// 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/uio.h>#include <linux/vmalloc.h>#include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h"#include "opdef.h"#include "kbuf.h"#include "memmap.h" /* BIDs are addressed by a 16-bit field in a CQE */#define MAX_BIDS_PER_BGID (1 << 16) /* Mapped buffer ring, return io_uring_buf from head */#define io_ring_head_to_buf(br, head, mask) (&(br)->bufs[(head) & (mask)]) struct io_provide_buf { struct file *file; __u64 addr; __u32 len; __u32 bgid; __u32 nbufs; __u16 bid;}; static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len){ /* No data consumed, return false early to avoid consuming the buffer */ if (!len) return false; while (len) { struct io_uring_buf *buf; u32 buf_len, this_len; buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask); buf_len = READ_ONCE(buf->len); this_len = min_t(u32, len, buf_len); buf_len -= this_len; /* Stop looping for invalid buffer length of 0 */ if (buf_len > bl->min_left_sub_one || !this_len) { WRITE_ONCE(buf->addr, READ_ONCE(buf->addr) + this_len); WRITE_ONCE(buf->len, buf_len); return false; } WRITE_ONCE(buf->len, 0); bl->head++; len -= this_len; } return true;} bool io_kbuf_commit(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr){ if (unlikely(!(req->flags & REQ_F_BUFFERS_COMMIT))) return true; req->flags &= ~REQ_F_BUFFERS_COMMIT; if (unlikely(len < 0)) return true; if (bl->flags & IOBL_INC) return io_kbuf_inc_commit(bl, len); bl->head += nr; return true;} static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, unsigned int bgid){ lockdep_assert_held(&ctx->uring_lock); 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){ /* * Store buffer group ID and finally mark the list as visible. * The normal lookup doesn't care about the visibility as we're * always under the ->uring_lock, but lookups from mmap do. */ bl->bgid = bgid; guard(mutex)(&ctx->mmap_lock); return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));} void io_kbuf_drop_legacy(struct io_kiocb *req){ if (WARN_ON_ONCE(!(req->flags & REQ_F_BUFFER_SELECTED))) return; req->flags &= ~REQ_F_BUFFER_SELECTED; kfree(req->kbuf); req->kbuf = NULL;} bool 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; io_ring_submit_lock(ctx, issue_flags); buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); /* * If the buffer list was upgraded to a ring-based one, or removed, * while the request was in-flight in io-wq, drop it. */ if (bl && !(bl->flags & IOBL_BUF_RING)) { list_add(&buf->list, &bl->buf_list); bl->nbufs++; } else { kfree(buf); } req->flags &= ~REQ_F_BUFFER_SELECTED; req->kbuf = NULL; io_ring_submit_unlock(ctx, issue_flags); return true;} 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); bl->nbufs--; if (*len == 0 || *len > kbuf->len) *len = kbuf->len; if (list_empty(&bl->buf_list)) req->flags |= REQ_F_BL_EMPTY; req->flags |= REQ_F_BUFFER_SELECTED; req->kbuf = kbuf; req->buf_index = kbuf->bid; return u64_to_user_ptr(kbuf->addr); } return NULL;} static int io_provided_buffers_select(struct io_kiocb *req, size_t *len, struct io_buffer_list *bl, struct iovec *iov){ void __user *buf; buf = io_provided_buffer_select(req, len, bl); if (unlikely(!buf)) return -ENOBUFS; iov[0].iov_base = buf; iov[0].iov_len = *len; return 1;} static bool io_should_commit(struct io_kiocb *req, unsigned int issue_flags){ /* * 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). */ if (issue_flags & IO_URING_F_UNLOCKED) return true; /* uring_cmd commits kbuf upfront, no need to