linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Steven Price <steven.price@arm.com>
To: Chinwen Chang <chinwen.chang@mediatek.com>,
	Matthias Brugger <matthias.bgg@gmail.com>,
	Michel Lespinasse <walken@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Vlastimil Babka <vbabka@suse.cz>,
	Daniel Jordan <daniel.m.jordan@oracle.com>,
	Davidlohr Bueso <dbueso@suse.de>,
	Alexey Dobriyan <adobriyan@gmail.com>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Jason Gunthorpe <jgg@ziepe.ca>, Song Liu <songliubraving@fb.com>,
	Jimmy Assarsson <jimmyassarsson@gmail.com>,
	Huang Ying <ying.huang@intel.com>,
	Daniel Kiss <daniel.kiss@arm.com>,
	Laurent Dufour <ldufour@linux.ibm.com>
Cc: linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linux-mediatek@lists.infradead.org,
	linux-fsdevel@vger.kernel.org, wsd_upstream@mediatek.com
Subject: Re: [PATCH v3 3/3] mm: proc: smaps_rollup: do not stall write attempts on mmap_lock
Date: Mon, 17 Aug 2020 09:38:43 +0100	[thread overview]
Message-ID: <db0d40e2-72f3-09d5-c162-9c49218f128f@arm.com> (raw)
In-Reply-To: <1597472419-32314-4-git-send-email-chinwen.chang@mediatek.com>

On 15/08/2020 07:20, Chinwen Chang wrote:
> smaps_rollup will try to grab mmap_lock and go through the whole vma
> list until it finishes the iterating. When encountering large processes,
> the mmap_lock will be held for a longer time, which may block other
> write requests like mmap and munmap from progressing smoothly.
> 
> There are upcoming mmap_lock optimizations like range-based locks, but
> the lock applied to smaps_rollup would be the coarse type, which doesn't
> avoid the occurrence of unpleasant contention.
> 
> To solve aforementioned issue, we add a check which detects whether
> anyone wants to grab mmap_lock for write attempts.
> 
> Change since v1:
> - If current VMA is freed after dropping the lock, it will return
> - incomplete result. To fix this issue, refine the code flow as
> - suggested by Steve. [1]
> 
> Change since v2:
> - When getting back the mmap lock, the address where you stopped last
> - time could now be in the middle of a vma. Add one more check to handle
> - this case as suggested by Michel. [2]
> 
> [1] https://lore.kernel.org/lkml/bf40676e-b14b-44cd-75ce-419c70194783@arm.com/
> [2] https://lore.kernel.org/lkml/CANN689FtCsC71cjAjs0GPspOhgo_HRj+diWsoU1wr98YPktgWg@mail.gmail.com/
> 
> Signed-off-by: Chinwen Chang <chinwen.chang@mediatek.com>
> CC: Steven Price <steven.price@arm.com>
> CC: Michel Lespinasse <walken@google.com>

