Merge branch 'akpm/master' into master

30 files changed, 245 insertions, 82 deletions

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 4affd5b6150c..24c4a4db5c2e 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -481,3 +481,4 @@
 549	common	faccessat2			sys_faccessat2
 550	common	watch_mount			sys_watch_mount
 551	common	fsinfo				sys_fsinfo
+552	common	process_madvise			sys_process_madvise
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index a68443d0a8ee..d345ab40f747 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -455,3 +455,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 86a9d7b3eabe..949788f5ba40 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		442
+#define __NR_compat_syscalls		443
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index c10990736770..34a614cc0130 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -891,6 +891,8 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2)
 __SYSCALL(__NR_watch_mount, sys_watch_mount)
 #define __NR_fsinfo 441
 __SYSCALL(__NR_fsinfo, sys_fsinfo)
+#define __NR_process_madvise 442
+__SYSCALL(__NR_process_madvise, compat_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 8d1611dbffe4..437532a411b5 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -362,3 +362,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 079b85781168..04fbee8f5e17 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -441,3 +441,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index e596b24209b3..1e05fce04016 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -447,3 +447,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	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 84ebfee47acb..a204f01c1c24 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -380,3 +380,4 @@
 439	n32	faccessat2			sys_faccessat2
 440	n32	watch_mount			sys_watch_mount
 441	n32	fsinfo				sys_fsinfo
+442	n32	process_madvise			compat_sys_process_madvise
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index ca88651df43a..0db6e3d540f3 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -356,3 +356,4 @@
 439	n64	faccessat2			sys_faccessat2
 440	n64	watch_mount			sys_watch_mount
 441	n64	fsinfo				sys_fsinfo
+442	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 02dddb858562..c531231a2383 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -429,3 +429,4 @@
 439	o32	faccessat2			sys_faccessat2
 440	o32	watch_mount			sys_watch_mount
 441	o32	fsinfo				sys_fsinfo
+442	o32	process_madvise			sys_process_madvise		compat_sys_process_madvise
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index b7646de8ca8f..48090b11f1f2 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise		compat_sys_process_madvise
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 3fa45ad7666b..56c9df0f539d 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -531,3 +531,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise		compat_sys_process_madvise
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 60169f960745..88a91abc0bca 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -444,3 +444,4 @@
 439  common	faccessat2		sys_faccessat2			sys_faccessat2
 440	common	watch_mount		sys_watch_mount			sys_watch_mount
 441	common	fsinfo			sys_fsinfo			sys_fsinfo
+442	common	process_madvise		sys_process_madvise		compat_sys_process_madvise
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 6ff815773779..5de0035a9967 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -444,3 +444,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 93efb7eacad5..42e68b35bdb4 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -487,3 +487,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise		compat_sys_process_madvise
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index cdac678ee140..9e0cdf55ca56 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -446,3 +446,4 @@
 439	i386	faccessat2		sys_faccessat2
 440	i386	watch_mount		sys_watch_mount
 441	i386	fsinfo			sys_fsinfo
+442	i386	process_madvise		sys_process_madvise		compat_sys_process_madvise
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 06001131634b..6ee78ddd03d7 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -363,6 +363,7 @@
 439	common	faccessat2		sys_faccessat2
 440	common	watch_mount		sys_watch_mount
 441	common	fsinfo			sys_fsinfo
+442	64	process_madvise		sys_process_madvise
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
@@ -406,3 +407,4 @@
 545	x32	execveat		compat_sys_execveat
 546	x32	preadv2			compat_sys_preadv64v2
 547	x32	pwritev2		compat_sys_pwritev64v2
+548	x32	process_madvise		compat_sys_process_madvise
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 709e8e4e2b58..f74cbc2fa7c8 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -412,3 +412,4 @@
 439	common	faccessat2			sys_faccessat2
 440	common	watch_mount			sys_watch_mount
 441	common	fsinfo				sys_fsinfo
+442	common	process_madvise			sys_process_madvise
diff --git a/fs/io_uring.c b/fs/io_uring.c
index dc506b75659c..93ad3e2a1e1f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3855,7 +3855,7 @@ static int io_madvise(struct io_kiocb *req, bool force_nonblock)
 	if (force_nonblock)
 		return -EAGAIN;
 
