mirror of
https://github.com/torvalds/linux
synced 2026-07-22 18:20:51 +09:00
Unlocking robust non-PI futexes happens in user space with the following sequence: 1) robust_list_set_op_pending(mutex); 2) robust_list_remove(mutex); lval = 0; 3) lval = atomic_xchg(lock, lval); 4) if (lval & WAITERS) 5) sys_futex(WAKE,....); 6) robust_list_clear_op_pending(); That opens a window between #3 and #6 where the mutex could be acquired by some other task which observes that it is the last user and: A) unmaps the mutex memory B) maps a different file, which ends up covering the same address When the original task exits before reaching #6 then the kernel robust list handling observes the pending op entry and tries to fix up user space. In case that the newly mapped data contains the TID of the exiting thread at the address of the mutex/futex the kernel will set the owner died bit in that memory and therefore corrupting unrelated data. PI futexes have a similar problem both for the non-contented user space unlock and the in kernel unlock: 1) robust_list_set_op_pending(mutex); 2) robust_list_remove(mutex); lval = gettid(); 3) if (!atomic_try_cmpxchg(lock, lval, 0)) 4) sys_futex(UNLOCK_PI,....); 5) robust_list_clear_op_pending(); Address the first part of the problem where the futexes have waiters and need to enter the kernel anyway. Add a new FUTEX_ROBUST_UNLOCK flag, which is valid for the sys_futex() FUTEX_UNLOCK_PI, FUTEX_WAKE, FUTEX_WAKE_BITSET operations. This deliberately omits FUTEX_WAKE_OP from this treatment as it's unclear whether this is needed and there is no usage of it in glibc either to investigate. For the futex2 syscall family this needs to be implemented with a new syscall. The sys_futex() case [ab]uses the @uaddr2 argument to hand the pointer to robust_list_head::list_pending_op into the kernel. This argument is only evaluated when the FUTEX_ROBUST_UNLOCK bit is set and is therefore backward compatible. This is an explicit argument to avoid the lookup of the robust list pointer and retrieving the pending op pointer from there. User space has the pointer already available so it can just put it into the @uaddr2 argument. Aside of that this allows the usage of multiple robust lists in the future without any changes to the internal functions as they just operate on the provided pointer. This requires a second flag FUTEX_ROBUST_LIST32 which indicates that the robust list pointer points to an u32 and not to an u64. This is required for two reasons: 1) sys_futex() has no compat variant 2) The gaming emulators use both both 64-bit and compat 32-bit robust lists in the same 64-bit application As a consequence 32-bit applications have to set this flag unconditionally so they can run on a 64-bit kernel in compat mode unmodified. 32-bit kernels return an error code when the flag is not set. 64-bit kernels will happily clear the full 64 bits if user space fails to set it. In case of FUTEX_UNLOCK_PI this clears the robust list pending op when the unlock succeeded. In case of errors, the user space value is still locked by the caller and therefore the above cannot happen. In case of FUTEX_WAKE* this does the unlock of the futex in the kernel and clears the robust list pending op when the unlock was successful. If not, the user space value is still locked and user space has to deal with the returned error. That means that the unlocking of non-PI robust futexes has to use the same try_cmpxchg() unlock scheme as PI futexes. If the clearing of the pending list op fails (fault) then the kernel clears the