linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
To: Reza Arbab <arbab@linux.vnet.ibm.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org,
	Balbir Singh <bsingharora@gmail.com>,
	Alistair Popple <apopple@au1.ibm.com>
Subject: Re: [PATCH v3 4/5] powerpc/mm: add radix__remove_section_mapping()
Date: Mon, 19 Dec 2016 15:18:07 +0530	[thread overview]
Message-ID: <87wpewtfl4.fsf@linux.vnet.ibm.com> (raw)
In-Reply-To: <1481831443-22761-5-git-send-email-arbab@linux.vnet.ibm.com>

Reza Arbab <arbab@linux.vnet.ibm.com> writes:

> Tear down and free the four-level page tables of the linear mapping
> during memory hotremove.
>
> We borrow the basic structure of remove_pagetable() and friends from the
> identically-named x86 functions.
>

Can you add more details here, which explain why we don't need to follow
the RCU page table free when doing memory hotunplug ?

> Signed-off-by: Reza Arbab <arbab@linux.vnet.ibm.com>
> ---
>  arch/powerpc/include/asm/book3s/64/radix.h |   1 +
>  arch/powerpc/mm/pgtable-book3s64.c         |   2 +-
>  arch/powerpc/mm/pgtable-radix.c            | 163 +++++++++++++++++++++++++++++
>  3 files changed, 165 insertions(+), 1 deletion(-)
>
....
....


> +static void remove_pte_table(pte_t *pte_start, unsigned long addr,
> +			     unsigned long end)
> +{
> +	unsigned long next;
> +	pte_t *pte;
> +
> +	pte = pte_start + pte_index(addr);
> +	for (; addr < end; addr = next, pte++) {
> +		next = (addr + PAGE_SIZE) & PAGE_MASK;
> +		if (next > end)
> +			next = end;
> +
> +		if (!pte_present(*pte))
> +			continue;
> +
> +		spin_lock(&init_mm.page_table_lock);
> +		pte_clear(&init_mm, addr, pte);
> +		spin_unlock(&init_mm.page_table_lock);
> +	}
> +
> +	flush_tlb_mm(&init_mm);

Why call a flush here. we do that at the end of remove_page_table .
Isn't that sufficient ?

> +}
> +
> +static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
> +			     unsigned long end, unsigned long map_page_size)
> +{
> +	unsigned long next;
> +	pte_t *pte_base;
> +	pmd_t *pmd;
> +
> +	pmd = pmd_start + pmd_index(addr);
> +	for (; addr < end; addr = next, pmd++) {
> +		next = pmd_addr_end(addr, end);
> +
> +		if (!pmd_present(*pmd))
> +			continue;
> +
> +		if (map_page_size == PMD_SIZE) {
> +			spin_lock(&init_mm.page_table_lock);
> +			pte_clear(&init_mm, addr, (pte_t *)pmd);
> +			spin_unlock(&init_mm.page_table_lock);
> +
> +			continue;
> +		}
> +
> +		pte_base = (pte_t *)pmd_page_vaddr(*pmd);
> +		remove_pte_table(pte_base, addr, next);
> +		free_pte_table(pte_base, pmd);
> +	}
> +}
> +
> +static void remove_pud_table(pud_t *pud_start, unsigned long addr,
> +			     unsigned long end, unsigned long map_page_size)
> +{
> +	unsigned long next;
> +	pmd_t *pmd_base;
> +	pud_t *pud;
> +
> +	pud = pud_start + pud_index(addr);
> +	for (; addr < end; addr = next, pud++) {
> +		next = pud_addr_end(addr, end);
> +
> +		if (!pud_present(*pud))
> +			continue;
> +
> +		if (map_page_size == PUD_SIZE) {
> +			spin_lock(&init_mm.page_table_lock);
> +			pte_clear(&init_mm, addr, (pte_t *)pud);
> +			spin_unlock(&init_mm.page_table_lock);
> +
> +			continue;
> +		}
> +
> +		pmd_base = (pmd_t *)pud_page_vaddr(*pud);
> +		remove_pmd_table(pmd_base, addr, next, map_page_size);
> +		free_pmd_table(pmd_base, pud);
> +	}
> +}
> +
> +static void remove_pagetable(unsigned long start, unsigned long end,
> +			     unsigned long map_page_size)
> +{
> +	unsigned long next;
> +	unsigned long addr;
> +	pgd_t *pgd;
> +	pud_t *pud;
> +
> +	for (addr = start; addr < end; addr = next) {
> +		next = pgd_addr_end(addr, end);
> +
> +		pgd = pgd_offset_k(addr);
> +		if (!pgd_present(*pgd))
> +			continue;
> +
> +		pud = (pud_t *)pgd_page_vaddr(*pgd);
> +		remove_pud_table(pud, addr, next, map_page_size);
> +		free_pud_table(pud, pgd);
> +	}
> +
> +	flush_tlb_mm(&init_mm);


