mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 01:10:04 +00:00
![Sean Christopherson](/assets/img/avatar_default.png)
Invoke rseq's NOTIFY_RESUME handler when processing the flag prior to
transferring to a KVM guest, which is roughly equivalent to an exit to
userspace and processes many of the same pending actions. While the task
cannot be in an rseq critical section as the KVM path is reachable only
by via ioctl(KVM_RUN), the side effects that apply to rseq outside of a
critical section still apply, e.g. the current CPU needs to be updated if
the task is migrated.
Clearing TIF_NOTIFY_RESUME without informing rseq can lead to segfaults
and other badness in userspace VMMs that use rseq in combination with KVM,
e.g. due to the CPU ID being stale after task migration.
Fixes: 72c3c0fe54
("x86/kvm: Use generic xfer to guest work function")
Reported-by: Peter Foley <pefoley@google.com>
Bisected-by: Doug Evans <dje@google.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210901203030.1292304-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
387 lines
10 KiB
C
387 lines
10 KiB
C
// SPDX-License-Identifier: GPL-2.0+
|
|
/*
|
|
* Restartable sequences system call
|
|
*
|
|
* Copyright (C) 2015, Google, Inc.,
|
|
* Paul Turner <pjt@google.com> and Andrew Hunter <ahh@google.com>
|
|
* Copyright (C) 2015-2018, EfficiOS Inc.,
|
|
* Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/rseq.h>
|
|
#include <linux/types.h>
|
|
#include <asm/ptrace.h>
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/rseq.h>
|
|
|
|
#define RSEQ_CS_PREEMPT_MIGRATE_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE | \
|
|
RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT)
|
|
|
|
/*
|
|
*
|
|
* Restartable sequences are a lightweight interface that allows
|
|
* user-level code to be executed atomically relative to scheduler
|
|
* preemption and signal delivery. Typically used for implementing
|
|
* per-cpu operations.
|
|
*
|
|
* It allows user-space to perform update operations on per-cpu data
|
|
* without requiring heavy-weight atomic operations.
|
|
*
|
|
* Detailed algorithm of rseq user-space assembly sequences:
|
|
*
|
|
* init(rseq_cs)
|
|
* cpu = TLS->rseq::cpu_id_start
|
|
* [1] TLS->rseq::rseq_cs = rseq_cs
|
|
* [start_ip] ----------------------------
|
|
* [2] if (cpu != TLS->rseq::cpu_id)
|
|
* goto abort_ip;
|
|
* [3] <last_instruction_in_cs>
|
|
* [post_commit_ip] ----------------------------
|
|
*
|
|
* The address of jump target abort_ip must be outside the critical
|
|
* region, i.e.:
|
|
*
|
|
* [abort_ip] < [start_ip] || [abort_ip] >= [post_commit_ip]
|
|
*
|
|
* Steps [2]-[3] (inclusive) need to be a sequence of instructions in
|
|
* userspace that can handle being interrupted between any of those
|
|
* instructions, and then resumed to the abort_ip.
|
|
*
|
|
* 1. Userspace stores the address of the struct rseq_cs assembly
|
|
* block descriptor into the rseq_cs field of the registered
|
|
* struct rseq TLS area. This update is performed through a single
|
|
* store within the inline assembly instruction sequence.
|
|
* [start_ip]
|
|
*
|
|
* 2. Userspace tests to check whether the current cpu_id field match
|
|
* the cpu number loaded before start_ip, branching to abort_ip
|
|
* in case of a mismatch.
|
|
*
|
|
* If the sequence is preempted or interrupted by a signal
|
|
* at or after start_ip and before post_commit_ip, then the kernel
|
|
* clears TLS->__rseq_abi::rseq_cs, and sets the user-space return
|
|
* ip to abort_ip before returning to user-space, so the preempted
|
|
* execution resumes at abort_ip.
|
|
*
|
|
* 3. Userspace critical section final instruction before
|
|
* post_commit_ip is the commit. The critical section is
|
|
* self-terminating.
|
|
* [post_commit_ip]
|
|
*
|
|
* 4. <success>
|
|
*
|
|
* On failure at [2], or if interrupted by preempt or signal delivery
|
|
* between [1] and [3]:
|
|
*
|
|
* [abort_ip]
|
|
* F1. <failure>
|
|
*/
|
|
|
|
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)))
|
|
goto efault;
|
|
unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end);
|
|
unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end);
|
|
user_write_access_end();
|
|
trace_rseq_update(t);
|
|
return 0;
|
|
|
|
efault_end:
|
|
user_write_access_end();
|
|
efault:
|
|
return -EFAULT;
|
|
}
|
|
|
|
static int rseq_reset_rseq_cpu_id(struct task_struct *t)
|
|
{
|
|
u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED;
|
|
|
|
/*
|
|
* Reset cpu_id_start to its initial state (0).
