diff options
Diffstat (limited to 'io_uring')
| -rw-r--r-- | io_uring/io_uring.c | 81 | ||||
| -rw-r--r-- | io_uring/openclose.c | 6 | ||||
| -rw-r--r-- | io_uring/rw.c | 58 |
3 files changed, 89 insertions, 56 deletions
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index e8096d502a7c..93db3e4e7b68 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1948,6 +1948,14 @@ fail: ret = io_issue_sqe(req, issue_flags); if (ret != -EAGAIN) break; + + /* + * If REQ_F_NOWAIT is set, then don't wait or retry with + * poll. -EAGAIN is final for that case. + */ + if (req->flags & REQ_F_NOWAIT) + break; + /* * We can get EAGAIN for iopolled IO even though we're * forcing a sync submission from here, since we can't @@ -2485,10 +2493,21 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) return 0; } +static bool current_pending_io(void) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx) + return false; + return percpu_counter_read_positive(&tctx->inflight); +} + /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { + int io_wait, ret; + if (unlikely(READ_ONCE(ctx->check_cq))) return 1; if (unlikely(!llist_empty(&ctx->work_llist))) @@ -2499,11 +2518,22 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return -EINTR; if (unlikely(io_should_wake(iowq))) return 0; + + /* + * Mark us as being in io_wait if we have pending requests, so cpufreq + * can take into account that the task is waiting for IO - turns out + * to be important for low QD IO. + */ + io_wait = current->in_iowait; + if (current_pending_io()) + current->in_iowait = 1; + ret = 0; if (iowq->timeout == KTIME_MAX) schedule(); else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS)) - return -ETIME; - return 0; + ret = -ETIME; + current->in_iowait = io_wait; + return ret; } /* @@ -3418,8 +3448,6 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); - struct vm_unmapped_area_info info; void *ptr; /* @@ -3434,32 +3462,29 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp, if (IS_ERR(ptr)) return -ENOMEM; - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.low_limit = max(PAGE_SIZE, mmap_min_addr); - info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); + /* + * Some architectures have strong cache aliasing requirements. + * For such architectures we need a coherent mapping which aliases + * kernel memory *and* userspace memory. To achieve that: + * - use a NULL file pointer to reference physical memory, and + * - use the kernel virtual address of the shared io_uring context + * (instead of the userspace-provided address, which has to be 0UL + * anyway). + * - use the same pgoff which the get_unmapped_area() uses to + * calculate the page colouring. + * For architectures without such aliasing requirements, the + * architecture will return any suitable mapping because addr is 0. + */ + filp = NULL; + flags |= MAP_SHARED; + pgoff = 0; /* has been translated to ptr above */ #ifdef SHM_COLOUR - info.align_mask = PAGE_MASK & (SHM_COLOUR - 1UL); + addr = (uintptr_t) ptr; + pgoff = addr >> PAGE_SHIFT; #else - info.align_mask = PAGE_MASK & (SHMLBA - 1UL); + addr = 0UL; #endif - info.align_offset = (unsigned long) ptr; - - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - addr = vm_unmapped_area(&info); - if (offset_in_page(addr)) { - info.flags = 0; - info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = mmap_end; - addr = vm_unmapped_area(&info); - } - - return addr; + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); } #else /* !CONFIG_MMU */ @@ -3859,7 +3884,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, ctx->syscall_iopoll = 1; ctx->compat = in_compat_syscall(); - if (!capable(CAP_IPC_LOCK)) + if (!ns_capable_noaudit(&init_user_ns, CAP_IPC_LOCK)) ctx->user = get_uid(current_user()); /* diff --git a/io_uring/openclose.c b/io_uring/openclose.c index 10ca57f5bd24..e3fae26e025d 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -35,9 +35,11 @@ static bool io_openat_force_async(struct io_open *open) { /* * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, - * it'll always -EAGAIN + * it'll always -EAGAIN. Note that we test for __O_TMPFILE because + * O_TMPFILE includes O_DIRECTORY, which isn't a flag we need to force + * async for. */ - return