auto-commit */ if (!io_file_can_poll(req) && !io_is_uring_cmd(req)) return true; return false;} static struct io_br_sel 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; __u16 tail, head = bl->head; struct io_br_sel sel = { }; struct io_uring_buf *buf; u32 buf_len; tail = smp_load_acquire(&br->tail); if (unlikely(tail == head)) return sel; if (head + 1 == tail) req->flags |= REQ_F_BL_EMPTY; buf = io_ring_head_to_buf(br, head, bl->mask); buf_len = READ_ONCE(buf->len); if (*len == 0 || *len > buf_len) *len = buf_len; sel.addr = u64_to_user_ptr(READ_ONCE(buf->addr)); if (unlikely(!access_ok(sel.addr, *len))) { sel.addr = NULL; return sel; } req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; req->buf_index = READ_ONCE(buf->bid); sel.buf_list = bl; if (io_should_commit(req, issue_flags)) { if (!io_kbuf_commit(req, sel.buf_list, *len, 1)) req->flags |= REQ_F_BUF_MORE; sel.buf_list = NULL; } return sel;} struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len, unsigned buf_group, unsigned int issue_flags){ struct io_ring_ctx *ctx = req->ctx; struct io_br_sel sel = { }; struct io_buffer_list *bl; io_ring_submit_lock(ctx, issue_flags); bl = io_buffer_get_list(ctx, buf_group); if (likely(bl)) { if (bl->flags & IOBL_BUF_RING) sel = io_ring_buffer_select(req, len, bl, issue_flags); else sel.addr = io_provided_buffer_select(req, len, bl); } io_ring_submit_unlock(ctx, issue_flags); return sel;} /* cap it at a reasonable 256, will be one page even for 4K */#define PEEK_MAX_IMPORT 256 static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_buffer_list *bl){ struct io_uring_buf_ring *br = bl->buf_ring; struct iovec *org_iovs = arg->iovs; struct iovec *iov = arg->iovs; int nr_iovs = arg->nr_iovs; __u16 nr_avail, tail, head; struct io_uring_buf *buf; tail = smp_load_acquire(&br->tail); head = bl->head; nr_avail = min_t(__u16, tail - head, UIO_MAXIOV); if (unlikely(!nr_avail)) return -ENOBUFS; /* MAX_RW_COUNT is the universal Linux per-call IO maximum */ arg->max_len = min_t(size_t, arg->max_len, MAX_RW_COUNT); buf = io_ring_head_to_buf(br, head, bl->mask); if (arg->max_len) { u32 len = READ_ONCE(buf->len); size_t needed; if (unlikely(!len)) return -ENOBUFS; needed = (arg->max_len + len - 1) / len; needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT); if (nr_avail > needed) nr_avail = needed; } /* * only alloc a bigger array if we know we have data to map, eg not * a speculative peek operation. */ if (arg->mode & KBUF_MODE_EXPAND && nr_avail > nr_iovs && arg->max_len) { iov = kmalloc_objs(struct iovec, nr_avail); if (unlikely(!iov)) return -ENOMEM; arg->iovs = iov; nr_iovs = nr_avail; } else if (nr_avail < nr_iovs) { nr_iovs = nr_avail; } /* set it to max, if not set, so we can use it unconditionally */ if (!arg->max_len) arg->max_len = MAX_RW_COUNT; req->buf_index = READ_ONCE(buf->bid); do { u32 len = READ_ONCE(buf->len); /* truncate end piece, if needed, for non partial buffers */ if (len > arg->max_len) { len = arg->max_len; if (!