-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Bagas Sanjaya
Reviewed-by: Jarkko Sakkinen
Acked-by: Kai Huang
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V8:
- Limit text width to 80 characters to be consistent.
V6:
- Remove mentioning of VMM
reclamation and per-cgroup reclamation
both work properly with all pages tracked in per-cgroup LRUs.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko
ronous per-cgroup EPC reclamation when the usage reaches the
threshold after try_charge() is successful.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Tested-by: Jarkk
ing to
the global LRU directly.
This allows EPC page being able to be tracked in "per-cgroup" LRU when
that becomes ready.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haita
, it turns off swapping before start,
and turns swapping back on afterwards.
Add README to document how to run the tests.
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Jarkko Sakkinen
Acked-by: Kai Huang
---
V13:
- More improvement on handling error cases and style fixes
ot;) SGX_NR_TO_SCAN pages
_across_ the given EPC cgroup _AND_ its descendants, and then do the
actual reclaim in one batch. But this is unnecessarily complicated at
this stage to address such rare cases.
Signed-off-by: Haitao Huang
Reviewed-by: Kai Huang
Reviewed-by: Jarkko Sakkinen
-
Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko Sakkinen
---
V17:
- Make comment for spinlock more accurate.
V15:
- Add comment for spinlock. (Jarkko, Kai)
V6:
- removed
shold.
Later patches will reorganize the tracking and reclamation code in the
global reclaimer and implement per-cgroup tracking and reclaiming.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-of
g/all/a0d8f037c4a075d56bf79f432438412985f7ff7a.1652137848.git.reinette.cha...@intel.com/T/#u
Signed-off-by: Haitao Huang
Reviewed-by: Kai Huang
Reviewed-by: Jarkko Sakkinen
---
V17:
- Improve comments and capitalization. (Kai)
---
arch/x86/kernel/cpu/sgx/epc_cgroup.c | 15 +++
arch/x86/k
for an mm struct from enclave's mm_list.
Signed-off-by: Haitao Huang
Reported-by: Mikko Ylinen
Reviewed-by: Kai Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V10:
- Pass mm struct instead of a boolean 'indirect'. (Dave, Jarkko)
V9:
en Carlson Accardi
Signed-off-by: Kristen Carlson Accardi
Signed-off-by: Haitao Huang
Reviewed-by: Kai Huang
Reviewed-by: Jarkko Sakkinen
---
V17:
- Fix grammar in commit and improve comments.(Kai)
- Fix error in initializing 'next' in sgx_cgroup_next_descendant_pre()
V16:
- Revise comm
From: Kristen Carlson Accardi
Add SGX EPC memory, MISC_CG_RES_SGX_EPC, to be a valid resource type
for the misc controller.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko
needs start a global level reclamation from the
root. Expose misc_cg_root() for the SGX driver to access.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Tejun Heo
Reviewed-by: Kai Huang
Tested-by: J
eparate the two
cases.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Co-developed-by: Kristen Carlson Accardi
Signed-off-by: Kristen Carlson Accardi
Signed-off-by: Haitao Huang
Reviewed-by: Kai Huang
Reviewed-by: Jarkko Sakkinen
---
V17:
- remove comments in sgx_can
sc_cg' to the callbacks but not the 'struct misc_res' because
the latter doesn't have a pointer pointing back to 'struct misc_cg'.
Link:
https://lore.kernel.org/lkml/op.2kdw36otwjv...@hhuan26-mobl.amr.corp.intel.com/
Signed-off-by: Kristen Carlson Accardi
Co-developed-b
Replace boolean parameters for 'reclaim' in the function
sgx_alloc_epc_page() and its callers with an enum.
