if (bl->flags & IOBL_BUF_RING) {
i = bl->buf_ring->tail - bl->head;
- if (bl->buf_nr_pages) {
- int j;
-
- if (!(bl->flags & IOBL_MMAP)) {
- for (j = 0; j < bl->buf_nr_pages; j++)
- unpin_user_page(bl->buf_pages[j]);
- }
- io_pages_unmap(bl->buf_ring, &bl->buf_pages,
- &bl->buf_nr_pages, bl->flags & IOBL_MMAP);
- bl->flags &= ~IOBL_MMAP;
- }
+ io_free_region(ctx, &bl->region);
/* make sure it's seen as empty */
INIT_LIST_HEAD(&bl->buf_list);
bl->flags &= ~IOBL_BUF_RING;
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 = NULL;
- struct page **pages;
- int nr_pages, ret;
-
- 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);
-
- br = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
- if (!br) {
- ret = -ENOMEM;
- goto error_unpin;
- }
-
-#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)) {
- ret = -EINVAL;
- goto error_unpin;
- }
-#endif
- bl->buf_pages = pages;
- bl->buf_nr_pages = nr_pages;
- bl->buf_ring = br;
- bl->flags |= IOBL_BUF_RING;
- bl->flags &= ~IOBL_MMAP;
- return 0;
-error_unpin:
- unpin_user_pages(pages, nr_pages);
- kvfree(pages);
- vunmap(br);
- return ret;
-}
-
-static int io_alloc_pbuf_ring(struct io_ring_ctx *ctx,
- struct io_uring_buf_reg *reg,
- struct io_buffer_list *bl)
-{
- size_t ring_size;
-
- ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring);
-
- bl->buf_ring = io_pages_map(&bl->buf_pages, &bl->buf_nr_pages, ring_size);
- if (IS_ERR(bl->buf_ring)) {
- bl->buf_ring = NULL;
- return -ENOMEM;
- }
-
- bl->flags |= (IOBL_BUF_RING | IOBL_MMAP);
- 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;
+ struct io_uring_region_desc rd;
+ struct io_uring_buf_ring *br;
+ unsigned long mmap_offset;
+ unsigned long ring_size;
int ret;
lockdep_assert_held(&ctx->uring_lock);
return -EINVAL;
if (reg.flags & ~(IOU_PBUF_RING_MMAP | IOU_PBUF_RING_INC))
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;
return -ENOMEM;
}
- if (!(reg.flags & IOU_PBUF_RING_MMAP))
- ret = io_pin_pbuf_ring(®, bl);
- else
- ret = io_alloc_pbuf_ring(ctx, ®, bl);
+ mmap_offset = reg.bgid << IORING_OFF_PBUF_SHIFT;
+ ring_size = flex_array_size(br, bufs, reg.ring_entries);
- if (!ret) {
- bl->nr_entries = reg.ring_entries;
- bl->mask = reg.ring_entries - 1;
- if (reg.flags & IOU_PBUF_RING_INC)
- bl->flags |= IOBL_INC;
+ memset(&rd, 0, sizeof(rd));
+ rd.size = PAGE_ALIGN(ring_size);
+ if (!(reg.flags & IOU_PBUF_RING_MMAP)) {
+ rd.user_addr = reg.ring_addr;
+ rd.flags |= IORING_MEM_REGION_TYPE_USER;
+ }
+ ret = io_create_region_mmap_safe(ctx, &bl->region, &rd, mmap_offset);
+ if (ret)
+ goto fail;
+ br = io_region_get_ptr(&bl->region);
- io_buffer_add_list(ctx, bl, reg.bgid);
- return 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.flags & IOU_PBUF_RING_MMAP) &&
+ ((reg.ring_addr | (unsigned long)br) & (SHM_COLOUR - 1))) {
+ ret = -EINVAL;
+ goto fail;
}
+#endif
+ bl->nr_entries = reg.ring_entries;
+ bl->mask = reg.ring_entries - 1;
+ bl->flags |= IOBL_BUF_RING;
+ bl->buf_ring = br;
+ if (reg.flags & IOU_PBUF_RING_INC)
+ bl->flags |= IOBL_INC;
+ io_buffer_add_list(ctx, bl, reg.bgid);
+ return 0;
+fail:
+ io_free_region(ctx, &bl->region);
kfree(free_bl);
return ret;
}
return 0;
}
-struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
- unsigned long bgid)
-{
- struct io_buffer_list *bl;
-
- bl = xa_load(&ctx->io_bl_xa, bgid);
- /* must be a mmap'able buffer ring and have pages */
- if (bl && bl->flags & IOBL_MMAP)
- return bl;
-
- return ERR_PTR(-EINVAL);
-}
-
-int io_pbuf_mmap(struct file *file, struct vm_area_struct *vma)
+struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx,
+ unsigned int bgid)
{
- struct io_ring_ctx *ctx = file->private_data;
- loff_t pgoff = vma->vm_pgoff << PAGE_SHIFT;
struct io_buffer_list *bl;
- int bgid;
lockdep_assert_held(&ctx->mmap_lock);
