Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     linux-kernel@vger.kernel.org, Thomas Gleixner <tglx@linutronix.de>,
        "Paul E . McKenney" <paulmck@kernel.org>,
        Boqun Feng <boqun.feng@gmail.com>,
        "H . Peter Anvin" <hpa@zytor.com>, Paul Turner <pjt@google.com>,
        linux-api@vger.kernel.org, Christian Brauner <brauner@kernel.org>,
        Florian Weimer <fw@deneb.enyo.de>, David.Laight@ACULAB.COM,
        carlos@redhat.com, Peter Oskolkov <posk@posk.io>,
        Alexander Mikhalitsyn <alexander@mihalicyn.com>,
        Chris Kennelly <ckennelly@google.com>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Subject: [PATCH v5 03/24] rseq: Extend struct rseq with numa node id
Date:   Thu,  3 Nov 2022 16:03:38 -0400
Message-Id: <20221103200359.328736-4-mathieu.desnoyers@efficios.com>
In-Reply-To: <20221103200359.328736-1-mathieu.desnoyers@efficios.com>
References: <20221103200359.328736-1-mathieu.desnoyers@efficios.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Adding the NUMA node id to struct rseq is a straightforward thing to do,
and a good way to figure out if anything in the user-space ecosystem
prevents extending struct rseq.

This NUMA node id field allows memory allocators such as tcmalloc to
take advantage of fast access to the current NUMA node id to perform
NUMA-aware memory allocation.

It can also be useful for implementing fast-paths for NUMA-aware
user-space mutexes.

It also allows implementing getcpu(2) purely in user-space.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
---
Changes since v4:
- Use __entry->cpu_id as argument for cpu_to_node() in the rseq_update
  tracepoint.
---
 include/trace/events/rseq.h |  4 +++-
 include/uapi/linux/rseq.h   |  8 ++++++++
 kernel/rseq.c               | 19 +++++++++++++------
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/include/trace/events/rseq.h b/include/trace/events/rseq.h
index a04a64bc1a00..dde7a359b4ef 100644
--- a/include/trace/events/rseq.h
+++ b/include/trace/events/rseq.h
@@ -16,13 +16,15 @@ TRACE_EVENT(rseq_update,
 
 	TP_STRUCT__entry(
 		__field(s32, cpu_id)
+		__field(s32, node_id)
 	),
 
 	TP_fast_assign(
 		__entry->cpu_id = raw_smp_processor_id();
+		__entry->node_id = cpu_to_node(__entry->cpu_id);
 	),
 
-	TP_printk("cpu_id=%d", __entry->cpu_id)
+	TP_printk("cpu_id=%d node_id=%d", __entry->cpu_id, __entry->node_id)
 );
 
 TRACE_EVENT(rseq_ip_fixup,
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 05d3c4cdeb40..1cb90a435c5c 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -131,6 +131,14 @@ struct rseq {
 	 */
 	__u32 flags;
 
+	/*
+	 * Restartable sequences node_id field. Updated by the kernel. Read by
+	 * user-space with single-copy atomicity semantics. This field should
+	 * only be read by the thread which registered this data structure.
+	 * Aligned on 32-bit. Contains the current NUMA node ID.
+	 */
+	__u32 node_id;
+
 	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
diff --git a/kernel/rseq.c b/kernel/rseq.c
index c1058b3f10ac..e21ad8929958 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -85,15 +85,17 @@
  *   F1. <failure>
  */
 
-static int rseq_update_cpu_id(struct task_struct *t)
+static int rseq_update_cpu_node_id(struct task_struct *t)
 {
-	u32 cpu_id = raw_smp_processor_id();
 	struct rseq __user *rseq = t->rseq;
+	u32 cpu_id = raw_smp_processor_id();
+	u32 node_id = cpu_to_node(cpu_id);
 
 	if (!user_write_access_begin(rseq, t->rseq_len))
 		goto efault;
 	unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end);
 	unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end);
+	unsafe_put_user(node_id, &rseq->node_id, efault_end);
 	/*
 	 * Additional feature fields added after ORIG_RSEQ_SIZE
 	 * need to be conditionally updated only if
@@ -109,9 +111,9 @@ static int rseq_update_cpu_id(struct task_struct *t)
 	return -EFAULT;
 }
 
-static int rseq_reset_rseq_cpu_id(struct task_struct *t)
+static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
 {
-	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED;
+	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0;
 
 	/*
 	 * Reset cpu_id_start to its initial state (0).
@@ -125,6 +127,11 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
 	 */
 	if (put_user(cpu_id, &t->rseq->cpu_id))
 		return -EFAULT;
+	/*
+	 * Reset node_id to its initial state (0).
+	 */
+	if (put_user(node_id, &t->rseq->node_id))
+		return -EFAULT;
 	/*
 	 * Additional feature fields added after ORIG_RSEQ_SIZE
 	 * need to be conditionally reset only if
@@ -299,7 +306,7 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 		if (unlikely(ret < 0))
 			goto error;
 	}
-	if (unlikely(rseq_update_cpu_id(t)))
+	if (unlikely(rseq_update_cpu_node_id(t)))
 		goto error;
 	return;
 
@@ -346,7 +353,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 			return -EINVAL;
 		if (current->rseq_sig != sig)
 			return -EPERM;
-		ret = rseq_reset_rseq_cpu_id(current);
+		ret = rseq_reset_rseq_cpu_node_id(current);
 		if (ret)
 			return ret;
 		current->rseq = NULL;
-- 
2.25.1