// 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;}; struct io_buf_free { struct hlist_node list; void *mem; size_t size; int inuse;}; static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned int bgid){ if (bl && bgid < BGID_ARRAY) return &bl[bgid]; return xa_load(&ctx->io_bl_xa, bgid);} 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 __io_buffer_get_list(ctx, ctx->io_bl, 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 the RCU lookup from mmap does. */ bl->bgid = bgid; smp_store_release(&bl->is_ready, 1); if (bgid < BGID_ARRAY) return 0; return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));} 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; /* * 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 false; 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 true;} 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){ struct io_buffer_list *bl; int i; bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL); if (!bl) return -ENOMEM; for (i = 0; i < BGID_ARRAY; i++) { INIT_LIST_HEAD(&bl[i].buf_list); bl[i].bgid = i; } smp_store_release(&ctx->io_bl, bl); return 0;} /* * Mark the given mapped range as free for reuse */static void io_kbuf_mark_free(struct io_ring_ctx *ctx, struct io_buffer_list *bl){ struct io_buf_free *ibf; hlist_for_each_entry(ibf, &ctx->io_buf_list, list) { if (bl->buf_ring == ibf->mem) { ibf->inuse = 0; return; } } /* can't happen... */ WARN_ON_ONCE(1);} 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) { /* * io_kbuf_list_free() will free the page(s) at * ->release() time. */ io_kbuf_mark_free(ctx, bl); 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_rcu(bl, rcu); } /* * Move deferred locked entries to cache before pruning */ 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); 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); Lines 1–500 of 786. 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/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; }; struct io_buf_free { struct hlist_node list; void *mem; size_t size; int inuse; }; static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned int bgid) { if (bl && bgid < BGID_ARRAY) return &bl[bgid]; return xa_load(&ctx->io_bl_xa, bgid); } 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 __io_buffer_get_list(ctx, ctx->io_bl, 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 the RCU lookup from mmap does. */ bl->bgid = bgid; smp_store_release(&bl->is_ready, 1); if (bgid < BGID_ARRAY) return 0; return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } 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; /* * 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 false; 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 true; } 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) { struct io_buffer_list *bl; int i; bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL); if (!bl) return -ENOMEM; for (i = 0; i < BGID_ARRAY; i++) { INIT_LIST_HEAD(&bl[i].buf_list); bl[i].bgid = i; } smp_store_release(&ctx->io_bl, bl); return 0; } /* * Mark the given mapped range as free for reuse */ static void io_kbuf_mark_free(struct io_ring_ctx *ctx, struct io_buffer_list *bl) { struct io_buf_free *ibf; hlist_for_each_entry(ibf, &ctx->io_buf_list, list) { if (bl->buf_ring == ibf->mem) { ibf->inuse = 0; return; } } /* can't happen... */ WARN_ON_ONCE(1); } 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) { /* * io_kbuf_list_free() will free the page(s) at * ->release() time. */ io_kbuf_mark_free(ctx, bl); 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_rcu(bl, rcu); } /* * Move deferred locked entries to cache before pruning */ 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); 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);