Also opportunistically remove non-static declaration of
__sgx_alloc_epc_page() and a typo
Signed-off-by: Haitao Huang
Suggested-by: Jarkko Sakkinen
Suggested-by: Dave Hansen
R
-sgx/20240531222630.4634-1-haitao.hu...@linux.intel.com/T/#t
[20]v15:
https://lore.kernel.org/linux-sgx/20240617125321.36658-1-haitao.hu...@linux.intel.com/T/#t
[21]v16:
https://lore.kernel.org/lkml/20240821015404.6038-1-haitao.hu...@linux.intel.com/T/#t
Haitao Huang (7):
x86/sgx: Replace boolea
+static struct sgx_cgroup *sgx_cgroup_next_descendant_pre(struct
sgx_cgroup *root,
+struct sgx_cgroup *cg)
+{
+ struct cgroup_subsys_state *next;
+
+ rcu_read_lock();
+ for (;;) {
+ next = css_next_descendant
, it turns off swapping before start,
and turns swapping back on afterwards.
Add README to document how to run the tests.
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Jarkko Sakkinen
---
V13:
- More improvement on handling error cases and style fixes.
- Add settings file
-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Bagas Sanjaya
Reviewed-by: Jarkko Sakkinen
Acked-by: Kai Huang
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V8:
- Limit text width to 80 characters to be consistent.
V6:
- Remove mentioning of VMM
reclamation and per-cgroup reclamation
both work properly with all pages tracked in per-cgroup LRUs.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko
g/all/a0d8f037c4a075d56bf79f432438412985f7ff7a.1652137848.git.reinette.cha...@intel.com/T/#u
Signed-off-by: Haitao Huang
---
arch/x86/kernel/cpu/sgx/epc_cgroup.c | 15 +++
arch/x86/kernel/cpu/sgx/epc_cgroup.h | 3 +++
arch/x86/kernel/cpu/sgx/main.c | 4
3 files changed, 22 inser
be to
have a new function to only "scan" (or "isolate") SGX_NR_TO_SCAN pages
_across_ the given EPC cgroup _AND_ its descendants, and then do the
actual reclaim in one batch. But this is unnecessarily complicated at
this stage to address such rare cases.
Signed-off-by: Haitao Hu
for an mm struct from enclave's mm_list.
Signed-off-by: Haitao Huang
Reported-by: Mikko Ylinen
Reviewed-by: Kai Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V10:
- Pass mm struct instead of a boolean 'indirect'. (Dave, Jarkko)
V9:
ronous per-cgroup EPC reclamation when the usage reaches the
threshold after try_charge() is successful.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Tested-by: Jarkk
en Carlson Accardi
Signed-off-by: Kristen Carlson Accardi
Signed-off-by: Haitao Huang
---
V16:
- Revise commit log to define reclamation requirement and the design more
clearly. (Kai)
- Revise sgx_cgroup_reclaim_pages() to scan cgroups in subtree more
fairly, track next_cg in each sgx_cgroup and a
ing to
the global LRU directly.
This allows EPC page being able to be tracked in "per-cgroup" LRU when
that becomes ready.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haita
eparate the two
cases.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Co-developed-by: Kristen Carlson Accardi
Signed-off-by: Kristen Carlson Accardi
Signed-off-by: Haitao Huang
---
v16:
- Regroup all abstraction related to global LRU usage to this patch from
diffe
Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko Sakkinen
---
V15:
- Add comment for spinlock. (Jarkko, Kai)
V6:
- removed introduction to unreclaimables in commit message.
V4
shold.
Later patches will reorganize the tracking and reclamation code in the
global reclaimer and implement per-cgroup tracking and reclaiming.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-of
From: Kristen Carlson Accardi
Add SGX EPC memory, MISC_CG_RES_SGX_EPC, to be a valid resource type
for the misc controller.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko
needs start a global level reclamation from the
root. Export misc_cg_root() for the SGX driver to access.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Tejun Heo
Reviewed-by: Kai Huang
Tested-by: J
sc_cg' to the callbacks but not the 'struct misc_res' because
the latter doesn't have a pointer pointing back to 'struct misc_cg'.