registered robust list pointer if it matches to prevent that exit() will try to handle invalid data. That's a valid paranoid decision because the robust list head sits usually in the TLS and if the TLS is not longer accessible then the chance for fixing up the resulting mess is very close to zero. The problem of non-contended unlocks still exists and will be addressed separately. Signed-off-by: Thomas Gleixner <tglx@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: André Almeida <andrealmeid@igalia.com> Link: https://patch.msgid.link/20260602090535.670514505@kernel.org
337 lines
8.5 KiB
C
337 lines
8.5 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/kernel.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/file.h>
|
|
#include <linux/io_uring.h>
|
|
|
|
#include <uapi/linux/io_uring.h>
|
|
|
|
#include "../kernel/futex/futex.h"
|
|
#include "io_uring.h"
|
|
#include "alloc_cache.h"
|
|
#include "futex.h"
|
|
|
|
struct io_futex {
|
|
struct file *file;
|
|
void __user *uaddr;
|
|
unsigned long futex_val;
|
|
unsigned long futex_mask;
|
|
u32 futex_flags;
|
|
unsigned int futex_nr;
|
|
bool futexv_unqueued;
|
|
};
|
|
|
|
struct io_futex_data {
|
|
struct futex_q q;
|
|
struct io_kiocb *req;
|
|
};
|
|
|
|
struct io_futexv_data {
|
|
unsigned long owned;
|
|
struct futex_vector futexv[];
|
|
};
|
|
|
|
#define IO_FUTEX_ALLOC_CACHE_MAX 32
|
|
|
|
bool io_futex_cache_init(struct io_ring_ctx *ctx)
|
|
{
|
|
return io_alloc_cache_init(&ctx->futex_cache, IO_FUTEX_ALLOC_CACHE_MAX,
|
|
sizeof(struct io_futex_data), 0);
|
|
}
|
|
|
|
void io_futex_cache_free(struct io_ring_ctx *ctx)
|
|
{
|
|
io_alloc_cache_free(&ctx->futex_cache, kfree);
|
|
}
|
|
|
|
static void __io_futex_complete(struct io_tw_req tw_req, io_tw_token_t tw)
|
|
{
|
|
hlist_del_init(&tw_req.req->hash_node);
|
|
io_req_task_complete(tw_req, tw);
|
|
}
|
|
|
|
static void io_futex_complete(struct io_tw_req tw_req, io_tw_token_t tw)
|
|
{
|
|
struct io_kiocb *req = tw_req.req;
|
|
struct io_ring_ctx *ctx = req->ctx;
|
|
|
|
io_tw_lock(ctx, tw);
|
|
io_cache_free(&ctx->futex_cache, req->async_data);
|
|
io_req_async_data_clear(req, 0);
|
|
__io_futex_complete(tw_req, tw);
|
|
}
|
|
|
|
static void io_futexv_complete(struct io_tw_req tw_req, io_tw_token_t tw)
|
|
{
|
|
struct io_kiocb *req = tw_req.req;
|
|
struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
|
|
struct io_futexv_data *ifd = req->async_data;
|
|
|
|
io_tw_lock(req->ctx, tw);
|
|
|
|
if (!iof->futexv_unqueued) {
|
|
int res;
|
|
|
|
res = futex_unqueue_multiple(ifd->futexv, iof->futex_nr);
|
|
if (res != -1)
|
|
io_req_set_res(req, res, 0);
|
|
}
|
|
|
|
io_req_async_data_free(req);
|
|
__io_futex_complete(tw_req, tw);
|
|
}
|
|
|
|
static bool io_futexv_claim(struct io_futexv_data *ifd)
|
|
{
|
|
if (test_bit(0, &ifd->owned) || test_and_set_bit_lock(0, &ifd->owned))
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
static bool __io_futex_cancel(struct io_kiocb *req)
|
|
{
|
|
/* futex wake already done or in progress */
|
|
if (req->opcode == IORING_OP_FUTEX_WAIT) {
|
|
struct io_futex_data *ifd = req->async_data;
|
|
|
|
if (!futex_unqueue(&ifd->q))
|
|
return false;
|
|
req->io_task_work.func = io_futex_complete;
|
|
} else {
|
|
struct io_futexv_data *ifd = req->async_data;
|
|
|
|
if (!io_futexv_claim(ifd))
|
|
return false;
|
|
req->io_task_work.func = io_futexv_complete;
|
|
}
|
|
|
|
hlist_del_init(&req->hash_node);
|
|
io_req_set_res(req, -ECANCELED, 0);
|
|
io_req_task_work_add(req);
|
|
return true;
|
|
}
|
|
|
|
