mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
synced 2026-10-30 22:03:17 +01:00
Hengyu Liang
b59cabf9b4
Commit8078486e1d("io_uring: use region api for SQ") and commit81a4058e0c("io_uring: use region api for CQ") made io_uring_setup() allocate the rings with io_create_region(). However, io_create_region() charges the memory to RLIMIT_MEMLOCK, and the rings had been exempt from that limit since commit26bfa89e25("io_uring: place ring SQ/CQ arrays under memcg memory limits"). As of now, a user without CAP_IPC_LOCK gets ENOMEM from io_uring_setup() when their rings exceed the limit, which is 8 MiB by default. PostgreSQL developers have already hit this in their io_uring tests [1]. The issue can be reproduced with a simple liburing program, run as an unprivileged user: #include <liburing.h> #include <stdio.h> int main(void) { static struct io_uring ring[64]; int i; for (i = 0; i < 64; i++) if (io_uring_queue_init(4096, &ring[i], 0) < 0) break; printf("%d rings\n", i); return 0; } Before those commits (v6.13), it prints "64 rings". After those commits (v6.14), it prints "21 rings". This patch makes io_create_region() take the user to charge, and passes no user for the SQ/CQ rings. Link: https://www.postgresql.org/message-id/flat/[email protected] [1] Fixes:8078486e1d("io_uring: use region api for SQ") Fixes:81a4058e0c("io_uring: use region api for CQ") Cc: [email protected] Signed-off-by: Hengyu Liang <[email protected]> Link: https://lore.kernel.org/io-uring/[email protected]/ Signed-off-by: Jens Axboe <[email protected]>
53 lines
1.5 KiB
C
53 lines
1.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef IO_URING_MEMMAP_H
|
|
#define IO_URING_MEMMAP_H
|
|
|
|
#define IORING_MAP_OFF_PARAM_REGION 0x20000000ULL
|
|
#define IORING_MAP_OFF_ZCRX_REGION 0x30000000ULL
|
|
|
|
#define IORING_OFF_ZCRX_SHIFT 16
|
|
|
|
struct page **io_pin_pages(unsigned long uaddr, unsigned long len, int *npages);
|
|
|
|
#ifndef CONFIG_MMU
|
|
unsigned int io_uring_nommu_mmap_capabilities(struct file *file);
|
|
#endif
|
|
unsigned long io_uring_get_unmapped_area(struct file *file, unsigned long addr,
|
|
unsigned long len, unsigned long pgoff,
|
|
unsigned long flags);
|
|
int io_uring_mmap(struct file *file, struct vm_area_struct *vma);
|
|
|
|
void io_free_region(struct user_struct *user, struct io_mapped_region *mr);
|
|
int io_create_region(struct user_struct *user, struct io_mapped_region *mr,
|
|
struct io_uring_region_desc *reg,
|
|
unsigned long mmap_offset);
|
|
|
|
static inline void *io_region_get_ptr(struct io_mapped_region *mr)
|
|
{
|
|
return mr->ptr;
|
|
}
|
|
|
|
static inline bool io_region_is_set(struct io_mapped_region *mr)
|
|
{
|
|
return !!mr->nr_pages;
|
|
}
|
|
|
|
static inline void io_region_publish(struct io_ring_ctx *ctx,
|
|
struct io_mapped_region *src_region,
|
|
struct io_mapped_region *dst_region)
|
|
{
|
|
/*
|
|
* Once published mmap can find it without holding only the ->mmap_lock
|
|
* and not ->uring_lock.
|
|
*/
|
|
guard(mutex)(&ctx->mmap_lock);
|
|
*dst_region = *src_region;
|
|
}
|
|
|
|
static inline size_t io_region_size(struct io_mapped_region *mr)
|
|
{
|
|
return (size_t) mr->nr_pages << PAGE_SHIFT;
|
|
}
|
|
|
|
#endif
|