@@ -479,3 +479,4 @@
547 common openat2 sys_openat2
548 common pidfd_getfd sys_pidfd_getfd
549 common faccessat2 sys_faccessat2
+550 common process_madvise sys_process_madvise
@@ -887,6 +887,8 @@ __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
@@ -453,3 +453,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -360,3 +360,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -439,3 +439,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -445,3 +445,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -378,3 +378,4 @@
437 n32 openat2 sys_openat2
438 n32 pidfd_getfd sys_pidfd_getfd
439 n32 faccessat2 sys_faccessat2
+440 n32 process_madvise sys_process_madvise
@@ -354,3 +354,4 @@
437 n64 openat2 sys_openat2
438 n64 pidfd_getfd sys_pidfd_getfd
439 n64 faccessat2 sys_faccessat2
+440 n64 process_madvise sys_process_madvise
@@ -427,3 +427,4 @@
437 o32 openat2 sys_openat2
438 o32 pidfd_getfd sys_pidfd_getfd
439 o32 faccessat2 sys_faccessat2
+440 o32 process_madvise sys_process_madvise
@@ -437,3 +437,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -529,3 +529,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -442,3 +442,4 @@
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
@@ -442,3 +442,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -485,3 +485,4 @@
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 i386 openat2 sys_openat2
438 i386 pidfd_getfd sys_pidfd_getfd
439 i386 faccessat2 sys_faccessat2
+440 i386 process_madvise sys_process_madvise
@@ -361,6 +361,7 @@
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
@@ -410,3 +410,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
@@ -879,6 +879,8 @@ 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, const struct iovec __user *vec,
+ size_t vlen, int behavior, unsigned int 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 +17,8 @@
#include <linux/falloc.h>
#include <linux/fadvise.h>
#include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/uio.h>
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
@@ -27,7 +29,6 @@
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/mmu_notifier.h>
-#include <linux/sched/mm.h>
#include <asm/tlb.h>
@@ -988,6 +989,18 @@ 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.
*
@@ -1035,6 +1048,11 @@ 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
@@ -1151,3 +1169,76 @@ SYSCALL_DEFINE3(madvise, unsigned long,
{
return do_madvise(current->mm, start, len_in, behavior);
}
+
+SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
+ size_t, vlen, int, behavior, unsigned int, flags)
+{
+ ssize_t ret;
+ struct iovec iovstack[UIO_FASTIOV], iovec;
+ struct iovec *iov = iovstack;
+ struct iov_iter iter;
+ struct pid *pid;
+ struct task_struct *task;
+ struct mm_struct *mm;
+ size_t total_len;
+ unsigned int f_flags;
+
+ if (flags != 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+ if (ret < 0)
+ goto out;
+
+ pid = pidfd_get_pid(pidfd, &f_flags);
+ if (IS_ERR(pid)) {
+ ret = PTR_ERR(pid);
+ goto free_iov;
+ }
+
+ task = get_pid_task(pid, PIDTYPE_PID);
+ if (!task) {
+ ret = -ESRCH;
+ goto put_pid;
+ }
+
+ if (task->mm != current->mm &&
+ !process_madvise_behavior_valid(behavior)) {
+ ret = -EINVAL;
+ goto release_task;
+ }
+
+ 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;
+ }
+
+ total_len = iov_iter_count(&iter);
+
+ while (iov_iter_count(&iter)) {
+ iovec = iov_iter_iovec(&iter);
+ ret = do_madvise(mm, (unsigned long)iovec.iov_base,
+ iovec.iov_len, behavior);
+ if (ret < 0)
+ break;
+ iov_iter_advance(&iter, iovec.iov_len);
+ }
+
+ if (ret == 0)
+ ret = total_len - iov_iter_count(&iter);
+
+ mmput(mm);
+ return ret;
+
+release_task:
+ put_task_struct(task);
+put_pid:
+ put_pid(pid);
+free_iov:
+ kfree(iov);
+out:
+ return ret;
+}