(bl->flags & IOBL_INC)) { arg->partial_map = 1; if (iov != arg->iovs) break; } } iov->iov_base = u64_to_user_ptr(READ_ONCE(buf->addr)); iov->iov_len = len; if (unlikely(!access_ok(iov->iov_base, len))) { if (arg->iovs != org_iovs) kfree(arg->iovs); return -EFAULT; } iov++; arg->out_len += len; arg->max_len -= len; if (!arg->max_len) break; buf = io_ring_head_to_buf(br, ++head, bl->mask); } while (--nr_iovs); if (arg->iovs != org_iovs && (arg->mode & KBUF_MODE_FREE)) kfree(org_iovs); if (head == tail) req->flags |= REQ_F_BL_EMPTY; req->flags |= REQ_F_BUFFER_RING; return iov - arg->iovs;} int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel, unsigned int issue_flags){ struct io_ring_ctx *ctx = req->ctx; int ret = -ENOENT; io_ring_submit_lock(ctx, issue_flags); sel->buf_list = io_buffer_get_list(ctx, arg->buf_group); if (unlikely(!sel->buf_list)) goto out_unlock; if (sel->buf_list->flags & IOBL_BUF_RING) { ret = io_ring_buffers_peek(req, arg, sel->buf_list); /* * Don't recycle these buffers if we need to go through poll. * Nobody else can use them anyway, and holding on to provided * buffers for a send/write operation would happen on the app * side anyway with normal buffers. Besides, we already * committed them, they cannot be put back in the queue. */ if (ret > 0) { req->flags |= REQ_F_BUFFERS_COMMIT | REQ_F_BL_NO_RECYCLE; if (!io_kbuf_commit(req, sel->buf_list, arg->out_len, ret)) req->flags |= REQ_F_BUF_MORE; } } else { ret = io_provided_buffers_select(req, &arg->out_len, sel->buf_list, arg->iovs); }out_unlock: if (issue_flags & IO_URING_F_UNLOCKED) { sel->buf_list = NULL; mutex_unlock(&ctx->uring_lock); } return ret;} int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel){ struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret; lockdep_assert_held(&ctx->uring_lock); bl = io_buffer_get_list(ctx, arg->buf_group); if (unlikely(!bl)) return -ENOENT; if (bl->flags & IOBL_BUF_RING) { ret = io_ring_buffers_peek(req, arg, bl); if (ret > 0) req->flags |= REQ_F_BUFFERS_COMMIT; sel->buf_list = bl; return ret; } /* don't support multiple buffer selections for legacy */ sel->buf_list = NULL; return io_provided_buffers_select(req, &arg->max_len, bl, arg->iovs);} static inline bool __io_put_kbuf_ring(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr){ bool ret = true; if (bl) ret = io_kbuf_commit(req, bl, len, nr); if (ret && (req->flags & REQ_F_BUF_MORE)) ret = false; req->flags &= ~(REQ_F_BUFFER_RING | REQ_F_BUF_MORE); return ret;} unsigned int __io_put_kbufs(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nbufs){ unsigned int ret; ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT); if (unlikely(!(req->flags & REQ_F_BUFFER_RING))) { io_kbuf_drop_legacy(req); return ret; } if (!__io_put_kbuf_ring(req, bl, len, nbufs)) ret |= IORING_CQE_F_BUF_MORE; return ret;} static int io_remove_buffers_legacy(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned long nbufs){ unsigned long i = 0; struct io_buffer *nxt; /* protects io_buffers_cache */ lockdep_assert_held(&ctx->uring_lock); WARN_ON_ONCE(bl->flags & IOBL_BUF_RING); for (i = 0; i < nbufs && !list_empty(&bl->buf_list); i++) { nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); list_del(&nxt->list); bl->nbufs--; kfree(nxt); cond_resched(); } return i;} static void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl){ if (bl->flags & IOBL_BUF_RING) io_free_region(ctx->user, &bl->region); else io_remove_buffers_legacy(ctx, bl, -1U); kfree(bl);} void io_destroy_buffers(struct io_ring_ctx *ctx){ struct io_buffer_list *bl; while (1) { unsigned long index = 0; scoped_guard(mutex, &ctx->mmap_lock) { bl = xa_find(&ctx->io_bl_xa, &index, ULONG_MAX, XA_PRESENT); if (bl) xa_erase(&ctx->io_bl_xa, bl->bgid); } if (!bl) break; io_put_bl(ctx, bl); }} static void io_destroy_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl){ scoped_guard(mutex, &ctx->mmap_lock) WARN_ON_ONCE(xa_erase(&ctx->io_bl_xa, bl->bgid) != bl); io_put_bl(ctx, bl);} 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)Lines 1–500 of 776. Load more
