From: Jens Axboe axboe@kernel.dk
mainline inclusion from mainline-5.1-rc1 commit edafccee56ff31678a091ddb7219aba9b28bc3cb category: feature bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=27 CVE: NA ---------------------------
If we have fixed user buffers, we can map them into the kernel when we setup the io_uring. That avoids the need to do get_user_pages() for each and every IO.
To utilize this feature, the application must call io_uring_register() after having setup an io_uring instance, passing in IORING_REGISTER_BUFFERS as the opcode. The argument must be a pointer to an iovec array, and the nr_args should contain how many iovecs the application wishes to map.
If successful, these buffers are now mapped into the kernel, eligible for IO. To use these fixed buffers, the application must use the IORING_OP_READ_FIXED and IORING_OP_WRITE_FIXED opcodes, and then set sqe->index to the desired buffer index. sqe->addr..sqe->addr+seq->len must point to somewhere inside the indexed buffer.
The application may register buffers throughout the lifetime of the io_uring instance. It can call io_uring_register() with IORING_UNREGISTER_BUFFERS as the opcode to unregister the current set of buffers, and then register a new set. The application need not unregister buffers explicitly before shutting down the io_uring instance.
It's perfectly valid to setup a larger buffer, and then sometimes only use parts of it for an IO. As long as the range is within the originally mapped region, it will work just fine.
For now, buffers must not be file backed. If file backed buffers are passed in, the registration will fail with -1/EOPNOTSUPP. This restriction may be relaxed in the future.
RLIMIT_MEMLOCK is used to check how much memory we can pin. A somewhat arbitrary 1G per buffer size is also imposed.
Reviewed-by: Hannes Reinecke hare@suse.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Zhihao Cheng chengzhihao1@huawei.com [add ITER_BVEC for iov_iter_bvec in 4.19] Signed-off-by: yangerkun yangerkun@huawei.com Reviewed-by: zhangyi (F) yi.zhang@huawei.com Signed-off-by: Cheng Jian cj.chengjian@huawei.com --- arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + fs/io_uring.c | 374 ++++++++++++++++++++++++- include/linux/syscalls.h | 2 + include/uapi/asm-generic/unistd.h | 4 +- include/uapi/linux/io_uring.h | 13 +- kernel/sys_ni.c | 1 + 7 files changed, 381 insertions(+), 15 deletions(-)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 481c126259e9..2eefd2a7c1ce 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -400,3 +400,4 @@ 386 i386 rseq sys_rseq __ia32_sys_rseq 425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup 426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter +427 i386 io_uring_register sys_io_uring_register __ia32_sys_io_uring_register diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 6a32a430c8e0..65c026185e61 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,7 @@ 334 common rseq __x64_sys_rseq 425 common io_uring_setup __x64_sys_io_uring_setup 426 common io_uring_enter __x64_sys_io_uring_enter +427 common io_uring_register __x64_sys_io_uring_register
# # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/fs/io_uring.c b/fs/io_uring.c index 31f43ed894ba..762df0beb199 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -45,6 +45,7 @@ #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/blkdev.h> +#include <linux/bvec.h> #include <linux/net.h> #include <net/sock.h> #include <net/af_unix.h> @@ -52,6 +53,8 @@ #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <linux/nospec.h> +#include <linux/sizes.h> +#include <linux/hugetlb.h>
#include <uapi/linux/io_uring.h>
@@ -81,6 +84,13 @@ struct io_cq_ring { struct io_uring_cqe cqes[]; };
+struct io_mapped_ubuf { + u64 ubuf; + size_t len; + struct bio_vec *bvec; + unsigned int nr_bvecs; +}; + struct io_ring_ctx { struct { struct percpu_ref refs; @@ -113,6 +123,10 @@ struct io_ring_ctx { struct fasync_struct *cq_fasync; } ____cacheline_aligned_in_smp;
+ /* if used, fixed mapped user buffers */ + unsigned nr_user_bufs; + struct io_mapped_ubuf *user_bufs; + struct user_struct *user;