|
|
*/
|
|
if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
|
|
return -EFAULT;
|
|
/*
|
|
* Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
|
|
* in after unregistration can figure out that rseq needs to be
|
|
* registered again.
|
|
*/
|
|
if (put_user(cpu_id, &t->rseq->cpu_id))
|
|
return -EFAULT;
|
|
return 0;
|
|
}
|
|
|
|
static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
|
|
{
|
|
struct rseq_cs __user *urseq_cs;
|
|
u64 ptr;
|
|
u32 __user *usig;
|
|
u32 sig;
|
|
int ret;
|
|
|
|
#ifdef CONFIG_64BIT
|
|
if (get_user(ptr, &t->rseq->rseq_cs.ptr64))
|
|
return -EFAULT;
|
|
#else
|
|
if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
|
|
return -EFAULT;
|
|
#endif
|
|
if (!ptr) {
|
|
memset(rseq_cs, 0, sizeof(*rseq_cs));
|
|
return 0;
|
|
}
|
|
if (ptr >= TASK_SIZE)
|
|
return -EINVAL;
|
|
urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
|
|
if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
|
|
return -EFAULT;
|
|
|
|
if (rseq_cs->start_ip >= TASK_SIZE ||
|
|
rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
|
|
rseq_cs->abort_ip >= TASK_SIZE ||
|
|
rseq_cs->version > 0)
|
|
return -EINVAL;
|
|
/* Check for overflow. */
|
|
if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
|
|
return -EINVAL;
|
|
/* Ensure that abort_ip is not in the critical section. */
|
|
if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
|
|
return -EINVAL;
|
|
|
|
usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
|
|
ret = get_user(sig, usig);
|
|
if (ret)
|
|
return ret;
|
|
|
|
if (current->rseq_sig != sig) {
|
|
printk_ratelimited(KERN_WARNING
|
|
"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
|
|
sig, current->rseq_sig, current->pid, usig);
|
|
return -EINVAL;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
|
|
{
|
|
u32 flags, event_mask;
|
|
int ret;
|
|
|
|
/* Get thread flags. */
|
|
ret = get_user(flags, &t->rseq->flags);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/* Take critical section flags into account. */
|
|
flags |= cs_flags;
|
|
|
|
/*
|
|
* Restart on signal can only be inhibited when restart on
|
|
* preempt and restart on migrate are inhibited too. Otherwise,
|
|
* a preempted signal handler could fail to restart the prior
|
|
* execution context on sigreturn.
|
|
*/
|
|
if (unlikely((flags & RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL) &&
|
|
(flags & RSEQ_CS_PREEMPT_MIGRATE_FLAGS) !=
|
|
RSEQ_CS_PREEMPT_MIGRATE_FLAGS))
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* Load and clear event mask atomically with respect to
|
|
* scheduler preemption.
|
|
*/
|
|
preempt_disable();
|
|
event_mask = t->rseq_event_mask;
|
|
t->rseq_event_mask = 0;
|
|
preempt_enable();
|
|
|
|
return !!(event_mask & ~flags);
|
|
}
|
|
|
|
static int clear_rseq_cs(struct task_struct *t)
|
|
{
|
|
/*
|
|
* The rseq_cs field is set to NULL on preemption or signal
|
|
* delivery on top of rseq assembly block, as well as on top
|
|
* of code outside of the rseq assembly block. This performs
|
|
* a lazy clear of the rseq_cs field.
|
|
*
|
|
* Set rseq_cs to NULL.
|
|
*/
|
|
#ifdef CONFIG_64BIT
|
|
return put_user(0UL, &t->rseq->rseq_cs.ptr64);
|
|
#else
|
|
if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
|
|
return -EFAULT;
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* Unsigned comparison will be true when ip >= start_ip, and when
|
|
* ip < start_ip + post_commit_offset.
|
|
*/
|
|
static bool in_rseq_cs(unsigned long ip, struct rseq_cs *rseq_cs)
|
|
{
|
|
return ip - rseq_cs->start_ip < rseq_cs->post_commit_offset;
|
|
}
|
|
|
|
static int rseq_ip_fixup(struct pt_regs *regs)
|
|
{
|
|
unsigned long ip = instruction_pointer(regs);
|
|
struct task_struct *t = current;
|
|
struct rseq_cs rseq_cs;
|
|
int ret;
|
|
|
|
ret = rseq_get_rseq_cs(t, &rseq_cs);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/*
|
|
* Handle potentially not being within a critical section.
|
|
* If not nested over a rseq critical section, restart is useless.