So we want to flush the full kernel tlb when we do a hotplug ?
May be check using flush_tlb_kernel_range(). Also that flush_tlb_mm() do
check for mm_is_thread_local(). Do we update init_mm correct to handle
that check ? I assume we want a tlbie() here instead of tlbiel() ?


> +}
> +
>  int radix__create_section_mapping(unsigned long start, unsigned long end)
>  {
>  	unsigned long page_size = 1 << mmu_psize_defs[mmu_linear_psize].shift;
> @@ -482,6 +635,16 @@ int radix__create_section_mapping(unsigned long start, unsigned long end)
>
>  	return 0;
>  }
> +
> +int radix__remove_section_mapping(unsigned long start, unsigned long end)
> +{
> +	unsigned long page_size = 1 << mmu_psize_defs[mmu_linear_psize].shift;
> +
> +	start = _ALIGN_DOWN(start, page_size);
> +	remove_pagetable(start, end, page_size);
> +
> +	return 0;
> +}
>  #endif /* CONFIG_MEMORY_HOTPLUG */
>
>  #ifdef CONFIG_SPARSEMEM_VMEMMAP


-aneesh

  reply	other threads:[~2016-12-19  9:48 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-12-15 19:50 [PATCH v3 0/5] powerpc/mm: enable memory hotplug on radix Reza Arbab
2016-12-15 19:50 ` [PATCH v3 1/5] powerpc/mm: set the radix linear page mapping size Reza Arbab
2016-12-19  8:58   ` Aneesh Kumar K.V
2016-12-19 20:53     ` Benjamin Herrenschmidt
2016-12-20  2:02       ` Aneesh Kumar K.V
2016-12-15 19:50 ` [PATCH v3 2/5] powerpc/mm: refactor {create, remove}_section_mapping() Reza Arbab
2016-12-19  9:00   ` Aneesh Kumar K.V
2016-12-19 18:00     ` [PATCH v3 2/5] powerpc/mm: refactor {create,remove}_section_mapping() Reza Arbab
2016-12-20  5:26   ` Balbir Singh
2016-12-15 19:50 ` [PATCH v3 3/5] powerpc/mm: add radix__create_section_mapping() Reza Arbab
2016-12-19  9:04   ` Aneesh Kumar K.V
2016-12-19 18:06     ` Reza Arbab
2016-12-21  7:03     ` Anshuman Khandual
2016-12-20  6:28   ` Balbir Singh
2016-12-20 15:32     ` Reza Arbab
2016-12-15 19:50 ` [PATCH v3 4/5] powerpc/mm: add radix__remove_section_mapping() Reza Arbab
2016-12-19  9:48   ` Aneesh Kumar K.V [this message]
2016-12-19 18:11     ` Reza Arbab
2016-12-19 20:59     ` Benjamin Herrenschmidt
2016-12-15 19:50 ` [PATCH v3 5/5] powerpc/mm: unstub radix__vmemmap_remove_mapping() Reza Arbab
2016-12-16 14:38 ` [PATCH v3 0/5] powerpc/mm: enable memory hotplug on radix Balbir Singh
2016-12-19 17:58   ` Reza Arbab
2016-12-21  6:54     ` Anshuman Khandual

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=87wpewtfl4.fsf@linux.vnet.ibm.com \
    --to=aneesh.kumar@linux.vnet.ibm.com \
    --cc=apopple@au1.ibm.com \
    --cc=arbab@linux.vnet.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=bsingharora@gmail.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).