| // SPDX-License-Identifier: GPL-2.0 |
| #include <linux/kernel.h> |
| #include <linux/errno.h> |
| #include <linux/fs.h> |
| #include <linux/file.h> |
| #include <linux/mm.h> |
| #include <linux/slab.h> |
| #include <linux/namei.h> |
| #include <linux/poll.h> |
| #include <linux/io_uring.h> |
| |
| #include <uapi/linux/io_uring.h> |
| |
| #include "io_uring.h" |
| #include "opdef.h" |
| #include "kbuf.h" |
| |
| #define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) |
| |
| #define BGID_ARRAY 64 |
| |
| /* BIDs are addressed by a 16-bit field in a CQE */ |
| #define MAX_BIDS_PER_BGID (1 << 16) |
| |
| struct kmem_cache *io_buf_cachep; |
| |
| struct io_provide_buf { |
| struct file *file; |
| __u64 addr; |
| __u32 len; |
| __u32 bgid; |
| __u32 nbufs; |
| __u16 bid; |
| }; |
| |
| static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, |
| unsigned int bgid) |
| { |
| if (ctx->io_bl && bgid < BGID_ARRAY) |
| return &ctx->io_bl[bgid]; |
| |
| return xa_load(&ctx->io_bl_xa, bgid); |
| } |
| |
| static int io_buffer_add_list(struct io_ring_ctx *ctx, |
| struct io_buffer_list *bl, unsigned int bgid) |
| { |
| bl->bgid = bgid; |
| if (bgid < BGID_ARRAY) |
| return 0; |
| |
| return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); |
| } |
| |
| void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags) |
| { |
| struct io_ring_ctx *ctx = req->ctx; |
| struct io_buffer_list *bl; |
| struct io_buffer *buf; |
| |
| /* |
| * For legacy provided buffer mode, don't recycle if we already did |
| * IO to this buffer. For ring-mapped provided buffer mode, we should |
| * increment ring->head to explicitly monopolize the buffer to avoid |
| * multiple use. |
| */ |
| if (req->flags & REQ_F_PARTIAL_IO) |
| return; |
| |
| io_ring_submit_lock(ctx, issue_flags); |
| |
| buf = req->kbuf; |
| bl = io_buffer_get_list(ctx, buf->bgid); |
| list_add(&buf->list, &bl->buf_list); |
| req->flags &= ~REQ_F_BUFFER_SELECTED; |
| req->buf_index = buf->bgid; |
| |
| io_ring_submit_unlock(ctx, issue_flags); |
| return; |
| } |
| |
| unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags) |
| { |
| unsigned int cflags; |
| |
| /* |
| * We can add this buffer back to two lists: |
| * |
| * 1) The io_buffers_cache list. This one is protected by the |
| * ctx->uring_lock. If we already hold this lock, add back to this |
| * list as we can grab it from issue as well. |
| * 2) The io_buffers_comp list. This one is protected by the |
| * ctx->completion_lock. |
| * |
| * We migrate buffers from the comp_list to the issue cache list |
| * when we need one. |
| */ |
| if (req->flags & REQ_F_BUFFER_RING) { |
| /* no buffers to recycle for this case */ |
| cflags = __io_put_kbuf_list(req, NULL); |
| } else if (issue_flags & IO_URING_F_UNLOCKED) { |
| struct io_ring_ctx *ctx = req->ctx; |
| |
| spin_lock(&ctx->completion_lock); |
| cflags = __io_put_kbuf_list(req, &ctx->io_buffers_comp); |
| spin_unlock(&ctx->completion_lock); |
| } else { |
| lockdep_assert_held(&req->ctx->uring_lock); |
| |
| cflags = __io_put_kbuf_list(req, &req->ctx->io_buffers_cache); |
| } |
| return cflags; |
| } |
| |
| static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len, |
| struct io_buffer_list *bl) |
| { |
| if (!list_empty(&bl->buf_list)) { |
| struct io_buffer *kbuf; |
| |
| kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list); |
| list_del(&kbuf->list); |
| if (*len == 0 || *len > kbuf->len) |
| *len = kbuf->len; |
| req->flags |= REQ_F_BUFFER_SELECTED; |
