| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20191230194042.67789-5-alex.kogan@oracle.com>
Date: Mon, 30 Dec 2019 14:40:41 -0500
From: Alex Kogan <alex.kogan@...cle.com>
To: linux@...linux.org.uk, peterz@...radead.org, mingo@...hat.com,
will.deacon@....com, arnd@...db.de, longman@...hat.com,
linux-arch@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org, tglx@...utronix.de, bp@...en8.de,
hpa@...or.com, x86@...nel.org, guohanjun@...wei.com,
jglauber@...vell.com
Cc: steven.sistare@...cle.com, daniel.m.jordan@...cle.com,
alex.kogan@...cle.com, dave.dice@...cle.com
Subject: [PATCH v8 4/5] locking/qspinlock: Introduce starvation avoidance into CNA
Keep track of the number of intra-node lock handoffs, and force
inter-node handoff once this number reaches a preset threshold.
The default value for the threshold can be overridden with
the new kernel boot command-line option "numa_spinlock_threshold".
Signed-off-by: Alex Kogan <alex.kogan@...cle.com>
Reviewed-by: Steve Sistare <steven.sistare@...cle.com>
---
.../admin-guide/kernel-parameters.txt | 8 ++++
kernel/locking/qspinlock.c | 3 ++
kernel/locking/qspinlock_cna.h | 41 ++++++++++++++++++-
3 files changed, 51 insertions(+), 1 deletion(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index b68cb80e477f..30d79819a3b0 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3200,6 +3200,14 @@
Not specifying this option is equivalent to
numa_spinlock=auto.
+ numa_spinlock_threshold= [NUMA, PV_OPS]
+ Set the threshold for the number of intra-node
+ lock hand-offs before the NUMA-aware spinlock
+ is forced to be passed to a thread on another NUMA node.
+ Valid values are in the [0..31] range. Smaller values
+ result in a more fair, but less performant spinlock, and
+ vice versa. The default value is 16.
+
cpu0_hotplug [X86] Turn on CPU0 hotplug feature when
CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
Some features depend on CPU0. Known dependencies are:
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 609980a53841..e382d8946ccc 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -597,6 +597,9 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath);
#if !defined(_GEN_CNA_LOCK_SLOWPATH) && defined(CONFIG_NUMA_AWARE_SPINLOCKS)
#define _GEN_CNA_LOCK_SLOWPATH
+#undef pv_init_node
+#define pv_init_node cna_init_node
+
#undef pv_wait_head_or_lock
#define pv_wait_head_or_lock cna_pre_scan
diff --git a/kernel/locking/qspinlock_cna.h b/kernel/locking/qspinlock_cna.h
index 3c99a4a6184b..30feff02865d 100644
--- a/kernel/locking/qspinlock_cna.h
+++ b/kernel/locking/qspinlock_cna.h
@@ -51,13 +51,25 @@ struct cna_node {
int numa_node;
u32 encoded_tail;
u32 pre_scan_result; /* encoded tail or enum val */
+ u32 intra_count;
};
enum {
LOCAL_WAITER_FOUND = 2, /* 0 and 1 are reserved for @locked */
+ FLUSH_SECONDARY_QUEUE = 3,
MIN_ENCODED_TAIL
};
+/*
+ * Controls the threshold for the number of intra-node lock hand-offs before
+ * the NUMA-aware variant of spinlock is forced to be passed to a thread on
+ * another NUMA node. By default, the chosen value provides reasonable
+ * long-term fairness without sacrificing performance compared to a lock
+ * that does not have any fairness guarantees. The default setting can
+ * be changed with the "numa_spinlock_threshold" boot option.
+ */
+int intra_node_handoff_threshold __ro_after_init = 1 << 16;
+
static void __init cna_init_nodes_per_cpu(unsigned int cpu)
{
struct mcs_spinlock *base = per_cpu_ptr(&qnodes[0].mcs, cpu);
@@ -97,6 +109,11 @@ static int __init cna_init_nodes(void)
}
early_initcall(cna_init_nodes);
+static __always_inline void cna_init_node(struct mcs_spinlock *node)
+{
+ ((struct cna_node *)node)->intra_count = 0;
+}
+
/* this function is called only when the primary queue is empty */
static inline bool cna_try_change_tail(struct qspinlock *lock, u32 val,
struct mcs_spinlock *node)
@@ -233,7 +250,9 @@ __always_inline u32 cna_pre_scan(struct qspinlock *lock,
{
struct cna_node *cn = (struct cna_node *)node;
- cn->pre_scan_result = cna_scan_main_queue(node, node);
+ cn->pre_scan_result =
+ cn->intra_count == intra_node_handoff_threshold ?
+ FLUSH_SECONDARY_QUEUE : cna_scan_main_queue(node, node);
return 0;
}
@@ -263,6 +282,9 @@ static inline void cna_pass_lock(struct mcs_spinlock *node,
* if we acquired the MCS lock when its queue was empty
*/
val = node->locked ? node->locked : 1;
+ /* inc @intra_count if the secondary queue is not empty */
+ ((struct cna_node *)next_holder)->intra_count =
+ cn->intra_count + (node->locked > 1);
} else if (node->locked > 1) { /* if secondary queue is not empty */
/* next holder will be the first node in the secondary queue */
tail_2nd = decode_tail(node->locked);
@@ -317,3 +339,20 @@ void cna_configure_spin_lock_slowpath(void)
pr_info("Enabling CNA spinlock\n");
}
}
+
+static int __init numa_spinlock_threshold_setup(char *str)
+{
+ int new_threshold_param;
+
+ if (get_option(&str, &new_threshold_param)) {
+ /* valid value is between 0 and 31 */
+ if (new_threshold_param < 0 || new_threshold_param > 31)
+ return 0;
+
+ intra_node_handoff_threshold = 1 << new_threshold_param;
+ return 1;
+ }
+
+ return 0;
+}
+__setup("numa_spinlock_threshold=", numa_spinlock_threshold_setup);
--
2.21.0 (Apple Git-122.2)
Powered by blists - more mailing lists