-	ret = do_madvise(ma->addr, ma->len, ma->advice);
+	ret = do_madvise(NULL, current->mm, ma->addr, ma->len, ma->advice);
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_req_complete(req, ret);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..4f374e6a7ed8 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -823,6 +823,10 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd,
 		unsigned long vlen, loff_t pos, rwf_t flags);
 #endif
 
+asmlinkage ssize_t compat_sys_process_madvise(compat_int_t pidfd,
+		const struct compat_iovec __user *vec,
+		compat_ulong_t vlen, compat_int_t behavior,
+		compat_uint_t flags);
 
 /*
  * Deprecated system calls which are still defined in
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a911aa3114ef..8ab941cf73f4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2548,7 +2548,8 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
 		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
-extern int do_madvise(unsigned long start, size_t len_in, int behavior);
+extern int do_madvise(struct task_struct *target_task, struct mm_struct *mm,
+		unsigned long start, size_t len_in, int behavior);
 
 #ifdef CONFIG_MMU
 extern int __mm_populate(unsigned long addr, unsigned long len,
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 176d6cf80e7c..86e0e7cb7872 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -77,6 +77,7 @@ extern const struct file_operations pidfd_fops;
 struct file;
 
 extern struct pid *pidfd_pid(const struct file *file);
+struct pid *pidfd_get_pid(unsigned int fd);
 
 static inline struct pid *get_pid(struct pid *pid)
 {
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8b9d12c7a447..88520eb343b8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -880,6 +880,8 @@ 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,
+		unsigned long 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 fa3d6815466a..c0b5f8b609eb 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -863,9 +863,11 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2)
 __SYSCALL(__NR_watch_mount, sys_watch_mount)
 #define __NR_fsinfo 441
 __SYSCALL(__NR_fsinfo, sys_fsinfo)
+#define __NR_process_madvise 442
+__SC_COMP(__NR_process_madvise, sys_process_madvise, compat_sys_process_madvise)
 
 #undef __NR_syscalls
-#define __NR_syscalls 442
+#define __NR_syscalls 443
 
 /*
  * 32 bit systems traditionally used different
diff --git a/kernel/exit.c b/kernel/exit.c
index 733e80f334e7..62912406d74a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1474,23 +1474,6 @@ end:
 	return retval;
 }
 
-static struct pid *pidfd_get_pid(unsigned int fd)
-{
-	struct fd f;
-	struct pid *pid;
-
-	f = fdget(fd);
-	if (!f.file)
-		return ERR_PTR(-EBADF);
-
-	pid = pidfd_pid(f.file);
-	if (!IS_ERR(pid))
-		get_pid(pid);
-
-	fdput(f);
-	return pid;
-}
-
 static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 			  int options, struct rusage *ru)
 {
diff --git a/kernel/pid.c b/kernel/pid.c
index b2562a7ce525..a9cbab0194d9 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -519,6 +519,23 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 	return idr_get_next(&ns->idr, &nr);
 }
 
+struct pid *pidfd_get_pid(unsigned int fd)
+{
+	struct fd f;
+	struct pid *pid;
+
+	f = fdget(fd);
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	pid = pidfd_pid(f.file);
+	if (!IS_ERR(pid))
+		get_pid(pid);
+
+	fdput(f);
+	return pid;
+}
+
 /**
  * pidfd_create() - Create a new pid file descriptor.
  *
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 8a4ae67bb08b..b5a30f4ea460 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -284,6 +284,8 @@ COND_SYSCALL(mlockall);
 COND_SYSCALL(munlockall);
 COND_SYSCALL(mincore);
 COND_SYSCALL(madvise);
+COND_SYSCALL(process_madvise);
+COND_SYSCALL_COMPAT(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 b59bbd6c9982..843f6fad3b89 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -17,17 +17,20 @@
 #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>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/compat.h>
 #include <linux/pagewalk.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/mmu_notifier.h>
 #include <linux/sched/mm.h>
+#include <linux/uio.h>
 
 #include <asm/tlb.h>
 
@@ -36,6 +39,7 @@
 struct madvise_walk_private {
 	struct mmu_gather *tlb;
 	bool pageout;
+	struct task_struct *target_task;
 };
 
 /*
@@ -255,6 +259,7 @@ static long madvise_willneed(struct vm_area_struct *vma,
 			     struct vm_area_struct **prev,
 			     unsigned long start, unsigned long end)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
 	loff_t offset;
 