int io_futex_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
|
|
unsigned int issue_flags)
|
|
{
|
|
return io_cancel_remove(ctx, cd, issue_flags, &ctx->futex_list, __io_futex_cancel);
|
|
}
|
|
|
|
bool io_futex_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
|
|
bool cancel_all)
|
|
{
|
|
return io_cancel_remove_all(ctx, tctx, &ctx->futex_list, cancel_all, __io_futex_cancel);
|
|
}
|
|
|
|
int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
|
|
{
|
|
struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
|
|
u32 flags;
|
|
|
|
if (unlikely(sqe->len || sqe->futex_flags || sqe->buf_index ||
|
|
sqe->file_index))
|
|
return -EINVAL;
|
|
|
|
iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
|
|
iof->futex_val = READ_ONCE(sqe->addr2);
|
|
iof->futex_mask = READ_ONCE(sqe->addr3);
|
|
flags = READ_ONCE(sqe->fd);
|
|
|
|
if (flags & ~FUTEX2_VALID_MASK)
|
|
return -EINVAL;
|
|
|
|
iof->futex_flags = futex2_to_flags(flags);
|
|
if (!futex_flags_valid(iof->futex_flags))
|
|
return -EINVAL;
|
|
|
|
if (!futex_validate_input(iof->futex_flags, iof->futex_val) ||
|
|
!futex_validate_input(iof->futex_flags, iof->futex_mask))
|
|
return -EINVAL;
|
|
|
|
/* Mark as inflight, so file exit cancelation will find it */
|
|
io_req_track_inflight(req);
|
|
return 0;
|
|
}
|
|
|
|
static void io_futex_wakev_fn(struct wake_q_head *wake_q, struct futex_q *q)
|
|
{
|
|
struct io_kiocb *req = q->wake_data;
|
|
struct io_futexv_data *ifd = req->async_data;
|
|
|
|
if (!io_futexv_claim(ifd)) {
|
|
__futex_wake_mark(q);
|
|
return;
|
|
}
|
|
if (unlikely(!__futex_wake_mark(q)))
|
|
return;
|
|
|
|
io_req_set_res(req, 0, 0);
|
|
req->io_task_work.func = io_futexv_complete;
|
|
io_req_task_work_add(req);
|
|
}
|
|
|
|
int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
|
|
{
|
|
struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
|
|
struct io_futexv_data *ifd;
|
|
int ret;
|
|
|
|
/* No flags or mask supported for waitv */
|
|
if (unlikely(sqe->fd || sqe->buf_index || sqe->file_index ||
|
|
sqe->addr2 || sqe->futex_flags || sqe->addr3))
|
|
return -EINVAL;
|
|
|
|
iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
|
|
iof->futex_nr = READ_ONCE(sqe->len);
|
|
if (!iof->futex_nr || iof->futex_nr > FUTEX_WAITV_MAX)
|
|
return -EINVAL;
|
|
|
|
ifd = kzalloc_flex(struct io_futexv_data, futexv, iof->futex_nr,
|
|
GFP_KERNEL_ACCOUNT);
|
|
if (!ifd)
|
|
return -ENOMEM;
|
|
|
|
ret = futex_parse_waitv(ifd->futexv, iof->uaddr, iof->futex_nr,
|
|
io_futex_wakev_fn, req);
|
|
if (ret) {
|
|
kfree(ifd);
|
|
return ret;
|
|
}
|
|
|
|
/* Mark as inflight, so file exit cancelation will find it */
|
|
io_req_track_inflight(req);
|
|
iof->futexv_unqueued = 0;
|
|
req->flags |= REQ_F_ASYNC_DATA;
|
|
req->async_data = ifd;
|
|
return 0;
|
|
}
|
|
|
|
static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q)
|
|
{
|
|
struct io_futex_data *ifd = container_of(q, struct io_futex_data, q);
|
|
struct io_kiocb *req = ifd->req;
|
|
|
|
if (unlikely(!__futex_wake_mark(q)))
|
|
return;
|
|
|
|
io_req_set_res(req, 0, 0);
|
|
req->io_task_work.func = io_futex_complete;
|
|
io_req_task_work_add(req);
|
|
}
|
|
|
|
int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags)
|
|
{
|
|
struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
|
|
struct io_futexv_data *ifd = req->async_data;
|
|
struct io_ring_ctx *ctx = req->ctx;
|
|
int ret, woken = -1;
|
|
|
|
io_ring_submit_lock(ctx, issue_flags);
|
|
|
|
ret = futex_wait_multiple_setup(ifd->futexv, iof->futex_nr, &woken);
|
|
|
|
/*
|
|
* Error case, ret is < 0. Mark the request as failed.
