From: "Jarkko Sakkinen" <jarkko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
To: Haitao Huang
<haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>,
dave.hansen-VuQAYsv1563Yd54FQh9/CA@public.gmane.org,
tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-sgx-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: kai.huang-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org,
reinette.chatre-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org,
zhiquan1.li-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org,
kristen-VuQAYsv1563Yd54FQh9/CA@public.gmane.org,
seanjc-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org,
zhanb-0li6OtcxBFHby3iVrkZq2A@public.gmane.org,
anakrish-0li6OtcxBFHby3iVrkZq2A@public.gmane.org,
mikko.ylinen-VuQAYsv1563Yd54FQh9/CA@public.gmane.org
Subject: Re: [PATCH v3 00/28] Add Cgroup support for SGX EPC memory
Date: Mon, 17 Jul 2023 11:02:16 +0000 [thread overview]
Message-ID: <CU4EA8H87W7J.11BOV563ZK2JX@seitikki> (raw)
In-Reply-To: <20230712230202.47929-1-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
On Wed Jul 12, 2023 at 11:01 PM UTC, Haitao Huang wrote:
> SGX EPC memory allocations are separate from normal RAM allocations, and is
> managed solely by the SGX subsystem. The existing cgroup memory controller
> cannot be used to limit or account for SGX EPC memory, which is a desirable
> feature in some environments, e.g., support for pod level control in a
> Kubernates cluster on a VM or baremetal host [1,2] in those environments.
>
> This patchset implements the support for sgx_epc memory within the misc
> cgroup controller. The user can use the misc cgroup controller to set and
> enforce a max limit on total EPC usage per cgroup. The implementation
> reports current usage and events of reaching the limit per cgroup as well
> as the total system capacity.
>
> This work was originally authored by Sean Christopherson a few years ago,
> and previously modified by Kristen C. Accardi to work with more recent
> kernels, and to utilize the misc cgroup controller rather than a custom
> controller. Now I updated the patches based on review comments on the V2
> series[3], simplified a few aspects of the implementation/design and fixed
> some stability issues found from testing, while keeping the same user space
> facing interfaces.
>
> The patchset adds support for multiple LRUs to track both reclaimable EPC
> pages (i.e. pages the reclaimer knows about), as well as unreclaimable EPC
> pages (i.e. pages which the reclaimer isn't aware of, such as VA pages).
> These pages are assigned to an LRU, as well as an enclave, so that an
> enclave's full EPC usage can be tracked, and limited to a max value. During
> OOM events, an enclave can be have its memory zapped, and all the EPC pages
> not tracked by the reclaimer can be freed.
>
> I appreciate your comments and feedback.
>
> Summary of changes from v2: (more details in commit logs)
>
> * Added EPC states to replace flags in sgx_epc_page struct. (Jarkko)
> * Unrolled wrappers for cond_resched, list (Dave)
> * Separate patches for adding reclaimable and unreclaimable lists. (Dave)
> * Other improvments on patch flow, commit messages, styles. (Dave, Jarkko)
> * Simplified the cgroup tree walking with plain
> css_for_each_descendant_pre.
> * Fixed race conditions and crashes.
> * OOM killer to wait for the victim enclave pages being reclaimed.
> * Unblock the user by handling misc_max_write callback asynchronously.
> * Rebased onto 6.4 and no longer base this series on the MCA patchset.
> * Fix an overflow in misc_try_charge.
> * Fix a NULL pointer in SGX PF handler.
> * Updated and included the SGX selftest patches previously reviewed. Those
> patches fix issues triggered in high EPC pressure required for cgroup
> testing.
> * Added test scripts to help setup and test SGX EPC cgroups.