open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE); + return open->how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE); } static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) diff --git a/io_uring/rw.c b/io_uring/rw.c index 1bce2208b65c..b3435033fadf 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -105,6 +105,7 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) } else { rw->kiocb.ki_ioprio = get_current_ioprio(); } + rw->kiocb.dio_complete = NULL; rw->addr = READ_ONCE(sqe->addr); rw->len = READ_ONCE(sqe->len); @@ -220,17 +221,12 @@ static bool io_rw_should_reissue(struct io_kiocb *req) } #endif -static void kiocb_end_write(struct io_kiocb *req) +static void io_req_end_write(struct io_kiocb *req) { - /* - * Tell lockdep we inherited freeze protection from submission - * thread. - */ if (req->flags & REQ_F_ISREG) { - struct super_block *sb = file_inode(req->file)->i_sb; + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); - __sb_writers_acquired(sb, SB_FREEZE_WRITE); - sb_end_write(sb); + kiocb_end_write(&rw->kiocb); } } @@ -243,7 +239,7 @@ static void io_req_io_end(struct io_kiocb *req) struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); if (rw->kiocb.ki_flags & IOCB_WRITE) { - kiocb_end_write(req); + io_req_end_write(req); fsnotify_modify(req->file); } else { fsnotify_access(req->file); @@ -285,6 +281,15 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res) void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts) { + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); + struct kiocb *kiocb = &rw->kiocb; + + if ((kiocb->ki_flags & IOCB_DIO_CALLER_COMP) && kiocb->dio_complete) { + long res = kiocb->dio_complete(rw->kiocb.private); + + io_req_set_res(req, io_fixup_rw_res(req, res), 0); + } + io_req_io_end(req); if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { @@ -300,9 +305,11 @@ static void io_complete_rw(struct kiocb *kiocb, long res) struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb); struct io_kiocb *req = cmd_to_io_kiocb(rw); - if (__io_complete_rw_common(req, res)) - return; - io_req_set_res(req, io_fixup_rw_res(req, res), 0); + if (!kiocb->dio_complete || !(kiocb->ki_flags & IOCB_DIO_CALLER_COMP)) { + if (__io_complete_rw_common(req, res)) + return; + io_req_set_res(req, io_fixup_rw_res(req, res), 0); + } req->io_task_work.func = io_req_rw_complete; __io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE); } @@ -313,7 +320,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) struct io_kiocb *req = cmd_to_io_kiocb(rw); if (kiocb->ki_flags & IOCB_WRITE) - kiocb_end_write(req); + io_req_end_write(req); if (unlikely(res != req->cqe.res)) { if (res == -EAGAIN && io_rw_should_reissue(req)) { req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; @@ -902,19 +909,18 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) return ret; } + if (req->flags & REQ_F_ISREG) + kiocb_start_write(kiocb); + kiocb->ki_flags |= IOCB_WRITE; + /* - * Open-code file_start_write here to grab freeze protection, - * which will be released by another thread in - * io_complete_rw(). Fool lockdep by telling it the lock got - * released so that it doesn't complain about the held lock when - * we return to userspace. + * For non-polled IO, set IOCB_DIO_CALLER_COMP, stating that our handler + * groks deferring the completion to task context. This isn't + * necessary and useful for polled IO as that can always complete + * directly. */ - if (req->flags & REQ_F_ISREG) { - sb_start_write(file_inode(req->file)->i_sb); - __sb_writers_release(file_inode(req->file)->i_sb, - SB_FREEZE_WRITE); - } - kiocb->ki_flags |= IOCB_WRITE; + if (!(kiocb->ki_flags & IOCB_HIPRI)) + kiocb->ki_flags |= IOCB_DIO_CALLER_COMP; if (likely(req->file->f_op->write_iter)) ret2 = call_write_iter(req->file, kiocb, &s->iter); @@ -961,7 +967,7 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) io->bytes_done += ret2; if (kiocb->ki_flags & IOCB_WRITE) - kiocb_end_write(req); + io_req_end_write(req); return ret ? ret : -EAGAIN; } done: @@ -972,7 +978,7 @@ copy_iov: ret = io_setup_async_rw(req, iovec, s, false); if (!ret) { if (kiocb->ki_flags & IOCB_WRITE) - kiocb_end_write(req); + io_req_end_write(req); return -EAGAIN; } return ret; |