| req->kbuf = kbuf; |
| req->buf_index = kbuf->bid; |
| return u64_to_user_ptr(kbuf->addr); |
| } |
| return NULL; |
| } |
| |
| static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, |
| struct io_buffer_list *bl, |
| unsigned int issue_flags) |
| { |
| struct io_uring_buf_ring *br = bl->buf_ring; |
| struct io_uring_buf *buf; |
| __u16 head = bl->head; |
| |
| if (unlikely(smp_load_acquire(&br->tail) == head)) |
| return NULL; |
| |
| head &= bl->mask; |
| /* mmaped buffers are always contig */ |
| if (bl->is_mmap || head < IO_BUFFER_LIST_BUF_PER_PAGE) { |
| buf = &br->bufs[head]; |
| } else { |
| int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1); |
| int index = head / IO_BUFFER_LIST_BUF_PER_PAGE; |
| buf = page_address(bl->buf_pages[index]); |
| buf += off; |
| } |
| if (*len == 0 || *len > buf->len) |
| *len = buf->len; |
| req->flags |= REQ_F_BUFFER_RING; |
| req->buf_list = bl; |
| req->buf_index = buf->bid; |
| |
| if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) { |
| /* |
| * If we came in unlocked, we have no choice but to consume the |
| * buffer here, otherwise nothing ensures that the buffer won't |
| * get used by others. This does mean it'll be pinned until the |
| * IO completes, coming in unlocked means we're being called from |
| * io-wq context and there may be further retries in async hybrid |
| * mode. For the locked case, the caller must call commit when |
| * the transfer completes (or if we get -EAGAIN and must poll of |
| * retry). |
| */ |
| req->buf_list = NULL; |
| bl->head++; |
| } |
| return u64_to_user_ptr(buf->addr); |
| } |
| |
| void __user *io_buffer_select(struct io_kiocb *req, size_t *len, |
| unsigned int issue_flags) |
| { |
| struct io_ring_ctx *ctx = req->ctx; |
| struct io_buffer_list *bl; |
| void __user *ret = NULL; |
| |
| io_ring_submit_lock(req->ctx, issue_flags); |
| |
| bl = io_buffer_get_list(ctx, req->buf_index); |
| if (likely(bl)) { |
| if (bl->is_mapped) |
| ret = io_ring_buffer_select(req, len, bl, issue_flags); |
| else |
| ret = io_provided_buffer_select(req, len, bl); |
| } |
| io_ring_submit_unlock(req->ctx, issue_flags); |
| return ret; |
| } |
| |
| static __cold int io_init_bl_list(struct io_ring_ctx *ctx) |
| { |
| int i; |
| |
| ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), |
| GFP_KERNEL); |
| if (!ctx->io_bl) |
| return -ENOMEM; |
| |
| for (i = 0; i < BGID_ARRAY; i++) { |
| INIT_LIST_HEAD(&ctx->io_bl[i].buf_list); |
| ctx->io_bl[i].bgid = i; |
| } |
| |
| return 0; |
| } |
| |
| static int __io_remove_buffers(struct io_ring_ctx *ctx, |
| struct io_buffer_list *bl, unsigned nbufs) |
| { |
| unsigned i = 0; |
| |
| /* shouldn't happen */ |
| if (!nbufs) |
| return 0; |
| |
| if (bl->is_mapped) { |
| i = bl->buf_ring->tail - bl->head; |
| if (bl->is_mmap) { |
| folio_put(virt_to_folio(bl->buf_ring)); |
| bl->buf_ring = NULL; |
| bl->is_mmap = 0; |
| } else if (bl->buf_nr_pages) { |
| int j; |
| |
| for (j = 0; j < bl->buf_nr_pages; j++) |
| unpin_user_page(bl->buf_pages[j]); |
| kvfree(bl->buf_pages); |
| bl->buf_pages = NULL; |
| bl->buf_nr_pages = 0; |
| } |
| /* make sure it's seen as empty */ |
| INIT_LIST_HEAD(&bl->buf_list); |
| bl->is_mapped = 0; |
| return i; |
| } |
| |
| /* protects io_buffers_cache */ |
| lockdep_assert_held(&ctx->uring_lock); |
| |
| while (!list_empty(&bl->buf_list)) { |
| struct io_buffer *nxt; |
| |
| nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); |
| list_move(&nxt->list, &ctx->io_buffers_cache); |