struct completion ctx_done; @@ -732,6 +746,46 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } }
+static int io_import_fixed(struct io_ring_ctx *ctx, int rw, + const struct io_uring_sqe *sqe, + struct iov_iter *iter) +{ + size_t len = READ_ONCE(sqe->len); + struct io_mapped_ubuf *imu; + unsigned index, buf_index; + size_t offset; + u64 buf_addr; + + /* attempt to use fixed buffers without having provided iovecs */ + if (unlikely(!ctx->user_bufs)) + return -EFAULT; + + buf_index = READ_ONCE(sqe->buf_index); + if (unlikely(buf_index >= ctx->nr_user_bufs)) + return -EFAULT; + + index = array_index_nospec(buf_index, ctx->nr_user_bufs); + imu = &ctx->user_bufs[index]; + buf_addr = READ_ONCE(sqe->addr); + + /* overflow */ + if (buf_addr + len < buf_addr) + return -EFAULT; + /* not inside the mapped region */ + if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len) + return -EFAULT; + + /* + * May not be a start of buffer, set size appropriately + * and advance us to the beginning. + */ + offset = buf_addr - imu->ubuf; + iov_iter_bvec(iter, ITER_BVEC | rw, imu->bvec, imu->nr_bvecs, offset + len); + if (offset) + iov_iter_advance(iter, offset); + return 0; +} + static int io_import_iovec(struct io_ring_ctx *ctx, int rw, const struct sqe_submit *s, struct iovec **iovec, struct iov_iter *iter) @@ -739,6 +793,23 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw, const struct io_uring_sqe *sqe = s->sqe; void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); size_t sqe_len = READ_ONCE(sqe->len); + u8 opcode; + + /* + * We're reading ->opcode for the second time, but the first read + * doesn't care whether it's _FIXED or not, so it doesn't matter + * whether ->opcode changes concurrently. The first read does care + * about whether it is a READ or a WRITE, so we don't trust this read + * for that purpose and instead let the caller pass in the read/write + * flag. + */ + opcode = READ_ONCE(sqe->opcode); + if (opcode == IORING_OP_READ_FIXED || + opcode == IORING_OP_WRITE_FIXED) { + ssize_t ret = io_import_fixed(ctx, rw, sqe, iter); + *iovec = NULL; + return ret; + }
if (!s->has_user) return -EFAULT; @@ -886,7 +957,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (unlikely(sqe->addr || sqe->ioprio)) + if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL;
fd = READ_ONCE(sqe->fd); @@ -945,9 +1016,19 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, ret = io_nop(req, req->user_data); break; case IORING_OP_READV: + if (unlikely(s->sqe->buf_index)) + return -EINVAL; ret = io_read(req, s, force_nonblock, state); break; case IORING_OP_WRITEV: + if (unlikely(s->sqe->buf_index)) + return -EINVAL; + ret = io_write(req, s, force_nonblock, state); + break; + case IORING_OP_READ_FIXED: + ret = io_read(req, s, force_nonblock, state); + break; + case IORING_OP_WRITE_FIXED: ret = io_write(req, s, force_nonblock, state); break; case IORING_OP_FSYNC: @@ -976,28 +1057,46 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; }
+static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) +{ + u8 opcode = READ_ONCE(sqe->opcode); + + return !(opcode == IORING_OP_READ_FIXED || + opcode == IORING_OP_WRITE_FIXED); +} + static void io_sq_wq_submit_work(struct work_struct *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; struct io_ring_ctx *ctx = req->ctx; - mm_segment_t old_fs = get_fs(); + mm_segment_t old_fs; + bool needs_user; int ret;
/* Ensure we clear previously set forced non-block flag */ req->flags &= ~REQ_F_FORCE_NONBLOCK; req->rw.ki_flags &= ~IOCB_NOWAIT;
- if (!mmget_not_zero(ctx->sqo_mm)) { - ret = -EFAULT; - goto err; - } - - use_mm(ctx->sqo_mm); - set_fs(USER_DS); - s->has_user = true; s->needs_lock = true; + s->has_user = false; + + /* + * If we're doing IO to fixed buffers, we don't need to get/set + * user context + */ + needs_user = io_sqe_needs_user(s->sqe); + if (needs_user) { + if (!mmget_not_zero(ctx->sqo_mm)) { + ret = -EFAULT; + goto err; + } + use_mm(ctx->sqo_mm); + old_fs = get_fs(); + set_fs(USER_DS); + s->has_user = true; + }
