Thread (26 messages) 26 messages, 4 authors, 2021-01-08

RE: [PATCH 02/11] mm: call import_iovec() instead of rw_copy_check_uvector() in process_vm_rw()

From: David Laight <hidden>
Date: 2020-09-21 15:44:10
Also in: io-uring, keyrings, linux-arch, linux-arm-kernel, linux-block, linux-fsdevel, linux-mips, linux-mm, linux-s390, linux-scsi, linux-security-module, lkml, netdev, sparclinux

From: Al Viro
Sent: 21 September 2020 16:30

On Mon, Sep 21, 2020 at 03:21:35PM +0000, David Laight wrote:
quoted
You really don't want to be looping through the array twice.
Profiles, please.
I did some profiling of send() v sendmsg() much earlier in the year.
I can't remember the exact details but the extra cost of sendmsg()
is far more than you might expect.
(I was timing sending fully built IPv4 UDP packets using a raw socket.)

About half the difference does away if you change the
copy_from_user() to __copy_from_user() when reading the struct msghdr
and iov[] from userspace (user copy hardening is expensive).

The rest is just code path, my gut feeling is that a lot of that
is in import_iovec().

Remember semdmsg() is likely to be called with an iov count of 1.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help