linux-kernel - Re: [PATCH 1/1] powerpc: mm: Check if serialize_against_pte

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <c1ff17e2-902d-87e6-3c1d-fc5db2428b69@linux.ibm.com>
Date:   Tue, 17 Sep 2019 08:26:01 +0530
From:   "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>
To:     Leonardo Bras <leonardo@...ux.ibm.com>,
        linuxppc-dev@...ts.ozlabs.org, linux-kernel@...r.kernel.org
Cc:     Benjamin Herrenschmidt <benh@...nel.crashing.org>,
        Paul Mackerras <paulus@...ba.org>,
        Michael Ellerman <mpe@...erman.id.au>,
        Christophe Leroy <christophe.leroy@....fr>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Mike Rapoport <rppt@...ux.ibm.com>,
        Nicholas Piggin <npiggin@...il.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Jason Gunthorpe <jgg@...pe.ca>,
        Vlastimil Babka <vbabka@...e.cz>,
        Dan Williams <dan.j.williams@...el.com>,
        Christoph Lameter <cl@...ux.com>,
        "Tobin C. Harding" <tobin@...nel.org>,
        Jann Horn <jannh@...gle.com>,
        Jesper Dangaard Brouer <brouer@...hat.com>,
        Souptick Joarder <jrdr.linux@...il.com>,
        Ralph Campbell <rcampbell@...dia.com>,
        Andrey Ryabinin <aryabinin@...tuozzo.com>,
        Davidlohr Bueso <dave@...olabs.net>
Subject: Re: [PATCH 1/1] powerpc: mm: Check if serialize_against_pte_lookup()
 really needs to run

On 9/17/19 2:25 AM, Leonardo Bras wrote:
> If a process (qemu) with a lot of CPUs (128) try to munmap() a large chunk
> of memory (496GB) mapped with THP, it takes an average of 275 seconds,
> which can cause a lot of problems to the load (in qemu case, the guest
> will lock for this time).
> 
> Trying to find the source of this bug, I found out most of this time is
> spent on serialize_against_pte_lookup(). This function will take a lot of
> time in smp_call_function_many() if there is more than a couple CPUs
> running the user process. Since it has to happen to all THP mapped, it will
> take a very long time for large amounts of memory.
> 
> By the docs, serialize_against_pte_lookup() is needed in order to avoid
> pmd_t to pte_t casting inside find_current_mm_pte() to happen concurrently
> with the next part of the functions it's called in.
> It does so by calling a do_nothing() on each CPU in mm->cpu_bitmap[];
> 
> So, by what I could understand, if there is no find_current_mm_pte()
> running, there is no need to call serialize_against_pte_lookup().
> 
> So, to avoid the cost of running serialize_against_pte_lookup(), I propose
> a counter that keeps track of how many find_current_mm_pte() are currently
> running, and if there is none, just skip smp_call_function_many().
> 
> On my workload (qemu), I could see munmap's time reduction from 275 seconds
> to 418ms.
> 
> Signed-off-by: Leonardo Bras <leonardo@...ux.ibm.com>

We could possibly avoid that serialize for a full task exit unmap. ie, 
when tlb->fullmm == 1 . But that won't help the Qemu case because it 
does an umap of the guest ram range for which tlb->fullmm != 1.

> 
> ---
> I need more experienced people's help in order to understand if this is
> really a valid improvement, and if mm_struct is the best place to put such
> counter.
> 
> Thanks!
> ---
>   arch/powerpc/include/asm/pte-walk.h | 3 +++
>   arch/powerpc/mm/book3s64/pgtable.c  | 2 ++
>   include/linux/mm_types.h            | 1 +
>   3 files changed, 6 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/pte-walk.h b/arch/powerpc/include/asm/pte-walk.h
> index 33fa5dd8ee6a..3b82cb3bd563 100644
> --- a/arch/powerpc/include/asm/pte-walk.h
> +++ b/arch/powerpc/include/asm/pte-walk.h
> @@ -40,6 +40,8 @@ static inline pte_t *find_current_mm_pte(pgd_t *pgdir, unsigned long ea,
>   {
>   	pte_t *pte;
>   
> +	atomic64_inc(&current->mm->lockless_ptlookup_count);
> +
>   	VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__);
>   	VM_WARN(pgdir != current->mm->pgd,
>   		"%s lock less page table lookup called on wrong mm\n", __func__);
> @@ -53,6 +55,7 @@ static inline pte_t *find_current_mm_pte(pgd_t *pgdir, unsigned long ea,
>   	if (hshift)
>   		WARN_ON(*hshift);
>   #endif
> +	atomic64_dec(&current->mm->lockless_ptlookup_count);
>   	return pte;
>   }



That is not correct. We need to keep the count updated  across the 
local_irq_disable()/local_irq_enable(). That is we mostly should have a 
variant like start_lockless_pgtbl_walk()/end_lockless_pgtbl_walk(). Also 
there is hash_page_mm which we need to make sure we are protected 
against w.r.t collapse pmd.

>   
> diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
> index 7d0e0d0d22c4..8f6fc2f80071 100644
> --- a/arch/powerpc/mm/book3s64/pgtable.c
> +++ b/arch/powerpc/mm/book3s64/pgtable.c
> @@ -95,6 +95,8 @@ static void do_nothing(void *unused)
>   void serialize_against_pte_lookup(struct mm_struct *mm)
>   {
>   	smp_mb();
> +	if (atomic64_read(&mm->lockless_ptlookup_count) == 0)
> +		return;
>   	smp_call_function_many(mm_cpumask(mm), do_nothing, NULL, 1);
>   }
>   
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 6a7a1083b6fb..97fb2545e967 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -518,6 +518,7 @@ struct mm_struct {
>   #endif
>   	} __randomize_layout;
>   
> +	atomic64_t lockless_ptlookup_count;
>   	/*
>   	 * The mm_cpumask needs to be at the end of mm_struct, because it
>   	 * is dynamically sized based on nr_cpu_ids.
> 

Move that to ppc64 specific mm_context_t.


-aneesh