>
> [1]https://lore.kernel.org/all/DM6PR21MB11772A6ED915825854B419D6C4989@DM6PR21MB1177.namprd21.prod.outlook.com/
> [2]https://lore.kernel.org/all/ZD7Iutppjj+muH4p@himmelriiki/
> [3]https://lore.kernel.org/all/20221202183655.3767674-1-kristen-VuQAYsv1561eoWH0uzbU5w@public.gmane.orgel.com/
> [4]Documentation/arch/x86/sgx.rst, Section "Virtual EPC"
>
> Haitao Huang (6):
> x86/sgx: Store struct sgx_encl when allocating new VA pages
> x86/sgx: Introduce EPC page states
> x86/sgx: fix a NULL pointer
> cgroup/misc: Fix an overflow
> selftests/sgx: Retry the ioctl()'s returned with EAGAIN
> selftests/sgx: Add scripts for epc cgroup testing
>
> Jarkko Sakkinen (3):
> selftests/sgx: Move ENCL_HEAP_SIZE_DEFAULT to main.c
> selftests/sgx: Use encl->encl_size in sigstruct.c
> selftests/sgx: Include the dynamic heap size to the ELRANGE
> calculation
>
> Kristen Carlson Accardi (9):
> x86/sgx: Add 'struct sgx_epc_lru_lists' to encapsulate lru list(s)
> x86/sgx: Use sgx_epc_lru_lists for existing active page list
> x86/sgx: Store reclaimable epc pages in sgx_epc_lru_lists
> x86/sgx: store unreclaimable EPC pages in sgx_epc_lru_lists
> x86/sgx: Use a list to track to-be-reclaimed pages
> cgroup/misc: Add per resource callbacks for CSS events
> cgroup/misc: Add SGX EPC resource type and export APIs for SGX driver
> x86/sgx: Limit process EPC usage with misc cgroup controller
> Docs/x86/sgx: Add description for cgroup support
>
> Sean Christopherson (9):
> x86/sgx: Add EPC page flags to identify owner type
> x86/sgx: Introduce RECLAIM_IN_PROGRESS state
> x86/sgx: Allow reclaiming up to 32 pages, but scan 16 by default
> x85/sgx: Return the number of EPC pages that were successfully
> reclaimed
> x86/sgx: Add option to ignore age of page during EPC reclaim
> x86/sgx: Prepare for multiple LRUs
> x86/sgx: Expose sgx_reclaim_pages() for use by EPC cgroup
> x86/sgx: Add helper to grab pages from an arbitrary EPC LRU
> x86/sgx: Add EPC OOM path to forcefully reclaim EPC
>
> Vijay Dhanraj (1):
> selftests/sgx: Add SGX selftest augment_via_eaccept_long
>
> Documentation/arch/x86/sgx.rst | 77 ++++
> arch/x86/Kconfig | 13 +
> arch/x86/kernel/cpu/sgx/Makefile | 1 +
> arch/x86/kernel/cpu/sgx/driver.c | 27 +-
> arch/x86/kernel/cpu/sgx/encl.c | 95 +++-
> arch/x86/kernel/cpu/sgx/encl.h | 4 +-
> arch/x86/kernel/cpu/sgx/epc_cgroup.c | 406 ++++++++++++++++++
> arch/x86/kernel/cpu/sgx/epc_cgroup.h | 60 +++
> arch/x86/kernel/cpu/sgx/ioctl.c | 25 +-
> arch/x86/kernel/cpu/sgx/main.c | 406 ++++++++++++++----
> arch/x86/kernel/cpu/sgx/sgx.h | 113 ++++-
> include/linux/misc_cgroup.h | 34 ++
> kernel/cgroup/misc.c | 63 ++-
> tools/testing/selftests/sgx/load.c | 8 +-
> tools/testing/selftests/sgx/main.c | 177 +++++++-
> tools/testing/selftests/sgx/main.h | 6 +-
> .../selftests/sgx/run_tests_in_misc_cg.sh | 68 +++
> tools/testing/selftests/sgx/setup_epc_cg.sh | 29 ++
> tools/testing/selftests/sgx/sigstruct.c | 8 +-
> .../selftests/sgx/watch_misc_for_tests.sh | 13 +
> 20 files changed, 1446 insertions(+), 187 deletions(-)
> create mode 100644 arch/x86/kernel/cpu/sgx/epc_cgroup.c
> create mode 100644 arch/x86/kernel/cpu/sgx/epc_cgroup.h
> create mode 100755 tools/testing/selftests/sgx/run_tests_in_misc_cg.sh
> create mode 100755 tools/testing/selftests/sgx/setup_epc_cg.sh
> create mode 100755 tools/testing/selftests/sgx/watch_misc_for_tests.sh
>
> --
> 2.25.1
Thanks for taking the effort, must have been tedious!