Reviewed-by: Steven Price <steven.price@arm.com>

> ---
>   fs/proc/task_mmu.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++---
>   1 file changed, 70 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 76e623a..945904e 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -846,7 +846,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
>   	struct mem_size_stats mss;
>   	struct mm_struct *mm;
>   	struct vm_area_struct *vma;
> -	unsigned long last_vma_end = 0;
> +	unsigned long last_vma_end = 0, last_stopped = 0;
>   	int ret = 0;
>   
>   	priv->task = get_proc_task(priv->inode);
> @@ -867,9 +867,76 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
>   
>   	hold_task_mempolicy(priv);
>   
> -	for (vma = priv->mm->mmap; vma; vma = vma->vm_next) {
> -		smap_gather_stats(vma, &mss, 0);
> +	for (vma = priv->mm->mmap; vma;) {
> +		smap_gather_stats(vma, &mss, last_stopped);
> +		last_stopped = 0;
>   		last_vma_end = vma->vm_end;
> +
> +		/*
> +		 * Release mmap_lock temporarily if someone wants to
> +		 * access it for write request.
> +		 */
> +		if (mmap_lock_is_contended(mm)) {
> +			mmap_read_unlock(mm);
> +			ret = mmap_read_lock_killable(mm);
> +			if (ret) {
> +				release_task_mempolicy(priv);
> +				goto out_put_mm;
> +			}
> +
> +			/*
> +			 * After dropping the lock, there are four cases to
> +			 * consider. See the following example for explanation.
> +			 *
> +			 *   +------+------+-----------+
> +			 *   | VMA1 | VMA2 | VMA3      |
> +			 *   +------+------+-----------+
> +			 *   |      |      |           |
> +			 *  4k     8k     16k         400k
> +			 *
> +			 * Suppose we drop the lock after reading VMA2 due to
> +			 * contention, then we get:
> +			 *
> +			 *	last_vma_end = 16k
> +			 *
> +			 * 1) VMA2 is freed, but VMA3 exists:
> +			 *
> +			 *    find_vma(mm, 16k - 1) will return VMA3.
> +			 *    In this case, just continue from VMA3.
> +			 *
> +			 * 2) VMA2 still exists:
> +			 *
> +			 *    find_vma(mm, 16k - 1) will return VMA2.
> +			 *    Iterate the loop like the original one.
> +			 *
> +			 * 3) No more VMAs can be found:
> +			 *
> +			 *    find_vma(mm, 16k - 1) will return NULL.
> +			 *    No more things to do, just break.
> +			 *
> +			 * 4) (last_vma_end - 1) is the middle of a vma (VMA'):
> +			 *
> +			 *    find_vma(mm, 16k - 1) will return VMA' whose range
> +			 *    contains last_vma_end.
> +			 *    Iterate VMA' from last_vma_end.
> +			 */
> +			vma = find_vma(mm, last_vma_end - 1);
> +			/* Case 3 above */
> +			if (!vma)
> +				break;
> +
> +			/* Case 1 above */
> +			if (vma->vm_start >= last_vma_end)
> +				continue;
> +
> +			/* Case 4 above */
> +			if (vma->vm_end > last_vma_end) {
> +				last_stopped = last_vma_end;
> +				continue;

Note that instead of having last_stopped, you could replace the above 
with a direct call:

   smap_gather_stats(vma, &mss, last_vma_end);

I'm not sure which is cleaner though. last_stopped is a bit messy (it's 
easily confused with last_vma_end), but having just the one call site 
for smap_gather_stats() is nice too.

Steve

> +			}
> +		}
> +		/* Case 2 above */
> +		vma = vma->vm_next;
>   	}
>   
>   	show_vma_header_prefix(m, priv->mm->mmap->vm_start,
> 


  parent reply	other threads:[~2020-08-17  8:38 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <1597472419-32314-1-git-send-email-chinwen.chang@mediatek.com>
     [not found] ` <1597472419-32314-3-git-send-email-chinwen.chang@mediatek.com>
2020-08-17  8:38   ` [PATCH v3 2/3] mm: smaps*: extend smap_gather_stats to support specified beginning Steven Price
     [not found] ` <1597472419-32314-4-git-send-email-chinwen.chang@mediatek.com>
2020-08-17  8:38   ` Steven Price [this message]
2020-08-17  9:15     ` [PATCH v3 3/3] mm: proc: smaps_rollup: do not stall write attempts on mmap_lock Chinwen Chang

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=db0d40e2-72f3-09d5-c162-9c49218f128f@arm.com \
    --to=steven.price@arm.com \
    --cc=adobriyan@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=chinwen.chang@mediatek.com \
    --cc=daniel.kiss@arm.com \
    --cc=daniel.m.jordan@oracle.com \
    --cc=dbueso@suse.de \
    --cc=jgg@ziepe.ca \
    --cc=jimmyassarsson@gmail.com \
    --cc=ldufour@linux.ibm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mediatek@lists.infradead.org \
    --cc=matthias.bgg@gmail.com \
    --cc=songliubraving@fb.com \
    --cc=vbabka@suse.cz \
    --cc=walken@google.com \
    --cc=willy@infradead.org \
    --cc=wsd_upstream@mediatek.com \
    --cc=ying.huang@intel.com \
    --subject='Re: [PATCH v3 3/3] mm: proc: smaps_rollup: do not stall write attempts on mmap_lock' \
    /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

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).