| if (++i == nbufs) |
| return i; |
| cond_resched(); |
| } |
| |
| return i; |
| } |
| |
| void io_destroy_buffers(struct io_ring_ctx *ctx) |
| { |
| struct io_buffer_list *bl; |
| struct list_head *item, *tmp; |
| struct io_buffer *buf; |
| unsigned long index; |
| int i; |
| |
| for (i = 0; i < BGID_ARRAY; i++) { |
| if (!ctx->io_bl) |
| break; |
| __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); |
| } |
| |
| xa_for_each(&ctx->io_bl_xa, index, bl) { |
| xa_erase(&ctx->io_bl_xa, bl->bgid); |
| __io_remove_buffers(ctx, bl, -1U); |
| kfree(bl); |
| } |
| |
| list_for_each_safe(item, tmp, &ctx->io_buffers_cache) { |
| buf = list_entry(item, struct io_buffer, list); |
| kmem_cache_free(io_buf_cachep, buf); |
| } |
| } |
| |
| int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) |
| { |
| struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); |
| u64 tmp; |
| |
| if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off || |
| sqe->splice_fd_in) |
| return -EINVAL; |
| |
| tmp = READ_ONCE(sqe->fd); |
| if (!tmp || tmp > MAX_BIDS_PER_BGID) |
| return -EINVAL; |
| |
| memset(p, 0, sizeof(*p)); |
| p->nbufs = tmp; |
| p->bgid = READ_ONCE(sqe->buf_group); |
| return 0; |
| } |
| |
| int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) |
| { |
| struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); |
| struct io_ring_ctx *ctx = req->ctx; |
| struct io_buffer_list *bl; |
| int ret = 0; |
| |
| io_ring_submit_lock(ctx, issue_flags); |
| |
| ret = -ENOENT; |
| bl = io_buffer_get_list(ctx, p->bgid); |
| if (bl) { |
| ret = -EINVAL; |
| /* can't use provide/remove buffers command on mapped buffers */ |
| if (!bl->is_mapped) |
| ret = __io_remove_buffers(ctx, bl, p->nbufs); |
| } |
| io_ring_submit_unlock(ctx, issue_flags); |
| if (ret < 0) |
| req_set_fail(req); |
| io_req_set_res(req, ret, 0); |
| return IOU_OK; |
| } |
| |
| int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) |
| { |
| unsigned long size, tmp_check; |
| struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); |
| u64 tmp; |
| |
| if (sqe->rw_flags || sqe->splice_fd_in) |
| return -EINVAL; |
| |
| tmp = READ_ONCE(sqe->fd); |
| if (!tmp || tmp > MAX_BIDS_PER_BGID) |
| return -E2BIG; |
| p->nbufs = tmp; |
| p->addr = READ_ONCE(sqe->addr); |
| p->len = READ_ONCE(sqe->len); |
| |
| if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs, |
| &size)) |
| return -EOVERFLOW; |
| if (check_add_overflow((unsigned long)p->addr, size, &tmp_check)) |
| return -EOVERFLOW; |
| |
| size = (unsigned long)p->len * p->nbufs; |
| if (!access_ok(u64_to_user_ptr(p->addr), size)) |
| return -EFAULT; |
| |
| p->bgid = READ_ONCE(sqe->buf_group); |
| tmp = READ_ONCE(sqe->off); |
| if (tmp > USHRT_MAX) |
| return -E2BIG; |
| if (tmp + p->nbufs > MAX_BIDS_PER_BGID) |
| return -EINVAL; |
| p->bid = tmp; |
| return 0; |
| } |
| |
| #define IO_BUFFER_ALLOC_BATCH 64 |
| |
| static int io_refill_buffer_cache(struct io_ring_ctx *ctx) |
| { |
| struct io_buffer *bufs[IO_BUFFER_ALLOC_BATCH]; |
| int allocated; |
| |
| /* |
| * Completions that don't happen inline (eg not under uring_lock) will |
| * add to ->io_buffers_comp. If we don't have any free buffers, check |
| * the completion list and splice those entries first. |
| */ |
| if (!list_empty_careful(&ctx->io_buffers_comp)) { |
| spin_lock(&ctx->completion_lock); |
| if (!list_empty(&ctx->io_buffers_comp)) { |
| list_splice_init(&ctx->io_buffers_comp, |
| &ctx->io_buffers_cache); |