Link:
https://lore.kernel.org/lkml/op.2kdw36otwjv...@hhuan26-mobl.amr.corp.intel.com/
Signed-off-by: Kristen Carlson Accardi
Co-developed-b
Replace boolean parameters for 'reclaim' in the function
sgx_alloc_epc_page() and its callers with an enum.
Also opportunistically remove non-static declaration of
__sgx_alloc_epc_page() and a typo
Signed-off-by: Haitao Huang
Suggested-by: Jarkko Sakkinen
Suggested-by: Dave Hansen
R
467-1-haitao.hu...@linux.intel.com/
[17]v12:
https://lore.kernel.org/lkml/20240416032011.58578-1-haitao.hu...@linux.intel.com/
[18]v13:
https://lore.kernel.org/lkml/20240430195108.5676-1-haitao.hu...@linux.intel.com/
[19]v14:
https://lore.kernel.org/linux-sgx/20240531222630.4634-1-haitao.hu...@l
esc |= SGX_ENCL_PAGE_BUSY;
mutex_unlock(&encl->lock);
sgx_zap_enclave_ptes(encl, addr);
Reviewed-by: Haitao Huang
Thanks
Haitao
reclaimed. A
future commit will introduce a new case when the enclave page is being
removed; this new case will set only the SGX_ENCL_PAGE_BUSY flag.
LGTM.
Reviewed-by: Haitao Huang
Thanks
Haitao
On Thu, 20 Jun 2024 08:28:57 -0500, Huang, Kai wrote:
On 18/06/2024 12:53 am, Huang, Haitao wrote:
From: Kristen Carlson Accardi
Currently in the EPC page allocation, the kernel simply fails the
allocation when the current EPC cgroup fails to charge due to its usage
reaching limit. This
+ if (cgroup_subsys_enabled(misc_cgrp_subsys)) {
+ sgx_cg_wq = alloc_workqueue("sgx_cg_wq", WQ_UNBOUND |
WQ_FREEZABLE,
+ WQ_UNBOUND_MAX_ACTIVE);
+ return -ENOMEM;
Argh, missing if(!sgx_cg_wq), sorry for the brain far
Hi Kai
On Thu, 20 Jun 2024 05:30:16 -0500, Huang, Kai wrote:
On 18/06/2024 12:53 am, Huang, Haitao wrote:
From: Kristen Carlson Accardi
Previous patches have implemented all infrastructure needed for
per-cgroup EPC page tracking and reclaiming. But all reclaimable EPC
pages are still track
On Tue, 18 Jun 2024 18:15:37 -0500, Huang, Kai wrote:
On Tue, 2024-06-18 at 07:56 -0500, Haitao Huang wrote:
On Tue, 18 Jun 2024 06:31:09 -0500, Huang, Kai
wrote:
>
> > @@ -921,7 +956,8 @@ static int __init sgx_init(void)
> > if (!sgx_page_cache_init())
> >
On Tue, 18 Jun 2024 06:31:09 -0500, Huang, Kai wrote:
@@ -921,7 +956,8 @@ static int __init sgx_init(void)
if (!sgx_page_cache_init())
return -ENOMEM;
- if (!sgx_page_reclaimer_init()) {
+ if (!sgx_page_reclaimer_init() || !sgx_cgroup_init()) {
+
On Mon, 10 Jun 2024 17:39:53 -0500, Huang, Kai wrote:
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -1045,7 +1045,7 @@ static int __init sgx_init(void)
if (!sgx_page_cache_init())
return -ENOMEM;
-if (!sgx_page_reclaimer_init()) {
+if
, just call _misc_cg_res_free(cg, MISC_CG_RES_TYPES)
to free all.
That makes sense now, Will do that.
(BTW you need comment inline :-)
Thanks
Haitao
On 2024/6/6 22:51, Haitao Huang wrote:
On Thu, 06 Jun 2024 08:37:31 -0500, chenridong
wrote:
If _misc_cg_res_alloc fails, maybe some
On Thu, 06 Jun 2024 08:37:31 -0500, chenridong
wrote:
If _misc_cg_res_alloc fails, maybe some types do not call ->alloc(), but
all types ->free() callback >will be called, is that ok?
