for-6.7/io_uring-2023-10-30

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmU/vcMQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpmnaD/4spcYjSSdeHVh3J60QuWjMYOM//E/BNb6e
 3I2L6Is2RLuDGhVhHKfRfkJQy1UPKYKu5TZewUnwC3bz12kWGc8CZBF4WgM0159T
 0uBm2ZtsstSCONA16tQdmE7gt5MJ6KFO0rsubm/AxNWxTnpyrbrX512TkkJTBrfC
 ZluAKxGviZOcrl9ROoVMc/FeMmaKVcT79mDuLp0y+Pmb2KO3y9bWTs/wpmEPNVro
 P7n/j9B4dBQC3Saij/wCdcsodkHUaCfCnRK3g34JKeACb+Kclg7QSzinb3TZjeEw
 o98l1XMiejkPJDIxYmWPTmdzqu6AUnT3Geq6eL463/PUOjgkzet6idYfk6XQgRyz
 AhFzA6KruMJ+IhOs974KtmDJj+7LbGkMUpW0kEqKWpXFEO2t+yG6Ue4cdC2FtsqV
 m/ojTTeejVqJ1RLng9IqVMT/X6sqpTtBOikNIJeWyDZQGpOOBxkG9qyoYxNQTOAr
 280UwcFMgsRDQMpi9uIsc7uE7QvN/RYL9nqm49bxJTRm/sRsABPb71yWcbrHSAjh
 y2tprYqG0V4qK7ogCiqDt8qdq/nZS6d1mN/th33yGAHtWEStTyFKNuYmPOrzLtWb
 tvnmYGA7YxcpSMEPHQbYG5TlmoWoTlzUlwJ1OWGzqdlPw7USCwjFfTZVJuKm6wkR
 u0uTkYhn4A==
 =okQ8
 -----END PGP SIGNATURE-----

Merge tag 'for-6.7/io_uring-2023-10-30' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "This contains the core io_uring updates, of which there are not many,
  and adds support for using WAITID through io_uring and hence not
  needing to block on these kinds of events.

  Outside of that, tweaks to the legacy provided buffer handling and
  some cleanups related to cancelations for uring_cmd support"

* tag 'for-6.7/io_uring-2023-10-30' of git://git.kernel.dk/linux:
  io_uring/poll: use IOU_F_TWQ_LAZY_WAKE for wakeups
  io_uring/kbuf: Use slab for struct io_buffer objects
  io_uring/kbuf: Allow the full buffer id space for provided buffers
  io_uring/kbuf: Fix check of BID wrapping in provided buffers
  io_uring/rsrc: cleanup io_pin_pages()
  io_uring: cancelable uring_cmd
  io_uring: retain top 8bits of uring_cmd flags for kernel internal use
  io_uring: add IORING_OP_WAITID support
  exit: add internal include file with helpers
  exit: add kernel_waitid_prepare() helper
  exit: move core of do_wait() into helper
  exit: abstract out should_wake helper for child_wait_callback()
  io_uring/rw: add support for IORING_OP_READ_MULTISHOT
  io_uring/rw: mark readv/writev as vectored in the opcode definition
  io_uring/rw: split io_read() into a helper
This commit is contained in:
Linus Torvalds 2023-11-01 11:09:19 -10:00
commit ffa059b262
19 changed files with 783 additions and 121 deletions