| spin_unlock(&ctx->completion_lock); |
| return 0; |
| } |
| spin_unlock(&ctx->completion_lock); |
| } |
| |
| /* |
| * No free buffers and no completion entries either. Allocate a new |
| * batch of buffer entries and add those to our freelist. |
| */ |
| |
| allocated = kmem_cache_alloc_bulk(io_buf_cachep, GFP_KERNEL_ACCOUNT, |
| ARRAY_SIZE(bufs), (void **) bufs); |
| if (unlikely(!allocated)) { |
| /* |
| * Bulk alloc is all-or-nothing. If we fail to get a batch, |
| * retry single alloc to be on the safe side. |
| */ |
| bufs[0] = kmem_cache_alloc(io_buf_cachep, GFP_KERNEL); |
| if (!bufs[0]) |
| return -ENOMEM; |
| allocated = 1; |
| } |
| |
| while (allocated) |
| list_add_tail(&bufs[--allocated]->list, &ctx->io_buffers_cache); |
| |
| return 0; |
| } |
| |
| static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf, |
| struct io_buffer_list *bl) |
| { |
| struct io_buffer *buf; |
| u64 addr = pbuf->addr; |
| int i, bid = pbuf->bid; |
| |
| for (i = 0; i < pbuf->nbufs; i++) { |
| if (list_empty(&ctx->io_buffers_cache) && |
| io_refill_buffer_cache(ctx)) |
| break; |
| buf = list_first_entry(&ctx->io_buffers_cache, struct io_buffer, |
| list); |
| list_move_tail(&buf->list, &bl->buf_list); |
| buf->addr = addr; |
| buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT); |
| buf->bid = bid; |
| buf->bgid = pbuf->bgid; |
| addr += pbuf->len; |
| bid++; |
| cond_resched(); |
| } |
| |
| return i ? 0 : -ENOMEM; |
| } |
| |
| int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) |
| { |
| struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); |
| struct io_ring_ctx *ctx = req->ctx; |
| struct io_buffer_list *bl; |
| int ret = 0; |
| |
| io_ring_submit_lock(ctx, issue_flags); |
| |
| if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { |
| ret = io_init_bl_list(ctx); |
| if (ret) |
| goto err; |
| } |
| |
| bl = io_buffer_get_list(ctx, p->bgid); |
| if (unlikely(!bl)) { |
| bl = kzalloc(sizeof(*bl), GFP_KERNEL_ACCOUNT); |
| if (!bl) { |
| ret = -ENOMEM; |
| goto err; |
| } |
| INIT_LIST_HEAD(&bl->buf_list); |
| ret = io_buffer_add_list(ctx, bl, p->bgid); |
| if (ret) { |
| kfree(bl); |
| goto err; |
| } |
| } |
| /* can't add buffers via this command for a mapped buffer ring */ |
| if (bl->is_mapped) { |
| ret = -EINVAL; |
| goto err; |
| } |
| |
| ret = io_add_buffers(ctx, p, bl); |
| err: |
| io_ring_submit_unlock(ctx, issue_flags); |
| |
| if (ret < 0) |
| req_set_fail(req); |
| io_req_set_res(req, ret, 0); |
| return IOU_OK; |
| } |
| |
| static int io_pin_pbuf_ring(struct io_uring_buf_reg *reg, |
| struct io_buffer_list *bl) |
| { |
| struct io_uring_buf_ring *br; |
| struct page **pages; |
| int i, nr_pages; |
| |
| pages = io_pin_pages(reg->ring_addr, |
| flex_array_size(br, bufs, reg->ring_entries), |
| &nr_pages); |
| if (IS_ERR(pages)) |
| return PTR_ERR(pages); |
| |
| /* |
| * Apparently some 32-bit boxes (ARM) will return highmem pages, |
| * which then need to be mapped. We could support that, but it'd |
| * complicate the code and slowdown the common cases quite a bit. |
| * So just error out, returning -EINVAL just like we did on kernels |
| * that didn't support mapped buffer rings. |
| */ |
| for (i = 0; i < nr_pages; i++) |
| if (PageHighMem(pages[i])) |
| goto error_unpin; |
| |
| br = page_address(pages[0]); |
| #ifdef SHM_COLOUR |
| /* |
| * On platforms that have specific aliasing requirements, SHM_COLOUR |
| * is set and we must guarantee that the kernel and user side align |