Not sure I understand. Are you suggesting we ignore failures from
->alloc() callback in _misc_cg_r
On Thu, 06 Jun 2024 00:32:55 -0500, Jarkko Sakkinen
wrote:
On Wed Jun 5, 2024 at 6:33 PM EEST, Haitao Huang wrote:
sgx_cgroup_try_charge() expects sgx_cg_wq, so it would break unless we
check and return 0 which was the initially implemented in v12. But then
Kai had some concern on that we
Hi Jarkko
Thanks for your review.
On Tue, 04 Jun 2024 17:00:34 -0500, Jarkko Sakkinen
wrote:
On Sat Jun 1, 2024 at 1:26 AM EEST, Haitao Huang wrote:
With different cgroups, the script starts one or multiple concurrent SGX
selftests (test_sgx), each to run the
On Tue, 28 May 2024 11:23:13 -0500, Dave Hansen
wrote:
On 5/17/24 04:06, Dmitrii Kuvaiskii wrote:
...
First, why is SGX so special here? How is the SGX problem different
than what the core mm code does?
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -25,6 +25
, it turns off swapping before start,
and turns swapping back on afterwards.
Add README to document how to run the tests.
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Jarkko Sakkinen
---
V13:
- More improvement on handling error cases and style fixes.
- Add settings file
-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Bagas Sanjaya
Reviewed-by: Jarkko Sakkinen
Acked-by: Kai Huang
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V8:
- Limit text width to 80 characters to be consistent.
V6:
- Remove mentioning of VMM
: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V14:
- Update global reclamation to use the new
for an mm struct from enclave's mm_list.
Signed-off-by: Haitao Huang
Reported-by: Mikko Ylinen
Reviewed-by: Kai Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V10:
- Pass mm struct instead of a boolean 'indirect'. (Dave, Jarkko)
V9:
Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Tested-by: Jarkko Sakkinen
---
V13:
- Revert to BUG_ON() in case of workq allocation failure in init and
only alloc if misc is enabled.
V11:
- Print error
laimable EPC pages are still tracked in the global LRU thus
no per-cgroup reclamation is actually active at the moment. Per-cgroup
tracking and reclamation will be turned on in the end after all
necessary infrastructure is in place.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
s to
sgx_can_reclaim_global().
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko Sakkinen
---
ing to
the global LRU directly.
This allows EPC page being able to be tracked in "per-cgroup" LRU when
that becomes ready.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haita
Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko Sakkinen
---
V6:
- removed introduction to unreclaimables in commit message.
V4:
- Removed unneeded comments for the spinlock
shold.
Later patches will reorganize the tracking and reclamation code in the
global reclaimer and implement per-cgroup tracking and reclaiming.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-of
From: Kristen Carlson Accardi
Add SGX EPC memory, MISC_CG_RES_SGX_EPC, to be a valid resource type
for the misc controller.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko
sten Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Tejun Heo
Reviewed-by: Kai Huang
Tested-by: Jarkko Sakkinen
---
V12:
- Add comments in commit to clarify reason to pass in misc_cg, not
misc_res. (Kai)
- Remove unlikely (Kai)
needs start a global level reclamation from the
root. Export misc_cg_root() for the SGX driver to access.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Tejun Heo
Reviewed-by: Kai Huang
Tested-by: J
Replace boolean parameters for 'reclaim' in the function
sgx_alloc_epc_page() and its callers with an enum.