// 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/uio.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "opdef.h" #include "kbuf.h" #include "memmap.h" /* BIDs are addressed by a 16-bit field in a CQE */ #define MAX_BIDS_PER_BGID (1 << 16) /* Mapped buffer ring, return io_uring_buf from head */ #define io_ring_head_to_buf(br, head, mask) (&(br)->bufs[(head) & (mask)]) struct io_provide_buf { struct file *file; __u64 addr; __u32 len; __u32 bgid; __u32 nbufs; __u16 bid; }; static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len) { /* No data consumed, return false early to avoid consuming the buffer */ if (!len) return false; while (len) { struct io_uring_buf *buf; u32 buf_len, this_len; buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask); buf_len = READ_ONCE(buf->len); this_len = min_t(u32, len, buf_len); buf_len -= this_len; /* Stop looping for invalid buffer length of 0 */ if (buf_len > bl->min_left_sub_one || !this_len) { WRITE_ONCE(buf->addr, READ_ONCE(buf->addr) + this_len); WRITE_ONCE(buf->len, buf_len); return false; } WRITE_ONCE(buf->len, 0); bl->head++; len -= this_len; } return true; } bool io_kbuf_commit(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr) { if (unlikely(!(req->flags & REQ_F_BUFFERS_COMMIT))) return true; req->flags &= ~REQ_F_BUFFERS_COMMIT; if (unlikely(len < 0)) return true; if (bl->flags & IOBL_INC) return io_kbuf_inc_commit(bl, len); bl->head += nr; return true; } static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, unsigned int bgid) { lockdep_assert_held(&ctx->uring_lock); 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) { /* * Store buffer group ID and finally mark the list as visible. * The normal lookup doesn't care about the visibility as we're * always under the ->uring_lock, but lookups from mmap do. */ bl->bgid = bgid; guard(mutex)(&ctx->mmap_lock); return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } void io_kbuf_drop_legacy(struct io_kiocb *req) { if (WARN_ON_ONCE(!(req->flags & REQ_F_BUFFER_SELECTED))) return; req->flags &= ~REQ_F_BUFFER_SELECTED; kfree(req->kbuf); req->kbuf = NULL; } bool 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; io_ring_submit_lock(ctx, issue_flags); buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); /* * If the buffer list was upgraded to a ring-based one, or removed, * while the request was in-flight in io-wq, drop it. */ if (bl && !(bl->flags & IOBL_BUF_RING)) { list_add(&buf->list, &bl->buf_list); bl->nbufs++; } else { kfree(buf); } req->flags &= ~REQ_F_BUFFER_SELECTED; req->kbuf = NULL; io_ring_submit_unlock(ctx, issue_flags); return true; } 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); bl->nbufs--; if (*len == 0 || *len > kbuf->len) *len = kbuf->len; if (list_empty(&bl->buf_list)) req->flags |= REQ_F_BL_EMPTY; req->flags |= REQ_F_BUFFER_SELECTED; req->kbuf = kbuf; req->buf_index = kbuf->bid; return u64_to_user_ptr(kbuf->addr); } return NULL; } static int io_provided_buffers_select(struct io_kiocb *req, size_t *len, struct io_buffer_list *bl, struct iovec *iov) { void __user *buf; buf = io_provided_buffer_select(req, len, bl); if (unlikely(!buf)) return -ENOBUFS; iov[0].iov_base = buf; iov[0].iov_len = *len; return 1; } static bool io_should_commit(struct io_kiocb *req, unsigned int issue_flags) { /* * 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). */ if (issue_flags & IO_URING_F_UNLOCKED) return true; /* uring_cmd