| * nicely. We cannot do that if IOU_PBUF_RING_MMAP isn't set and |
| * the application mmap's the provided ring buffer. Fail the request |
| * if we, by chance, don't end up with aligned addresses. The app |
| * should use IOU_PBUF_RING_MMAP instead, and liburing will handle |
| * this transparently. |
| */ |
| if ((reg->ring_addr | (unsigned long) br) & (SHM_COLOUR - 1)) |
| goto error_unpin; |
| #endif |
| bl->buf_pages = pages; |
| bl->buf_nr_pages = nr_pages; |
| bl->buf_ring = br; |
| bl->is_mapped = 1; |
| bl->is_mmap = 0; |
| return 0; |
| error_unpin: |
| for (i = 0; i < nr_pages; i++) |
| unpin_user_page(pages[i]); |
| kvfree(pages); |
| return -EINVAL; |
| } |
| |
| static int io_alloc_pbuf_ring(struct io_uring_buf_reg *reg, |
| struct io_buffer_list *bl) |
| { |
| gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; |
| size_t ring_size; |
| void *ptr; |
| |
| ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring); |
| ptr = (void *) __get_free_pages(gfp, get_order(ring_size)); |
| if (!ptr) |
| return -ENOMEM; |
| |
| bl->buf_ring = ptr; |
| bl->is_mapped = 1; |
| bl->is_mmap = 1; |
| return 0; |
| } |
| |
| int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) |
| { |
| struct io_uring_buf_reg reg; |
| struct io_buffer_list *bl, *free_bl = NULL; |
| int ret; |
| |
| if (copy_from_user(®, arg, sizeof(reg))) |
| return -EFAULT; |
| |
| if (reg.resv[0] || reg.resv[1] || reg.resv[2]) |
| return -EINVAL; |
| if (reg.flags & ~IOU_PBUF_RING_MMAP) |
| return -EINVAL; |
| if (!(reg.flags & IOU_PBUF_RING_MMAP)) { |
| if (!reg.ring_addr) |
| return -EFAULT; |
| if (reg.ring_addr & ~PAGE_MASK) |
| return -EINVAL; |
| } else { |
| if (reg.ring_addr) |
| return -EINVAL; |
| } |
| |
| if (!is_power_of_2(reg.ring_entries)) |
| return -EINVAL; |
| |
| /* cannot disambiguate full vs empty due to head/tail size */ |
| if (reg.ring_entries >= 65536) |
| return -EINVAL; |
| |
| if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { |
| int ret = io_init_bl_list(ctx); |
| if (ret) |
| return ret; |
| } |
| |
| bl = io_buffer_get_list(ctx, reg.bgid); |
| if (bl) { |
| /* if mapped buffer ring OR classic exists, don't allow */ |
| if (bl->is_mapped || !list_empty(&bl->buf_list)) |
| return -EEXIST; |
| } else { |
| free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL); |
| if (!bl) |
| return -ENOMEM; |
| } |
| |
| if (!(reg.flags & IOU_PBUF_RING_MMAP)) |
| ret = io_pin_pbuf_ring(®, bl); |
| else |
| ret = io_alloc_pbuf_ring(®, bl); |
| |
| if (!ret) { |
| bl->nr_entries = reg.ring_entries; |
| bl->mask = reg.ring_entries - 1; |
| |
| io_buffer_add_list(ctx, bl, reg.bgid); |
| return 0; |
| } |
| |
| kfree(free_bl); |
| return ret; |
| } |
| |
| int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) |
| { |
| struct io_uring_buf_reg reg; |
| struct io_buffer_list *bl; |
| |
| if (copy_from_user(®, arg, sizeof(reg))) |
| return -EFAULT; |
| if (reg.resv[0] || reg.resv[1] || reg.resv[2]) |
| return -EINVAL; |
| if (reg.flags) |
| return -EINVAL; |
| |
| bl = io_buffer_get_list(ctx, reg.bgid); |
| if (!bl) |
| return -ENOENT; |
| if (!bl->is_mapped) |
| return -EINVAL; |
| |
| __io_remove_buffers(ctx, bl, -1U); |
| if (bl->bgid >= BGID_ARRAY) { |
| xa_erase(&ctx->io_bl_xa, bl->bgid); |
| kfree(bl); |
| } |
| return 0; |
| } |
| |
| void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid) |
| { |
| struct io_buffer_list *bl; |
| |
| bl = io_buffer_get_list(ctx, bgid); |
| if (!bl || !bl->is_mmap) |
| return NULL; |
| |
| return bl->buf_ring; |
| } |