BR, Jarkko
next prev parent reply other threads:[~2023-07-17 11:02 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-12 23:01 [PATCH v3 00/28] Add Cgroup support for SGX EPC memory Haitao Huang
2023-07-12 23:01 ` [PATCH v3 04/28] x86/sgx: Use sgx_epc_lru_lists for existing active page list Haitao Huang
2023-07-17 12:47 ` Jarkko Sakkinen
2023-07-31 20:43 ` Haitao Huang
2023-07-12 23:01 ` [PATCH v3 05/28] x86/sgx: Store reclaimable epc pages in sgx_epc_lru_lists Haitao Huang
2023-07-12 23:01 ` [PATCH v3 07/28] x86/sgx: Introduce EPC page states Haitao Huang
2023-07-12 23:01 ` [PATCH v3 08/28] x86/sgx: Introduce RECLAIM_IN_PROGRESS state Haitao Huang
2023-07-12 23:01 ` [PATCH v3 11/28] x85/sgx: Return the number of EPC pages that were successfully reclaimed Haitao Huang
2023-07-29 12:47 ` Pavel Machek
[not found] ` <ZMUKd7KY6Kquubjf-1kjADaKPMenrBKCeMvbIDA@public.gmane.org>
2023-07-31 11:10 ` Jarkko Sakkinen
[not found] ` <20230712230202.47929-1-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
2023-07-12 23:01 ` [PATCH v3 01/28] x86/sgx: Store struct sgx_encl when allocating new VA pages Haitao Huang
2023-07-17 11:14 ` Jarkko Sakkinen
2023-07-12 23:01 ` [PATCH v3 02/28] x86/sgx: Add EPC page flags to identify owner type Haitao Huang
[not found] ` <20230712230202.47929-3-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
2023-07-17 12:41 ` Jarkko Sakkinen
2023-07-17 12:43 ` Jarkko Sakkinen
2023-07-12 23:01 ` [PATCH v3 03/28] x86/sgx: Add 'struct sgx_epc_lru_lists' to encapsulate lru list(s) Haitao Huang
[not found] ` <20230712230202.47929-4-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
2023-07-17 12:45 ` Jarkko Sakkinen
2023-07-17 13:23 ` Haitao Huang
[not found] ` <op.17794m01wjvjmi-yDQzE4XY+yVaPPhiJ6yCxLKMmGWinSIL2HeeBUIffwg@public.gmane.org>
2023-07-17 14:39 ` Jarkko Sakkinen
2023-07-24 10:04 ` Huang, Kai
[not found] ` <4f5496d2e0ea8edba430e7de7304bdd840616146.camel-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2023-07-24 14:55 ` Haitao Huang
2023-07-24 23:31 ` Huang, Kai
[not found] ` <9ffb02a3344807f2c173fe8c7cb000cd6c7843b6.camel-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2023-07-31 20:35 ` Haitao Huang
2023-07-12 23:01 ` [PATCH v3 06/28] x86/sgx: store unreclaimable EPC pages in sgx_epc_lru_lists Haitao Huang
2023-07-12 23:01 ` [PATCH v3 09/28] x86/sgx: Use a list to track to-be-reclaimed pages Haitao Huang
2023-07-12 23:01 ` [PATCH v3 10/28] x86/sgx: Allow reclaiming up to 32 pages, but scan 16 by default Haitao Huang
2023-07-12 23:01 ` [PATCH v3 12/28] x86/sgx: Add option to ignore age of page during EPC reclaim Haitao Huang
2023-07-12 23:01 ` [PATCH v3 13/28] x86/sgx: Prepare for multiple LRUs Haitao Huang
2023-07-12 23:01 ` [PATCH v3 14/28] x86/sgx: Expose sgx_reclaim_pages() for use by EPC cgroup Haitao Huang
2023-07-12 23:01 ` [PATCH v3 15/28] x86/sgx: Add helper to grab pages from an arbitrary EPC LRU Haitao Huang
