Re: [PATCH] Add support for usbfs zerocopy.
From: Sasha Levin
Date: Wed Feb 24 2016 - 14:30:20 EST
On 11/25/2015 07:19 PM, Steinar H. Gunderson wrote:
> Add a new interface for userspace to preallocate memory that can be
> used with usbfs. This gives two primary benefits:
>
> - Zerocopy; data no longer needs to be copied between the userspace
> and the kernel, but can instead be read directly by the driver from
> userspace's buffers. This works for all kinds of transfers (even if
> nonsensical for control and interrupt transfers); isochronous also
> no longer need to memset() the buffer to zero to avoid leaking kernel data.
>
> - Once the buffers are allocated, USB transfers can no longer fail due to
> memory fragmentation; previously, long-running programs could run into
> problems finding a large enough contiguous memory chunk, especially on
> embedded systems or at high rates.
>
> Memory is allocated by using mmap() against the usbfs file descriptor,
> and similarly deallocated by munmap(). Once memory has been allocated,
> using it as pointers to a bulk or isochronous operation means you will
> automatically get zerocopy behavior. Note that this also means you cannot
> modify outgoing data until the transfer is complete. The same holds for
> data on the same cache lines as incoming data; DMA modifying them at the
> same time could lead to your changes being overwritten.
>
> There's a new capability USBDEVFS_CAP_MMAP that userspace can query to see
> if the running kernel supports this functionality, if just trying mmap() is
> not acceptable.
>
> Largely based on a patch by Markus Rechberger with some updates. The original
> patch can be found at:
>
> http://sundtek.de/support/devio_mmap_v0.4.diff
>
> Signed-off-by: Steinar H. Gunderson <sesse@xxxxxxxxxx>
> Signed-off-by: Markus Rechberger <mrechberger@xxxxxxxxx>
> Acked-by: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>
Hi,
I'm seeing the following warning while fuzzing:
[ 1595.188189] WARNING: CPU: 3 PID: 26063 at mm/page_alloc.c:3207 __alloc_pages_nodemask+0x960/0x29e0()
[ 1595.188287] Modules linked in:
[ 1595.188316] CPU: 3 PID: 26063 Comm: syz-executor Not tainted 4.5.0-rc5-next-20160223-sasha-00022-g03b30f1-dirty #2982
[ 1595.188362] 1ffff1001460ce89 ffff8800a30674d0 ffffffffa03cecad ffffffff00000003
[ 1595.188380] fffffbfff5829420 0000000041b58ab3 ffffffffabb334e2 ffffffffa03ceb15
[ 1595.188395] ffffffff9e5964c0 0000000041b58ab3 ffffffffabb4e542 ffffffff9e6ee830
[ 1595.188401] Call Trace:
[ 1595.188445] dump_stack (lib/dump_stack.c:53)
[ 1595.188529] warn_slowpath_common (kernel/panic.c:483)
[ 1595.188552] warn_slowpath_null (kernel/panic.c:517)
[ 1595.188561] __alloc_pages_nodemask (mm/page_alloc.c:3207 mm/page_alloc.c:3467)
[ 1595.188768] alloc_pages_current (mm/mempolicy.c:2088)
[ 1595.188784] alloc_kmem_pages (mm/page_alloc.c:3648)
[ 1595.188802] kmalloc_order (mm/slab_common.c:1014)
[ 1595.188819] __kmalloc (include/linux/slab.h:397 include/linux/slab.h:404 mm/slub.c:3573)
[ 1595.188870] hcd_buffer_alloc (include/linux/slab.h:477 drivers/usb/core/buffer.c:130)
[ 1595.188934] usb_alloc_coherent (drivers/usb/core/usb.c:736)
[ 1595.188941] usbdev_mmap (drivers/usb/core/devio.c:243)
[ 1595.189014] mmap_region (mm/mmap.c:1502)
[ 1595.189335] do_mmap (mm/mmap.c:1282)
[ 1595.189352] vm_mmap_pgoff (mm/util.c:335)
[ 1595.189384] SyS_mmap_pgoff (mm/mmap.c:1331 mm/mmap.c:1289)
[ 1595.189429] SyS_mmap (arch/x86/kernel/sys_x86_64.c:86)
[ 1595.189437] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:200)
Thanks,
Sasha