@@ -289,12 +294,12 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	 */
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 	get_file(file);
-	mmap_read_unlock(current->mm);
+	mmap_read_unlock(mm);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return 0;
 }
 
@@ -315,6 +320,10 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
+	if (private->target_task &&
+			fatal_signal_pending(private->target_task))
+		return -EINTR;
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (pmd_trans_huge(*pmd)) {
 		pmd_t orig_pmd;
@@ -476,12 +485,14 @@ static const struct mm_walk_ops cold_walk_ops = {
 };
 
 static void madvise_cold_page_range(struct mmu_gather *tlb,
+			     struct task_struct *task,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end)
 {
 	struct madvise_walk_private walk_private = {
 		.pageout = false,
 		.tlb = tlb,
+		.target_task = task,
 	};
 
 	tlb_start_vma(tlb, vma);
@@ -489,7 +500,8 @@ static void madvise_cold_page_range(struct mmu_gather *tlb,
 	tlb_end_vma(tlb, vma);
 }
 
-static long madvise_cold(struct vm_area_struct *vma,
+static long madvise_cold(struct task_struct *task,
+			struct vm_area_struct *vma,
 			struct vm_area_struct **prev,
 			unsigned long start_addr, unsigned long end_addr)
 {
@@ -502,19 +514,21 @@ static long madvise_cold(struct vm_area_struct *vma,
 
 	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
-	madvise_cold_page_range(&tlb, vma, start_addr, end_addr);
+	madvise_cold_page_range(&tlb, task, vma, start_addr, end_addr);
 	tlb_finish_mmu(&tlb, start_addr, end_addr);
 
 	return 0;
 }
 
 static void madvise_pageout_page_range(struct mmu_gather *tlb,
+			     struct task_struct *task,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end)
 {
 	struct madvise_walk_private walk_private = {
 		.pageout = true,
 		.tlb = tlb,
+		.target_task = task,
 	};
 
 	tlb_start_vma(tlb, vma);
@@ -538,7 +552,8 @@ static inline bool can_do_pageout(struct vm_area_struct *vma)
 		inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
 }
 
-static long madvise_pageout(struct vm_area_struct *vma,
+static long madvise_pageout(struct task_struct *task,
+			struct vm_area_struct *vma,
 			struct vm_area_struct **prev,
 			unsigned long start_addr, unsigned long end_addr)
 {
@@ -554,7 +569,7 @@ static long madvise_pageout(struct vm_area_struct *vma,
 
 	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
-	madvise_pageout_page_range(&tlb, vma, start_addr, end_addr);
+	madvise_pageout_page_range(&tlb, task, vma, start_addr, end_addr);
 	tlb_finish_mmu(&tlb, start_addr, end_addr);
 
 	return 0;
@@ -683,7 +698,6 @@ out:
 	if (nr_swap) {
 		if (current->mm == mm)
 			sync_mm_rss(mm);
-
 		add_mm_counter(mm, MM_SWAPENTS, nr_swap);
 	}
 	arch_leave_lazy_mmu_mode();
@@ -763,6 +777,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 				  unsigned long start, unsigned long end,
 				  int behavior)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	*prev = vma;
 	if (!can_madv_lru_vma(vma))
 		return -EINVAL;
@@ -770,8 +786,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	if (!userfaultfd_remove(vma, start, end)) {
 		*prev = NULL; /* mmap_lock has been dropped, prev is stale */
 
-		mmap_read_lock(current->mm);
-		vma = find_vma(current->mm, start);
+		mmap_read_lock(mm);
+		vma = find_vma(mm, start);
 		if (!vma)
 			return -ENOMEM;
 		if (start < vma->vm_start) {
@@ -825,6 +841,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 	loff_t offset;
 	int error;
 	struct file *f;
+	struct mm_struct *mm = vma->vm_mm;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 
@@ -852,13 +869,13 @@ static long madvise_remove(struct vm_area_struct *vma,
 	get_file(f);
 	if (userfaultfd_remove(vma, start, end)) {
 		/* mmap_lock was not released by userfaultfd_remove() */
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
 	fput(f);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return error;
 }
 
