linux-kernel - [RFC PATCH 2/3] rseq: extend struct rseq with per thread group vcpu id

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220201192540.10439-2-mathieu.desnoyers@efficios.com>
Date:   Tue,  1 Feb 2022 14:25:39 -0500
From:   Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Boqun Feng <boqun.feng@...il.com>,
        "H . Peter Anvin" <hpa@...or.com>, Paul Turner <pjt@...gle.com>,
        linux-api@...r.kernel.org,
        Christian Brauner <christian.brauner@...ntu.com>,
        Florian Weimer <fw@...eb.enyo.de>, David.Laight@...LAB.COM,
        carlos@...hat.com, Peter Oskolkov <posk@...k.io>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Subject: [RFC PATCH 2/3] rseq: extend struct rseq with per thread group vcpu id

If a thread group has fewer threads than cores, or is limited to run on
few cores concurrently through sched affinity or cgroup cpusets, the
virtual cpu ids will be values close to 0, thus allowing efficient use
of user-space memory for per-cpu data structures.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
---
 include/uapi/linux/rseq.h | 15 +++++++++++++++
 kernel/rseq.c             | 16 +++++++++++++++-
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 386c25b5bbdb..d687ac79e62c 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -154,6 +154,21 @@ struct rseq {
 	 * rseq_len. Use the offset immediately after the node_id field as
 	 * rseq_len.
 	 */
+
+	/*
+	 * Restartable sequences tg_vcpu_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 thread's virtual CPU ID
+	 * (allocated uniquely within thread group).
+	 */
+	__u32 tg_vcpu_id;
+
+	/*
+	 * This is a valid end of rseq ABI for the purpose of rseq registration
+	 * rseq_len. Use the offset immediately after the tg_vcpu_id field as
+	 * rseq_len.
+	 */
 } __attribute__((aligned(4 * sizeof(__u64))));
 
 #endif /* _UAPI_LINUX_RSEQ_H */
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 13f6d0419f31..37b43735a400 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -86,10 +86,14 @@ static int rseq_update_cpu_node_id(struct task_struct *t)
 	struct rseq __user *rseq = t->rseq;
 	u32 cpu_id = raw_smp_processor_id();
 	u32 node_id = cpu_to_node(cpu_id);
+	u32 tg_vcpu_id = task_tg_vcpu_id(t);
 
 	if (!user_write_access_begin(rseq, t->rseq_len))
 		goto efault;
 	switch (t->rseq_len) {
+	case offsetofend(struct rseq, tg_vcpu_id):
+		unsafe_put_user(tg_vcpu_id, &rseq->tg_vcpu_id, efault_end);
+		fallthrough;
 	case offsetofend(struct rseq, node_id):
 		unsafe_put_user(node_id, &rseq->node_id, efault_end);
 		fallthrough;
@@ -112,9 +116,17 @@ static int rseq_update_cpu_node_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, node_id = 0;
+	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0,
+	    tg_vcpu_id = 0;
 
 	switch (t->rseq_len) {
+	case offsetofend(struct rseq, tg_vcpu_id):
+		/*
+		 * Reset tg_vcpu_id to its initial state (0).
+		 */
+		if (put_user(tg_vcpu_id, &t->rseq->tg_vcpu_id))
+			return -EFAULT;
+		fallthrough;
 	case offsetofend(struct rseq, node_id):
 		/*
 		 * Reset node_id to its initial state (0).
@@ -396,6 +408,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 	if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)))
 		return -EINVAL;
 	switch (rseq_len) {
+	case offsetofend(struct rseq, tg_vcpu_id):
+		fallthrough;
 	case offsetofend(struct rseq, node_id):
 		fallthrough;
 	case offsetofend(struct rseq, padding1):
-- 
2.17.1