Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1499305

Re: [RFC 0/6] Module for tracking/accounting shared memory buffers

From Al Viro <viro@ZenIV.linux.org.uk>
Newsgroups linux.kernel
Subject Re: [RFC 0/6] Module for tracking/accounting shared memory buffers
Date 2016-10-12 02:50 +0200
Message-ID <srfU5-5mL-1@gated-at.bofh.it> (permalink)
References <srf7H-4Py-7@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Tue, Oct 11, 2016 at 04:50:04PM -0700, Ruchi Kandoi wrote:

> memtrack maintains a per-process list of shared buffer references, which is
> exported to userspace as /proc/[pid]/memtrack.  Buffers can be optionally
> "tagged" with a short string: for example, Android userspace would use this
> tag to identify whether buffers were allocated on behalf of the camera stack,
> GL, etc.  memtrack also exports the VMAs associated with these buffers so
> that pages already included in the process's mm counters aren't double-counted.
> 
> Shared-buffer allocators can hook into memtrack by embedding
> struct memtrack_buffer in their buffer metadata, calling
> memtrack_buffer_{init,remove} at buffer allocation and free time, and
> memtrack_buffer_{install,uninstall} when a userspace process takes or
> drops a reference to the buffer.  For fd-backed buffers like dma-bufs, hooks in
> fdtable.c and fork.c automatically notify memtrack when references are added or
> removed from a process's fd table.
> 
> This patchstack adds memtrack hooks into dma-buf and ion.  If there's upstream
> interest in memtrack, it can be extended to other memory allocators as well,
> such as GEM implementations.

No, with a side of Hell, No.  Not to mention anything else,
	* descriptor tables do not belong to any specific task_struct and
actions done by one show up in all who share that thing.
	* shared descriptor table does not imply belonging to the same
group.
	* shared descriptor table can become unshared at any point, invisibly
for that Fine Piece Of Software.
	* while we are at it, blocking allocation under several spinlocks
(and with interrupts disabled, for good measure) is generally considered
a bloody bad idea.

That - just from the quick look through that patchset.  Bringing task_struct
into the API is already sufficient for a NAK.

Back to linux.kernel | Previous | NextPrevious in thread | Next in thread | Find similar | Unroll thread


Thread

[RFC 0/6] Module for tracking/accounting shared memory buffers Ruchi Kandoi <kandoiruchi@google.com> - 2016-10-12 02:00 +0200
  [RFC 1/6] fs: add installed and uninstalled file_operations Ruchi Kandoi <kandoiruchi@google.com> - 2016-10-12 02:00 +0200
  [RFC 4/6] memtrack: Adds the accounting to keep track of all mmaped/unmapped pages. Ruchi Kandoi <kandoiruchi@google.com> - 2016-10-12 02:00 +0200
  [RFC 5/6] memtrack: Add memtrack accounting for forked processes. Ruchi Kandoi <kandoiruchi@google.com> - 2016-10-12 02:00 +0200
  [RFC 6/6] drivers: staging: ion: add ION_IOC_TAG ioctl Ruchi Kandoi <kandoiruchi@google.com> - 2016-10-12 02:00 +0200
    Re: [RFC 6/6] drivers: staging: ion: add ION_IOC_TAG ioctl "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2016-10-12 05:40 +0200
  [RFC 2/6] drivers: misc: add memtrack Ruchi Kandoi <kandoiruchi@google.com> - 2016-10-12 02:00 +0200
  Re: [RFC 0/6] Module for tracking/accounting shared memory buffers Al Viro <viro@ZenIV.linux.org.uk> - 2016-10-12 02:50 +0200
  Re: [RFC 0/6] Module for tracking/accounting shared memory buffers Rob Clark <robdclark@gmail.com> - 2016-10-12 03:20 +0200
  Re: [RFC 0/6] Module for tracking/accounting shared memory buffers Dave Hansen <dave.hansen@linux.intel.com> - 2016-10-12 19:30 +0200

csiph-web