Also opportunistically remove non-static declaration of
__sgx_alloc_epc_page() and a typo
Signed-off-by: Haitao Huang
Suggested-by: Jarkko Sakkinen
Suggested-by: Dave Hansen
R
nel.org/lkml/20240416032011.58578-1-haitao.hu...@linux.intel.com/
[18]v13:
https://lore.kernel.org/lkml/20240430195108.5676-1-haitao.hu...@linux.intel.com/
Haitao Huang (3):
x86/sgx: Replace boolean parameters with enums
x86/sgx: Charge mem_cgroup for per-cgroup reclamation
selftests/sgx: Add scri
On Wed, 15 May 2024 16:55:59 -0500, Haitao Huang
wrote:
On Wed, 15 May 2024 01:55:21 -0500, Bojun Zhu
wrote:
EDMM's ioctl()s support batch operations, which may be
time-consuming. Try to explicitly give up the CPU as the prefix
operation at the every begin of "for loop"
t_t sgx_encl_eaug_page(struct
vm_area_struct *vma,
err_out_shrink:
sgx_encl_shrink(encl, va_page);
err_out_epc:
- sgx_encl_free_epc_page(epc_page);
+ sgx_free_epc_page(epc_page);
err_out_unlock:
mutex_unlock(&encl->lock);
kfree(encl_page);
Reviewed-by: Haitao Huang
ave_ptes().
*/
+ entry->desc |= SGX_ENCL_PAGE_BEING_REMOVED;
mutex_unlock(&encl->lock);
sgx_zap_enclave_ptes(encl, addr);
Reviewed-by: Haitao Huang
On Wed, 15 May 2024 01:55:21 -0500, Bojun Zhu
wrote:
EDMM's ioctl()s support batch operations, which may be
time-consuming. Try to explicitly give up the CPU as the prefix
operation at the every begin of "for loop" in
sgx_enclave_{ modify_types | restrict_permissions | remove_pages}
to give o
On Mon, 06 May 2024 19:10:42 -0500, Huang, Kai wrote:
On 1/05/2024 7:51 am, Haitao Huang wrote:
static void sgx_reclaim_pages_global(struct mm_struct *charge_mm)
{
- sgx_reclaim_pages(&sgx_global_lru, charge_mm);
+ if (IS_ENABLED(CONFIG_CGROUP_
Hi Kai
Sorry there seems to be some delay in receiving my emails.
On Thu, 02 May 2024 18:23:06 -0500, Huang, Kai wrote:
On 1/05/2024 7:51 am, Haitao Huang wrote:
From: Kristen Carlson Accardi
For the global reclaimer to determine if any page available for
reclamation at the global level
-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Bagas Sanjaya
Acked-by: Kai Huang
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V8:
- Limit text width to 80 characters to be consistent.
V6:
- Remove mentioning of VMM specific behavior on handling
, it turns off swapping before start,
and turns swapping back on afterwards.
Add README to document how to run the tests.
Signed-off-by: Haitao Huang
---
V13:
- More improvement on handling error cases and style fixes.
- Add settings file for custom timeout
V12:
- Integrate the scripts to the
reclamation
both work properly with all pages tracked in per-cgroup LRUs.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
s to
sgx_can_reclaim_global().
Rename sgx_should_reclaim() to sgx_should_reclaim_global() as it is used
to check if a global reclamation should be performed.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao H
Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Tested-by: Jarkko Sakkinen
---
V13:
- Revert to BUG_ON() in case of workq allocation failure in init and
only alloc if misc is enabled.
V11:
- Print error instead of WARN (Kai)
- Add check
thus
no per-cgroup reclamation is actually active at the moment. Per-cgroup
tracking and reclamation will be turned on in the end after all
necessary infrastructure is in place.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-
ing to
the global LRU directly.
This allows EPC page being able to be tracked in "per-cgroup" LRU when
that becomes ready.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haita
Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Cc: Sean Christopherson
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko Sakkinen
---
V6:
- removed introduction to unreclaimables in commit message.
V4:
- Removed unneeded comments for the spinlock
for an mm struct from enclave's mm_list.
Signed-off-by: Haitao Huang
Reported-by: Mikko Ylinen
Reviewed-by: Kai Huang
Tested-by: Mikko Ylinen
Tested-by: Jarkko Sakkinen
---
V10:
- Pass mm struct instead of a boolean 'indirect'. (Dave, Jarkko)
V9:
- Reduce number of if sta
shold.
