public inbox for cgroups@vger.kernel.org
 help / color / mirror / Atom feed
From: Haitao Huang <haitao.huang@linux.intel.com>
To: jarkko@kernel.org, dave.hansen@linux.intel.com, tj@kernel.org,
	linux-kernel@vger.kernel.org, linux-sgx@vger.kernel.org,
	cgroups@vger.kernel.org, Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>
Cc: kai.huang@intel.com, reinette.chatre@intel.com,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	zhiquan1.li@intel.com, kristen@linux.intel.com,
	seanjc@google.com
Subject: [PATCH v3 08/28] x86/sgx: Introduce RECLAIM_IN_PROGRESS state
Date: Wed, 12 Jul 2023 16:01:42 -0700	[thread overview]
Message-ID: <20230712230202.47929-9-haitao.huang@linux.intel.com> (raw)
In-Reply-To: <20230712230202.47929-1-haitao.huang@linux.intel.com>

From: Sean Christopherson <sean.j.christopherson@intel.com>

When a page is being reclaimed from the page pool (sgx_global_lru),
there is an intermediate stage where a page may have been identified
as a candidate for reclaiming, but has not yet been reclaimed.
Currently such pages are list_del_init()'d from the global LRU, and
stored in a an array on stack. To prevent another thread from dropping
the same page in the middle of reclaiming, sgx_drop_epc_page() checks
for list_empty(&page->list).

In future patches these pages need be list_move()'d into a temporary
list that is shared with multiple cgroup reclaimers. so list_empty()
should no longer be used for this purpose. Add a RECLAIM_IN_PROGRESS
state to explicitly designate such intermediate state of EPC in the
reclaiming process. Do not drop any page in this state in
sgx_drop_epc_page().

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Kristen Carlson Accardi <kristen@linux.intel.com>
Signed-off-by: Haitao Huang <haitao.huang@linux.intel.com>
Cc: Sean Christopherson <seanjc@google.com>

V3:
- Extend the sgx_epc_page_state enum introduced earlier to replace the
flag based approach.
---
 arch/x86/kernel/cpu/sgx/main.c | 21 ++++++++++-----------
 arch/x86/kernel/cpu/sgx/sgx.h  | 16 ++++++++++++++++
 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 02c358f10383..9eea9038758f 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -313,13 +313,15 @@ static void sgx_reclaim_pages(void)
 		list_del_init(&epc_page->list);
 		encl_page = epc_page->encl_page;
 
-		if (kref_get_unless_zero(&encl_page->encl->refcount) != 0)
+		if (kref_get_unless_zero(&encl_page->encl->refcount) != 0) {
+			sgx_epc_page_set_state(epc_page, SGX_EPC_PAGE_RECLAIM_IN_PROGRESS);
 			chunk[cnt++] = epc_page;
-		else
+		} else {
 			/* The owner is freeing the page. No need to add the
 			 * page back to the list of reclaimable pages.
 			 */
 			sgx_epc_page_reset_state(epc_page);
+		}
 	}
 	spin_unlock(&sgx_global_lru.lock);
 
@@ -531,16 +533,13 @@ void sgx_record_epc_page(struct sgx_epc_page *page, unsigned long flags)
 int sgx_drop_epc_page(struct sgx_epc_page *page)
 {
 	spin_lock(&sgx_global_lru.lock);
-	if (sgx_epc_page_reclaimable(page->flags)) {
-		/* The page is being reclaimed. */
-		if (list_empty(&page->list)) {
-			spin_unlock(&sgx_global_lru.lock);
-			return -EBUSY;
-		}
-
-		list_del(&page->list);
-		sgx_epc_page_reset_state(page);
+	if (sgx_epc_page_reclaim_in_progress(page->flags)) {
+		spin_unlock(&sgx_global_lru.lock);
+		return -EBUSY;
 	}
+
+	list_del(&page->list);
+	sgx_epc_page_reset_state(page);
 	spin_unlock(&sgx_global_lru.lock);
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 057905eba466..f26ed4c0d12f 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -40,6 +40,8 @@ enum sgx_epc_page_state {
 
 	/* Page is in use and tracked in a reclaimable LRU list
 	 * Becomes NOT_TRACKED after sgx_drop_epc()
+	 * Becomes RECLAIM_IN_PROGRESS in sgx_reclaim_pages() when identified
+	 * for reclaiming
 	 */
 	SGX_EPC_PAGE_RECLAIMABLE = 2,
 
@@ -50,6 +52,14 @@ enum sgx_epc_page_state {
 	 */
 	SGX_EPC_PAGE_UNRECLAIMABLE = 3,
 
+	/* Page is being prepared for reclaimation, tracked in a temporary
+	 * isolated list by the reclaimer.
+	 * Changes in sgx_reclaim_pages() back to RECLAIMABLE if preparation
+	 * fails for any reason.
+	 * Becomes NOT_TRACKED if reclaimed successfully in sgx_reclaim_pages()
+	 * and immediately sgx_free_epc() is called to make it FREE.
+	 */
+	SGX_EPC_PAGE_RECLAIM_IN_PROGRESS = 4,
 };
 
 #define SGX_EPC_PAGE_STATE_MASK GENMASK(2, 0)
@@ -82,6 +92,12 @@ static inline void sgx_epc_page_set_state(struct sgx_epc_page *page, unsigned lo
 	page->flags |= (flags & SGX_EPC_PAGE_STATE_MASK);
 }
 
+static inline bool sgx_epc_page_reclaim_in_progress(unsigned long flags)
+{
+	return SGX_EPC_PAGE_RECLAIM_IN_PROGRESS == (flags &
+						    SGX_EPC_PAGE_STATE_MASK);
+}
+
 static inline bool sgx_epc_page_reclaimable(unsigned long flags)
 {
 	return SGX_EPC_PAGE_RECLAIMABLE == (flags & SGX_EPC_PAGE_STATE_MASK);
-- 
2.25.1


  parent reply	other threads:[~2023-07-12 23:01 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 ` Haitao Huang [this message]
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   ` [PATCH v3 00/28] Add Cgroup support for SGX EPC memory Jarkko Sakkinen
2023-07-24 19:09   ` 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=20230712230202.47929-9-haitao.huang@linux.intel.com \
    --to=haitao.huang@linux.intel.com \
    --cc=bp@alien8.de \
    --cc=cgroups@vger.kernel.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=jarkko@kernel.org \
    --cc=kai.huang@intel.com \
    --cc=kristen@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-sgx@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=reinette.chatre@intel.com \
    --cc=sean.j.christopherson@intel.com \
    --cc=seanjc@google.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=x86@kernel.org \
    --cc=zhiquan1.li@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox