linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Nicholas Piggin <npiggin@gmail.com>
To: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: 'Vlastimil Babka' <vbabka@suse.cz>,
	'Alexander Viro' <viro@zeniv.linux.org.uk>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, 'Michal Hocko' <mhocko@kernel.org>,
	netdev@vger.kernel.org, Eric Dumazet <eric.dumazet@gmail.com>
Subject: Re: [PATCH] fs/select: add vmalloc fallback for select(2)
Date: Fri, 23 Sep 2016 17:24:34 +1000	[thread overview]
Message-ID: <20160923172434.7ad8f2e0@roar.ozlabs.ibm.com> (raw)
In-Reply-To: <006101d21565$b60a8a70$221f9f50$@alibaba-inc.com>

On Fri, 23 Sep 2016 14:42:53 +0800
"Hillf Danton" <hillf.zj@alibaba-inc.com> wrote:

> > 
> > The select(2) syscall performs a kmalloc(size, GFP_KERNEL) where size grows
> > with the number of fds passed. We had a customer report page allocation
> > failures of order-4 for this allocation. This is a costly order, so it might
> > easily fail, as the VM expects such allocation to have a lower-order fallback.
> > 
> > Such trivial fallback is vmalloc(), as the memory doesn't have to be
> > physically contiguous. Also the allocation is temporary for the duration of the
> > syscall, so it's unlikely to stress vmalloc too much.
> > 
> > Note that the poll(2) syscall seems to use a linked list of order-0 pages, so
> > it doesn't need this kind of fallback.

How about something like this? (untested)

Eric isn't wrong about vmalloc sucking :)

Thanks,
Nick


---
 fs/select.c | 57 +++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 43 insertions(+), 14 deletions(-)

diff --git a/fs/select.c b/fs/select.c
index 8ed9da5..3b4834c 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -555,6 +555,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 	void *bits;
 	int ret, max_fds;
 	unsigned int size;
+	size_t nr_bytes;
 	struct fdtable *fdt;
 	/* Allocate small arguments on the stack to save memory and be faster */
 	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
@@ -576,21 +577,39 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 	 * since we used fdset we need to allocate memory in units of
 	 * long-words. 
 	 */
-	size = FDS_BYTES(n);
+	ret = -ENOMEM;
 	bits = stack_fds;
-	if (size > sizeof(stack_fds) / 6) {
-		/* Not enough space in on-stack array; must use kmalloc */
+	size = FDS_BYTES(n);
+	nr_bytes = 6 * size;
+
+	if (unlikely(nr_bytes > PAGE_SIZE)) {
+		/* Avoid multi-page allocation if possible */
 		ret = -ENOMEM;
-		bits = kmalloc(6 * size, GFP_KERNEL);
-		if (!bits)
-			goto out_nofds;
+		fds.in = kmalloc(size, GFP_KERNEL);
+		fds.out = kmalloc(size, GFP_KERNEL);
+		fds.ex = kmalloc(size, GFP_KERNEL);
+		fds.res_in = kmalloc(size, GFP_KERNEL);
+		fds.res_out = kmalloc(size, GFP_KERNEL);
+		fds.res_ex = kmalloc(size, GFP_KERNEL);
+
+		if (!(fds.in && fds.out && fds.ex &&
+				fds.res_in && fds.res_out && fds.res_ex))
+			goto out;
+	} else {
+		if (nr_bytes > sizeof(stack_fds)) {
+			/* Not enough space in on-stack array */
+			if (nr_bytes > PAGE_SIZE * 2)
+			bits = kmalloc(nr_bytes, GFP_KERNEL);
+			if (!bits)
+				goto out_nofds;
+		}
+		fds.in      = bits;
+		fds.out     = bits +   size;
+		fds.ex      = bits + 2*size;
+		fds.res_in  = bits + 3*size;
+		fds.res_out = bits + 4*size;
+		fds.res_ex  = bits + 5*size;
 	}
-	fds.in      = bits;
-	fds.out     = bits +   size;
-	fds.ex      = bits + 2*size;
-	fds.res_in  = bits + 3*size;
-	fds.res_out = bits + 4*size;
-	fds.res_ex  = bits + 5*size;
 
 	if ((ret = get_fd_set(n, inp, fds.in)) ||
 	    (ret = get_fd_set(n, outp, fds.out)) ||
@@ -617,8 +636,18 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 		ret = -EFAULT;
 
 out:
-	if (bits != stack_fds)
-		kfree(bits);
+	if (unlikely(nr_bytes > PAGE_SIZE)) {
+		kfree(fds.in);
+		kfree(fds.out);
+		kfree(fds.ex);
+		kfree(fds.res_in);
+		kfree(fds.res_out);
+		kfree(fds.res_ex);
+	} else {
+		if (bits != stack_fds)
+			kfree(bits);
+	}
+
 out_nofds:
 	return ret;
 }
-- 
2.9.3

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2016-09-23  7:24 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-22 15:28 [PATCH] fs/select: add vmalloc fallback for select(2) Vlastimil Babka
2016-09-22 16:24 ` Eric Dumazet
2016-09-22 16:40   ` Vlastimil Babka
2016-09-23  6:42 ` Hillf Danton
2016-09-23  7:24   ` Nicholas Piggin [this message]
2016-09-23 16:47     ` Jason Baron
2016-09-27  8:44       ` Vlastimil Babka
2016-09-27 11:24         ` Nicholas Piggin
2016-09-27 11:37           ` David Laight
2016-09-27 11:42             ` Nicholas Piggin
2016-09-27 11:51               ` Vlastimil Babka
2016-09-28 16:30                 ` David Laight
2016-09-28 20:04                   ` Vlastimil Babka

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=20160923172434.7ad8f2e0@roar.ozlabs.ibm.com \
    --to=npiggin@gmail.com \
    --cc=eric.dumazet@gmail.com \
    --cc=hillf.zj@alibaba-inc.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    /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).