Later patches will reorganize the tracking and reclamation code in the
global reclaimer and implement per-cgroup tracking and reclaiming.
Co-developed-by: Sean Christopherson
Signed-off-by: Sean Christopherson
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-of
From: Kristen Carlson Accardi
Add SGX EPC memory, MISC_CG_RES_SGX_EPC, to be a valid resource type
for the misc controller.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Kai Huang
Tested-by: Jarkko
needs start a global level reclamation from the
root. Export misc_cg_root() for the SGX driver to access.
Signed-off-by: Kristen Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Tejun Heo
Reviewed-by: Kai Huang
Tested-by: J
sten Carlson Accardi
Co-developed-by: Haitao Huang
Signed-off-by: Haitao Huang
Reviewed-by: Jarkko Sakkinen
Reviewed-by: Tejun Heo
Reviewed-by: Kai Huang
Tested-by: Jarkko Sakkinen
---
V12:
- Add comments in commit to clarify reason to pass in misc_cg, not
misc_res. (Kai)
- Remove unlikely (Kai)
el.org/linux-sgx/20240328002229.30264-1-haitao.hu...@linux.intel.com/T/#t
[16]v11:
https://lore.kernel.org/lkml/20240410182558.41467-1-haitao.hu...@linux.intel.com/
[17]v12:
https://lore.kernel.org/lkml/20240416032011.58578-1-haitao.hu...@linux.intel.com/
Haitao Huang (3):
x86/sgx: Replace boolean parameter
Replace boolean parameters for 'reclaim' in the function
sgx_alloc_epc_page() and its callers with an enum.
Also opportunistically remove non-static declaration of
__sgx_alloc_epc_page() and a typo
Signed-off-by: Haitao Huang
Suggested-by: Jarkko Sakkinen
Suggested-by: Dave Hansen
R
On Mon, 29 Apr 2024 17:18:05 -0500, Huang, Kai wrote:
/*
@@ -42,7 +63,8 @@ static inline struct sgx_epc_lru_list
*sgx_lru_list(struct sgx_epc_page *epc_pag
*/
static inline bool sgx_can_reclaim(void)
{
-return !list_empty(&sgx_global_lru.reclaimable);
+return !sgx_cgroup_lru_e
On Mon, 29 Apr 2024 11:43:05 -0500, Jarkko Sakkinen
wrote:
On Mon Apr 29, 2024 at 7:18 PM EEST, Haitao Huang wrote:
Hi Jarkko
On Sun, 28 Apr 2024 17:03:17 -0500, Jarkko Sakkinen
wrote:
> On Fri Apr 26, 2024 at 5:28 PM EEST, Dave Hansen wrote:
>> On 4/16/24 07:15, Jarkko Sakki
Hi Jarkko
On Sun, 28 Apr 2024 17:03:17 -0500, Jarkko Sakkinen
wrote:
On Fri Apr 26, 2024 at 5:28 PM EEST, Dave Hansen wrote:
On 4/16/24 07:15, Jarkko Sakkinen wrote:
> On Tue Apr 16, 2024 at 8:42 AM EEST, Huang, Kai wrote:
> Yes, exactly. I'd take one week break and cycle the kselftest par
On Mon, 29 Apr 2024 05:49:13 -0500, Huang, Kai wrote:
+/*
+ * Get the per-cgroup or global LRU list that tracks the given
reclaimable page.
+ */
static inline struct sgx_epc_lru_list *sgx_lru_list(struct
sgx_epc_page *epc_page)
{
+#ifdef CONFIG_CGROUP_MISC
+ /*
+* epc_pa
Hi Jarkko
On Tue, 16 Apr 2024 11:08:11 -0500, Jarkko Sakkinen
wrote:
On Tue Apr 16, 2024 at 5:54 PM EEST, Haitao Huang wrote:
I did declare the configs in the config file but I missed it in my patch
as stated earlier. IIUC, that would not cause this error though.
