From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
To: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: linux-sgx@vger.kernel.org
Subject: Re: [PATCH v2 00/17] v23 updates
Date: Tue, 17 Sep 2019 22:08:31 +0300 [thread overview]
Message-ID: <20190917190752.GF10244@linux.intel.com> (raw)
In-Reply-To: <20190916183742.GK18871@linux.intel.com>
On Mon, Sep 16, 2019 at 11:37:43AM -0700, Sean Christopherson wrote:
> On Mon, Sep 16, 2019 at 11:01:43AM +0300, Jarkko Sakkinen wrote:
> > On Mon, Sep 16, 2019 at 10:58:06AM +0300, Jarkko Sakkinen wrote:
> > > On Mon, Sep 16, 2019 at 07:14:00AM +0300, Jarkko Sakkinen wrote:
> > > > My flush of updates for v23. Contains a bunch of clean ups and bug
> > > > fixes with the main focus on the page reclaimer. The main goal has
> > > > been to disclose all the other possibilities for failure after
> > > > ENCLS[EBLOCK] other than EPCM conflict when the whole EPC is
> > > > invalidated.
> > >
> > > I have at least one more update to the reclaimer but want to merge these
> > > first.
> > >
> > > It adds optional struct epc_page **reclaimed_page to
> > > sgx_reclaim_pages(). If NULL, the function will just append everything
> > > to the free pool. Otherwise, it will use it to return one of the
> > > reclaimed pages if there are any.
> > >
> > > sgx_alloc_page() then does the following when @reclaim=true:
> > >
> > > 1. If page in free page pool, take one.
> > > 2. If not, try to reclaim one.
> > > 3. If nothing was reclaimed -ENOMEM.
> > >
> > > Right now sgx_alloc_page() can in theory take however long.
> > >
> > > I wonder why we do not return -ENOMEM also when @reclaim=false. Where
> > > did this returning -EBUSY came from? Can't recall.
> >
> > Checked. I guess it is just for ELDU flow but does not make sense
> > otherwise. Tuning sgx_vma_fault() should be enough. I mean with
> > the above change we would start to return -EBUSY sometimes in
> > OOM situations.
>
> Returning -EBUSY is done to differentiate between the case where reclaim
> is possible, i.e. sgx_active_page_list is *not* empty, but disallowed, and
> the case where reclaim is impossible, i.e. sgx_active_page_list is empty.
> If reclaim is impossible then the fault handler should signal SIGSEGV so
> that processes start dying and/or killing enclaves to free up EPC.
>
> Barring a kernel bug, I don't think it's possible for sgx_active_page_list
> to be empty when only the driver is supported, but both KVM and EPC cgroup
> support will introduce (relatively common) scenarios where there are no
> pages on the active/reclaimable list. Technically we probably don't need
> the -EBUSY logic, but my vote is to keep it since it's a nice fallback in
> case there are kernel bugs.
OK, my root question is I guess, why want to differentiate those cases?
Both are as far as I'm concerned situations where there is no memory
available.
And now my changes after these patches add yet another case: active
page list was not empty but nothing could be reclaimed. Is the
granularity really needed for something here?
/Jarkko
next prev parent reply other threads:[~2019-09-17 19:08 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-16 4:14 [PATCH v2 00/17] v23 updates Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 01/17] selftest/x86/sgx: Remove encl_piggy.h Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 02/17] x86/sgx: Clean up internal includes Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 03/17] x86/sgx: Write backing storage only if EWB is successful Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 04/17] x86/sgx: Rename 'j' as 'cnt' in sgx_reclaim_pages() Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 05/17] x86/sgx: Turn encls_failed() as inline function Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 06/17] x86/sgx: Move sgx_einit() to encls.c Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 07/17] x86/sgx: Remove pages in sgx_reclaimer_write() Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 08/17] x86/sgx: Calculate page index " Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 09/17] x86/sgx: Move SGX_ENCL_DEAD check to sgx_reclaimer_write() Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 10/17] x86/sgx: Free VA slot when the EWB flow fails Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 11/17] x86/sgx: Call sgx_encl_destroy() " Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 12/17] x86/sgx: Open code sgx_reclaimer_get() and sgx_reclaimer_put() Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 13/17] x86/sgx: Introduce sgx_can_reclaim() Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 14/17] x86/sgx: Replace section->free_cnt with a global sgx_nr_free_pages Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 15/17] x86/sgx: sgx_vma_access(): Do not return -ECANCELED on invalid TCS pages Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 16/17] x86/sgx: Introduce sgx_encl_get_backing() Jarkko Sakkinen
2019-09-16 4:14 ` [PATCH v2 17/17] x86/sgx: Fix pages in the BLOCKED state ending up to the free pool Jarkko Sakkinen
2019-09-16 7:58 ` [PATCH v2 00/17] v23 updates Jarkko Sakkinen
2019-09-16 8:01 ` Jarkko Sakkinen
2019-09-16 18:37 ` Sean Christopherson
2019-09-17 19:08 ` Jarkko Sakkinen [this message]
2019-09-17 19:27 ` Sean Christopherson
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=20190917190752.GF10244@linux.intel.com \
--to=jarkko.sakkinen@linux.intel.com \
--cc=linux-sgx@vger.kernel.org \
--cc=sean.j.christopherson@intel.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.