@@ -925,7 +942,8 @@ static int madvise_inject_error(int behavior,
 #endif
 
 static long
-madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
+madvise_vma(struct task_struct *task, struct vm_area_struct *vma,
+		struct vm_area_struct **prev,
 		unsigned long start, unsigned long end, int behavior)
 {
 	switch (behavior) {
@@ -934,9 +952,9 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	case MADV_WILLNEED:
 		return madvise_willneed(vma, prev, start, end);
 	case MADV_COLD:
-		return madvise_cold(vma, prev, start, end);
+		return madvise_cold(task, vma, prev, start, end);
 	case MADV_PAGEOUT:
-		return madvise_pageout(vma, prev, start, end);
+		return madvise_pageout(task, vma, prev, start, end);
 	case MADV_FREE:
 	case MADV_DONTNEED:
 		return madvise_dontneed_free(vma, prev, start, end, behavior);
@@ -983,6 +1001,18 @@ 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.
  *
@@ -1030,6 +1060,11 @@ 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
@@ -1044,7 +1079,8 @@ madvise_behavior_valid(int behavior)
  *  -EBADF  - map exists, but area maps something that isn't a file.
  *  -EAGAIN - a kernel resource was temporarily unavailable.
  */
-int do_madvise(unsigned long start, size_t len_in, int behavior)
+int do_madvise(struct task_struct *target_task, struct mm_struct *mm,
+		unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -1082,7 +1118,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 
 	write = madvise_need_mmap_write(behavior);
 	if (write) {
-		if (mmap_write_lock_killable(current->mm))
+		if (mmap_write_lock_killable(mm))
 			return -EINTR;
 
 		/*
@@ -1097,12 +1133,12 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 		 * but for now we have the mmget_still_valid()
 		 * model.
 		 */
-		if (!mmget_still_valid(current->mm)) {
-			mmap_write_unlock(current->mm);
+		if (!mmget_still_valid(mm)) {
+			mmap_write_unlock(mm);
 			return -EINTR;
 		}
 	} else {
-		mmap_read_lock(current->mm);
+		mmap_read_lock(mm);
 	}
 
 	/*
@@ -1110,7 +1146,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 	 * ranges, just ignore them, but return -ENOMEM at the end.
 	 * - different from the way of handling in mlock etc.
 	 */
-	vma = find_vma_prev(current->mm, start, &prev);
+	vma = find_vma_prev(mm, start, &prev);
 	if (vma && start > vma->vm_start)
 		prev = vma;
 
@@ -1135,7 +1171,8 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 			tmp = end;
 
 		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
-		error = madvise_vma(vma, &prev, start, tmp, behavior);
+		error = madvise_vma(target_task, vma, &prev,
+					start, tmp, behavior);
 		if (error)
 			goto out;
 		start = tmp;
@@ -1147,19 +1184,122 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 		if (prev)
 			vma = prev->vm_next;
 		else	/* madvise_remove dropped mmap_lock */
-			vma = find_vma(current->mm, start);
+			vma = find_vma(mm, start);
 	}
 out:
 	blk_finish_plug(&plug);
 	if (write)
-		mmap_write_unlock(current->mm);
+		mmap_write_unlock(mm);
 	else
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 
 	return error;
 }
 
 SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
-	return do_madvise(start, len_in, behavior);
+	return do_madvise(current, current->mm, start, len_in, behavior);
+}
+
+static int process_madvise_vec(struct task_struct *target_task,
+		struct mm_struct *mm, struct iov_iter *iter, int behavior)
+{
+	struct iovec iovec;
+	int ret = 0;
+
+	while (iov_iter_count(iter)) {
+		iovec = iov_iter_iovec(iter);
+		ret = do_madvise(target_task, mm, (unsigned long)iovec.iov_base,
+					iovec.iov_len, behavior);
+		if (ret < 0)
+			break;
+		iov_iter_advance(iter, iovec.iov_len);
+	}
+
+	return ret;
+}
+
+static ssize_t do_process_madvise(int pidfd, struct iov_iter *iter,
+				int behavior, unsigned int flags)
+{
+	ssize_t ret;
+	struct pid *pid;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	size_t total_len = iov_iter_count(iter);
+
+	if (flags != 0)
+		return -EINVAL;
+
+	pid = pidfd_get_pid(pidfd);
+	if (IS_ERR(pid))
+		return PTR_ERR(pid);
+
+	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;
+	}
+
+	ret = process_madvise_vec(task, mm, iter, behavior);
+	if (ret >= 0)
+		ret = total_len - iov_iter_count(iter);
+
+	mmput(mm);
+release_task:
+	put_task_struct(task);
+put_pid:
+	put_pid(pid);
+	return ret;
+}
+
+SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
+		unsigned long, vlen, int, behavior, unsigned int, flags)
+{
+	ssize_t ret;
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+
+	ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret >= 0) {
+		ret = do_process_madvise(pidfd, &iter, behavior, flags);
+		kfree(iov);
+	}
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE5(process_madvise, compat_int_t, pidfd,
+			const struct compat_iovec __user *, vec,
+			compat_ulong_t, vlen,
+			compat_int_t, behavior,
+			compat_uint_t, flags)
+
+{
+	ssize_t ret;
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+
+	ret = compat_import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack),
+				&iov, &iter);
+	if (ret >= 0) {
+		ret = do_process_madvise(pidfd, &iter, behavior, flags);
+		kfree(iov);
+	}
+	return ret;
 }
+#endif
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index d979a837d84b..a229d4694954 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1673,16 +1673,6 @@ int unpoison_memory(unsigned long pfn)
 }
 EXPORT_SYMBOL(unpoison_memory);
 
