (is_gru_paddr(paddr))
> >  		goto inval;
> > -	paddr = paddr & ~((1UL << ps) - 1);
> > -	*gpa = uv_soc_phys_ram_to_gpa(paddr);
> > -	*pageshift = ps;
> > +	paddr = paddr & ~((1UL << *pageshift) - 1);
> > +	*gpa = uv_soc_phys_ram_to_gpa(paddr);
> > +
> >  	return VTOP_SUCCESS;
> >  
> >  inval:
> > -- 
> > 2.7.4
>