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>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Subject: [PATCH v4 02/25] rseq: Introduce extensible rseq ABI
Date: Thu, 22 Sep 2022 06:59:17 -0400 [thread overview]
Message-ID: <20220922105941.237830-3-mathieu.desnoyers@efficios.com> (raw)
In-Reply-To: <20220922105941.237830-1-mathieu.desnoyers@efficios.com>
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@efficios.com>
---
include/linux/sched.h | 4 ++++
kernel/ptrace.c | 2 +-
kernel/rseq.c | 33 +++++++++++++++++++++++++++------
3 files changed, 32 insertions(+), 7 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c46f3a63b758..6a80ce113d0e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1291,6 +1291,7 @@ 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
@@ -2324,10 +2325,12 @@ 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;
}
@@ -2336,6 +2339,7 @@ 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 1893d909e45c..90de1ea51088 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 97ac20b4f738..46dc5c2ce2b7 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_PREEMPT_MIGRATE_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE | \
RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT)
@@ -86,10 +89,15 @@ 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;
@@ -116,6 +124,11 @@ 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;
}
@@ -336,7 +349,7 @@ 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;
@@ -345,6 +358,7 @@ 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;
}
@@ -357,7 +371,7 @@ 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;
@@ -366,15 +380,22 @@ 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.
+ *
+ * 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))
+ rseq_len < ORIG_RSEQ_SIZE ||
+ (rseq_len != ORIG_RSEQ_SIZE && 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
--
2.25.1
next prev parent reply other threads:[~2022-09-22 11:05 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-22 10:59 [PATCH v4 00/25] RSEQ node id and virtual cpu id extensions Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 01/25] rseq: Introduce feature size and alignment ELF auxiliary vector entries Mathieu Desnoyers
2022-10-10 12:42 ` Florian Weimer
2022-10-17 16:09 ` Mathieu Desnoyers
2022-10-17 17:32 ` Mathieu Desnoyers
2022-10-18 15:34 ` Florian Weimer
2022-10-18 19:00 ` Mathieu Desnoyers
2022-09-22 10:59 ` Mathieu Desnoyers [this message]
2022-09-22 10:59 ` [PATCH v4 03/25] rseq: Extend struct rseq with numa node id Mathieu Desnoyers
2022-09-23 11:13 ` Peter Zijlstra
2022-09-23 13:00 ` Mathieu Desnoyers
2022-09-23 13:09 ` [PATCH v4.1 03/25 1/1] " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 04/25] selftests/rseq: Use ELF auxiliary vector for extensible rseq Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 05/25] selftests/rseq: Implement rseq numa node id field selftest Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 06/25] lib: Invert _find_next_bit source arguments Mathieu Desnoyers
2022-09-27 8:04 ` kernel test robot
2022-09-22 10:59 ` [PATCH v4 07/25] lib: Implement find_{first,next}_{zero,one}_and_zero_bit Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 08/25] cpumask: Implement cpumask_{first,next}_{zero,one}_and_zero Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 09/25] sched: Introduce per memory space current virtual cpu id Mathieu Desnoyers
2022-09-27 13:43 ` [PATCH v4.1 " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 10/25] rseq: Extend struct rseq with per memory space vcpu id Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 11/25] selftests/rseq: Remove RSEQ_SKIP_FASTPATH code Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 12/25] selftests/rseq: Implement rseq vm_vcpu_id field support Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 13/25] selftests/rseq: x86: Template memory ordering and percpu access mode Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 14/25] selftests/rseq: arm: " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 15/25] selftests/rseq: arm64: " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 16/25] selftests/rseq: mips: " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 17/25] selftests/rseq: ppc: " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 18/25] selftests/rseq: s390: " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 19/25] selftests/rseq: riscv: " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 20/25] selftests/rseq: Implement basic percpu ops vm_vcpu_id test Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 21/25] selftests/rseq: Implement parametrized " Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 22/25] selftests/rseq: x86: Implement rseq_load_u32_u32 Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 23/25] selftests/rseq: Implement numa node id vs vm_vcpu_id invariant test Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 24/25] selftests/rseq: parametrized test: Report/abort on negative cpu id Mathieu Desnoyers
2022-09-22 10:59 ` [PATCH v4 25/25] tracing/rseq: Add mm_vcpu_id field to rseq_update Mathieu Desnoyers
2022-09-22 15:14 ` kernel test robot
2022-09-22 15:33 ` [PATCH v4.1 " Mathieu Desnoyers
2022-09-23 9:55 ` [PATCH v4 " kernel test robot
[not found] ` <e753568d-599c-d81a-8456-085bbbb0264d@efficios.com>
[not found] ` <CAEE+ybnLUHjU5-dWcWgcWiq-AM4ocquSbZ=PWiuexEsPB8P5Gw@mail.gmail.com>
2022-09-23 13:46 ` [PATCH v4 00/25] RSEQ node id and virtual cpu id extensions Mathieu Desnoyers
2022-10-10 13:04 ` Florian Weimer
2022-10-17 16:05 ` Mathieu Desnoyers
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=20220922105941.237830-3-mathieu.desnoyers@efficios.com \
--to=mathieu.desnoyers@efficios.com \
--cc=David.Laight@ACULAB.COM \
--cc=alexander@mihalicyn.com \
--cc=boqun.feng@gmail.com \
--cc=brauner@kernel.org \
--cc=carlos@redhat.com \
--cc=fw@deneb.enyo.de \
--cc=hpa@zytor.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=posk@posk.io \
--cc=tglx@linutronix.de \
/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;
as well as URLs for NNTP newsgroup(s).