commits kbuf upfront, no need to auto-commit */ if (!io_file_can_poll(req) && !io_is_uring_cmd(req)) return true; return false; } static struct io_br_sel 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; __u16 tail, head = bl->head; struct io_br_sel sel = { }; struct io_uring_buf *buf; u32 buf_len; tail = smp_load_acquire(&br->tail); if (unlikely(tail == head)) return sel; if (head + 1 == tail) req->flags |= REQ_F_BL_EMPTY; buf = io_ring_head_to_buf(br, head, bl->mask); buf_len = READ_ONCE(buf->len); if (*len == 0 || *len > buf_len) *len = buf_len; sel.addr = u64_to_user_ptr(READ_ONCE(buf->addr)); if (unlikely(!access_ok(sel.addr, *len))) { sel.addr = NULL; return sel; } req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; req->buf_index = READ_ONCE(buf->bid); sel.buf_list = bl; if (io_should_commit(req, issue_flags)) { if (!io_kbuf_commit(req, sel.buf_list, *len, 1)) req->flags |= REQ_F_BUF_MORE; sel.buf_list = NULL; } return sel; } struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len, unsigned buf_group, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_br_sel sel = { }; struct io_buffer_list *bl; io_ring_submit_lock(ctx, issue_flags); bl = io_buffer_get_list(ctx, buf_group); if (likely(bl)) { if (bl->flags & IOBL_BUF_RING) sel = io_ring_buffer_select(req, len, bl, issue_flags); else sel.addr = io_provided_buffer_select(req, len, bl); } io_ring_submit_unlock(ctx, issue_flags); return sel; } /* cap it at a reasonable 256, will be one page even for 4K */ #define PEEK_MAX_IMPORT 256 static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_buffer_list *bl) { struct io_uring_buf_ring *br = bl->buf_ring; struct iovec *org_iovs = arg->iovs; struct iovec *iov = arg->iovs; int nr_iovs = arg->nr_iovs; __u16 nr_avail, tail, head; struct io_uring_buf *buf; tail = smp_load_acquire(&br->tail); head = bl->head; nr_avail = min_t(__u16, tail - head, UIO_MAXIOV); if (unlikely(!nr_avail)) return -ENOBUFS; /* MAX_RW_COUNT is the universal Linux per-call IO maximum */ arg->max_len = min_t(size_t, arg->max_len, MAX_RW_COUNT); buf = io_ring_head_to_buf(br, head, bl->mask); if (arg->max_len) { u32 len = READ_ONCE(buf->len); size_t needed; if (unlikely(!len)) return -ENOBUFS; needed = (arg->max_len + len - 1) / len; needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT); if (nr_avail > needed) nr_avail = needed; } /* * only alloc a bigger array if we know we have data to map, eg not * a speculative peek operation. */ if (arg->mode & KBUF_MODE_EXPAND && nr_avail > nr_iovs && arg->max_len) { iov = kmalloc_objs(struct iovec, nr_avail); if (unlikely(!iov)) return -ENOMEM; arg->iovs = iov; nr_iovs = nr_avail; } else if (nr_avail < nr_iovs) { nr_iovs = nr_avail; } /* set it to max, if not set, so we can use it unconditionally */ if (!arg->max_len) arg->max_len = MAX_RW_COUNT; req->buf_index = READ_ONCE(buf->bid); do { u32 len = READ_ONCE(buf->len); /* truncate end piece, if needed, for non partial buffers */ if (len > arg->max_len) { len = arg->max_len; if (!