-static struct page *new_page(struct page *p, unsigned long private)
-{
-	struct migration_target_control mtc = {
-		.nid = page_to_nid(p),
-		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
-	};
-
-	return alloc_migration_target(p, (unsigned long)&mtc);
-}
-
 /*
  * Safely get reference count of an arbitrary page.
  * Returns 0 for a free page, -EIO for a zero refcount page
@@ -1794,6 +1784,10 @@ static int __soft_offline_page(struct page *page)
 	char const *msg_page[] = {"page", "hugepage"};
 	bool huge = PageHuge(page);
 	LIST_HEAD(pagelist);
+	struct migration_target_control mtc = {
+		.nid = NUMA_NO_NODE,
+		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+	};
 
 	/*
 	 * Check PageHWPoison again inside page lock because PageHWPoison
@@ -1829,8 +1823,8 @@ static int __soft_offline_page(struct page *page)
 	}
 
 	if (isolate_page(hpage, &pagelist)) {
-		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
-					MIGRATE_SYNC, MR_MEMORY_FAILURE);
+		ret = migrate_pages(&pagelist, alloc_migration_target, NULL,
+			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (!ret) {
 			bool release = !huge;
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e9d5ab5d3ca0..7f62d69660e0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1274,27 +1274,6 @@ found:
 	return 0;
 }
 
-static struct page *new_node_page(struct page *page, unsigned long private)
-{
-	nodemask_t nmask = node_states[N_MEMORY];
-	struct migration_target_control mtc = {
-		.nid = page_to_nid(page),
-		.nmask = &nmask,
-		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
-	};
-
-	/*
-	 * try to allocate from a different node but reuse this node if there
-	 * are no other online nodes to be used (e.g. we are offlining a part
-	 * of the only existing node)
-	 */
-	node_clear(mtc.nid, nmask);
-	if (nodes_empty(nmask))
-		node_set(mtc.nid, nmask);
-
-	return alloc_migration_target(page, (unsigned long)&mtc);
-}
-
 static int
 do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -1354,9 +1333,28 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		put_page(page);
 	}
 	if (!list_empty(&source)) {
-		/* Allocate a new page from the nearest neighbor node */
-		ret = migrate_pages(&source, new_node_page, NULL, 0,
-					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
+		nodemask_t nmask = node_states[N_MEMORY];
+		struct migration_target_control mtc = {
+			.nmask = &nmask,
+			.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+		};
+
+		/*
+		 * We have checked that migration range is on a single zone so
+		 * we can use the nid of the first page to all the others.
+		 */
+		mtc.nid = page_to_nid(list_first_entry(&source, struct page, lru));
+
+		/*
+		 * try to allocate from a different node but reuse this node
+		 * if there are no other online nodes to be used (e.g. we are
+		 * offlining a part of the only existing node)
+		 */
+		node_clear(mtc.nid, nmask);
+		if (nodes_empty(nmask))
+			node_set(mtc.nid, nmask);
+		ret = migrate_pages(&source, alloc_migration_target, NULL,
+			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
 		if (ret) {
 			list_for_each_entry(page, &source, lru) {
 				pr_warn("migrating pfn %lx failed ret:%d ",