Files
linux/io_uring/rsrc.h

150 lines
4.3 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
#ifndef IOU_RSRC_H
#define IOU_RSRC_H
#include <linux/io_uring_types.h>
#include <linux/lockdep.h>
#define IO_VEC_CACHE_SOFT_CAP 256
enum {
IORING_RSRC_FILE = 0,
IORING_RSRC_BUFFER = 1,
};
struct io_rsrc_node {
unsigned char type;
int refs;
io_uring/rsrc: get rid of per-ring io_rsrc_node list Work in progress, but get rid of the per-ring serialization of resource nodes, like registered buffers and files. Main issue here is that one node can otherwise hold up a bunch of other nodes from getting freed, which is especially a problem for file resource nodes and networked workloads where some descriptors may not see activity in a long time. As an example, instantiate an io_uring ring fd and create a sparse registered file table. Even 2 will do. Then create a socket and register it as fixed file 0, F0. The number of open files in the app is now 5, with 0/1/2 being the usual stdin/out/err, 3 being the ring fd, and 4 being the socket. Register this socket (eg "the listener") in slot 0 of the registered file table. Now add an operation on the socket that uses slot 0. Finally, loop N times, where each loop creates a new socket, registers said socket as a file, then unregisters the socket, and finally closes the socket. This is roughly similar to what a basic accept loop would look like. At the end of this loop, it's not unreasonable to expect that there would still be 5 open files. Each socket created and registered in the loop is also unregistered and closed. But since the listener socket registered first still has references to its resource node due to still being active, each subsequent socket unregistration is stuck behind it for reclaim. Hence 5 + N files are still open at that point, where N is awaiting the final put held up by the listener socket. Rewrite the io_rsrc_node handling to NOT rely on serialization. Struct io_kiocb now gets explicit resource nodes assigned, with each holding a reference to the parent node. A parent node is either of type FILE or BUFFER, which are the two types of nodes that exist. A request can have two nodes assigned, if it's using both registered files and buffers. Since request issue and task_work completion is both under the ring private lock, no atomics are needed to handle these references. It's a simple unlocked inc/dec. As before, the registered buffer or file table each hold a reference as well to the registered nodes. Final put of the node will remove the node and free the underlying resource, eg unmap the buffer or put the file. Outside of removing the stall in resource reclaim described above, it has the following advantages: 1) It's a lot simpler than the previous scheme, and easier to follow. No need to specific quiesce handling anymore. 2) There are no resource node allocations in the fast path, all of that happens at resource registration time. 3) The structs related to resource handling can all get simplified quite a bit, like io_rsrc_node and io_rsrc_data. io_rsrc_put can go away completely. 4) Handling of resource tags is much simpler, and doesn't require persistent storage as it can simply get assigned up front at registration time. Just copy them in one-by-one at registration time and assign to the resource node. The only real downside is that a request is now explicitly limited to pinning 2 resources, one file and one buffer, where before just assigning a resource node to a request would pin all of them. The upside is that it's easier to follow now, as an individual resource is explicitly referenced and assigned to the request. With this in place, the above mentioned example will be using exactly 5 files at the end of the loop, not N. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-10-25 19:27:39 -06:00
u64 tag;
union {
unsigned long file_ptr;
struct io_mapped_ubuf *buf;
};
};
enum {
IO_IMU_DEST = 1 << ITER_DEST,
IO_IMU_SOURCE = 1 << ITER_SOURCE,
};
struct io_mapped_ubuf {
u64 ubuf;
unsigned int len;
unsigned int nr_bvecs;
unsigned int folio_shift;
refcount_t refs;
unsigned long acct_pages;
void (*release)(void *);
void *priv;
bool is_kbuf;
u8 dir;
struct bio_vec bvec[] __counted_by(nr_bvecs);
};
struct io_imu_folio_data {
/* Head folio can be partially included in the fixed buf */
unsigned int nr_pages_head;
/* For non-head/tail folios, has to be fully included */
unsigned int nr_pages_mid;
unsigned int folio_shift;
unsigned int nr_folios;
unsigned long first_folio_page_idx;
};
bool io_rsrc_cache_init(struct io_ring_ctx *ctx);
void io_rsrc_cache_free(struct io_ring_ctx *ctx);
struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type);
void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node);
void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data);
int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr);
struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
unsigned issue_flags);
int io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
u64 buf_addr, size_t len, int ddir,
unsigned issue_flags);
int io_import_reg_vec(int ddir, struct iov_iter *iter,
struct io_kiocb *req, struct iou_vec *vec,
unsigned nr_iovs, unsigned issue_flags);
int io_prep_reg_iovec(struct io_kiocb *req, struct iou_vec *iv,
const struct iovec __user *uvec, size_t uvec_segs);
int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg);
int io_sqe_buffers_unregister(struct io_ring_ctx *ctx);
int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
unsigned int nr_args, u64 __user *tags);
int io_sqe_files_unregister(struct io_ring_ctx *ctx);
int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
unsigned nr_args, u64 __user *tags);
int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
unsigned nr_args);
int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
unsigned size, unsigned type);
int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
unsigned int size, unsigned int type);
int io_validate_user_buf_range(u64 uaddr, u64 ulen);
bool io_check_coalesce_buffer(struct page **page_array, int nr_pages,
struct io_imu_folio_data *data);
static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data,
int index)
{
if (index < data->nr)
return data->nodes[array_index_nospec(index, data->nr)];
return NULL;
}
static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
{
lockdep_assert_held(&ctx->uring_lock);
if (!--node->refs)
io_free_rsrc_node(ctx, node);
}
static inline bool io_reset_rsrc_node(struct io_ring_ctx *ctx,
struct io_rsrc_data *data, int index)
{
struct io_rsrc_node *node = data->nodes[index];
if (!node)
return false;
io_put_rsrc_node(ctx, node);
data->nodes[index] = NULL;
return true;
}
int io_files_update(struct io_kiocb *req, unsigned int issue_flags);
int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int __io_account_mem(struct user_struct *user, unsigned long nr_pages);
int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages);
void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages);
static inline void __io_unaccount_mem(struct user_struct *user,
unsigned long nr_pages)
{
atomic_long_sub(nr_pages, &user->locked_vm);
}
void io_vec_free(struct iou_vec *iv);
int io_vec_realloc(struct iou_vec *iv, unsigned nr_entries);
static inline void io_vec_reset_iovec(struct iou_vec *iv,
struct iovec *iovec, unsigned nr)
{
io_vec_free(iv);
iv->iovec = iovec;
iv->nr = nr;
}
static inline void io_alloc_cache_vec_kasan(struct iou_vec *iv)
{
if (IS_ENABLED(CONFIG_KASAN))
io_vec_free(iv);
}
#endif