[tip: sched/core] rseq: Introduce extensible rseq ABI

From: tip-bot2 for Mathieu Desnoyers
Date: Tue Dec 27 2022 - 07:17:13 EST


The following commit has been merged into the sched/core branch of tip:

Commit-ID: ee3e3ac05c2631ce1f12d88c9cc9a092f8fe947a
Gitweb: https://git.kernel.org/tip/ee3e3ac05c2631ce1f12d88c9cc9a092f8fe947a
Author: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
AuthorDate: Tue, 22 Nov 2022 15:39:05 -05:00
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Tue, 27 Dec 2022 12:52:10 +01:00

rseq: Introduce extensible rseq ABI

Introduce the extensible rseq ABI, where the feature size supported by
the kernel and the required alignment are communicated to user-space
through ELF auxiliary vectors.

This allows user-space to call rseq registration with a rseq_len of
either 32 bytes for the original struct rseq size (which includes
padding), or larger.

If rseq_len is larger than 32 bytes, then it must be large enough to
contain the feature size communicated to user-space through ELF
auxiliary vectors.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20221122203932.231377-4-mathieu.desnoyers@xxxxxxxxxxxx
---
include/linux/sched.h | 4 ++++
kernel/ptrace.c | 2 +-
kernel/rseq.c | 37 ++++++++++++++++++++++++++++++-------
3 files changed, 35 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 853d08f..e0bc020 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1302,6 +1302,7 @@ struct task_struct {

#ifdef CONFIG_RSEQ
struct rseq __user *rseq;
+ u32 rseq_len;
u32 rseq_sig;
/*
* RmW on rseq_event_mask must be performed atomically
@@ -2352,10 +2353,12 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
if (clone_flags & CLONE_VM) {
t->rseq = NULL;
+ t->rseq_len = 0;
t->rseq_sig = 0;
t->rseq_event_mask = 0;
} else {
t->rseq = current->rseq;
+ t->rseq_len = current->rseq_len;
t->rseq_sig = current->rseq_sig;
t->rseq_event_mask = current->rseq_event_mask;
}
@@ -2364,6 +2367,7 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
static inline void rseq_execve(struct task_struct *t)
{
t->rseq = NULL;
+ t->rseq_len = 0;
t->rseq_sig = 0;
t->rseq_event_mask = 0;
}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 5448219..0786450 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -813,7 +813,7 @@ static long ptrace_get_rseq_configuration(struct task_struct *task,
{
struct ptrace_rseq_configuration conf = {
.rseq_abi_pointer = (u64)(uintptr_t)task->rseq,
- .rseq_abi_size = sizeof(*task->rseq),
+ .rseq_abi_size = task->rseq_len,
.signature = task->rseq_sig,
.flags = 0,
};
diff --git a/kernel/rseq.c b/kernel/rseq.c
index d38ab94..7962738 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -18,6 +18,9 @@
#define CREATE_TRACE_POINTS
#include <trace/events/rseq.h>

+/* The original rseq structure size (including padding) is 32 bytes. */
+#define ORIG_RSEQ_SIZE 32
+
#define RSEQ_CS_NO_RESTART_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT | \
RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \
RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE)
@@ -87,10 +90,15 @@ static int rseq_update_cpu_id(struct task_struct *t)
u32 cpu_id = raw_smp_processor_id();
struct rseq __user *rseq = t->rseq;

- if (!user_write_access_begin(rseq, sizeof(*rseq)))
+ 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);
+ /*
+ * Additional feature fields added after ORIG_RSEQ_SIZE
+ * need to be conditionally updated only if
+ * t->rseq_len != ORIG_RSEQ_SIZE.
+ */
user_write_access_end();
trace_rseq_update(t);
return 0;
@@ -117,6 +125,11 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
*/
if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
+ /*
+ * Additional feature fields added after ORIG_RSEQ_SIZE
+ * need to be conditionally reset only if
+ * t->rseq_len != ORIG_RSEQ_SIZE.
+ */
return 0;
}

@@ -344,7 +357,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
/* Unregister rseq for current thread. */
if (current->rseq != rseq || !current->rseq)
return -EINVAL;
- if (rseq_len != sizeof(*rseq))
+ if (rseq_len != current->rseq_len)
return -EINVAL;
if (current->rseq_sig != sig)
return -EPERM;
@@ -353,6 +366,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
return ret;
current->rseq = NULL;
current->rseq_sig = 0;
+ current->rseq_len = 0;
return 0;
}

@@ -365,7 +379,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
* the provided address differs from the prior
* one.
*/
- if (current->rseq != rseq || rseq_len != sizeof(*rseq))
+ if (current->rseq != rseq || rseq_len != current->rseq_len)
return -EINVAL;
if (current->rseq_sig != sig)
return -EPERM;
@@ -374,15 +388,24 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
}

/*
- * If there was no rseq previously registered,
- * ensure the provided rseq is properly aligned and valid.
+ * If there was no rseq previously registered, ensure the provided rseq
+ * is properly aligned, as communcated to user-space through the ELF
+ * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq
+ * size, the required alignment is the original struct rseq alignment.
+ *
+ * In order to be valid, rseq_len is either the original rseq size, or
+ * large enough to contain all supported fields, as communicated to
+ * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE.
*/
- if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
- rseq_len != sizeof(*rseq))
+ if (rseq_len < ORIG_RSEQ_SIZE ||
+ (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) ||
+ (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
+ rseq_len < offsetof(struct rseq, end))))
return -EINVAL;
if (!access_ok(rseq, rseq_len))
return -EFAULT;
current->rseq = rseq;
+ current->rseq_len = rseq_len;
current->rseq_sig = sig;
/*
* If rseq was previously inactive, and has just been