|
|
* Clear the rseq_cs pointer and return.
|
|
*/
|
|
if (!in_rseq_cs(ip, &rseq_cs))
|
|
return clear_rseq_cs(t);
|
|
ret = rseq_need_restart(t, rseq_cs.flags);
|
|
if (ret <= 0)
|
|
return ret;
|
|
ret = clear_rseq_cs(t);
|
|
if (ret)
|
|
return ret;
|
|
trace_rseq_ip_fixup(ip, rseq_cs.start_ip, rseq_cs.post_commit_offset,
|
|
rseq_cs.abort_ip);
|
|
instruction_pointer_set(regs, (unsigned long)rseq_cs.abort_ip);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* This resume handler must always be executed between any of:
|
|
* - preemption,
|
|
* - signal delivery,
|
|
* and return to user-space.
|
|
*
|
|
* This is how we can ensure that the entire rseq critical section
|
|
* will issue the commit instruction only if executed atomically with
|
|
* respect to other threads scheduled on the same CPU, and with respect
|
|
* to signal handlers.
|
|
*/
|
|
void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
|
|
{
|
|
struct task_struct *t = current;
|
|
int ret, sig;
|
|
|
|
if (unlikely(t->flags & PF_EXITING))
|
|
return;
|
|
|
|
/*
|
|
* regs is NULL if and only if the caller is in a syscall path. Skip
|
|
* fixup and leave rseq_cs as is so that rseq_sycall() will detect and
|
|
* kill a misbehaving userspace on debug kernels.
|
|
*/
|
|
if (regs) {
|
|
ret = rseq_ip_fixup(regs);
|
|
if (unlikely(ret < 0))
|
|
goto error;
|
|
}
|
|
if (unlikely(rseq_update_cpu_id(t)))
|
|
goto error;
|
|
return;
|
|
|
|
error:
|
|
sig = ksig ? ksig->sig : 0;
|
|
force_sigsegv(sig);
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_RSEQ
|
|
|
|
/*
|
|
* Terminate the process if a syscall is issued within a restartable
|
|
* sequence.
|
|
*/
|
|
void rseq_syscall(struct pt_regs *regs)
|
|
{
|
|
unsigned long ip = instruction_pointer(regs);
|
|
struct task_struct *t = current;
|
|
struct rseq_cs rseq_cs;
|
|
|
|
if (!t->rseq)
|
|
return;
|
|
if (rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs))
|
|
force_sig(SIGSEGV);
|
|
}
|
|
|
|
#endif
|
|
|
|
/*
|
|
* sys_rseq - setup restartable sequences for caller thread.
|
|
*/
|
|
SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
|
|
int, flags, u32, sig)
|
|
{
|
|
int ret;
|
|
|
|
if (flags & RSEQ_FLAG_UNREGISTER) {
|
|
if (flags & ~RSEQ_FLAG_UNREGISTER)
|
|
return -EINVAL;
|
|
/* Unregister rseq for current thread. */
|
|
if (current->rseq != rseq || !current->rseq)
|
|
return -EINVAL;
|
|
if (rseq_len != sizeof(*rseq))
|
|
return -EINVAL;
|
|
if (current->rseq_sig != sig)
|
|
return -EPERM;
|
|
ret = rseq_reset_rseq_cpu_id(current);
|
|
if (ret)
|
|
return ret;
|
|
current->rseq = NULL;
|
|
current->rseq_sig = 0;
|
|
return 0;
|
|
}
|
|
|
|
if (unlikely(flags))
|
|
return -EINVAL;
|
|
|
|
if (current->rseq) {
|
|
/*
|
|
* If rseq is already registered, check whether
|
|
* the provided address differs from the prior
|
|
* one.
|
|
*/
|
|
if (current->rseq != rseq || rseq_len != sizeof(*rseq))
|
|
return -EINVAL;
|
|
if (current->rseq_sig != sig)
|
|
return -EPERM;
|
|
/* Already registered. */
|
|
return -EBUSY;
|
|
}
|
|
|
|
/*
|
|
* If there was no rseq previously registered,
|
|
* ensure the provided rseq is properly aligned and valid.
|
|
*/
|
|
if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
|
|
rseq_len != sizeof(*rseq))
|
|
return -EINVAL;
|
|
if (!access_ok(rseq, rseq_len))
|
|
return -EFAULT;
|
|
current->rseq = rseq;
|
|
current->rseq_sig = sig;
|
|
/*
|
|
* If rseq was previously inactive, and has just been
|
|
* registered, ensure the cpu_id_start and cpu_id fields
|
|
* are updated before returning to user-space.
|
|
*/
|
|
rseq_set_notify_resume(current);
|
|
|
|
return 0;
|
|
}
|