Maybe I should exit with
On Tue, 23 Apr 2024 17:13:15 -0500, Huang, Kai wrote:
On Tue, 2024-04-23 at 10:30 -0500, Haitao Huang wrote:
> > It's a workaround because you use the capacity==0 but it does not
really
> > mean to disable the misc cgroup for specific resource IIUC.
>
> Please
On Wed, 17 Apr 2024 18:51:28 -0500, Huang, Kai wrote:
On 16/04/2024 3:20 pm, Haitao Huang wrote:
From: Kristen Carlson Accardi
Currently in the EPC page allocation, the kernel simply fails the
allocation when the current EPC cgroup fails to charge due to its usage
reaching limit. This is
On Tue, 23 Apr 2024 09:19:53 -0500, Huang, Kai wrote:
On Tue, 2024-04-23 at 08:08 -0500, Haitao Huang wrote:
On Mon, 22 Apr 2024 17:16:34 -0500, Huang, Kai
wrote:
> On Mon, 2024-04-22 at 11:17 -0500, Haitao Huang wrote:
> > On Sun, 21 Apr 2024 19:22:27 -0500, Huang, Kai
On Mon, 22 Apr 2024 17:16:34 -0500, Huang, Kai wrote:
On Mon, 2024-04-22 at 11:17 -0500, Haitao Huang wrote:
On Sun, 21 Apr 2024 19:22:27 -0500, Huang, Kai
wrote:
> On Fri, 2024-04-19 at 20:14 -0500, Haitao Huang wrote:
> > > > I think we can add support for "sgx
Hi Jarkko
On Mon, 15 Apr 2024 14:08:44 -0500, Jarkko Sakkinen
wrote:
I did run the basic test by manually creating the cgroup so you could
add tested-by from my side to the other kernel patches expect this one
I've reviewed it enough rounds and given various code suggestions etc.
For me it
On Sun, 21 Apr 2024 19:22:27 -0500, Huang, Kai wrote:
On Fri, 2024-04-19 at 20:14 -0500, Haitao Huang wrote:
> > I think we can add support for "sgx_cgroup=disabled" in future if
indeed
> > needed. But just for init failure, no?
> >
>
> It's not abo
On Fri, 19 Apr 2024 17:44:59 -0500, Huang, Kai wrote:
On Fri, 2024-04-19 at 13:55 -0500, Haitao Huang wrote:
On Thu, 18 Apr 2024 20:32:14 -0500, Huang, Kai
wrote:
>
>
> On 16/04/2024 3:20 pm, Haitao Huang wrote:
> > From: Kristen Carlson Accardi
> > In cases EPC pa
On Thu, 18 Apr 2024 20:32:14 -0500, Huang, Kai wrote:
On 16/04/2024 3:20 pm, Haitao Huang wrote:
From: Kristen Carlson Accardi
In cases EPC pages need be allocated during a page fault and the cgroup
usage is near its limit, an asynchronous reclamation needs be triggered
to avoid blocking
On Thu, 18 Apr 2024 18:29:53 -0500, Huang, Kai wrote:
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/epc_cgroup.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _SGX_EPC_CGROUP_H_
+#define _SGX_EPC_CGROUP_H_
+
+#include
I don't see why you need here. Also, ...
+#include
On Tue, 16 Apr 2024 08:22:06 -0500, Huang, Kai wrote:
On Mon, 2024-04-15 at 20:20 -0700, Haitao Huang wrote:
From: Kristen Carlson Accardi
SGX Enclave Page Cache (EPC) memory allocations are separate from normal
RAM allocations, and are managed solely by the SGX subsystem. The
existing
On Tue, 16 Apr 2024 17:21:24 -0500, Haitao Huang
wrote:
On Tue, 16 Apr 2024 17:04:21 -0500, Haitao Huang
wrote:
On Tue, 16 Apr 2024 11:08:11 -0500, Jarkko Sakkinen
wrote:
On Tue Apr 16, 2024 at 5:54 PM EEST, Haitao Huang wrote:
I did declare the configs in the config file but I
1 - 100 of 393 matches
Mail list logo