(bl->flags & IOBL_INC)) { arg->partial_map = 1; if (iov != arg->iovs) break; } } iov->iov_base = u64_to_user_ptr(READ_ONCE(buf->addr)); iov->iov_len = len; if (unlikely(!access_ok(iov->iov_base, len))) { if (arg->iovs != org_iovs) kfree(arg->iovs); return -EFAULT; } iov++; arg->out_len += len; arg->max_len -= len; if (!arg->max_len) break; buf = io_ring_head_to_buf(br, ++head, bl->mask); } while (--nr_iovs); if (arg->iovs != org_iovs && (arg->mode & KBUF_MODE_FREE)) kfree(org_iovs); if (head == tail) req->flags |= REQ_F_BL_EMPTY; req->flags |= REQ_F_BUFFER_RING; return iov - arg->iovs; } int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; int ret = -ENOENT; io_ring_submit_lock(ctx, issue_flags); sel->buf_list = io_buffer_get_list(ctx, arg->buf_group); if (unlikely(!sel->buf_list)) goto out_unlock; if (sel->buf_list->flags & IOBL_BUF_RING) { ret = io_ring_buffers_peek(req, arg, sel->buf_list); /* * Don't recycle these buffers if we need to go through poll. * Nobody else can use them anyway, and holding on to provided * buffers for a send/write operation would happen on the app * side anyway with normal buffers. Besides, we already * committed them, they cannot be put back in the queue. */ if (ret > 0) { req->flags |= REQ_F_BUFFERS_COMMIT | REQ_F_BL_NO_RECYCLE; if (!io_kbuf_commit(req, sel->buf_list, arg->out_len, ret)) req->flags |= REQ_F_BUF_MORE; } } else { ret = io_provided_buffers_select(req, &arg->out_len, sel->buf_list, arg->iovs); } out_unlock: if (issue_flags & IO_URING_F_UNLOCKED) { sel->buf_list = NULL; mutex_unlock(&ctx->uring_lock); } return ret; } int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel) { struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret; lockdep_assert_held(&ctx->uring_lock); bl = io_buffer_get_list(ctx, arg->buf_group); if (unlikely(!bl)) return -ENOENT; if (bl->flags & IOBL_BUF_RING) { ret = io_ring_buffers_peek(req, arg, bl); if (ret > 0) req->flags |= REQ_F_BUFFERS_COMMIT; sel->buf_list = bl; return ret; } /* don't support multiple buffer selections for legacy */ sel->buf_list = NULL; return io_provided_buffers_select(req, &arg->max_len, bl, arg->iovs); } static inline bool __io_put_kbuf_ring(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr) { bool ret = true; if (bl) ret = io_kbuf_commit(req, bl, len, nr); if (ret && (req->flags & REQ_F_BUF_MORE)) ret = false; req->flags &= ~(REQ_F_BUFFER_RING | REQ_F_BUF_MORE); return ret; } unsigned int __io_put_kbufs(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nbufs) { unsigned int ret; ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT); if (unlikely(!(req->flags & REQ_F_BUFFER_RING))) { io_kbuf_drop_legacy(req); return ret; } if (!__io_put_kbuf_ring(req, bl, len, nbufs)) ret |= IORING_CQE_F_BUF_MORE; return ret; } static int io_remove_buffers_legacy(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned long nbufs) { unsigned long i = 0; struct io_buffer *nxt; /* protects io_buffers_cache */ lockdep_assert_held(&ctx->uring_lock); WARN_ON_ONCE(bl->flags & IOBL_BUF_RING); for (i = 0; i < nbufs && !list_empty(&bl->buf_list); i++) { nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); list_del(&nxt->list); bl->nbufs--; kfree(nxt); cond_resched(); } return i; } static void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) { if (bl->flags & IOBL_BUF_RING) io_free_region(ctx->user, &bl->region); else io_remove_buffers_legacy(ctx, bl, -1U); kfree(bl); } void io_destroy_buffers(struct io_ring_ctx *ctx) { struct io_buffer_list *bl; while (1) { unsigned long index = 0; scoped_guard(mutex, &ctx->mmap_lock) { bl = xa_find(&ctx->io_bl_xa, &index, ULONG_MAX, XA_PRESENT); if (bl) xa_erase(&ctx->io_bl_xa, bl->bgid); } if (!bl) break; io_put_bl(ctx, bl); } } static void io_destroy_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) { scoped_guard(mutex, &ctx->mmap_lock) WARN_ON_ONCE(xa_erase(&ctx->io_bl_xa, bl->bgid) != bl); io_put_bl(ctx, bl); } 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)