Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zi Yan <zi.yan@sent.com>
To:     Dave Hansen <dave.hansen@linux.intel.com>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        Keith Busch <keith.busch@intel.com>,
        Fengguang Wu <fengguang.wu@intel.com>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Cc:     Daniel Jordan <daniel.m.jordan@oracle.com>,
        Michal Hocko <mhocko@kernel.org>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Mel Gorman <mgorman@techsingularity.net>,
        John Hubbard <jhubbard@nvidia.com>,
        Mark Hairgrove <mhairgrove@nvidia.com>,
        Nitin Gupta <nigupta@nvidia.com>,
        Javier Cabezas <jcabezas@nvidia.com>,
        David Nellans <dnellans@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 20/25] memory manage: Add memory manage syscall.
Date:   Wed,  3 Apr 2019 19:00:41 -0700
Message-Id: <20190404020046.32741-21-zi.yan@sent.com>
In-Reply-To: <20190404020046.32741-1-zi.yan@sent.com>
References: <20190404020046.32741-1-zi.yan@sent.com>
Reply-To: ziy@nvidia.com
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Zi Yan <ziy@nvidia.com>

This prepares for the following patches to provide a user API to
manipulate pages in two memory nodes with the help of memcg.

missing memcg_max_size_node()

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 arch/x86/entry/syscalls/syscall_64.tbl |   1 +
 include/linux/sched/coredump.h         |   1 +
 include/linux/syscalls.h               |   5 ++
 include/uapi/linux/mempolicy.h         |   1 +
 mm/Makefile                            |   1 +
 mm/internal.h                          |   2 +
 mm/memory_manage.c                     | 109 +++++++++++++++++++++++++++++++++
 mm/mempolicy.c                         |   2 +-
 8 files changed, 121 insertions(+), 1 deletion(-)
 create mode 100644 mm/memory_manage.c

diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 863a21e..fa8def3 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -344,6 +344,7 @@
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
 335	common	exchange_pages	__x64_sys_exchange_pages
+336	common	mm_manage		__x64_sys_mm_manage
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ecdc654..9aa9d94b 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -73,6 +73,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_OOM_VICTIM		25	/* mm is the oom victim */
 #define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
+#define MMF_MM_MANAGE		27
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
 				 MMF_DISABLE_THP_MASK)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2c1eb49..47d56c5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1208,6 +1208,11 @@ asmlinkage long sys_exchange_pages(pid_t pid, unsigned long nr_pages,
 				const void __user * __user *to_pages,
 				int __user *status,
 				int flags);
+asmlinkage long sys_mm_manage(pid_t pid, unsigned long nr_pages,
+				unsigned long maxnode,
+				const unsigned long __user *old_nodes,
+				const unsigned long __user *new_nodes,
+				int flags);
 
 /*
  * Not a real system call, but a placeholder for syscalls which are
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index a9d03e5..4722bb7 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -52,6 +52,7 @@ enum {
 #define MPOL_MF_MOVE_DMA (1<<5)	/* Use DMA page copy routine */
 #define MPOL_MF_MOVE_MT  (1<<6)	/* Use multi-threaded page copy routine */
 #define MPOL_MF_MOVE_CONCUR  (1<<7)	/* Move pages in a batch */
+#define MPOL_MF_EXCHANGE	(1<<8)	/* Exchange pages */
 
 #define MPOL_MF_VALID	(MPOL_MF_STRICT   | 	\
 			 MPOL_MF_MOVE     | 	\
diff --git a/mm/Makefile b/mm/Makefile
index 2f1f1ad..5302d79 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -47,6 +47,7 @@ obj-y += memblock.o
 obj-y += copy_page.o
 obj-y += exchange.o
 obj-y += exchange_page.o
+obj-y += memory_manage.o
 
 ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
diff --git a/mm/internal.h b/mm/internal.h
index cf63bf6..94feb14 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -574,5 +574,7 @@ bool buffer_migrate_lock_buffers(struct buffer_head *head,
 int writeout(struct address_space *mapping, struct page *page);
 int expected_page_refs(struct address_space *mapping, struct page *page);
 
+int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
+		     unsigned long maxnode);
 
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/memory_manage.c b/mm/memory_manage.c
new file mode 100644
index 0000000..b8f3654
--- /dev/null
+++ b/mm/memory_manage.c
@@ -0,0 +1,109 @@
+/*
+ * A syscall used to move pages between two nodes.
+ */
+
+#include <linux/sched/mm.h>
+#include <linux/cpuset.h>
+#include <linux/mempolicy.h>
+#include <linux/nodemask.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+
+#include "internal.h"
+
+
+SYSCALL_DEFINE6(mm_manage, pid_t, pid, unsigned long, nr_pages,
+		unsigned long, maxnode,
+		const unsigned long __user *, slow_nodes,
+		const unsigned long __user *, fast_nodes,
+		int, flags)
+{
+	const struct cred *cred = current_cred(), *tcred;
+	struct task_struct *task;
+	struct mm_struct *mm = NULL;
+	int err;
+	nodemask_t task_nodes;
+	nodemask_t *slow;
+	nodemask_t *fast;
+	NODEMASK_SCRATCH(scratch);
+
+	if (!scratch)
+		return -ENOMEM;
+
+	slow = &scratch->mask1;
+	fast = &scratch->mask2;
+
+	err = get_nodes(slow, slow_nodes, maxnode);
+	if (err)
+		goto out;
+
+	err = get_nodes(fast, fast_nodes, maxnode);
+	if (err)
+		goto out;
+
+	/* Check flags */
+	if (flags & ~(MPOL_MF_MOVE_MT|
+				  MPOL_MF_MOVE_DMA|
+				  MPOL_MF_MOVE_CONCUR|
+				  MPOL_MF_EXCHANGE))
+		return -EINVAL;
+
+	/* Find the mm_struct */
+	rcu_read_lock();
+	task = pid ? find_task_by_vpid(pid) : current;
+	if (!task) {
+		rcu_read_unlock();
+		err = -ESRCH;
+		goto out;
+	}
+	get_task_struct(task);
+
+	err = -EINVAL;
+	/*
+	 * Check if this process has the right to modify the specified
+	 * process. The right exists if the process has administrative
+	 * capabilities, superuser privileges or the same
+	 * userid as the target process.
+	 */
+	tcred = __task_cred(task);
+	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
+	    !capable(CAP_SYS_NICE)) {
+		rcu_read_unlock();
+		err = -EPERM;
+		goto out_put;
+	}
+	rcu_read_unlock();
+
+	err = security_task_movememory(task);
+	if (err)
+		goto out_put;
+
+	task_nodes = cpuset_mems_allowed(task);
+	mm = get_task_mm(task);
+	put_task_struct(task);
+
+	if (!mm) {
+		err = -EINVAL;
+		goto out;
+	}
+	if (test_bit(MMF_MM_MANAGE, &mm->flags)) {
+		mmput(mm);
+		goto out;
+	} else {
+		set_bit(MMF_MM_MANAGE, &mm->flags);
+	}
+
+
+	clear_bit(MMF_MM_MANAGE, &mm->flags);
+	mmput(mm);
+out:
+	NODEMASK_SCRATCH_FREE(scratch);
+
+	return err;
+
+out_put:
+	put_task_struct(task);
+	goto out;
+
+}
\ No newline at end of file
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0e30049..168d17f8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1249,7 +1249,7 @@ static long do_mbind(unsigned long start, unsigned long len,
  */
 
 /* Copy a node mask from user space. */
-static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
+int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
 		     unsigned long maxnode)
 {
 	unsigned long k;
-- 
2.7.4