mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 10:45:23 +07:00
da8b44d5a9
This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
165 lines
4.5 KiB
C
165 lines
4.5 KiB
C
#ifndef _LINUX_POLL_H
|
|
#define _LINUX_POLL_H
|
|
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/string.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/sysctl.h>
|
|
#include <asm/uaccess.h>
|
|
#include <uapi/linux/poll.h>
|
|
|
|
extern struct ctl_table epoll_table[]; /* for sysctl */
|
|
/* ~832 bytes of stack space used max in sys_select/sys_poll before allocating
|
|
additional memory. */
|
|
#define MAX_STACK_ALLOC 832
|
|
#define FRONTEND_STACK_ALLOC 256
|
|
#define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC
|
|
#define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC
|
|
#define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC)
|
|
#define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry))
|
|
|
|
#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM)
|
|
|
|
struct poll_table_struct;
|
|
|
|
/*
|
|
* structures and helpers for f_op->poll implementations
|
|
*/
|
|
typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *);
|
|
|
|
/*
|
|
* Do not touch the structure directly, use the access functions
|
|
* poll_does_not_wait() and poll_requested_events() instead.
|
|
*/
|
|
typedef struct poll_table_struct {
|
|
poll_queue_proc _qproc;
|
|
unsigned long _key;
|
|
} poll_table;
|
|
|
|
static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
|
|
{
|
|
if (p && p->_qproc && wait_address)
|
|
p->_qproc(filp, wait_address, p);
|
|
}
|
|
|
|
/*
|
|
* Return true if it is guaranteed that poll will not wait. This is the case
|
|
* if the poll() of another file descriptor in the set got an event, so there
|
|
* is no need for waiting.
|
|
*/
|
|
static inline bool poll_does_not_wait(const poll_table *p)
|
|
{
|
|
return p == NULL || p->_qproc == NULL;
|
|
}
|
|
|
|
/*
|
|
* Return the set of events that the application wants to poll for.
|
|
* This is useful for drivers that need to know whether a DMA transfer has
|
|
* to be started implicitly on poll(). You typically only want to do that
|
|
* if the application is actually polling for POLLIN and/or POLLOUT.
|
|
*/
|
|
static inline unsigned long poll_requested_events(const poll_table *p)
|
|
{
|
|
return p ? p->_key : ~0UL;
|
|
}
|
|
|
|
static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
|
|
{
|
|
pt->_qproc = qproc;
|
|
pt->_key = ~0UL; /* all events enabled */
|
|
}
|
|
|
|
struct poll_table_entry {
|
|
struct file *filp;
|
|
unsigned long key;
|
|
wait_queue_t wait;
|
|
wait_queue_head_t *wait_address;
|
|
};
|
|
|
|
/*
|
|
* Structures and helpers for select/poll syscall
|
|
*/
|
|
struct poll_wqueues {
|
|
poll_table pt;
|
|
struct poll_table_page *table;
|
|
struct task_struct *polling_task;
|
|
int triggered;
|
|
int error;
|
|
int inline_index;
|
|
struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES];
|
|
};
|
|
|
|
extern void poll_initwait(struct poll_wqueues *pwq);
|
|
extern void poll_freewait(struct poll_wqueues *pwq);
|
|
extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
|
|
ktime_t *expires, unsigned long slack);
|
|
extern u64 select_estimate_accuracy(struct timespec *tv);
|
|
|
|
|
|
static inline int poll_schedule(struct poll_wqueues *pwq, int state)
|
|
{
|
|
return poll_schedule_timeout(pwq, state, NULL, 0);
|
|
}
|
|
|
|
/*
|
|
* Scalable version of the fd_set.
|
|
*/
|
|
|
|
typedef struct {
|
|
unsigned long *in, *out, *ex;
|
|
unsigned long *res_in, *res_out, *res_ex;
|
|
} fd_set_bits;
|
|
|
|
/*
|
|
* How many longwords for "nr" bits?
|
|
*/
|
|
#define FDS_BITPERLONG (8*sizeof(long))
|
|
#define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG)
|
|
#define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long))
|
|
|
|
/*
|
|
* We do a VERIFY_WRITE here even though we are only reading this time:
|
|
* we'll write to it eventually..
|
|
*
|
|
* Use "unsigned long" accesses to let user-mode fd_set's be long-aligned.
|
|
*/
|
|
static inline
|
|
int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
|
|
{
|
|
nr = FDS_BYTES(nr);
|
|
if (ufdset)
|
|
return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0;
|
|
|
|
memset(fdset, 0, nr);
|
|
return 0;
|
|
}
|
|
|
|
static inline unsigned long __must_check
|
|
set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
|
|
{
|
|
if (ufdset)
|
|
return __copy_to_user(ufdset, fdset, FDS_BYTES(nr));
|
|
return 0;
|
|
}
|
|
|
|
static inline
|
|
void zero_fd_set(unsigned long nr, unsigned long *fdset)
|
|
{
|
|
memset(fdset, 0, FDS_BYTES(nr));
|
|
}
|
|
|
|
#define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
|
|
|
|
extern int do_select(int n, fd_set_bits *fds, struct timespec *end_time);
|
|
extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
|
|
struct timespec *end_time);
|
|
extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
|
|
fd_set __user *exp, struct timespec *end_time);
|
|
|
|
extern int poll_select_set_timeout(struct timespec *to, long sec, long nsec);
|
|
|
|
#endif /* _LINUX_POLL_H */
|