2023-07-12 23:01 ` [PATCH v3 16/28] x86/sgx: Add EPC OOM path to forcefully reclaim EPC Haitao Huang
2023-07-12 23:01 ` [PATCH v3 17/28] x86/sgx: fix a NULL pointer Haitao Huang
[not found] ` <20230712230202.47929-18-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
2023-07-17 12:48 ` Jarkko Sakkinen
2023-07-17 12:49 ` Jarkko Sakkinen
2023-07-17 13:14 ` Haitao Huang
[not found] ` <op.1779qgkdwjvjmi-yDQzE4XY+yVaPPhiJ6yCxLKMmGWinSIL2HeeBUIffwg@public.gmane.org>
2023-07-17 14:33 ` Jarkko Sakkinen
2023-07-17 15:49 ` Dave Hansen
2023-07-17 18:49 ` Haitao Huang
[not found] ` <ffe26e8b-9f2a-4f06-aadf-9dfb1421be76-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2023-07-17 18:52 ` Jarkko Sakkinen
2023-07-12 23:01 ` [PATCH v3 18/28] cgroup/misc: Fix an overflow Haitao Huang
[not found] ` <20230712230202.47929-19-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
2023-07-17 13:15 ` Jarkko Sakkinen
2023-07-12 23:01 ` [PATCH v3 19/28] cgroup/misc: Add per resource callbacks for CSS events Haitao Huang
2023-07-17 13:16 ` Jarkko Sakkinen
2023-07-12 23:01 ` [PATCH v3 20/28] cgroup/misc: Add SGX EPC resource type and export APIs for SGX driver Haitao Huang
2023-07-12 23:01 ` [PATCH v3 21/28] x86/sgx: Limit process EPC usage with misc cgroup controller Haitao Huang
[not found] ` <20230712230202.47929-22-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
2023-07-13 0:03 ` Randy Dunlap
2023-08-17 15:12 ` Mikko Ylinen
2023-07-17 11:02 ` Jarkko Sakkinen [this message]
2023-07-24 19:09 ` [PATCH v3 00/28] Add Cgroup support for SGX EPC memory Sohil Mehta
2023-07-25 17:16 ` Haitao Huang
2023-07-12 23:01 ` [PATCH v3 22/28] Docs/x86/sgx: Add description for cgroup support Haitao Huang
2023-07-13 0:10 ` Randy Dunlap
2023-07-14 20:01 ` Haitao Huang
2023-07-14 20:26 ` Haitao Huang
[not found] ` <20230712230202.47929-23-haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>
2023-08-17 15:18 ` Mikko Ylinen
2023-08-17 15:04 ` [PATCH v3 00/28] Add Cgroup support for SGX EPC memory Mikko Ylinen
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=CU4EA8H87W7J.11BOV563ZK2JX@seitikki \
--to=jarkko-dgejt+ai2ygdnm+yrofe0a@public.gmane.org \
--cc=anakrish-0li6OtcxBFHby3iVrkZq2A@public.gmane.org \
--cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=dave.hansen-VuQAYsv1563Yd54FQh9/CA@public.gmane.org \
--cc=haitao.huang-VuQAYsv1563Yd54FQh9/CA@public.gmane.org \
--cc=kai.huang-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
--cc=kristen-VuQAYsv1563Yd54FQh9/CA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-sgx-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=mikko.ylinen-VuQAYsv1563Yd54FQh9/CA@public.gmane.org \
--cc=reinette.chatre-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
--cc=seanjc-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=zhanb-0li6OtcxBFHby3iVrkZq2A@public.gmane.org \
--cc=zhiquan1.li-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
/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