do { ret = __io_submit_sqe(ctx, req, s, false, NULL); @@ -1011,9 +1110,11 @@ static void io_sq_wq_submit_work(struct work_struct *work) cond_resched(); } while (1);
- set_fs(old_fs); - unuse_mm(ctx->sqo_mm); - mmput(ctx->sqo_mm); + if (needs_user) { + set_fs(old_fs); + unuse_mm(ctx->sqo_mm); + mmput(ctx->sqo_mm); + } err: if (ret) { io_cqring_add_event(ctx, sqe->user_data, ret, 0); @@ -1317,6 +1418,198 @@ static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries) return (bytes + PAGE_SIZE - 1) / PAGE_SIZE; }
+static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) +{ + int i, j; + + if (!ctx->user_bufs) + return -ENXIO; + + for (i = 0; i < ctx->nr_user_bufs; i++) { + struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; + + for (j = 0; j < imu->nr_bvecs; j++) + put_page(imu->bvec[j].bv_page); + + if (ctx->account_mem) + io_unaccount_mem(ctx->user, imu->nr_bvecs); + kfree(imu->bvec); + imu->nr_bvecs = 0; + } + + kfree(ctx->user_bufs); + ctx->user_bufs = NULL; + ctx->nr_user_bufs = 0; + return 0; +} + +static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, + void __user *arg, unsigned index) +{ + struct iovec __user *src; + +#ifdef CONFIG_COMPAT + if (ctx->compat) { + struct compat_iovec __user *ciovs; + struct compat_iovec ciov; + + ciovs = (struct compat_iovec __user *) arg; + if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) + return -EFAULT; + + dst->iov_base = (void __user *) (unsigned long) ciov.iov_base; + dst->iov_len = ciov.iov_len; + return 0; + } +#endif + src = (struct iovec __user *) arg; + if (copy_from_user(dst, &src[index], sizeof(*dst))) + return -EFAULT; + return 0; +} + +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct vm_area_struct **vmas = NULL; + struct page **pages = NULL; + int i, j, got_pages = 0; + int ret = -EINVAL; + + if (ctx->user_bufs) + return -EBUSY; + if (!nr_args || nr_args > UIO_MAXIOV) + return -EINVAL; + + ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf), + GFP_KERNEL); + if (!ctx->user_bufs) + return -ENOMEM; + + for (i = 0; i < nr_args; i++) { + struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; + unsigned long off, start, end, ubuf; + int pret, nr_pages; + struct iovec iov; + size_t size; + + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; + + /* + * Don't impose further limits on the size and buffer + * constraints here, we'll -EINVAL later when IO is + * submitted if they are wrong. + */ + ret = -EFAULT; + if (!iov.iov_base || !iov.iov_len) + goto err; + + /* arbitrary limit, but we need something */ + if (iov.iov_len > SZ_1G) + goto err; + + ubuf = (unsigned long) iov.iov_base; + end = (ubuf + iov.iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = ubuf >> PAGE_SHIFT; + nr_pages = end - start; + + if (ctx->account_mem) { + ret = io_account_mem(ctx->user, nr_pages); + if (ret) + goto err; + } + + ret = 0; + if (!pages || nr_pages > got_pages) { + kfree(vmas); + kfree(pages); + pages = kmalloc_array(nr_pages, sizeof(struct page *), + GFP_KERNEL); + vmas = kmalloc_array(nr_pages, + sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!pages || !vmas) { + ret = -ENOMEM; + if (ctx->account_mem) + io_unaccount_mem(ctx->user, nr_pages); + goto err; + } + got_pages = nr_pages; + } + + imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec), + GFP_KERNEL); + ret = -ENOMEM; + if (!imu->bvec) { + if (ctx->account_mem) + io_unaccount_mem(ctx->user, nr_pages); + goto err; + } + + ret = 0; + down_read(¤t->mm->mmap_sem); + pret = get_user_pages_longterm(ubuf, nr_pages, FOLL_WRITE, + pages, vmas); + if (pret == nr_pages) { + /* don't support file backed memory */ + for (j = 0; j < nr_pages; j++) { + struct vm_area_struct *vma = vmas[j]; + + if (vma->vm_file && + !is_file_hugepages(vma->vm_file)) { + ret = -EOPNOTSUPP; + break; + } + } + } else { + ret = pret < 0 ? pret : -EFAULT; + } + up_read(¤t->mm->mmap_sem); + if (ret) { + /* + * if we did partial map, or found file backed vmas, + * release any pages we did get + */ + if (pret > 0) { + for (j = 0; j < pret; j++) + put_page(pages[j]); + } + if (ctx->account_mem) + io_unaccount_mem(ctx->user, nr_pages); + goto err; + } + + off = ubuf & ~PAGE_MASK; + size = iov.iov_len; + for (j = 0; j < nr_pages; j++) { + size_t vec_len; + + vec_len = min_t(size_t, size, PAGE_SIZE - off); + imu->bvec[j].bv_page = pages[j]; + imu->bvec[j].bv_len = vec_len; + imu->bvec[j].bv_offset = off; + off = 0; + size -= vec_len; + } + /* store original address for later verification */ + imu->ubuf = ubuf; + imu->len = iov.iov_len; + imu->nr_bvecs = nr_pages; + + ctx->nr_user_bufs++; + } + kfree(pages); + kfree(vmas); + return 0; +err: + kfree(pages); + kfree(vmas); + io_sqe_buffer_unregister(ctx); + return ret; +} + static void io_ring_ctx_free(struct io_ring_ctx *ctx) { if (ctx->sqo_wq) @@ -1325,6 +1618,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) mmdrop(ctx->sqo_mm);
io_iopoll_reap_events(ctx); + io_sqe_buffer_unregister(ctx);
#if defined(CONFIG_UNIX) if (ctx->ring_sock) @@ -1689,6 +1983,60 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, return io_uring_setup(entries, params); }
+static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, + void __user *arg, unsigned nr_args) +{ + int ret; + + percpu_ref_kill(&ctx->refs); + wait_for_completion(&ctx->ctx_done); + + switch (opcode) { + case IORING_REGISTER_BUFFERS: + ret = io_sqe_buffer_register(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_BUFFERS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_sqe_buffer_unregister(ctx); + break; + default: + ret = -EINVAL; + break; + } + + /* bring the ctx back to life */ + reinit_completion(&ctx->ctx_done); + percpu_ref_reinit(&ctx->refs); + return ret; +} + +SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, + void __user *, arg, unsigned int, nr_args) +{ + struct io_ring_ctx *ctx; + long ret = -EBADF; + struct fd f; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = -EOPNOTSUPP; + if (f.file->f_op != &io_uring_fops) + goto out_fput; + + ctx = f.file->private_data; + + mutex_lock(&ctx->uring_lock); + ret = __io_uring_register(ctx, opcode, arg, nr_args); + mutex_unlock(&ctx->uring_lock); +out_fput: + fdput(f); + return ret; +} + static int __init io_uring_init(void) { req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d3f921b040ee..82660e1ceaca 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -315,6 +315,8 @@ asmlinkage long sys_io_uring_setup(u32 entries, asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, u32 min_complete, u32 flags, const sigset_t __user *sig, size_t sigsz); +asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op, + void __user *arg, unsigned int nr_args);
/* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 5bb61bc98200..4c1ba6d0dac8 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -744,9 +744,11 @@ __SYSCALL(__NR_rseq, sys_rseq) __SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) #define __NR_io_uring_enter 426 __SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) +#define __NR_io_uring_register 427 +__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
#undef __NR_syscalls -#define __NR_syscalls 427 +#define __NR_syscalls 428
/* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 5c457ea396e6..cf28f7a11f12 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -27,7 +27,10 @@ struct io_uring_sqe { __u32 fsync_flags; }; __u64 user_data; /* data to be passed back at completion time */ - __u64 __pad2[3]; + union { + __u16 buf_index; /* index into fixed buffers, if used */ + __u64 __pad2[3]; + }; };
/* @@ -39,6 +42,8 @@ struct io_uring_sqe { #define IORING_OP_READV 1 #define IORING_OP_WRITEV 2 #define IORING_OP_FSYNC 3 +#define IORING_OP_READ_FIXED 4 +#define IORING_OP_WRITE_FIXED 5
/* * sqe->fsync_flags @@ -103,4 +108,10 @@ struct io_uring_params { struct io_cqring_offsets cq_off; };
+/* + * io_uring_register(2) opcodes and arguments + */ +#define IORING_REGISTER_BUFFERS 0 +#define IORING_UNREGISTER_BUFFERS 1 + #endif diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 5cc38830e6cc..8cfc5dd43bf0 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -48,6 +48,7 @@ COND_SYSCALL_COMPAT(io_getevents); COND_SYSCALL_COMPAT(io_pgetevents); COND_SYSCALL(io_uring_setup); COND_SYSCALL(io_uring_enter); +COND_SYSCALL(io_uring_register);
/* fs/xattr.c */