- bgid = (pgoff & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
- bl = io_pbuf_get_bl(ctx, bgid);
- if (IS_ERR(bl))
- return PTR_ERR(bl);
+ bl = xa_load(&ctx->io_bl_xa, bgid);
+ if (!bl || !(bl->flags & IOBL_BUF_RING))
+ return NULL;
+ if (WARN_ON_ONCE(!io_region_is_set(&bl->region)))
+ return NULL;
- return io_uring_mmap_pages(ctx, vma, bl->buf_pages, bl->buf_nr_pages);
+ return &bl->region;
}
return page_address(page);
}
-static void *io_mem_alloc_single(struct page **pages, int nr_pages, size_t size,
- gfp_t gfp)
-{
- void *ret;
- int i;
-
- for (i = 0; i < nr_pages; i++) {
- pages[i] = alloc_page(gfp);
- if (!pages[i])
- goto err;
- }
-
- ret = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
- if (ret)
- return ret;
-err:
- while (i--)
- put_page(pages[i]);
- return ERR_PTR(-ENOMEM);
-}
-
-void *io_pages_map(struct page ***out_pages, unsigned short *npages,
- size_t size)
-{
- gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN;
- struct page **pages;
- int nr_pages;
- void *ret;
-
- nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
- pages = kvmalloc_array(nr_pages, sizeof(struct page *), gfp);
- if (!pages)
- return ERR_PTR(-ENOMEM);
-
- ret = io_mem_alloc_compound(pages, nr_pages, size, gfp);
- if (!IS_ERR(ret))
- goto done;
- if (nr_pages == 1)
- goto fail;
-
- ret = io_mem_alloc_single(pages, nr_pages, size, gfp);
- if (!IS_ERR(ret)) {
-done:
- *out_pages = pages;
- *npages = nr_pages;
- return ret;
- }
-fail:
- kvfree(pages);
- *out_pages = NULL;
- *npages = 0;
- return ret;
-}
-
-void io_pages_unmap(void *ptr, struct page ***pages, unsigned short *npages,
- bool put_pages)
-{
- bool do_vunmap = false;
-
- if (!ptr)
- return;
-
- if (put_pages && *npages) {
- struct page **to_free = *pages;
- int i;
-
- /*
- * Only did vmap for the non-compound multiple page case.
- * For the compound page, we just need to put the head.
- */
- if (PageCompound(to_free[0]))
- *npages = 1;
- else if (*npages > 1)
- do_vunmap = true;
- for (i = 0; i < *npages; i++)
- put_page(to_free[i]);
- }
- if (do_vunmap)
- vunmap(ptr);
- kvfree(*pages);
- *pages = NULL;
- *npages = 0;
-}
-
struct page **io_pin_pages(unsigned long uaddr, unsigned long len, int *npages)
{
unsigned long start, end, nr_pages;
return ERR_PTR(-EFAULT);
return ctx->sq_sqes;
case IORING_OFF_PBUF_RING: {
- struct io_buffer_list *bl;
+ struct io_mapped_region *region;
unsigned int bgid;
- void *ptr;
bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
- bl = io_pbuf_get_bl(ctx, bgid);
- if (IS_ERR(bl))
- return bl;
- ptr = bl->buf_ring;
- return ptr;
+ region = io_pbuf_get_region(ctx, bgid);
+ if (!region)
+ return ERR_PTR(-EINVAL);
+ return io_region_validate_mmap(ctx, region);
}
case IORING_MAP_OFF_PARAM_REGION:
return io_region_validate_mmap(ctx, &ctx->param_region);
return ERR_PTR(-EINVAL);
}
-int io_uring_mmap_pages(struct io_ring_ctx *ctx, struct vm_area_struct *vma,
- struct page **pages, int npages)
-{
- unsigned long nr_pages = npages;
-
- vm_flags_set(vma, VM_DONTEXPAND);
- return vm_insert_pages(vma, vma->vm_start, pages, &nr_pages);
-}
-
#ifdef CONFIG_MMU
static int io_region_mmap(struct io_ring_ctx *ctx,
return io_region_mmap(ctx, &ctx->ring_region, vma, page_limit);
case IORING_OFF_SQES:
return io_region_mmap(ctx, &ctx->sq_region, vma, UINT_MAX);
- case IORING_OFF_PBUF_RING:
- return io_pbuf_mmap(file, vma);
+ case IORING_OFF_PBUF_RING: {
+ struct io_mapped_region *region;
+ unsigned int bgid;
+
+ bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
+ region = io_pbuf_get_region(ctx, bgid);
+ if (!region)
+ return -EINVAL;
+
+ return io_region_mmap(ctx, region, vma, UINT_MAX);
+ }
case IORING_MAP_OFF_PARAM_REGION:
return io_region_mmap(ctx, &ctx->param_region, vma, UINT_MAX);
}
projects / linux-block.git / commitdiff