|
|
*/
|
|
if (unlikely(ret < 0)) {
|
|
io_ring_submit_unlock(ctx, issue_flags);
|
|
req_set_fail(req);
|
|
io_req_set_res(req, ret, 0);
|
|
io_req_async_data_free(req);
|
|
return IOU_COMPLETE;
|
|
}
|
|
|
|
/*
|
|
* 0 return means that we successfully setup the waiters, and that
|
|
* nobody triggered a wakeup while we were doing so. If the wakeup
|
|
* happened post setup, the task_work will be run post this issue and
|
|
* under the submission lock. 1 means We got woken while setting up,
|
|
* let that side do the completion. Note that
|
|
* futex_wait_multiple_setup() will have unqueued all the futexes in
|
|
* this case. Mark us as having done that already, since this is
|
|
* different from normal wakeup.
|
|
*/
|
|
if (!ret) {
|
|
/*
|
|
* If futex_wait_multiple_setup() returns 0 for a
|
|
* successful setup, then the task state will not be
|
|
* runnable. This is fine for the sync syscall, as
|
|
* it'll be blocking unless we already got one of the
|
|
* futexes woken, but it obviously won't work for an
|
|
* async invocation. Mark us runnable again.
|
|
*/
|
|
__set_current_state(TASK_RUNNING);
|
|
hlist_add_head(&req->hash_node, &ctx->futex_list);
|
|
} else {
|
|
iof->futexv_unqueued = 1;
|
|
if (woken != -1)
|
|
io_req_set_res(req, woken, 0);
|
|
}
|
|
|
|
io_ring_submit_unlock(ctx, issue_flags);
|
|
return IOU_ISSUE_SKIP_COMPLETE;
|
|
}
|
|
|
|
int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
|
|
{
|
|
struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
|
|
struct io_ring_ctx *ctx = req->ctx;
|
|
struct io_futex_data *ifd = NULL;
|
|
int ret;
|
|
|
|
if (!iof->futex_mask) {
|
|
ret = -EINVAL;
|
|
goto done;
|
|
}
|
|
|
|
io_ring_submit_lock(ctx, issue_flags);
|
|
ifd = io_cache_alloc(&ctx->futex_cache, GFP_NOWAIT);
|
|
if (!ifd) {
|
|
ret = -ENOMEM;
|
|
goto done_unlock;
|
|
}
|
|
|
|
req->flags |= REQ_F_ASYNC_DATA;
|
|
req->async_data = ifd;
|
|
ifd->q = futex_q_init;
|
|
ifd->q.bitset = iof->futex_mask;
|
|
ifd->q.wake = io_futex_wake_fn;
|
|
ifd->req = req;
|
|
|
|
ret = futex_wait_setup(iof->uaddr, iof->futex_val, iof->futex_flags,
|
|
&ifd->q, NULL, NULL);
|
|
if (!ret) {
|
|
hlist_add_head(&req->hash_node, &ctx->futex_list);
|
|
io_ring_submit_unlock(ctx, issue_flags);
|
|
|
|
return IOU_ISSUE_SKIP_COMPLETE;
|
|
}
|
|
|
|
done_unlock:
|
|
io_ring_submit_unlock(ctx, issue_flags);
|
|
done:
|
|
if (ret < 0)
|
|
req_set_fail(req);
|
|
io_req_set_res(req, ret, 0);
|
|
io_req_async_data_free(req);
|
|
return IOU_COMPLETE;
|
|
}
|
|
|
|
int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags)
|
|
{
|
|
struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
|
|
int ret;
|
|
|
|
/*
|
|
* Strict flags - ensure that waking 0 futexes yields a 0 result.
|
|
* See commit 43adf8449510 ("futex: FLAGS_STRICT") for details.
|
|
*/
|
|
ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags, NULL,
|
|
iof->futex_val, iof->futex_mask);
|
|
if (ret < 0)
|
|
req_set_fail(req);
|
|
io_req_set_res(req, ret, 0);
|
|
return IOU_COMPLETE;
|
|
}
|