io_uring: change the poll type to be 32-bits

poll events should be 32-bits to cover EPOLLEXCLUSIVE.

Explicit word-swap the poll32_events for big endian to make sure the ABI
is not changed.  We call this feature IORING_FEAT_POLL_32BITS,
applications who want to use EPOLLEXCLUSIVE should check the feature bit
first.

Signed-off-by: Jiufei Xue <jiufei.xue@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a78201b9617965acf762c1480c36e9dfb3d71eba..0eb063daa9b5feb47d0e8230bda1e466b885c311 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4589,7 +4589,7 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
        struct io_poll_iocb *poll = &req->poll;
-       u16 events;
+       u32 events;
 
        if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
                return -EINVAL;
@@ -4598,7 +4598,10 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
        if (!poll->file)
                return -EBADF;
 
-       events = READ_ONCE(sqe->poll_events);
+       events = READ_ONCE(sqe->poll32_events);
+#ifdef __BIG_ENDIAN
+       events = swahw32(events);
+#endif
        poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
 
        io_get_req_task(req);
@@ -7928,7 +7931,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 
        p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
                        IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
-                       IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
+                       IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
+                       IORING_FEAT_POLL_32BITS;
 
        if (copy_to_user(params, p, sizeof(*p))) {
                ret = -EFAULT;
@@ -8217,7 +8221,8 @@ static int __init io_uring_init(void)
        BUILD_BUG_SQE_ELEM(28, /* compat */   int, rw_flags);
        BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags);
        BUILD_BUG_SQE_ELEM(28, __u32,  fsync_flags);
-       BUILD_BUG_SQE_ELEM(28, __u16,  poll_events);
+       BUILD_BUG_SQE_ELEM(28, /* compat */ __u16,  poll_events);
+       BUILD_BUG_SQE_ELEM(28, __u32,  poll32_events);
        BUILD_BUG_SQE_ELEM(28, __u32,  sync_range_flags);
        BUILD_BUG_SQE_ELEM(28, __u32,  msg_flags);
        BUILD_BUG_SQE_ELEM(28, __u32,  timeout_flags);

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 92c22699a5a74e44111926657e0c65ac74f135a2..8d033961cb7841987d1b32243bf321ec11fe00b5 100644 (file)
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -31,7 +31,8 @@ struct io_uring_sqe {
        union {
                __kernel_rwf_t  rw_flags;
                __u32           fsync_flags;
-               __u16           poll_events;
+               __u16           poll_events;    /* compatibility */
+               __u32           poll32_events;  /* word-reversed for BE */
                __u32           sync_range_flags;
                __u32           msg_flags;
                __u32           timeout_flags;
@@ -248,6 +249,7 @@ struct io_uring_params {
 #define IORING_FEAT_RW_CUR_POS         (1U << 3)
 #define IORING_FEAT_CUR_PERSONALITY    (1U << 4)
 #define IORING_FEAT_FAST_POLL          (1U << 5)
+#define IORING_FEAT_POLL_32BITS        (1U << 6)
 
 /*
  * io_uring_register(2) opcodes and arguments

diff --git a/tools/io_uring/liburing.h b/tools/io_uring/liburing.h
index 5f305c86b892007dcaa4a9ae786ad5a5a7aa858f..28a837b6069dfd2adc9ff6fd8958fffb13c3a9f6 100644 (file)
--- a/tools/io_uring/liburing.h
+++ b/tools/io_uring/liburing.h
@@ -10,6 +10,7 @@ extern "C" {
 #include <string.h>
 #include "../../include/uapi/linux/io_uring.h"
 #include <inttypes.h>
+#include <linux/swab.h>
 #include "barrier.h"
 
 /*
@@ -145,11 +146,14 @@ static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd,
 }
 
 static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd,
-                                         short poll_mask)
+                                         unsigned poll_mask)
 {
        memset(sqe, 0, sizeof(*sqe));
        sqe->opcode = IORING_OP_POLL_ADD;
        sqe->fd = fd;
+#if __BYTE_ORDER == __BIG_ENDIAN
+       poll_mask = __swahw32(poll_mask);
+#endif
        sqe->poll_events = poll_mask;
 }