@@ -478,3 +478,4 @@
547 common openat2 sys_openat2
548 common pidfd_getfd sys_pidfd_getfd
549 common faccessat2 sys_faccessat2
+550 common process_madvise sys_process_madvise
@@ -885,6 +885,8 @@ __SYSCALL(__NR_openat2, sys_openat2)
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_faccessat2 439
__SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
/*
* Please add new compat syscalls above this comment and update
@@ -38,7 +38,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 440
+#define __NR_compat_syscalls 441
#endif
#define __ARCH_WANT_SYS_CLONE
@@ -452,3 +452,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -359,3 +359,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -438,3 +438,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -444,3 +444,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -377,3 +377,4 @@
437 n32 openat2 sys_openat2
438 n32 pidfd_getfd sys_pidfd_getfd
439 n32 faccessat2 sys_faccessat2
+440 n32 process_madvise sys_process_madvise
@@ -353,3 +353,4 @@
437 n64 openat2 sys_openat2
438 n64 pidfd_getfd sys_pidfd_getfd
439 n64 faccessat2 sys_faccessat2
+440 n64 process_madvise sys_process_madvise
@@ -426,3 +426,4 @@
437 o32 openat2 sys_openat2
438 o32 pidfd_getfd sys_pidfd_getfd
439 o32 faccessat2 sys_faccessat2
+440 o32 process_madvise sys_process_madvise
@@ -436,3 +436,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -528,3 +528,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -441,3 +441,4 @@
437 common openat2 sys_openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise sys_process_madvise
@@ -441,3 +441,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -484,3 +484,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -443,3 +443,4 @@
437 i386 openat2 sys_openat2
438 i386 pidfd_getfd sys_pidfd_getfd
439 i386 faccessat2 sys_faccessat2
+440 i386 process_madvise sys_process_madvise
@@ -360,6 +360,7 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
#
# x32-specific system call numbers start at 512 to avoid cache impact
@@ -409,3 +409,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -878,6 +878,8 @@ asmlinkage long sys_munlockall(void);
asmlinkage long sys_mincore(unsigned long start, size_t len,
unsigned char __user * vec);
asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior);
+asmlinkage long sys_process_madvise(int pidfd, unsigned long start,
+ size_t len, int behavior, unsigned long flags);
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
unsigned long prot, unsigned long pgoff,
unsigned long flags);
@@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2)
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_faccessat2 439
__SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
#undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
/*
* 32 bit systems traditionally used different
@@ -280,6 +280,7 @@ COND_SYSCALL(mlockall);
COND_SYSCALL(munlockall);
COND_SYSCALL(mincore);
COND_SYSCALL(madvise);
+COND_SYSCALL(process_madvise);
COND_SYSCALL(remap_file_pages);
COND_SYSCALL(mbind);
COND_SYSCALL_COMPAT(mbind);
@@ -17,6 +17,7 @@
#include <linux/falloc.h>
#include <linux/fadvise.h>
#include <linux/sched.h>
+#include <linux/sched/mm.h>
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
@@ -995,6 +996,18 @@ madvise_behavior_valid(int behavior)
}
}
+static bool
+process_madvise_behavior_valid(int behavior)
+{
+ switch (behavior) {
+ case MADV_COLD:
+ case MADV_PAGEOUT:
+ return true;
+ default:
+ return false;
+ }
+}
+
/*
* The madvise(2) system call.
*
@@ -1042,6 +1055,11 @@ madvise_behavior_valid(int behavior)
* MADV_DONTDUMP - the application wants to prevent pages in the given range
* from being included in its core dump.
* MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
+ * MADV_COLD - the application is not expected to use this memory soon,
+ * deactivate pages in this range so that they can be reclaimed
+ * easily if memory pressure hanppens.
+ * MADV_PAGEOUT - the application is not expected to use this memory soon,
+ * page out the pages in this range immediately.
*
* return values:
* zero - success
@@ -1176,3 +1194,49 @@ SYSCALL_DEFINE3(madvise, unsigned long,
{
return do_madvise(current, current->mm, start, len_in, behavior);
}
+
+SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start,
+ size_t, len_in, int, behavior, unsigned long, flags)
+{
+ int ret;
+ struct fd f;
+ struct pid *pid;
+ struct task_struct *task;
+ struct mm_struct *mm;
+
+ if (flags != 0)
+ return -EINVAL;
+
+ if (!process_madvise_behavior_valid(behavior))
+ return -EINVAL;
+
+ f = fdget(pidfd);
+ if (!f.file)
+ return -EBADF;
+
+ pid = pidfd_pid(f.file);
+ if (IS_ERR(pid)) {
+ ret = PTR_ERR(pid);
+ goto fdput;
+ }
+
+ task = get_pid_task(pid, PIDTYPE_PID);
+ if (!task) {
+ ret = -ESRCH;
+ goto fdput;
+ }
+
+ mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+ if (IS_ERR_OR_NULL(mm)) {
+ ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
+ goto release_task;
+ }
+
+ ret = do_madvise(task, mm, start, len_in, behavior);
+ mmput(mm);
+release_task:
+ put_task_struct(task);
+fdput:
+ fdput(f);
+ return ret;
+}