Merge "mm: support vector address ranges for process_madvise"

arch/alpha/kernel/syscalls/syscall.tbl

@@ -475,3 +475,4 @@
 543	common	fspick				sys_fspick
 544	common	pidfd_open			sys_pidfd_open
 # 545 reserved for clone3
+546	common	process_madvise			sys_process_madvise

arch/arm/tools/syscall.tbl

@@ -449,3 +449,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
+436	common	process_madvise			sys_process_madvise

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		436
+#define __NR_compat_syscalls		437
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

arch/arm64/include/asm/unistd32.h

@@ -879,6 +879,8 @@ __SYSCALL(__NR_fspick, sys_fspick)
 __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
 #define __NR_clone3 435
 __SYSCALL(__NR_clone3, sys_clone3)
+#define __NR_process_madvise 436
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/ia64/kernel/syscalls/syscall.tbl

@@ -356,3 +356,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+436	common	process_madvise			sys_process_madvise

arch/m68k/kernel/syscalls/syscall.tbl

@@ -435,3 +435,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+436	common	process_madvise			sys_process_madvise

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -441,3 +441,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
+436	common	process_madvise			sys_process_madvise

arch/mips/kernel/syscalls/syscall_n32.tbl

@@ -374,3 +374,4 @@
 433	n32	fspick				sys_fspick
 434	n32	pidfd_open			sys_pidfd_open
 435	n32	clone3				__sys_clone3
+436	n32	process_madvise			sys_process_madvise

arch/mips/kernel/syscalls/syscall_n64.tbl

@@ -350,3 +350,4 @@
 433	n64	fspick				sys_fspick
 434	n64	pidfd_open			sys_pidfd_open
 435	n64	clone3				__sys_clone3
+436	n64	process_madvise			sys_process_madvise

arch/parisc/kernel/syscalls/syscall.tbl

@@ -433,3 +433,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3_wrapper
+436	common	process_madvise			sys_process_madvise

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -517,3 +517,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	nospu	clone3				ppc_clone3
+436	common	process_madvise			sys_process_madvise

arch/s390/kernel/syscalls/syscall.tbl

@@ -438,3 +438,4 @@
 433  common	fspick			sys_fspick			sys_fspick
 434  common	pidfd_open		sys_pidfd_open			sys_pidfd_open
 435  common	clone3			sys_clone3			sys_clone3
+443  common	process_madvise		sys_process_madvise		sys_process_madvise

arch/sh/kernel/syscalls/syscall.tbl

@@ -438,3 +438,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+436	common	process_madvise			sys_process_madvise

arch/sparc/kernel/syscalls/syscall.tbl

@@ -481,3 +481,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+436	common	process_madvise			sys_process_madvise

arch/x86/entry/syscalls/syscall_32.tbl

@@ -440,3 +440,4 @@
 433	i386	fspick			sys_fspick			__ia32_sys_fspick
 434	i386	pidfd_open		sys_pidfd_open			__ia32_sys_pidfd_open
 435	i386	clone3			sys_clone3			__ia32_sys_clone3
+436	i386	process_madvise		sys_process_madvise

arch/x86/entry/syscalls/syscall_64.tbl

@@ -357,6 +357,7 @@
 433	common	fspick			__x64_sys_fspick
 434	common	pidfd_open		__x64_sys_pidfd_open
 435	common	clone3			__x64_sys_clone3/ptregs
+436	common	process_madvise		sys_process_madvise
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -406,3 +406,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
+443	common	process_madvise			sys_process_madvise

include/linux/pid.h

@@ -75,6 +75,7 @@ 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)
 {

include/linux/syscalls.h

@@ -874,6 +874,9 @@ 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 which, pid_t upid,
+		const struct iovec __user *vec, unsigned long vlen,
+		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);

include/uapi/asm-generic/unistd.h

@@ -850,9 +850,11 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
 #define __NR_clone3 435
 __SYSCALL(__NR_clone3, sys_clone3)
 #endif
+#define __NR_process_madvise 436
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 #undef __NR_syscalls
-#define __NR_syscalls 436
+#define __NR_syscalls 437
 
 /*
  * 32 bit systems traditionally used different

kernel/exit.c

@@ -1470,23 +1470,6 @@ 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)
 {

kernel/pid.c

@@ -454,6 +454,23 @@ 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.
  *

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);

mm/madvise.c

@@ -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>
@@ -38,6 +39,7 @@
 struct madvise_walk_private {
 	struct mmu_gather *tlb;
 	bool pageout;
+	struct task_struct *target_task;
 };
 
 /*
@@ -318,6 +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;
@@ -479,12 +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);
@@ -492,7 +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)
 {
@@ -505,19 +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);
@@ -541,7 +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)
 {
@@ -557,7 +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;
@@ -937,7 +949,8 @@ 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) {
@@ -946,9 +959,9 @@ 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);
@@ -995,6 +1008,22 @@ madvise_behavior_valid(int behavior)
 	}
 }
 
+static bool
+process_madvise_behavior_valid(int behavior)
+{
+	switch (behavior) {
+	case MADV_COLD:
+	case MADV_PAGEOUT:
+#ifdef CONFIG_KSM
+	case MADV_MERGEABLE:
+	case MADV_UNMERGEABLE:
+#endif
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * The madvise(2) system call.
  *
@@ -1042,6 +1071,11 @@ 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
@@ -1148,7 +1182,8 @@ int do_madvise(struct task_struct *target_task, struct mm_struct *mm,
 			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;
@@ -1176,3 +1211,92 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
 	return do_madvise(current, current->mm, start, len_in, behavior);
 }
+
+static int do_process_madvise(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;
+}
+
+SYSCALL_DEFINE6(process_madvise, int, which, pid_t, upid,
+		const struct iovec __user *, vec, unsigned long, vlen,
+		int, behavior, unsigned long, flags)
+{
+	ssize_t ret;
+	struct pid *pid;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	switch (which) {
+	case P_PID:
+		if (upid <= 0)
+			return -EINVAL;
+
+		pid = find_get_pid(upid);
+		if (!pid)
+			return -ESRCH;
+		break;
+	case P_PIDFD:
+		if (upid < 0)
+			return -EINVAL;
+
+		pid = pidfd_get_pid(upid);
+		if (IS_ERR(pid))
+			return PTR_ERR(pid);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	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 = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret >= 0) {
+		size_t total_len = iov_iter_count(&iter);
+
+		ret = do_process_madvise(task, mm, &iter, behavior);
+		if (ret >= 0)
+			ret = total_len - iov_iter_count(&iter);
+		kfree(iov);
+	}
+	mmput(mm);
+release_task:
+	put_task_struct(task);
+put_pid:
+	put_pid(pid);
+	return ret;
+}