View file

@ -74,6 +74,8 @@
#include <asm/unistd.h>
#include <asm/mmu_context.h>
#include "exit.h"
/*
* The default value should be high enough to not crash a system that randomly
* crashes its kernel from time to time, but low enough to at least not permit
@ -1037,26 +1039,6 @@ SYSCALL_DEFINE1(exit_group, int, error_code)
return 0;
}
struct waitid_info {
pid_t pid;
uid_t uid;
int status;
int cause;
};
struct wait_opts {
enum pid_type wo_type;
int wo_flags;
struct pid *wo_pid;
struct waitid_info *wo_info;
int wo_stat;
struct rusage *wo_rusage;
wait_queue_entry_t child_wait;
int notask_error;
};
static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
return wo->wo_type == PIDTYPE_MAX ||
@ -1520,6 +1502,17 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
return 0;
}
bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p)
{
if (!eligible_pid(wo, p))
return false;
if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent)
return false;
return true;
}
static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
int sync, void *key)
{
@ -1527,13 +1520,10 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
child_wait);
struct task_struct *p = key;
if (!eligible_pid(wo, p))
return 0;
if (pid_child_should_wake(wo, p))
return default_wake_function(wait, mode, sync, key);
if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
return 0;
return default_wake_function(wait, mode, sync, key);
return 0;
}
void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
@ -1582,16 +1572,10 @@ static int do_wait_pid(struct wait_opts *wo)
return 0;
}
static long do_wait(struct wait_opts *wo)
long __do_wait(struct wait_opts *wo)
{
int retval;
long retval;
trace_sched_process_wait(wo->wo_pid);
init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
wo->child_wait.private = current;
add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
repeat:
/*
* If there is nothing that can match our criteria, just get out.
* We will clear ->notask_error to zero if we see any child that
@ -1603,24 +1587,23 @@ repeat:
(!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type)))
goto notask;
set_current_state(TASK_INTERRUPTIBLE);
read_lock(&tasklist_lock);
if (wo->wo_type == PIDTYPE_PID) {
retval = do_wait_pid(wo);
if (retval)
goto end;
return retval;
} else {
struct task_struct *tsk = current;
do {
retval = do_wait_thread(wo, tsk);
if (retval)
goto end;
return retval;
retval = ptrace_do_wait(wo, tsk);
if (retval)
goto end;
return retval;
if (wo->wo_flags & __WNOTHREAD)
break;
@ -1630,27 +1613,44 @@ repeat:
notask:
retval = wo->notask_error;
if (!retval && !(wo->wo_flags & WNOHANG)) {
retval = -ERESTARTSYS;
if (!signal_pending(current)) {
schedule();
goto repeat;
}
}
end:
if (!retval && !(wo->wo_flags & WNOHANG))
return -ERESTARTSYS;
return retval;
}
static long do_wait(struct wait_opts *wo)
{
int retval;
trace_sched_process_wait(wo->wo_pid);
init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
wo->child_wait.private = current;
add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
do {
set_current_state(TASK_INTERRUPTIBLE);
retval = __do_wait(wo);
if (retval != -ERESTARTSYS)
break;
if (signal_pending(current))
break;
schedule();
} while (1);
__set_current_state(TASK_RUNNING);
remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
return retval;
}
static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
int options, struct rusage *ru)
int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
struct waitid_info *infop, int options,
struct rusage *ru)
{
struct wait_opts wo;
unsigned int f_flags = 0;
struct pid *pid = NULL;
enum pid_type type;
long ret;
unsigned int f_flags = 0;
if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
__WNOTHREAD|__WCLONE|__WALL))
@ -1693,19 +1693,32 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
return -EINVAL;
}
wo.wo_type = type;
wo.wo_pid = pid;
wo.wo_flags = options;
wo.wo_info = infop;
wo.wo_rusage = ru;
wo->wo_type = type;
wo->wo_pid = pid;
wo->wo_flags = options;
wo->wo_info = infop;
wo->wo_rusage = ru;
if (f_flags & O_NONBLOCK)
wo.wo_flags |= WNOHANG;
wo->wo_flags |= WNOHANG;
return 0;
}
static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
int options, struct rusage *ru)
{
struct wait_opts wo;
long ret;
ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru);
if (ret)
return ret;
ret = do_wait(&wo);
if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK))
if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG))
ret = -EAGAIN;
put_pid(pid);
put_pid(wo.wo_pid);
return ret;
}

30
kernel/exit.h Normal file
View file

@ -0,0 +1,30 @@
// SPDX-License-Identifier: GPL-2.0-only
#ifndef LINUX_WAITID_H
#define LINUX_WAITID_H
struct waitid_info {
pid_t pid;
uid_t uid;
int status;
int cause;
};
struct wait_opts {
enum pid_type wo_type;
int wo_flags;
struct pid *wo_pid;
struct waitid_info *wo_info;
int wo_stat;
struct rusage *wo_rusage;
wait_queue_entry_t child_wait;
int notask_error;
};
bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p);
long __do_wait(struct wait_opts *wo);
int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
struct waitid_info *infop, int options,
struct rusage *ru);
#endif