diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index ec8bed9e7b75b6a9b22fd75a36d614c2712982cc..ee7b01bb7346c9c57843e68a3fff34ad703601fa 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 171077cbf419b419ab7d906a23c7ed120a129ccb..d056a548358ea024fc64f3a107849951a26838d7 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -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
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 3b859596840de5238645308ecd1bf389401822c5..b3b2019f8d16bbeef51948c249dcfb6dbd97a0fb 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -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
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 2a3ad9b9accd55d28ba9268b6a6415a8d65faff2..107f08e03b9fdc4d54b41c7fca707727e1524c92 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -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
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 4799c96c325f14f232b2168f52869f06ac574c9e..b96ed8b8a508999112a1d8065db035d90efaec0c 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 81fc799d839234f00c0b13e56959f5f165827a97..625fb6d3284240e0d8bc96556c0b3ff92b350540 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index b4e263916f4132a9a710f4f6fc4f604f675d9e3a..aae729c95cf99d23e056c510651c6f3126d4ceff 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index cf72a0206a87c2d318c2b9433120a832db911684..32817c954435d7c7dba4a126b35054f18ae0d9ee 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -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
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 557f9954a2b9a8fd66179f572d0fcffb63638bcd..9e4ea3c31b1ce026fdad266866b60be6426d882b 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -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
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index a17aab5abeb2d618b54081b1adc8b69939135d24..29f5f28cf5cea83d6119637ea57d40ad6abe4d40 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -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
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index ae3dab371f6f85990331dd0767a41ed9cf22ff53..38c63e5404bcd0dbebbe493e824549be565d9163 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 9d7fb4ced290406cef9417176cdacf557d4a0b9b..1275daec7fec365024fd50d2b43d42616d829b20 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 1c3b48165e86fe79a67fa6db544c457163e32c66..28c16800048344821461943d58f99ff1f50ab4c6 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index ae0a00beea5f2e8f2b8335c634a5f7341323c345..783738448ff555f66baa8d9b559dce0d3e08b325 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 37ec52b34c73c5d163911030e9f1b2d5cc6c6ee9..78160260991be726ff888371314cfd10b82d5b6a 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9b6931f8d5551ec7f2837a8f2a416aea58649796..0d0667a9fbd70aeb9e297342b9f855a457d45ea4 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -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
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 347809649ba28fa15be86511d563ff9d427ecaea..1f47e24fb65cf8a7525be8a53934eb4fa63da7d1 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -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
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 6276e3c2d3fc0d82ac59907e43c3895f42f54a74..b070f272995d6447895287704a0c76237619c2cc 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -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
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 06db09875aa4a73aec07c53d2cf0465e1090ad10..2eda7678fe1d974b7a29a3e53ea92105e95fd0a4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -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);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f2b5d72a46c23b9f9abd6b439b29e1192bf59dff..2056318988f774931c4e0a3104144bf4a75ff52f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -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
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c925d1e1777efcf828e2796ce135d0e4c546dc31..f27ac94d5fa7270ba9f272be1bcba6a903149206 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -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);
diff --git a/mm/madvise.c b/mm/madvise.c
index d550ef045288e8c6b2fe13ffa6968ca83d72a0ae..416a56b8e757bf3465ab13cea51e0751ade2c745 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -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, start, size_t, len_in, int, behavior)
{
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;
+}